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		97.12 116	96.80 113	98.08 130	99.30 68	94.56 228	98.05 249	99.71 1	93.57 237	97.09 157	98.91 117	88.17 218	99.89 47	96.87 131	99.56 87	99.81 17

HyFIR lowres test		96.90 124	96.49 130	98.14 121	99.33 59	95.56 173	97.38 309	99.65 2	92.34 286	97.61 144	98.20 196	89.29 187	99.10 210	96.97 119	97.60 188	99.77 27

MVS_111021_LR		98.34 53	98.23 48	98.67 76	99.27 78	96.90 103	97.95 259	99.58 3	97.14 58	98.44 91	99.01 102	95.03 73	99.62 137	97.91 68	99.75 42	99.50 91

MVS_111021_HR		98.47 38	98.34 35	98.88 68	99.22 89	97.32 83	97.91 264	99.58 3	97.20 53	98.33 97	99.00 103	95.99 36	99.64 131	98.05 61	99.76 38	99.69 56

PGM-MVS		98.49 35	98.23 48	99.27 34	99.72 12	98.08 58	98.99 82	99.49 5	95.43 137	99.03 47	99.32 49	95.56 48	99.94 8	96.80 136	99.77 32	99.78 21

ACMMP		98.23 57	97.95 63	99.09 52	99.74 7	97.62 73	99.03 72	99.41 6	95.98 110	97.60 145	99.36 42	94.45 85	99.93 25	97.14 113	98.85 136	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 44	98.51 18	98.13 124	99.30 68	95.25 190	98.85 119	99.39 7	97.94 14	99.74 9	99.62 3	92.59 110	99.91 39	99.65 7	99.52 93	99.25 133

fmvsm_s_conf0.5_n_a		98.38 47	98.42 25	98.27 109	99.09 106	95.41 180	98.86 117	99.37 8	97.69 21	99.78 6	99.61 4	92.38 113	99.91 39	99.58 10	99.43 105	99.49 96

test_fmvsm_n_1920		98.87 10	99.01 3	98.45 95	99.42 55	96.43 127	98.96 90	99.36 9	98.63 5	99.86 2	99.51 13	95.91 39	99.97 1	99.72 5	99.75 42	98.94 176

test_fmvsmconf_n		98.92 7	98.87 6	99.04 55	98.88 126	97.25 90	98.82 127	99.34 10	98.75 3	99.80 5	99.61 4	95.16 68	99.95 7	99.70 6	99.80 20	99.93 1

CSCG		97.85 71	97.74 68	98.20 118	99.67 25	95.16 194	99.22 37	99.32 11	93.04 261	97.02 163	98.92 116	95.36 57	99.91 39	97.43 104	99.64 69	99.52 86

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 47	99.41 56	97.54 76	98.89 104	99.31 12	98.49 8	99.86 2	99.42 29	96.45 24	99.96 4	99.86 1	99.74 46	99.90 3

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 51	99.43 54	97.48 78	98.88 109	99.30 13	98.47 9	99.85 4	99.43 28	96.71 17	99.96 4	99.86 1	99.80 20	99.89 5

patch_mono-2		98.36 50	98.87 6	96.82 219	99.53 36	90.68 325	98.64 170	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		96.73 130	96.60 125	97.12 198	99.25 81	95.35 185	98.26 222	99.26 15	94.28 194	97.94 120	97.46 258	92.74 108	99.81 81	96.88 128	93.32 281	96.20 345

PVSNet_Blended		97.38 103	97.12 99	98.14 121	99.25 81	95.35 185	97.28 320	99.26 15	93.13 257	97.94 120	98.21 195	92.74 108	99.81 81	96.88 128	99.40 110	99.27 129

fmvsm_s_conf0.1_n		98.18 59	98.21 51	98.11 128	98.54 160	95.24 191	98.87 114	99.24 17	97.50 31	99.70 13	99.67 1	91.33 147	99.89 47	99.47 12	99.54 90	99.21 138

UniMVSNet_NR-MVSNet		95.71 180	95.15 189	97.40 181	96.84 301	96.97 99	98.74 147	99.24 17	95.16 153	93.88 274	97.72 237	91.68 135	98.31 308	95.81 165	87.25 357	96.92 270

WR-MVS_H		95.05 220	94.46 224	96.81 220	96.86 300	95.82 165	99.24 32	99.24 17	93.87 213	92.53 321	96.84 316	90.37 167	98.24 316	93.24 248	87.93 348	96.38 338

SDMVSNet		96.85 126	96.42 131	98.14 121	99.30 68	96.38 131	99.21 40	99.23 20	95.92 112	95.96 207	98.76 136	85.88 264	99.44 169	97.93 66	95.59 242	98.60 207

FC-MVSNet-test		96.42 143	96.05 145	97.53 173	96.95 293	97.27 85	99.36 15	99.23 20	95.83 119	93.93 271	98.37 175	92.00 128	98.32 306	96.02 159	92.72 291	97.00 264

VPA-MVSNet		95.75 177	95.11 193	97.69 160	97.24 273	97.27 85	98.94 94	99.23 20	95.13 154	95.51 215	97.32 269	85.73 266	98.91 238	97.33 109	89.55 328	96.89 278

FIs		96.51 140	96.12 143	97.67 163	97.13 284	97.54 76	99.36 15	99.22 23	95.89 115	94.03 267	98.35 177	91.98 129	98.44 287	96.40 147	92.76 290	97.01 263

tfpnnormal		93.66 296	92.70 306	96.55 248	96.94 294	95.94 155	98.97 85	99.19 24	91.04 327	91.38 339	97.34 267	84.94 282	98.61 268	85.45 364	89.02 338	95.11 366

UniMVSNet (Re)		95.78 176	95.19 188	97.58 170	96.99 291	97.47 80	98.79 141	99.18 25	95.60 129	93.92 272	97.04 296	91.68 135	98.48 280	95.80 167	87.66 351	96.79 288

fmvsm_s_conf0.1_n_a		98.08 60	98.04 60	98.21 116	97.66 241	95.39 181	98.89 104	99.17 26	97.24 50	99.76 8	99.67 1	91.13 152	99.88 56	99.39 13	99.41 107	99.35 115

PVSNet_Blended_VisFu		97.70 78	97.46 83	98.44 97	99.27 78	95.91 160	98.63 173	99.16 27	94.48 189	97.67 137	98.88 119	92.80 107	99.91 39	97.11 114	99.12 122	99.50 91

test_fmvsmvis_n_1920		98.44 41	98.51 18	98.23 115	98.33 179	96.15 142	98.97 85	99.15 28	98.55 7	98.45 89	99.55 6	94.26 91	99.97 1	99.65 7	99.66 62	98.57 212

CHOSEN 280x420		97.18 113	97.18 98	97.20 189	98.81 134	93.27 277	95.78 375	99.15 28	95.25 149	96.79 176	98.11 202	92.29 116	99.07 213	98.56 29	99.85 5	99.25 133

D2MVS		95.18 213	95.08 194	95.48 300	97.10 286	92.07 298	98.30 216	99.13 30	94.02 203	92.90 309	96.73 320	89.48 181	98.73 259	94.48 211	93.60 275	95.65 358

PHI-MVS		98.34 53	98.06 58	99.18 42	99.15 100	98.12 57	99.04 68	99.09 31	93.32 247	98.83 64	99.10 86	96.54 21	99.83 69	97.70 85	99.76 38	99.59 79

sd_testset		96.17 155	95.76 158	97.42 178	99.30 68	94.34 237	98.82 127	99.08 32	95.92 112	95.96 207	98.76 136	82.83 315	99.32 181	95.56 176	95.59 242	98.60 207

UA-Net		97.96 64	97.62 71	98.98 59	98.86 129	97.47 80	98.89 104	99.08 32	96.67 82	98.72 72	99.54 8	93.15 104	99.81 81	94.87 195	98.83 137	99.65 69

PatchMatch-RL		96.59 135	96.03 147	98.27 109	99.31 64	96.51 123	97.91 264	99.06 34	93.72 224	96.92 168	98.06 205	88.50 213	99.65 129	91.77 291	99.00 128	98.66 203

3Dnovator	94.51 5	97.46 94	96.93 108	99.07 53	97.78 229	97.64 71	99.35 17	99.06 34	97.02 64	93.75 281	99.16 77	89.25 189	99.92 31	97.22 112	99.75 42	99.64 71

MSLP-MVS++		98.56 29	98.57 15	98.55 83	99.26 80	96.80 107	98.71 156	99.05 36	97.28 45	98.84 62	99.28 54	96.47 23	99.40 173	98.52 36	99.70 55	99.47 100

PS-CasMVS		94.67 244	93.99 255	96.71 224	96.68 311	95.26 189	99.13 54	99.03 37	93.68 230	92.33 327	97.95 216	85.35 274	98.10 324	93.59 240	88.16 347	96.79 288

TranMVSNet+NR-MVSNet		95.14 215	94.48 222	97.11 199	96.45 324	96.36 133	99.03 72	99.03 37	95.04 161	93.58 284	97.93 217	88.27 216	98.03 330	94.13 222	86.90 362	96.95 269

PEN-MVS		94.42 264	93.73 276	96.49 252	96.28 330	94.84 211	99.17 47	99.00 39	93.51 238	92.23 329	97.83 229	86.10 260	97.90 340	92.55 271	86.92 361	96.74 293

Vis-MVSNet		97.42 100	97.11 100	98.34 105	98.66 149	96.23 138	99.22 37	99.00 39	96.63 84	98.04 109	99.21 65	88.05 224	99.35 178	96.01 160	99.21 118	99.45 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DU-MVS		95.42 196	94.76 209	97.40 181	96.53 318	96.97 99	98.66 168	98.99 41	95.43 137	93.88 274	97.69 240	88.57 208	98.31 308	95.81 165	87.25 357	96.92 270

test_fmvsmconf0.1_n		98.58 23	98.44 24	98.99 57	97.73 235	97.15 95	98.84 123	98.97 42	98.75 3	99.43 27	99.54 8	93.29 102	99.93 25	99.64 9	99.79 26	99.89 5

VPNet		94.99 224	94.19 238	97.40 181	97.16 282	96.57 120	98.71 156	98.97 42	95.67 127	94.84 229	98.24 194	80.36 331	98.67 265	96.46 144	87.32 356	96.96 267

OpenMVS	93.04 13	95.83 174	95.00 197	98.32 106	97.18 281	97.32 83	99.21 40	98.97 42	89.96 344	91.14 341	99.05 97	86.64 250	99.92 31	93.38 244	99.47 100	97.73 241

HFP-MVS		98.63 17	98.40 26	99.32 28	99.72 12	98.29 45	99.23 33	98.96 45	96.10 108	98.94 53	99.17 74	96.06 32	99.92 31	97.62 89	99.78 30	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 54	99.23 33	98.95 46	96.10 108	98.93 57	99.19 72	95.70 45	99.94 8	97.62 89	99.79 26	99.78 21

CP-MVSNet		94.94 231	94.30 232	96.83 218	96.72 309	95.56 173	99.11 56	98.95 46	93.89 211	92.42 326	97.90 219	87.19 241	98.12 323	94.32 216	88.21 345	96.82 287

NR-MVSNet		94.98 226	94.16 241	97.44 176	96.53 318	97.22 92	98.74 147	98.95 46	94.96 166	89.25 358	97.69 240	89.32 186	98.18 318	94.59 208	87.40 354	96.92 270

region2R		98.61 18	98.38 28	99.29 29	99.74 7	98.16 53	99.23 33	98.93 50	96.15 105	98.94 53	99.17 74	95.91 39	99.94 8	97.55 98	99.79 26	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 73	97.40 87	98.96 62	98.88 126	97.55 75	98.63 173	98.93 50	96.74 78	99.02 48	98.84 123	90.33 169	99.83 69	98.53 30	96.66 209	99.50 91

UGNet		96.78 129	96.30 137	98.19 120	98.24 187	95.89 162	98.88 109	98.93 50	97.39 38	96.81 174	97.84 226	82.60 316	99.90 45	96.53 142	99.49 97	98.79 186
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		97.39 102	96.98 107	98.61 79	98.60 156	96.61 116	98.22 224	98.93 50	93.97 207	98.01 115	98.48 162	91.98 129	99.85 63	96.45 145	98.15 168	99.39 112

QAPM		96.29 149	95.40 173	98.96 62	97.85 225	97.60 74	99.23 33	98.93 50	89.76 348	93.11 305	99.02 98	89.11 194	99.93 25	91.99 285	99.62 72	99.34 116

DPE-MVS		98.92 7	98.67 12	99.65 2	99.58 32	99.20 9	98.42 204	98.91 56	97.58 27	99.54 22	99.46 24	97.10 12	99.94 8	97.64 88	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		96.93 122	96.27 138	98.92 64	99.50 41	97.63 72	98.85 119	98.90 57	84.80 382	97.77 127	99.11 84	92.84 106	99.66 128	94.85 196	99.77 32	99.47 100

LS3D		97.16 114	96.66 124	98.68 75	98.53 161	97.19 93	98.93 96	98.90 57	92.83 270	95.99 205	99.37 38	92.12 124	99.87 58	93.67 238	99.57 81	98.97 172

DELS-MVS		98.40 46	98.20 52	98.99 57	99.00 114	97.66 70	97.75 283	98.89 59	97.71 19	98.33 97	98.97 105	94.97 74	99.88 56	98.42 44	99.76 38	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 69	97.46 83	99.06 54	99.53 36	98.35 42	98.33 209	98.89 59	92.62 275	98.05 107	98.94 113	95.34 58	99.65 129	96.04 158	99.42 106	99.19 143

AdaColmap		97.15 115	96.70 120	98.48 92	99.16 98	96.69 113	98.01 253	98.89 59	94.44 191	96.83 171	98.68 142	90.69 163	99.76 107	94.36 213	99.29 117	98.98 171

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 52	99.74 37

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 85	98.88 62					99.94 8	98.47 38	99.81 13	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 47	99.26 29	98.88 62	97.52 29	99.41 28	98.78 130	96.00 35	99.79 98	97.79 77	99.59 77	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		94.10 287	93.26 296	96.61 236	99.11 104	94.28 238	99.01 77	98.88 62	86.43 372	92.81 311	97.57 252	81.66 320	98.68 264	94.83 197	89.02 338	96.88 279

XVS		98.70 14	98.49 21	99.34 23	99.70 22	98.35 42	99.29 24	98.88 62	97.40 36	98.46 86	99.20 67	95.90 41	99.89 47	97.85 73	99.74 46	99.78 21

X-MVStestdata		94.06 291	92.30 314	99.34 23	99.70 22	98.35 42	99.29 24	98.88 62	97.40 36	98.46 86	43.50 405	95.90 41	99.89 47	97.85 73	99.74 46	99.78 21

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 75	98.87 69	97.65 22	99.73 10	99.48 18	97.53 7	99.94 8	98.43 42	99.81 13	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 20	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 64	99.34 18	98.87 69	95.96 111	98.60 81	99.13 82	96.05 33	99.94 8	97.77 78	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 59	98.87 69	97.38 39	99.35 32	99.40 31	97.78 5	99.87 58	97.77 78	99.85 5	99.78 21
Skip Steuart: Steuart Systems R&D Blog.
DeepPCF-MVS	96.37 2	97.93 67	98.48 23	96.30 269	99.00 114	89.54 344	97.43 305	98.87 69	98.16 11	99.26 36	99.38 37	96.12 31	99.64 131	98.30 49	99.77 32	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 35	98.20 52	99.35 22	99.73 11	98.39 34	99.19 44	98.86 75	95.77 121	98.31 99	99.10 86	95.46 51	99.93 25	97.57 97	99.81 13	99.74 37

DTE-MVSNet		93.98 293	93.26 296	96.14 274	96.06 339	94.39 234	99.20 42	98.86 75	93.06 260	91.78 335	97.81 231	85.87 265	97.58 354	90.53 312	86.17 366	96.46 335

SD-MVS		98.64 16	98.68 11	98.53 87	99.33 59	98.36 41	98.90 100	98.85 78	97.28 45	99.72 12	99.39 32	96.63 20	97.60 352	98.17 54	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 48		98.84 79					99.70 119			99.65 69

Anonymous20240529		95.10 217	94.22 236	97.75 154	99.01 113	94.26 240	98.87 114	98.83 80	85.79 378	96.64 179	98.97 105	78.73 341	99.85 63	96.27 149	94.89 247	99.12 154

9.14			98.06 58		99.47 47		98.71 156	98.82 81	94.36 193	99.16 44	99.29 53	96.05 33	99.81 81	97.00 117	99.71 54

SR-MVS		98.57 27	98.35 32	99.24 36	99.53 36	98.18 51	99.09 60	98.82 81	96.58 85	99.10 46	99.32 49	95.39 54	99.82 76	97.70 85	99.63 70	99.72 45

GST-MVS		98.43 43	98.12 55	99.34 23	99.72 12	98.38 35	99.09 60	98.82 81	95.71 125	98.73 71	99.06 96	95.27 62	99.93 25	97.07 116	99.63 70	99.72 45

HPM-MVS_fast		98.38 47	98.13 54	99.12 50	99.75 3	97.86 64	99.44 11	98.82 81	94.46 190	98.94 53	99.20 67	95.16 68	99.74 111	97.58 92	99.85 5	99.77 27

APD-MVS		98.35 52	98.00 62	99.42 16	99.51 39	98.72 21	98.80 136	98.82 81	94.52 187	99.23 37	99.25 61	95.54 50	99.80 88	96.52 143	99.77 32	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	95.12 155	99.32 33	99.39 32	96.22 26	99.84 67	97.72 81	99.73 49	99.67 65

ACMMP_NAP		98.61 18	98.30 41	99.55 9	99.62 30	98.95 17	98.82 127	98.81 86	95.80 120	99.16 44	99.47 20	95.37 56	99.92 31	97.89 70	99.75 42	99.79 19

APD-MVS_3200maxsize		98.53 32	98.33 39	99.15 46	99.50 41	97.92 63	99.15 49	98.81 86	96.24 101	99.20 38	99.37 38	95.30 60	99.80 88	97.73 80	99.67 60	99.72 45

WR-MVS		95.15 214	94.46 224	97.22 188	96.67 312	96.45 125	98.21 225	98.81 86	94.15 197	93.16 301	97.69 240	87.51 235	98.30 310	95.29 185	88.62 342	96.90 277

mPP-MVS		98.51 33	98.26 43	99.25 35	99.75 3	98.04 59	99.28 26	98.81 86	96.24 101	98.35 96	99.23 62	95.46 51	99.94 8	97.42 105	99.81 13	99.77 27

CNVR-MVS		98.78 11	98.56 16	99.45 15	99.32 62	98.87 19	98.47 196	98.81 86	97.72 17	98.76 68	99.16 77	97.05 13	99.78 101	98.06 59	99.66 62	99.69 56

CPTT-MVS		97.72 76	97.32 91	98.92 64	99.64 28	97.10 96	99.12 55	98.81 86	92.34 286	98.09 105	99.08 94	93.01 105	99.92 31	96.06 157	99.77 32	99.75 35

SR-MVS-dyc-post		98.54 31	98.35 32	99.13 48	99.49 45	97.86 64	99.11 56	98.80 93	96.49 90	99.17 41	99.35 44	95.34 58	99.82 76	97.72 81	99.65 65	99.71 49

RE-MVS-def			98.34 35		99.49 45	97.86 64	99.11 56	98.80 93	96.49 90	99.17 41	99.35 44	95.29 61		97.72 81	99.65 65	99.71 49

SMA-MVS		98.58 23	98.25 44	99.56 8	99.51 39	99.04 15	98.95 91	98.80 93	93.67 232	99.37 31	99.52 11	96.52 22	99.89 47	98.06 59	99.81 13	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 50	98.10 57	99.13 48	99.74 7	97.82 68	99.53 8	98.80 93	94.63 181	98.61 80	98.97 105	95.13 70	99.77 106	97.65 87	99.83 12	99.79 19
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPMNet		92.81 314	91.34 323	97.24 187	97.00 289	93.43 268	94.96 381	98.80 93	82.27 387	96.93 166	92.12 390	86.98 245	99.82 76	76.32 393	96.65 210	98.46 216

ZD-MVS					99.46 49	98.70 23		98.79 98	93.21 252	98.67 73	98.97 105	95.70 45	99.83 69	96.07 154	99.58 80

MP-MVS		98.33 55	98.01 61	99.28 32	99.75 3	98.18 51	99.22 37	98.79 98	96.13 106	97.92 123	99.23 62	94.54 80	99.94 8	96.74 139	99.78 30	99.73 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CANet		98.05 62	97.76 67	98.90 67	98.73 138	97.27 85	98.35 207	98.78 100	97.37 41	97.72 134	98.96 110	91.53 143	99.92 31	98.79 23	99.65 65	99.51 89

MP-MVS-pluss		98.31 56	97.92 64	99.49 12	99.72 12	98.88 18	98.43 202	98.78 100	94.10 199	97.69 136	99.42 29	95.25 64	99.92 31	98.09 58	99.80 20	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 59	98.50 193	98.78 100	97.72 17	98.92 59	99.28 54	95.27 62	99.82 76	97.55 98	99.77 32	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 72	97.60 72	98.44 97	99.12 102	95.97 152	97.75 283	98.78 100	96.89 70	98.46 86	99.22 64	93.90 97	99.68 125	94.81 199	99.52 93	99.67 65

NCCC		98.61 18	98.35 32	99.38 18	99.28 77	98.61 26	98.45 197	98.76 104	97.82 16	98.45 89	98.93 114	96.65 19	99.83 69	97.38 107	99.41 107	99.71 49

PLC	95.07 4	97.20 112	96.78 116	98.44 97	99.29 73	96.31 137	98.14 237	98.76 104	92.41 284	96.39 195	98.31 184	94.92 76	99.78 101	94.06 226	98.77 140	99.23 135
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
h-mvs33		96.17 155	95.62 170	97.81 148	99.03 110	94.45 230	98.64 170	98.75 106	97.48 32	98.67 73	98.72 139	89.76 176	99.86 62	97.95 64	81.59 379	99.11 155

DeepC-MVS	95.98 3	97.88 68	97.58 73	98.77 71	99.25 81	96.93 101	98.83 125	98.75 106	96.96 67	96.89 170	99.50 15	90.46 166	99.87 58	97.84 75	99.76 38	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	98.90 100	98.74 108	97.27 49	98.02 112	99.39 32	94.81 77	99.96 4	97.91 68	99.79 26	99.77 27

ab-mvs		96.42 143	95.71 163	98.55 83	98.63 153	96.75 110	97.88 271	98.74 108	93.84 214	96.54 188	98.18 198	85.34 275	99.75 109	95.93 161	96.35 219	99.15 150

TEST9					99.31 64	98.50 29	97.92 262	98.73 111	92.63 274	97.74 131	98.68 142	96.20 28	99.80 88

train_agg		97.97 63	97.52 79	99.33 26	99.31 64	98.50 29	97.92 262	98.73 111	92.98 263	97.74 131	98.68 142	96.20 28	99.80 88	96.59 140	99.57 81	99.68 61

test_8					99.29 73	98.44 31	97.89 270	98.72 113	92.98 263	97.70 135	98.66 145	96.20 28	99.80 88

agg_prior					99.30 68	98.38 35		98.72 113		97.57 147			99.81 81

无先验							97.58 297	98.72 113	91.38 313				99.87 58	93.36 246		99.60 77

save fliter					99.46 49	98.38 35	98.21 225	98.71 116	97.95 13

WTY-MVS		97.37 105	96.92 109	98.72 73	98.86 129	96.89 105	98.31 214	98.71 116	95.26 148	97.67 137	98.56 156	92.21 121	99.78 101	95.89 162	96.85 204	99.48 98

3Dnovator+	94.38 6	97.43 99	96.78 116	99.38 18	97.83 226	98.52 28	99.37 14	98.71 116	97.09 62	92.99 308	99.13 82	89.36 185	99.89 47	96.97 119	99.57 81	99.71 49

旧先验1					99.29 73	97.48 78		98.70 119			99.09 92	95.56 48			99.47 100	99.61 75

EI-MVSNet-Vis-set		98.47 38	98.39 27	98.69 74	99.46 49	96.49 124	98.30 216	98.69 120	97.21 52	98.84 62	99.36 42	95.41 53	99.78 101	98.62 26	99.65 65	99.80 18

新几何1				99.16 45	99.34 57	98.01 61		98.69 120	90.06 343	98.13 102	98.95 112	94.60 79	99.89 47	91.97 287	99.47 100	99.59 79

API-MVS		97.41 101	97.25 93	97.91 141	98.70 143	96.80 107	98.82 127	98.69 120	94.53 185	98.11 103	98.28 187	94.50 84	99.57 142	94.12 223	99.49 97	97.37 254

EI-MVSNet-UG-set		98.41 45	98.34 35	98.61 79	99.45 52	96.32 135	98.28 219	98.68 123	97.17 55	98.74 69	99.37 38	95.25 64	99.79 98	98.57 27	99.54 90	99.73 42

testdata				98.26 112	99.20 92	95.36 183		98.68 123	91.89 300	98.60 81	99.10 86	94.44 86	99.82 76	94.27 218	99.44 104	99.58 83

MCST-MVS		98.65 15	98.37 29	99.48 13	99.60 31	98.87 19	98.41 205	98.68 123	97.04 63	98.52 85	98.80 128	96.78 16	99.83 69	97.93 66	99.61 73	99.74 37

PVSNet	91.96 18	96.35 147	96.15 142	96.96 209	99.17 94	92.05 299	96.08 368	98.68 123	93.69 228	97.75 130	97.80 232	88.86 203	99.69 124	94.26 219	99.01 127	99.15 150

MAR-MVS		96.91 123	96.40 133	98.45 95	98.69 146	96.90 103	98.66 168	98.68 123	92.40 285	97.07 160	97.96 215	91.54 142	99.75 109	93.68 236	98.92 130	98.69 198
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 77	99.32 62	96.62 114		98.67 128	93.27 251	97.81 126	98.97 105	95.18 67	99.83 69	93.84 232	99.46 103	99.50 91

CDPH-MVS		97.94 66	97.49 80	99.28 32	99.47 47	98.44 31	97.91 264	98.67 128	92.57 278	98.77 67	98.85 122	95.93 38	99.72 113	95.56 176	99.69 57	99.68 61

UnsupCasMVSNet_eth		90.99 332	89.92 335	94.19 341	94.08 376	89.83 337	97.13 334	98.67 128	93.69 228	85.83 378	96.19 341	75.15 369	96.74 369	89.14 336	79.41 387	96.00 350

TSAR-MVS + MP.		98.78 11	98.62 13	99.24 36	99.69 24	98.28 46	99.14 51	98.66 131	96.84 71	99.56 20	99.31 51	96.34 25	99.70 119	98.32 48	99.73 49	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	98.72 155	98.66 131	97.51 30	98.15 101	98.83 125	95.70 45	99.92 31	97.53 100	99.67 60	99.66 68

test222					99.23 88	97.17 94	97.40 307	98.66 131	88.68 362	98.05 107	98.96 110	94.14 93			99.53 92	99.61 75

test11								98.66 131

XXY-MVS		95.20 212	94.45 226	97.46 174	96.75 307	96.56 121	98.86 117	98.65 135	93.30 249	93.27 298	98.27 190	84.85 284	98.87 245	94.82 198	91.26 307	96.96 267

IU-MVS					99.71 19	99.23 7		98.64 136	95.28 147	99.63 18				98.35 47	99.81 13	99.83 13

TAPA-MVS	93.98 7	95.35 203	94.56 218	97.74 155	99.13 101	94.83 213	98.33 209	98.64 136	86.62 370	96.29 197	98.61 148	94.00 96	99.29 183	80.00 384	99.41 107	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 20	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 20	99.86 8

F-COLMAP		97.09 118	96.80 113	97.97 137	99.45 52	94.95 207	98.55 186	98.62 140	93.02 262	96.17 200	98.58 153	94.01 95	99.81 81	93.95 228	98.90 131	99.14 152

test_fmvsmconf0.01_n		97.86 69	97.54 78	98.83 69	95.48 358	96.83 106	98.95 91	98.60 141	98.58 6	98.93 57	99.55 6	88.57 208	99.91 39	99.54 11	99.61 73	99.77 27

EIA-MVS		97.75 74	97.58 73	98.27 109	98.38 169	96.44 126	99.01 77	98.60 141	95.88 117	97.26 152	97.53 255	94.97 74	99.33 180	97.38 107	99.20 119	99.05 165

PAPM_NR		97.46 94	97.11 100	98.50 89	99.50 41	96.41 130	98.63 173	98.60 141	95.18 152	97.06 161	98.06 205	94.26 91	99.57 142	93.80 234	98.87 135	99.52 86

cdsmvs_eth3d_5k		23.98 375	31.98 377	0.00 393	0.00 416	0.00 418	0.00 404	98.59 144	0.00 411	0.00 412	98.61 148	90.60 164	0.00 412	0.00 411	0.00 410	0.00 408

1314		96.25 154	95.73 159	97.79 149	97.13 284	95.55 175	98.19 230	98.59 144	93.47 241	92.03 333	97.82 230	91.33 147	99.49 159	94.62 205	98.44 156	98.32 224

CVMVSNet		95.43 195	96.04 146	93.57 345	97.93 221	83.62 383	98.12 240	98.59 144	95.68 126	96.56 184	99.02 98	87.51 235	97.51 357	93.56 242	97.44 191	99.60 77

OMC-MVS		97.55 92	97.34 90	98.20 118	99.33 59	95.92 159	98.28 219	98.59 144	95.52 133	97.97 117	99.10 86	93.28 103	99.49 159	95.09 190	98.88 133	99.19 143

LTVRE_ROB	92.95 15	94.60 247	93.90 261	96.68 228	97.41 265	94.42 232	98.52 188	98.59 144	91.69 306	91.21 340	98.35 177	84.87 283	99.04 217	91.06 304	93.44 279	96.60 311
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		96.71 131	96.84 112	96.31 268	99.11 104	89.74 339	99.05 65	98.58 149	98.08 12	99.87 1	99.37 38	78.48 345	99.93 25	99.29 14	99.69 57	99.27 129

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 85	98.58 149	97.62 24	99.45 25	99.46 24	97.42 9	99.94 8	98.47 38	99.81 13	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		94.24 275	93.33 293	96.97 208	97.19 280	93.38 273	98.74 147	98.57 151	91.21 325	93.81 278	98.58 153	72.85 379	98.77 257	95.05 192	93.93 265	98.77 193

PAPR		96.84 127	96.24 140	98.65 77	98.72 142	96.92 102	97.36 313	98.57 151	93.33 246	96.67 178	97.57 252	94.30 89	99.56 145	91.05 306	98.59 148	99.47 100

HQP_MVS		96.14 157	95.90 152	96.85 217	97.42 262	94.60 226	98.80 136	98.56 153	97.28 45	95.34 217	98.28 187	87.09 242	99.03 218	96.07 154	94.27 250	96.92 270

plane_prior5								98.56 153					99.03 218	96.07 154	94.27 250	96.92 270

ETV-MVS		97.96 64	97.81 65	98.40 102	98.42 166	97.27 85	98.73 151	98.55 155	96.84 71	98.38 93	97.44 261	95.39 54	99.35 178	97.62 89	98.89 132	98.58 211

mvs_tets		95.41 198	95.00 197	96.65 229	95.58 354	94.42 232	99.00 79	98.55 155	95.73 124	93.21 300	98.38 174	83.45 313	98.63 267	97.09 115	94.00 261	96.91 275

LPG-MVS_test		95.62 186	95.34 179	96.47 255	97.46 257	93.54 263	98.99 82	98.54 157	94.67 179	94.36 249	98.77 132	85.39 272	99.11 206	95.71 171	94.15 256	96.76 291

LGP-MVS_train				96.47 255	97.46 257	93.54 263		98.54 157	94.67 179	94.36 249	98.77 132	85.39 272	99.11 206	95.71 171	94.15 256	96.76 291

test_cas_vis1_n_1920		97.38 103	97.36 89	97.45 175	98.95 121	93.25 279	99.00 79	98.53 159	97.70 20	99.77 7	99.35 44	84.71 289	99.85 63	98.57 27	99.66 62	99.26 131

test12				99.18 42	99.16 98	98.19 50		98.53 159		98.07 106		95.13 70	99.72 113		99.56 87	99.63 73

CNLPA		97.45 97	97.03 104	98.73 72	99.05 108	97.44 82	98.07 247	98.53 159	95.32 145	96.80 175	98.53 157	93.32 101	99.72 113	94.31 217	99.31 116	99.02 167

jajsoiax		95.45 194	95.03 196	96.73 223	95.42 362	94.63 221	99.14 51	98.52 162	95.74 122	93.22 299	98.36 176	83.87 309	98.65 266	96.95 121	94.04 259	96.91 275

XVG-OURS		96.55 139	96.41 132	96.99 205	98.75 137	93.76 254	97.50 302	98.52 162	95.67 127	96.83 171	99.30 52	88.95 202	99.53 153	95.88 163	96.26 229	97.69 243

xiu_mvs_v1_base_debu		97.60 86	97.56 75	97.72 156	98.35 172	95.98 147	97.86 273	98.51 164	97.13 59	99.01 49	98.40 171	91.56 139	99.80 88	98.53 30	98.68 141	97.37 254

xiu_mvs_v1_base		97.60 86	97.56 75	97.72 156	98.35 172	95.98 147	97.86 273	98.51 164	97.13 59	99.01 49	98.40 171	91.56 139	99.80 88	98.53 30	98.68 141	97.37 254

xiu_mvs_v1_base_debi		97.60 86	97.56 75	97.72 156	98.35 172	95.98 147	97.86 273	98.51 164	97.13 59	99.01 49	98.40 171	91.56 139	99.80 88	98.53 30	98.68 141	97.37 254

PS-MVSNAJ		97.73 75	97.77 66	97.62 168	98.68 147	95.58 172	97.34 315	98.51 164	97.29 44	98.66 77	97.88 222	94.51 81	99.90 45	97.87 72	99.17 121	97.39 252

cascas		94.63 246	93.86 265	96.93 211	96.91 297	94.27 239	96.00 372	98.51 164	85.55 379	94.54 237	96.23 338	84.20 302	98.87 245	95.80 167	96.98 202	97.66 244

CS-MVS-test		98.49 35	98.50 20	98.46 94	99.20 92	97.05 97	99.64 4	98.50 169	97.45 35	98.88 60	99.14 81	95.25 64	99.15 199	98.83 22	99.56 87	99.20 139

PS-MVSNAJss		96.43 142	96.26 139	96.92 214	95.84 348	95.08 199	99.16 48	98.50 169	95.87 118	93.84 277	98.34 181	94.51 81	98.61 268	96.88 128	93.45 278	97.06 260

MVS		94.67 244	93.54 286	98.08 130	96.88 299	96.56 121	98.19 230	98.50 169	78.05 392	92.69 316	98.02 208	91.07 156	99.63 134	90.09 317	98.36 162	98.04 232

XVG-OURS-SEG-HR		96.51 140	96.34 134	97.02 204	98.77 136	93.76 254	97.79 281	98.50 169	95.45 136	96.94 165	99.09 92	87.87 229	99.55 152	96.76 138	95.83 241	97.74 240

PVSNet_0	88.72 19	91.28 328	90.03 334	95.00 316	97.99 214	87.29 375	94.84 384	98.50 169	92.06 296	89.86 352	95.19 364	79.81 335	99.39 176	92.27 277	69.79 398	98.33 223

ACMH	92.88 16	94.55 251	93.95 257	96.34 266	97.63 243	93.26 278	98.81 135	98.49 174	93.43 243	89.74 353	98.53 157	81.91 318	99.08 212	93.69 235	93.30 282	96.70 300
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CS-MVS		98.44 41	98.49 21	98.31 107	99.08 107	96.73 111	99.67 3	98.47 175	97.17 55	98.94 53	99.10 86	95.73 44	99.13 202	98.71 24	99.49 97	99.09 157

xiu_mvs_v2_base		97.66 82	97.70 69	97.56 172	98.61 155	95.46 178	97.44 303	98.46 176	97.15 57	98.65 78	98.15 199	94.33 88	99.80 88	97.84 75	98.66 145	97.41 250

HQP3-MVS								98.46 176							94.18 254

HQP-MVS		95.72 178	95.40 173	96.69 227	97.20 277	94.25 241	98.05 249	98.46 176	96.43 93	94.45 241	97.73 235	86.75 248	98.96 229	95.30 183	94.18 254	96.86 283

CLD-MVS		95.62 186	95.34 179	96.46 258	97.52 254	93.75 256	97.27 321	98.46 176	95.53 132	94.42 246	98.00 211	86.21 258	98.97 225	96.25 152	94.37 248	96.66 306
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		94.54 252	94.14 243	95.75 292	96.55 317	91.65 307	98.11 242	98.44 180	94.96 166	94.22 257	97.90 219	79.18 339	99.11 206	94.05 227	93.85 266	96.48 333

casdiffmvs_mvg		97.72 76	97.48 82	98.44 97	98.42 166	96.59 119	98.92 98	98.44 180	96.20 103	97.76 128	99.20 67	91.66 137	99.23 189	98.27 53	98.41 159	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	95.34 204	94.98 199	96.43 260	97.67 239	93.48 267	98.73 151	98.44 180	94.94 169	92.53 321	98.53 157	84.50 295	99.14 201	95.48 180	94.00 261	96.66 306
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	93.85 9	95.69 183	95.38 177	96.61 236	97.61 244	93.84 252	98.91 99	98.44 180	95.25 149	94.28 253	98.47 163	86.04 263	99.12 204	95.50 179	93.95 264	96.87 281
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+		97.12 116	96.69 121	98.39 103	98.19 195	96.72 112	97.37 311	98.43 184	93.71 225	97.65 141	98.02 208	92.20 122	99.25 186	96.87 131	97.79 180	99.19 143

EC-MVSNet		98.21 58	98.11 56	98.49 91	98.34 177	97.26 89	99.61 5	98.43 184	96.78 74	98.87 61	98.84 123	93.72 98	99.01 223	98.91 20	99.50 95	99.19 143

anonymousdsp		95.42 196	94.91 203	96.94 210	95.10 365	95.90 161	99.14 51	98.41 186	93.75 219	93.16 301	97.46 258	87.50 237	98.41 297	95.63 175	94.03 260	96.50 330

PMMVS		96.60 134	96.33 135	97.41 179	97.90 223	93.93 249	97.35 314	98.41 186	92.84 269	97.76 128	97.45 260	91.10 155	99.20 193	96.26 150	97.91 175	99.11 155

MVSFormer		97.57 90	97.49 80	97.84 144	98.07 206	95.76 167	99.47 9	98.40 188	94.98 164	98.79 65	98.83 125	92.34 114	98.41 297	96.91 122	99.59 77	99.34 116

test_djsdf		96.00 162	95.69 166	96.93 211	95.72 350	95.49 177	99.47 9	98.40 188	94.98 164	94.58 236	97.86 223	89.16 192	98.41 297	96.91 122	94.12 258	96.88 279

sasdasda		97.67 80	97.23 94	98.98 59	98.70 143	98.38 35	99.34 18	98.39 190	96.76 76	97.67 137	97.40 265	92.26 117	99.49 159	98.28 50	96.28 227	99.08 161

OPM-MVS		95.69 183	95.33 181	96.76 222	96.16 336	94.63 221	98.43 202	98.39 190	96.64 83	95.02 226	98.78 130	85.15 279	99.05 214	95.21 189	94.20 253	96.60 311
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
canonicalmvs		97.67 80	97.23 94	98.98 59	98.70 143	98.38 35	99.34 18	98.39 190	96.76 76	97.67 137	97.40 265	92.26 117	99.49 159	98.28 50	96.28 227	99.08 161

DP-MVS		96.59 135	95.93 151	98.57 81	99.34 57	96.19 141	98.70 160	98.39 190	89.45 354	94.52 238	99.35 44	91.85 132	99.85 63	92.89 262	98.88 133	99.68 61

MGCFI-Net		97.62 85	97.19 97	98.92 64	98.66 149	98.20 49	99.32 23	98.38 194	96.69 81	97.58 146	97.42 264	92.10 125	99.50 158	98.28 50	96.25 230	99.08 161

dcpmvs_2		98.08 60	98.59 14	96.56 243	99.57 33	90.34 332	99.15 49	98.38 194	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 89	97.40 87	98.13 124	98.32 182	95.81 166	98.06 248	98.37 196	96.20 103	98.74 69	98.89 118	91.31 149	99.25 186	98.16 55	98.52 151	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	94.30 270	93.77 272	95.88 287	97.81 228	92.04 300	98.71 156	98.37 196	93.99 206	90.60 347	98.47 163	80.86 328	99.05 214	92.75 264	92.40 293	96.55 319

MSDG		95.93 168	95.30 184	97.83 145	98.90 124	95.36 183	96.83 355	98.37 196	91.32 318	94.43 245	98.73 138	90.27 170	99.60 139	90.05 320	98.82 138	98.52 213

DPM-MVS		97.55 92	96.99 106	99.23 38	99.04 109	98.55 27	97.17 330	98.35 199	94.85 173	97.93 122	98.58 153	95.07 72	99.71 118	92.60 266	99.34 114	99.43 109

CMPMVS	66.06 21	89.70 341	89.67 337	89.78 366	93.19 382	76.56 392	97.00 339	98.35 199	80.97 389	81.57 388	97.75 234	74.75 371	98.61 268	89.85 323	93.63 273	94.17 377
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		94.19 278	93.43 291	96.47 255	95.90 345	94.38 235	99.26 29	98.34 201	91.99 297	92.76 313	97.13 281	88.31 215	98.52 278	89.48 332	87.70 350	96.52 325

CDS-MVSNet		96.99 120	96.69 121	97.90 142	98.05 210	95.98 147	98.20 227	98.33 202	93.67 232	96.95 164	98.49 161	93.54 99	98.42 289	95.24 188	97.74 183	99.31 122
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
casdiffmvs		97.63 84	97.41 86	98.28 108	98.33 179	96.14 143	98.82 127	98.32 203	96.38 98	97.95 118	99.21 65	91.23 151	99.23 189	98.12 56	98.37 160	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 83	97.44 85	98.25 113	98.35 172	96.20 139	99.00 79	98.32 203	96.33 100	98.03 110	99.17 74	91.35 146	99.16 196	98.10 57	98.29 166	99.39 112

cl22		94.68 241	94.19 238	96.13 275	98.11 204	93.60 261	96.94 342	98.31 205	92.43 283	93.32 297	96.87 314	86.51 251	98.28 314	94.10 225	91.16 308	96.51 328

test_yl		97.22 109	96.78 116	98.54 85	98.73 138	96.60 117	98.45 197	98.31 205	94.70 175	98.02 112	98.42 169	90.80 160	99.70 119	96.81 134	96.79 206	99.34 116

DCV-MVSNet		97.22 109	96.78 116	98.54 85	98.73 138	96.60 117	98.45 197	98.31 205	94.70 175	98.02 112	98.42 169	90.80 160	99.70 119	96.81 134	96.79 206	99.34 116

nrg030		96.28 151	95.72 160	97.96 140	96.90 298	98.15 54	99.39 12	98.31 205	95.47 135	94.42 246	98.35 177	92.09 126	98.69 261	97.50 102	89.05 336	97.04 261

TAMVS		97.02 119	96.79 115	97.70 159	98.06 209	95.31 188	98.52 188	98.31 205	93.95 208	97.05 162	98.61 148	93.49 100	98.52 278	95.33 182	97.81 179	99.29 127

EPP-MVSNet		97.46 94	97.28 92	97.99 136	98.64 152	95.38 182	99.33 22	98.31 205	93.61 236	97.19 154	99.07 95	94.05 94	99.23 189	96.89 126	98.43 158	99.37 114

UnsupCasMVSNet_bld		87.17 352	85.12 359	93.31 350	91.94 386	88.77 357	94.92 383	98.30 211	84.30 384	82.30 386	90.04 392	63.96 392	97.25 361	85.85 361	74.47 397	93.93 383

Vis-MVSNet (Re-imp)		96.87 125	96.55 127	97.83 145	98.73 138	95.46 178	99.20 42	98.30 211	94.96 166	96.60 183	98.87 120	90.05 172	98.59 271	93.67 238	98.60 147	99.46 104

TSAR-MVS + GP.		98.38 47	98.24 46	98.81 70	99.22 89	97.25 90	98.11 242	98.29 213	97.19 54	98.99 52	99.02 98	96.22 26	99.67 126	98.52 36	98.56 150	99.51 89

MS-PatchMatch		93.84 295	93.63 281	94.46 337	96.18 333	89.45 345	97.76 282	98.27 214	92.23 291	92.13 331	97.49 256	79.50 336	98.69 261	89.75 325	99.38 112	95.25 362

EI-MVSNet		95.96 164	95.83 154	96.36 264	97.93 221	93.70 260	98.12 240	98.27 214	93.70 227	95.07 224	99.02 98	92.23 120	98.54 276	94.68 201	93.46 276	96.84 285

MVSTER		96.06 160	95.72 160	97.08 201	98.23 189	95.93 158	98.73 151	98.27 214	94.86 171	95.07 224	98.09 203	88.21 217	98.54 276	96.59 140	93.46 276	96.79 288

FMVSNet2		94.47 261	93.61 282	97.04 203	98.21 191	96.43 127	98.79 141	98.27 214	92.46 279	93.50 290	97.09 286	81.16 323	98.00 333	91.09 302	91.93 297	96.70 300

FMVSNet3		94.97 228	94.26 234	97.11 199	98.18 197	96.62 114	98.56 185	98.26 218	93.67 232	94.09 263	97.10 282	84.25 298	98.01 331	92.08 280	92.14 294	96.70 300

Fast-Effi-MVS+		96.28 151	95.70 165	98.03 133	98.29 184	95.97 152	98.58 179	98.25 219	91.74 303	95.29 221	97.23 276	91.03 157	99.15 199	92.90 260	97.96 174	98.97 172

PAPM		94.95 229	94.00 253	97.78 150	97.04 288	95.65 170	96.03 371	98.25 219	91.23 323	94.19 259	97.80 232	91.27 150	98.86 247	82.61 378	97.61 187	98.84 183

test_fmvs1_n		95.90 170	95.99 149	95.63 295	98.67 148	88.32 366	99.26 29	98.22 221	96.40 96	99.67 14	99.26 57	73.91 376	99.70 119	99.02 18	99.50 95	98.87 180

CANet_DTU		96.96 121	96.55 127	98.21 116	98.17 200	96.07 145	97.98 257	98.21 222	97.24 50	97.13 156	98.93 114	86.88 247	99.91 39	95.00 193	99.37 113	98.66 203

HY-MVS	93.96 8	96.82 128	96.23 141	98.57 81	98.46 165	97.00 98	98.14 237	98.21 222	93.95 208	96.72 177	97.99 212	91.58 138	99.76 107	94.51 210	96.54 214	98.95 175

test_fmvs1		96.42 143	96.67 123	95.66 294	98.82 133	88.53 362	98.80 136	98.20 224	96.39 97	99.64 17	99.20 67	80.35 332	99.67 126	99.04 17	99.57 81	98.78 189

PCF-MVS	93.45 11	94.68 241	93.43 291	98.42 101	98.62 154	96.77 109	95.48 379	98.20 224	84.63 383	93.34 296	98.32 183	88.55 211	99.81 81	84.80 370	98.96 129	98.68 199
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v8		94.47 261	93.77 272	96.57 242	96.36 327	94.83 213	99.05 65	98.19 226	91.92 299	93.16 301	96.97 304	88.82 205	98.48 280	91.69 293	87.79 349	96.39 337

v10		94.29 272	93.55 285	96.51 251	96.39 326	94.80 215	98.99 82	98.19 226	91.35 316	93.02 307	96.99 302	88.09 221	98.41 297	90.50 313	88.41 344	96.33 341

mvs_anonymous		96.70 132	96.53 129	97.18 192	98.19 195	93.78 253	98.31 214	98.19 226	94.01 204	94.47 240	98.27 190	92.08 127	98.46 284	97.39 106	97.91 175	99.31 122

AllTest		95.24 209	94.65 214	96.99 205	99.25 81	93.21 281	98.59 177	98.18 229	91.36 314	93.52 287	98.77 132	84.67 290	99.72 113	89.70 327	97.87 177	98.02 233

TestCases				96.99 205	99.25 81	93.21 281		98.18 229	91.36 314	93.52 287	98.77 132	84.67 290	99.72 113	89.70 327	97.87 177	98.02 233

GBi-Net		94.49 258	93.80 269	96.56 243	98.21 191	95.00 201	98.82 127	98.18 229	92.46 279	94.09 263	97.07 289	81.16 323	97.95 336	92.08 280	92.14 294	96.72 296

test1		94.49 258	93.80 269	96.56 243	98.21 191	95.00 201	98.82 127	98.18 229	92.46 279	94.09 263	97.07 289	81.16 323	97.95 336	92.08 280	92.14 294	96.72 296

FMVSNet1		93.19 309	92.07 316	96.56 243	97.54 251	95.00 201	98.82 127	98.18 229	90.38 338	92.27 328	97.07 289	73.68 377	97.95 336	89.36 334	91.30 305	96.72 296

v1192		94.32 269	93.58 283	96.53 249	96.10 337	94.45 230	98.50 193	98.17 234	91.54 309	94.19 259	97.06 293	86.95 246	98.43 288	90.14 316	89.57 326	96.70 300

v1240		94.06 291	93.29 295	96.34 266	96.03 341	93.90 250	98.44 200	98.17 234	91.18 326	94.13 262	97.01 301	86.05 261	98.42 289	89.13 337	89.50 330	96.70 300

v144192		94.39 266	93.70 278	96.48 254	96.06 339	94.35 236	98.58 179	98.16 236	91.45 311	94.33 251	97.02 299	87.50 237	98.45 285	91.08 303	89.11 335	96.63 308

Fast-Effi-MVS+-dtu		95.87 171	95.85 153	95.91 284	97.74 234	91.74 305	98.69 162	98.15 237	95.56 131	94.92 227	97.68 243	88.98 200	98.79 255	93.19 250	97.78 181	97.20 258

v1921920		94.20 277	93.47 289	96.40 263	95.98 342	94.08 246	98.52 188	98.15 237	91.33 317	94.25 255	97.20 279	86.41 255	98.42 289	90.04 321	89.39 332	96.69 305

v1144		94.59 249	93.92 258	96.60 238	96.21 331	94.78 217	98.59 177	98.14 239	91.86 302	94.21 258	97.02 299	87.97 225	98.41 297	91.72 292	89.57 326	96.61 310

IterMVS-LS		95.46 192	95.21 187	96.22 272	98.12 203	93.72 259	98.32 213	98.13 240	93.71 225	94.26 254	97.31 270	92.24 119	98.10 324	94.63 203	90.12 319	96.84 285
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GeoE		96.58 137	96.07 144	98.10 129	98.35 172	95.89 162	99.34 18	98.12 241	93.12 258	96.09 201	98.87 120	89.71 178	98.97 225	92.95 258	98.08 171	99.43 109

EU-MVSNet		93.66 296	94.14 243	92.25 361	95.96 344	83.38 385	98.52 188	98.12 241	94.69 177	92.61 318	98.13 201	87.36 240	96.39 377	91.82 289	90.00 321	96.98 265

IterMVS		94.09 288	93.85 266	94.80 325	97.99 214	90.35 331	97.18 328	98.12 241	93.68 230	92.46 325	97.34 267	84.05 304	97.41 359	92.51 273	91.33 304	96.62 309
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_vis1_n		95.47 191	95.13 190	96.49 252	97.77 230	90.41 330	99.27 28	98.11 244	96.58 85	99.66 15	99.18 73	67.00 389	99.62 137	99.21 15	99.40 110	99.44 107

IterMVS-SCA-FT		94.11 286	93.87 264	94.85 322	97.98 216	90.56 328	97.18 328	98.11 244	93.75 219	92.58 319	97.48 257	83.97 306	97.41 359	92.48 275	91.30 305	96.58 313

COLMAP_ROB	93.27 12	95.33 205	94.87 206	96.71 224	99.29 73	93.24 280	98.58 179	98.11 244	89.92 345	93.57 285	99.10 86	86.37 256	99.79 98	90.78 309	98.10 170	97.09 259
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
hse-mvs2		95.71 180	95.30 184	96.93 211	98.50 162	93.53 265	98.36 206	98.10 247	97.48 32	98.67 73	97.99 212	89.76 176	99.02 221	97.95 64	80.91 383	98.22 227

AUN-MVS		94.53 254	93.73 276	96.92 214	98.50 162	93.52 266	98.34 208	98.10 247	93.83 216	95.94 209	97.98 214	85.59 269	99.03 218	94.35 214	80.94 382	98.22 227

Effi-MVS+-dtu		96.29 149	96.56 126	95.51 299	97.89 224	90.22 333	98.80 136	98.10 247	96.57 87	96.45 193	96.66 323	90.81 159	98.91 238	95.72 170	97.99 172	97.40 251

1112_ss		96.63 133	96.00 148	98.50 89	98.56 157	96.37 132	98.18 235	98.10 247	92.92 266	94.84 229	98.43 167	92.14 123	99.58 141	94.35 214	96.51 215	99.56 85

V42		94.78 237	94.14 243	96.70 226	96.33 329	95.22 192	98.97 85	98.09 251	92.32 288	94.31 252	97.06 293	88.39 214	98.55 274	92.90 260	88.87 340	96.34 339

miper_enhance_ethall		95.10 217	94.75 210	96.12 276	97.53 253	93.73 258	96.61 362	98.08 252	92.20 294	93.89 273	96.65 325	92.44 112	98.30 310	94.21 220	91.16 308	96.34 339

v2v482		94.69 239	94.03 249	96.65 229	96.17 334	94.79 216	98.67 166	98.08 252	92.72 272	94.00 268	97.16 280	87.69 234	98.45 285	92.91 259	88.87 340	96.72 296

CL-MVSNet_self_test		90.11 338	89.14 341	93.02 354	91.86 387	88.23 368	96.51 365	98.07 254	90.49 333	90.49 348	94.41 372	84.75 287	95.34 386	80.79 382	74.95 395	95.50 359

miper_ehance_all_eth		95.01 221	94.69 213	95.97 281	97.70 237	93.31 276	97.02 338	98.07 254	92.23 291	93.51 289	96.96 306	91.85 132	98.15 320	93.68 236	91.16 308	96.44 336

eth_miper_zixun_eth		94.68 241	94.41 229	95.47 301	97.64 242	91.71 306	96.73 359	98.07 254	92.71 273	93.64 282	97.21 278	90.54 165	98.17 319	93.38 244	89.76 323	96.54 320

MVS_Test		97.28 107	97.00 105	98.13 124	98.33 179	95.97 152	98.74 147	98.07 254	94.27 195	98.44 91	98.07 204	92.48 111	99.26 185	96.43 146	98.19 167	99.16 149

Test_1112_low_res		96.34 148	95.66 169	98.36 104	98.56 157	95.94 155	97.71 286	98.07 254	92.10 295	94.79 233	97.29 271	91.75 134	99.56 145	94.17 221	96.50 216	99.58 83

alignmvs		97.56 91	97.07 103	99.01 56	98.66 149	98.37 40	98.83 125	98.06 259	96.74 78	98.00 116	97.65 244	90.80 160	99.48 164	98.37 46	96.56 213	99.19 143

RPSCF		94.87 233	95.40 173	93.26 351	98.89 125	82.06 389	98.33 209	98.06 259	90.30 340	96.56 184	99.26 57	87.09 242	99.49 159	93.82 233	96.32 221	98.24 225

miper_lstm_enhance		94.33 268	94.07 247	95.11 313	97.75 231	90.97 317	97.22 323	98.03 261	91.67 307	92.76 313	96.97 304	90.03 173	97.78 347	92.51 273	89.64 325	96.56 317

c3_l		94.79 236	94.43 228	95.89 286	97.75 231	93.12 285	97.16 332	98.03 261	92.23 291	93.46 292	97.05 295	91.39 144	98.01 331	93.58 241	89.21 334	96.53 322

pm-mvs1		93.94 294	93.06 298	96.59 239	96.49 321	95.16 194	98.95 91	98.03 261	92.32 288	91.08 342	97.84 226	84.54 294	98.41 297	92.16 278	86.13 368	96.19 346

iter_conf05		96.13 158	95.79 155	97.15 195	98.16 201	95.99 146	98.88 109	97.98 264	95.91 114	95.58 214	98.46 165	85.53 270	98.59 271	97.88 71	93.75 268	96.86 283

mvsmamba		96.57 138	96.32 136	97.32 185	96.60 314	96.43 127	99.54 7	97.98 264	96.49 90	95.20 222	98.64 146	90.82 158	98.55 274	97.97 63	93.65 272	96.98 265

v148		94.29 272	93.76 274	95.91 284	96.10 337	92.93 288	98.58 179	97.97 266	92.59 277	93.47 291	96.95 308	88.53 212	98.32 306	92.56 270	87.06 359	96.49 331

IS-MVSNet		97.22 109	96.88 110	98.25 113	98.85 131	96.36 133	99.19 44	97.97 266	95.39 139	97.23 153	98.99 104	91.11 154	98.93 235	94.60 206	98.59 148	99.47 100

cl____		94.51 256	94.01 252	96.02 278	97.58 246	93.40 272	97.05 336	97.96 268	91.73 305	92.76 313	97.08 288	89.06 196	98.13 322	92.61 265	90.29 317	96.52 325

KD-MVS_self_test		90.38 336	89.38 339	93.40 348	92.85 384	88.94 356	97.95 259	97.94 269	90.35 339	90.25 349	93.96 377	79.82 334	95.94 382	84.62 372	76.69 393	95.33 361

DIV-MVS_self_test		94.52 255	94.03 249	95.99 279	97.57 250	93.38 273	97.05 336	97.94 269	91.74 303	92.81 311	97.10 282	89.12 193	98.07 328	92.60 266	90.30 316	96.53 322

pmmvs6		91.77 323	90.63 328	95.17 311	94.69 373	91.24 314	98.67 166	97.92 271	86.14 374	89.62 354	97.56 254	75.79 367	98.34 304	90.75 310	84.56 370	95.94 352

RRT_MVS		95.98 163	95.78 156	96.56 243	96.48 322	94.22 243	99.57 6	97.92 271	95.89 115	93.95 270	98.70 140	89.27 188	98.42 289	97.23 111	93.02 285	97.04 261

jason		97.32 106	97.08 102	98.06 132	97.45 260	95.59 171	97.87 272	97.91 273	94.79 174	98.55 83	98.83 125	91.12 153	99.23 189	97.58 92	99.60 75	99.34 116
jason: jason.
ppachtmachnet_test		93.22 307	92.63 307	94.97 317	95.45 360	90.84 321	96.88 351	97.88 274	90.60 332	92.08 332	97.26 272	88.08 222	97.86 345	85.12 366	90.33 315	96.22 344

tpm cat1		93.36 301	92.80 303	95.07 315	97.58 246	87.97 370	96.76 357	97.86 275	82.17 388	93.53 286	96.04 345	86.13 259	99.13 202	89.24 335	95.87 240	98.10 231

tt0805		94.54 252	93.85 266	96.63 233	97.98 216	93.06 287	98.77 143	97.84 276	93.67 232	93.80 279	98.04 207	76.88 362	98.96 229	94.79 200	92.86 288	97.86 237

EG-PatchMatch MVS		91.13 330	90.12 333	94.17 342	94.73 372	89.00 353	98.13 239	97.81 277	89.22 358	85.32 382	96.46 331	67.71 387	98.42 289	87.89 350	93.82 267	95.08 367

BH-untuned		95.95 165	95.72 160	96.65 229	98.55 159	92.26 294	98.23 223	97.79 278	93.73 222	94.62 235	98.01 210	88.97 201	99.00 224	93.04 255	98.51 152	98.68 199

lupinMVS		97.44 98	97.22 96	98.12 127	98.07 206	95.76 167	97.68 288	97.76 279	94.50 188	98.79 65	98.61 148	92.34 114	99.30 182	97.58 92	99.59 77	99.31 122

VDDNet		95.36 202	94.53 219	97.86 143	98.10 205	95.13 197	98.85 119	97.75 280	90.46 335	98.36 94	99.39 32	73.27 378	99.64 131	97.98 62	96.58 212	98.81 185

ADS-MVSNet		95.00 222	94.45 226	96.63 233	98.00 212	91.91 301	96.04 369	97.74 281	90.15 341	96.47 191	96.64 326	87.89 227	98.96 229	90.08 318	97.06 197	99.02 167

tpmvs		94.60 247	94.36 231	95.33 307	97.46 257	88.60 360	96.88 351	97.68 282	91.29 320	93.80 279	96.42 333	88.58 207	99.24 188	91.06 304	96.04 236	98.17 229

pmmvs4		94.69 239	93.99 255	96.81 220	95.74 349	95.94 155	97.40 307	97.67 283	90.42 337	93.37 295	97.59 250	89.08 195	98.20 317	92.97 257	91.67 301	96.30 342

our_test_3		93.65 298	93.30 294	94.69 327	95.45 360	89.68 342	96.91 345	97.65 284	91.97 298	91.66 337	96.88 312	89.67 179	97.93 339	88.02 348	91.49 303	96.48 333

MVP-Stereo		94.28 274	93.92 258	95.35 306	94.95 367	92.60 291	97.97 258	97.65 284	91.61 308	90.68 346	97.09 286	86.32 257	98.42 289	89.70 327	99.34 114	95.02 369
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
KD-MVS_2432*1600		89.61 343	87.96 350	94.54 332	94.06 377	91.59 308	95.59 377	97.63 286	89.87 346	88.95 360	94.38 374	78.28 347	96.82 367	84.83 368	68.05 399	95.21 363

miper_refine_blended		89.61 343	87.96 350	94.54 332	94.06 377	91.59 308	95.59 377	97.63 286	89.87 346	88.95 360	94.38 374	78.28 347	96.82 367	84.83 368	68.05 399	95.21 363

SCA		95.46 192	95.13 190	96.46 258	97.67 239	91.29 313	97.33 316	97.60 288	94.68 178	96.92 168	97.10 282	83.97 306	98.89 242	92.59 268	98.32 165	99.20 139

testing91		94.98 226	94.25 235	97.20 189	97.94 219	93.41 270	98.00 255	97.58 289	94.99 163	95.45 216	96.04 345	77.20 358	99.42 172	94.97 194	96.02 237	98.78 189

FA-MVS(test-final)		96.41 146	95.94 150	97.82 147	98.21 191	95.20 193	97.80 279	97.58 289	93.21 252	97.36 150	97.70 238	89.47 182	99.56 145	94.12 223	97.99 172	98.71 197

GA-MVS		94.81 235	94.03 249	97.14 196	97.15 283	93.86 251	96.76 357	97.58 289	94.00 205	94.76 234	97.04 296	80.91 326	98.48 280	91.79 290	96.25 230	99.09 157

Anonymous20240521		91.18 329	90.44 330	93.42 346	93.70 380	88.47 363	98.94 94	97.56 292	88.46 363	89.56 356	95.08 367	77.15 360	96.97 365	83.92 373	89.55 328	94.82 371

test20.03		90.89 333	90.38 331	92.43 357	93.48 381	88.14 369	98.33 209	97.56 292	93.40 244	87.96 366	96.71 322	80.69 330	94.13 392	79.15 387	86.17 366	95.01 370

CR-MVSNet		94.76 238	94.15 242	96.59 239	97.00 289	93.43 268	94.96 381	97.56 292	92.46 279	96.93 166	96.24 336	88.15 219	97.88 344	87.38 351	96.65 210	98.46 216

Patchmtry		93.22 307	92.35 313	95.84 288	96.77 304	93.09 286	94.66 388	97.56 292	87.37 368	92.90 309	96.24 336	88.15 219	97.90 340	87.37 352	90.10 320	96.53 322

tpmrst		95.63 185	95.69 166	95.44 303	97.54 251	88.54 361	96.97 340	97.56 292	93.50 239	97.52 148	96.93 310	89.49 180	99.16 196	95.25 187	96.42 218	98.64 205

FMVSNet5		91.81 322	90.92 325	94.49 334	97.21 276	92.09 297	98.00 255	97.55 297	89.31 357	90.86 344	95.61 359	74.48 373	95.32 387	85.57 362	89.70 324	96.07 349

testgi		93.06 312	92.45 312	94.88 321	96.43 325	89.90 336	98.75 144	97.54 298	95.60 129	91.63 338	97.91 218	74.46 374	97.02 364	86.10 358	93.67 270	97.72 242

mvsany_test1		97.69 79	97.70 69	97.66 166	98.24 187	94.18 244	97.53 299	97.53 299	95.52 133	99.66 15	99.51 13	94.30 89	99.56 145	98.38 45	98.62 146	99.23 135

PatchmatchNet		95.71 180	95.52 171	96.29 270	97.58 246	90.72 324	96.84 354	97.52 300	94.06 200	97.08 158	96.96 306	89.24 190	98.90 241	92.03 284	98.37 160	99.26 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDA-MVSNet-bldmvs		89.97 340	88.35 346	94.83 324	95.21 364	91.34 311	97.64 292	97.51 301	88.36 364	71.17 399	96.13 343	79.22 338	96.63 374	83.65 374	86.27 365	96.52 325

USDC		93.33 304	92.71 305	95.21 309	96.83 302	90.83 322	96.91 345	97.50 302	93.84 214	90.72 345	98.14 200	77.69 352	98.82 252	89.51 331	93.21 284	95.97 351

ITE_SJBPF				95.44 303	97.42 262	91.32 312		97.50 302	95.09 159	93.59 283	98.35 177	81.70 319	98.88 244	89.71 326	93.39 280	96.12 347

Patchmatch-test		94.42 264	93.68 280	96.63 233	97.60 245	91.76 303	94.83 385	97.49 304	89.45 354	94.14 261	97.10 282	88.99 197	98.83 251	85.37 365	98.13 169	99.29 127

Syy-MVS		92.55 317	92.61 308	92.38 358	97.39 266	83.41 384	97.91 264	97.46 305	93.16 255	93.42 293	95.37 362	84.75 287	96.12 379	77.00 392	96.99 199	97.60 246

myMVS_eth3d		92.73 315	92.01 317	94.89 320	97.39 266	90.94 318	97.91 264	97.46 305	93.16 255	93.42 293	95.37 362	68.09 385	96.12 379	88.34 344	96.99 199	97.60 246

YYNet1		90.70 335	89.39 338	94.62 331	94.79 371	90.65 326	97.20 325	97.46 305	87.54 367	72.54 397	95.74 352	86.51 251	96.66 373	86.00 359	86.76 364	96.54 320

MDA-MVSNet_test_wron		90.71 334	89.38 339	94.68 328	94.83 369	90.78 323	97.19 327	97.46 305	87.60 366	72.41 398	95.72 356	86.51 251	96.71 372	85.92 360	86.80 363	96.56 317

BH-RMVSNet		95.92 169	95.32 182	97.69 160	98.32 182	94.64 220	98.19 230	97.45 309	94.56 183	96.03 203	98.61 148	85.02 280	99.12 204	90.68 311	99.06 123	99.30 125

MIMVSNet1		89.67 342	88.28 347	93.82 343	92.81 385	91.08 316	98.01 253	97.45 309	87.95 365	87.90 367	95.87 350	67.63 388	94.56 391	78.73 389	88.18 346	95.83 354

OurMVSNet-221017-0		94.21 276	94.00 253	94.85 322	95.60 353	89.22 349	98.89 104	97.43 311	95.29 146	92.18 330	98.52 160	82.86 314	98.59 271	93.46 243	91.76 299	96.74 293

BH-w/o		95.38 199	95.08 194	96.26 271	98.34 177	91.79 302	97.70 287	97.43 311	92.87 268	94.24 256	97.22 277	88.66 206	98.84 248	91.55 295	97.70 185	98.16 230

VDD-MVS		95.82 175	95.23 186	97.61 169	98.84 132	93.98 248	98.68 163	97.40 313	95.02 162	97.95 118	99.34 48	74.37 375	99.78 101	98.64 25	96.80 205	99.08 161

Gipuma		78.40 364	76.75 367	83.38 378	95.54 355	80.43 391	79.42 402	97.40 313	64.67 399	73.46 396	80.82 400	45.65 399	93.14 396	66.32 400	87.43 353	76.56 402
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FE-MVS		95.62 186	94.90 204	97.78 150	98.37 171	94.92 208	97.17 330	97.38 315	90.95 329	97.73 133	97.70 238	85.32 277	99.63 134	91.18 299	98.33 163	98.79 186

new-patchmatchnet		88.50 348	87.45 353	91.67 363	90.31 392	85.89 379	97.16 332	97.33 316	89.47 353	83.63 385	92.77 386	76.38 363	95.06 389	82.70 377	77.29 392	94.06 381

ADS-MVSNet2		94.58 250	94.40 230	95.11 313	98.00 212	88.74 358	96.04 369	97.30 317	90.15 341	96.47 191	96.64 326	87.89 227	97.56 355	90.08 318	97.06 197	99.02 167

MDTV_nov1_ep13			95.40 173		97.48 255	88.34 365	96.85 353	97.29 318	93.74 221	97.48 149	97.26 272	89.18 191	99.05 214	91.92 288	97.43 192

pmmvs5		93.65 298	92.97 301	95.68 293	95.49 357	92.37 292	98.20 227	97.28 319	89.66 350	92.58 319	97.26 272	82.14 317	98.09 326	93.18 251	90.95 311	96.58 313

EPNet_dtu		95.21 211	94.95 202	95.99 279	96.17 334	90.45 329	98.16 236	97.27 320	96.77 75	93.14 304	98.33 182	90.34 168	98.42 289	85.57 362	98.81 139	99.09 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20231206		91.66 324	91.10 324	93.33 349	94.02 379	87.35 374	98.58 179	97.26 321	90.48 334	90.16 350	96.31 334	83.83 310	96.53 375	79.36 386	89.90 322	96.12 347

test_fmvs2		93.43 300	93.58 283	92.95 355	96.97 292	83.91 382	99.19 44	97.24 322	95.74 122	95.20 222	98.27 190	69.65 382	98.72 260	96.26 150	93.73 269	96.24 343

test_0402		91.32 326	90.27 332	94.48 335	96.60 314	91.12 315	98.50 193	97.22 323	86.10 375	88.30 365	96.98 303	77.65 354	97.99 334	78.13 390	92.94 287	94.34 373

dp		94.15 282	93.90 261	94.90 319	97.31 270	86.82 377	96.97 340	97.19 324	91.22 324	96.02 204	96.61 328	85.51 271	99.02 221	90.00 322	94.30 249	98.85 181

testing99		94.83 234	94.08 246	97.07 202	97.94 219	93.13 283	98.10 244	97.17 325	94.86 171	95.34 217	96.00 348	76.31 364	99.40 173	95.08 191	95.90 238	98.68 199

testing3		93.19 309	92.48 311	95.30 308	98.07 206	92.27 293	98.64 170	97.17 325	93.94 210	93.98 269	97.04 296	67.97 386	96.01 381	88.40 343	97.14 196	97.63 245

ETVMVS		94.50 257	93.44 290	97.68 162	98.18 197	95.35 185	98.19 230	97.11 327	93.73 222	96.40 194	95.39 361	74.53 372	98.84 248	91.10 301	96.31 222	98.84 183

thres200		95.25 208	94.57 217	97.28 186	98.81 134	94.92 208	98.20 227	97.11 327	95.24 151	96.54 188	96.22 340	84.58 293	99.53 153	87.93 349	96.50 216	97.39 252

dmvs_re		94.48 260	94.18 240	95.37 305	97.68 238	90.11 335	98.54 187	97.08 329	94.56 183	94.42 246	97.24 275	84.25 298	97.76 348	91.02 307	92.83 289	98.24 225

PatchT		93.06 312	91.97 318	96.35 265	96.69 310	92.67 290	94.48 389	97.08 329	86.62 370	97.08 158	92.23 389	87.94 226	97.90 340	78.89 388	96.69 208	98.49 215

TDRefinement		91.06 331	89.68 336	95.21 309	85.35 403	91.49 310	98.51 192	97.07 331	91.47 310	88.83 363	97.84 226	77.31 356	99.09 211	92.79 263	77.98 391	95.04 368

LF4IMVS		93.14 311	92.79 304	94.20 340	95.88 346	88.67 359	97.66 290	97.07 331	93.81 217	91.71 336	97.65 244	77.96 351	98.81 253	91.47 296	91.92 298	95.12 365

testing11		95.00 222	94.28 233	97.16 194	97.96 218	93.36 275	98.09 245	97.06 333	94.94 169	95.33 220	96.15 342	76.89 361	99.40 173	95.77 169	96.30 223	98.72 194

Anonymous202405211		95.28 207	94.49 221	97.67 163	99.00 114	93.75 256	98.70 160	97.04 334	90.66 331	96.49 190	98.80 128	78.13 349	99.83 69	96.21 153	95.36 246	99.44 107

baseline1		95.84 173	95.12 192	98.01 135	98.49 164	95.98 147	98.73 151	97.03 335	95.37 142	96.22 198	98.19 197	89.96 174	99.16 196	94.60 206	87.48 352	98.90 179

MIMVSNet		93.26 306	92.21 315	96.41 261	97.73 235	93.13 283	95.65 376	97.03 335	91.27 322	94.04 266	96.06 344	75.33 368	97.19 362	86.56 355	96.23 232	98.92 178

MM		98.51 33	98.24 46	99.33 26	99.12 102	98.14 56	98.93 96	97.02 337	98.96 1	99.17 41	99.47 20	91.97 131	99.94 8	99.85 4	99.69 57	99.91 2

EPNet		97.28 107	96.87 111	98.51 88	94.98 366	96.14 143	98.90 100	97.02 337	98.28 10	95.99 205	99.11 84	91.36 145	99.89 47	96.98 118	99.19 120	99.50 91
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TR-MVS		94.94 231	94.20 237	97.17 193	97.75 231	94.14 245	97.59 296	97.02 337	92.28 290	95.75 212	97.64 246	83.88 308	98.96 229	89.77 324	96.15 234	98.40 218

JIA-IIPM		93.35 302	92.49 310	95.92 283	96.48 322	90.65 326	95.01 380	96.96 340	85.93 376	96.08 202	87.33 395	87.70 233	98.78 256	91.35 297	95.58 244	98.34 222

pmmvs-eth3d		90.36 337	89.05 342	94.32 339	91.10 390	92.12 296	97.63 295	96.95 341	88.86 361	84.91 383	93.13 384	78.32 346	96.74 369	88.70 340	81.81 378	94.09 379

tfpn200view9		95.32 206	94.62 215	97.43 177	98.94 122	94.98 204	98.68 163	96.93 342	95.33 143	96.55 186	96.53 329	84.23 300	99.56 145	88.11 345	96.29 224	97.76 238

thres400		95.38 199	94.62 215	97.65 167	98.94 122	94.98 204	98.68 163	96.93 342	95.33 143	96.55 186	96.53 329	84.23 300	99.56 145	88.11 345	96.29 224	98.40 218

thres100view900		95.38 199	94.70 212	97.41 179	98.98 119	94.92 208	98.87 114	96.90 344	95.38 140	96.61 182	96.88 312	84.29 296	99.56 145	88.11 345	96.29 224	97.76 238

thres600view7		95.49 190	94.77 208	97.67 163	98.98 119	95.02 200	98.85 119	96.90 344	95.38 140	96.63 180	96.90 311	84.29 296	99.59 140	88.65 342	96.33 220	98.40 218

test_method		79.03 360	78.17 362	81.63 382	86.06 402	54.40 413	82.75 401	96.89 346	39.54 405	80.98 390	95.57 360	58.37 395	94.73 390	84.74 371	78.61 388	95.75 355

CostFormer		94.95 229	94.73 211	95.60 297	97.28 271	89.06 351	97.53 299	96.89 346	89.66 350	96.82 173	96.72 321	86.05 261	98.95 234	95.53 178	96.13 235	98.79 186

new_pmnet		90.06 339	89.00 343	93.22 352	94.18 374	88.32 366	96.42 367	96.89 346	86.19 373	85.67 379	93.62 379	77.18 359	97.10 363	81.61 380	89.29 333	94.23 375

OpenMVS_ROB	86.42 20	89.00 346	87.43 354	93.69 344	93.08 383	89.42 346	97.91 264	96.89 346	78.58 391	85.86 377	94.69 369	69.48 383	98.29 313	77.13 391	93.29 283	93.36 386

tpm2		94.19 278	93.76 274	95.46 302	97.23 274	89.04 352	97.31 318	96.85 350	87.08 369	96.21 199	96.79 318	83.75 312	98.74 258	92.43 276	96.23 232	98.59 209

TransMVSNet (Re)		92.67 316	91.51 322	96.15 273	96.58 316	94.65 219	98.90 100	96.73 351	90.86 330	89.46 357	97.86 223	85.62 268	98.09 326	86.45 356	81.12 380	95.71 356

ambc				89.49 367	86.66 400	75.78 393	92.66 394	96.72 352		86.55 375	92.50 388	46.01 398	97.90 340	90.32 314	82.09 375	94.80 372

LCM-MVSNet		78.70 363	76.24 368	86.08 372	77.26 409	71.99 400	94.34 390	96.72 352	61.62 400	76.53 392	89.33 393	33.91 408	92.78 397	81.85 379	74.60 396	93.46 385

TinyColmap		92.31 320	91.53 321	94.65 330	96.92 295	89.75 338	96.92 343	96.68 354	90.45 336	89.62 354	97.85 225	76.06 366	98.81 253	86.74 354	92.51 292	95.41 360

Baseline_NR-MVSNet		94.35 267	93.81 268	95.96 282	96.20 332	94.05 247	98.61 176	96.67 355	91.44 312	93.85 276	97.60 249	88.57 208	98.14 321	94.39 212	86.93 360	95.68 357

SixPastTwentyTwo		93.34 303	92.86 302	94.75 326	95.67 351	89.41 347	98.75 144	96.67 355	93.89 211	90.15 351	98.25 193	80.87 327	98.27 315	90.90 308	90.64 313	96.57 315

testing222		94.12 285	93.03 299	97.37 184	98.02 211	94.66 218	97.94 261	96.65 357	94.63 181	95.78 211	95.76 351	71.49 380	98.92 236	91.17 300	95.88 239	98.52 213

test_fmvs3		87.17 352	87.06 355	87.50 370	91.21 389	75.66 394	99.05 65	96.61 358	92.79 271	88.85 362	92.78 385	43.72 400	93.49 393	93.95 228	84.56 370	93.34 387

EGC-MVSNET		75.22 367	69.54 370	92.28 360	94.81 370	89.58 343	97.64 292	96.50 359	1.82 410	5.57 411	95.74 352	68.21 384	96.26 378	73.80 395	91.71 300	90.99 390

APD_test1		88.22 349	88.01 349	88.86 368	95.98 342	74.66 398	97.21 324	96.44 360	83.96 385	86.66 374	97.90 219	60.95 394	97.84 346	82.73 376	90.23 318	94.09 379

WB-MVS		84.86 357	85.33 358	83.46 377	89.48 394	69.56 402	98.19 230	96.42 361	89.55 352	81.79 387	94.67 370	84.80 285	90.12 400	52.44 403	80.64 384	90.69 391

bld_raw_dy_0_64		95.72 178	94.98 199	97.97 137	98.29 184	95.68 169	99.04 68	96.34 362	96.51 88	95.86 210	98.44 166	78.73 341	99.44 169	97.58 92	93.99 263	98.78 189

test_f		86.07 356	85.39 357	88.10 369	89.28 395	75.57 395	97.73 285	96.33 363	89.41 356	85.35 381	91.56 391	43.31 402	95.53 384	91.32 298	84.23 372	93.21 388

SSC-MVS		84.27 358	84.71 361	82.96 381	89.19 396	68.83 403	98.08 246	96.30 364	89.04 360	81.37 389	94.47 371	84.60 292	89.89 401	49.80 405	79.52 386	90.15 392

iter_conf05_11		96.28 151	95.69 166	98.03 133	98.29 184	95.88 164	97.43 305	96.24 365	96.50 89	98.26 100	98.30 186	78.78 340	99.44 169	97.58 92	99.84 10	98.78 189

LFMVS		95.86 172	94.98 199	98.47 93	98.87 128	96.32 135	98.84 123	96.02 366	93.40 244	98.62 79	99.20 67	74.99 370	99.63 134	97.72 81	97.20 195	99.46 104

IB-MVS	91.98 17	93.27 305	91.97 318	97.19 191	97.47 256	93.41 270	97.09 335	95.99 367	93.32 247	92.47 324	95.73 354	78.06 350	99.53 153	94.59 208	82.98 374	98.62 206
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		94.08 289	93.51 287	95.80 289	95.53 356	92.89 289	97.38 309	95.97 368	95.11 156	92.51 323	96.66 323	87.71 231	96.94 366	87.03 353	93.67 270	97.57 248

WB-MVSnew		94.19 278	94.04 248	94.66 329	96.82 303	92.14 295	97.86 273	95.96 369	93.50 239	95.64 213	96.77 319	88.06 223	97.99 334	84.87 367	96.86 203	93.85 384

FPMVS		77.62 366	77.14 366	79.05 384	79.25 407	60.97 409	95.79 374	95.94 370	65.96 398	67.93 400	94.40 373	37.73 404	88.88 403	68.83 399	88.46 343	87.29 396

Patchmatch-RL test		91.49 325	90.85 326	93.41 347	91.37 388	84.40 380	92.81 393	95.93 371	91.87 301	87.25 369	94.87 368	88.99 197	96.53 375	92.54 272	82.00 376	99.30 125

tpm		94.13 283	93.80 269	95.12 312	96.50 320	87.91 371	97.44 303	95.89 372	92.62 275	96.37 196	96.30 335	84.13 303	98.30 310	93.24 248	91.66 302	99.14 152

LCM-MVSNet-Re		95.22 210	95.32 182	94.91 318	98.18 197	87.85 372	98.75 144	95.66 373	95.11 156	88.96 359	96.85 315	90.26 171	97.65 350	95.65 174	98.44 156	99.22 137

mvsany_test3		88.80 347	88.04 348	91.09 365	89.78 393	81.57 390	97.83 278	95.49 374	93.81 217	87.53 368	93.95 378	56.14 396	97.43 358	94.68 201	83.13 373	94.26 374

ET-MVSNet_ETH3D		94.13 283	92.98 300	97.58 170	98.22 190	96.20 139	97.31 318	95.37 375	94.53 185	79.56 391	97.63 248	86.51 251	97.53 356	96.91 122	90.74 312	99.02 167

MVS_0304		98.47 38	98.22 50	99.21 39	99.00 114	97.80 69	98.88 109	95.32 376	98.86 2	98.53 84	99.44 27	94.38 87	99.94 8	99.86 1	99.70 55	99.90 3

test-LLR		95.10 217	94.87 206	95.80 289	96.77 304	89.70 340	96.91 345	95.21 377	95.11 156	94.83 231	95.72 356	87.71 231	98.97 225	93.06 253	98.50 153	98.72 194

test-mter		94.08 289	93.51 287	95.80 289	96.77 304	89.70 340	96.91 345	95.21 377	92.89 267	94.83 231	95.72 356	77.69 352	98.97 225	93.06 253	98.50 153	98.72 194

PM-MVS		87.77 350	86.55 356	91.40 364	91.03 391	83.36 386	96.92 343	95.18 379	91.28 321	86.48 376	93.42 381	53.27 397	96.74 369	89.43 333	81.97 377	94.11 378

DeepMVS_CX				86.78 371	97.09 287	72.30 399		95.17 380	75.92 393	84.34 384	95.19 364	70.58 381	95.35 385	79.98 385	89.04 337	92.68 389

K. test v3		92.55 317	91.91 320	94.48 335	95.64 352	89.24 348	99.07 62	94.88 381	94.04 201	86.78 372	97.59 250	77.64 355	97.64 351	92.08 280	89.43 331	96.57 315

TESTMET0.1,1		94.18 281	93.69 279	95.63 295	96.92 295	89.12 350	96.91 345	94.78 382	93.17 254	94.88 228	96.45 332	78.52 344	98.92 236	93.09 252	98.50 153	98.85 181

pmmvs3		86.67 355	84.86 360	92.11 362	88.16 397	87.19 376	96.63 361	94.75 383	79.88 390	87.22 370	92.75 387	66.56 390	95.20 388	81.24 381	76.56 394	93.96 382

door								94.64 384

thisisatest0515		95.61 189	94.89 205	97.76 153	98.15 202	95.15 196	96.77 356	94.41 385	92.95 265	97.18 155	97.43 262	84.78 286	99.45 168	94.63 203	97.73 184	98.68 199

door-mid								94.37 386

tttt0517		96.07 159	95.51 172	97.78 150	98.41 168	94.84 211	99.28 26	94.33 387	94.26 196	97.64 142	98.64 146	84.05 304	99.47 166	95.34 181	97.60 188	99.03 166

DSMNet-mixed		92.52 319	92.58 309	92.33 359	94.15 375	82.65 387	98.30 216	94.26 388	89.08 359	92.65 317	95.73 354	85.01 281	95.76 383	86.24 357	97.76 182	98.59 209

thisisatest0530		96.01 161	95.36 178	97.97 137	98.38 169	95.52 176	98.88 109	94.19 389	94.04 201	97.64 142	98.31 184	83.82 311	99.46 167	95.29 185	97.70 185	98.93 177

MTMP							98.89 104	94.14 390

baseline2		95.11 216	94.52 220	96.87 216	96.65 313	93.56 262	98.27 221	94.10 391	93.45 242	92.02 334	97.43 262	87.45 239	99.19 194	93.88 231	97.41 193	97.87 236

PMVS	61.03 23	65.95 370	63.57 374	73.09 387	57.90 412	51.22 414	85.05 400	93.93 392	54.45 401	44.32 407	83.57 396	13.22 411	89.15 402	58.68 402	81.00 381	78.91 401
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS		94.30 270	93.89 263	95.53 298	97.83 226	88.95 355	97.52 301	93.25 393	94.44 191	96.63 180	97.07 289	78.70 343	99.28 184	91.99 285	97.56 190	98.36 221

testf1		79.02 361	77.70 363	82.99 379	88.10 398	66.90 404	94.67 386	93.11 394	71.08 396	74.02 394	93.41 382	34.15 406	93.25 394	72.25 396	78.50 389	88.82 394

APD_test2		79.02 361	77.70 363	82.99 379	88.10 398	66.90 404	94.67 386	93.11 394	71.08 396	74.02 394	93.41 382	34.15 406	93.25 394	72.25 396	78.50 389	88.82 394

PMMVS2		77.95 365	75.44 369	85.46 373	82.54 404	74.95 396	94.23 391	93.08 396	72.80 395	74.68 393	87.38 394	36.36 405	91.56 398	73.95 394	63.94 401	89.87 393

MVS-HIRNet		89.46 345	88.40 345	92.64 356	97.58 246	82.15 388	94.16 392	93.05 397	75.73 394	90.90 343	82.52 397	79.42 337	98.33 305	83.53 375	98.68 141	97.43 249

test1111		95.94 167	95.78 156	96.41 261	98.99 118	90.12 334	99.04 68	92.45 398	96.99 66	98.03 110	99.27 56	81.40 321	99.48 164	96.87 131	99.04 124	99.63 73

ECVR-MVS		95.95 165	95.71 163	96.65 229	99.02 111	90.86 320	99.03 72	91.80 399	96.96 67	98.10 104	99.26 57	81.31 322	99.51 157	96.90 125	99.04 124	99.59 79

EPMVS		94.99 224	94.48 222	96.52 250	97.22 275	91.75 304	97.23 322	91.66 400	94.11 198	97.28 151	96.81 317	85.70 267	98.84 248	93.04 255	97.28 194	98.97 172

dmvs_testset		87.64 351	88.93 344	83.79 376	95.25 363	63.36 407	97.20 325	91.17 401	93.07 259	85.64 380	95.98 349	85.30 278	91.52 399	69.42 398	87.33 355	96.49 331

lessismore_v0				94.45 338	94.93 368	88.44 364		91.03 402		86.77 373	97.64 246	76.23 365	98.42 289	90.31 315	85.64 369	96.51 328

test_vis1_rt		91.29 327	90.65 327	93.19 353	97.45 260	86.25 378	98.57 184	90.90 403	93.30 249	86.94 371	93.59 380	62.07 393	99.11 206	97.48 103	95.58 244	94.22 376

ANet_high		69.08 368	65.37 372	80.22 383	65.99 411	71.96 401	90.91 397	90.09 404	82.62 386	49.93 406	78.39 401	29.36 409	81.75 404	62.49 401	38.52 405	86.95 398

gg-mvs-nofinetune		92.21 321	90.58 329	97.13 197	96.75 307	95.09 198	95.85 373	89.40 405	85.43 380	94.50 239	81.98 398	80.80 329	98.40 303	92.16 278	98.33 163	97.88 235

GG-mvs-BLEND				96.59 239	96.34 328	94.98 204	96.51 365	88.58 406		93.10 306	94.34 376	80.34 333	98.05 329	89.53 330	96.99 199	96.74 293

E-PMN		64.94 371	64.25 373	67.02 388	82.28 405	59.36 411	91.83 396	85.63 407	52.69 402	60.22 403	77.28 402	41.06 403	80.12 406	46.15 406	41.14 403	61.57 404

EMVS		64.07 372	63.26 375	66.53 389	81.73 406	58.81 412	91.85 395	84.75 408	51.93 404	59.09 404	75.13 403	43.32 401	79.09 407	42.03 407	39.47 404	61.69 403

tmp_tt		68.90 369	66.97 371	74.68 386	50.78 413	59.95 410	87.13 398	83.47 409	38.80 406	62.21 402	96.23 338	64.70 391	76.91 408	88.91 339	30.49 406	87.19 397

test_vis3_rt		79.22 359	77.40 365	84.67 375	86.44 401	74.85 397	97.66 290	81.43 410	84.98 381	67.12 401	81.91 399	28.09 410	97.60 352	88.96 338	80.04 385	81.55 399

MVE	62.14 22	63.28 373	59.38 376	74.99 385	74.33 410	65.47 406	85.55 399	80.50 411	52.02 403	51.10 405	75.00 404	10.91 414	80.50 405	51.60 404	53.40 402	78.99 400
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2506		94.44 263	93.91 260	96.04 277	99.02 111	88.99 354	99.06 63	79.47 412	96.96 67	98.36 94	99.26 57	77.21 357	99.52 156	96.78 137	99.04 124	99.59 79

N_pmnet		87.12 354	87.77 352	85.17 374	95.46 359	61.92 408	97.37 311	70.66 413	85.83 377	88.73 364	96.04 345	85.33 276	97.76 348	80.02 383	90.48 314	95.84 353

wuyk23d		30.17 374	30.18 378	30.16 390	78.61 408	43.29 415	66.79 403	14.21 414	17.31 407	14.82 410	11.93 410	11.55 413	41.43 409	37.08 408	19.30 407	5.76 407

testmvs		21.48 376	24.95 379	11.09 392	14.89 414	6.47 417	96.56 363	9.87 415	7.55 408	17.93 408	39.02 406	9.43 415	5.90 411	16.56 410	12.72 408	20.91 406

test123		20.95 377	23.72 380	12.64 391	13.54 415	8.19 416	96.55 364	6.13 416	7.48 409	16.74 409	37.98 407	12.97 412	6.05 410	16.69 409	5.43 409	23.68 405

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

pcd_1.5k_mvsjas		7.88 379	10.50 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	94.51 81	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

n2								0.00 417

nn								0.00 417

ab-mvs-re		8.20 378	10.94 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	98.43 167	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						90.94 318								88.66 341

PC_three_1452									95.08 160	99.60 19	99.16 77	97.86 2	98.47 283	97.52 101	99.72 52	99.74 37

eth-test2					0.00 416

eth-test					0.00 416

OPU-MVS				99.37 20	99.24 87	99.05 14	99.02 75				99.16 77	97.81 3	99.37 177	97.24 110	99.73 49	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												89.45 183				99.20 139

sam_mvs												88.99 197

test_post1							96.68 360				30.43 409	87.85 230	98.69 261	92.59 268

test_post											31.83 408	88.83 204	98.91 238

patchmatchnet-post											95.10 366	89.42 184	98.89 242

gm-plane-assit					95.88 346	87.47 373			89.74 349		96.94 309		99.19 194	93.32 247

test9_res														96.39 148	99.57 81	99.69 56

agg_prior2														95.87 164	99.57 81	99.68 61

test_prior4						98.01 61	97.86 273

test_prior2							97.80 279		96.12 107	97.89 125	98.69 141	95.96 37		96.89 126	99.60 75

旧先验2							97.57 298		91.30 319	98.67 73			99.80 88	95.70 173

新几何2							97.64 292

原ACMM2							97.67 289

testdata2													99.89 47	91.65 294

segment_acmp												96.85 14

testdata1							97.32 317		96.34 99

plane_prior7					97.42 262	94.63 221

plane_prior6					97.35 269	94.61 224						87.09 242

plane_prior4											98.28 187

plane_prior3						94.61 224			97.02 64	95.34 217

plane_prior2							98.80 136		97.28 45

plane_prior1					97.37 268

plane_prior						94.60 226	98.44 200		96.74 78						94.22 252

HQP5-MVS						94.25 241

HQP-NCC					97.20 277		98.05 249		96.43 93	94.45 241

ACMP_Plane					97.20 277		98.05 249		96.43 93	94.45 241

BP-MVS														95.30 183

HQP4-MVS										94.45 241			98.96 229			96.87 281

HQP2-MVS												86.75 248

NP-MVS					97.28 271	94.51 229					97.73 235

MDTV_nov1_ep13_2view						84.26 381	96.89 350		90.97 328	97.90 124		89.89 175		93.91 230		99.18 148

ACMMP++_ref															92.97 286

ACMMP++															93.61 274

Test By Simon												94.64 78

High-resolution multi-view benchmark