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.

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 12	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 10	100.00 1	99.85 22

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 66	99.87 12	98.13 133	98.08 168	99.95 1	99.45 37	99.98 2	99.75 13	99.80 1	99.97 5	99.82 7	99.99 5	99.99 2

test_fmvsmconf0.1_n		99.49 12	99.54 11	99.34 75	99.78 23	98.11 134	97.77 214	99.90 11	99.33 51	99.97 3	99.66 29	99.71 3	99.96 12	99.79 12	99.99 5	99.96 7

test_cas_vis1_n_1920		98.33 166	98.68 101	97.27 311	99.69 54	92.29 360	98.03 176	99.85 17	97.62 196	99.96 4	99.62 36	93.98 283	99.74 240	99.52 33	99.86 80	99.79 32

mvsany_test3		98.87 82	98.92 71	98.74 179	99.38 140	96.94 226	98.58 111	99.10 232	96.49 282	99.96 4	99.81 6	98.18 84	99.45 354	98.97 66	99.79 115	99.83 24

test_fmvsm_n_1920		99.33 27	99.45 19	98.99 137	99.57 81	97.73 180	97.93 191	99.83 22	99.22 61	99.93 6	99.30 101	99.42 10	99.96 12	99.85 5	99.99 5	99.29 218

ANet_high		99.57 7	99.67 5	99.28 87	99.89 6	98.09 137	99.14 54	99.93 5	99.82 5	99.93 6	99.81 6	99.17 18	99.94 36	99.31 42	100.00 1	99.82 27

test_fmvsmconf_n		99.44 15	99.48 15	99.31 85	99.64 69	98.10 136	97.68 225	99.84 20	99.29 56	99.92 8	99.57 45	99.60 5	99.96 12	99.74 17	99.98 12	99.89 14

test_fmvsmvis_n_1920		99.26 35	99.49 13	98.54 207	99.66 62	96.97 222	98.00 182	99.85 17	99.24 60	99.92 8	99.50 62	99.39 11	99.95 24	99.89 3	99.98 12	98.71 315

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 130	99.20 45	99.65 48	99.48 33	99.92 8	99.71 19	98.07 93	99.96 12	99.53 31	100.00 1	99.93 10

test_vis3_rt		99.14 49	99.17 46	99.07 122	99.78 23	98.38 111	98.92 79	99.94 2	97.80 185	99.91 11	99.67 27	97.15 162	98.91 398	99.76 15	99.56 215	99.92 11

fmvsm_s_conf0.1_n		99.16 47	99.33 29	98.64 184	99.71 45	96.10 251	97.87 202	99.85 17	98.56 130	99.90 12	99.68 22	98.69 41	99.85 126	99.72 20	99.98 12	99.97 4

mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 36	99.27 58	99.90 12	99.74 15	99.68 4	99.97 5	99.55 30	99.99 5	99.88 17

wuyk23d		96.06 308	97.62 225	91.38 398	98.65 301	98.57 98	98.85 87	96.95 361	96.86 266	99.90 12	99.16 134	99.18 17	98.40 406	89.23 395	99.77 125	77.18 418

test_vis1_n_1920		98.40 156	98.92 71	96.81 334	99.74 35	90.76 385	98.15 158	99.91 9	98.33 140	99.89 15	99.55 52	95.07 253	99.88 89	99.76 15	99.93 43	99.79 32

jajsoiax		99.58 6	99.61 8	99.48 53	99.87 12	98.61 94	99.28 37	99.66 47	99.09 86	99.89 15	99.68 22	99.53 7	99.97 5	99.50 34	99.99 5	99.87 18

fmvsm_s_conf0.1_n_a		99.17 44	99.30 35	98.80 163	99.75 33	96.59 240	97.97 190	99.86 15	98.22 151	99.88 17	99.71 19	98.59 50	99.84 144	99.73 18	99.98 12	99.98 3

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 19	99.69 5	99.58 58	99.90 3	99.86 18	99.78 10	99.58 6	99.95 24	99.00 64	99.95 30	99.78 35

fmvsm_s_conf0.5_n		99.09 57	99.26 40	98.61 192	99.55 93	96.09 254	97.74 219	99.81 25	98.55 131	99.85 19	99.55 52	98.60 49	99.84 144	99.69 23	99.98 12	99.89 14

pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 31	99.64 19	99.84 20	99.83 4	99.50 8	99.87 106	99.36 39	99.92 54	99.64 66

fmvsm_l_conf0.5_n		99.21 41	99.28 37	99.02 134	99.64 69	97.28 204	97.82 207	99.76 31	98.73 114	99.82 21	99.09 150	98.81 32	99.95 24	99.86 4	99.96 23	99.83 24

test_fmvs3		99.12 54	99.41 21	98.25 238	99.76 29	95.07 289	99.05 64	99.94 2	97.78 187	99.82 21	99.84 3	98.56 54	99.71 253	99.96 1	99.96 23	99.97 4

mamv4		99.44 15	99.39 23	99.58 19	99.30 159	99.74 2	99.04 65	99.81 25	99.77 7	99.82 21	99.57 45	97.82 112	99.98 4	99.53 31	99.89 71	99.01 266

fmvsm_s_conf0.5_n_a		99.10 56	99.20 44	98.78 169	99.55 93	96.59 240	97.79 211	99.82 24	98.21 152	99.81 24	99.53 58	98.46 60	99.84 144	99.70 21	99.97 19	99.90 13

Anonymous20231211		99.27 33	99.27 38	99.26 92	99.29 161	98.18 128	99.49 9	99.51 87	99.70 12	99.80 25	99.68 22	96.84 178	99.83 161	99.21 51	99.91 61	99.77 37

test_vis1_n		98.31 169	98.50 126	97.73 278	99.76 29	94.17 313	98.68 102	99.91 9	96.31 290	99.79 26	99.57 45	92.85 302	99.42 359	99.79 12	99.84 85	99.60 79

fmvsm_l_conf0.5_n_a		99.19 43	99.27 38	98.94 144	99.65 63	97.05 218	97.80 210	99.76 31	98.70 117	99.78 27	99.11 144	98.79 34	99.95 24	99.85 5	99.96 23	99.83 24

test_f		98.67 119	98.87 76	98.05 255	99.72 42	95.59 266	98.51 123	99.81 25	96.30 292	99.78 27	99.82 5	96.14 213	98.63 404	99.82 7	99.93 43	99.95 8

OurMVSNet-221017-0		99.37 25	99.31 33	99.53 37	99.91 3	98.98 69	99.63 7	99.58 58	99.44 39	99.78 27	99.76 12	96.39 203	99.92 51	99.44 37	99.92 54	99.68 56

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 25	99.85 16	99.11 63	99.90 1	99.78 29	99.63 21	99.78 27	99.67 27	99.48 9	99.81 185	99.30 43	99.97 19	99.77 37
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
TransMVSNet (Re)		99.44 15	99.47 17	99.36 66	99.80 20	98.58 97	99.27 39	99.57 65	99.39 44	99.75 31	99.62 36	99.17 18	99.83 161	99.06 59	99.62 192	99.66 60

test_fmvs2		98.70 108	98.97 68	97.89 262	99.54 98	94.05 316	98.55 114	99.92 7	96.78 270	99.72 32	99.78 10	96.60 195	99.67 273	99.91 2	99.90 67	99.94 9

NR-MVSNet		98.95 73	98.82 82	99.36 66	99.16 195	98.72 89	99.22 42	99.20 207	99.10 83	99.72 32	98.76 227	96.38 205	99.86 114	98.00 127	99.82 95	99.50 130

mvsany_test1		97.60 230	97.54 228	97.77 270	97.72 363	95.35 277	95.36 366	97.13 355	94.13 351	99.71 34	99.33 95	97.93 105	99.30 376	97.60 153	98.94 314	98.67 323

MIMVSNet1		99.38 24	99.32 31	99.55 27	99.86 14	99.19 41	99.41 14	99.59 56	99.59 27	99.71 34	99.57 45	97.12 163	99.90 66	99.21 51	99.87 76	99.54 113

test_djsdf		99.52 10	99.51 12	99.53 37	99.86 14	98.74 84	99.39 17	99.56 72	99.11 76	99.70 36	99.73 17	99.00 22	99.97 5	99.26 46	99.98 12	99.89 14

SixPastTwentyTwo		98.75 100	98.62 110	99.16 107	99.83 18	97.96 157	99.28 37	98.20 325	99.37 46	99.70 36	99.65 33	92.65 306	99.93 42	99.04 61	99.84 85	99.60 79

new-patchmatchnet		98.35 162	98.74 88	97.18 314	99.24 171	92.23 362	96.42 313	99.48 98	98.30 143	99.69 38	99.53 58	97.44 146	99.82 171	98.84 74	99.77 125	99.49 134

LCM-MVSNet-Re		98.64 123	98.48 131	99.11 114	98.85 256	98.51 104	98.49 126	99.83 22	98.37 137	99.69 38	99.46 70	98.21 82	99.92 51	94.13 326	99.30 263	98.91 287

test_fmvs1_n		98.09 191	98.28 160	97.52 297	99.68 56	93.47 339	98.63 105	99.93 5	95.41 323	99.68 40	99.64 34	91.88 315	99.48 347	99.82 7	99.87 76	99.62 70

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 54	99.66 17	99.68 40	99.66 29	98.44 61	99.95 24	99.73 18	99.96 23	99.75 46

SSC-MVS		98.71 104	98.74 88	98.62 189	99.72 42	96.08 256	98.74 92	98.64 305	99.74 10	99.67 42	99.24 115	94.57 268	99.95 24	99.11 55	99.24 272	99.82 27

SED-MVS		98.91 77	98.72 92	99.49 51	99.49 115	99.17 43	98.10 166	99.31 168	98.03 166	99.66 43	99.02 163	98.36 65	99.88 89	96.91 195	99.62 192	99.41 171

test_241102_ONE					99.49 115	99.17 43		99.31 168	97.98 169	99.66 43	98.90 197	98.36 65	99.48 347

dcpmvs_2		98.78 95	99.11 54	97.78 269	99.56 89	93.67 335	99.06 62	99.86 15	99.50 32	99.66 43	99.26 110	97.21 160	99.99 2	98.00 127	99.91 61	99.68 56

anonymousdsp		99.51 11	99.47 17	99.62 9	99.88 9	99.08 67	99.34 20	99.69 39	98.93 104	99.65 46	99.72 18	98.93 26	99.95 24	99.11 55	100.00 1	99.82 27

pm-mvs1		99.44 15	99.48 15	99.33 80	99.80 20	98.63 91	99.29 33	99.63 50	99.30 55	99.65 46	99.60 41	99.16 20	99.82 171	99.07 58	99.83 92	99.56 102

ACMH	96.65 7	99.25 36	99.24 42	99.26 92	99.72 42	98.38 111	99.07 61	99.55 76	98.30 143	99.65 46	99.45 74	99.22 15	99.76 228	98.44 100	99.77 125	99.64 66
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SDMVSNet		99.23 40	99.32 31	98.96 141	99.68 56	97.35 200	98.84 89	99.48 98	99.69 13	99.63 49	99.68 22	99.03 21	99.96 12	97.97 129	99.92 54	99.57 96

sd_testset		99.28 32	99.31 33	99.19 103	99.68 56	98.06 146	99.41 14	99.30 176	99.69 13	99.63 49	99.68 22	99.25 14	99.96 12	97.25 170	99.92 54	99.57 96

SD-MVS		98.40 156	98.68 101	97.54 295	98.96 233	97.99 150	97.88 199	99.36 145	98.20 156	99.63 49	99.04 160	98.76 35	95.33 418	96.56 233	99.74 141	99.31 213
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
KD-MVS_self_test		99.25 36	99.18 45	99.44 59	99.63 73	99.06 68	98.69 101	99.54 80	99.31 53	99.62 52	99.53 58	97.36 150	99.86 114	99.24 50	99.71 157	99.39 181

MVStest1		95.86 315	95.60 311	96.63 339	95.87 415	91.70 366	97.93 191	98.94 256	98.03 166	99.56 53	99.66 29	71.83 404	98.26 408	99.35 40	99.24 272	99.91 12

PEN-MVS		99.41 21	99.34 28	99.62 9	99.73 36	99.14 56	99.29 33	99.54 80	99.62 24	99.56 53	99.42 77	98.16 88	99.96 12	98.78 76	99.93 43	99.77 37

DTE-MVSNet		99.43 19	99.35 26	99.66 7	99.71 45	99.30 21	99.31 27	99.51 87	99.64 19	99.56 53	99.46 70	98.23 77	99.97 5	98.78 76	99.93 43	99.72 48

casdiffmvs_mvg		99.12 54	99.16 48	98.99 137	99.43 134	97.73 180	98.00 182	99.62 51	99.22 61	99.55 56	99.22 120	98.93 26	99.75 235	98.66 87	99.81 99	99.50 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvs1		97.72 222	97.94 200	97.07 321	98.66 297	92.39 357	97.68 225	99.81 25	95.20 327	99.54 57	99.44 75	91.56 318	99.41 360	99.78 14	99.77 125	99.40 180

Anonymous20240529		98.93 75	98.87 76	99.12 112	99.19 185	98.22 127	99.01 67	98.99 254	99.25 59	99.54 57	99.37 84	97.04 167	99.80 192	97.89 132	99.52 227	99.35 200

EU-MVSNet		97.66 227	98.50 126	95.13 376	99.63 73	85.84 406	98.35 142	98.21 324	98.23 150	99.54 57	99.46 70	95.02 254	99.68 270	98.24 109	99.87 76	99.87 18

DeepC-MVS	97.60 4	98.97 70	98.93 70	99.10 116	99.35 151	97.98 153	98.01 181	99.46 109	97.56 204	99.54 57	99.50 62	98.97 23	99.84 144	98.06 122	99.92 54	99.49 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TDRefinement		99.42 20	99.38 24	99.55 27	99.76 29	99.33 20	99.68 6	99.71 36	99.38 45	99.53 61	99.61 39	98.64 44	99.80 192	98.24 109	99.84 85	99.52 124

ACMH+	96.62 9	99.08 61	99.00 64	99.33 80	99.71 45	98.83 79	98.60 109	99.58 58	99.11 76	99.53 61	99.18 128	98.81 32	99.67 273	96.71 219	99.77 125	99.50 130

reproduce_model		99.15 48	98.97 68	99.67 4	99.33 154	99.44 10	98.15 158	99.47 106	99.12 75	99.52 63	99.32 99	98.31 71	99.90 66	97.78 141	99.73 144	99.66 60

WB-MVS		98.52 145	98.55 119	98.43 221	99.65 63	95.59 266	98.52 118	98.77 291	99.65 18	99.52 63	99.00 175	94.34 274	99.93 42	98.65 88	98.83 319	99.76 42

v8		99.01 64	99.16 48	98.57 199	99.47 124	96.31 248	98.90 80	99.47 106	99.03 94	99.52 63	99.57 45	96.93 174	99.81 185	99.60 25	99.98 12	99.60 79

VPA-MVSNet		99.30 29	99.30 35	99.28 87	99.49 115	98.36 116	99.00 69	99.45 113	99.63 21	99.52 63	99.44 75	98.25 75	99.88 89	99.09 57	99.84 85	99.62 70

K. test v3		98.00 197	97.66 221	99.03 132	99.79 22	97.56 189	99.19 49	92.47 404	99.62 24	99.52 63	99.66 29	89.61 332	99.96 12	99.25 48	99.81 99	99.56 102

tfpnnormal		98.90 79	98.90 73	98.91 150	99.67 60	97.82 170	99.00 69	99.44 117	99.45 37	99.51 68	99.24 115	98.20 83	99.86 114	95.92 270	99.69 167	99.04 262

WR-MVS_H		99.33 27	99.22 43	99.65 8	99.71 45	99.24 29	99.32 23	99.55 76	99.46 36	99.50 69	99.34 93	97.30 152	99.93 42	98.90 69	99.93 43	99.77 37

reproduce-ours		99.09 57	98.90 73	99.67 4	99.27 164	99.49 6	98.00 182	99.42 126	99.05 91	99.48 70	99.27 106	98.29 73	99.89 77	97.61 151	99.71 157	99.62 70

our_new_method		99.09 57	98.90 73	99.67 4	99.27 164	99.49 6	98.00 182	99.42 126	99.05 91	99.48 70	99.27 106	98.29 73	99.89 77	97.61 151	99.71 157	99.62 70

v10		98.97 70	99.11 54	98.55 204	99.44 129	96.21 250	98.90 80	99.55 76	98.73 114	99.48 70	99.60 41	96.63 194	99.83 161	99.70 21	99.99 5	99.61 78

DP-MVS		98.93 75	98.81 84	99.28 87	99.21 178	98.45 108	98.46 131	99.33 161	99.63 21	99.48 70	99.15 138	97.23 158	99.75 235	97.17 173	99.66 183	99.63 69

N_pmnet		97.63 229	97.17 250	98.99 137	99.27 164	97.86 164	95.98 336	93.41 401	95.25 325	99.47 74	98.90 197	95.63 237	99.85 126	96.91 195	99.73 144	99.27 221

test1111		96.49 297	96.82 271	95.52 369	99.42 135	87.08 403	99.22 42	87.14 417	99.11 76	99.46 75	99.58 43	88.69 338	99.86 114	98.80 75	99.95 30	99.62 70

nrg030		99.40 22	99.35 26	99.54 30	99.58 76	99.13 59	98.98 72	99.48 98	99.68 15	99.46 75	99.26 110	98.62 47	99.73 245	99.17 54	99.92 54	99.76 42

PS-CasMVS		99.40 22	99.33 29	99.62 9	99.71 45	99.10 64	99.29 33	99.53 83	99.53 31	99.46 75	99.41 81	98.23 77	99.95 24	98.89 71	99.95 30	99.81 30

v1240		98.55 138	98.62 110	98.32 232	99.22 176	95.58 268	97.51 248	99.45 113	97.16 250	99.45 78	99.24 115	96.12 215	99.85 126	99.60 25	99.88 73	99.55 109

DPE-MVS		98.59 132	98.26 164	99.57 20	99.27 164	99.15 51	97.01 281	99.39 135	97.67 192	99.44 79	98.99 176	97.53 137	99.89 77	95.40 292	99.68 172	99.66 60
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
testf1		99.25 36	99.16 48	99.51 46	99.89 6	99.63 4	98.71 99	99.69 39	98.90 106	99.43 80	99.35 89	98.86 28	99.67 273	97.81 138	99.81 99	99.24 228

APD_test2		99.25 36	99.16 48	99.51 46	99.89 6	99.63 4	98.71 99	99.69 39	98.90 106	99.43 80	99.35 89	98.86 28	99.67 273	97.81 138	99.81 99	99.24 228

FMVSNet1		99.17 44	99.17 46	99.17 104	99.55 93	98.24 122	99.20 45	99.44 117	99.21 63	99.43 80	99.55 52	97.82 112	99.86 114	98.42 102	99.89 71	99.41 171

mvs5depth		99.30 29	99.59 9	98.44 220	99.65 63	95.35 277	99.82 3	99.94 2	99.83 4	99.42 83	99.94 2	98.13 91	99.96 12	99.63 24	99.96 23	100.00 1

pmmvs-eth3d		98.47 149	98.34 153	98.86 155	99.30 159	97.76 176	97.16 276	99.28 187	95.54 316	99.42 83	99.19 124	97.27 155	99.63 295	97.89 132	99.97 19	99.20 235

IU-MVS					99.49 115	99.15 51		98.87 271	92.97 367	99.41 85				96.76 212	99.62 192	99.66 60

IterMVS-SCA-FT		97.85 215	98.18 173	96.87 330	99.27 164	91.16 379	95.53 358	99.25 196	99.10 83	99.41 85	99.35 89	93.10 295	99.96 12	98.65 88	99.94 38	99.49 134

test20.03		98.78 95	98.77 87	98.78 169	99.46 125	97.20 211	97.78 212	99.24 201	99.04 93	99.41 85	98.90 197	97.65 123	99.76 228	97.70 147	99.79 115	99.39 181

PC_three_1452									93.27 363	99.40 88	98.54 261	98.22 80	97.00 414	95.17 295	99.45 241	99.49 134

FC-MVSNet-test		99.27 33	99.25 41	99.34 75	99.77 26	98.37 113	99.30 32	99.57 65	99.61 26	99.40 88	99.50 62	97.12 163	99.85 126	99.02 63	99.94 38	99.80 31

EG-PatchMatch MVS		98.99 66	99.01 63	98.94 144	99.50 108	97.47 193	98.04 175	99.59 56	98.15 163	99.40 88	99.36 88	98.58 53	99.76 228	98.78 76	99.68 172	99.59 85

v1921920		98.54 140	98.60 115	98.38 226	99.20 182	95.76 265	97.56 242	99.36 145	97.23 244	99.38 91	99.17 132	96.02 218	99.84 144	99.57 27	99.90 67	99.54 113

IterMVS-LS		98.55 138	98.70 98	98.09 248	99.48 122	94.73 297	97.22 271	99.39 135	98.97 100	99.38 91	99.31 100	96.00 220	99.93 42	98.58 91	99.97 19	99.60 79
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
lessismore_v0				98.97 140	99.73 36	97.53 191		86.71 418		99.37 93	99.52 61	89.93 330	99.92 51	98.99 65	99.72 152	99.44 161

XXY-MVS		99.14 49	99.15 53	99.10 116	99.76 29	97.74 178	98.85 87	99.62 51	98.48 134	99.37 93	99.49 67	98.75 36	99.86 114	98.20 112	99.80 110	99.71 49

ECVR-MVS		96.42 299	96.61 285	95.85 361	99.38 140	88.18 399	99.22 42	86.00 419	99.08 88	99.36 95	99.57 45	88.47 343	99.82 171	98.52 97	99.95 30	99.54 113

TranMVSNet+NR-MVSNet		99.17 44	99.07 60	99.46 58	99.37 146	98.87 77	98.39 138	99.42 126	99.42 42	99.36 95	99.06 151	98.38 64	99.95 24	98.34 105	99.90 67	99.57 96

APDe-MVS		98.99 66	98.79 85	99.60 14	99.21 178	99.15 51	98.87 84	99.48 98	97.57 202	99.35 97	99.24 115	97.83 109	99.89 77	97.88 135	99.70 164	99.75 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
casdiffmvs		98.95 73	99.00 64	98.81 161	99.38 140	97.33 201	97.82 207	99.57 65	99.17 72	99.35 97	99.17 132	98.35 68	99.69 261	98.46 99	99.73 144	99.41 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PM-MVS		98.82 89	98.72 92	99.12 112	99.64 69	98.54 102	97.98 187	99.68 44	97.62 196	99.34 99	99.18 128	97.54 135	99.77 222	97.79 140	99.74 141	99.04 262

Anonymous20240521		98.69 111	98.87 76	98.16 246	99.77 26	95.11 288	99.08 58	99.44 117	99.34 50	99.33 100	99.55 52	94.10 282	99.94 36	99.25 48	99.96 23	99.42 168

v1192		98.60 130	98.66 104	98.41 223	99.27 164	95.88 260	97.52 246	99.36 145	97.41 222	99.33 100	99.20 123	96.37 206	99.82 171	99.57 27	99.92 54	99.55 109

CP-MVSNet		99.21 41	99.09 57	99.56 25	99.65 63	98.96 74	99.13 55	99.34 156	99.42 42	99.33 100	99.26 110	97.01 171	99.94 36	98.74 81	99.93 43	99.79 32

IterMVS		97.73 221	98.11 182	96.57 340	99.24 171	90.28 388	95.52 360	99.21 205	98.86 109	99.33 100	99.33 95	93.11 294	99.94 36	98.49 98	99.94 38	99.48 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepPCF-MVS	96.93 5	98.32 167	98.01 192	99.23 99	98.39 331	98.97 70	95.03 374	99.18 215	96.88 264	99.33 100	98.78 223	98.16 88	99.28 380	96.74 214	99.62 192	99.44 161

COLMAP_ROB	96.50 10	98.99 66	98.85 80	99.41 62	99.58 76	99.10 64	98.74 92	99.56 72	99.09 86	99.33 100	99.19 124	98.40 63	99.72 252	95.98 268	99.76 137	99.42 168
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v144192		98.54 140	98.57 118	98.45 218	99.21 178	95.98 257	97.63 233	99.36 145	97.15 252	99.32 106	99.18 128	95.84 232	99.84 144	99.50 34	99.91 61	99.54 113

v148		98.45 151	98.60 115	98.00 258	99.44 129	94.98 290	97.44 254	99.06 237	98.30 143	99.32 106	98.97 182	96.65 193	99.62 298	98.37 103	99.85 81	99.39 181

MSP-MVS		98.40 156	98.00 193	99.61 12	99.57 81	99.25 28	98.57 112	99.35 150	97.55 206	99.31 108	97.71 328	94.61 267	99.88 89	96.14 262	99.19 283	99.70 54
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
reproduce_monomvs		95.00 337	95.25 326	94.22 384	97.51 383	83.34 416	97.86 203	98.44 314	98.51 132	99.29 109	99.30 101	67.68 411	99.56 320	98.89 71	99.81 99	99.77 37

VPNet		98.87 82	98.83 81	99.01 135	99.70 52	97.62 187	98.43 134	99.35 150	99.47 35	99.28 110	99.05 158	96.72 190	99.82 171	98.09 119	99.36 252	99.59 85

v2v482		98.56 134	98.62 110	98.37 228	99.42 135	95.81 263	97.58 240	99.16 222	97.90 178	99.28 110	99.01 172	95.98 225	99.79 205	99.33 41	99.90 67	99.51 127

ambc				98.24 240	98.82 262	95.97 258	98.62 107	99.00 253		99.27 112	99.21 121	96.99 172	99.50 341	96.55 236	99.50 236	99.26 224

Patchmatch-RL test		97.26 256	97.02 258	97.99 259	99.52 103	95.53 270	96.13 331	99.71 36	97.47 213	99.27 112	99.16 134	84.30 371	99.62 298	97.89 132	99.77 125	98.81 301

v1144		98.60 130	98.66 104	98.41 223	99.36 147	95.90 259	97.58 240	99.34 156	97.51 209	99.27 112	99.15 138	96.34 208	99.80 192	99.47 36	99.93 43	99.51 127

Vis-MVSNet		99.34 26	99.36 25	99.27 90	99.73 36	98.26 120	99.17 50	99.78 29	99.11 76	99.27 112	99.48 68	98.82 31	99.95 24	98.94 67	99.93 43	99.59 85
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DVP-MVS++		98.90 79	98.70 98	99.51 46	98.43 326	99.15 51	99.43 12	99.32 163	98.17 159	99.26 116	99.02 163	98.18 84	99.88 89	97.07 183	99.45 241	99.49 134

FOURS1					99.73 36	99.67 3	99.43 12	99.54 80	99.43 41	99.26 116

test_241102_TWO								99.30 176	98.03 166	99.26 116	99.02 163	97.51 140	99.88 89	96.91 195	99.60 199	99.66 60

test0726					99.50 108	99.21 32	98.17 157	99.35 150	97.97 170	99.26 116	99.06 151	97.61 129

V42		98.78 95	98.78 86	98.76 173	99.44 129	97.04 219	98.27 146	99.19 211	97.87 180	99.25 120	99.16 134	96.84 178	99.78 216	99.21 51	99.84 85	99.46 153

TSAR-MVS + MP.		98.63 125	98.49 130	99.06 128	99.64 69	97.90 161	98.51 123	98.94 256	96.96 259	99.24 121	98.89 203	97.83 109	99.81 185	96.88 202	99.49 237	99.48 144
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
FIs		99.14 49	99.09 57	99.29 86	99.70 52	98.28 119	99.13 55	99.52 86	99.48 33	99.24 121	99.41 81	96.79 184	99.82 171	98.69 86	99.88 73	99.76 42

TSAR-MVS + GP.		98.18 185	97.98 195	98.77 172	98.71 278	97.88 162	96.32 319	98.66 302	96.33 288	99.23 123	98.51 265	97.48 145	99.40 361	97.16 174	99.46 239	99.02 265

ppachtmachnet_test		97.50 236	97.74 213	96.78 336	98.70 282	91.23 378	94.55 389	99.05 240	96.36 287	99.21 124	98.79 221	96.39 203	99.78 216	96.74 214	99.82 95	99.34 202

Baseline_NR-MVSNet		98.98 69	98.86 79	99.36 66	99.82 19	98.55 99	97.47 252	99.57 65	99.37 46	99.21 124	99.61 39	96.76 187	99.83 161	98.06 122	99.83 92	99.71 49

EI-MVSNet-UG-set		98.69 111	98.71 95	98.62 189	99.10 206	96.37 245	97.23 268	98.87 271	99.20 65	99.19 126	98.99 176	97.30 152	99.85 126	98.77 79	99.79 115	99.65 65

testgi		98.32 167	98.39 146	98.13 247	99.57 81	95.54 269	97.78 212	99.49 96	97.37 226	99.19 126	97.65 332	98.96 24	99.49 344	96.50 240	98.99 308	99.34 202

baseline		98.96 72	99.02 62	98.76 173	99.38 140	97.26 206	98.49 126	99.50 89	98.86 109	99.19 126	99.06 151	98.23 77	99.69 261	98.71 84	99.76 137	99.33 207

FMVSNet2		98.49 147	98.40 143	98.75 175	98.90 245	97.14 217	98.61 108	99.13 228	98.59 124	99.19 126	99.28 104	94.14 278	99.82 171	97.97 129	99.80 110	99.29 218

EI-MVSNet-Vis-set		98.68 116	98.70 98	98.63 188	99.09 209	96.40 244	97.23 268	98.86 276	99.20 65	99.18 130	98.97 182	97.29 154	99.85 126	98.72 83	99.78 120	99.64 66

TAMVS		98.24 179	98.05 188	98.80 163	99.07 213	97.18 213	97.88 199	98.81 285	96.66 276	99.17 131	99.21 121	94.81 262	99.77 222	96.96 193	99.88 73	99.44 161

UniMVSNet (Re)		98.87 82	98.71 95	99.35 72	99.24 171	98.73 87	97.73 221	99.38 137	98.93 104	99.12 132	98.73 230	96.77 185	99.86 114	98.63 90	99.80 110	99.46 153

Anonymous202405211		97.90 203	97.50 231	99.08 120	98.90 245	98.25 121	98.53 117	96.16 374	98.87 108	99.11 133	98.86 207	90.40 328	99.78 216	97.36 164	99.31 260	99.19 240

VDD-MVS		98.56 134	98.39 146	99.07 122	99.13 202	98.07 143	98.59 110	97.01 357	99.59 27	99.11 133	99.27 106	94.82 260	99.79 205	98.34 105	99.63 189	99.34 202

XVG-OURS-SEG-HR		98.49 147	98.28 160	99.14 110	99.49 115	98.83 79	96.54 305	99.48 98	97.32 231	99.11 133	98.61 255	99.33 13	99.30 376	96.23 255	98.38 343	99.28 220

LPG-MVS_test		98.71 104	98.46 135	99.47 56	99.57 81	98.97 70	98.23 149	99.48 98	96.60 277	99.10 136	99.06 151	98.71 39	99.83 161	95.58 288	99.78 120	99.62 70

LGP-MVS_train				99.47 56	99.57 81	98.97 70		99.48 98	96.60 277	99.10 136	99.06 151	98.71 39	99.83 161	95.58 288	99.78 120	99.62 70

DVP-MVS		98.77 98	98.52 123	99.52 42	99.50 108	99.21 32	98.02 178	98.84 280	97.97 170	99.08 138	99.02 163	97.61 129	99.88 89	96.99 189	99.63 189	99.48 144
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_THIRD									98.17 159	99.08 138	99.02 163	97.89 106	99.88 89	97.07 183	99.71 157	99.70 54

EI-MVSNet		98.40 156	98.51 124	98.04 256	99.10 206	94.73 297	97.20 272	98.87 271	98.97 100	99.06 140	99.02 163	96.00 220	99.80 192	98.58 91	99.82 95	99.60 79

UniMVSNet_NR-MVSNet		98.86 85	98.68 101	99.40 64	99.17 193	98.74 84	97.68 225	99.40 133	99.14 74	99.06 140	98.59 257	96.71 191	99.93 42	98.57 93	99.77 125	99.53 121

DU-MVS		98.82 89	98.63 108	99.39 65	99.16 195	98.74 84	97.54 244	99.25 196	98.84 112	99.06 140	98.76 227	96.76 187	99.93 42	98.57 93	99.77 125	99.50 130

MVSTER		96.86 282	96.55 289	97.79 268	97.91 357	94.21 311	97.56 242	98.87 271	97.49 212	99.06 140	99.05 158	80.72 384	99.80 192	98.44 100	99.82 95	99.37 190

TinyColmap		97.89 205	97.98 195	97.60 287	98.86 253	94.35 308	96.21 325	99.44 117	97.45 220	99.06 140	98.88 204	97.99 102	99.28 380	94.38 320	99.58 208	99.18 242

test_part2					99.36 147	99.10 64				99.05 145

XVG-OURS		98.53 142	98.34 153	99.11 114	99.50 108	98.82 81	95.97 337	99.50 89	97.30 233	99.05 145	98.98 180	99.35 12	99.32 373	95.72 281	99.68 172	99.18 242

our_test_3		97.39 247	97.73 215	96.34 346	98.70 282	89.78 391	94.61 387	98.97 255	96.50 281	99.04 147	98.85 210	95.98 225	99.84 144	97.26 169	99.67 178	99.41 171

UA-Net		99.47 13	99.40 22	99.70 2	99.49 115	99.29 23	99.80 4	99.72 35	99.82 5	99.04 147	99.81 6	98.05 96	99.96 12	98.85 73	99.99 5	99.86 21

ACMM	96.08 12	98.91 77	98.73 90	99.48 53	99.55 93	99.14 56	98.07 170	99.37 141	97.62 196	99.04 147	98.96 185	98.84 30	99.79 205	97.43 161	99.65 184	99.49 134
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
APD-MVS_3200maxsize		98.84 86	98.61 114	99.53 37	99.19 185	99.27 26	98.49 126	99.33 161	98.64 118	99.03 150	98.98 180	97.89 106	99.85 126	96.54 237	99.42 245	99.46 153

HyFIR lowres test		97.19 263	96.60 287	98.96 141	99.62 75	97.28 204	95.17 370	99.50 89	94.21 349	99.01 151	98.32 289	86.61 350	99.99 2	97.10 181	99.84 85	99.60 79

CVMVSNet		96.25 304	97.21 249	93.38 395	99.10 206	80.56 422	97.20 272	98.19 327	96.94 261	99.00 152	99.02 163	89.50 334	99.80 192	96.36 249	99.59 203	99.78 35

PVSNet_Blended_VisFu		98.17 187	98.15 178	98.22 241	99.73 36	95.15 285	97.36 258	99.68 44	94.45 344	98.99 153	99.27 106	96.87 177	99.94 36	97.13 179	99.91 61	99.57 96

APD_test1		98.83 87	98.66 104	99.34 75	99.78 23	99.47 9	98.42 136	99.45 113	98.28 148	98.98 154	99.19 124	97.76 116	99.58 315	96.57 229	99.55 218	98.97 275

SMA-MVS		98.40 156	98.03 190	99.51 46	99.16 195	99.21 32	98.05 173	99.22 204	94.16 350	98.98 154	99.10 147	97.52 139	99.79 205	96.45 243	99.64 186	99.53 121
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
XVG-ACMP-BASELINE		98.56 134	98.34 153	99.22 100	99.54 98	98.59 96	97.71 222	99.46 109	97.25 238	98.98 154	98.99 176	97.54 135	99.84 144	95.88 271	99.74 141	99.23 230

IS-MVSNet		98.19 184	97.90 204	99.08 120	99.57 81	97.97 154	99.31 27	98.32 320	99.01 96	98.98 154	99.03 162	91.59 317	99.79 205	95.49 290	99.80 110	99.48 144

balanced_conf03		98.63 125	98.72 92	98.38 226	98.66 297	96.68 239	98.90 80	99.42 126	98.99 97	98.97 158	99.19 124	95.81 233	99.85 126	98.77 79	99.77 125	98.60 327

MP-MVS-pluss		98.57 133	98.23 168	99.60 14	99.69 54	99.35 16	97.16 276	99.38 137	94.87 334	98.97 158	98.99 176	98.01 98	99.88 89	97.29 167	99.70 164	99.58 91
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VDDNet		98.21 182	97.95 198	99.01 135	99.58 76	97.74 178	99.01 67	97.29 351	99.67 16	98.97 158	99.50 62	90.45 327	99.80 192	97.88 135	99.20 280	99.48 144

USDC		97.41 246	97.40 236	97.44 304	98.94 235	93.67 335	95.17 370	99.53 83	94.03 354	98.97 158	99.10 147	95.29 247	99.34 370	95.84 277	99.73 144	99.30 216

MM		98.22 180	97.99 194	98.91 150	98.66 297	96.97 222	97.89 198	94.44 392	99.54 30	98.95 162	99.14 141	93.50 290	99.92 51	99.80 11	99.96 23	99.85 22

SR-MVS-dyc-post		98.81 91	98.55 119	99.57 20	99.20 182	99.38 12	98.48 129	99.30 176	98.64 118	98.95 162	98.96 185	97.49 144	99.86 114	96.56 233	99.39 248	99.45 157

RE-MVS-def			98.58 117		99.20 182	99.38 12	98.48 129	99.30 176	98.64 118	98.95 162	98.96 185	97.75 117		96.56 233	99.39 248	99.45 157

GBi-Net		98.65 121	98.47 133	99.17 104	98.90 245	98.24 122	99.20 45	99.44 117	98.59 124	98.95 162	99.55 52	94.14 278	99.86 114	97.77 142	99.69 167	99.41 171

test1		98.65 121	98.47 133	99.17 104	98.90 245	98.24 122	99.20 45	99.44 117	98.59 124	98.95 162	99.55 52	94.14 278	99.86 114	97.77 142	99.69 167	99.41 171

FMVSNet3		97.50 236	97.24 247	98.29 236	98.08 350	95.83 262	97.86 203	98.91 264	97.89 179	98.95 162	98.95 189	87.06 347	99.81 185	97.77 142	99.69 167	99.23 230

test_0402		98.76 99	98.71 95	98.93 146	99.56 89	98.14 132	98.45 133	99.34 156	99.28 57	98.95 162	98.91 194	98.34 69	99.79 205	95.63 285	99.91 61	98.86 294

HPM-MVS_fast		99.01 64	98.82 82	99.57 20	99.71 45	99.35 16	99.00 69	99.50 89	97.33 229	98.94 169	98.86 207	98.75 36	99.82 171	97.53 157	99.71 157	99.56 102

Anonymous20231206		98.21 182	98.21 169	98.20 242	99.51 105	95.43 275	98.13 160	99.32 163	96.16 295	98.93 170	98.82 216	96.00 220	99.83 161	97.32 166	99.73 144	99.36 196

YYNet1		97.60 230	97.67 218	97.39 307	99.04 221	93.04 346	95.27 367	98.38 319	97.25 238	98.92 171	98.95 189	95.48 244	99.73 245	96.99 189	98.74 323	99.41 171

GeoE		99.05 62	98.99 66	99.25 95	99.44 129	98.35 117	98.73 96	99.56 72	98.42 136	98.91 172	98.81 218	98.94 25	99.91 60	98.35 104	99.73 144	99.49 134

SteuartSystems-ACMMP		98.79 93	98.54 121	99.54 30	99.73 36	99.16 47	98.23 149	99.31 168	97.92 176	98.90 173	98.90 197	98.00 99	99.88 89	96.15 261	99.72 152	99.58 91
Skip Steuart: Steuart Systems R&D Blog.
RPSCF		98.62 128	98.36 150	99.42 60	99.65 63	99.42 11	98.55 114	99.57 65	97.72 190	98.90 173	99.26 110	96.12 215	99.52 335	95.72 281	99.71 157	99.32 209

D2MVS		97.84 216	97.84 208	97.83 265	99.14 200	94.74 296	96.94 285	98.88 269	95.84 308	98.89 175	98.96 185	94.40 272	99.69 261	97.55 154	99.95 30	99.05 258

MTAPA		98.88 81	98.64 107	99.61 12	99.67 60	99.36 15	98.43 134	99.20 207	98.83 113	98.89 175	98.90 197	96.98 173	99.92 51	97.16 174	99.70 164	99.56 102

WR-MVS		98.40 156	98.19 172	99.03 132	99.00 226	97.65 184	96.85 291	98.94 256	98.57 127	98.89 175	98.50 269	95.60 238	99.85 126	97.54 156	99.85 81	99.59 85

SR-MVS		98.71 104	98.43 139	99.57 20	99.18 192	99.35 16	98.36 141	99.29 184	98.29 146	98.88 178	98.85 210	97.53 137	99.87 106	96.14 262	99.31 260	99.48 144

AllTest		98.44 152	98.20 170	99.16 107	99.50 108	98.55 99	98.25 148	99.58 58	96.80 268	98.88 178	99.06 151	97.65 123	99.57 317	94.45 314	99.61 197	99.37 190

TestCases				99.16 107	99.50 108	98.55 99		99.58 58	96.80 268	98.88 178	99.06 151	97.65 123	99.57 317	94.45 314	99.61 197	99.37 190

MDA-MVSNet_test_wron		97.60 230	97.66 221	97.41 306	99.04 221	93.09 342	95.27 367	98.42 316	97.26 237	98.88 178	98.95 189	95.43 245	99.73 245	97.02 186	98.72 325	99.41 171

tt0805		98.69 111	98.62 110	98.90 153	99.75 33	99.30 21	99.15 53	96.97 359	98.86 109	98.87 182	97.62 335	98.63 46	98.96 395	99.41 38	98.29 347	98.45 338

VNet		98.42 153	98.30 158	98.79 166	98.79 268	97.29 203	98.23 149	98.66 302	99.31 53	98.85 183	98.80 219	94.80 263	99.78 216	98.13 116	99.13 291	99.31 213

CSCG		98.68 116	98.50 126	99.20 101	99.45 128	98.63 91	98.56 113	99.57 65	97.87 180	98.85 183	98.04 310	97.66 122	99.84 144	96.72 217	99.81 99	99.13 251

CHOSEN 1792x2688		97.49 238	97.14 254	98.54 207	99.68 56	96.09 254	96.50 308	99.62 51	91.58 382	98.84 185	98.97 182	92.36 308	99.88 89	96.76 212	99.95 30	99.67 59

SF-MVS		98.53 142	98.27 163	99.32 82	99.31 156	98.75 83	98.19 153	99.41 130	96.77 271	98.83 186	98.90 197	97.80 114	99.82 171	95.68 284	99.52 227	99.38 188

mvs_anonymous		97.83 218	98.16 177	96.87 330	98.18 343	91.89 364	97.31 262	98.90 265	97.37 226	98.83 186	99.46 70	96.28 209	99.79 205	98.90 69	98.16 354	98.95 278

MDA-MVSNet-bldmvs		97.94 201	97.91 203	98.06 253	99.44 129	94.96 291	96.63 303	99.15 227	98.35 138	98.83 186	99.11 144	94.31 275	99.85 126	96.60 226	98.72 325	99.37 190

PMMVS2		98.07 193	98.08 186	98.04 256	99.41 137	94.59 303	94.59 388	99.40 133	97.50 210	98.82 189	98.83 213	96.83 180	99.84 144	97.50 159	99.81 99	99.71 49

ACMMP		98.75 100	98.50 126	99.52 42	99.56 89	99.16 47	98.87 84	99.37 141	97.16 250	98.82 189	99.01 172	97.71 119	99.87 106	96.29 253	99.69 167	99.54 113
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
ACMP	95.32 15	98.41 154	98.09 183	99.36 66	99.51 105	98.79 82	97.68 225	99.38 137	95.76 310	98.81 191	98.82 216	98.36 65	99.82 171	94.75 304	99.77 125	99.48 144
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMMP_NAP		98.75 100	98.48 131	99.57 20	99.58 76	99.29 23	97.82 207	99.25 196	96.94 261	98.78 192	99.12 143	98.02 97	99.84 144	97.13 179	99.67 178	99.59 85

LFMVS		97.20 262	96.72 277	98.64 184	98.72 275	96.95 225	98.93 78	94.14 398	99.74 10	98.78 192	99.01 172	84.45 368	99.73 245	97.44 160	99.27 267	99.25 225

Patchmtry		97.35 249	96.97 260	98.50 214	97.31 389	96.47 243	98.18 154	98.92 262	98.95 103	98.78 192	99.37 84	85.44 362	99.85 126	95.96 269	99.83 92	99.17 246

test2506		92.39 373	91.89 375	93.89 389	99.38 140	82.28 419	99.32 23	66.03 425	99.08 88	98.77 195	99.57 45	66.26 415	99.84 144	98.71 84	99.95 30	99.54 113

c3_l		97.36 248	97.37 239	97.31 308	98.09 349	93.25 341	95.01 375	99.16 222	97.05 254	98.77 195	98.72 232	92.88 300	99.64 292	96.93 194	99.76 137	99.05 258

UnsupCasMVSNet_eth		97.89 205	97.60 226	98.75 175	99.31 156	97.17 214	97.62 234	99.35 150	98.72 116	98.76 197	98.68 239	92.57 307	99.74 240	97.76 146	95.60 403	99.34 202

OPM-MVS		98.56 134	98.32 157	99.25 95	99.41 137	98.73 87	97.13 278	99.18 215	97.10 253	98.75 198	98.92 193	98.18 84	99.65 289	96.68 221	99.56 215	99.37 190
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DeepC-MVS_fast	96.85 6	98.30 170	98.15 178	98.75 175	98.61 302	97.23 207	97.76 217	99.09 234	97.31 232	98.75 198	98.66 244	97.56 133	99.64 292	96.10 265	99.55 218	99.39 181
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
miper_lstm_enhance		97.18 264	97.16 251	97.25 313	98.16 344	92.85 348	95.15 372	99.31 168	97.25 238	98.74 200	98.78 223	90.07 329	99.78 216	97.19 172	99.80 110	99.11 253

MVSMamba_PlusPlus		98.83 87	98.98 67	98.36 229	99.32 155	96.58 242	98.90 80	99.41 130	99.75 8	98.72 201	99.50 62	96.17 212	99.94 36	99.27 45	99.78 120	98.57 331

APD-MVS		98.10 189	97.67 218	99.42 60	99.11 204	98.93 75	97.76 217	99.28 187	94.97 331	98.72 201	98.77 225	97.04 167	99.85 126	93.79 336	99.54 220	99.49 134
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
miper_ehance_all_eth		97.06 271	97.03 257	97.16 318	97.83 359	93.06 343	94.66 384	99.09 234	95.99 303	98.69 203	98.45 274	92.73 305	99.61 304	96.79 208	99.03 301	98.82 297

RRT-MVS		97.88 207	97.98 195	97.61 286	98.15 345	93.77 332	98.97 73	99.64 49	99.16 73	98.69 203	99.42 77	91.60 316	99.89 77	97.63 150	98.52 341	99.16 249

PGM-MVS		98.66 120	98.37 149	99.55 27	99.53 101	99.18 42	98.23 149	99.49 96	97.01 258	98.69 203	98.88 204	98.00 99	99.89 77	95.87 274	99.59 203	99.58 91

GST-MVS		98.61 129	98.30 158	99.52 42	99.51 105	99.20 38	98.26 147	99.25 196	97.44 221	98.67 206	98.39 279	97.68 120	99.85 126	96.00 266	99.51 229	99.52 124

tttt0517		95.64 323	94.98 333	97.64 284	99.36 147	93.81 330	98.72 97	90.47 412	98.08 165	98.67 206	98.34 286	73.88 402	99.92 51	97.77 142	99.51 229	99.20 235

test_one_0601					99.39 139	99.20 38		99.31 168	98.49 133	98.66 208	99.02 163	97.64 126

OpenMVS_ROB	95.38 14	95.84 317	95.18 330	97.81 267	98.41 330	97.15 216	97.37 257	98.62 306	83.86 410	98.65 209	98.37 282	94.29 276	99.68 270	88.41 396	98.62 337	96.60 401

MS-PatchMatch		97.68 225	97.75 212	97.45 303	98.23 341	93.78 331	97.29 264	98.84 280	96.10 297	98.64 210	98.65 246	96.04 217	99.36 366	96.84 206	99.14 289	99.20 235

cl____		97.02 274	96.83 270	97.58 289	97.82 360	94.04 318	94.66 384	99.16 222	97.04 255	98.63 211	98.71 233	88.68 340	99.69 261	97.00 187	99.81 99	99.00 270

DIV-MVS_self_test		97.02 274	96.84 269	97.58 289	97.82 360	94.03 319	94.66 384	99.16 222	97.04 255	98.63 211	98.71 233	88.69 338	99.69 261	97.00 187	99.81 99	99.01 266

pmmvs5		97.64 228	97.49 232	98.08 251	99.14 200	95.12 287	96.70 300	99.05 240	93.77 357	98.62 213	98.83 213	93.23 291	99.75 235	98.33 107	99.76 137	99.36 196

ab-mvs		98.41 154	98.36 150	98.59 195	99.19 185	97.23 207	99.32 23	98.81 285	97.66 193	98.62 213	99.40 83	96.82 181	99.80 192	95.88 271	99.51 229	98.75 312

pmmvs4		97.58 233	97.28 244	98.51 210	98.84 257	96.93 227	95.40 365	98.52 311	93.60 359	98.61 215	98.65 246	95.10 252	99.60 305	96.97 192	99.79 115	98.99 271

HPM-MVS		98.79 93	98.53 122	99.59 18	99.65 63	99.29 23	99.16 51	99.43 123	96.74 272	98.61 215	98.38 281	98.62 47	99.87 106	96.47 241	99.67 178	99.59 85
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CL-MVSNet_self_test		97.44 243	97.22 248	98.08 251	98.57 311	95.78 264	94.30 394	98.79 288	96.58 279	98.60 217	98.19 298	94.74 266	99.64 292	96.41 245	98.84 318	98.82 297

Gipuma		99.03 63	99.16 48	98.64 184	99.94 2	98.51 104	99.32 23	99.75 34	99.58 29	98.60 217	99.62 36	98.22 80	99.51 340	97.70 147	99.73 144	97.89 370
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CDS-MVSNet		97.69 224	97.35 241	98.69 181	98.73 273	97.02 221	96.92 289	98.75 295	95.89 307	98.59 219	98.67 241	92.08 313	99.74 240	96.72 217	99.81 99	99.32 209
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EPP-MVSNet		98.30 170	98.04 189	99.07 122	99.56 89	97.83 167	99.29 33	98.07 331	99.03 94	98.59 219	99.13 142	92.16 311	99.90 66	96.87 203	99.68 172	99.49 134

h-mvs33		97.77 219	97.33 243	99.10 116	99.21 178	97.84 166	98.35 142	98.57 308	99.11 76	98.58 221	99.02 163	88.65 341	99.96 12	98.11 117	96.34 395	99.49 134

hse-mvs2		97.46 240	97.07 255	98.64 184	98.73 273	97.33 201	97.45 253	97.64 344	99.11 76	98.58 221	97.98 313	88.65 341	99.79 205	98.11 117	97.39 378	98.81 301

HFP-MVS		98.71 104	98.44 138	99.51 46	99.49 115	99.16 47	98.52 118	99.31 168	97.47 213	98.58 221	98.50 269	97.97 103	99.85 126	96.57 229	99.59 203	99.53 121

eth_miper_zixun_eth		97.23 260	97.25 246	97.17 316	98.00 353	92.77 350	94.71 381	99.18 215	97.27 236	98.56 224	98.74 229	91.89 314	99.69 261	97.06 185	99.81 99	99.05 258

ACMMPR		98.70 108	98.42 141	99.54 30	99.52 103	99.14 56	98.52 118	99.31 168	97.47 213	98.56 224	98.54 261	97.75 117	99.88 89	96.57 229	99.59 203	99.58 91

new_pmnet		96.99 278	96.76 275	97.67 280	98.72 275	94.89 292	95.95 341	98.20 325	92.62 373	98.55 226	98.54 261	94.88 259	99.52 335	93.96 330	99.44 244	98.59 330

3Dnovator	98.27 2	98.81 91	98.73 90	99.05 129	98.76 269	97.81 173	99.25 40	99.30 176	98.57 127	98.55 226	99.33 95	97.95 104	99.90 66	97.16 174	99.67 178	99.44 161

9.14			97.78 210		99.07 213		97.53 245	99.32 163	95.53 317	98.54 228	98.70 236	97.58 131	99.76 228	94.32 321	99.46 239

diffmvs		98.22 180	98.24 167	98.17 244	99.00 226	95.44 274	96.38 315	99.58 58	97.79 186	98.53 229	98.50 269	96.76 187	99.74 240	97.95 131	99.64 186	99.34 202
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OMC-MVS		97.88 207	97.49 232	99.04 131	98.89 250	98.63 91	96.94 285	99.25 196	95.02 329	98.53 229	98.51 265	97.27 155	99.47 350	93.50 344	99.51 229	99.01 266

jason		97.45 242	97.35 241	97.76 273	99.24 171	93.93 324	95.86 346	98.42 316	94.24 348	98.50 231	98.13 300	94.82 260	99.91 60	97.22 171	99.73 144	99.43 165
jason: jason.
patch_mono-2		98.51 146	98.63 108	98.17 244	99.38 140	94.78 294	97.36 258	99.69 39	98.16 162	98.49 232	99.29 103	97.06 166	99.97 5	98.29 108	99.91 61	99.76 42

FA-MVS(test-final)		96.99 278	96.82 271	97.50 299	98.70 282	94.78 294	99.34 20	96.99 358	95.07 328	98.48 233	99.33 95	88.41 344	99.65 289	96.13 264	98.92 316	98.07 363

MVP-Stereo		98.08 192	97.92 202	98.57 199	98.96 233	96.79 231	97.90 197	99.18 215	96.41 286	98.46 234	98.95 189	95.93 229	99.60 305	96.51 239	98.98 310	99.31 213
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
DELS-MVS		98.27 174	98.20 170	98.48 215	98.86 253	96.70 237	95.60 356	99.20 207	97.73 189	98.45 235	98.71 233	97.50 141	99.82 171	98.21 111	99.59 203	98.93 283
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
region2R		98.69 111	98.40 143	99.54 30	99.53 101	99.17 43	98.52 118	99.31 168	97.46 218	98.44 236	98.51 265	97.83 109	99.88 89	96.46 242	99.58 208	99.58 91

BH-untuned		96.83 283	96.75 276	97.08 319	98.74 272	93.33 340	96.71 299	98.26 322	96.72 273	98.44 236	97.37 349	95.20 249	99.47 350	91.89 368	97.43 376	98.44 341

LS3D		98.63 125	98.38 148	99.36 66	97.25 390	99.38 12	99.12 57	99.32 163	99.21 63	98.44 236	98.88 204	97.31 151	99.80 192	96.58 227	99.34 256	98.92 284

xiu_mvs_v1_base_debu		97.86 210	98.17 174	96.92 327	98.98 230	93.91 325	96.45 310	99.17 219	97.85 182	98.41 239	97.14 356	98.47 57	99.92 51	98.02 124	99.05 297	96.92 395

xiu_mvs_v1_base		97.86 210	98.17 174	96.92 327	98.98 230	93.91 325	96.45 310	99.17 219	97.85 182	98.41 239	97.14 356	98.47 57	99.92 51	98.02 124	99.05 297	96.92 395

xiu_mvs_v1_base_debi		97.86 210	98.17 174	96.92 327	98.98 230	93.91 325	96.45 310	99.17 219	97.85 182	98.41 239	97.14 356	98.47 57	99.92 51	98.02 124	99.05 297	96.92 395

Patchmatch-test		96.55 293	96.34 295	97.17 316	98.35 332	93.06 343	98.40 137	97.79 336	97.33 229	98.41 239	98.67 241	83.68 375	99.69 261	95.16 296	99.31 260	98.77 309

baseline1		95.96 313	95.44 319	97.52 297	98.51 318	93.99 322	98.39 138	96.09 376	98.21 152	98.40 243	97.76 326	86.88 348	99.63 295	95.42 291	89.27 416	98.95 278

MSDG		97.71 223	97.52 230	98.28 237	98.91 244	96.82 230	94.42 391	99.37 141	97.65 194	98.37 244	98.29 291	97.40 148	99.33 372	94.09 327	99.22 276	98.68 322

WBMVS		95.18 332	94.78 338	96.37 345	97.68 371	89.74 392	95.80 350	98.73 298	97.54 207	98.30 245	98.44 275	70.06 405	99.82 171	96.62 224	99.87 76	99.54 113

miper_enhance_ethall		96.01 310	95.74 305	96.81 334	96.41 409	92.27 361	93.69 403	98.89 268	91.14 389	98.30 245	97.35 351	90.58 326	99.58 315	96.31 251	99.03 301	98.60 327

MVS_0304		97.44 243	97.01 259	98.72 180	96.42 408	96.74 235	97.20 272	91.97 408	98.46 135	98.30 245	98.79 221	92.74 304	99.91 60	99.30 43	99.94 38	99.52 124

CP-MVS		98.70 108	98.42 141	99.52 42	99.36 147	99.12 61	98.72 97	99.36 145	97.54 207	98.30 245	98.40 278	97.86 108	99.89 77	96.53 238	99.72 152	99.56 102

UnsupCasMVSNet_bld		97.30 253	96.92 263	98.45 218	99.28 162	96.78 234	96.20 326	99.27 190	95.42 320	98.28 249	98.30 290	93.16 293	99.71 253	94.99 298	97.37 379	98.87 293

ITE_SJBPF				98.87 154	99.22 176	98.48 106		99.35 150	97.50 210	98.28 249	98.60 256	97.64 126	99.35 369	93.86 334	99.27 267	98.79 307

mmtdpeth		99.30 29	99.42 20	98.92 149	99.58 76	96.89 229	99.48 10	99.92 7	99.92 2	98.26 251	99.80 9	98.33 70	99.91 60	99.56 29	99.95 30	99.97 4

thisisatest0530		95.27 330	94.45 341	97.74 276	99.19 185	94.37 307	97.86 203	90.20 413	97.17 249	98.22 252	97.65 332	73.53 403	99.90 66	96.90 200	99.35 254	98.95 278

CS-MVS		99.13 52	99.10 56	99.24 97	99.06 217	99.15 51	99.36 19	99.88 13	99.36 49	98.21 253	98.46 273	98.68 42	99.93 42	99.03 62	99.85 81	98.64 324

test_yl		96.69 287	96.29 297	97.90 260	98.28 336	95.24 281	97.29 264	97.36 347	98.21 152	98.17 254	97.86 320	86.27 352	99.55 324	94.87 302	98.32 344	98.89 289

DCV-MVSNet		96.69 287	96.29 297	97.90 260	98.28 336	95.24 281	97.29 264	97.36 347	98.21 152	98.17 254	97.86 320	86.27 352	99.55 324	94.87 302	98.32 344	98.89 289

SPE-MVS-test		99.13 52	99.09 57	99.26 92	99.13 202	98.97 70	99.31 27	99.88 13	99.44 39	98.16 256	98.51 265	98.64 44	99.93 42	98.91 68	99.85 81	98.88 292

MVSFormer		98.26 176	98.43 139	97.77 270	98.88 251	93.89 328	99.39 17	99.56 72	99.11 76	98.16 256	98.13 300	93.81 286	99.97 5	99.26 46	99.57 212	99.43 165

lupinMVS		97.06 271	96.86 267	97.65 282	98.88 251	93.89 328	95.48 361	97.97 333	93.53 360	98.16 256	97.58 336	93.81 286	99.91 60	96.77 211	99.57 212	99.17 246

Vis-MVSNet (Re-imp)		97.46 240	97.16 251	98.34 231	99.55 93	96.10 251	98.94 77	98.44 314	98.32 142	98.16 256	98.62 253	88.76 337	99.73 245	93.88 333	99.79 115	99.18 242

TAPA-MVS	96.21 11	96.63 291	95.95 302	98.65 183	98.93 237	98.09 137	96.93 287	99.28 187	83.58 411	98.13 260	97.78 324	96.13 214	99.40 361	93.52 342	99.29 265	98.45 338
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
EC-MVSNet		99.09 57	99.05 61	99.20 101	99.28 162	98.93 75	99.24 41	99.84 20	99.08 88	98.12 261	98.37 282	98.72 38	99.90 66	99.05 60	99.77 125	98.77 309

ZNCC-MVS		98.68 116	98.40 143	99.54 30	99.57 81	99.21 32	98.46 131	99.29 184	97.28 235	98.11 262	98.39 279	98.00 99	99.87 106	96.86 205	99.64 186	99.55 109

MVS_111021_LR		98.30 170	98.12 181	98.83 158	99.16 195	98.03 148	96.09 333	99.30 176	97.58 201	98.10 263	98.24 293	98.25 75	99.34 370	96.69 220	99.65 184	99.12 252

mPP-MVS		98.64 123	98.34 153	99.54 30	99.54 98	99.17 43	98.63 105	99.24 201	97.47 213	98.09 264	98.68 239	97.62 128	99.89 77	96.22 256	99.62 192	99.57 96

3Dnovator+	97.89 3	98.69 111	98.51 124	99.24 97	98.81 264	98.40 109	99.02 66	99.19 211	98.99 97	98.07 265	99.28 104	97.11 165	99.84 144	96.84 206	99.32 258	99.47 151

PHI-MVS		98.29 173	97.95 198	99.34 75	98.44 325	99.16 47	98.12 163	99.38 137	96.01 302	98.06 266	98.43 276	97.80 114	99.67 273	95.69 283	99.58 208	99.20 235

CLD-MVS		97.49 238	97.16 251	98.48 215	99.07 213	97.03 220	94.71 381	99.21 205	94.46 342	98.06 266	97.16 354	97.57 132	99.48 347	94.46 313	99.78 120	98.95 278
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ZD-MVS					99.01 225	98.84 78		99.07 236	94.10 352	98.05 268	98.12 302	96.36 207	99.86 114	92.70 361	99.19 283

MVS_Test		98.18 185	98.36 150	97.67 280	98.48 319	94.73 297	98.18 154	99.02 248	97.69 191	98.04 269	99.11 144	97.22 159	99.56 320	98.57 93	98.90 317	98.71 315

MonoMVSNet		96.25 304	96.53 291	95.39 373	96.57 404	91.01 380	98.82 90	97.68 341	98.57 127	98.03 270	99.37 84	90.92 323	97.78 411	94.99 298	93.88 411	97.38 391

FMVSNet5		96.01 310	95.20 329	98.41 223	97.53 378	96.10 251	98.74 92	99.50 89	97.22 247	98.03 270	99.04 160	69.80 406	99.88 89	97.27 168	99.71 157	99.25 225

MVS_111021_HR		98.25 178	98.08 186	98.75 175	99.09 209	97.46 194	95.97 337	99.27 190	97.60 200	97.99 272	98.25 292	98.15 90	99.38 365	96.87 203	99.57 212	99.42 168

FE-MVS		95.66 322	94.95 335	97.77 270	98.53 316	95.28 280	99.40 16	96.09 376	93.11 366	97.96 273	99.26 110	79.10 393	99.77 222	92.40 365	98.71 327	98.27 354

MCST-MVS		98.00 197	97.63 224	99.10 116	99.24 171	98.17 129	96.89 290	98.73 298	95.66 311	97.92 274	97.70 330	97.17 161	99.66 284	96.18 260	99.23 275	99.47 151

MG-MVS		96.77 286	96.61 285	97.26 312	98.31 335	93.06 343	95.93 342	98.12 330	96.45 285	97.92 274	98.73 230	93.77 288	99.39 363	91.19 382	99.04 300	99.33 207

MSLP-MVS++		98.02 195	98.14 180	97.64 284	98.58 309	95.19 284	97.48 250	99.23 203	97.47 213	97.90 276	98.62 253	97.04 167	98.81 401	97.55 154	99.41 246	98.94 282

cl22		95.79 318	95.39 322	96.98 324	96.77 401	92.79 349	94.40 392	98.53 310	94.59 339	97.89 277	98.17 299	82.82 380	99.24 382	96.37 247	99.03 301	98.92 284

mvsmamba		97.57 234	97.26 245	98.51 210	98.69 287	96.73 236	98.74 92	97.25 352	97.03 257	97.88 278	99.23 119	90.95 322	99.87 106	96.61 225	99.00 306	98.91 287

test_vis1_rt		97.75 220	97.72 216	97.83 265	98.81 264	96.35 246	97.30 263	99.69 39	94.61 338	97.87 279	98.05 309	96.26 210	98.32 407	98.74 81	98.18 351	98.82 297

BH-RMVSNet		96.83 283	96.58 288	97.58 289	98.47 320	94.05 316	96.67 301	97.36 347	96.70 275	97.87 279	97.98 313	95.14 251	99.44 356	90.47 390	98.58 339	99.25 225

MIMVSNet		96.62 292	96.25 300	97.71 279	99.04 221	94.66 300	99.16 51	96.92 363	97.23 244	97.87 279	99.10 147	86.11 356	99.65 289	91.65 372	99.21 279	98.82 297

LF4IMVS		97.90 203	97.69 217	98.52 209	99.17 193	97.66 183	97.19 275	99.47 106	96.31 290	97.85 282	98.20 297	96.71 191	99.52 335	94.62 308	99.72 152	98.38 348

CPTT-MVS		97.84 216	97.36 240	99.27 90	99.31 156	98.46 107	98.29 144	99.27 190	94.90 333	97.83 283	98.37 282	94.90 256	99.84 144	93.85 335	99.54 220	99.51 127

CMPMVS	75.91 23	96.29 302	95.44 319	98.84 157	96.25 411	98.69 90	97.02 280	99.12 229	88.90 401	97.83 283	98.86 207	89.51 333	98.90 399	91.92 367	99.51 229	98.92 284
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
E-PMN		94.17 348	94.37 343	93.58 392	96.86 398	85.71 408	90.11 414	97.07 356	98.17 159	97.82 285	97.19 353	84.62 367	98.94 396	89.77 392	97.68 369	96.09 408

CDPH-MVS		97.26 256	96.66 283	99.07 122	99.00 226	98.15 130	96.03 335	99.01 251	91.21 388	97.79 286	97.85 322	96.89 176	99.69 261	92.75 359	99.38 251	99.39 181

HQP_MVS		97.99 200	97.67 218	98.93 146	99.19 185	97.65 184	97.77 214	99.27 190	98.20 156	97.79 286	97.98 313	94.90 256	99.70 257	94.42 316	99.51 229	99.45 157

plane_prior3						97.78 175			97.41 222	97.79 286

MDTV_nov1_ep13_2view						74.92 424	97.69 224		90.06 397	97.75 289		85.78 358		93.52 342		98.69 319

pmmvs3		95.03 335	94.40 342	96.93 326	97.70 368	92.53 354	95.08 373	97.71 339	88.57 402	97.71 290	98.08 307	79.39 391	99.82 171	96.19 258	99.11 295	98.43 343

DP-MVS Recon		97.33 251	96.92 263	98.57 199	99.09 209	97.99 150	96.79 293	99.35 150	93.18 364	97.71 290	98.07 308	95.00 255	99.31 374	93.97 329	99.13 291	98.42 345

QAPM		97.31 252	96.81 273	98.82 159	98.80 267	97.49 192	99.06 62	99.19 211	90.22 394	97.69 292	99.16 134	96.91 175	99.90 66	90.89 387	99.41 246	99.07 256

SCA		96.41 300	96.66 283	95.67 365	98.24 339	88.35 397	95.85 348	96.88 364	96.11 296	97.67 293	98.67 241	93.10 295	99.85 126	94.16 322	99.22 276	98.81 301

Effi-MVS+-dtu		98.26 176	97.90 204	99.35 72	98.02 352	99.49 6	98.02 178	99.16 222	98.29 146	97.64 294	97.99 312	96.44 202	99.95 24	96.66 222	98.93 315	98.60 327

CNVR-MVS		98.17 187	97.87 206	99.07 122	98.67 292	98.24 122	97.01 281	98.93 259	97.25 238	97.62 295	98.34 286	97.27 155	99.57 317	96.42 244	99.33 257	99.39 181

PVSNet_BlendedMVS		97.55 235	97.53 229	97.60 287	98.92 241	93.77 332	96.64 302	99.43 123	94.49 340	97.62 295	99.18 128	96.82 181	99.67 273	94.73 305	99.93 43	99.36 196

PVSNet_Blended		96.88 281	96.68 280	97.47 302	98.92 241	93.77 332	94.71 381	99.43 123	90.98 390	97.62 295	97.36 350	96.82 181	99.67 273	94.73 305	99.56 215	98.98 272

alignmvs		97.35 249	96.88 266	98.78 169	98.54 314	98.09 137	97.71 222	97.69 340	99.20 65	97.59 298	95.90 377	88.12 346	99.55 324	98.18 113	98.96 312	98.70 318

MP-MVS		98.46 150	98.09 183	99.54 30	99.57 81	99.22 31	98.50 125	99.19 211	97.61 199	97.58 299	98.66 244	97.40 148	99.88 89	94.72 307	99.60 199	99.54 113
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DSMNet-mixed		97.42 245	97.60 226	96.87 330	99.15 199	91.46 369	98.54 116	99.12 229	92.87 370	97.58 299	99.63 35	96.21 211	99.90 66	95.74 280	99.54 220	99.27 221

test0.0.03 1		94.51 341	93.69 350	96.99 323	96.05 412	93.61 338	94.97 376	93.49 400	96.17 293	97.57 301	94.88 398	82.30 381	99.01 394	93.60 340	94.17 410	98.37 350

PCF-MVS	92.86 18	94.36 343	93.00 360	98.42 222	98.70 282	97.56 189	93.16 406	99.11 231	79.59 415	97.55 302	97.43 345	92.19 310	99.73 245	79.85 415	99.45 241	97.97 369
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
XVS		98.72 103	98.45 136	99.53 37	99.46 125	99.21 32	98.65 103	99.34 156	98.62 122	97.54 303	98.63 251	97.50 141	99.83 161	96.79 208	99.53 224	99.56 102

X-MVStestdata		94.32 344	92.59 362	99.53 37	99.46 125	99.21 32	98.65 103	99.34 156	98.62 122	97.54 303	45.85 419	97.50 141	99.83 161	96.79 208	99.53 224	99.56 102

旧先验2							95.76 351		88.56 403	97.52 305			99.66 284	94.48 312

PMVS	91.26 20	97.86 210	97.94 200	97.65 282	99.71 45	97.94 159	98.52 118	98.68 301	98.99 97	97.52 305	99.35 89	97.41 147	98.18 409	91.59 374	99.67 178	96.82 398
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ETV-MVS		98.03 194	97.86 207	98.56 203	98.69 287	98.07 143	97.51 248	99.50 89	98.10 164	97.50 307	95.51 384	98.41 62	99.88 89	96.27 254	99.24 272	97.71 382

PS-MVSNAJ		97.08 270	97.39 237	96.16 357	98.56 312	92.46 355	95.24 369	98.85 279	97.25 238	97.49 308	95.99 374	98.07 93	99.90 66	96.37 247	98.67 333	96.12 407

xiu_mvs_v2_base		97.16 266	97.49 232	96.17 355	98.54 314	92.46 355	95.45 362	98.84 280	97.25 238	97.48 309	96.49 365	98.31 71	99.90 66	96.34 250	98.68 332	96.15 406

sasdasda		98.34 163	98.26 164	98.58 196	98.46 322	97.82 170	98.96 74	99.46 109	99.19 69	97.46 310	95.46 388	98.59 50	99.46 352	98.08 120	98.71 327	98.46 335

canonicalmvs		98.34 163	98.26 164	98.58 196	98.46 322	97.82 170	98.96 74	99.46 109	99.19 69	97.46 310	95.46 388	98.59 50	99.46 352	98.08 120	98.71 327	98.46 335

testdata				98.09 248	98.93 237	95.40 276		98.80 287	90.08 396	97.45 312	98.37 282	95.26 248	99.70 257	93.58 341	98.95 313	99.17 246

thres600view7		94.45 342	93.83 348	96.29 348	99.06 217	91.53 368	97.99 186	94.24 396	98.34 139	97.44 313	95.01 394	79.84 387	99.67 273	84.33 407	98.23 348	97.66 383

EMVS		93.83 354	94.02 346	93.23 396	96.83 400	84.96 409	89.77 415	96.32 373	97.92 176	97.43 314	96.36 371	86.17 354	98.93 397	87.68 399	97.73 368	95.81 409

MGCFI-Net		98.34 163	98.28 160	98.51 210	98.47 320	97.59 188	98.96 74	99.48 98	99.18 71	97.40 315	95.50 385	98.66 43	99.50 341	98.18 113	98.71 327	98.44 341

thres100view900		94.19 347	93.67 351	95.75 364	99.06 217	91.35 372	98.03 176	94.24 396	98.33 140	97.40 315	94.98 396	79.84 387	99.62 298	83.05 409	98.08 359	96.29 402

Fast-Effi-MVS+-dtu		98.27 174	98.09 183	98.81 161	98.43 326	98.11 134	97.61 236	99.50 89	98.64 118	97.39 317	97.52 340	98.12 92	99.95 24	96.90 200	98.71 327	98.38 348

API-MVS		97.04 273	96.91 265	97.42 305	97.88 358	98.23 126	98.18 154	98.50 312	97.57 202	97.39 317	96.75 361	96.77 185	99.15 389	90.16 391	99.02 304	94.88 412

PatchMatch-RL		97.24 259	96.78 274	98.61 192	99.03 224	97.83 167	96.36 316	99.06 237	93.49 362	97.36 319	97.78 324	95.75 234	99.49 344	93.44 345	98.77 322	98.52 333

ttmdpeth		97.91 202	98.02 191	97.58 289	98.69 287	94.10 315	98.13 160	98.90 265	97.95 172	97.32 320	99.58 43	95.95 228	98.75 402	96.41 245	99.22 276	99.87 18

sss		97.21 261	96.93 261	98.06 253	98.83 259	95.22 283	96.75 297	98.48 313	94.49 340	97.27 321	97.90 319	92.77 303	99.80 192	96.57 229	99.32 258	99.16 249

KD-MVS_2432*1600		92.87 369	91.99 371	95.51 370	91.37 421	89.27 393	94.07 396	98.14 328	95.42 320	97.25 322	96.44 368	67.86 409	99.24 382	91.28 379	96.08 400	98.02 365

miper_refine_blended		92.87 369	91.99 371	95.51 370	91.37 421	89.27 393	94.07 396	98.14 328	95.42 320	97.25 322	96.44 368	67.86 409	99.24 382	91.28 379	96.08 400	98.02 365

WTY-MVS		96.67 289	96.27 299	97.87 263	98.81 264	94.61 302	96.77 295	97.92 335	94.94 332	97.12 324	97.74 327	91.11 321	99.82 171	93.89 332	98.15 355	99.18 242

tfpn200view9		94.03 351	93.44 353	95.78 363	98.93 237	91.44 370	97.60 237	94.29 394	97.94 174	97.10 325	94.31 403	79.67 389	99.62 298	83.05 409	98.08 359	96.29 402

thres400		94.14 349	93.44 353	96.24 351	98.93 237	91.44 370	97.60 237	94.29 394	97.94 174	97.10 325	94.31 403	79.67 389	99.62 298	83.05 409	98.08 359	97.66 383

PatchmatchNet		95.58 324	95.67 309	95.30 375	97.34 388	87.32 402	97.65 231	96.65 367	95.30 324	97.07 327	98.69 237	84.77 365	99.75 235	94.97 300	98.64 334	98.83 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNLPA		97.17 265	96.71 278	98.55 204	98.56 312	98.05 147	96.33 318	98.93 259	96.91 263	97.06 328	97.39 347	94.38 273	99.45 354	91.66 371	99.18 285	98.14 359

WB-MVSnew		95.73 320	95.57 314	96.23 352	96.70 402	90.70 386	96.07 334	93.86 399	95.60 314	97.04 329	95.45 391	96.00 220	99.55 324	91.04 383	98.31 346	98.43 343

NCCC		97.86 210	97.47 235	99.05 129	98.61 302	98.07 143	96.98 283	98.90 265	97.63 195	97.04 329	97.93 318	95.99 224	99.66 284	95.31 293	98.82 321	99.43 165

TR-MVS		95.55 325	95.12 331	96.86 333	97.54 376	93.94 323	96.49 309	96.53 371	94.36 347	97.03 331	96.61 363	94.26 277	99.16 388	86.91 403	96.31 396	97.47 389

MDTV_nov1_ep13			95.22 328		97.06 396	83.20 417	97.74 219	96.16 374	94.37 346	96.99 332	98.83 213	83.95 373	99.53 331	93.90 331	97.95 366

CANet		97.87 209	97.76 211	98.19 243	97.75 362	95.51 271	96.76 296	99.05 240	97.74 188	96.93 333	98.21 296	95.59 239	99.89 77	97.86 137	99.93 43	99.19 240

EPMVS		93.72 356	93.27 355	95.09 378	96.04 413	87.76 400	98.13 160	85.01 420	94.69 337	96.92 334	98.64 249	78.47 398	99.31 374	95.04 297	96.46 394	98.20 356

AdaColmap		97.14 267	96.71 278	98.46 217	98.34 333	97.80 174	96.95 284	98.93 259	95.58 315	96.92 334	97.66 331	95.87 231	99.53 331	90.97 384	99.14 289	98.04 364

thisisatest0515		94.12 350	93.16 357	96.97 325	98.60 304	92.90 347	93.77 402	90.61 411	94.10 352	96.91 336	95.87 378	74.99 401	99.80 192	94.52 311	99.12 294	98.20 356

CR-MVSNet		96.28 303	95.95 302	97.28 310	97.71 366	94.22 309	98.11 164	98.92 262	92.31 376	96.91 336	99.37 84	85.44 362	99.81 185	97.39 163	97.36 381	97.81 375

RPMNet		97.02 274	96.93 261	97.30 309	97.71 366	94.22 309	98.11 164	99.30 176	99.37 46	96.91 336	99.34 93	86.72 349	99.87 106	97.53 157	97.36 381	97.81 375

HPM-MVS++		98.10 189	97.64 223	99.48 53	99.09 209	99.13 59	97.52 246	98.75 295	97.46 218	96.90 339	97.83 323	96.01 219	99.84 144	95.82 278	99.35 254	99.46 153

PatchT		96.65 290	96.35 294	97.54 295	97.40 386	95.32 279	97.98 187	96.64 368	99.33 51	96.89 340	99.42 77	84.32 370	99.81 185	97.69 149	97.49 372	97.48 388

1112_ss		97.29 255	96.86 267	98.58 196	99.34 153	96.32 247	96.75 297	99.58 58	93.14 365	96.89 340	97.48 342	92.11 312	99.86 114	96.91 195	99.54 220	99.57 96

test222					98.92 241	96.93 227	95.54 357	98.78 290	85.72 408	96.86 342	98.11 303	94.43 270			99.10 296	99.23 230

thres200		93.72 356	93.14 358	95.46 372	98.66 297	91.29 374	96.61 304	94.63 391	97.39 224	96.83 343	93.71 406	79.88 386	99.56 320	82.40 412	98.13 356	95.54 411

UGNet		98.53 142	98.45 136	98.79 166	97.94 355	96.96 224	99.08 58	98.54 309	99.10 83	96.82 344	99.47 69	96.55 197	99.84 144	98.56 96	99.94 38	99.55 109
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
Test_1112_low_res		96.99 278	96.55 289	98.31 234	99.35 151	95.47 273	95.84 349	99.53 83	91.51 384	96.80 345	98.48 272	91.36 319	99.83 161	96.58 227	99.53 224	99.62 70

testing3		93.51 358	92.09 368	97.75 274	98.60 304	94.40 306	97.32 261	95.26 387	97.56 204	96.79 346	95.50 385	53.57 424	99.77 222	95.26 294	98.97 311	99.08 254

新几何1				98.91 150	98.94 235	97.76 176		98.76 292	87.58 405	96.75 347	98.10 304	94.80 263	99.78 216	92.73 360	99.00 306	99.20 235

Effi-MVS+		98.02 195	97.82 209	98.62 189	98.53 316	97.19 212	97.33 260	99.68 44	97.30 233	96.68 348	97.46 344	98.56 54	99.80 192	96.63 223	98.20 350	98.86 294

GA-MVS		95.86 315	95.32 325	97.49 300	98.60 304	94.15 314	93.83 401	97.93 334	95.49 318	96.68 348	97.42 346	83.21 376	99.30 376	96.22 256	98.55 340	99.01 266

EIA-MVS		98.00 197	97.74 213	98.80 163	98.72 275	98.09 137	98.05 173	99.60 55	97.39 224	96.63 350	95.55 383	97.68 120	99.80 192	96.73 216	99.27 267	98.52 333

F-COLMAP		97.30 253	96.68 280	99.14 110	99.19 185	98.39 110	97.27 267	99.30 176	92.93 368	96.62 351	98.00 311	95.73 235	99.68 270	92.62 362	98.46 342	99.35 200

PAPM_NR		96.82 285	96.32 296	98.30 235	99.07 213	96.69 238	97.48 250	98.76 292	95.81 309	96.61 352	96.47 367	94.12 281	99.17 387	90.82 388	97.78 367	99.06 257

dmvs_re		95.98 312	95.39 322	97.74 276	98.86 253	97.45 195	98.37 140	95.69 385	97.95 172	96.56 353	95.95 375	90.70 325	97.68 412	88.32 397	96.13 399	98.11 360

test12				98.93 146	98.58 309	97.83 167		98.66 302		96.53 354		95.51 242	99.69 261		99.13 291	99.27 221

BH-w/o		95.13 333	94.89 337	95.86 360	98.20 342	91.31 373	95.65 354	97.37 346	93.64 358	96.52 355	95.70 381	93.04 298	99.02 392	88.10 398	95.82 402	97.24 393

ADS-MVSNet2		95.43 328	94.98 333	96.76 337	98.14 346	91.74 365	97.92 194	97.76 337	90.23 392	96.51 356	98.91 194	85.61 359	99.85 126	92.88 354	96.90 388	98.69 319

ADS-MVSNet		95.24 331	94.93 336	96.18 354	98.14 346	90.10 390	97.92 194	97.32 350	90.23 392	96.51 356	98.91 194	85.61 359	99.74 240	92.88 354	96.90 388	98.69 319

114514_t		96.50 296	95.77 304	98.69 181	99.48 122	97.43 197	97.84 206	99.55 76	81.42 414	96.51 356	98.58 258	95.53 240	99.67 273	93.41 346	99.58 208	98.98 272

PVSNet	93.40 17	95.67 321	95.70 307	95.57 368	98.83 259	88.57 395	92.50 408	97.72 338	92.69 372	96.49 359	96.44 368	93.72 289	99.43 357	93.61 339	99.28 266	98.71 315

DPM-MVS		96.32 301	95.59 313	98.51 210	98.76 269	97.21 210	94.54 390	98.26 322	91.94 379	96.37 360	97.25 352	93.06 297	99.43 357	91.42 377	98.74 323	98.89 289

tpmrst		95.07 334	95.46 317	93.91 388	97.11 393	84.36 414	97.62 234	96.96 360	94.98 330	96.35 361	98.80 219	85.46 361	99.59 309	95.60 286	96.23 397	97.79 378

OpenMVS	96.65 7	97.09 269	96.68 280	98.32 232	98.32 334	97.16 215	98.86 86	99.37 141	89.48 398	96.29 362	99.15 138	96.56 196	99.90 66	92.90 353	99.20 280	97.89 370

UWE-MVS		92.38 374	91.76 377	94.21 385	97.16 392	84.65 411	95.42 364	88.45 416	95.96 304	96.17 363	95.84 380	66.36 414	99.71 253	91.87 369	98.64 334	98.28 353

Fast-Effi-MVS+		97.67 226	97.38 238	98.57 199	98.71 278	97.43 197	97.23 268	99.45 113	94.82 335	96.13 364	96.51 364	98.52 56	99.91 60	96.19 258	98.83 319	98.37 350

test_prior2							95.74 352		96.48 283	96.11 365	97.63 334	95.92 230		94.16 322	99.20 280

dp		93.47 359	93.59 352	93.13 397	96.64 403	81.62 421	97.66 229	96.42 372	92.80 371	96.11 365	98.64 249	78.55 397	99.59 309	93.31 347	92.18 415	98.16 358

原ACMM1				98.35 230	98.90 245	96.25 249		98.83 284	92.48 374	96.07 367	98.10 304	95.39 246	99.71 253	92.61 363	98.99 308	99.08 254

PMMVS		96.51 294	95.98 301	98.09 248	97.53 378	95.84 261	94.92 377	98.84 280	91.58 382	96.05 368	95.58 382	95.68 236	99.66 284	95.59 287	98.09 358	98.76 311

tpm		94.67 340	94.34 344	95.66 366	97.68 371	88.42 396	97.88 199	94.90 388	94.46 342	96.03 369	98.56 260	78.66 394	99.79 205	95.88 271	95.01 406	98.78 308

TEST9					98.71 278	98.08 141	95.96 339	99.03 245	91.40 385	95.85 370	97.53 338	96.52 198	99.76 228

train_agg		97.10 268	96.45 293	99.07 122	98.71 278	98.08 141	95.96 339	99.03 245	91.64 380	95.85 370	97.53 338	96.47 200	99.76 228	93.67 338	99.16 286	99.36 196

test_8					98.67 292	98.01 149	95.91 345	99.02 248	91.64 380	95.79 372	97.50 341	96.47 200	99.76 228

agg_prior					98.68 291	97.99 150		99.01 251		95.59 373			99.77 222

PLC	94.65 16	96.51 294	95.73 306	98.85 156	98.75 271	97.91 160	96.42 313	99.06 237	90.94 391	95.59 373	97.38 348	94.41 271	99.59 309	90.93 385	98.04 364	99.05 258
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HQP4-MVS										95.56 375			99.54 329			99.32 209

HQP-NCC					98.67 292		96.29 321		96.05 298	95.55 376

ACMP_Plane					98.67 292		96.29 321		96.05 298	95.55 376

HQP-MVS		97.00 277	96.49 292	98.55 204	98.67 292	96.79 231	96.29 321	99.04 243	96.05 298	95.55 376	96.84 359	93.84 284	99.54 329	92.82 356	99.26 270	99.32 209

MAR-MVS		96.47 298	95.70 307	98.79 166	97.92 356	99.12 61	98.28 145	98.60 307	92.16 378	95.54 379	96.17 372	94.77 265	99.52 335	89.62 393	98.23 348	97.72 381
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
AUN-MVS		96.24 306	95.45 318	98.60 194	98.70 282	97.22 209	97.38 256	97.65 342	95.95 305	95.53 380	97.96 317	82.11 383	99.79 205	96.31 251	97.44 375	98.80 306

tpmvs		95.02 336	95.25 326	94.33 382	96.39 410	85.87 405	98.08 168	96.83 365	95.46 319	95.51 381	98.69 237	85.91 357	99.53 331	94.16 322	96.23 397	97.58 386

MVS-HIRNet		94.32 344	95.62 310	90.42 399	98.46 322	75.36 423	96.29 321	89.13 415	95.25 325	95.38 382	99.75 13	92.88 300	99.19 386	94.07 328	99.39 248	96.72 400

PAPR		95.29 329	94.47 340	97.75 274	97.50 384	95.14 286	94.89 378	98.71 300	91.39 386	95.35 383	95.48 387	94.57 268	99.14 390	84.95 406	97.37 379	98.97 275

HY-MVS	95.94 13	95.90 314	95.35 324	97.55 294	97.95 354	94.79 293	98.81 91	96.94 362	92.28 377	95.17 384	98.57 259	89.90 331	99.75 235	91.20 381	97.33 383	98.10 361

CANet_DTU		97.26 256	97.06 256	97.84 264	97.57 373	94.65 301	96.19 327	98.79 288	97.23 244	95.14 385	98.24 293	93.22 292	99.84 144	97.34 165	99.84 85	99.04 262

cascas		94.79 339	94.33 345	96.15 358	96.02 414	92.36 359	92.34 410	99.26 195	85.34 409	95.08 386	94.96 397	92.96 299	98.53 405	94.41 319	98.59 338	97.56 387

CostFormer		93.97 352	93.78 349	94.51 381	97.53 378	85.83 407	97.98 187	95.96 378	89.29 400	94.99 387	98.63 251	78.63 395	99.62 298	94.54 310	96.50 393	98.09 362

Syy-MVS		96.04 309	95.56 315	97.49 300	97.10 394	94.48 304	96.18 328	96.58 369	95.65 312	94.77 388	92.29 415	91.27 320	99.36 366	98.17 115	98.05 362	98.63 325

myMVS_eth3d		91.92 380	90.45 382	96.30 347	97.10 394	90.90 382	96.18 328	96.58 369	95.65 312	94.77 388	92.29 415	53.88 423	99.36 366	89.59 394	98.05 362	98.63 325

ETVMVS		92.60 371	91.08 380	97.18 314	97.70 368	93.65 337	96.54 305	95.70 383	96.51 280	94.68 390	92.39 414	61.80 421	99.50 341	86.97 401	97.41 377	98.40 346

CHOSEN 280x420		95.51 327	95.47 316	95.65 367	98.25 338	88.27 398	93.25 405	98.88 269	93.53 360	94.65 391	97.15 355	86.17 354	99.93 42	97.41 162	99.93 43	98.73 314

JIA-IIPM		95.52 326	95.03 332	97.00 322	96.85 399	94.03 319	96.93 287	95.82 381	99.20 65	94.63 392	99.71 19	83.09 377	99.60 305	94.42 316	94.64 407	97.36 392

MVS		93.19 364	92.09 368	96.50 342	96.91 397	94.03 319	98.07 170	98.06 332	68.01 417	94.56 393	96.48 366	95.96 227	99.30 376	83.84 408	96.89 390	96.17 404

1314		95.74 319	95.60 311	96.17 355	97.53 378	92.75 351	98.07 170	98.31 321	91.22 387	94.25 394	96.68 362	95.53 240	99.03 391	91.64 373	97.18 385	96.74 399

tpm cat1		93.29 362	93.13 359	93.75 390	97.39 387	84.74 410	97.39 255	97.65 342	83.39 412	94.16 395	98.41 277	82.86 379	99.39 363	91.56 375	95.35 405	97.14 394

test-LLR		93.90 353	93.85 347	94.04 386	96.53 405	84.62 412	94.05 398	92.39 405	96.17 293	94.12 396	95.07 392	82.30 381	99.67 273	95.87 274	98.18 351	97.82 373

test-mter		92.33 376	91.76 377	94.04 386	96.53 405	84.62 412	94.05 398	92.39 405	94.00 355	94.12 396	95.07 392	65.63 417	99.67 273	95.87 274	98.18 351	97.82 373

tpm2		93.09 365	92.58 363	94.62 380	97.56 374	86.53 404	97.66 229	95.79 382	86.15 407	94.07 398	98.23 295	75.95 399	99.53 331	90.91 386	96.86 391	97.81 375

dmvs_testset		92.94 368	92.21 367	95.13 376	98.59 307	90.99 381	97.65 231	92.09 407	96.95 260	94.00 399	93.55 407	92.34 309	96.97 415	72.20 418	92.52 413	97.43 390

TESTMET0.1,1		92.19 378	91.77 376	93.46 393	96.48 407	82.80 418	94.05 398	91.52 410	94.45 344	94.00 399	94.88 398	66.65 413	99.56 320	95.78 279	98.11 357	98.02 365

UBG		93.25 363	92.32 364	96.04 359	97.72 363	90.16 389	95.92 344	95.91 380	96.03 301	93.95 401	93.04 411	69.60 407	99.52 335	90.72 389	97.98 365	98.45 338

PVSNet_0	89.98 21	91.15 382	90.30 385	93.70 391	97.72 363	84.34 415	90.24 412	97.42 345	90.20 395	93.79 402	93.09 410	90.90 324	98.89 400	86.57 404	72.76 419	97.87 372

FPMVS		93.44 360	92.23 366	97.08 319	99.25 170	97.86 164	95.61 355	97.16 354	92.90 369	93.76 403	98.65 246	75.94 400	95.66 416	79.30 416	97.49 372	97.73 380

testing91		93.32 361	92.27 365	96.47 343	97.54 376	91.25 376	96.17 330	96.76 366	97.18 248	93.65 404	93.50 408	65.11 418	99.63 295	93.04 351	97.45 374	98.53 332

testing99		93.04 367	91.98 373	96.23 352	97.53 378	90.70 386	96.35 317	95.94 379	96.87 265	93.41 405	93.43 409	63.84 420	99.59 309	93.24 349	97.19 384	98.40 346

EPNet		96.14 307	95.44 319	98.25 238	90.76 423	95.50 272	97.92 194	94.65 390	98.97 100	92.98 406	98.85 210	89.12 336	99.87 106	95.99 267	99.68 172	99.39 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing222		91.96 379	90.37 383	96.72 338	97.47 385	92.59 352	96.11 332	94.76 389	96.83 267	92.90 407	92.87 412	57.92 422	99.55 324	86.93 402	97.52 371	98.00 368

testing11		93.08 366	92.02 370	96.26 350	97.56 374	90.83 384	96.32 319	95.70 383	96.47 284	92.66 408	93.73 405	64.36 419	99.59 309	93.77 337	97.57 370	98.37 350

baseline2		93.73 355	92.83 361	96.42 344	97.70 368	91.28 375	96.84 292	89.77 414	93.96 356	92.44 409	95.93 376	79.14 392	99.77 222	92.94 352	96.76 392	98.21 355

IB-MVS	91.63 19	92.24 377	90.90 381	96.27 349	97.22 391	91.24 377	94.36 393	93.33 402	92.37 375	92.24 410	94.58 402	66.20 416	99.89 77	93.16 350	94.63 408	97.66 383
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
gg-mvs-nofinetune		92.37 375	91.20 379	95.85 361	95.80 416	92.38 358	99.31 27	81.84 422	99.75 8	91.83 411	99.74 15	68.29 408	99.02 392	87.15 400	97.12 386	96.16 405

DeepMVS_CX				93.44 394	98.24 339	94.21 311		94.34 393	64.28 418	91.34 412	94.87 400	89.45 335	92.77 419	77.54 417	93.14 412	93.35 414

PAPM		91.88 381	90.34 384	96.51 341	98.06 351	92.56 353	92.44 409	97.17 353	86.35 406	90.38 413	96.01 373	86.61 350	99.21 385	70.65 419	95.43 404	97.75 379

ET-MVSNet_ETH3D		94.30 346	93.21 356	97.58 289	98.14 346	94.47 305	94.78 380	93.24 403	94.72 336	89.56 414	95.87 378	78.57 396	99.81 185	96.91 195	97.11 387	98.46 335

dongtai		76.24 386	75.95 389	77.12 402	92.39 420	67.91 426	90.16 413	59.44 427	82.04 413	89.42 415	94.67 401	49.68 425	81.74 420	48.06 420	77.66 418	81.72 416

EPNet_dtu		94.93 338	94.78 338	95.38 374	93.58 419	87.68 401	96.78 294	95.69 385	97.35 228	89.14 416	98.09 306	88.15 345	99.49 344	94.95 301	99.30 263	98.98 272
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GG-mvs-BLEND				94.76 379	94.54 418	92.13 363	99.31 27	80.47 423		88.73 417	91.01 417	67.59 412	98.16 410	82.30 413	94.53 409	93.98 413

tmp_tt		78.77 385	78.73 388	78.90 401	58.45 426	74.76 425	94.20 395	78.26 424	39.16 419	86.71 418	92.82 413	80.50 385	75.19 421	86.16 405	92.29 414	86.74 415

MVE	83.40 22	92.50 372	91.92 374	94.25 383	98.83 259	91.64 367	92.71 407	83.52 421	95.92 306	86.46 419	95.46 388	95.20 249	95.40 417	80.51 414	98.64 334	95.73 410
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		79.78 384	79.50 387	80.62 400	80.21 425	45.76 428	70.82 416	98.41 318	31.08 420	80.89 420	97.71 328	84.85 364	97.37 413	91.51 376	80.03 417	98.75 312

kuosan		69.30 387	68.95 390	70.34 403	87.68 424	65.00 427	91.11 411	59.90 426	69.02 416	74.46 421	88.89 418	48.58 426	68.03 422	28.61 421	72.33 420	77.99 417

EGC-MVSNET		85.24 383	80.54 386	99.34 75	99.77 26	99.20 38	99.08 58	99.29 184	12.08 421	20.84 422	99.42 77	97.55 134	99.85 126	97.08 182	99.72 152	98.96 277

testmvs		17.12 389	20.53 392	6.87 405	12.05 427	4.20 430	93.62 404	6.73 428	4.62 423	10.41 423	24.33 420	8.28 428	3.56 424	9.69 423	15.07 421	12.86 420

test123		17.04 390	20.11 393	7.82 404	10.25 428	4.91 429	94.80 379	4.47 429	4.93 422	10.00 424	24.28 421	9.69 427	3.64 423	10.14 422	12.43 422	14.92 419

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

cdsmvs_eth3d_5k		24.66 388	32.88 391	0.00 406	0.00 429	0.00 431	0.00 417	99.10 232	0.00 424	0.00 425	97.58 336	99.21 16	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		8.17 391	10.90 394	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	98.07 93	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

ab-mvs-re		8.12 392	10.83 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	97.48 342	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						90.90 382								91.37 378

MSC_two_6792asdad				99.32 82	98.43 326	98.37 113		98.86 276					99.89 77	97.14 177	99.60 199	99.71 49

No_MVS				99.32 82	98.43 326	98.37 113		98.86 276					99.89 77	97.14 177	99.60 199	99.71 49

eth-test2					0.00 429

eth-test					0.00 429

OPU-MVS				98.82 159	98.59 307	98.30 118	98.10 166				98.52 264	98.18 84	98.75 402	94.62 308	99.48 238	99.41 171

save fliter					99.11 204	97.97 154	96.53 307	99.02 248	98.24 149

test_0728_SECOND				99.60 14	99.50 108	99.23 30	98.02 178	99.32 163					99.88 89	96.99 189	99.63 189	99.68 56

GSMVS																98.81 301

sam_mvs1												84.74 366				98.81 301

sam_mvs												84.29 372

MTGPA								99.20 207

test_post1							97.59 239				20.48 423	83.07 378	99.66 284	94.16 322

test_post											21.25 422	83.86 374	99.70 257

patchmatchnet-post											98.77 225	84.37 369	99.85 126

MTMP							97.93 191	91.91 409

gm-plane-assit					94.83 417	81.97 420			88.07 404		94.99 395		99.60 305	91.76 370

test9_res														93.28 348	99.15 288	99.38 188

agg_prior2														92.50 364	99.16 286	99.37 190

test_prior4						97.97 154	95.86 346

test_prior				98.95 143	98.69 287	97.95 158		99.03 245					99.59 309			99.30 216

新几何2							95.93 342

旧先验1					98.82 262	97.45 195		98.76 292			98.34 286	95.50 243			99.01 305	99.23 230

无先验							95.74 352	98.74 297	89.38 399				99.73 245	92.38 366		99.22 234

原ACMM2							95.53 358

testdata2													99.79 205	92.80 358

segment_acmp												97.02 170

testdata1							95.44 363		96.32 289

plane_prior7					99.19 185	97.87 163

plane_prior6					98.99 229	97.70 182						94.90 256

plane_prior5								99.27 190					99.70 257	94.42 316	99.51 229	99.45 157

plane_prior4											97.98 313

plane_prior2							97.77 214		98.20 156

plane_prior1					99.05 220

plane_prior						97.65 184	97.07 279		96.72 273						99.36 252

n2								0.00 430

nn								0.00 430

door-mid								99.57 65

test11								98.87 271

door								99.41 130

HQP5-MVS						96.79 231

BP-MVS														92.82 356

HQP3-MVS								99.04 243							99.26 270

HQP2-MVS												93.84 284

NP-MVS					98.84 257	97.39 199					96.84 359

ACMMP++_ref															99.77 125

ACMMP++															99.68 172

Test By Simon												96.52 198

High-resolution multi-view benchmark