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		97.12 114	96.80 111	98.08 128	99.30 68	94.56 226	98.05 248	99.71 1	93.57 235	97.09 154	98.91 117	88.17 216	99.89 47	96.87 128	99.56 86	99.81 17

HyFIR lowres test		96.90 122	96.49 128	98.14 119	99.33 59	95.56 171	97.38 307	99.65 2	92.34 284	97.61 142	98.20 196	89.29 185	99.10 206	96.97 116	97.60 187	99.77 27

MVS_111021_LR		98.34 53	98.23 48	98.67 74	99.27 78	96.90 101	97.95 258	99.58 3	97.14 58	98.44 91	99.01 102	95.03 73	99.62 137	97.91 66	99.75 41	99.50 91

MVS_111021_HR		98.47 38	98.34 35	98.88 66	99.22 89	97.32 81	97.91 263	99.58 3	97.20 53	98.33 97	99.00 103	95.99 36	99.64 131	98.05 59	99.76 37	99.69 56

PGM-MVS		98.49 35	98.23 48	99.27 34	99.72 12	98.08 56	98.99 81	99.49 5	95.43 135	99.03 47	99.32 49	95.56 48	99.94 8	96.80 133	99.77 31	99.78 21

ACMMP		98.23 57	97.95 63	99.09 52	99.74 7	97.62 71	99.03 71	99.41 6	95.98 107	97.60 143	99.36 42	94.45 85	99.93 25	97.14 110	98.85 135	99.70 53
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n		98.42 44	98.51 18	98.13 122	99.30 68	95.25 188	98.85 118	99.39 7	97.94 14	99.74 9	99.62 3	92.59 110	99.91 39	99.65 7	99.52 92	99.25 133

fmvsm_s_conf0.5_n_a		98.38 47	98.42 25	98.27 107	99.09 106	95.41 178	98.86 116	99.37 8	97.69 21	99.78 6	99.61 4	92.38 113	99.91 39	99.58 10	99.43 104	99.49 96

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

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

CSCG		97.85 71	97.74 68	98.20 116	99.67 25	95.16 192	99.22 35	99.32 11	93.04 259	97.02 160	98.92 116	95.36 57	99.91 39	97.43 101	99.64 68	99.52 86

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

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

patch_mono-2		98.36 50	98.87 6	96.82 217	99.53 36	90.68 323	98.64 169	99.29 14	97.88 15	99.19 40	99.52 11	96.80 15	99.97 1	99.11 16	99.86 1	99.82 16

PVSNet_BlendedMVS		96.73 128	96.60 123	97.12 195	99.25 81	95.35 183	98.26 221	99.26 15	94.28 192	97.94 119	97.46 258	92.74 108	99.81 81	96.88 125	93.32 279	96.20 343

PVSNet_Blended		97.38 101	97.12 97	98.14 119	99.25 81	95.35 183	97.28 318	99.26 15	93.13 255	97.94 119	98.21 195	92.74 108	99.81 81	96.88 125	99.40 109	99.27 129

fmvsm_s_conf0.1_n		98.18 59	98.21 51	98.11 126	98.54 158	95.24 189	98.87 113	99.24 17	97.50 31	99.70 13	99.67 1	91.33 145	99.89 47	99.47 12	99.54 89	99.21 138

UniMVSNet_NR-MVSNet		95.71 178	95.15 188	97.40 177	96.84 298	96.97 97	98.74 146	99.24 17	95.16 151	93.88 272	97.72 237	91.68 133	98.31 306	95.81 163	87.25 355	96.92 266

WR-MVS_H		95.05 218	94.46 222	96.81 218	96.86 297	95.82 163	99.24 30	99.24 17	93.87 211	92.53 319	96.84 314	90.37 165	98.24 314	93.24 246	87.93 346	96.38 336

SDMVSNet		96.85 124	96.42 129	98.14 119	99.30 68	96.38 130	99.21 38	99.23 20	95.92 110	95.96 204	98.76 136	85.88 263	99.44 167	97.93 64	95.59 239	98.60 203

FC-MVSNet-test		96.42 141	96.05 144	97.53 169	96.95 290	97.27 83	99.36 15	99.23 20	95.83 117	93.93 269	98.37 176	92.00 126	98.32 304	96.02 157	92.72 289	97.00 260

VPA-MVSNet		95.75 175	95.11 192	97.69 156	97.24 270	97.27 83	98.94 93	99.23 20	95.13 152	95.51 212	97.32 267	85.73 266	98.91 234	97.33 106	89.55 326	96.89 274

FIs		96.51 138	96.12 141	97.67 159	97.13 281	97.54 74	99.36 15	99.22 23	95.89 113	94.03 265	98.35 178	91.98 127	98.44 285	96.40 145	92.76 288	97.01 259

tfpnnormal		93.66 294	92.70 304	96.55 246	96.94 291	95.94 154	98.97 84	99.19 24	91.04 325	91.38 337	97.34 265	84.94 282	98.61 264	85.45 362	89.02 336	95.11 364

UniMVSNet (Re)		95.78 174	95.19 187	97.58 166	96.99 288	97.47 78	98.79 140	99.18 25	95.60 127	93.92 270	97.04 294	91.68 133	98.48 278	95.80 165	87.66 349	96.79 286

fmvsm_s_conf0.1_n_a		98.08 60	98.04 60	98.21 114	97.66 238	95.39 179	98.89 103	99.17 26	97.24 50	99.76 8	99.67 1	91.13 150	99.88 56	99.39 13	99.41 106	99.35 115

PVSNet_Blended_VisFu		97.70 78	97.46 83	98.44 95	99.27 78	95.91 159	98.63 172	99.16 27	94.48 187	97.67 136	98.88 119	92.80 107	99.91 39	97.11 111	99.12 121	99.50 91

test_fmvsmvis_n_1920		98.44 41	98.51 18	98.23 113	98.33 178	96.15 141	98.97 84	99.15 28	98.55 7	98.45 89	99.55 6	94.26 91	99.97 1	99.65 7	99.66 61	98.57 208

CHOSEN 280x420		97.18 111	97.18 96	97.20 186	98.81 134	93.27 275	95.78 373	99.15 28	95.25 147	96.79 173	98.11 202	92.29 116	99.07 209	98.56 29	99.85 5	99.25 133

D2MVS		95.18 211	95.08 193	95.48 298	97.10 283	92.07 296	98.30 215	99.13 30	94.02 201	92.90 307	96.73 318	89.48 179	98.73 255	94.48 209	93.60 272	95.65 356

PHI-MVS		98.34 53	98.06 58	99.18 42	99.15 100	98.12 55	99.04 68	99.09 31	93.32 245	98.83 64	99.10 86	96.54 21	99.83 69	97.70 84	99.76 37	99.59 79

sd_testset		96.17 153	95.76 157	97.42 174	99.30 68	94.34 235	98.82 126	99.08 32	95.92 110	95.96 204	98.76 136	82.83 315	99.32 177	95.56 174	95.59 239	98.60 203

UA-Net		97.96 64	97.62 71	98.98 59	98.86 129	97.47 78	98.89 103	99.08 32	96.67 80	98.72 72	99.54 8	93.15 104	99.81 81	94.87 193	98.83 136	99.65 69

PatchMatch-RL		96.59 133	96.03 146	98.27 107	99.31 64	96.51 122	97.91 263	99.06 34	93.72 222	96.92 165	98.06 205	88.50 211	99.65 129	91.77 289	99.00 127	98.66 199

3Dnovator	94.51 5	97.46 92	96.93 106	99.07 53	97.78 226	97.64 69	99.35 17	99.06 34	97.02 64	93.75 279	99.16 77	89.25 187	99.92 31	97.22 109	99.75 41	99.64 71

MSLP-MVS++		98.56 29	98.57 15	98.55 81	99.26 80	96.80 105	98.71 155	99.05 36	97.28 45	98.84 62	99.28 54	96.47 23	99.40 169	98.52 36	99.70 54	99.47 100

PS-CasMVS		94.67 242	93.99 253	96.71 222	96.68 308	95.26 187	99.13 52	99.03 37	93.68 228	92.33 325	97.95 216	85.35 274	98.10 322	93.59 238	88.16 345	96.79 286

TranMVSNet+NR-MVSNet		95.14 213	94.48 220	97.11 196	96.45 321	96.36 132	99.03 71	99.03 37	95.04 159	93.58 282	97.93 217	88.27 214	98.03 328	94.13 220	86.90 360	96.95 265

PEN-MVS		94.42 262	93.73 274	96.49 250	96.28 328	94.84 209	99.17 45	99.00 39	93.51 236	92.23 327	97.83 229	86.10 259	97.90 338	92.55 269	86.92 359	96.74 291

Vis-MVSNet		97.42 98	97.11 98	98.34 103	98.66 148	96.23 137	99.22 35	99.00 39	96.63 82	98.04 108	99.21 65	88.05 222	99.35 174	96.01 158	99.21 117	99.45 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DU-MVS		95.42 194	94.76 207	97.40 177	96.53 315	96.97 97	98.66 167	98.99 41	95.43 135	93.88 272	97.69 240	88.57 206	98.31 306	95.81 163	87.25 355	96.92 266

test_fmvsmconf0.1_n		98.58 23	98.44 24	98.99 57	97.73 232	97.15 93	98.84 122	98.97 42	98.75 3	99.43 27	99.54 8	93.29 102	99.93 25	99.64 9	99.79 25	99.89 5

VPNet		94.99 222	94.19 236	97.40 177	97.16 279	96.57 118	98.71 155	98.97 42	95.67 125	94.84 226	98.24 194	80.36 331	98.67 261	96.46 142	87.32 354	96.96 263

OpenMVS	93.04 13	95.83 172	95.00 196	98.32 104	97.18 278	97.32 81	99.21 38	98.97 42	89.96 342	91.14 339	99.05 97	86.64 249	99.92 31	93.38 242	99.47 99	97.73 237

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

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

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

CP-MVSNet		94.94 229	94.30 230	96.83 216	96.72 306	95.56 171	99.11 55	98.95 46	93.89 209	92.42 324	97.90 219	87.19 240	98.12 321	94.32 214	88.21 343	96.82 285

NR-MVSNet		94.98 224	94.16 239	97.44 172	96.53 315	97.22 90	98.74 146	98.95 46	94.96 164	89.25 356	97.69 240	89.32 184	98.18 316	94.59 206	87.40 352	96.92 266

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

APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 33	98.96 16	99.39 12	98.93 50	97.38 39	99.41 28	99.54 8	96.66 18	99.84 67	98.86 21	99.85 5	99.87 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
VNet		97.79 73	97.40 87	98.96 61	98.88 126	97.55 73	98.63 172	98.93 50	96.74 77	99.02 48	98.84 123	90.33 167	99.83 69	98.53 30	96.66 208	99.50 91

UGNet		96.78 127	96.30 135	98.19 118	98.24 184	95.89 161	98.88 108	98.93 50	97.39 38	96.81 171	97.84 226	82.60 316	99.90 45	96.53 140	99.49 96	98.79 184
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		97.39 100	96.98 105	98.61 77	98.60 154	96.61 114	98.22 223	98.93 50	93.97 205	98.01 114	98.48 162	91.98 127	99.85 63	96.45 143	98.15 167	99.39 112

QAPM		96.29 148	95.40 171	98.96 61	97.85 222	97.60 72	99.23 31	98.93 50	89.76 346	93.11 303	99.02 98	89.11 192	99.93 25	91.99 283	99.62 71	99.34 116

DPE-MVS		98.92 7	98.67 12	99.65 2	99.58 32	99.20 9	98.42 203	98.91 56	97.58 27	99.54 22	99.46 24	97.10 12	99.94 8	97.64 87	99.84 10	99.83 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
114514_t		96.93 120	96.27 136	98.92 63	99.50 41	97.63 70	98.85 118	98.90 57	84.80 380	97.77 126	99.11 84	92.84 106	99.66 128	94.85 194	99.77 31	99.47 100

LS3D		97.16 112	96.66 122	98.68 73	98.53 159	97.19 91	98.93 95	98.90 57	92.83 268	95.99 202	99.37 38	92.12 123	99.87 58	93.67 236	99.57 80	98.97 170

DELS-MVS		98.40 46	98.20 52	98.99 57	99.00 114	97.66 68	97.75 282	98.89 59	97.71 19	98.33 97	98.97 105	94.97 74	99.88 56	98.42 44	99.76 37	99.42 111
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DP-MVS Recon		97.86 69	97.46 83	99.06 54	99.53 36	98.35 41	98.33 208	98.89 59	92.62 273	98.05 106	98.94 113	95.34 58	99.65 129	96.04 156	99.42 105	99.19 143

AdaColmap		97.15 113	96.70 118	98.48 90	99.16 98	96.69 111	98.01 252	98.89 59	94.44 189	96.83 168	98.68 142	90.69 161	99.76 107	94.36 211	99.29 116	98.98 169

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

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

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

MSP-MVS		98.74 13	98.55 17	99.29 29	99.75 3	98.23 46	99.26 27	98.88 62	97.52 29	99.41 28	98.78 130	96.00 35	99.79 98	97.79 76	99.59 76	99.85 10
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
Anonymous20231211		94.10 285	93.26 294	96.61 234	99.11 104	94.28 236	99.01 76	98.88 62	86.43 370	92.81 309	97.57 252	81.66 320	98.68 260	94.83 195	89.02 336	96.88 275

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

X-MVStestdata		94.06 289	92.30 312	99.34 23	99.70 22	98.35 41	99.29 22	98.88 62	97.40 36	98.46 86	43.50 403	95.90 41	99.89 47	97.85 71	99.74 45	99.78 21

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

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

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

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

SteuartSystems-ACMMP		98.90 9	98.75 10	99.36 21	99.22 89	98.43 33	99.10 58	98.87 69	97.38 39	99.35 32	99.40 31	97.78 5	99.87 58	97.77 77	99.85 5	99.78 21
Skip Steuart: Steuart Systems R&D Blog.
DeepPCF-MVS	96.37 2	97.93 67	98.48 23	96.30 267	99.00 114	89.54 342	97.43 304	98.87 69	98.16 11	99.26 36	99.38 37	96.12 31	99.64 131	98.30 49	99.77 31	99.72 45

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

ZNCC-MVS		98.49 35	98.20 52	99.35 22	99.73 11	98.39 34	99.19 42	98.86 75	95.77 119	98.31 99	99.10 86	95.46 51	99.93 25	97.57 94	99.81 12	99.74 37

DTE-MVSNet		93.98 291	93.26 294	96.14 272	96.06 337	94.39 232	99.20 40	98.86 75	93.06 258	91.78 333	97.81 231	85.87 264	97.58 352	90.53 310	86.17 364	96.46 333

SD-MVS		98.64 16	98.68 11	98.53 85	99.33 59	98.36 40	98.90 99	98.85 78	97.28 45	99.72 12	99.39 32	96.63 20	97.60 350	98.17 52	99.85 5	99.64 71
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
test_prior				99.19 40	99.31 64	98.22 47		98.84 79					99.70 119			99.65 69

Anonymous20240529		95.10 215	94.22 234	97.75 150	99.01 113	94.26 238	98.87 113	98.83 80	85.79 376	96.64 176	98.97 105	78.73 340	99.85 63	96.27 147	94.89 244	99.12 154

9.14			98.06 58		99.47 47		98.71 155	98.82 81	94.36 191	99.16 44	99.29 53	96.05 33	99.81 81	97.00 114	99.71 53

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

GST-MVS		98.43 43	98.12 55	99.34 23	99.72 12	98.38 35	99.09 59	98.82 81	95.71 123	98.73 71	99.06 96	95.27 62	99.93 25	97.07 113	99.63 69	99.72 45

HPM-MVS_fast		98.38 47	98.13 54	99.12 50	99.75 3	97.86 62	99.44 11	98.82 81	94.46 188	98.94 53	99.20 67	95.16 68	99.74 111	97.58 91	99.85 5	99.77 27

APD-MVS		98.35 52	98.00 62	99.42 16	99.51 39	98.72 21	98.80 135	98.82 81	94.52 185	99.23 37	99.25 61	95.54 50	99.80 88	96.52 141	99.77 31	99.74 37
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SF-MVS		98.59 21	98.32 40	99.41 17	99.54 35	98.71 22	99.04 68	98.81 86	95.12 153	99.32 33	99.39 32	96.22 26	99.84 67	97.72 80	99.73 48	99.67 65

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

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

WR-MVS		95.15 212	94.46 222	97.22 185	96.67 309	96.45 124	98.21 224	98.81 86	94.15 195	93.16 299	97.69 240	87.51 234	98.30 308	95.29 183	88.62 340	96.90 273

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

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

CPTT-MVS		97.72 76	97.32 91	98.92 63	99.64 28	97.10 94	99.12 53	98.81 86	92.34 284	98.09 104	99.08 94	93.01 105	99.92 31	96.06 155	99.77 31	99.75 35

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

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

SMA-MVS		98.58 23	98.25 44	99.56 8	99.51 39	99.04 15	98.95 90	98.80 93	93.67 230	99.37 31	99.52 11	96.52 22	99.89 47	98.06 57	99.81 12	99.76 34
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
HPM-MVS		98.36 50	98.10 57	99.13 48	99.74 7	97.82 66	99.53 8	98.80 93	94.63 179	98.61 80	98.97 105	95.13 70	99.77 106	97.65 86	99.83 11	99.79 19
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPMNet		92.81 312	91.34 321	97.24 184	97.00 286	93.43 266	94.96 379	98.80 93	82.27 385	96.93 163	92.12 388	86.98 244	99.82 76	76.32 391	96.65 209	98.46 212

ZD-MVS					99.46 49	98.70 23		98.79 98	93.21 250	98.67 73	98.97 105	95.70 45	99.83 69	96.07 152	99.58 79

MP-MVS		98.33 55	98.01 61	99.28 32	99.75 3	98.18 49	99.22 35	98.79 98	96.13 102	97.92 122	99.23 62	94.54 80	99.94 8	96.74 136	99.78 29	99.73 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CANet		98.05 62	97.76 67	98.90 65	98.73 138	97.27 83	98.35 206	98.78 100	97.37 41	97.72 133	98.96 110	91.53 141	99.92 31	98.79 23	99.65 64	99.51 89

MP-MVS-pluss		98.31 56	97.92 64	99.49 12	99.72 12	98.88 18	98.43 201	98.78 100	94.10 197	97.69 135	99.42 29	95.25 64	99.92 31	98.09 56	99.80 19	99.67 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepC-MVS_fast	96.70 1	98.55 30	98.34 35	99.18 42	99.25 81	98.04 57	98.50 192	98.78 100	97.72 17	98.92 59	99.28 54	95.27 62	99.82 76	97.55 95	99.77 31	99.69 56
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		97.81 72	97.60 72	98.44 95	99.12 102	95.97 151	97.75 282	98.78 100	96.89 70	98.46 86	99.22 64	93.90 97	99.68 125	94.81 197	99.52 92	99.67 65

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

PLC	95.07 4	97.20 110	96.78 114	98.44 95	99.29 73	96.31 136	98.14 236	98.76 104	92.41 282	96.39 192	98.31 185	94.92 76	99.78 101	94.06 224	98.77 139	99.23 135
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
h-mvs33		96.17 153	95.62 168	97.81 144	99.03 110	94.45 228	98.64 169	98.75 106	97.48 32	98.67 73	98.72 139	89.76 174	99.86 62	97.95 62	81.59 377	99.11 155

DeepC-MVS	95.98 3	97.88 68	97.58 73	98.77 69	99.25 81	96.93 99	98.83 124	98.75 106	96.96 67	96.89 167	99.50 15	90.46 164	99.87 58	97.84 73	99.76 37	99.52 86
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MTGPA								98.74 108

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

ab-mvs		96.42 141	95.71 162	98.55 81	98.63 151	96.75 108	97.88 270	98.74 108	93.84 212	96.54 185	98.18 198	85.34 275	99.75 109	95.93 159	96.35 218	99.15 150

TEST9					99.31 64	98.50 29	97.92 261	98.73 111	92.63 272	97.74 130	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	97.92 261	98.73 111	92.98 261	97.74 130	98.68 142	96.20 28	99.80 88	96.59 137	99.57 80	99.68 61

test_8					99.29 73	98.44 31	97.89 269	98.72 113	92.98 261	97.70 134	98.66 145	96.20 28	99.80 88

agg_prior					99.30 68	98.38 35		98.72 113		97.57 144			99.81 81

无先验							97.58 296	98.72 113	91.38 311				99.87 58	93.36 244		99.60 77

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

WTY-MVS		97.37 103	96.92 107	98.72 71	98.86 129	96.89 103	98.31 213	98.71 116	95.26 146	97.67 136	98.56 156	92.21 120	99.78 101	95.89 160	96.85 203	99.48 98

3Dnovator+	94.38 6	97.43 97	96.78 114	99.38 18	97.83 223	98.52 28	99.37 14	98.71 116	97.09 62	92.99 306	99.13 82	89.36 183	99.89 47	96.97 116	99.57 80	99.71 49

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

EI-MVSNet-Vis-set		98.47 38	98.39 27	98.69 72	99.46 49	96.49 123	98.30 215	98.69 120	97.21 52	98.84 62	99.36 42	95.41 53	99.78 101	98.62 26	99.65 64	99.80 18

新几何1				99.16 45	99.34 57	98.01 59		98.69 120	90.06 341	98.13 101	98.95 112	94.60 79	99.89 47	91.97 285	99.47 99	99.59 79

API-MVS		97.41 99	97.25 93	97.91 137	98.70 143	96.80 105	98.82 126	98.69 120	94.53 183	98.11 102	98.28 187	94.50 84	99.57 142	94.12 221	99.49 96	97.37 250

EI-MVSNet-UG-set		98.41 45	98.34 35	98.61 77	99.45 52	96.32 134	98.28 218	98.68 123	97.17 55	98.74 69	99.37 38	95.25 64	99.79 98	98.57 27	99.54 89	99.73 42

testdata				98.26 110	99.20 92	95.36 181		98.68 123	91.89 298	98.60 81	99.10 86	94.44 86	99.82 76	94.27 216	99.44 103	99.58 83

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

PVSNet	91.96 18	96.35 146	96.15 140	96.96 207	99.17 94	92.05 297	96.08 366	98.68 123	93.69 226	97.75 129	97.80 232	88.86 201	99.69 124	94.26 217	99.01 126	99.15 150

MAR-MVS		96.91 121	96.40 131	98.45 93	98.69 145	96.90 101	98.66 167	98.68 123	92.40 283	97.07 157	97.96 215	91.54 140	99.75 109	93.68 234	98.92 129	98.69 194
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
原ACMM1				98.65 75	99.32 62	96.62 112		98.67 128	93.27 249	97.81 125	98.97 105	95.18 67	99.83 69	93.84 230	99.46 102	99.50 91

CDPH-MVS		97.94 66	97.49 80	99.28 32	99.47 47	98.44 31	97.91 263	98.67 128	92.57 276	98.77 67	98.85 122	95.93 38	99.72 113	95.56 174	99.69 56	99.68 61

UnsupCasMVSNet_eth		90.99 330	89.92 333	94.19 339	94.08 374	89.83 335	97.13 332	98.67 128	93.69 226	85.83 376	96.19 339	75.15 367	96.74 367	89.14 334	79.41 385	96.00 348

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

test222					99.23 88	97.17 92	97.40 305	98.66 131	88.68 360	98.05 106	98.96 110	94.14 93			99.53 91	99.61 75

test11								98.66 131

XXY-MVS		95.20 210	94.45 224	97.46 170	96.75 304	96.56 119	98.86 116	98.65 135	93.30 247	93.27 296	98.27 190	84.85 284	98.87 241	94.82 196	91.26 305	96.96 263

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

TAPA-MVS	93.98 7	95.35 201	94.56 216	97.74 151	99.13 101	94.83 211	98.33 208	98.64 136	86.62 368	96.29 194	98.61 148	94.00 96	99.29 179	80.00 382	99.41 106	99.09 157
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MSC_two_6792asdad				99.62 6	99.17 94	99.08 11		98.63 138					99.94 8	98.53 30	99.80 19	99.86 8

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

F-COLMAP		97.09 116	96.80 111	97.97 134	99.45 52	94.95 205	98.55 185	98.62 140	93.02 260	96.17 197	98.58 153	94.01 95	99.81 81	93.95 226	98.90 130	99.14 152

test_fmvsmconf0.01_n		97.86 69	97.54 78	98.83 67	95.48 356	96.83 104	98.95 90	98.60 141	98.58 6	98.93 57	99.55 6	88.57 206	99.91 39	99.54 11	99.61 72	99.77 27

EIA-MVS		97.75 74	97.58 73	98.27 107	98.38 168	96.44 125	99.01 76	98.60 141	95.88 115	97.26 149	97.53 255	94.97 74	99.33 176	97.38 104	99.20 118	99.05 163

PAPM_NR		97.46 92	97.11 98	98.50 87	99.50 41	96.41 129	98.63 172	98.60 141	95.18 150	97.06 158	98.06 205	94.26 91	99.57 142	93.80 232	98.87 134	99.52 86

cdsmvs_eth3d_5k		23.98 373	31.98 375	0.00 391	0.00 414	0.00 416	0.00 402	98.59 144	0.00 409	0.00 410	98.61 148	90.60 162	0.00 410	0.00 409	0.00 408	0.00 406

1314		96.25 152	95.73 158	97.79 145	97.13 281	95.55 173	98.19 229	98.59 144	93.47 239	92.03 331	97.82 230	91.33 145	99.49 158	94.62 203	98.44 155	98.32 220

CVMVSNet		95.43 193	96.04 145	93.57 343	97.93 218	83.62 381	98.12 239	98.59 144	95.68 124	96.56 181	99.02 98	87.51 234	97.51 355	93.56 240	97.44 190	99.60 77

OMC-MVS		97.55 90	97.34 90	98.20 116	99.33 59	95.92 158	98.28 218	98.59 144	95.52 131	97.97 116	99.10 86	93.28 103	99.49 158	95.09 188	98.88 132	99.19 143

LTVRE_ROB	92.95 15	94.60 245	93.90 259	96.68 226	97.41 262	94.42 230	98.52 187	98.59 144	91.69 304	91.21 338	98.35 178	84.87 283	99.04 213	91.06 302	93.44 277	96.60 309
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		96.71 129	96.84 110	96.31 266	99.11 104	89.74 337	99.05 65	98.58 149	98.08 12	99.87 1	99.37 38	78.48 343	99.93 25	99.29 14	99.69 56	99.27 129

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 84	98.58 149	97.62 24	99.45 25	99.46 24	97.42 9	99.94 8	98.47 38	99.81 12	99.69 56
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
UniMVSNet_ETH3D		94.24 273	93.33 291	96.97 206	97.19 277	93.38 271	98.74 146	98.57 151	91.21 323	93.81 276	98.58 153	72.85 377	98.77 253	95.05 190	93.93 261	98.77 189

PAPR		96.84 125	96.24 138	98.65 75	98.72 142	96.92 100	97.36 311	98.57 151	93.33 244	96.67 175	97.57 252	94.30 89	99.56 145	91.05 304	98.59 147	99.47 100

HQP_MVS		96.14 155	95.90 151	96.85 215	97.42 259	94.60 224	98.80 135	98.56 153	97.28 45	95.34 214	98.28 187	87.09 241	99.03 214	96.07 152	94.27 247	96.92 266

plane_prior5								98.56 153					99.03 214	96.07 152	94.27 247	96.92 266

ETV-MVS		97.96 64	97.81 65	98.40 100	98.42 165	97.27 83	98.73 150	98.55 155	96.84 71	98.38 93	97.44 261	95.39 54	99.35 174	97.62 88	98.89 131	98.58 207

mvs_tets		95.41 196	95.00 196	96.65 227	95.58 352	94.42 230	99.00 78	98.55 155	95.73 122	93.21 298	98.38 175	83.45 313	98.63 263	97.09 112	94.00 258	96.91 271

LPG-MVS_test		95.62 184	95.34 177	96.47 253	97.46 254	93.54 261	98.99 81	98.54 157	94.67 177	94.36 247	98.77 132	85.39 272	99.11 202	95.71 169	94.15 253	96.76 289

LGP-MVS_train				96.47 253	97.46 254	93.54 261		98.54 157	94.67 177	94.36 247	98.77 132	85.39 272	99.11 202	95.71 169	94.15 253	96.76 289

test_cas_vis1_n_1920		97.38 101	97.36 89	97.45 171	98.95 121	93.25 277	99.00 78	98.53 159	97.70 20	99.77 7	99.35 44	84.71 289	99.85 63	98.57 27	99.66 61	99.26 131

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

CNLPA		97.45 95	97.03 102	98.73 70	99.05 108	97.44 80	98.07 246	98.53 159	95.32 143	96.80 172	98.53 157	93.32 101	99.72 113	94.31 215	99.31 115	99.02 165

jajsoiax		95.45 192	95.03 195	96.73 221	95.42 360	94.63 219	99.14 49	98.52 162	95.74 120	93.22 297	98.36 177	83.87 309	98.65 262	96.95 118	94.04 256	96.91 271

XVG-OURS		96.55 137	96.41 130	96.99 203	98.75 137	93.76 252	97.50 301	98.52 162	95.67 125	96.83 168	99.30 52	88.95 200	99.53 153	95.88 161	96.26 227	97.69 239

xiu_mvs_v1_base_debu		97.60 84	97.56 75	97.72 152	98.35 171	95.98 146	97.86 272	98.51 164	97.13 59	99.01 49	98.40 172	91.56 137	99.80 88	98.53 30	98.68 140	97.37 250

xiu_mvs_v1_base		97.60 84	97.56 75	97.72 152	98.35 171	95.98 146	97.86 272	98.51 164	97.13 59	99.01 49	98.40 172	91.56 137	99.80 88	98.53 30	98.68 140	97.37 250

xiu_mvs_v1_base_debi		97.60 84	97.56 75	97.72 152	98.35 171	95.98 146	97.86 272	98.51 164	97.13 59	99.01 49	98.40 172	91.56 137	99.80 88	98.53 30	98.68 140	97.37 250

PS-MVSNAJ		97.73 75	97.77 66	97.62 164	98.68 146	95.58 170	97.34 313	98.51 164	97.29 44	98.66 77	97.88 222	94.51 81	99.90 45	97.87 70	99.17 120	97.39 248

cascas		94.63 244	93.86 263	96.93 209	96.91 294	94.27 237	96.00 370	98.51 164	85.55 377	94.54 235	96.23 336	84.20 302	98.87 241	95.80 165	96.98 201	97.66 240

CS-MVS-test		98.49 35	98.50 20	98.46 92	99.20 92	97.05 95	99.64 4	98.50 169	97.45 35	98.88 60	99.14 81	95.25 64	99.15 195	98.83 22	99.56 86	99.20 139

PS-MVSNAJss		96.43 140	96.26 137	96.92 212	95.84 346	95.08 197	99.16 46	98.50 169	95.87 116	93.84 275	98.34 182	94.51 81	98.61 264	96.88 125	93.45 276	97.06 256

MVS		94.67 242	93.54 284	98.08 128	96.88 296	96.56 119	98.19 229	98.50 169	78.05 390	92.69 314	98.02 208	91.07 154	99.63 134	90.09 315	98.36 161	98.04 228

XVG-OURS-SEG-HR		96.51 138	96.34 132	97.02 202	98.77 136	93.76 252	97.79 280	98.50 169	95.45 134	96.94 162	99.09 92	87.87 227	99.55 152	96.76 135	95.83 238	97.74 236

PVSNet_0	88.72 19	91.28 326	90.03 332	95.00 314	97.99 211	87.29 373	94.84 382	98.50 169	92.06 294	89.86 350	95.19 362	79.81 335	99.39 172	92.27 275	69.79 396	98.33 219

ACMH	92.88 16	94.55 249	93.95 255	96.34 264	97.63 240	93.26 276	98.81 134	98.49 174	93.43 241	89.74 351	98.53 157	81.91 318	99.08 208	93.69 233	93.30 280	96.70 298
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CS-MVS		98.44 41	98.49 21	98.31 105	99.08 107	96.73 109	99.67 3	98.47 175	97.17 55	98.94 53	99.10 86	95.73 44	99.13 198	98.71 24	99.49 96	99.09 157

xiu_mvs_v2_base		97.66 81	97.70 69	97.56 168	98.61 153	95.46 176	97.44 302	98.46 176	97.15 57	98.65 78	98.15 199	94.33 88	99.80 88	97.84 73	98.66 144	97.41 246

HQP3-MVS								98.46 176							94.18 251

HQP-MVS		95.72 177	95.40 171	96.69 225	97.20 274	94.25 239	98.05 248	98.46 176	96.43 89	94.45 239	97.73 235	86.75 247	98.96 225	95.30 181	94.18 251	96.86 280

CLD-MVS		95.62 184	95.34 177	96.46 256	97.52 251	93.75 254	97.27 319	98.46 176	95.53 130	94.42 244	98.00 211	86.21 257	98.97 221	96.25 150	94.37 245	96.66 304
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		94.54 250	94.14 241	95.75 290	96.55 314	91.65 305	98.11 241	98.44 180	94.96 164	94.22 255	97.90 219	79.18 339	99.11 202	94.05 225	93.85 262	96.48 331

casdiffmvs_mvg		97.72 76	97.48 82	98.44 95	98.42 165	96.59 117	98.92 97	98.44 180	96.20 99	97.76 127	99.20 67	91.66 135	99.23 185	98.27 51	98.41 158	99.49 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMP	93.49 10	95.34 202	94.98 198	96.43 258	97.67 236	93.48 265	98.73 150	98.44 180	94.94 167	92.53 319	98.53 157	84.50 295	99.14 197	95.48 178	94.00 258	96.66 304
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	93.85 9	95.69 181	95.38 175	96.61 234	97.61 241	93.84 250	98.91 98	98.44 180	95.25 147	94.28 251	98.47 164	86.04 262	99.12 200	95.50 177	93.95 260	96.87 277
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+		97.12 114	96.69 119	98.39 101	98.19 192	96.72 110	97.37 309	98.43 184	93.71 223	97.65 139	98.02 208	92.20 121	99.25 182	96.87 128	97.79 179	99.19 143

EC-MVSNet		98.21 58	98.11 56	98.49 89	98.34 176	97.26 87	99.61 5	98.43 184	96.78 74	98.87 61	98.84 123	93.72 98	99.01 219	98.91 20	99.50 94	99.19 143

anonymousdsp		95.42 194	94.91 201	96.94 208	95.10 363	95.90 160	99.14 49	98.41 186	93.75 217	93.16 299	97.46 258	87.50 236	98.41 295	95.63 173	94.03 257	96.50 328

PMMVS		96.60 132	96.33 133	97.41 175	97.90 220	93.93 247	97.35 312	98.41 186	92.84 267	97.76 127	97.45 260	91.10 153	99.20 189	96.26 148	97.91 174	99.11 155

MVSFormer		97.57 88	97.49 80	97.84 140	98.07 203	95.76 165	99.47 9	98.40 188	94.98 162	98.79 65	98.83 125	92.34 114	98.41 295	96.91 119	99.59 76	99.34 116

test_djsdf		96.00 160	95.69 165	96.93 209	95.72 348	95.49 175	99.47 9	98.40 188	94.98 162	94.58 234	97.86 223	89.16 190	98.41 295	96.91 119	94.12 255	96.88 275

OPM-MVS		95.69 181	95.33 179	96.76 220	96.16 334	94.63 219	98.43 201	98.39 190	96.64 81	95.02 223	98.78 130	85.15 279	99.05 210	95.21 187	94.20 250	96.60 309
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	97.67 136	97.40 264	92.26 117	99.49 158	98.28 50	96.28 226	99.08 161

DP-MVS		96.59 133	95.93 150	98.57 79	99.34 57	96.19 140	98.70 159	98.39 190	89.45 352	94.52 236	99.35 44	91.85 130	99.85 63	92.89 260	98.88 132	99.68 61

dcpmvs_2		98.08 60	98.59 14	96.56 241	99.57 33	90.34 330	99.15 47	98.38 193	96.82 73	99.29 34	99.49 17	95.78 43	99.57 142	98.94 19	99.86 1	99.77 27

diffmvs		97.58 87	97.40 87	98.13 122	98.32 181	95.81 164	98.06 247	98.37 194	96.20 99	98.74 69	98.89 118	91.31 147	99.25 182	98.16 53	98.52 150	99.34 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMH+	92.99 14	94.30 268	93.77 270	95.88 285	97.81 225	92.04 298	98.71 155	98.37 194	93.99 204	90.60 345	98.47 164	80.86 328	99.05 210	92.75 262	92.40 291	96.55 317

MSDG		95.93 166	95.30 183	97.83 141	98.90 124	95.36 181	96.83 353	98.37 194	91.32 316	94.43 243	98.73 138	90.27 168	99.60 139	90.05 318	98.82 137	98.52 209

DPM-MVS		97.55 90	96.99 104	99.23 38	99.04 109	98.55 27	97.17 328	98.35 197	94.85 171	97.93 121	98.58 153	95.07 72	99.71 118	92.60 264	99.34 113	99.43 109

CMPMVS	66.06 21	89.70 339	89.67 335	89.78 364	93.19 380	76.56 390	97.00 337	98.35 197	80.97 387	81.57 386	97.75 234	74.75 369	98.61 264	89.85 321	93.63 270	94.17 375
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		94.19 276	93.43 289	96.47 253	95.90 343	94.38 233	99.26 27	98.34 199	91.99 295	92.76 311	97.13 279	88.31 213	98.52 275	89.48 330	87.70 348	96.52 323

CDS-MVSNet		96.99 118	96.69 119	97.90 138	98.05 207	95.98 146	98.20 226	98.33 200	93.67 230	96.95 161	98.49 161	93.54 99	98.42 287	95.24 186	97.74 182	99.31 122
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
casdiffmvs		97.63 83	97.41 86	98.28 106	98.33 178	96.14 142	98.82 126	98.32 201	96.38 94	97.95 117	99.21 65	91.23 149	99.23 185	98.12 54	98.37 159	99.48 98
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		97.64 82	97.44 85	98.25 111	98.35 171	96.20 138	99.00 78	98.32 201	96.33 96	98.03 109	99.17 74	91.35 144	99.16 192	98.10 55	98.29 165	99.39 112

cl22		94.68 239	94.19 236	96.13 273	98.11 201	93.60 259	96.94 340	98.31 203	92.43 281	93.32 295	96.87 312	86.51 250	98.28 312	94.10 223	91.16 306	96.51 326

test_yl		97.22 107	96.78 114	98.54 83	98.73 138	96.60 115	98.45 196	98.31 203	94.70 173	98.02 111	98.42 170	90.80 158	99.70 119	96.81 131	96.79 205	99.34 116

DCV-MVSNet		97.22 107	96.78 114	98.54 83	98.73 138	96.60 115	98.45 196	98.31 203	94.70 173	98.02 111	98.42 170	90.80 158	99.70 119	96.81 131	96.79 205	99.34 116

nrg030		96.28 150	95.72 159	97.96 136	96.90 295	98.15 52	99.39 12	98.31 203	95.47 133	94.42 244	98.35 178	92.09 124	98.69 257	97.50 99	89.05 334	97.04 257

TAMVS		97.02 117	96.79 113	97.70 155	98.06 206	95.31 186	98.52 187	98.31 203	93.95 206	97.05 159	98.61 148	93.49 100	98.52 275	95.33 180	97.81 178	99.29 127

EPP-MVSNet		97.46 92	97.28 92	97.99 133	98.64 150	95.38 180	99.33 21	98.31 203	93.61 234	97.19 151	99.07 95	94.05 94	99.23 185	96.89 123	98.43 157	99.37 114

UnsupCasMVSNet_bld		87.17 350	85.12 357	93.31 348	91.94 384	88.77 355	94.92 381	98.30 209	84.30 382	82.30 384	90.04 390	63.96 390	97.25 359	85.85 359	74.47 395	93.93 381

Vis-MVSNet (Re-imp)		96.87 123	96.55 125	97.83 141	98.73 138	95.46 176	99.20 40	98.30 209	94.96 164	96.60 180	98.87 120	90.05 170	98.59 267	93.67 236	98.60 146	99.46 104

TSAR-MVS + GP.		98.38 47	98.24 46	98.81 68	99.22 89	97.25 88	98.11 241	98.29 211	97.19 54	98.99 52	99.02 98	96.22 26	99.67 126	98.52 36	98.56 149	99.51 89

MS-PatchMatch		93.84 293	93.63 279	94.46 335	96.18 331	89.45 343	97.76 281	98.27 212	92.23 289	92.13 329	97.49 256	79.50 336	98.69 257	89.75 323	99.38 111	95.25 360

EI-MVSNet		95.96 162	95.83 153	96.36 262	97.93 218	93.70 258	98.12 239	98.27 212	93.70 225	95.07 221	99.02 98	92.23 119	98.54 273	94.68 199	93.46 274	96.84 282

MVSTER		96.06 158	95.72 159	97.08 198	98.23 186	95.93 157	98.73 150	98.27 212	94.86 169	95.07 221	98.09 203	88.21 215	98.54 273	96.59 137	93.46 274	96.79 286

FMVSNet2		94.47 259	93.61 280	97.04 200	98.21 188	96.43 126	98.79 140	98.27 212	92.46 277	93.50 288	97.09 284	81.16 323	98.00 331	91.09 300	91.93 295	96.70 298

FMVSNet3		94.97 226	94.26 232	97.11 196	98.18 194	96.62 112	98.56 184	98.26 216	93.67 230	94.09 261	97.10 280	84.25 298	98.01 329	92.08 278	92.14 292	96.70 298

Fast-Effi-MVS+		96.28 150	95.70 164	98.03 131	98.29 183	95.97 151	98.58 178	98.25 217	91.74 301	95.29 218	97.23 274	91.03 155	99.15 195	92.90 258	97.96 173	98.97 170

PAPM		94.95 227	94.00 251	97.78 146	97.04 285	95.65 168	96.03 369	98.25 217	91.23 321	94.19 257	97.80 232	91.27 148	98.86 243	82.61 376	97.61 186	98.84 181

test_fmvs1_n		95.90 168	95.99 148	95.63 293	98.67 147	88.32 364	99.26 27	98.22 219	96.40 92	99.67 14	99.26 57	73.91 374	99.70 119	99.02 18	99.50 94	98.87 178

CANet_DTU		96.96 119	96.55 125	98.21 114	98.17 197	96.07 144	97.98 256	98.21 220	97.24 50	97.13 153	98.93 114	86.88 246	99.91 39	95.00 191	99.37 112	98.66 199

HY-MVS	93.96 8	96.82 126	96.23 139	98.57 79	98.46 163	97.00 96	98.14 236	98.21 220	93.95 206	96.72 174	97.99 212	91.58 136	99.76 107	94.51 208	96.54 213	98.95 173

test_fmvs1		96.42 141	96.67 121	95.66 292	98.82 133	88.53 360	98.80 135	98.20 222	96.39 93	99.64 17	99.20 67	80.35 332	99.67 126	99.04 17	99.57 80	98.78 187

PCF-MVS	93.45 11	94.68 239	93.43 289	98.42 99	98.62 152	96.77 107	95.48 377	98.20 222	84.63 381	93.34 294	98.32 184	88.55 209	99.81 81	84.80 368	98.96 128	98.68 195
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v8		94.47 259	93.77 270	96.57 240	96.36 324	94.83 211	99.05 65	98.19 224	91.92 297	93.16 299	96.97 302	88.82 203	98.48 278	91.69 291	87.79 347	96.39 335

v10		94.29 270	93.55 283	96.51 249	96.39 323	94.80 213	98.99 81	98.19 224	91.35 314	93.02 305	96.99 300	88.09 219	98.41 295	90.50 311	88.41 342	96.33 339

mvs_anonymous		96.70 130	96.53 127	97.18 189	98.19 192	93.78 251	98.31 213	98.19 224	94.01 202	94.47 238	98.27 190	92.08 125	98.46 282	97.39 103	97.91 174	99.31 122

AllTest		95.24 207	94.65 212	96.99 203	99.25 81	93.21 279	98.59 176	98.18 227	91.36 312	93.52 285	98.77 132	84.67 290	99.72 113	89.70 325	97.87 176	98.02 229

TestCases				96.99 203	99.25 81	93.21 279		98.18 227	91.36 312	93.52 285	98.77 132	84.67 290	99.72 113	89.70 325	97.87 176	98.02 229

GBi-Net		94.49 256	93.80 267	96.56 241	98.21 188	95.00 199	98.82 126	98.18 227	92.46 277	94.09 261	97.07 287	81.16 323	97.95 334	92.08 278	92.14 292	96.72 294

test1		94.49 256	93.80 267	96.56 241	98.21 188	95.00 199	98.82 126	98.18 227	92.46 277	94.09 261	97.07 287	81.16 323	97.95 334	92.08 278	92.14 292	96.72 294

FMVSNet1		93.19 307	92.07 314	96.56 241	97.54 248	95.00 199	98.82 126	98.18 227	90.38 336	92.27 326	97.07 287	73.68 375	97.95 334	89.36 332	91.30 303	96.72 294

v1192		94.32 267	93.58 281	96.53 247	96.10 335	94.45 228	98.50 192	98.17 232	91.54 307	94.19 257	97.06 291	86.95 245	98.43 286	90.14 314	89.57 324	96.70 298

v1240		94.06 289	93.29 293	96.34 264	96.03 339	93.90 248	98.44 199	98.17 232	91.18 324	94.13 260	97.01 299	86.05 260	98.42 287	89.13 335	89.50 328	96.70 298

v144192		94.39 264	93.70 276	96.48 252	96.06 337	94.35 234	98.58 178	98.16 234	91.45 309	94.33 249	97.02 297	87.50 236	98.45 283	91.08 301	89.11 333	96.63 306

Fast-Effi-MVS+-dtu		95.87 169	95.85 152	95.91 282	97.74 231	91.74 303	98.69 161	98.15 235	95.56 129	94.92 224	97.68 243	88.98 198	98.79 251	93.19 248	97.78 180	97.20 254

v1921920		94.20 275	93.47 287	96.40 261	95.98 340	94.08 244	98.52 187	98.15 235	91.33 315	94.25 253	97.20 277	86.41 254	98.42 287	90.04 319	89.39 330	96.69 303

v1144		94.59 247	93.92 256	96.60 236	96.21 329	94.78 215	98.59 176	98.14 237	91.86 300	94.21 256	97.02 297	87.97 223	98.41 295	91.72 290	89.57 324	96.61 308

IterMVS-LS		95.46 190	95.21 186	96.22 270	98.12 200	93.72 257	98.32 212	98.13 238	93.71 223	94.26 252	97.31 268	92.24 118	98.10 322	94.63 201	90.12 317	96.84 282
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GeoE		96.58 135	96.07 143	98.10 127	98.35 171	95.89 161	99.34 18	98.12 239	93.12 256	96.09 198	98.87 120	89.71 176	98.97 221	92.95 256	98.08 170	99.43 109

EU-MVSNet		93.66 294	94.14 241	92.25 359	95.96 342	83.38 383	98.52 187	98.12 239	94.69 175	92.61 316	98.13 201	87.36 239	96.39 375	91.82 287	90.00 319	96.98 261

IterMVS		94.09 286	93.85 264	94.80 323	97.99 211	90.35 329	97.18 326	98.12 239	93.68 228	92.46 323	97.34 265	84.05 304	97.41 357	92.51 271	91.33 302	96.62 307
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_vis1_n		95.47 189	95.13 189	96.49 250	97.77 227	90.41 328	99.27 26	98.11 242	96.58 83	99.66 15	99.18 73	67.00 387	99.62 137	99.21 15	99.40 109	99.44 107

IterMVS-SCA-FT		94.11 284	93.87 262	94.85 320	97.98 213	90.56 326	97.18 326	98.11 242	93.75 217	92.58 317	97.48 257	83.97 306	97.41 357	92.48 273	91.30 303	96.58 311

COLMAP_ROB	93.27 12	95.33 203	94.87 204	96.71 222	99.29 73	93.24 278	98.58 178	98.11 242	89.92 343	93.57 283	99.10 86	86.37 255	99.79 98	90.78 307	98.10 169	97.09 255
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
hse-mvs2		95.71 178	95.30 183	96.93 209	98.50 160	93.53 263	98.36 205	98.10 245	97.48 32	98.67 73	97.99 212	89.76 174	99.02 217	97.95 62	80.91 381	98.22 223

AUN-MVS		94.53 252	93.73 274	96.92 212	98.50 160	93.52 264	98.34 207	98.10 245	93.83 214	95.94 206	97.98 214	85.59 269	99.03 214	94.35 212	80.94 380	98.22 223

Effi-MVS+-dtu		96.29 148	96.56 124	95.51 297	97.89 221	90.22 331	98.80 135	98.10 245	96.57 85	96.45 190	96.66 321	90.81 157	98.91 234	95.72 168	97.99 171	97.40 247

1112_ss		96.63 131	96.00 147	98.50 87	98.56 155	96.37 131	98.18 234	98.10 245	92.92 264	94.84 226	98.43 168	92.14 122	99.58 141	94.35 212	96.51 214	99.56 85

V42		94.78 235	94.14 241	96.70 224	96.33 327	95.22 190	98.97 84	98.09 249	92.32 286	94.31 250	97.06 291	88.39 212	98.55 271	92.90 258	88.87 338	96.34 337

miper_enhance_ethall		95.10 215	94.75 208	96.12 274	97.53 250	93.73 256	96.61 360	98.08 250	92.20 292	93.89 271	96.65 323	92.44 112	98.30 308	94.21 218	91.16 306	96.34 337

v2v482		94.69 237	94.03 247	96.65 227	96.17 332	94.79 214	98.67 165	98.08 250	92.72 270	94.00 266	97.16 278	87.69 233	98.45 283	92.91 257	88.87 338	96.72 294

CL-MVSNet_self_test		90.11 336	89.14 339	93.02 352	91.86 385	88.23 366	96.51 363	98.07 252	90.49 331	90.49 346	94.41 370	84.75 287	95.34 384	80.79 380	74.95 393	95.50 357

miper_ehance_all_eth		95.01 219	94.69 211	95.97 279	97.70 234	93.31 274	97.02 336	98.07 252	92.23 289	93.51 287	96.96 304	91.85 130	98.15 318	93.68 234	91.16 306	96.44 334

eth_miper_zixun_eth		94.68 239	94.41 227	95.47 299	97.64 239	91.71 304	96.73 357	98.07 252	92.71 271	93.64 280	97.21 276	90.54 163	98.17 317	93.38 242	89.76 321	96.54 318

MVS_Test		97.28 105	97.00 103	98.13 122	98.33 178	95.97 151	98.74 146	98.07 252	94.27 193	98.44 91	98.07 204	92.48 111	99.26 181	96.43 144	98.19 166	99.16 149

Test_1112_low_res		96.34 147	95.66 167	98.36 102	98.56 155	95.94 154	97.71 285	98.07 252	92.10 293	94.79 230	97.29 269	91.75 132	99.56 145	94.17 219	96.50 215	99.58 83

iter_conf_final		96.42 141	96.12 141	97.34 181	98.46 163	96.55 121	99.08 61	98.06 257	96.03 106	95.63 210	98.46 166	87.72 229	98.59 267	97.84 73	93.80 264	96.87 277

alignmvs		97.56 89	97.07 101	99.01 56	98.66 148	98.37 39	98.83 124	98.06 257	96.74 77	98.00 115	97.65 244	90.80 158	99.48 162	98.37 46	96.56 212	99.19 143

RPSCF		94.87 231	95.40 171	93.26 349	98.89 125	82.06 387	98.33 208	98.06 257	90.30 338	96.56 181	99.26 57	87.09 241	99.49 158	93.82 231	96.32 220	98.24 221

miper_lstm_enhance		94.33 266	94.07 245	95.11 311	97.75 228	90.97 315	97.22 321	98.03 260	91.67 305	92.76 311	96.97 302	90.03 171	97.78 345	92.51 271	89.64 323	96.56 315

c3_l		94.79 234	94.43 226	95.89 284	97.75 228	93.12 283	97.16 330	98.03 260	92.23 289	93.46 290	97.05 293	91.39 142	98.01 329	93.58 239	89.21 332	96.53 320

pm-mvs1		93.94 292	93.06 296	96.59 237	96.49 318	95.16 192	98.95 90	98.03 260	92.32 286	91.08 340	97.84 226	84.54 294	98.41 295	92.16 276	86.13 366	96.19 344

iter_conf05		96.13 156	95.79 154	97.15 192	98.16 198	95.99 145	98.88 108	97.98 263	95.91 112	95.58 211	98.46 166	85.53 270	98.59 267	97.88 69	93.75 265	96.86 280

mvsmamba		96.57 136	96.32 134	97.32 182	96.60 311	96.43 126	99.54 7	97.98 263	96.49 86	95.20 219	98.64 146	90.82 156	98.55 271	97.97 61	93.65 269	96.98 261

v148		94.29 270	93.76 272	95.91 282	96.10 335	92.93 286	98.58 178	97.97 265	92.59 275	93.47 289	96.95 306	88.53 210	98.32 304	92.56 268	87.06 357	96.49 329

IS-MVSNet		97.22 107	96.88 108	98.25 111	98.85 131	96.36 132	99.19 42	97.97 265	95.39 137	97.23 150	98.99 104	91.11 152	98.93 231	94.60 204	98.59 147	99.47 100

cl____		94.51 254	94.01 250	96.02 276	97.58 243	93.40 270	97.05 334	97.96 267	91.73 303	92.76 311	97.08 286	89.06 194	98.13 320	92.61 263	90.29 315	96.52 323

KD-MVS_self_test		90.38 334	89.38 337	93.40 346	92.85 382	88.94 354	97.95 258	97.94 268	90.35 337	90.25 347	93.96 375	79.82 334	95.94 380	84.62 370	76.69 391	95.33 359

DIV-MVS_self_test		94.52 253	94.03 247	95.99 277	97.57 247	93.38 271	97.05 334	97.94 268	91.74 301	92.81 309	97.10 280	89.12 191	98.07 326	92.60 264	90.30 314	96.53 320

pmmvs6		91.77 321	90.63 326	95.17 309	94.69 371	91.24 312	98.67 165	97.92 270	86.14 372	89.62 352	97.56 254	75.79 365	98.34 302	90.75 308	84.56 368	95.94 350

RRT_MVS		95.98 161	95.78 155	96.56 241	96.48 319	94.22 241	99.57 6	97.92 270	95.89 113	93.95 268	98.70 140	89.27 186	98.42 287	97.23 108	93.02 283	97.04 257

jason		97.32 104	97.08 100	98.06 130	97.45 257	95.59 169	97.87 271	97.91 272	94.79 172	98.55 83	98.83 125	91.12 151	99.23 185	97.58 91	99.60 74	99.34 116
jason: jason.
ppachtmachnet_test		93.22 305	92.63 305	94.97 315	95.45 358	90.84 319	96.88 349	97.88 273	90.60 330	92.08 330	97.26 270	88.08 220	97.86 343	85.12 364	90.33 313	96.22 342

tpm cat1		93.36 299	92.80 301	95.07 313	97.58 243	87.97 368	96.76 355	97.86 274	82.17 386	93.53 284	96.04 343	86.13 258	99.13 198	89.24 333	95.87 237	98.10 227

tt0805		94.54 250	93.85 264	96.63 231	97.98 213	93.06 285	98.77 142	97.84 275	93.67 230	93.80 277	98.04 207	76.88 360	98.96 225	94.79 198	92.86 286	97.86 233

EG-PatchMatch MVS		91.13 328	90.12 331	94.17 340	94.73 370	89.00 351	98.13 238	97.81 276	89.22 356	85.32 380	96.46 329	67.71 385	98.42 287	87.89 348	93.82 263	95.08 365

BH-untuned		95.95 163	95.72 159	96.65 227	98.55 157	92.26 292	98.23 222	97.79 277	93.73 220	94.62 233	98.01 210	88.97 199	99.00 220	93.04 253	98.51 151	98.68 195

lupinMVS		97.44 96	97.22 95	98.12 125	98.07 203	95.76 165	97.68 287	97.76 278	94.50 186	98.79 65	98.61 148	92.34 114	99.30 178	97.58 91	99.59 76	99.31 122

VDDNet		95.36 200	94.53 217	97.86 139	98.10 202	95.13 195	98.85 118	97.75 279	90.46 333	98.36 94	99.39 32	73.27 376	99.64 131	97.98 60	96.58 211	98.81 183

ADS-MVSNet		95.00 220	94.45 224	96.63 231	98.00 209	91.91 299	96.04 367	97.74 280	90.15 339	96.47 188	96.64 324	87.89 225	98.96 225	90.08 316	97.06 196	99.02 165

tpmvs		94.60 245	94.36 229	95.33 305	97.46 254	88.60 358	96.88 349	97.68 281	91.29 318	93.80 277	96.42 331	88.58 205	99.24 184	91.06 302	96.04 233	98.17 225

pmmvs4		94.69 237	93.99 253	96.81 218	95.74 347	95.94 154	97.40 305	97.67 282	90.42 335	93.37 293	97.59 250	89.08 193	98.20 315	92.97 255	91.67 299	96.30 340

our_test_3		93.65 296	93.30 292	94.69 325	95.45 358	89.68 340	96.91 343	97.65 283	91.97 296	91.66 335	96.88 310	89.67 177	97.93 337	88.02 346	91.49 301	96.48 331

MVP-Stereo		94.28 272	93.92 256	95.35 304	94.95 365	92.60 289	97.97 257	97.65 283	91.61 306	90.68 344	97.09 284	86.32 256	98.42 287	89.70 325	99.34 113	95.02 367
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
KD-MVS_2432*1600		89.61 341	87.96 348	94.54 330	94.06 375	91.59 306	95.59 375	97.63 285	89.87 344	88.95 358	94.38 372	78.28 345	96.82 365	84.83 366	68.05 397	95.21 361

miper_refine_blended		89.61 341	87.96 348	94.54 330	94.06 375	91.59 306	95.59 375	97.63 285	89.87 344	88.95 358	94.38 372	78.28 345	96.82 365	84.83 366	68.05 397	95.21 361

SCA		95.46 190	95.13 189	96.46 256	97.67 236	91.29 311	97.33 314	97.60 287	94.68 176	96.92 165	97.10 280	83.97 306	98.89 238	92.59 266	98.32 164	99.20 139

testing91		94.98 224	94.25 233	97.20 186	97.94 216	93.41 268	98.00 254	97.58 288	94.99 161	95.45 213	96.04 343	77.20 356	99.42 168	94.97 192	96.02 234	98.78 187

FA-MVS(test-final)		96.41 145	95.94 149	97.82 143	98.21 188	95.20 191	97.80 278	97.58 288	93.21 250	97.36 147	97.70 238	89.47 180	99.56 145	94.12 221	97.99 171	98.71 193

GA-MVS		94.81 233	94.03 247	97.14 193	97.15 280	93.86 249	96.76 355	97.58 288	94.00 203	94.76 231	97.04 294	80.91 326	98.48 278	91.79 288	96.25 228	99.09 157

Anonymous20240521		91.18 327	90.44 328	93.42 344	93.70 378	88.47 361	98.94 93	97.56 291	88.46 361	89.56 354	95.08 365	77.15 358	96.97 363	83.92 371	89.55 326	94.82 369

test20.03		90.89 331	90.38 329	92.43 355	93.48 379	88.14 367	98.33 208	97.56 291	93.40 242	87.96 364	96.71 320	80.69 330	94.13 390	79.15 385	86.17 364	95.01 368

CR-MVSNet		94.76 236	94.15 240	96.59 237	97.00 286	93.43 266	94.96 379	97.56 291	92.46 277	96.93 163	96.24 334	88.15 217	97.88 342	87.38 349	96.65 209	98.46 212

Patchmtry		93.22 305	92.35 311	95.84 286	96.77 301	93.09 284	94.66 386	97.56 291	87.37 366	92.90 307	96.24 334	88.15 217	97.90 338	87.37 350	90.10 318	96.53 320

tpmrst		95.63 183	95.69 165	95.44 301	97.54 248	88.54 359	96.97 338	97.56 291	93.50 237	97.52 145	96.93 308	89.49 178	99.16 192	95.25 185	96.42 217	98.64 201

FMVSNet5		91.81 320	90.92 323	94.49 332	97.21 273	92.09 295	98.00 254	97.55 296	89.31 355	90.86 342	95.61 357	74.48 371	95.32 385	85.57 360	89.70 322	96.07 347

testgi		93.06 310	92.45 310	94.88 319	96.43 322	89.90 334	98.75 143	97.54 297	95.60 127	91.63 336	97.91 218	74.46 372	97.02 362	86.10 356	93.67 267	97.72 238

mvsany_test1		97.69 79	97.70 69	97.66 162	98.24 184	94.18 242	97.53 298	97.53 298	95.52 131	99.66 15	99.51 13	94.30 89	99.56 145	98.38 45	98.62 145	99.23 135

PatchmatchNet		95.71 178	95.52 169	96.29 268	97.58 243	90.72 322	96.84 352	97.52 299	94.06 198	97.08 155	96.96 304	89.24 188	98.90 237	92.03 282	98.37 159	99.26 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDA-MVSNet-bldmvs		89.97 338	88.35 344	94.83 322	95.21 362	91.34 309	97.64 291	97.51 300	88.36 362	71.17 397	96.13 341	79.22 338	96.63 372	83.65 372	86.27 363	96.52 323

USDC		93.33 302	92.71 303	95.21 307	96.83 299	90.83 320	96.91 343	97.50 301	93.84 212	90.72 343	98.14 200	77.69 350	98.82 248	89.51 329	93.21 282	95.97 349

ITE_SJBPF				95.44 301	97.42 259	91.32 310		97.50 301	95.09 157	93.59 281	98.35 178	81.70 319	98.88 240	89.71 324	93.39 278	96.12 345

Patchmatch-test		94.42 262	93.68 278	96.63 231	97.60 242	91.76 301	94.83 383	97.49 303	89.45 352	94.14 259	97.10 280	88.99 195	98.83 247	85.37 363	98.13 168	99.29 127

Syy-MVS		92.55 315	92.61 306	92.38 356	97.39 263	83.41 382	97.91 263	97.46 304	93.16 253	93.42 291	95.37 360	84.75 287	96.12 377	77.00 390	96.99 198	97.60 242

myMVS_eth3d		92.73 313	92.01 315	94.89 318	97.39 263	90.94 316	97.91 263	97.46 304	93.16 253	93.42 291	95.37 360	68.09 383	96.12 377	88.34 342	96.99 198	97.60 242

YYNet1		90.70 333	89.39 336	94.62 329	94.79 369	90.65 324	97.20 323	97.46 304	87.54 365	72.54 395	95.74 350	86.51 250	96.66 371	86.00 357	86.76 362	96.54 318

MDA-MVSNet_test_wron		90.71 332	89.38 337	94.68 326	94.83 367	90.78 321	97.19 325	97.46 304	87.60 364	72.41 396	95.72 354	86.51 250	96.71 370	85.92 358	86.80 361	96.56 315

BH-RMVSNet		95.92 167	95.32 180	97.69 156	98.32 181	94.64 218	98.19 229	97.45 308	94.56 181	96.03 200	98.61 148	85.02 280	99.12 200	90.68 309	99.06 122	99.30 125

MIMVSNet1		89.67 340	88.28 345	93.82 341	92.81 383	91.08 314	98.01 252	97.45 308	87.95 363	87.90 365	95.87 348	67.63 386	94.56 389	78.73 387	88.18 344	95.83 352

OurMVSNet-221017-0		94.21 274	94.00 251	94.85 320	95.60 351	89.22 347	98.89 103	97.43 310	95.29 144	92.18 328	98.52 160	82.86 314	98.59 267	93.46 241	91.76 297	96.74 291

BH-w/o		95.38 197	95.08 193	96.26 269	98.34 176	91.79 300	97.70 286	97.43 310	92.87 266	94.24 254	97.22 275	88.66 204	98.84 244	91.55 293	97.70 184	98.16 226

VDD-MVS		95.82 173	95.23 185	97.61 165	98.84 132	93.98 246	98.68 162	97.40 312	95.02 160	97.95 117	99.34 48	74.37 373	99.78 101	98.64 25	96.80 204	99.08 161

Gipuma		78.40 362	76.75 365	83.38 376	95.54 353	80.43 389	79.42 400	97.40 312	64.67 397	73.46 394	80.82 398	45.65 397	93.14 394	66.32 398	87.43 351	76.56 400
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FE-MVS		95.62 184	94.90 202	97.78 146	98.37 170	94.92 206	97.17 328	97.38 314	90.95 327	97.73 132	97.70 238	85.32 277	99.63 134	91.18 297	98.33 162	98.79 184

bld_raw_dy_0_64		95.74 176	95.31 182	97.03 201	96.35 325	95.76 165	99.12 53	97.37 315	95.97 108	94.70 232	98.48 162	85.80 265	98.49 277	96.55 139	93.48 273	96.84 282

new-patchmatchnet		88.50 346	87.45 351	91.67 361	90.31 390	85.89 377	97.16 330	97.33 316	89.47 351	83.63 383	92.77 384	76.38 361	95.06 387	82.70 375	77.29 390	94.06 379

ADS-MVSNet2		94.58 248	94.40 228	95.11 311	98.00 209	88.74 356	96.04 367	97.30 317	90.15 339	96.47 188	96.64 324	87.89 225	97.56 353	90.08 316	97.06 196	99.02 165

MDTV_nov1_ep13			95.40 171		97.48 252	88.34 363	96.85 351	97.29 318	93.74 219	97.48 146	97.26 270	89.18 189	99.05 210	91.92 286	97.43 191

pmmvs5		93.65 296	92.97 299	95.68 291	95.49 355	92.37 290	98.20 226	97.28 319	89.66 348	92.58 317	97.26 270	82.14 317	98.09 324	93.18 249	90.95 309	96.58 311

EPNet_dtu		95.21 209	94.95 200	95.99 277	96.17 332	90.45 327	98.16 235	97.27 320	96.77 75	93.14 302	98.33 183	90.34 166	98.42 287	85.57 360	98.81 138	99.09 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20231206		91.66 322	91.10 322	93.33 347	94.02 377	87.35 372	98.58 178	97.26 321	90.48 332	90.16 348	96.31 332	83.83 310	96.53 373	79.36 384	89.90 320	96.12 345

test_fmvs2		93.43 298	93.58 281	92.95 353	96.97 289	83.91 380	99.19 42	97.24 322	95.74 120	95.20 219	98.27 190	69.65 380	98.72 256	96.26 148	93.73 266	96.24 341

test_0402		91.32 324	90.27 330	94.48 333	96.60 311	91.12 313	98.50 192	97.22 323	86.10 373	88.30 363	96.98 301	77.65 352	97.99 332	78.13 388	92.94 285	94.34 371

dp		94.15 280	93.90 259	94.90 317	97.31 267	86.82 375	96.97 338	97.19 324	91.22 322	96.02 201	96.61 326	85.51 271	99.02 217	90.00 320	94.30 246	98.85 179

testing99		94.83 232	94.08 244	97.07 199	97.94 216	93.13 281	98.10 243	97.17 325	94.86 169	95.34 214	96.00 346	76.31 362	99.40 169	95.08 189	95.90 235	98.68 195

testing3		93.19 307	92.48 309	95.30 306	98.07 203	92.27 291	98.64 169	97.17 325	93.94 208	93.98 267	97.04 294	67.97 384	96.01 379	88.40 341	97.14 195	97.63 241

ETVMVS		94.50 255	93.44 288	97.68 158	98.18 194	95.35 183	98.19 229	97.11 327	93.73 220	96.40 191	95.39 359	74.53 370	98.84 244	91.10 299	96.31 221	98.84 181

thres200		95.25 206	94.57 215	97.28 183	98.81 134	94.92 206	98.20 226	97.11 327	95.24 149	96.54 185	96.22 338	84.58 293	99.53 153	87.93 347	96.50 215	97.39 248

dmvs_re		94.48 258	94.18 238	95.37 303	97.68 235	90.11 333	98.54 186	97.08 329	94.56 181	94.42 244	97.24 273	84.25 298	97.76 346	91.02 305	92.83 287	98.24 221

PatchT		93.06 310	91.97 316	96.35 263	96.69 307	92.67 288	94.48 387	97.08 329	86.62 368	97.08 155	92.23 387	87.94 224	97.90 338	78.89 386	96.69 207	98.49 211

TDRefinement		91.06 329	89.68 334	95.21 307	85.35 401	91.49 308	98.51 191	97.07 331	91.47 308	88.83 361	97.84 226	77.31 354	99.09 207	92.79 261	77.98 389	95.04 366

LF4IMVS		93.14 309	92.79 302	94.20 338	95.88 344	88.67 357	97.66 289	97.07 331	93.81 215	91.71 334	97.65 244	77.96 349	98.81 249	91.47 294	91.92 296	95.12 363

testing11		95.00 220	94.28 231	97.16 191	97.96 215	93.36 273	98.09 244	97.06 333	94.94 167	95.33 217	96.15 340	76.89 359	99.40 169	95.77 167	96.30 222	98.72 190

Anonymous202405211		95.28 205	94.49 219	97.67 159	99.00 114	93.75 254	98.70 159	97.04 334	90.66 329	96.49 187	98.80 128	78.13 347	99.83 69	96.21 151	95.36 243	99.44 107

baseline1		95.84 171	95.12 191	98.01 132	98.49 162	95.98 146	98.73 150	97.03 335	95.37 140	96.22 195	98.19 197	89.96 172	99.16 192	94.60 204	87.48 350	98.90 177

MIMVSNet		93.26 304	92.21 313	96.41 259	97.73 232	93.13 281	95.65 374	97.03 335	91.27 320	94.04 264	96.06 342	75.33 366	97.19 360	86.56 353	96.23 229	98.92 176

MM		98.51 33	98.24 46	99.33 26	99.12 102	98.14 54	98.93 95	97.02 337	98.96 1	99.17 41	99.47 20	91.97 129	99.94 8	99.85 4	99.69 56	99.91 2

EPNet		97.28 105	96.87 109	98.51 86	94.98 364	96.14 142	98.90 99	97.02 337	98.28 10	95.99 202	99.11 84	91.36 143	99.89 47	96.98 115	99.19 119	99.50 91
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TR-MVS		94.94 229	94.20 235	97.17 190	97.75 228	94.14 243	97.59 295	97.02 337	92.28 288	95.75 208	97.64 246	83.88 308	98.96 225	89.77 322	96.15 231	98.40 214

JIA-IIPM		93.35 300	92.49 308	95.92 281	96.48 319	90.65 324	95.01 378	96.96 340	85.93 374	96.08 199	87.33 393	87.70 232	98.78 252	91.35 295	95.58 241	98.34 218

pmmvs-eth3d		90.36 335	89.05 340	94.32 337	91.10 388	92.12 294	97.63 294	96.95 341	88.86 359	84.91 381	93.13 382	78.32 344	96.74 367	88.70 338	81.81 376	94.09 377

tfpn200view9		95.32 204	94.62 213	97.43 173	98.94 122	94.98 202	98.68 162	96.93 342	95.33 141	96.55 183	96.53 327	84.23 300	99.56 145	88.11 343	96.29 223	97.76 234

thres400		95.38 197	94.62 213	97.65 163	98.94 122	94.98 202	98.68 162	96.93 342	95.33 141	96.55 183	96.53 327	84.23 300	99.56 145	88.11 343	96.29 223	98.40 214

thres100view900		95.38 197	94.70 210	97.41 175	98.98 119	94.92 206	98.87 113	96.90 344	95.38 138	96.61 179	96.88 310	84.29 296	99.56 145	88.11 343	96.29 223	97.76 234

thres600view7		95.49 188	94.77 206	97.67 159	98.98 119	95.02 198	98.85 118	96.90 344	95.38 138	96.63 177	96.90 309	84.29 296	99.59 140	88.65 340	96.33 219	98.40 214

test_method		79.03 358	78.17 360	81.63 380	86.06 400	54.40 411	82.75 399	96.89 346	39.54 403	80.98 388	95.57 358	58.37 393	94.73 388	84.74 369	78.61 386	95.75 353

CostFormer		94.95 227	94.73 209	95.60 295	97.28 268	89.06 349	97.53 298	96.89 346	89.66 348	96.82 170	96.72 319	86.05 260	98.95 230	95.53 176	96.13 232	98.79 184

new_pmnet		90.06 337	89.00 341	93.22 350	94.18 372	88.32 364	96.42 365	96.89 346	86.19 371	85.67 377	93.62 377	77.18 357	97.10 361	81.61 378	89.29 331	94.23 373

OpenMVS_ROB	86.42 20	89.00 344	87.43 352	93.69 342	93.08 381	89.42 344	97.91 263	96.89 346	78.58 389	85.86 375	94.69 367	69.48 381	98.29 311	77.13 389	93.29 281	93.36 384

tpm2		94.19 276	93.76 272	95.46 300	97.23 271	89.04 350	97.31 316	96.85 350	87.08 367	96.21 196	96.79 316	83.75 312	98.74 254	92.43 274	96.23 229	98.59 205

TransMVSNet (Re)		92.67 314	91.51 320	96.15 271	96.58 313	94.65 217	98.90 99	96.73 351	90.86 328	89.46 355	97.86 223	85.62 268	98.09 324	86.45 354	81.12 378	95.71 354

ambc				89.49 365	86.66 398	75.78 391	92.66 392	96.72 352		86.55 373	92.50 386	46.01 396	97.90 338	90.32 312	82.09 373	94.80 370

LCM-MVSNet		78.70 361	76.24 366	86.08 370	77.26 407	71.99 398	94.34 388	96.72 352	61.62 398	76.53 390	89.33 391	33.91 406	92.78 395	81.85 377	74.60 394	93.46 383

TinyColmap		92.31 318	91.53 319	94.65 328	96.92 292	89.75 336	96.92 341	96.68 354	90.45 334	89.62 352	97.85 225	76.06 364	98.81 249	86.74 352	92.51 290	95.41 358

Baseline_NR-MVSNet		94.35 265	93.81 266	95.96 280	96.20 330	94.05 245	98.61 175	96.67 355	91.44 310	93.85 274	97.60 249	88.57 206	98.14 319	94.39 210	86.93 358	95.68 355

SixPastTwentyTwo		93.34 301	92.86 300	94.75 324	95.67 349	89.41 345	98.75 143	96.67 355	93.89 209	90.15 349	98.25 193	80.87 327	98.27 313	90.90 306	90.64 311	96.57 313

testing222		94.12 283	93.03 297	97.37 180	98.02 208	94.66 216	97.94 260	96.65 357	94.63 179	95.78 207	95.76 349	71.49 378	98.92 232	91.17 298	95.88 236	98.52 209

test_fmvs3		87.17 350	87.06 353	87.50 368	91.21 387	75.66 392	99.05 65	96.61 358	92.79 269	88.85 360	92.78 383	43.72 398	93.49 391	93.95 226	84.56 368	93.34 385

EGC-MVSNET		75.22 365	69.54 368	92.28 358	94.81 368	89.58 341	97.64 291	96.50 359	1.82 408	5.57 409	95.74 350	68.21 382	96.26 376	73.80 393	91.71 298	90.99 388

APD_test1		88.22 347	88.01 347	88.86 366	95.98 340	74.66 396	97.21 322	96.44 360	83.96 383	86.66 372	97.90 219	60.95 392	97.84 344	82.73 374	90.23 316	94.09 377

WB-MVS		84.86 355	85.33 356	83.46 375	89.48 392	69.56 400	98.19 229	96.42 361	89.55 350	81.79 385	94.67 368	84.80 285	90.12 398	52.44 401	80.64 382	90.69 389

test_f		86.07 354	85.39 355	88.10 367	89.28 393	75.57 393	97.73 284	96.33 362	89.41 354	85.35 379	91.56 389	43.31 400	95.53 382	91.32 296	84.23 370	93.21 386

SSC-MVS		84.27 356	84.71 359	82.96 379	89.19 394	68.83 401	98.08 245	96.30 363	89.04 358	81.37 387	94.47 369	84.60 292	89.89 399	49.80 403	79.52 384	90.15 390

LFMVS		95.86 170	94.98 198	98.47 91	98.87 128	96.32 134	98.84 122	96.02 364	93.40 242	98.62 79	99.20 67	74.99 368	99.63 134	97.72 80	97.20 194	99.46 104

IB-MVS	91.98 17	93.27 303	91.97 316	97.19 188	97.47 253	93.41 268	97.09 333	95.99 365	93.32 245	92.47 322	95.73 352	78.06 348	99.53 153	94.59 206	82.98 372	98.62 202
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		94.08 287	93.51 285	95.80 287	95.53 354	92.89 287	97.38 307	95.97 366	95.11 154	92.51 321	96.66 321	87.71 230	96.94 364	87.03 351	93.67 267	97.57 244

WB-MVSnew		94.19 276	94.04 246	94.66 327	96.82 300	92.14 293	97.86 272	95.96 367	93.50 237	95.64 209	96.77 317	88.06 221	97.99 332	84.87 365	96.86 202	93.85 382

FPMVS		77.62 364	77.14 364	79.05 382	79.25 405	60.97 407	95.79 372	95.94 368	65.96 396	67.93 398	94.40 371	37.73 402	88.88 401	68.83 397	88.46 341	87.29 394

Patchmatch-RL test		91.49 323	90.85 324	93.41 345	91.37 386	84.40 378	92.81 391	95.93 369	91.87 299	87.25 367	94.87 366	88.99 195	96.53 373	92.54 270	82.00 374	99.30 125

tpm		94.13 281	93.80 267	95.12 310	96.50 317	87.91 369	97.44 302	95.89 370	92.62 273	96.37 193	96.30 333	84.13 303	98.30 308	93.24 246	91.66 300	99.14 152

LCM-MVSNet-Re		95.22 208	95.32 180	94.91 316	98.18 194	87.85 370	98.75 143	95.66 371	95.11 154	88.96 357	96.85 313	90.26 169	97.65 348	95.65 172	98.44 155	99.22 137

mvsany_test3		88.80 345	88.04 346	91.09 363	89.78 391	81.57 388	97.83 277	95.49 372	93.81 215	87.53 366	93.95 376	56.14 394	97.43 356	94.68 199	83.13 371	94.26 372

ET-MVSNet_ETH3D		94.13 281	92.98 298	97.58 166	98.22 187	96.20 138	97.31 316	95.37 373	94.53 183	79.56 389	97.63 248	86.51 250	97.53 354	96.91 119	90.74 310	99.02 165

MVS_0304		98.47 38	98.22 50	99.21 39	99.00 114	97.80 67	98.88 108	95.32 374	98.86 2	98.53 84	99.44 27	94.38 87	99.94 8	99.86 1	99.70 54	99.90 3

test-LLR		95.10 215	94.87 204	95.80 287	96.77 301	89.70 338	96.91 343	95.21 375	95.11 154	94.83 228	95.72 354	87.71 230	98.97 221	93.06 251	98.50 152	98.72 190

test-mter		94.08 287	93.51 285	95.80 287	96.77 301	89.70 338	96.91 343	95.21 375	92.89 265	94.83 228	95.72 354	77.69 350	98.97 221	93.06 251	98.50 152	98.72 190

PM-MVS		87.77 348	86.55 354	91.40 362	91.03 389	83.36 384	96.92 341	95.18 377	91.28 319	86.48 374	93.42 379	53.27 395	96.74 367	89.43 331	81.97 375	94.11 376

DeepMVS_CX				86.78 369	97.09 284	72.30 397		95.17 378	75.92 391	84.34 382	95.19 362	70.58 379	95.35 383	79.98 383	89.04 335	92.68 387

K. test v3		92.55 315	91.91 318	94.48 333	95.64 350	89.24 346	99.07 62	94.88 379	94.04 199	86.78 370	97.59 250	77.64 353	97.64 349	92.08 278	89.43 329	96.57 313

TESTMET0.1,1		94.18 279	93.69 277	95.63 293	96.92 292	89.12 348	96.91 343	94.78 380	93.17 252	94.88 225	96.45 330	78.52 342	98.92 232	93.09 250	98.50 152	98.85 179

pmmvs3		86.67 353	84.86 358	92.11 360	88.16 395	87.19 374	96.63 359	94.75 381	79.88 388	87.22 368	92.75 385	66.56 388	95.20 386	81.24 379	76.56 392	93.96 380

door								94.64 382

thisisatest0515		95.61 187	94.89 203	97.76 149	98.15 199	95.15 194	96.77 354	94.41 383	92.95 263	97.18 152	97.43 262	84.78 286	99.45 166	94.63 201	97.73 183	98.68 195

door-mid								94.37 384

tttt0517		96.07 157	95.51 170	97.78 146	98.41 167	94.84 209	99.28 24	94.33 385	94.26 194	97.64 140	98.64 146	84.05 304	99.47 164	95.34 179	97.60 187	99.03 164

DSMNet-mixed		92.52 317	92.58 307	92.33 357	94.15 373	82.65 385	98.30 215	94.26 386	89.08 357	92.65 315	95.73 352	85.01 281	95.76 381	86.24 355	97.76 181	98.59 205

thisisatest0530		96.01 159	95.36 176	97.97 134	98.38 168	95.52 174	98.88 108	94.19 387	94.04 199	97.64 140	98.31 185	83.82 311	99.46 165	95.29 183	97.70 184	98.93 175

MTMP							98.89 103	94.14 388

baseline2		95.11 214	94.52 218	96.87 214	96.65 310	93.56 260	98.27 220	94.10 389	93.45 240	92.02 332	97.43 262	87.45 238	99.19 190	93.88 229	97.41 192	97.87 232

PMVS	61.03 23	65.95 368	63.57 372	73.09 385	57.90 410	51.22 412	85.05 398	93.93 390	54.45 399	44.32 405	83.57 394	13.22 409	89.15 400	58.68 400	81.00 379	78.91 399
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS		94.30 268	93.89 261	95.53 296	97.83 223	88.95 353	97.52 300	93.25 391	94.44 189	96.63 177	97.07 287	78.70 341	99.28 180	91.99 283	97.56 189	98.36 217

testf1		79.02 359	77.70 361	82.99 377	88.10 396	66.90 402	94.67 384	93.11 392	71.08 394	74.02 392	93.41 380	34.15 404	93.25 392	72.25 394	78.50 387	88.82 392

APD_test2		79.02 359	77.70 361	82.99 377	88.10 396	66.90 402	94.67 384	93.11 392	71.08 394	74.02 392	93.41 380	34.15 404	93.25 392	72.25 394	78.50 387	88.82 392

PMMVS2		77.95 363	75.44 367	85.46 371	82.54 402	74.95 394	94.23 389	93.08 394	72.80 393	74.68 391	87.38 392	36.36 403	91.56 396	73.95 392	63.94 399	89.87 391

MVS-HIRNet		89.46 343	88.40 343	92.64 354	97.58 243	82.15 386	94.16 390	93.05 395	75.73 392	90.90 341	82.52 395	79.42 337	98.33 303	83.53 373	98.68 140	97.43 245

test1111		95.94 165	95.78 155	96.41 259	98.99 118	90.12 332	99.04 68	92.45 396	96.99 66	98.03 109	99.27 56	81.40 321	99.48 162	96.87 128	99.04 123	99.63 73

ECVR-MVS		95.95 163	95.71 162	96.65 227	99.02 111	90.86 318	99.03 71	91.80 397	96.96 67	98.10 103	99.26 57	81.31 322	99.51 157	96.90 122	99.04 123	99.59 79

EPMVS		94.99 222	94.48 220	96.52 248	97.22 272	91.75 302	97.23 320	91.66 398	94.11 196	97.28 148	96.81 315	85.70 267	98.84 244	93.04 253	97.28 193	98.97 170

dmvs_testset		87.64 349	88.93 342	83.79 374	95.25 361	63.36 405	97.20 323	91.17 399	93.07 257	85.64 378	95.98 347	85.30 278	91.52 397	69.42 396	87.33 353	96.49 329

lessismore_v0				94.45 336	94.93 366	88.44 362		91.03 400		86.77 371	97.64 246	76.23 363	98.42 287	90.31 313	85.64 367	96.51 326

test_vis1_rt		91.29 325	90.65 325	93.19 351	97.45 257	86.25 376	98.57 183	90.90 401	93.30 247	86.94 369	93.59 378	62.07 391	99.11 202	97.48 100	95.58 241	94.22 374

ANet_high		69.08 366	65.37 370	80.22 381	65.99 409	71.96 399	90.91 395	90.09 402	82.62 384	49.93 404	78.39 399	29.36 407	81.75 402	62.49 399	38.52 403	86.95 396

gg-mvs-nofinetune		92.21 319	90.58 327	97.13 194	96.75 304	95.09 196	95.85 371	89.40 403	85.43 378	94.50 237	81.98 396	80.80 329	98.40 301	92.16 276	98.33 162	97.88 231

GG-mvs-BLEND				96.59 237	96.34 326	94.98 202	96.51 363	88.58 404		93.10 304	94.34 374	80.34 333	98.05 327	89.53 328	96.99 198	96.74 291

E-PMN		64.94 369	64.25 371	67.02 386	82.28 403	59.36 409	91.83 394	85.63 405	52.69 400	60.22 401	77.28 400	41.06 401	80.12 404	46.15 404	41.14 401	61.57 402

EMVS		64.07 370	63.26 373	66.53 387	81.73 404	58.81 410	91.85 393	84.75 406	51.93 402	59.09 402	75.13 401	43.32 399	79.09 405	42.03 405	39.47 402	61.69 401

tmp_tt		68.90 367	66.97 369	74.68 384	50.78 411	59.95 408	87.13 396	83.47 407	38.80 404	62.21 400	96.23 336	64.70 389	76.91 406	88.91 337	30.49 404	87.19 395

test_vis3_rt		79.22 357	77.40 363	84.67 373	86.44 399	74.85 395	97.66 289	81.43 408	84.98 379	67.12 399	81.91 397	28.09 408	97.60 350	88.96 336	80.04 383	81.55 397

MVE	62.14 22	63.28 371	59.38 374	74.99 383	74.33 408	65.47 404	85.55 397	80.50 409	52.02 401	51.10 403	75.00 402	10.91 412	80.50 403	51.60 402	53.40 400	78.99 398
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2506		94.44 261	93.91 258	96.04 275	99.02 111	88.99 352	99.06 63	79.47 410	96.96 67	98.36 94	99.26 57	77.21 355	99.52 156	96.78 134	99.04 123	99.59 79

N_pmnet		87.12 352	87.77 350	85.17 372	95.46 357	61.92 406	97.37 309	70.66 411	85.83 375	88.73 362	96.04 343	85.33 276	97.76 346	80.02 381	90.48 312	95.84 351

wuyk23d		30.17 372	30.18 376	30.16 388	78.61 406	43.29 413	66.79 401	14.21 412	17.31 405	14.82 408	11.93 408	11.55 411	41.43 407	37.08 406	19.30 405	5.76 405

testmvs		21.48 374	24.95 377	11.09 390	14.89 412	6.47 415	96.56 361	9.87 413	7.55 406	17.93 406	39.02 404	9.43 413	5.90 409	16.56 408	12.72 406	20.91 404

test123		20.95 375	23.72 378	12.64 389	13.54 413	8.19 414	96.55 362	6.13 414	7.48 407	16.74 407	37.98 405	12.97 410	6.05 408	16.69 407	5.43 407	23.68 403

test_blank		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

pcd_1.5k_mvsjas		7.88 377	10.50 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	94.51 81	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

n2								0.00 415

nn								0.00 415

ab-mvs-re		8.20 376	10.94 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	98.43 168	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

WAC-MVS						90.94 316								88.66 339

PC_three_1452									95.08 158	99.60 19	99.16 77	97.86 2	98.47 281	97.52 98	99.72 51	99.74 37

eth-test2					0.00 414

eth-test					0.00 414

OPU-MVS				99.37 20	99.24 87	99.05 14	99.02 74				99.16 77	97.81 3	99.37 173	97.24 107	99.73 48	99.70 53

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

GSMVS																99.20 139

test_part2					99.63 29	99.18 10				99.27 35

sam_mvs1												89.45 181				99.20 139

sam_mvs												88.99 195

test_post1							96.68 358				30.43 407	87.85 228	98.69 257	92.59 266

test_post											31.83 406	88.83 202	98.91 234

patchmatchnet-post											95.10 364	89.42 182	98.89 238

gm-plane-assit					95.88 344	87.47 371			89.74 347		96.94 307		99.19 190	93.32 245

test9_res														96.39 146	99.57 80	99.69 56

agg_prior2														95.87 162	99.57 80	99.68 61

test_prior4						98.01 59	97.86 272

test_prior2							97.80 278		96.12 103	97.89 124	98.69 141	95.96 37		96.89 123	99.60 74

旧先验2							97.57 297		91.30 317	98.67 73			99.80 88	95.70 171

新几何2							97.64 291

原ACMM2							97.67 288

testdata2													99.89 47	91.65 292

segment_acmp												96.85 14

testdata1							97.32 315		96.34 95

plane_prior7					97.42 259	94.63 219

plane_prior6					97.35 266	94.61 222						87.09 241

plane_prior4											98.28 187

plane_prior3						94.61 222			97.02 64	95.34 214

plane_prior2							98.80 135		97.28 45

plane_prior1					97.37 265

plane_prior						94.60 224	98.44 199		96.74 77						94.22 249

HQP5-MVS						94.25 239

HQP-NCC					97.20 274		98.05 248		96.43 89	94.45 239

ACMP_Plane					97.20 274		98.05 248		96.43 89	94.45 239

BP-MVS														95.30 181

HQP4-MVS										94.45 239			98.96 225			96.87 277

HQP2-MVS												86.75 247

NP-MVS					97.28 268	94.51 227					97.73 235

MDTV_nov1_ep13_2view						84.26 379	96.89 348		90.97 326	97.90 123		89.89 173		93.91 228		99.18 148

ACMMP++_ref															92.97 284

ACMMP++															93.61 271

Test By Simon												94.64 78

High-resolution multi-view benchmark