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.

CHOSEN 1792x2688		97.12 113	96.80 110	98.08 128	99.30 68	94.56 224	98.05 245	99.71 1	93.57 229	97.09 154	98.91 117	88.17 216	99.89 47	96.87 128	99.56 86	99.81 17

HyFIR lowres test		96.90 121	96.49 127	98.14 119	99.33 59	95.56 171	97.38 300	99.65 2	92.34 277	97.61 142	98.20 196	89.29 185	99.10 202	96.97 116	97.60 187	99.77 27

MVS_111021_LR		98.34 52	98.23 47	98.67 74	99.27 78	96.90 101	97.95 254	99.58 3	97.14 58	98.44 91	99.01 102	95.03 73	99.62 137	97.91 66	99.75 41	99.50 91

MVS_111021_HR		98.47 37	98.34 35	98.88 66	99.22 89	97.32 81	97.91 258	99.58 3	97.20 53	98.33 97	99.00 103	95.99 36	99.64 131	98.05 59	99.76 37	99.69 56

PGM-MVS		98.49 34	98.23 47	99.27 34	99.72 12	98.08 56	98.99 81	99.49 5	95.43 135	99.03 47	99.32 49	95.56 48	99.94 8	96.80 133	99.77 31	99.78 21

ACMMP		98.23 56	97.95 62	99.09 52	99.74 7	97.62 71	99.03 71	99.41 6	95.98 107	97.60 143	99.36 42	94.45 85	99.93 25	97.14 110	98.85 135	99.70 53
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
fmvsm_s_conf0.5_n		98.42 43	98.51 18	98.13 122	99.30 68	95.25 187	98.85 118	99.39 7	97.94 14	99.74 9	99.62 3	92.59 110	99.91 39	99.65 7	99.52 92	99.25 133

fmvsm_s_conf0.5_n_a		98.38 46	98.42 25	98.27 107	99.09 105	95.41 178	98.86 116	99.37 8	97.69 21	99.78 6	99.61 4	92.38 113	99.91 39	99.58 10	99.43 104	99.49 96

test_fmvsm_n_1920		98.87 10	99.01 3	98.45 93	99.42 55	96.43 126	98.96 89	99.36 9	98.63 5	99.86 2	99.51 13	95.91 39	99.97 1	99.72 5	99.75 41	98.94 174

test_fmvsmconf_n		98.92 7	98.87 6	99.04 55	98.88 125	97.25 88	98.82 126	99.34 10	98.75 3	99.80 5	99.61 4	95.16 68	99.95 7	99.70 6	99.80 19	99.93 1

CSCG		97.85 70	97.74 67	98.20 116	99.67 25	95.16 191	99.22 35	99.32 11	93.04 252	97.02 160	98.92 116	95.36 57	99.91 39	97.43 101	99.64 68	99.52 86

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 47	99.41 56	97.54 74	98.89 103	99.31 12	98.49 8	99.86 2	99.42 29	96.45 24	99.96 4	99.86 1	99.74 45	99.90 3

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 51	99.43 54	97.48 76	98.88 108	99.30 13	98.47 9	99.85 4	99.43 28	96.71 17	99.96 4	99.86 1	99.80 19	99.89 5

patch_mono-2		98.36 49	98.87 6	96.82 212	99.53 36	90.68 317	98.64 169	99.29 14	97.88 15	99.19 40	99.52 11	96.80 15	99.97 1	99.11 16	99.86 1	99.82 16

PVSNet_BlendedMVS		96.73 127	96.60 122	97.12 191	99.25 81	95.35 183	98.26 221	99.26 15	94.28 187	97.94 119	97.46 258	92.74 108	99.81 81	96.88 125	93.32 272	96.20 337

PVSNet_Blended		97.38 100	97.12 96	98.14 119	99.25 81	95.35 183	97.28 311	99.26 15	93.13 248	97.94 119	98.21 195	92.74 108	99.81 81	96.88 125	99.40 109	99.27 129

fmvsm_s_conf0.1_n		98.18 58	98.21 50	98.11 126	98.54 157	95.24 188	98.87 113	99.24 17	97.50 31	99.70 13	99.67 1	91.33 145	99.89 47	99.47 12	99.54 89	99.21 138

UniMVSNet_NR-MVSNet		95.71 177	95.15 187	97.40 176	96.84 291	96.97 97	98.74 146	99.24 17	95.16 151	93.88 265	97.72 237	91.68 133	98.31 300	95.81 163	87.25 348	96.92 260

WR-MVS_H		95.05 217	94.46 221	96.81 213	96.86 290	95.82 163	99.24 30	99.24 17	93.87 206	92.53 312	96.84 313	90.37 165	98.24 308	93.24 243	87.93 339	96.38 330

SDMVSNet		96.85 123	96.42 128	98.14 119	99.30 68	96.38 130	99.21 38	99.23 20	95.92 110	95.96 202	98.76 136	85.88 262	99.44 167	97.93 64	95.59 232	98.60 199

FC-MVSNet-test		96.42 140	96.05 143	97.53 168	96.95 283	97.27 83	99.36 15	99.23 20	95.83 117	93.93 262	98.37 176	92.00 126	98.32 298	96.02 157	92.72 282	97.00 254

VPA-MVSNet		95.75 174	95.11 191	97.69 156	97.24 263	97.27 83	98.94 93	99.23 20	95.13 152	95.51 208	97.32 267	85.73 265	98.91 229	97.33 106	89.55 319	96.89 268

FIs		96.51 137	96.12 140	97.67 158	97.13 274	97.54 74	99.36 15	99.22 23	95.89 113	94.03 258	98.35 178	91.98 127	98.44 279	96.40 145	92.76 281	97.01 253

tfpnnormal		93.66 286	92.70 296	96.55 241	96.94 284	95.94 154	98.97 84	99.19 24	91.04 318	91.38 330	97.34 265	84.94 281	98.61 258	85.45 356	89.02 329	95.11 358

UniMVSNet (Re)		95.78 173	95.19 186	97.58 165	96.99 281	97.47 78	98.79 140	99.18 25	95.60 127	93.92 263	97.04 293	91.68 133	98.48 272	95.80 165	87.66 342	96.79 280

fmvsm_s_conf0.1_n_a		98.08 59	98.04 59	98.21 114	97.66 231	95.39 179	98.89 103	99.17 26	97.24 50	99.76 8	99.67 1	91.13 150	99.88 56	99.39 13	99.41 106	99.35 115

PVSNet_Blended_VisFu		97.70 77	97.46 82	98.44 95	99.27 78	95.91 159	98.63 172	99.16 27	94.48 183	97.67 136	98.88 119	92.80 107	99.91 39	97.11 111	99.12 121	99.50 91

test_fmvsmvis_n_1920		98.44 40	98.51 18	98.23 113	98.33 177	96.15 141	98.97 84	99.15 28	98.55 7	98.45 89	99.55 6	94.26 91	99.97 1	99.65 7	99.66 61	98.57 204

CHOSEN 280x420		97.18 110	97.18 95	97.20 184	98.81 133	93.27 271	95.78 366	99.15 28	95.25 147	96.79 173	98.11 202	92.29 116	99.07 205	98.56 29	99.85 5	99.25 133

D2MVS		95.18 210	95.08 192	95.48 292	97.10 276	92.07 290	98.30 215	99.13 30	94.02 196	92.90 300	96.73 316	89.48 179	98.73 249	94.48 206	93.60 265	95.65 350

PHI-MVS		98.34 52	98.06 57	99.18 42	99.15 100	98.12 55	99.04 68	99.09 31	93.32 238	98.83 64	99.10 86	96.54 21	99.83 69	97.70 84	99.76 37	99.59 79

sd_testset		96.17 152	95.76 156	97.42 173	99.30 68	94.34 233	98.82 126	99.08 32	95.92 110	95.96 202	98.76 136	82.83 314	99.32 174	95.56 173	95.59 232	98.60 199

UA-Net		97.96 63	97.62 70	98.98 59	98.86 128	97.47 78	98.89 103	99.08 32	96.67 80	98.72 72	99.54 8	93.15 104	99.81 81	94.87 190	98.83 136	99.65 69

PatchMatch-RL		96.59 132	96.03 145	98.27 107	99.31 64	96.51 122	97.91 258	99.06 34	93.72 216	96.92 165	98.06 205	88.50 211	99.65 129	91.77 285	99.00 127	98.66 195

3Dnovator	94.51 5	97.46 91	96.93 105	99.07 53	97.78 219	97.64 69	99.35 17	99.06 34	97.02 64	93.75 272	99.16 77	89.25 187	99.92 31	97.22 109	99.75 41	99.64 71

MSLP-MVS++		98.56 29	98.57 15	98.55 81	99.26 80	96.80 105	98.71 155	99.05 36	97.28 45	98.84 62	99.28 54	96.47 23	99.40 168	98.52 36	99.70 54	99.47 100

PS-CasMVS		94.67 238	93.99 248	96.71 217	96.68 300	95.26 186	99.13 52	99.03 37	93.68 222	92.33 318	97.95 216	85.35 273	98.10 316	93.59 235	88.16 338	96.79 280

TranMVSNet+NR-MVSNet		95.14 212	94.48 219	97.11 192	96.45 313	96.36 132	99.03 71	99.03 37	95.04 159	93.58 275	97.93 217	88.27 214	98.03 322	94.13 217	86.90 353	96.95 259

PEN-MVS		94.42 257	93.73 268	96.49 245	96.28 320	94.84 208	99.17 45	99.00 39	93.51 230	92.23 320	97.83 229	86.10 258	97.90 331	92.55 266	86.92 352	96.74 285

Vis-MVSNet		97.42 97	97.11 97	98.34 103	98.66 147	96.23 137	99.22 35	99.00 39	96.63 82	98.04 108	99.21 65	88.05 221	99.35 171	96.01 158	99.21 117	99.45 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DU-MVS		95.42 193	94.76 206	97.40 176	96.53 307	96.97 97	98.66 167	98.99 41	95.43 135	93.88 265	97.69 240	88.57 206	98.31 300	95.81 163	87.25 348	96.92 260

test_fmvsmconf0.1_n		98.58 23	98.44 24	98.99 57	97.73 225	97.15 93	98.84 122	98.97 42	98.75 3	99.43 27	99.54 8	93.29 102	99.93 25	99.64 9	99.79 25	99.89 5

VPNet		94.99 220	94.19 233	97.40 176	97.16 272	96.57 118	98.71 155	98.97 42	95.67 125	94.84 219	98.24 194	80.36 330	98.67 255	96.46 142	87.32 347	96.96 257

OpenMVS	93.04 13	95.83 171	95.00 195	98.32 104	97.18 271	97.32 81	99.21 38	98.97 42	89.96 335	91.14 332	99.05 97	86.64 248	99.92 31	93.38 239	99.47 99	97.73 231

HFP-MVS		98.63 17	98.40 26	99.32 28	99.72 12	98.29 44	99.23 31	98.96 45	96.10 104	98.94 53	99.17 74	96.06 32	99.92 31	97.62 88	99.78 29	99.75 35

FOURS1					99.82 1	98.66 24	99.69 1	98.95 46	97.46 34	99.39 30

ACMMPR		98.59 21	98.36 30	99.29 29	99.74 7	98.15 52	99.23 31	98.95 46	96.10 104	98.93 57	99.19 72	95.70 45	99.94 8	97.62 88	99.79 25	99.78 21

CP-MVSNet		94.94 226	94.30 229	96.83 211	96.72 298	95.56 171	99.11 55	98.95 46	93.89 204	92.42 317	97.90 219	87.19 239	98.12 315	94.32 211	88.21 336	96.82 279

NR-MVSNet		94.98 222	94.16 236	97.44 171	96.53 307	97.22 90	98.74 146	98.95 46	94.96 163	89.25 349	97.69 240	89.32 184	98.18 310	94.59 203	87.40 345	96.92 260

region2R		98.61 18	98.38 28	99.29 29	99.74 7	98.16 51	99.23 31	98.93 50	96.15 101	98.94 53	99.17 74	95.91 39	99.94 8	97.55 95	99.79 25	99.78 21

APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 33	98.96 16	99.39 12	98.93 50	97.38 39	99.41 28	99.54 8	96.66 18	99.84 67	98.86 21	99.85 5	99.87 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
VNet		97.79 72	97.40 86	98.96 61	98.88 125	97.55 73	98.63 172	98.93 50	96.74 77	99.02 48	98.84 123	90.33 167	99.83 69	98.53 30	96.66 206	99.50 91

UGNet		96.78 126	96.30 134	98.19 118	98.24 183	95.89 161	98.88 108	98.93 50	97.39 38	96.81 171	97.84 226	82.60 315	99.90 45	96.53 140	99.49 96	98.79 183
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
sss		97.39 99	96.98 104	98.61 77	98.60 153	96.61 114	98.22 223	98.93 50	93.97 200	98.01 114	98.48 162	91.98 127	99.85 63	96.45 143	98.15 167	99.39 112

QAPM		96.29 147	95.40 170	98.96 61	97.85 216	97.60 72	99.23 31	98.93 50	89.76 339	93.11 296	99.02 98	89.11 192	99.93 25	91.99 280	99.62 71	99.34 116

DPE-MVS		98.92 7	98.67 12	99.65 2	99.58 32	99.20 9	98.42 203	98.91 56	97.58 27	99.54 22	99.46 24	97.10 12	99.94 8	97.64 87	99.84 10	99.83 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
114514_t		96.93 119	96.27 135	98.92 63	99.50 41	97.63 70	98.85 118	98.90 57	84.80 373	97.77 126	99.11 84	92.84 106	99.66 128	94.85 191	99.77 31	99.47 100

LS3D		97.16 111	96.66 121	98.68 73	98.53 158	97.19 91	98.93 95	98.90 57	92.83 261	95.99 200	99.37 38	92.12 123	99.87 58	93.67 233	99.57 80	98.97 170

DELS-MVS		98.40 45	98.20 51	98.99 57	99.00 113	97.66 68	97.75 276	98.89 59	97.71 19	98.33 97	98.97 105	94.97 74	99.88 56	98.42 44	99.76 37	99.42 111
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
DP-MVS Recon		97.86 68	97.46 82	99.06 54	99.53 36	98.35 41	98.33 208	98.89 59	92.62 266	98.05 106	98.94 113	95.34 58	99.65 129	96.04 156	99.42 105	99.19 143

AdaColmap		97.15 112	96.70 117	98.48 90	99.16 98	96.69 111	98.01 249	98.89 59	94.44 185	96.83 168	98.68 142	90.69 161	99.76 107	94.36 208	99.29 116	98.98 169

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 94	99.23 7	99.69 1	98.88 62	97.32 42	99.53 23	99.47 20	97.81 3	99.94 8	98.47 38	99.72 51	99.74 37

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 84	98.88 62					99.94 8	98.47 38	99.81 12	99.84 12

test0726					99.72 12	99.25 2	99.06 63	98.88 62	97.62 24	99.56 20	99.50 15	97.42 9

MSP-MVS		98.74 13	98.55 17	99.29 29	99.75 3	98.23 46	99.26 27	98.88 62	97.52 29	99.41 28	98.78 130	96.00 35	99.79 98	97.79 76	99.59 76	99.85 10
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
Anonymous20231211		94.10 277	93.26 287	96.61 229	99.11 103	94.28 234	99.01 76	98.88 62	86.43 363	92.81 302	97.57 252	81.66 319	98.68 254	94.83 192	89.02 329	96.88 269

XVS		98.70 14	98.49 21	99.34 23	99.70 22	98.35 41	99.29 22	98.88 62	97.40 36	98.46 86	99.20 67	95.90 41	99.89 47	97.85 71	99.74 45	99.78 21

X-MVStestdata		94.06 281	92.30 304	99.34 23	99.70 22	98.35 41	99.29 22	98.88 62	97.40 36	98.46 86	43.50 396	95.90 41	99.89 47	97.85 71	99.74 45	99.78 21

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 74	98.87 69	97.65 22	99.73 10	99.48 18	97.53 7	99.94 8	98.43 42	99.81 12	99.70 53

test_241102_TWO								98.87 69	97.65 22	99.53 23	99.48 18	97.34 11	99.94 8	98.43 42	99.80 19	99.83 13

test_241102_ONE					99.71 19	99.24 5		98.87 69	97.62 24	99.73 10	99.39 32	97.53 7	99.74 111

CP-MVS		98.57 27	98.36 30	99.19 40	99.66 26	97.86 62	99.34 18	98.87 69	95.96 109	98.60 81	99.13 82	96.05 33	99.94 8	97.77 77	99.86 1	99.77 27

SteuartSystems-ACMMP		98.90 9	98.75 10	99.36 21	99.22 89	98.43 33	99.10 58	98.87 69	97.38 39	99.35 32	99.40 31	97.78 5	99.87 58	97.77 77	99.85 5	99.78 21
Skip Steuart: Steuart Systems R&D Blog.
DeepPCF-MVS	96.37 2	97.93 66	98.48 23	96.30 262	99.00 113	89.54 336	97.43 297	98.87 69	98.16 11	99.26 36	99.38 37	96.12 31	99.64 131	98.30 49	99.77 31	99.72 45

test_one_0601					99.66 26	99.25 2		98.86 75	97.55 28	99.20 38	99.47 20	97.57 6

ZNCC-MVS		98.49 34	98.20 51	99.35 22	99.73 11	98.39 34	99.19 42	98.86 75	95.77 119	98.31 99	99.10 86	95.46 51	99.93 25	97.57 94	99.81 12	99.74 37

DTE-MVSNet		93.98 283	93.26 287	96.14 267	96.06 329	94.39 230	99.20 40	98.86 75	93.06 251	91.78 326	97.81 231	85.87 263	97.58 345	90.53 304	86.17 357	96.46 327

SD-MVS		98.64 16	98.68 11	98.53 85	99.33 59	98.36 40	98.90 99	98.85 78	97.28 45	99.72 12	99.39 32	96.63 20	97.60 343	98.17 52	99.85 5	99.64 71
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
test_prior				99.19 40	99.31 64	98.22 47		98.84 79					99.70 119			99.65 69

Anonymous20240529		95.10 214	94.22 231	97.75 150	99.01 112	94.26 236	98.87 113	98.83 80	85.79 369	96.64 176	98.97 105	78.73 339	99.85 63	96.27 147	94.89 237	99.12 154

9.14			98.06 57		99.47 47		98.71 155	98.82 81	94.36 186	99.16 44	99.29 53	96.05 33	99.81 81	97.00 114	99.71 53

SR-MVS		98.57 27	98.35 32	99.24 36	99.53 36	98.18 49	99.09 59	98.82 81	96.58 83	99.10 46	99.32 49	95.39 54	99.82 76	97.70 84	99.63 69	99.72 45

GST-MVS		98.43 42	98.12 54	99.34 23	99.72 12	98.38 35	99.09 59	98.82 81	95.71 123	98.73 71	99.06 96	95.27 62	99.93 25	97.07 113	99.63 69	99.72 45

HPM-MVS_fast		98.38 46	98.13 53	99.12 50	99.75 3	97.86 62	99.44 11	98.82 81	94.46 184	98.94 53	99.20 67	95.16 68	99.74 111	97.58 91	99.85 5	99.77 27

APD-MVS		98.35 51	98.00 61	99.42 16	99.51 39	98.72 21	98.80 135	98.82 81	94.52 181	99.23 37	99.25 61	95.54 50	99.80 88	96.52 141	99.77 31	99.74 37
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SF-MVS		98.59 21	98.32 40	99.41 17	99.54 35	98.71 22	99.04 68	98.81 86	95.12 153	99.32 33	99.39 32	96.22 26	99.84 67	97.72 80	99.73 48	99.67 65

ACMMP_NAP		98.61 18	98.30 41	99.55 9	99.62 30	98.95 17	98.82 126	98.81 86	95.80 118	99.16 44	99.47 20	95.37 56	99.92 31	97.89 68	99.75 41	99.79 19

APD-MVS_3200maxsize		98.53 32	98.33 39	99.15 46	99.50 41	97.92 61	99.15 47	98.81 86	96.24 97	99.20 38	99.37 38	95.30 60	99.80 88	97.73 79	99.67 59	99.72 45

WR-MVS		95.15 211	94.46 221	97.22 183	96.67 301	96.45 124	98.21 224	98.81 86	94.15 190	93.16 292	97.69 240	87.51 233	98.30 302	95.29 182	88.62 333	96.90 267

mPP-MVS		98.51 33	98.26 43	99.25 35	99.75 3	98.04 57	99.28 24	98.81 86	96.24 97	98.35 96	99.23 62	95.46 51	99.94 8	97.42 102	99.81 12	99.77 27

CNVR-MVS		98.78 11	98.56 16	99.45 15	99.32 62	98.87 19	98.47 195	98.81 86	97.72 17	98.76 68	99.16 77	97.05 13	99.78 101	98.06 57	99.66 61	99.69 56

CPTT-MVS		97.72 75	97.32 90	98.92 63	99.64 28	97.10 94	99.12 53	98.81 86	92.34 277	98.09 104	99.08 94	93.01 105	99.92 31	96.06 155	99.77 31	99.75 35

SR-MVS-dyc-post		98.54 31	98.35 32	99.13 48	99.49 45	97.86 62	99.11 55	98.80 93	96.49 86	99.17 41	99.35 44	95.34 58	99.82 76	97.72 80	99.65 64	99.71 49

RE-MVS-def			98.34 35		99.49 45	97.86 62	99.11 55	98.80 93	96.49 86	99.17 41	99.35 44	95.29 61		97.72 80	99.65 64	99.71 49

SMA-MVS		98.58 23	98.25 44	99.56 8	99.51 39	99.04 15	98.95 90	98.80 93	93.67 224	99.37 31	99.52 11	96.52 22	99.89 47	98.06 57	99.81 12	99.76 34
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
HPM-MVS		98.36 49	98.10 56	99.13 48	99.74 7	97.82 66	99.53 8	98.80 93	94.63 176	98.61 80	98.97 105	95.13 70	99.77 106	97.65 86	99.83 11	99.79 19
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPMNet		92.81 304	91.34 313	97.24 182	97.00 279	93.43 264	94.96 372	98.80 93	82.27 378	96.93 163	92.12 381	86.98 243	99.82 76	76.32 384	96.65 207	98.46 207

ZD-MVS					99.46 49	98.70 23		98.79 98	93.21 243	98.67 73	98.97 105	95.70 45	99.83 69	96.07 152	99.58 79

MP-MVS		98.33 54	98.01 60	99.28 32	99.75 3	98.18 49	99.22 35	98.79 98	96.13 102	97.92 122	99.23 62	94.54 80	99.94 8	96.74 136	99.78 29	99.73 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CANet		98.05 61	97.76 66	98.90 65	98.73 137	97.27 83	98.35 206	98.78 100	97.37 41	97.72 133	98.96 110	91.53 141	99.92 31	98.79 23	99.65 64	99.51 89

MP-MVS-pluss		98.31 55	97.92 63	99.49 12	99.72 12	98.88 18	98.43 201	98.78 100	94.10 192	97.69 135	99.42 29	95.25 64	99.92 31	98.09 56	99.80 19	99.67 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepC-MVS_fast	96.70 1	98.55 30	98.34 35	99.18 42	99.25 81	98.04 57	98.50 192	98.78 100	97.72 17	98.92 59	99.28 54	95.27 62	99.82 76	97.55 95	99.77 31	99.69 56
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		97.81 71	97.60 71	98.44 95	99.12 102	95.97 151	97.75 276	98.78 100	96.89 70	98.46 86	99.22 64	93.90 97	99.68 125	94.81 194	99.52 92	99.67 65

NCCC		98.61 18	98.35 32	99.38 18	99.28 77	98.61 26	98.45 196	98.76 104	97.82 16	98.45 89	98.93 114	96.65 19	99.83 69	97.38 104	99.41 106	99.71 49

PLC	95.07 4	97.20 109	96.78 113	98.44 95	99.29 73	96.31 136	98.14 235	98.76 104	92.41 275	96.39 190	98.31 185	94.92 76	99.78 101	94.06 221	98.77 139	99.23 135
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
h-mvs33		96.17 152	95.62 167	97.81 144	99.03 109	94.45 226	98.64 169	98.75 106	97.48 32	98.67 73	98.72 139	89.76 174	99.86 62	97.95 62	81.59 370	99.11 155

DeepC-MVS	95.98 3	97.88 67	97.58 72	98.77 69	99.25 81	96.93 99	98.83 124	98.75 106	96.96 67	96.89 167	99.50 15	90.46 164	99.87 58	97.84 73	99.76 37	99.52 86
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MTGPA								98.74 108

MTAPA		98.58 23	98.29 42	99.46 14	99.76 2	98.64 25	98.90 99	98.74 108	97.27 49	98.02 111	99.39 32	94.81 77	99.96 4	97.91 66	99.79 25	99.77 27

ab-mvs		96.42 140	95.71 161	98.55 81	98.63 150	96.75 108	97.88 265	98.74 108	93.84 207	96.54 184	98.18 198	85.34 274	99.75 109	95.93 159	96.35 216	99.15 150

TEST9					99.31 64	98.50 29	97.92 256	98.73 111	92.63 265	97.74 130	98.68 142	96.20 28	99.80 88

train_agg		97.97 62	97.52 78	99.33 26	99.31 64	98.50 29	97.92 256	98.73 111	92.98 254	97.74 130	98.68 142	96.20 28	99.80 88	96.59 137	99.57 80	99.68 61

test_8					99.29 73	98.44 31	97.89 264	98.72 113	92.98 254	97.70 134	98.66 145	96.20 28	99.80 88

agg_prior					99.30 68	98.38 35		98.72 113		97.57 144			99.81 81

无先验							97.58 290	98.72 113	91.38 304				99.87 58	93.36 241		99.60 77

save fliter					99.46 49	98.38 35	98.21 224	98.71 116	97.95 13

WTY-MVS		97.37 102	96.92 106	98.72 71	98.86 128	96.89 103	98.31 213	98.71 116	95.26 146	97.67 136	98.56 156	92.21 120	99.78 101	95.89 160	96.85 201	99.48 98

3Dnovator+	94.38 6	97.43 96	96.78 113	99.38 18	97.83 217	98.52 28	99.37 14	98.71 116	97.09 62	92.99 299	99.13 82	89.36 183	99.89 47	96.97 116	99.57 80	99.71 49

旧先验1					99.29 73	97.48 76		98.70 119			99.09 92	95.56 48			99.47 99	99.61 75

EI-MVSNet-Vis-set		98.47 37	98.39 27	98.69 72	99.46 49	96.49 123	98.30 215	98.69 120	97.21 52	98.84 62	99.36 42	95.41 53	99.78 101	98.62 26	99.65 64	99.80 18

新几何1				99.16 45	99.34 57	98.01 59		98.69 120	90.06 334	98.13 101	98.95 112	94.60 79	99.89 47	91.97 281	99.47 99	99.59 79

API-MVS		97.41 98	97.25 92	97.91 137	98.70 142	96.80 105	98.82 126	98.69 120	94.53 179	98.11 102	98.28 187	94.50 84	99.57 142	94.12 218	99.49 96	97.37 244

EI-MVSNet-UG-set		98.41 44	98.34 35	98.61 77	99.45 52	96.32 134	98.28 218	98.68 123	97.17 55	98.74 69	99.37 38	95.25 64	99.79 98	98.57 27	99.54 89	99.73 42

testdata				98.26 110	99.20 92	95.36 181		98.68 123	91.89 291	98.60 81	99.10 86	94.44 86	99.82 76	94.27 213	99.44 103	99.58 83

MCST-MVS		98.65 15	98.37 29	99.48 13	99.60 31	98.87 19	98.41 204	98.68 123	97.04 63	98.52 85	98.80 128	96.78 16	99.83 69	97.93 64	99.61 72	99.74 37

PVSNet	91.96 18	96.35 145	96.15 139	96.96 202	99.17 94	92.05 291	96.08 359	98.68 123	93.69 220	97.75 129	97.80 232	88.86 201	99.69 124	94.26 214	99.01 126	99.15 150

MAR-MVS		96.91 120	96.40 130	98.45 93	98.69 144	96.90 101	98.66 167	98.68 123	92.40 276	97.07 157	97.96 215	91.54 140	99.75 109	93.68 231	98.92 129	98.69 191
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
原ACMM1				98.65 75	99.32 62	96.62 112		98.67 128	93.27 242	97.81 125	98.97 105	95.18 67	99.83 69	93.84 227	99.46 102	99.50 91

CDPH-MVS		97.94 65	97.49 79	99.28 32	99.47 47	98.44 31	97.91 258	98.67 128	92.57 269	98.77 67	98.85 122	95.93 38	99.72 113	95.56 173	99.69 56	99.68 61

UnsupCasMVSNet_eth		90.99 322	89.92 325	94.19 332	94.08 366	89.83 329	97.13 325	98.67 128	93.69 220	85.83 369	96.19 337	75.15 362	96.74 360	89.14 328	79.41 378	96.00 342

TSAR-MVS + MP.		98.78 11	98.62 13	99.24 36	99.69 24	98.28 45	99.14 49	98.66 131	96.84 71	99.56 20	99.31 51	96.34 25	99.70 119	98.32 48	99.73 48	99.73 42
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		98.58 23	98.25 44	99.55 9	99.50 41	99.08 11	98.72 154	98.66 131	97.51 30	98.15 100	98.83 125	95.70 45	99.92 31	97.53 97	99.67 59	99.66 68

test222					99.23 88	97.17 92	97.40 298	98.66 131	88.68 353	98.05 106	98.96 110	94.14 93			99.53 91	99.61 75

test11								98.66 131

XXY-MVS		95.20 209	94.45 223	97.46 169	96.75 296	96.56 119	98.86 116	98.65 135	93.30 240	93.27 289	98.27 190	84.85 283	98.87 236	94.82 193	91.26 298	96.96 257

IU-MVS					99.71 19	99.23 7		98.64 136	95.28 145	99.63 18				98.35 47	99.81 12	99.83 13

TAPA-MVS	93.98 7	95.35 200	94.56 215	97.74 151	99.13 101	94.83 210	98.33 208	98.64 136	86.62 361	96.29 192	98.61 148	94.00 96	99.29 176	80.00 375	99.41 106	99.09 157
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MSC_two_6792asdad				99.62 6	99.17 94	99.08 11		98.63 138					99.94 8	98.53 30	99.80 19	99.86 8

No_MVS				99.62 6	99.17 94	99.08 11		98.63 138					99.94 8	98.53 30	99.80 19	99.86 8

F-COLMAP		97.09 115	96.80 110	97.97 134	99.45 52	94.95 204	98.55 185	98.62 140	93.02 253	96.17 195	98.58 153	94.01 95	99.81 81	93.95 223	98.90 130	99.14 152

test_fmvsmconf0.01_n		97.86 68	97.54 77	98.83 67	95.48 348	96.83 104	98.95 90	98.60 141	98.58 6	98.93 57	99.55 6	88.57 206	99.91 39	99.54 11	99.61 72	99.77 27

EIA-MVS		97.75 73	97.58 72	98.27 107	98.38 167	96.44 125	99.01 76	98.60 141	95.88 115	97.26 149	97.53 255	94.97 74	99.33 173	97.38 104	99.20 118	99.05 163

PAPM_NR		97.46 91	97.11 97	98.50 87	99.50 41	96.41 129	98.63 172	98.60 141	95.18 150	97.06 158	98.06 205	94.26 91	99.57 142	93.80 229	98.87 134	99.52 86

cdsmvs_eth3d_5k		23.98 365	31.98 367	0.00 384	0.00 406	0.00 409	0.00 395	98.59 144	0.00 402	0.00 403	98.61 148	90.60 162	0.00 403	0.00 402	0.00 401	0.00 399

1314		96.25 151	95.73 157	97.79 145	97.13 274	95.55 173	98.19 229	98.59 144	93.47 232	92.03 324	97.82 230	91.33 145	99.49 158	94.62 200	98.44 155	98.32 214

CVMVSNet		95.43 192	96.04 144	93.57 336	97.93 212	83.62 374	98.12 238	98.59 144	95.68 124	96.56 180	99.02 98	87.51 233	97.51 348	93.56 237	97.44 189	99.60 77

OMC-MVS		97.55 89	97.34 89	98.20 116	99.33 59	95.92 158	98.28 218	98.59 144	95.52 131	97.97 116	99.10 86	93.28 103	99.49 158	95.09 187	98.88 132	99.19 143

LTVRE_ROB	92.95 15	94.60 241	93.90 254	96.68 221	97.41 255	94.42 228	98.52 187	98.59 144	91.69 297	91.21 331	98.35 178	84.87 282	99.04 209	91.06 296	93.44 270	96.60 303
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
test_vis1_n_1920		96.71 128	96.84 109	96.31 261	99.11 103	89.74 331	99.05 65	98.58 149	98.08 12	99.87 1	99.37 38	78.48 341	99.93 25	99.29 14	99.69 56	99.27 129

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 84	98.58 149	97.62 24	99.45 25	99.46 24	97.42 9	99.94 8	98.47 38	99.81 12	99.69 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
UniMVSNet_ETH3D		94.24 267	93.33 284	96.97 201	97.19 270	93.38 268	98.74 146	98.57 151	91.21 316	93.81 269	98.58 153	72.85 371	98.77 247	95.05 188	93.93 254	98.77 187

PAPR		96.84 124	96.24 137	98.65 75	98.72 141	96.92 100	97.36 304	98.57 151	93.33 237	96.67 175	97.57 252	94.30 89	99.56 145	91.05 298	98.59 147	99.47 100

HQP_MVS		96.14 154	95.90 150	96.85 210	97.42 252	94.60 222	98.80 135	98.56 153	97.28 45	95.34 209	98.28 187	87.09 240	99.03 210	96.07 152	94.27 240	96.92 260

plane_prior5								98.56 153					99.03 210	96.07 152	94.27 240	96.92 260

ETV-MVS		97.96 63	97.81 64	98.40 100	98.42 164	97.27 83	98.73 150	98.55 155	96.84 71	98.38 93	97.44 261	95.39 54	99.35 171	97.62 88	98.89 131	98.58 203

mvs_tets		95.41 195	95.00 195	96.65 222	95.58 344	94.42 228	99.00 78	98.55 155	95.73 122	93.21 291	98.38 175	83.45 312	98.63 257	97.09 112	94.00 251	96.91 265

LPG-MVS_test		95.62 183	95.34 176	96.47 248	97.46 247	93.54 259	98.99 81	98.54 157	94.67 174	94.36 240	98.77 132	85.39 271	99.11 198	95.71 168	94.15 246	96.76 283

LGP-MVS_train				96.47 248	97.46 247	93.54 259		98.54 157	94.67 174	94.36 240	98.77 132	85.39 271	99.11 198	95.71 168	94.15 246	96.76 283

test_cas_vis1_n_1920		97.38 100	97.36 88	97.45 170	98.95 120	93.25 273	99.00 78	98.53 159	97.70 20	99.77 7	99.35 44	84.71 288	99.85 63	98.57 27	99.66 61	99.26 131

test12				99.18 42	99.16 98	98.19 48		98.53 159		98.07 105		95.13 70	99.72 113		99.56 86	99.63 73

CNLPA		97.45 94	97.03 101	98.73 70	99.05 107	97.44 80	98.07 243	98.53 159	95.32 143	96.80 172	98.53 157	93.32 101	99.72 113	94.31 212	99.31 115	99.02 165

jajsoiax		95.45 191	95.03 194	96.73 216	95.42 352	94.63 217	99.14 49	98.52 162	95.74 120	93.22 290	98.36 177	83.87 308	98.65 256	96.95 118	94.04 249	96.91 265

XVG-OURS		96.55 136	96.41 129	96.99 198	98.75 136	93.76 250	97.50 294	98.52 162	95.67 125	96.83 168	99.30 52	88.95 200	99.53 153	95.88 161	96.26 223	97.69 233

xiu_mvs_v1_base_debu		97.60 83	97.56 74	97.72 152	98.35 170	95.98 146	97.86 267	98.51 164	97.13 59	99.01 49	98.40 172	91.56 137	99.80 88	98.53 30	98.68 140	97.37 244

xiu_mvs_v1_base		97.60 83	97.56 74	97.72 152	98.35 170	95.98 146	97.86 267	98.51 164	97.13 59	99.01 49	98.40 172	91.56 137	99.80 88	98.53 30	98.68 140	97.37 244

xiu_mvs_v1_base_debi		97.60 83	97.56 74	97.72 152	98.35 170	95.98 146	97.86 267	98.51 164	97.13 59	99.01 49	98.40 172	91.56 137	99.80 88	98.53 30	98.68 140	97.37 244

PS-MVSNAJ		97.73 74	97.77 65	97.62 163	98.68 145	95.58 170	97.34 306	98.51 164	97.29 44	98.66 77	97.88 222	94.51 81	99.90 45	97.87 70	99.17 120	97.39 242

cascas		94.63 240	93.86 257	96.93 204	96.91 287	94.27 235	96.00 363	98.51 164	85.55 370	94.54 228	96.23 334	84.20 301	98.87 236	95.80 165	96.98 200	97.66 234

CS-MVS-test		98.49 34	98.50 20	98.46 92	99.20 92	97.05 95	99.64 4	98.50 169	97.45 35	98.88 60	99.14 81	95.25 64	99.15 191	98.83 22	99.56 86	99.20 139

PS-MVSNAJss		96.43 139	96.26 136	96.92 207	95.84 338	95.08 196	99.16 46	98.50 169	95.87 116	93.84 268	98.34 182	94.51 81	98.61 258	96.88 125	93.45 269	97.06 250

MVS		94.67 238	93.54 278	98.08 128	96.88 289	96.56 119	98.19 229	98.50 169	78.05 383	92.69 307	98.02 208	91.07 154	99.63 134	90.09 309	98.36 161	98.04 222

XVG-OURS-SEG-HR		96.51 137	96.34 131	97.02 197	98.77 135	93.76 250	97.79 274	98.50 169	95.45 134	96.94 162	99.09 92	87.87 226	99.55 152	96.76 135	95.83 231	97.74 230

PVSNet_0	88.72 19	91.28 318	90.03 324	95.00 308	97.99 208	87.29 366	94.84 375	98.50 169	92.06 287	89.86 343	95.19 355	79.81 334	99.39 169	92.27 272	69.79 389	98.33 213

ACMH	92.88 16	94.55 245	93.95 250	96.34 259	97.63 233	93.26 272	98.81 134	98.49 174	93.43 234	89.74 344	98.53 157	81.91 317	99.08 204	93.69 230	93.30 273	96.70 292
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CS-MVS		98.44 40	98.49 21	98.31 105	99.08 106	96.73 109	99.67 3	98.47 175	97.17 55	98.94 53	99.10 86	95.73 44	99.13 194	98.71 24	99.49 96	99.09 157

xiu_mvs_v2_base		97.66 80	97.70 68	97.56 167	98.61 152	95.46 176	97.44 295	98.46 176	97.15 57	98.65 78	98.15 199	94.33 88	99.80 88	97.84 73	98.66 144	97.41 240

HQP3-MVS								98.46 176							94.18 244

HQP-MVS		95.72 176	95.40 170	96.69 220	97.20 267	94.25 237	98.05 245	98.46 176	96.43 89	94.45 232	97.73 235	86.75 246	98.96 221	95.30 180	94.18 244	96.86 274

CLD-MVS		95.62 183	95.34 176	96.46 251	97.52 244	93.75 252	97.27 312	98.46 176	95.53 130	94.42 237	98.00 211	86.21 256	98.97 217	96.25 150	94.37 238	96.66 298
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XVG-ACMP-BASELINE		94.54 246	94.14 238	95.75 285	96.55 306	91.65 299	98.11 240	98.44 180	94.96 163	94.22 248	97.90 219	79.18 338	99.11 198	94.05 222	93.85 255	96.48 325

casdiffmvs_mvg		97.72 75	97.48 81	98.44 95	98.42 164	96.59 117	98.92 97	98.44 180	96.20 99	97.76 127	99.20 67	91.66 135	99.23 181	98.27 51	98.41 158	99.49 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMP	93.49 10	95.34 201	94.98 197	96.43 253	97.67 229	93.48 263	98.73 150	98.44 180	94.94 166	92.53 312	98.53 157	84.50 294	99.14 193	95.48 177	94.00 251	96.66 298
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	93.85 9	95.69 180	95.38 174	96.61 229	97.61 234	93.84 248	98.91 98	98.44 180	95.25 147	94.28 244	98.47 164	86.04 261	99.12 196	95.50 176	93.95 253	96.87 271
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+		97.12 113	96.69 118	98.39 101	98.19 191	96.72 110	97.37 302	98.43 184	93.71 217	97.65 139	98.02 208	92.20 121	99.25 178	96.87 128	97.79 179	99.19 143

EC-MVSNet		98.21 57	98.11 55	98.49 89	98.34 175	97.26 87	99.61 5	98.43 184	96.78 74	98.87 61	98.84 123	93.72 98	99.01 215	98.91 20	99.50 94	99.19 143

anonymousdsp		95.42 193	94.91 200	96.94 203	95.10 355	95.90 160	99.14 49	98.41 186	93.75 212	93.16 292	97.46 258	87.50 235	98.41 289	95.63 172	94.03 250	96.50 322

PMMVS		96.60 131	96.33 132	97.41 174	97.90 214	93.93 245	97.35 305	98.41 186	92.84 260	97.76 127	97.45 260	91.10 153	99.20 185	96.26 148	97.91 174	99.11 155

MVSFormer		97.57 87	97.49 79	97.84 140	98.07 201	95.76 165	99.47 9	98.40 188	94.98 161	98.79 65	98.83 125	92.34 114	98.41 289	96.91 119	99.59 76	99.34 116

test_djsdf		96.00 159	95.69 164	96.93 204	95.72 340	95.49 175	99.47 9	98.40 188	94.98 161	94.58 227	97.86 223	89.16 190	98.41 289	96.91 119	94.12 248	96.88 269

OPM-MVS		95.69 180	95.33 178	96.76 215	96.16 326	94.63 217	98.43 201	98.39 190	96.64 81	95.02 216	98.78 130	85.15 278	99.05 206	95.21 186	94.20 243	96.60 303
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
canonicalmvs		97.67 79	97.23 93	98.98 59	98.70 142	98.38 35	99.34 18	98.39 190	96.76 76	97.67 136	97.40 264	92.26 117	99.49 158	98.28 50	96.28 222	99.08 161

DP-MVS		96.59 132	95.93 149	98.57 79	99.34 57	96.19 140	98.70 159	98.39 190	89.45 345	94.52 229	99.35 44	91.85 130	99.85 63	92.89 257	98.88 132	99.68 61

dcpmvs_2		98.08 59	98.59 14	96.56 236	99.57 33	90.34 324	99.15 47	98.38 193	96.82 73	99.29 34	99.49 17	95.78 43	99.57 142	98.94 19	99.86 1	99.77 27

diffmvs		97.58 86	97.40 86	98.13 122	98.32 180	95.81 164	98.06 244	98.37 194	96.20 99	98.74 69	98.89 118	91.31 147	99.25 178	98.16 53	98.52 150	99.34 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMH+	92.99 14	94.30 263	93.77 264	95.88 280	97.81 218	92.04 292	98.71 155	98.37 194	93.99 199	90.60 338	98.47 164	80.86 327	99.05 206	92.75 259	92.40 284	96.55 311

MSDG		95.93 165	95.30 182	97.83 141	98.90 123	95.36 181	96.83 346	98.37 194	91.32 309	94.43 236	98.73 138	90.27 168	99.60 139	90.05 312	98.82 137	98.52 205

DPM-MVS		97.55 89	96.99 103	99.23 38	99.04 108	98.55 27	97.17 321	98.35 197	94.85 168	97.93 121	98.58 153	95.07 72	99.71 118	92.60 261	99.34 113	99.43 109

CMPMVS	66.06 21	89.70 331	89.67 327	89.78 357	93.19 372	76.56 383	97.00 330	98.35 197	80.97 380	81.57 379	97.75 234	74.75 364	98.61 258	89.85 315	93.63 263	94.17 369
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		94.19 270	93.43 282	96.47 248	95.90 335	94.38 231	99.26 27	98.34 199	91.99 288	92.76 304	97.13 279	88.31 213	98.52 269	89.48 324	87.70 341	96.52 317

CDS-MVSNet		96.99 117	96.69 118	97.90 138	98.05 205	95.98 146	98.20 226	98.33 200	93.67 224	96.95 161	98.49 161	93.54 99	98.42 281	95.24 185	97.74 182	99.31 122
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
casdiffmvs		97.63 82	97.41 85	98.28 106	98.33 177	96.14 142	98.82 126	98.32 201	96.38 94	97.95 117	99.21 65	91.23 149	99.23 181	98.12 54	98.37 159	99.48 98
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		97.64 81	97.44 84	98.25 111	98.35 170	96.20 138	99.00 78	98.32 201	96.33 96	98.03 109	99.17 74	91.35 144	99.16 188	98.10 55	98.29 165	99.39 112

cl22		94.68 235	94.19 233	96.13 268	98.11 199	93.60 257	96.94 333	98.31 203	92.43 274	93.32 288	96.87 311	86.51 249	98.28 306	94.10 220	91.16 299	96.51 320

test_yl		97.22 106	96.78 113	98.54 83	98.73 137	96.60 115	98.45 196	98.31 203	94.70 170	98.02 111	98.42 170	90.80 158	99.70 119	96.81 131	96.79 203	99.34 116

DCV-MVSNet		97.22 106	96.78 113	98.54 83	98.73 137	96.60 115	98.45 196	98.31 203	94.70 170	98.02 111	98.42 170	90.80 158	99.70 119	96.81 131	96.79 203	99.34 116

nrg030		96.28 149	95.72 158	97.96 136	96.90 288	98.15 52	99.39 12	98.31 203	95.47 133	94.42 237	98.35 178	92.09 124	98.69 251	97.50 99	89.05 327	97.04 251

TAMVS		97.02 116	96.79 112	97.70 155	98.06 204	95.31 185	98.52 187	98.31 203	93.95 201	97.05 159	98.61 148	93.49 100	98.52 269	95.33 179	97.81 178	99.29 127

EPP-MVSNet		97.46 91	97.28 91	97.99 133	98.64 149	95.38 180	99.33 21	98.31 203	93.61 228	97.19 151	99.07 95	94.05 94	99.23 181	96.89 123	98.43 157	99.37 114

UnsupCasMVSNet_bld		87.17 342	85.12 349	93.31 341	91.94 376	88.77 348	94.92 374	98.30 209	84.30 375	82.30 377	90.04 383	63.96 383	97.25 352	85.85 353	74.47 388	93.93 375

Vis-MVSNet (Re-imp)		96.87 122	96.55 124	97.83 141	98.73 137	95.46 176	99.20 40	98.30 209	94.96 163	96.60 179	98.87 120	90.05 170	98.59 261	93.67 233	98.60 146	99.46 104

TSAR-MVS + GP.		98.38 46	98.24 46	98.81 68	99.22 89	97.25 88	98.11 240	98.29 211	97.19 54	98.99 52	99.02 98	96.22 26	99.67 126	98.52 36	98.56 149	99.51 89

MS-PatchMatch		93.84 285	93.63 273	94.46 328	96.18 323	89.45 337	97.76 275	98.27 212	92.23 282	92.13 322	97.49 256	79.50 335	98.69 251	89.75 317	99.38 111	95.25 354

EI-MVSNet		95.96 161	95.83 152	96.36 257	97.93 212	93.70 256	98.12 238	98.27 212	93.70 219	95.07 214	99.02 98	92.23 119	98.54 267	94.68 196	93.46 267	96.84 276

MVSTER		96.06 157	95.72 158	97.08 194	98.23 185	95.93 157	98.73 150	98.27 212	94.86 167	95.07 214	98.09 203	88.21 215	98.54 267	96.59 137	93.46 267	96.79 280

FMVSNet2		94.47 254	93.61 274	97.04 195	98.21 187	96.43 126	98.79 140	98.27 212	92.46 270	93.50 281	97.09 284	81.16 322	98.00 325	91.09 294	91.93 288	96.70 292

FMVSNet3		94.97 223	94.26 230	97.11 192	98.18 193	96.62 112	98.56 184	98.26 216	93.67 224	94.09 254	97.10 280	84.25 297	98.01 323	92.08 275	92.14 285	96.70 292

Fast-Effi-MVS+		96.28 149	95.70 163	98.03 131	98.29 182	95.97 151	98.58 178	98.25 217	91.74 294	95.29 211	97.23 274	91.03 155	99.15 191	92.90 255	97.96 173	98.97 170

PAPM		94.95 224	94.00 246	97.78 146	97.04 278	95.65 168	96.03 362	98.25 217	91.23 314	94.19 250	97.80 232	91.27 148	98.86 238	82.61 369	97.61 186	98.84 181

test_fmvs1_n		95.90 167	95.99 147	95.63 288	98.67 146	88.32 357	99.26 27	98.22 219	96.40 92	99.67 14	99.26 57	73.91 368	99.70 119	99.02 18	99.50 94	98.87 178

CANet_DTU		96.96 118	96.55 124	98.21 114	98.17 195	96.07 144	97.98 252	98.21 220	97.24 50	97.13 153	98.93 114	86.88 245	99.91 39	95.00 189	99.37 112	98.66 195

HY-MVS	93.96 8	96.82 125	96.23 138	98.57 79	98.46 162	97.00 96	98.14 235	98.21 220	93.95 201	96.72 174	97.99 212	91.58 136	99.76 107	94.51 205	96.54 211	98.95 173

test_fmvs1		96.42 140	96.67 120	95.66 287	98.82 132	88.53 353	98.80 135	98.20 222	96.39 93	99.64 17	99.20 67	80.35 331	99.67 126	99.04 17	99.57 80	98.78 186

PCF-MVS	93.45 11	94.68 235	93.43 282	98.42 99	98.62 151	96.77 107	95.48 370	98.20 222	84.63 374	93.34 287	98.32 184	88.55 209	99.81 81	84.80 361	98.96 128	98.68 192
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v8		94.47 254	93.77 264	96.57 235	96.36 316	94.83 210	99.05 65	98.19 224	91.92 290	93.16 292	96.97 301	88.82 203	98.48 272	91.69 287	87.79 340	96.39 329

v10		94.29 264	93.55 277	96.51 244	96.39 315	94.80 212	98.99 81	98.19 224	91.35 307	93.02 298	96.99 299	88.09 219	98.41 289	90.50 305	88.41 335	96.33 333

mvs_anonymous		96.70 129	96.53 126	97.18 186	98.19 191	93.78 249	98.31 213	98.19 224	94.01 197	94.47 231	98.27 190	92.08 125	98.46 276	97.39 103	97.91 174	99.31 122

AllTest		95.24 206	94.65 211	96.99 198	99.25 81	93.21 275	98.59 176	98.18 227	91.36 305	93.52 278	98.77 132	84.67 289	99.72 113	89.70 319	97.87 176	98.02 223

TestCases				96.99 198	99.25 81	93.21 275		98.18 227	91.36 305	93.52 278	98.77 132	84.67 289	99.72 113	89.70 319	97.87 176	98.02 223

GBi-Net		94.49 251	93.80 261	96.56 236	98.21 187	95.00 198	98.82 126	98.18 227	92.46 270	94.09 254	97.07 287	81.16 322	97.95 327	92.08 275	92.14 285	96.72 288

test1		94.49 251	93.80 261	96.56 236	98.21 187	95.00 198	98.82 126	98.18 227	92.46 270	94.09 254	97.07 287	81.16 322	97.95 327	92.08 275	92.14 285	96.72 288

FMVSNet1		93.19 299	92.07 306	96.56 236	97.54 241	95.00 198	98.82 126	98.18 227	90.38 329	92.27 319	97.07 287	73.68 369	97.95 327	89.36 326	91.30 296	96.72 288

v1192		94.32 262	93.58 275	96.53 242	96.10 327	94.45 226	98.50 192	98.17 232	91.54 300	94.19 250	97.06 290	86.95 244	98.43 280	90.14 308	89.57 317	96.70 292

v1240		94.06 281	93.29 286	96.34 259	96.03 331	93.90 246	98.44 199	98.17 232	91.18 317	94.13 253	97.01 298	86.05 259	98.42 281	89.13 329	89.50 321	96.70 292

v144192		94.39 259	93.70 270	96.48 247	96.06 329	94.35 232	98.58 178	98.16 234	91.45 302	94.33 242	97.02 296	87.50 235	98.45 277	91.08 295	89.11 326	96.63 300

Fast-Effi-MVS+-dtu		95.87 168	95.85 151	95.91 277	97.74 224	91.74 297	98.69 161	98.15 235	95.56 129	94.92 217	97.68 243	88.98 198	98.79 245	93.19 245	97.78 180	97.20 248

v1921920		94.20 269	93.47 281	96.40 256	95.98 332	94.08 242	98.52 187	98.15 235	91.33 308	94.25 246	97.20 277	86.41 253	98.42 281	90.04 313	89.39 323	96.69 297

v1144		94.59 243	93.92 251	96.60 231	96.21 321	94.78 214	98.59 176	98.14 237	91.86 293	94.21 249	97.02 296	87.97 222	98.41 289	91.72 286	89.57 317	96.61 302

IterMVS-LS		95.46 189	95.21 185	96.22 265	98.12 198	93.72 255	98.32 212	98.13 238	93.71 217	94.26 245	97.31 268	92.24 118	98.10 316	94.63 198	90.12 310	96.84 276
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GeoE		96.58 134	96.07 142	98.10 127	98.35 170	95.89 161	99.34 18	98.12 239	93.12 249	96.09 196	98.87 120	89.71 176	98.97 217	92.95 253	98.08 170	99.43 109

EU-MVSNet		93.66 286	94.14 238	92.25 352	95.96 334	83.38 376	98.52 187	98.12 239	94.69 172	92.61 309	98.13 201	87.36 238	96.39 368	91.82 283	90.00 312	96.98 255

IterMVS		94.09 278	93.85 258	94.80 317	97.99 208	90.35 323	97.18 319	98.12 239	93.68 222	92.46 316	97.34 265	84.05 303	97.41 350	92.51 268	91.33 295	96.62 301
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_vis1_n		95.47 188	95.13 188	96.49 245	97.77 220	90.41 322	99.27 26	98.11 242	96.58 83	99.66 15	99.18 73	67.00 380	99.62 137	99.21 15	99.40 109	99.44 107

IterMVS-SCA-FT		94.11 276	93.87 256	94.85 314	97.98 210	90.56 320	97.18 319	98.11 242	93.75 212	92.58 310	97.48 257	83.97 305	97.41 350	92.48 270	91.30 296	96.58 305

COLMAP_ROB	93.27 12	95.33 202	94.87 203	96.71 217	99.29 73	93.24 274	98.58 178	98.11 242	89.92 336	93.57 276	99.10 86	86.37 254	99.79 98	90.78 301	98.10 169	97.09 249
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
hse-mvs2		95.71 177	95.30 182	96.93 204	98.50 159	93.53 261	98.36 205	98.10 245	97.48 32	98.67 73	97.99 212	89.76 174	99.02 213	97.95 62	80.91 374	98.22 217

AUN-MVS		94.53 248	93.73 268	96.92 207	98.50 159	93.52 262	98.34 207	98.10 245	93.83 209	95.94 204	97.98 214	85.59 268	99.03 210	94.35 209	80.94 373	98.22 217

Effi-MVS+-dtu		96.29 147	96.56 123	95.51 291	97.89 215	90.22 325	98.80 135	98.10 245	96.57 85	96.45 189	96.66 319	90.81 157	98.91 229	95.72 167	97.99 171	97.40 241

1112_ss		96.63 130	96.00 146	98.50 87	98.56 154	96.37 131	98.18 233	98.10 245	92.92 257	94.84 219	98.43 168	92.14 122	99.58 141	94.35 209	96.51 212	99.56 85

V42		94.78 231	94.14 238	96.70 219	96.33 319	95.22 189	98.97 84	98.09 249	92.32 279	94.31 243	97.06 290	88.39 212	98.55 265	92.90 255	88.87 331	96.34 331

miper_enhance_ethall		95.10 214	94.75 207	96.12 269	97.53 243	93.73 254	96.61 353	98.08 250	92.20 285	93.89 264	96.65 321	92.44 112	98.30 302	94.21 215	91.16 299	96.34 331

v2v482		94.69 233	94.03 242	96.65 222	96.17 324	94.79 213	98.67 165	98.08 250	92.72 263	94.00 259	97.16 278	87.69 232	98.45 277	92.91 254	88.87 331	96.72 288

CL-MVSNet_self_test		90.11 328	89.14 331	93.02 345	91.86 377	88.23 359	96.51 356	98.07 252	90.49 324	90.49 339	94.41 363	84.75 286	95.34 377	80.79 373	74.95 386	95.50 351

miper_ehance_all_eth		95.01 218	94.69 210	95.97 274	97.70 227	93.31 270	97.02 329	98.07 252	92.23 282	93.51 280	96.96 303	91.85 130	98.15 312	93.68 231	91.16 299	96.44 328

eth_miper_zixun_eth		94.68 235	94.41 226	95.47 293	97.64 232	91.71 298	96.73 350	98.07 252	92.71 264	93.64 273	97.21 276	90.54 163	98.17 311	93.38 239	89.76 314	96.54 312

MVS_Test		97.28 104	97.00 102	98.13 122	98.33 177	95.97 151	98.74 146	98.07 252	94.27 188	98.44 91	98.07 204	92.48 111	99.26 177	96.43 144	98.19 166	99.16 149

Test_1112_low_res		96.34 146	95.66 166	98.36 102	98.56 154	95.94 154	97.71 279	98.07 252	92.10 286	94.79 223	97.29 269	91.75 132	99.56 145	94.17 216	96.50 213	99.58 83

iter_conf_final		96.42 140	96.12 140	97.34 179	98.46 162	96.55 121	99.08 61	98.06 257	96.03 106	95.63 206	98.46 166	87.72 228	98.59 261	97.84 73	93.80 257	96.87 271

alignmvs		97.56 88	97.07 100	99.01 56	98.66 147	98.37 39	98.83 124	98.06 257	96.74 77	98.00 115	97.65 244	90.80 158	99.48 162	98.37 46	96.56 210	99.19 143

RPSCF		94.87 228	95.40 170	93.26 342	98.89 124	82.06 380	98.33 208	98.06 257	90.30 331	96.56 180	99.26 57	87.09 240	99.49 158	93.82 228	96.32 218	98.24 215

miper_lstm_enhance		94.33 261	94.07 241	95.11 305	97.75 221	90.97 309	97.22 314	98.03 260	91.67 298	92.76 304	96.97 301	90.03 171	97.78 338	92.51 268	89.64 316	96.56 309

c3_l		94.79 230	94.43 225	95.89 279	97.75 221	93.12 278	97.16 323	98.03 260	92.23 282	93.46 283	97.05 292	91.39 142	98.01 323	93.58 236	89.21 325	96.53 314

pm-mvs1		93.94 284	93.06 289	96.59 232	96.49 310	95.16 191	98.95 90	98.03 260	92.32 279	91.08 333	97.84 226	84.54 293	98.41 289	92.16 273	86.13 359	96.19 338

iter_conf05		96.13 155	95.79 153	97.15 188	98.16 196	95.99 145	98.88 108	97.98 263	95.91 112	95.58 207	98.46 166	85.53 269	98.59 261	97.88 69	93.75 258	96.86 274

mvsmamba		96.57 135	96.32 133	97.32 180	96.60 303	96.43 126	99.54 7	97.98 263	96.49 86	95.20 212	98.64 146	90.82 156	98.55 265	97.97 61	93.65 262	96.98 255

v148		94.29 264	93.76 266	95.91 277	96.10 327	92.93 281	98.58 178	97.97 265	92.59 268	93.47 282	96.95 305	88.53 210	98.32 298	92.56 265	87.06 350	96.49 323

IS-MVSNet		97.22 106	96.88 107	98.25 111	98.85 130	96.36 132	99.19 42	97.97 265	95.39 137	97.23 150	98.99 104	91.11 152	98.93 227	94.60 201	98.59 147	99.47 100

cl____		94.51 250	94.01 245	96.02 271	97.58 236	93.40 267	97.05 327	97.96 267	91.73 296	92.76 304	97.08 286	89.06 194	98.13 314	92.61 260	90.29 308	96.52 317

KD-MVS_self_test		90.38 326	89.38 329	93.40 339	92.85 374	88.94 347	97.95 254	97.94 268	90.35 330	90.25 340	93.96 368	79.82 333	95.94 373	84.62 363	76.69 384	95.33 353

DIV-MVS_self_test		94.52 249	94.03 242	95.99 272	97.57 240	93.38 268	97.05 327	97.94 268	91.74 294	92.81 302	97.10 280	89.12 191	98.07 320	92.60 261	90.30 307	96.53 314

pmmvs6		91.77 313	90.63 318	95.17 303	94.69 363	91.24 306	98.67 165	97.92 270	86.14 365	89.62 345	97.56 254	75.79 360	98.34 296	90.75 302	84.56 361	95.94 344

RRT_MVS		95.98 160	95.78 154	96.56 236	96.48 311	94.22 239	99.57 6	97.92 270	95.89 113	93.95 261	98.70 140	89.27 186	98.42 281	97.23 108	93.02 276	97.04 251

jason		97.32 103	97.08 99	98.06 130	97.45 250	95.59 169	97.87 266	97.91 272	94.79 169	98.55 83	98.83 125	91.12 151	99.23 181	97.58 91	99.60 74	99.34 116
jason: jason.
ppachtmachnet_test		93.22 297	92.63 297	94.97 309	95.45 350	90.84 313	96.88 342	97.88 273	90.60 323	92.08 323	97.26 270	88.08 220	97.86 336	85.12 358	90.33 306	96.22 336

tpm cat1		93.36 291	92.80 293	95.07 307	97.58 236	87.97 361	96.76 348	97.86 274	82.17 379	93.53 277	96.04 340	86.13 257	99.13 194	89.24 327	95.87 230	98.10 221

tt0805		94.54 246	93.85 258	96.63 226	97.98 210	93.06 280	98.77 142	97.84 275	93.67 224	93.80 270	98.04 207	76.88 356	98.96 221	94.79 195	92.86 279	97.86 227

EG-PatchMatch MVS		91.13 320	90.12 323	94.17 333	94.73 362	89.00 345	98.13 237	97.81 276	89.22 349	85.32 373	96.46 327	67.71 378	98.42 281	87.89 342	93.82 256	95.08 359

BH-untuned		95.95 162	95.72 158	96.65 222	98.55 156	92.26 287	98.23 222	97.79 277	93.73 215	94.62 226	98.01 210	88.97 199	99.00 216	93.04 250	98.51 151	98.68 192

lupinMVS		97.44 95	97.22 94	98.12 125	98.07 201	95.76 165	97.68 281	97.76 278	94.50 182	98.79 65	98.61 148	92.34 114	99.30 175	97.58 91	99.59 76	99.31 122

VDDNet		95.36 199	94.53 216	97.86 139	98.10 200	95.13 194	98.85 118	97.75 279	90.46 326	98.36 94	99.39 32	73.27 370	99.64 131	97.98 60	96.58 209	98.81 182

ADS-MVSNet		95.00 219	94.45 223	96.63 226	98.00 206	91.91 293	96.04 360	97.74 280	90.15 332	96.47 187	96.64 322	87.89 224	98.96 221	90.08 310	97.06 195	99.02 165

tpmvs		94.60 241	94.36 228	95.33 299	97.46 247	88.60 351	96.88 342	97.68 281	91.29 311	93.80 270	96.42 329	88.58 205	99.24 180	91.06 296	96.04 229	98.17 219

pmmvs4		94.69 233	93.99 248	96.81 213	95.74 339	95.94 154	97.40 298	97.67 282	90.42 328	93.37 286	97.59 250	89.08 193	98.20 309	92.97 252	91.67 292	96.30 334

our_test_3		93.65 288	93.30 285	94.69 319	95.45 350	89.68 334	96.91 336	97.65 283	91.97 289	91.66 328	96.88 309	89.67 177	97.93 330	88.02 340	91.49 294	96.48 325

MVP-Stereo		94.28 266	93.92 251	95.35 298	94.95 357	92.60 284	97.97 253	97.65 283	91.61 299	90.68 337	97.09 284	86.32 255	98.42 281	89.70 319	99.34 113	95.02 361
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
KD-MVS_2432*1600		89.61 333	87.96 340	94.54 323	94.06 367	91.59 300	95.59 368	97.63 285	89.87 337	88.95 351	94.38 365	78.28 343	96.82 358	84.83 359	68.05 390	95.21 355

miper_refine_blended		89.61 333	87.96 340	94.54 323	94.06 367	91.59 300	95.59 368	97.63 285	89.87 337	88.95 351	94.38 365	78.28 343	96.82 358	84.83 359	68.05 390	95.21 355

SCA		95.46 189	95.13 188	96.46 251	97.67 229	91.29 305	97.33 307	97.60 287	94.68 173	96.92 165	97.10 280	83.97 305	98.89 233	92.59 263	98.32 164	99.20 139

FA-MVS(test-final)		96.41 144	95.94 148	97.82 143	98.21 187	95.20 190	97.80 272	97.58 288	93.21 243	97.36 147	97.70 238	89.47 180	99.56 145	94.12 218	97.99 171	98.71 190

GA-MVS		94.81 229	94.03 242	97.14 189	97.15 273	93.86 247	96.76 348	97.58 288	94.00 198	94.76 224	97.04 293	80.91 325	98.48 272	91.79 284	96.25 224	99.09 157

Anonymous20240521		91.18 319	90.44 320	93.42 337	93.70 370	88.47 354	98.94 93	97.56 290	88.46 354	89.56 347	95.08 358	77.15 355	96.97 356	83.92 364	89.55 319	94.82 363

test20.03		90.89 323	90.38 321	92.43 348	93.48 371	88.14 360	98.33 208	97.56 290	93.40 235	87.96 357	96.71 318	80.69 329	94.13 383	79.15 378	86.17 357	95.01 362

CR-MVSNet		94.76 232	94.15 237	96.59 232	97.00 279	93.43 264	94.96 372	97.56 290	92.46 270	96.93 163	96.24 332	88.15 217	97.88 335	87.38 343	96.65 207	98.46 207

Patchmtry		93.22 297	92.35 303	95.84 281	96.77 293	93.09 279	94.66 379	97.56 290	87.37 359	92.90 300	96.24 332	88.15 217	97.90 331	87.37 344	90.10 311	96.53 314

tpmrst		95.63 182	95.69 164	95.44 295	97.54 241	88.54 352	96.97 331	97.56 290	93.50 231	97.52 145	96.93 307	89.49 178	99.16 188	95.25 184	96.42 215	98.64 197

FMVSNet5		91.81 312	90.92 315	94.49 325	97.21 266	92.09 289	98.00 251	97.55 295	89.31 348	90.86 335	95.61 351	74.48 365	95.32 378	85.57 354	89.70 315	96.07 341

testgi		93.06 302	92.45 302	94.88 313	96.43 314	89.90 328	98.75 143	97.54 296	95.60 127	91.63 329	97.91 218	74.46 366	97.02 355	86.10 350	93.67 260	97.72 232

mvsany_test1		97.69 78	97.70 68	97.66 161	98.24 183	94.18 240	97.53 292	97.53 297	95.52 131	99.66 15	99.51 13	94.30 89	99.56 145	98.38 45	98.62 145	99.23 135

PatchmatchNet		95.71 177	95.52 168	96.29 263	97.58 236	90.72 316	96.84 345	97.52 298	94.06 193	97.08 155	96.96 303	89.24 188	98.90 232	92.03 279	98.37 159	99.26 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDA-MVSNet-bldmvs		89.97 330	88.35 336	94.83 316	95.21 354	91.34 303	97.64 285	97.51 299	88.36 355	71.17 390	96.13 338	79.22 337	96.63 365	83.65 365	86.27 356	96.52 317

USDC		93.33 294	92.71 295	95.21 301	96.83 292	90.83 314	96.91 336	97.50 300	93.84 207	90.72 336	98.14 200	77.69 348	98.82 242	89.51 323	93.21 275	95.97 343

ITE_SJBPF				95.44 295	97.42 252	91.32 304		97.50 300	95.09 157	93.59 274	98.35 178	81.70 318	98.88 235	89.71 318	93.39 271	96.12 339

Patchmatch-test		94.42 257	93.68 272	96.63 226	97.60 235	91.76 295	94.83 376	97.49 302	89.45 345	94.14 252	97.10 280	88.99 195	98.83 241	85.37 357	98.13 168	99.29 127

Syy-MVS		92.55 307	92.61 298	92.38 349	97.39 256	83.41 375	97.91 258	97.46 303	93.16 246	93.42 284	95.37 353	84.75 286	96.12 370	77.00 383	96.99 197	97.60 236

myMVS_eth3d		92.73 305	92.01 307	94.89 312	97.39 256	90.94 310	97.91 258	97.46 303	93.16 246	93.42 284	95.37 353	68.09 376	96.12 370	88.34 336	96.99 197	97.60 236

YYNet1		90.70 325	89.39 328	94.62 322	94.79 361	90.65 318	97.20 316	97.46 303	87.54 358	72.54 388	95.74 344	86.51 249	96.66 364	86.00 351	86.76 355	96.54 312

MDA-MVSNet_test_wron		90.71 324	89.38 329	94.68 320	94.83 359	90.78 315	97.19 318	97.46 303	87.60 357	72.41 389	95.72 348	86.51 249	96.71 363	85.92 352	86.80 354	96.56 309

BH-RMVSNet		95.92 166	95.32 179	97.69 156	98.32 180	94.64 216	98.19 229	97.45 307	94.56 177	96.03 198	98.61 148	85.02 279	99.12 196	90.68 303	99.06 122	99.30 125

MIMVSNet1		89.67 332	88.28 337	93.82 334	92.81 375	91.08 308	98.01 249	97.45 307	87.95 356	87.90 358	95.87 343	67.63 379	94.56 382	78.73 380	88.18 337	95.83 346

OurMVSNet-221017-0		94.21 268	94.00 246	94.85 314	95.60 343	89.22 341	98.89 103	97.43 309	95.29 144	92.18 321	98.52 160	82.86 313	98.59 261	93.46 238	91.76 290	96.74 285

BH-w/o		95.38 196	95.08 192	96.26 264	98.34 175	91.79 294	97.70 280	97.43 309	92.87 259	94.24 247	97.22 275	88.66 204	98.84 239	91.55 289	97.70 184	98.16 220

VDD-MVS		95.82 172	95.23 184	97.61 164	98.84 131	93.98 244	98.68 162	97.40 311	95.02 160	97.95 117	99.34 48	74.37 367	99.78 101	98.64 25	96.80 202	99.08 161

Gipuma		78.40 354	76.75 357	83.38 369	95.54 345	80.43 382	79.42 393	97.40 311	64.67 390	73.46 387	80.82 391	45.65 390	93.14 387	66.32 391	87.43 344	76.56 393
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FE-MVS		95.62 183	94.90 201	97.78 146	98.37 169	94.92 205	97.17 321	97.38 313	90.95 320	97.73 132	97.70 238	85.32 276	99.63 134	91.18 293	98.33 162	98.79 183

bld_raw_dy_0_64		95.74 175	95.31 181	97.03 196	96.35 317	95.76 165	99.12 53	97.37 314	95.97 108	94.70 225	98.48 162	85.80 264	98.49 271	96.55 139	93.48 266	96.84 276

new-patchmatchnet		88.50 338	87.45 343	91.67 354	90.31 382	85.89 370	97.16 323	97.33 315	89.47 344	83.63 376	92.77 377	76.38 357	95.06 380	82.70 368	77.29 383	94.06 373

ADS-MVSNet2		94.58 244	94.40 227	95.11 305	98.00 206	88.74 349	96.04 360	97.30 316	90.15 332	96.47 187	96.64 322	87.89 224	97.56 346	90.08 310	97.06 195	99.02 165

MDTV_nov1_ep13			95.40 170		97.48 245	88.34 356	96.85 344	97.29 317	93.74 214	97.48 146	97.26 270	89.18 189	99.05 206	91.92 282	97.43 190

pmmvs5		93.65 288	92.97 291	95.68 286	95.49 347	92.37 285	98.20 226	97.28 318	89.66 341	92.58 310	97.26 270	82.14 316	98.09 318	93.18 246	90.95 302	96.58 305

EPNet_dtu		95.21 208	94.95 199	95.99 272	96.17 324	90.45 321	98.16 234	97.27 319	96.77 75	93.14 295	98.33 183	90.34 166	98.42 281	85.57 354	98.81 138	99.09 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20231206		91.66 314	91.10 314	93.33 340	94.02 369	87.35 365	98.58 178	97.26 320	90.48 325	90.16 341	96.31 330	83.83 309	96.53 366	79.36 377	89.90 313	96.12 339

test_fmvs2		93.43 290	93.58 275	92.95 346	96.97 282	83.91 373	99.19 42	97.24 321	95.74 120	95.20 212	98.27 190	69.65 373	98.72 250	96.26 148	93.73 259	96.24 335

test_0402		91.32 316	90.27 322	94.48 326	96.60 303	91.12 307	98.50 192	97.22 322	86.10 366	88.30 356	96.98 300	77.65 350	97.99 326	78.13 381	92.94 278	94.34 365

dp		94.15 273	93.90 254	94.90 311	97.31 260	86.82 368	96.97 331	97.19 323	91.22 315	96.02 199	96.61 324	85.51 270	99.02 213	90.00 314	94.30 239	98.85 179

testing3		93.19 299	92.48 301	95.30 300	98.07 201	92.27 286	98.64 169	97.17 324	93.94 203	93.98 260	97.04 293	67.97 377	96.01 372	88.40 335	97.14 194	97.63 235

thres200		95.25 205	94.57 214	97.28 181	98.81 133	94.92 205	98.20 226	97.11 325	95.24 149	96.54 184	96.22 336	84.58 292	99.53 153	87.93 341	96.50 213	97.39 242

dmvs_re		94.48 253	94.18 235	95.37 297	97.68 228	90.11 327	98.54 186	97.08 326	94.56 177	94.42 237	97.24 273	84.25 297	97.76 339	91.02 299	92.83 280	98.24 215

PatchT		93.06 302	91.97 308	96.35 258	96.69 299	92.67 283	94.48 380	97.08 326	86.62 361	97.08 155	92.23 380	87.94 223	97.90 331	78.89 379	96.69 205	98.49 206

TDRefinement		91.06 321	89.68 326	95.21 301	85.35 393	91.49 302	98.51 191	97.07 328	91.47 301	88.83 354	97.84 226	77.31 352	99.09 203	92.79 258	77.98 382	95.04 360

LF4IMVS		93.14 301	92.79 294	94.20 331	95.88 336	88.67 350	97.66 283	97.07 328	93.81 210	91.71 327	97.65 244	77.96 347	98.81 243	91.47 290	91.92 289	95.12 357

Anonymous202405211		95.28 204	94.49 218	97.67 158	99.00 113	93.75 252	98.70 159	97.04 330	90.66 322	96.49 186	98.80 128	78.13 345	99.83 69	96.21 151	95.36 236	99.44 107

baseline1		95.84 170	95.12 190	98.01 132	98.49 161	95.98 146	98.73 150	97.03 331	95.37 140	96.22 193	98.19 197	89.96 172	99.16 188	94.60 201	87.48 343	98.90 177

MIMVSNet		93.26 296	92.21 305	96.41 254	97.73 225	93.13 277	95.65 367	97.03 331	91.27 313	94.04 257	96.06 339	75.33 361	97.19 353	86.56 347	96.23 225	98.92 176

MM				99.33 26		98.14 54	98.93 95	97.02 333	98.96 1	99.17 41	99.47 20	91.97 129	99.94 8	99.85 4	99.69 56	99.91 2

EPNet		97.28 104	96.87 108	98.51 86	94.98 356	96.14 142	98.90 99	97.02 333	98.28 10	95.99 200	99.11 84	91.36 143	99.89 47	96.98 115	99.19 119	99.50 91
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TR-MVS		94.94 226	94.20 232	97.17 187	97.75 221	94.14 241	97.59 289	97.02 333	92.28 281	95.75 205	97.64 246	83.88 307	98.96 221	89.77 316	96.15 227	98.40 209

JIA-IIPM		93.35 292	92.49 300	95.92 276	96.48 311	90.65 318	95.01 371	96.96 336	85.93 367	96.08 197	87.33 386	87.70 231	98.78 246	91.35 291	95.58 234	98.34 212

pmmvs-eth3d		90.36 327	89.05 332	94.32 330	91.10 380	92.12 288	97.63 288	96.95 337	88.86 352	84.91 374	93.13 375	78.32 342	96.74 360	88.70 332	81.81 369	94.09 371

tfpn200view9		95.32 203	94.62 212	97.43 172	98.94 121	94.98 201	98.68 162	96.93 338	95.33 141	96.55 182	96.53 325	84.23 299	99.56 145	88.11 337	96.29 219	97.76 228

thres400		95.38 196	94.62 212	97.65 162	98.94 121	94.98 201	98.68 162	96.93 338	95.33 141	96.55 182	96.53 325	84.23 299	99.56 145	88.11 337	96.29 219	98.40 209

thres100view900		95.38 196	94.70 209	97.41 174	98.98 118	94.92 205	98.87 113	96.90 340	95.38 138	96.61 178	96.88 309	84.29 295	99.56 145	88.11 337	96.29 219	97.76 228

thres600view7		95.49 187	94.77 205	97.67 158	98.98 118	95.02 197	98.85 118	96.90 340	95.38 138	96.63 177	96.90 308	84.29 295	99.59 140	88.65 334	96.33 217	98.40 209

test_method		79.03 350	78.17 352	81.63 373	86.06 392	54.40 404	82.75 392	96.89 342	39.54 396	80.98 381	95.57 352	58.37 386	94.73 381	84.74 362	78.61 379	95.75 347

CostFormer		94.95 224	94.73 208	95.60 290	97.28 261	89.06 343	97.53 292	96.89 342	89.66 341	96.82 170	96.72 317	86.05 259	98.95 226	95.53 175	96.13 228	98.79 183

new_pmnet		90.06 329	89.00 333	93.22 343	94.18 364	88.32 357	96.42 358	96.89 342	86.19 364	85.67 370	93.62 370	77.18 354	97.10 354	81.61 371	89.29 324	94.23 367

OpenMVS_ROB	86.42 20	89.00 336	87.43 344	93.69 335	93.08 373	89.42 338	97.91 258	96.89 342	78.58 382	85.86 368	94.69 360	69.48 374	98.29 305	77.13 382	93.29 274	93.36 377

tpm2		94.19 270	93.76 266	95.46 294	97.23 264	89.04 344	97.31 309	96.85 346	87.08 360	96.21 194	96.79 315	83.75 311	98.74 248	92.43 271	96.23 225	98.59 201

TransMVSNet (Re)		92.67 306	91.51 312	96.15 266	96.58 305	94.65 215	98.90 99	96.73 347	90.86 321	89.46 348	97.86 223	85.62 267	98.09 318	86.45 348	81.12 371	95.71 348

ambc				89.49 358	86.66 390	75.78 384	92.66 385	96.72 348		86.55 366	92.50 379	46.01 389	97.90 331	90.32 306	82.09 366	94.80 364

LCM-MVSNet		78.70 353	76.24 358	86.08 363	77.26 399	71.99 391	94.34 381	96.72 348	61.62 391	76.53 383	89.33 384	33.91 399	92.78 388	81.85 370	74.60 387	93.46 376

TinyColmap		92.31 310	91.53 311	94.65 321	96.92 285	89.75 330	96.92 334	96.68 350	90.45 327	89.62 345	97.85 225	76.06 359	98.81 243	86.74 346	92.51 283	95.41 352

Baseline_NR-MVSNet		94.35 260	93.81 260	95.96 275	96.20 322	94.05 243	98.61 175	96.67 351	91.44 303	93.85 267	97.60 249	88.57 206	98.14 313	94.39 207	86.93 351	95.68 349

SixPastTwentyTwo		93.34 293	92.86 292	94.75 318	95.67 341	89.41 339	98.75 143	96.67 351	93.89 204	90.15 342	98.25 193	80.87 326	98.27 307	90.90 300	90.64 304	96.57 307

test_fmvs3		87.17 342	87.06 345	87.50 361	91.21 379	75.66 385	99.05 65	96.61 353	92.79 262	88.85 353	92.78 376	43.72 391	93.49 384	93.95 223	84.56 361	93.34 378

EGC-MVSNET		75.22 357	69.54 360	92.28 351	94.81 360	89.58 335	97.64 285	96.50 354	1.82 401	5.57 402	95.74 344	68.21 375	96.26 369	73.80 386	91.71 291	90.99 381

APD_test1		88.22 339	88.01 339	88.86 359	95.98 332	74.66 389	97.21 315	96.44 355	83.96 376	86.66 365	97.90 219	60.95 385	97.84 337	82.73 367	90.23 309	94.09 371

WB-MVS		84.86 347	85.33 348	83.46 368	89.48 384	69.56 393	98.19 229	96.42 356	89.55 343	81.79 378	94.67 361	84.80 284	90.12 391	52.44 394	80.64 375	90.69 382

test_f		86.07 346	85.39 347	88.10 360	89.28 385	75.57 386	97.73 278	96.33 357	89.41 347	85.35 372	91.56 382	43.31 393	95.53 375	91.32 292	84.23 363	93.21 379

SSC-MVS		84.27 348	84.71 351	82.96 372	89.19 386	68.83 394	98.08 242	96.30 358	89.04 351	81.37 380	94.47 362	84.60 291	89.89 392	49.80 396	79.52 377	90.15 383

LFMVS		95.86 169	94.98 197	98.47 91	98.87 127	96.32 134	98.84 122	96.02 359	93.40 235	98.62 79	99.20 67	74.99 363	99.63 134	97.72 80	97.20 193	99.46 104

IB-MVS	91.98 17	93.27 295	91.97 308	97.19 185	97.47 246	93.41 266	97.09 326	95.99 360	93.32 238	92.47 315	95.73 346	78.06 346	99.53 153	94.59 203	82.98 365	98.62 198
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
test0.0.03 1		94.08 279	93.51 279	95.80 282	95.53 346	92.89 282	97.38 300	95.97 361	95.11 154	92.51 314	96.66 319	87.71 229	96.94 357	87.03 345	93.67 260	97.57 238

FPMVS		77.62 356	77.14 356	79.05 375	79.25 397	60.97 400	95.79 365	95.94 362	65.96 389	67.93 391	94.40 364	37.73 395	88.88 394	68.83 390	88.46 334	87.29 387

Patchmatch-RL test		91.49 315	90.85 316	93.41 338	91.37 378	84.40 371	92.81 384	95.93 363	91.87 292	87.25 360	94.87 359	88.99 195	96.53 366	92.54 267	82.00 367	99.30 125

tpm		94.13 274	93.80 261	95.12 304	96.50 309	87.91 362	97.44 295	95.89 364	92.62 266	96.37 191	96.30 331	84.13 302	98.30 302	93.24 243	91.66 293	99.14 152

LCM-MVSNet-Re		95.22 207	95.32 179	94.91 310	98.18 193	87.85 363	98.75 143	95.66 365	95.11 154	88.96 350	96.85 312	90.26 169	97.65 341	95.65 171	98.44 155	99.22 137

mvsany_test3		88.80 337	88.04 338	91.09 356	89.78 383	81.57 381	97.83 271	95.49 366	93.81 210	87.53 359	93.95 369	56.14 387	97.43 349	94.68 196	83.13 364	94.26 366

ET-MVSNet_ETH3D		94.13 274	92.98 290	97.58 165	98.22 186	96.20 138	97.31 309	95.37 367	94.53 179	79.56 382	97.63 248	86.51 249	97.53 347	96.91 119	90.74 303	99.02 165

MVS_0304		98.47 37	98.22 49	99.21 39	99.00 113	97.80 67	98.88 108	95.32 368	98.86 2	98.53 84	99.44 27	94.38 87	99.94 8	99.86 1	99.70 54	99.90 3

test-LLR		95.10 214	94.87 203	95.80 282	96.77 293	89.70 332	96.91 336	95.21 369	95.11 154	94.83 221	95.72 348	87.71 229	98.97 217	93.06 248	98.50 152	98.72 188

test-mter		94.08 279	93.51 279	95.80 282	96.77 293	89.70 332	96.91 336	95.21 369	92.89 258	94.83 221	95.72 348	77.69 348	98.97 217	93.06 248	98.50 152	98.72 188

PM-MVS		87.77 340	86.55 346	91.40 355	91.03 381	83.36 377	96.92 334	95.18 371	91.28 312	86.48 367	93.42 372	53.27 388	96.74 360	89.43 325	81.97 368	94.11 370

DeepMVS_CX				86.78 362	97.09 277	72.30 390		95.17 372	75.92 384	84.34 375	95.19 355	70.58 372	95.35 376	79.98 376	89.04 328	92.68 380

K. test v3		92.55 307	91.91 310	94.48 326	95.64 342	89.24 340	99.07 62	94.88 373	94.04 194	86.78 363	97.59 250	77.64 351	97.64 342	92.08 275	89.43 322	96.57 307

TESTMET0.1,1		94.18 272	93.69 271	95.63 288	96.92 285	89.12 342	96.91 336	94.78 374	93.17 245	94.88 218	96.45 328	78.52 340	98.92 228	93.09 247	98.50 152	98.85 179

pmmvs3		86.67 345	84.86 350	92.11 353	88.16 387	87.19 367	96.63 352	94.75 375	79.88 381	87.22 361	92.75 378	66.56 381	95.20 379	81.24 372	76.56 385	93.96 374

door								94.64 376

thisisatest0515		95.61 186	94.89 202	97.76 149	98.15 197	95.15 193	96.77 347	94.41 377	92.95 256	97.18 152	97.43 262	84.78 285	99.45 166	94.63 198	97.73 183	98.68 192

door-mid								94.37 378

tttt0517		96.07 156	95.51 169	97.78 146	98.41 166	94.84 208	99.28 24	94.33 379	94.26 189	97.64 140	98.64 146	84.05 303	99.47 164	95.34 178	97.60 187	99.03 164

DSMNet-mixed		92.52 309	92.58 299	92.33 350	94.15 365	82.65 378	98.30 215	94.26 380	89.08 350	92.65 308	95.73 346	85.01 280	95.76 374	86.24 349	97.76 181	98.59 201

thisisatest0530		96.01 158	95.36 175	97.97 134	98.38 167	95.52 174	98.88 108	94.19 381	94.04 194	97.64 140	98.31 185	83.82 310	99.46 165	95.29 182	97.70 184	98.93 175

MTMP							98.89 103	94.14 382

baseline2		95.11 213	94.52 217	96.87 209	96.65 302	93.56 258	98.27 220	94.10 383	93.45 233	92.02 325	97.43 262	87.45 237	99.19 186	93.88 226	97.41 191	97.87 226

PMVS	61.03 23	65.95 360	63.57 364	73.09 378	57.90 402	51.22 405	85.05 391	93.93 384	54.45 392	44.32 398	83.57 387	13.22 402	89.15 393	58.68 393	81.00 372	78.91 392
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		79.02 351	77.70 353	82.99 370	88.10 388	66.90 395	94.67 377	93.11 385	71.08 387	74.02 385	93.41 373	34.15 397	93.25 385	72.25 387	78.50 380	88.82 385

APD_test2		79.02 351	77.70 353	82.99 370	88.10 388	66.90 395	94.67 377	93.11 385	71.08 387	74.02 385	93.41 373	34.15 397	93.25 385	72.25 387	78.50 380	88.82 385

PMMVS2		77.95 355	75.44 359	85.46 364	82.54 394	74.95 387	94.23 382	93.08 387	72.80 386	74.68 384	87.38 385	36.36 396	91.56 389	73.95 385	63.94 392	89.87 384

MVS-HIRNet		89.46 335	88.40 335	92.64 347	97.58 236	82.15 379	94.16 383	93.05 388	75.73 385	90.90 334	82.52 388	79.42 336	98.33 297	83.53 366	98.68 140	97.43 239

test1111		95.94 164	95.78 154	96.41 254	98.99 117	90.12 326	99.04 68	92.45 389	96.99 66	98.03 109	99.27 56	81.40 320	99.48 162	96.87 128	99.04 123	99.63 73

ECVR-MVS		95.95 162	95.71 161	96.65 222	99.02 110	90.86 312	99.03 71	91.80 390	96.96 67	98.10 103	99.26 57	81.31 321	99.51 157	96.90 122	99.04 123	99.59 79

EPMVS		94.99 220	94.48 219	96.52 243	97.22 265	91.75 296	97.23 313	91.66 391	94.11 191	97.28 148	96.81 314	85.70 266	98.84 239	93.04 250	97.28 192	98.97 170

dmvs_testset		87.64 341	88.93 334	83.79 367	95.25 353	63.36 398	97.20 316	91.17 392	93.07 250	85.64 371	95.98 342	85.30 277	91.52 390	69.42 389	87.33 346	96.49 323

lessismore_v0				94.45 329	94.93 358	88.44 355		91.03 393		86.77 364	97.64 246	76.23 358	98.42 281	90.31 307	85.64 360	96.51 320

test_vis1_rt		91.29 317	90.65 317	93.19 344	97.45 250	86.25 369	98.57 183	90.90 394	93.30 240	86.94 362	93.59 371	62.07 384	99.11 198	97.48 100	95.58 234	94.22 368

ANet_high		69.08 358	65.37 362	80.22 374	65.99 401	71.96 392	90.91 388	90.09 395	82.62 377	49.93 397	78.39 392	29.36 400	81.75 395	62.49 392	38.52 396	86.95 389

gg-mvs-nofinetune		92.21 311	90.58 319	97.13 190	96.75 296	95.09 195	95.85 364	89.40 396	85.43 371	94.50 230	81.98 389	80.80 328	98.40 295	92.16 273	98.33 162	97.88 225

GG-mvs-BLEND				96.59 232	96.34 318	94.98 201	96.51 356	88.58 397		93.10 297	94.34 367	80.34 332	98.05 321	89.53 322	96.99 197	96.74 285

E-PMN		64.94 361	64.25 363	67.02 379	82.28 395	59.36 402	91.83 387	85.63 398	52.69 393	60.22 394	77.28 393	41.06 394	80.12 397	46.15 397	41.14 394	61.57 395

EMVS		64.07 362	63.26 365	66.53 380	81.73 396	58.81 403	91.85 386	84.75 399	51.93 395	59.09 395	75.13 394	43.32 392	79.09 398	42.03 398	39.47 395	61.69 394

tmp_tt		68.90 359	66.97 361	74.68 377	50.78 403	59.95 401	87.13 389	83.47 400	38.80 397	62.21 393	96.23 334	64.70 382	76.91 399	88.91 331	30.49 397	87.19 388

test_vis3_rt		79.22 349	77.40 355	84.67 366	86.44 391	74.85 388	97.66 283	81.43 401	84.98 372	67.12 392	81.91 390	28.09 401	97.60 343	88.96 330	80.04 376	81.55 390

MVE	62.14 22	63.28 363	59.38 366	74.99 376	74.33 400	65.47 397	85.55 390	80.50 402	52.02 394	51.10 396	75.00 395	10.91 405	80.50 396	51.60 395	53.40 393	78.99 391
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2506		94.44 256	93.91 253	96.04 270	99.02 110	88.99 346	99.06 63	79.47 403	96.96 67	98.36 94	99.26 57	77.21 353	99.52 156	96.78 134	99.04 123	99.59 79

N_pmnet		87.12 344	87.77 342	85.17 365	95.46 349	61.92 399	97.37 302	70.66 404	85.83 368	88.73 355	96.04 340	85.33 275	97.76 339	80.02 374	90.48 305	95.84 345

wuyk23d		30.17 364	30.18 368	30.16 381	78.61 398	43.29 406	66.79 394	14.21 405	17.31 398	14.82 401	11.93 401	11.55 404	41.43 400	37.08 399	19.30 398	5.76 398

testmvs		21.48 366	24.95 369	11.09 383	14.89 404	6.47 408	96.56 354	9.87 406	7.55 399	17.93 399	39.02 397	9.43 406	5.90 402	16.56 401	12.72 399	20.91 397

test123		20.95 367	23.72 370	12.64 382	13.54 405	8.19 407	96.55 355	6.13 407	7.48 400	16.74 400	37.98 398	12.97 403	6.05 401	16.69 400	5.43 400	23.68 396

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

pcd_1.5k_mvsjas		7.88 369	10.50 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	94.51 81	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

n2								0.00 408

nn								0.00 408

ab-mvs-re		8.20 368	10.94 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	98.43 168	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						90.94 310								88.66 333

PC_three_1452									95.08 158	99.60 19	99.16 77	97.86 2	98.47 275	97.52 98	99.72 51	99.74 37

eth-test2					0.00 406

eth-test					0.00 406

OPU-MVS				99.37 20	99.24 87	99.05 14	99.02 74				99.16 77	97.81 3	99.37 170	97.24 107	99.73 48	99.70 53

test_0728_THIRD									97.32 42	99.45 25	99.46 24	97.88 1	99.94 8	98.47 38	99.86 1	99.85 10

GSMVS																99.20 139

test_part2					99.63 29	99.18 10				99.27 35

sam_mvs1												89.45 181				99.20 139

sam_mvs												88.99 195

test_post1							96.68 351				30.43 400	87.85 227	98.69 251	92.59 263

test_post											31.83 399	88.83 202	98.91 229

patchmatchnet-post											95.10 357	89.42 182	98.89 233

gm-plane-assit					95.88 336	87.47 364			89.74 340		96.94 306		99.19 186	93.32 242

test9_res														96.39 146	99.57 80	99.69 56

agg_prior2														95.87 162	99.57 80	99.68 61

test_prior4						98.01 59	97.86 267

test_prior2							97.80 272		96.12 103	97.89 124	98.69 141	95.96 37		96.89 123	99.60 74

旧先验2							97.57 291		91.30 310	98.67 73			99.80 88	95.70 170

新几何2							97.64 285

原ACMM2							97.67 282

testdata2													99.89 47	91.65 288

segment_acmp												96.85 14

testdata1							97.32 308		96.34 95

plane_prior7					97.42 252	94.63 217

plane_prior6					97.35 259	94.61 220						87.09 240

plane_prior4											98.28 187

plane_prior3						94.61 220			97.02 64	95.34 209

plane_prior2							98.80 135		97.28 45

plane_prior1					97.37 258

plane_prior						94.60 222	98.44 199		96.74 77						94.22 242

HQP5-MVS						94.25 237

HQP-NCC					97.20 267		98.05 245		96.43 89	94.45 232

ACMP_Plane					97.20 267		98.05 245		96.43 89	94.45 232

BP-MVS														95.30 180

HQP4-MVS										94.45 232			98.96 221			96.87 271

HQP2-MVS												86.75 246

NP-MVS					97.28 261	94.51 225					97.73 235

MDTV_nov1_ep13_2view						84.26 372	96.89 341		90.97 319	97.90 123		89.89 173		93.91 225		99.18 148

ACMMP++_ref															92.97 277

ACMMP++															93.61 264

Test By Simon												94.64 78

High-resolution multi-view benchmark