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		97.12 129	96.80 126	98.08 141	99.30 72	94.56 236	98.05 265	99.71 1	93.57 255	97.09 172	98.91 126	88.17 230	99.89 54	96.87 142	99.56 94	99.81 18

HyFIR lowres test		96.90 138	96.49 144	98.14 132	99.33 63	95.56 180	97.38 329	99.65 2	92.34 305	97.61 158	98.20 205	89.29 199	99.10 226	96.97 130	97.60 201	99.77 30

MVS_111021_LR		98.34 58	98.23 54	98.67 84	99.27 82	96.90 114	97.95 276	99.58 3	97.14 66	98.44 102	99.01 111	95.03 79	99.62 146	97.91 80	99.75 48	99.50 95

MVS_111021_HR		98.47 43	98.34 41	98.88 72	99.22 95	97.32 91	97.91 283	99.58 3	97.20 61	98.33 108	99.00 112	95.99 40	99.64 139	98.05 73	99.76 42	99.69 60

PGM-MVS		98.49 40	98.23 54	99.27 38	99.72 12	98.08 62	98.99 86	99.49 5	95.43 146	99.03 55	99.32 55	95.56 52	99.94 10	96.80 148	99.77 36	99.78 24

ACMMP		98.23 64	97.95 72	99.09 56	99.74 7	97.62 77	99.03 76	99.41 6	95.98 119	97.60 159	99.36 48	94.45 91	99.93 29	97.14 124	98.85 148	99.70 57
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 49	98.51 22	98.13 135	99.30 72	95.25 198	98.85 127	99.39 7	97.94 21	99.74 13	99.62 3	92.59 117	99.91 45	99.65 10	99.52 100	99.25 141

fmvsm_s_conf0.5_n_a		98.38 52	98.42 30	98.27 120	99.09 112	95.41 188	98.86 123	99.37 8	97.69 28	99.78 9	99.61 4	92.38 120	99.91 45	99.58 14	99.43 112	99.49 100

test_fmvsm_n_1920		98.87 14	99.01 3	98.45 106	99.42 58	96.43 138	98.96 94	99.36 9	98.63 8	99.86 4	99.51 20	95.91 43	99.97 1	99.72 7	99.75 48	98.94 188

test_fmvsmconf_n		98.92 10	98.87 6	99.04 59	98.88 133	97.25 99	98.82 135	99.34 10	98.75 6	99.80 7	99.61 4	95.16 73	99.95 8	99.70 9	99.80 24	99.93 1

CSCG		97.85 80	97.74 78	98.20 129	99.67 25	95.16 202	99.22 36	99.32 11	93.04 279	97.02 178	98.92 125	95.36 61	99.91 45	97.43 116	99.64 76	99.52 90

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 51	99.41 59	97.54 81	98.89 110	99.31 12	98.49 12	99.86 4	99.42 35	96.45 24	99.96 4	99.86 1	99.74 52	99.90 3

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 55	99.43 57	97.48 83	98.88 116	99.30 13	98.47 13	99.85 6	99.43 34	96.71 17	99.96 4	99.86 1	99.80 24	99.89 4

patch_mono-2		98.36 55	98.87 6	96.82 229	99.53 36	90.68 337	98.64 183	99.29 14	97.88 22	99.19 48	99.52 18	96.80 15	99.97 1	99.11 22	99.86 2	99.82 17

fmvsm_s_conf0.5_n_3		98.53 36	98.45 28	98.79 75	99.23 93	97.32 91	98.80 144	99.26 15	98.82 2	99.87 2	99.60 8	90.95 165	99.93 29	99.76 6	99.73 55	99.12 163

PVSNet_BlendedMVS		96.73 144	96.60 139	97.12 208	99.25 85	95.35 193	98.26 237	99.26 15	94.28 209	97.94 132	97.46 270	92.74 115	99.81 88	96.88 139	93.32 295	96.20 362

PVSNet_Blended		97.38 114	97.12 111	98.14 132	99.25 85	95.35 193	97.28 340	99.26 15	93.13 275	97.94 132	98.21 204	92.74 115	99.81 88	96.88 139	99.40 117	99.27 136

fmvsm_l_conf0.5_n_3		98.90 12	98.74 14	99.37 22	99.36 60	98.25 50	98.89 110	99.24 18	98.77 5	99.89 1	99.59 10	93.39 106	99.96 4	99.78 5	99.76 42	99.89 4

fmvsm_s_conf0.1_n		98.18 67	98.21 56	98.11 139	98.54 170	95.24 199	98.87 119	99.24 18	97.50 39	99.70 17	99.67 1	91.33 154	99.89 54	99.47 16	99.54 97	99.21 147

UniMVSNet_NR-MVSNet		95.71 189	95.15 201	97.40 192	96.84 318	96.97 110	98.74 157	99.24 18	95.16 163	93.88 289	97.72 247	91.68 142	98.31 325	95.81 178	87.25 374	96.92 286

WR-MVS_H		95.05 233	94.46 238	96.81 230	96.86 317	95.82 173	99.24 30	99.24 18	93.87 231	92.53 339	96.84 333	90.37 174	98.24 333	93.24 264	87.93 365	96.38 355

SDMVSNet		96.85 140	96.42 145	98.14 132	99.30 72	96.38 141	99.21 39	99.23 22	95.92 121	95.96 224	98.76 148	85.88 277	99.44 183	97.93 78	95.59 259	98.60 221

FC-MVSNet-test		96.42 156	96.05 158	97.53 184	96.95 310	97.27 94	99.36 13	99.23 22	95.83 127	93.93 286	98.37 185	92.00 135	98.32 323	96.02 172	92.72 304	97.00 280

VPA-MVSNet		95.75 187	95.11 205	97.69 171	97.24 290	97.27 94	98.94 98	99.23 22	95.13 164	95.51 231	97.32 283	85.73 279	98.91 254	97.33 121	89.55 344	96.89 294

FIs		96.51 153	96.12 156	97.67 174	97.13 301	97.54 81	99.36 13	99.22 25	95.89 123	94.03 283	98.35 187	91.98 136	98.44 303	96.40 159	92.76 303	97.01 279

fmvsm_s_conf0.5_n_2		98.30 63	98.21 56	98.57 90	99.25 85	97.11 105	98.66 179	99.20 26	98.82 2	99.79 8	99.60 8	89.38 196	99.92 36	99.80 4	99.38 119	98.69 210

tfpnnormal		93.66 311	92.70 322	96.55 258	96.94 311	95.94 164	98.97 89	99.19 27	91.04 346	91.38 358	97.34 280	84.94 294	98.61 286	85.45 383	89.02 355	95.11 384

UniMVSNet (Re)		95.78 186	95.19 200	97.58 181	96.99 308	97.47 85	98.79 151	99.18 28	95.60 138	93.92 287	97.04 312	91.68 142	98.48 296	95.80 180	87.66 368	96.79 305

fmvsm_s_conf0.1_n_a		98.08 69	98.04 68	98.21 127	97.66 257	95.39 189	98.89 110	99.17 29	97.24 58	99.76 12	99.67 1	91.13 159	99.88 63	99.39 17	99.41 114	99.35 120

PVSNet_Blended_VisFu		97.70 88	97.46 94	98.44 108	99.27 82	95.91 169	98.63 186	99.16 30	94.48 204	97.67 151	98.88 130	92.80 114	99.91 45	97.11 125	99.12 131	99.50 95

test_fmvsmvis_n_1920		98.44 46	98.51 22	98.23 126	98.33 191	96.15 152	98.97 89	99.15 31	98.55 11	98.45 100	99.55 13	94.26 96	99.97 1	99.65 10	99.66 69	98.57 227

CHOSEN 280x420		97.18 125	97.18 110	97.20 199	98.81 142	93.27 285	95.78 395	99.15 31	95.25 159	96.79 191	98.11 211	92.29 123	99.07 229	98.56 41	99.85 6	99.25 141

D2MVS		95.18 225	95.08 206	95.48 313	97.10 303	92.07 309	98.30 231	99.13 33	94.02 219	92.90 327	96.73 338	89.48 191	98.73 276	94.48 226	93.60 289	95.65 375

PHI-MVS		98.34 58	98.06 66	99.18 46	99.15 106	98.12 61	99.04 73	99.09 34	93.32 265	98.83 74	99.10 93	96.54 21	99.83 76	97.70 97	99.76 42	99.59 83

sd_testset		96.17 167	95.76 169	97.42 189	99.30 72	94.34 245	98.82 135	99.08 35	95.92 121	95.96 224	98.76 148	82.83 327	99.32 195	95.56 189	95.59 259	98.60 221

UA-Net		97.96 73	97.62 81	98.98 63	98.86 137	97.47 85	98.89 110	99.08 35	96.67 92	98.72 83	99.54 15	93.15 110	99.81 88	94.87 210	98.83 149	99.65 73

PatchMatch-RL		96.59 149	96.03 160	98.27 120	99.31 68	96.51 134	97.91 283	99.06 37	93.72 242	96.92 183	98.06 214	88.50 225	99.65 136	91.77 307	99.00 139	98.66 216

3Dnovator	94.51 5	97.46 105	96.93 121	99.07 57	97.78 245	97.64 75	99.35 15	99.06 37	97.02 72	93.75 297	99.16 84	89.25 200	99.92 36	97.22 123	99.75 48	99.64 75

MSLP-MVS++		98.56 33	98.57 19	98.55 93	99.26 84	96.80 118	98.71 166	99.05 39	97.28 53	98.84 72	99.28 60	96.47 23	99.40 186	98.52 48	99.70 62	99.47 104

PS-CasMVS		94.67 258	93.99 270	96.71 234	96.68 329	95.26 197	99.13 57	99.03 40	93.68 248	92.33 345	97.95 225	85.35 286	98.10 341	93.59 256	88.16 364	96.79 305

TranMVSNet+NR-MVSNet		95.14 227	94.48 236	97.11 209	96.45 341	96.36 143	99.03 76	99.03 40	95.04 171	93.58 300	97.93 226	88.27 228	98.03 347	94.13 238	86.90 379	96.95 284

PEN-MVS		94.42 279	93.73 291	96.49 262	96.28 347	94.84 219	99.17 49	99.00 42	93.51 256	92.23 347	97.83 239	86.10 273	97.90 357	92.55 287	86.92 378	96.74 310

Vis-MVSNet		97.42 111	97.11 112	98.34 116	98.66 158	96.23 148	99.22 36	99.00 42	96.63 94	98.04 121	99.21 72	88.05 236	99.35 191	96.01 173	99.21 127	99.45 110
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DU-MVS		95.42 207	94.76 220	97.40 192	96.53 335	96.97 110	98.66 179	98.99 44	95.43 146	93.88 289	97.69 250	88.57 220	98.31 325	95.81 178	87.25 374	96.92 286

test_fmvsmconf0.1_n		98.58 27	98.44 29	98.99 61	97.73 251	97.15 104	98.84 131	98.97 45	98.75 6	99.43 31	99.54 15	93.29 108	99.93 29	99.64 12	99.79 30	99.89 4

VPNet		94.99 237	94.19 252	97.40 192	97.16 299	96.57 131	98.71 166	98.97 45	95.67 136	94.84 244	98.24 203	80.36 347	98.67 282	96.46 156	87.32 373	96.96 282

OpenMVS	93.04 13	95.83 184	95.00 209	98.32 117	97.18 298	97.32 91	99.21 39	98.97 45	89.96 364	91.14 360	99.05 105	86.64 262	99.92 36	93.38 260	99.47 107	97.73 258

HFP-MVS		98.63 21	98.40 31	99.32 32	99.72 12	98.29 47	99.23 32	98.96 48	96.10 117	98.94 62	99.17 81	96.06 36	99.92 36	97.62 102	99.78 34	99.75 38

FOURS1					99.82 1	98.66 24	99.69 1	98.95 49	97.46 42	99.39 34

ACMMPR		98.59 25	98.36 35	99.29 33	99.74 7	98.15 58	99.23 32	98.95 49	96.10 117	98.93 66	99.19 79	95.70 49	99.94 10	97.62 102	99.79 30	99.78 24

CP-MVSNet		94.94 244	94.30 246	96.83 228	96.72 327	95.56 180	99.11 60	98.95 49	93.89 229	92.42 344	97.90 229	87.19 253	98.12 340	94.32 232	88.21 362	96.82 304

NR-MVSNet		94.98 239	94.16 255	97.44 187	96.53 335	97.22 101	98.74 157	98.95 49	94.96 177	89.25 378	97.69 250	89.32 198	98.18 335	94.59 223	87.40 371	96.92 286

region2R		98.61 22	98.38 33	99.29 33	99.74 7	98.16 57	99.23 32	98.93 53	96.15 113	98.94 62	99.17 81	95.91 43	99.94 10	97.55 110	99.79 30	99.78 24

APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 33	98.96 16	99.39 10	98.93 53	97.38 47	99.41 32	99.54 15	96.66 18	99.84 74	98.86 29	99.85 6	99.87 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
VNet		97.79 83	97.40 98	98.96 66	98.88 133	97.55 79	98.63 186	98.93 53	96.74 86	99.02 56	98.84 134	90.33 176	99.83 76	98.53 42	96.66 226	99.50 95

UGNet		96.78 143	96.30 150	98.19 131	98.24 199	95.89 171	98.88 116	98.93 53	97.39 46	96.81 189	97.84 236	82.60 328	99.90 52	96.53 154	99.49 104	98.79 199
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		97.39 113	96.98 120	98.61 88	98.60 166	96.61 127	98.22 240	98.93 53	93.97 225	98.01 127	98.48 174	91.98 136	99.85 70	96.45 157	98.15 181	99.39 116

QAPM		96.29 162	95.40 184	98.96 66	97.85 241	97.60 78	99.23 32	98.93 53	89.76 368	93.11 323	99.02 107	89.11 205	99.93 29	91.99 301	99.62 79	99.34 122

DPE-MVS		98.92 10	98.67 16	99.65 2	99.58 32	99.20 9	98.42 219	98.91 59	97.58 34	99.54 26	99.46 31	97.10 12	99.94 10	97.64 101	99.84 11	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		96.93 136	96.27 151	98.92 68	99.50 42	97.63 76	98.85 127	98.90 60	84.80 402	97.77 140	99.11 91	92.84 113	99.66 135	94.85 211	99.77 36	99.47 104

LS3D		97.16 126	96.66 138	98.68 83	98.53 171	97.19 102	98.93 101	98.90 60	92.83 288	95.99 222	99.37 44	92.12 131	99.87 65	93.67 254	99.57 88	98.97 184

DELS-MVS		98.40 51	98.20 58	98.99 61	99.00 120	97.66 74	97.75 304	98.89 62	97.71 26	98.33 108	98.97 114	94.97 80	99.88 63	98.42 56	99.76 42	99.42 115
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 78	97.46 94	99.06 58	99.53 36	98.35 44	98.33 224	98.89 62	92.62 294	98.05 119	98.94 122	95.34 62	99.65 136	96.04 171	99.42 113	99.19 152

AdaColmap		97.15 127	96.70 134	98.48 103	99.16 104	96.69 124	98.01 270	98.89 62	94.44 206	96.83 186	98.68 154	90.69 170	99.76 114	94.36 229	99.29 126	98.98 183

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 100	99.23 7	99.69 1	98.88 65	97.32 50	99.53 27	99.47 27	97.81 3	99.94 10	98.47 50	99.72 59	99.74 40

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 89	98.88 65					99.94 10	98.47 50	99.81 15	99.84 12

test0726					99.72 12	99.25 2	99.06 67	98.88 65	97.62 31	99.56 24	99.50 22	97.42 9

MSP-MVS		98.74 17	98.55 21	99.29 33	99.75 3	98.23 51	99.26 27	98.88 65	97.52 37	99.41 32	98.78 141	96.00 39	99.79 105	97.79 88	99.59 84	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		94.10 302	93.26 311	96.61 247	99.11 110	94.28 247	99.01 81	98.88 65	86.43 392	92.81 329	97.57 264	81.66 332	98.68 281	94.83 212	89.02 355	96.88 295

XVS		98.70 18	98.49 25	99.34 26	99.70 22	98.35 44	99.29 22	98.88 65	97.40 44	98.46 97	99.20 74	95.90 45	99.89 54	97.85 84	99.74 52	99.78 24

X-MVStestdata		94.06 306	92.30 332	99.34 26	99.70 22	98.35 44	99.29 22	98.88 65	97.40 44	98.46 97	43.50 428	95.90 45	99.89 54	97.85 84	99.74 52	99.78 24

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 79	98.87 72	97.65 29	99.73 14	99.48 25	97.53 7	99.94 10	98.43 54	99.81 15	99.70 57

test_241102_TWO								98.87 72	97.65 29	99.53 27	99.48 25	97.34 11	99.94 10	98.43 54	99.80 24	99.83 13

test_241102_ONE					99.71 19	99.24 5		98.87 72	97.62 31	99.73 14	99.39 38	97.53 7	99.74 118

CP-MVS		98.57 31	98.36 35	99.19 44	99.66 26	97.86 69	99.34 16	98.87 72	95.96 120	98.60 92	99.13 89	96.05 37	99.94 10	97.77 89	99.86 2	99.77 30

SteuartSystems-ACMMP		98.90 12	98.75 13	99.36 24	99.22 95	98.43 33	99.10 63	98.87 72	97.38 47	99.35 36	99.40 37	97.78 5	99.87 65	97.77 89	99.85 6	99.78 24
Skip Steuart: Steuart Systems R&D Blog.
DeepPCF-MVS	96.37 2	97.93 76	98.48 27	96.30 279	99.00 120	89.54 361	97.43 326	98.87 72	98.16 15	99.26 44	99.38 43	96.12 35	99.64 139	98.30 61	99.77 36	99.72 49

test_one_0601					99.66 26	99.25 2		98.86 78	97.55 36	99.20 46	99.47 27	97.57 6

ZNCC-MVS		98.49 40	98.20 58	99.35 25	99.73 11	98.39 34	99.19 44	98.86 78	95.77 130	98.31 110	99.10 93	95.46 55	99.93 29	97.57 109	99.81 15	99.74 40

DTE-MVSNet		93.98 308	93.26 311	96.14 284	96.06 356	94.39 242	99.20 42	98.86 78	93.06 278	91.78 353	97.81 241	85.87 278	97.58 373	90.53 330	86.17 383	96.46 352

SD-MVS		98.64 20	98.68 15	98.53 97	99.33 63	98.36 43	98.90 106	98.85 81	97.28 53	99.72 16	99.39 38	96.63 20	97.60 371	98.17 66	99.85 6	99.64 75
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
reproduce_model		98.94 7	98.81 10	99.34 26	99.52 39	98.26 49	98.94 98	98.84 82	98.06 17	99.35 36	99.61 4	96.39 27	99.94 10	98.77 32	99.82 14	99.83 13

test_prior				99.19 44	99.31 68	98.22 52		98.84 82					99.70 126			99.65 73

reproduce-ours		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 123	98.83 84	98.06 17	99.29 40	99.58 11	96.40 25	99.94 10	98.68 34	99.81 15	99.81 18

our_new_method		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 123	98.83 84	98.06 17	99.29 40	99.58 11	96.40 25	99.94 10	98.68 34	99.81 15	99.81 18

Anonymous20240529		95.10 230	94.22 250	97.75 165	99.01 119	94.26 249	98.87 119	98.83 84	85.79 398	96.64 194	98.97 114	78.73 357	99.85 70	96.27 162	94.89 264	99.12 163

fmvsm_s_conf0.1_n_2		98.14 68	98.02 69	98.53 97	98.88 133	97.07 107	98.69 172	98.82 87	98.78 4	99.77 10	99.61 4	88.83 215	99.91 45	99.71 8	99.07 132	98.61 220

9.14			98.06 66		99.47 50		98.71 166	98.82 87	94.36 208	99.16 52	99.29 59	96.05 37	99.81 88	97.00 128	99.71 61

SR-MVS		98.57 31	98.35 37	99.24 40	99.53 36	98.18 55	99.09 64	98.82 87	96.58 95	99.10 54	99.32 55	95.39 58	99.82 83	97.70 97	99.63 77	99.72 49

GST-MVS		98.43 48	98.12 62	99.34 26	99.72 12	98.38 35	99.09 64	98.82 87	95.71 134	98.73 82	99.06 104	95.27 66	99.93 29	97.07 127	99.63 77	99.72 49

HPM-MVS_fast		98.38 52	98.13 61	99.12 54	99.75 3	97.86 69	99.44 9	98.82 87	94.46 205	98.94 62	99.20 74	95.16 73	99.74 118	97.58 105	99.85 6	99.77 30

APD-MVS		98.35 57	98.00 71	99.42 16	99.51 40	98.72 21	98.80 144	98.82 87	94.52 202	99.23 45	99.25 68	95.54 54	99.80 95	96.52 155	99.77 36	99.74 40
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SF-MVS		98.59 25	98.32 46	99.41 17	99.54 35	98.71 22	99.04 73	98.81 93	95.12 165	99.32 39	99.39 38	96.22 30	99.84 74	97.72 92	99.73 55	99.67 69

ACMMP_NAP		98.61 22	98.30 47	99.55 9	99.62 30	98.95 17	98.82 135	98.81 93	95.80 128	99.16 52	99.47 27	95.37 60	99.92 36	97.89 82	99.75 48	99.79 22

APD-MVS_3200maxsize		98.53 36	98.33 45	99.15 50	99.50 42	97.92 68	99.15 51	98.81 93	96.24 109	99.20 46	99.37 44	95.30 64	99.80 95	97.73 91	99.67 66	99.72 49

WR-MVS		95.15 226	94.46 238	97.22 198	96.67 330	96.45 136	98.21 241	98.81 93	94.15 213	93.16 319	97.69 250	87.51 247	98.30 327	95.29 199	88.62 359	96.90 293

mPP-MVS		98.51 38	98.26 49	99.25 39	99.75 3	98.04 63	99.28 24	98.81 93	96.24 109	98.35 107	99.23 69	95.46 55	99.94 10	97.42 117	99.81 15	99.77 30

CNVR-MVS		98.78 15	98.56 20	99.45 15	99.32 66	98.87 19	98.47 211	98.81 93	97.72 24	98.76 79	99.16 84	97.05 13	99.78 108	98.06 71	99.66 69	99.69 60

CPTT-MVS		97.72 86	97.32 102	98.92 68	99.64 28	97.10 106	99.12 58	98.81 93	92.34 305	98.09 116	99.08 102	93.01 111	99.92 36	96.06 170	99.77 36	99.75 38

SR-MVS-dyc-post		98.54 35	98.35 37	99.13 52	99.49 46	97.86 69	99.11 60	98.80 100	96.49 98	99.17 49	99.35 50	95.34 62	99.82 83	97.72 92	99.65 72	99.71 53

RE-MVS-def			98.34 41		99.49 46	97.86 69	99.11 60	98.80 100	96.49 98	99.17 49	99.35 50	95.29 65		97.72 92	99.65 72	99.71 53

SMA-MVS		98.58 27	98.25 50	99.56 8	99.51 40	99.04 15	98.95 95	98.80 100	93.67 250	99.37 35	99.52 18	96.52 22	99.89 54	98.06 71	99.81 15	99.76 37
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 55	98.10 65	99.13 52	99.74 7	97.82 73	99.53 6	98.80 100	94.63 194	98.61 91	98.97 114	95.13 75	99.77 113	97.65 100	99.83 13	99.79 22
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPMNet		92.81 331	91.34 342	97.24 197	97.00 306	93.43 276	94.96 402	98.80 100	82.27 409	96.93 181	92.12 413	86.98 257	99.82 83	76.32 414	96.65 227	98.46 232

ZD-MVS					99.46 52	98.70 23		98.79 105	93.21 270	98.67 84	98.97 114	95.70 49	99.83 76	96.07 167	99.58 87

MP-MVS		98.33 60	98.01 70	99.28 36	99.75 3	98.18 55	99.22 36	98.79 105	96.13 114	97.92 135	99.23 69	94.54 86	99.94 10	96.74 151	99.78 34	99.73 45
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CANet		98.05 71	97.76 77	98.90 71	98.73 146	97.27 94	98.35 222	98.78 107	97.37 49	97.72 147	98.96 119	91.53 150	99.92 36	98.79 31	99.65 72	99.51 93

MP-MVS-pluss		98.31 61	97.92 73	99.49 12	99.72 12	98.88 18	98.43 217	98.78 107	94.10 215	97.69 150	99.42 35	95.25 68	99.92 36	98.09 70	99.80 24	99.67 69
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepC-MVS_fast	96.70 1	98.55 34	98.34 41	99.18 46	99.25 85	98.04 63	98.50 208	98.78 107	97.72 24	98.92 68	99.28 60	95.27 66	99.82 83	97.55 110	99.77 36	99.69 60
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 82	97.60 82	98.44 108	99.12 108	95.97 161	97.75 304	98.78 107	96.89 78	98.46 97	99.22 71	93.90 102	99.68 132	94.81 214	99.52 100	99.67 69

NCCC		98.61 22	98.35 37	99.38 18	99.28 81	98.61 26	98.45 212	98.76 111	97.82 23	98.45 100	98.93 123	96.65 19	99.83 76	97.38 119	99.41 114	99.71 53

PLC	95.07 4	97.20 124	96.78 129	98.44 108	99.29 77	96.31 147	98.14 253	98.76 111	92.41 303	96.39 210	98.31 194	94.92 82	99.78 108	94.06 242	98.77 152	99.23 143
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
h-mvs33		96.17 167	95.62 180	97.81 158	99.03 116	94.45 238	98.64 183	98.75 113	97.48 40	98.67 84	98.72 151	89.76 184	99.86 69	97.95 76	81.59 399	99.11 166

DeepC-MVS	95.98 3	97.88 77	97.58 83	98.77 76	99.25 85	96.93 112	98.83 133	98.75 113	96.96 75	96.89 185	99.50 22	90.46 173	99.87 65	97.84 86	99.76 42	99.52 90
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MTGPA								98.74 115

MTAPA		98.58 27	98.29 48	99.46 14	99.76 2	98.64 25	98.90 106	98.74 115	97.27 57	98.02 124	99.39 38	94.81 83	99.96 4	97.91 80	99.79 30	99.77 30

ab-mvs		96.42 156	95.71 174	98.55 93	98.63 163	96.75 121	97.88 290	98.74 115	93.84 232	96.54 203	98.18 207	85.34 287	99.75 116	95.93 174	96.35 236	99.15 159

TEST9					99.31 68	98.50 29	97.92 281	98.73 118	92.63 293	97.74 144	98.68 154	96.20 32	99.80 95

train_agg		97.97 72	97.52 89	99.33 30	99.31 68	98.50 29	97.92 281	98.73 118	92.98 281	97.74 144	98.68 154	96.20 32	99.80 95	96.59 152	99.57 88	99.68 65

test_8					99.29 77	98.44 31	97.89 289	98.72 120	92.98 281	97.70 149	98.66 157	96.20 32	99.80 95

agg_prior					99.30 72	98.38 35		98.72 120		97.57 161			99.81 88

无先验							97.58 318	98.72 120	91.38 332				99.87 65	93.36 262		99.60 81

save fliter					99.46 52	98.38 35	98.21 241	98.71 123	97.95 20

mamv4		97.13 128	98.11 63	94.17 360	98.97 126	83.70 403	98.66 179	98.71 123	94.63 194	97.83 138	98.90 127	96.25 29	99.55 162	99.27 19	99.76 42	99.27 136

WTY-MVS		97.37 116	96.92 122	98.72 80	98.86 137	96.89 116	98.31 229	98.71 123	95.26 158	97.67 151	98.56 168	92.21 128	99.78 108	95.89 175	96.85 220	99.48 102

3Dnovator+	94.38 6	97.43 110	96.78 129	99.38 18	97.83 242	98.52 28	99.37 12	98.71 123	97.09 70	92.99 326	99.13 89	89.36 197	99.89 54	96.97 130	99.57 88	99.71 53

旧先验1					99.29 77	97.48 83		98.70 127			99.09 100	95.56 52			99.47 107	99.61 79

EI-MVSNet-Vis-set		98.47 43	98.39 32	98.69 82	99.46 52	96.49 135	98.30 231	98.69 128	97.21 60	98.84 72	99.36 48	95.41 57	99.78 108	98.62 37	99.65 72	99.80 21

新几何1				99.16 49	99.34 61	98.01 65		98.69 128	90.06 363	98.13 113	98.95 121	94.60 85	99.89 54	91.97 303	99.47 107	99.59 83

API-MVS		97.41 112	97.25 105	97.91 151	98.70 151	96.80 118	98.82 135	98.69 128	94.53 200	98.11 114	98.28 196	94.50 90	99.57 152	94.12 239	99.49 104	97.37 271

EI-MVSNet-UG-set		98.41 50	98.34 41	98.61 88	99.45 55	96.32 145	98.28 234	98.68 131	97.17 63	98.74 80	99.37 44	95.25 68	99.79 105	98.57 39	99.54 97	99.73 45

testdata				98.26 123	99.20 98	95.36 191		98.68 131	91.89 319	98.60 92	99.10 93	94.44 92	99.82 83	94.27 234	99.44 111	99.58 87

MCST-MVS		98.65 19	98.37 34	99.48 13	99.60 31	98.87 19	98.41 220	98.68 131	97.04 71	98.52 95	98.80 139	96.78 16	99.83 76	97.93 78	99.61 80	99.74 40

PVSNet	91.96 18	96.35 160	96.15 155	96.96 219	99.17 100	92.05 310	96.08 388	98.68 131	93.69 246	97.75 143	97.80 242	88.86 214	99.69 131	94.26 235	99.01 137	99.15 159

MAR-MVS		96.91 137	96.40 147	98.45 106	98.69 154	96.90 114	98.66 179	98.68 131	92.40 304	97.07 175	97.96 224	91.54 149	99.75 116	93.68 252	98.92 141	98.69 210
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 86	99.32 66	96.62 125		98.67 136	93.27 269	97.81 139	98.97 114	95.18 72	99.83 76	93.84 248	99.46 110	99.50 95

CDPH-MVS		97.94 75	97.49 91	99.28 36	99.47 50	98.44 31	97.91 283	98.67 136	92.57 297	98.77 78	98.85 133	95.93 42	99.72 120	95.56 189	99.69 63	99.68 65

UnsupCasMVSNet_eth		90.99 352	89.92 355	94.19 359	94.08 397	89.83 351	97.13 354	98.67 136	93.69 246	85.83 399	96.19 359	75.15 390	96.74 389	89.14 354	79.41 408	96.00 367

TSAR-MVS + MP.		98.78 15	98.62 17	99.24 40	99.69 24	98.28 48	99.14 54	98.66 139	96.84 79	99.56 24	99.31 57	96.34 28	99.70 126	98.32 60	99.73 55	99.73 45
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 27	98.25 50	99.55 9	99.50 42	99.08 11	98.72 165	98.66 139	97.51 38	98.15 111	98.83 136	95.70 49	99.92 36	97.53 112	99.67 66	99.66 72

test222					99.23 93	97.17 103	97.40 327	98.66 139	88.68 382	98.05 119	98.96 119	94.14 98			99.53 99	99.61 79

test11								98.66 139

XXY-MVS		95.20 224	94.45 240	97.46 185	96.75 325	96.56 132	98.86 123	98.65 143	93.30 267	93.27 315	98.27 199	84.85 296	98.87 261	94.82 213	91.26 321	96.96 282

reproduce_monomvs		94.77 251	94.67 226	95.08 328	98.40 179	89.48 362	98.80 144	98.64 144	97.57 35	93.21 317	97.65 255	80.57 346	98.83 267	97.72 92	89.47 347	96.93 285

IU-MVS					99.71 19	99.23 7		98.64 144	95.28 157	99.63 22				98.35 59	99.81 15	99.83 13

TAPA-MVS	93.98 7	95.35 214	94.56 232	97.74 166	99.13 107	94.83 221	98.33 224	98.64 144	86.62 390	96.29 212	98.61 159	94.00 101	99.29 198	80.00 405	99.41 114	99.09 168
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MSC_two_6792asdad				99.62 6	99.17 100	99.08 11		98.63 147					99.94 10	98.53 42	99.80 24	99.86 8

No_MVS				99.62 6	99.17 100	99.08 11		98.63 147					99.94 10	98.53 42	99.80 24	99.86 8

F-COLMAP		97.09 131	96.80 126	97.97 148	99.45 55	94.95 215	98.55 200	98.62 149	93.02 280	96.17 217	98.58 164	94.01 100	99.81 88	93.95 244	98.90 142	99.14 161

test_fmvsmconf0.01_n		97.86 78	97.54 88	98.83 73	95.48 376	96.83 117	98.95 95	98.60 150	98.58 9	98.93 66	99.55 13	88.57 220	99.91 45	99.54 15	99.61 80	99.77 30

balanced_conf03		98.45 45	98.35 37	98.74 78	98.65 161	97.55 79	99.19 44	98.60 150	96.72 89	99.35 36	98.77 143	95.06 78	99.55 162	98.95 26	99.87 1	99.12 163

EIA-MVS		97.75 84	97.58 83	98.27 120	98.38 180	96.44 137	99.01 81	98.60 150	95.88 124	97.26 166	97.53 267	94.97 80	99.33 194	97.38 119	99.20 128	99.05 177

PAPM_NR		97.46 105	97.11 112	98.50 100	99.50 42	96.41 140	98.63 186	98.60 150	95.18 162	97.06 176	98.06 214	94.26 96	99.57 152	93.80 250	98.87 146	99.52 90

cdsmvs_eth3d_5k		23.98 398	31.98 400	0.00 416	0.00 439	0.00 441	0.00 427	98.59 154	0.00 434	0.00 435	98.61 159	90.60 171	0.00 435	0.00 434	0.00 433	0.00 431

1314		96.25 166	95.73 170	97.79 159	97.13 301	95.55 182	98.19 246	98.59 154	93.47 259	92.03 351	97.82 240	91.33 154	99.49 173	94.62 220	98.44 169	98.32 240

CVMVSNet		95.43 206	96.04 159	93.57 366	97.93 236	83.62 404	98.12 256	98.59 154	95.68 135	96.56 199	99.02 107	87.51 247	97.51 376	93.56 258	97.44 204	99.60 81

OMC-MVS		97.55 103	97.34 101	98.20 129	99.33 63	95.92 168	98.28 234	98.59 154	95.52 142	97.97 129	99.10 93	93.28 109	99.49 173	95.09 205	98.88 144	99.19 152

LTVRE_ROB	92.95 15	94.60 261	93.90 276	96.68 238	97.41 282	94.42 240	98.52 202	98.59 154	91.69 325	91.21 359	98.35 187	84.87 295	99.04 233	91.06 322	93.44 293	96.60 328
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		96.71 145	96.84 125	96.31 278	99.11 110	89.74 354	99.05 69	98.58 159	98.08 16	99.87 2	99.37 44	78.48 360	99.93 29	99.29 18	99.69 63	99.27 136

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 89	98.58 159	97.62 31	99.45 29	99.46 31	97.42 9	99.94 10	98.47 50	99.81 15	99.69 60
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
MVSMamba_PlusPlus		98.31 61	98.19 60	98.67 84	98.96 127	97.36 89	99.24 30	98.57 161	94.81 186	98.99 60	98.90 127	95.22 71	99.59 149	99.15 21	99.84 11	99.07 176

UniMVSNet_ETH3D		94.24 290	93.33 308	96.97 218	97.19 297	93.38 281	98.74 157	98.57 161	91.21 344	93.81 293	98.58 164	72.85 400	98.77 274	95.05 207	93.93 281	98.77 205

PAPR		96.84 141	96.24 153	98.65 86	98.72 150	96.92 113	97.36 333	98.57 161	93.33 264	96.67 193	97.57 264	94.30 94	99.56 155	91.05 324	98.59 160	99.47 104

HQP_MVS		96.14 169	95.90 165	96.85 227	97.42 279	94.60 234	98.80 144	98.56 164	97.28 53	95.34 233	98.28 196	87.09 254	99.03 234	96.07 167	94.27 267	96.92 286

plane_prior5								98.56 164					99.03 234	96.07 167	94.27 267	96.92 286

ETV-MVS		97.96 73	97.81 75	98.40 113	98.42 176	97.27 94	98.73 161	98.55 166	96.84 79	98.38 104	97.44 273	95.39 58	99.35 191	97.62 102	98.89 143	98.58 226

mvs_tets		95.41 209	95.00 209	96.65 239	95.58 371	94.42 240	99.00 83	98.55 166	95.73 133	93.21 317	98.38 184	83.45 325	98.63 284	97.09 126	94.00 278	96.91 291

LPG-MVS_test		95.62 195	95.34 190	96.47 265	97.46 274	93.54 271	98.99 86	98.54 168	94.67 192	94.36 265	98.77 143	85.39 284	99.11 222	95.71 184	94.15 273	96.76 308

LGP-MVS_train				96.47 265	97.46 274	93.54 271		98.54 168	94.67 192	94.36 265	98.77 143	85.39 284	99.11 222	95.71 184	94.15 273	96.76 308

test_cas_vis1_n_1920		97.38 114	97.36 100	97.45 186	98.95 128	93.25 288	99.00 83	98.53 170	97.70 27	99.77 10	99.35 50	84.71 301	99.85 70	98.57 39	99.66 69	99.26 139

test12				99.18 46	99.16 104	98.19 54		98.53 170		98.07 117		95.13 75	99.72 120		99.56 94	99.63 77

CNLPA		97.45 108	97.03 116	98.73 79	99.05 114	97.44 87	98.07 263	98.53 170	95.32 155	96.80 190	98.53 169	93.32 107	99.72 120	94.31 233	99.31 125	99.02 179

GDP-MVS		97.64 93	97.28 103	98.71 81	98.30 196	97.33 90	99.05 69	98.52 173	96.34 106	98.80 75	99.05 105	89.74 186	99.51 169	96.86 145	98.86 147	99.28 135

jajsoiax		95.45 204	95.03 208	96.73 233	95.42 380	94.63 229	99.14 54	98.52 173	95.74 131	93.22 316	98.36 186	83.87 321	98.65 283	96.95 132	94.04 276	96.91 291

XVG-OURS		96.55 152	96.41 146	96.99 215	98.75 145	93.76 262	97.50 323	98.52 173	95.67 136	96.83 186	99.30 58	88.95 213	99.53 165	95.88 176	96.26 246	97.69 260

xiu_mvs_v1_base_debu		97.60 97	97.56 85	97.72 167	98.35 183	95.98 156	97.86 293	98.51 176	97.13 67	99.01 57	98.40 181	91.56 146	99.80 95	98.53 42	98.68 153	97.37 271

xiu_mvs_v1_base		97.60 97	97.56 85	97.72 167	98.35 183	95.98 156	97.86 293	98.51 176	97.13 67	99.01 57	98.40 181	91.56 146	99.80 95	98.53 42	98.68 153	97.37 271

xiu_mvs_v1_base_debi		97.60 97	97.56 85	97.72 167	98.35 183	95.98 156	97.86 293	98.51 176	97.13 67	99.01 57	98.40 181	91.56 146	99.80 95	98.53 42	98.68 153	97.37 271

PS-MVSNAJ		97.73 85	97.77 76	97.62 179	98.68 156	95.58 179	97.34 335	98.51 176	97.29 52	98.66 88	97.88 232	94.51 87	99.90 52	97.87 83	99.17 130	97.39 269

cascas		94.63 260	93.86 280	96.93 221	96.91 314	94.27 248	96.00 392	98.51 176	85.55 399	94.54 253	96.23 356	84.20 314	98.87 261	95.80 180	96.98 217	97.66 261

SPE-MVS-test		98.49 40	98.50 24	98.46 105	99.20 98	97.05 108	99.64 4	98.50 181	97.45 43	98.88 69	99.14 88	95.25 68	99.15 214	98.83 30	99.56 94	99.20 148

PS-MVSNAJss		96.43 155	96.26 152	96.92 224	95.84 365	95.08 207	99.16 50	98.50 181	95.87 125	93.84 292	98.34 191	94.51 87	98.61 286	96.88 139	93.45 292	97.06 277

MVS		94.67 258	93.54 301	98.08 141	96.88 316	96.56 132	98.19 246	98.50 181	78.05 414	92.69 334	98.02 217	91.07 163	99.63 142	90.09 335	98.36 175	98.04 249

XVG-OURS-SEG-HR		96.51 153	96.34 148	97.02 214	98.77 144	93.76 262	97.79 302	98.50 181	95.45 145	96.94 180	99.09 100	87.87 241	99.55 162	96.76 150	95.83 258	97.74 257

PVSNet_0	88.72 19	91.28 347	90.03 354	95.00 330	97.99 229	87.29 394	94.84 405	98.50 181	92.06 315	89.86 372	95.19 385	79.81 351	99.39 189	92.27 293	69.79 421	98.33 239

SSC-MVS3.2		93.59 315	93.13 313	94.97 331	96.81 321	89.71 355	97.95 276	98.49 186	94.59 197	93.50 306	96.91 327	77.74 369	98.37 319	91.69 309	90.47 330	96.83 303

ACMH	92.88 16	94.55 266	93.95 272	96.34 276	97.63 259	93.26 286	98.81 143	98.49 186	93.43 261	89.74 373	98.53 169	81.91 330	99.08 228	93.69 251	93.30 296	96.70 317
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CS-MVS		98.44 46	98.49 25	98.31 118	99.08 113	96.73 122	99.67 3	98.47 188	97.17 63	98.94 62	99.10 93	95.73 48	99.13 217	98.71 33	99.49 104	99.09 168

xiu_mvs_v2_base		97.66 92	97.70 79	97.56 183	98.61 165	95.46 186	97.44 324	98.46 189	97.15 65	98.65 89	98.15 208	94.33 93	99.80 95	97.84 86	98.66 157	97.41 267

HQP3-MVS								98.46 189							94.18 271

HQP-MVS		95.72 188	95.40 184	96.69 237	97.20 294	94.25 250	98.05 265	98.46 189	96.43 100	94.45 257	97.73 245	86.75 260	98.96 245	95.30 197	94.18 271	96.86 300

CLD-MVS		95.62 195	95.34 190	96.46 268	97.52 271	93.75 264	97.27 341	98.46 189	95.53 141	94.42 262	98.00 220	86.21 271	98.97 241	96.25 165	94.37 265	96.66 323
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		94.54 267	94.14 257	95.75 304	96.55 334	91.65 318	98.11 258	98.44 193	94.96 177	94.22 273	97.90 229	79.18 356	99.11 222	94.05 243	93.85 282	96.48 350

casdiffmvs_mvg		97.72 86	97.48 93	98.44 108	98.42 176	96.59 130	98.92 103	98.44 193	96.20 111	97.76 141	99.20 74	91.66 144	99.23 204	98.27 65	98.41 172	99.49 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMP	93.49 10	95.34 215	94.98 211	96.43 270	97.67 255	93.48 275	98.73 161	98.44 193	94.94 181	92.53 339	98.53 169	84.50 307	99.14 216	95.48 193	94.00 278	96.66 323
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	93.85 9	95.69 192	95.38 188	96.61 247	97.61 260	93.84 260	98.91 105	98.44 193	95.25 159	94.28 269	98.47 175	86.04 276	99.12 220	95.50 192	93.95 280	96.87 298
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+		97.12 129	96.69 135	98.39 114	98.19 207	96.72 123	97.37 331	98.43 197	93.71 243	97.65 155	98.02 217	92.20 129	99.25 201	96.87 142	97.79 193	99.19 152

EC-MVSNet		98.21 66	98.11 63	98.49 102	98.34 188	97.26 98	99.61 5	98.43 197	96.78 82	98.87 70	98.84 134	93.72 103	99.01 239	98.91 28	99.50 102	99.19 152

anonymousdsp		95.42 207	94.91 214	96.94 220	95.10 384	95.90 170	99.14 54	98.41 199	93.75 237	93.16 319	97.46 270	87.50 249	98.41 312	95.63 188	94.03 277	96.50 347

PMMVS		96.60 148	96.33 149	97.41 190	97.90 238	93.93 257	97.35 334	98.41 199	92.84 287	97.76 141	97.45 272	91.10 162	99.20 208	96.26 163	97.91 188	99.11 166

MVSFormer		97.57 101	97.49 91	97.84 154	98.07 218	95.76 175	99.47 7	98.40 201	94.98 175	98.79 76	98.83 136	92.34 121	98.41 312	96.91 133	99.59 84	99.34 122

test_djsdf		96.00 173	95.69 177	96.93 221	95.72 367	95.49 185	99.47 7	98.40 201	94.98 175	94.58 252	97.86 233	89.16 203	98.41 312	96.91 133	94.12 275	96.88 295

sasdasda		97.67 90	97.23 106	98.98 63	98.70 151	98.38 35	99.34 16	98.39 203	96.76 84	97.67 151	97.40 277	92.26 124	99.49 173	98.28 62	96.28 244	99.08 172

OPM-MVS		95.69 192	95.33 193	96.76 232	96.16 353	94.63 229	98.43 217	98.39 203	96.64 93	95.02 241	98.78 141	85.15 291	99.05 230	95.21 204	94.20 270	96.60 328
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
canonicalmvs		97.67 90	97.23 106	98.98 63	98.70 151	98.38 35	99.34 16	98.39 203	96.76 84	97.67 151	97.40 277	92.26 124	99.49 173	98.28 62	96.28 244	99.08 172

DP-MVS		96.59 149	95.93 164	98.57 90	99.34 61	96.19 151	98.70 170	98.39 203	89.45 374	94.52 254	99.35 50	91.85 139	99.85 70	92.89 278	98.88 144	99.68 65

MGCFI-Net		97.62 96	97.19 109	98.92 68	98.66 158	98.20 53	99.32 21	98.38 207	96.69 90	97.58 160	97.42 276	92.10 132	99.50 172	98.28 62	96.25 247	99.08 172

dcpmvs_2		98.08 69	98.59 18	96.56 254	99.57 33	90.34 346	99.15 51	98.38 207	96.82 81	99.29 40	99.49 24	95.78 47	99.57 152	98.94 27	99.86 2	99.77 30

diffmvs		97.58 100	97.40 98	98.13 135	98.32 194	95.81 174	98.06 264	98.37 209	96.20 111	98.74 80	98.89 129	91.31 156	99.25 201	98.16 67	98.52 164	99.34 122
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMH+	92.99 14	94.30 285	93.77 287	95.88 298	97.81 244	92.04 311	98.71 166	98.37 209	93.99 224	90.60 366	98.47 175	80.86 343	99.05 230	92.75 280	92.40 307	96.55 336

MSDG		95.93 178	95.30 196	97.83 155	98.90 131	95.36 191	96.83 375	98.37 209	91.32 337	94.43 261	98.73 150	90.27 178	99.60 148	90.05 338	98.82 150	98.52 228

DPM-MVS		97.55 103	96.99 118	99.23 42	99.04 115	98.55 27	97.17 350	98.35 212	94.85 185	97.93 134	98.58 164	95.07 77	99.71 125	92.60 282	99.34 123	99.43 113

RRT-MVS		97.03 132	96.78 129	97.77 163	97.90 238	94.34 245	99.12 58	98.35 212	95.87 125	98.06 118	98.70 152	86.45 267	99.63 142	98.04 74	98.54 163	99.35 120

CMPMVS	66.06 21	89.70 361	89.67 357	89.78 387	93.19 403	76.56 413	97.00 359	98.35 212	80.97 411	81.57 409	97.75 244	74.75 392	98.61 286	89.85 341	93.63 287	94.17 398
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		94.19 293	93.43 306	96.47 265	95.90 362	94.38 243	99.26 27	98.34 215	91.99 316	92.76 331	97.13 296	88.31 227	98.52 294	89.48 350	87.70 367	96.52 342

CDS-MVSNet		96.99 134	96.69 135	97.90 152	98.05 223	95.98 156	98.20 243	98.33 216	93.67 250	96.95 179	98.49 173	93.54 104	98.42 305	95.24 202	97.74 196	99.31 128
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
casdiffmvs		97.63 95	97.41 97	98.28 119	98.33 191	96.14 153	98.82 135	98.32 217	96.38 105	97.95 130	99.21 72	91.23 158	99.23 204	98.12 68	98.37 173	99.48 102
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 93	97.44 96	98.25 124	98.35 183	96.20 149	99.00 83	98.32 217	96.33 108	98.03 122	99.17 81	91.35 153	99.16 211	98.10 69	98.29 179	99.39 116

cl22		94.68 255	94.19 252	96.13 285	98.11 216	93.60 269	96.94 362	98.31 219	92.43 302	93.32 314	96.87 331	86.51 263	98.28 331	94.10 241	91.16 322	96.51 345

test_yl		97.22 121	96.78 129	98.54 95	98.73 146	96.60 128	98.45 212	98.31 219	94.70 188	98.02 124	98.42 179	90.80 167	99.70 126	96.81 146	96.79 222	99.34 122

DCV-MVSNet		97.22 121	96.78 129	98.54 95	98.73 146	96.60 128	98.45 212	98.31 219	94.70 188	98.02 124	98.42 179	90.80 167	99.70 126	96.81 146	96.79 222	99.34 122

nrg030		96.28 164	95.72 171	97.96 150	96.90 315	98.15 58	99.39 10	98.31 219	95.47 144	94.42 262	98.35 187	92.09 133	98.69 278	97.50 114	89.05 353	97.04 278

TAMVS		97.02 133	96.79 128	97.70 170	98.06 221	95.31 196	98.52 202	98.31 219	93.95 226	97.05 177	98.61 159	93.49 105	98.52 294	95.33 196	97.81 192	99.29 133

EPP-MVSNet		97.46 105	97.28 103	97.99 147	98.64 162	95.38 190	99.33 20	98.31 219	93.61 254	97.19 169	99.07 103	94.05 99	99.23 204	96.89 137	98.43 171	99.37 118

UnsupCasMVSNet_bld		87.17 373	85.12 380	93.31 371	91.94 409	88.77 375	94.92 404	98.30 225	84.30 404	82.30 407	90.04 415	63.96 414	97.25 380	85.85 380	74.47 420	93.93 404

Vis-MVSNet (Re-imp)		96.87 139	96.55 141	97.83 155	98.73 146	95.46 186	99.20 42	98.30 225	94.96 177	96.60 198	98.87 131	90.05 180	98.59 289	93.67 254	98.60 159	99.46 108

TSAR-MVS + GP.		98.38 52	98.24 52	98.81 74	99.22 95	97.25 99	98.11 258	98.29 227	97.19 62	98.99 60	99.02 107	96.22 30	99.67 133	98.52 48	98.56 162	99.51 93

MS-PatchMatch		93.84 310	93.63 296	94.46 354	96.18 350	89.45 363	97.76 303	98.27 228	92.23 310	92.13 349	97.49 268	79.50 353	98.69 278	89.75 343	99.38 119	95.25 380

EI-MVSNet		95.96 174	95.83 167	96.36 274	97.93 236	93.70 268	98.12 256	98.27 228	93.70 245	95.07 239	99.02 107	92.23 127	98.54 292	94.68 216	93.46 290	96.84 301

MVSTER		96.06 171	95.72 171	97.08 211	98.23 201	95.93 167	98.73 161	98.27 228	94.86 183	95.07 239	98.09 212	88.21 229	98.54 292	96.59 152	93.46 290	96.79 305

FMVSNet2		94.47 276	93.61 297	97.04 213	98.21 203	96.43 138	98.79 151	98.27 228	92.46 298	93.50 306	97.09 301	81.16 336	98.00 350	91.09 319	91.93 311	96.70 317

FMVSNet3		94.97 241	94.26 248	97.11 209	98.18 209	96.62 125	98.56 199	98.26 232	93.67 250	94.09 279	97.10 297	84.25 310	98.01 348	92.08 296	92.14 308	96.70 317

Fast-Effi-MVS+		96.28 164	95.70 176	98.03 144	98.29 197	95.97 161	98.58 192	98.25 233	91.74 322	95.29 237	97.23 290	91.03 164	99.15 214	92.90 276	97.96 187	98.97 184

PAPM		94.95 242	94.00 268	97.78 160	97.04 305	95.65 177	96.03 391	98.25 233	91.23 342	94.19 275	97.80 242	91.27 157	98.86 263	82.61 398	97.61 200	98.84 196

test_fmvs1_n		95.90 180	95.99 162	95.63 308	98.67 157	88.32 385	99.26 27	98.22 235	96.40 103	99.67 18	99.26 63	73.91 397	99.70 126	99.02 25	99.50 102	98.87 193

CANet_DTU		96.96 135	96.55 141	98.21 127	98.17 212	96.07 155	97.98 274	98.21 236	97.24 58	97.13 171	98.93 123	86.88 259	99.91 45	95.00 208	99.37 121	98.66 216

HY-MVS	93.96 8	96.82 142	96.23 154	98.57 90	98.46 175	97.00 109	98.14 253	98.21 236	93.95 226	96.72 192	97.99 221	91.58 145	99.76 114	94.51 225	96.54 231	98.95 187

test_fmvs1		96.42 156	96.67 137	95.66 307	98.82 141	88.53 381	98.80 144	98.20 238	96.39 104	99.64 21	99.20 74	80.35 348	99.67 133	99.04 24	99.57 88	98.78 202

PCF-MVS	93.45 11	94.68 255	93.43 306	98.42 112	98.62 164	96.77 120	95.48 399	98.20 238	84.63 403	93.34 313	98.32 193	88.55 223	99.81 88	84.80 390	98.96 140	98.68 212
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v8		94.47 276	93.77 287	96.57 253	96.36 344	94.83 221	99.05 69	98.19 240	91.92 318	93.16 319	96.97 320	88.82 217	98.48 296	91.69 309	87.79 366	96.39 354

v10		94.29 287	93.55 300	96.51 261	96.39 343	94.80 223	98.99 86	98.19 240	91.35 335	93.02 325	96.99 318	88.09 233	98.41 312	90.50 331	88.41 361	96.33 358

mvs_anonymous		96.70 146	96.53 143	97.18 202	98.19 207	93.78 261	98.31 229	98.19 240	94.01 222	94.47 256	98.27 199	92.08 134	98.46 300	97.39 118	97.91 188	99.31 128

WBMVS		94.56 265	94.04 262	96.10 287	98.03 225	93.08 296	97.82 299	98.18 243	94.02 219	93.77 296	96.82 334	81.28 335	98.34 320	95.47 194	91.00 325	96.88 295

AllTest		95.24 221	94.65 227	96.99 215	99.25 85	93.21 290	98.59 190	98.18 243	91.36 333	93.52 303	98.77 143	84.67 302	99.72 120	89.70 345	97.87 190	98.02 250

TestCases				96.99 215	99.25 85	93.21 290		98.18 243	91.36 333	93.52 303	98.77 143	84.67 302	99.72 120	89.70 345	97.87 190	98.02 250

GBi-Net		94.49 273	93.80 284	96.56 254	98.21 203	95.00 209	98.82 135	98.18 243	92.46 298	94.09 279	97.07 304	81.16 336	97.95 353	92.08 296	92.14 308	96.72 313

test1		94.49 273	93.80 284	96.56 254	98.21 203	95.00 209	98.82 135	98.18 243	92.46 298	94.09 279	97.07 304	81.16 336	97.95 353	92.08 296	92.14 308	96.72 313

FMVSNet1		93.19 325	92.07 334	96.56 254	97.54 268	95.00 209	98.82 135	98.18 243	90.38 358	92.27 346	97.07 304	73.68 398	97.95 353	89.36 352	91.30 319	96.72 313

v1192		94.32 284	93.58 298	96.53 259	96.10 354	94.45 238	98.50 208	98.17 249	91.54 328	94.19 275	97.06 308	86.95 258	98.43 304	90.14 334	89.57 342	96.70 317

v1240		94.06 306	93.29 310	96.34 276	96.03 358	93.90 258	98.44 215	98.17 249	91.18 345	94.13 278	97.01 317	86.05 274	98.42 305	89.13 355	89.50 346	96.70 317

v144192		94.39 281	93.70 293	96.48 264	96.06 356	94.35 244	98.58 192	98.16 251	91.45 330	94.33 267	97.02 315	87.50 249	98.45 301	91.08 321	89.11 352	96.63 325

Fast-Effi-MVS+-dtu		95.87 181	95.85 166	95.91 295	97.74 250	91.74 316	98.69 172	98.15 252	95.56 140	94.92 242	97.68 253	88.98 211	98.79 272	93.19 266	97.78 194	97.20 275

v1921920		94.20 292	93.47 304	96.40 273	95.98 359	94.08 254	98.52 202	98.15 252	91.33 336	94.25 271	97.20 293	86.41 268	98.42 305	90.04 339	89.39 349	96.69 322

v1144		94.59 263	93.92 273	96.60 249	96.21 348	94.78 225	98.59 190	98.14 254	91.86 321	94.21 274	97.02 315	87.97 237	98.41 312	91.72 308	89.57 342	96.61 327

IterMVS-LS		95.46 202	95.21 199	96.22 282	98.12 215	93.72 267	98.32 228	98.13 255	93.71 243	94.26 270	97.31 284	92.24 126	98.10 341	94.63 218	90.12 335	96.84 301
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GeoE		96.58 151	96.07 157	98.10 140	98.35 183	95.89 171	99.34 16	98.12 256	93.12 276	96.09 218	98.87 131	89.71 187	98.97 241	92.95 274	98.08 184	99.43 113

EU-MVSNet		93.66 311	94.14 257	92.25 382	95.96 361	83.38 406	98.52 202	98.12 256	94.69 190	92.61 336	98.13 210	87.36 252	96.39 398	91.82 305	90.00 337	96.98 281

IterMVS		94.09 303	93.85 281	94.80 340	97.99 229	90.35 345	97.18 348	98.12 256	93.68 248	92.46 343	97.34 280	84.05 316	97.41 378	92.51 289	91.33 318	96.62 326
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_vis1_n		95.47 201	95.13 202	96.49 262	97.77 246	90.41 344	99.27 26	98.11 259	96.58 95	99.66 19	99.18 80	67.00 410	99.62 146	99.21 20	99.40 117	99.44 111

IterMVS-SCA-FT		94.11 301	93.87 279	94.85 337	97.98 231	90.56 341	97.18 348	98.11 259	93.75 237	92.58 337	97.48 269	83.97 318	97.41 378	92.48 291	91.30 319	96.58 330

COLMAP_ROB	93.27 12	95.33 216	94.87 217	96.71 234	99.29 77	93.24 289	98.58 192	98.11 259	89.92 365	93.57 301	99.10 93	86.37 269	99.79 105	90.78 327	98.10 183	97.09 276
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
hse-mvs2		95.71 189	95.30 196	96.93 221	98.50 172	93.53 273	98.36 221	98.10 262	97.48 40	98.67 84	97.99 221	89.76 184	99.02 237	97.95 76	80.91 404	98.22 243

AUN-MVS		94.53 269	93.73 291	96.92 224	98.50 172	93.52 274	98.34 223	98.10 262	93.83 234	95.94 226	97.98 223	85.59 282	99.03 234	94.35 230	80.94 403	98.22 243

Effi-MVS+-dtu		96.29 162	96.56 140	95.51 312	97.89 240	90.22 347	98.80 144	98.10 262	96.57 97	96.45 208	96.66 341	90.81 166	98.91 254	95.72 183	97.99 185	97.40 268

1112_ss		96.63 147	96.00 161	98.50 100	98.56 167	96.37 142	98.18 251	98.10 262	92.92 284	94.84 244	98.43 177	92.14 130	99.58 151	94.35 230	96.51 232	99.56 89

V42		94.78 250	94.14 257	96.70 236	96.33 346	95.22 200	98.97 89	98.09 266	92.32 307	94.31 268	97.06 308	88.39 226	98.55 291	92.90 276	88.87 357	96.34 356

miper_enhance_ethall		95.10 230	94.75 221	96.12 286	97.53 270	93.73 266	96.61 382	98.08 267	92.20 313	93.89 288	96.65 343	92.44 119	98.30 327	94.21 236	91.16 322	96.34 356

v2v482		94.69 253	94.03 264	96.65 239	96.17 351	94.79 224	98.67 177	98.08 267	92.72 290	94.00 284	97.16 294	87.69 246	98.45 301	92.91 275	88.87 357	96.72 313

CL-MVSNet_self_test		90.11 358	89.14 361	93.02 375	91.86 410	88.23 387	96.51 385	98.07 269	90.49 353	90.49 367	94.41 394	84.75 299	95.34 407	80.79 403	74.95 418	95.50 376

miper_ehance_all_eth		95.01 234	94.69 225	95.97 292	97.70 253	93.31 284	97.02 358	98.07 269	92.23 310	93.51 305	96.96 322	91.85 139	98.15 337	93.68 252	91.16 322	96.44 353

eth_miper_zixun_eth		94.68 255	94.41 243	95.47 314	97.64 258	91.71 317	96.73 379	98.07 269	92.71 291	93.64 298	97.21 292	90.54 172	98.17 336	93.38 260	89.76 339	96.54 337

MVS_Test		97.28 118	97.00 117	98.13 135	98.33 191	95.97 161	98.74 157	98.07 269	94.27 210	98.44 102	98.07 213	92.48 118	99.26 200	96.43 158	98.19 180	99.16 158

Test_1112_low_res		96.34 161	95.66 179	98.36 115	98.56 167	95.94 164	97.71 307	98.07 269	92.10 314	94.79 248	97.29 285	91.75 141	99.56 155	94.17 237	96.50 233	99.58 87

alignmvs		97.56 102	97.07 115	99.01 60	98.66 158	98.37 42	98.83 133	98.06 274	96.74 86	98.00 128	97.65 255	90.80 167	99.48 178	98.37 58	96.56 230	99.19 152

RPSCF		94.87 246	95.40 184	93.26 372	98.89 132	82.06 410	98.33 224	98.06 274	90.30 360	96.56 199	99.26 63	87.09 254	99.49 173	93.82 249	96.32 238	98.24 241

miper_lstm_enhance		94.33 283	94.07 261	95.11 326	97.75 247	90.97 328	97.22 343	98.03 276	91.67 326	92.76 331	96.97 320	90.03 181	97.78 365	92.51 289	89.64 341	96.56 334

c3_l		94.79 249	94.43 242	95.89 297	97.75 247	93.12 294	97.16 352	98.03 276	92.23 310	93.46 309	97.05 311	91.39 151	98.01 348	93.58 257	89.21 351	96.53 339

pm-mvs1		93.94 309	93.06 314	96.59 250	96.49 338	95.16 202	98.95 95	98.03 276	92.32 307	91.08 361	97.84 236	84.54 306	98.41 312	92.16 294	86.13 386	96.19 363

v148		94.29 287	93.76 289	95.91 295	96.10 354	92.93 298	98.58 192	97.97 279	92.59 296	93.47 308	96.95 324	88.53 224	98.32 323	92.56 286	87.06 376	96.49 348

IS-MVSNet		97.22 121	96.88 123	98.25 124	98.85 139	96.36 143	99.19 44	97.97 279	95.39 149	97.23 167	98.99 113	91.11 161	98.93 251	94.60 221	98.59 160	99.47 104

cl____		94.51 271	94.01 267	96.02 289	97.58 263	93.40 280	97.05 356	97.96 281	91.73 324	92.76 331	97.08 303	89.06 207	98.13 339	92.61 281	90.29 333	96.52 342

KD-MVS_self_test		90.38 356	89.38 359	93.40 369	92.85 405	88.94 374	97.95 276	97.94 282	90.35 359	90.25 368	93.96 399	79.82 350	95.94 403	84.62 392	76.69 416	95.33 378

DIV-MVS_self_test		94.52 270	94.03 264	95.99 290	97.57 267	93.38 281	97.05 356	97.94 282	91.74 322	92.81 329	97.10 297	89.12 204	98.07 345	92.60 282	90.30 332	96.53 339

pmmvs6		91.77 342	90.63 347	95.17 324	94.69 392	91.24 325	98.67 177	97.92 284	86.14 394	89.62 374	97.56 266	75.79 388	98.34 320	90.75 328	84.56 388	95.94 369

jason		97.32 117	97.08 114	98.06 143	97.45 277	95.59 178	97.87 291	97.91 285	94.79 187	98.55 94	98.83 136	91.12 160	99.23 204	97.58 105	99.60 82	99.34 122
jason: jason.
ppachtmachnet_test		93.22 323	92.63 323	94.97 331	95.45 378	90.84 333	96.88 371	97.88 286	90.60 352	92.08 350	97.26 286	88.08 234	97.86 362	85.12 386	90.33 331	96.22 361

tpm cat1		93.36 317	92.80 319	95.07 329	97.58 263	87.97 389	96.76 377	97.86 287	82.17 410	93.53 302	96.04 365	86.13 272	99.13 217	89.24 353	95.87 257	98.10 248

tt0805		94.54 267	93.85 281	96.63 244	97.98 231	93.06 297	98.77 153	97.84 288	93.67 250	93.80 294	98.04 216	76.88 382	98.96 245	94.79 215	92.86 301	97.86 254

EG-PatchMatch MVS		91.13 350	90.12 353	94.17 360	94.73 391	89.00 371	98.13 255	97.81 289	89.22 378	85.32 403	96.46 349	67.71 408	98.42 305	87.89 369	93.82 283	95.08 385

BH-untuned		95.95 175	95.72 171	96.65 239	98.55 169	92.26 304	98.23 239	97.79 290	93.73 240	94.62 251	98.01 219	88.97 212	99.00 240	93.04 271	98.51 165	98.68 212

lupinMVS		97.44 109	97.22 108	98.12 138	98.07 218	95.76 175	97.68 309	97.76 291	94.50 203	98.79 76	98.61 159	92.34 121	99.30 197	97.58 105	99.59 84	99.31 128

VDDNet		95.36 213	94.53 233	97.86 153	98.10 217	95.13 205	98.85 127	97.75 292	90.46 355	98.36 105	99.39 38	73.27 399	99.64 139	97.98 75	96.58 229	98.81 198

ADS-MVSNet		95.00 235	94.45 240	96.63 244	98.00 227	91.91 312	96.04 389	97.74 293	90.15 361	96.47 206	96.64 344	87.89 239	98.96 245	90.08 336	97.06 212	99.02 179

BP-MVS1		97.82 81	97.51 90	98.76 77	98.25 198	97.39 88	99.15 51	97.68 294	96.69 90	98.47 96	99.10 93	90.29 177	99.51 169	98.60 38	99.35 122	99.37 118

tpmvs		94.60 261	94.36 245	95.33 320	97.46 274	88.60 379	96.88 371	97.68 294	91.29 339	93.80 294	96.42 351	88.58 219	99.24 203	91.06 322	96.04 253	98.17 245

pmmvs4		94.69 253	93.99 270	96.81 230	95.74 366	95.94 164	97.40 327	97.67 296	90.42 357	93.37 312	97.59 262	89.08 206	98.20 334	92.97 273	91.67 315	96.30 359

our_test_3		93.65 313	93.30 309	94.69 342	95.45 378	89.68 358	96.91 365	97.65 297	91.97 317	91.66 356	96.88 329	89.67 188	97.93 356	88.02 366	91.49 317	96.48 350

MVP-Stereo		94.28 289	93.92 273	95.35 319	94.95 386	92.60 301	97.97 275	97.65 297	91.61 327	90.68 365	97.09 301	86.32 270	98.42 305	89.70 345	99.34 123	95.02 388
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
KD-MVS_2432*1600		89.61 363	87.96 371	94.54 349	94.06 398	91.59 319	95.59 397	97.63 299	89.87 366	88.95 380	94.38 396	78.28 362	96.82 387	84.83 388	68.05 422	95.21 381

miper_refine_blended		89.61 363	87.96 371	94.54 349	94.06 398	91.59 319	95.59 397	97.63 299	89.87 366	88.95 380	94.38 396	78.28 362	96.82 387	84.83 388	68.05 422	95.21 381

SCA		95.46 202	95.13 202	96.46 268	97.67 255	91.29 324	97.33 336	97.60 301	94.68 191	96.92 183	97.10 297	83.97 318	98.89 258	92.59 284	98.32 178	99.20 148

testing91		94.98 239	94.25 249	97.20 199	97.94 234	93.41 278	98.00 272	97.58 302	94.99 174	95.45 232	96.04 365	77.20 376	99.42 185	94.97 209	96.02 254	98.78 202

FA-MVS(test-final)		96.41 159	95.94 163	97.82 157	98.21 203	95.20 201	97.80 300	97.58 302	93.21 270	97.36 164	97.70 248	89.47 192	99.56 155	94.12 239	97.99 185	98.71 209

GA-MVS		94.81 248	94.03 264	97.14 205	97.15 300	93.86 259	96.76 377	97.58 302	94.00 223	94.76 250	97.04 312	80.91 341	98.48 296	91.79 306	96.25 247	99.09 168

Anonymous20240521		91.18 349	90.44 349	93.42 367	93.70 401	88.47 382	98.94 98	97.56 305	88.46 383	89.56 376	95.08 388	77.15 378	96.97 384	83.92 393	89.55 344	94.82 390

test20.03		90.89 353	90.38 350	92.43 378	93.48 402	88.14 388	98.33 224	97.56 305	93.40 262	87.96 386	96.71 340	80.69 345	94.13 413	79.15 408	86.17 383	95.01 389

CR-MVSNet		94.76 252	94.15 256	96.59 250	97.00 306	93.43 276	94.96 402	97.56 305	92.46 298	96.93 181	96.24 354	88.15 231	97.88 361	87.38 370	96.65 227	98.46 232

Patchmtry		93.22 323	92.35 331	95.84 299	96.77 322	93.09 295	94.66 409	97.56 305	87.37 388	92.90 327	96.24 354	88.15 231	97.90 357	87.37 371	90.10 336	96.53 339

tpmrst		95.63 194	95.69 177	95.44 316	97.54 268	88.54 380	96.97 360	97.56 305	93.50 257	97.52 162	96.93 326	89.49 190	99.16 211	95.25 201	96.42 235	98.64 218

FMVSNet5		91.81 341	90.92 344	94.49 351	97.21 293	92.09 308	98.00 272	97.55 310	89.31 377	90.86 363	95.61 380	74.48 394	95.32 408	85.57 381	89.70 340	96.07 366

testgi		93.06 329	92.45 330	94.88 336	96.43 342	89.90 350	98.75 154	97.54 311	95.60 138	91.63 357	97.91 228	74.46 395	97.02 383	86.10 377	93.67 285	97.72 259

mvsany_test1		97.69 89	97.70 79	97.66 177	98.24 199	94.18 252	97.53 320	97.53 312	95.52 142	99.66 19	99.51 20	94.30 94	99.56 155	98.38 57	98.62 158	99.23 143

PatchmatchNet		95.71 189	95.52 181	96.29 280	97.58 263	90.72 336	96.84 374	97.52 313	94.06 216	97.08 173	96.96 322	89.24 201	98.90 257	92.03 300	98.37 173	99.26 139
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDA-MVSNet-bldmvs		89.97 360	88.35 366	94.83 339	95.21 382	91.34 322	97.64 313	97.51 314	88.36 384	71.17 422	96.13 361	79.22 355	96.63 394	83.65 394	86.27 382	96.52 342

USDC		93.33 320	92.71 321	95.21 322	96.83 319	90.83 334	96.91 365	97.50 315	93.84 232	90.72 364	98.14 209	77.69 370	98.82 269	89.51 349	93.21 298	95.97 368

ITE_SJBPF				95.44 316	97.42 279	91.32 323		97.50 315	95.09 169	93.59 299	98.35 187	81.70 331	98.88 260	89.71 344	93.39 294	96.12 364

Patchmatch-test		94.42 279	93.68 295	96.63 244	97.60 261	91.76 314	94.83 406	97.49 317	89.45 374	94.14 277	97.10 297	88.99 208	98.83 267	85.37 384	98.13 182	99.29 133

mvsmamba		97.25 120	96.99 118	98.02 145	98.34 188	95.54 183	99.18 48	97.47 318	95.04 171	98.15 111	98.57 167	89.46 193	99.31 196	97.68 99	99.01 137	99.22 145

Syy-MVS		92.55 336	92.61 324	92.38 379	97.39 283	83.41 405	97.91 283	97.46 319	93.16 273	93.42 310	95.37 383	84.75 299	96.12 400	77.00 413	96.99 214	97.60 263

myMVS_eth3d		92.73 333	92.01 335	94.89 335	97.39 283	90.94 329	97.91 283	97.46 319	93.16 273	93.42 310	95.37 383	68.09 406	96.12 400	88.34 362	96.99 214	97.60 263

YYNet1		90.70 355	89.39 358	94.62 347	94.79 390	90.65 338	97.20 345	97.46 319	87.54 387	72.54 420	95.74 372	86.51 263	96.66 393	86.00 378	86.76 381	96.54 337

MDA-MVSNet_test_wron		90.71 354	89.38 359	94.68 343	94.83 388	90.78 335	97.19 347	97.46 319	87.60 386	72.41 421	95.72 376	86.51 263	96.71 392	85.92 379	86.80 380	96.56 334

BH-RMVSNet		95.92 179	95.32 194	97.69 171	98.32 194	94.64 228	98.19 246	97.45 323	94.56 198	96.03 220	98.61 159	85.02 292	99.12 220	90.68 329	99.06 133	99.30 131

MIMVSNet1		89.67 362	88.28 367	93.82 363	92.81 406	91.08 327	98.01 270	97.45 323	87.95 385	87.90 387	95.87 370	67.63 409	94.56 412	78.73 410	88.18 363	95.83 371

OurMVSNet-221017-0		94.21 291	94.00 268	94.85 337	95.60 370	89.22 367	98.89 110	97.43 325	95.29 156	92.18 348	98.52 172	82.86 326	98.59 289	93.46 259	91.76 313	96.74 310

BH-w/o		95.38 210	95.08 206	96.26 281	98.34 188	91.79 313	97.70 308	97.43 325	92.87 286	94.24 272	97.22 291	88.66 218	98.84 264	91.55 312	97.70 198	98.16 246

VDD-MVS		95.82 185	95.23 198	97.61 180	98.84 140	93.98 256	98.68 174	97.40 327	95.02 173	97.95 130	99.34 54	74.37 396	99.78 108	98.64 36	96.80 221	99.08 172

Gipuma		78.40 387	76.75 390	83.38 400	95.54 372	80.43 412	79.42 425	97.40 327	64.67 422	73.46 419	80.82 423	45.65 422	93.14 417	66.32 421	87.43 370	76.56 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FE-MVS		95.62 195	94.90 215	97.78 160	98.37 182	94.92 216	97.17 350	97.38 329	90.95 348	97.73 146	97.70 248	85.32 289	99.63 142	91.18 316	98.33 176	98.79 199

MonoMVSNet		95.51 199	95.45 183	95.68 305	95.54 372	90.87 331	98.92 103	97.37 330	95.79 129	95.53 230	97.38 279	89.58 189	97.68 368	96.40 159	92.59 305	98.49 230

new-patchmatchnet		88.50 369	87.45 374	91.67 384	90.31 415	85.89 399	97.16 352	97.33 331	89.47 373	83.63 406	92.77 409	76.38 383	95.06 410	82.70 397	77.29 414	94.06 402

myMVS_eth3d28		95.12 228	94.62 228	96.64 243	98.17 212	92.17 305	98.02 269	97.32 332	95.41 148	96.22 213	96.05 364	78.01 366	99.13 217	95.22 203	97.16 209	98.60 221

mmtdpeth		93.12 328	92.61 324	94.63 346	97.60 261	89.68 358	99.21 39	97.32 332	94.02 219	97.72 147	94.42 393	77.01 380	99.44 183	99.05 23	77.18 415	94.78 393

ADS-MVSNet2		94.58 264	94.40 244	95.11 326	98.00 227	88.74 377	96.04 389	97.30 334	90.15 361	96.47 206	96.64 344	87.89 239	97.56 374	90.08 336	97.06 212	99.02 179

ttmdpeth		92.61 335	91.96 338	94.55 348	94.10 396	90.60 340	98.52 202	97.29 335	92.67 292	90.18 369	97.92 227	79.75 352	97.79 364	91.09 319	86.15 385	95.26 379

MDTV_nov1_ep13			95.40 184		97.48 272	88.34 384	96.85 373	97.29 335	93.74 239	97.48 163	97.26 286	89.18 202	99.05 230	91.92 304	97.43 205

pmmvs5		93.65 313	92.97 317	95.68 305	95.49 375	92.37 302	98.20 243	97.28 337	89.66 370	92.58 337	97.26 286	82.14 329	98.09 343	93.18 267	90.95 326	96.58 330

EPNet_dtu		95.21 223	94.95 213	95.99 290	96.17 351	90.45 342	98.16 252	97.27 338	96.77 83	93.14 322	98.33 192	90.34 175	98.42 305	85.57 381	98.81 151	99.09 168
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20231206		91.66 343	91.10 343	93.33 370	94.02 400	87.35 393	98.58 192	97.26 339	90.48 354	90.16 370	96.31 352	83.83 322	96.53 395	79.36 407	89.90 338	96.12 364

test_fmvs2		93.43 316	93.58 298	92.95 376	96.97 309	83.91 402	99.19 44	97.24 340	95.74 131	95.20 238	98.27 199	69.65 403	98.72 277	96.26 163	93.73 284	96.24 360

test_0402		91.32 345	90.27 351	94.48 352	96.60 332	91.12 326	98.50 208	97.22 341	86.10 395	88.30 385	96.98 319	77.65 372	97.99 351	78.13 411	92.94 300	94.34 394

testing3-2		95.45 204	95.34 190	95.77 303	98.69 154	88.75 376	98.87 119	97.21 342	96.13 114	97.22 168	97.68 253	77.95 368	99.65 136	97.58 105	96.77 224	98.91 191

UBG		95.32 217	94.72 223	97.13 206	98.05 223	93.26 286	97.87 291	97.20 343	94.96 177	96.18 216	95.66 379	80.97 340	99.35 191	94.47 227	97.08 211	98.78 202

dp		94.15 297	93.90 276	94.90 334	97.31 287	86.82 396	96.97 360	97.19 344	91.22 343	96.02 221	96.61 346	85.51 283	99.02 237	90.00 340	94.30 266	98.85 194

testing99		94.83 247	94.08 260	97.07 212	97.94 234	93.13 292	98.10 260	97.17 345	94.86 183	95.34 233	96.00 368	76.31 384	99.40 186	95.08 206	95.90 255	98.68 212

testing3		93.19 325	92.48 329	95.30 321	98.07 218	92.27 303	98.64 183	97.17 345	93.94 228	93.98 285	97.04 312	67.97 407	96.01 402	88.40 361	97.14 210	97.63 262

ETVMVS		94.50 272	93.44 305	97.68 173	98.18 209	95.35 193	98.19 246	97.11 347	93.73 240	96.40 209	95.39 382	74.53 393	98.84 264	91.10 318	96.31 239	98.84 196

thres200		95.25 220	94.57 231	97.28 196	98.81 142	94.92 216	98.20 243	97.11 347	95.24 161	96.54 203	96.22 358	84.58 305	99.53 165	87.93 368	96.50 233	97.39 269

dmvs_re		94.48 275	94.18 254	95.37 318	97.68 254	90.11 349	98.54 201	97.08 349	94.56 198	94.42 262	97.24 289	84.25 310	97.76 366	91.02 325	92.83 302	98.24 241

PatchT		93.06 329	91.97 336	96.35 275	96.69 328	92.67 300	94.48 412	97.08 349	86.62 390	97.08 173	92.23 412	87.94 238	97.90 357	78.89 409	96.69 225	98.49 230

TDRefinement		91.06 351	89.68 356	95.21 322	85.35 426	91.49 321	98.51 207	97.07 351	91.47 329	88.83 383	97.84 236	77.31 374	99.09 227	92.79 279	77.98 413	95.04 387

LF4IMVS		93.14 327	92.79 320	94.20 358	95.88 363	88.67 378	97.66 311	97.07 351	93.81 235	91.71 354	97.65 255	77.96 367	98.81 270	91.47 313	91.92 312	95.12 383

testing11		95.00 235	94.28 247	97.16 204	97.96 233	93.36 283	98.09 261	97.06 353	94.94 181	95.33 236	96.15 360	76.89 381	99.40 186	95.77 182	96.30 240	98.72 206

Anonymous202405211		95.28 219	94.49 235	97.67 174	99.00 120	93.75 264	98.70 170	97.04 354	90.66 351	96.49 205	98.80 139	78.13 364	99.83 76	96.21 166	95.36 263	99.44 111

baseline1		95.84 183	95.12 204	98.01 146	98.49 174	95.98 156	98.73 161	97.03 355	95.37 152	96.22 213	98.19 206	89.96 182	99.16 211	94.60 221	87.48 369	98.90 192

MIMVSNet		93.26 322	92.21 333	96.41 271	97.73 251	93.13 292	95.65 396	97.03 355	91.27 341	94.04 282	96.06 363	75.33 389	97.19 381	86.56 374	96.23 249	98.92 190

MM		98.51 38	98.24 52	99.33 30	99.12 108	98.14 60	98.93 101	97.02 357	98.96 1	99.17 49	99.47 27	91.97 138	99.94 10	99.85 3	99.69 63	99.91 2

EPNet		97.28 118	96.87 124	98.51 99	94.98 385	96.14 153	98.90 106	97.02 357	98.28 14	95.99 222	99.11 91	91.36 152	99.89 54	96.98 129	99.19 129	99.50 95
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TR-MVS		94.94 244	94.20 251	97.17 203	97.75 247	94.14 253	97.59 317	97.02 357	92.28 309	95.75 228	97.64 258	83.88 320	98.96 245	89.77 342	96.15 251	98.40 234

JIA-IIPM		93.35 318	92.49 328	95.92 294	96.48 339	90.65 338	95.01 401	96.96 360	85.93 396	96.08 219	87.33 418	87.70 245	98.78 273	91.35 314	95.58 261	98.34 238

pmmvs-eth3d		90.36 357	89.05 362	94.32 357	91.10 413	92.12 307	97.63 316	96.95 361	88.86 381	84.91 404	93.13 407	78.32 361	96.74 389	88.70 358	81.81 398	94.09 400

tfpn200view9		95.32 217	94.62 228	97.43 188	98.94 129	94.98 212	98.68 174	96.93 362	95.33 153	96.55 201	96.53 347	84.23 312	99.56 155	88.11 363	96.29 241	97.76 255

thres400		95.38 210	94.62 228	97.65 178	98.94 129	94.98 212	98.68 174	96.93 362	95.33 153	96.55 201	96.53 347	84.23 312	99.56 155	88.11 363	96.29 241	98.40 234

thres100view900		95.38 210	94.70 224	97.41 190	98.98 124	94.92 216	98.87 119	96.90 364	95.38 150	96.61 197	96.88 329	84.29 308	99.56 155	88.11 363	96.29 241	97.76 255

thres600view7		95.49 200	94.77 219	97.67 174	98.98 124	95.02 208	98.85 127	96.90 364	95.38 150	96.63 195	96.90 328	84.29 308	99.59 149	88.65 360	96.33 237	98.40 234

test_method		79.03 382	78.17 384	81.63 404	86.06 425	54.40 436	82.75 424	96.89 366	39.54 428	80.98 412	95.57 381	58.37 418	94.73 411	84.74 391	78.61 410	95.75 372

CostFormer		94.95 242	94.73 222	95.60 310	97.28 288	89.06 369	97.53 320	96.89 366	89.66 370	96.82 188	96.72 339	86.05 274	98.95 250	95.53 191	96.13 252	98.79 199

new_pmnet		90.06 359	89.00 363	93.22 373	94.18 394	88.32 385	96.42 387	96.89 366	86.19 393	85.67 400	93.62 401	77.18 377	97.10 382	81.61 400	89.29 350	94.23 396

OpenMVS_ROB	86.42 20	89.00 367	87.43 375	93.69 364	93.08 404	89.42 364	97.91 283	96.89 366	78.58 413	85.86 398	94.69 390	69.48 404	98.29 330	77.13 412	93.29 297	93.36 407

tpm2		94.19 293	93.76 289	95.46 315	97.23 291	89.04 370	97.31 338	96.85 370	87.08 389	96.21 215	96.79 336	83.75 324	98.74 275	92.43 292	96.23 249	98.59 224

MVStest1		89.53 365	87.99 370	94.14 362	94.39 393	90.42 343	98.25 238	96.84 371	82.81 406	81.18 411	97.33 282	77.09 379	96.94 385	85.27 385	78.79 409	95.06 386

TransMVSNet (Re)		92.67 334	91.51 341	96.15 283	96.58 333	94.65 227	98.90 106	96.73 372	90.86 349	89.46 377	97.86 233	85.62 281	98.09 343	86.45 375	81.12 401	95.71 373

ambc				89.49 388	86.66 423	75.78 415	92.66 417	96.72 373		86.55 396	92.50 411	46.01 421	97.90 357	90.32 332	82.09 395	94.80 392

LCM-MVSNet		78.70 385	76.24 391	86.08 393	77.26 432	71.99 423	94.34 413	96.72 373	61.62 423	76.53 415	89.33 416	33.91 431	92.78 418	81.85 399	74.60 419	93.46 406

TinyColmap		92.31 339	91.53 340	94.65 345	96.92 312	89.75 353	96.92 363	96.68 375	90.45 356	89.62 374	97.85 235	76.06 387	98.81 270	86.74 373	92.51 306	95.41 377

Baseline_NR-MVSNet		94.35 282	93.81 283	95.96 293	96.20 349	94.05 255	98.61 189	96.67 376	91.44 331	93.85 291	97.60 261	88.57 220	98.14 338	94.39 228	86.93 377	95.68 374

SixPastTwentyTwo		93.34 319	92.86 318	94.75 341	95.67 368	89.41 365	98.75 154	96.67 376	93.89 229	90.15 371	98.25 202	80.87 342	98.27 332	90.90 326	90.64 328	96.57 332

testing222		94.12 300	93.03 315	97.37 195	98.02 226	94.66 226	97.94 279	96.65 378	94.63 194	95.78 227	95.76 371	71.49 401	98.92 252	91.17 317	95.88 256	98.52 228

test_fmvs3		87.17 373	87.06 376	87.50 391	91.21 412	75.66 416	99.05 69	96.61 379	92.79 289	88.85 382	92.78 408	43.72 423	93.49 414	93.95 244	84.56 388	93.34 408

mvs5depth		91.23 348	90.17 352	94.41 356	92.09 408	89.79 352	95.26 400	96.50 380	90.73 350	91.69 355	97.06 308	76.12 386	98.62 285	88.02 366	84.11 391	94.82 390

EGC-MVSNET		75.22 390	69.54 393	92.28 381	94.81 389	89.58 360	97.64 313	96.50 380	1.82 433	5.57 434	95.74 372	68.21 405	96.26 399	73.80 416	91.71 314	90.99 411

APD_test1		88.22 370	88.01 369	88.86 389	95.98 359	74.66 421	97.21 344	96.44 382	83.96 405	86.66 395	97.90 229	60.95 417	97.84 363	82.73 396	90.23 334	94.09 400

WB-MVS		84.86 378	85.33 379	83.46 399	89.48 417	69.56 425	98.19 246	96.42 383	89.55 372	81.79 408	94.67 391	84.80 297	90.12 421	52.44 425	80.64 405	90.69 412

test_f		86.07 377	85.39 378	88.10 390	89.28 418	75.57 417	97.73 306	96.33 384	89.41 376	85.35 402	91.56 414	43.31 425	95.53 405	91.32 315	84.23 390	93.21 409

SSC-MVS		84.27 379	84.71 382	82.96 403	89.19 419	68.83 426	98.08 262	96.30 385	89.04 380	81.37 410	94.47 392	84.60 304	89.89 422	49.80 427	79.52 407	90.15 413

LFMVS		95.86 182	94.98 211	98.47 104	98.87 136	96.32 145	98.84 131	96.02 386	93.40 262	98.62 90	99.20 74	74.99 391	99.63 142	97.72 92	97.20 208	99.46 108

IB-MVS	91.98 17	93.27 321	91.97 336	97.19 201	97.47 273	93.41 278	97.09 355	95.99 387	93.32 265	92.47 342	95.73 374	78.06 365	99.53 165	94.59 223	82.98 394	98.62 219
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		94.08 304	93.51 302	95.80 300	95.53 374	92.89 299	97.38 329	95.97 388	95.11 166	92.51 341	96.66 341	87.71 243	96.94 385	87.03 372	93.67 285	97.57 265

WB-MVSnew		94.19 293	94.04 262	94.66 344	96.82 320	92.14 306	97.86 293	95.96 389	93.50 257	95.64 229	96.77 337	88.06 235	97.99 351	84.87 387	96.86 218	93.85 405

FPMVS		77.62 389	77.14 389	79.05 407	79.25 430	60.97 432	95.79 394	95.94 390	65.96 421	67.93 423	94.40 395	37.73 427	88.88 424	68.83 420	88.46 360	87.29 418

Patchmatch-RL test		91.49 344	90.85 345	93.41 368	91.37 411	84.40 400	92.81 416	95.93 391	91.87 320	87.25 389	94.87 389	88.99 208	96.53 395	92.54 288	82.00 396	99.30 131

tpm		94.13 298	93.80 284	95.12 325	96.50 337	87.91 390	97.44 324	95.89 392	92.62 294	96.37 211	96.30 353	84.13 315	98.30 327	93.24 264	91.66 316	99.14 161

LCM-MVSNet-Re		95.22 222	95.32 194	94.91 333	98.18 209	87.85 391	98.75 154	95.66 393	95.11 166	88.96 379	96.85 332	90.26 179	97.65 369	95.65 187	98.44 169	99.22 145

MVS_0304		98.23 64	97.91 74	99.21 43	98.06 221	97.96 67	98.58 192	95.51 394	98.58 9	98.87 70	99.26 63	92.99 112	99.95 8	99.62 13	99.67 66	99.73 45

mvsany_test3		88.80 368	88.04 368	91.09 386	89.78 416	81.57 411	97.83 298	95.49 395	93.81 235	87.53 388	93.95 400	56.14 419	97.43 377	94.68 216	83.13 393	94.26 395

ET-MVSNet_ETH3D		94.13 298	92.98 316	97.58 181	98.22 202	96.20 149	97.31 338	95.37 396	94.53 200	79.56 414	97.63 260	86.51 263	97.53 375	96.91 133	90.74 327	99.02 179

test-LLR		95.10 230	94.87 217	95.80 300	96.77 322	89.70 356	96.91 365	95.21 397	95.11 166	94.83 246	95.72 376	87.71 243	98.97 241	93.06 269	98.50 166	98.72 206

test-mter		94.08 304	93.51 302	95.80 300	96.77 322	89.70 356	96.91 365	95.21 397	92.89 285	94.83 246	95.72 376	77.69 370	98.97 241	93.06 269	98.50 166	98.72 206

PM-MVS		87.77 371	86.55 377	91.40 385	91.03 414	83.36 407	96.92 363	95.18 399	91.28 340	86.48 397	93.42 403	53.27 420	96.74 389	89.43 351	81.97 397	94.11 399

DeepMVS_CX				86.78 392	97.09 304	72.30 422		95.17 400	75.92 416	84.34 405	95.19 385	70.58 402	95.35 406	79.98 406	89.04 354	92.68 410

K. test v3		92.55 336	91.91 339	94.48 352	95.64 369	89.24 366	99.07 66	94.88 401	94.04 217	86.78 393	97.59 262	77.64 373	97.64 370	92.08 296	89.43 348	96.57 332

TESTMET0.1,1		94.18 296	93.69 294	95.63 308	96.92 312	89.12 368	96.91 365	94.78 402	93.17 272	94.88 243	96.45 350	78.52 359	98.92 252	93.09 268	98.50 166	98.85 194

pmmvs3		86.67 376	84.86 381	92.11 383	88.16 420	87.19 395	96.63 381	94.75 403	79.88 412	87.22 390	92.75 410	66.56 411	95.20 409	81.24 402	76.56 417	93.96 403

door								94.64 404

thisisatest0515		95.61 198	94.89 216	97.76 164	98.15 214	95.15 204	96.77 376	94.41 405	92.95 283	97.18 170	97.43 274	84.78 298	99.45 182	94.63 218	97.73 197	98.68 212

door-mid								94.37 406

tttt0517		96.07 170	95.51 182	97.78 160	98.41 178	94.84 219	99.28 24	94.33 407	94.26 211	97.64 156	98.64 158	84.05 316	99.47 180	95.34 195	97.60 201	99.03 178

DSMNet-mixed		92.52 338	92.58 326	92.33 380	94.15 395	82.65 408	98.30 231	94.26 408	89.08 379	92.65 335	95.73 374	85.01 293	95.76 404	86.24 376	97.76 195	98.59 224

thisisatest0530		96.01 172	95.36 189	97.97 148	98.38 180	95.52 184	98.88 116	94.19 409	94.04 217	97.64 156	98.31 194	83.82 323	99.46 181	95.29 199	97.70 198	98.93 189

MTMP							98.89 110	94.14 410

baseline2		95.11 229	94.52 234	96.87 226	96.65 331	93.56 270	98.27 236	94.10 411	93.45 260	92.02 352	97.43 274	87.45 251	99.19 209	93.88 247	97.41 206	97.87 253

PMVS	61.03 23	65.95 393	63.57 397	73.09 410	57.90 435	51.22 437	85.05 423	93.93 412	54.45 424	44.32 430	83.57 419	13.22 434	89.15 423	58.68 424	81.00 402	78.91 424
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS		94.30 285	93.89 278	95.53 311	97.83 242	88.95 373	97.52 322	93.25 413	94.44 206	96.63 195	97.07 304	78.70 358	99.28 199	91.99 301	97.56 203	98.36 237

testf1		79.02 383	77.70 385	82.99 401	88.10 421	66.90 427	94.67 407	93.11 414	71.08 419	74.02 417	93.41 404	34.15 429	93.25 415	72.25 417	78.50 411	88.82 415

APD_test2		79.02 383	77.70 385	82.99 401	88.10 421	66.90 427	94.67 407	93.11 414	71.08 419	74.02 417	93.41 404	34.15 429	93.25 415	72.25 417	78.50 411	88.82 415

PMMVS2		77.95 388	75.44 392	85.46 394	82.54 427	74.95 419	94.23 414	93.08 416	72.80 418	74.68 416	87.38 417	36.36 428	91.56 419	73.95 415	63.94 424	89.87 414

MVS-HIRNet		89.46 366	88.40 365	92.64 377	97.58 263	82.15 409	94.16 415	93.05 417	75.73 417	90.90 362	82.52 420	79.42 354	98.33 322	83.53 395	98.68 153	97.43 266

UWE-MVS-28		92.79 332	92.51 327	93.62 365	96.46 340	86.28 397	97.93 280	92.71 418	94.17 212	94.78 249	97.16 294	81.05 339	96.43 397	81.45 401	96.86 218	98.14 247

test1111		95.94 177	95.78 168	96.41 271	98.99 123	90.12 348	99.04 73	92.45 419	96.99 74	98.03 122	99.27 62	81.40 333	99.48 178	96.87 142	99.04 134	99.63 77

ECVR-MVS		95.95 175	95.71 174	96.65 239	99.02 117	90.86 332	99.03 76	91.80 420	96.96 75	98.10 115	99.26 63	81.31 334	99.51 169	96.90 136	99.04 134	99.59 83

EPMVS		94.99 237	94.48 236	96.52 260	97.22 292	91.75 315	97.23 342	91.66 421	94.11 214	97.28 165	96.81 335	85.70 280	98.84 264	93.04 271	97.28 207	98.97 184

dmvs_testset		87.64 372	88.93 364	83.79 398	95.25 381	63.36 430	97.20 345	91.17 422	93.07 277	85.64 401	95.98 369	85.30 290	91.52 420	69.42 419	87.33 372	96.49 348

lessismore_v0				94.45 355	94.93 387	88.44 383		91.03 423		86.77 394	97.64 258	76.23 385	98.42 305	90.31 333	85.64 387	96.51 345

test_vis1_rt		91.29 346	90.65 346	93.19 374	97.45 277	86.25 398	98.57 198	90.90 424	93.30 267	86.94 392	93.59 402	62.07 416	99.11 222	97.48 115	95.58 261	94.22 397

ANet_high		69.08 391	65.37 395	80.22 406	65.99 434	71.96 424	90.91 420	90.09 425	82.62 408	49.93 429	78.39 424	29.36 432	81.75 426	62.49 422	38.52 428	86.95 420

gg-mvs-nofinetune		92.21 340	90.58 348	97.13 206	96.75 325	95.09 206	95.85 393	89.40 426	85.43 400	94.50 255	81.98 421	80.80 344	98.40 318	92.16 294	98.33 176	97.88 252

GG-mvs-BLEND				96.59 250	96.34 345	94.98 212	96.51 385	88.58 427		93.10 324	94.34 398	80.34 349	98.05 346	89.53 348	96.99 214	96.74 310

E-PMN		64.94 394	64.25 396	67.02 411	82.28 428	59.36 434	91.83 419	85.63 428	52.69 425	60.22 426	77.28 425	41.06 426	80.12 428	46.15 428	41.14 426	61.57 427

EMVS		64.07 395	63.26 398	66.53 412	81.73 429	58.81 435	91.85 418	84.75 429	51.93 427	59.09 427	75.13 426	43.32 424	79.09 430	42.03 430	39.47 427	61.69 426

tmp_tt		68.90 392	66.97 394	74.68 409	50.78 436	59.95 433	87.13 421	83.47 430	38.80 429	62.21 425	96.23 356	64.70 412	76.91 431	88.91 357	30.49 429	87.19 419

test_vis3_rt		79.22 381	77.40 388	84.67 396	86.44 424	74.85 420	97.66 311	81.43 431	84.98 401	67.12 424	81.91 422	28.09 433	97.60 371	88.96 356	80.04 406	81.55 422

MVE	62.14 22	63.28 396	59.38 399	74.99 408	74.33 433	65.47 429	85.55 422	80.50 432	52.02 426	51.10 428	75.00 427	10.91 437	80.50 427	51.60 426	53.40 425	78.99 423
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2506		94.44 278	93.91 275	96.04 288	99.02 117	88.99 372	99.06 67	79.47 433	96.96 75	98.36 105	99.26 63	77.21 375	99.52 168	96.78 149	99.04 134	99.59 83

kuosan		78.45 386	77.69 387	80.72 405	92.73 407	75.32 418	94.63 410	74.51 434	75.96 415	80.87 413	93.19 406	63.23 415	79.99 429	42.56 429	81.56 400	86.85 421

dongtai		82.47 380	81.88 383	84.22 397	95.19 383	76.03 414	94.59 411	74.14 435	82.63 407	87.19 391	96.09 362	64.10 413	87.85 425	58.91 423	84.11 391	88.78 417

N_pmnet		87.12 375	87.77 373	85.17 395	95.46 377	61.92 431	97.37 331	70.66 436	85.83 397	88.73 384	96.04 365	85.33 288	97.76 366	80.02 404	90.48 329	95.84 370

wuyk23d		30.17 397	30.18 401	30.16 413	78.61 431	43.29 438	66.79 426	14.21 437	17.31 430	14.82 433	11.93 433	11.55 436	41.43 432	37.08 431	19.30 430	5.76 430

testmvs		21.48 399	24.95 402	11.09 415	14.89 437	6.47 440	96.56 383	9.87 438	7.55 431	17.93 431	39.02 429	9.43 438	5.90 434	16.56 433	12.72 431	20.91 429

test123		20.95 400	23.72 403	12.64 414	13.54 438	8.19 439	96.55 384	6.13 439	7.48 432	16.74 432	37.98 430	12.97 435	6.05 433	16.69 432	5.43 432	23.68 428

mmdepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

monomultidepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

test_blank		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet_test		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

DCPMVS		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

pcd_1.5k_mvsjas		7.88 402	10.50 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	94.51 87	0.00 435	0.00 434	0.00 433	0.00 431

sosnet-low-res		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uncertanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

Regformer		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

n2								0.00 440

nn								0.00 440

ab-mvs-re		8.20 401	10.94 404	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	98.43 177	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

WAC-MVS						90.94 329								88.66 359

PC_three_1452									95.08 170	99.60 23	99.16 84	97.86 2	98.47 299	97.52 113	99.72 59	99.74 40

eth-test2					0.00 439

eth-test					0.00 439

OPU-MVS				99.37 22	99.24 92	99.05 14	99.02 79				99.16 84	97.81 3	99.37 190	97.24 122	99.73 55	99.70 57

test_0728_THIRD									97.32 50	99.45 29	99.46 31	97.88 1	99.94 10	98.47 50	99.86 2	99.85 10

GSMVS																99.20 148

test_part2					99.63 29	99.18 10				99.27 43

sam_mvs1												89.45 194				99.20 148

sam_mvs												88.99 208

test_post1							96.68 380				30.43 432	87.85 242	98.69 278	92.59 284

test_post											31.83 431	88.83 215	98.91 254

patchmatchnet-post											95.10 387	89.42 195	98.89 258

gm-plane-assit					95.88 363	87.47 392			89.74 369		96.94 325		99.19 209	93.32 263

test9_res														96.39 161	99.57 88	99.69 60

agg_prior2														95.87 177	99.57 88	99.68 65

test_prior4						98.01 65	97.86 293

test_prior2							97.80 300		96.12 116	97.89 137	98.69 153	95.96 41		96.89 137	99.60 82

旧先验2							97.57 319		91.30 338	98.67 84			99.80 95	95.70 186

新几何2							97.64 313

原ACMM2							97.67 310

testdata2													99.89 54	91.65 311

segment_acmp												96.85 14

testdata1							97.32 337		96.34 106

plane_prior7					97.42 279	94.63 229

plane_prior6					97.35 286	94.61 232						87.09 254

plane_prior4											98.28 196

plane_prior3						94.61 232			97.02 72	95.34 233

plane_prior2							98.80 144		97.28 53

plane_prior1					97.37 285

plane_prior						94.60 234	98.44 215		96.74 86						94.22 269

HQP5-MVS						94.25 250

HQP-NCC					97.20 294		98.05 265		96.43 100	94.45 257

ACMP_Plane					97.20 294		98.05 265		96.43 100	94.45 257

BP-MVS														95.30 197

HQP4-MVS										94.45 257			98.96 245			96.87 298

HQP2-MVS												86.75 260

NP-MVS					97.28 288	94.51 237					97.73 245

MDTV_nov1_ep13_2view						84.26 401	96.89 370		90.97 347	97.90 136		89.89 183		93.91 246		99.18 157

ACMMP++_ref															92.97 299

ACMMP++															93.61 288

Test By Simon												94.64 84

High-resolution multi-view benchmark