High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 2	99.97 6	99.74 75	99.01 238	99.99 11	99.99 3	99.98 13	99.88 47	99.97 2	99.99 8	99.96 9	100.00 1	99.98 4

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 2	99.98 3	99.76 63	99.12 206	100.00 1	100.00 1	99.99 7	99.91 28	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_fmvsm_n_1920		99.84 16	99.85 17	99.83 31	99.82 72	99.70 92	99.17 186	99.97 19	99.99 3	99.96 24	99.82 80	99.94 4	100.00 1	99.95 12	100.00 1	99.80 50

test_vis3_rt		99.89 3	99.90 4	99.87 20	99.98 3	99.75 69	99.70 35	100.00 1	99.73 78	100.00 1	99.89 38	99.79 16	99.88 196	99.98 1	100.00 1	99.98 4

IterMVS-SCA-FT		99.00 221	99.16 152	98.51 336	99.75 129	95.90 382	98.07 349	99.84 65	99.84 55	99.89 53	99.73 135	96.01 313	99.99 8	99.33 96	100.00 1	99.63 134

new-patchmatchnet		99.35 132	99.57 73	98.71 328	99.82 72	96.62 367	98.55 303	99.75 109	99.50 131	99.88 62	99.87 52	99.31 64	99.88 196	99.43 76	100.00 1	99.62 145

anonymousdsp		99.80 24	99.77 35	99.90 7	99.96 7	99.88 12	99.73 27	99.85 59	99.70 89	99.92 43	99.93 21	99.45 49	99.97 34	99.36 89	100.00 1	99.85 37

UA-Net		99.78 28	99.76 38	99.86 24	99.72 141	99.71 85	99.91 4	99.95 30	99.96 19	99.71 137	99.91 28	99.15 83	99.97 34	99.50 70	100.00 1	99.90 24

PS-MVSNAJss		99.84 16	99.82 24	99.89 10	99.96 7	99.77 56	99.68 46	99.85 59	99.95 20	99.98 13	99.92 25	99.28 68	99.98 21	99.75 41	100.00 1	99.94 16

jajsoiax		99.89 3	99.89 6	99.89 10	99.96 7	99.78 51	99.70 35	99.86 54	99.89 37	99.98 13	99.90 33	99.94 4	99.98 21	99.75 41	100.00 1	99.90 24

mvs_tets		99.90 2	99.90 4	99.90 7	99.96 7	99.79 48	99.72 30	99.88 49	99.92 28	99.98 13	99.93 21	99.94 4	99.98 21	99.77 40	100.00 1	99.92 22

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 19	99.99 3	100.00 1	99.98 13	99.78 17	100.00 1	99.92 21	100.00 1	99.87 32

test_djsdf		99.84 16	99.81 25	99.91 2	99.94 18	99.84 24	99.77 16	99.80 84	99.73 78	99.97 20	99.92 25	99.77 19	99.98 21	99.43 76	100.00 1	99.90 24

IterMVS		98.97 225	99.16 152	98.42 341	99.74 135	95.64 386	98.06 351	99.83 67	99.83 60	99.85 74	99.74 131	96.10 312	99.99 8	99.27 107	100.00 1	99.63 134
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ANet_high		99.88 6	99.87 11	99.91 2	99.99 1	99.91 4	99.65 59	100.00 1	99.90 31	100.00 1	99.97 14	99.61 34	99.97 34	99.75 41	100.00 1	99.84 39

mmtdpeth		99.78 28	99.83 21	99.66 119	99.85 57	99.05 240	99.79 12	99.97 19	100.00 1	99.43 234	99.94 19	99.64 28	99.94 79	99.83 33	99.99 16	99.98 4

mvs5depth		99.88 6	99.91 3	99.80 46	99.92 28	99.42 168	99.94 3	100.00 1	99.97 16	99.89 53	99.99 12	99.63 30	99.97 34	99.87 31	99.99 16	100.00 1

fmvsm_l_conf0.5_n_a		99.80 24	99.79 29	99.84 28	99.88 43	99.64 112	99.12 206	99.91 38	99.98 14	99.95 32	99.67 180	99.67 27	99.99 8	99.94 16	99.99 16	99.88 28

fmvsm_l_conf0.5_n		99.80 24	99.78 33	99.85 26	99.88 43	99.66 103	99.11 211	99.91 38	99.98 14	99.96 24	99.64 192	99.60 36	99.99 8	99.95 12	99.99 16	99.88 28

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 2	99.95 15	99.82 37	99.10 214	99.98 12	99.99 3	99.98 13	99.91 28	99.68 26	99.93 97	99.93 19	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 10	99.93 24	99.78 51	99.07 224	99.98 12	99.99 3	99.98 13	99.90 33	99.88 8	99.92 123	99.93 19	99.99 16	99.98 4

fmvsm_s_conf0.5_n		99.83 20	99.81 25	99.87 20	99.85 57	99.78 51	99.03 233	99.96 25	99.99 3	99.97 20	99.84 69	99.78 17	99.92 123	99.92 21	99.99 16	99.92 22

test_fmvsmconf_n		99.85 12	99.84 20	99.88 16	99.91 30	99.73 78	98.97 250	99.98 12	99.99 3	99.96 24	99.85 63	99.93 7	99.99 8	99.94 16	99.99 16	99.93 18

test_fmvsmvis_n_1920		99.84 16	99.86 13	99.81 41	99.88 43	99.55 140	99.17 186	99.98 12	99.99 3	99.96 24	99.84 69	99.96 3	99.99 8	99.96 9	99.99 16	99.88 28

test_vis1_n_1920		99.72 38	99.88 7	99.27 254	99.93 24	97.84 332	99.34 129	100.00 1	99.99 3	99.99 7	99.82 80	99.87 9	99.99 8	99.97 4	99.99 16	99.97 9

test_fmvs2		99.72 38	99.85 17	99.34 233	99.91 30	98.08 320	99.48 102	100.00 1	99.90 31	99.99 7	99.91 28	99.50 48	99.98 21	99.98 1	99.99 16	99.96 12

test_fmvs3		99.83 20	99.93 2	99.53 177	99.96 7	98.62 281	99.67 50	100.00 1	99.95 20	100.00 1	99.95 16	99.85 10	99.99 8	99.98 1	99.99 16	99.98 4

test_f		99.75 34	99.88 7	99.37 226	99.96 7	98.21 306	99.51 95	100.00 1	99.94 23	100.00 1	99.93 21	99.58 38	99.94 79	99.97 4	99.99 16	99.97 9

test2506		94.73 383	94.59 384	95.15 399	99.59 190	85.90 425	99.75 22	74.01 427	99.89 37	99.71 137	99.86 59	79.00 416	99.90 163	99.52 67	99.99 16	99.65 119

test1111		97.74 322	98.16 295	96.49 393	99.60 185	89.86 423	99.71 34	91.21 419	99.89 37	99.88 62	99.87 52	93.73 339	99.90 163	99.56 60	99.99 16	99.70 82

ECVR-MVS		97.73 323	98.04 302	96.78 387	99.59 190	90.81 419	99.72 30	90.43 421	99.89 37	99.86 71	99.86 59	93.60 341	99.89 182	99.46 73	99.99 16	99.65 119

pmmvs-eth3d		99.48 91	99.47 89	99.51 182	99.77 113	99.41 174	98.81 271	99.66 156	99.42 156	99.75 119	99.66 185	99.20 78	99.76 326	98.98 144	99.99 16	99.36 256

v7n		99.82 22	99.80 28	99.88 16	99.96 7	99.84 24	99.82 9	99.82 72	99.84 55	99.94 35	99.91 28	99.13 88	99.96 55	99.83 33	99.99 16	99.83 43

v8		99.68 47	99.69 45	99.65 125	99.80 86	99.40 175	99.66 54	99.76 104	99.64 107	99.93 38	99.85 63	98.66 154	99.84 262	99.88 29	99.99 16	99.71 79

v10		99.69 44	99.69 45	99.66 119	99.81 80	99.39 178	99.66 54	99.75 109	99.60 122	99.92 43	99.87 52	98.75 141	99.86 229	99.90 25	99.99 16	99.73 73

CHOSEN 1792x2688		99.39 122	99.30 130	99.65 125	99.88 43	99.25 208	98.78 278	99.88 49	98.66 259	99.96 24	99.79 100	97.45 263	99.93 97	99.34 93	99.99 16	99.78 59

PVSNet_Blended_VisFu		99.40 118	99.38 108	99.44 202	99.90 36	98.66 274	98.94 255	99.91 38	97.97 322	99.79 99	99.73 135	99.05 102	99.97 34	99.15 124	99.99 16	99.68 94

IterMVS-LS		99.41 116	99.47 89	99.25 260	99.81 80	98.09 317	98.85 263	99.76 104	99.62 112	99.83 81	99.64 192	98.54 170	99.97 34	99.15 124	99.99 16	99.68 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepC-MVS	98.90 4	99.62 66	99.61 61	99.67 112	99.72 141	99.44 161	99.24 164	99.71 131	99.27 172	99.93 38	99.90 33	99.70 24	99.93 97	98.99 142	99.99 16	99.64 129
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 16	99.91 30	99.90 7	99.96 1	99.92 34	99.90 31	99.97 20	99.87 52	99.81 14	99.95 64	99.54 63	99.99 16	99.80 50
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
fmvsm_s_conf0.5_n_a		99.82 22	99.79 29	99.89 10	99.85 57	99.82 37	99.03 233	99.96 25	99.99 3	99.97 20	99.84 69	99.58 38	99.93 97	99.92 21	99.98 41	99.93 18

MM		99.18 179	99.05 186	99.55 171	99.35 288	98.81 260	99.05 225	97.79 393	99.99 3	99.48 222	99.59 232	96.29 308	99.95 64	99.94 16	99.98 41	99.88 28

test_fmvs1_n		99.68 47	99.81 25	99.28 251	99.95 15	97.93 329	99.49 100	100.00 1	99.82 62	99.99 7	99.89 38	99.21 77	99.98 21	99.97 4	99.98 41	99.93 18

mvsany_test3		99.85 12	99.88 7	99.75 76	99.95 15	99.37 183	99.53 88	99.98 12	99.77 76	99.99 7	99.95 16	99.85 10	99.94 79	99.95 12	99.98 41	99.94 16

Anonymous20240521		99.44 106	99.42 102	99.49 186	99.89 38	98.96 247	99.62 64	99.76 104	99.85 52	99.82 82	99.88 47	96.39 303	99.97 34	99.59 55	99.98 41	99.55 181

D2MVS		99.22 165	99.19 149	99.29 248	99.69 156	98.74 267	98.81 271	99.41 276	98.55 270	99.68 147	99.69 165	98.13 221	99.87 210	98.82 160	99.98 41	99.24 281

CHOSEN 280x420		98.41 287	98.41 270	98.40 342	99.34 297	95.89 383	96.94 405	99.44 270	98.80 243	99.25 278	99.52 259	93.51 342	99.98 21	98.94 153	99.98 41	99.32 266

MVS_0304		98.61 262	98.30 283	99.52 179	97.88 416	98.95 248	98.76 280	94.11 415	99.84 55	99.32 264	99.57 242	95.57 319	99.95 64	99.68 47	99.98 41	99.68 94

v1192		99.57 71	99.57 73	99.57 165	99.77 113	99.22 215	99.04 230	99.60 197	99.18 187	99.87 70	99.72 142	99.08 95	99.85 247	99.89 28	99.98 41	99.66 111

v1144		99.54 80	99.53 84	99.59 156	99.79 98	99.28 201	99.10 214	99.61 186	99.20 185	99.84 77	99.73 135	98.67 152	99.84 262	99.86 32	99.98 41	99.64 129

OurMVSNet-221017-0		99.75 34	99.71 41	99.84 28	99.96 7	99.83 29	99.83 7	99.85 59	99.80 68	99.93 38	99.93 21	98.54 170	99.93 97	99.59 55	99.98 41	99.76 68

UGNet		99.38 124	99.34 118	99.49 186	98.90 370	98.90 255	99.70 35	99.35 295	99.86 46	98.57 356	99.81 87	98.50 180	99.93 97	99.38 85	99.98 41	99.66 111
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
MIMVSNet1		99.66 54	99.62 57	99.80 46	99.94 18	99.87 14	99.69 42	99.77 99	99.78 72	99.93 38	99.89 38	97.94 234	99.92 123	99.65 50	99.98 41	99.62 145

Vis-MVSNet		99.75 34	99.74 39	99.79 53	99.88 43	99.66 103	99.69 42	99.92 34	99.67 98	99.77 111	99.75 127	99.61 34	99.98 21	99.35 92	99.98 41	99.72 76
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_cas_vis1_n_1920		99.76 33	99.86 13	99.45 198	99.93 24	98.40 294	99.30 143	99.98 12	99.94 23	99.99 7	99.89 38	99.80 15	99.97 34	99.96 9	99.97 55	99.97 9

test_fmvs1		99.48 91	99.65 52	98.97 295	99.54 221	97.16 355	99.11 211	99.98 12	99.78 72	99.96 24	99.81 87	98.72 146	99.97 34	99.95 12	99.97 55	99.79 57

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 7	99.89 38	99.91 4	99.89 5	99.71 131	99.93 25	99.95 32	99.89 38	99.71 22	99.96 55	99.51 68	99.97 55	99.84 39

CANet		99.11 196	99.05 186	99.28 251	98.83 379	98.56 284	98.71 286	99.41 276	99.25 176	99.23 282	99.22 333	97.66 257	99.94 79	99.19 116	99.97 55	99.33 263

pmmvs6		99.86 10	99.86 13	99.83 31	99.94 18	99.90 7	99.83 7	99.91 38	99.85 52	99.94 35	99.95 16	99.73 21	99.90 163	99.65 50	99.97 55	99.69 88

v144192		99.55 77	99.54 80	99.58 159	99.78 105	99.20 220	99.11 211	99.62 179	99.18 187	99.89 53	99.72 142	98.66 154	99.87 210	99.88 29	99.97 55	99.66 111

v1921920		99.56 74	99.57 73	99.55 171	99.75 129	99.11 229	99.05 225	99.61 186	99.15 198	99.88 62	99.71 150	99.08 95	99.87 210	99.90 25	99.97 55	99.66 111

FC-MVSNet-test		99.70 42	99.65 52	99.86 24	99.88 43	99.86 18	99.72 30	99.78 96	99.90 31	99.82 82	99.83 73	98.45 185	99.87 210	99.51 68	99.97 55	99.86 34

v2v482		99.50 85	99.47 89	99.58 159	99.78 105	99.25 208	99.14 196	99.58 212	99.25 176	99.81 89	99.62 210	98.24 209	99.84 262	99.83 33	99.97 55	99.64 129

Patchmtry		98.78 248	98.54 260	99.49 186	98.89 373	99.19 221	99.32 135	99.67 151	99.65 105	99.72 132	99.79 100	91.87 358	99.95 64	98.00 226	99.97 55	99.33 263

PVSNet_BlendedMVS		99.03 211	99.01 198	99.09 281	99.54 221	97.99 323	98.58 297	99.82 72	97.62 341	99.34 259	99.71 150	98.52 177	99.77 323	97.98 227	99.97 55	99.52 204

FMVSNet1		99.66 54	99.63 56	99.73 90	99.78 105	99.77 56	99.68 46	99.70 136	99.67 98	99.82 82	99.83 73	98.98 111	99.90 163	99.24 108	99.97 55	99.53 194

HyFIR lowres test		98.91 234	98.64 247	99.73 90	99.85 57	99.47 150	98.07 349	99.83 67	98.64 261	99.89 53	99.60 227	92.57 350	100.00 1	99.33 96	99.97 55	99.72 76

SDMVSNet		99.77 32	99.77 35	99.76 66	99.80 86	99.65 109	99.63 61	99.86 54	99.97 16	99.89 53	99.89 38	99.52 46	99.99 8	99.42 81	99.96 68	99.65 119

sd_testset		99.78 28	99.78 33	99.80 46	99.80 86	99.76 63	99.80 11	99.79 90	99.97 16	99.89 53	99.89 38	99.53 45	99.99 8	99.36 89	99.96 68	99.65 119

test_vis1_n		99.68 47	99.79 29	99.36 230	99.94 18	98.18 309	99.52 89	100.00 1	99.86 46	100.00 1	99.88 47	98.99 109	99.96 55	99.97 4	99.96 68	99.95 13

patch_mono-2		99.51 84	99.46 93	99.64 132	99.70 152	99.11 229	99.04 230	99.87 51	99.71 84	99.47 224	99.79 100	98.24 209	99.98 21	99.38 85	99.96 68	99.83 43

dcpmvs_2		99.61 68	99.64 55	99.53 177	99.79 98	98.82 259	99.58 79	99.97 19	99.95 20	99.96 24	99.76 122	98.44 186	99.99 8	99.34 93	99.96 68	99.78 59

ppachtmachnet_test		98.89 239	99.12 162	98.20 353	99.66 171	95.24 392	97.63 379	99.68 146	99.08 205	99.78 103	99.62 210	98.65 156	99.88 196	98.02 222	99.96 68	99.48 220

Anonymous20231211		99.62 66	99.57 73	99.76 66	99.61 183	99.60 128	99.81 10	99.73 119	99.82 62	99.90 49	99.90 33	97.97 233	99.86 229	99.42 81	99.96 68	99.80 50

nrg030		99.70 42	99.66 50	99.82 36	99.76 117	99.84 24	99.61 70	99.70 136	99.93 25	99.78 103	99.68 176	99.10 90	99.78 315	99.45 74	99.96 68	99.83 43

v1240		99.56 74	99.58 69	99.51 182	99.80 86	99.00 241	99.00 241	99.65 166	99.15 198	99.90 49	99.75 127	99.09 92	99.88 196	99.90 25	99.96 68	99.67 102

PS-CasMVS		99.66 54	99.58 69	99.89 10	99.80 86	99.85 19	99.66 54	99.73 119	99.62 112	99.84 77	99.71 150	98.62 158	99.96 55	99.30 101	99.96 68	99.86 34

casdiffmvs_mvg		99.68 47	99.68 48	99.69 107	99.81 80	99.59 130	99.29 150	99.90 43	99.71 84	99.79 99	99.73 135	99.54 43	99.84 262	99.36 89	99.96 68	99.65 119
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TAMVS		99.49 89	99.45 95	99.63 139	99.48 250	99.42 168	99.45 109	99.57 214	99.66 102	99.78 103	99.83 73	97.85 241	99.86 229	99.44 75	99.96 68	99.61 155

test_0402		99.22 165	99.14 156	99.45 198	99.79 98	99.43 165	99.28 152	99.68 146	99.54 126	99.40 248	99.56 246	99.07 97	99.82 287	96.01 360	99.96 68	99.11 314

reproduce_monomvs		97.40 336	97.46 330	97.20 383	99.05 355	91.91 411	99.20 174	99.18 331	99.84 55	99.86 71	99.75 127	80.67 406	99.83 277	99.69 45	99.95 81	99.85 37

WBMVS		97.50 333	97.18 339	98.48 338	98.85 377	95.89 383	98.44 319	99.52 245	99.53 128	99.52 211	99.42 285	80.10 409	99.86 229	99.24 108	99.95 81	99.68 94

our_test_3		98.85 243	99.09 174	98.13 355	99.66 171	94.90 396	97.72 375	99.58 212	99.07 207	99.64 160	99.62 210	98.19 217	99.93 97	98.41 190	99.95 81	99.55 181

CANet_DTU		98.91 234	98.85 230	99.09 281	98.79 385	98.13 312	98.18 335	99.31 304	99.48 134	98.86 327	99.51 261	96.56 294	99.95 64	99.05 138	99.95 81	99.19 297

pmmvs5		99.19 175	99.11 165	99.42 208	99.76 117	98.88 256	98.55 303	99.73 119	98.82 239	99.72 132	99.62 210	96.56 294	99.82 287	99.32 98	99.95 81	99.56 178

V42		99.56 74	99.54 80	99.63 139	99.79 98	99.46 154	99.39 117	99.59 203	99.24 178	99.86 71	99.70 158	98.55 168	99.82 287	99.79 39	99.95 81	99.60 159

EU-MVSNet		99.39 122	99.62 57	98.72 326	99.88 43	96.44 370	99.56 84	99.85 59	99.90 31	99.90 49	99.85 63	98.09 223	99.83 277	99.58 58	99.95 81	99.90 24

PMMVS2		99.48 91	99.45 95	99.57 165	99.76 117	98.99 242	98.09 346	99.90 43	98.95 219	99.78 103	99.58 235	99.57 40	99.93 97	99.48 71	99.95 81	99.79 57

DTE-MVSNet		99.68 47	99.61 61	99.88 16	99.80 86	99.87 14	99.67 50	99.71 131	99.72 82	99.84 77	99.78 110	98.67 152	99.97 34	99.30 101	99.95 81	99.80 50

WR-MVS_H		99.61 68	99.53 84	99.87 20	99.80 86	99.83 29	99.67 50	99.75 109	99.58 125	99.85 74	99.69 165	98.18 219	99.94 79	99.28 106	99.95 81	99.83 43

K. test v3		98.87 241	98.60 250	99.69 107	99.93 24	99.46 154	99.74 24	94.97 410	99.78 72	99.88 62	99.88 47	93.66 340	99.97 34	99.61 53	99.95 81	99.64 129

TDRefinement		99.72 38	99.70 42	99.77 59	99.90 36	99.85 19	99.86 6	99.92 34	99.69 92	99.78 103	99.92 25	99.37 58	99.88 196	98.93 154	99.95 81	99.60 159

Gipuma		99.57 71	99.59 66	99.49 186	99.98 3	99.71 85	99.72 30	99.84 65	99.81 65	99.94 35	99.78 110	98.91 121	99.71 342	98.41 190	99.95 81	99.05 334
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v148		99.40 118	99.41 104	99.39 220	99.76 117	98.94 249	99.09 218	99.59 203	99.17 192	99.81 89	99.61 219	98.41 190	99.69 351	99.32 98	99.94 94	99.53 194

casdiffmvs		99.63 60	99.61 61	99.67 112	99.79 98	99.59 130	99.13 202	99.85 59	99.79 70	99.76 114	99.72 142	99.33 63	99.82 287	99.21 112	99.94 94	99.59 166
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PEN-MVS		99.66 54	99.59 66	99.89 10	99.83 65	99.87 14	99.66 54	99.73 119	99.70 89	99.84 77	99.73 135	98.56 167	99.96 55	99.29 104	99.94 94	99.83 43

CP-MVSNet		99.54 80	99.43 100	99.87 20	99.76 117	99.82 37	99.57 82	99.61 186	99.54 126	99.80 93	99.64 192	97.79 245	99.95 64	99.21 112	99.94 94	99.84 39

baseline		99.63 60	99.62 57	99.66 119	99.80 86	99.62 119	99.44 111	99.80 84	99.71 84	99.72 132	99.69 165	99.15 83	99.83 277	99.32 98	99.94 94	99.53 194

FMVSNet2		99.35 132	99.28 137	99.55 171	99.49 245	99.35 190	99.45 109	99.57 214	99.44 146	99.70 141	99.74 131	97.21 274	99.87 210	99.03 139	99.94 94	99.44 234

ACMMP++_ref															99.94 94

eth_miper_zixun_eth		98.68 259	98.71 243	98.60 332	99.10 349	96.84 364	97.52 387	99.54 231	98.94 220	99.58 187	99.48 271	96.25 309	99.76 326	98.01 225	99.93 101	99.21 290

FIs		99.65 59	99.58 69	99.84 28	99.84 61	99.85 19	99.66 54	99.75 109	99.86 46	99.74 127	99.79 100	98.27 207	99.85 247	99.37 88	99.93 101	99.83 43

pmmvs4		99.13 191	99.06 182	99.36 230	99.57 205	99.10 234	98.01 355	99.25 317	98.78 246	99.58 187	99.44 282	98.24 209	99.76 326	98.74 171	99.93 101	99.22 287

XXY-MVS		99.71 41	99.67 49	99.81 41	99.89 38	99.72 83	99.59 77	99.82 72	99.39 157	99.82 82	99.84 69	99.38 56	99.91 145	99.38 85	99.93 101	99.80 50

mamv4		99.73 37	99.74 39	99.70 105	99.66 171	99.87 14	99.69 42	99.93 32	99.93 25	99.93 38	99.86 59	99.07 97	100.00 1	99.66 48	99.92 105	99.24 281

pm-mvs1		99.79 27	99.79 29	99.78 56	99.91 30	99.83 29	99.76 20	99.87 51	99.73 78	99.89 53	99.87 52	99.63 30	99.87 210	99.54 63	99.92 105	99.63 134

EI-MVSNet		99.38 124	99.44 98	99.21 264	99.58 195	98.09 317	99.26 157	99.46 265	99.62 112	99.75 119	99.67 180	98.54 170	99.85 247	99.15 124	99.92 105	99.68 94

TranMVSNet+NR-MVSNet		99.54 80	99.47 89	99.76 66	99.58 195	99.64 112	99.30 143	99.63 176	99.61 116	99.71 137	99.56 246	98.76 139	99.96 55	99.14 130	99.92 105	99.68 94

lessismore_v0				99.64 132	99.86 53	99.38 180		90.66 420		99.89 53	99.83 73	94.56 330	99.97 34	99.56 60	99.92 105	99.57 176

SixPastTwentyTwo		99.42 112	99.30 130	99.76 66	99.92 28	99.67 101	99.70 35	99.14 336	99.65 105	99.89 53	99.90 33	96.20 310	99.94 79	99.42 81	99.92 105	99.67 102

MVSTER		98.47 282	98.22 288	99.24 262	99.06 354	98.35 300	99.08 221	99.46 265	99.27 172	99.75 119	99.66 185	88.61 386	99.85 247	99.14 130	99.92 105	99.52 204

N_pmnet		98.73 254	98.53 261	99.35 232	99.72 141	98.67 271	98.34 324	94.65 411	98.35 296	99.79 99	99.68 176	98.03 227	99.93 97	98.28 199	99.92 105	99.44 234

CSCG		99.37 127	99.29 135	99.60 154	99.71 144	99.46 154	99.43 113	99.85 59	98.79 244	99.41 243	99.60 227	98.92 119	99.92 123	98.02 222	99.92 105	99.43 240

CMPMVS	77.52 23	98.50 278	98.19 293	99.41 215	98.33 407	99.56 137	99.01 238	99.59 203	95.44 391	99.57 190	99.80 90	95.64 316	99.46 406	96.47 342	99.92 105	99.21 290
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EG-PatchMatch MVS		99.57 71	99.56 78	99.62 148	99.77 113	99.33 193	99.26 157	99.76 104	99.32 166	99.80 93	99.78 110	99.29 66	99.87 210	99.15 124	99.91 115	99.66 111

MVSMamba_PlusPlus		99.55 77	99.58 69	99.47 192	99.68 164	99.40 175	99.52 89	99.70 136	99.92 28	99.77 111	99.86 59	98.28 205	99.96 55	99.54 63	99.90 116	99.05 334

miper_lstm_enhance		98.65 261	98.60 250	98.82 321	99.20 329	97.33 351	97.78 373	99.66 156	99.01 212	99.59 185	99.50 264	94.62 329	99.85 247	98.12 216	99.90 116	99.26 278

SPE-MVS-test		99.68 47	99.70 42	99.64 132	99.57 205	99.83 29	99.78 14	99.97 19	99.92 28	99.50 219	99.38 296	99.57 40	99.95 64	99.69 45	99.90 116	99.15 305

EI-MVSNet-UG-set		99.48 91	99.50 86	99.42 208	99.57 205	98.65 277	99.24 164	99.46 265	99.68 94	99.80 93	99.66 185	98.99 109	99.89 182	99.19 116	99.90 116	99.72 76

diffmvs		99.34 137	99.32 123	99.39 220	99.67 170	98.77 265	98.57 301	99.81 81	99.61 116	99.48 222	99.41 286	98.47 181	99.86 229	98.97 146	99.90 116	99.53 194
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
YYNet1		98.95 231	98.99 209	98.84 316	99.64 176	97.14 357	98.22 334	99.32 300	98.92 225	99.59 185	99.66 185	97.40 265	99.83 277	98.27 200	99.90 116	99.55 181

GBi-Net		99.42 112	99.31 125	99.73 90	99.49 245	99.77 56	99.68 46	99.70 136	99.44 146	99.62 173	99.83 73	97.21 274	99.90 163	98.96 148	99.90 116	99.53 194

FMVSNet5		97.80 320	97.25 337	99.42 208	98.83 379	98.97 245	99.38 120	99.80 84	98.87 231	99.25 278	99.69 165	80.60 408	99.91 145	98.96 148	99.90 116	99.38 250

test1		99.42 112	99.31 125	99.73 90	99.49 245	99.77 56	99.68 46	99.70 136	99.44 146	99.62 173	99.83 73	97.21 274	99.90 163	98.96 148	99.90 116	99.53 194

FMVSNet3		98.80 247	98.63 249	99.32 241	99.13 340	98.72 268	99.10 214	99.48 259	99.23 180	99.62 173	99.64 192	92.57 350	99.86 229	98.96 148	99.90 116	99.39 248

cl____		98.54 273	98.41 270	98.92 303	99.03 359	97.80 336	97.46 389	99.59 203	98.90 227	99.60 182	99.46 278	93.85 336	99.78 315	97.97 229	99.89 126	99.17 301

DIV-MVS_self_test		98.54 273	98.42 269	98.92 303	99.03 359	97.80 336	97.46 389	99.59 203	98.90 227	99.60 182	99.46 278	93.87 335	99.78 315	97.97 229	99.89 126	99.18 299

CS-MVS		99.67 53	99.70 42	99.58 159	99.53 227	99.84 24	99.79 12	99.96 25	99.90 31	99.61 179	99.41 286	99.51 47	99.95 64	99.66 48	99.89 126	98.96 347

EI-MVSNet-Vis-set		99.47 99	99.49 88	99.42 208	99.57 205	98.66 274	99.24 164	99.46 265	99.67 98	99.79 99	99.65 190	98.97 113	99.89 182	99.15 124	99.89 126	99.71 79

DSMNet-mixed		99.48 91	99.65 52	98.95 298	99.71 144	97.27 352	99.50 96	99.82 72	99.59 124	99.41 243	99.85 63	99.62 33	100.00 1	99.53 66	99.89 126	99.59 166

Vis-MVSNet (Re-imp)		98.77 249	98.58 255	99.34 233	99.78 105	98.88 256	99.61 70	99.56 219	99.11 204	99.24 281	99.56 246	93.00 348	99.78 315	97.43 280	99.89 126	99.35 259

EPP-MVSNet		99.17 184	99.00 202	99.66 119	99.80 86	99.43 165	99.70 35	99.24 320	99.48 134	99.56 197	99.77 119	94.89 325	99.93 97	98.72 173	99.89 126	99.63 134

CLD-MVS		98.76 250	98.57 256	99.33 236	99.57 205	98.97 245	97.53 385	99.55 225	96.41 378	99.27 276	99.13 341	99.07 97	99.78 315	96.73 325	99.89 126	99.23 285
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ACMH	98.42 6	99.59 70	99.54 80	99.72 96	99.86 53	99.62 119	99.56 84	99.79 90	98.77 248	99.80 93	99.85 63	99.64 28	99.85 247	98.70 174	99.89 126	99.70 82
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testf1		99.63 60	99.60 64	99.72 96	99.94 18	99.95 2	99.47 105	99.89 45	99.43 152	99.88 62	99.80 90	99.26 72	99.90 163	98.81 162	99.88 135	99.32 266

APD_test2		99.63 60	99.60 64	99.72 96	99.94 18	99.95 2	99.47 105	99.89 45	99.43 152	99.88 62	99.80 90	99.26 72	99.90 163	98.81 162	99.88 135	99.32 266

balanced_conf03		99.50 85	99.50 86	99.50 184	99.42 273	99.49 147	99.52 89	99.75 109	99.86 46	99.78 103	99.71 150	98.20 216	99.90 163	99.39 84	99.88 135	99.10 316

GeoE		99.69 44	99.66 50	99.78 56	99.76 117	99.76 63	99.60 76	99.82 72	99.46 141	99.75 119	99.56 246	99.63 30	99.95 64	99.43 76	99.88 135	99.62 145

c3_l		98.72 255	98.71 243	98.72 326	99.12 342	97.22 354	97.68 378	99.56 219	98.90 227	99.54 204	99.48 271	96.37 304	99.73 336	97.88 236	99.88 135	99.21 290

VPA-MVSNet		99.66 54	99.62 57	99.79 53	99.68 164	99.75 69	99.62 64	99.69 143	99.85 52	99.80 93	99.81 87	98.81 129	99.91 145	99.47 72	99.88 135	99.70 82

MDA-MVSNet_test_wron		98.95 231	98.99 209	98.85 314	99.64 176	97.16 355	98.23 333	99.33 298	98.93 223	99.56 197	99.66 185	97.39 267	99.83 277	98.29 198	99.88 135	99.55 181

XVG-OURS		99.21 170	99.06 182	99.65 125	99.82 72	99.62 119	97.87 370	99.74 115	98.36 291	99.66 157	99.68 176	99.71 22	99.90 163	96.84 319	99.88 135	99.43 240

CDS-MVSNet		99.22 165	99.13 158	99.50 184	99.35 288	99.11 229	98.96 252	99.54 231	99.46 141	99.61 179	99.70 158	96.31 306	99.83 277	99.34 93	99.88 135	99.55 181
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS-MVSNet		99.03 211	98.85 230	99.55 171	99.80 86	99.25 208	99.73 27	99.15 335	99.37 159	99.61 179	99.71 150	94.73 328	99.81 302	97.70 258	99.88 135	99.58 171

USDC		98.96 228	98.93 218	99.05 289	99.54 221	97.99 323	97.07 403	99.80 84	98.21 308	99.75 119	99.77 119	98.43 187	99.64 381	97.90 234	99.88 135	99.51 206

ACMH+	98.40 8	99.50 85	99.43 100	99.71 101	99.86 53	99.76 63	99.32 135	99.77 99	99.53 128	99.77 111	99.76 122	99.26 72	99.78 315	97.77 247	99.88 135	99.60 159

mvsany_test1		99.44 106	99.45 95	99.40 217	99.37 282	98.64 279	97.90 369	99.59 203	99.27 172	99.92 43	99.82 80	99.74 20	99.93 97	99.55 62	99.87 147	99.63 134

SD-MVS		99.01 219	99.30 130	98.15 354	99.50 240	99.40 175	98.94 255	99.61 186	99.22 184	99.75 119	99.82 80	99.54 43	95.51 421	97.48 277	99.87 147	99.54 189
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
UniMVSNet (Re)		99.37 127	99.26 141	99.68 109	99.51 234	99.58 134	98.98 249	99.60 197	99.43 152	99.70 141	99.36 302	97.70 249	99.88 196	99.20 115	99.87 147	99.59 166

WR-MVS		99.11 196	98.93 218	99.66 119	99.30 308	99.42 168	98.42 320	99.37 291	99.04 210	99.57 190	99.20 337	96.89 286	99.86 229	98.66 178	99.87 147	99.70 82

NR-MVSNet		99.40 118	99.31 125	99.68 109	99.43 268	99.55 140	99.73 27	99.50 254	99.46 141	99.88 62	99.36 302	97.54 260	99.87 210	98.97 146	99.87 147	99.63 134

LPG-MVS_test		99.22 165	99.05 186	99.74 81	99.82 72	99.63 117	99.16 192	99.73 119	97.56 342	99.64 160	99.69 165	99.37 58	99.89 182	96.66 329	99.87 147	99.69 88

LGP-MVS_train				99.74 81	99.82 72	99.63 117		99.73 119	97.56 342	99.64 160	99.69 165	99.37 58	99.89 182	96.66 329	99.87 147	99.69 88

COLMAP_ROB	98.06 12	99.45 104	99.37 111	99.70 105	99.83 65	99.70 92	99.38 120	99.78 96	99.53 128	99.67 152	99.78 110	99.19 79	99.86 229	97.32 286	99.87 147	99.55 181
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test20.03		99.55 77	99.54 80	99.58 159	99.79 98	99.37 183	99.02 236	99.89 45	99.60 122	99.82 82	99.62 210	98.81 129	99.89 182	99.43 76	99.86 155	99.47 224

Baseline_NR-MVSNet		99.49 89	99.37 111	99.82 36	99.91 30	99.84 24	98.83 266	99.86 54	99.68 94	99.65 159	99.88 47	97.67 253	99.87 210	99.03 139	99.86 155	99.76 68

EC-MVSNet		99.69 44	99.69 45	99.68 109	99.71 144	99.91 4	99.76 20	99.96 25	99.86 46	99.51 217	99.39 294	99.57 40	99.93 97	99.64 52	99.86 155	99.20 294

MSDG		99.08 200	98.98 212	99.37 226	99.60 185	99.13 227	97.54 383	99.74 115	98.84 237	99.53 209	99.55 253	99.10 90	99.79 312	97.07 306	99.86 155	99.18 299

EGC-MVSNET		89.05 386	85.52 389	99.64 132	99.89 38	99.78 51	99.56 84	99.52 245	24.19 421	49.96 422	99.83 73	99.15 83	99.92 123	97.71 255	99.85 159	99.21 290

Patchmatch-RL test		98.60 265	98.36 275	99.33 236	99.77 113	99.07 237	98.27 329	99.87 51	98.91 226	99.74 127	99.72 142	90.57 375	99.79 312	98.55 184	99.85 159	99.11 314

APDe-MVS		99.48 91	99.36 114	99.85 26	99.55 219	99.81 42	99.50 96	99.69 143	98.99 213	99.75 119	99.71 150	98.79 134	99.93 97	98.46 188	99.85 159	99.80 50
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMP	97.51 14	99.05 207	98.84 232	99.67 112	99.78 105	99.55 140	98.88 259	99.66 156	97.11 368	99.47 224	99.60 227	99.07 97	99.89 182	96.18 355	99.85 159	99.58 171
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PMVS	92.94 21	98.82 245	98.81 236	98.85 314	99.84 61	97.99 323	99.20 174	99.47 262	99.71 84	99.42 237	99.82 80	98.09 223	99.47 404	93.88 401	99.85 159	99.07 332
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Anonymous20231206		99.35 132	99.31 125	99.47 192	99.74 135	99.06 239	99.28 152	99.74 115	99.23 180	99.72 132	99.53 257	97.63 259	99.88 196	99.11 132	99.84 164	99.48 220

HPM-MVS_fast		99.43 109	99.30 130	99.80 46	99.83 65	99.81 42	99.52 89	99.70 136	98.35 296	99.51 217	99.50 264	99.31 64	99.88 196	98.18 211	99.84 164	99.69 88

XVG-ACMP-BASELINE		99.23 157	99.10 173	99.63 139	99.82 72	99.58 134	98.83 266	99.72 128	98.36 291	99.60 182	99.71 150	98.92 119	99.91 145	97.08 305	99.84 164	99.40 246

new_pmnet		98.88 240	98.89 226	98.84 316	99.70 152	97.62 341	98.15 338	99.50 254	97.98 321	99.62 173	99.54 255	98.15 220	99.94 79	97.55 272	99.84 164	98.95 349

Test_1112_low_res		98.95 231	98.73 241	99.63 139	99.68 164	99.15 226	98.09 346	99.80 84	97.14 366	99.46 228	99.40 290	96.11 311	99.89 182	99.01 141	99.84 164	99.84 39

1112_ss		99.05 207	98.84 232	99.67 112	99.66 171	99.29 199	98.52 309	99.82 72	97.65 340	99.43 234	99.16 339	96.42 300	99.91 145	99.07 137	99.84 164	99.80 50

3Dnovator	99.15 2	99.43 109	99.36 114	99.65 125	99.39 277	99.42 168	99.70 35	99.56 219	99.23 180	99.35 255	99.80 90	99.17 81	99.95 64	98.21 206	99.84 164	99.59 166

LF4IMVS		99.01 219	98.92 222	99.27 254	99.71 144	99.28 201	98.59 295	99.77 99	98.32 302	99.39 250	99.41 286	98.62 158	99.84 262	96.62 334	99.84 164	98.69 373

ACMMP_NAP		99.28 146	99.11 165	99.79 53	99.75 129	99.81 42	98.95 253	99.53 240	98.27 305	99.53 209	99.73 135	98.75 141	99.87 210	97.70 258	99.83 172	99.68 94

AllTest		99.21 170	99.07 180	99.63 139	99.78 105	99.64 112	99.12 206	99.83 67	98.63 262	99.63 164	99.72 142	98.68 149	99.75 330	96.38 347	99.83 172	99.51 206

TestCases				99.63 139	99.78 105	99.64 112		99.83 67	98.63 262	99.63 164	99.72 142	98.68 149	99.75 330	96.38 347	99.83 172	99.51 206

PM-MVS		99.36 130	99.29 135	99.58 159	99.83 65	99.66 103	98.95 253	99.86 54	98.85 234	99.81 89	99.73 135	98.40 194	99.92 123	98.36 193	99.83 172	99.17 301

EPNet		98.13 308	97.77 323	99.18 269	94.57 424	97.99 323	99.24 164	97.96 388	99.74 77	97.29 397	99.62 210	93.13 345	99.97 34	98.59 182	99.83 172	99.58 171
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended		98.70 257	98.59 252	99.02 291	99.54 221	97.99 323	97.58 382	99.82 72	95.70 389	99.34 259	98.98 365	98.52 177	99.77 323	97.98 227	99.83 172	99.30 272

MVS-HIRNet		97.86 317	98.22 288	96.76 388	99.28 313	91.53 415	98.38 322	92.60 418	99.13 200	99.31 269	99.96 15	97.18 278	99.68 363	98.34 195	99.83 172	99.07 332

RPSCF		99.18 179	99.02 195	99.64 132	99.83 65	99.85 19	99.44 111	99.82 72	98.33 301	99.50 219	99.78 110	97.90 236	99.65 379	96.78 322	99.83 172	99.44 234

TinyColmap		98.97 225	98.93 218	99.07 286	99.46 260	98.19 307	97.75 374	99.75 109	98.79 244	99.54 204	99.70 158	98.97 113	99.62 383	96.63 333	99.83 172	99.41 244

reproduce_model		99.50 85	99.40 105	99.83 31	99.60 185	99.83 29	99.12 206	99.68 146	99.49 133	99.80 93	99.79 100	99.01 106	99.93 97	98.24 203	99.82 181	99.73 73

test_vis1_rt		99.45 104	99.46 93	99.41 215	99.71 144	98.63 280	98.99 246	99.96 25	99.03 211	99.95 32	99.12 345	98.75 141	99.84 262	99.82 37	99.82 181	99.77 63

MP-MVS-pluss		99.14 189	98.92 222	99.80 46	99.83 65	99.83 29	98.61 290	99.63 176	96.84 373	99.44 230	99.58 235	98.81 129	99.91 145	97.70 258	99.82 181	99.67 102
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDA-MVSNet-bldmvs		99.06 204	99.05 186	99.07 286	99.80 86	97.83 333	98.89 258	99.72 128	99.29 168	99.63 164	99.70 158	96.47 298	99.89 182	98.17 213	99.82 181	99.50 211

jason		99.16 185	99.11 165	99.32 241	99.75 129	98.44 291	98.26 331	99.39 286	98.70 256	99.74 127	99.30 315	98.54 170	99.97 34	98.48 187	99.82 181	99.55 181
jason: jason.
HPM-MVS		99.25 153	99.07 180	99.78 56	99.81 80	99.75 69	99.61 70	99.67 151	97.72 337	99.35 255	99.25 326	99.23 75	99.92 123	97.21 300	99.82 181	99.67 102
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
114514_t		98.49 280	98.11 298	99.64 132	99.73 138	99.58 134	99.24 164	99.76 104	89.94 412	99.42 237	99.56 246	97.76 248	99.86 229	97.74 252	99.82 181	99.47 224

CP-MVS		99.23 157	99.05 186	99.75 76	99.66 171	99.66 103	99.38 120	99.62 179	98.38 289	99.06 308	99.27 321	98.79 134	99.94 79	97.51 276	99.82 181	99.66 111

PHI-MVS		99.11 196	98.95 216	99.59 156	99.13 340	99.59 130	99.17 186	99.65 166	97.88 330	99.25 278	99.46 278	98.97 113	99.80 309	97.26 293	99.82 181	99.37 253

wuyk23d		97.58 330	99.13 158	92.93 400	99.69 156	99.49 147	99.52 89	99.77 99	97.97 322	99.96 24	99.79 100	99.84 12	99.94 79	95.85 369	99.82 181	79.36 418

reproduce-ours		99.46 100	99.35 116	99.82 36	99.56 216	99.83 29	99.05 225	99.65 166	99.45 144	99.78 103	99.78 110	98.93 116	99.93 97	98.11 217	99.81 191	99.70 82

our_new_method		99.46 100	99.35 116	99.82 36	99.56 216	99.83 29	99.05 225	99.65 166	99.45 144	99.78 103	99.78 110	98.93 116	99.93 97	98.11 217	99.81 191	99.70 82

CVMVSNet		98.61 262	98.88 227	97.80 367	99.58 195	93.60 404	99.26 157	99.64 174	99.66 102	99.72 132	99.67 180	93.26 343	99.93 97	99.30 101	99.81 191	99.87 32

UniMVSNet_NR-MVSNet		99.37 127	99.25 143	99.72 96	99.47 256	99.56 137	98.97 250	99.61 186	99.43 152	99.67 152	99.28 319	97.85 241	99.95 64	99.17 121	99.81 191	99.65 119

DU-MVS		99.33 140	99.21 147	99.71 101	99.43 268	99.56 137	98.83 266	99.53 240	99.38 158	99.67 152	99.36 302	97.67 253	99.95 64	99.17 121	99.81 191	99.63 134

DeepPCF-MVS	98.42 6	99.18 179	99.02 195	99.67 112	99.22 324	99.75 69	97.25 397	99.47 262	98.72 253	99.66 157	99.70 158	99.29 66	99.63 382	98.07 221	99.81 191	99.62 145

ACMM	98.09 11	99.46 100	99.38 108	99.72 96	99.80 86	99.69 96	99.13 202	99.65 166	98.99 213	99.64 160	99.72 142	99.39 52	99.86 229	98.23 204	99.81 191	99.60 159
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ZNCC-MVS		99.22 165	99.04 192	99.77 59	99.76 117	99.73 78	99.28 152	99.56 219	98.19 310	99.14 297	99.29 318	98.84 128	99.92 123	97.53 275	99.80 198	99.64 129

test_0728_THIRD									99.18 187	99.62 173	99.61 219	98.58 164	99.91 145	97.72 253	99.80 198	99.77 63

SteuartSystems-ACMMP		99.30 144	99.14 156	99.76 66	99.87 50	99.66 103	99.18 181	99.60 197	98.55 270	99.57 190	99.67 180	99.03 105	99.94 79	97.01 307	99.80 198	99.69 88
Skip Steuart: Steuart Systems R&D Blog.
DP-MVS		99.48 91	99.39 106	99.74 81	99.57 205	99.62 119	99.29 150	99.61 186	99.87 43	99.74 127	99.76 122	98.69 148	99.87 210	98.20 207	99.80 198	99.75 71

PCF-MVS	96.03 18	96.73 352	95.86 364	99.33 236	99.44 265	99.16 224	96.87 406	99.44 270	86.58 414	98.95 314	99.40 290	94.38 331	99.88 196	87.93 412	99.80 198	98.95 349
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
SMA-MVS		99.19 175	99.00 202	99.73 90	99.46 260	99.73 78	99.13 202	99.52 245	97.40 353	99.57 190	99.64 192	98.93 116	99.83 277	97.61 269	99.79 203	99.63 134
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
MTAPA		99.35 132	99.20 148	99.80 46	99.81 80	99.81 42	99.33 132	99.53 240	99.27 172	99.42 237	99.63 203	98.21 214	99.95 64	97.83 246	99.79 203	99.65 119

ACMMP++															99.79 203

ACMMP		99.25 153	99.08 176	99.74 81	99.79 98	99.68 99	99.50 96	99.65 166	98.07 316	99.52 211	99.69 165	98.57 165	99.92 123	97.18 302	99.79 203	99.63 134
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
OMC-MVS		98.90 236	98.72 242	99.44 202	99.39 277	99.42 168	98.58 297	99.64 174	97.31 358	99.44 230	99.62 210	98.59 162	99.69 351	96.17 356	99.79 203	99.22 287

tfpnnormal		99.43 109	99.38 108	99.60 154	99.87 50	99.75 69	99.59 77	99.78 96	99.71 84	99.90 49	99.69 165	98.85 127	99.90 163	97.25 297	99.78 208	99.15 305

HQP_MVS		98.90 236	98.68 246	99.55 171	99.58 195	99.24 212	98.80 274	99.54 231	98.94 220	99.14 297	99.25 326	97.24 272	99.82 287	95.84 370	99.78 208	99.60 159

plane_prior5								99.54 231					99.82 287	95.84 370	99.78 208	99.60 159

mPP-MVS		99.19 175	99.00 202	99.76 66	99.76 117	99.68 99	99.38 120	99.54 231	98.34 300	99.01 310	99.50 264	98.53 174	99.93 97	97.18 302	99.78 208	99.66 111

OPM-MVS		99.26 152	99.13 158	99.63 139	99.70 152	99.61 125	98.58 297	99.48 259	98.50 277	99.52 211	99.63 203	99.14 86	99.76 326	97.89 235	99.77 212	99.51 206
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MVS_111021_LR		99.13 191	99.03 194	99.42 208	99.58 195	99.32 195	97.91 368	99.73 119	98.68 257	99.31 269	99.48 271	99.09 92	99.66 373	97.70 258	99.77 212	99.29 275

MIMVSNet		98.43 285	98.20 290	99.11 278	99.53 227	98.38 298	99.58 79	98.61 364	98.96 217	99.33 261	99.76 122	90.92 368	99.81 302	97.38 283	99.76 214	99.15 305

MVS_111021_HR		99.12 193	99.02 195	99.40 217	99.50 240	99.11 229	97.92 366	99.71 131	98.76 251	99.08 304	99.47 275	99.17 81	99.54 396	97.85 242	99.76 214	99.54 189

DPE-MVS		99.14 189	98.92 222	99.82 36	99.57 205	99.77 56	98.74 282	99.60 197	98.55 270	99.76 114	99.69 165	98.23 213	99.92 123	96.39 346	99.75 216	99.76 68
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + MP.		99.34 137	99.24 145	99.63 139	99.82 72	99.37 183	99.26 157	99.35 295	98.77 248	99.57 190	99.70 158	99.27 71	99.88 196	97.71 255	99.75 216	99.65 119
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HFP-MVS		99.25 153	99.08 176	99.76 66	99.73 138	99.70 92	99.31 140	99.59 203	98.36 291	99.36 253	99.37 298	98.80 133	99.91 145	97.43 280	99.75 216	99.68 94

ACMMPR		99.23 157	99.06 182	99.76 66	99.74 135	99.69 96	99.31 140	99.59 203	98.36 291	99.35 255	99.38 296	98.61 160	99.93 97	97.43 280	99.75 216	99.67 102

MP-MVS		99.06 204	98.83 234	99.76 66	99.76 117	99.71 85	99.32 135	99.50 254	98.35 296	98.97 312	99.48 271	98.37 196	99.92 123	95.95 366	99.75 216	99.63 134
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
QAPM		98.40 289	97.99 305	99.65 125	99.39 277	99.47 150	99.67 50	99.52 245	91.70 409	98.78 338	99.80 90	98.55 168	99.95 64	94.71 390	99.75 216	99.53 194

DeepC-MVS_fast	98.47 5	99.23 157	99.12 162	99.56 168	99.28 313	99.22 215	98.99 246	99.40 283	99.08 205	99.58 187	99.64 192	98.90 124	99.83 277	97.44 279	99.75 216	99.63 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
GST-MVS		99.16 185	98.96 215	99.75 76	99.73 138	99.73 78	99.20 174	99.55 225	98.22 307	99.32 264	99.35 307	98.65 156	99.91 145	96.86 316	99.74 223	99.62 145

region2R		99.23 157	99.05 186	99.77 59	99.76 117	99.70 92	99.31 140	99.59 203	98.41 285	99.32 264	99.36 302	98.73 145	99.93 97	97.29 288	99.74 223	99.67 102

PGM-MVS		99.20 172	99.01 198	99.77 59	99.75 129	99.71 85	99.16 192	99.72 128	97.99 320	99.42 237	99.60 227	98.81 129	99.93 97	96.91 313	99.74 223	99.66 111

TransMVSNet (Re)		99.78 28	99.77 35	99.81 41	99.91 30	99.85 19	99.75 22	99.86 54	99.70 89	99.91 46	99.89 38	99.60 36	99.87 210	99.59 55	99.74 223	99.71 79

TSAR-MVS + GP.		99.12 193	99.04 192	99.38 223	99.34 297	99.16 224	98.15 338	99.29 308	98.18 311	99.63 164	99.62 210	99.18 80	99.68 363	98.20 207	99.74 223	99.30 272

KD-MVS_self_test		99.63 60	99.59 66	99.76 66	99.84 61	99.90 7	99.37 124	99.79 90	99.83 60	99.88 62	99.85 63	98.42 189	99.90 163	99.60 54	99.73 228	99.49 216

XVS		99.27 150	99.11 165	99.75 76	99.71 144	99.71 85	99.37 124	99.61 186	99.29 168	98.76 339	99.47 275	98.47 181	99.88 196	97.62 267	99.73 228	99.67 102

X-MVStestdata		96.09 368	94.87 380	99.75 76	99.71 144	99.71 85	99.37 124	99.61 186	99.29 168	98.76 339	61.30 430	98.47 181	99.88 196	97.62 267	99.73 228	99.67 102

VDD-MVS		99.20 172	99.11 165	99.44 202	99.43 268	98.98 243	99.50 96	98.32 381	99.80 68	99.56 197	99.69 165	96.99 284	99.85 247	98.99 142	99.73 228	99.50 211

ab-mvs		99.33 140	99.28 137	99.47 192	99.57 205	99.39 178	99.78 14	99.43 273	98.87 231	99.57 190	99.82 80	98.06 226	99.87 210	98.69 176	99.73 228	99.15 305

TAPA-MVS	97.92 13	98.03 313	97.55 329	99.46 195	99.47 256	99.44 161	98.50 311	99.62 179	86.79 413	99.07 307	99.26 324	98.26 208	99.62 383	97.28 290	99.73 228	99.31 270
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DVP-MVS		99.32 142	99.17 151	99.77 59	99.69 156	99.80 46	99.14 196	99.31 304	99.16 194	99.62 173	99.61 219	98.35 198	99.91 145	97.88 236	99.72 234	99.61 155
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
test_0728_SECOND				99.83 31	99.70 152	99.79 48	99.14 196	99.61 186					99.92 123	97.88 236	99.72 234	99.77 63

3Dnovator+	98.92 3	99.35 132	99.24 145	99.67 112	99.35 288	99.47 150	99.62 64	99.50 254	99.44 146	99.12 300	99.78 110	98.77 138	99.94 79	97.87 239	99.72 234	99.62 145

plane_prior						99.24 212	98.42 320		97.87 331						99.71 237

APD-MVS		98.87 241	98.59 252	99.71 101	99.50 240	99.62 119	99.01 238	99.57 214	96.80 375	99.54 204	99.63 203	98.29 204	99.91 145	95.24 382	99.71 237	99.61 155
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
APD_test1		99.36 130	99.28 137	99.61 151	99.89 38	99.89 10	99.32 135	99.74 115	99.18 187	99.69 144	99.75 127	98.41 190	99.84 262	97.85 242	99.70 239	99.10 316

SED-MVS		99.40 118	99.28 137	99.77 59	99.69 156	99.82 37	99.20 174	99.54 231	99.13 200	99.82 82	99.63 203	98.91 121	99.92 123	97.85 242	99.70 239	99.58 171

IU-MVS					99.69 156	99.77 56		99.22 324	97.50 348	99.69 144				97.75 251	99.70 239	99.77 63

ambc				99.20 266	99.35 288	98.53 285	99.17 186	99.46 265		99.67 152	99.80 90	98.46 184	99.70 345	97.92 232	99.70 239	99.38 250

MSC_two_6792asdad				99.74 81	99.03 359	99.53 143		99.23 321					99.92 123	97.77 247	99.69 243	99.78 59

No_MVS				99.74 81	99.03 359	99.53 143		99.23 321					99.92 123	97.77 247	99.69 243	99.78 59

test_241102_TWO								99.54 231	99.13 200	99.76 114	99.63 203	98.32 203	99.92 123	97.85 242	99.69 243	99.75 71

MVSFormer		99.41 116	99.44 98	99.31 244	99.57 205	98.40 294	99.77 16	99.80 84	99.73 78	99.63 164	99.30 315	98.02 228	99.98 21	99.43 76	99.69 243	99.55 181

lupinMVS		98.96 228	98.87 228	99.24 262	99.57 205	98.40 294	98.12 342	99.18 331	98.28 304	99.63 164	99.13 341	98.02 228	99.97 34	98.22 205	99.69 243	99.35 259

SF-MVS		99.10 199	98.93 218	99.62 148	99.58 195	99.51 145	99.13 202	99.65 166	97.97 322	99.42 237	99.61 219	98.86 126	99.87 210	96.45 344	99.68 248	99.49 216

Anonymous20240529		99.42 112	99.34 118	99.65 125	99.53 227	99.60 128	99.63 61	99.39 286	99.47 138	99.76 114	99.78 110	98.13 221	99.86 229	98.70 174	99.68 248	99.49 216

MSLP-MVS++		99.05 207	99.09 174	98.91 305	99.21 326	98.36 299	98.82 270	99.47 262	98.85 234	98.90 322	99.56 246	98.78 136	99.09 411	98.57 183	99.68 248	99.26 278

DELS-MVS		99.34 137	99.30 130	99.48 190	99.51 234	99.36 187	98.12 342	99.53 240	99.36 162	99.41 243	99.61 219	99.22 76	99.87 210	99.21 112	99.68 248	99.20 294
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
PVSNet	97.47 15	98.42 286	98.44 267	98.35 344	99.46 260	96.26 375	96.70 408	99.34 297	97.68 339	99.00 311	99.13 341	97.40 265	99.72 338	97.59 271	99.68 248	99.08 327

LS3D		99.24 156	99.11 165	99.61 151	98.38 405	99.79 48	99.57 82	99.68 146	99.61 116	99.15 295	99.71 150	98.70 147	99.91 145	97.54 273	99.68 248	99.13 313

HQP3-MVS								99.37 291							99.67 254

CPTT-MVS		98.74 252	98.44 267	99.64 132	99.61 183	99.38 180	99.18 181	99.55 225	96.49 377	99.27 276	99.37 298	97.11 280	99.92 123	95.74 373	99.67 254	99.62 145

HQP-MVS		98.36 291	98.02 304	99.39 220	99.31 304	98.94 249	97.98 359	99.37 291	97.45 350	98.15 372	98.83 378	96.67 291	99.70 345	94.73 388	99.67 254	99.53 194

MVS_Test		99.28 146	99.31 125	99.19 267	99.35 288	98.79 263	99.36 127	99.49 258	99.17 192	99.21 287	99.67 180	98.78 136	99.66 373	99.09 134	99.66 257	99.10 316

CDPH-MVS		98.56 271	98.20 290	99.61 151	99.50 240	99.46 154	98.32 326	99.41 276	95.22 394	99.21 287	99.10 349	98.34 200	99.82 287	95.09 386	99.66 257	99.56 178

tttt0517		97.62 328	97.20 338	98.90 311	99.76 117	97.40 349	99.48 102	94.36 412	99.06 209	99.70 141	99.49 268	84.55 402	99.94 79	98.73 172	99.65 259	99.36 256

ITE_SJBPF				99.38 223	99.63 178	99.44 161		99.73 119	98.56 269	99.33 261	99.53 257	98.88 125	99.68 363	96.01 360	99.65 259	99.02 343

ttmdpeth		99.48 91	99.55 79	99.29 248	99.76 117	98.16 311	99.33 132	99.95 30	99.79 70	99.36 253	99.89 38	99.13 88	99.77 323	99.09 134	99.64 261	99.93 18

9.14			98.64 247		99.45 264		98.81 271	99.60 197	97.52 347	99.28 275	99.56 246	98.53 174	99.83 277	95.36 381	99.64 261

Patchmatch-test		98.10 310	97.98 307	98.48 338	99.27 315	96.48 369	99.40 115	99.07 340	98.81 241	99.23 282	99.57 242	90.11 379	99.87 210	96.69 326	99.64 261	99.09 321

sss		98.90 236	98.77 240	99.27 254	99.48 250	98.44 291	98.72 284	99.32 300	97.94 326	99.37 252	99.35 307	96.31 306	99.91 145	98.85 156	99.63 264	99.47 224

cl22		97.56 331	97.28 335	98.40 342	98.37 406	96.75 365	97.24 398	99.37 291	97.31 358	99.41 243	99.22 333	87.30 388	99.37 408	97.70 258	99.62 265	99.08 327

miper_ehance_all_eth		98.59 268	98.59 252	98.59 333	98.98 365	97.07 358	97.49 388	99.52 245	98.50 277	99.52 211	99.37 298	96.41 302	99.71 342	97.86 240	99.62 265	99.00 345

miper_enhance_ethall		98.03 313	97.94 313	98.32 347	98.27 408	96.43 371	96.95 404	99.41 276	96.37 380	99.43 234	98.96 369	94.74 327	99.69 351	97.71 255	99.62 265	98.83 364

SCA		98.11 309	98.36 275	97.36 378	99.20 329	92.99 406	98.17 337	98.49 371	98.24 306	99.10 303	99.57 242	96.01 313	99.94 79	96.86 316	99.62 265	99.14 310

MS-PatchMatch		99.00 221	98.97 213	99.09 281	99.11 347	98.19 307	98.76 280	99.33 298	98.49 279	99.44 230	99.58 235	98.21 214	99.69 351	98.20 207	99.62 265	99.39 248

APD-MVS_3200maxsize		99.31 143	99.16 152	99.74 81	99.53 227	99.75 69	99.27 155	99.61 186	99.19 186	99.57 190	99.64 192	98.76 139	99.90 163	97.29 288	99.62 265	99.56 178

EPNet_dtu		97.62 328	97.79 322	97.11 386	96.67 421	92.31 409	98.51 310	98.04 386	99.24 178	95.77 413	99.47 275	93.78 338	99.66 373	98.98 144	99.62 265	99.37 253
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SR-MVS-dyc-post		99.27 150	99.11 165	99.73 90	99.54 221	99.74 75	99.26 157	99.62 179	99.16 194	99.52 211	99.64 192	98.41 190	99.91 145	97.27 291	99.61 272	99.54 189

RE-MVS-def			99.13 158		99.54 221	99.74 75	99.26 157	99.62 179	99.16 194	99.52 211	99.64 192	98.57 165		97.27 291	99.61 272	99.54 189

MG-MVS		98.52 275	98.39 272	98.94 299	99.15 337	97.39 350	98.18 335	99.21 327	98.89 230	99.23 282	99.63 203	97.37 268	99.74 333	94.22 395	99.61 272	99.69 88

DVP-MVS++		99.38 124	99.25 143	99.77 59	99.03 359	99.77 56	99.74 24	99.61 186	99.18 187	99.76 114	99.61 219	99.00 107	99.92 123	97.72 253	99.60 275	99.62 145

PC_three_1452									97.56 342	99.68 147	99.41 286	99.09 92	97.09 418	96.66 329	99.60 275	99.62 145

OPU-MVS				99.29 248	99.12 342	99.44 161	99.20 174				99.40 290	99.00 107	98.84 414	96.54 336	99.60 275	99.58 171

HPM-MVS++		98.96 228	98.70 245	99.74 81	99.52 232	99.71 85	98.86 261	99.19 330	98.47 281	98.59 353	99.06 352	98.08 225	99.91 145	96.94 311	99.60 275	99.60 159

mvsmamba		99.08 200	98.95 216	99.45 198	99.36 285	99.18 223	99.39 117	98.81 353	99.37 159	99.35 255	99.70 158	96.36 305	99.94 79	98.66 178	99.59 279	99.22 287

CNVR-MVS		98.99 224	98.80 238	99.56 168	99.25 319	99.43 165	98.54 306	99.27 312	98.58 268	98.80 334	99.43 283	98.53 174	99.70 345	97.22 299	99.59 279	99.54 189

Anonymous202405211		98.75 251	98.46 265	99.63 139	99.34 297	99.66 103	99.47 105	97.65 394	99.28 171	99.56 197	99.50 264	93.15 344	99.84 262	98.62 181	99.58 281	99.40 246

MVP-Stereo		99.16 185	99.08 176	99.43 206	99.48 250	99.07 237	99.08 221	99.55 225	98.63 262	99.31 269	99.68 176	98.19 217	99.78 315	98.18 211	99.58 281	99.45 229
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVStest1		98.22 304	98.09 299	98.62 330	99.04 358	96.23 376	99.20 174	99.92 34	99.44 146	99.98 13	99.87 52	85.87 399	99.67 368	99.91 24	99.57 283	99.95 13

ADS-MVSNet2		97.78 321	97.66 328	98.12 356	99.14 338	95.36 389	99.22 171	98.75 356	96.97 369	98.25 368	99.64 192	90.90 369	99.94 79	96.51 338	99.56 284	99.08 327

ADS-MVSNet		97.72 326	97.67 327	97.86 365	99.14 338	94.65 397	99.22 171	98.86 349	96.97 369	98.25 368	99.64 192	90.90 369	99.84 262	96.51 338	99.56 284	99.08 327

LCM-MVSNet-Re		99.28 146	99.15 155	99.67 112	99.33 302	99.76 63	99.34 129	99.97 19	98.93 223	99.91 46	99.79 100	98.68 149	99.93 97	96.80 321	99.56 284	99.30 272

API-MVS		98.38 290	98.39 272	98.35 344	98.83 379	99.26 205	99.14 196	99.18 331	98.59 267	98.66 347	98.78 382	98.61 160	99.57 392	94.14 396	99.56 284	96.21 415

xiu_mvs_v1_base_debu		99.23 157	99.34 118	98.91 305	99.59 190	98.23 303	98.47 314	99.66 156	99.61 116	99.68 147	98.94 371	99.39 52	99.97 34	99.18 118	99.55 288	98.51 384

xiu_mvs_v1_base		99.23 157	99.34 118	98.91 305	99.59 190	98.23 303	98.47 314	99.66 156	99.61 116	99.68 147	98.94 371	99.39 52	99.97 34	99.18 118	99.55 288	98.51 384

xiu_mvs_v1_base_debi		99.23 157	99.34 118	98.91 305	99.59 190	98.23 303	98.47 314	99.66 156	99.61 116	99.68 147	98.94 371	99.39 52	99.97 34	99.18 118	99.55 288	98.51 384

OpenMVS	98.12 10	98.23 302	97.89 318	99.26 257	99.19 331	99.26 205	99.65 59	99.69 143	91.33 410	98.14 376	99.77 119	98.28 205	99.96 55	95.41 379	99.55 288	98.58 380

MVE	92.54 22	96.66 354	96.11 358	98.31 349	99.68 164	97.55 343	97.94 364	95.60 409	99.37 159	90.68 420	98.70 386	96.56 294	98.61 416	86.94 417	99.55 288	98.77 370
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SR-MVS		99.19 175	99.00 202	99.74 81	99.51 234	99.72 83	99.18 181	99.60 197	98.85 234	99.47 224	99.58 235	98.38 195	99.92 123	96.92 312	99.54 293	99.57 176

thisisatest0530		97.45 334	96.95 345	98.94 299	99.68 164	97.73 338	99.09 218	94.19 414	98.61 266	99.56 197	99.30 315	84.30 403	99.93 97	98.27 200	99.54 293	99.16 303

tt0805		99.63 60	99.57 73	99.81 41	99.87 50	99.88 12	99.58 79	98.70 358	99.72 82	99.91 46	99.60 227	99.43 50	99.81 302	99.81 38	99.53 295	99.73 73

MSP-MVS		99.04 210	98.79 239	99.81 41	99.78 105	99.73 78	99.35 128	99.57 214	98.54 273	99.54 204	98.99 362	96.81 288	99.93 97	96.97 310	99.53 295	99.77 63
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
AdaColmap		98.60 265	98.35 277	99.38 223	99.12 342	99.22 215	98.67 287	99.42 275	97.84 334	98.81 332	99.27 321	97.32 270	99.81 302	95.14 384	99.53 295	99.10 316

ETV-MVS		99.18 179	99.18 150	99.16 270	99.34 297	99.28 201	99.12 206	99.79 90	99.48 134	98.93 316	98.55 392	99.40 51	99.93 97	98.51 186	99.52 298	98.28 394

SSC-MVS		99.52 83	99.42 102	99.83 31	99.86 53	99.65 109	99.52 89	99.81 81	99.87 43	99.81 89	99.79 100	96.78 289	99.99 8	99.83 33	99.51 299	99.86 34

EIA-MVS		99.12 193	99.01 198	99.45 198	99.36 285	99.62 119	99.34 129	99.79 90	98.41 285	98.84 329	98.89 375	98.75 141	99.84 262	98.15 215	99.51 299	98.89 358

MCST-MVS		99.02 213	98.81 236	99.65 125	99.58 195	99.49 147	98.58 297	99.07 340	98.40 287	99.04 309	99.25 326	98.51 179	99.80 309	97.31 287	99.51 299	99.65 119

mvs_anonymous		99.28 146	99.39 106	98.94 299	99.19 331	97.81 334	99.02 236	99.55 225	99.78 72	99.85 74	99.80 90	98.24 209	99.86 229	99.57 59	99.50 302	99.15 305

CNLPA		98.57 270	98.34 278	99.28 251	99.18 334	99.10 234	98.34 324	99.41 276	98.48 280	98.52 358	98.98 365	97.05 282	99.78 315	95.59 375	99.50 302	98.96 347

ZD-MVS					99.43 268	99.61 125		99.43 273	96.38 379	99.11 301	99.07 351	97.86 239	99.92 123	94.04 398	99.49 304

test_prior2							97.95 363		97.87 331	98.05 378	99.05 353	97.90 236		95.99 363	99.49 304

pmmvs3		98.08 311	97.80 320	98.91 305	99.41 275	97.69 340	97.87 370	99.66 156	95.87 385	99.50 219	99.51 261	90.35 377	99.97 34	98.55 184	99.47 306	99.08 327

test12				99.54 176	99.29 310	99.33 193		99.16 334		98.43 363		97.54 260	99.82 287		99.47 306	99.48 220

agg_prior2														94.58 391	99.46 308	99.50 211

test9_res														95.10 385	99.44 309	99.50 211

train_agg		98.35 294	97.95 309	99.57 165	99.35 288	99.35 190	98.11 344	99.41 276	94.90 398	97.92 382	98.99 362	98.02 228	99.85 247	95.38 380	99.44 309	99.50 211

VPNet		99.46 100	99.37 111	99.71 101	99.82 72	99.59 130	99.48 102	99.70 136	99.81 65	99.69 144	99.58 235	97.66 257	99.86 229	99.17 121	99.44 309	99.67 102

DP-MVS Recon		98.50 278	98.23 287	99.31 244	99.49 245	99.46 154	98.56 302	99.63 176	94.86 400	98.85 328	99.37 298	97.81 243	99.59 390	96.08 357	99.44 309	98.88 359

LFMVS		98.46 283	98.19 293	99.26 257	99.24 321	98.52 287	99.62 64	96.94 402	99.87 43	99.31 269	99.58 235	91.04 366	99.81 302	98.68 177	99.42 313	99.45 229

Fast-Effi-MVS+		99.02 213	98.87 228	99.46 195	99.38 280	99.50 146	99.04 230	99.79 90	97.17 364	98.62 350	98.74 384	99.34 62	99.95 64	98.32 197	99.41 314	98.92 354

PatchmatchNet		97.65 327	97.80 320	97.18 384	98.82 382	92.49 408	99.17 186	98.39 377	98.12 312	98.79 336	99.58 235	90.71 373	99.89 182	97.23 298	99.41 314	99.16 303
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0515		96.98 346	96.42 353	98.66 329	99.42 273	97.47 345	97.27 396	94.30 413	97.24 360	99.15 295	98.86 377	85.01 400	99.87 210	97.10 304	99.39 316	98.63 374

原ACMM1				99.37 226	99.47 256	98.87 258		99.27 312	96.74 376	98.26 367	99.32 311	97.93 235	99.82 287	95.96 365	99.38 317	99.43 240

test222					99.51 234	99.08 236	97.83 372	99.29 308	95.21 395	98.68 346	99.31 313	97.28 271			99.38 317	99.43 240

F-COLMAP		98.74 252	98.45 266	99.62 148	99.57 205	99.47 150	98.84 264	99.65 166	96.31 381	98.93 316	99.19 338	97.68 252	99.87 210	96.52 337	99.37 319	99.53 194

DPM-MVS		98.28 297	97.94 313	99.32 241	99.36 285	99.11 229	97.31 395	98.78 355	96.88 371	98.84 329	99.11 348	97.77 246	99.61 388	94.03 399	99.36 320	99.23 285

旧先验1					99.49 245	99.29 199		99.26 314			99.39 294	97.67 253			99.36 320	99.46 228

dmvs_re		98.69 258	98.48 263	99.31 244	99.55 219	99.42 168	99.54 87	98.38 378	99.32 166	98.72 342	98.71 385	96.76 290	99.21 409	96.01 360	99.35 322	99.31 270

PS-MVSNAJ		99.00 221	99.08 176	98.76 324	99.37 282	98.10 316	98.00 357	99.51 250	99.47 138	99.41 243	98.50 395	99.28 68	99.97 34	98.83 158	99.34 323	98.20 400

testing3		96.48 358	95.63 369	99.01 292	99.23 323	97.81 334	98.90 257	99.10 339	98.72 253	97.84 388	97.92 406	72.44 422	99.85 247	97.21 300	99.33 324	99.35 259

xiu_mvs_v2_base		99.02 213	99.11 165	98.77 323	99.37 282	98.09 317	98.13 341	99.51 250	99.47 138	99.42 237	98.54 393	99.38 56	99.97 34	98.83 158	99.33 324	98.24 396

新几何1				99.52 179	99.50 240	99.22 215		99.26 314	95.66 390	98.60 352	99.28 319	97.67 253	99.89 182	95.95 366	99.32 326	99.45 229

VDDNet		98.97 225	98.82 235	99.42 208	99.71 144	98.81 260	99.62 64	98.68 359	99.81 65	99.38 251	99.80 90	94.25 332	99.85 247	98.79 164	99.32 326	99.59 166

FA-MVS(test-final)		98.52 275	98.32 280	99.10 280	99.48 250	98.67 271	99.77 16	98.60 366	97.35 356	99.63 164	99.80 90	93.07 346	99.84 262	97.92 232	99.30 328	98.78 368

VNet		99.18 179	99.06 182	99.56 168	99.24 321	99.36 187	99.33 132	99.31 304	99.67 98	99.47 224	99.57 242	96.48 297	99.84 262	99.15 124	99.30 328	99.47 224

PatchMatch-RL		98.68 259	98.47 264	99.30 247	99.44 265	99.28 201	98.14 340	99.54 231	97.12 367	99.11 301	99.25 326	97.80 244	99.70 345	96.51 338	99.30 328	98.93 352

Effi-MVS+-dtu		99.07 203	98.92 222	99.52 179	98.89 373	99.78 51	99.15 194	99.66 156	99.34 163	98.92 319	99.24 331	97.69 251	99.98 21	98.11 217	99.28 331	98.81 365

testdata				99.42 208	99.51 234	98.93 252		99.30 307	96.20 382	98.87 326	99.40 290	98.33 202	99.89 182	96.29 350	99.28 331	99.44 234

OpenMVS_ROB	97.31 17	97.36 339	96.84 349	98.89 312	99.29 310	99.45 159	98.87 260	99.48 259	86.54 415	99.44 230	99.74 131	97.34 269	99.86 229	91.61 405	99.28 331	97.37 411

NCCC		98.82 245	98.57 256	99.58 159	99.21 326	99.31 196	98.61 290	99.25 317	98.65 260	98.43 363	99.26 324	97.86 239	99.81 302	96.55 335	99.27 334	99.61 155

testgi		99.29 145	99.26 141	99.37 226	99.75 129	98.81 260	98.84 264	99.89 45	98.38 289	99.75 119	99.04 355	99.36 61	99.86 229	99.08 136	99.25 335	99.45 229

PLC	97.35 16	98.36 291	97.99 305	99.48 190	99.32 303	99.24 212	98.50 311	99.51 250	95.19 396	98.58 354	98.96 369	96.95 285	99.83 277	95.63 374	99.25 335	99.37 253
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Fast-Effi-MVS+-dtu		99.20 172	99.12 162	99.43 206	99.25 319	99.69 96	99.05 225	99.82 72	99.50 131	98.97 312	99.05 353	98.98 111	99.98 21	98.20 207	99.24 337	98.62 375

PMMVS		98.49 280	98.29 285	99.11 278	98.96 367	98.42 293	97.54 383	99.32 300	97.53 346	98.47 361	98.15 402	97.88 238	99.82 287	97.46 278	99.24 337	99.09 321

WB-MVS		99.44 106	99.32 123	99.80 46	99.81 80	99.61 125	99.47 105	99.81 81	99.82 62	99.71 137	99.72 142	96.60 293	99.98 21	99.75 41	99.23 339	99.82 49

EPMVS		96.53 356	96.32 354	97.17 385	98.18 411	92.97 407	99.39 117	89.95 422	98.21 308	98.61 351	99.59 232	86.69 397	99.72 338	96.99 308	99.23 339	98.81 365

alignmvs		98.28 297	97.96 308	99.25 260	99.12 342	98.93 252	99.03 233	98.42 374	99.64 107	98.72 342	97.85 407	90.86 371	99.62 383	98.88 155	99.13 341	99.19 297

FE-MVS		97.85 318	97.42 332	99.15 272	99.44 265	98.75 266	99.77 16	98.20 384	95.85 386	99.33 261	99.80 90	88.86 385	99.88 196	96.40 345	99.12 342	98.81 365

cascas		96.99 345	96.82 351	97.48 374	97.57 420	95.64 386	96.43 410	99.56 219	91.75 408	97.13 402	97.61 413	95.58 318	98.63 415	96.68 327	99.11 343	98.18 401

BH-RMVSNet		98.41 287	98.14 296	99.21 264	99.21 326	98.47 288	98.60 292	98.26 382	98.35 296	98.93 316	99.31 313	97.20 277	99.66 373	94.32 393	99.10 344	99.51 206

RRT-MVS		99.08 200	99.00 202	99.33 236	99.27 315	98.65 277	99.62 64	99.93 32	99.66 102	99.67 152	99.82 80	95.27 323	99.93 97	98.64 180	99.09 345	99.41 244

UWE-MVS		96.21 366	95.78 366	97.49 373	98.53 400	93.83 403	98.04 352	93.94 416	98.96 217	98.46 362	98.17 401	79.86 410	99.87 210	96.99 308	99.06 346	98.78 368

MAR-MVS		98.24 301	97.92 315	99.19 267	98.78 387	99.65 109	99.17 186	99.14 336	95.36 392	98.04 379	98.81 381	97.47 262	99.72 338	95.47 378	99.06 346	98.21 398
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
GA-MVS		97.99 316	97.68 326	98.93 302	99.52 232	98.04 321	97.19 399	99.05 343	98.32 302	98.81 332	98.97 367	89.89 382	99.41 407	98.33 196	99.05 348	99.34 262

EMVS		96.96 347	97.28 335	95.99 398	98.76 390	91.03 417	95.26 415	98.61 364	99.34 163	98.92 319	98.88 376	93.79 337	99.66 373	92.87 402	99.05 348	97.30 412

E-PMN		97.14 344	97.43 331	96.27 395	98.79 385	91.62 414	95.54 413	99.01 346	99.44 146	98.88 323	99.12 345	92.78 349	99.68 363	94.30 394	99.03 350	97.50 408

tpmrst		97.73 323	98.07 301	96.73 390	98.71 394	92.00 410	99.10 214	98.86 349	98.52 275	98.92 319	99.54 255	91.90 356	99.82 287	98.02 222	99.03 350	98.37 391

PatchT		98.45 284	98.32 280	98.83 318	98.94 368	98.29 301	99.24 164	98.82 352	99.84 55	99.08 304	99.76 122	91.37 361	99.94 79	98.82 160	99.00 352	98.26 395

WB-MVSnew		98.34 296	98.14 296	98.96 296	98.14 414	97.90 331	98.27 329	97.26 401	98.63 262	98.80 334	98.00 405	97.77 246	99.90 163	97.37 284	98.98 353	99.09 321

CL-MVSNet_self_test		98.71 256	98.56 259	99.15 272	99.22 324	98.66 274	97.14 400	99.51 250	98.09 315	99.54 204	99.27 321	96.87 287	99.74 333	98.43 189	98.96 354	99.03 338

test_yl		98.25 299	97.95 309	99.13 276	99.17 335	98.47 288	99.00 241	98.67 361	98.97 215	99.22 285	99.02 360	91.31 362	99.69 351	97.26 293	98.93 355	99.24 281

DCV-MVSNet		98.25 299	97.95 309	99.13 276	99.17 335	98.47 288	99.00 241	98.67 361	98.97 215	99.22 285	99.02 360	91.31 362	99.69 351	97.26 293	98.93 355	99.24 281

MGCFI-Net		99.02 213	99.01 198	99.06 288	99.11 347	98.60 282	99.63 61	99.67 151	99.63 109	98.58 354	97.65 410	99.07 97	99.57 392	98.85 156	98.92 357	99.03 338

sasdasda		99.02 213	99.00 202	99.09 281	99.10 349	98.70 269	99.61 70	99.66 156	99.63 109	98.64 348	97.65 410	99.04 103	99.54 396	98.79 164	98.92 357	99.04 336

canonicalmvs		99.02 213	99.00 202	99.09 281	99.10 349	98.70 269	99.61 70	99.66 156	99.63 109	98.64 348	97.65 410	99.04 103	99.54 396	98.79 164	98.92 357	99.04 336

MDTV_nov1_ep13			97.73 324		98.70 395	90.83 418	99.15 194	98.02 387	98.51 276	98.82 331	99.61 219	90.98 367	99.66 373	96.89 315	98.92 357

PAPM_NR		98.36 291	98.04 302	99.33 236	99.48 250	98.93 252	98.79 277	99.28 311	97.54 345	98.56 357	98.57 390	97.12 279	99.69 351	94.09 397	98.90 361	99.38 250

FPMVS		96.32 362	95.50 370	98.79 322	99.60 185	98.17 310	98.46 318	98.80 354	97.16 365	96.28 409	99.63 203	82.19 404	99.09 411	88.45 411	98.89 362	99.10 316

tpm cat1		96.78 350	96.98 344	96.16 397	98.85 377	90.59 421	99.08 221	99.32 300	92.37 406	97.73 393	99.46 278	91.15 365	99.69 351	96.07 358	98.80 363	98.21 398

test-LLR		97.15 342	96.95 345	97.74 370	98.18 411	95.02 394	97.38 391	96.10 404	98.00 318	97.81 389	98.58 388	90.04 380	99.91 145	97.69 264	98.78 364	98.31 392

test-mter		96.23 365	95.73 367	97.74 370	98.18 411	95.02 394	97.38 391	96.10 404	97.90 327	97.81 389	98.58 388	79.12 415	99.91 145	97.69 264	98.78 364	98.31 392

TESTMET0.1,1		96.24 364	95.84 365	97.41 377	98.24 409	93.84 402	97.38 391	95.84 408	98.43 282	97.81 389	98.56 391	79.77 412	99.89 182	97.77 247	98.77 366	98.52 383

CR-MVSNet		98.35 294	98.20 290	98.83 318	99.05 355	98.12 313	99.30 143	99.67 151	97.39 354	99.16 293	99.79 100	91.87 358	99.91 145	98.78 168	98.77 366	98.44 389

RPMNet		98.60 265	98.53 261	98.83 318	99.05 355	98.12 313	99.30 143	99.62 179	99.86 46	99.16 293	99.74 131	92.53 352	99.92 123	98.75 170	98.77 366	98.44 389

WTY-MVS		98.59 268	98.37 274	99.26 257	99.43 268	98.40 294	98.74 282	99.13 338	98.10 313	99.21 287	99.24 331	94.82 326	99.90 163	97.86 240	98.77 366	99.49 216

UBG		96.53 356	95.95 361	98.29 351	98.87 376	96.31 374	98.48 313	98.07 385	98.83 238	97.32 395	96.54 425	79.81 411	99.62 383	96.84 319	98.74 370	98.95 349

Effi-MVS+		99.06 204	98.97 213	99.34 233	99.31 304	98.98 243	98.31 327	99.91 38	98.81 241	98.79 336	98.94 371	99.14 86	99.84 262	98.79 164	98.74 370	99.20 294

PAPR		97.56 331	97.07 341	99.04 290	98.80 383	98.11 315	97.63 379	99.25 317	94.56 403	98.02 380	98.25 400	97.43 264	99.68 363	90.90 408	98.74 370	99.33 263

Syy-MVS		98.17 307	97.85 319	99.15 272	98.50 402	98.79 263	98.60 292	99.21 327	97.89 328	96.76 404	96.37 427	95.47 321	99.57 392	99.10 133	98.73 373	99.09 321

myMVS_eth3d		95.63 379	94.73 381	98.34 346	98.50 402	96.36 372	98.60 292	99.21 327	97.89 328	96.76 404	96.37 427	72.10 423	99.57 392	94.38 392	98.73 373	99.09 321

tpmvs		97.39 337	97.69 325	96.52 392	98.41 404	91.76 412	99.30 143	98.94 348	97.74 336	97.85 387	99.55 253	92.40 355	99.73 336	96.25 352	98.73 373	98.06 403

dp		96.86 348	97.07 341	96.24 396	98.68 396	90.30 422	99.19 180	98.38 378	97.35 356	98.23 370	99.59 232	87.23 389	99.82 287	96.27 351	98.73 373	98.59 378

XVG-OURS-SEG-HR		99.16 185	98.99 209	99.66 119	99.84 61	99.64 112	98.25 332	99.73 119	98.39 288	99.63 164	99.43 283	99.70 24	99.90 163	97.34 285	98.64 377	99.44 234

thres600view7		96.60 355	96.16 357	97.93 362	99.63 178	96.09 380	99.18 181	97.57 395	98.77 248	98.72 342	97.32 415	87.04 391	99.72 338	88.57 410	98.62 378	97.98 404

thres200		96.09 368	95.68 368	97.33 380	99.48 250	96.22 377	98.53 308	97.57 395	98.06 317	98.37 365	96.73 422	86.84 395	99.61 388	86.99 416	98.57 379	96.16 416

1314		98.00 315	97.90 317	98.27 352	98.90 370	97.45 347	99.30 143	99.06 342	94.98 397	97.21 399	99.12 345	98.43 187	99.67 368	95.58 376	98.56 380	97.71 407

dmvs_testset		97.27 340	96.83 350	98.59 333	99.46 260	97.55 343	99.25 163	96.84 403	98.78 246	97.24 398	97.67 409	97.11 280	98.97 413	86.59 418	98.54 381	99.27 276

thres100view900		96.39 360	96.03 360	97.47 375	99.63 178	95.93 381	99.18 181	97.57 395	98.75 252	98.70 345	97.31 416	87.04 391	99.67 368	87.62 413	98.51 382	96.81 413

tfpn200view9		96.30 363	95.89 362	97.53 372	99.58 195	96.11 378	99.00 241	97.54 398	98.43 282	98.52 358	96.98 418	86.85 393	99.67 368	87.62 413	98.51 382	96.81 413

thres400		96.40 359	95.89 362	97.92 363	99.58 195	96.11 378	99.00 241	97.54 398	98.43 282	98.52 358	96.98 418	86.85 393	99.67 368	87.62 413	98.51 382	97.98 404

MVS		95.72 378	94.63 383	98.99 293	98.56 399	97.98 328	99.30 143	98.86 349	72.71 419	97.30 396	99.08 350	98.34 200	99.74 333	89.21 409	98.33 385	99.26 278

BH-untuned		98.22 304	98.09 299	98.58 335	99.38 280	97.24 353	98.55 303	98.98 347	97.81 335	99.20 292	98.76 383	97.01 283	99.65 379	94.83 387	98.33 385	98.86 361

testing11		96.05 370	95.41 372	97.97 360	98.78 387	95.27 391	98.59 295	98.23 383	98.86 233	96.56 407	96.91 420	75.20 418	99.69 351	97.26 293	98.29 387	98.93 352

test_method		91.72 384	92.32 387	89.91 402	93.49 425	70.18 428	90.28 416	99.56 219	61.71 420	95.39 415	99.52 259	93.90 334	99.94 79	98.76 169	98.27 388	99.62 145

testing91		96.00 371	95.32 375	98.02 357	98.76 390	95.39 388	98.38 322	98.65 363	98.82 239	96.84 403	96.71 423	75.06 419	99.71 342	96.46 343	98.23 389	98.98 346

gg-mvs-nofinetune		95.87 374	95.17 379	97.97 360	98.19 410	96.95 360	99.69 42	89.23 423	99.89 37	96.24 411	99.94 19	81.19 405	99.51 402	93.99 400	98.20 390	97.44 409

HY-MVS	98.23 9	98.21 306	97.95 309	98.99 293	99.03 359	98.24 302	99.61 70	98.72 357	96.81 374	98.73 341	99.51 261	94.06 333	99.86 229	96.91 313	98.20 390	98.86 361

UnsupCasMVSNet_bld		98.55 272	98.27 286	99.40 217	99.56 216	99.37 183	97.97 362	99.68 146	97.49 349	99.08 304	99.35 307	95.41 322	99.82 287	97.70 258	98.19 392	99.01 344

tpm2		96.35 361	96.22 356	96.73 390	98.88 375	91.75 413	99.21 173	98.51 369	93.27 405	97.89 384	99.21 335	84.83 401	99.70 345	96.04 359	98.18 393	98.75 372

testing222		95.60 381	94.59 384	98.61 331	98.66 397	97.45 347	98.54 306	97.90 391	98.53 274	96.54 408	96.47 426	70.62 425	99.81 302	95.91 368	98.15 394	98.56 382

tmp_tt		95.75 377	95.42 371	96.76 388	89.90 426	94.42 398	98.86 261	97.87 392	78.01 417	99.30 274	99.69 165	97.70 249	95.89 419	99.29 104	98.14 395	99.95 13

baseline2		96.83 349	96.28 355	98.46 340	99.09 352	96.91 362	98.83 266	93.87 417	97.23 361	96.23 412	98.36 397	88.12 387	99.90 163	96.68 327	98.14 395	98.57 381

ETVMVS		96.14 367	95.22 377	98.89 312	98.80 383	98.01 322	98.66 288	98.35 380	98.71 255	97.18 400	96.31 429	74.23 421	99.75 330	96.64 332	98.13 397	98.90 356

CostFormer		96.71 353	96.79 352	96.46 394	98.90 370	90.71 420	99.41 114	98.68 359	94.69 402	98.14 376	99.34 310	86.32 398	99.80 309	97.60 270	98.07 398	98.88 359

testing99		95.86 375	95.19 378	97.87 364	98.76 390	95.03 393	98.62 289	98.44 373	98.68 257	96.67 406	96.66 424	74.31 420	99.69 351	96.51 338	98.03 399	98.90 356

AUN-MVS		97.82 319	97.38 333	99.14 275	99.27 315	98.53 285	98.72 284	99.02 344	98.10 313	97.18 400	99.03 359	89.26 384	99.85 247	97.94 231	97.91 400	99.03 338

DeepMVS_CX				97.98 359	99.69 156	96.95 360		99.26 314	75.51 418	95.74 414	98.28 399	96.47 298	99.62 383	91.23 407	97.89 401	97.38 410

hse-mvs2		98.52 275	98.30 283	99.16 270	99.29 310	98.60 282	98.77 279	99.02 344	99.68 94	99.32 264	99.04 355	92.50 353	99.85 247	99.24 108	97.87 402	99.03 338

PAPM		95.61 380	94.71 382	98.31 349	99.12 342	96.63 366	96.66 409	98.46 372	90.77 411	96.25 410	98.68 387	93.01 347	99.69 351	81.60 419	97.86 403	98.62 375

JIA-IIPM		98.06 312	97.92 315	98.50 337	98.59 398	97.02 359	98.80 274	98.51 369	99.88 42	97.89 384	99.87 52	91.89 357	99.90 163	98.16 214	97.68 404	98.59 378

ET-MVSNet_ETH3D		96.78 350	96.07 359	98.91 305	99.26 318	97.92 330	97.70 377	96.05 407	97.96 325	92.37 419	98.43 396	87.06 390	99.90 163	98.27 200	97.56 405	98.91 355

dongtai		89.37 385	88.91 388	90.76 401	99.19 331	77.46 426	95.47 414	87.82 425	92.28 407	94.17 418	98.82 380	71.22 424	95.54 420	63.85 420	97.34 406	99.27 276

TR-MVS		97.44 335	97.15 340	98.32 347	98.53 400	97.46 346	98.47 314	97.91 390	96.85 372	98.21 371	98.51 394	96.42 300	99.51 402	92.16 404	97.29 407	97.98 404

BH-w/o		97.20 341	97.01 343	97.76 368	99.08 353	95.69 385	98.03 354	98.52 368	95.76 388	97.96 381	98.02 403	95.62 317	99.47 404	92.82 403	97.25 408	98.12 402

KD-MVS_2432*1600		95.89 372	95.41 372	97.31 381	94.96 422	93.89 400	97.09 401	99.22 324	97.23 361	98.88 323	99.04 355	79.23 413	99.54 396	96.24 353	96.81 409	98.50 387

miper_refine_blended		95.89 372	95.41 372	97.31 381	94.96 422	93.89 400	97.09 401	99.22 324	97.23 361	98.88 323	99.04 355	79.23 413	99.54 396	96.24 353	96.81 409	98.50 387

UnsupCasMVSNet_eth		98.83 244	98.57 256	99.59 156	99.68 164	99.45 159	98.99 246	99.67 151	99.48 134	99.55 202	99.36 302	94.92 324	99.86 229	98.95 152	96.57 411	99.45 229

h-mvs33		98.61 262	98.34 278	99.44 202	99.60 185	98.67 271	99.27 155	99.44 270	99.68 94	99.32 264	99.49 268	92.50 353	100.00 1	99.24 108	96.51 412	99.65 119

GG-mvs-BLEND				97.36 378	97.59 418	96.87 363	99.70 35	88.49 424		94.64 417	97.26 417	80.66 407	99.12 410	91.50 406	96.50 413	96.08 417

tpm		97.15 342	96.95 345	97.75 369	98.91 369	94.24 399	99.32 135	97.96 388	97.71 338	98.29 366	99.32 311	86.72 396	99.92 123	98.10 220	96.24 414	99.09 321

MonoMVSNet		98.23 302	98.32 280	97.99 358	98.97 366	96.62 367	99.49 100	98.42 374	99.62 112	99.40 248	99.79 100	95.51 320	98.58 417	97.68 266	95.98 415	98.76 371

test0.0.03 1		97.37 338	96.91 348	98.74 325	97.72 417	97.57 342	97.60 381	97.36 400	98.00 318	99.21 287	98.02 403	90.04 380	99.79 312	98.37 192	95.89 416	98.86 361

kuosan		85.65 387	84.57 390	88.90 403	97.91 415	77.11 427	96.37 411	87.62 426	85.24 416	85.45 421	96.83 421	69.94 426	90.98 422	45.90 421	95.83 417	98.62 375

IB-MVS	95.41 20	95.30 382	94.46 386	97.84 366	98.76 390	95.33 390	97.33 394	96.07 406	96.02 384	95.37 416	97.41 414	76.17 417	99.96 55	97.54 273	95.44 418	98.22 397
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
baseline1		97.73 323	97.33 334	98.96 296	99.30 308	97.73 338	99.40 115	98.42 374	99.33 165	99.46 228	99.21 335	91.18 364	99.82 287	98.35 194	91.26 419	99.32 266

PVSNet_0	95.53 19	95.85 376	95.31 376	97.47 375	98.78 387	93.48 405	95.72 412	99.40 283	96.18 383	97.37 394	97.73 408	95.73 315	99.58 391	95.49 377	81.40 420	99.36 256

testmvs		28.94 389	33.33 391	15.79 405	26.03 427	9.81 430	96.77 407	15.67 428	11.55 423	23.87 424	50.74 433	19.03 428	8.53 424	23.21 423	33.07 421	29.03 420

test123		29.31 388	33.05 393	18.08 404	25.93 428	12.24 429	97.53 385	10.93 429	11.78 422	24.21 423	50.08 434	21.04 427	8.60 423	23.51 422	32.43 422	33.39 419

mmdepth		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet_test		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

cdsmvs_eth3d_5k		24.88 390	33.17 392	0.00 406	0.00 429	0.00 431	0.00 417	99.62 179	0.00 424	0.00 425	99.13 341	99.82 13	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		16.61 391	22.14 394	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	99.28 68	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

ab-mvs-re		8.26 402	11.02 405	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	99.16 339	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		8.33 392	11.11 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	100.00 1	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						96.36 372								95.20 383

FOURS1					99.83 65	99.89 10	99.74 24	99.71 131	99.69 92	99.63 164

test_one_0601					99.63 178	99.76 63		99.55 225	99.23 180	99.31 269	99.61 219	98.59 162

eth-test2					0.00 429

eth-test					0.00 429

test_241102_ONE					99.69 156	99.82 37		99.54 231	99.12 203	99.82 82	99.49 268	98.91 121	99.52 401

save fliter					99.53 227	99.25 208	98.29 328	99.38 290	99.07 207

test0726					99.69 156	99.80 46	99.24 164	99.57 214	99.16 194	99.73 131	99.65 190	98.35 198

GSMVS																99.14 310

test_part2					99.62 182	99.67 101				99.55 202

sam_mvs1												90.81 372				99.14 310

sam_mvs												90.52 376

MTGPA								99.53 240

test_post1							99.14 196				51.63 432	89.54 383	99.82 287	96.86 316

test_post											52.41 431	90.25 378	99.86 229

patchmatchnet-post											99.62 210	90.58 374	99.94 79

MTMP							99.09 218	98.59 367

gm-plane-assit					97.59 418	89.02 424			93.47 404		98.30 398		99.84 262	96.38 347

TEST9					99.35 288	99.35 190	98.11 344	99.41 276	94.83 401	97.92 382	98.99 362	98.02 228	99.85 247

test_8					99.34 297	99.31 196	98.08 348	99.40 283	94.90 398	97.87 386	98.97 367	98.02 228	99.84 262

agg_prior					99.35 288	99.36 187		99.39 286		97.76 392			99.85 247

test_prior4						99.19 221	98.00 357

test_prior				99.46 195	99.35 288	99.22 215		99.39 286					99.69 351			99.48 220

旧先验2							97.94 364		95.33 393	98.94 315			99.88 196	96.75 323

新几何2							98.04 352

无先验							98.01 355	99.23 321	95.83 387				99.85 247	95.79 372		99.44 234

原ACMM2							97.92 366

testdata2													99.89 182	95.99 363

segment_acmp												98.37 196

testdata1							97.72 375		97.86 333

plane_prior7					99.58 195	99.38 180

plane_prior6					99.47 256	99.26 205						97.24 272

plane_prior4											99.25 326

plane_prior3						99.31 196			98.36 291	99.14 297

plane_prior2							98.80 274		98.94 220

plane_prior1					99.51 234

n2								0.00 430

nn								0.00 430

door-mid								99.83 67

test11								99.29 308

door								99.77 99

HQP5-MVS						98.94 249

HQP-NCC					99.31 304		97.98 359		97.45 350	98.15 372

ACMP_Plane					99.31 304		97.98 359		97.45 350	98.15 372

BP-MVS														94.73 388

HQP4-MVS										98.15 372			99.70 345			99.53 194

HQP2-MVS												96.67 291

NP-MVS					99.40 276	99.13 227					98.83 378

MDTV_nov1_ep13_2view						91.44 416	99.14 196		97.37 355	99.21 287		91.78 360		96.75 323		99.03 338

Test By Simon												98.41 190

High-resolution multi-view benchmark