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.

mamv4		98.21 2	97.86 3	99.26 1	98.24 81	99.36 1	96.10 70	99.32 2	98.75 2	99.58 2	98.70 23	91.78 147	99.88 1	98.60 1	99.67 23	98.54 138

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

fmvsm_s_conf0.5_n_3		95.20 101	95.95 67	92.94 216	96.60 205	82.18 266	93.13 197	98.39 32	91.44 145	97.16 75	97.68 83	93.03 116	97.82 290	97.54 3	98.63 187	98.81 99

test_fmvsmconf0.01_n		95.90 65	96.09 58	95.31 98	97.30 151	89.21 103	94.24 152	98.76 13	86.25 274	97.56 48	98.66 24	95.73 23	98.44 220	97.35 4	98.99 126	98.27 170

fmvsm_s_conf0.5_n_9		95.58 80	95.91 72	94.59 136	97.25 152	86.26 180	92.96 205	97.86 113	91.88 118	97.52 52	98.13 46	91.45 160	98.54 202	97.17 5	98.99 126	98.98 69

fmvsm_s_conf0.5_n_10		94.63 126	95.11 114	93.18 206	96.28 238	83.51 232	93.00 202	98.25 45	88.37 226	97.43 57	97.70 81	88.90 215	98.63 189	97.15 6	98.90 142	97.41 267

fmvsm_s_conf0.1_n_2		94.38 139	94.78 128	93.19 205	97.07 165	81.72 273	91.97 258	97.51 157	87.05 261	97.31 66	97.92 67	88.29 226	98.15 252	97.10 7	98.81 158	99.70 5

Elysia		96.00 59	96.36 42	94.91 115	98.01 99	85.96 189	95.29 109	97.90 106	95.31 46	98.14 31	97.28 123	88.82 217	99.51 21	97.08 8	99.38 63	99.26 35

StellarMVS		96.00 59	96.36 42	94.91 115	98.01 99	85.96 189	95.29 109	97.90 106	95.31 46	98.14 31	97.28 123	88.82 217	99.51 21	97.08 8	99.38 63	99.26 35

fmvsm_s_conf0.5_n_2		94.25 151	94.63 140	93.10 208	96.65 195	81.75 272	91.72 276	97.25 181	86.93 265	97.20 74	97.67 85	88.44 224	98.14 255	97.06 10	98.77 166	99.42 24

fmvsm_s_conf0.5_n_4		94.26 147	94.58 142	93.31 198	96.40 224	82.73 257	92.59 225	97.41 164	86.60 266	96.33 121	97.07 145	89.91 205	98.07 260	96.88 11	98.01 263	99.13 49

test_fmvsmconf0.1_n		95.61 77	95.72 84	95.26 99	96.85 179	89.20 104	93.51 183	98.60 16	85.68 293	97.42 60	98.30 41	95.34 39	98.39 221	96.85 12	98.98 128	98.19 179

LTVRE_ROB	93.87 1	97.93 3	98.16 2	97.26 30	98.81 32	93.86 35	99.07 2	98.98 9	97.01 18	98.92 6	98.78 19	95.22 46	98.61 191	96.85 12	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 25	96.42 37	97.68 8	98.00 101	94.03 29	96.97 19	97.61 143	87.68 246	98.45 22	98.77 20	94.20 83	99.50 24	96.70 14	99.40 61	99.53 17

test_fmvsmconf_n		95.43 86	95.50 92	95.22 104	96.48 218	89.19 105	93.23 194	98.36 35	85.61 296	96.92 90	98.02 55	95.23 45	98.38 224	96.69 15	98.95 137	98.09 188

fmvsm_s_conf0.5_n_5		94.50 133	94.80 125	93.60 182	96.80 184	84.93 210	92.81 212	97.59 147	85.27 303	96.85 95	97.29 121	91.48 159	98.05 263	96.67 16	98.47 206	97.83 229

fmvsm_s_conf0.5_n_8		94.70 122	95.34 102	92.78 226	96.77 187	81.50 278	92.64 223	98.50 21	91.51 142	97.22 73	97.93 62	88.07 231	98.45 218	96.62 17	98.80 161	98.39 156

MM		94.41 138	94.14 162	95.22 104	95.84 279	87.21 149	94.31 150	90.92 385	94.48 59	92.80 297	97.52 99	85.27 279	99.49 30	96.58 18	99.57 36	98.97 72

MVSFormer		92.18 239	92.23 232	92.04 261	94.74 334	80.06 298	97.15 15	97.37 166	88.98 204	88.83 382	92.79 365	77.02 361	99.60 10	96.41 19	96.75 332	96.46 320

test_djsdf		96.62 31	96.49 34	97.01 36	98.55 51	91.77 63	97.15 15	97.37 166	88.98 204	98.26 27	98.86 15	93.35 103	99.60 10	96.41 19	99.45 49	99.66 9

test_fmvsmvis_n_1920		95.08 107	95.40 98	94.13 157	96.66 194	87.75 139	93.44 187	98.49 23	85.57 297	98.27 24	97.11 141	94.11 86	97.75 301	96.26 21	98.72 176	96.89 300

v7n		96.82 17	97.31 15	95.33 95	98.54 53	86.81 162	96.83 24	98.07 79	96.59 26	98.46 21	98.43 38	92.91 119	99.52 20	96.25 22	99.76 10	99.65 11

mvs_tets		96.83 16	96.71 26	97.17 31	98.83 29	92.51 52	96.58 37	97.61 143	87.57 248	98.80 11	98.90 14	96.50 12	99.59 14	96.15 23	99.47 45	99.40 27

fmvsm_s_conf0.5_n_6		94.14 157	94.54 145	92.95 214	96.51 214	82.74 256	92.71 218	98.13 67	86.56 268	96.44 114	96.85 163	88.51 221	98.05 263	96.03 24	99.09 113	98.06 189

lecture		97.32 7	97.64 7	96.33 55	99.01 15	90.77 80	96.90 21	98.60 16	96.30 34	97.74 41	98.00 56	96.87 8	99.39 54	95.95 25	99.42 54	98.84 96

jajsoiax		96.59 35	96.42 37	97.12 33	98.76 35	92.49 53	96.44 47	97.42 163	86.96 262	98.71 14	98.72 22	95.36 38	99.56 18	95.92 26	99.45 49	99.32 32

fmvsm_l_conf0.5_n_3		95.19 102	95.36 100	94.68 128	96.79 186	87.49 143	93.05 200	98.38 33	87.21 255	96.59 109	97.76 79	94.20 83	98.11 256	95.90 27	98.40 211	98.42 151

OurMVSNet-221017-0		96.80 20	96.75 25	96.96 39	99.03 12	91.85 61	97.98 7	98.01 91	94.15 65	98.93 5	99.07 10	88.07 231	99.57 15	95.86 28	99.69 17	99.46 22

fmvsm_l_conf0.5_n_9		94.51 132	95.11 114	92.72 228	96.70 191	83.14 244	91.91 264	97.89 109	88.44 222	97.30 67	97.57 92	91.60 152	97.54 316	95.82 29	98.74 174	97.47 262

KinetiMVS		95.09 106	95.40 98	94.15 154	97.42 144	84.35 217	93.91 169	96.69 229	94.41 61	96.67 103	97.25 126	87.67 240	99.14 99	95.78 30	98.81 158	98.97 72

test_fmvsm_n_1920		94.72 120	94.74 131	94.67 129	96.30 237	88.62 117	93.19 195	98.07 79	85.63 295	97.08 79	97.35 116	90.86 178	97.66 308	95.70 31	98.48 205	97.74 242

fmvsm_s_conf0.1_n		94.19 156	94.41 147	93.52 190	97.22 156	84.37 215	93.73 175	95.26 296	84.45 320	95.76 157	98.00 56	91.85 145	97.21 339	95.62 32	97.82 277	98.98 69

fmvsm_s_conf0.5_n		94.00 163	94.20 160	93.42 195	96.69 192	84.37 215	93.38 189	95.13 300	84.50 319	95.40 178	97.55 98	91.77 148	97.20 340	95.59 33	97.79 278	98.69 119

fmvsm_l_conf0.5_n		93.79 169	93.81 171	93.73 177	96.16 251	86.26 180	92.46 232	96.72 227	81.69 356	95.77 156	97.11 141	90.83 180	97.82 290	95.58 34	97.99 266	97.11 285

reproduce_model		97.35 5	97.24 16	97.70 5	98.44 65	95.08 12	95.88 81	98.50 21	96.62 25	98.27 24	97.93 62	94.57 73	99.50 24	95.57 35	99.35 67	98.52 141

fmvsm_s_conf0.1_n_a		94.26 147	94.37 150	93.95 165	97.36 147	85.72 197	94.15 157	95.44 289	83.25 333	95.51 171	98.05 51	92.54 128	97.19 342	95.55 36	97.46 300	98.94 80

fmvsm_s_conf0.5_n_a		94.02 162	94.08 165	93.84 171	96.72 190	85.73 196	93.65 181	95.23 298	83.30 331	95.13 201	97.56 94	92.22 137	97.17 343	95.51 37	97.41 302	98.64 128

MP-MVS-pluss		96.08 56	95.92 71	96.57 48	99.06 10	91.21 69	93.25 192	98.32 38	87.89 238	96.86 92	97.38 109	95.55 30	99.39 54	95.47 38	99.47 45	99.11 53
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_fmvs3		92.42 227	92.40 228	92.46 246	93.80 363	87.28 147	93.86 171	97.05 196	76.86 401	96.25 129	98.66 24	82.87 301	91.26 444	95.44 39	96.83 328	98.82 97

MVSMamba_PlusPlus		94.82 117	95.89 73	91.62 276	97.82 113	78.88 332	96.52 39	97.60 145	97.14 17	94.23 233	98.48 35	87.01 253	99.71 3	95.43 40	98.80 161	96.28 328

PS-MVSNAJss		96.01 58	96.04 63	95.89 72	98.82 30	88.51 123	95.57 96	97.88 110	88.72 212	98.81 10	98.86 15	90.77 181	99.60 10	95.43 40	99.53 40	99.57 16

TestfortrainingZip a		95.98 62	96.18 52	95.38 91	98.69 37	87.60 142	96.32 55	98.58 18	88.79 209	97.38 64	96.22 218	95.11 51	99.39 54	95.41 42	99.10 110	99.16 45

tt0805		95.42 89	95.93 70	93.86 170	98.75 36	88.47 124	97.68 9	94.29 322	96.48 27	95.38 179	93.63 343	94.89 64	97.94 278	95.38 43	96.92 325	95.17 371

fmvsm_l_conf0.5_n_a		93.59 177	93.63 182	93.49 192	96.10 258	85.66 199	92.32 243	96.57 240	81.32 359	95.63 166	97.14 138	90.19 195	97.73 304	95.37 44	98.03 260	97.07 290

UA-Net		97.35 5	97.24 16	97.69 6	98.22 82	93.87 34	98.42 6	98.19 56	96.95 19	95.46 176	99.23 9	93.45 98	99.57 15	95.34 45	99.89 2	99.63 12

reproduce-ours		97.28 8	97.19 18	97.57 12	98.37 70	94.84 13	95.57 96	98.40 30	96.36 32	98.18 28	97.78 74	95.47 32	99.50 24	95.26 46	99.33 73	98.36 158

our_new_method		97.28 8	97.19 18	97.57 12	98.37 70	94.84 13	95.57 96	98.40 30	96.36 32	98.18 28	97.78 74	95.47 32	99.50 24	95.26 46	99.33 73	98.36 158

MGCNet		92.88 207	92.27 231	94.69 127	92.35 391	86.03 187	92.88 210	89.68 393	90.53 173	91.52 334	96.43 195	82.52 308	99.32 76	95.01 48	99.54 39	98.71 115

BP-MVS1		91.77 247	91.10 264	93.75 175	96.42 222	83.40 234	94.10 161	91.89 373	91.27 149	93.36 267	94.85 292	64.43 422	99.29 80	94.88 49	98.74 174	98.56 137

ACMH	88.36 12	96.59 35	97.43 10	94.07 159	98.56 48	85.33 205	96.33 53	98.30 41	94.66 55	98.72 12	98.30 41	97.51 5	98.00 272	94.87 50	99.59 30	98.86 92
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v10		94.68 124	95.27 108	92.90 219	96.57 207	80.15 294	94.65 136	97.57 149	90.68 167	97.43 57	98.00 56	88.18 228	99.15 97	94.84 51	99.55 38	99.41 26

SixPastTwentyTwo		94.91 112	95.21 109	93.98 161	98.52 55	83.19 242	95.93 78	94.84 308	94.86 54	98.49 19	98.74 21	81.45 318	99.60 10	94.69 52	99.39 62	99.15 47

TDRefinement		97.68 4	97.60 9	97.93 3	99.02 13	95.95 9	98.61 3	98.81 11	97.41 14	97.28 70	98.46 36	94.62 71	98.84 147	94.64 53	99.53 40	98.99 65

v1240		93.29 188	93.71 179	92.06 260	96.01 268	77.89 350	91.81 272	97.37 166	85.12 308	96.69 102	96.40 199	86.67 261	99.07 115	94.51 54	98.76 168	99.22 40

mmtdpeth		95.82 69	96.02 65	95.23 102	96.91 174	88.62 117	96.49 43	99.26 4	95.07 50	93.41 263	99.29 7	90.25 194	97.27 336	94.49 55	99.01 125	99.80 3

fmvsm_s_conf0.5_n_7		93.61 175	93.94 168	92.63 235	96.11 257	82.76 255	90.81 302	97.55 151	86.57 267	93.14 283	97.69 82	90.17 197	96.83 362	94.46 56	98.93 138	98.31 165

APDe-MVS		96.46 39	96.64 29	95.93 67	97.68 127	89.38 101	96.90 21	98.41 29	92.52 95	97.43 57	97.92 67	95.11 51	99.50 24	94.45 57	99.30 80	98.92 86
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMP_NAP		96.21 52	96.12 57	96.49 52	98.90 22	91.42 67	94.57 140	98.03 88	90.42 177	96.37 119	97.35 116	95.68 25	99.25 87	94.44 58	99.34 71	98.80 101

ZNCC-MVS		96.42 43	96.20 51	97.07 34	98.80 34	92.79 50	96.08 72	98.16 65	91.74 131	95.34 183	96.36 206	95.68 25	99.44 34	94.41 59	99.28 88	98.97 72

v8		94.65 125	95.29 106	92.74 227	96.65 195	79.77 309	94.59 137	97.17 187	91.86 119	97.47 56	97.93 62	88.16 229	99.08 109	94.32 60	99.47 45	99.38 28

HPM-MVS_fast		97.01 12	96.89 22	97.39 25	99.12 8	93.92 32	97.16 14	98.17 62	93.11 87	96.48 112	97.36 113	96.92 6	99.34 70	94.31 61	99.38 63	98.92 86

MTAPA		96.65 30	96.38 41	97.47 19	98.95 21	94.05 27	95.88 81	97.62 141	94.46 60	96.29 126	96.94 155	93.56 93	99.37 65	94.29 62	99.42 54	98.99 65

WR-MVS_H		96.60 33	97.05 21	95.24 101	99.02 13	86.44 174	96.78 28	98.08 76	97.42 13	98.48 20	97.86 72	91.76 150	99.63 8	94.23 63	99.84 3	99.66 9

v1921920		93.26 190	93.61 184	92.19 252	96.04 267	78.31 344	91.88 267	97.24 183	85.17 306	96.19 137	96.19 222	86.76 260	99.05 116	94.18 64	98.84 150	99.22 40

v1192		93.49 179	93.78 174	92.62 237	96.16 251	79.62 311	91.83 271	97.22 185	86.07 280	96.10 141	96.38 204	87.22 248	99.02 121	94.14 65	98.88 145	99.22 40

mvs5depth		95.28 97	95.82 80	93.66 179	96.42 222	83.08 246	97.35 12	99.28 3	96.44 29	96.20 134	99.65 2	84.10 289	98.01 270	94.06 66	98.93 138	99.87 1

MSC_two_6792asdad				95.90 70	96.54 210	89.57 94		96.87 215					99.41 44	94.06 66	99.30 80	98.72 112

No_MVS				95.90 70	96.54 210	89.57 94		96.87 215					99.41 44	94.06 66	99.30 80	98.72 112

HPM-MVS		96.81 19	96.62 30	97.36 27	98.89 23	93.53 42	97.51 10	98.44 26	92.35 101	95.95 147	96.41 198	96.71 11	99.42 38	93.99 69	99.36 66	99.13 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DVP-MVS++		95.93 63	96.34 44	94.70 126	96.54 210	86.66 168	98.45 4	98.22 53	93.26 85	97.54 49	97.36 113	93.12 111	99.38 63	93.88 70	98.68 182	98.04 193

test_0728_THIRD									93.26 85	97.40 62	97.35 116	94.69 68	99.34 70	93.88 70	99.42 54	98.89 89

nrg030		96.32 48	96.55 33	95.62 82	97.83 112	88.55 122	95.77 85	98.29 44	92.68 91	98.03 35	97.91 69	95.13 49	98.95 133	93.85 72	99.49 44	99.36 30

v144192		93.20 197	93.54 188	92.16 256	96.05 263	78.26 345	91.95 259	97.14 189	84.98 313	95.96 146	96.11 230	87.08 252	99.04 119	93.79 73	98.84 150	99.17 44

HFP-MVS		96.39 46	96.17 55	97.04 35	98.51 56	93.37 43	96.30 63	97.98 94	92.35 101	95.63 166	96.47 192	95.37 36	99.27 86	93.78 74	99.14 107	98.48 146

EI-MVSNet-UG-set		94.35 143	94.27 158	94.59 136	92.46 390	85.87 193	92.42 236	94.69 315	93.67 78	96.13 138	95.84 244	91.20 168	98.86 144	93.78 74	98.23 236	99.03 61

ACMMPR		96.46 39	96.14 56	97.41 24	98.60 45	93.82 37	96.30 63	97.96 98	92.35 101	95.57 169	96.61 184	94.93 63	99.41 44	93.78 74	99.15 106	99.00 63

EI-MVSNet-Vis-set		94.36 142	94.28 156	94.61 132	92.55 387	85.98 188	92.44 234	94.69 315	93.70 75	96.12 139	95.81 246	91.24 165	98.86 144	93.76 77	98.22 240	98.98 69

region2R		96.41 44	96.09 58	97.38 26	98.62 42	93.81 39	96.32 55	97.96 98	92.26 104	95.28 188	96.57 187	95.02 57	99.41 44	93.63 78	99.11 109	98.94 80

EC-MVSNet		95.44 85	95.62 88	94.89 117	96.93 173	87.69 140	96.48 44	99.14 7	93.93 70	92.77 299	94.52 310	93.95 89	99.49 30	93.62 79	99.22 97	97.51 260

XVS		96.49 37	96.18 52	97.44 20	98.56 48	93.99 30	96.50 41	97.95 101	94.58 56	94.38 230	96.49 191	94.56 74	99.39 54	93.57 80	99.05 118	98.93 82

X-MVStestdata		90.70 270	88.45 321	97.44 20	98.56 48	93.99 30	96.50 41	97.95 101	94.58 56	94.38 230	26.89 473	94.56 74	99.39 54	93.57 80	99.05 118	98.93 82

SMA-MVS		95.77 71	95.54 91	96.47 53	98.27 77	91.19 70	95.09 118	97.79 126	86.48 269	97.42 60	97.51 103	94.47 79	99.29 80	93.55 82	99.29 83	98.93 82
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		93.43 182	93.18 200	94.16 153	97.32 150	85.29 206	93.36 190	93.94 332	88.09 233	97.12 78	96.43 195	80.11 329	98.98 125	93.53 83	98.76 168	98.21 175

v1144		93.50 178	93.81 171	92.57 240	96.28 238	79.61 312	91.86 270	96.96 202	86.95 263	95.91 150	96.32 208	87.65 241	98.96 131	93.51 84	98.88 145	99.13 49

SR-MVS-dyc-post		96.84 15	96.60 32	97.56 14	98.07 91	95.27 10	96.37 50	98.12 69	95.66 43	97.00 85	97.03 149	94.85 65	99.42 38	93.49 85	98.84 150	98.00 198

RE-MVS-def			96.66 27		98.07 91	95.27 10	96.37 50	98.12 69	95.66 43	97.00 85	97.03 149	95.40 35		93.49 85	98.84 150	98.00 198

SteuartSystems-ACMMP		96.40 45	96.30 46	96.71 44	98.63 41	91.96 59	95.70 87	98.01 91	93.34 84	96.64 106	96.57 187	94.99 59	99.36 66	93.48 87	99.34 71	98.82 97
Skip Steuart: Steuart Systems R&D Blog.
CS-MVS		95.77 71	95.58 90	96.37 54	96.84 180	91.72 65	96.73 30	99.06 8	94.23 63	92.48 308	94.79 297	93.56 93	99.49 30	93.47 88	99.05 118	97.89 220

ACMMP		96.61 32	96.34 44	97.43 22	98.61 44	93.88 33	96.95 20	98.18 58	92.26 104	96.33 121	96.84 166	95.10 53	99.40 51	93.47 88	99.33 73	99.02 62
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.		94.96 111	94.75 129	95.57 84	98.86 27	88.69 114	96.37 50	96.81 220	85.23 304	94.75 220	97.12 140	91.85 145	99.40 51	93.45 90	98.33 223	98.62 132
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_fmvs2		90.62 275	90.40 285	91.29 293	91.93 407	85.46 203	92.70 219	96.48 247	74.44 416	94.91 214	97.59 91	75.52 372	90.57 447	93.44 91	96.56 337	97.84 228

DVP-MVS		95.82 69	96.18 52	94.72 125	98.51 56	86.69 166	95.20 115	97.00 199	91.85 120	97.40 62	97.35 116	95.58 28	99.34 70	93.44 91	99.31 78	98.13 186
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				94.88 118	98.55 51	86.72 165	95.20 115	98.22 53					99.38 63	93.44 91	99.31 78	98.53 140

MSP-MVS		95.34 92	94.63 140	97.48 18	98.67 39	94.05 27	96.41 49	98.18 58	91.26 150	95.12 202	95.15 278	86.60 263	99.50 24	93.43 94	96.81 329	98.89 89
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 28	97.43 10	94.49 143	99.13 6	84.09 225	96.61 36	97.97 96	97.91 9	98.64 17	98.13 46	95.24 44	99.65 5	93.39 95	99.84 3	99.72 4

Vis-MVSNet		95.50 83	95.48 93	95.56 85	98.11 88	89.40 100	95.35 103	98.22 53	92.36 100	94.11 237	98.07 50	92.02 141	99.44 34	93.38 96	97.67 287	97.85 227
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
APD-MVS_3200maxsize		96.82 17	96.65 28	97.32 29	97.95 105	93.82 37	96.31 59	98.25 45	95.51 45	96.99 87	97.05 148	95.63 27	99.39 54	93.31 97	98.88 145	98.75 107

SED-MVS		96.00 59	96.41 40	94.76 123	98.51 56	86.97 156	95.21 113	98.10 73	91.95 113	97.63 44	97.25 126	96.48 13	99.35 67	93.29 98	99.29 83	97.95 208

test_241102_TWO								98.10 73	91.95 113	97.54 49	97.25 126	95.37 36	99.35 67	93.29 98	99.25 91	98.49 145

DTE-MVSNet		96.74 25	97.43 10	94.67 129	99.13 6	84.68 213	96.51 40	97.94 104	98.14 7	98.67 16	98.32 40	95.04 55	99.69 4	93.27 100	99.82 7	99.62 13

3Dnovator+	92.74 2	95.86 68	95.77 82	96.13 58	96.81 183	90.79 79	96.30 63	97.82 121	96.13 36	94.74 221	97.23 129	91.33 162	99.16 96	93.25 101	98.30 229	98.46 147

K. test v3		93.37 184	93.27 198	93.66 179	98.05 93	82.62 258	94.35 147	86.62 418	96.05 39	97.51 53	98.85 17	76.59 368	99.65 5	93.21 102	98.20 243	98.73 111

Anonymous20231211		96.60 33	97.13 20	95.00 110	97.46 142	86.35 178	97.11 18	98.24 49	97.58 12	98.72 12	98.97 12	93.15 110	99.15 97	93.18 103	99.74 13	99.50 19

GST-MVS		96.24 51	95.99 66	97.00 37	98.65 40	92.71 51	95.69 89	98.01 91	92.08 111	95.74 160	96.28 212	95.22 46	99.42 38	93.17 104	99.06 115	98.88 91

CP-MVS		96.44 42	96.08 60	97.54 15	98.29 75	94.62 18	96.80 26	98.08 76	92.67 93	95.08 206	96.39 203	94.77 67	99.42 38	93.17 104	99.44 52	98.58 135

mPP-MVS		96.46 39	96.05 62	97.69 6	98.62 42	94.65 17	96.45 45	97.74 130	92.59 94	95.47 174	96.68 180	94.50 76	99.42 38	93.10 106	99.26 90	98.99 65

ACMM	88.83 9	96.30 50	96.07 61	96.97 38	98.39 67	92.95 48	94.74 130	98.03 88	90.82 162	97.15 76	96.85 163	96.25 18	99.00 123	93.10 106	99.33 73	98.95 79
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		96.19 53	96.80 24	94.38 148	98.99 19	83.82 228	96.31 59	97.53 154	97.60 11	98.34 23	97.52 99	91.98 143	99.63 8	93.08 108	99.81 8	99.70 5

v2v482		93.29 188	93.63 182	92.29 247	96.35 230	78.82 334	91.77 275	96.28 254	88.45 221	95.70 164	96.26 215	86.02 270	98.90 137	93.02 109	98.81 158	99.14 48

IU-MVS					98.51 56	86.66 168		96.83 219	72.74 429	95.83 154				93.00 110	99.29 83	98.64 128

SR-MVS		96.70 27	96.42 37	97.54 15	98.05 93	94.69 15	96.13 69	98.07 79	95.17 49	96.82 96	96.73 176	95.09 54	99.43 37	92.99 111	98.71 178	98.50 143

PEN-MVS		96.69 28	97.39 13	94.61 132	99.16 4	84.50 214	96.54 38	98.05 83	98.06 8	98.64 17	98.25 43	95.01 58	99.65 5	92.95 112	99.83 5	99.68 7

FC-MVSNet-test		95.32 93	95.88 74	93.62 181	98.49 63	81.77 270	95.90 80	98.32 38	93.93 70	97.53 51	97.56 94	88.48 222	99.40 51	92.91 113	99.83 5	99.68 7

MED-MVS test				95.52 86	98.69 37	88.21 129	96.32 55	98.58 18	88.79 209	97.38 64	96.22 218		99.39 54	92.89 114	99.10 110	98.96 76

ME-MVS		95.61 77	95.65 87	95.49 88	97.62 131	88.21 129	94.21 155	97.87 112	92.48 96	96.38 117	96.22 218	94.06 87	99.32 76	92.89 114	99.10 110	98.96 76

OPM-MVS		95.61 77	95.45 94	96.08 59	98.49 63	91.00 72	92.65 222	97.33 174	90.05 182	96.77 99	96.85 163	95.04 55	98.56 199	92.77 116	99.06 115	98.70 116
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PGM-MVS		96.32 48	95.94 68	97.43 22	98.59 47	93.84 36	95.33 105	98.30 41	91.40 147	95.76 157	96.87 162	95.26 43	99.45 33	92.77 116	99.21 98	99.00 63

CNVR-MVS		94.58 129	94.29 155	95.46 90	96.94 171	89.35 102	91.81 272	96.80 221	89.66 189	93.90 249	95.44 268	92.80 123	98.72 171	92.74 118	98.52 200	98.32 163

DeepC-MVS	91.39 4	95.43 86	95.33 104	95.71 79	97.67 128	90.17 87	93.86 171	98.02 90	87.35 251	96.22 132	97.99 59	94.48 78	99.05 116	92.73 119	99.68 20	97.93 211
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SD-MVS		95.19 102	95.73 83	93.55 185	96.62 204	88.88 113	94.67 134	98.05 83	91.26 150	97.25 72	96.40 199	95.42 34	94.36 423	92.72 120	99.19 100	97.40 271
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
EU-MVSNet		87.39 356	86.71 361	89.44 351	93.40 368	76.11 381	94.93 126	90.00 392	57.17 468	95.71 163	97.37 110	64.77 421	97.68 307	92.67 121	94.37 396	94.52 396

lessismore_v0				93.87 169	98.05 93	83.77 229		80.32 460		97.13 77	97.91 69	77.49 353	99.11 107	92.62 122	98.08 254	98.74 110

GDP-MVS		91.56 253	90.83 272	93.77 174	96.34 231	83.65 230	93.66 179	98.12 69	87.32 253	92.98 291	94.71 300	63.58 428	99.30 79	92.61 123	98.14 247	98.35 161

Anonymous20240521		92.86 210	93.57 186	90.74 317	96.57 207	75.50 388	94.15 157	95.60 279	89.38 194	95.90 151	97.90 71	80.39 328	97.96 276	92.60 124	99.68 20	98.75 107

sc_t1		97.21 10	97.71 5	95.71 79	99.06 10	88.89 111	96.72 31	97.79 126	98.34 3	98.97 3	99.40 5	96.81 9	98.79 158	92.58 125	99.72 15	99.45 23

MVS_Test		92.57 223	93.29 195	90.40 329	93.53 366	75.85 384	92.52 228	96.96 202	88.73 211	92.35 317	96.70 179	90.77 181	98.37 228	92.53 126	95.49 365	96.99 296

balanced_conf03		93.45 181	94.17 161	91.28 294	95.81 283	78.40 340	96.20 67	97.48 160	88.56 220	95.29 187	97.20 134	85.56 278	99.21 90	92.52 127	98.91 141	96.24 331

3Dnovator	92.54 3	94.80 118	94.90 121	94.47 144	95.47 307	87.06 153	96.63 35	97.28 180	91.82 126	94.34 232	97.41 107	90.60 188	98.65 187	92.47 128	98.11 250	97.70 244

AstraMVS		92.75 214	92.73 213	92.79 225	97.02 166	81.48 279	92.88 210	90.62 389	87.99 235	96.48 112	96.71 178	82.02 313	98.48 214	92.44 129	98.46 207	98.40 155

SF-MVS		95.88 67	95.88 74	95.87 73	98.12 87	89.65 93	95.58 95	98.56 20	91.84 123	96.36 120	96.68 180	94.37 80	99.32 76	92.41 130	99.05 118	98.64 128

V42		93.43 182	93.58 185	92.97 212	95.34 313	81.22 283	92.67 220	96.49 246	87.25 254	96.20 134	96.37 205	87.32 247	98.85 146	92.39 131	98.21 241	98.85 95

casdiffmvs_mvg		95.10 105	95.62 88	93.53 188	96.25 244	83.23 239	92.66 221	98.19 56	93.06 88	97.49 54	97.15 137	94.78 66	98.71 177	92.27 132	98.72 176	98.65 122
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		84.79 384	84.06 387	86.98 395	77.73 476	74.76 390	91.08 296	85.63 428	77.70 393	96.86 92	97.97 60	41.05 474	88.24 460	92.22 133	96.28 344	97.94 210

HPM-MVS++		95.02 108	94.39 148	96.91 41	97.88 109	93.58 41	94.09 162	96.99 201	91.05 155	92.40 313	95.22 277	91.03 176	99.25 87	92.11 134	98.69 181	97.90 218

UniMVSNet (Re)		95.32 93	95.15 111	95.80 75	97.79 116	88.91 110	92.91 208	98.07 79	93.46 81	96.31 124	95.97 239	90.14 198	99.34 70	92.11 134	99.64 26	99.16 45

XVG-OURS-SEG-HR		95.38 90	95.00 120	96.51 50	98.10 89	94.07 24	92.46 232	98.13 67	90.69 166	93.75 251	96.25 216	98.03 2	97.02 352	92.08 136	95.55 363	98.45 148

LPG-MVS_test		96.38 47	96.23 49	96.84 42	98.36 73	92.13 56	95.33 105	98.25 45	91.78 127	97.07 80	97.22 131	96.38 16	99.28 84	92.07 137	99.59 30	99.11 53

LGP-MVS_train				96.84 42	98.36 73	92.13 56		98.25 45	91.78 127	97.07 80	97.22 131	96.38 16	99.28 84	92.07 137	99.59 30	99.11 53

guyue		92.60 219	92.62 219	92.52 243	96.73 188	81.00 286	93.00 202	91.83 375	88.28 228	96.38 117	96.23 217	80.71 326	98.37 228	92.06 139	98.37 221	98.20 177

tttt0517		89.81 304	88.90 314	92.55 241	97.00 168	79.73 310	95.03 122	83.65 444	89.88 185	95.30 185	94.79 297	53.64 451	99.39 54	91.99 140	98.79 164	98.54 138

EI-MVSNet		92.99 203	93.26 199	92.19 252	92.12 400	79.21 325	92.32 243	94.67 317	91.77 129	95.24 192	95.85 242	87.14 251	98.49 210	91.99 140	98.26 232	98.86 92

MP-MVS		96.14 54	95.68 85	97.51 17	98.81 32	94.06 25	96.10 70	97.78 128	92.73 90	93.48 261	96.72 177	94.23 82	99.42 38	91.99 140	99.29 83	99.05 60
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
IterMVS-LS		93.78 170	94.28 156	92.27 248	96.27 241	79.21 325	91.87 268	96.78 222	91.77 129	96.57 111	97.07 145	87.15 250	98.74 169	91.99 140	99.03 124	98.86 92
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		91.65 250	91.55 250	91.94 263	93.89 359	79.22 324	87.56 390	93.51 339	91.53 139	95.37 181	96.62 183	78.65 342	98.90 137	91.89 144	94.95 381	97.70 244

EGC-MVSNET		80.97 418	75.73 436	96.67 46	98.85 28	94.55 19	96.83 24	96.60 237	2.44 475	5.32 476	98.25 43	92.24 136	98.02 269	91.85 145	99.21 98	97.45 264

SPE-MVS-test		95.32 93	95.10 116	95.96 63	96.86 178	90.75 81	96.33 53	99.20 5	93.99 67	91.03 344	93.73 341	93.52 95	99.55 19	91.81 146	99.45 49	97.58 254

tt0320-xc		97.00 13	97.67 6	94.98 111	98.89 23	86.94 159	96.72 31	98.46 24	98.28 5	98.86 8	99.43 4	96.80 10	98.51 208	91.79 147	99.76 10	99.50 19

LS3D		96.11 55	95.83 78	96.95 40	94.75 333	94.20 23	97.34 13	97.98 94	97.31 15	95.32 184	96.77 169	93.08 113	99.20 93	91.79 147	98.16 245	97.44 266

DPE-MVS		95.89 66	95.88 74	95.92 69	97.93 106	89.83 91	93.46 185	98.30 41	92.37 99	97.75 40	96.95 154	95.14 48	99.51 21	91.74 149	99.28 88	98.41 152
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
tt0320		96.97 14	97.64 7	94.96 113	98.89 23	86.86 161	96.85 23	98.45 25	98.29 4	98.88 7	99.45 3	96.48 13	98.54 202	91.73 150	99.72 15	99.47 21

FIs		94.90 113	95.35 101	93.55 185	98.28 76	81.76 271	95.33 105	98.14 66	93.05 89	97.07 80	97.18 135	87.65 241	99.29 80	91.72 151	99.69 17	99.61 14

Gipuma		95.31 96	95.80 81	93.81 173	97.99 104	90.91 74	96.42 48	97.95 101	96.69 22	91.78 331	98.85 17	91.77 148	95.49 400	91.72 151	99.08 114	95.02 380
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
baseline		94.26 147	94.80 125	92.64 232	96.08 260	80.99 287	93.69 177	98.04 87	90.80 163	94.89 215	96.32 208	93.19 108	98.48 214	91.68 153	98.51 202	98.43 150

alignmvs		93.26 190	92.85 207	94.50 141	95.70 289	87.45 144	93.45 186	95.76 274	91.58 136	95.25 191	92.42 376	81.96 315	98.72 171	91.61 154	97.87 275	97.33 276

UniMVSNet_NR-MVSNet		95.35 91	95.21 109	95.76 76	97.69 126	88.59 120	92.26 249	97.84 117	94.91 53	96.80 97	95.78 250	90.42 190	99.41 44	91.60 155	99.58 34	99.29 34

DU-MVS		95.28 97	95.12 113	95.75 77	97.75 118	88.59 120	92.58 226	97.81 122	93.99 67	96.80 97	95.90 240	90.10 201	99.41 44	91.60 155	99.58 34	99.26 35

EG-PatchMatch MVS		94.54 131	94.67 138	94.14 156	97.87 111	86.50 170	92.00 257	96.74 226	88.16 232	96.93 89	97.61 90	93.04 115	97.90 279	91.60 155	98.12 249	98.03 196

MGCFI-Net		94.44 136	94.67 138	93.75 175	95.56 301	85.47 202	95.25 112	98.24 49	91.53 139	95.04 208	92.21 378	94.94 62	98.54 202	91.56 158	97.66 288	97.24 280

test_0402		95.73 73	96.22 50	94.26 151	98.19 84	85.77 195	93.24 193	97.24 183	96.88 21	97.69 42	97.77 78	94.12 85	99.13 102	91.54 159	99.29 83	97.88 221

sasdasda		94.59 127	94.69 133	94.30 149	95.60 298	87.03 154	95.59 92	98.24 49	91.56 137	95.21 194	92.04 383	94.95 60	98.66 184	91.45 160	97.57 293	97.20 282

canonicalmvs		94.59 127	94.69 133	94.30 149	95.60 298	87.03 154	95.59 92	98.24 49	91.56 137	95.21 194	92.04 383	94.95 60	98.66 184	91.45 160	97.57 293	97.20 282

XVG-OURS		94.72 120	94.12 163	96.50 51	98.00 101	94.23 22	91.48 283	98.17 62	90.72 165	95.30 185	96.47 192	87.94 236	96.98 353	91.41 162	97.61 291	98.30 167

pmmvs6		96.80 20	97.36 14	95.15 107	99.12 8	87.82 138	96.68 33	97.86 113	96.10 37	98.14 31	99.28 8	97.94 3	98.21 244	91.38 163	99.69 17	99.42 24

diffmvs_AUTHOR		92.34 231	92.70 216	91.26 295	94.20 349	78.42 339	89.12 361	97.60 145	87.16 256	93.17 282	95.50 264	88.66 219	97.57 315	91.30 164	97.61 291	97.79 235

VortexMVS		92.13 240	92.56 222	90.85 313	94.54 342	76.17 380	92.30 246	96.63 236	86.20 276	96.66 105	96.79 168	79.87 331	98.16 250	91.27 165	98.76 168	98.24 172

XVG-ACMP-BASELINE		95.68 75	95.34 102	96.69 45	98.40 66	93.04 45	94.54 144	98.05 83	90.45 176	96.31 124	96.76 171	92.91 119	98.72 171	91.19 166	99.42 54	98.32 163

test_fmvs1_n		88.73 330	88.38 323	89.76 345	92.06 402	82.53 259	92.30 246	96.59 239	71.14 437	92.58 305	95.41 272	68.55 398	89.57 455	91.12 167	95.66 360	97.18 284

RPSCF		95.58 80	94.89 122	97.62 9	97.58 134	96.30 8	95.97 77	97.53 154	92.42 97	93.41 263	97.78 74	91.21 167	97.77 298	91.06 168	97.06 317	98.80 101

h-mvs33		92.89 206	91.99 240	95.58 83	96.97 169	90.55 83	93.94 168	94.01 330	89.23 197	93.95 246	96.19 222	76.88 364	99.14 99	91.02 169	95.71 359	97.04 294

hse-mvs2		92.24 237	91.20 260	95.38 91	96.16 251	90.65 82	92.52 228	92.01 372	89.23 197	93.95 246	92.99 360	76.88 364	98.69 180	91.02 169	96.03 350	96.81 304

casdiffmvs		94.32 145	94.80 125	92.85 221	96.05 263	81.44 280	92.35 240	98.05 83	91.53 139	95.75 159	96.80 167	93.35 103	98.49 210	91.01 171	98.32 225	98.64 128
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		94.55 130	94.68 137	94.15 154	97.23 154	85.11 208	94.14 159	97.34 173	88.71 213	95.26 189	95.50 264	94.65 70	99.12 103	90.94 172	98.40 211	98.23 173

c3_l		91.32 260	91.42 255	91.00 307	92.29 393	76.79 369	87.52 393	96.42 249	85.76 291	94.72 223	93.89 337	82.73 304	98.16 250	90.93 173	98.55 195	98.04 193

TranMVSNet+NR-MVSNet		96.07 57	96.26 48	95.50 87	98.26 78	87.69 140	93.75 174	97.86 113	95.96 42	97.48 55	97.14 138	95.33 40	99.44 34	90.79 174	99.76 10	99.38 28

test_vis1_n		89.01 320	89.01 310	89.03 359	92.57 386	82.46 261	92.62 224	96.06 265	73.02 427	90.40 355	95.77 251	74.86 374	89.68 453	90.78 175	94.98 380	94.95 382

UniMVSNet_ETH3D		97.13 11	97.72 4	95.35 93	99.51 2	87.38 145	97.70 8	97.54 152	98.16 6	98.94 4	99.33 6	97.84 4	99.08 109	90.73 176	99.73 14	99.59 15

9.14			94.81 124		97.49 139		94.11 160	98.37 34	87.56 249	95.38 179	96.03 234	94.66 69	99.08 109	90.70 177	98.97 133

diffmvs		91.74 248	91.93 242	91.15 302	93.06 375	78.17 346	88.77 373	97.51 157	86.28 273	92.42 312	93.96 334	88.04 233	97.46 323	90.69 178	96.67 335	97.82 232
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		87.59 351	87.27 347	88.54 370	88.32 453	81.26 282	90.43 319	95.72 276	70.55 443	91.70 332	94.63 304	68.13 399	89.42 457	90.59 179	95.34 371	94.94 384

dcpmvs_2		93.96 164	95.01 119	90.82 315	97.60 132	74.04 402	93.68 178	98.85 10	89.80 187	97.82 37	97.01 152	91.14 172	99.21 90	90.56 180	98.59 192	99.19 43

RRT-MVS		92.28 233	93.01 202	90.07 338	94.06 355	73.01 409	95.36 102	97.88 110	92.24 106	95.16 199	97.52 99	78.51 346	99.29 80	90.55 181	95.83 357	97.92 216

MVSTER		89.32 312	88.75 317	91.03 304	90.10 437	76.62 375	90.85 300	94.67 317	82.27 349	95.24 192	95.79 247	61.09 438	98.49 210	90.49 182	98.26 232	97.97 206

DP-MVS		95.62 76	95.84 77	94.97 112	97.16 159	88.62 117	94.54 144	97.64 139	96.94 20	96.58 110	97.32 120	93.07 114	98.72 171	90.45 183	98.84 150	97.57 255

ACMP	88.15 13	95.71 74	95.43 96	96.54 49	98.17 85	91.73 64	94.24 152	98.08 76	89.46 192	96.61 108	96.47 192	95.85 22	99.12 103	90.45 183	99.56 37	98.77 106
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS_111021_LR		93.66 172	93.28 197	94.80 121	96.25 244	90.95 73	90.21 325	95.43 291	87.91 236	93.74 253	94.40 316	92.88 121	96.38 379	90.39 185	98.28 230	97.07 290

NormalMVS		94.10 158	93.36 194	96.31 56	99.01 15	90.84 77	94.70 132	97.90 106	90.98 156	93.22 277	95.73 253	78.94 338	99.12 103	90.38 186	99.42 54	98.97 72

SymmetryMVS		93.26 190	92.36 229	95.97 62	97.13 162	90.84 77	94.70 132	91.61 379	90.98 156	93.22 277	95.73 253	78.94 338	99.12 103	90.38 186	98.53 198	97.97 206

ANet_high		94.83 116	96.28 47	90.47 326	96.65 195	73.16 407	94.33 148	98.74 14	96.39 31	98.09 34	98.93 13	93.37 102	98.70 178	90.38 186	99.68 20	99.53 17

DeepPCF-MVS	90.46 6	94.20 154	93.56 187	96.14 57	95.96 270	92.96 47	89.48 349	97.46 161	85.14 307	96.23 131	95.42 269	93.19 108	98.08 259	90.37 189	98.76 168	97.38 274

MSLP-MVS++		93.25 193	93.88 170	91.37 288	96.34 231	82.81 251	93.11 198	97.74 130	89.37 195	94.08 239	95.29 276	90.40 192	96.35 381	90.35 190	98.25 234	94.96 381

PM-MVS		93.33 187	92.67 218	95.33 95	96.58 206	94.06 25	92.26 249	92.18 365	85.92 283	96.22 132	96.61 184	85.64 276	95.99 391	90.35 190	98.23 236	95.93 345

test_vis1_n_1920		89.45 309	89.85 296	88.28 377	93.59 365	76.71 374	90.67 308	97.78 128	79.67 375	90.30 358	96.11 230	76.62 367	92.17 440	90.31 192	93.57 413	95.96 343

ACMH+	88.43 11	96.48 38	96.82 23	95.47 89	98.54 53	89.06 107	95.65 90	98.61 15	96.10 37	98.16 30	97.52 99	96.90 7	98.62 190	90.30 193	99.60 28	98.72 112

DIV-MVS_self_test		90.65 273	90.56 281	90.91 311	91.85 408	76.99 365	86.75 407	95.36 294	85.52 300	94.06 241	94.89 290	77.37 357	97.99 274	90.28 194	98.97 133	97.76 239

cl____		90.65 273	90.56 281	90.91 311	91.85 408	76.98 366	86.75 407	95.36 294	85.53 298	94.06 241	94.89 290	77.36 358	97.98 275	90.27 195	98.98 128	97.76 239

PHI-MVS		94.34 144	93.80 173	95.95 64	95.65 294	91.67 66	94.82 128	97.86 113	87.86 239	93.04 288	94.16 326	91.58 153	98.78 162	90.27 195	98.96 135	97.41 267

patch_mono-2		92.46 226	92.72 215	91.71 272	96.65 195	78.91 331	88.85 367	97.17 187	83.89 326	92.45 310	96.76 171	89.86 207	97.09 348	90.24 197	98.59 192	99.12 52

MVS_111021_HR		93.63 173	93.42 193	94.26 151	96.65 195	86.96 158	89.30 356	96.23 258	88.36 227	93.57 257	94.60 306	93.45 98	97.77 298	90.23 198	98.38 216	98.03 196

NCCC		94.08 160	93.54 188	95.70 81	96.49 216	89.90 90	92.39 238	96.91 208	90.64 168	92.33 320	94.60 306	90.58 189	98.96 131	90.21 199	97.70 285	98.23 173

viewdifsd2359ckpt11		93.36 185	93.99 166	91.48 283	95.50 305	78.39 342	90.47 314	96.69 229	88.59 217	96.03 144	96.88 160	93.48 96	97.63 311	90.20 200	98.07 255	98.41 152

viewmsd2359difaftdt		93.36 185	93.99 166	91.48 283	95.50 305	78.39 342	90.47 314	96.69 229	88.59 217	96.03 144	96.88 160	93.48 96	97.63 311	90.20 200	98.07 255	98.41 152

pm-mvs1		95.43 86	95.94 68	93.93 166	98.38 68	85.08 209	95.46 101	97.12 192	91.84 123	97.28 70	98.46 36	95.30 42	97.71 305	90.17 202	99.42 54	98.99 65

RPMNet		90.31 288	90.14 291	90.81 316	91.01 423	78.93 328	92.52 228	98.12 69	91.91 116	89.10 378	96.89 159	68.84 397	99.41 44	90.17 202	92.70 430	94.08 403

NR-MVSNet		95.28 97	95.28 107	95.26 99	97.75 118	87.21 149	95.08 119	97.37 166	93.92 72	97.65 43	95.90 240	90.10 201	99.33 75	90.11 204	99.66 24	99.26 35

COLMAP_ROB	91.06 5	96.75 24	96.62 30	97.13 32	98.38 68	94.31 21	96.79 27	98.32 38	96.69 22	96.86 92	97.56 94	95.48 31	98.77 165	90.11 204	99.44 52	98.31 165
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Baseline_NR-MVSNet		94.47 135	95.09 117	92.60 239	98.50 62	80.82 290	92.08 253	96.68 232	93.82 73	96.29 126	98.56 30	90.10 201	97.75 301	90.10 206	99.66 24	99.24 39

v148		92.87 209	93.29 195	91.62 276	96.25 244	77.72 354	91.28 288	95.05 301	89.69 188	95.93 149	96.04 233	87.34 246	98.38 224	90.05 207	97.99 266	98.78 103

MCST-MVS		92.91 205	92.51 223	94.10 158	97.52 137	85.72 197	91.36 287	97.13 191	80.33 368	92.91 295	94.24 322	91.23 166	98.72 171	89.99 208	97.93 271	97.86 225

miper_lstm_enhance		89.90 301	89.80 297	90.19 337	91.37 419	77.50 356	83.82 447	95.00 303	84.84 316	93.05 287	94.96 288	76.53 369	95.20 409	89.96 209	98.67 184	97.86 225

ambc				92.98 211	96.88 176	83.01 248	95.92 79	96.38 251		96.41 116	97.48 105	88.26 227	97.80 293	89.96 209	98.93 138	98.12 187

CPTT-MVS		94.74 119	94.12 163	96.60 47	98.15 86	93.01 46	95.84 83	97.66 138	89.21 200	93.28 271	95.46 266	88.89 216	98.98 125	89.80 211	98.82 156	97.80 234

viewmacassd2359aftdt		93.83 168	94.36 152	92.24 249	96.45 219	79.58 314	91.60 278	97.96 98	89.14 201	95.05 207	97.09 144	93.69 91	98.48 214	89.79 212	98.43 209	98.65 122

miper_ehance_all_eth		90.48 277	90.42 284	90.69 318	91.62 415	76.57 376	86.83 405	96.18 262	83.38 330	94.06 241	92.66 370	82.20 310	98.04 265	89.79 212	97.02 319	97.45 264

eth_miper_zixun_eth		90.72 269	90.61 279	91.05 303	92.04 403	76.84 368	86.91 402	96.67 233	85.21 305	94.41 228	93.92 335	79.53 334	98.26 239	89.76 214	97.02 319	98.06 189

VPA-MVSNet		95.14 104	95.67 86	93.58 184	97.76 117	83.15 243	94.58 139	97.58 148	93.39 82	97.05 83	98.04 53	93.25 106	98.51 208	89.75 215	99.59 30	99.08 57

DELS-MVS		92.05 242	92.16 234	91.72 271	94.44 344	80.13 296	87.62 387	97.25 181	87.34 252	92.22 322	93.18 357	89.54 210	98.73 170	89.67 216	98.20 243	96.30 326
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
thisisatest0530		88.69 331	87.52 343	92.20 251	96.33 233	79.36 319	92.81 212	84.01 443	86.44 270	93.67 254	92.68 369	53.62 452	99.25 87	89.65 217	98.45 208	98.00 198

DeepC-MVS_fast	89.96 7	93.73 171	93.44 191	94.60 135	96.14 254	87.90 135	93.36 190	97.14 189	85.53 298	93.90 249	95.45 267	91.30 164	98.59 195	89.51 218	98.62 188	97.31 277
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet		92.38 229	91.99 240	93.52 190	93.82 362	83.46 233	91.14 292	97.00 199	89.81 186	86.47 416	94.04 329	87.90 237	99.21 90	89.50 219	98.27 231	97.90 218

reproduce_monomvs		87.13 364	86.90 356	87.84 387	90.92 425	68.15 435	91.19 290	93.75 334	85.84 288	94.21 235	95.83 245	42.99 469	97.10 347	89.46 220	97.88 274	98.26 171

TSAR-MVS + GP.		93.07 202	92.41 227	95.06 109	95.82 281	90.87 76	90.97 297	92.61 358	88.04 234	94.61 224	93.79 340	88.08 230	97.81 292	89.41 221	98.39 215	96.50 316

testf1		96.77 22	96.49 34	97.60 10	99.01 15	96.70 4	96.31 59	98.33 36	94.96 51	97.30 67	97.93 62	96.05 20	97.90 279	89.32 222	99.23 94	98.19 179

APD_test2		96.77 22	96.49 34	97.60 10	99.01 15	96.70 4	96.31 59	98.33 36	94.96 51	97.30 67	97.93 62	96.05 20	97.90 279	89.32 222	99.23 94	98.19 179

APD-MVS		95.00 109	94.69 133	95.93 67	97.38 145	90.88 75	94.59 137	97.81 122	89.22 199	95.46 176	96.17 226	93.42 101	99.34 70	89.30 224	98.87 148	97.56 257
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
xiu_mvs_v1_base_debu		91.47 256	91.52 251	91.33 290	95.69 290	81.56 275	89.92 336	96.05 267	83.22 334	91.26 339	90.74 402	91.55 154	98.82 149	89.29 225	95.91 353	93.62 418

xiu_mvs_v1_base		91.47 256	91.52 251	91.33 290	95.69 290	81.56 275	89.92 336	96.05 267	83.22 334	91.26 339	90.74 402	91.55 154	98.82 149	89.29 225	95.91 353	93.62 418

xiu_mvs_v1_base_debi		91.47 256	91.52 251	91.33 290	95.69 290	81.56 275	89.92 336	96.05 267	83.22 334	91.26 339	90.74 402	91.55 154	98.82 149	89.29 225	95.91 353	93.62 418

HQP_MVS		94.26 147	93.93 169	95.23 102	97.71 123	88.12 131	94.56 141	97.81 122	91.74 131	93.31 268	95.59 259	86.93 256	98.95 133	89.26 228	98.51 202	98.60 133

plane_prior5								97.81 122					98.95 133	89.26 228	98.51 202	98.60 133

Patchmatch-RL test		88.81 326	88.52 319	89.69 348	95.33 314	79.94 303	86.22 420	92.71 354	78.46 389	95.80 155	94.18 325	66.25 412	95.33 406	89.22 230	98.53 198	93.78 412

PatchT		87.51 353	88.17 334	85.55 415	90.64 427	66.91 440	92.02 256	86.09 422	92.20 107	89.05 381	97.16 136	64.15 424	96.37 380	89.21 231	92.98 428	93.37 422

test_f		86.65 371	87.13 352	85.19 419	90.28 435	86.11 185	86.52 416	91.66 377	69.76 447	95.73 162	97.21 133	69.51 396	81.28 469	89.15 232	94.40 393	88.17 455

CSCG		94.69 123	94.75 129	94.52 140	97.55 136	87.87 136	95.01 123	97.57 149	92.68 91	96.20 134	93.44 349	91.92 144	98.78 162	89.11 233	99.24 93	96.92 298

KD-MVS_self_test		94.10 158	94.73 132	92.19 252	97.66 129	79.49 317	94.86 127	97.12 192	89.59 191	96.87 91	97.65 87	90.40 192	98.34 231	89.08 234	99.35 67	98.75 107

test_vis3_rt		90.40 280	90.03 292	91.52 282	92.58 385	88.95 109	90.38 320	97.72 133	73.30 424	97.79 38	97.51 103	77.05 360	87.10 462	89.03 235	94.89 382	98.50 143

cl22		89.02 318	88.50 320	90.59 324	89.76 439	76.45 377	86.62 412	94.03 327	82.98 341	92.65 302	92.49 371	72.05 386	97.53 317	88.93 236	97.02 319	97.78 237

VDD-MVS		94.37 141	94.37 150	94.40 147	97.49 139	86.07 186	93.97 166	93.28 343	94.49 58	96.24 130	97.78 74	87.99 235	98.79 158	88.92 237	99.14 107	98.34 162

AUN-MVS		90.05 298	88.30 325	95.32 97	96.09 259	90.52 84	92.42 236	92.05 371	82.08 352	88.45 394	92.86 362	65.76 414	98.69 180	88.91 238	96.07 349	96.75 308

TransMVSNet (Re)		95.27 100	96.04 63	92.97 212	98.37 70	81.92 269	95.07 120	96.76 225	93.97 69	97.77 39	98.57 29	95.72 24	97.90 279	88.89 239	99.23 94	99.08 57

SSM_0407		94.23 152	94.56 144	93.24 203	96.65 195	82.79 252	93.66 179	97.84 117	91.46 143	95.19 196	96.56 189	92.50 132	98.99 124	88.83 240	98.32 225	97.93 211

SSM_0404		94.38 139	94.69 133	93.43 194	97.16 159	83.23 239	93.95 167	97.84 117	91.46 143	95.70 164	96.56 189	92.50 132	99.08 109	88.83 240	98.23 236	97.98 202

viewdifsd2359ckpt07		93.63 173	94.33 154	91.55 279	96.19 249	77.86 351	90.11 331	97.74 130	90.76 164	96.11 140	96.61 184	94.37 80	98.27 238	88.82 242	98.23 236	98.51 142

CR-MVSNet		87.89 342	87.12 353	90.22 334	91.01 423	78.93 328	92.52 228	92.81 350	73.08 426	89.10 378	96.93 156	67.11 404	97.64 310	88.80 243	92.70 430	94.08 403

CVMVSNet		85.16 380	84.72 378	86.48 403	92.12 400	70.19 425	92.32 243	88.17 404	56.15 469	90.64 351	95.85 242	67.97 402	96.69 367	88.78 244	90.52 446	92.56 434

FMVSNet1		94.84 115	95.13 112	93.97 162	97.60 132	84.29 218	95.99 74	96.56 241	92.38 98	97.03 84	98.53 31	90.12 199	98.98 125	88.78 244	99.16 105	98.65 122

ZD-MVS					97.23 154	90.32 85		97.54 152	84.40 321	94.78 219	95.79 247	92.76 124	99.39 54	88.72 246	98.40 211

train_agg		92.71 216	91.83 246	95.35 93	96.45 219	89.46 96	90.60 310	96.92 206	79.37 379	90.49 352	94.39 317	91.20 168	98.88 140	88.66 247	98.43 209	97.72 243

mamba_0408		93.60 176	93.72 176	93.27 201	96.65 195	82.79 252	88.81 370	97.68 135	90.62 170	95.19 196	96.01 235	91.54 157	99.08 109	88.63 248	98.32 225	97.93 211

SSM_04072		93.25 193	93.72 176	91.84 265	96.65 195	82.79 252	88.81 370	97.68 135	90.62 170	95.19 196	96.01 235	91.54 157	94.81 415	88.63 248	98.32 225	97.93 211

Anonymous20240529		95.50 83	95.83 78	94.50 141	97.33 149	85.93 191	95.19 117	96.77 224	96.64 24	97.61 47	98.05 51	93.23 107	98.79 158	88.60 250	99.04 123	98.78 103

viewcassd2359sk11		93.16 198	93.51 190	92.13 258	96.07 261	79.59 313	90.88 299	97.97 96	87.82 240	94.23 233	96.19 222	92.31 134	98.53 205	88.58 251	97.51 295	98.28 168

viewmanbaseed2359cas		93.08 199	93.43 192	92.01 262	95.69 290	79.29 321	91.15 291	97.70 134	87.45 250	94.18 236	96.12 229	92.31 134	98.37 228	88.58 251	97.73 280	98.38 157

test1111		90.39 282	90.61 279	89.74 346	98.04 96	71.50 420	95.59 92	79.72 462	89.41 193	95.94 148	98.14 45	70.79 391	98.81 154	88.52 253	99.32 77	98.90 88

icg_test_0407_2		91.18 262	91.92 243	88.94 361	95.19 317	76.72 370	84.66 438	96.89 209	85.92 283	93.55 258	94.50 311	91.06 173	92.99 436	88.49 254	97.07 313	97.10 286

IMVS_0407		92.28 233	92.83 208	90.63 322	95.19 317	76.72 370	92.79 215	96.89 209	85.92 283	93.55 258	94.50 311	91.06 173	98.07 260	88.49 254	97.07 313	97.10 286

IMVS_0404		90.67 272	91.06 265	89.50 349	95.19 317	76.72 370	86.58 414	96.89 209	85.92 283	89.17 377	94.50 311	85.77 271	94.67 416	88.49 254	97.07 313	97.10 286

IMVS_0403		92.20 238	92.70 216	90.69 318	95.19 317	76.72 370	92.39 238	96.89 209	85.92 283	93.66 255	94.50 311	90.18 196	98.24 242	88.49 254	97.07 313	97.10 286

test_prior2							90.21 325		89.33 196	90.77 347	94.81 294	90.41 191		88.21 258	98.55 195

APD_test1		95.91 64	95.42 97	97.36 27	98.82 30	96.62 7	95.64 91	97.64 139	93.38 83	95.89 152	97.23 129	93.35 103	97.66 308	88.20 259	98.66 186	97.79 235

D2MVS		89.93 300	89.60 302	90.92 309	94.03 356	78.40 340	88.69 375	94.85 307	78.96 386	93.08 285	95.09 283	74.57 375	96.94 355	88.19 260	98.96 135	97.41 267

IS-MVSNet		94.49 134	94.35 153	94.92 114	98.25 80	86.46 173	97.13 17	94.31 321	96.24 35	96.28 128	96.36 206	82.88 300	99.35 67	88.19 260	99.52 42	98.96 76

test9_res														88.16 262	98.40 211	97.83 229

UGNet		93.08 199	92.50 224	94.79 122	93.87 360	87.99 134	95.07 120	94.26 324	90.64 168	87.33 412	97.67 85	86.89 258	98.49 210	88.10 263	98.71 178	97.91 217
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		85.42 378	84.57 381	87.96 382	97.81 114	66.53 443	96.14 68	56.35 476	89.04 202	93.55 258	98.10 48	42.88 472	98.68 182	88.09 264	99.18 102	98.67 120

test_cas_vis1_n_1920		88.25 338	88.27 328	88.20 379	92.19 398	78.92 330	89.45 350	95.44 289	75.29 413	93.23 276	95.65 258	71.58 388	90.23 451	88.05 265	93.55 415	95.44 367

FA-MVS(test-final)		91.81 246	91.85 245	91.68 274	94.95 324	79.99 302	96.00 73	93.44 341	87.80 241	94.02 244	97.29 121	77.60 352	98.45 218	88.04 266	97.49 297	96.61 310

ETV-MVS		92.99 203	92.74 211	93.72 178	95.86 278	86.30 179	92.33 242	97.84 117	91.70 134	92.81 296	86.17 445	92.22 137	99.19 94	88.03 267	97.73 280	95.66 359

EIA-MVS		92.35 230	92.03 238	93.30 200	95.81 283	83.97 226	92.80 214	98.17 62	87.71 244	89.79 369	87.56 435	91.17 171	99.18 95	87.97 268	97.27 306	96.77 306

mvs_anonymous		90.37 284	91.30 259	87.58 389	92.17 399	68.00 436	89.84 339	94.73 314	83.82 327	93.22 277	97.40 108	87.54 243	97.40 329	87.94 269	95.05 379	97.34 275

IterMVS		90.18 290	90.16 288	90.21 335	93.15 373	75.98 383	87.56 390	92.97 348	86.43 271	94.09 238	96.40 199	78.32 347	97.43 326	87.87 270	94.69 389	97.23 281
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_enhance_ethall		88.42 335	87.87 338	90.07 338	88.67 452	75.52 387	85.10 431	95.59 283	75.68 406	92.49 307	89.45 419	78.96 337	97.88 283	87.86 271	97.02 319	96.81 304

ET-MVSNet_ETH3D		86.15 373	84.27 384	91.79 268	93.04 376	81.28 281	87.17 398	86.14 421	79.57 376	83.65 438	88.66 425	57.10 444	98.18 248	87.74 272	95.40 368	95.90 348

Effi-MVS+-dtu		93.90 167	92.60 221	97.77 4	94.74 334	96.67 6	94.00 164	95.41 292	89.94 183	91.93 330	92.13 381	90.12 199	98.97 130	87.68 273	97.48 298	97.67 247

SDMVSNet		94.43 137	95.02 118	92.69 230	97.93 106	82.88 250	91.92 263	95.99 270	93.65 79	95.51 171	98.63 26	94.60 72	96.48 373	87.57 274	99.35 67	98.70 116

WR-MVS		93.49 179	93.72 176	92.80 224	97.57 135	80.03 300	90.14 328	95.68 277	93.70 75	96.62 107	95.39 274	87.21 249	99.04 119	87.50 275	99.64 26	99.33 31

tfpnnormal		94.27 146	94.87 123	92.48 244	97.71 123	80.88 289	94.55 143	95.41 292	93.70 75	96.67 103	97.72 80	91.40 161	98.18 248	87.45 276	99.18 102	98.36 158

jason		89.17 314	88.32 324	91.70 273	95.73 288	80.07 297	88.10 382	93.22 344	71.98 432	90.09 360	92.79 365	78.53 345	98.56 199	87.43 277	97.06 317	96.46 320
jason: jason.
Effi-MVS+		92.79 211	92.74 211	92.94 216	95.10 321	83.30 237	94.00 164	97.53 154	91.36 148	89.35 376	90.65 407	94.01 88	98.66 184	87.40 278	95.30 372	96.88 302

FMVSNet2		92.78 212	92.73 213	92.95 214	95.40 309	81.98 268	94.18 156	95.53 287	88.63 214	96.05 142	97.37 110	81.31 320	98.81 154	87.38 279	98.67 184	98.06 189

EPP-MVSNet		93.91 166	93.68 181	94.59 136	98.08 90	85.55 201	97.44 11	94.03 327	94.22 64	94.94 212	96.19 222	82.07 312	99.57 15	87.28 280	98.89 143	98.65 122

PC_three_1452									75.31 412	95.87 153	95.75 252	92.93 118	96.34 383	87.18 281	98.68 182	98.04 193

ECVR-MVS		90.12 293	90.16 288	90.00 342	97.81 114	72.68 413	95.76 86	78.54 465	89.04 202	95.36 182	98.10 48	70.51 393	98.64 188	87.10 282	99.18 102	98.67 120

VDDNet		94.03 161	94.27 158	93.31 198	98.87 26	82.36 262	95.51 100	91.78 376	97.19 16	96.32 123	98.60 28	84.24 287	98.75 166	87.09 283	98.83 155	98.81 99

agg_prior2														87.06 284	98.36 222	97.98 202

LF4IMVS		92.72 215	92.02 239	94.84 120	95.65 294	91.99 58	92.92 207	96.60 237	85.08 310	92.44 311	93.62 344	86.80 259	96.35 381	86.81 285	98.25 234	96.18 334

GBi-Net		93.21 195	92.96 203	93.97 162	95.40 309	84.29 218	95.99 74	96.56 241	88.63 214	95.10 203	98.53 31	81.31 320	98.98 125	86.74 286	98.38 216	98.65 122

test1		93.21 195	92.96 203	93.97 162	95.40 309	84.29 218	95.99 74	96.56 241	88.63 214	95.10 203	98.53 31	81.31 320	98.98 125	86.74 286	98.38 216	98.65 122

FMVSNet3		90.78 267	90.32 287	92.16 256	93.03 377	79.92 304	92.54 227	94.95 305	86.17 279	95.10 203	96.01 235	69.97 395	98.75 166	86.74 286	98.38 216	97.82 232

viewdifsd2359ckpt13		92.57 223	92.48 226	92.83 222	95.60 298	82.35 264	91.80 274	97.49 159	85.04 311	93.14 283	95.41 272	90.94 177	98.25 240	86.68 289	96.24 346	97.87 224

lupinMVS		88.34 337	87.31 345	91.45 285	94.74 334	80.06 298	87.23 395	92.27 364	71.10 438	88.83 382	91.15 395	77.02 361	98.53 205	86.67 290	96.75 332	95.76 353

OMC-MVS		94.22 153	93.69 180	95.81 74	97.25 152	91.27 68	92.27 248	97.40 165	87.10 260	94.56 225	95.42 269	93.74 90	98.11 256	86.62 291	98.85 149	98.06 189

mvsany_test3		89.11 316	88.21 333	91.83 266	91.30 420	90.25 86	88.09 383	78.76 463	76.37 404	96.43 115	98.39 39	83.79 292	90.43 450	86.57 292	94.20 401	94.80 388

pmmvs-eth3d		91.54 254	90.73 277	93.99 160	95.76 287	87.86 137	90.83 301	93.98 331	78.23 391	94.02 244	96.22 218	82.62 307	96.83 362	86.57 292	98.33 223	97.29 278

BP-MVS														86.55 294

HQP-MVS		92.09 241	91.49 254	93.88 168	96.36 227	84.89 211	91.37 284	97.31 175	87.16 256	88.81 384	93.40 350	84.76 284	98.60 193	86.55 294	97.73 280	98.14 185

viewdifsd2359ckpt09		92.60 219	92.34 230	93.36 196	95.94 273	83.36 235	92.35 240	97.93 105	83.17 337	92.92 294	94.66 303	89.87 206	98.57 197	86.51 296	97.71 284	98.15 183

ppachtmachnet_test		88.61 332	88.64 318	88.50 373	91.76 410	70.99 423	84.59 439	92.98 347	79.30 383	92.38 314	93.53 348	79.57 333	97.45 324	86.50 297	97.17 310	97.07 290

MIMVSNet1		95.52 82	95.45 94	95.72 78	99.14 5	89.02 108	96.23 66	96.87 215	93.73 74	97.87 36	98.49 34	90.73 185	99.05 116	86.43 298	99.60 28	99.10 56

PVSNet_Blended_VisFu		91.63 251	91.20 260	92.94 216	97.73 121	83.95 227	92.14 252	97.46 161	78.85 388	92.35 317	94.98 287	84.16 288	99.08 109	86.36 299	96.77 331	95.79 352

Fast-Effi-MVS+-dtu		92.77 213	92.16 234	94.58 139	94.66 339	88.25 127	92.05 254	96.65 234	89.62 190	90.08 361	91.23 394	92.56 127	98.60 193	86.30 300	96.27 345	96.90 299

OPU-MVS				95.15 107	96.84 180	89.43 98	95.21 113				95.66 257	93.12 111	98.06 262	86.28 301	98.61 189	97.95 208

PMVS	87.21 14	94.97 110	95.33 104	93.91 167	98.97 20	97.16 3	95.54 99	95.85 273	96.47 28	93.40 266	97.46 106	95.31 41	95.47 401	86.18 302	98.78 165	89.11 451
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
OpenMVS	89.45 8	92.27 236	92.13 237	92.68 231	94.53 343	84.10 224	95.70 87	97.03 197	82.44 348	91.14 343	96.42 197	88.47 223	98.38 224	85.95 303	97.47 299	95.55 364

Syy-MVS		84.81 383	84.93 377	84.42 426	91.71 412	63.36 459	85.89 423	81.49 453	81.03 360	85.13 424	81.64 463	77.44 354	95.00 411	85.94 304	94.12 404	94.91 385

CDPH-MVS		92.67 217	91.83 246	95.18 106	96.94 171	88.46 125	90.70 307	97.07 195	77.38 395	92.34 319	95.08 284	92.67 126	98.88 140	85.74 305	98.57 194	98.20 177

SSC-MVS		90.16 291	92.96 203	81.78 441	97.88 109	48.48 474	90.75 304	87.69 409	96.02 41	96.70 101	97.63 89	85.60 277	97.80 293	85.73 306	98.60 191	99.06 59

CANet_DTU		89.85 303	89.17 306	91.87 264	92.20 397	80.02 301	90.79 303	95.87 272	86.02 281	82.53 449	91.77 387	80.01 330	98.57 197	85.66 307	97.70 285	97.01 295

ITE_SJBPF				95.95 64	97.34 148	93.36 44		96.55 244	91.93 115	94.82 217	95.39 274	91.99 142	97.08 349	85.53 308	97.96 269	97.41 267

FE-MVSNET		92.02 243	92.22 233	91.41 287	96.63 203	79.08 327	91.53 280	96.84 218	85.52 300	95.16 199	96.14 227	83.97 290	97.50 319	85.48 309	98.75 172	97.64 249

new-patchmatchnet		88.97 322	90.79 275	83.50 434	94.28 348	55.83 470	85.34 430	93.56 338	86.18 278	95.47 174	95.73 253	83.10 297	96.51 372	85.40 310	98.06 257	98.16 182

viewmambaseed2359dif		90.77 268	90.81 273	90.64 321	93.46 367	77.04 362	88.83 368	96.29 253	80.79 366	92.21 323	95.11 281	88.99 214	97.28 334	85.39 311	96.20 348	97.59 253

EPNet		89.80 305	88.25 329	94.45 145	83.91 471	86.18 183	93.87 170	87.07 416	91.16 154	80.64 459	94.72 299	78.83 340	98.89 139	85.17 312	98.89 143	98.28 168
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmtry		90.11 294	89.92 294	90.66 320	90.35 434	77.00 364	92.96 205	92.81 350	90.25 180	94.74 221	96.93 156	67.11 404	97.52 318	85.17 312	98.98 128	97.46 263

旧先验2							90.00 334		68.65 451	92.71 301			96.52 371	85.15 314

MDA-MVSNet-bldmvs		91.04 263	90.88 269	91.55 279	94.68 338	80.16 293	85.49 428	92.14 368	90.41 178	94.93 213	95.79 247	85.10 281	96.93 357	85.15 314	94.19 403	97.57 255

Anonymous202405211		92.58 221	92.50 224	92.83 222	96.55 209	83.22 241	92.43 235	91.64 378	94.10 66	95.59 168	96.64 182	81.88 317	97.50 319	85.12 316	98.52 200	97.77 238

AllTest		94.88 114	94.51 146	96.00 60	98.02 97	92.17 54	95.26 111	98.43 27	90.48 174	95.04 208	96.74 174	92.54 128	97.86 287	85.11 317	98.98 128	97.98 202

TestCases				96.00 60	98.02 97	92.17 54		98.43 27	90.48 174	95.04 208	96.74 174	92.54 128	97.86 287	85.11 317	98.98 128	97.98 202

VPNet		93.08 199	93.76 175	91.03 304	98.60 45	75.83 386	91.51 281	95.62 278	91.84 123	95.74 160	97.10 143	89.31 211	98.32 232	85.07 319	99.06 115	98.93 82

LFMVS		91.33 259	91.16 263	91.82 267	96.27 241	79.36 319	95.01 123	85.61 431	96.04 40	94.82 217	97.06 147	72.03 387	98.46 217	84.96 320	98.70 180	97.65 248

VNet		92.67 217	92.96 203	91.79 268	96.27 241	80.15 294	91.95 259	94.98 304	92.19 108	94.52 227	96.07 232	87.43 245	97.39 330	84.83 321	98.38 216	97.83 229

our_test_3		87.55 352	87.59 342	87.44 391	91.76 410	70.48 424	83.83 446	90.55 390	79.79 372	92.06 328	92.17 380	78.63 344	95.63 396	84.77 322	94.73 387	96.22 332

TAPA-MVS	88.58 10	92.49 225	91.75 248	94.73 124	96.50 215	89.69 92	92.91 208	97.68 135	78.02 392	92.79 298	94.10 327	90.85 179	97.96 276	84.76 323	98.16 245	96.54 311
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		91.28 261	90.86 270	92.53 242	95.45 308	82.53 259	89.25 359	96.52 245	85.00 312	89.91 365	88.55 428	92.94 117	98.84 147	84.72 324	95.44 367	96.22 332

GA-MVS		87.70 346	86.82 358	90.31 330	93.27 371	77.22 361	84.72 436	92.79 352	85.11 309	89.82 367	90.07 408	66.80 407	97.76 300	84.56 325	94.27 399	95.96 343

QAPM		92.88 207	92.77 209	93.22 204	95.82 281	83.31 236	96.45 45	97.35 172	83.91 325	93.75 251	96.77 169	89.25 212	98.88 140	84.56 325	97.02 319	97.49 261

mvsmamba		90.24 289	89.43 303	92.64 232	95.52 303	82.36 262	96.64 34	92.29 363	81.77 354	92.14 325	96.28 212	70.59 392	99.10 108	84.44 327	95.22 375	96.47 319

SSC-MVS3.2		89.88 302	91.06 265	86.31 409	95.90 275	63.76 457	82.68 452	92.43 362	91.42 146	92.37 316	94.58 308	86.34 265	96.60 369	84.35 328	99.50 43	98.57 136

UnsupCasMVSNet_eth		90.33 286	90.34 286	90.28 331	94.64 340	80.24 292	89.69 344	95.88 271	85.77 290	93.94 248	95.69 256	81.99 314	92.98 437	84.21 329	91.30 441	97.62 250

testing3		83.66 395	82.52 400	87.08 393	95.84 279	65.84 448	89.80 341	77.17 469	88.17 231	90.84 346	88.63 426	30.95 477	98.11 256	84.05 330	97.19 309	97.28 279

CLD-MVS		91.82 245	91.41 256	93.04 209	96.37 225	83.65 230	86.82 406	97.29 178	84.65 318	92.27 321	89.67 416	92.20 139	97.85 289	83.95 331	99.47 45	97.62 250
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
114514_t		90.51 276	89.80 297	92.63 235	98.00 101	82.24 265	93.40 188	97.29 178	65.84 459	89.40 375	94.80 296	86.99 254	98.75 166	83.88 332	98.61 189	96.89 300

DP-MVS Recon		92.31 232	91.88 244	93.60 182	97.18 158	86.87 160	91.10 294	97.37 166	84.92 314	92.08 327	94.08 328	88.59 220	98.20 245	83.50 333	98.14 247	95.73 354

YYNet1		88.17 339	88.24 330	87.93 383	92.21 396	73.62 404	80.75 458	88.77 397	82.51 347	94.99 211	95.11 281	82.70 305	93.70 429	83.33 334	93.83 409	96.48 318

MDA-MVSNet_test_wron		88.16 340	88.23 331	87.93 383	92.22 395	73.71 403	80.71 459	88.84 396	82.52 346	94.88 216	95.14 279	82.70 305	93.61 430	83.28 335	93.80 410	96.46 320

XXY-MVS		92.58 221	93.16 201	90.84 314	97.75 118	79.84 305	91.87 268	96.22 260	85.94 282	95.53 170	97.68 83	92.69 125	94.48 419	83.21 336	97.51 295	98.21 175

cascas		87.02 367	86.28 370	89.25 357	91.56 417	76.45 377	84.33 442	96.78 222	71.01 439	86.89 415	85.91 446	81.35 319	96.94 355	83.09 337	95.60 362	94.35 400

test-LLR		83.58 396	83.17 395	84.79 423	89.68 441	66.86 441	83.08 449	84.52 440	83.07 339	82.85 445	84.78 454	62.86 432	93.49 431	82.85 338	94.86 383	94.03 406

test-mter		81.21 416	80.01 424	84.79 423	89.68 441	66.86 441	83.08 449	84.52 440	73.85 421	82.85 445	84.78 454	43.66 468	93.49 431	82.85 338	94.86 383	94.03 406

pmmvs4		88.95 323	87.70 341	92.70 229	94.30 347	85.60 200	87.22 396	92.16 367	74.62 415	89.75 371	94.19 324	77.97 350	96.41 377	82.71 340	96.36 342	96.09 337

testdata				91.03 304	96.87 177	82.01 267		94.28 323	71.55 434	92.46 309	95.42 269	85.65 275	97.38 332	82.64 341	97.27 306	93.70 415

MonoMVSNet		88.46 334	89.28 304	85.98 411	90.52 430	70.07 429	95.31 108	94.81 311	88.38 224	93.47 262	96.13 228	73.21 380	95.07 410	82.61 342	89.12 450	92.81 431

thisisatest0515		84.72 385	82.99 397	89.90 343	92.96 379	75.33 389	84.36 441	83.42 445	77.37 396	88.27 397	86.65 440	53.94 450	98.72 171	82.56 343	97.40 303	95.67 358

PS-MVSNAJ		88.86 325	88.99 311	88.48 374	94.88 325	74.71 391	86.69 409	95.60 279	80.88 363	87.83 404	87.37 438	90.77 181	98.82 149	82.52 344	94.37 396	91.93 439

xiu_mvs_v2_base		89.00 321	89.19 305	88.46 375	94.86 327	74.63 393	86.97 400	95.60 279	80.88 363	87.83 404	88.62 427	91.04 175	98.81 154	82.51 345	94.38 395	91.93 439

WB-MVS		89.44 310	92.15 236	81.32 442	97.73 121	48.22 475	89.73 342	87.98 407	95.24 48	96.05 142	96.99 153	85.18 280	96.95 354	82.45 346	97.97 268	98.78 103

PAPM_NR		91.03 264	90.81 273	91.68 274	96.73 188	81.10 285	93.72 176	96.35 252	88.19 230	88.77 388	92.12 382	85.09 282	97.25 337	82.40 347	93.90 408	96.68 309

test_yl		90.11 294	89.73 300	91.26 295	94.09 353	79.82 306	90.44 316	92.65 355	90.90 158	93.19 280	93.30 352	73.90 377	98.03 266	82.23 348	96.87 326	95.93 345

DCV-MVSNet		90.11 294	89.73 300	91.26 295	94.09 353	79.82 306	90.44 316	92.65 355	90.90 158	93.19 280	93.30 352	73.90 377	98.03 266	82.23 348	96.87 326	95.93 345

DPM-MVS		89.35 311	88.40 322	92.18 255	96.13 256	84.20 222	86.96 401	96.15 264	75.40 410	87.36 411	91.55 392	83.30 295	98.01 270	82.17 350	96.62 336	94.32 401

MG-MVS		89.54 307	89.80 297	88.76 365	94.88 325	72.47 416	89.60 345	92.44 361	85.82 289	89.48 373	95.98 238	82.85 302	97.74 303	81.87 351	95.27 373	96.08 338

PatchmatchNet		85.22 379	84.64 379	86.98 395	89.51 445	69.83 431	90.52 312	87.34 413	78.87 387	87.22 413	92.74 367	66.91 406	96.53 370	81.77 352	86.88 456	94.58 395
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TinyColmap		92.00 244	92.76 210	89.71 347	95.62 297	77.02 363	90.72 306	96.17 263	87.70 245	95.26 189	96.29 210	92.54 128	96.45 376	81.77 352	98.77 166	95.66 359

sd_testset		93.94 165	94.39 148	92.61 238	97.93 106	83.24 238	93.17 196	95.04 302	93.65 79	95.51 171	98.63 26	94.49 77	95.89 393	81.72 354	99.35 67	98.70 116

test_vis1_rt		85.58 377	84.58 380	88.60 369	87.97 454	86.76 163	85.45 429	93.59 336	66.43 456	87.64 407	89.20 422	79.33 335	85.38 466	81.59 355	89.98 449	93.66 416

ttmdpeth		86.91 369	86.57 363	87.91 385	89.68 441	74.24 400	91.49 282	87.09 414	79.84 370	89.46 374	97.86 72	65.42 416	91.04 445	81.57 356	96.74 334	98.44 149

原ACMM1				92.87 220	96.91 174	84.22 221		97.01 198	76.84 402	89.64 372	94.46 315	88.00 234	98.70 178	81.53 357	98.01 263	95.70 357

1112_ss		88.42 335	87.41 344	91.45 285	96.69 192	80.99 287	89.72 343	96.72 227	73.37 423	87.00 414	90.69 405	77.38 356	98.20 245	81.38 358	93.72 411	95.15 373

MS-PatchMatch		88.05 341	87.75 339	88.95 360	93.28 370	77.93 348	87.88 385	92.49 360	75.42 409	92.57 306	93.59 346	80.44 327	94.24 426	81.28 359	92.75 429	94.69 394

LCM-MVSNet-Re		94.20 154	94.58 142	93.04 209	95.91 274	83.13 245	93.79 173	99.19 6	92.00 112	98.84 9	98.04 53	93.64 92	99.02 121	81.28 359	98.54 197	96.96 297

tpmrst		82.85 404	82.93 398	82.64 437	87.65 455	58.99 467	90.14 328	87.90 408	75.54 408	83.93 437	91.63 390	66.79 409	95.36 404	81.21 361	81.54 466	93.57 421

无先验							89.94 335	95.75 275	70.81 441				98.59 195	81.17 362		94.81 387

新几何1				93.17 207	97.16 159	87.29 146		94.43 319	67.95 453	91.29 338	94.94 289	86.97 255	98.23 243	81.06 363	97.75 279	93.98 408

MSDG		90.82 265	90.67 278	91.26 295	94.16 350	83.08 246	86.63 411	96.19 261	90.60 172	91.94 329	91.89 385	89.16 213	95.75 395	80.96 364	94.51 392	94.95 382

mvsany_test1		83.91 394	82.93 398	86.84 400	86.18 464	85.93 191	81.11 457	75.03 470	70.80 442	88.57 393	94.63 304	83.08 298	87.38 461	80.39 365	86.57 457	87.21 457

pmmvs5		87.87 343	87.14 351	90.07 338	93.26 372	76.97 367	88.89 365	92.18 365	73.71 422	88.36 395	93.89 337	76.86 366	96.73 366	80.32 366	96.81 329	96.51 313

PVSNet_BlendedMVS		90.35 285	89.96 293	91.54 281	94.81 329	78.80 336	90.14 328	96.93 204	79.43 378	88.68 391	95.06 285	86.27 267	98.15 252	80.27 367	98.04 259	97.68 246

PVSNet_Blended		88.74 329	88.16 335	90.46 328	94.81 329	78.80 336	86.64 410	96.93 204	74.67 414	88.68 391	89.18 423	86.27 267	98.15 252	80.27 367	96.00 351	94.44 398

testdata2													98.03 266	80.24 369

FE-MVS		89.06 317	88.29 326	91.36 289	94.78 331	79.57 315	96.77 29	90.99 383	84.87 315	92.96 292	96.29 210	60.69 440	98.80 157	80.18 370	97.11 312	95.71 355

F-COLMAP		92.28 233	91.06 265	95.95 64	97.52 137	91.90 60	93.53 182	97.18 186	83.98 324	88.70 390	94.04 329	88.41 225	98.55 201	80.17 371	95.99 352	97.39 272

EPMVS		81.17 417	80.37 420	83.58 433	85.58 466	65.08 452	90.31 323	71.34 471	77.31 398	85.80 420	91.30 393	59.38 441	92.70 438	79.99 372	82.34 465	92.96 429

TESTMET0.1,1		79.09 431	78.04 433	82.25 439	87.52 457	64.03 456	83.08 449	80.62 459	70.28 445	80.16 460	83.22 460	44.13 466	90.56 448	79.95 373	93.36 417	92.15 437

Test_1112_low_res		87.50 354	86.58 362	90.25 333	96.80 184	77.75 353	87.53 392	96.25 256	69.73 448	86.47 416	93.61 345	75.67 371	97.88 283	79.95 373	93.20 421	95.11 377

CL-MVSNet_self_test		90.04 299	89.90 295	90.47 326	95.24 315	77.81 352	86.60 413	92.62 357	85.64 294	93.25 275	93.92 335	83.84 291	96.06 388	79.93 375	98.03 260	97.53 259

OpenMVS_ROB	85.12 16	89.52 308	89.05 308	90.92 309	94.58 341	81.21 284	91.10 294	93.41 342	77.03 400	93.41 263	93.99 333	83.23 296	97.80 293	79.93 375	94.80 386	93.74 414

CNLPA		91.72 249	91.20 260	93.26 202	96.17 250	91.02 71	91.14 292	95.55 286	90.16 181	90.87 345	93.56 347	86.31 266	94.40 422	79.92 377	97.12 311	94.37 399

ab-mvs		92.40 228	92.62 219	91.74 270	97.02 166	81.65 274	95.84 83	95.50 288	86.95 263	92.95 293	97.56 94	90.70 186	97.50 319	79.63 378	97.43 301	96.06 339

test_post1							90.21 325				5.85 477	65.36 417	96.00 390	79.61 379

SCA		87.43 355	87.21 349	88.10 381	92.01 404	71.98 418	89.43 351	88.11 405	82.26 350	88.71 389	92.83 363	78.65 342	97.59 313	79.61 379	93.30 419	94.75 391

tpmvs		84.22 389	83.97 388	84.94 421	87.09 460	65.18 450	91.21 289	88.35 400	82.87 342	85.21 422	90.96 400	65.24 419	96.75 365	79.60 381	85.25 459	92.90 430

baseline1		87.62 350	87.31 345	88.54 370	94.71 337	74.27 399	93.10 199	88.20 403	86.20 276	92.18 324	93.04 358	73.21 380	95.52 398	79.32 382	85.82 458	95.83 350

tpm		84.38 388	84.08 386	85.30 418	90.47 432	63.43 458	89.34 354	85.63 428	77.24 399	87.62 408	95.03 286	61.00 439	97.30 333	79.26 383	91.09 444	95.16 372

BH-untuned		90.68 271	90.90 268	90.05 341	95.98 269	79.57 315	90.04 332	94.94 306	87.91 236	94.07 240	93.00 359	87.76 238	97.78 297	79.19 384	95.17 376	92.80 432

API-MVS		91.52 255	91.61 249	91.26 295	94.16 350	86.26 180	94.66 135	94.82 309	91.17 153	92.13 326	91.08 397	90.03 204	97.06 351	79.09 385	97.35 305	90.45 449

1314		86.46 372	86.33 369	86.87 399	91.65 414	74.54 394	91.94 261	94.10 326	74.28 418	84.78 429	87.33 439	83.03 299	95.00 411	78.72 386	91.16 443	91.06 446

BH-RMVSNet		90.47 278	90.44 283	90.56 325	95.21 316	78.65 338	89.15 360	93.94 332	88.21 229	92.74 300	94.22 323	86.38 264	97.88 283	78.67 387	95.39 369	95.14 374

MVP-Stereo		90.07 297	88.92 312	93.54 187	96.31 235	86.49 171	90.93 298	95.59 283	79.80 371	91.48 335	95.59 259	80.79 324	97.39 330	78.57 388	91.19 442	96.76 307
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDTV_nov1_ep13			83.88 391		89.42 446	61.52 461	88.74 374	87.41 411	73.99 420	84.96 428	94.01 332	65.25 418	95.53 397	78.02 389	93.16 422

Vis-MVSNet (Re-imp)		90.42 279	90.16 288	91.20 300	97.66 129	77.32 359	94.33 148	87.66 410	91.20 152	92.99 289	95.13 280	75.40 373	98.28 234	77.86 390	99.19 100	97.99 201

sss		87.23 359	86.82 358	88.46 375	93.96 357	77.94 347	86.84 404	92.78 353	77.59 394	87.61 409	91.83 386	78.75 341	91.92 441	77.84 391	94.20 401	95.52 366

IB-MVS	77.21 19	83.11 399	81.05 411	89.29 355	91.15 421	75.85 384	85.66 427	86.00 423	79.70 374	82.02 453	86.61 441	48.26 455	98.39 221	77.84 391	92.22 435	93.63 417
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		86.10 374	86.01 371	86.38 407	90.63 428	74.22 401	89.57 346	86.69 417	85.73 292	89.81 368	92.83 363	65.24 419	91.04 445	77.82 393	95.78 358	93.88 411

USDC		89.02 318	89.08 307	88.84 364	95.07 322	74.50 396	88.97 363	96.39 250	73.21 425	93.27 272	96.28 212	82.16 311	96.39 378	77.55 394	98.80 161	95.62 362

CDS-MVSNet		89.55 306	88.22 332	93.53 188	95.37 312	86.49 171	89.26 357	93.59 336	79.76 373	91.15 342	92.31 377	77.12 359	98.38 224	77.51 395	97.92 272	95.71 355
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
N_pmnet		88.90 324	87.25 348	93.83 172	94.40 346	93.81 39	84.73 434	87.09 414	79.36 381	93.26 273	92.43 375	79.29 336	91.68 442	77.50 396	97.22 308	96.00 341

AdaColmap		91.63 251	91.36 257	92.47 245	95.56 301	86.36 177	92.24 251	96.27 255	88.88 208	89.90 366	92.69 368	91.65 151	98.32 232	77.38 397	97.64 289	92.72 433

CostFormer		83.09 400	82.21 403	85.73 412	89.27 447	67.01 439	90.35 321	86.47 419	70.42 444	83.52 441	93.23 355	61.18 437	96.85 361	77.21 398	88.26 454	93.34 423

E-PMN		80.72 421	80.86 414	80.29 445	85.11 468	68.77 433	72.96 465	81.97 451	87.76 243	83.25 444	83.01 461	62.22 435	89.17 458	77.15 399	94.31 398	82.93 463

PLC	85.34 15	90.40 280	88.92 312	94.85 119	96.53 213	90.02 88	91.58 279	96.48 247	80.16 369	86.14 418	92.18 379	85.73 273	98.25 240	76.87 400	94.61 391	96.30 326
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MAR-MVS		90.32 287	88.87 316	94.66 131	94.82 328	91.85 61	94.22 154	94.75 313	80.91 362	87.52 410	88.07 433	86.63 262	97.87 286	76.67 401	96.21 347	94.25 402
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
EPNet_dtu		85.63 376	84.37 382	89.40 353	86.30 463	74.33 398	91.64 277	88.26 401	84.84 316	72.96 469	89.85 409	71.27 390	97.69 306	76.60 402	97.62 290	96.18 334
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		82.94 402	81.72 405	86.59 401	92.55 387	66.53 443	86.08 422	85.70 426	85.47 302	83.95 436	85.70 448	45.87 461	97.07 350	76.58 403	93.56 414	96.17 336

JIA-IIPM		85.08 381	83.04 396	91.19 301	87.56 456	86.14 184	89.40 353	84.44 442	88.98 204	82.20 450	97.95 61	56.82 446	96.15 384	76.55 404	83.45 462	91.30 444

PatchMatch-RL		89.18 313	88.02 337	92.64 232	95.90 275	92.87 49	88.67 377	91.06 382	80.34 367	90.03 363	91.67 389	83.34 294	94.42 421	76.35 405	94.84 385	90.64 448

testing91		83.56 397	82.45 401	86.91 398	92.92 380	67.29 437	86.33 418	88.07 406	86.22 275	84.26 433	85.76 447	48.15 457	97.17 343	76.27 406	94.08 407	96.27 329

FMVSNet5		87.82 345	86.56 364	91.62 276	92.31 392	79.81 308	93.49 184	94.81 311	83.26 332	91.36 337	96.93 156	52.77 453	97.49 322	76.07 407	98.03 260	97.55 258

PMMVS		83.00 401	81.11 410	88.66 368	83.81 472	86.44 174	82.24 454	85.65 427	61.75 466	82.07 451	85.64 449	79.75 332	91.59 443	75.99 408	93.09 425	87.94 456

CMPMVS	68.83 22	87.28 358	85.67 374	92.09 259	88.77 451	85.42 204	90.31 323	94.38 320	70.02 446	88.00 400	93.30 352	73.78 379	94.03 428	75.96 409	96.54 338	96.83 303
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EMVS		80.35 424	80.28 422	80.54 444	84.73 470	69.07 432	72.54 467	80.73 458	87.80 241	81.66 455	81.73 462	62.89 431	89.84 452	75.79 410	94.65 390	82.71 464

WBMVS		84.00 392	83.48 392	85.56 414	92.71 383	61.52 461	83.82 447	89.38 395	79.56 377	90.74 348	93.20 356	48.21 456	97.28 334	75.63 411	98.10 252	97.88 221

HyFIR lowres test		87.19 362	85.51 375	92.24 249	97.12 164	80.51 291	85.03 432	96.06 265	66.11 458	91.66 333	92.98 361	70.12 394	99.14 99	75.29 412	95.23 374	97.07 290

UnsupCasMVSNet_bld		88.50 333	88.03 336	89.90 343	95.52 303	78.88 332	87.39 394	94.02 329	79.32 382	93.06 286	94.02 331	80.72 325	94.27 424	75.16 413	93.08 426	96.54 311

WTY-MVS		86.93 368	86.50 368	88.24 378	94.96 323	74.64 392	87.19 397	92.07 370	78.29 390	88.32 396	91.59 391	78.06 349	94.27 424	74.88 414	93.15 423	95.80 351

WAC-MVS						61.25 463								74.55 415

KD-MVS_2432*1600		82.17 408	80.75 415	86.42 405	82.04 473	70.09 427	81.75 455	90.80 386	82.56 344	90.37 356	89.30 420	42.90 470	96.11 386	74.47 416	92.55 432	93.06 425

miper_refine_blended		82.17 408	80.75 415	86.42 405	82.04 473	70.09 427	81.75 455	90.80 386	82.56 344	90.37 356	89.30 420	42.90 470	96.11 386	74.47 416	92.55 432	93.06 425

testing3-2		83.95 393	84.22 385	83.13 436	96.28 238	54.34 473	88.51 379	83.01 448	92.19 108	89.09 380	90.98 398	45.51 462	97.44 325	74.38 418	98.01 263	97.60 252

baseline2		83.38 398	81.54 408	88.90 362	91.38 418	72.84 412	88.78 372	81.22 455	78.97 385	79.82 461	87.56 435	61.73 436	97.80 293	74.30 419	90.05 448	96.05 340

testing11		81.98 411	80.52 418	86.38 407	92.69 384	67.13 438	85.79 425	84.80 439	82.16 351	81.19 458	85.41 450	45.24 463	96.88 360	74.14 420	93.24 420	95.14 374

gm-plane-assit					87.08 461	59.33 466			71.22 436		83.58 459		97.20 340	73.95 421

test20.03		90.80 266	90.85 271	90.63 322	95.63 296	79.24 323	89.81 340	92.87 349	89.90 184	94.39 229	96.40 199	85.77 271	95.27 408	73.86 422	99.05 118	97.39 272

TAMVS		90.16 291	89.05 308	93.49 192	96.49 216	86.37 176	90.34 322	92.55 359	80.84 365	92.99 289	94.57 309	81.94 316	98.20 245	73.51 423	98.21 241	95.90 348

CHOSEN 1792x2688		87.19 362	85.92 373	91.00 307	97.13 162	79.41 318	84.51 440	95.60 279	64.14 462	90.07 362	94.81 294	78.26 348	97.14 346	73.34 424	95.38 370	96.46 320

thres600view7		87.66 348	87.10 354	89.36 354	96.05 263	73.17 406	92.72 216	85.31 434	91.89 117	93.29 270	90.97 399	63.42 429	98.39 221	73.23 425	96.99 324	96.51 313

dp		79.28 430	78.62 430	81.24 443	85.97 465	56.45 469	86.91 402	85.26 436	72.97 428	81.45 457	89.17 424	56.01 448	95.45 402	73.19 426	76.68 468	91.82 442

pmmvs3		80.83 420	78.96 428	86.45 404	87.23 459	77.48 357	84.87 433	82.31 450	63.83 463	85.03 426	89.50 418	49.66 454	93.10 434	73.12 427	95.10 377	88.78 454

MDTV_nov1_ep13_2view						42.48 478	88.45 380		67.22 455	83.56 440		66.80 407		72.86 428		94.06 405

TR-MVS		87.70 346	87.17 350	89.27 356	94.11 352	79.26 322	88.69 375	91.86 374	81.94 353	90.69 350	89.79 413	82.82 303	97.42 327	72.65 429	91.98 438	91.14 445

PAPR		87.65 349	86.77 360	90.27 332	92.85 382	77.38 358	88.56 378	96.23 258	76.82 403	84.98 427	89.75 415	86.08 269	97.16 345	72.33 430	93.35 418	96.26 330

Anonymous20231206		88.77 328	88.29 326	90.20 336	96.31 235	78.81 335	89.56 347	93.49 340	74.26 419	92.38 314	95.58 262	82.21 309	95.43 403	72.07 431	98.75 172	96.34 324

MVS		84.98 382	84.30 383	87.01 394	91.03 422	77.69 355	91.94 261	94.16 325	59.36 467	84.23 434	87.50 437	85.66 274	96.80 364	71.79 432	93.05 427	86.54 459

tpm cat1		80.61 422	79.46 425	84.07 430	88.78 450	65.06 453	89.26 357	88.23 402	62.27 465	81.90 454	89.66 417	62.70 434	95.29 407	71.72 433	80.60 467	91.86 441

HY-MVS	82.50 18	86.81 370	85.93 372	89.47 350	93.63 364	77.93 348	94.02 163	91.58 380	75.68 406	83.64 439	93.64 342	77.40 355	97.42 327	71.70 434	92.07 437	93.05 427

testgi		90.38 283	91.34 258	87.50 390	97.49 139	71.54 419	89.43 351	95.16 299	88.38 224	94.54 226	94.68 302	92.88 121	93.09 435	71.60 435	97.85 276	97.88 221

BH-w/o		87.21 360	87.02 355	87.79 388	94.77 332	77.27 360	87.90 384	93.21 346	81.74 355	89.99 364	88.39 430	83.47 293	96.93 357	71.29 436	92.43 434	89.15 450

thres100view900		87.35 357	86.89 357	88.72 366	96.14 254	73.09 408	93.00 202	85.31 434	92.13 110	93.26 273	90.96 400	63.42 429	98.28 234	71.27 437	96.54 338	94.79 389

tfpn200view9		87.05 366	86.52 366	88.67 367	95.77 285	72.94 410	91.89 265	86.00 423	90.84 160	92.61 303	89.80 411	63.93 425	98.28 234	71.27 437	96.54 338	94.79 389

thres400		87.20 361	86.52 366	89.24 358	95.77 285	72.94 410	91.89 265	86.00 423	90.84 160	92.61 303	89.80 411	63.93 425	98.28 234	71.27 437	96.54 338	96.51 313

myMVS_eth3d		79.62 429	78.26 432	83.72 432	91.71 412	61.25 463	85.89 423	81.49 453	81.03 360	85.13 424	81.64 463	32.12 476	95.00 411	71.17 440	94.12 404	94.91 385

tpm2		81.46 413	80.35 421	84.80 422	89.90 438	65.14 451	90.44 316	85.36 433	65.82 460	82.05 452	92.44 374	57.94 443	96.69 367	70.71 441	88.49 453	92.56 434

ADS-MVSNet2		84.01 391	82.20 404	89.41 352	89.04 448	76.37 379	87.57 388	90.98 384	72.71 430	84.46 430	92.45 372	68.08 400	96.48 373	70.58 442	83.97 460	95.38 368

ADS-MVSNet		82.25 406	81.55 407	84.34 427	89.04 448	65.30 449	87.57 388	85.13 438	72.71 430	84.46 430	92.45 372	68.08 400	92.33 439	70.58 442	83.97 460	95.38 368

PVSNet	76.22 20	82.89 403	82.37 402	84.48 425	93.96 357	64.38 455	78.60 461	88.61 398	71.50 435	84.43 432	86.36 444	74.27 376	94.60 418	69.87 444	93.69 412	94.46 397

CHOSEN 280x420		80.04 427	77.97 434	86.23 410	90.13 436	74.53 395	72.87 466	89.59 394	66.38 457	76.29 466	85.32 451	56.96 445	95.36 404	69.49 445	94.72 388	88.79 453

thres200		85.85 375	85.18 376	87.88 386	94.44 344	72.52 415	89.08 362	86.21 420	88.57 219	91.44 336	88.40 429	64.22 423	98.00 272	68.35 446	95.88 356	93.12 424

dmvs_re		84.69 386	83.94 389	86.95 397	92.24 394	82.93 249	89.51 348	87.37 412	84.38 322	85.37 421	85.08 453	72.44 383	86.59 463	68.05 447	91.03 445	91.33 443

PCF-MVS	84.52 17	89.12 315	87.71 340	93.34 197	96.06 262	85.84 194	86.58 414	97.31 175	68.46 452	93.61 256	93.89 337	87.51 244	98.52 207	67.85 448	98.11 250	95.66 359
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
new_pmnet		81.22 415	81.01 413	81.86 440	90.92 425	70.15 426	84.03 443	80.25 461	70.83 440	85.97 419	89.78 414	67.93 403	84.65 467	67.44 449	91.90 439	90.78 447

gg-mvs-nofinetune		82.10 410	81.02 412	85.34 417	87.46 458	71.04 421	94.74 130	67.56 472	96.44 29	79.43 462	98.99 11	45.24 463	96.15 384	67.18 450	92.17 436	88.85 452

DSMNet-mixed		82.21 407	81.56 406	84.16 429	89.57 444	70.00 430	90.65 309	77.66 467	54.99 470	83.30 443	97.57 92	77.89 351	90.50 449	66.86 451	95.54 364	91.97 438

SD_0403		88.79 327	88.88 315	88.51 372	95.89 277	72.58 414	94.27 151	95.24 297	83.77 329	87.92 403	94.38 319	87.70 239	96.47 375	66.36 452	94.40 393	96.49 317

test0.0.03 1		82.48 405	81.47 409	85.48 416	89.70 440	73.57 405	84.73 434	81.64 452	83.07 339	88.13 399	86.61 441	62.86 432	89.10 459	66.24 453	90.29 447	93.77 413

MIMVSNet		87.13 364	86.54 365	88.89 363	96.05 263	76.11 381	94.39 146	88.51 399	81.37 358	88.27 397	96.75 173	72.38 384	95.52 398	65.71 454	95.47 366	95.03 379

UBG		80.28 426	78.94 429	84.31 428	92.86 381	61.77 460	83.87 445	83.31 447	77.33 397	82.78 447	83.72 458	47.60 459	96.06 388	65.47 455	93.48 416	95.11 377

UWE-MVS		80.29 425	79.10 426	83.87 431	91.97 406	59.56 465	86.50 417	77.43 468	75.40 410	87.79 406	88.10 432	44.08 467	96.90 359	64.23 456	96.36 342	95.14 374

PMMVS2		81.31 414	83.44 393	74.92 451	90.52 430	46.49 477	69.19 468	85.23 437	84.30 323	87.95 402	94.71 300	76.95 363	84.36 468	64.07 457	98.09 253	93.89 410

FPMVS		84.50 387	83.28 394	88.16 380	96.32 234	94.49 20	85.76 426	85.47 432	83.09 338	85.20 423	94.26 321	63.79 427	86.58 464	63.72 458	91.88 440	83.40 462

MVS-HIRNet		78.83 432	80.60 417	73.51 452	93.07 374	47.37 476	87.10 399	78.00 466	68.94 450	77.53 464	97.26 125	71.45 389	94.62 417	63.28 459	88.74 452	78.55 467

myMVS_eth3d28		80.97 418	80.42 419	82.62 438	93.35 369	58.25 468	84.70 437	85.62 430	86.31 272	84.04 435	85.20 452	46.00 460	94.07 427	62.93 460	95.65 361	95.53 365

WB-MVSnew		84.20 390	83.89 390	85.16 420	91.62 415	66.15 447	88.44 381	81.00 456	76.23 405	87.98 401	87.77 434	84.98 283	93.35 433	62.85 461	94.10 406	95.98 342

testing222		80.54 423	78.53 431	86.58 402	92.54 389	68.60 434	86.24 419	82.72 449	83.78 328	82.68 448	84.24 456	39.25 475	95.94 392	60.25 462	95.09 378	95.20 370

wuyk23d		87.83 344	90.79 275	78.96 448	90.46 433	88.63 116	92.72 216	90.67 388	91.65 135	98.68 15	97.64 88	96.06 19	77.53 470	59.84 463	99.41 60	70.73 468

GG-mvs-BLEND				83.24 435	85.06 469	71.03 422	94.99 125	65.55 474		74.09 468	75.51 468	44.57 465	94.46 420	59.57 464	87.54 455	84.24 461

PVSNet_0	70.34 21	74.58 435	72.96 438	79.47 446	90.63 428	66.24 445	73.26 464	83.40 446	63.67 464	78.02 463	78.35 467	72.53 382	89.59 454	56.68 465	60.05 471	82.57 465

ETVMVS		79.85 428	77.94 435	85.59 413	92.97 378	66.20 446	86.13 421	80.99 457	81.41 357	83.52 441	83.89 457	41.81 473	94.98 414	56.47 466	94.25 400	95.61 363

MVE	59.87 23	73.86 436	72.65 439	77.47 449	87.00 462	74.35 397	61.37 470	60.93 475	67.27 454	69.69 470	86.49 443	81.24 323	72.33 472	56.45 467	83.45 462	85.74 460
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PAPM		81.91 412	80.11 423	87.31 392	93.87 360	72.32 417	84.02 444	93.22 344	69.47 449	76.13 467	89.84 410	72.15 385	97.23 338	53.27 468	89.02 451	92.37 436

test_method		50.44 438	48.94 441	54.93 453	39.68 479	12.38 482	28.59 471	90.09 391	6.82 473	41.10 475	78.41 466	54.41 449	70.69 473	50.12 469	51.26 472	81.72 466

dmvs_testset		78.23 433	78.99 427	75.94 450	91.99 405	55.34 472	88.86 366	78.70 464	82.69 343	81.64 456	79.46 465	75.93 370	85.74 465	48.78 470	82.85 464	86.76 458

tmp_tt		37.97 440	44.33 442	18.88 457	11.80 480	21.54 481	63.51 469	45.66 479	4.23 474	51.34 473	50.48 472	59.08 442	22.11 476	44.50 471	68.35 470	13.00 472

UWE-MVS-28		74.73 434	73.18 437	79.35 447	85.42 467	55.55 471	87.63 386	65.92 473	74.39 417	77.33 465	88.19 431	47.63 458	89.48 456	39.01 472	93.14 424	93.03 428

DeepMVS_CX				53.83 454	70.38 477	64.56 454		48.52 478	33.01 472	65.50 472	74.21 469	56.19 447	46.64 475	38.45 473	70.07 469	50.30 470

dongtai		53.72 437	53.79 440	53.51 455	79.69 475	36.70 479	77.18 462	32.53 481	71.69 433	68.63 471	60.79 470	26.65 478	73.11 471	30.67 474	36.29 473	50.73 469

kuosan		43.63 439	44.25 443	41.78 456	66.04 478	34.37 480	75.56 463	32.62 480	53.25 471	50.46 474	51.18 471	25.28 479	49.13 474	13.44 475	30.41 474	41.84 471

test123		9.49 442	12.01 445	1.91 458	2.87 481	1.30 483	82.38 453	1.34 483	1.36 476	2.84 477	6.56 475	2.45 480	0.97 477	2.73 476	5.56 475	3.47 473

testmvs		9.02 443	11.42 446	1.81 459	2.77 482	1.13 484	79.44 460	1.90 482	1.18 477	2.65 478	6.80 474	1.95 481	0.87 478	2.62 477	3.45 476	3.44 474

mmdepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

monomultidepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

test_blank		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet_test		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

DCPMVS		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

cdsmvs_eth3d_5k		23.35 441	31.13 444	0.00 460	0.00 483	0.00 485	0.00 472	95.58 285	0.00 478	0.00 479	91.15 395	93.43 100	0.00 479	0.00 478	0.00 477	0.00 475

pcd_1.5k_mvsjas		7.56 444	10.09 447	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	90.77 181	0.00 479	0.00 478	0.00 477	0.00 475

sosnet-low-res		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uncertanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

Regformer		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

ab-mvs-re		7.56 444	10.08 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	90.69 405	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

TestfortrainingZip							96.32 55

FOURS1					99.21 3	94.68 16	98.45 4	98.81 11	97.73 10	98.27 24

test_one_0601					98.26 78	87.14 151		98.18 58	94.25 62	96.99 87	97.36 113	95.13 49

eth-test2					0.00 483

eth-test					0.00 483

test_241102_ONE					98.51 56	86.97 156		98.10 73	91.85 120	97.63 44	97.03 149	96.48 13	98.95 133

save fliter					97.46 142	88.05 133	92.04 255	97.08 194	87.63 247

test0726					98.51 56	86.69 166	95.34 104	98.18 58	91.85 120	97.63 44	97.37 110	95.58 28

GSMVS																94.75 391

test_part2					98.21 83	89.41 99				96.72 100

sam_mvs1												66.64 410				94.75 391

sam_mvs												66.41 411

MTGPA								97.62 141

test_post											6.07 476	65.74 415	95.84 394

patchmatchnet-post											91.71 388	66.22 413	97.59 313

MTMP							94.82 128	54.62 477

TEST9					96.45 219	89.46 96	90.60 310	96.92 206	79.09 384	90.49 352	94.39 317	91.31 163	98.88 140

test_8					96.37 225	89.14 106	90.51 313	96.89 209	79.37 379	90.42 354	94.36 320	91.20 168	98.82 149

agg_prior					96.20 247	88.89 111		96.88 214		90.21 359			98.78 162

test_prior4						89.91 89	90.74 305

test_prior				94.61 132	95.95 271	87.23 148		97.36 171					98.68 182			97.93 211

新几何2							90.02 333

旧先验1					96.20 247	84.17 223		94.82 309			95.57 263	89.57 209			97.89 273	96.32 325

原ACMM2							89.34 354

test222					96.95 170	85.27 207	88.83 368	93.61 335	65.09 461	90.74 348	94.85 292	84.62 286			97.36 304	93.91 409

segment_acmp												92.14 140

testdata1							88.96 364		88.44 222

test12				94.43 146	95.95 271	86.75 164		96.24 257		89.76 370		89.79 208	98.79 158		97.95 270	97.75 241

plane_prior7					97.71 123	88.68 115

plane_prior6					97.21 157	88.23 128						86.93 256

plane_prior4											95.59 259

plane_prior3						88.43 126			90.35 179	93.31 268

plane_prior2							94.56 141		91.74 131

plane_prior1					97.38 145

plane_prior						88.12 131	93.01 201		88.98 204						98.06 257

n2								0.00 484

nn								0.00 484

door-mid								92.13 369

test11								96.65 234

door								91.26 381

HQP5-MVS						84.89 211

HQP-NCC					96.36 227		91.37 284		87.16 256	88.81 384

ACMP_Plane					96.36 227		91.37 284		87.16 256	88.81 384

HQP4-MVS										88.81 384			98.61 191			98.15 183

HQP3-MVS								97.31 175							97.73 280

HQP2-MVS												84.76 284

NP-MVS					96.82 182	87.10 152					93.40 350

ACMMP++_ref															98.82 156

ACMMP++															99.25 91

Test By Simon												90.61 187

High-resolution multi-view benchmark