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.

test_fmvsm_n_1920		97.55 16	97.89 4	96.53 106	98.41 86	91.73 131	98.01 67	99.02 1	96.37 13	99.30 7	98.92 25	92.39 44	99.79 46	99.16 14	99.46 45	98.08 237

PGM-MVS		96.81 58	96.53 69	97.65 48	99.35 25	93.53 66	97.65 131	98.98 2	92.22 184	97.14 77	98.44 64	91.17 71	99.85 21	94.35 169	99.46 45	99.57 36

MVS_111021_HR		96.68 69	96.58 68	96.99 85	98.46 80	92.31 111	96.20 310	98.90 3	94.30 88	95.86 137	97.74 149	92.33 45	99.38 137	96.04 96	99.42 55	99.28 77

test_fmvsmconf_n		97.49 21	97.56 16	97.29 65	97.44 165	92.37 108	97.91 86	98.88 4	95.83 19	98.92 24	99.05 14	91.45 61	99.80 40	99.12 16	99.46 45	99.69 15

lecture		97.58 15	97.63 11	97.43 59	99.37 19	92.93 87	98.86 7	98.85 5	95.27 36	98.65 36	98.90 27	91.97 52	99.80 40	97.63 37	99.21 82	99.57 36

ACMMP		96.27 86	95.93 88	97.28 67	99.24 33	92.62 99	98.25 40	98.81 6	92.99 144	94.56 191	98.39 68	88.96 102	99.85 21	94.57 163	97.63 163	99.36 72
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
MVS_111021_LR		96.24 87	96.19 85	96.39 125	98.23 106	91.35 154	96.24 307	98.79 7	93.99 98	95.80 139	97.65 160	89.92 91	99.24 151	95.87 100	99.20 87	98.58 180

patch_mono-2		96.83 57	97.44 24	95.01 234	99.05 45	85.39 387	96.98 221	98.77 8	94.70 68	97.99 52	98.66 45	93.61 21	99.91 1	97.67 36	99.50 39	99.72 14

fmvsm_s_conf0.5_n		96.85 54	97.13 31	96.04 152	98.07 121	90.28 207	97.97 78	98.76 9	94.93 50	98.84 29	99.06 12	88.80 106	99.65 79	99.06 18	98.63 122	98.18 222

fmvsm_l_conf0.5_n		97.65 9	97.75 8	97.34 62	98.21 107	92.75 93	97.83 99	98.73 10	95.04 47	99.30 7	98.84 38	93.34 25	99.78 49	99.32 7	99.13 96	99.50 52

fmvsm_s_conf0.5_n_a		96.75 62	96.93 46	96.20 141	97.64 151	90.72 188	98.00 68	98.73 10	94.55 75	98.91 25	99.08 8	88.22 118	99.63 88	98.91 21	98.37 136	98.25 217

fmvsm_s_conf0.5_n_10		97.29 31	97.40 26	96.97 87	98.24 101	91.96 127	97.89 89	98.72 12	96.77 7	99.46 3	99.06 12	87.78 127	99.84 26	99.40 4	99.27 74	99.12 94

fmvsm_l_conf0.5_n_9		97.59 13	97.79 6	96.97 87	98.28 95	91.49 145	97.61 141	98.71 13	97.10 5	99.70 1	98.93 24	90.95 76	99.77 52	99.35 6	99.53 32	99.65 21

FC-MVSNet-test		93.94 191	93.57 183	95.04 232	95.48 325	91.45 150	98.12 56	98.71 13	93.37 126	90.23 306	96.70 231	87.66 129	97.85 360	91.49 234	90.39 346	95.83 335

UniMVSNet (Re)		93.31 218	92.55 231	95.61 194	95.39 331	93.34 72	97.39 176	98.71 13	93.14 139	90.10 315	94.83 334	87.71 128	98.03 333	91.67 232	83.99 422	95.46 354

MED-MVS test				98.00 25	99.56 1	94.50 36	98.69 11	98.70 16	93.45 123	98.73 31	98.53 53		99.86 10	97.40 49	99.58 23	99.65 21

MED-MVS		98.07 1	98.08 1	98.06 21	99.56 1	94.50 36	98.69 11	98.70 16	95.63 25	98.73 31	98.95 20	95.46 7	99.86 10	97.40 49	99.58 23	99.82 1

fmvsm_l_conf0.5_n_a		97.63 11	97.76 7	97.26 69	98.25 100	92.59 101	97.81 104	98.68 18	94.93 50	99.24 10	98.87 33	93.52 22	99.79 46	99.32 7	99.21 82	99.40 66

FIs		94.09 182	93.70 179	95.27 219	95.70 314	92.03 123	98.10 57	98.68 18	93.36 128	90.39 303	96.70 231	87.63 132	97.94 351	92.25 212	90.50 345	95.84 334

WR-MVS_H		92.00 275	91.35 272	93.95 308	95.09 358	89.47 245	98.04 64	98.68 18	91.46 216	88.34 368	94.68 341	85.86 174	97.56 392	85.77 372	84.24 420	94.82 407

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 178	97.76 142	89.57 238	97.66 130	98.66 21	95.36 32	99.03 16	98.90 27	88.39 114	99.73 61	99.17 13	98.66 120	98.08 237

VPA-MVSNet		93.24 220	92.48 236	95.51 204	95.70 314	92.39 107	97.86 92	98.66 21	92.30 181	92.09 263	95.37 309	80.49 301	98.40 283	93.95 175	85.86 393	95.75 343

fmvsm_l_conf0.5_n_3		97.64 10	97.60 13	97.79 35	98.14 114	93.94 57	97.93 84	98.65 23	96.70 8	99.38 5	99.07 11	89.92 91	99.81 35	99.16 14	99.43 52	99.61 30

fmvsm_s_conf0.5_n_3		97.15 36	97.36 28	96.52 108	97.98 126	91.19 162	97.84 96	98.65 23	97.08 6	99.25 9	99.10 6	87.88 125	99.79 46	99.32 7	99.18 89	98.59 179

fmvsm_s_conf0.5_n_8		97.32 28	97.48 23	96.85 89	98.28 95	91.07 170	97.76 109	98.62 25	97.53 2	99.20 12	99.12 5	88.24 117	99.81 35	99.41 3	99.17 90	99.67 16

fmvsm_s_conf0.5_n_2		96.62 70	96.82 55	96.02 155	97.98 126	90.43 198	97.50 156	98.59 26	96.59 10	99.31 6	99.08 8	84.47 211	99.75 58	99.37 5	98.45 132	97.88 250

UniMVSNet_NR-MVSNet		93.37 216	92.67 225	95.47 210	95.34 337	92.83 90	97.17 204	98.58 27	92.98 149	90.13 311	95.80 285	88.37 116	97.85 360	91.71 229	83.93 423	95.73 345

CSCG		96.05 90	95.91 89	96.46 118	99.24 33	90.47 195	98.30 33	98.57 28	89.01 313	93.97 211	97.57 172	92.62 40	99.76 54	94.66 157	99.27 74	99.15 88

fmvsm_s_conf0.5_n_9		97.33 27	97.57 15	96.62 102	98.43 83	90.32 206	97.80 105	98.53 29	97.24 4	99.62 2	99.14 2	88.65 109	99.80 40	99.54 1	99.15 93	99.74 10

fmvsm_s_conf0.5_n_6		97.08 39	97.17 30	96.81 90	97.28 170	91.73 131	97.75 111	98.50 30	94.86 54	99.22 11	98.78 42	89.75 94	99.76 54	99.10 17	99.29 72	98.94 125

MSLP-MVS++		96.94 48	97.06 35	96.59 103	98.72 64	91.86 129	97.67 127	98.49 31	94.66 71	97.24 73	98.41 67	92.31 47	98.94 196	96.61 71	99.46 45	98.96 118

HyFIR lowres test		93.66 203	92.92 213	95.87 167	98.24 101	89.88 224	94.58 397	98.49 31	85.06 413	93.78 215	95.78 289	82.86 248	98.67 251	91.77 227	95.71 244	99.07 103

CHOSEN 1792x2688		94.15 177	93.51 189	96.06 150	98.27 97	89.38 250	95.18 379	98.48 33	85.60 403	93.76 216	97.11 205	83.15 238	99.61 91	91.33 237	98.72 118	99.19 83

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 214	97.29 169	88.38 294	97.23 198	98.47 34	95.14 41	98.43 41	99.09 7	87.58 133	99.72 65	98.80 25	99.21 82	98.02 241

fmvsm_s_conf0.5_n_5		97.00 45	96.97 43	97.09 80	97.58 161	92.56 102	97.68 126	98.47 34	94.02 96	98.90 26	98.89 30	88.94 103	99.78 49	99.18 12	99.03 105	98.93 129

PHI-MVS		96.77 60	96.46 76	97.71 46	98.40 87	94.07 53	98.21 48	98.45 36	89.86 282	97.11 79	98.01 106	92.52 42	99.69 73	96.03 97	99.53 32	99.36 72

fmvsm_s_conf0.1_n		96.58 73	96.77 60	96.01 158	96.67 231	90.25 208	97.91 86	98.38 37	94.48 79	98.84 29	99.14 2	88.06 120	99.62 90	98.82 23	98.60 124	98.15 226

PVSNet_BlendedMVS		94.06 183	93.92 173	94.47 273	98.27 97	89.46 247	96.73 253	98.36 38	90.17 275	94.36 196	95.24 317	88.02 121	99.58 99	93.44 189	90.72 341	94.36 428

PVSNet_Blended		94.87 150	94.56 149	95.81 174	98.27 97	89.46 247	95.47 358	98.36 38	88.84 322	94.36 196	96.09 274	88.02 121	99.58 99	93.44 189	98.18 145	98.40 202

3Dnovator	91.36 5	95.19 129	94.44 158	97.44 58	96.56 247	93.36 71	98.65 16	98.36 38	94.12 92	89.25 345	98.06 99	82.20 265	99.77 52	93.41 191	99.32 70	99.18 85

TestfortrainingZip a		97.79 7	97.62 12	98.28 10	99.56 1	95.15 24	98.69 11	98.35 41	95.63 25	98.95 19	98.95 20	93.45 23	99.88 4	96.63 69	98.41 135	99.82 1

FOURS1					99.55 4	93.34 72	99.29 1	98.35 41	94.98 48	98.49 39

DPE-MVS		97.86 5	97.65 10	98.47 5	99.17 38	95.78 8	97.21 201	98.35 41	95.16 40	98.71 35	98.80 40	95.05 11	99.89 3	96.70 68	99.73 1	99.73 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ME-MVS		97.54 17	97.39 27	98.00 25	99.21 36	94.50 36	97.75 111	98.34 44	94.23 89	98.15 47	98.53 53	93.32 28	99.84 26	97.40 49	99.58 23	99.65 21

fmvsm_s_conf0.1_n_a		96.40 79	96.47 73	96.16 143	95.48 325	90.69 189	97.91 86	98.33 45	94.07 94	98.93 21	99.14 2	87.44 141	99.61 91	98.63 26	98.32 138	98.18 222

HFP-MVS		97.14 37	96.92 47	97.83 31	99.42 10	94.12 51	98.52 20	98.32 46	93.21 131	97.18 74	98.29 84	92.08 49	99.83 31	95.63 114	99.59 19	99.54 45

ACMMPR		97.07 41	96.84 51	97.79 35	99.44 9	93.88 58	98.52 20	98.31 47	93.21 131	97.15 76	98.33 78	91.35 65	99.86 10	95.63 114	99.59 19	99.62 27

test_fmvsmvis_n_1920		96.70 65	96.84 51	96.31 130	96.62 233	91.73 131	97.98 72	98.30 48	96.19 14	96.10 126	98.95 20	89.42 95	99.76 54	98.90 22	99.08 100	97.43 277

APDe-MVS		97.82 6	97.73 9	98.08 20	99.15 39	94.82 30	98.81 8	98.30 48	94.76 66	98.30 43	98.90 27	93.77 19	99.68 75	97.93 28	99.69 3	99.75 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 6	95.36 14	98.31 32	98.29 50	94.92 52	98.99 18	98.92 25	95.08 9

MSP-MVS		97.59 13	97.54 17	97.73 43	99.40 14	93.77 62	98.53 19	98.29 50	95.55 29	98.56 38	97.81 140	93.90 17	99.65 79	96.62 70	99.21 82	99.77 4
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
DVP-MVS++		98.06 2	97.99 2	98.28 10	98.67 67	95.39 12	99.29 1	98.28 52	94.78 63	98.93 21	98.87 33	96.04 2	99.86 10	97.45 45	99.58 23	99.59 32

test_0728_SECOND				98.51 4	99.45 6	95.93 6	98.21 48	98.28 52					99.86 10	97.52 41	99.67 6	99.75 8

CP-MVS		97.02 43	96.81 56	97.64 50	99.33 26	93.54 65	98.80 9	98.28 52	92.99 144	96.45 112	98.30 83	91.90 53	99.85 21	95.61 116	99.68 4	99.54 45

test_fmvsmconf0.1_n		97.09 38	97.06 35	97.19 74	95.67 316	92.21 115	97.95 81	98.27 55	95.78 23	98.40 42	99.00 16	89.99 89	99.78 49	99.06 18	99.41 58	99.59 32

SED-MVS		98.05 3	97.99 2	98.24 12	99.42 10	95.30 18	98.25 40	98.27 55	95.13 42	99.19 13	98.89 30	95.54 5	99.85 21	97.52 41	99.66 10	99.56 40

test_241102_TWO								98.27 55	95.13 42	98.93 21	98.89 30	94.99 12	99.85 21	97.52 41	99.65 13	99.74 10

test_241102_ONE					99.42 10	95.30 18		98.27 55	95.09 45	99.19 13	98.81 39	95.54 5	99.65 79

SF-MVS		97.39 24	97.13 31	98.17 17	99.02 48	95.28 20	98.23 44	98.27 55	92.37 177	98.27 44	98.65 47	93.33 26	99.72 65	96.49 75	99.52 34	99.51 49

SteuartSystems-ACMMP		97.62 12	97.53 18	97.87 29	98.39 89	94.25 45	98.43 27	98.27 55	95.34 34	98.11 48	98.56 49	94.53 13	99.71 67	96.57 73	99.62 17	99.65 21
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 27	95.20 21		98.25 61	95.13 42	98.48 40	98.87 33	95.16 8

PVSNet_Blended_VisFu		95.27 119	94.91 129	96.38 126	98.20 108	90.86 180	97.27 192	98.25 61	90.21 274	94.18 204	97.27 194	87.48 140	99.73 61	93.53 186	97.77 161	98.55 183

region2R		97.07 41	96.84 51	97.77 39	99.46 5	93.79 60	98.52 20	98.24 63	93.19 134	97.14 77	98.34 75	91.59 60	99.87 8	95.46 122	99.59 19	99.64 25

PS-CasMVS		91.55 297	90.84 297	93.69 325	94.96 362	88.28 298	97.84 96	98.24 63	91.46 216	88.04 379	95.80 285	79.67 317	97.48 405	87.02 352	84.54 417	95.31 368

DU-MVS		92.90 238	92.04 247	95.49 207	94.95 363	92.83 90	97.16 205	98.24 63	93.02 143	90.13 311	95.71 292	83.47 229	97.85 360	91.71 229	83.93 423	95.78 339

9.14			96.75 61		98.93 56		97.73 116	98.23 66	91.28 226	97.88 56	98.44 64	93.00 30	99.65 79	95.76 106	99.47 44

reproduce_model		97.51 20	97.51 20	97.50 55	98.99 52	93.01 83	97.79 107	98.21 67	95.73 24	97.99 52	99.03 15	92.63 39	99.82 33	97.80 30	99.42 55	99.67 16

D2MVS		91.30 314	90.95 291	92.35 380	94.71 378	85.52 381	96.18 312	98.21 67	88.89 320	86.60 408	93.82 390	79.92 313	97.95 349	89.29 288	90.95 338	93.56 444

reproduce-ours		97.53 18	97.51 20	97.60 52	98.97 53	93.31 74	97.71 122	98.20 69	95.80 21	97.88 56	98.98 18	92.91 31	99.81 35	97.68 32	99.43 52	99.67 16

our_new_method		97.53 18	97.51 20	97.60 52	98.97 53	93.31 74	97.71 122	98.20 69	95.80 21	97.88 56	98.98 18	92.91 31	99.81 35	97.68 32	99.43 52	99.67 16

SDMVSNet		94.17 174	93.61 182	95.86 170	98.09 117	91.37 152	97.35 180	98.20 69	93.18 136	91.79 271	97.28 192	79.13 326	98.93 197	94.61 160	92.84 304	97.28 285

XVS		97.18 34	96.96 45	97.81 33	99.38 17	94.03 55	98.59 17	98.20 69	94.85 55	96.59 100	98.29 84	91.70 56	99.80 40	95.66 109	99.40 60	99.62 27

X-MVStestdata		91.71 284	89.67 353	97.81 33	99.38 17	94.03 55	98.59 17	98.20 69	94.85 55	96.59 100	32.69 545	91.70 56	99.80 40	95.66 109	99.40 60	99.62 27

ACMMP_NAP		97.20 33	96.86 49	98.23 13	99.09 40	95.16 23	97.60 142	98.19 74	92.82 159	97.93 55	98.74 44	91.60 59	99.86 10	96.26 80	99.52 34	99.67 16

CP-MVSNet		91.89 280	91.24 279	93.82 317	95.05 359	88.57 285	97.82 101	98.19 74	91.70 205	88.21 374	95.76 290	81.96 270	97.52 403	87.86 317	84.65 411	95.37 364

ZNCC-MVS		96.96 46	96.67 64	97.85 30	99.37 19	94.12 51	98.49 24	98.18 76	92.64 167	96.39 114	98.18 91	91.61 58	99.88 4	95.59 119	99.55 29	99.57 36

SMA-MVS		97.35 25	97.03 40	98.30 9	99.06 44	95.42 11	97.94 82	98.18 76	90.57 265	98.85 28	98.94 23	93.33 26	99.83 31	96.72 66	99.68 4	99.63 26
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
PEN-MVS		91.20 319	90.44 316	93.48 343	94.49 386	87.91 318	97.76 109	98.18 76	91.29 223	87.78 383	95.74 291	80.35 304	97.33 417	85.46 376	82.96 433	95.19 379

DELS-MVS		96.61 71	96.38 80	97.30 64	97.79 140	93.19 79	95.96 327	98.18 76	95.23 37	95.87 136	97.65 160	91.45 61	99.70 72	95.87 100	99.44 51	99.00 112
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
tfpnnormal		89.70 372	88.40 378	93.60 334	95.15 354	90.10 212	97.56 147	98.16 80	87.28 375	86.16 415	94.63 345	77.57 354	98.05 329	74.48 467	84.59 415	92.65 458

VNet		95.89 98	95.45 101	97.21 72	98.07 121	92.94 86	97.50 156	98.15 81	93.87 102	97.52 63	97.61 167	85.29 194	99.53 113	95.81 105	95.27 257	99.16 86

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 225	98.09 117	86.63 353	96.00 325	98.15 81	95.43 30	97.95 54	98.56 49	93.40 24	99.36 138	96.77 63	99.48 43	99.45 59

SD-MVS		97.41 23	97.53 18	97.06 83	98.57 78	94.46 39	97.92 85	98.14 83	94.82 59	99.01 17	98.55 51	94.18 15	97.41 412	96.94 58	99.64 14	99.32 74
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
GST-MVS		96.85 54	96.52 70	97.82 32	99.36 23	94.14 50	98.29 34	98.13 84	92.72 162	96.70 92	98.06 99	91.35 65	99.86 10	94.83 145	99.28 73	99.47 58

UA-Net		95.95 95	95.53 97	97.20 73	97.67 147	92.98 85	97.65 131	98.13 84	94.81 61	96.61 98	98.35 72	88.87 104	99.51 118	90.36 263	97.35 177	99.11 96

QAPM		93.45 214	92.27 241	96.98 86	96.77 224	92.62 99	98.39 29	98.12 86	84.50 421	88.27 372	97.77 145	82.39 262	99.81 35	85.40 377	98.81 113	98.51 188

Vis-MVSNet		95.23 124	94.81 135	96.51 112	97.18 175	91.58 142	98.26 39	98.12 86	94.38 86	94.90 179	98.15 94	82.28 263	98.92 199	91.45 236	98.58 126	99.01 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 241	91.68 262	96.40 123	95.34 337	92.73 95	98.27 37	98.12 86	84.86 416	85.78 424	97.75 146	78.89 336	99.74 59	87.50 340	98.65 121	96.73 304

TranMVSNet+NR-MVSNet		92.50 250	91.63 263	95.14 226	94.76 374	92.07 120	97.53 153	98.11 89	92.90 155	89.56 333	96.12 269	83.16 237	97.60 389	89.30 287	83.20 432	95.75 343

CPTT-MVS		95.57 109	95.19 114	96.70 93	99.27 31	91.48 147	98.33 31	98.11 89	87.79 359	95.17 168	98.03 103	87.09 149	99.61 91	93.51 187	99.42 55	99.02 106

APD-MVS		96.95 47	96.60 66	98.01 23	99.03 47	94.93 29	97.72 119	98.10 91	91.50 214	98.01 51	98.32 80	92.33 45	99.58 99	94.85 142	99.51 37	99.53 48
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 52	96.60 66	97.64 50	99.40 14	93.44 67	98.50 23	98.09 92	93.27 130	95.95 134	98.33 78	91.04 73	99.88 4	95.20 127	99.57 28	99.60 31

ZD-MVS					99.05 45	94.59 34		98.08 93	89.22 306	97.03 82	98.10 95	92.52 42	99.65 79	94.58 162	99.31 71

MTGPA								98.08 93

MTAPA		97.08 39	96.78 59	97.97 28	99.37 19	94.42 41	97.24 194	98.08 93	95.07 46	96.11 125	98.59 48	90.88 79	99.90 2	96.18 92	99.50 39	99.58 35

CNVR-MVS		97.68 8	97.44 24	98.37 7	98.90 59	95.86 7	97.27 192	98.08 93	95.81 20	97.87 59	98.31 81	94.26 14	99.68 75	97.02 57	99.49 42	99.57 36

DP-MVS Recon		95.68 103	95.12 119	97.37 61	99.19 37	94.19 47	97.03 212	98.08 93	88.35 340	95.09 170	97.65 160	89.97 90	99.48 125	92.08 221	98.59 125	98.44 199

SR-MVS		97.01 44	96.86 49	97.47 57	99.09 40	93.27 76	97.98 72	98.07 98	93.75 106	97.45 65	98.48 61	91.43 63	99.59 96	96.22 83	99.27 74	99.54 45

MCST-MVS		97.18 34	96.84 51	98.20 16	99.30 29	95.35 16	97.12 208	98.07 98	93.54 117	96.08 127	97.69 155	93.86 18	99.71 67	96.50 74	99.39 62	99.55 43

NR-MVSNet		92.34 259	91.27 278	95.53 199	94.95 363	93.05 82	97.39 176	98.07 98	92.65 165	84.46 436	95.71 292	85.00 201	97.77 371	89.71 275	83.52 429	95.78 339

MP-MVS-pluss		96.70 65	96.27 83	97.98 27	99.23 35	94.71 31	96.96 223	98.06 101	90.67 255	95.55 152	98.78 42	91.07 72	99.86 10	96.58 72	99.55 29	99.38 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 58	96.71 63	97.12 77	99.01 51	92.31 111	97.98 72	98.06 101	93.11 140	97.44 66	98.55 51	90.93 77	99.55 109	96.06 93	99.25 79	99.51 49

MP-MVS		96.77 60	96.45 77	97.72 44	99.39 16	93.80 59	98.41 28	98.06 101	93.37 126	95.54 154	98.34 75	90.59 83	99.88 4	94.83 145	99.54 31	99.49 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 74	96.27 83	97.22 71	99.32 27	92.74 94	98.74 10	98.06 101	90.57 265	96.77 89	98.35 72	90.21 86	99.53 113	94.80 149	99.63 16	99.38 70

HPM-MVS		96.69 67	96.45 77	97.40 60	99.36 23	93.11 81	98.87 6	98.06 101	91.17 234	96.40 113	97.99 109	90.99 74	99.58 99	95.61 116	99.61 18	99.49 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 165	93.80 175	96.64 95	97.07 182	91.97 125	96.32 297	98.06 101	88.94 318	94.50 193	96.78 226	84.60 208	99.27 148	91.90 222	96.02 233	98.68 173

DeepC-MVS	93.07 3	96.06 89	95.66 93	97.29 65	97.96 128	93.17 80	97.30 186	98.06 101	93.92 100	93.38 231	98.66 45	86.83 152	99.73 61	95.60 118	99.22 81	98.96 118
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 29	97.03 40	98.11 19	98.77 62	95.06 27	97.34 181	98.04 108	95.96 15	97.09 80	97.88 127	93.18 29	99.71 67	95.84 104	99.17 90	99.56 40

DeepC-MVS_fast	93.89 2	96.93 49	96.64 65	97.78 37	98.64 73	94.30 42	97.41 171	98.04 108	94.81 61	96.59 100	98.37 70	91.24 68	99.64 87	95.16 129	99.52 34	99.42 65
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 51	96.80 57	97.11 79	99.02 48	92.34 109	97.98 72	98.03 110	93.52 120	97.43 68	98.51 56	91.40 64	99.56 107	96.05 94	99.26 77	99.43 63

RE-MVS-def			96.72 62		99.02 48	92.34 109	97.98 72	98.03 110	93.52 120	97.43 68	98.51 56	90.71 81		96.05 94	99.26 77	99.43 63

RPMNet		88.98 378	87.05 392	94.77 253	94.45 388	87.19 336	90.23 482	98.03 110	77.87 481	92.40 249	87.55 483	80.17 308	99.51 118	68.84 489	93.95 290	97.60 270

save fliter					98.91 58	94.28 43	97.02 214	98.02 113	95.35 33

TEST9					98.70 65	94.19 47	96.41 283	98.02 113	88.17 344	96.03 128	97.56 174	92.74 36	99.59 96

train_agg		96.30 85	95.83 92	97.72 44	98.70 65	94.19 47	96.41 283	98.02 113	88.58 331	96.03 128	97.56 174	92.73 37	99.59 96	95.04 131	99.37 66	99.39 68

test_8					98.67 67	94.06 54	96.37 291	98.01 116	88.58 331	95.98 133	97.55 176	92.73 37	99.58 99

fmvsm_s_conf0.5_n_11		97.30 29	97.59 14	96.43 120	98.42 84	91.37 152	98.04 64	98.00 117	97.30 3	99.45 4	99.21 1	89.28 97	99.80 40	99.27 10	99.35 68	98.12 229

agg_prior					98.67 67	93.79 60		98.00 117		95.68 146			99.57 106

test_prior				97.23 70	98.67 67	92.99 84		98.00 117					99.41 133			99.29 75

WR-MVS		92.34 259	91.53 267	94.77 253	95.13 356	90.83 181	96.40 287	97.98 120	91.88 200	89.29 342	95.54 303	82.50 258	97.80 367	89.79 274	85.27 402	95.69 346

HPM-MVS++		97.34 26	96.97 43	98.47 5	99.08 42	96.16 5	97.55 152	97.97 121	95.59 27	96.61 98	97.89 122	92.57 41	99.84 26	95.95 99	99.51 37	99.40 66

CANet		96.39 80	96.02 87	97.50 55	97.62 154	93.38 69	97.02 214	97.96 122	95.42 31	94.86 180	97.81 140	87.38 143	99.82 33	96.88 60	99.20 87	99.29 75

114514_t		93.95 190	93.06 207	96.63 99	99.07 43	91.61 139	97.46 167	97.96 122	77.99 479	93.00 240	97.57 172	86.14 170	99.33 140	89.22 291	99.15 93	98.94 125

IU-MVS					99.42 10	95.39 12		97.94 124	90.40 272	98.94 20				97.41 48	99.66 10	99.74 10

MSC_two_6792asdad				98.86 1	98.67 67	96.94 1		97.93 125					99.86 10	97.68 32	99.67 6	99.77 4

No_MVS				98.86 1	98.67 67	96.94 1		97.93 125					99.86 10	97.68 32	99.67 6	99.77 4

fmvsm_s_conf0.1_n_2		96.33 84	96.44 79	96.00 159	97.30 168	90.37 204	97.53 153	97.92 127	96.52 11	99.14 15	99.08 8	83.21 235	99.74 59	99.22 11	98.06 150	97.88 250

Anonymous20231211		90.63 344	89.42 360	94.27 288	98.24 101	89.19 262	98.05 63	97.89 128	79.95 470	88.25 373	94.96 326	72.56 400	98.13 312	89.70 276	85.14 404	95.49 350

原ACMM1				96.38 126	98.59 75	91.09 169		97.89 128	87.41 371	95.22 167	97.68 156	90.25 85	99.54 111	87.95 316	99.12 98	98.49 191

CDPH-MVS		95.97 94	95.38 107	97.77 39	98.93 56	94.44 40	96.35 292	97.88 130	86.98 379	96.65 96	97.89 122	91.99 51	99.47 126	92.26 210	99.46 45	99.39 68

test11								97.88 130

EIA-MVS		95.53 111	95.47 100	95.71 189	97.06 185	89.63 234	97.82 101	97.87 132	93.57 113	93.92 213	95.04 323	90.61 82	98.95 194	94.62 159	98.68 119	98.54 184

CS-MVS		96.86 52	97.06 35	96.26 136	98.16 113	91.16 167	99.09 3	97.87 132	95.30 35	97.06 81	98.03 103	91.72 54	98.71 244	97.10 55	99.17 90	98.90 134

无先验							95.79 339	97.87 132	83.87 431				99.65 79	87.68 330		98.89 140

3Dnovator+	91.43 4	95.40 113	94.48 156	98.16 18	96.90 203	95.34 17	98.48 25	97.87 132	94.65 72	88.53 364	98.02 105	83.69 225	99.71 67	93.18 195	98.96 108	99.44 61

VPNet		92.23 267	91.31 275	94.99 236	95.56 321	90.96 173	97.22 200	97.86 136	92.96 150	90.96 294	96.62 243	75.06 375	98.20 305	91.90 222	83.65 428	95.80 337

TestfortrainingZip				98.34 8	98.54 79	96.25 4	98.69 11	97.85 137	94.15 91	98.17 46	97.94 113	94.00 16	99.63 88		97.45 173	99.15 88

test_vis1_n_1920		94.17 174	94.58 148	92.91 364	97.42 166	82.02 435	97.83 99	97.85 137	94.68 69	98.10 49	98.49 58	70.15 421	99.32 142	97.91 29	98.82 112	97.40 279

DVP-MVS		97.91 4	97.81 5	98.22 15	99.45 6	95.36 14	98.21 48	97.85 137	94.92 52	98.73 31	98.87 33	95.08 9	99.84 26	97.52 41	99.67 6	99.48 56
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
TSAR-MVS + MP.		97.42 22	97.33 29	97.69 47	99.25 32	94.24 46	98.07 61	97.85 137	93.72 107	98.57 37	98.35 72	93.69 20	99.40 134	97.06 56	99.46 45	99.44 61
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		96.89 50	97.04 39	96.45 119	98.29 94	91.66 138	99.03 4	97.85 137	95.84 18	96.90 84	97.97 111	91.24 68	98.75 233	96.92 59	99.33 69	98.94 125

test_fmvsmconf0.01_n		96.15 88	95.85 91	97.03 84	92.66 442	91.83 130	97.97 78	97.84 142	95.57 28	97.53 62	99.00 16	84.20 218	99.76 54	98.82 23	99.08 100	99.48 56

GDP-MVS		95.62 106	95.13 117	97.09 80	96.79 217	93.26 77	97.89 89	97.83 143	93.58 112	96.80 86	97.82 138	83.06 242	99.16 163	94.40 166	97.95 156	98.87 145

BridgeMVS		96.84 56	96.89 48	96.68 94	97.63 153	92.22 114	98.17 54	97.82 144	94.44 81	98.23 45	97.36 187	90.97 75	99.22 153	97.74 31	99.66 10	98.61 177

AdaColmap		94.34 169	93.68 180	96.31 130	98.59 75	91.68 137	96.59 272	97.81 145	89.87 281	92.15 259	97.06 209	83.62 228	99.54 111	89.34 286	98.07 149	97.70 263

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 103	98.07 121	91.97 125	98.14 55	97.79 146	90.43 270	97.34 71	97.52 177	91.29 67	99.19 156	98.12 27	99.64 14	98.60 178

KinetiMVS		95.26 120	94.75 141	96.79 91	96.99 195	92.05 121	97.82 101	97.78 147	94.77 65	96.46 110	97.70 153	80.62 298	99.34 139	92.37 209	98.28 140	98.97 115

ETV-MVS		96.02 91	95.89 90	96.40 123	97.16 176	92.44 106	97.47 165	97.77 148	94.55 75	96.48 108	94.51 351	91.23 70	98.92 199	95.65 112	98.19 144	97.82 258

新几何1				97.32 63	98.60 74	93.59 64		97.75 149	81.58 461	95.75 141	97.85 132	90.04 88	99.67 77	86.50 358	99.13 96	98.69 172

旧先验1					98.38 90	93.38 69		97.75 149			98.09 97	92.30 48			99.01 106	99.16 86

EC-MVSNet		96.42 78	96.47 73	96.26 136	97.01 193	91.52 144	98.89 5	97.75 149	94.42 82	96.64 97	97.68 156	89.32 96	98.60 266	97.45 45	99.11 99	98.67 174

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 99	98.24 101	91.20 161	96.89 231	97.73 152	94.74 67	96.49 107	98.49 58	90.88 79	99.58 99	96.44 76	98.32 138	99.13 91

PAPM_NR		95.01 140	94.59 147	96.26 136	98.89 60	90.68 190	97.24 194	97.73 152	91.80 201	92.93 245	96.62 243	89.13 100	99.14 168	89.21 292	97.78 160	98.97 115

Anonymous20240529		91.98 276	90.73 304	95.73 187	98.14 114	89.40 249	97.99 69	97.72 154	79.63 472	93.54 224	97.41 184	69.94 423	99.56 107	91.04 244	91.11 334	98.22 219

CHOSEN 280x420		93.12 226	92.72 224	94.34 281	96.71 230	87.27 332	90.29 481	97.72 154	86.61 387	91.34 283	95.29 311	84.29 217	98.41 282	93.25 193	98.94 109	97.35 282

EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 116	98.20 108	90.93 177	96.86 234	97.72 154	94.67 70	96.16 124	98.46 62	90.43 84	99.58 99	96.23 82	97.96 155	98.90 134

LS3D		93.57 207	92.61 229	96.47 116	97.59 157	91.61 139	97.67 127	97.72 154	85.17 411	90.29 305	98.34 75	84.60 208	99.73 61	83.85 400	98.27 141	98.06 239

PAPR		94.18 173	93.42 196	96.48 115	97.64 151	91.42 151	95.55 353	97.71 158	88.99 315	92.34 255	95.82 284	89.19 98	99.11 171	86.14 364	97.38 175	98.90 134

UGNet		94.04 185	93.28 199	96.31 130	96.85 208	91.19 162	97.88 91	97.68 159	94.40 84	93.00 240	96.18 264	73.39 394	99.61 91	91.72 228	98.46 131	98.13 227
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
testdata				95.46 211	98.18 112	88.90 274		97.66 160	82.73 450	97.03 82	98.07 98	90.06 87	98.85 206	89.67 277	98.98 107	98.64 175

test12				97.65 48	98.46 80	94.26 44		97.66 160		95.52 155		90.89 78	99.46 127		99.25 79	99.22 82

DTE-MVSNet		90.56 345	89.75 351	93.01 360	93.95 401	87.25 333	97.64 135	97.65 162	90.74 250	87.12 396	95.68 295	79.97 312	97.00 430	83.33 401	81.66 439	94.78 414

TAPA-MVS	90.10 7	92.30 262	91.22 281	95.56 196	98.33 92	89.60 236	96.79 245	97.65 162	81.83 458	91.52 277	97.23 197	87.94 123	98.91 201	71.31 482	98.37 136	98.17 225
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 227	92.45 237	95.05 230	98.09 117	89.21 259	96.89 231	97.64 164	93.18 136	91.79 271	97.28 192	75.35 374	98.65 256	88.99 298	92.84 304	97.28 285

test_cas_vis1_n_1920		94.48 167	94.55 152	94.28 287	96.78 222	86.45 359	97.63 137	97.64 164	93.32 129	97.68 61	98.36 71	73.75 390	99.08 178	96.73 65	99.05 102	97.31 284

NormalMVS		96.36 82	96.11 86	97.12 77	99.37 19	92.90 88	97.99 69	97.63 166	95.92 16	96.57 103	97.93 114	85.34 192	99.50 121	94.99 134	99.21 82	98.97 115

Elysia		94.00 187	93.12 204	96.64 95	96.08 300	92.72 96	97.50 156	97.63 166	91.15 236	94.82 181	97.12 203	74.98 377	99.06 184	90.78 249	98.02 151	98.12 229

StellarMVS		94.00 187	93.12 204	96.64 95	96.08 300	92.72 96	97.50 156	97.63 166	91.15 236	94.82 181	97.12 203	74.98 377	99.06 184	90.78 249	98.02 151	98.12 229

cdsmvs_eth3d_5k		23.24 509	30.99 502	0.00 534	0.00 557	0.00 559	0.00 545	97.63 166	0.00 552	0.00 553	96.88 222	84.38 213	0.00 553	0.00 551	0.00 551	0.00 549

DPM-MVS		95.69 102	94.92 128	98.01 23	98.08 120	95.71 10	95.27 370	97.62 170	90.43 270	95.55 152	97.07 208	91.72 54	99.50 121	89.62 279	98.94 109	98.82 153

sasdasda		96.02 91	95.45 101	97.75 41	97.59 157	95.15 24	98.28 35	97.60 171	94.52 77	96.27 119	96.12 269	87.65 130	99.18 159	96.20 88	94.82 266	98.91 131

canonicalmvs		96.02 91	95.45 101	97.75 41	97.59 157	95.15 24	98.28 35	97.60 171	94.52 77	96.27 119	96.12 269	87.65 130	99.18 159	96.20 88	94.82 266	98.91 131

test222					98.24 101	92.21 115	95.33 365	97.60 171	79.22 474	95.25 164	97.84 134	88.80 106			99.15 93	98.72 169

cascas		91.20 319	90.08 333	94.58 266	94.97 361	89.16 263	93.65 440	97.59 174	79.90 471	89.40 337	92.92 420	75.36 373	98.36 290	92.14 215	94.75 269	96.23 316

E2		95.20 126	95.00 125	95.79 178	96.79 217	89.66 231	96.82 240	97.58 175	92.35 178	95.28 162	97.83 136	86.68 155	98.76 227	94.79 152	96.92 196	98.95 122

E3		95.20 126	95.00 125	95.79 178	96.77 224	89.66 231	96.82 240	97.58 175	92.35 178	95.28 162	97.83 136	86.69 154	98.76 227	94.79 152	96.92 196	98.95 122

h-mvs33		94.15 177	93.52 188	96.04 152	97.81 139	90.22 209	97.62 140	97.58 175	95.19 38	96.74 90	97.45 180	83.67 226	99.61 91	95.85 102	79.73 447	98.29 215

E5new		95.04 136	94.88 130	95.52 200	96.62 233	89.02 267	97.29 187	97.57 178	92.54 168	95.04 171	97.89 122	85.65 182	98.77 221	94.92 137	96.44 224	98.78 157

E6new		95.04 136	94.88 130	95.52 200	96.60 238	89.02 267	97.29 187	97.57 178	92.54 168	95.04 171	97.90 120	85.66 180	98.77 221	94.92 137	96.44 224	98.78 157

E6		95.04 136	94.88 130	95.52 200	96.60 238	89.02 267	97.29 187	97.57 178	92.54 168	95.04 171	97.90 120	85.66 180	98.77 221	94.92 137	96.44 224	98.78 157

E5		95.04 136	94.88 130	95.52 200	96.62 233	89.02 267	97.29 187	97.57 178	92.54 168	95.04 171	97.89 122	85.65 182	98.77 221	94.92 137	96.44 224	98.78 157

MGCFI-Net		95.94 96	95.40 105	97.56 54	97.59 157	94.62 33	98.21 48	97.57 178	94.41 83	96.17 123	96.16 267	87.54 135	99.17 161	96.19 90	94.73 271	98.91 131

MVSFormer		95.37 114	95.16 115	95.99 160	96.34 272	91.21 159	98.22 46	97.57 178	91.42 218	96.22 121	97.32 188	86.20 168	97.92 354	94.07 172	99.05 102	98.85 147

test_djsdf		93.07 229	92.76 219	94.00 302	93.49 420	88.70 279	98.22 46	97.57 178	91.42 218	90.08 317	95.55 302	82.85 249	97.92 354	94.07 172	91.58 325	95.40 361

OMC-MVS		95.09 133	94.70 142	96.25 139	98.46 80	91.28 155	96.43 279	97.57 178	92.04 196	94.77 186	97.96 112	87.01 150	99.09 176	91.31 238	96.77 204	98.36 206

E4		95.09 133	94.86 134	95.77 181	96.58 242	89.56 239	96.85 235	97.56 186	92.50 172	95.03 175	97.86 130	86.03 171	98.78 217	94.71 155	96.65 214	98.96 118

viewcassd2359sk11		95.26 120	95.09 121	95.80 175	96.95 199	89.72 230	96.80 244	97.56 186	92.21 186	95.37 160	97.80 142	87.17 148	98.77 221	94.82 147	97.10 190	98.90 134

PS-MVSNAJss		93.74 200	93.51 189	94.44 275	93.91 403	89.28 257	97.75 111	97.56 186	92.50 172	89.94 319	96.54 247	88.65 109	98.18 308	93.83 181	90.90 339	95.86 331

casdiffmvs_mvg		95.81 101	95.57 94	96.51 112	96.87 205	91.49 145	97.50 156	97.56 186	93.99 98	95.13 169	97.92 117	87.89 124	98.78 217	95.97 98	97.33 178	99.26 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
cashybrid2		95.67 104	95.55 95	96.03 154	96.95 199	90.12 211	97.72 119	97.55 190	94.10 93	95.23 165	98.18 91	87.32 144	98.80 215	95.40 123	97.52 167	99.19 83

E3new		95.28 118	95.11 120	95.80 175	97.03 190	89.76 228	96.78 249	97.54 191	92.06 195	95.40 158	97.75 146	87.49 139	98.76 227	94.85 142	97.10 190	98.88 142

jajsoiax		92.42 255	91.89 255	94.03 301	93.33 428	88.50 290	97.73 116	97.53 192	92.00 198	88.85 356	96.50 249	75.62 372	98.11 316	93.88 179	91.56 326	95.48 351

mvs_tets		92.31 261	91.76 258	93.94 310	93.41 425	88.29 297	97.63 137	97.53 192	92.04 196	88.76 359	96.45 251	74.62 382	98.09 321	93.91 177	91.48 327	95.45 356

dcpmvs_2		96.37 81	97.05 38	94.31 285	98.96 55	84.11 408	97.56 147	97.51 194	93.92 100	97.43 68	98.52 55	92.75 35	99.32 142	97.32 54	99.50 39	99.51 49

HQP_MVS		93.78 199	93.43 194	94.82 246	96.21 279	89.99 217	97.74 114	97.51 194	94.85 55	91.34 283	96.64 236	81.32 282	98.60 266	93.02 201	92.23 313	95.86 331

plane_prior5								97.51 194					98.60 266	93.02 201	92.23 313	95.86 331

hybridcas		95.46 112	95.29 110	95.96 162	96.83 211	90.08 213	97.63 137	97.49 197	93.76 105	94.79 184	98.04 101	86.87 151	98.72 242	94.71 155	97.53 166	99.08 100

viewmanbaseed2359cas		95.24 123	95.02 123	95.91 164	96.87 205	89.98 219	96.82 240	97.49 197	92.26 182	95.47 156	97.82 138	86.47 160	98.69 246	94.80 149	97.20 186	99.06 104

reproduce_monomvs		91.30 314	91.10 286	91.92 394	96.82 214	82.48 429	97.01 217	97.49 197	94.64 73	88.35 367	95.27 314	70.53 416	98.10 317	95.20 127	84.60 414	95.19 379

viewmacassd2359aftdt		95.07 135	94.80 136	95.87 167	96.53 252	89.84 225	96.90 230	97.48 200	92.44 174	95.36 161	97.89 122	85.23 195	98.68 248	94.40 166	97.00 194	99.09 98

PS-MVSNAJ		95.37 114	95.33 109	95.49 207	97.35 167	90.66 191	95.31 367	97.48 200	93.85 103	96.51 106	95.70 294	88.65 109	99.65 79	94.80 149	98.27 141	96.17 320

API-MVS		94.84 152	94.49 155	95.90 165	97.90 134	92.00 124	97.80 105	97.48 200	89.19 307	94.81 183	96.71 229	88.84 105	99.17 161	88.91 301	98.76 117	96.53 309

MG-MVS		95.61 107	95.38 107	96.31 130	98.42 84	90.53 193	96.04 321	97.48 200	93.47 122	95.67 147	98.10 95	89.17 99	99.25 150	91.27 239	98.77 116	99.13 91

MAR-MVS		94.22 172	93.46 191	96.51 112	98.00 125	92.19 118	97.67 127	97.47 204	88.13 348	93.00 240	95.84 282	84.86 206	99.51 118	87.99 315	98.17 146	97.83 257
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
CLD-MVS		92.98 233	92.53 233	94.32 283	96.12 295	89.20 260	95.28 368	97.47 204	92.66 164	89.90 320	95.62 298	80.58 299	98.40 283	92.73 206	92.40 311	95.38 363
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 312	90.22 329	94.68 258	94.86 370	87.86 319	97.23 198	97.46 206	87.99 349	89.90 320	96.92 220	66.35 451	98.23 302	90.30 264	90.99 337	97.96 244

nrg030		94.05 184	93.31 198	96.27 135	95.22 348	94.59 34	98.34 30	97.46 206	92.93 151	91.21 292	96.64 236	87.23 147	98.22 303	94.99 134	85.80 394	95.98 330

XVG-OURS		93.72 201	93.35 197	94.80 251	97.07 182	88.61 283	94.79 392	97.46 206	91.97 199	93.99 209	97.86 130	81.74 276	98.88 203	92.64 207	92.67 309	96.92 299

LPG-MVS_test		92.94 236	92.56 230	94.10 296	96.16 290	88.26 299	97.65 131	97.46 206	91.29 223	90.12 313	97.16 200	79.05 329	98.73 237	92.25 212	91.89 321	95.31 368

LGP-MVS_train				94.10 296	96.16 290	88.26 299		97.46 206	91.29 223	90.12 313	97.16 200	79.05 329	98.73 237	92.25 212	91.89 321	95.31 368

MVS		91.71 284	90.44 316	95.51 204	95.20 350	91.59 141	96.04 321	97.45 211	73.44 489	87.36 392	95.60 299	85.42 191	99.10 173	85.97 369	97.46 169	95.83 335

XVG-OURS-SEG-HR		93.86 196	93.55 184	94.81 248	97.06 185	88.53 289	95.28 368	97.45 211	91.68 206	94.08 208	97.68 156	82.41 261	98.90 202	93.84 180	92.47 310	96.98 294

baseline		95.58 108	95.42 104	96.08 147	96.78 222	90.41 199	97.16 205	97.45 211	93.69 110	95.65 148	97.85 132	87.29 145	98.68 248	95.66 109	97.25 184	99.13 91

ab-mvs		93.57 207	92.55 231	96.64 95	97.28 170	91.96 127	95.40 361	97.45 211	89.81 286	93.22 237	96.28 260	79.62 320	99.46 127	90.74 252	93.11 301	98.50 189

xiu_mvs_v2_base		95.32 117	95.29 110	95.40 213	97.22 172	90.50 194	95.44 360	97.44 215	93.70 109	96.46 110	96.18 264	88.59 113	99.53 113	94.79 152	97.81 159	96.17 320

1314		92.81 245	92.03 248	95.14 226	95.33 340	89.52 244	96.04 321	97.44 215	87.72 363	86.25 413	95.33 310	83.84 223	98.79 216	89.26 289	97.05 193	97.11 292

casdiffmvs		95.64 105	95.49 98	96.08 147	96.76 228	90.45 196	97.29 187	97.44 215	94.00 97	95.46 157	97.98 110	87.52 138	98.73 237	95.64 113	97.33 178	99.08 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt07		94.76 158	94.68 143	95.01 234	96.76 228	87.41 328	96.38 289	97.43 218	92.65 165	94.52 192	97.75 146	85.55 188	98.81 212	94.36 168	96.69 211	98.82 153

XXY-MVS		92.16 269	91.23 280	94.95 242	94.75 375	90.94 176	97.47 165	97.43 218	89.14 308	88.90 352	96.43 252	79.71 316	98.24 301	89.56 280	87.68 375	95.67 347

anonymousdsp		92.16 269	91.55 266	93.97 306	92.58 444	89.55 241	97.51 155	97.42 220	89.42 301	88.40 366	94.84 333	80.66 297	97.88 359	91.87 224	91.28 331	94.48 423

Effi-MVS+		94.93 145	94.45 157	96.36 128	96.61 236	91.47 148	96.41 283	97.41 221	91.02 242	94.50 193	95.92 278	87.53 136	98.78 217	93.89 178	96.81 203	98.84 151

RRT-MVS		94.51 165	94.35 161	94.98 238	96.40 265	86.55 356	97.56 147	97.41 221	93.19 134	94.93 178	97.04 210	79.12 327	99.30 146	96.19 90	97.32 180	99.09 98

casdiffseed414692147		94.55 163	94.02 169	96.15 144	96.61 236	90.79 183	97.42 169	97.39 223	92.18 191	93.95 212	97.64 163	84.37 214	98.66 254	90.68 254	95.91 237	99.00 112

HQP3-MVS								97.39 223							92.10 318

HQP-MVS		93.19 223	92.74 222	94.54 269	95.86 306	89.33 253	96.65 263	97.39 223	93.55 114	90.14 307	95.87 280	80.95 288	98.50 276	92.13 218	92.10 318	95.78 339

PLC	91.00 6	94.11 181	93.43 194	96.13 145	98.58 77	91.15 168	96.69 259	97.39 223	87.29 374	91.37 281	96.71 229	88.39 114	99.52 117	87.33 345	97.13 189	97.73 261
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
diffmvs_AUTHOR		95.33 116	95.27 112	95.50 206	96.37 270	89.08 265	96.08 318	97.38 227	93.09 142	96.53 105	97.74 149	86.45 161	98.68 248	96.32 78	97.48 168	98.75 165

v7n		90.76 337	89.86 344	93.45 345	93.54 417	87.60 326	97.70 125	97.37 228	88.85 321	87.65 385	94.08 381	81.08 287	98.10 317	84.68 386	83.79 427	94.66 420

UnsupCasMVSNet_eth		85.99 425	84.45 427	90.62 430	89.97 468	82.40 432	93.62 441	97.37 228	89.86 282	78.59 479	92.37 430	65.25 463	95.35 466	82.27 415	70.75 487	94.10 434

viewdifsd2359ckpt13		94.87 150	94.52 153	95.90 165	96.88 204	90.19 210	96.92 227	97.36 230	91.26 227	94.65 188	97.46 179	85.79 177	98.64 258	93.64 184	96.76 205	98.88 142

ACMM	89.79 8	92.96 234	92.50 235	94.35 279	96.30 275	88.71 278	97.58 143	97.36 230	91.40 220	90.53 300	96.65 235	79.77 315	98.75 233	91.24 240	91.64 323	95.59 349
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 140	94.76 138	95.75 184	96.58 242	91.71 134	96.25 304	97.35 232	92.99 144	96.70 92	96.63 240	82.67 253	99.44 130	96.22 83	97.46 169	96.11 326

xiu_mvs_v1_base		95.01 140	94.76 138	95.75 184	96.58 242	91.71 134	96.25 304	97.35 232	92.99 144	96.70 92	96.63 240	82.67 253	99.44 130	96.22 83	97.46 169	96.11 326

xiu_mvs_v1_base_debi		95.01 140	94.76 138	95.75 184	96.58 242	91.71 134	96.25 304	97.35 232	92.99 144	96.70 92	96.63 240	82.67 253	99.44 130	96.22 83	97.46 169	96.11 326

diffmvs		95.25 122	95.13 117	95.63 192	96.43 264	89.34 252	95.99 326	97.35 232	92.83 158	96.31 117	97.37 186	86.44 162	98.67 251	96.26 80	97.19 187	98.87 145
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 161	94.02 169	96.79 91	97.71 145	92.05 121	96.59 272	97.35 232	90.61 261	94.64 189	96.93 217	86.41 163	99.39 135	91.20 241	94.71 272	98.94 125

viewdifsd2359ckpt09		94.81 155	94.37 160	96.12 146	96.91 201	90.75 187	96.94 224	97.31 237	90.51 268	94.31 198	97.38 185	85.70 179	98.71 244	93.54 185	96.75 206	98.90 134

balanced_ft_v1		95.56 110	95.40 105	96.07 149	97.16 176	90.36 205	98.23 44	97.31 237	92.89 156	96.36 115	97.11 205	83.28 233	99.26 149	97.40 49	98.80 114	98.58 180

SSM_0407		94.54 164	94.12 168	95.80 175	96.79 217	90.38 201	96.79 245	97.29 239	91.24 228	93.68 217	97.60 168	85.03 199	98.67 251	92.14 215	96.51 217	98.35 208

SSM_0404		94.73 160	94.31 163	95.98 161	97.05 187	90.90 179	97.01 217	97.29 239	91.24 228	94.17 205	97.60 168	85.03 199	98.76 227	92.14 215	97.30 181	98.29 215

F-COLMAP		93.58 205	92.98 211	95.37 214	98.40 87	88.98 271	97.18 203	97.29 239	87.75 362	90.49 301	97.10 207	85.21 196	99.50 121	86.70 355	96.72 209	97.63 265

VortexMVS		92.88 240	92.64 226	93.58 336	96.58 242	87.53 327	96.93 226	97.28 242	92.78 161	89.75 325	94.99 324	82.73 252	97.76 372	94.60 161	88.16 370	95.46 354

onestephybrid01		95.12 132	95.01 124	95.46 211	96.39 269	88.92 272	96.28 302	97.27 243	92.67 163	96.00 132	97.73 152	86.28 164	98.66 254	95.58 120	96.85 200	98.79 156

nocashy02		95.18 130	95.15 116	95.26 221	96.31 274	88.25 301	96.29 300	97.27 243	93.61 111	95.65 148	97.91 119	86.79 153	98.64 258	95.69 108	96.82 202	98.88 142

hybridnocas07		94.93 145	94.78 137	95.37 214	96.27 276	88.62 282	96.10 316	97.26 245	92.35 178	95.58 151	97.48 178	85.60 187	98.65 256	95.47 121	96.90 198	98.85 147

XVG-ACMP-BASELINE		90.93 332	90.21 330	93.09 358	94.31 394	85.89 374	95.33 365	97.26 245	91.06 241	89.38 338	95.44 308	68.61 434	98.60 266	89.46 282	91.05 335	94.79 412

PCF-MVS	89.48 11	91.56 296	89.95 341	96.36 128	96.60 238	92.52 104	92.51 464	97.26 245	79.41 473	88.90 352	96.56 246	84.04 222	99.55 109	77.01 457	97.30 181	97.01 293
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
hybrid		94.76 158	94.60 146	95.27 219	96.24 278	88.36 295	96.05 320	97.25 248	91.40 220	95.40 158	97.59 170	85.48 190	98.63 261	95.23 126	96.71 210	98.83 152

ACMP	89.59 10	92.62 249	92.14 244	94.05 299	96.40 265	88.20 306	97.36 179	97.25 248	91.52 213	88.30 370	96.64 236	78.46 341	98.72 242	91.86 225	91.48 327	95.23 375
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 205	93.46 191	93.94 310	96.19 283	86.16 368	93.73 434	97.24 250	91.54 209	93.50 226	97.04 210	85.64 185	96.91 433	90.68 254	95.59 248	98.76 161

IMVS_0407		93.94 191	93.75 177	94.49 272	96.19 283	86.16 368	96.35 292	97.24 250	91.54 209	93.50 226	97.04 210	85.64 185	98.54 273	90.68 254	95.59 248	98.76 161

IMVS_0404		92.44 253	91.92 253	94.00 302	96.19 283	86.16 368	93.84 431	97.24 250	91.54 209	88.17 376	97.04 210	76.96 359	97.09 424	90.68 254	95.59 248	98.76 161

IMVS_0403		93.98 189	93.79 176	94.55 268	96.19 283	86.16 368	96.35 292	97.24 250	91.54 209	93.59 221	97.04 210	85.86 174	98.73 237	90.68 254	95.59 248	98.76 161

OPM-MVS		93.28 219	92.76 219	94.82 246	94.63 381	90.77 185	96.65 263	97.18 254	93.72 107	91.68 275	97.26 195	79.33 324	98.63 261	92.13 218	92.28 312	95.07 384
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 238	92.02 249	95.56 196	98.19 110	90.80 182	95.27 370	97.18 254	87.96 350	91.86 270	95.68 295	80.44 302	98.99 192	84.01 395	97.54 165	96.89 300

alignmvs		95.87 100	95.23 113	97.78 37	97.56 163	95.19 22	97.86 92	97.17 256	94.39 85	96.47 109	96.40 254	85.89 173	99.20 155	96.21 87	95.11 262	98.95 122

MVS_Test		94.89 148	94.62 145	95.68 190	96.83 211	89.55 241	96.70 257	97.17 256	91.17 234	95.60 150	96.11 273	87.87 126	98.76 227	93.01 203	97.17 188	98.72 169

Fast-Effi-MVS+		93.46 211	92.75 221	95.59 195	96.77 224	90.03 214	96.81 243	97.13 258	88.19 343	91.30 286	94.27 369	86.21 167	98.63 261	87.66 333	96.46 223	98.12 229

usedtu_dtu_shiyan1		91.65 288	90.67 308	94.60 260	93.65 414	90.95 174	94.86 389	97.12 259	89.69 290	89.21 346	93.62 400	81.17 285	97.67 379	87.54 337	89.14 357	95.17 381

FE-MVSNET3		91.65 288	90.67 308	94.60 260	93.65 414	90.95 174	94.86 389	97.12 259	89.69 290	89.21 346	93.62 400	81.17 285	97.67 379	87.54 337	89.14 357	95.17 381

EI-MVSNet		93.03 231	92.88 215	93.48 343	95.77 312	86.98 341	96.44 277	97.12 259	90.66 257	91.30 286	97.64 163	86.56 157	98.05 329	89.91 270	90.55 343	95.41 358

MVSTER		93.20 222	92.81 218	94.37 278	96.56 247	89.59 237	97.06 211	97.12 259	91.24 228	91.30 286	95.96 276	82.02 269	98.05 329	93.48 188	90.55 343	95.47 353

viewmambaseed2359dif		94.28 170	94.14 166	94.71 256	96.21 279	86.97 342	95.93 329	97.11 263	89.00 314	95.00 177	97.70 153	86.02 172	98.59 270	93.71 183	96.59 216	98.57 182

test_yl		94.78 156	94.23 164	96.43 120	97.74 143	91.22 157	96.85 235	97.10 264	91.23 231	95.71 143	96.93 217	84.30 215	99.31 144	93.10 196	95.12 260	98.75 165

DCV-MVSNet		94.78 156	94.23 164	96.43 120	97.74 143	91.22 157	96.85 235	97.10 264	91.23 231	95.71 143	96.93 217	84.30 215	99.31 144	93.10 196	95.12 260	98.75 165

LTVRE_ROB	88.41 13	90.99 328	89.92 343	94.19 290	96.18 287	89.55 241	96.31 298	97.09 266	87.88 353	85.67 425	95.91 279	78.79 337	98.57 271	81.50 420	89.98 348	94.44 426
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
viewmsd2359difaftdt		93.46 211	93.23 201	94.17 291	96.12 295	85.42 383	96.43 279	97.08 267	92.91 152	94.21 201	98.00 107	80.82 294	98.74 235	94.41 165	89.05 359	98.34 212

test_fmvs1_n		92.73 247	92.88 215	92.29 384	96.08 300	81.05 443	97.98 72	97.08 267	90.72 252	96.79 88	98.18 91	63.07 468	98.45 280	97.62 39	98.42 134	97.36 280

v10		91.04 326	90.23 327	93.49 342	94.12 397	88.16 309	97.32 184	97.08 267	88.26 342	88.29 371	94.22 374	82.17 266	97.97 341	86.45 359	84.12 421	94.33 429

dtuplus		94.16 176	93.98 171	94.70 257	96.18 287	86.85 345	96.04 321	97.07 270	89.75 288	95.02 176	97.79 144	84.94 204	98.62 264	92.62 208	96.43 228	98.62 176

viewdifsd2359ckpt11		93.46 211	93.22 202	94.17 291	96.11 297	85.42 383	96.43 279	97.07 270	92.91 152	94.20 202	98.00 107	80.82 294	98.73 237	94.42 164	89.04 361	98.34 212

mamba_0408		93.70 202	92.99 208	95.83 172	96.79 217	90.38 201	88.69 491	97.07 270	90.96 244	93.68 217	97.31 190	84.97 202	98.76 227	90.95 245	96.51 217	98.35 208

SSM_04072		93.51 210	92.99 208	95.05 230	96.79 217	90.38 201	88.69 491	97.07 270	90.96 244	93.68 217	97.31 190	84.97 202	96.42 444	90.95 245	96.51 217	98.35 208

v144192		91.06 325	90.28 323	93.39 346	93.66 412	87.23 335	96.83 239	97.07 270	87.43 370	89.69 328	94.28 368	81.48 279	98.00 336	87.18 349	84.92 410	94.93 392

v1192		91.07 324	90.23 327	93.58 336	93.70 409	87.82 321	96.73 253	97.07 270	87.77 360	89.58 331	94.32 366	80.90 292	97.97 341	86.52 357	85.48 397	94.95 388

v8		91.29 316	90.53 315	93.57 338	94.15 396	88.12 310	97.34 181	97.06 276	88.99 315	88.32 369	94.26 371	83.08 240	98.01 335	87.62 335	83.92 425	94.57 422

mvs_anonymous		93.82 197	93.74 178	94.06 298	96.44 263	85.41 385	95.81 337	97.05 277	89.85 284	90.09 316	96.36 256	87.44 141	97.75 374	93.97 174	96.69 211	99.02 106

IterMVS-LS		92.29 263	91.94 252	93.34 348	96.25 277	86.97 342	96.57 275	97.05 277	90.67 255	89.50 336	94.80 336	86.59 156	97.64 384	89.91 270	86.11 392	95.40 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 335	90.03 338	93.29 350	93.55 416	86.96 344	96.74 252	97.04 279	87.36 372	89.52 335	94.34 363	80.23 307	97.97 341	86.27 360	85.21 403	94.94 390

CDS-MVSNet		94.14 180	93.54 185	95.93 163	96.18 287	91.46 149	96.33 296	97.04 279	88.97 317	93.56 222	96.51 248	87.55 134	97.89 358	89.80 273	95.95 235	98.44 199
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 371	89.26 364	91.19 419	95.16 351	80.29 454	94.53 399	97.03 281	91.79 202	88.86 355	94.10 378	69.94 423	97.82 364	85.29 378	86.66 388	95.45 356

v1144		91.37 309	90.60 311	93.68 328	93.89 404	88.23 302	96.84 238	97.03 281	88.37 339	89.69 328	94.39 358	82.04 268	97.98 338	87.80 320	85.37 399	94.84 401

v1240		90.70 341	89.85 345	93.23 352	93.51 419	86.80 346	96.61 269	97.02 283	87.16 377	89.58 331	94.31 367	79.55 321	97.98 338	85.52 375	85.44 398	94.90 395

EPP-MVSNet		95.22 125	95.04 122	95.76 182	97.49 164	89.56 239	98.67 15	97.00 284	90.69 253	94.24 200	97.62 166	89.79 93	98.81 212	93.39 192	96.49 221	98.92 130

V42		91.58 295	90.87 293	93.73 321	94.05 400	88.50 290	97.32 184	96.97 285	88.80 327	89.71 326	94.33 364	82.54 257	98.05 329	89.01 297	85.07 406	94.64 421

test_fmvs1		93.21 221	93.53 186	92.25 387	96.55 249	81.20 442	97.40 175	96.96 286	90.68 254	96.80 86	98.04 101	69.25 429	98.40 283	97.58 40	98.50 127	97.16 291

FMVSNet2		91.31 313	90.08 333	94.99 236	96.51 256	92.21 115	97.41 171	96.95 287	88.82 324	88.62 361	94.75 338	73.87 386	97.42 411	85.20 381	88.55 367	95.35 365

ACMH	87.59 16	90.53 346	89.42 360	93.87 315	96.21 279	87.92 316	97.24 194	96.94 288	88.45 337	83.91 447	96.27 261	71.92 403	98.62 264	84.43 389	89.43 354	95.05 386
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 310	90.27 324	94.59 262	96.51 256	91.18 164	97.50 156	96.93 289	88.82 324	89.35 339	94.51 351	73.87 386	97.29 419	86.12 365	88.82 362	95.31 368

test1		91.35 310	90.27 324	94.59 262	96.51 256	91.18 164	97.50 156	96.93 289	88.82 324	89.35 339	94.51 351	73.87 386	97.29 419	86.12 365	88.82 362	95.31 368

FMVSNet3		91.78 282	90.69 307	95.03 233	96.53 252	92.27 113	97.02 214	96.93 289	89.79 287	89.35 339	94.65 344	77.01 357	97.47 406	86.12 365	88.82 362	95.35 365

FMVSNet1		89.88 366	88.31 379	94.59 262	95.41 330	91.18 164	97.50 156	96.93 289	86.62 386	87.41 390	94.51 351	65.94 456	97.29 419	83.04 404	87.43 378	95.31 368

GeoE		93.89 194	93.28 199	95.72 188	96.96 198	89.75 229	98.24 43	96.92 293	89.47 298	92.12 261	97.21 198	84.42 212	98.39 288	87.71 325	96.50 220	99.01 109

SymmetryMVS		95.94 96	95.54 96	97.15 75	97.85 136	92.90 88	97.99 69	96.91 294	95.92 16	96.57 103	97.93 114	85.34 192	99.50 121	94.99 134	96.39 229	99.05 105

miper_enhance_ethall		91.54 299	91.01 289	93.15 356	95.35 336	87.07 340	93.97 423	96.90 295	86.79 383	89.17 348	93.43 413	86.55 158	97.64 384	89.97 269	86.93 383	94.74 417

eth_miper_zixun_eth		91.02 327	90.59 312	92.34 382	95.33 340	84.35 404	94.10 420	96.90 295	88.56 333	88.84 357	94.33 364	84.08 220	97.60 389	88.77 305	84.37 419	95.06 385

TAMVS		94.01 186	93.46 191	95.64 191	96.16 290	90.45 196	96.71 256	96.89 297	89.27 305	93.46 229	96.92 220	87.29 145	97.94 351	88.70 307	95.74 242	98.53 185

miper_ehance_all_eth		91.59 293	91.13 284	92.97 362	95.55 322	86.57 354	94.47 404	96.88 298	87.77 360	88.88 354	94.01 383	86.22 166	97.54 399	89.49 281	86.93 383	94.79 412

v2v482		91.59 293	90.85 296	93.80 318	93.87 405	88.17 308	96.94 224	96.88 298	89.54 295	89.53 334	94.90 330	81.70 277	98.02 334	89.25 290	85.04 408	95.20 376

CNLPA		94.28 170	93.53 186	96.52 108	98.38 90	92.55 103	96.59 272	96.88 298	90.13 278	91.91 267	97.24 196	85.21 196	99.09 176	87.64 334	97.83 158	97.92 247

PAPM		91.52 300	90.30 322	95.20 223	95.30 343	89.83 226	93.38 446	96.85 301	86.26 394	88.59 362	95.80 285	84.88 205	98.15 310	75.67 463	95.93 236	97.63 265

c3_l		91.38 307	90.89 292	92.88 366	95.58 320	86.30 362	94.68 394	96.84 302	88.17 344	88.83 358	94.23 372	85.65 182	97.47 406	89.36 285	84.63 412	94.89 396

pm-mvs1		90.72 340	89.65 355	93.96 307	94.29 395	89.63 234	97.79 107	96.82 303	89.07 310	86.12 418	95.48 307	78.61 339	97.78 369	86.97 353	81.67 438	94.46 424

test_vis1_n		92.37 258	92.26 242	92.72 372	94.75 375	82.64 425	98.02 66	96.80 304	91.18 233	97.77 60	97.93 114	58.02 479	98.29 298	97.63 37	98.21 143	97.23 288

CMPMVS	62.92 21	85.62 431	84.92 420	87.74 458	89.14 473	73.12 491	94.17 418	96.80 304	73.98 486	73.65 489	94.93 328	66.36 450	97.61 388	83.95 397	91.28 331	92.48 463
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 353	89.77 349	91.78 403	94.33 392	84.72 401	95.55 353	96.73 306	86.17 396	86.36 412	95.28 313	71.28 409	97.80 367	84.09 394	98.14 147	92.81 454

Effi-MVS+-dtu		93.08 228	93.21 203	92.68 375	96.02 303	83.25 418	97.14 207	96.72 307	93.85 103	91.20 293	93.44 410	83.08 240	98.30 297	91.69 231	95.73 243	96.50 311

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 68	98.31 93	93.39 68	96.79 245	96.72 307	94.17 90	97.44 66	97.66 159	92.76 34	99.33 140	96.86 62	97.76 162	99.08 100

1112_ss		93.37 216	92.42 238	96.21 140	97.05 187	90.99 171	96.31 298	96.72 307	86.87 382	89.83 323	96.69 233	86.51 159	99.14 168	88.12 312	93.67 295	98.50 189

PVSNet	86.66 18	92.24 266	91.74 261	93.73 321	97.77 141	83.69 415	92.88 455	96.72 307	87.91 352	93.00 240	94.86 332	78.51 340	99.05 187	86.53 356	97.45 173	98.47 194

miper_lstm_enhance		90.50 349	90.06 337	91.83 399	95.33 340	83.74 412	93.86 429	96.70 311	87.56 368	87.79 382	93.81 391	83.45 231	96.92 432	87.39 343	84.62 413	94.82 407

v148		90.99 328	90.38 318	92.81 369	93.83 406	85.80 375	96.78 249	96.68 312	89.45 300	88.75 360	93.93 387	82.96 246	97.82 364	87.83 318	83.25 430	94.80 410

ACMH+	87.92 14	90.20 357	89.18 366	93.25 351	96.48 259	86.45 359	96.99 220	96.68 312	88.83 323	84.79 435	96.22 263	70.16 420	98.53 274	84.42 390	88.04 371	94.77 415

CANet_DTU		94.37 168	93.65 181	96.55 105	96.46 262	92.13 119	96.21 308	96.67 314	94.38 86	93.53 225	97.03 215	79.34 323	99.71 67	90.76 251	98.45 132	97.82 258

cl____		90.96 331	90.32 320	92.89 365	95.37 334	86.21 365	94.46 406	96.64 315	87.82 356	88.15 377	94.18 375	82.98 244	97.54 399	87.70 326	85.59 395	94.92 394

HY-MVS	89.66 9	93.87 195	92.95 212	96.63 99	97.10 181	92.49 105	95.64 350	96.64 315	89.05 312	93.00 240	95.79 288	85.77 178	99.45 129	89.16 295	94.35 274	97.96 244

Test_1112_low_res		92.84 243	91.84 256	95.85 171	97.04 189	89.97 221	95.53 355	96.64 315	85.38 406	89.65 330	95.18 318	85.86 174	99.10 173	87.70 326	93.58 300	98.49 191

DIV-MVS_self_test		90.97 330	90.33 319	92.88 366	95.36 335	86.19 367	94.46 406	96.63 318	87.82 356	88.18 375	94.23 372	82.99 243	97.53 401	87.72 323	85.57 396	94.93 392

Fast-Effi-MVS+-dtu		92.29 263	91.99 250	93.21 354	95.27 344	85.52 381	97.03 212	96.63 318	92.09 193	89.11 350	95.14 320	80.33 305	98.08 322	87.54 337	94.74 270	96.03 329

UnsupCasMVSNet_bld		82.13 450	79.46 455	90.14 436	88.00 488	82.47 430	90.89 479	96.62 320	78.94 475	75.61 484	84.40 498	56.63 482	96.31 446	77.30 454	66.77 496	91.63 475

cl22		91.21 318	90.56 314	93.14 357	96.09 299	86.80 346	94.41 408	96.58 321	87.80 358	88.58 363	93.99 385	80.85 293	97.62 387	89.87 272	86.93 383	94.99 387

jason		94.84 152	94.39 159	96.18 142	95.52 323	90.93 177	96.09 317	96.52 322	89.28 304	96.01 131	97.32 188	84.70 207	98.77 221	95.15 130	98.91 111	98.85 147
jason: jason.
tt0805		91.09 323	90.07 336	94.16 294	95.61 318	88.31 296	97.56 147	96.51 323	89.56 294	89.17 348	95.64 297	67.08 448	98.38 289	91.07 243	88.44 368	95.80 337

AUN-MVS		91.76 283	90.75 302	94.81 248	97.00 194	88.57 285	96.65 263	96.49 324	89.63 292	92.15 259	96.12 269	78.66 338	98.50 276	90.83 247	79.18 450	97.36 280

hse-mvs2		93.45 214	92.99 208	94.81 248	97.02 192	88.59 284	96.69 259	96.47 325	95.19 38	96.74 90	96.16 267	83.67 226	98.48 279	95.85 102	79.13 451	97.35 282

SD_0403		90.01 361	90.02 339	89.96 440	95.65 317	76.76 477	95.76 341	96.46 326	90.58 264	86.59 409	96.29 259	82.12 267	94.78 470	73.00 477	93.76 293	98.35 208

EG-PatchMatch MVS		87.02 407	85.44 409	91.76 405	92.67 441	85.00 395	96.08 318	96.45 327	83.41 442	79.52 473	93.49 406	57.10 481	97.72 376	79.34 445	90.87 340	92.56 460

KD-MVS_self_test		85.95 426	84.95 419	88.96 452	89.55 472	79.11 470	95.13 382	96.42 328	85.91 399	84.07 445	90.48 455	70.03 422	94.82 469	80.04 436	72.94 476	92.94 452

FE-MVSNET2		86.36 417	84.68 425	91.39 413	87.67 490	86.47 358	96.21 308	96.41 329	87.87 354	79.31 475	89.64 463	65.29 461	95.58 460	82.42 413	77.28 457	92.14 472

pmmvs6		87.81 393	86.19 401	92.69 374	91.32 458	86.30 362	97.34 181	96.41 329	80.59 469	84.05 446	94.37 360	67.37 443	97.67 379	84.75 385	79.51 449	94.09 436

PMMVS		92.86 241	92.34 239	94.42 277	94.92 366	86.73 349	94.53 399	96.38 331	84.78 418	94.27 199	95.12 322	83.13 239	98.40 283	91.47 235	96.49 221	98.12 229

RPSCF		90.75 338	90.86 294	90.42 433	96.84 209	76.29 481	95.61 351	96.34 332	83.89 429	91.38 280	97.87 128	76.45 363	98.78 217	87.16 350	92.23 313	96.20 318

BP-MVS1		95.89 98	95.49 98	97.08 82	96.67 231	93.20 78	98.08 59	96.32 333	94.56 74	96.32 116	97.84 134	84.07 221	99.15 165	96.75 64	98.78 115	98.90 134

MSDG		91.42 305	90.24 326	94.96 241	97.15 179	88.91 273	93.69 437	96.32 333	85.72 402	86.93 405	96.47 250	80.24 306	98.98 193	80.57 433	95.05 263	96.98 294

blended_shiyan6		87.55 397	85.52 408	93.64 331	88.78 478	88.50 290	95.23 373	96.30 335	82.80 448	86.09 419	87.70 481	73.69 392	97.56 392	87.70 326	71.36 483	94.86 397

blend_shiyan4		86.87 408	84.61 426	93.67 329	88.87 476	88.70 279	95.17 380	96.30 335	82.80 448	86.16 415	87.11 486	65.12 464	97.55 394	87.73 321	72.21 479	94.75 416

WBMVS		90.69 343	89.99 340	92.81 369	96.48 259	85.00 395	95.21 376	96.30 335	89.46 299	89.04 351	94.05 382	72.45 401	97.82 364	89.46 282	87.41 380	95.61 348

blended_shiyan8		87.58 396	85.55 407	93.66 330	88.76 480	88.54 287	95.21 376	96.29 338	82.81 447	86.25 413	87.73 480	73.70 391	97.58 391	87.81 319	71.42 482	94.85 400

OurMVSNet-221017-0		90.51 348	90.19 331	91.44 411	93.41 425	81.25 440	96.98 221	96.28 339	91.68 206	86.55 410	96.30 258	74.20 385	97.98 338	88.96 300	87.40 381	95.09 383

wanda-best-256-512		87.29 400	85.21 413	93.53 339	88.54 484	88.21 304	94.51 402	96.27 340	82.69 451	85.92 421	86.89 489	73.04 395	97.55 394	87.68 330	71.36 483	94.83 402

FE-blended-shiyan7		87.29 400	85.21 413	93.53 339	88.54 484	88.21 304	94.51 402	96.27 340	82.69 451	85.92 421	86.89 489	73.03 396	97.55 394	87.68 330	71.36 483	94.83 402

MVP-Stereo		90.74 339	90.08 333	92.71 373	93.19 430	88.20 306	95.86 333	96.27 340	86.07 397	84.86 434	94.76 337	77.84 352	97.75 374	83.88 399	98.01 153	92.17 471
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 144	94.56 149	96.29 134	96.34 272	91.21 159	95.83 335	96.27 340	88.93 319	96.22 121	96.88 222	86.20 168	98.85 206	95.27 125	99.05 102	98.82 153

BH-untuned		92.94 236	92.62 228	93.92 314	97.22 172	86.16 368	96.40 287	96.25 344	90.06 279	89.79 324	96.17 266	83.19 236	98.35 291	87.19 348	97.27 183	97.24 287

CL-MVSNet_self_test		86.31 419	85.15 416	89.80 442	88.83 477	81.74 438	93.93 426	96.22 345	86.67 385	85.03 432	90.80 453	78.09 348	94.50 471	74.92 466	71.86 480	93.15 450

IS-MVSNet		94.90 147	94.52 153	96.05 151	97.67 147	90.56 192	98.44 26	96.22 345	93.21 131	93.99 209	97.74 149	85.55 188	98.45 280	89.98 268	97.86 157	99.14 90

FA-MVS(test-final)		93.52 209	92.92 213	95.31 218	96.77 224	88.54 287	94.82 391	96.21 347	89.61 293	94.20 202	95.25 316	83.24 234	99.14 168	90.01 267	96.16 232	98.25 217

gbinet_0.2-2-1-0.02		87.30 399	85.16 415	93.69 325	88.70 483	88.81 276	95.14 381	96.20 348	83.03 445	86.14 417	87.06 487	71.26 410	97.40 413	87.46 341	71.49 481	94.86 397

GA-MVS		91.38 307	90.31 321	94.59 262	94.65 380	87.62 325	94.34 411	96.19 349	90.73 251	90.35 304	93.83 388	71.84 404	97.96 345	87.22 347	93.61 298	98.21 220

LuminaMVS		94.89 148	94.35 161	96.53 106	95.48 325	92.80 92	96.88 233	96.18 350	92.85 157	95.92 135	96.87 224	81.44 280	98.83 209	96.43 77	97.10 190	97.94 246

IterMVS-SCA-FT		90.31 351	89.81 347	91.82 400	95.52 323	84.20 407	94.30 414	96.15 351	90.61 261	87.39 391	94.27 369	75.80 369	96.44 443	87.34 344	86.88 387	94.82 407

IterMVS		90.15 359	89.67 353	91.61 407	95.48 325	83.72 413	94.33 412	96.12 352	89.99 280	87.31 394	94.15 377	75.78 371	96.27 447	86.97 353	86.89 386	94.83 402
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 246	91.51 270	96.52 108	98.77 62	90.99 171	97.38 178	96.08 353	82.38 454	89.29 342	97.87 128	83.77 224	99.69 73	81.37 426	96.69 211	98.89 140

pmmvs4		90.93 332	89.85 345	94.17 291	93.34 427	90.79 183	94.60 396	96.02 354	84.62 419	87.45 388	95.15 319	81.88 274	97.45 408	87.70 326	87.87 373	94.27 433

ppachtmachnet_test		88.35 388	87.29 387	91.53 408	92.45 447	83.57 416	93.75 433	95.97 355	84.28 422	85.32 430	94.18 375	79.00 335	96.93 431	75.71 462	84.99 409	94.10 434

Anonymous20240521		86.42 416	85.44 409	89.34 449	90.33 465	79.79 460	96.73 253	95.92 356	83.71 434	83.25 451	91.36 450	63.92 466	96.01 448	78.39 449	85.36 400	92.22 469

ITE_SJBPF				92.43 378	95.34 337	85.37 388		95.92 356	91.47 215	87.75 384	96.39 255	71.00 412	97.96 345	82.36 414	89.86 350	93.97 439

test_fmvs2		89.77 370	89.93 342	89.31 450	93.68 411	76.37 480	97.64 135	95.90 358	89.84 285	91.49 278	96.26 262	58.77 477	97.10 423	94.65 158	91.13 333	94.46 424

USDC		88.94 379	87.83 384	92.27 385	94.66 379	84.96 397	93.86 429	95.90 358	87.34 373	83.40 449	95.56 301	67.43 442	98.19 307	82.64 412	89.67 352	93.66 443

COLMAP_ROB	87.81 15	90.40 350	89.28 363	93.79 319	97.95 129	87.13 339	96.92 227	95.89 360	82.83 446	86.88 407	97.18 199	73.77 389	99.29 147	78.44 448	93.62 297	94.95 388
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 197	93.08 206	96.02 155	97.88 135	89.96 222	97.72 119	95.85 361	92.43 175	95.86 137	98.44 64	68.42 438	99.39 135	96.31 79	94.85 264	98.71 171

VDDNet		93.05 230	92.07 245	96.02 155	96.84 209	90.39 200	98.08 59	95.85 361	86.22 395	95.79 140	98.46 62	67.59 441	99.19 156	94.92 137	94.85 264	98.47 194

mvsmamba		94.57 162	94.14 166	95.87 167	97.03 190	89.93 223	97.84 96	95.85 361	91.34 222	94.79 184	96.80 225	80.67 296	98.81 212	94.85 142	98.12 148	98.85 147

Vis-MVSNet (Re-imp)		94.15 177	93.88 174	94.95 242	97.61 155	87.92 316	98.10 57	95.80 364	92.22 184	93.02 239	97.45 180	84.53 210	97.91 357	88.24 311	97.97 154	99.02 106

MM		97.29 31	96.98 42	98.23 13	98.01 124	95.03 28	98.07 61	95.76 365	97.78 1	97.52 63	98.80 40	88.09 119	99.86 10	99.44 2	99.37 66	99.80 3

KD-MVS_2432*1600		84.81 437	82.64 440	91.31 414	91.07 460	85.34 389	91.22 473	95.75 366	85.56 404	83.09 452	90.21 458	67.21 444	95.89 450	77.18 455	62.48 502	92.69 456

miper_refine_blended		84.81 437	82.64 440	91.31 414	91.07 460	85.34 389	91.22 473	95.75 366	85.56 404	83.09 452	90.21 458	67.21 444	95.89 450	77.18 455	62.48 502	92.69 456

FE-MVS		92.05 274	91.05 287	95.08 229	96.83 211	87.93 315	93.91 428	95.70 368	86.30 392	94.15 206	94.97 325	76.59 361	99.21 154	84.10 393	96.86 199	98.09 236

tpm cat1		88.36 387	87.21 390	91.81 401	95.13 356	80.55 449	92.58 463	95.70 368	74.97 485	87.45 388	91.96 442	78.01 351	98.17 309	80.39 435	88.74 365	96.72 305

our_test_3		88.78 383	87.98 383	91.20 418	92.45 447	82.53 427	93.61 442	95.69 370	85.77 401	84.88 433	93.71 393	79.99 311	96.78 439	79.47 442	86.24 389	94.28 432

BH-w/o		92.14 271	91.75 259	93.31 349	96.99 195	85.73 378	95.67 345	95.69 370	88.73 329	89.26 344	94.82 335	82.97 245	98.07 326	85.26 380	96.32 230	96.13 325

CR-MVSNet		90.82 336	89.77 349	93.95 308	94.45 388	87.19 336	90.23 482	95.68 372	86.89 381	92.40 249	92.36 433	80.91 290	97.05 426	81.09 430	93.95 290	97.60 270

Patchmtry		88.64 385	87.25 388	92.78 371	94.09 398	86.64 350	89.82 486	95.68 372	80.81 466	87.63 386	92.36 433	80.91 290	97.03 427	78.86 446	85.12 405	94.67 419

testing91		91.90 279	91.02 288	94.53 270	96.54 250	86.55 356	95.86 333	95.64 374	91.77 203	91.89 268	93.47 408	69.94 423	98.86 204	90.23 266	93.86 292	98.18 222

BH-RMVSNet		92.72 248	91.97 251	94.97 240	97.16 176	87.99 314	96.15 314	95.60 375	90.62 260	91.87 269	97.15 202	78.41 342	98.57 271	83.16 402	97.60 164	98.36 206

PVSNet_0	82.17 19	85.46 432	83.64 433	90.92 422	95.27 344	79.49 466	90.55 480	95.60 375	83.76 433	83.00 454	89.95 460	71.09 411	97.97 341	82.75 410	60.79 504	95.31 368

guyue		95.17 131	94.96 127	95.82 173	96.97 197	89.65 233	97.56 147	95.58 377	94.82 59	95.72 142	97.42 183	82.90 247	98.84 208	96.71 67	96.93 195	98.96 118

SCA		91.84 281	91.18 283	93.83 316	95.59 319	84.95 398	94.72 393	95.58 377	90.82 247	92.25 257	93.69 395	75.80 369	98.10 317	86.20 362	95.98 234	98.45 196

MonoMVSNet		91.92 277	91.77 257	92.37 379	92.94 435	83.11 421	97.09 210	95.55 379	92.91 152	90.85 296	94.55 348	81.27 284	96.52 442	93.01 203	87.76 374	97.47 276

dtuonly		90.88 334	91.13 284	90.13 437	92.98 434	75.01 484	92.74 460	95.54 380	87.69 364	91.37 281	96.61 245	79.65 319	98.15 310	87.44 342	96.21 231	97.23 288

usedtu_blend_shiyan5		87.06 406	84.84 421	93.69 325	88.54 484	88.70 279	95.83 335	95.54 380	78.74 476	85.92 421	86.89 489	73.03 396	97.55 394	87.73 321	71.36 483	94.83 402

AllTest		90.23 355	88.98 369	93.98 304	97.94 130	86.64 350	96.51 276	95.54 380	85.38 406	85.49 427	96.77 227	70.28 418	99.15 165	80.02 437	92.87 302	96.15 323

TestCases				93.98 304	97.94 130	86.64 350		95.54 380	85.38 406	85.49 427	96.77 227	70.28 418	99.15 165	80.02 437	92.87 302	96.15 323

mmtdpeth		89.70 372	88.96 370	91.90 396	95.84 311	84.42 403	97.46 167	95.53 384	90.27 273	94.46 195	90.50 454	69.74 427	98.95 194	97.39 53	69.48 490	92.34 465

tpmvs		89.83 369	89.15 367	91.89 397	94.92 366	80.30 453	93.11 451	95.46 385	86.28 393	88.08 378	92.65 423	80.44 302	98.52 275	81.47 422	89.92 349	96.84 301

pmmvs5		89.86 368	88.87 373	92.82 368	92.86 437	86.23 364	96.26 303	95.39 386	84.24 424	87.12 396	94.51 351	74.27 384	97.36 416	87.61 336	87.57 376	94.86 397

PatchmatchNet		91.91 278	91.35 272	93.59 335	95.38 332	84.11 408	93.15 450	95.39 386	89.54 295	92.10 262	93.68 397	82.82 250	98.13 312	84.81 384	95.32 256	98.52 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 304	91.32 274	91.79 402	95.15 354	79.20 469	93.42 445	95.37 388	88.55 334	93.49 228	93.67 398	82.49 259	98.27 300	90.41 261	89.34 355	97.90 248

Anonymous20231206		87.09 405	86.14 402	89.93 441	91.22 459	80.35 451	96.11 315	95.35 389	83.57 437	84.16 441	93.02 418	73.54 393	95.61 458	72.16 479	86.14 391	93.84 441

MIMVSNet1		84.93 435	83.05 437	90.56 431	89.56 471	84.84 400	95.40 361	95.35 389	83.91 428	80.38 469	92.21 438	57.23 480	93.34 486	70.69 485	82.75 436	93.50 445

TDRefinement		86.53 412	84.76 423	91.85 398	82.23 507	84.25 405	96.38 289	95.35 389	84.97 415	84.09 444	94.94 327	65.76 457	98.34 294	84.60 388	74.52 468	92.97 451

TR-MVS		91.48 303	90.59 312	94.16 294	96.40 265	87.33 329	95.67 345	95.34 392	87.68 365	91.46 279	95.52 304	76.77 360	98.35 291	82.85 407	93.61 298	96.79 303

EPNet_dtu		91.71 284	91.28 277	92.99 361	93.76 408	83.71 414	96.69 259	95.28 393	93.15 138	87.02 401	95.95 277	83.37 232	97.38 415	79.46 443	96.84 201	97.88 250
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 400	85.79 404	91.78 403	94.80 373	87.28 331	95.49 357	95.28 393	84.09 426	83.85 448	91.82 443	62.95 469	94.17 476	78.48 447	85.34 401	93.91 440

MDTV_nov1_ep13			90.76 300		95.22 348	80.33 452	93.03 453	95.28 393	88.14 347	92.84 246	93.83 388	81.34 281	98.08 322	82.86 405	94.34 275

LF4IMVS		87.94 391	87.25 388	89.98 439	92.38 450	80.05 459	94.38 409	95.25 396	87.59 367	84.34 438	94.74 339	64.31 465	97.66 383	84.83 383	87.45 377	92.23 468

TransMVSNet (Re)		88.94 379	87.56 385	93.08 359	94.35 391	88.45 293	97.73 116	95.23 397	87.47 369	84.26 440	95.29 311	79.86 314	97.33 417	79.44 444	74.44 470	93.45 447

test20.03		86.14 423	85.40 411	88.35 453	90.12 466	80.06 458	95.90 332	95.20 398	88.59 330	81.29 463	93.62 400	71.43 408	92.65 492	71.26 483	81.17 441	92.34 465

new-patchmatchnet		83.18 444	81.87 447	87.11 462	86.88 494	75.99 483	93.70 435	95.18 399	85.02 414	77.30 482	88.40 473	65.99 455	93.88 482	74.19 471	70.18 488	91.47 480

MDA-MVSNet_test_wron		85.87 429	84.23 430	90.80 428	92.38 450	82.57 426	93.17 448	95.15 400	82.15 455	67.65 496	92.33 436	78.20 344	95.51 463	77.33 452	79.74 446	94.31 431

YYNet1		85.87 429	84.23 430	90.78 429	92.38 450	82.46 431	93.17 448	95.14 401	82.12 456	67.69 494	92.36 433	78.16 347	95.50 464	77.31 453	79.73 447	94.39 427

Baseline_NR-MVSNet		91.20 319	90.62 310	92.95 363	93.83 406	88.03 312	97.01 217	95.12 402	88.42 338	89.70 327	95.13 321	83.47 229	97.44 409	89.66 278	83.24 431	93.37 448

thres200		92.23 267	91.39 271	94.75 255	97.61 155	89.03 266	96.60 271	95.09 403	92.08 194	93.28 234	94.00 384	78.39 343	99.04 190	81.26 429	94.18 281	96.19 319

ADS-MVSNet		89.89 365	88.68 375	93.53 339	95.86 306	84.89 399	90.93 477	95.07 404	83.23 443	91.28 289	91.81 444	79.01 333	97.85 360	79.52 440	91.39 329	97.84 255

pmmvs-eth3d		86.22 421	84.45 427	91.53 408	88.34 487	87.25 333	94.47 404	95.01 405	83.47 439	79.51 474	89.61 464	69.75 426	95.71 455	83.13 403	76.73 461	91.64 474

Anonymous202405211		92.07 273	90.83 298	95.76 182	98.19 110	88.75 277	97.58 143	95.00 406	86.00 398	93.64 220	97.45 180	66.24 453	99.53 113	90.68 254	92.71 307	99.01 109

MDA-MVSNet-bldmvs		85.00 434	82.95 439	91.17 420	93.13 432	83.33 417	94.56 398	95.00 406	84.57 420	65.13 500	92.65 423	70.45 417	95.85 452	73.57 474	77.49 456	94.33 429

ambc				86.56 467	83.60 502	70.00 495	85.69 503	94.97 408		80.60 468	88.45 472	37.42 501	96.84 436	82.69 411	75.44 466	92.86 453

testgi		87.97 390	87.21 390	90.24 435	92.86 437	80.76 444	96.67 262	94.97 408	91.74 204	85.52 426	95.83 283	62.66 472	94.47 473	76.25 459	88.36 369	95.48 351

myMVS_eth3d28		91.52 300	90.97 290	93.17 355	96.91 201	83.24 419	95.61 351	94.96 410	92.24 183	91.98 265	93.28 415	69.31 428	98.40 283	88.71 306	95.68 245	97.88 250

dp		88.90 381	88.26 381	90.81 426	94.58 384	76.62 479	92.85 457	94.93 411	85.12 412	90.07 318	93.07 417	75.81 368	98.12 315	80.53 434	87.42 379	97.71 262

test_fmvs3		83.21 443	83.02 438	83.78 471	86.77 495	68.34 498	96.76 251	94.91 412	86.49 388	84.14 443	89.48 465	36.04 502	91.73 495	91.86 225	80.77 443	91.26 482

test_0402		86.46 415	84.79 422	91.45 410	95.02 360	85.55 380	96.29 300	94.89 413	80.90 463	82.21 458	93.97 386	68.21 439	97.29 419	62.98 498	88.68 366	91.51 477

tfpn200view9		92.38 257	91.52 268	94.95 242	97.85 136	89.29 255	97.41 171	94.88 414	92.19 189	93.27 235	94.46 356	78.17 345	99.08 178	81.40 423	94.08 285	96.48 312

CVMVSNet		91.23 317	91.75 259	89.67 443	95.77 312	74.69 485	96.44 277	94.88 414	85.81 400	92.18 258	97.64 163	79.07 328	95.58 460	88.06 314	95.86 240	98.74 168

thres400		92.42 255	91.52 268	95.12 228	97.85 136	89.29 255	97.41 171	94.88 414	92.19 189	93.27 235	94.46 356	78.17 345	99.08 178	81.40 423	94.08 285	96.98 294

tt0320		85.39 433	83.12 436	92.19 389	93.44 424	85.79 376	96.19 311	94.87 417	71.19 493	82.92 455	91.76 446	58.43 478	96.81 437	81.03 431	78.26 455	93.98 438

EPNet		95.20 126	94.56 149	97.14 76	92.80 439	92.68 98	97.85 95	94.87 417	96.64 9	92.46 248	97.80 142	86.23 165	99.65 79	93.72 182	98.62 123	99.10 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 291	90.72 305	94.32 283	96.48 259	86.11 373	95.81 337	94.76 419	91.55 208	91.75 273	93.44 410	68.55 436	98.82 210	90.43 260	93.69 294	98.04 240

sc_t1		86.48 414	84.10 432	93.63 332	93.45 423	85.76 377	96.79 245	94.71 420	73.06 490	86.45 411	94.35 361	55.13 485	97.95 349	84.38 391	78.55 454	97.18 290

SixPastTwentyTwo		89.15 377	88.54 377	90.98 421	93.49 420	80.28 455	96.70 257	94.70 421	90.78 248	84.15 442	95.57 300	71.78 405	97.71 377	84.63 387	85.07 406	94.94 390

thres100view900		92.43 254	91.58 265	94.98 238	97.92 132	89.37 251	97.71 122	94.66 422	92.20 187	93.31 233	94.90 330	78.06 349	99.08 178	81.40 423	94.08 285	96.48 312

thres600view7		92.49 252	91.60 264	95.18 224	97.91 133	89.47 245	97.65 131	94.66 422	92.18 191	93.33 232	94.91 329	78.06 349	99.10 173	81.61 419	94.06 289	96.98 294

PatchT		88.87 382	87.42 386	93.22 353	94.08 399	85.10 393	89.51 487	94.64 424	81.92 457	92.36 252	88.15 476	80.05 310	97.01 429	72.43 478	93.65 296	97.54 273

baseline1		92.82 244	91.90 254	95.55 198	97.20 174	90.77 185	97.19 202	94.58 425	92.20 187	92.36 252	96.34 257	84.16 219	98.21 304	89.20 293	83.90 426	97.68 264

AstraMVS		94.82 154	94.64 144	95.34 217	96.36 271	88.09 311	97.58 143	94.56 426	94.98 48	95.70 145	97.92 117	81.93 273	98.93 197	96.87 61	95.88 238	98.99 114

UBG		91.55 297	90.76 300	93.94 310	96.52 255	85.06 394	95.22 374	94.54 427	90.47 269	91.98 265	92.71 422	72.02 402	98.74 235	88.10 313	95.26 258	98.01 242

Gipuma		67.86 472	65.41 473	75.18 490	92.66 442	73.45 489	66.50 524	94.52 428	53.33 514	57.80 510	66.07 519	30.81 504	89.20 499	48.15 514	78.88 453	62.90 523
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 287	90.75 302	94.47 273	96.53 252	86.56 355	95.76 341	94.51 429	91.10 240	91.24 291	93.59 403	68.59 435	98.86 204	91.10 242	94.29 277	98.00 243

dtuonlycased		85.91 427	85.69 405	86.60 466	92.42 449	76.96 476	93.66 439	94.49 430	86.68 384	80.87 464	92.00 439	71.52 406	93.23 489	79.58 439	79.97 445	89.60 489

CostFormer		91.18 322	90.70 306	92.62 376	94.84 371	81.76 437	94.09 421	94.43 431	84.15 425	92.72 247	93.77 392	79.43 322	98.20 305	90.70 253	92.18 316	97.90 248

tpm2		89.96 362	89.21 365	92.23 388	94.91 368	81.25 440	93.78 432	94.42 432	80.62 468	91.56 276	93.44 410	76.44 364	97.94 351	85.60 374	92.08 320	97.49 274

testing3-2		92.10 272	92.05 246	92.27 385	97.71 145	79.56 463	97.42 169	94.41 433	93.53 118	93.22 237	95.49 305	69.16 430	99.11 171	93.25 193	94.22 279	98.13 227

MGCNet		96.74 64	96.31 81	98.02 22	96.87 205	94.65 32	97.58 143	94.39 434	96.47 12	97.16 75	98.39 68	87.53 136	99.87 8	98.97 20	99.41 58	99.55 43

JIA-IIPM		88.26 389	87.04 393	91.91 395	93.52 418	81.42 439	89.38 488	94.38 435	80.84 465	90.93 295	80.74 507	79.22 325	97.92 354	82.76 409	91.62 324	96.38 315

dmvs_re		90.21 356	89.50 358	92.35 380	95.47 329	85.15 391	95.70 344	94.37 436	90.94 246	88.42 365	93.57 404	74.63 381	95.67 457	82.80 408	89.57 353	96.22 317

Patchmatch-test		89.42 375	87.99 382	93.70 324	95.27 344	85.11 392	88.98 489	94.37 436	81.11 462	87.10 399	93.69 395	82.28 263	97.50 404	74.37 469	94.76 268	98.48 193

LCM-MVSNet		72.55 460	69.39 465	82.03 475	70.81 529	65.42 505	90.12 484	94.36 438	55.02 511	65.88 498	81.72 504	24.16 512	89.96 496	74.32 470	68.10 494	90.71 485

ADS-MVSNet2		89.45 374	88.59 376	92.03 392	95.86 306	82.26 433	90.93 477	94.32 439	83.23 443	91.28 289	91.81 444	79.01 333	95.99 449	79.52 440	91.39 329	97.84 255

mvs5depth		86.53 412	85.08 417	90.87 423	88.74 481	82.52 428	91.91 468	94.23 440	86.35 391	87.11 398	93.70 394	66.52 449	97.76 372	81.37 426	75.80 463	92.31 467

EU-MVSNet		88.72 384	88.90 372	88.20 455	93.15 431	74.21 487	96.63 268	94.22 441	85.18 410	87.32 393	95.97 275	76.16 366	94.98 468	85.27 379	86.17 390	95.41 358

usedtu_dtu_shiyan2		80.00 453	76.91 459	89.27 451	82.13 508	79.69 462	95.45 359	94.20 442	72.95 491	75.80 483	87.75 479	44.44 497	94.30 475	70.64 486	68.81 493	93.84 441

tt0320-xc		84.83 436	82.33 444	92.31 383	93.66 412	86.20 366	96.17 313	94.06 443	71.26 492	82.04 460	92.22 437	55.07 486	96.72 440	81.49 421	75.04 467	94.02 437

MIMVSNet		88.50 386	86.76 396	93.72 323	94.84 371	87.77 322	91.39 471	94.05 444	86.41 390	87.99 380	92.59 426	63.27 467	95.82 454	77.44 451	92.84 304	97.57 272

OpenMVS_ROB	81.14 20	84.42 439	82.28 445	90.83 424	90.06 467	84.05 410	95.73 343	94.04 445	73.89 488	80.17 472	91.53 448	59.15 476	97.64 384	66.92 492	89.05 359	90.80 484

TinyColmap		86.82 410	85.35 412	91.21 416	94.91 368	82.99 423	93.94 425	94.02 446	83.58 436	81.56 462	94.68 341	62.34 473	98.13 312	75.78 461	87.35 382	92.52 462

ETVMVS		90.52 347	89.14 368	94.67 259	96.81 216	87.85 320	95.91 331	93.97 447	89.71 289	92.34 255	92.48 428	65.41 459	97.96 345	81.37 426	94.27 278	98.21 220

IB-MVS	87.33 17	89.91 363	88.28 380	94.79 252	95.26 347	87.70 323	95.12 383	93.95 448	89.35 303	87.03 400	92.49 427	70.74 415	99.19 156	89.18 294	81.37 440	97.49 274
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
Syy-MVS		87.13 404	87.02 394	87.47 459	95.16 351	73.21 490	95.00 385	93.93 449	88.55 334	86.96 402	91.99 440	75.90 367	94.00 479	61.59 500	94.11 282	95.20 376

myMVS_eth3d		87.18 403	86.38 399	89.58 444	95.16 351	79.53 464	95.00 385	93.93 449	88.55 334	86.96 402	91.99 440	56.23 483	94.00 479	75.47 465	94.11 282	95.20 376

testing222		90.31 351	88.96 370	94.35 279	96.54 250	87.29 330	95.50 356	93.84 451	90.97 243	91.75 273	92.96 419	62.18 474	98.00 336	82.86 405	94.08 285	97.76 260

test_f		80.57 452	79.62 454	83.41 473	83.38 504	67.80 500	93.57 443	93.72 452	80.80 467	77.91 481	87.63 482	33.40 503	92.08 494	87.14 351	79.04 452	90.34 486

LCM-MVSNet-Re		92.50 250	92.52 234	92.44 377	96.82 214	81.89 436	96.92 227	93.71 453	92.41 176	84.30 439	94.60 346	85.08 198	97.03 427	91.51 233	97.36 176	98.40 202

tpm		90.25 354	89.74 352	91.76 405	93.92 402	79.73 461	93.98 422	93.54 454	88.28 341	91.99 264	93.25 416	77.51 355	97.44 409	87.30 346	87.94 372	98.12 229

ET-MVSNet_ETH3D		91.49 302	90.11 332	95.63 192	96.40 265	91.57 143	95.34 364	93.48 455	90.60 263	75.58 485	95.49 305	80.08 309	96.79 438	94.25 170	89.76 351	98.52 186

LFMVS		93.60 204	92.63 227	96.52 108	98.13 116	91.27 156	97.94 82	93.39 456	90.57 265	96.29 118	98.31 81	69.00 431	99.16 163	94.18 171	95.87 239	99.12 94

MVStest1		82.38 449	80.04 453	89.37 447	87.63 491	82.83 424	95.03 384	93.37 457	73.90 487	73.50 490	94.35 361	62.89 470	93.25 488	73.80 472	65.92 498	92.04 473

FE-MVSNET		83.85 440	81.97 446	89.51 445	87.19 493	83.19 420	95.21 376	93.17 458	83.45 440	78.90 477	89.05 468	65.46 458	93.84 483	69.71 488	75.56 465	91.51 477

Patchmatch-RL test		87.38 398	86.24 400	90.81 426	88.74 481	78.40 473	88.12 498	93.17 458	87.11 378	82.17 459	89.29 466	81.95 271	95.60 459	88.64 308	77.02 458	98.41 201

ttmdpeth		85.91 427	84.76 423	89.36 448	89.14 473	80.25 456	95.66 348	93.16 460	83.77 432	83.39 450	95.26 315	66.24 453	95.26 467	80.65 432	75.57 464	92.57 459

test-LLR		91.42 305	91.19 282	92.12 390	94.59 382	80.66 446	94.29 415	92.98 461	91.11 238	90.76 298	92.37 430	79.02 331	98.07 326	88.81 303	96.74 207	97.63 265

test-mter		90.19 358	89.54 357	92.12 390	94.59 382	80.66 446	94.29 415	92.98 461	87.68 365	90.76 298	92.37 430	67.67 440	98.07 326	88.81 303	96.74 207	97.63 265

WB-MVSnew		89.88 366	89.56 356	90.82 425	94.57 385	83.06 422	95.65 349	92.85 463	87.86 355	90.83 297	94.10 378	79.66 318	96.88 434	76.34 458	94.19 280	92.54 461

testing3		87.67 394	86.88 395	90.05 438	96.14 293	80.71 445	97.10 209	92.85 463	90.15 277	87.54 387	94.55 348	55.70 484	94.10 477	73.77 473	94.10 284	95.35 365

test_method		66.11 474	64.89 474	69.79 497	72.62 527	35.23 535	65.19 525	92.83 465	20.35 531	65.20 499	88.08 477	43.14 499	82.70 512	73.12 476	63.46 500	91.45 481

test0.0.03 1		89.37 376	88.70 374	91.41 412	92.47 446	85.63 379	95.22 374	92.70 466	91.11 238	86.91 406	93.65 399	79.02 331	93.19 490	78.00 450	89.18 356	95.41 358

new_pmnet		82.89 447	81.12 452	88.18 456	89.63 470	80.18 457	91.77 469	92.57 467	76.79 483	75.56 486	88.23 475	61.22 475	94.48 472	71.43 481	82.92 434	89.87 487

mvsany_test1		93.93 193	93.98 171	93.78 320	94.94 365	86.80 346	94.62 395	92.55 468	88.77 328	96.85 85	98.49 58	88.98 101	98.08 322	95.03 132	95.62 247	96.46 314

0.4-1-1-0.2		86.27 420	83.62 434	94.20 289	90.38 464	87.69 324	91.04 476	92.52 469	83.43 441	85.22 431	81.49 505	65.31 460	98.29 298	88.90 302	74.30 471	96.64 307

0.3-1-1-0.015		86.11 424	83.37 435	94.34 281	90.58 463	88.02 313	91.64 470	92.45 470	83.56 438	84.46 436	81.84 503	62.73 471	98.31 295	88.98 299	74.09 472	96.70 306

thisisatest0515		92.29 263	91.30 276	95.25 222	96.60 238	88.90 274	94.36 410	92.32 471	87.92 351	93.43 230	94.57 347	77.28 356	99.00 191	89.42 284	95.86 240	97.86 254

0.4-1-1-0.1		86.83 409	84.27 429	94.50 271	91.39 457	88.23 302	92.62 462	92.27 472	84.04 427	86.01 420	83.30 500	65.29 461	98.31 295	89.08 296	74.45 469	96.96 298

thisisatest0530		93.03 231	92.21 243	95.49 207	97.07 182	89.11 264	97.49 164	92.19 473	90.16 276	94.09 207	96.41 253	76.43 365	99.05 187	90.38 262	95.68 245	98.31 214

tttt0517		92.96 234	92.33 240	94.87 245	97.11 180	87.16 338	97.97 78	92.09 474	90.63 259	93.88 214	97.01 216	76.50 362	99.06 184	90.29 265	95.45 254	98.38 204

K. test v3		87.64 395	86.75 397	90.32 434	93.02 433	79.48 467	96.61 269	92.08 475	90.66 257	80.25 471	94.09 380	67.21 444	96.65 441	85.96 370	80.83 442	94.83 402

TESTMET0.1,1		90.06 360	89.42 360	91.97 393	94.41 390	80.62 448	94.29 415	91.97 476	87.28 375	90.44 302	92.47 429	68.79 432	97.67 379	88.50 310	96.60 215	97.61 269

PM-MVS		83.48 442	81.86 448	88.31 454	87.83 489	77.59 475	93.43 444	91.75 477	86.91 380	80.63 467	89.91 461	44.42 498	95.84 453	85.17 382	76.73 461	91.50 479

baseline2		91.63 290	90.86 294	93.94 310	94.33 392	86.32 361	95.92 330	91.64 478	89.37 302	86.94 404	94.69 340	81.62 278	98.69 246	88.64 308	94.57 273	96.81 302

ArgMatch-Sym		83.08 446	81.73 449	87.11 462	91.53 455	76.72 478	92.86 456	91.54 479	83.66 435	82.34 457	93.45 409	44.99 496	92.15 493	81.78 418	73.46 475	92.47 464

APD_test1		79.31 455	77.70 457	84.14 470	89.11 475	69.07 497	92.36 467	91.50 480	69.07 495	73.87 488	92.63 425	39.93 500	94.32 474	70.54 487	80.25 444	89.02 491

FPMVS		71.27 463	69.85 464	75.50 489	74.64 519	59.03 514	91.30 472	91.50 480	58.80 506	57.92 509	88.28 474	29.98 506	85.53 508	53.43 511	82.84 435	81.95 506

ArgMatch-SfM		83.09 445	81.67 450	87.34 461	91.48 456	76.29 481	92.76 459	91.31 482	84.26 423	81.99 461	93.35 414	45.52 495	92.98 491	81.83 417	72.49 478	92.76 455

door								91.13 483

door-mid								91.06 484

EGC-MVSNET		68.77 470	63.01 478	86.07 469	92.49 445	82.24 434	93.96 424	90.96 485	0.71 551	2.62 552	90.89 452	53.66 487	93.46 484	57.25 507	84.55 416	82.51 505

mvsany_test3		83.59 441	82.44 443	87.03 464	83.80 500	73.82 488	93.70 435	90.92 486	86.42 389	82.51 456	90.26 457	46.76 494	95.71 455	90.82 248	76.76 460	91.57 476

pmmvs3		79.97 454	77.50 458	87.39 460	82.80 506	79.38 468	92.70 461	90.75 487	70.69 494	78.66 478	87.47 484	51.34 490	93.40 485	73.39 475	69.65 489	89.38 490

UWE-MVS		89.91 363	89.48 359	91.21 416	95.88 305	78.23 474	94.91 388	90.26 488	89.11 309	92.35 254	94.52 350	68.76 433	97.96 345	83.95 397	95.59 248	97.42 278

DSMNet-mixed		86.34 418	86.12 403	87.00 465	89.88 469	70.43 493	94.93 387	90.08 489	77.97 480	85.42 429	92.78 421	74.44 383	93.96 481	74.43 468	95.14 259	96.62 308

MVS-HIRNet		82.47 448	81.21 451	86.26 468	95.38 332	69.21 496	88.96 490	89.49 490	66.28 498	80.79 466	74.08 514	68.48 437	97.39 414	71.93 480	95.47 253	92.18 470

WB-MVS		76.77 457	76.63 460	77.18 483	85.32 497	56.82 517	94.53 399	89.39 491	82.66 453	71.35 492	89.18 467	75.03 376	88.88 500	35.42 519	66.79 495	85.84 497

test1111		93.19 223	92.82 217	94.30 286	97.58 161	84.56 402	98.21 48	89.02 492	93.53 118	94.58 190	98.21 88	72.69 398	99.05 187	93.06 199	98.48 130	99.28 77

SSC-MVS		76.05 458	75.83 461	76.72 487	84.77 498	56.22 518	94.32 413	88.96 493	81.82 459	70.52 493	88.91 469	74.79 380	88.71 501	33.69 521	64.71 499	85.23 500

ECVR-MVS		93.19 223	92.73 223	94.57 267	97.66 149	85.41 385	98.21 48	88.23 494	93.43 124	94.70 187	98.21 88	72.57 399	99.07 182	93.05 200	98.49 128	99.25 80

EPMVS		90.70 341	89.81 347	93.37 347	94.73 377	84.21 406	93.67 438	88.02 495	89.50 297	92.38 251	93.49 406	77.82 353	97.78 369	86.03 368	92.68 308	98.11 235

ANet_high		63.94 478	59.58 481	77.02 484	61.24 536	66.06 502	85.66 504	87.93 496	78.53 478	42.94 519	71.04 516	25.42 510	80.71 516	52.60 512	30.83 527	84.28 502

PMMVS2		70.19 466	66.92 470	80.01 477	76.35 517	65.67 503	86.22 502	87.58 497	64.83 502	62.38 503	80.29 509	26.78 508	88.49 503	63.79 496	54.07 509	85.88 496

LoFTR		72.43 462	68.71 468	83.60 472	85.67 496	65.61 504	88.04 499	87.40 498	66.11 499	55.94 512	85.54 494	25.43 509	95.55 462	60.87 501	63.38 501	89.63 488

lessismore_v0				90.45 432	91.96 453	79.09 471		87.19 499		80.32 470	94.39 358	66.31 452	97.55 394	84.00 396	76.84 459	94.70 418

PMVS	53.92 22	58.58 481	55.40 484	68.12 499	51.00 549	48.64 523	78.86 511	87.10 500	46.77 517	35.84 526	74.28 513	8.76 535	86.34 506	42.07 516	73.91 473	69.38 515
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 411	86.41 398	88.02 457	92.87 436	74.60 486	95.38 363	86.70 501	88.17 344	87.28 395	94.67 343	70.83 414	93.30 487	67.45 490	94.31 276	96.17 320

test_vis1_rt		86.16 422	85.06 418	89.46 446	93.47 422	80.46 450	96.41 283	86.61 502	85.22 409	79.15 476	88.64 471	52.41 489	97.06 425	93.08 198	90.57 342	90.87 483

testf1		69.31 468	66.76 471	76.94 485	78.61 515	61.93 508	88.27 496	86.11 503	55.62 509	59.69 504	85.31 496	20.19 518	89.32 497	57.62 505	69.44 491	79.58 508

APD_test2		69.31 468	66.76 471	76.94 485	78.61 515	61.93 508	88.27 496	86.11 503	55.62 509	59.69 504	85.31 496	20.19 518	89.32 497	57.62 505	69.44 491	79.58 508

gg-mvs-nofinetune		87.82 392	85.61 406	94.44 275	94.46 387	89.27 258	91.21 475	84.61 505	80.88 464	89.89 322	74.98 512	71.50 407	97.53 401	85.75 373	97.21 185	96.51 310

MatchFormer		67.84 473	63.81 477	79.93 478	83.26 505	60.99 512	87.61 500	84.49 506	54.89 512	51.76 513	81.06 506	22.08 516	94.10 477	50.36 513	58.82 505	84.72 501

dmvs_testset		81.38 451	82.60 442	77.73 482	91.74 454	51.49 520	93.03 453	84.21 507	89.07 310	78.28 480	91.25 451	76.97 358	88.53 502	56.57 508	82.24 437	93.16 449

GG-mvs-BLEND				93.62 333	93.69 410	89.20 260	92.39 466	83.33 508		87.98 381	89.84 462	71.00 412	96.87 435	82.08 416	95.40 255	94.80 410

MTMP							97.86 92	82.03 509

DeepMVS_CX				74.68 492	90.84 462	64.34 507		81.61 510	65.34 500	67.47 497	88.01 478	48.60 493	80.13 517	62.33 499	73.68 474	79.58 508

DenseAffine		72.53 461	69.17 467	82.59 474	87.49 492	70.91 492	88.38 495	81.13 511	67.58 497	64.27 502	87.44 485	23.61 514	88.47 504	66.10 493	56.56 506	88.38 492

MASt3R-SfM		71.17 464	70.37 463	73.55 493	74.50 520	51.20 521	82.17 509	80.88 512	64.49 503	72.54 491	91.37 449	25.17 511	81.85 513	75.86 460	66.37 497	87.59 493

E-PMN		53.28 483	52.56 486	55.43 504	74.43 521	47.13 528	83.63 508	76.30 513	42.23 518	42.59 520	62.22 523	28.57 507	74.40 521	31.53 522	31.51 525	44.78 527

test2506		91.60 292	90.78 299	94.04 300	97.66 149	83.81 411	98.27 37	75.53 514	93.43 124	95.23 165	98.21 88	67.21 444	99.07 182	93.01 203	98.49 128	99.25 80

EMVS		52.08 486	51.31 488	54.39 506	72.62 527	45.39 530	83.84 507	75.51 515	41.13 519	40.77 522	59.65 525	30.08 505	73.60 522	28.31 524	29.90 531	44.18 528

ELoFTR		60.03 480	55.86 483	72.52 494	67.65 531	48.49 524	76.21 514	75.14 516	53.94 513	45.93 517	79.98 510	9.14 534	85.06 509	55.39 509	39.36 522	84.02 503

test_vis3_rt		72.73 459	70.55 462	79.27 479	80.02 512	68.13 499	93.92 427	74.30 517	76.90 482	58.99 508	73.58 515	20.29 517	95.37 465	84.16 392	72.80 477	74.31 511

RoMa-SfM		70.64 465	67.48 469	80.09 476	84.70 499	66.61 501	88.62 493	73.09 518	65.10 501	64.98 501	88.91 469	22.38 515	87.00 505	63.51 497	56.06 507	86.67 495

MVE	50.73 23	53.25 484	48.81 489	66.58 502	65.34 532	57.50 516	72.49 515	70.94 519	40.15 520	39.28 523	63.51 520	6.89 538	73.48 523	38.29 517	42.38 519	68.76 517
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DKM		67.96 471	64.19 476	79.27 479	83.41 503	64.35 506	86.88 501	68.11 520	63.15 504	59.36 506	86.08 493	16.45 526	86.15 507	64.54 495	49.73 511	87.32 494

tmp_tt		51.94 487	53.82 485	46.29 509	33.73 554	45.30 531	78.32 512	67.24 521	18.02 533	50.93 515	87.05 488	52.99 488	53.11 528	70.76 484	25.29 536	40.46 530

kuosan		65.27 475	64.66 475	67.11 501	83.80 500	61.32 511	88.53 494	60.77 522	68.22 496	67.67 495	80.52 508	49.12 492	70.76 524	29.67 523	53.64 510	69.26 516

dongtai		69.99 467	69.33 466	71.98 495	88.78 478	61.64 510	89.86 485	59.93 523	75.67 484	74.96 487	85.45 495	50.19 491	81.66 514	43.86 515	55.27 508	72.63 514

RoMa-HiRes		64.40 476	60.91 479	74.89 491	78.66 514	58.85 515	85.22 505	58.46 524	58.65 507	59.29 507	86.60 492	16.97 523	83.91 510	59.14 503	45.20 514	81.91 507

DKM-HiRes		64.02 477	59.97 480	76.17 488	79.46 513	59.20 513	84.48 506	58.37 525	58.52 508	56.03 511	83.71 499	13.19 532	83.72 511	60.49 502	45.50 513	85.59 498

GLUNet-SfM		46.44 489	41.21 498	62.14 503	51.92 546	38.44 534	58.72 527	57.51 526	34.08 521	34.61 527	67.84 518	11.40 533	74.90 520	35.48 518	19.30 541	73.08 513

PDCNetPlus		61.05 479	58.26 482	69.44 498	75.52 518	55.68 519	81.49 510	51.76 527	62.45 505	51.54 514	82.02 502	23.69 513	78.90 518	65.91 494	29.91 530	73.74 512

PMatch-SfM		57.38 482	52.53 487	71.95 496	68.62 530	49.38 522	77.61 513	45.82 528	52.41 515	46.59 516	82.04 501	4.86 549	81.03 515	58.34 504	36.49 524	85.43 499

ALIKED-LG		47.63 488	45.22 491	54.88 505	81.48 509	48.47 525	71.83 517	45.44 529	32.66 522	37.07 524	63.26 522	19.21 520	63.71 525	15.49 533	40.53 520	52.46 524

N_pmnet		78.73 456	78.71 456	78.79 481	92.80 439	46.50 529	94.14 419	43.71 530	78.61 477	80.83 465	91.66 447	74.94 379	96.36 445	67.24 491	84.45 418	93.50 445

ALIKED-NN		46.19 490	43.87 492	53.16 508	80.39 511	47.77 526	69.82 523	43.65 531	27.89 523	36.60 525	63.35 521	17.30 522	61.29 527	15.84 532	39.98 521	50.41 526

ALIKED-MNN		45.42 491	42.62 494	53.80 507	80.52 510	47.58 527	70.83 520	43.05 532	27.21 524	34.32 528	61.10 524	14.85 529	62.94 526	14.90 534	36.82 523	50.89 525

SP-DiffGlue		43.94 492	43.32 493	45.79 512	47.79 551	33.03 536	63.37 526	42.65 533	25.71 525	41.26 521	69.27 517	18.83 521	38.88 535	34.96 520	46.05 512	65.47 522

SP-SuperGlue		43.33 494	42.50 495	45.81 511	73.95 524	31.24 539	71.34 518	41.17 534	23.96 526	33.42 529	56.47 527	16.72 525	39.64 533	21.11 528	44.32 516	66.57 519

SP-LightGlue		43.37 493	42.49 496	46.03 510	74.26 522	31.37 538	71.24 519	40.98 535	23.86 527	33.18 530	56.34 529	16.78 524	39.73 532	21.09 529	44.68 515	66.97 518

SP-MNN		42.11 496	40.98 499	45.49 513	72.87 525	30.19 543	70.72 521	39.96 536	20.98 529	30.21 533	55.72 531	15.26 528	40.07 531	19.70 531	43.42 518	66.21 520

XFeat-MNN		35.01 497	34.34 500	37.02 515	42.54 552	25.71 550	54.01 529	39.41 537	20.70 530	30.13 534	55.85 530	14.08 530	44.62 529	22.90 526	29.45 534	40.75 529

SP-NN		42.37 495	41.40 497	45.29 514	72.86 526	30.45 541	70.32 522	39.16 538	22.21 528	31.32 531	56.73 526	15.45 527	39.53 534	20.27 530	44.25 517	65.88 521

XFeat-NN		33.93 498	33.70 501	34.60 516	41.69 553	24.48 551	51.85 530	36.02 539	19.55 532	31.20 532	56.38 528	13.46 531	40.91 530	22.51 527	30.65 528	38.42 531

PMatch-Up-SfM		52.53 485	47.58 490	67.36 500	63.24 534	43.29 532	72.10 516	34.71 540	47.03 516	43.51 518	79.07 511	3.90 552	75.83 519	54.68 510	30.02 529	82.95 504

SIFT-NN		28.47 499	28.54 503	28.27 517	64.38 533	31.62 537	48.50 531	24.78 541	14.32 534	19.55 535	40.46 532	7.22 536	31.96 537	6.20 537	31.47 526	21.24 532

SIFT-MNN		27.50 500	27.40 504	27.80 518	61.71 535	30.57 540	46.59 532	24.66 542	14.04 535	17.35 536	39.90 533	6.52 539	31.80 538	6.13 538	29.65 532	21.04 533

SIFT-NN-NCMNet		27.16 501	27.05 505	27.51 519	59.97 538	30.42 542	46.49 533	24.52 543	13.94 537	17.23 537	39.47 534	6.39 540	31.40 539	5.94 539	29.49 533	20.72 535

SIFT-NN-UMatch		25.24 504	25.01 508	25.92 524	54.55 544	27.33 547	44.97 534	22.85 544	13.97 536	13.40 541	39.41 535	6.28 541	30.23 542	5.83 540	23.82 537	20.21 536

SIFT-NCM-Cal		25.87 502	25.57 506	26.75 520	60.60 537	29.37 544	44.96 535	22.64 545	13.57 540	11.67 544	37.90 539	5.81 544	31.26 540	5.32 545	27.70 535	19.63 538

SIFT-NN-CMatch		25.59 503	25.23 507	26.67 522	56.47 542	28.89 546	42.75 536	22.52 546	13.89 538	16.98 538	39.39 536	6.26 542	30.38 541	5.77 541	22.99 538	20.75 534

SIFT-ConvMatch		24.62 506	24.14 510	26.03 523	58.66 539	29.15 545	40.80 539	21.31 547	13.69 539	13.51 540	38.52 537	5.65 545	30.22 543	5.51 544	19.65 540	18.73 540

SIFT-NN-PointCN		23.81 508	23.84 511	23.73 527	52.41 545	22.80 553	42.30 538	20.98 548	13.02 544	15.14 539	37.74 541	6.20 543	28.40 546	5.52 543	21.24 539	19.98 537

SIFT-UMatch		24.03 507	23.67 512	25.10 525	57.10 541	26.49 549	42.43 537	20.05 549	13.49 541	12.40 543	38.51 538	5.45 547	30.07 544	5.56 542	18.08 542	18.74 539

SIFT-CM-Cal		23.18 510	22.70 513	24.60 526	57.42 540	26.79 548	37.63 541	18.36 550	13.35 542	12.57 542	37.37 542	5.54 546	28.79 545	5.17 547	16.92 545	18.23 541

SIFT-PointCN		20.70 512	20.89 515	20.14 529	51.62 548	18.11 554	37.52 542	17.71 551	12.03 546	10.05 548	33.23 544	4.33 551	25.40 549	4.55 549	16.94 544	16.90 543

SIFT-UM-Cal		22.52 511	22.27 514	23.27 528	56.41 543	23.87 552	39.94 540	16.81 552	13.33 543	10.54 545	37.90 539	5.16 548	28.36 547	5.23 546	15.12 546	17.57 542

SIFT-PCN-Cal		20.26 513	20.34 516	20.01 530	51.70 547	17.74 555	35.64 543	16.15 553	11.90 547	10.28 547	33.69 543	4.55 550	25.68 548	4.57 548	14.59 547	16.60 544

SIFT-NCMNet		17.70 514	17.74 517	17.60 531	49.47 550	16.50 556	30.22 544	10.39 554	11.77 548	8.79 549	29.74 546	3.61 554	22.42 550	3.97 550	11.69 548	13.89 545

wuyk23d		25.11 505	24.57 509	26.74 521	73.98 523	39.89 533	57.88 528	9.80 555	12.27 545	10.39 546	6.97 551	7.03 537	36.44 536	25.43 525	17.39 543	3.89 548

testmvs		13.36 515	16.33 518	4.48 533	5.04 555	2.26 558	93.18 447	3.28 556	2.70 549	8.24 550	21.66 547	2.29 555	2.19 551	7.58 535	2.96 549	9.00 547

test123		13.04 516	15.66 519	5.18 532	4.51 556	3.45 557	92.50 465	1.81 557	2.50 550	7.58 551	20.15 548	3.67 553	2.18 552	7.13 536	1.07 550	9.90 546

mmdepth		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

uanet_test		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

pcd_1.5k_mvsjas		7.39 518	9.85 521	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	88.65 109	0.00 553	0.00 551	0.00 551	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

n2								0.00 558

nn								0.00 558

ab-mvs-re		8.06 517	10.74 520	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	96.69 233	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

WAC-MVS						79.53 464								75.56 464

PC_three_1452									90.77 249	98.89 27	98.28 86	96.24 1	98.35 291	95.76 106	99.58 23	99.59 32

eth-test2					0.00 557

eth-test					0.00 557

OPU-MVS				98.55 3	98.82 61	96.86 3	98.25 40				98.26 87	96.04 2	99.24 151	95.36 124	99.59 19	99.56 40

test_0728_THIRD									94.78 63	98.73 31	98.87 33	95.87 4	99.84 26	97.45 45	99.72 2	99.77 4

GSMVS																98.45 196

test_part2					99.28 30	95.74 9				98.10 49

sam_mvs1												82.76 251				98.45 196

sam_mvs												81.94 272

test_post1							92.81 458				16.58 550	80.53 300	97.68 378	86.20 362

test_post											17.58 549	81.76 275	98.08 322

patchmatchnet-post											90.45 456	82.65 256	98.10 317

gm-plane-assit					93.22 429	78.89 472			84.82 417		93.52 405		98.64 258	87.72 323

test9_res														94.81 148	99.38 63	99.45 59

agg_prior2														93.94 176	99.38 63	99.50 52

test_prior4						93.66 63	96.42 282

test_prior2							96.35 292		92.80 160	96.03 128	97.59 170	92.01 50		95.01 133	99.38 63

旧先验2							95.94 328		81.66 460	97.34 71			98.82 210	92.26 210

新几何2							95.79 339

原ACMM2							95.67 345

testdata2													99.67 77	85.96 370

segment_acmp												92.89 33

testdata1							95.26 372		93.10 141

plane_prior7					96.21 279	89.98 219

plane_prior6					96.10 298	90.00 215						81.32 282

plane_prior4											96.64 236

plane_prior3						90.00 215			94.46 80	91.34 283

plane_prior2							97.74 114		94.85 55

plane_prior1					96.14 293

plane_prior						89.99 217	97.24 194		94.06 95						92.16 317

HQP5-MVS						89.33 253

HQP-NCC					95.86 306		96.65 263		93.55 114	90.14 307

ACMP_Plane					95.86 306		96.65 263		93.55 114	90.14 307

BP-MVS														92.13 218

HQP4-MVS										90.14 307			98.50 276			95.78 339

HQP2-MVS												80.95 288

NP-MVS					95.99 304	89.81 227					95.87 280

MDTV_nov1_ep13_2view						70.35 494	93.10 452		83.88 430	93.55 223		82.47 260		86.25 361		98.38 204

ACMMP++_ref															90.30 347

ACMMP++															91.02 336

Test By Simon												88.73 108

High-resolution multi-view benchmark