High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 2

fmvsm_s_conf0.5_n_3		95.20 102	95.95 68	92.94 231	96.60 220	82.18 309	93.13 208	98.39 33	91.44 151	97.16 78	97.68 85	93.03 129	97.82 317	97.54 2	98.63 210	98.81 102

test_fmvsmconf0.01_n		95.90 65	96.09 58	95.31 102	97.30 156	89.21 134	94.24 156	98.76 12	86.25 306	97.56 50	98.66 24	95.73 23	98.44 237	97.35 3	98.99 135	98.27 183

fmvsm_s_conf0.5_n_9		95.58 80	95.91 73	94.59 146	97.25 157	86.26 217	92.96 218	97.86 127	91.88 123	97.52 54	98.13 46	91.45 175	98.54 215	97.17 4	98.99 135	98.98 70

fmvsm_s_conf0.5_n_10		94.63 130	95.11 121	93.18 221	96.28 260	83.51 272	93.00 215	98.25 47	88.37 244	97.43 59	97.70 83	88.90 234	98.63 195	97.15 5	98.90 156	97.41 292

fmvsm_s_conf0.1_n_2		94.38 148	94.78 138	93.19 220	97.07 172	81.72 316	91.97 277	97.51 173	87.05 289	97.31 68	97.92 68	88.29 248	98.15 274	97.10 6	98.81 174	99.70 5

Elysia		96.00 60	96.36 43	94.91 122	98.01 101	85.96 228	95.29 111	97.90 119	95.31 45	98.14 31	97.28 132	88.82 236	99.51 20	97.08 7	99.38 63	99.26 37

StellarMVS		96.00 60	96.36 43	94.91 122	98.01 101	85.96 228	95.29 111	97.90 119	95.31 45	98.14 31	97.28 132	88.82 236	99.51 20	97.08 7	99.38 63	99.26 37

fmvsm_s_conf0.5_n_2		94.25 160	94.63 150	93.10 223	96.65 210	81.75 315	91.72 295	97.25 198	86.93 293	97.20 77	97.67 87	88.44 246	98.14 277	97.06 9	98.77 184	99.42 24

fmvsm_s_conf0.5_n_4		94.26 156	94.58 152	93.31 213	96.40 243	82.73 300	92.59 243	97.41 180	86.60 294	96.33 132	97.07 158	89.91 223	98.07 287	96.88 10	98.01 295	99.13 50

test_fmvsmconf0.1_n		95.61 77	95.72 85	95.26 104	96.85 191	89.20 135	93.51 193	98.60 16	85.68 327	97.42 62	98.30 41	95.34 39	98.39 238	96.85 11	98.98 137	98.19 193

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 29	98.81 32	93.86 41	99.07 2	98.98 8	97.01 17	98.92 6	98.78 20	95.22 47	98.61 197	96.85 11	99.77 9	99.31 33
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
anonymousdsp		96.74 24	96.42 38	97.68 7	98.00 103	94.03 29	96.97 19	97.61 157	87.68 267	98.45 22	98.77 21	94.20 90	99.50 23	96.70 13	99.40 61	99.53 17

test_fmvsmconf_n		95.43 87	95.50 93	95.22 109	96.48 235	89.19 136	93.23 205	98.36 36	85.61 330	96.92 94	98.02 55	95.23 46	98.38 242	96.69 14	98.95 147	98.09 203

fmvsm_s_conf0.5_n_5		94.50 138	94.80 135	93.60 194	96.80 195	84.93 249	92.81 230	97.59 161	85.27 339	96.85 100	97.29 130	91.48 174	98.05 290	96.67 15	98.47 233	97.83 248

fmvsm_s_conf0.5_n_8		94.70 125	95.34 105	92.78 243	96.77 200	81.50 321	92.64 241	98.50 21	91.51 148	97.22 76	97.93 63	88.07 253	98.45 235	96.62 16	98.80 177	98.39 169

MM		94.41 147	94.14 175	95.22 109	95.84 302	87.21 186	94.31 153	90.92 439	94.48 58	92.80 332	97.52 101	85.27 306	99.49 29	96.58 17	99.57 35	98.97 73

MVSFormer		92.18 261	92.23 253	92.04 286	94.74 365	80.06 350	97.15 15	97.37 182	88.98 220	88.83 448	92.79 411	77.02 411	99.60 9	96.41 18	96.75 381	96.46 355

test_djsdf		96.62 30	96.49 35	97.01 35	98.55 54	91.77 86	97.15 15	97.37 182	88.98 220	98.26 27	98.86 16	93.35 113	99.60 9	96.41 18	99.45 48	99.66 9

test_fmvsmvis_n_1920		95.08 108	95.40 101	94.13 167	96.66 209	87.75 177	93.44 197	98.49 23	85.57 331	98.27 24	97.11 153	94.11 93	97.75 330	96.26 20	98.72 198	96.89 330

v7n		96.82 16	97.31 14	95.33 99	98.54 56	86.81 199	96.83 24	98.07 87	96.59 25	98.46 21	98.43 38	92.91 132	99.52 19	96.25 21	99.76 10	99.65 11

mvs_tets		96.83 15	96.71 26	97.17 30	98.83 29	92.51 71	96.58 39	97.61 157	87.57 270	98.80 11	98.90 15	96.50 12	99.59 13	96.15 22	99.47 44	99.40 27

fmvsm_s_conf0.5_n_6		94.14 166	94.54 155	92.95 229	96.51 231	82.74 299	92.71 236	98.13 74	86.56 296	96.44 123	96.85 178	88.51 243	98.05 290	96.03 23	99.09 118	98.06 204

lecture		97.32 6	97.64 6	96.33 54	99.01 15	90.77 108	96.90 21	98.60 16	96.30 33	97.74 42	98.00 56	96.87 8	99.39 55	95.95 24	99.42 54	98.84 98

jajsoiax		96.59 34	96.42 38	97.12 32	98.76 35	92.49 72	96.44 49	97.42 179	86.96 290	98.71 14	98.72 23	95.36 38	99.56 17	95.92 25	99.45 48	99.32 32

fmvsm_l_conf0.5_n_3		95.19 103	95.36 103	94.68 137	96.79 198	87.49 180	93.05 211	98.38 34	87.21 280	96.59 117	97.76 81	94.20 90	98.11 278	95.90 26	98.40 240	98.42 161

OurMVSNet-221017-0		96.80 19	96.75 25	96.96 38	99.03 12	91.85 83	97.98 7	98.01 103	94.15 64	98.93 5	99.07 10	88.07 253	99.57 14	95.86 27	99.69 17	99.46 22

fmvsm_l_conf0.5_n_9		94.51 137	95.11 121	92.72 245	96.70 206	83.14 285	91.91 283	97.89 123	88.44 240	97.30 69	97.57 94	91.60 166	97.54 346	95.82 28	98.74 192	97.47 286

KinetiMVS		95.09 107	95.40 101	94.15 164	97.42 149	84.35 257	93.91 175	96.69 252	94.41 60	96.67 111	97.25 135	87.67 262	99.14 102	95.78 29	98.81 174	98.97 73

test_fmvsm_n_1920		94.72 123	94.74 141	94.67 139	96.30 259	88.62 149	93.19 206	98.07 87	85.63 329	97.08 83	97.35 124	90.86 195	97.66 337	95.70 30	98.48 232	97.74 264

fmvsm_s_conf0.5_n_11		94.91 113	95.44 98	93.33 212	96.45 237	83.11 287	93.56 191	98.64 14	89.76 200	95.70 181	97.97 60	92.32 147	98.08 283	95.62 31	98.95 147	98.79 106

fmvsm_s_conf0.1_n		94.19 165	94.41 159	93.52 203	97.22 161	84.37 255	93.73 182	95.26 326	84.45 362	95.76 172	98.00 56	91.85 159	97.21 376	95.62 31	97.82 312	98.98 70

fmvsm_s_conf0.5_n		94.00 174	94.20 173	93.42 208	96.69 207	84.37 255	93.38 199	95.13 332	84.50 361	95.40 198	97.55 100	91.77 161	97.20 377	95.59 33	97.79 313	98.69 128

fmvsm_l_conf0.5_n		93.79 181	93.81 186	93.73 188	96.16 274	86.26 217	92.46 250	96.72 249	81.69 413	95.77 169	97.11 153	90.83 197	97.82 317	95.58 34	97.99 299	97.11 310

reproduce_model		97.35 4	97.24 15	97.70 4	98.44 68	95.08 12	95.88 83	98.50 21	96.62 24	98.27 24	97.93 63	94.57 79	99.50 23	95.57 35	99.35 67	98.52 151

fmvsm_s_conf0.1_n_a		94.26 156	94.37 162	93.95 176	97.36 152	85.72 236	94.15 161	95.44 317	83.25 383	95.51 191	98.05 51	92.54 141	97.19 379	95.55 36	97.46 340	98.94 81

fmvsm_s_conf0.5_n_a		94.02 172	94.08 178	93.84 182	96.72 205	85.73 235	93.65 188	95.23 328	83.30 381	95.13 225	97.56 96	92.22 151	97.17 380	95.51 37	97.41 343	98.64 138

MP-MVS-pluss		96.08 57	95.92 72	96.57 47	99.06 10	91.21 95	93.25 203	98.32 39	87.89 259	96.86 97	97.38 115	95.55 30	99.39 55	95.47 38	99.47 44	99.11 54
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_fmvs3		92.42 248	92.40 247	92.46 267	93.80 399	87.28 184	93.86 177	97.05 214	76.86 468	96.25 141	98.66 24	82.87 330	91.26 499	95.44 39	96.83 377	98.82 99

MVSMamba_PlusPlus		94.82 119	95.89 74	91.62 307	97.82 116	78.88 394	96.52 41	97.60 159	97.14 16	94.23 261	98.48 35	87.01 279	99.71 2	95.43 40	98.80 177	96.28 367

PS-MVSNAJss		96.01 59	96.04 63	95.89 71	98.82 30	88.51 155	95.57 98	97.88 124	88.72 228	98.81 10	98.86 16	90.77 198	99.60 9	95.43 40	99.53 39	99.57 16

TestfortrainingZip a		96.50 36	96.80 23	95.62 84	98.69 38	88.28 159	96.32 57	98.06 91	94.10 65	97.65 44	97.37 116	94.54 82	99.28 86	95.41 42	99.04 128	99.30 34

tt0805		95.42 90	95.93 71	93.86 181	98.75 36	88.47 156	97.68 9	94.29 359	96.48 26	95.38 199	93.63 382	94.89 66	97.94 305	95.38 43	96.92 373	95.17 416

fmvsm_l_conf0.5_n_a		93.59 189	93.63 197	93.49 205	96.10 281	85.66 238	92.32 261	96.57 263	81.32 422	95.63 186	97.14 149	90.19 213	97.73 333	95.37 44	98.03 292	97.07 315

UA-Net		97.35 4	97.24 15	97.69 5	98.22 84	93.87 40	98.42 6	98.19 62	96.95 18	95.46 196	99.23 9	93.45 108	99.57 14	95.34 45	99.89 2	99.63 12

reproduce-ours		97.28 7	97.19 17	97.57 11	98.37 73	94.84 13	95.57 98	98.40 30	96.36 31	98.18 28	97.78 76	95.47 32	99.50 23	95.26 46	99.33 73	98.36 171

our_new_method		97.28 7	97.19 17	97.57 11	98.37 73	94.84 13	95.57 98	98.40 30	96.36 31	98.18 28	97.78 76	95.47 32	99.50 23	95.26 46	99.33 73	98.36 171

MGCNet		92.88 224	92.27 252	94.69 136	92.35 436	86.03 225	92.88 227	89.68 447	90.53 180	91.52 379	96.43 213	82.52 337	99.32 78	95.01 48	99.54 38	98.71 124

BP-MVS1		91.77 271	91.10 291	93.75 186	96.42 241	83.40 274	94.10 165	91.89 426	91.27 155	93.36 299	94.85 325	64.43 493	99.29 82	94.88 49	98.74 192	98.56 148

ACMH	88.36 12	96.59 34	97.43 9	94.07 169	98.56 50	85.33 244	96.33 55	98.30 42	94.66 54	98.72 12	98.30 41	97.51 5	98.00 299	94.87 50	99.59 29	98.86 94
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v10		94.68 127	95.27 111	92.90 234	96.57 223	80.15 346	94.65 139	97.57 164	90.68 173	97.43 59	98.00 56	88.18 250	99.15 100	94.84 51	99.55 37	99.41 26

fmvsm_l_mol_unc0.5_1		94.01 173	95.09 124	90.74 363	96.48 235	76.52 449	89.38 394	97.59 161	89.00 219	98.96 3	98.98 12	91.62 165	97.76 328	94.82 52	99.01 132	97.93 228

SixPastTwentyTwo		94.91 113	95.21 112	93.98 172	98.52 58	83.19 283	95.93 80	94.84 341	94.86 53	98.49 19	98.74 22	81.45 347	99.60 9	94.69 53	99.39 62	99.15 48

TDRefinement		97.68 3	97.60 8	97.93 2	99.02 13	95.95 8	98.61 3	98.81 10	97.41 13	97.28 72	98.46 36	94.62 77	98.84 150	94.64 54	99.53 39	98.99 66

v1240		93.29 203	93.71 194	92.06 285	96.01 291	77.89 415	91.81 291	97.37 182	85.12 346	96.69 110	96.40 217	86.67 288	99.07 118	94.51 55	98.76 186	99.22 42

mmtdpeth		95.82 69	96.02 65	95.23 107	96.91 186	88.62 149	96.49 45	99.26 3	95.07 49	93.41 295	99.29 7	90.25 212	97.27 369	94.49 56	99.01 132	99.80 3

fmvsm_s_conf0.5_n_7		93.61 187	93.94 183	92.63 251	96.11 280	82.76 298	90.81 327	97.55 166	86.57 295	93.14 317	97.69 84	90.17 215	96.83 401	94.46 57	98.93 150	98.31 178

APDe-MVS		96.46 39	96.64 29	95.93 66	97.68 130	89.38 132	96.90 21	98.41 29	92.52 98	97.43 59	97.92 68	95.11 52	99.50 23	94.45 58	99.30 80	98.92 87
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMP_NAP		96.21 53	96.12 57	96.49 51	98.90 22	91.42 93	94.57 143	98.03 100	90.42 184	96.37 129	97.35 124	95.68 25	99.25 90	94.44 59	99.34 71	98.80 104

ZNCC-MVS		96.42 43	96.20 52	97.07 33	98.80 34	92.79 65	96.08 74	98.16 71	91.74 136	95.34 203	96.36 225	95.68 25	99.44 34	94.41 60	99.28 88	98.97 73

v8		94.65 128	95.29 109	92.74 244	96.65 210	79.77 363	94.59 140	97.17 204	91.86 124	97.47 58	97.93 63	88.16 251	99.08 112	94.32 61	99.47 44	99.38 28

HPM-MVS_fast		97.01 11	96.89 21	97.39 24	99.12 8	93.92 37	97.16 14	98.17 68	93.11 89	96.48 120	97.36 121	96.92 6	99.34 71	94.31 62	99.38 63	98.92 87

MTAPA		96.65 29	96.38 42	97.47 18	98.95 21	94.05 27	95.88 83	97.62 155	94.46 59	96.29 138	96.94 169	93.56 103	99.37 66	94.29 63	99.42 54	98.99 66

WR-MVS_H		96.60 32	97.05 20	95.24 106	99.02 13	86.44 211	96.78 28	98.08 84	97.42 12	98.48 20	97.86 74	91.76 163	99.63 7	94.23 64	99.84 3	99.66 9

v1921920		93.26 205	93.61 199	92.19 277	96.04 290	78.31 408	91.88 286	97.24 200	85.17 343	96.19 149	96.19 241	86.76 286	99.05 119	94.18 65	98.84 166	99.22 42

v1192		93.49 193	93.78 189	92.62 254	96.16 274	79.62 367	91.83 290	97.22 202	86.07 312	96.10 153	96.38 223	87.22 272	99.02 124	94.14 66	98.88 161	99.22 42

test-260524					97.94 108	87.97 172		97.94 116		96.37 129		93.24 117	99.34 71	94.10 67	99.19 103

mvs5depth		95.28 98	95.82 81	93.66 191	96.42 241	83.08 288	97.35 12	99.28 2	96.44 28	96.20 146	99.65 2	84.10 316	98.01 297	94.06 68	98.93 150	99.87 1

MSC_two_6792asdad				95.90 69	96.54 226	89.57 125		96.87 235					99.41 44	94.06 68	99.30 80	98.72 121

No_MVS				95.90 69	96.54 226	89.57 125		96.87 235					99.41 44	94.06 68	99.30 80	98.72 121

HPM-MVS		96.81 18	96.62 31	97.36 26	98.89 23	93.53 52	97.51 10	98.44 26	92.35 104	95.95 159	96.41 216	96.71 11	99.42 38	93.99 71	99.36 66	99.13 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SP-LightGlue		90.98 294	90.67 306	91.92 292	91.04 481	91.02 97	90.68 335	94.22 363	89.56 206	90.35 414	92.90 406	77.08 407	89.38 514	93.92 72	96.27 401	95.35 413

DVP-MVS++		95.93 63	96.34 45	94.70 135	96.54 226	86.66 205	98.45 4	98.22 59	93.26 87	97.54 51	97.36 121	93.12 122	99.38 64	93.88 73	98.68 205	98.04 208

test_0728_THIRD									93.26 87	97.40 64	97.35 124	94.69 74	99.34 71	93.88 73	99.42 54	98.89 91

nrg030		96.32 49	96.55 34	95.62 84	97.83 115	88.55 154	95.77 87	98.29 45	92.68 94	98.03 35	97.91 71	95.13 50	98.95 136	93.85 75	99.49 43	99.36 30

v144192		93.20 212	93.54 203	92.16 281	96.05 286	78.26 409	91.95 278	97.14 206	84.98 352	95.96 158	96.11 250	87.08 278	99.04 122	93.79 76	98.84 166	99.17 46

HFP-MVS		96.39 46	96.17 55	97.04 34	98.51 59	93.37 53	96.30 66	97.98 106	92.35 104	95.63 186	96.47 210	95.37 36	99.27 89	93.78 77	99.14 113	98.48 156

EI-MVSNet-UG-set		94.35 152	94.27 171	94.59 146	92.46 433	85.87 232	92.42 254	94.69 349	93.67 80	96.13 150	95.84 265	91.20 184	98.86 147	93.78 77	98.23 266	99.03 62

ACMMPR		96.46 39	96.14 56	97.41 23	98.60 47	93.82 43	96.30 66	97.96 110	92.35 104	95.57 189	96.61 201	94.93 64	99.41 44	93.78 77	99.15 112	99.00 64

EI-MVSNet-Vis-set		94.36 151	94.28 169	94.61 142	92.55 430	85.98 227	92.44 252	94.69 349	93.70 77	96.12 151	95.81 267	91.24 181	98.86 147	93.76 80	98.22 270	98.98 70

region2R		96.41 44	96.09 58	97.38 25	98.62 44	93.81 45	96.32 57	97.96 110	92.26 107	95.28 209	96.57 204	95.02 58	99.41 44	93.63 81	99.11 115	98.94 81

EC-MVSNet		95.44 86	95.62 89	94.89 124	96.93 185	87.69 178	96.48 46	99.14 6	93.93 72	92.77 334	94.52 343	93.95 97	99.49 29	93.62 82	99.22 99	97.51 283

XVS		96.49 37	96.18 53	97.44 19	98.56 50	93.99 32	96.50 43	97.95 113	94.58 55	94.38 258	96.49 209	94.56 80	99.39 55	93.57 83	99.05 123	98.93 83

X-MVStestdata		90.70 301	88.45 363	97.44 19	98.56 50	93.99 32	96.50 43	97.95 113	94.58 55	94.38 258	26.89 556	94.56 80	99.39 55	93.57 83	99.05 123	98.93 83

SMA-MVS		95.77 71	95.54 92	96.47 52	98.27 80	91.19 96	95.09 120	97.79 140	86.48 298	97.42 62	97.51 105	94.47 86	99.29 82	93.55 85	99.29 83	98.93 83
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
LuminaMVS		93.43 197	93.18 215	94.16 163	97.32 155	85.29 245	93.36 200	93.94 373	88.09 253	97.12 82	96.43 213	80.11 359	98.98 128	93.53 86	98.76 186	98.21 189

v1144		93.50 192	93.81 186	92.57 257	96.28 260	79.61 368	91.86 289	96.96 221	86.95 291	95.91 162	96.32 227	87.65 264	98.96 134	93.51 87	98.88 161	99.13 50

SR-MVS-dyc-post		96.84 14	96.60 33	97.56 13	98.07 93	95.27 9	96.37 52	98.12 77	95.66 42	97.00 89	97.03 162	94.85 69	99.42 38	93.49 88	98.84 166	98.00 213

RE-MVS-def			96.66 27		98.07 93	95.27 9	96.37 52	98.12 77	95.66 42	97.00 89	97.03 162	95.40 35		93.49 88	98.84 166	98.00 213

SteuartSystems-ACMMP		96.40 45	96.30 47	96.71 43	98.63 43	91.96 81	95.70 89	98.01 103	93.34 86	96.64 114	96.57 204	94.99 60	99.36 67	93.48 90	99.34 71	98.82 99
Skip Steuart: Steuart Systems R&D Blog.
CS-MVS		95.77 71	95.58 91	96.37 53	96.84 192	91.72 88	96.73 30	99.06 7	94.23 62	92.48 344	94.79 330	93.56 103	99.49 29	93.47 91	99.05 123	97.89 239

ACMMP		96.61 31	96.34 45	97.43 21	98.61 46	93.88 38	96.95 20	98.18 64	92.26 107	96.33 132	96.84 181	95.10 54	99.40 52	93.47 91	99.33 73	99.02 63
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
TSAR-MVS + MP.		94.96 112	94.75 139	95.57 87	98.86 27	88.69 146	96.37 52	96.81 241	85.23 340	94.75 245	97.12 152	91.85 159	99.40 52	93.45 93	98.33 252	98.62 142
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_fmvs2		90.62 308	90.40 317	91.29 329	91.93 454	85.46 242	92.70 237	96.48 270	74.44 485	94.91 239	97.59 93	75.52 426	90.57 502	93.44 94	96.56 390	97.84 247

DVP-MVS		95.82 69	96.18 53	94.72 134	98.51 59	86.69 203	95.20 117	97.00 217	91.85 125	97.40 64	97.35 124	95.58 28	99.34 71	93.44 94	99.31 78	98.13 201
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				94.88 125	98.55 54	86.72 202	95.20 117	98.22 59					99.38 64	93.44 94	99.31 78	98.53 150

MSP-MVS		95.34 93	94.63 150	97.48 17	98.67 41	94.05 27	96.41 51	98.18 64	91.26 156	95.12 226	95.15 308	86.60 290	99.50 23	93.43 97	96.81 378	98.89 91
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
PS-CasMVS		96.69 27	97.43 9	94.49 153	99.13 6	84.09 265	96.61 37	97.97 108	97.91 8	98.64 17	98.13 46	95.24 45	99.65 4	93.39 98	99.84 3	99.72 4

Vis-MVSNet		95.50 83	95.48 94	95.56 88	98.11 90	89.40 131	95.35 105	98.22 59	92.36 103	94.11 265	98.07 50	92.02 155	99.44 34	93.38 99	97.67 325	97.85 246
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
APD-MVS_3200maxsize		96.82 16	96.65 28	97.32 28	97.95 107	93.82 43	96.31 62	98.25 47	95.51 44	96.99 91	97.05 161	95.63 27	99.39 55	93.31 100	98.88 161	98.75 115

SP-SuperGlue		91.30 287	91.15 290	91.75 299	91.06 480	90.99 100	90.32 353	93.55 387	90.63 176	91.17 390	93.82 376	79.84 363	88.92 518	93.30 101	96.63 387	95.34 414

SED-MVS		96.00 60	96.41 41	94.76 132	98.51 59	86.97 193	95.21 115	98.10 81	91.95 118	97.63 46	97.25 135	96.48 13	99.35 68	93.29 102	99.29 83	97.95 223

test_241102_TWO								98.10 81	91.95 118	97.54 51	97.25 135	95.37 36	99.35 68	93.29 102	99.25 91	98.49 155

DTE-MVSNet		96.74 24	97.43 9	94.67 139	99.13 6	84.68 252	96.51 42	97.94 116	98.14 6	98.67 16	98.32 40	95.04 56	99.69 3	93.27 104	99.82 7	99.62 13

3Dnovator+	92.74 2	95.86 68	95.77 83	96.13 57	96.80 195	90.79 107	96.30 66	97.82 135	96.13 35	94.74 246	97.23 138	91.33 178	99.16 99	93.25 105	98.30 258	98.46 157

K. test v3		93.37 199	93.27 213	93.66 191	98.05 95	82.62 301	94.35 150	86.62 478	96.05 38	97.51 55	98.85 18	76.59 421	99.65 4	93.21 106	98.20 273	98.73 120

Anonymous20231211		96.60 32	97.13 19	95.00 116	97.46 146	86.35 215	97.11 18	98.24 55	97.58 11	98.72 12	98.97 13	93.15 121	99.15 100	93.18 107	99.74 13	99.50 19

GST-MVS		96.24 52	95.99 66	97.00 36	98.65 42	92.71 67	95.69 91	98.01 103	92.08 116	95.74 177	96.28 231	95.22 47	99.42 38	93.17 108	99.06 120	98.88 93

CP-MVS		96.44 42	96.08 60	97.54 14	98.29 78	94.62 18	96.80 26	98.08 84	92.67 96	95.08 231	96.39 222	94.77 73	99.42 38	93.17 108	99.44 51	98.58 146

mPP-MVS		96.46 39	96.05 62	97.69 5	98.62 44	94.65 17	96.45 47	97.74 144	92.59 97	95.47 194	96.68 195	94.50 83	99.42 38	93.10 110	99.26 90	98.99 66

ACMM	88.83 9	96.30 51	96.07 61	96.97 37	98.39 70	92.95 62	94.74 132	98.03 100	90.82 168	97.15 79	96.85 178	96.25 18	99.00 126	93.10 110	99.33 73	98.95 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		96.19 54	96.80 23	94.38 158	98.99 19	83.82 268	96.31 62	97.53 170	97.60 10	98.34 23	97.52 101	91.98 157	99.63 7	93.08 112	99.81 8	99.70 5

v2v482		93.29 203	93.63 197	92.29 269	96.35 252	78.82 396	91.77 294	96.28 279	88.45 239	95.70 181	96.26 234	86.02 297	98.90 140	93.02 113	98.80 177	99.14 49

IU-MVS					98.51 59	86.66 205		96.83 240	72.74 501	95.83 167				93.00 114	99.29 83	98.64 138

SR-MVS		96.70 26	96.42 38	97.54 14	98.05 95	94.69 15	96.13 72	98.07 87	95.17 48	96.82 101	96.73 191	95.09 55	99.43 37	92.99 115	98.71 200	98.50 153

PEN-MVS		96.69 27	97.39 12	94.61 142	99.16 4	84.50 254	96.54 40	98.05 93	98.06 7	98.64 17	98.25 43	95.01 59	99.65 4	92.95 116	99.83 5	99.68 7

FC-MVSNet-test		95.32 94	95.88 75	93.62 193	98.49 66	81.77 313	95.90 82	98.32 39	93.93 72	97.53 53	97.56 96	88.48 244	99.40 52	92.91 117	99.83 5	99.68 7

aaatest				95.52 89	98.69 38	88.21 162	96.32 57	98.58 18	88.79 226	97.38 66	96.22 237		99.39 55	92.89 118	99.10 116	98.96 77

MED-MVS		96.38 47	96.63 30	95.63 83	98.69 38	88.21 162	96.32 57	98.58 18	94.10 65	97.38 66	97.37 116	95.11 52	99.39 55	92.89 118	99.19 103	99.30 34

aaEdge-Enhanced		95.61 77	95.65 88	95.49 91	97.62 134	88.21 162	94.21 159	97.87 126	92.48 99	96.38 127	96.22 237	94.06 94	99.32 78	92.89 118	99.10 116	98.96 77

OPM-MVS		95.61 77	95.45 95	96.08 58	98.49 66	91.00 99	92.65 240	97.33 190	90.05 194	96.77 105	96.85 178	95.04 56	98.56 212	92.77 121	99.06 120	98.70 125
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PGM-MVS		96.32 49	95.94 69	97.43 21	98.59 49	93.84 42	95.33 107	98.30 42	91.40 153	95.76 172	96.87 177	95.26 44	99.45 33	92.77 121	99.21 100	99.00 64

CNVR-MVS		94.58 133	94.29 167	95.46 93	96.94 182	89.35 133	91.81 291	96.80 242	89.66 203	93.90 277	95.44 292	92.80 136	98.72 175	92.74 123	98.52 227	98.32 176

DeepC-MVS	91.39 4	95.43 87	95.33 107	95.71 78	97.67 131	90.17 118	93.86 177	98.02 102	87.35 274	96.22 144	97.99 59	94.48 85	99.05 119	92.73 124	99.68 20	97.93 228
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SD-MVS		95.19 103	95.73 84	93.55 197	96.62 219	88.88 145	94.67 137	98.05 93	91.26 156	97.25 75	96.40 217	95.42 34	94.36 470	92.72 125	99.19 103	97.40 296
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
RA-MVS			94.99 129		98.72 37	93.97 35	96.61 37	98.40 30	81.54 417	96.90 95	97.09 156	93.76 99	99.48 32	92.69 126	99.23 95

EU-MVSNet		87.39 412	86.71 417	89.44 407	93.40 409	76.11 454	94.93 128	90.00 446	57.17 548	95.71 180	97.37 116	64.77 492	97.68 336	92.67 127	94.37 470	94.52 444

lessismore_v0				93.87 180	98.05 95	83.77 269		80.32 540		97.13 80	97.91 71	77.49 398	99.11 110	92.62 128	98.08 285	98.74 119

GDP-MVS		91.56 278	90.83 300	93.77 185	96.34 253	83.65 270	93.66 186	98.12 77	87.32 276	92.98 326	94.71 333	63.58 499	99.30 81	92.61 129	98.14 278	98.35 174

Anonymous20240521		92.86 228	93.57 201	90.74 363	96.57 223	75.50 462	94.15 161	95.60 306	89.38 209	95.90 163	97.90 73	80.39 358	97.96 303	92.60 130	99.68 20	98.75 115

sc_t1		97.21 9	97.71 4	95.71 78	99.06 10	88.89 143	96.72 31	97.79 140	98.34 2	98.97 2	99.40 5	96.81 9	98.79 161	92.58 131	99.72 15	99.45 23

MVS_Test		92.57 244	93.29 210	90.40 377	93.53 404	75.85 457	92.52 246	96.96 221	88.73 227	92.35 353	96.70 194	90.77 198	98.37 246	92.53 132	95.49 428	96.99 321

BridgeMVS		93.45 195	94.17 174	91.28 330	95.81 306	78.40 402	96.20 70	97.48 176	88.56 238	95.29 207	97.20 143	85.56 305	99.21 93	92.52 133	98.91 155	96.24 370

3Dnovator	92.54 3	94.80 121	94.90 130	94.47 154	95.47 333	87.06 190	96.63 36	97.28 197	91.82 131	94.34 260	97.41 113	90.60 205	98.65 192	92.47 134	98.11 281	97.70 266

AstraMVS		92.75 233	92.73 232	92.79 242	97.02 177	81.48 322	92.88 227	90.62 443	87.99 256	96.48 120	96.71 193	82.02 342	98.48 230	92.44 135	98.46 234	98.40 168

SF-MVS		95.88 67	95.88 75	95.87 72	98.12 89	89.65 124	95.58 97	98.56 20	91.84 128	96.36 131	96.68 195	94.37 87	99.32 78	92.41 136	99.05 123	98.64 138

V42		93.43 197	93.58 200	92.97 227	95.34 339	81.22 328	92.67 238	96.49 269	87.25 278	96.20 146	96.37 224	87.32 270	98.85 149	92.39 137	98.21 271	98.85 97

Casviewmamba		95.48 85	95.97 67	94.04 170	96.94 182	84.57 253	93.96 172	98.29 45	93.94 71	96.76 106	97.14 149	95.27 43	98.72 175	92.37 138	99.02 131	98.82 99

casdiffmvs_mvg		95.10 106	95.62 89	93.53 201	96.25 266	83.23 280	92.66 239	98.19 62	93.06 90	97.49 56	97.15 148	94.78 72	98.71 182	92.27 139	98.72 198	98.65 132
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVStest1		84.79 449	84.06 454	86.98 467	77.73 556	74.76 465	91.08 317	85.63 490	77.70 460	96.86 97	97.97 60	41.05 552	88.24 522	92.22 140	96.28 400	97.94 225

HPM-MVS++		95.02 109	94.39 160	96.91 40	97.88 112	93.58 51	94.09 166	96.99 219	91.05 161	92.40 349	95.22 306	91.03 192	99.25 90	92.11 141	98.69 204	97.90 237

UniMVSNet (Re)		95.32 94	95.15 114	95.80 74	97.79 119	88.91 142	92.91 225	98.07 87	93.46 83	96.31 135	95.97 260	90.14 216	99.34 71	92.11 141	99.64 25	99.16 47

XVG-OURS-SEG-HR		95.38 91	95.00 128	96.51 49	98.10 91	94.07 24	92.46 250	98.13 74	90.69 172	93.75 281	96.25 235	98.03 2	97.02 390	92.08 143	95.55 426	98.45 158

LPG-MVS_test		96.38 47	96.23 50	96.84 41	98.36 76	92.13 78	95.33 107	98.25 47	91.78 132	97.07 84	97.22 140	96.38 16	99.28 86	92.07 144	99.59 29	99.11 54

LGP-MVS_train				96.84 41	98.36 76	92.13 78		98.25 47	91.78 132	97.07 84	97.22 140	96.38 16	99.28 86	92.07 144	99.59 29	99.11 54

guyue		92.60 240	92.62 238	92.52 264	96.73 203	81.00 331	93.00 215	91.83 428	88.28 246	96.38 127	96.23 236	80.71 355	98.37 246	92.06 146	98.37 250	98.20 191

tttt0517		89.81 340	88.90 352	92.55 258	97.00 179	79.73 366	95.03 124	83.65 512	89.88 197	95.30 205	94.79 330	53.64 523	99.39 55	91.99 147	98.79 181	98.54 149

EI-MVSNet		92.99 219	93.26 214	92.19 277	92.12 447	79.21 387	92.32 261	94.67 351	91.77 134	95.24 216	95.85 263	87.14 276	98.49 225	91.99 147	98.26 261	98.86 94

MP-MVS		96.14 55	95.68 86	97.51 16	98.81 32	94.06 25	96.10 73	97.78 142	92.73 93	93.48 293	96.72 192	94.23 89	99.42 38	91.99 147	99.29 83	99.05 61
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
IterMVS-LS		93.78 182	94.28 169	92.27 270	96.27 263	79.21 387	91.87 287	96.78 243	91.77 134	96.57 119	97.07 158	87.15 275	98.74 172	91.99 147	99.03 130	98.86 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		91.65 275	91.55 274	91.94 291	93.89 394	79.22 386	87.56 436	93.51 388	91.53 145	95.37 201	96.62 200	78.65 377	98.90 140	91.89 151	94.95 454	97.70 266

EGC-MVSNET		80.97 489	75.73 510	96.67 45	98.85 28	94.55 19	96.83 24	96.60 260	2.44 558	5.32 561	98.25 43	92.24 150	98.02 296	91.85 152	99.21 100	97.45 288

SPE-MVS-test		95.32 94	95.10 123	95.96 62	96.86 190	90.75 109	96.33 55	99.20 4	93.99 68	91.03 395	93.73 379	93.52 105	99.55 18	91.81 153	99.45 48	97.58 277

tt0320-xc		97.00 12	97.67 5	94.98 117	98.89 23	86.94 196	96.72 31	98.46 24	98.28 4	98.86 8	99.43 4	96.80 10	98.51 223	91.79 154	99.76 10	99.50 19

LS3D		96.11 56	95.83 79	96.95 39	94.75 362	94.20 23	97.34 13	97.98 106	97.31 14	95.32 204	96.77 184	93.08 124	99.20 96	91.79 154	98.16 275	97.44 290

DPE-MVS		95.89 66	95.88 75	95.92 68	97.93 109	89.83 122	93.46 195	98.30 42	92.37 102	97.75 40	96.95 168	95.14 49	99.51 20	91.74 156	99.28 88	98.41 164
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
tt0320		96.97 13	97.64 6	94.96 120	98.89 23	86.86 198	96.85 23	98.45 25	98.29 3	98.88 7	99.45 3	96.48 13	98.54 215	91.73 157	99.72 15	99.47 21

FIs		94.90 115	95.35 104	93.55 197	98.28 79	81.76 314	95.33 107	98.14 73	93.05 91	97.07 84	97.18 144	87.65 264	99.29 82	91.72 158	99.69 17	99.61 14

Gipuma		95.31 97	95.80 82	93.81 184	97.99 106	90.91 102	96.42 50	97.95 113	96.69 21	91.78 373	98.85 18	91.77 161	95.49 443	91.72 158	99.08 119	95.02 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
baseline		94.26 156	94.80 135	92.63 251	96.08 283	80.99 332	93.69 184	98.04 99	90.80 169	94.89 240	96.32 227	93.19 119	98.48 230	91.68 160	98.51 229	98.43 160

alignmvs		93.26 205	92.85 226	94.50 151	95.70 314	87.45 181	93.45 196	95.76 301	91.58 141	95.25 215	92.42 428	81.96 344	98.72 175	91.61 161	97.87 310	97.33 301

UniMVSNet_NR-MVSNet		95.35 92	95.21 112	95.76 75	97.69 129	88.59 152	92.26 267	97.84 131	94.91 52	96.80 102	95.78 272	90.42 208	99.41 44	91.60 162	99.58 33	99.29 36

DU-MVS		95.28 98	95.12 120	95.75 76	97.75 121	88.59 152	92.58 244	97.81 136	93.99 68	96.80 102	95.90 261	90.10 219	99.41 44	91.60 162	99.58 33	99.26 37

EG-PatchMatch MVS		94.54 136	94.67 148	94.14 166	97.87 114	86.50 207	92.00 276	96.74 248	88.16 252	96.93 93	97.61 92	93.04 128	97.90 306	91.60 162	98.12 280	98.03 211

MGCFI-Net		94.44 145	94.67 148	93.75 186	95.56 327	85.47 241	95.25 114	98.24 55	91.53 145	95.04 233	92.21 435	94.94 63	98.54 215	91.56 165	97.66 326	97.24 305

test_0402		95.73 73	96.22 51	94.26 161	98.19 86	85.77 234	93.24 204	97.24 200	96.88 20	97.69 43	97.77 80	94.12 92	99.13 105	91.54 166	99.29 83	97.88 240

sasdasda		94.59 131	94.69 143	94.30 159	95.60 324	87.03 191	95.59 94	98.24 55	91.56 143	95.21 218	92.04 441	94.95 61	98.66 189	91.45 167	97.57 332	97.20 307

canonicalmvs		94.59 131	94.69 143	94.30 159	95.60 324	87.03 191	95.59 94	98.24 55	91.56 143	95.21 218	92.04 441	94.95 61	98.66 189	91.45 167	97.57 332	97.20 307

XVG-OURS		94.72 123	94.12 176	96.50 50	98.00 103	94.23 22	91.48 302	98.17 68	90.72 171	95.30 205	96.47 210	87.94 258	96.98 391	91.41 169	97.61 329	98.30 180

pmmvs6		96.80 19	97.36 13	95.15 112	99.12 8	87.82 176	96.68 33	97.86 127	96.10 36	98.14 31	99.28 8	97.94 3	98.21 264	91.38 170	99.69 17	99.42 24

RoMa-HiRes		94.64 129	94.29 167	95.68 81	97.47 145	93.88 38	93.83 179	96.23 283	88.05 254	97.75 40	96.20 240	88.58 242	94.93 461	91.33 171	99.17 110	98.22 188

diffmvs_AUTHOR		92.34 253	92.70 235	91.26 331	94.20 382	78.42 401	89.12 402	97.60 159	87.16 283	93.17 316	95.50 288	88.66 239	97.57 345	91.30 172	97.61 329	97.79 254

VortexMVS		92.13 262	92.56 241	90.85 356	94.54 373	76.17 453	92.30 264	96.63 259	86.20 308	96.66 113	96.79 183	79.87 362	98.16 272	91.27 173	98.76 186	98.24 185

XVG-ACMP-BASELINE		95.68 75	95.34 105	96.69 44	98.40 69	93.04 59	94.54 147	98.05 93	90.45 183	96.31 135	96.76 186	92.91 132	98.72 175	91.19 174	99.42 54	98.32 176

hybridcas		94.81 120	95.45 95	92.88 236	96.74 202	81.36 324	93.32 202	98.13 74	92.16 113	96.79 104	96.98 167	94.91 65	98.53 219	91.16 175	98.90 156	98.75 115

E5new		94.50 138	95.15 114	92.55 258	97.04 173	80.27 342	92.96 218	98.25 47	90.18 188	95.77 169	97.45 109	94.85 69	98.59 202	91.16 175	98.73 194	98.79 106

E6new		94.50 138	95.15 114	92.55 258	97.04 173	80.28 340	92.96 218	98.25 47	90.18 188	95.76 172	97.45 109	94.86 67	98.59 202	91.16 175	98.73 194	98.79 106

E6		94.50 138	95.15 114	92.55 258	97.04 173	80.28 340	92.96 218	98.25 47	90.18 188	95.76 172	97.45 109	94.86 67	98.59 202	91.16 175	98.73 194	98.79 106

E5		94.50 138	95.15 114	92.55 258	97.04 173	80.27 342	92.96 218	98.25 47	90.18 188	95.77 169	97.45 109	94.85 69	98.59 202	91.16 175	98.73 194	98.79 106

test_fmvs1_n		88.73 372	88.38 365	89.76 398	92.06 449	82.53 302	92.30 264	96.59 262	71.14 511	92.58 341	95.41 297	68.55 469	89.57 511	91.12 180	95.66 423	97.18 309

RPSCF		95.58 80	94.89 132	97.62 8	97.58 137	96.30 7	95.97 79	97.53 170	92.42 100	93.41 295	97.78 76	91.21 183	97.77 325	91.06 181	97.06 363	98.80 104

h-mvs33		92.89 223	91.99 262	95.58 86	96.97 180	90.55 111	93.94 174	94.01 371	89.23 212	93.95 274	96.19 241	76.88 416	99.14 102	91.02 182	95.71 421	97.04 319

hse-mvs2		92.24 259	91.20 286	95.38 96	96.16 274	90.65 110	92.52 246	92.01 425	89.23 212	93.95 274	92.99 400	76.88 416	98.69 185	91.02 182	96.03 409	96.81 335

casdiffmvs		94.32 154	94.80 135	92.85 238	96.05 286	81.44 323	92.35 258	98.05 93	91.53 145	95.75 176	96.80 182	93.35 113	98.49 225	91.01 184	98.32 254	98.64 138
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GeoE		94.55 135	94.68 147	94.15 164	97.23 159	85.11 247	94.14 163	97.34 189	88.71 229	95.26 212	95.50 288	94.65 76	99.12 106	90.94 185	98.40 240	98.23 186

c3_l		91.32 286	91.42 279	91.00 346	92.29 438	76.79 440	87.52 439	96.42 273	85.76 325	94.72 248	93.89 372	82.73 333	98.16 272	90.93 186	98.55 220	98.04 208

DKM-HiRes		92.87 226	91.94 264	95.65 82	97.16 164	93.66 48	90.90 323	94.27 361	87.11 287	95.29 207	95.39 299	77.59 397	95.36 447	90.86 187	98.92 154	97.94 225

viewmamba		92.69 236	93.03 219	91.69 304	93.92 393	79.50 375	89.92 369	97.33 190	88.86 225	93.13 319	95.79 268	90.97 193	97.65 339	90.86 187	96.45 395	97.94 225

TranMVSNet+NR-MVSNet		96.07 58	96.26 49	95.50 90	98.26 81	87.69 178	93.75 181	97.86 127	95.96 41	97.48 57	97.14 149	95.33 40	99.44 34	90.79 189	99.76 10	99.38 28

test_vis1_n		89.01 362	89.01 348	89.03 419	92.57 429	82.46 304	92.62 242	96.06 292	73.02 498	90.40 410	95.77 273	74.86 430	89.68 509	90.78 190	94.98 452	94.95 428

UniMVSNet_ETH3D		97.13 10	97.72 3	95.35 97	99.51 2	87.38 182	97.70 8	97.54 167	98.16 5	98.94 4	99.33 6	97.84 4	99.08 112	90.73 191	99.73 14	99.59 15

9.14			94.81 134		97.49 142		94.11 164	98.37 35	87.56 271	95.38 199	96.03 254	94.66 75	99.08 112	90.70 192	98.97 143

diffmvs		91.74 273	91.93 265	91.15 339	93.06 418	78.17 410	88.77 416	97.51 173	86.28 305	92.42 348	93.96 369	88.04 255	97.46 353	90.69 193	96.67 385	97.82 251
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvs1		87.59 404	87.27 397	88.54 436	88.32 525	81.26 326	90.43 347	95.72 303	70.55 518	91.70 374	94.63 337	68.13 470	89.42 513	90.59 194	95.34 436	94.94 430

dcpmvs_2		93.96 176	95.01 127	90.82 359	97.60 135	74.04 479	93.68 185	98.85 9	89.80 199	97.82 37	97.01 165	91.14 188	99.21 93	90.56 195	98.59 216	99.19 45

SP-NN		88.21 384	87.96 382	88.97 422	89.33 518	87.99 169	88.06 429	90.93 438	85.48 337	84.50 503	91.11 460	77.25 405	84.79 542	90.55 196	94.42 466	94.14 454

RRT-MVS		92.28 255	93.01 220	90.07 387	94.06 388	73.01 487	95.36 104	97.88 124	92.24 109	95.16 223	97.52 101	78.51 381	99.29 82	90.55 196	95.83 418	97.92 234

balanced_ft_v1		92.65 239	93.17 216	91.10 340	94.47 375	77.32 428	96.67 34	96.70 251	88.23 248	93.70 285	97.16 145	83.33 322	99.41 44	90.51 198	97.76 315	96.57 343

MVSTER		89.32 350	88.75 355	91.03 343	90.10 506	76.62 447	90.85 325	94.67 351	82.27 403	95.24 216	95.79 268	61.09 509	98.49 225	90.49 199	98.26 261	97.97 221

DP-MVS		95.62 76	95.84 78	94.97 118	97.16 164	88.62 149	94.54 147	97.64 153	96.94 19	96.58 118	97.32 128	93.07 126	98.72 175	90.45 200	98.84 166	97.57 278

ACMP	88.15 13	95.71 74	95.43 99	96.54 48	98.17 87	91.73 87	94.24 156	98.08 84	89.46 207	96.61 116	96.47 210	95.85 22	99.12 106	90.45 200	99.56 36	98.77 114
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS_111021_LR		93.66 184	93.28 212	94.80 130	96.25 266	90.95 101	90.21 357	95.43 319	87.91 257	93.74 283	94.40 349	92.88 134	96.38 421	90.39 202	98.28 259	97.07 315

NormalMVS		94.10 167	93.36 209	96.31 55	99.01 15	90.84 105	94.70 135	97.90 119	90.98 162	93.22 311	95.73 275	78.94 371	99.12 106	90.38 203	99.42 54	98.97 73

SymmetryMVS		93.26 205	92.36 249	95.97 61	97.13 168	90.84 105	94.70 135	91.61 432	90.98 162	93.22 311	95.73 275	78.94 371	99.12 106	90.38 203	98.53 224	97.97 221

ANet_high		94.83 118	96.28 48	90.47 374	96.65 210	73.16 485	94.33 151	98.74 13	96.39 30	98.09 34	98.93 14	93.37 112	98.70 183	90.38 203	99.68 20	99.53 17

DeepPCF-MVS	90.46 6	94.20 163	93.56 202	96.14 56	95.96 293	92.96 61	89.48 389	97.46 177	85.14 345	96.23 143	95.42 294	93.19 119	98.08 283	90.37 206	98.76 186	97.38 299

SP-MNN		89.68 343	89.55 340	90.06 390	90.43 500	88.06 167	89.60 383	92.13 421	86.42 302	89.57 435	92.55 420	78.14 389	87.91 524	90.35 207	96.74 383	94.22 453

MSLP-MVS++		93.25 208	93.88 185	91.37 323	96.34 253	82.81 294	93.11 209	97.74 144	89.37 210	94.08 267	95.29 304	90.40 210	96.35 423	90.35 207	98.25 263	94.96 427

PM-MVS		93.33 202	92.67 237	95.33 99	96.58 222	94.06 25	92.26 267	92.18 417	85.92 317	96.22 144	96.61 201	85.64 303	95.99 433	90.35 207	98.23 266	95.93 387

test_vis1_n_1920		89.45 347	89.85 331	88.28 443	93.59 403	76.71 446	90.67 336	97.78 142	79.67 440	90.30 415	96.11 250	76.62 420	92.17 491	90.31 210	93.57 489	95.96 385

ACMH+	88.43 11	96.48 38	96.82 22	95.47 92	98.54 56	89.06 139	95.65 92	98.61 15	96.10 36	98.16 30	97.52 101	96.90 7	98.62 196	90.30 211	99.60 27	98.72 121

DIV-MVS_self_test		90.65 305	90.56 313	90.91 354	91.85 456	76.99 435	86.75 457	95.36 322	85.52 335	94.06 269	94.89 321	77.37 403	97.99 301	90.28 212	98.97 143	97.76 259

cl____		90.65 305	90.56 313	90.91 354	91.85 456	76.98 436	86.75 457	95.36 322	85.53 332	94.06 269	94.89 321	77.36 404	97.98 302	90.27 213	98.98 137	97.76 259

PHI-MVS		94.34 153	93.80 188	95.95 63	95.65 319	91.67 89	94.82 130	97.86 127	87.86 260	93.04 323	94.16 361	91.58 167	98.78 165	90.27 213	98.96 145	97.41 292

patch_mono-2		92.46 247	92.72 234	91.71 302	96.65 210	78.91 393	88.85 410	97.17 204	83.89 374	92.45 346	96.76 186	89.86 225	97.09 385	90.24 215	98.59 216	99.12 53

MVS_111021_HR		93.63 185	93.42 208	94.26 161	96.65 210	86.96 195	89.30 397	96.23 283	88.36 245	93.57 289	94.60 339	93.45 108	97.77 325	90.23 216	98.38 245	98.03 211

NCCC		94.08 169	93.54 203	95.70 80	96.49 233	89.90 121	92.39 256	96.91 228	90.64 174	92.33 356	94.60 339	90.58 206	98.96 134	90.21 217	97.70 323	98.23 186

viewdifsd2359ckpt11		93.36 200	93.99 179	91.48 315	95.50 331	78.39 404	90.47 342	96.69 252	88.59 233	96.03 156	96.88 175	93.48 106	97.63 341	90.20 218	98.07 287	98.41 164

viewmsd2359difaftdt		93.36 200	93.99 179	91.48 315	95.50 331	78.39 404	90.47 342	96.69 252	88.59 233	96.03 156	96.88 175	93.48 106	97.63 341	90.20 218	98.07 287	98.41 164

pm-mvs1		95.43 87	95.94 69	93.93 177	98.38 71	85.08 248	95.46 103	97.12 210	91.84 128	97.28 72	98.46 36	95.30 42	97.71 334	90.17 220	99.42 54	98.99 66

RPMNet		90.31 322	90.14 325	90.81 360	91.01 483	78.93 390	92.52 246	98.12 77	91.91 121	89.10 443	96.89 174	68.84 468	99.41 44	90.17 220	92.70 506	94.08 455

NR-MVSNet		95.28 98	95.28 110	95.26 104	97.75 121	87.21 186	95.08 121	97.37 182	93.92 74	97.65 44	95.90 261	90.10 219	99.33 77	90.11 222	99.66 23	99.26 37

COLMAP_ROB	91.06 5	96.75 23	96.62 31	97.13 31	98.38 71	94.31 21	96.79 27	98.32 39	96.69 21	96.86 97	97.56 96	95.48 31	98.77 168	90.11 222	99.44 51	98.31 178
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Baseline_NR-MVSNet		94.47 144	95.09 124	92.60 256	98.50 65	80.82 336	92.08 272	96.68 255	93.82 75	96.29 138	98.56 30	90.10 219	97.75 330	90.10 224	99.66 23	99.24 41

v148		92.87 226	93.29 210	91.62 307	96.25 266	77.72 421	91.28 308	95.05 333	89.69 201	95.93 161	96.04 253	87.34 269	98.38 242	90.05 225	97.99 299	98.78 111

E4		94.00 174	94.53 156	92.42 268	96.78 199	79.99 354	91.33 307	98.16 71	89.69 201	95.27 210	97.16 145	93.94 98	98.64 193	89.99 226	98.42 239	98.61 143

MCST-MVS		92.91 222	92.51 242	94.10 168	97.52 140	85.72 236	91.36 306	97.13 208	80.33 432	92.91 330	94.24 356	91.23 182	98.72 175	89.99 226	97.93 306	97.86 244

miper_lstm_enhance		89.90 337	89.80 332	90.19 385	91.37 472	77.50 423	83.82 516	95.00 335	84.84 355	93.05 322	94.96 318	76.53 422	95.20 454	89.96 228	98.67 207	97.86 244

ambc				92.98 226	96.88 188	83.01 290	95.92 81	96.38 275		96.41 126	97.48 107	88.26 249	97.80 320	89.96 228	98.93 150	98.12 202

CPTT-MVS		94.74 122	94.12 176	96.60 46	98.15 88	93.01 60	95.84 85	97.66 152	89.21 215	93.27 304	95.46 290	88.89 235	98.98 128	89.80 230	98.82 172	97.80 253

viewmacassd2359aftdt		93.83 180	94.36 164	92.24 273	96.45 237	79.58 372	91.60 297	97.96 110	89.14 216	95.05 232	97.09 156	93.69 101	98.48 230	89.79 231	98.43 237	98.65 132

miper_ehance_all_eth		90.48 310	90.42 316	90.69 366	91.62 466	76.57 448	86.83 455	96.18 288	83.38 380	94.06 269	92.66 417	82.20 339	98.04 292	89.79 231	97.02 366	97.45 288

eth_miper_zixun_eth		90.72 300	90.61 309	91.05 341	92.04 450	76.84 439	86.91 452	96.67 256	85.21 341	94.41 256	93.92 370	79.53 366	98.26 257	89.76 233	97.02 366	98.06 204

VPA-MVSNet		95.14 105	95.67 87	93.58 196	97.76 120	83.15 284	94.58 142	97.58 163	93.39 84	97.05 87	98.04 53	93.25 116	98.51 223	89.75 234	99.59 29	99.08 58

PMatch-Up-SfM		92.38 250	91.36 281	95.46 93	96.22 269	92.32 74	89.61 382	95.31 324	85.08 348	96.71 108	96.12 248	75.90 424	97.27 369	89.73 235	97.54 334	96.78 337

SP-DiffGlue		90.34 319	90.20 321	90.76 362	90.52 495	90.29 115	90.37 349	94.02 369	87.19 281	93.85 279	92.55 420	78.24 385	87.50 525	89.68 236	95.41 431	94.49 445

DELS-MVS		92.05 265	92.16 255	91.72 301	94.44 376	80.13 348	87.62 433	97.25 198	87.34 275	92.22 359	93.18 397	89.54 229	98.73 174	89.67 237	98.20 273	96.30 365
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DKM		92.97 221	92.35 250	94.81 129	96.53 229	93.72 47	90.94 321	94.88 339	85.21 341	96.42 125	95.18 307	83.11 325	93.06 484	89.66 238	99.24 93	97.64 271

thisisatest0530		88.69 373	87.52 388	92.20 276	96.33 255	79.36 381	92.81 230	84.01 509	86.44 300	93.67 286	92.68 416	53.62 524	99.25 90	89.65 239	98.45 235	98.00 213

DeepC-MVS_fast	89.96 7	93.73 183	93.44 206	94.60 145	96.14 277	87.90 173	93.36 200	97.14 206	85.53 332	93.90 277	95.45 291	91.30 180	98.59 202	89.51 240	98.62 212	97.31 302
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet		92.38 250	91.99 262	93.52 203	93.82 398	83.46 273	91.14 313	97.00 217	89.81 198	86.47 485	94.04 364	87.90 259	99.21 93	89.50 241	98.27 260	97.90 237

reproduce_monomvs		87.13 421	86.90 410	87.84 456	90.92 486	68.15 514	91.19 311	93.75 378	85.84 322	94.21 263	95.83 266	42.99 545	97.10 384	89.46 242	97.88 309	98.26 184

TSAR-MVS + GP.		93.07 218	92.41 246	95.06 114	95.82 304	90.87 104	90.97 320	92.61 410	88.04 255	94.61 251	93.79 377	88.08 252	97.81 319	89.41 243	98.39 244	96.50 351

testf1		96.77 21	96.49 35	97.60 9	99.01 15	96.70 3	96.31 62	98.33 37	94.96 50	97.30 69	97.93 63	96.05 20	97.90 306	89.32 244	99.23 95	98.19 193

APD_test2		96.77 21	96.49 35	97.60 9	99.01 15	96.70 3	96.31 62	98.33 37	94.96 50	97.30 69	97.93 63	96.05 20	97.90 306	89.32 244	99.23 95	98.19 193

APD-MVS		95.00 110	94.69 143	95.93 66	97.38 150	90.88 103	94.59 140	97.81 136	89.22 214	95.46 196	96.17 245	93.42 111	99.34 71	89.30 246	98.87 164	97.56 280
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
xiu_mvs_v1_base_debu		91.47 282	91.52 275	91.33 326	95.69 315	81.56 318	89.92 369	96.05 294	83.22 384	91.26 385	90.74 466	91.55 168	98.82 152	89.29 247	95.91 414	93.62 470

xiu_mvs_v1_base		91.47 282	91.52 275	91.33 326	95.69 315	81.56 318	89.92 369	96.05 294	83.22 384	91.26 385	90.74 466	91.55 168	98.82 152	89.29 247	95.91 414	93.62 470

xiu_mvs_v1_base_debi		91.47 282	91.52 275	91.33 326	95.69 315	81.56 318	89.92 369	96.05 294	83.22 384	91.26 385	90.74 466	91.55 168	98.82 152	89.29 247	95.91 414	93.62 470

HQP_MVS		94.26 156	93.93 184	95.23 107	97.71 126	88.12 165	94.56 144	97.81 136	91.74 136	93.31 301	95.59 282	86.93 282	98.95 136	89.26 250	98.51 229	98.60 144

plane_prior5								97.81 136					98.95 136	89.26 250	98.51 229	98.60 144

Patchmatch-RL test		88.81 368	88.52 361	89.69 402	95.33 340	79.94 356	86.22 474	92.71 405	78.46 456	95.80 168	94.18 360	66.25 483	95.33 450	89.22 252	98.53 224	93.78 464

PatchT		87.51 408	88.17 377	85.55 488	90.64 491	66.91 519	92.02 275	86.09 484	92.20 110	89.05 447	97.16 145	64.15 495	96.37 422	89.21 253	92.98 504	93.37 475

E2		93.53 190	93.96 181	92.25 271	96.39 244	79.76 364	91.06 318	98.05 93	88.58 235	94.71 249	96.64 197	93.08 124	98.57 208	89.16 254	97.97 301	98.42 161

E3		93.53 190	93.96 181	92.25 271	96.39 244	79.76 364	91.06 318	98.05 93	88.58 235	94.71 249	96.64 197	93.07 126	98.57 208	89.16 254	97.97 301	98.42 161

test_f		86.65 430	87.13 404	85.19 492	90.28 502	86.11 223	86.52 467	91.66 430	69.76 523	95.73 179	97.21 142	69.51 465	81.28 548	89.15 256	94.40 467	88.17 519

PMatch-SfM		91.76 272	90.58 312	95.30 103	95.64 321	91.67 89	89.49 388	94.79 346	84.45 362	96.31 135	96.02 255	71.68 454	97.26 371	89.13 257	97.75 316	96.98 322

CSCG		94.69 126	94.75 139	94.52 150	97.55 139	87.87 174	95.01 125	97.57 164	92.68 94	96.20 146	93.44 388	91.92 158	98.78 165	89.11 258	99.24 93	96.92 327

KD-MVS_self_test		94.10 167	94.73 142	92.19 277	97.66 132	79.49 376	94.86 129	97.12 210	89.59 205	96.87 96	97.65 89	90.40 210	98.34 249	89.08 259	99.35 67	98.75 115

test_vis3_rt		90.40 313	90.03 327	91.52 313	92.58 428	88.95 141	90.38 348	97.72 147	73.30 495	97.79 38	97.51 105	77.05 408	87.10 532	89.03 260	94.89 455	98.50 153

hybridnocas07		91.51 281	91.66 272	91.04 342	93.14 416	78.03 411	88.75 418	96.92 225	85.97 315	91.63 378	95.31 303	87.67 262	97.31 364	88.97 261	96.61 389	97.79 254

cl22		89.02 360	88.50 362	90.59 372	89.76 510	76.45 450	86.62 463	94.03 367	82.98 392	92.65 338	92.49 423	72.05 452	97.53 347	88.93 262	97.02 366	97.78 257

VDD-MVS		94.37 150	94.37 162	94.40 157	97.49 142	86.07 224	93.97 171	93.28 393	94.49 57	96.24 142	97.78 76	87.99 257	98.79 161	88.92 263	99.14 113	98.34 175

AUN-MVS		90.05 333	88.30 368	95.32 101	96.09 282	90.52 113	92.42 254	92.05 424	82.08 406	88.45 461	92.86 407	65.76 485	98.69 185	88.91 264	96.07 408	96.75 340

TransMVSNet (Re)		95.27 101	96.04 63	92.97 227	98.37 73	81.92 312	95.07 122	96.76 247	93.97 70	97.77 39	98.57 29	95.72 24	97.90 306	88.89 265	99.23 95	99.08 58

SSM_0407		94.23 161	94.56 154	93.24 218	96.65 210	82.79 295	93.66 186	97.84 131	91.46 149	95.19 220	96.56 206	92.50 145	98.99 127	88.83 266	98.32 254	97.93 228

SSM_0404		94.38 148	94.69 143	93.43 207	97.16 164	83.23 280	93.95 173	97.84 131	91.46 149	95.70 181	96.56 206	92.50 145	99.08 112	88.83 266	98.23 266	97.98 217

viewdifsd2359ckpt07		93.63 185	94.33 166	91.55 310	96.19 272	77.86 416	90.11 364	97.74 144	90.76 170	96.11 152	96.61 201	94.37 87	98.27 256	88.82 268	98.23 266	98.51 152

CR-MVSNet		87.89 394	87.12 405	90.22 382	91.01 483	78.93 390	92.52 246	92.81 401	73.08 497	89.10 443	96.93 171	67.11 475	97.64 340	88.80 269	92.70 506	94.08 455

CVMVSNet		85.16 445	84.72 444	86.48 476	92.12 447	70.19 504	92.32 261	88.17 462	56.15 549	90.64 405	95.85 263	67.97 473	96.69 408	88.78 270	90.52 523	92.56 487

FMVSNet1		94.84 117	95.13 119	93.97 173	97.60 135	84.29 258	95.99 76	96.56 264	92.38 101	97.03 88	98.53 31	90.12 217	98.98 128	88.78 270	99.16 111	98.65 132

ZD-MVS					97.23 159	90.32 114		97.54 167	84.40 364	94.78 244	95.79 268	92.76 137	99.39 55	88.72 272	98.40 240

casdiffseed414692147		94.56 134	94.90 130	93.54 199	96.60 220	83.33 276	93.57 190	98.06 91	91.57 142	95.26 212	97.31 129	94.06 94	98.39 238	88.67 273	98.95 147	98.91 89

train_agg		92.71 235	91.83 269	95.35 97	96.45 237	89.46 127	90.60 338	96.92 225	79.37 444	90.49 406	94.39 350	91.20 184	98.88 143	88.66 274	98.43 237	97.72 265

mamba_0408		93.60 188	93.72 191	93.27 216	96.65 210	82.79 295	88.81 413	97.68 149	90.62 177	95.19 220	96.01 256	91.54 172	99.08 112	88.63 275	98.32 254	97.93 228

SSM_04072		93.25 208	93.72 191	91.84 294	96.65 210	82.79 295	88.81 413	97.68 149	90.62 177	95.19 220	96.01 256	91.54 172	94.81 462	88.63 275	98.32 254	97.93 228

Anonymous20240529		95.50 83	95.83 79	94.50 151	97.33 154	85.93 230	95.19 119	96.77 246	96.64 23	97.61 49	98.05 51	93.23 118	98.79 161	88.60 277	99.04 128	98.78 111

viewcassd2359sk11		93.16 213	93.51 205	92.13 283	96.07 284	79.59 369	90.88 324	97.97 108	87.82 261	94.23 261	96.19 241	92.31 148	98.53 219	88.58 278	97.51 335	98.28 181

viewmanbaseed2359cas		93.08 215	93.43 207	92.01 289	95.69 315	79.29 383	91.15 312	97.70 148	87.45 273	94.18 264	96.12 248	92.31 148	98.37 246	88.58 278	97.73 318	98.38 170

RoMa-SfM		93.45 195	92.92 225	95.03 115	96.77 200	94.01 31	93.01 213	95.19 330	83.99 371	97.28 72	95.33 302	87.17 274	93.66 477	88.55 280	99.00 134	97.42 291

test1111		90.39 315	90.61 309	89.74 400	98.04 98	71.50 499	95.59 94	79.72 542	89.41 208	95.94 160	98.14 45	70.79 458	98.81 157	88.52 281	99.32 77	98.90 90

icg_test_0407_2		91.18 290	91.92 266	88.94 424	95.19 345	76.72 442	84.66 502	96.89 229	85.92 317	93.55 290	94.50 344	91.06 189	92.99 485	88.49 282	97.07 359	97.10 311

IMVS_0407		92.28 255	92.83 227	90.63 370	95.19 345	76.72 442	92.79 233	96.89 229	85.92 317	93.55 290	94.50 344	91.06 189	98.07 287	88.49 282	97.07 359	97.10 311

IMVS_0404		90.67 304	91.06 292	89.50 404	95.19 345	76.72 442	86.58 465	96.89 229	85.92 317	89.17 442	94.50 344	85.77 298	94.67 463	88.49 282	97.07 359	97.10 311

IMVS_0403		92.20 260	92.70 235	90.69 366	95.19 345	76.72 442	92.39 256	96.89 229	85.92 317	93.66 287	94.50 344	90.18 214	98.24 260	88.49 282	97.07 359	97.10 311

onestephybrid01		92.06 264	92.07 259	92.04 286	93.45 408	80.93 334	89.82 375	96.78 243	87.60 269	91.68 375	95.43 293	88.73 238	97.43 356	88.32 286	96.85 376	97.76 259

test_prior2							90.21 357		89.33 211	90.77 401	94.81 327	90.41 209		88.21 287	98.55 220

APD_test1		95.91 64	95.42 100	97.36 26	98.82 30	96.62 6	95.64 93	97.64 153	93.38 85	95.89 164	97.23 138	93.35 113	97.66 337	88.20 288	98.66 209	97.79 254

D2MVS		89.93 336	89.60 338	90.92 352	94.03 389	78.40 402	88.69 420	94.85 340	78.96 452	93.08 320	95.09 313	74.57 431	96.94 394	88.19 289	98.96 145	97.41 292

IS-MVSNet		94.49 143	94.35 165	94.92 121	98.25 83	86.46 210	97.13 17	94.31 358	96.24 34	96.28 140	96.36 225	82.88 329	99.35 68	88.19 289	99.52 41	98.96 77

E3new		92.83 229	93.10 218	92.04 286	95.78 308	79.45 377	90.76 329	97.90 119	87.23 279	93.79 280	95.70 278	91.55 168	98.49 225	88.17 291	96.99 371	98.16 196

test9_res														88.16 292	98.40 240	97.83 248

FE-MVSNET2		94.07 170	94.47 158	92.90 234	97.45 148	81.26 326	93.58 189	97.54 167	88.28 246	96.46 122	97.92 68	91.41 176	98.74 172	88.12 293	99.44 51	98.69 128

UGNet		93.08 215	92.50 243	94.79 131	93.87 395	87.99 169	95.07 122	94.26 362	90.64 174	87.33 481	97.67 87	86.89 284	98.49 225	88.10 294	98.71 200	97.91 236
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
test2506		85.42 443	84.57 447	87.96 450	97.81 117	66.53 522	96.14 71	56.35 557	89.04 217	93.55 290	98.10 48	42.88 548	98.68 187	88.09 295	99.18 107	98.67 130

hybrid		91.14 291	91.24 285	90.83 358	93.15 414	77.49 424	88.76 417	96.87 235	84.51 360	91.25 388	95.23 305	87.14 276	97.25 372	88.05 296	96.24 404	97.76 259

test_cas_vis1_n_1920		88.25 383	88.27 371	88.20 446	92.19 443	78.92 392	89.45 390	95.44 317	75.29 482	93.23 310	95.65 281	71.58 455	90.23 506	88.05 296	93.55 491	95.44 410

FA-MVS(test-final)		91.81 270	91.85 268	91.68 305	94.95 353	79.99 354	96.00 75	93.44 391	87.80 262	94.02 272	97.29 130	77.60 396	98.45 235	88.04 298	97.49 337	96.61 342

ETV-MVS		92.99 219	92.74 230	93.72 189	95.86 301	86.30 216	92.33 260	97.84 131	91.70 139	92.81 331	86.17 512	92.22 151	99.19 97	88.03 299	97.73 318	95.66 402

EIA-MVS		92.35 252	92.03 260	93.30 214	95.81 306	83.97 266	92.80 232	98.17 68	87.71 265	89.79 430	87.56 500	91.17 187	99.18 98	87.97 300	97.27 349	96.77 338

mvs_anonymous		90.37 317	91.30 284	87.58 458	92.17 445	68.00 515	89.84 374	94.73 348	83.82 375	93.22 311	97.40 114	87.54 266	97.40 360	87.94 301	95.05 451	97.34 300

IterMVS		90.18 324	90.16 322	90.21 383	93.15 414	75.98 456	87.56 436	92.97 399	86.43 301	94.09 266	96.40 217	78.32 383	97.43 356	87.87 302	94.69 462	97.23 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_enhance_ethall		88.42 378	87.87 383	90.07 387	88.67 524	75.52 461	85.10 492	95.59 310	75.68 474	92.49 343	89.45 484	78.96 370	97.88 310	87.86 303	97.02 366	96.81 335

ET-MVSNet_ETH3D		86.15 436	84.27 450	91.79 297	93.04 419	81.28 325	87.17 447	86.14 482	79.57 441	83.65 514	88.66 490	57.10 516	98.18 268	87.74 304	95.40 432	95.90 390

Effi-MVS+-dtu		93.90 179	92.60 240	97.77 3	94.74 365	96.67 5	94.00 169	95.41 320	89.94 195	91.93 370	92.13 438	90.12 217	98.97 133	87.68 305	97.48 338	97.67 269

SDMVSNet		94.43 146	95.02 126	92.69 247	97.93 109	82.88 292	91.92 282	95.99 297	93.65 81	95.51 191	98.63 26	94.60 78	96.48 415	87.57 306	99.35 67	98.70 125

WR-MVS		93.49 193	93.72 191	92.80 241	97.57 138	80.03 352	90.14 361	95.68 304	93.70 77	96.62 115	95.39 299	87.21 273	99.04 122	87.50 307	99.64 25	99.33 31

tfpnnormal		94.27 155	94.87 133	92.48 265	97.71 126	80.88 335	94.55 146	95.41 320	93.70 77	96.67 111	97.72 82	91.40 177	98.18 268	87.45 308	99.18 107	98.36 171

jason		89.17 354	88.32 367	91.70 303	95.73 312	80.07 349	88.10 427	93.22 394	71.98 505	90.09 417	92.79 411	78.53 380	98.56 212	87.43 309	97.06 363	96.46 355
jason: jason.
Effi-MVS+		92.79 230	92.74 230	92.94 231	95.10 350	83.30 278	94.00 169	97.53 170	91.36 154	89.35 439	90.65 471	94.01 96	98.66 189	87.40 310	95.30 441	96.88 332

FMVSNet2		92.78 231	92.73 232	92.95 229	95.40 335	81.98 311	94.18 160	95.53 315	88.63 230	96.05 154	97.37 116	81.31 349	98.81 157	87.38 311	98.67 207	98.06 204

EPP-MVSNet		93.91 178	93.68 196	94.59 146	98.08 92	85.55 240	97.44 11	94.03 367	94.22 63	94.94 237	96.19 241	82.07 341	99.57 14	87.28 312	98.89 159	98.65 132

PC_three_1452									75.31 481	95.87 165	95.75 274	92.93 131	96.34 425	87.18 313	98.68 205	98.04 208

ECVR-MVS		90.12 327	90.16 322	90.00 392	97.81 117	72.68 491	95.76 88	78.54 546	89.04 217	95.36 202	98.10 48	70.51 460	98.64 193	87.10 314	99.18 107	98.67 130

VDDNet		94.03 171	94.27 171	93.30 214	98.87 26	82.36 305	95.51 102	91.78 429	97.19 15	96.32 134	98.60 28	84.24 314	98.75 169	87.09 315	98.83 171	98.81 102

agg_prior2														87.06 316	98.36 251	97.98 217

LF4IMVS		92.72 234	92.02 261	94.84 128	95.65 319	91.99 80	92.92 224	96.60 260	85.08 348	92.44 347	93.62 383	86.80 285	96.35 423	86.81 317	98.25 263	96.18 374

GBi-Net		93.21 210	92.96 221	93.97 173	95.40 335	84.29 258	95.99 76	96.56 264	88.63 230	95.10 228	98.53 31	81.31 349	98.98 128	86.74 318	98.38 245	98.65 132

test1		93.21 210	92.96 221	93.97 173	95.40 335	84.29 258	95.99 76	96.56 264	88.63 230	95.10 228	98.53 31	81.31 349	98.98 128	86.74 318	98.38 245	98.65 132

FMVSNet3		90.78 298	90.32 320	92.16 281	93.03 420	79.92 357	92.54 245	94.95 337	86.17 311	95.10 228	96.01 256	69.97 464	98.75 169	86.74 318	98.38 245	97.82 251

viewdifsd2359ckpt13		92.57 244	92.48 245	92.83 239	95.60 324	82.35 307	91.80 293	97.49 175	85.04 350	93.14 317	95.41 297	90.94 194	98.25 258	86.68 321	96.24 404	97.87 243

lupinMVS		88.34 382	87.31 395	91.45 317	94.74 365	80.06 350	87.23 444	92.27 416	71.10 512	88.83 448	91.15 458	77.02 411	98.53 219	86.67 322	96.75 381	95.76 396

OMC-MVS		94.22 162	93.69 195	95.81 73	97.25 157	91.27 94	92.27 266	97.40 181	87.10 288	94.56 252	95.42 294	93.74 100	98.11 278	86.62 323	98.85 165	98.06 204

mvsany_test3		89.11 356	88.21 376	91.83 295	91.30 473	90.25 116	88.09 428	78.76 544	76.37 472	96.43 124	98.39 39	83.79 319	90.43 505	86.57 324	94.20 475	94.80 435

pmmvs-eth3d		91.54 279	90.73 305	93.99 171	95.76 311	87.86 175	90.83 326	93.98 372	78.23 458	94.02 272	96.22 237	82.62 336	96.83 401	86.57 324	98.33 252	97.29 303

BP-MVS														86.55 326

HQP-MVS		92.09 263	91.49 278	93.88 179	96.36 249	84.89 250	91.37 303	97.31 192	87.16 283	88.81 450	93.40 389	84.76 311	98.60 200	86.55 326	97.73 318	98.14 200

viewdifsd2359ckpt09		92.60 240	92.34 251	93.36 210	95.94 296	83.36 275	92.35 258	97.93 118	83.17 387	92.92 329	94.66 336	89.87 224	98.57 208	86.51 328	97.71 322	98.15 198

ppachtmachnet_test		88.61 374	88.64 357	88.50 439	91.76 459	70.99 502	84.59 504	92.98 398	79.30 448	92.38 350	93.53 387	79.57 365	97.45 354	86.50 329	97.17 356	97.07 315

MIMVSNet1		95.52 82	95.45 95	95.72 77	99.14 5	89.02 140	96.23 69	96.87 235	93.73 76	97.87 36	98.49 34	90.73 202	99.05 119	86.43 330	99.60 27	99.10 57

PVSNet_Blended_VisFu		91.63 276	91.20 286	92.94 231	97.73 124	83.95 267	92.14 271	97.46 177	78.85 454	92.35 353	94.98 317	84.16 315	99.08 112	86.36 331	96.77 380	95.79 395

Fast-Effi-MVS+-dtu		92.77 232	92.16 255	94.58 149	94.66 370	88.25 160	92.05 273	96.65 257	89.62 204	90.08 421	91.23 457	92.56 140	98.60 200	86.30 332	96.27 401	96.90 328

OPU-MVS				95.15 112	96.84 192	89.43 129	95.21 115				95.66 280	93.12 122	98.06 289	86.28 333	98.61 213	97.95 223

PMVS	87.21 14	94.97 111	95.33 107	93.91 178	98.97 20	97.16 2	95.54 101	95.85 300	96.47 27	93.40 298	97.46 108	95.31 41	95.47 444	86.18 334	98.78 183	89.11 513
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ArgMatch-SfM		91.28 288	90.08 326	94.88 125	95.22 343	92.66 69	89.81 376	94.51 355	79.15 449	95.27 210	93.71 380	78.33 382	95.52 440	86.11 335	98.63 210	96.46 355

DenseAffine		91.92 268	90.90 295	94.97 118	96.37 246	93.07 57	90.35 350	93.65 381	84.62 359	95.66 185	94.38 352	78.19 387	94.97 460	86.02 336	98.90 156	96.87 333

OpenMVS	89.45 8	92.27 258	92.13 258	92.68 248	94.53 374	84.10 264	95.70 89	97.03 215	82.44 402	91.14 393	96.42 215	88.47 245	98.38 242	85.95 337	97.47 339	95.55 407

Syy-MVS		84.81 448	84.93 443	84.42 500	91.71 462	63.36 538	85.89 477	81.49 528	81.03 423	85.13 496	81.64 539	77.44 399	95.00 456	85.94 338	94.12 478	94.91 431

CDPH-MVS		92.67 237	91.83 269	95.18 111	96.94 182	88.46 157	90.70 334	97.07 213	77.38 462	92.34 355	95.08 314	92.67 139	98.88 143	85.74 339	98.57 218	98.20 191

SSC-MVS		90.16 325	92.96 221	81.78 518	97.88 112	48.48 556	90.75 330	87.69 469	96.02 40	96.70 109	97.63 91	85.60 304	97.80 320	85.73 340	98.60 215	99.06 60

CANet_DTU		89.85 339	89.17 344	91.87 293	92.20 442	80.02 353	90.79 328	95.87 299	86.02 313	82.53 525	91.77 448	80.01 360	98.57 208	85.66 341	97.70 323	97.01 320

ITE_SJBPF				95.95 63	97.34 153	93.36 55		96.55 267	91.93 120	94.82 242	95.39 299	91.99 156	97.08 386	85.53 342	97.96 304	97.41 292

FE-MVSNET		92.02 266	92.22 254	91.41 320	96.63 218	79.08 389	91.53 299	96.84 239	85.52 335	95.16 223	96.14 246	83.97 317	97.50 349	85.48 343	98.75 190	97.64 271

gbinet_0.2-2-1-0.02		88.14 388	86.86 412	91.99 290	90.70 490	80.51 338	87.36 443	93.01 397	83.45 379	90.38 411	82.42 537	72.73 443	98.54 215	85.40 344	96.27 401	96.90 328

new-patchmatchnet		88.97 364	90.79 303	83.50 510	94.28 381	55.83 551	85.34 491	93.56 386	86.18 310	95.47 194	95.73 275	83.10 326	96.51 414	85.40 344	98.06 289	98.16 196

viewmambaseed2359dif		90.77 299	90.81 301	90.64 369	93.46 407	77.04 432	88.83 411	96.29 278	80.79 430	92.21 361	95.11 311	88.99 233	97.28 366	85.39 346	96.20 407	97.59 276

PRO-TEST		90.68 302	90.65 308	90.79 361	93.47 405	76.93 438	92.17 270	96.97 220	84.00 370	89.28 440	92.10 440	86.75 287	98.48 230	85.17 347	95.93 413	96.95 326

EPNet		89.80 341	88.25 372	94.45 155	83.91 545	86.18 221	93.87 176	87.07 476	91.16 160	80.64 537	94.72 332	78.83 373	98.89 142	85.17 347	98.89 159	98.28 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmtry		90.11 328	89.92 329	90.66 368	90.35 501	77.00 434	92.96 218	92.81 401	90.25 187	94.74 246	96.93 171	67.11 475	97.52 348	85.17 347	98.98 137	97.46 287

旧先验2							90.00 367		68.65 527	92.71 337			96.52 413	85.15 350

MDA-MVSNet-bldmvs		91.04 292	90.88 297	91.55 310	94.68 369	80.16 345	85.49 488	92.14 420	90.41 185	94.93 238	95.79 268	85.10 308	96.93 396	85.15 350	94.19 477	97.57 278

Anonymous202405211		92.58 242	92.50 243	92.83 239	96.55 225	83.22 282	92.43 253	91.64 431	94.10 65	95.59 188	96.64 197	81.88 346	97.50 349	85.12 352	98.52 227	97.77 258

AllTest		94.88 116	94.51 157	96.00 59	98.02 99	92.17 75	95.26 113	98.43 27	90.48 181	95.04 233	96.74 189	92.54 141	97.86 314	85.11 353	98.98 137	97.98 217

TestCases				96.00 59	98.02 99	92.17 75		98.43 27	90.48 181	95.04 233	96.74 189	92.54 141	97.86 314	85.11 353	98.98 137	97.98 217

VPNet		93.08 215	93.76 190	91.03 343	98.60 47	75.83 460	91.51 300	95.62 305	91.84 128	95.74 177	97.10 155	89.31 230	98.32 250	85.07 355	99.06 120	98.93 83

ArgMatch-Sym		90.98 294	89.75 335	94.68 137	95.17 349	92.64 70	89.09 403	93.46 390	78.60 455	95.11 227	92.37 429	80.44 356	95.24 453	85.04 356	98.44 236	96.18 374

LFMVS		91.33 285	91.16 289	91.82 296	96.27 263	79.36 381	95.01 125	85.61 493	96.04 39	94.82 242	97.06 160	72.03 453	98.46 234	84.96 357	98.70 203	97.65 270

VNet		92.67 237	92.96 221	91.79 297	96.27 263	80.15 346	91.95 278	94.98 336	92.19 111	94.52 254	96.07 252	87.43 268	97.39 361	84.83 358	98.38 245	97.83 248

our_test_3		87.55 405	87.59 387	87.44 460	91.76 459	70.48 503	83.83 515	90.55 444	79.79 437	92.06 368	92.17 437	78.63 379	95.63 438	84.77 359	94.73 460	96.22 372

TAPA-MVS	88.58 10	92.49 246	91.75 271	94.73 133	96.50 232	89.69 123	92.91 225	97.68 149	78.02 459	92.79 333	94.10 362	90.85 196	97.96 303	84.76 360	98.16 275	96.54 344
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		91.28 288	90.86 298	92.53 263	95.45 334	82.53 302	89.25 400	96.52 268	85.00 351	89.91 426	88.55 493	92.94 130	98.84 150	84.72 361	95.44 430	96.22 372

GA-MVS		87.70 399	86.82 413	90.31 378	93.27 412	77.22 431	84.72 500	92.79 403	85.11 347	89.82 428	90.07 472	66.80 478	97.76 328	84.56 362	94.27 473	95.96 385

QAPM		92.88 224	92.77 228	93.22 219	95.82 304	83.31 277	96.45 47	97.35 188	83.91 373	93.75 281	96.77 184	89.25 231	98.88 143	84.56 362	97.02 366	97.49 285

mvsmamba		90.24 323	89.43 341	92.64 249	95.52 329	82.36 305	96.64 35	92.29 415	81.77 410	92.14 364	96.28 231	70.59 459	99.10 111	84.44 364	95.22 446	96.47 354

blended_shiyan8		88.43 377	87.44 390	91.40 321	92.37 434	79.45 377	87.43 440	93.92 375	82.51 399	91.24 389	85.41 518	74.35 432	98.23 262	84.43 365	95.28 442	96.52 347

blended_shiyan6		88.42 378	87.43 391	91.40 321	92.37 434	79.43 379	87.41 441	93.91 376	82.51 399	91.17 390	85.44 517	74.34 433	98.24 260	84.38 366	95.32 437	96.53 346

SSC-MVS3.2		89.88 338	91.06 292	86.31 482	95.90 298	63.76 536	82.68 521	92.43 414	91.42 152	92.37 352	94.58 341	86.34 292	96.60 411	84.35 367	99.50 42	98.57 147

UnsupCasMVSNet_eth		90.33 320	90.34 319	90.28 379	94.64 371	80.24 344	89.69 381	95.88 298	85.77 324	93.94 276	95.69 279	81.99 343	92.98 486	84.21 368	91.30 518	97.62 273

LoFTR		90.05 333	89.57 339	91.50 314	93.73 400	91.47 91	90.72 332	89.37 451	81.71 412	97.13 80	96.40 217	74.09 435	92.38 489	84.18 369	98.79 181	90.63 507

testing3		83.66 463	82.52 468	87.08 464	95.84 302	65.84 527	89.80 378	77.17 550	88.17 251	90.84 400	88.63 491	30.95 557	98.11 278	84.05 370	97.19 355	97.28 304

wanda-best-256-512		87.53 406	86.39 427	90.97 348	91.29 474	78.39 404	85.63 485	93.75 378	81.91 408	90.09 417	83.30 531	72.25 448	98.18 268	83.96 371	95.32 437	96.33 361

FE-blended-shiyan7		87.53 406	86.39 427	90.97 348	91.29 474	78.39 404	85.63 485	93.75 378	81.91 408	90.09 417	83.30 531	72.25 448	98.18 268	83.96 371	95.32 437	96.33 361

CLD-MVS		91.82 269	91.41 280	93.04 224	96.37 246	83.65 270	86.82 456	97.29 195	84.65 358	92.27 357	89.67 481	92.20 153	97.85 316	83.95 373	99.47 44	97.62 273
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
114514_t		90.51 309	89.80 332	92.63 251	98.00 103	82.24 308	93.40 198	97.29 195	65.84 537	89.40 438	94.80 329	86.99 280	98.75 169	83.88 374	98.61 213	96.89 330

ELoFTR		89.04 359	88.72 356	89.99 393	94.38 379	89.08 138	90.15 360	89.10 452	75.60 476	95.85 166	96.52 208	75.00 429	89.26 515	83.82 375	98.08 285	91.61 497

DP-MVS Recon		92.31 254	91.88 267	93.60 194	97.18 163	86.87 197	91.10 315	97.37 182	84.92 353	92.08 367	94.08 363	88.59 240	98.20 265	83.50 376	98.14 278	95.73 397

YYNet1		88.17 385	88.24 373	87.93 452	92.21 441	73.62 482	80.75 530	88.77 454	82.51 399	94.99 236	95.11 311	82.70 334	93.70 476	83.33 377	93.83 484	96.48 353

MDA-MVSNet_test_wron		88.16 387	88.23 374	87.93 452	92.22 440	73.71 481	80.71 531	88.84 453	82.52 398	94.88 241	95.14 309	82.70 334	93.61 478	83.28 378	93.80 485	96.46 355

XXY-MVS		92.58 242	93.16 217	90.84 357	97.75 121	79.84 358	91.87 287	96.22 286	85.94 316	95.53 190	97.68 85	92.69 138	94.48 466	83.21 379	97.51 335	98.21 189

cascas		87.02 425	86.28 430	89.25 416	91.56 468	76.45 450	84.33 508	96.78 243	71.01 514	86.89 484	85.91 513	81.35 348	96.94 394	83.09 380	95.60 425	94.35 450

test-LLR		83.58 464	83.17 462	84.79 496	89.68 512	66.86 520	83.08 518	84.52 504	83.07 390	82.85 521	84.78 523	62.86 503	93.49 479	82.85 381	94.86 456	94.03 458

test-mter		81.21 487	80.01 496	84.79 496	89.68 512	66.86 520	83.08 518	84.52 504	73.85 491	82.85 521	84.78 523	43.66 543	93.49 479	82.85 381	94.86 456	94.03 458

pmmvs4		88.95 365	87.70 386	92.70 246	94.30 380	85.60 239	87.22 445	92.16 419	74.62 484	89.75 432	94.19 359	77.97 393	96.41 419	82.71 383	96.36 397	96.09 378

testdata				91.03 343	96.87 189	82.01 310		94.28 360	71.55 508	92.46 345	95.42 294	85.65 302	97.38 363	82.64 384	97.27 349	93.70 467

usedtu_dtu_shiyan1		89.18 351	88.59 358	90.95 350	94.75 362	77.79 418	86.25 471	94.63 353	81.61 414	90.88 397	92.24 433	77.03 409	98.08 283	82.62 385	97.27 349	96.97 323

FE-MVSNET3		89.18 351	88.59 358	90.95 350	94.75 362	77.79 418	86.25 471	94.63 353	81.61 414	90.88 397	92.25 432	77.03 409	98.08 283	82.62 385	97.27 349	96.97 323

MonoMVSNet		88.46 376	89.28 342	85.98 484	90.52 495	70.07 508	95.31 110	94.81 344	88.38 242	93.47 294	96.13 247	73.21 440	95.07 455	82.61 387	89.12 527	92.81 484

thisisatest0515		84.72 450	82.99 465	89.90 394	92.96 422	75.33 463	84.36 507	83.42 514	77.37 463	88.27 464	86.65 507	53.94 522	98.72 175	82.56 388	97.40 344	95.67 401

PS-MVSNAJ		88.86 367	88.99 349	88.48 440	94.88 354	74.71 466	86.69 460	95.60 306	80.88 427	87.83 472	87.37 504	90.77 198	98.82 152	82.52 389	94.37 470	91.93 493

xiu_mvs_v2_base		89.00 363	89.19 343	88.46 441	94.86 356	74.63 468	86.97 450	95.60 306	80.88 427	87.83 472	88.62 492	91.04 191	98.81 157	82.51 390	94.38 469	91.93 493

WB-MVS		89.44 348	92.15 257	81.32 519	97.73 124	48.22 557	89.73 379	87.98 465	95.24 47	96.05 154	96.99 166	85.18 307	96.95 393	82.45 391	97.97 301	98.78 111

PAPM_NR		91.03 293	90.81 301	91.68 305	96.73 203	81.10 330	93.72 183	96.35 277	88.19 250	88.77 454	92.12 439	85.09 309	97.25 372	82.40 392	93.90 483	96.68 341

test_yl		90.11 328	89.73 336	91.26 331	94.09 386	79.82 359	90.44 344	92.65 407	90.90 164	93.19 314	93.30 391	73.90 436	98.03 293	82.23 393	96.87 374	95.93 387

DCV-MVSNet		90.11 328	89.73 336	91.26 331	94.09 386	79.82 359	90.44 344	92.65 407	90.90 164	93.19 314	93.30 391	73.90 436	98.03 293	82.23 393	96.87 374	95.93 387

DPM-MVS		89.35 349	88.40 364	92.18 280	96.13 279	84.20 262	86.96 451	96.15 291	75.40 479	87.36 480	91.55 455	83.30 323	98.01 297	82.17 395	96.62 388	94.32 451

dtuplus		90.63 307	90.59 311	90.74 363	93.85 397	77.43 426	89.01 405	96.16 290	81.42 419	92.77 334	95.54 287	88.59 240	97.28 366	81.99 396	96.00 410	97.50 284

MG-MVS		89.54 345	89.80 332	88.76 428	94.88 354	72.47 495	89.60 383	92.44 413	85.82 323	89.48 436	95.98 259	82.85 331	97.74 332	81.87 397	95.27 443	96.08 379

PatchmatchNet		85.22 444	84.64 445	86.98 467	89.51 516	69.83 510	90.52 340	87.34 473	78.87 453	87.22 482	92.74 413	66.91 477	96.53 412	81.77 398	86.88 534	94.58 443
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TinyColmap		92.00 267	92.76 229	89.71 401	95.62 323	77.02 433	90.72 332	96.17 289	87.70 266	95.26 212	96.29 229	92.54 141	96.45 418	81.77 398	98.77 184	95.66 402

sd_testset		93.94 177	94.39 160	92.61 255	97.93 109	83.24 279	93.17 207	95.04 334	93.65 81	95.51 191	98.63 26	94.49 84	95.89 435	81.72 400	99.35 67	98.70 125

test_vis1_rt		85.58 442	84.58 446	88.60 435	87.97 526	86.76 200	85.45 490	93.59 384	66.43 534	87.64 475	89.20 487	79.33 367	85.38 541	81.59 401	89.98 526	93.66 468

ttmdpeth		86.91 428	86.57 420	87.91 454	89.68 512	74.24 476	91.49 301	87.09 474	79.84 434	89.46 437	97.86 74	65.42 487	91.04 500	81.57 402	96.74 383	98.44 159

原ACMM1				92.87 237	96.91 186	84.22 261		97.01 216	76.84 469	89.64 433	94.46 348	88.00 256	98.70 183	81.53 403	98.01 295	95.70 400

usedtu_blend_shiyan5		89.08 357	88.33 366	91.34 325	91.29 474	79.59 369	94.02 167	97.13 208	90.07 193	90.09 417	83.30 531	72.25 448	98.10 281	81.45 404	95.32 437	96.33 361

blend_shiyan4		83.29 468	80.66 488	91.19 337	91.86 455	79.59 369	87.05 449	93.91 376	82.66 395	89.60 434	83.36 530	42.82 550	98.10 281	81.45 404	73.26 550	95.87 392

1112_ss		88.42 378	87.41 393	91.45 317	96.69 207	80.99 332	89.72 380	96.72 249	73.37 494	87.00 483	90.69 469	77.38 402	98.20 265	81.38 406	93.72 486	95.15 418

MS-PatchMatch		88.05 389	87.75 384	88.95 423	93.28 411	77.93 413	87.88 431	92.49 412	75.42 478	92.57 342	93.59 385	80.44 356	94.24 473	81.28 407	92.75 505	94.69 442

LCM-MVSNet-Re		94.20 163	94.58 152	93.04 224	95.91 297	83.13 286	93.79 180	99.19 5	92.00 117	98.84 9	98.04 53	93.64 102	99.02 124	81.28 407	98.54 223	96.96 325

tpmrst		82.85 474	82.93 466	82.64 513	87.65 527	58.99 547	90.14 361	87.90 466	75.54 477	83.93 511	91.63 452	66.79 480	95.36 447	81.21 409	81.54 544	93.57 474

无先验							89.94 368	95.75 302	70.81 516				98.59 202	81.17 410		94.81 434

新几何1				93.17 222	97.16 164	87.29 183		94.43 356	67.95 529	91.29 384	94.94 319	86.97 281	98.23 262	81.06 411	97.75 316	93.98 460

MSDG		90.82 296	90.67 306	91.26 331	94.16 383	83.08 288	86.63 462	96.19 287	90.60 179	91.94 369	91.89 445	89.16 232	95.75 437	80.96 412	94.51 465	94.95 428

mvsany_test1		83.91 461	82.93 466	86.84 472	86.18 537	85.93 230	81.11 529	75.03 551	70.80 517	88.57 460	94.63 337	83.08 327	87.38 527	80.39 413	86.57 535	87.21 528

pmmvs5		87.87 395	87.14 403	90.07 387	93.26 413	76.97 437	88.89 408	92.18 417	73.71 492	88.36 462	93.89 372	76.86 418	96.73 406	80.32 414	96.81 378	96.51 348

PVSNet_BlendedMVS		90.35 318	89.96 328	91.54 312	94.81 358	78.80 398	90.14 361	96.93 223	79.43 443	88.68 458	95.06 315	86.27 294	98.15 274	80.27 415	98.04 291	97.68 268

PVSNet_Blended		88.74 371	88.16 378	90.46 376	94.81 358	78.80 398	86.64 461	96.93 223	74.67 483	88.68 458	89.18 488	86.27 294	98.15 274	80.27 415	96.00 410	94.44 448

testdata2													98.03 293	80.24 417

FE-MVS		89.06 358	88.29 369	91.36 324	94.78 360	79.57 373	96.77 29	90.99 436	84.87 354	92.96 327	96.29 229	60.69 511	98.80 160	80.18 418	97.11 358	95.71 398

F-COLMAP		92.28 255	91.06 292	95.95 63	97.52 140	91.90 82	93.53 192	97.18 203	83.98 372	88.70 456	94.04 364	88.41 247	98.55 214	80.17 419	95.99 412	97.39 297

EPMVS		81.17 488	80.37 492	83.58 509	85.58 539	65.08 531	90.31 355	71.34 552	77.31 465	85.80 491	91.30 456	59.38 512	92.70 487	79.99 420	82.34 543	92.96 482

TESTMET0.1,1		79.09 504	78.04 507	82.25 515	87.52 529	64.03 535	83.08 518	80.62 537	70.28 520	80.16 538	83.22 534	44.13 541	90.56 503	79.95 421	93.36 493	92.15 491

Test_1112_low_res		87.50 410	86.58 419	90.25 381	96.80 195	77.75 420	87.53 438	96.25 281	69.73 524	86.47 485	93.61 384	75.67 425	97.88 310	79.95 421	93.20 497	95.11 422

CL-MVSNet_self_test		90.04 335	89.90 330	90.47 374	95.24 342	77.81 417	86.60 464	92.62 409	85.64 328	93.25 309	93.92 370	83.84 318	96.06 430	79.93 423	98.03 292	97.53 282

OpenMVS_ROB	85.12 16	89.52 346	89.05 346	90.92 352	94.58 372	81.21 329	91.10 315	93.41 392	77.03 467	93.41 295	93.99 368	83.23 324	97.80 320	79.93 423	94.80 459	93.74 466

CNLPA		91.72 274	91.20 286	93.26 217	96.17 273	91.02 97	91.14 313	95.55 314	90.16 192	90.87 399	93.56 386	86.31 293	94.40 469	79.92 425	97.12 357	94.37 449

SIFT-UMatch		87.96 391	87.52 388	89.29 412	91.48 469	92.84 64	85.46 489	83.94 510	87.47 272	91.86 371	92.92 404	76.78 419	87.35 528	79.73 426	98.00 298	87.69 522

MASt3R-SfM		82.76 475	82.17 473	84.53 498	83.29 548	86.01 226	82.08 525	80.49 538	63.10 544	92.22 359	94.20 358	69.18 467	77.62 549	79.63 427	95.37 435	89.94 511

ab-mvs		92.40 249	92.62 238	91.74 300	97.02 177	81.65 317	95.84 85	95.50 316	86.95 291	92.95 328	97.56 96	90.70 203	97.50 349	79.63 427	97.43 342	96.06 380

test_post1							90.21 357				5.85 561	65.36 488	96.00 432	79.61 429

SCA		87.43 411	87.21 399	88.10 448	92.01 451	71.98 497	89.43 391	88.11 463	82.26 404	88.71 455	92.83 408	78.65 377	97.59 343	79.61 429	93.30 495	94.75 438

tpmvs		84.22 455	83.97 455	84.94 494	87.09 533	65.18 529	91.21 309	88.35 457	82.87 393	85.21 494	90.96 464	65.24 490	96.75 405	79.60 431	85.25 537	92.90 483

baseline1		87.62 403	87.31 395	88.54 436	94.71 368	74.27 475	93.10 210	88.20 461	86.20 308	92.18 362	93.04 398	73.21 440	95.52 440	79.32 432	85.82 536	95.83 393

tpm		84.38 453	84.08 453	85.30 491	90.47 498	63.43 537	89.34 395	85.63 490	77.24 466	87.62 476	95.03 316	61.00 510	97.30 365	79.26 433	91.09 521	95.16 417

BH-untuned		90.68 302	90.90 295	90.05 391	95.98 292	79.57 373	90.04 365	94.94 338	87.91 257	94.07 268	93.00 399	87.76 260	97.78 324	79.19 434	95.17 447	92.80 485

dtuonly		84.38 453	85.24 441	81.80 517	87.13 532	58.46 548	81.58 528	92.71 405	74.41 486	85.68 492	92.62 418	78.17 388	92.13 492	79.15 435	95.73 420	94.82 433

API-MVS		91.52 280	91.61 273	91.26 331	94.16 383	86.26 217	94.66 138	94.82 342	91.17 159	92.13 365	91.08 461	90.03 222	97.06 389	79.09 436	97.35 346	90.45 508

dtuonlycased		90.11 328	90.39 318	89.28 414	97.09 171	72.61 492	85.75 481	95.27 325	81.57 416	94.42 255	94.89 321	90.47 207	96.81 403	78.74 437	95.27 443	98.41 164

1314		86.46 434	86.33 429	86.87 471	91.65 465	74.54 470	91.94 280	94.10 366	74.28 488	84.78 502	87.33 505	83.03 328	95.00 456	78.72 438	91.16 520	91.06 502

BH-RMVSNet		90.47 311	90.44 315	90.56 373	95.21 344	78.65 400	89.15 401	93.94 373	88.21 249	92.74 336	94.22 357	86.38 291	97.88 310	78.67 439	95.39 433	95.14 419

SIFT-MNN		87.81 398	87.11 406	89.90 394	92.19 443	93.62 49	86.73 459	84.68 503	87.19 281	90.95 396	92.80 410	73.54 439	87.09 534	78.62 440	97.32 347	88.98 514

MVP-Stereo		90.07 332	88.92 350	93.54 199	96.31 257	86.49 208	90.93 322	95.59 310	79.80 436	91.48 380	95.59 282	80.79 353	97.39 361	78.57 441	91.19 519	96.76 339
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDTV_nov1_ep13			83.88 458		89.42 517	61.52 540	88.74 419	87.41 471	73.99 490	84.96 500	94.01 367	65.25 489	95.53 439	78.02 442	93.16 498

Vis-MVSNet (Re-imp)		90.42 312	90.16 322	91.20 336	97.66 132	77.32 428	94.33 151	87.66 470	91.20 158	92.99 324	95.13 310	75.40 427	98.28 252	77.86 443	99.19 103	97.99 216

sss		87.23 416	86.82 413	88.46 441	93.96 391	77.94 412	86.84 454	92.78 404	77.59 461	87.61 478	91.83 447	78.75 375	91.92 493	77.84 444	94.20 475	95.52 409

IB-MVS	77.21 19	83.11 469	81.05 482	89.29 412	91.15 478	75.85 457	85.66 483	86.00 485	79.70 439	82.02 530	86.61 508	48.26 530	98.39 238	77.84 444	92.22 511	93.63 469
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
Patchmatch-test		86.10 437	86.01 431	86.38 480	90.63 492	74.22 477	89.57 385	86.69 477	85.73 326	89.81 429	92.83 408	65.24 490	91.04 500	77.82 446	95.78 419	93.88 463

USDC		89.02 360	89.08 345	88.84 427	95.07 351	74.50 472	88.97 406	96.39 274	73.21 496	93.27 304	96.28 231	82.16 340	96.39 420	77.55 447	98.80 177	95.62 405

CDS-MVSNet		89.55 344	88.22 375	93.53 201	95.37 338	86.49 208	89.26 398	93.59 384	79.76 438	91.15 392	92.31 431	77.12 406	98.38 242	77.51 448	97.92 307	95.71 398
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
N_pmnet		88.90 366	87.25 398	93.83 183	94.40 378	93.81 45	84.73 497	87.09 474	79.36 446	93.26 307	92.43 427	79.29 368	91.68 495	77.50 449	97.22 354	96.00 382

testing915		88.17 385	88.00 381	88.67 431	95.72 313	74.55 469	93.05 211	87.71 468	87.29 277	90.08 421	93.23 394	70.40 461	96.73 406	77.45 450	97.05 365	94.74 441

PatchmatchNet1														77.38 451	97.25 353	96.00 382
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
AdaColmap		91.63 276	91.36 281	92.47 266	95.56 327	86.36 214	92.24 269	96.27 280	88.88 224	89.90 427	92.69 415	91.65 164	98.32 250	77.38 451	97.64 327	92.72 486

SIFT-NCM-Cal		87.99 390	87.39 394	89.77 397	92.16 446	93.98 34	86.51 468	82.96 521	85.99 314	91.10 394	92.99 400	80.00 361	87.11 531	77.21 453	97.60 331	88.22 518

CostFormer		83.09 470	82.21 471	85.73 485	89.27 519	67.01 518	90.35 350	86.47 479	70.42 519	83.52 517	93.23 394	61.18 508	96.85 400	77.21 453	88.26 531	93.34 476

E-PMN		80.72 493	80.86 485	80.29 522	85.11 542	68.77 512	72.96 543	81.97 526	87.76 264	83.25 520	83.01 535	62.22 506	89.17 516	77.15 455	94.31 472	82.93 541

SIFT-PointCN		87.02 425	86.47 426	88.65 434	90.27 503	91.47 91	83.91 512	84.08 507	84.84 355	91.35 383	92.24 433	75.25 428	87.29 530	77.11 456	99.20 102	87.20 529

PLC	85.34 15	90.40 313	88.92 350	94.85 127	96.53 229	90.02 119	91.58 298	96.48 270	80.16 433	86.14 488	92.18 436	85.73 300	98.25 258	76.87 457	94.60 464	96.30 365
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SIFT-UM-Cal		87.93 393	87.42 392	89.44 407	90.95 485	92.71 67	84.33 508	88.32 458	86.32 303	90.41 409	92.73 414	78.78 374	88.31 521	76.83 458	98.16 275	87.31 526

MAR-MVS		90.32 321	88.87 354	94.66 141	94.82 357	91.85 83	94.22 158	94.75 347	80.91 426	87.52 479	88.07 498	86.63 289	97.87 313	76.67 459	96.21 406	94.25 452
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
SIFT-ConvMatch		87.94 392	87.21 399	90.11 386	91.67 464	93.60 50	85.55 487	83.12 519	86.48 298	92.15 363	92.98 402	78.11 390	88.58 520	76.60 460	98.25 263	88.14 520

EPNet_dtu		85.63 441	84.37 448	89.40 410	86.30 536	74.33 474	91.64 296	88.26 459	84.84 355	72.96 548	89.85 473	71.27 457	97.69 335	76.60 460	97.62 328	96.18 374
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		82.94 472	81.72 475	86.59 473	92.55 430	66.53 522	86.08 476	85.70 488	85.47 338	83.95 510	85.70 515	45.87 536	97.07 388	76.58 462	93.56 490	96.17 377

JIA-IIPM		85.08 446	83.04 463	91.19 337	87.56 528	86.14 222	89.40 393	84.44 506	88.98 220	82.20 526	97.95 62	56.82 518	96.15 426	76.55 463	83.45 540	91.30 500

PatchMatch-RL		89.18 351	88.02 380	92.64 249	95.90 298	92.87 63	88.67 422	91.06 435	80.34 431	90.03 424	91.67 451	83.34 321	94.42 468	76.35 464	94.84 458	90.64 506

SIFT-NN-UMatch		86.43 435	85.66 437	88.76 428	90.73 489	92.76 66	84.99 494	81.25 532	84.13 368	88.17 466	92.04 441	76.90 415	86.62 536	76.34 465	96.36 397	86.91 532

testing91		83.56 465	82.45 469	86.91 470	92.92 423	67.29 516	86.33 470	88.07 464	86.22 307	84.26 507	85.76 514	48.15 532	97.17 380	76.27 466	94.08 481	96.27 368

FMVSNet5		87.82 397	86.56 421	91.62 307	92.31 437	79.81 361	93.49 194	94.81 344	83.26 382	91.36 382	96.93 171	52.77 526	97.49 352	76.07 467	98.03 292	97.55 281

PMMVS		83.00 471	81.11 481	88.66 433	83.81 546	86.44 211	82.24 524	85.65 489	61.75 546	82.07 528	85.64 516	79.75 364	91.59 497	75.99 468	93.09 501	87.94 521

CMPMVS	68.83 22	87.28 415	85.67 436	92.09 284	88.77 523	85.42 243	90.31 355	94.38 357	70.02 521	88.00 468	93.30 391	73.78 438	94.03 475	75.96 469	96.54 391	96.83 334
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EMVS		80.35 496	80.28 494	80.54 521	84.73 544	69.07 511	72.54 545	80.73 536	87.80 262	81.66 532	81.73 538	62.89 502	89.84 508	75.79 470	94.65 463	82.71 542

WBMVS		84.00 459	83.48 459	85.56 487	92.71 426	61.52 540	83.82 516	89.38 450	79.56 442	90.74 402	93.20 396	48.21 531	97.28 366	75.63 471	98.10 283	97.88 240

PDCNetPlus		79.66 501	78.21 506	84.01 505	79.49 553	73.91 480	75.29 541	96.44 272	66.51 533	89.20 441	91.98 444	30.56 558	84.51 545	75.48 472	98.93 150	93.62 470

SIFT-CM-Cal		87.51 408	86.76 416	89.76 398	91.48 469	93.30 56	84.73 497	84.04 508	85.53 332	91.66 376	92.58 419	77.01 413	88.75 519	75.29 473	98.56 219	87.24 527

HyFIR lowres test		87.19 419	85.51 440	92.24 273	97.12 170	80.51 338	85.03 493	96.06 292	66.11 536	91.66 376	92.98 402	70.12 462	99.14 102	75.29 473	95.23 445	97.07 315

SIFT-NN-CMatch		86.64 431	85.79 434	89.18 418	91.21 477	93.07 57	84.60 503	80.33 539	84.07 369	89.10 443	91.58 454	78.69 376	87.33 529	75.28 475	97.28 348	87.13 530

0.4-1-1-0.1		77.15 507	73.55 512	87.95 451	85.49 540	75.84 459	80.59 533	82.87 522	73.51 493	73.61 547	68.65 547	42.84 549	97.22 375	75.20 476	79.18 546	90.80 504

UnsupCasMVSNet_bld		88.50 375	88.03 379	89.90 394	95.52 329	78.88 394	87.39 442	94.02 369	79.32 447	93.06 321	94.02 366	80.72 354	94.27 471	75.16 477	93.08 502	96.54 344

ALIKED-LG		89.78 342	88.57 360	93.39 209	93.97 390	95.11 11	94.30 154	95.57 313	79.81 435	93.27 304	94.93 320	72.44 445	92.52 488	75.11 478	97.77 314	92.53 489

SIFT-NN-PointCN		86.59 432	85.79 434	88.99 420	90.15 504	92.46 73	84.96 495	82.76 523	83.11 388	88.70 456	92.34 430	77.62 395	87.10 532	75.03 479	97.44 341	87.42 525

WTY-MVS		86.93 427	86.50 425	88.24 444	94.96 352	74.64 467	87.19 446	92.07 423	78.29 457	88.32 463	91.59 453	78.06 391	94.27 471	74.88 480	93.15 499	95.80 394

SIFT-PCN-Cal		87.04 424	86.65 418	88.22 445	90.09 507	90.20 117	83.84 514	85.36 495	85.16 344	91.83 372	91.84 446	78.22 386	87.02 535	74.79 481	98.71 200	87.44 524

MatchFormer		85.84 440	85.60 438	86.56 475	90.63 492	87.98 171	89.85 373	83.79 511	72.98 499	95.69 184	94.88 324	69.40 466	87.92 523	74.60 482	98.55 220	83.77 539

0.3-1-1-0.015		75.73 510	71.83 517	87.44 460	83.47 547	74.98 464	78.69 535	83.38 516	72.24 504	70.43 550	65.81 548	39.55 553	97.08 386	74.57 483	78.30 548	90.28 509

WAC-MVS						61.25 542								74.55 484

nomal-1		83.48 466	81.65 476	88.98 421	91.07 479	80.73 337	85.66 483	86.34 480	80.98 425	83.93 511	86.95 506	51.44 527	91.71 494	74.53 485	93.93 482	94.49 445

ALIKED-MNN		88.42 378	87.16 402	92.21 275	93.47 405	93.93 36	92.87 229	95.20 329	71.10 512	87.62 476	93.76 378	77.41 400	91.34 498	74.50 486	98.53 224	91.36 498

KD-MVS_2432*1600		82.17 479	80.75 486	86.42 478	82.04 550	70.09 506	81.75 526	90.80 440	82.56 396	90.37 412	89.30 485	42.90 546	96.11 428	74.47 487	92.55 508	93.06 478

miper_refine_blended		82.17 479	80.75 486	86.42 478	82.04 550	70.09 506	81.75 526	90.80 440	82.56 396	90.37 412	89.30 485	42.90 546	96.11 428	74.47 487	92.55 508	93.06 478

testing3-2		83.95 460	84.22 451	83.13 512	96.28 260	54.34 555	88.51 424	83.01 520	92.19 111	89.09 446	90.98 462	45.51 537	97.44 355	74.38 489	98.01 295	97.60 275

0.4-1-1-0.2		75.80 509	72.05 516	87.04 465	82.70 549	74.17 478	77.51 537	83.48 513	71.80 506	71.57 549	65.16 549	43.07 544	96.96 392	74.34 490	78.78 547	90.00 510

baseline2		83.38 467	81.54 479	88.90 425	91.38 471	72.84 490	88.78 415	81.22 533	78.97 451	79.82 539	87.56 500	61.73 507	97.80 320	74.30 491	90.05 525	96.05 381

XFeat-MNN		80.76 492	79.73 497	83.85 507	79.29 554	82.86 293	76.90 539	83.32 517	69.86 522	92.27 357	87.53 502	57.82 515	84.65 543	74.17 492	96.44 396	84.03 538

testing11		81.98 482	80.52 490	86.38 480	92.69 427	67.13 517	85.79 479	84.80 502	82.16 405	81.19 536	85.41 518	45.24 538	96.88 399	74.14 493	93.24 496	95.14 419

SIFT-NN-NCMNet		86.55 433	85.56 439	89.51 403	91.84 458	94.02 30	85.72 482	81.31 531	84.33 366	86.13 489	91.77 448	79.22 369	87.46 526	74.06 494	95.70 422	87.07 531

gm-plane-assit					87.08 534	59.33 546			71.22 510		83.58 529		97.20 377	73.95 495

test20.03		90.80 297	90.85 299	90.63 370	95.63 322	79.24 385	89.81 376	92.87 400	89.90 196	94.39 257	96.40 217	85.77 298	95.27 452	73.86 496	99.05 123	97.39 297

TAMVS		90.16 325	89.05 346	93.49 205	96.49 233	86.37 213	90.34 352	92.55 411	80.84 429	92.99 324	94.57 342	81.94 345	98.20 265	73.51 497	98.21 271	95.90 390

CHOSEN 1792x2688		87.19 419	85.92 433	91.00 346	97.13 168	79.41 380	84.51 505	95.60 306	64.14 541	90.07 423	94.81 327	78.26 384	97.14 383	73.34 498	95.38 434	96.46 355

thres600view7		87.66 401	87.10 407	89.36 411	96.05 286	73.17 484	92.72 234	85.31 497	91.89 122	93.29 303	90.97 463	63.42 500	98.39 238	73.23 499	96.99 371	96.51 348

dp		79.28 503	78.62 503	81.24 520	85.97 538	56.45 550	86.91 452	85.26 499	72.97 500	81.45 534	89.17 489	56.01 520	95.45 445	73.19 500	76.68 549	91.82 496

pmmvs3		80.83 491	78.96 501	86.45 477	87.23 531	77.48 425	84.87 496	82.31 525	63.83 542	85.03 498	89.50 483	49.66 528	93.10 482	73.12 501	95.10 448	88.78 517

usedtu_dtu_shiyan2		93.15 214	92.40 247	95.41 95	98.56 50	90.53 112	94.71 134	94.14 365	92.10 115	93.73 284	96.94 169	89.66 227	97.77 325	72.97 502	98.81 174	97.92 234

MDTV_nov1_ep13_2view						42.48 560	88.45 425		67.22 532	83.56 516		66.80 478		72.86 503		94.06 457

TR-MVS		87.70 399	87.17 401	89.27 415	94.11 385	79.26 384	88.69 420	91.86 427	81.94 407	90.69 404	89.79 477	82.82 332	97.42 358	72.65 504	91.98 514	91.14 501

PAPR		87.65 402	86.77 415	90.27 380	92.85 425	77.38 427	88.56 423	96.23 283	76.82 470	84.98 499	89.75 479	86.08 296	97.16 382	72.33 505	93.35 494	96.26 369

Anonymous20231206		88.77 370	88.29 369	90.20 384	96.31 257	78.81 397	89.56 386	93.49 389	74.26 489	92.38 350	95.58 285	82.21 338	95.43 446	72.07 506	98.75 190	96.34 360

SIFT-NCMNet		87.31 414	87.07 408	88.02 449	90.01 508	91.85 83	82.65 522	89.57 449	86.52 297	93.34 300	92.51 422	78.05 392	86.22 539	71.95 507	98.98 137	86.01 535

MVS		84.98 447	84.30 449	87.01 466	91.03 482	77.69 422	91.94 280	94.16 364	59.36 547	84.23 508	87.50 503	85.66 301	96.80 404	71.79 508	93.05 503	86.54 534

tpm cat1		80.61 494	79.46 498	84.07 504	88.78 522	65.06 532	89.26 398	88.23 460	62.27 545	81.90 531	89.66 482	62.70 505	95.29 451	71.72 509	80.60 545	91.86 495

HY-MVS	82.50 18	86.81 429	85.93 432	89.47 405	93.63 401	77.93 413	94.02 167	91.58 433	75.68 474	83.64 515	93.64 381	77.40 401	97.42 358	71.70 510	92.07 513	93.05 480

testgi		90.38 316	91.34 283	87.50 459	97.49 142	71.54 498	89.43 391	95.16 331	88.38 242	94.54 253	94.68 335	92.88 134	93.09 483	71.60 511	97.85 311	97.88 240

BH-w/o		87.21 417	87.02 409	87.79 457	94.77 361	77.27 430	87.90 430	93.21 396	81.74 411	89.99 425	88.39 495	83.47 320	96.93 396	71.29 512	92.43 510	89.15 512

thres100view900		87.35 413	86.89 411	88.72 430	96.14 277	73.09 486	93.00 215	85.31 497	92.13 114	93.26 307	90.96 464	63.42 500	98.28 252	71.27 513	96.54 391	94.79 436

tfpn200view9		87.05 423	86.52 423	88.67 431	95.77 309	72.94 488	91.89 284	86.00 485	90.84 166	92.61 339	89.80 475	63.93 496	98.28 252	71.27 513	96.54 391	94.79 436

thres400		87.20 418	86.52 423	89.24 417	95.77 309	72.94 488	91.89 284	86.00 485	90.84 166	92.61 339	89.80 475	63.93 496	98.28 252	71.27 513	96.54 391	96.51 348

myMVS_eth3d		79.62 502	78.26 505	83.72 508	91.71 462	61.25 542	85.89 477	81.49 528	81.03 423	85.13 496	81.64 539	32.12 556	95.00 456	71.17 516	94.12 478	94.91 431

tpm2		81.46 484	80.35 493	84.80 495	89.90 509	65.14 530	90.44 344	85.36 495	65.82 538	82.05 529	92.44 426	57.94 514	96.69 408	70.71 517	88.49 530	92.56 487

ADS-MVSNet2		84.01 458	82.20 472	89.41 409	89.04 520	76.37 452	87.57 434	90.98 437	72.71 502	84.46 504	92.45 424	68.08 471	96.48 415	70.58 518	83.97 538	95.38 411

ADS-MVSNet		82.25 477	81.55 478	84.34 501	89.04 520	65.30 528	87.57 434	85.13 501	72.71 502	84.46 504	92.45 424	68.08 471	92.33 490	70.58 518	83.97 538	95.38 411

FBQ-MVS		83.72 462	81.80 474	89.47 405	93.62 402	76.73 441	91.20 310	87.89 467	81.52 418	84.88 501	83.74 527	49.19 529	96.66 410	70.51 520	93.70 487	95.00 426

PVSNet	76.22 20	82.89 473	82.37 470	84.48 499	93.96 391	64.38 534	78.60 536	88.61 455	71.50 509	84.43 506	86.36 511	74.27 434	94.60 465	69.87 521	93.69 488	94.46 447

CHOSEN 280x420		80.04 499	77.97 508	86.23 483	90.13 505	74.53 471	72.87 544	89.59 448	66.38 535	76.29 544	85.32 520	56.96 517	95.36 447	69.49 522	94.72 461	88.79 516

ALIKED-NN		85.96 438	84.14 452	91.44 319	91.73 461	93.37 53	90.32 353	93.65 381	67.84 530	82.08 527	92.92 404	72.88 442	90.01 507	69.17 523	96.64 386	90.93 503

SIFT-NN		84.10 457	83.04 463	87.28 463	90.76 488	92.16 77	84.45 506	81.34 530	83.54 378	83.80 513	89.75 479	70.08 463	82.09 547	68.68 524	94.96 453	87.60 523

thres200		85.85 439	85.18 442	87.88 455	94.44 376	72.52 494	89.08 404	86.21 481	88.57 237	91.44 381	88.40 494	64.22 494	98.00 299	68.35 525	95.88 417	93.12 477

dmvs_re		84.69 451	83.94 456	86.95 469	92.24 439	82.93 291	89.51 387	87.37 472	84.38 365	85.37 493	85.08 522	72.44 445	86.59 537	68.05 526	91.03 522	91.33 499

PCF-MVS	84.52 17	89.12 355	87.71 385	93.34 211	96.06 285	85.84 233	86.58 465	97.31 192	68.46 528	93.61 288	93.89 372	87.51 267	98.52 222	67.85 527	98.11 281	95.66 402
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
new_pmnet		81.22 486	81.01 484	81.86 516	90.92 486	70.15 505	84.03 510	80.25 541	70.83 515	85.97 490	89.78 478	67.93 474	84.65 543	67.44 528	91.90 515	90.78 505

gg-mvs-nofinetune		82.10 481	81.02 483	85.34 490	87.46 530	71.04 500	94.74 132	67.56 553	96.44 28	79.43 540	98.99 11	45.24 538	96.15 426	67.18 529	92.17 512	88.85 515

XFeat-NN		75.97 508	74.88 511	79.25 525	77.98 555	79.81 361	70.81 546	79.50 543	64.75 540	86.32 487	82.83 536	53.44 525	76.70 551	66.89 530	91.40 517	81.23 545

DSMNet-mixed		82.21 478	81.56 477	84.16 503	89.57 515	70.00 509	90.65 337	77.66 548	54.99 550	83.30 519	97.57 94	77.89 394	90.50 504	66.86 531	95.54 427	91.97 492

SD_0403		88.79 369	88.88 353	88.51 438	95.89 300	72.58 493	94.27 155	95.24 327	83.77 377	87.92 471	94.38 352	87.70 261	96.47 417	66.36 532	94.40 467	96.49 352

test0.0.03 1		82.48 476	81.47 480	85.48 489	89.70 511	73.57 483	84.73 497	81.64 527	83.07 390	88.13 467	86.61 508	62.86 503	89.10 517	66.24 533	90.29 524	93.77 465

MIMVSNet		87.13 421	86.54 422	88.89 426	96.05 286	76.11 454	94.39 149	88.51 456	81.37 421	88.27 464	96.75 188	72.38 447	95.52 440	65.71 534	95.47 429	95.03 424

UBG		80.28 498	78.94 502	84.31 502	92.86 424	61.77 539	83.87 513	83.31 518	77.33 464	82.78 523	83.72 528	47.60 534	96.06 430	65.47 535	93.48 492	95.11 422

UWE-MVS		80.29 497	79.10 499	83.87 506	91.97 453	59.56 545	86.50 469	77.43 549	75.40 479	87.79 474	88.10 497	44.08 542	96.90 398	64.23 536	96.36 397	95.14 419

PMMVS2		81.31 485	83.44 460	74.92 529	90.52 495	46.49 559	69.19 547	85.23 500	84.30 367	87.95 470	94.71 333	76.95 414	84.36 546	64.07 537	98.09 284	93.89 462

FPMVS		84.50 452	83.28 461	88.16 447	96.32 256	94.49 20	85.76 480	85.47 494	83.09 389	85.20 495	94.26 355	63.79 498	86.58 538	63.72 538	91.88 516	83.40 540

MVS-HIRNet		78.83 505	80.60 489	73.51 530	93.07 417	47.37 558	87.10 448	78.00 547	68.94 526	77.53 542	97.26 134	71.45 456	94.62 464	63.28 539	88.74 529	78.55 546

myMVS_eth3d28		80.97 489	80.42 491	82.62 514	93.35 410	58.25 549	84.70 501	85.62 492	86.30 304	84.04 509	85.20 521	46.00 535	94.07 474	62.93 540	95.65 424	95.53 408

WB-MVSnew		84.20 456	83.89 457	85.16 493	91.62 466	66.15 526	88.44 426	81.00 534	76.23 473	87.98 469	87.77 499	84.98 310	93.35 481	62.85 541	94.10 480	95.98 384

testing222		80.54 495	78.53 504	86.58 474	92.54 432	68.60 513	86.24 473	82.72 524	83.78 376	82.68 524	84.24 525	39.25 554	95.94 434	60.25 542	95.09 449	95.20 415

wuyk23d		87.83 396	90.79 303	78.96 526	90.46 499	88.63 148	92.72 234	90.66 442	91.65 140	98.68 15	97.64 90	96.06 19	77.53 550	59.84 543	99.41 60	70.73 547

GG-mvs-BLEND				83.24 511	85.06 543	71.03 501	94.99 127	65.55 555		74.09 546	75.51 544	44.57 540	94.46 467	59.57 544	87.54 532	84.24 537

PVSNet_0	70.34 21	74.58 512	72.96 514	79.47 523	90.63 492	66.24 524	73.26 542	83.40 515	63.67 543	78.02 541	78.35 543	72.53 444	89.59 510	56.68 545	60.05 553	82.57 543

ETVMVS		79.85 500	77.94 509	85.59 486	92.97 421	66.20 525	86.13 475	80.99 535	81.41 420	83.52 517	83.89 526	41.81 551	94.98 459	56.47 546	94.25 474	95.61 406

MVE	59.87 23	73.86 513	72.65 515	77.47 527	87.00 535	74.35 473	61.37 549	60.93 556	67.27 531	69.69 551	86.49 510	81.24 352	72.32 553	56.45 547	83.45 540	85.74 536
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PAPM		81.91 483	80.11 495	87.31 462	93.87 395	72.32 496	84.02 511	93.22 394	69.47 525	76.13 545	89.84 474	72.15 451	97.23 374	53.27 548	89.02 528	92.37 490

test_method		50.44 516	48.94 520	54.93 532	39.68 560	12.38 566	28.59 551	90.09 445	6.82 556	41.10 557	78.41 542	54.41 521	70.69 554	50.12 549	51.26 554	81.72 544

dmvs_testset		78.23 506	78.99 500	75.94 528	91.99 452	55.34 553	88.86 409	78.70 545	82.69 394	81.64 533	79.46 541	75.93 423	85.74 540	48.78 550	82.85 542	86.76 533

tmp_tt		37.97 518	44.33 521	18.88 537	11.80 563	21.54 564	63.51 548	45.66 561	4.23 557	51.34 555	50.48 553	59.08 513	22.11 559	44.50 551	68.35 552	13.00 553

UWE-MVS-28		74.73 511	73.18 513	79.35 524	85.42 541	55.55 552	87.63 432	65.92 554	74.39 487	77.33 543	88.19 496	47.63 533	89.48 512	39.01 552	93.14 500	93.03 481

DeepMVS_CX				53.83 533	70.38 557	64.56 533		48.52 560	33.01 553	65.50 553	74.21 545	56.19 519	46.64 557	38.45 553	70.07 551	50.30 550

GLUNet-SfM		58.71 514	56.43 518	65.55 531	45.28 559	59.80 544	54.31 550	55.90 558	37.80 552	81.24 535	73.75 546	38.27 555	70.23 555	34.22 554	87.09 533	66.64 548

dongtai		53.72 515	53.79 519	53.51 534	79.69 552	36.70 561	77.18 538	32.53 564	71.69 507	68.63 552	60.79 551	26.65 559	73.11 552	30.67 555	36.29 557	50.73 549

MVS_clip		28.84 519	32.57 523	17.67 538	37.77 561	25.94 563	27.92 552	7.17 565	9.16 555	54.91 554	62.94 550	20.70 561	10.56 560	26.96 556	45.58 555	16.52 552

VLMVS_CLIP		26.72 520	28.23 525	22.16 536	23.46 562	19.29 565	25.04 553	38.45 562	10.30 554	37.65 558	43.37 554	16.55 562	34.48 558	19.59 557	39.68 556	12.71 554

kuosan		43.63 517	44.25 522	41.78 535	66.04 558	34.37 562	75.56 540	32.62 563	53.25 551	50.46 556	51.18 552	25.28 560	49.13 556	13.44 558	30.40 558	41.84 551

MVS_baseline		9.63 522	12.05 526	2.37 540	9.15 564	0.73 570	5.23 555	1.75 568	0.31 562	26.23 559	30.60 555	5.95 564	0.00 564	4.43 559	24.78 559	6.38 556

VLMVS		7.75 525	8.50 531	5.52 539	7.85 565	5.47 567	5.34 554	3.06 566	0.41 561	11.88 560	15.91 557	11.95 563	3.89 561	3.42 560	16.65 560	7.20 555

test123		9.49 523	12.01 527	1.91 541	2.87 566	1.30 568	82.38 523	1.34 569	1.36 559	2.84 562	6.56 559	2.45 565	0.97 562	2.73 561	5.56 561	3.47 557

testmvs		9.02 524	11.42 528	1.81 542	2.77 567	1.13 569	79.44 534	1.90 567	1.18 560	2.65 563	6.80 558	1.95 566	0.87 563	2.62 562	3.45 562	3.44 558

mmdepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet_test		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		23.35 521	31.13 524	0.00 543	0.00 568	0.00 571	0.00 556	95.58 312	0.00 563	0.00 564	91.15 458	93.43 110	0.00 564	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		7.56 526	10.09 529	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	90.77 198	0.00 564	0.00 563	0.00 563	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

ab-mvs-re		7.56 526	10.08 530	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	90.69 469	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet2					0.00 568	54.43 554	80.66 532	86.13 483	76.71 471
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.63 496
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip				93.68 190	95.25 341	86.20 220	96.32 57	96.38 275	92.81 92	92.13 365	93.87 375	87.28 271	98.61 197		95.07 450	96.23 371

FOURS1					99.21 3	94.68 16	98.45 4	98.81 10	97.73 9	98.27 24

test_one_0601					98.26 81	87.14 188		98.18 64	94.25 61	96.99 91	97.36 121	95.13 50

eth-test2					0.00 568

eth-test					0.00 568

test_241102_ONE					98.51 59	86.97 193		98.10 81	91.85 125	97.63 46	97.03 162	96.48 13	98.95 136

save fliter					97.46 146	88.05 168	92.04 274	97.08 212	87.63 268

test0726					98.51 59	86.69 203	95.34 106	98.18 64	91.85 125	97.63 46	97.37 116	95.58 28

GSMVS																94.75 438

test_part2					98.21 85	89.41 130				96.72 107

sam_mvs1												66.64 481				94.75 438

sam_mvs												66.41 482

MTGPA								97.62 155

test_post											6.07 560	65.74 486	95.84 436

patchmatchnet-post											91.71 450	66.22 484	97.59 343

MTMP							94.82 130	54.62 559

TEST9					96.45 237	89.46 127	90.60 338	96.92 225	79.09 450	90.49 406	94.39 350	91.31 179	98.88 143

test_8					96.37 246	89.14 137	90.51 341	96.89 229	79.37 444	90.42 408	94.36 354	91.20 184	98.82 152

agg_prior					96.20 270	88.89 143		96.88 234		90.21 416			98.78 165

test_prior4						89.91 120	90.74 331

test_prior				94.61 142	95.95 294	87.23 185		97.36 187					98.68 187			97.93 228

新几何2							90.02 366

旧先验1					96.20 270	84.17 263		94.82 342			95.57 286	89.57 228			97.89 308	96.32 364

原ACMM2							89.34 395

test222					96.95 181	85.27 246	88.83 411	93.61 383	65.09 539	90.74 402	94.85 325	84.62 313			97.36 345	93.91 461

segment_acmp												92.14 154

testdata1							88.96 407		88.44 240

test12				94.43 156	95.95 294	86.75 201		96.24 282		89.76 431		89.79 226	98.79 161		97.95 305	97.75 263

plane_prior7					97.71 126	88.68 147

plane_prior6					97.21 162	88.23 161						86.93 282

plane_prior4											95.59 282

plane_prior3						88.43 158			90.35 186	93.31 301

plane_prior2							94.56 144		91.74 136

plane_prior1					97.38 150

plane_prior						88.12 165	93.01 213		88.98 220						98.06 289

n2								0.00 570

nn								0.00 570

door-mid								92.13 421

test11								96.65 257

door								91.26 434

HQP5-MVS						84.89 250

HQP-NCC					96.36 249		91.37 303		87.16 283	88.81 450

ACMP_Plane					96.36 249		91.37 303		87.16 283	88.81 450

HQP4-MVS										88.81 450			98.61 197			98.15 198

HQP3-MVS								97.31 192							97.73 318

HQP2-MVS												84.76 311

NP-MVS					96.82 194	87.10 189					93.40 389

ACMMP++_ref															98.82 172

ACMMP++															99.25 91

Test By Simon												90.61 204

High-resolution multi-view benchmark