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		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 3	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 6

tt0320		99.07 6	99.29 4	98.43 63	99.55 24	95.92 87	98.97 10	99.53 25	99.67 3	99.79 2	99.71 3	98.33 14	99.78 59	98.11 49	99.92 15	99.57 55

tt0320-xc		99.10 4	99.31 3	98.49 58	99.57 20	96.09 80	98.91 11	99.55 23	99.67 3	99.78 3	99.69 4	98.63 10	99.77 70	98.02 55	99.93 11	99.60 43

mamv4		99.05 8	98.91 11	99.46 2	98.94 126	99.62 2	97.98 67	99.70 8	99.49 6	99.78 3	99.22 39	95.92 131	99.95 3	99.31 7	99.83 51	98.83 240

sc_t1		99.09 5	99.28 5	98.53 55	99.72 8	96.21 74	98.87 12	99.19 50	99.71 2	99.76 5	99.65 8	98.64 9	99.79 54	98.07 53	99.90 25	99.58 47

PS-MVSNAJss		98.53 28	98.63 24	98.21 84	99.68 12	94.82 136	98.10 59	99.21 46	96.91 109	99.75 6	99.45 18	95.82 137	99.92 6	98.80 29	99.96 4	99.89 4

UniMVSNet_ETH3D		99.12 3	99.28 5	98.65 46	99.77 5	96.34 70	99.18 6	99.20 48	99.67 3	99.73 7	99.65 8	99.15 3	99.86 28	97.22 91	99.92 15	99.77 15

test_fmvsmvis_n_1920		98.08 56	98.47 33	96.93 192	99.03 115	93.29 199	96.32 183	99.65 13	95.59 183	99.71 8	99.01 65	97.66 38	99.60 184	99.44 3	99.83 51	97.90 341

mvs_tets		98.90 9	98.94 9	98.75 35	99.69 11	96.48 64	98.54 26	99.22 45	96.23 140	99.71 8	99.48 15	98.77 7	99.93 4	98.89 27	99.95 5	99.84 8

wuyk23d		93.25 330	95.20 243	87.40 424	96.07 380	95.38 112	97.04 135	94.97 366	95.33 197	99.70 10	98.11 188	98.14 21	91.94 442	77.76 432	99.68 96	74.89 442

Anonymous20231211		98.55 25	98.76 17	97.94 106	98.79 148	94.37 155	98.84 14	99.15 58	99.37 7	99.67 11	99.43 20	95.61 149	99.72 104	98.12 48	99.86 35	99.73 25

jajsoiax		98.77 13	98.79 16	98.74 38	99.66 13	96.48 64	98.45 34	99.12 63	95.83 172	99.67 11	99.37 24	98.25 17	99.92 6	98.77 30	99.94 8	99.82 9

ANet_high		98.31 40	98.94 9	96.41 231	99.33 55	89.64 286	97.92 73	99.56 22	99.27 11	99.66 13	99.50 14	97.67 36	99.83 36	97.55 79	99.98 2	99.77 15

test_fmvsmconf0.01_n		98.57 22	98.74 20	98.06 95	99.39 48	94.63 143	96.70 163	99.82 1	95.44 193	99.64 14	99.52 12	98.96 4	99.74 92	99.38 5	99.86 35	99.81 10

pmmvs6		99.07 6	99.24 7	98.56 52	99.81 2	96.38 66	98.87 12	99.30 38	99.01 23	99.63 15	99.66 6	99.27 2	99.68 140	97.75 70	99.89 26	99.62 42

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 41	99.71 10	96.99 48	99.69 2	99.57 20	99.02 22	99.62 16	99.36 26	98.53 11	99.52 210	98.58 39	99.95 5	99.66 35
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
OurMVSNet-221017-0		98.61 20	98.61 28	98.63 48	99.77 5	96.35 69	99.17 7	99.05 84	98.05 61	99.61 17	99.52 12	93.72 211	99.88 23	98.72 35	99.88 28	99.65 38

test_fmvsmconf0.1_n		98.41 35	98.54 31	98.03 100	99.16 87	94.61 144	96.18 194	99.73 5	95.05 211	99.60 18	99.34 29	98.68 8	99.72 104	99.21 11	99.85 44	99.76 20

test_fmvsm_n_1920		98.08 56	98.29 50	97.43 151	98.88 137	93.95 172	96.17 198	99.57 20	95.66 178	99.52 19	98.71 100	97.04 70	99.64 164	99.21 11	99.87 33	98.69 260

fmvsm_s_conf0.1_n_2		97.68 107	98.18 54	96.20 244	99.06 107	89.08 302	95.51 252	99.72 6	96.06 151	99.48 20	99.24 36	95.18 164	99.60 184	99.45 2	99.88 28	99.94 3

TransMVSNet (Re)		98.38 36	98.67 22	97.51 138	99.51 31	93.39 197	98.20 54	98.87 135	98.23 54	99.48 20	99.27 34	98.47 13	99.55 201	96.52 118	99.53 151	99.60 43

LCM-MVSNet-Re		97.33 141	97.33 137	97.32 160	98.13 246	93.79 178	96.99 138	99.65 13	96.74 115	99.47 22	98.93 76	96.91 83	99.84 34	90.11 342	99.06 260	98.32 298

Elysia		98.19 47	98.37 41	97.66 126	99.28 59	93.52 189	97.35 116	98.90 123	98.63 33	99.45 23	98.32 151	94.31 194	99.91 14	99.19 13	99.88 28	99.54 67

StellarMVS		98.19 47	98.37 41	97.66 126	99.28 59	93.52 189	97.35 116	98.90 123	98.63 33	99.45 23	98.32 151	94.31 194	99.91 14	99.19 13	99.88 28	99.54 67

SixPastTwentyTwo		97.49 125	97.57 120	97.26 166	99.56 22	92.33 223	98.28 45	96.97 320	98.30 50	99.45 23	99.35 28	88.43 308	99.89 21	98.01 56	99.76 68	99.54 67

test_fmvsmconf_n		98.30 41	98.41 40	97.99 103	98.94 126	94.60 145	96.00 212	99.64 16	94.99 214	99.43 26	99.18 46	98.51 12	99.71 118	99.13 18	99.84 47	99.67 33

v7n		98.73 15	98.99 8	97.95 105	99.64 14	94.20 163	98.67 18	99.14 61	99.08 17	99.42 27	99.23 38	96.53 104	99.91 14	99.27 9	99.93 11	99.73 25

NR-MVSNet		97.96 66	97.86 83	98.26 76	98.73 157	95.54 102	98.14 57	98.73 174	97.79 66	99.42 27	97.83 219	94.40 192	99.78 59	95.91 150	99.76 68	99.46 102

fmvsm_s_conf0.5_n_2		97.59 119	98.07 61	96.17 248	98.78 152	89.10 301	95.33 268	99.55 23	95.96 160	99.41 29	99.10 56	95.18 164	99.59 186	99.43 4	99.86 35	99.81 10

MIMVSNet1		98.51 29	98.45 37	98.67 44	99.72 8	96.71 54	98.76 16	98.89 126	98.49 41	99.38 30	99.14 53	95.44 156	99.84 34	96.47 120	99.80 60	99.47 100

fmvsm_l_conf0.5_n_3		98.29 42	98.46 34	97.79 114	98.90 135	94.05 168	96.06 205	99.63 17	96.07 150	99.37 31	98.93 76	98.29 16	99.68 140	99.11 20	99.79 62	99.65 38

ACMH	93.61 9	98.44 33	98.76 17	97.51 138	99.43 41	93.54 188	98.23 49	99.05 84	97.40 92	99.37 31	99.08 60	98.79 6	99.47 226	97.74 71	99.71 87	99.50 82
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvsany_test3		96.21 205	95.93 223	97.05 183	97.40 329	94.33 157	95.76 232	94.20 376	89.10 355	99.36 33	99.60 11	93.97 204	97.85 413	95.40 188	98.63 304	98.99 212

anonymousdsp		98.72 18	98.63 24	98.99 14	99.62 16	97.29 41	98.65 22	99.19 50	95.62 181	99.35 34	99.37 24	97.38 48	99.90 18	98.59 38	99.91 19	99.77 15

test_djsdf		98.73 15	98.74 20	98.69 43	99.63 15	96.30 72	98.67 18	99.02 94	96.50 127	99.32 35	99.44 19	97.43 46	99.92 6	98.73 33	99.95 5	99.86 5

PEN-MVS		98.75 14	98.85 14	98.44 62	99.58 19	95.67 97	98.45 34	99.15 58	99.33 9	99.30 36	99.00 66	97.27 53	99.92 6	97.64 76	99.92 15	99.75 23

DTE-MVSNet		98.79 12	98.86 12	98.59 50	99.55 24	96.12 78	98.48 33	99.10 67	99.36 8	99.29 37	99.06 61	97.27 53	99.93 4	97.71 72	99.91 19	99.70 30

test_vis3_rt		97.04 153	96.98 159	97.23 170	98.44 205	95.88 88	96.82 148	99.67 10	90.30 341	99.27 38	99.33 31	94.04 201	96.03 433	97.14 97	97.83 345	99.78 14

pm-mvs1		98.47 32	98.67 22	97.86 110	99.52 30	94.58 146	98.28 45	99.00 105	97.57 79	99.27 38	99.22 39	98.32 15	99.50 215	97.09 99	99.75 77	99.50 82

ACMH+	93.58 10	98.23 46	98.31 47	97.98 104	99.39 48	95.22 125	97.55 103	99.20 48	98.21 55	99.25 40	98.51 125	98.21 18	99.40 252	94.79 220	99.72 84	99.32 139

Anonymous20240529		97.96 66	98.04 65	97.71 120	98.69 167	94.28 161	97.86 77	98.31 237	98.79 29	99.23 41	98.86 86	95.76 143	99.61 182	95.49 173	99.36 204	99.23 163

PS-CasMVS		98.73 15	98.85 14	98.39 67	99.55 24	95.47 109	98.49 31	99.13 62	99.22 13	99.22 42	98.96 72	97.35 49	99.92 6	97.79 67	99.93 11	99.79 13

SD-MVS		97.37 138	97.70 101	96.35 235	98.14 243	95.13 129	96.54 169	98.92 121	95.94 163	99.19 43	98.08 190	97.74 33	95.06 436	95.24 193	99.54 147	98.87 237
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
WR-MVS_H		98.65 19	98.62 26	98.75 35	99.51 31	96.61 60	98.55 25	99.17 53	99.05 20	99.17 44	98.79 88	95.47 154	99.89 21	97.95 59	99.91 19	99.75 23

fmvsm_s_conf0.5_n_8		97.66 109	98.12 56	96.27 240	98.79 148	89.43 292	95.76 232	99.42 31	97.49 84	99.16 45	99.04 62	94.56 187	99.69 134	99.18 15	99.73 79	99.70 30

dcpmvs_2		97.12 150	97.99 71	94.51 330	99.11 99	84.00 390	97.75 86	99.65 13	97.38 94	99.14 46	98.42 135	95.16 166	99.96 2	95.52 172	99.78 66	99.58 47

tfpnnormal		97.72 103	97.97 73	96.94 191	99.26 63	92.23 228	97.83 80	98.45 214	98.25 53	99.13 47	98.66 105	96.65 97	99.69 134	93.92 257	99.62 110	98.91 227

SSC-MVS		95.92 219	97.03 157	92.58 385	99.28 59	78.39 422	96.68 164	95.12 364	98.90 26	99.11 48	98.66 105	91.36 268	99.68 140	95.00 211	99.16 243	99.67 33

fmvsm_s_conf0.5_n_5		97.63 113	97.83 87	97.04 185	98.77 154	92.33 223	95.63 247	99.58 19	93.53 265	99.10 49	98.66 105	96.44 112	99.65 158	99.12 19	99.68 96	99.12 189

fmvsm_s_conf0.5_n_3		97.88 84	98.37 41	96.41 231	98.73 157	89.82 280	95.94 220	99.49 26	96.81 112	99.09 50	99.03 64	97.09 65	99.65 158	99.37 6	99.76 68	99.76 20

SED-MVS		97.94 73	97.90 77	98.07 93	99.22 73	95.35 115	96.79 153	98.83 152	96.11 146	99.08 51	98.24 169	97.87 28	99.72 104	95.44 181	99.51 161	99.14 182

test_241102_ONE					99.22 73	95.35 115		98.83 152	96.04 154	99.08 51	98.13 183	97.87 28	99.33 276

VPA-MVSNet		98.27 43	98.46 34	97.70 122	99.06 107	93.80 177	97.76 85	99.00 105	98.40 45	99.07 53	98.98 69	96.89 84	99.75 83	97.19 95	99.79 62	99.55 65

KinetiMVS		97.82 93	98.02 67	97.24 169	99.24 67	92.32 225	96.92 141	98.38 226	98.56 40	99.03 54	98.33 148	93.22 221	99.83 36	98.74 32	99.71 87	99.57 55

reproduce_model		98.54 26	98.33 46	99.15 4	99.06 107	98.04 12	97.04 135	99.09 72	98.42 44	99.03 54	98.71 100	96.93 79	99.83 36	97.09 99	99.63 107	99.56 61

nrg030		98.54 26	98.62 26	98.32 71	99.22 73	95.66 98	97.90 75	99.08 76	98.31 48	99.02 56	98.74 95	97.68 35	99.61 182	97.77 69	99.85 44	99.70 30

fmvsm_s_conf0.1_n		97.73 101	98.02 67	96.85 200	99.09 102	91.43 254	96.37 179	99.11 64	94.19 244	99.01 57	99.25 35	96.30 120	99.38 259	99.00 24	99.88 28	99.73 25

CP-MVSNet		98.42 34	98.46 34	98.30 74	99.46 38	95.22 125	98.27 47	98.84 146	99.05 20	99.01 57	98.65 109	95.37 158	99.90 18	97.57 78	99.91 19	99.77 15

fmvsm_l_conf0.5_n		97.68 107	97.81 90	97.27 164	98.92 131	92.71 216	95.89 224	99.41 34	93.36 271	99.00 59	98.44 133	96.46 111	99.65 158	99.09 21	99.76 68	99.45 106

casdiffmvs_mvg		97.83 90	98.11 58	97.00 189	98.57 185	92.10 237	95.97 216	99.18 52	97.67 78	99.00 59	98.48 130	97.64 39	99.50 215	96.96 106	99.54 147	99.40 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
FMVSNet1		97.95 70	98.08 60	97.56 133	99.14 97	93.67 182	98.23 49	98.66 192	97.41 91	99.00 59	99.19 42	95.47 154	99.73 98	95.83 155	99.76 68	99.30 144

TDRefinement		98.90 9	98.86 12	99.02 10	99.54 28	98.06 9	99.34 5	99.44 29	98.85 28	99.00 59	99.20 41	97.42 47	99.59 186	97.21 92	99.76 68	99.40 121

reproduce-ours		98.48 30	98.27 51	99.12 5	98.99 118	98.02 13	96.81 149	99.02 94	98.29 51	98.97 63	98.61 112	97.27 53	99.82 39	96.86 110	99.61 116	99.51 79

our_new_method		98.48 30	98.27 51	99.12 5	98.99 118	98.02 13	96.81 149	99.02 94	98.29 51	98.97 63	98.61 112	97.27 53	99.82 39	96.86 110	99.61 116	99.51 79

LuminaMVS		96.76 176	96.58 183	97.30 161	98.94 126	92.96 207	96.17 198	96.15 336	95.54 187	98.96 65	98.18 179	87.73 319	99.80 51	97.98 57	99.61 116	99.15 177

VortexMVS		96.04 213	96.56 186	94.49 332	97.60 313	84.36 385	96.05 206	98.67 189	94.74 220	98.95 66	98.78 91	87.13 326	99.50 215	97.37 88	99.76 68	99.60 43

K. test v3		96.44 195	96.28 205	96.95 190	99.41 44	91.53 250	97.65 95	90.31 423	98.89 27	98.93 67	99.36 26	84.57 348	99.92 6	97.81 65	99.56 136	99.39 126

testf1		98.57 22	98.45 37	98.93 22	99.79 3	98.78 3	97.69 91	99.42 31	97.69 75	98.92 68	98.77 92	97.80 30	99.25 297	96.27 131	99.69 92	98.76 251

APD_test2		98.57 22	98.45 37	98.93 22	99.79 3	98.78 3	97.69 91	99.42 31	97.69 75	98.92 68	98.77 92	97.80 30	99.25 297	96.27 131	99.69 92	98.76 251

fmvsm_l_conf0.5_n_a		97.60 116	97.76 98	97.11 176	98.92 131	92.28 226	95.83 227	99.32 36	93.22 277	98.91 70	98.49 126	96.31 119	99.64 164	99.07 22	99.76 68	99.40 121

fmvsm_s_conf0.1_n_a		97.80 96	98.01 69	97.18 171	99.17 86	92.51 219	96.57 167	99.15 58	93.68 261	98.89 71	99.30 32	96.42 114	99.37 264	99.03 23	99.83 51	99.66 35

FC-MVSNet-test		98.16 49	98.37 41	97.56 133	99.49 35	93.10 204	98.35 38	99.21 46	98.43 43	98.89 71	98.83 87	94.30 196	99.81 44	97.87 62	99.91 19	99.77 15

FOURS1					99.59 18	98.20 8	99.03 8	99.25 44	98.96 25	98.87 73

fmvsm_s_conf0.5_n_6		97.45 128	97.79 92	96.44 226	98.58 183	90.31 273	95.77 231	99.33 35	94.52 233	98.85 74	98.44 133	95.68 145	99.62 174	99.15 17	99.81 56	99.38 128

KD-MVS_self_test		97.86 88	98.07 61	97.25 167	99.22 73	92.81 211	97.55 103	98.94 119	97.10 104	98.85 74	98.88 84	95.03 170	99.67 149	97.39 86	99.65 103	99.26 156

WB-MVS		95.50 238	96.62 179	92.11 395	99.21 80	77.26 432	96.12 201	95.40 358	98.62 35	98.84 76	98.26 167	91.08 271	99.50 215	93.37 270	98.70 297	99.58 47

TranMVSNet+NR-MVSNet		98.33 37	98.30 49	98.43 63	99.07 105	95.87 89	96.73 161	99.05 84	98.67 31	98.84 76	98.45 131	97.58 43	99.88 23	96.45 121	99.86 35	99.54 67

fmvsm_s_conf0.5_n		97.62 114	97.89 80	96.80 204	98.79 148	91.44 253	96.14 200	99.06 80	94.19 244	98.82 78	98.98 69	96.22 125	99.38 259	98.98 26	99.86 35	99.58 47

new-patchmatchnet		95.67 232	96.58 183	92.94 376	97.48 321	80.21 417	92.96 362	98.19 252	94.83 218	98.82 78	98.79 88	93.31 219	99.51 214	95.83 155	99.04 261	99.12 189

EG-PatchMatch MVS		97.69 105	97.79 92	97.40 155	99.06 107	93.52 189	95.96 218	98.97 115	94.55 232	98.82 78	98.76 94	97.31 51	99.29 289	97.20 94	99.44 181	99.38 128

SDMVSNet		97.97 64	98.26 53	97.11 176	99.41 44	92.21 229	96.92 141	98.60 200	98.58 37	98.78 81	99.39 21	97.80 30	99.62 174	94.98 214	99.86 35	99.52 75

sd_testset		97.97 64	98.12 56	97.51 138	99.41 44	93.44 193	97.96 68	98.25 240	98.58 37	98.78 81	99.39 21	98.21 18	99.56 197	92.65 284	99.86 35	99.52 75

DPE-MVS		97.64 111	97.35 136	98.50 57	98.85 141	96.18 75	95.21 277	98.99 109	95.84 171	98.78 81	98.08 190	96.84 90	99.81 44	93.98 255	99.57 133	99.52 75
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
COLMAP_ROB	94.48 6	98.25 45	98.11 58	98.64 47	99.21 80	97.35 39	97.96 68	99.16 54	98.34 47	98.78 81	98.52 123	97.32 50	99.45 234	94.08 249	99.67 99	99.13 184
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
lessismore_v0				97.05 183	99.36 52	92.12 234		84.07 440		98.77 85	98.98 69	85.36 341	99.74 92	97.34 89	99.37 201	99.30 144

test_fmvs3		97.38 136	97.56 121	96.84 202	98.63 175	92.81 211	97.60 98	99.61 18	90.87 332	98.76 86	99.66 6	94.03 202	97.90 412	99.24 10	99.68 96	99.81 10

MVStest1		91.89 354	91.45 349	93.21 366	89.01 446	84.87 377	95.82 229	95.05 365	91.50 322	98.75 87	99.19 42	57.56 433	95.11 435	97.78 68	98.37 322	99.64 41

v8		97.60 116	98.06 64	96.23 241	98.71 163	89.44 291	97.43 113	98.82 160	97.29 99	98.74 88	99.10 56	93.86 206	99.68 140	98.61 37	99.94 8	99.56 61

DP-MVS		97.87 86	97.89 80	97.81 113	98.62 177	94.82 136	97.13 130	98.79 162	98.98 24	98.74 88	98.49 126	95.80 142	99.49 221	95.04 208	99.44 181	99.11 193

fmvsm_s_conf0.5_n_4		97.43 132	97.77 97	96.39 234	98.48 200	89.89 278	95.65 242	99.26 42	94.73 222	98.72 90	98.58 115	95.58 151	99.57 195	99.28 8	99.67 99	99.73 25

v10		97.55 121	97.97 73	96.31 238	98.60 179	89.64 286	97.44 111	99.02 94	96.60 120	98.72 90	99.16 50	93.48 216	99.72 104	98.76 31	99.92 15	99.58 47

AstraMVS		96.41 199	96.48 196	96.20 244	98.91 133	89.69 283	96.28 185	93.29 387	96.11 146	98.70 92	98.36 143	89.41 300	99.66 155	97.60 77	99.63 107	99.26 156

lecture		98.59 21	98.60 29	98.55 53	99.48 36	96.38 66	98.08 61	99.09 72	98.46 42	98.68 93	98.73 96	97.88 27	99.80 51	97.43 84	99.59 126	99.48 96

fmvsm_s_conf0.5_n_a		97.65 110	97.83 87	97.13 175	98.80 145	92.51 219	96.25 190	99.06 80	93.67 262	98.64 94	99.00 66	96.23 124	99.36 267	98.99 25	99.80 60	99.53 72

test0726					99.24 67	95.51 104	96.89 144	98.89 126	95.92 165	98.64 94	98.31 153	97.06 68

DVP-MVS++		97.96 66	97.90 77	98.12 91	97.75 291	95.40 110	99.03 8	98.89 126	96.62 118	98.62 96	98.30 157	96.97 75	99.75 83	95.70 158	99.25 232	99.21 165

test_241102_TWO								98.83 152	96.11 146	98.62 96	98.24 169	96.92 82	99.72 104	95.44 181	99.49 168	99.49 90

FIs		97.93 76	98.07 61	97.48 146	99.38 50	92.95 208	98.03 65	99.11 64	98.04 62	98.62 96	98.66 105	93.75 210	99.78 59	97.23 90	99.84 47	99.73 25

DeepC-MVS	95.41 4	97.82 93	97.70 101	98.16 86	98.78 152	95.72 93	96.23 192	99.02 94	93.92 254	98.62 96	98.99 68	97.69 34	99.62 174	96.18 135	99.87 33	99.15 177
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		98.14 50	98.03 66	98.47 61	98.72 160	96.04 82	98.07 62	99.10 67	95.96 160	98.59 100	98.69 103	96.94 77	99.81 44	96.64 113	99.58 130	99.57 55
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
guyue		96.21 205	96.29 204	95.98 257	98.80 145	89.14 299	96.40 174	94.34 375	95.99 159	98.58 101	98.13 183	87.42 323	99.64 164	97.39 86	99.55 142	99.16 176

XXY-MVS		97.54 122	97.70 101	97.07 182	99.46 38	92.21 229	97.22 124	99.00 105	94.93 217	98.58 101	98.92 78	97.31 51	99.41 250	94.44 233	99.43 190	99.59 46

test_0402		97.84 89	97.97 73	97.47 147	99.19 84	94.07 166	96.71 162	98.73 174	98.66 32	98.56 103	98.41 137	96.84 90	99.69 134	94.82 218	99.81 56	98.64 264

PM-MVS		97.36 140	97.10 151	98.14 89	98.91 133	96.77 53	96.20 193	98.63 198	93.82 255	98.54 104	98.33 148	93.98 203	99.05 330	95.99 145	99.45 180	98.61 269

DeepPCF-MVS	94.58 5	96.90 164	96.43 198	98.31 73	97.48 321	97.23 44	92.56 374	98.60 200	92.84 296	98.54 104	97.40 254	96.64 99	98.78 357	94.40 237	99.41 197	98.93 223

MSP-MVS		97.45 128	96.92 165	99.03 9	99.26 63	97.70 22	97.66 94	98.89 126	95.65 179	98.51 106	96.46 321	92.15 253	99.81 44	95.14 202	98.58 309	99.58 47
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
VDD-MVS		97.37 138	97.25 142	97.74 118	98.69 167	94.50 150	97.04 135	95.61 352	98.59 36	98.51 106	98.72 97	92.54 244	99.58 189	96.02 142	99.49 168	99.12 189

FMVSNet2		96.72 180	96.67 178	96.87 199	97.96 259	91.88 243	97.15 127	98.06 270	95.59 183	98.50 108	98.62 111	89.51 297	99.65 158	94.99 213	99.60 123	99.07 200

test_fmvs2		96.38 200	96.45 197	96.16 249	97.85 266	91.30 255	96.81 149	99.45 28	89.24 354	98.49 109	99.38 23	88.68 305	97.62 417	98.83 28	99.32 219	99.57 55

test1111		94.53 290	94.81 267	93.72 352	99.06 107	81.94 405	98.31 42	83.87 441	96.37 133	98.49 109	99.17 49	81.49 365	99.73 98	96.64 113	99.86 35	99.49 90

SMA-MVS		97.48 126	97.11 150	98.60 49	98.83 142	96.67 57	96.74 157	98.73 174	91.61 319	98.48 111	98.36 143	96.53 104	99.68 140	95.17 197	99.54 147	99.45 106
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
EU-MVSNet		94.25 297	94.47 286	93.60 355	98.14 243	82.60 400	97.24 123	92.72 394	85.08 402	98.48 111	98.94 75	82.59 363	98.76 360	97.47 83	99.53 151	99.44 116

RPSCF		97.87 86	97.51 126	98.95 18	99.15 90	98.43 7	97.56 102	99.06 80	96.19 143	98.48 111	98.70 102	94.72 178	99.24 301	94.37 238	99.33 217	99.17 173

v1240		96.74 177	97.02 158	95.91 263	98.18 234	88.52 312	95.39 261	98.88 133	93.15 285	98.46 114	98.40 140	92.80 233	99.71 118	98.45 42	99.49 168	99.49 90

VPNet		97.26 144	97.49 130	96.59 216	99.47 37	90.58 269	96.27 186	98.53 207	97.77 67	98.46 114	98.41 137	94.59 184	99.68 140	94.61 228	99.29 225	99.52 75

IterMVS-LS		96.92 162	97.29 139	95.79 267	98.51 194	88.13 323	95.10 281	98.66 192	96.99 105	98.46 114	98.68 104	92.55 242	99.74 92	96.91 107	99.79 62	99.50 82
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_7		97.13 149	97.50 128	96.04 253	98.43 206	89.03 303	94.92 292	99.00 105	94.51 234	98.42 117	98.96 72	94.97 174	99.54 204	98.42 43	99.85 44	99.56 61

test_f		95.82 224	95.88 226	95.66 274	97.61 311	93.21 203	95.61 248	98.17 253	86.98 383	98.42 117	99.47 16	90.46 280	94.74 438	97.71 72	98.45 318	99.03 205

ambc				96.56 220	98.23 227	91.68 249	97.88 76	98.13 261		98.42 117	98.56 119	94.22 198	99.04 332	94.05 252	99.35 209	98.95 217

DVP-MVS		97.78 98	97.65 108	98.16 86	99.24 67	95.51 104	96.74 157	98.23 243	95.92 165	98.40 120	98.28 162	97.06 68	99.71 118	95.48 177	99.52 156	99.26 156
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									96.62 118	98.40 120	98.28 162	97.10 63	99.71 118	95.70 158	99.62 110	99.58 47

VDDNet		96.98 159	96.84 168	97.41 154	99.40 47	93.26 201	97.94 71	95.31 360	99.26 12	98.39 122	99.18 46	87.85 318	99.62 174	95.13 204	99.09 254	99.35 137

PC_three_1452									87.24 379	98.37 123	97.44 251	97.00 73	96.78 428	92.01 293	99.25 232	99.21 165

Anonymous202405211		96.34 201	95.98 219	97.43 151	98.25 224	93.85 175	96.74 157	94.41 373	97.72 72	98.37 123	98.03 200	87.15 325	99.53 207	94.06 250	99.07 257	98.92 226

Baseline_NR-MVSNet		97.72 103	97.79 92	97.50 142	99.56 22	93.29 199	95.44 255	98.86 138	98.20 56	98.37 123	99.24 36	94.69 179	99.55 201	95.98 146	99.79 62	99.65 38

mvs5depth		98.06 59	98.58 30	96.51 222	98.97 122	89.65 285	99.43 4	99.81 2	99.30 10	98.36 126	99.86 2	93.15 223	99.88 23	98.50 41	99.84 47	99.99 1

IU-MVS					99.22 73	95.40 110		98.14 260	85.77 396	98.36 126				95.23 194	99.51 161	99.49 90

IterMVS-SCA-FT		95.86 222	96.19 209	94.85 313	97.68 299	85.53 364	92.42 380	97.63 297	96.99 105	98.36 126	98.54 122	87.94 313	99.75 83	97.07 102	99.08 255	99.27 155

ACMM	93.33 11	98.05 60	97.79 92	98.85 28	99.15 90	97.55 30	96.68 164	98.83 152	95.21 201	98.36 126	98.13 183	98.13 22	99.62 174	96.04 140	99.54 147	99.39 126
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		97.07 152	97.51 126	95.76 269	99.35 53	88.18 320	97.78 82	98.40 223	97.11 103	98.34 130	99.04 62	89.58 293	99.79 54	98.09 51	99.93 11	99.30 144

LPG-MVS_test		97.94 73	97.67 106	98.74 38	99.15 90	97.02 46	97.09 132	99.02 94	95.15 205	98.34 130	98.23 171	97.91 25	99.70 127	94.41 235	99.73 79	99.50 82

LGP-MVS_train				98.74 38	99.15 90	97.02 46		99.02 94	95.15 205	98.34 130	98.23 171	97.91 25	99.70 127	94.41 235	99.73 79	99.50 82

casdiffmvs		97.50 124	97.81 90	96.56 220	98.51 194	91.04 260	95.83 227	99.09 72	97.23 100	98.33 133	98.30 157	97.03 71	99.37 264	96.58 117	99.38 200	99.28 151
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Patchmatch-RL test		94.66 283	94.49 284	95.19 294	98.54 190	88.91 305	92.57 373	98.74 173	91.46 324	98.32 134	97.75 229	77.31 388	98.81 355	96.06 137	99.61 116	97.85 345

XVG-OURS		97.12 150	96.74 174	98.26 76	98.99 118	97.45 36	93.82 339	99.05 84	95.19 203	98.32 134	97.70 234	95.22 163	98.41 393	94.27 242	98.13 332	98.93 223

UniMVSNet_NR-MVSNet		97.83 90	97.65 108	98.37 68	98.72 160	95.78 91	95.66 240	99.02 94	98.11 58	98.31 136	97.69 235	94.65 183	99.85 31	97.02 104	99.71 87	99.48 96

DU-MVS		97.79 97	97.60 117	98.36 69	98.73 157	95.78 91	95.65 242	98.87 135	97.57 79	98.31 136	97.83 219	94.69 179	99.85 31	97.02 104	99.71 87	99.46 102

EI-MVSNet-UG-set		97.32 142	97.40 132	97.09 180	97.34 334	92.01 240	95.33 268	97.65 293	97.74 70	98.30 138	98.14 181	95.04 169	99.69 134	97.55 79	99.52 156	99.58 47

EI-MVSNet-Vis-set		97.32 142	97.39 133	97.11 176	97.36 331	92.08 238	95.34 267	97.65 293	97.74 70	98.29 139	98.11 188	95.05 168	99.68 140	97.50 81	99.50 165	99.56 61

test20.03		96.58 189	96.61 181	96.48 225	98.49 198	91.72 247	95.68 238	97.69 288	96.81 112	98.27 140	97.92 213	94.18 199	98.71 365	90.78 323	99.66 102	99.00 209

APD-MVS_3200maxsize		98.13 53	97.90 77	98.79 33	98.79 148	97.31 40	97.55 103	98.92 121	97.72 72	98.25 141	98.13 183	97.10 63	99.75 83	95.44 181	99.24 235	99.32 139

v148		96.58 189	96.97 160	95.42 287	98.63 175	87.57 336	95.09 282	97.90 275	95.91 167	98.24 142	97.96 207	93.42 217	99.39 256	96.04 140	99.52 156	99.29 150

ECVR-MVS		94.37 296	94.48 285	94.05 347	98.95 123	83.10 395	98.31 42	82.48 443	96.20 141	98.23 143	99.16 50	81.18 368	99.66 155	95.95 147	99.83 51	99.38 128

UniMVSNet (Re)		97.83 90	97.65 108	98.35 70	98.80 145	95.86 90	95.92 222	99.04 91	97.51 83	98.22 144	97.81 224	94.68 181	99.78 59	97.14 97	99.75 77	99.41 120

test_vis1_n		95.67 232	95.89 225	95.03 302	98.18 234	89.89 278	96.94 140	99.28 40	88.25 370	98.20 145	98.92 78	86.69 330	97.19 420	97.70 74	98.82 284	98.00 335

SR-MVS-dyc-post		98.14 50	97.84 84	99.02 10	98.81 143	98.05 10	97.55 103	98.86 138	97.77 67	98.20 145	98.07 192	96.60 102	99.76 76	95.49 173	99.20 237	99.26 156

RE-MVS-def			97.88 82		98.81 143	98.05 10	97.55 103	98.86 138	97.77 67	98.20 145	98.07 192	96.94 77		95.49 173	99.20 237	99.26 156

WR-MVS		96.90 164	96.81 170	97.16 172	98.56 187	92.20 232	94.33 312	98.12 262	97.34 96	98.20 145	97.33 265	92.81 232	99.75 83	94.79 220	99.81 56	99.54 67

v1921920		96.72 180	96.96 162	95.99 255	98.21 228	88.79 309	95.42 257	98.79 162	93.22 277	98.19 149	98.26 167	92.68 236	99.70 127	98.34 46	99.55 142	99.49 90

test_cas_vis1_n_1920		95.34 249	95.67 233	94.35 337	98.21 228	86.83 351	95.61 248	99.26 42	90.45 339	98.17 150	98.96 72	84.43 349	98.31 401	96.74 112	99.17 242	97.90 341

TSAR-MVS + MP.		97.42 134	97.23 144	98.00 102	99.38 50	95.00 132	97.63 97	98.20 247	93.00 289	98.16 151	98.06 197	95.89 132	99.72 104	95.67 162	99.10 253	99.28 151
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TinyColmap		96.00 217	96.34 202	94.96 307	97.90 264	87.91 328	94.13 326	98.49 211	94.41 237	98.16 151	97.76 226	96.29 122	98.68 371	90.52 335	99.42 193	98.30 302

XVG-OURS-SEG-HR		97.38 136	97.07 154	98.30 74	99.01 117	97.41 38	94.66 304	99.02 94	95.20 202	98.15 153	97.52 246	98.83 5	98.43 392	94.87 216	96.41 395	99.07 200

IS-MVSNet		96.93 161	96.68 177	97.70 122	99.25 66	94.00 170	98.57 23	96.74 329	98.36 46	98.14 154	97.98 206	88.23 311	99.71 118	93.10 280	99.72 84	99.38 128

CSCG		97.40 135	97.30 138	97.69 124	98.95 123	94.83 135	97.28 120	98.99 109	96.35 136	98.13 155	95.95 347	95.99 129	99.66 155	94.36 240	99.73 79	98.59 270

MP-MVS-pluss		97.69 105	97.36 135	98.70 42	99.50 34	96.84 51	95.38 262	98.99 109	92.45 304	98.11 156	98.31 153	97.25 58	99.77 70	96.60 115	99.62 110	99.48 96
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
v1192		96.83 171	97.06 155	96.15 250	98.28 219	89.29 294	95.36 263	98.77 167	93.73 257	98.11 156	98.34 147	93.02 230	99.67 149	98.35 45	99.58 130	99.50 82

OPM-MVS		97.54 122	97.25 142	98.41 65	99.11 99	96.61 60	95.24 275	98.46 213	94.58 231	98.10 158	98.07 192	97.09 65	99.39 256	95.16 199	99.44 181	99.21 165
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		96.69 183	96.90 167	96.03 254	98.25 224	88.92 304	95.49 253	98.77 167	93.05 287	98.09 159	98.29 161	92.51 247	99.70 127	98.11 49	99.56 136	99.47 100

N_pmnet		95.18 257	94.23 294	98.06 95	97.85 266	96.55 62	92.49 375	91.63 406	89.34 352	98.09 159	97.41 253	90.33 283	99.06 329	91.58 304	99.31 222	98.56 272

test_part2					99.03 115	96.07 81				98.08 161

SteuartSystems-ACMMP		98.02 62	97.76 98	98.79 33	99.43 41	97.21 45	97.15 127	98.90 123	96.58 122	98.08 161	97.87 217	97.02 72	99.76 76	95.25 192	99.59 126	99.40 121
Skip Steuart: Steuart Systems R&D Blog.
APD_test1		97.95 70	97.68 105	98.75 35	99.60 17	98.60 6	97.21 125	99.08 76	96.57 125	98.07 163	98.38 141	96.22 125	99.14 315	94.71 227	99.31 222	98.52 277

SR-MVS		98.00 63	97.66 107	99.01 12	98.77 154	97.93 15	97.38 115	98.83 152	97.32 97	98.06 164	97.85 218	96.65 97	99.77 70	95.00 211	99.11 251	99.32 139

XVG-ACMP-BASELINE		97.58 120	97.28 141	98.49 58	99.16 87	96.90 50	96.39 175	98.98 112	95.05 211	98.06 164	98.02 201	95.86 133	99.56 197	94.37 238	99.64 105	99.00 209

IterMVS		95.42 245	95.83 228	94.20 343	97.52 318	83.78 392	92.41 381	97.47 302	95.49 190	98.06 164	98.49 126	87.94 313	99.58 189	96.02 142	99.02 262	99.23 163
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TSAR-MVS + GP.		96.47 194	96.12 211	97.49 145	97.74 294	95.23 122	94.15 323	96.90 322	93.26 275	98.04 167	96.70 308	94.41 191	98.89 348	94.77 223	99.14 245	98.37 291

test_one_0601					99.05 113	95.50 107		98.87 135	97.21 102	98.03 168	98.30 157	96.93 79

testgi		96.07 211	96.50 195	94.80 316	99.26 63	87.69 335	95.96 218	98.58 204	95.08 208	98.02 169	96.25 332	97.92 24	97.60 418	88.68 365	98.74 291	99.11 193

V42		97.04 153	97.16 149	96.68 213	98.59 181	91.05 259	96.33 182	98.36 229	94.60 228	97.99 170	98.30 157	93.32 218	99.62 174	97.40 85	99.53 151	99.38 128

GBi-Net		96.99 156	96.80 171	97.56 133	97.96 259	93.67 182	98.23 49	98.66 192	95.59 183	97.99 170	99.19 42	89.51 297	99.73 98	94.60 229	99.44 181	99.30 144

test1		96.99 156	96.80 171	97.56 133	97.96 259	93.67 182	98.23 49	98.66 192	95.59 183	97.99 170	99.19 42	89.51 297	99.73 98	94.60 229	99.44 181	99.30 144

FMVSNet3		95.26 254	94.94 254	96.22 243	96.53 361	90.06 274	95.99 214	97.66 291	94.11 248	97.99 170	97.91 214	80.22 374	99.63 169	94.60 229	99.44 181	98.96 215

pmmvs-eth3d		96.49 192	96.18 210	97.42 153	98.25 224	94.29 158	94.77 300	98.07 269	89.81 348	97.97 174	98.33 148	93.11 224	99.08 327	95.46 180	99.84 47	98.89 231

v1144		96.84 168	97.08 153	96.13 251	98.42 208	89.28 295	95.41 259	98.67 189	94.21 242	97.97 174	98.31 153	93.06 225	99.65 158	98.06 54	99.62 110	99.45 106

ACMP	92.54 13	97.47 127	97.10 151	98.55 53	99.04 114	96.70 55	96.24 191	98.89 126	93.71 258	97.97 174	97.75 229	97.44 45	99.63 169	93.22 277	99.70 91	99.32 139
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
reproduce_monomvs		92.05 351	92.26 338	91.43 401	95.42 404	75.72 437	95.68 238	97.05 317	94.47 235	97.95 177	98.35 145	55.58 442	99.05 330	96.36 125	99.44 181	99.51 79

EI-MVSNet		96.63 186	96.93 163	95.74 270	97.26 339	88.13 323	95.29 273	97.65 293	96.99 105	97.94 178	98.19 176	92.55 242	99.58 189	96.91 107	99.56 136	99.50 82

MVSTER		94.21 300	93.93 307	95.05 301	95.83 389	86.46 354	95.18 278	97.65 293	92.41 305	97.94 178	98.00 205	72.39 412	99.58 189	96.36 125	99.56 136	99.12 189

ACMMP		98.05 60	97.75 100	98.93 22	99.23 70	97.60 26	98.09 60	98.96 116	95.75 176	97.91 180	98.06 197	96.89 84	99.76 76	95.32 189	99.57 133	99.43 117
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
MTAPA		98.14 50	97.84 84	99.06 7	99.44 40	97.90 16	97.25 121	98.73 174	97.69 75	97.90 181	97.96 207	95.81 141	99.82 39	96.13 136	99.61 116	99.45 106

LFMVS		95.32 251	94.88 261	96.62 214	98.03 250	91.47 252	97.65 95	90.72 418	99.11 15	97.89 182	98.31 153	79.20 376	99.48 224	93.91 258	99.12 250	98.93 223

ACMMP_NAP		97.89 83	97.63 113	98.67 44	99.35 53	96.84 51	96.36 180	98.79 162	95.07 209	97.88 183	98.35 145	97.24 59	99.72 104	96.05 139	99.58 130	99.45 106

VNet		96.84 168	96.83 169	96.88 198	98.06 249	92.02 239	96.35 181	97.57 299	97.70 74	97.88 183	97.80 225	92.40 249	99.54 204	94.73 225	98.96 266	99.08 198

HPM-MVS_fast		98.32 39	98.13 55	98.88 27	99.54 28	97.48 34	98.35 38	99.03 92	95.88 168	97.88 183	98.22 174	98.15 20	99.74 92	96.50 119	99.62 110	99.42 118

UA-Net		98.88 11	98.76 17	99.22 3	99.11 99	97.89 17	99.47 3	99.32 36	99.08 17	97.87 186	99.67 5	96.47 109	99.92 6	97.88 61	99.98 2	99.85 6

baseline		97.44 130	97.78 96	96.43 228	98.52 192	90.75 267	96.84 146	99.03 92	96.51 126	97.86 187	98.02 201	96.67 96	99.36 267	97.09 99	99.47 174	99.19 169

v2v482		96.78 175	97.06 155	95.95 260	98.57 185	88.77 310	95.36 263	98.26 239	95.18 204	97.85 188	98.23 171	92.58 240	99.63 169	97.80 66	99.69 92	99.45 106

SF-MVS		97.60 116	97.39 133	98.22 81	98.93 129	95.69 95	97.05 134	99.10 67	95.32 198	97.83 189	97.88 215	96.44 112	99.72 104	94.59 232	99.39 199	99.25 161

Vis-MVSNet		98.27 43	98.34 45	98.07 93	99.33 55	95.21 127	98.04 63	99.46 27	97.32 97	97.82 190	99.11 55	96.75 94	99.86 28	97.84 64	99.36 204	99.15 177
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
AllTest		97.20 147	96.92 165	98.06 95	99.08 103	96.16 76	97.14 129	99.16 54	94.35 239	97.78 191	98.07 192	95.84 134	99.12 319	91.41 305	99.42 193	98.91 227

TestCases				98.06 95	99.08 103	96.16 76		99.16 54	94.35 239	97.78 191	98.07 192	95.84 134	99.12 319	91.41 305	99.42 193	98.91 227

balanced_conf03		96.88 166	97.29 139	95.63 275	97.66 304	89.47 290	97.95 70	98.89 126	95.94 163	97.77 193	98.55 120	92.23 251	99.68 140	97.05 103	99.61 116	97.73 355

test_vis1_n_1920		95.77 226	96.41 199	93.85 348	98.55 188	84.86 378	95.91 223	99.71 7	92.72 299	97.67 194	98.90 82	87.44 322	98.73 362	97.96 58	98.85 280	97.96 337

GeoE		97.75 100	97.70 101	97.89 108	98.88 137	94.53 147	97.10 131	98.98 112	95.75 176	97.62 195	97.59 241	97.61 42	99.77 70	96.34 127	99.44 181	99.36 135

MDA-MVSNet-bldmvs		95.69 230	95.67 233	95.74 270	98.48 200	88.76 311	92.84 364	97.25 306	96.00 157	97.59 196	97.95 209	91.38 267	99.46 229	93.16 279	96.35 397	98.99 212

PGM-MVS		97.88 84	97.52 125	98.96 17	99.20 82	97.62 25	97.09 132	99.06 80	95.45 191	97.55 197	97.94 210	97.11 62	99.78 59	94.77 223	99.46 177	99.48 96

GST-MVS		97.82 93	97.49 130	98.81 31	99.23 70	97.25 42	97.16 126	98.79 162	95.96 160	97.53 198	97.40 254	96.93 79	99.77 70	95.04 208	99.35 209	99.42 118

YYNet1		94.73 275	94.84 264	94.41 335	97.47 325	85.09 374	90.29 419	95.85 346	92.52 301	97.53 198	97.76 226	91.97 259	99.18 308	93.31 274	96.86 380	98.95 217

TAMVS		95.49 239	94.94 254	97.16 172	98.31 215	93.41 196	95.07 285	96.82 325	91.09 330	97.51 200	97.82 222	89.96 289	99.42 241	88.42 368	99.44 181	98.64 264

LS3D		97.77 99	97.50 128	98.57 51	96.24 368	97.58 28	98.45 34	98.85 142	98.58 37	97.51 200	97.94 210	95.74 144	99.63 169	95.19 195	98.97 265	98.51 278

HFP-MVS		97.94 73	97.64 111	98.83 29	99.15 90	97.50 33	97.59 100	98.84 146	96.05 152	97.49 202	97.54 244	97.07 67	99.70 127	95.61 168	99.46 177	99.30 144

Patchmtry		95.03 265	94.59 280	96.33 236	94.83 415	90.82 264	96.38 178	97.20 308	96.59 121	97.49 202	98.57 117	77.67 383	99.38 259	92.95 283	99.62 110	98.80 244

MDA-MVSNet_test_wron		94.73 275	94.83 266	94.42 334	97.48 321	85.15 372	90.28 420	95.87 345	92.52 301	97.48 204	97.76 226	91.92 262	99.17 312	93.32 273	96.80 385	98.94 219

UnsupCasMVSNet_eth		95.91 220	95.73 232	96.44 226	98.48 200	91.52 251	95.31 271	98.45 214	95.76 174	97.48 204	97.54 244	89.53 296	98.69 368	94.43 234	94.61 420	99.13 184

tttt0517		93.31 327	92.56 335	95.57 278	98.71 163	87.86 329	97.44 111	87.17 435	95.79 173	97.47 206	96.84 298	64.12 426	99.81 44	96.20 134	99.32 219	99.02 208

ACMMPR		97.95 70	97.62 115	98.94 19	99.20 82	97.56 29	97.59 100	98.83 152	96.05 152	97.46 207	97.63 238	96.77 93	99.76 76	95.61 168	99.46 177	99.49 90

APD-MVS		97.00 155	96.53 192	98.41 65	98.55 188	96.31 71	96.32 183	98.77 167	92.96 294	97.44 208	97.58 243	95.84 134	99.74 92	91.96 294	99.35 209	99.19 169
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS		98.11 54	97.83 87	98.92 25	99.42 43	97.46 35	98.57 23	99.05 84	95.43 194	97.41 209	97.50 248	97.98 23	99.79 54	95.58 171	99.57 133	99.50 82
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
c3_l		95.20 256	95.32 240	94.83 315	96.19 372	86.43 356	91.83 393	98.35 232	93.47 268	97.36 210	97.26 269	88.69 304	99.28 291	95.41 187	99.36 204	98.78 247

EPP-MVSNet		96.84 168	96.58 183	97.65 128	99.18 85	93.78 179	98.68 17	96.34 334	97.91 64	97.30 211	98.06 197	88.46 307	99.85 31	93.85 259	99.40 198	99.32 139

DeepC-MVS_fast	94.34 7	96.74 177	96.51 194	97.44 150	97.69 298	94.15 164	96.02 210	98.43 217	93.17 284	97.30 211	97.38 260	95.48 153	99.28 291	93.74 262	99.34 212	98.88 235
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RRT-MVS		95.78 225	96.25 206	94.35 337	96.68 357	84.47 383	97.72 90	99.11 64	97.23 100	97.27 213	98.72 97	86.39 331	99.79 54	95.49 173	97.67 356	98.80 244

mvsany_test1		93.47 323	93.03 320	94.79 317	94.05 428	92.12 234	90.82 414	90.01 427	85.02 405	97.26 214	98.28 162	93.57 214	97.03 422	92.51 288	95.75 410	95.23 422

region2R		97.92 77	97.59 118	98.92 25	99.22 73	97.55 30	97.60 98	98.84 146	96.00 157	97.22 215	97.62 239	96.87 88	99.76 76	95.48 177	99.43 190	99.46 102

ITE_SJBPF				97.85 111	98.64 171	96.66 58		98.51 210	95.63 180	97.22 215	97.30 267	95.52 152	98.55 383	90.97 316	98.90 273	98.34 297

test_fmvs1_n		95.21 255	95.28 241	94.99 305	98.15 241	89.13 300	96.81 149	99.43 30	86.97 384	97.21 217	98.92 78	83.00 360	97.13 421	98.09 51	98.94 269	98.72 256

h-mvs33		96.29 202	95.63 236	98.26 76	98.50 197	96.11 79	96.90 143	97.09 314	96.58 122	97.21 217	98.19 176	84.14 350	99.78 59	95.89 151	96.17 402	98.89 231

hse-mvs2		95.77 226	95.09 249	97.79 114	97.84 271	95.51 104	95.66 240	95.43 357	96.58 122	97.21 217	96.16 335	84.14 350	99.54 204	95.89 151	96.92 377	98.32 298

9.14			96.69 176		98.53 191		96.02 210	98.98 112	93.23 276	97.18 220	97.46 249	96.47 109	99.62 174	92.99 281	99.32 219

OMC-MVS		96.48 193	96.00 217	97.91 107	98.30 216	96.01 85	94.86 296	98.60 200	91.88 314	97.18 220	97.21 272	96.11 127	99.04 332	90.49 338	99.34 212	98.69 260

our_test_3		94.20 302	94.58 281	93.07 369	96.16 374	81.20 411	90.42 418	96.84 323	90.72 334	97.14 222	97.13 276	90.47 279	99.11 322	94.04 253	98.25 327	98.91 227

MS-PatchMatch		94.83 272	94.91 258	94.57 327	96.81 355	87.10 346	94.23 318	97.34 305	88.74 362	97.14 222	97.11 279	91.94 261	98.23 405	92.99 281	97.92 340	98.37 291

eth_miper_zixun_eth		94.89 270	94.93 256	94.75 319	95.99 381	86.12 359	91.35 402	98.49 211	93.40 269	97.12 224	97.25 270	86.87 329	99.35 271	95.08 207	98.82 284	98.78 247

3Dnovator	96.53 2	97.61 115	97.64 111	97.50 142	97.74 294	93.65 186	98.49 31	98.88 133	96.86 111	97.11 225	98.55 120	95.82 137	99.73 98	95.94 148	99.42 193	99.13 184

cl____		94.73 275	94.64 274	95.01 303	95.85 388	87.00 347	91.33 403	98.08 265	93.34 272	97.10 226	97.33 265	84.01 354	99.30 285	95.14 202	99.56 136	98.71 259

DIV-MVS_self_test		94.73 275	94.64 274	95.01 303	95.86 387	87.00 347	91.33 403	98.08 265	93.34 272	97.10 226	97.34 264	84.02 353	99.31 282	95.15 201	99.55 142	98.72 256

PMMVS2		93.66 318	94.07 301	92.45 389	97.57 314	80.67 415	86.46 434	96.00 340	93.99 252	97.10 226	97.38 260	89.90 290	97.82 414	88.76 362	99.47 174	98.86 238

mPP-MVS		97.91 80	97.53 124	99.04 8	99.22 73	97.87 18	97.74 88	98.78 166	96.04 154	97.10 226	97.73 232	96.53 104	99.78 59	95.16 199	99.50 165	99.46 102

BH-untuned		94.69 280	94.75 270	94.52 329	97.95 262	87.53 337	94.07 328	97.01 318	93.99 252	97.10 226	95.65 354	92.65 238	98.95 345	87.60 378	96.74 386	97.09 380

tt0805		97.44 130	97.56 121	97.11 176	99.55 24	96.36 68	98.66 21	95.66 348	98.31 48	97.09 231	95.45 361	97.17 61	98.50 387	98.67 36	97.45 368	96.48 404

test2506		89.86 379	89.16 384	91.97 396	98.95 123	76.83 433	98.54 26	61.07 451	96.20 141	97.07 232	99.16 50	55.19 445	99.69 134	96.43 122	99.83 51	99.38 128

miper_ehance_all_eth		94.69 280	94.70 271	94.64 321	95.77 394	86.22 358	91.32 405	98.24 242	91.67 316	97.05 233	96.65 311	88.39 309	99.22 305	94.88 215	98.34 323	98.49 282

miper_lstm_enhance		94.81 274	94.80 268	94.85 313	96.16 374	86.45 355	91.14 409	98.20 247	93.49 267	97.03 234	97.37 262	84.97 345	99.26 295	95.28 190	99.56 136	98.83 240

UnsupCasMVSNet_bld		94.72 279	94.26 293	96.08 252	98.62 177	90.54 272	93.38 354	98.05 271	90.30 341	97.02 235	96.80 303	89.54 294	99.16 313	88.44 367	96.18 401	98.56 272

ppachtmachnet_test		94.49 292	94.84 264	93.46 358	96.16 374	82.10 402	90.59 416	97.48 301	90.53 338	97.01 236	97.59 241	91.01 272	99.36 267	93.97 256	99.18 241	98.94 219

SSC-MVS3.2		95.75 228	96.56 186	93.34 359	98.69 167	80.75 414	91.60 396	97.43 304	97.37 95	96.99 237	97.02 285	93.69 212	99.71 118	96.32 128	99.89 26	99.55 65

D2MVS		95.18 257	95.17 246	95.21 293	97.76 289	87.76 334	94.15 323	97.94 273	89.77 349	96.99 237	97.68 236	87.45 321	99.14 315	95.03 210	99.81 56	98.74 253

ab-mvs		96.59 187	96.59 182	96.60 215	98.64 171	92.21 229	98.35 38	97.67 289	94.45 236	96.99 237	98.79 88	94.96 175	99.49 221	90.39 339	99.07 257	98.08 321

Anonymous20231206		95.27 253	95.06 252	95.88 264	98.72 160	89.37 293	95.70 235	97.85 278	88.00 373	96.98 240	97.62 239	91.95 260	99.34 274	89.21 356	99.53 151	98.94 219

PVSNet_Blended_VisFu		95.95 218	95.80 229	96.42 229	99.28 59	90.62 268	95.31 271	99.08 76	88.40 367	96.97 241	98.17 180	92.11 255	99.78 59	93.64 266	99.21 236	98.86 238

mvs_anonymous		95.36 247	96.07 215	93.21 366	96.29 367	81.56 407	94.60 306	97.66 291	93.30 274	96.95 242	98.91 81	93.03 229	99.38 259	96.60 115	97.30 373	98.69 260

ZNCC-MVS		97.92 77	97.62 115	98.83 29	99.32 57	97.24 43	97.45 110	98.84 146	95.76 174	96.93 243	97.43 252	97.26 57	99.79 54	96.06 137	99.53 151	99.45 106

3Dnovator+	96.13 3	97.73 101	97.59 118	98.15 88	98.11 247	95.60 99	98.04 63	98.70 183	98.13 57	96.93 243	98.45 131	95.30 161	99.62 174	95.64 165	98.96 266	99.24 162

USDC		94.56 288	94.57 283	94.55 328	97.78 287	86.43 356	92.75 367	98.65 197	85.96 392	96.91 245	97.93 212	90.82 275	98.74 361	90.71 329	99.59 126	98.47 283

CP-MVS		97.92 77	97.56 121	98.99 14	98.99 118	97.82 19	97.93 72	98.96 116	96.11 146	96.89 246	97.45 250	96.85 89	99.78 59	95.19 195	99.63 107	99.38 128

OpenMVS_ROB	91.80 14	93.64 319	93.05 319	95.42 287	97.31 338	91.21 258	95.08 284	96.68 332	81.56 420	96.88 247	96.41 324	90.44 282	99.25 297	85.39 400	97.67 356	95.80 414

SymmetryMVS		96.43 197	95.85 227	98.17 85	98.58 183	95.57 100	96.87 145	95.29 361	96.94 108	96.85 248	97.88 215	85.36 341	99.76 76	95.63 166	99.27 228	99.19 169

MVSMamba_PlusPlus		97.43 132	97.98 72	95.78 268	98.88 137	89.70 282	98.03 65	98.85 142	99.18 14	96.84 249	99.12 54	93.04 226	99.91 14	98.38 44	99.55 142	97.73 355

test_fmvs1		94.51 291	94.60 278	94.26 342	95.91 383	87.92 327	95.35 266	99.02 94	86.56 388	96.79 250	98.52 123	82.64 362	97.00 424	97.87 62	98.71 295	97.88 343

test_yl		94.40 293	94.00 303	95.59 276	96.95 350	89.52 288	94.75 301	95.55 354	96.18 144	96.79 250	96.14 338	81.09 369	99.18 308	90.75 325	97.77 346	98.07 323

DCV-MVSNet		94.40 293	94.00 303	95.59 276	96.95 350	89.52 288	94.75 301	95.55 354	96.18 144	96.79 250	96.14 338	81.09 369	99.18 308	90.75 325	97.77 346	98.07 323

Gipuma		98.07 58	98.31 47	97.36 157	99.76 7	96.28 73	98.51 30	99.10 67	98.76 30	96.79 250	99.34 29	96.61 100	98.82 353	96.38 124	99.50 165	96.98 383
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
alignmvs		96.01 216	95.52 239	97.50 142	97.77 288	94.71 138	96.07 204	96.84 323	97.48 85	96.78 254	94.28 383	85.50 340	99.40 252	96.22 133	98.73 294	98.40 287

MM		96.87 167	96.62 179	97.62 130	97.72 296	93.30 198	96.39 175	92.61 397	97.90 65	96.76 255	98.64 110	90.46 280	99.81 44	99.16 16	99.94 8	99.76 20

CL-MVSNet_self_test		95.04 263	94.79 269	95.82 266	97.51 319	89.79 281	91.14 409	96.82 325	93.05 287	96.72 256	96.40 326	90.82 275	99.16 313	91.95 295	98.66 301	98.50 281

MSLP-MVS++		96.42 198	96.71 175	95.57 278	97.82 274	90.56 271	95.71 234	98.84 146	94.72 223	96.71 257	97.39 258	94.91 176	98.10 409	95.28 190	99.02 262	98.05 330

sasdasda		97.23 145	97.21 146	97.30 161	97.65 306	94.39 152	97.84 78	99.05 84	97.42 87	96.68 258	93.85 388	97.63 40	99.33 276	96.29 129	98.47 316	98.18 315

FA-MVS(test-final)		94.91 268	94.89 259	94.99 305	97.51 319	88.11 325	98.27 47	95.20 363	92.40 306	96.68 258	98.60 114	83.44 356	99.28 291	93.34 272	98.53 310	97.59 365

canonicalmvs		97.23 145	97.21 146	97.30 161	97.65 306	94.39 152	97.84 78	99.05 84	97.42 87	96.68 258	93.85 388	97.63 40	99.33 276	96.29 129	98.47 316	98.18 315

ZD-MVS					98.43 206	95.94 86		98.56 206	90.72 334	96.66 261	97.07 281	95.02 171	99.74 92	91.08 312	98.93 271

diffmvs		96.04 213	96.23 207	95.46 286	97.35 332	88.03 326	93.42 352	99.08 76	94.09 250	96.66 261	96.93 292	93.85 207	99.29 289	96.01 144	98.67 299	99.06 202
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
patch_mono-2		96.59 187	96.93 163	95.55 281	98.88 137	87.12 345	94.47 309	99.30 38	94.12 247	96.65 263	98.41 137	94.98 173	99.87 26	95.81 157	99.78 66	99.66 35

MVP-Stereo		95.69 230	95.28 241	96.92 193	98.15 241	93.03 205	95.64 246	98.20 247	90.39 340	96.63 264	97.73 232	91.63 265	99.10 325	91.84 299	97.31 372	98.63 266
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
mmtdpeth		98.33 37	98.53 32	97.71 120	99.07 105	93.44 193	98.80 15	99.78 4	99.10 16	96.61 265	99.63 10	95.42 157	99.73 98	98.53 40	99.86 35	99.95 2

MGCFI-Net		97.20 147	97.23 144	97.08 181	97.68 299	93.71 181	97.79 81	99.09 72	97.40 92	96.59 266	93.96 386	97.67 36	99.35 271	96.43 122	98.50 315	98.17 317

Vis-MVSNet (Re-imp)		95.11 260	94.85 263	95.87 265	99.12 98	89.17 296	97.54 108	94.92 368	96.50 127	96.58 267	97.27 268	83.64 355	99.48 224	88.42 368	99.67 99	98.97 214

MVS_111021_HR		96.73 179	96.54 191	97.27 164	98.35 213	93.66 185	93.42 352	98.36 229	94.74 220	96.58 267	96.76 306	96.54 103	98.99 338	94.87 216	99.27 228	99.15 177

thisisatest0530		92.71 338	91.76 347	95.56 280	98.42 208	88.23 318	96.03 209	87.35 434	94.04 251	96.56 269	95.47 360	64.03 427	99.77 70	94.78 222	99.11 251	98.68 263

MVS_111021_LR		96.82 172	96.55 189	97.62 130	98.27 221	95.34 117	93.81 341	98.33 233	94.59 230	96.56 269	96.63 312	96.61 100	98.73 362	94.80 219	99.34 212	98.78 247

DELS-MVS		96.17 208	96.23 207	95.99 255	97.55 317	90.04 275	92.38 383	98.52 208	94.13 246	96.55 271	97.06 282	94.99 172	99.58 189	95.62 167	99.28 226	98.37 291
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
GDP-MVS		95.39 246	94.89 259	96.90 196	98.26 223	91.91 242	96.48 172	99.28 40	95.06 210	96.54 272	97.12 278	74.83 400	99.82 39	97.19 95	99.27 228	98.96 215

baseline1		93.14 332	92.64 333	94.62 323	97.34 334	87.20 344	96.67 166	93.02 389	94.71 224	96.51 273	95.83 350	81.64 364	98.60 379	90.00 345	88.06 438	98.07 323

Patchmatch-test		93.60 320	93.25 317	94.63 322	96.14 378	87.47 338	96.04 208	94.50 372	93.57 263	96.47 274	96.97 289	76.50 391	98.61 377	90.67 332	98.41 321	97.81 349

HyFIR lowres test		93.72 315	92.65 332	96.91 195	98.93 129	91.81 246	91.23 407	98.52 208	82.69 416	96.46 275	96.52 319	80.38 373	99.90 18	90.36 340	98.79 286	99.03 205

QAPM		95.88 221	95.57 238	96.80 204	97.90 264	91.84 245	98.18 56	98.73 174	88.41 366	96.42 276	98.13 183	94.73 177	99.75 83	88.72 363	98.94 269	98.81 243

BH-RMVSNet		94.56 288	94.44 289	94.91 308	97.57 314	87.44 339	93.78 342	96.26 335	93.69 260	96.41 277	96.50 320	92.10 256	99.00 336	85.96 392	97.71 352	98.31 300

CNVR-MVS		96.92 162	96.55 189	98.03 100	98.00 257	95.54 102	94.87 295	98.17 253	94.60 228	96.38 278	97.05 283	95.67 147	99.36 267	95.12 205	99.08 255	99.19 169

thres600view7		92.03 352	91.43 350	93.82 349	98.19 231	84.61 381	96.27 186	90.39 420	96.81 112	96.37 279	93.11 392	73.44 410	99.49 221	80.32 424	97.95 339	97.36 373

thres100view900		91.76 357	91.26 357	93.26 362	98.21 228	84.50 382	96.39 175	90.39 420	96.87 110	96.33 280	93.08 396	73.44 410	99.42 241	78.85 429	97.74 349	95.85 412

MonoMVSNet		93.30 328	93.96 306	91.33 403	94.14 426	81.33 410	97.68 93	96.69 331	95.38 196	96.32 281	98.42 135	84.12 352	96.76 429	90.78 323	92.12 430	95.89 411

XVS		97.96 66	97.63 113	98.94 19	99.15 90	97.66 23	97.77 83	98.83 152	97.42 87	96.32 281	97.64 237	96.49 107	99.72 104	95.66 163	99.37 201	99.45 106

X-MVStestdata		92.86 335	90.83 364	98.94 19	99.15 90	97.66 23	97.77 83	98.83 152	97.42 87	96.32 281	36.50 446	96.49 107	99.72 104	95.66 163	99.37 201	99.45 106

MSDG		95.33 250	95.13 247	95.94 262	97.40 329	91.85 244	91.02 412	98.37 228	95.30 199	96.31 284	95.99 343	94.51 189	98.38 396	89.59 351	97.65 359	97.60 364

CDS-MVSNet		94.88 271	94.12 300	97.14 174	97.64 309	93.57 187	93.96 335	97.06 316	90.05 345	96.30 285	96.55 315	86.10 333	99.47 226	90.10 343	99.31 222	98.40 287
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CVMVSNet		92.33 344	92.79 327	90.95 405	97.26 339	75.84 436	95.29 273	92.33 400	81.86 418	96.27 286	98.19 176	81.44 366	98.46 391	94.23 244	98.29 326	98.55 274

FMVSNet5		93.39 325	92.35 336	96.50 223	95.83 389	90.81 266	97.31 118	98.27 238	92.74 298	96.27 286	98.28 162	62.23 428	99.67 149	90.86 319	99.36 204	99.03 205

TAPA-MVS	93.32 12	94.93 267	94.23 294	97.04 185	98.18 234	94.51 148	95.22 276	98.73 174	81.22 423	96.25 288	95.95 347	93.80 209	98.98 340	89.89 347	98.87 277	97.62 362
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
BP-MVS1		95.36 247	94.86 262	96.89 197	98.35 213	91.72 247	96.76 155	95.21 362	96.48 130	96.23 289	97.19 273	75.97 396	99.80 51	97.91 60	99.60 123	99.15 177

CHOSEN 1792x2688		94.10 304	93.41 315	96.18 247	99.16 87	90.04 275	92.15 386	98.68 186	79.90 428	96.22 290	97.83 219	87.92 317	99.42 241	89.18 357	99.65 103	99.08 198

FE-MVS		92.95 334	92.22 339	95.11 297	97.21 341	88.33 317	98.54 26	93.66 382	89.91 347	96.21 291	98.14 181	70.33 419	99.50 215	87.79 374	98.24 328	97.51 368

MCST-MVS		96.24 204	95.80 229	97.56 133	98.75 156	94.13 165	94.66 304	98.17 253	90.17 344	96.21 291	96.10 341	95.14 167	99.43 239	94.13 248	98.85 280	99.13 184

PHI-MVS		96.96 160	96.53 192	98.25 79	97.48 321	96.50 63	96.76 155	98.85 142	93.52 266	96.19 293	96.85 297	95.94 130	99.42 241	93.79 261	99.43 190	98.83 240

HQP_MVS		96.66 185	96.33 203	97.68 125	98.70 165	94.29 158	96.50 170	98.75 171	96.36 134	96.16 294	96.77 304	91.91 263	99.46 229	92.59 286	99.20 237	99.28 151

plane_prior3						94.51 148			95.29 200	96.16 294

miper_enhance_ethall		93.14 332	92.78 329	94.20 343	93.65 431	85.29 369	89.97 422	97.85 278	85.05 403	96.15 296	94.56 376	85.74 336	99.14 315	93.74 262	98.34 323	98.17 317

CS-MVS		98.09 55	98.01 69	98.32 71	98.45 204	96.69 56	98.52 29	99.69 9	98.07 60	96.07 297	97.19 273	96.88 86	99.86 28	97.50 81	99.73 79	98.41 286

MVS_Test		96.27 203	96.79 173	94.73 320	96.94 352	86.63 353	96.18 194	98.33 233	94.94 215	96.07 297	98.28 162	95.25 162	99.26 295	97.21 92	97.90 342	98.30 302

PCF-MVS	89.43 18	92.12 348	90.64 368	96.57 219	97.80 279	93.48 192	89.88 426	98.45 214	74.46 440	96.04 299	95.68 353	90.71 277	99.31 282	73.73 437	99.01 264	96.91 387
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CPTT-MVS		96.69 183	96.08 214	98.49 58	98.89 136	96.64 59	97.25 121	98.77 167	92.89 295	96.01 300	97.13 276	92.23 251	99.67 149	92.24 291	99.34 212	99.17 173

EC-MVSNet		97.90 82	97.94 76	97.79 114	98.66 170	95.14 128	98.31 42	99.66 12	97.57 79	95.95 301	97.01 288	96.99 74	99.82 39	97.66 75	99.64 105	98.39 289

PMVS	89.60 17	96.71 182	96.97 160	95.95 260	99.51 31	97.81 20	97.42 114	97.49 300	97.93 63	95.95 301	98.58 115	96.88 86	96.91 425	89.59 351	99.36 204	93.12 434
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
xiu_mvs_v1_base_debu		95.62 234	95.96 220	94.60 324	98.01 253	88.42 313	93.99 331	98.21 244	92.98 290	95.91 303	94.53 377	96.39 115	99.72 104	95.43 184	98.19 329	95.64 416

xiu_mvs_v1_base		95.62 234	95.96 220	94.60 324	98.01 253	88.42 313	93.99 331	98.21 244	92.98 290	95.91 303	94.53 377	96.39 115	99.72 104	95.43 184	98.19 329	95.64 416

xiu_mvs_v1_base_debi		95.62 234	95.96 220	94.60 324	98.01 253	88.42 313	93.99 331	98.21 244	92.98 290	95.91 303	94.53 377	96.39 115	99.72 104	95.43 184	98.19 329	95.64 416

WBMVS		91.11 364	90.72 366	92.26 392	95.99 381	77.98 427	91.47 399	95.90 344	91.63 317	95.90 306	96.45 322	59.60 430	99.46 229	89.97 346	99.59 126	99.33 138

tfpn200view9		91.55 359	91.00 359	93.21 366	98.02 251	84.35 386	95.70 235	90.79 416	96.26 138	95.90 306	92.13 413	73.62 407	99.42 241	78.85 429	97.74 349	95.85 412

thres400		91.68 358	91.00 359	93.71 353	98.02 251	84.35 386	95.70 235	90.79 416	96.26 138	95.90 306	92.13 413	73.62 407	99.42 241	78.85 429	97.74 349	97.36 373

cl22		93.25 330	92.84 326	94.46 333	94.30 421	86.00 360	91.09 411	96.64 333	90.74 333	95.79 309	96.31 330	78.24 380	98.77 358	94.15 247	98.34 323	98.62 267

API-MVS		95.09 262	95.01 253	95.31 290	96.61 359	94.02 169	96.83 147	97.18 310	95.60 182	95.79 309	94.33 382	94.54 188	98.37 398	85.70 394	98.52 311	93.52 431

DP-MVS Recon		95.55 237	95.13 247	96.80 204	98.51 194	93.99 171	94.60 306	98.69 184	90.20 343	95.78 311	96.21 334	92.73 235	98.98 340	90.58 334	98.86 279	97.42 372

CLD-MVS		95.47 242	95.07 250	96.69 212	98.27 221	92.53 218	91.36 401	98.67 189	91.22 329	95.78 311	94.12 384	95.65 148	98.98 340	90.81 321	99.72 84	98.57 271
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
旧先验2							93.35 355		77.95 435	95.77 313			98.67 372	90.74 328

pmmvs4		94.82 273	94.19 297	96.70 211	97.42 328	92.75 215	92.09 389	96.76 327	86.80 386	95.73 314	97.22 271	89.28 301	98.89 348	93.28 275	99.14 245	98.46 285

LF4IMVS		96.07 211	95.63 236	97.36 157	98.19 231	95.55 101	95.44 255	98.82 160	92.29 307	95.70 315	96.55 315	92.63 239	98.69 368	91.75 303	99.33 217	97.85 345

testdata				95.70 273	98.16 239	90.58 269		97.72 287	80.38 426	95.62 316	97.02 285	92.06 258	98.98 340	89.06 360	98.52 311	97.54 367

MVS_0304		95.71 229	95.18 245	97.33 159	94.85 413	92.82 209	95.36 263	90.89 415	95.51 188	95.61 317	97.82 222	88.39 309	99.78 59	98.23 47	99.91 19	99.40 121

MP-MVS		97.64 111	97.18 148	99.00 13	99.32 57	97.77 21	97.49 109	98.73 174	96.27 137	95.59 318	97.75 229	96.30 120	99.78 59	93.70 265	99.48 172	99.45 106
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ETV-MVS		96.13 210	95.90 224	96.82 203	97.76 289	93.89 173	95.40 260	98.95 118	95.87 169	95.58 319	91.00 424	96.36 118	99.72 104	93.36 271	98.83 283	96.85 390

mvsmamba		94.91 268	94.41 290	96.40 233	97.65 306	91.30 255	97.92 73	95.32 359	91.50 322	95.54 320	98.38 141	83.06 359	99.68 140	92.46 289	97.84 344	98.23 309

SPE-MVS-test		97.91 80	97.84 84	98.14 89	98.52 192	96.03 84	98.38 37	99.67 10	98.11 58	95.50 321	96.92 294	96.81 92	99.87 26	96.87 109	99.76 68	98.51 278

thres200		91.00 367	90.42 371	92.77 381	97.47 325	83.98 391	94.01 330	91.18 413	95.12 207	95.44 322	91.21 422	73.93 403	99.31 282	77.76 432	97.63 360	95.01 423

CDPH-MVS		95.45 244	94.65 273	97.84 112	98.28 219	94.96 133	93.73 343	98.33 233	85.03 404	95.44 322	96.60 313	95.31 160	99.44 237	90.01 344	99.13 247	99.11 193

NCCC		96.52 191	95.99 218	98.10 92	97.81 275	95.68 96	95.00 290	98.20 247	95.39 195	95.40 324	96.36 328	93.81 208	99.45 234	93.55 268	98.42 320	99.17 173

jason		94.39 295	94.04 302	95.41 289	98.29 217	87.85 331	92.74 369	96.75 328	85.38 401	95.29 325	96.15 336	88.21 312	99.65 158	94.24 243	99.34 212	98.74 253
jason: jason.
new_pmnet		92.34 343	91.69 348	94.32 339	96.23 370	89.16 297	92.27 384	92.88 391	84.39 413	95.29 325	96.35 329	85.66 338	96.74 430	84.53 407	97.56 361	97.05 381

pmmvs5		94.63 285	94.34 292	95.50 283	97.63 310	88.34 316	94.02 329	97.13 312	87.15 380	95.22 327	97.15 275	87.50 320	99.27 294	93.99 254	99.26 231	98.88 235

Effi-MVS+-dtu		96.81 173	96.09 213	98.99 14	96.90 354	98.69 5	96.42 173	98.09 264	95.86 170	95.15 328	95.54 358	94.26 197	99.81 44	94.06 250	98.51 314	98.47 283

testing3		89.72 381	88.26 390	94.10 346	97.66 304	84.30 388	94.80 297	88.25 432	94.66 225	95.07 329	92.51 408	41.15 451	99.43 239	91.81 300	98.44 319	98.55 274

KD-MVS_2432*1600		88.93 388	87.74 393	92.49 386	88.04 447	81.99 403	89.63 428	95.62 350	91.35 326	95.06 330	93.11 392	56.58 436	98.63 375	85.19 401	95.07 414	96.85 390

miper_refine_blended		88.93 388	87.74 393	92.49 386	88.04 447	81.99 403	89.63 428	95.62 350	91.35 326	95.06 330	93.11 392	56.58 436	98.63 375	85.19 401	95.07 414	96.85 390

HPM-MVS++		96.99 156	96.38 200	98.81 31	98.64 171	97.59 27	95.97 216	98.20 247	95.51 188	95.06 330	96.53 317	94.10 200	99.70 127	94.29 241	99.15 244	99.13 184

MIMVSNet		93.42 324	92.86 324	95.10 299	98.17 237	88.19 319	98.13 58	93.69 379	92.07 308	95.04 333	98.21 175	80.95 371	99.03 335	81.42 420	98.06 335	98.07 323

TR-MVS		92.54 340	92.20 340	93.57 356	96.49 362	86.66 352	93.51 350	94.73 369	89.96 346	94.95 334	93.87 387	90.24 288	98.61 377	81.18 422	94.88 417	95.45 420

PatchMatch-RL		94.61 286	93.81 308	97.02 188	98.19 231	95.72 93	93.66 344	97.23 307	88.17 371	94.94 335	95.62 356	91.43 266	98.57 380	87.36 384	97.68 355	96.76 396

MG-MVS		94.08 306	94.00 303	94.32 339	97.09 346	85.89 361	93.19 360	95.96 342	92.52 301	94.93 336	97.51 247	89.54 294	98.77 358	87.52 382	97.71 352	98.31 300

新几何1				97.25 167	98.29 217	94.70 140		97.73 286	77.98 434	94.83 337	96.67 310	92.08 257	99.45 234	88.17 372	98.65 303	97.61 363

Fast-Effi-MVS+-dtu		96.44 195	96.12 211	97.39 156	97.18 342	94.39 152	95.46 254	98.73 174	96.03 156	94.72 338	94.92 371	96.28 123	99.69 134	93.81 260	97.98 337	98.09 320

test0.0.03 1		90.11 372	89.21 380	92.83 379	93.89 429	86.87 350	91.74 394	88.74 431	92.02 310	94.71 339	91.14 423	73.92 404	94.48 439	83.75 413	92.94 426	97.16 379

test222					98.17 237	93.24 202	92.74 369	97.61 298	75.17 439	94.65 340	96.69 309	90.96 274			98.66 301	97.66 359

SCA		93.38 326	93.52 313	92.96 375	96.24 368	81.40 409	93.24 358	94.00 377	91.58 321	94.57 341	96.97 289	87.94 313	99.42 241	89.47 353	97.66 358	98.06 327

CNLPA		95.04 263	94.47 286	96.75 208	97.81 275	95.25 121	94.12 327	97.89 276	94.41 237	94.57 341	95.69 352	90.30 286	98.35 399	86.72 390	98.76 289	96.64 398

PVSNet_BlendedMVS		95.02 266	94.93 256	95.27 291	97.79 284	87.40 340	94.14 325	98.68 186	88.94 359	94.51 343	98.01 203	93.04 226	99.30 285	89.77 349	99.49 168	99.11 193

PVSNet_Blended		93.96 310	93.65 310	94.91 308	97.79 284	87.40 340	91.43 400	98.68 186	84.50 411	94.51 343	94.48 380	93.04 226	99.30 285	89.77 349	98.61 306	98.02 333

MVSFormer		96.14 209	96.36 201	95.49 284	97.68 299	87.81 332	98.67 18	99.02 94	96.50 127	94.48 345	96.15 336	86.90 327	99.92 6	98.73 33	99.13 247	98.74 253

lupinMVS		93.77 313	93.28 316	95.24 292	97.68 299	87.81 332	92.12 387	96.05 338	84.52 410	94.48 345	95.06 367	86.90 327	99.63 169	93.62 267	99.13 247	98.27 306

OpenMVS	94.22 8	95.48 241	95.20 243	96.32 237	97.16 343	91.96 241	97.74 88	98.84 146	87.26 378	94.36 347	98.01 203	93.95 205	99.67 149	90.70 330	98.75 290	97.35 375

PatchT		93.75 314	93.57 312	94.29 341	95.05 411	87.32 342	96.05 206	92.98 390	97.54 82	94.25 348	98.72 97	75.79 397	99.24 301	95.92 149	95.81 405	96.32 406

BH-w/o		92.14 347	91.94 342	92.73 382	97.13 345	85.30 368	92.46 377	95.64 349	89.33 353	94.21 349	92.74 404	89.60 292	98.24 404	81.68 419	94.66 419	94.66 425

ttmdpeth		94.05 307	94.15 299	93.75 351	95.81 391	85.32 367	96.00 212	94.93 367	92.07 308	94.19 350	99.09 58	85.73 337	96.41 432	90.98 315	98.52 311	99.53 72

xiu_mvs_v2_base		94.22 298	94.63 276	92.99 374	97.32 337	84.84 379	92.12 387	97.84 280	91.96 312	94.17 351	93.43 390	96.07 128	99.71 118	91.27 308	97.48 365	94.42 426

PS-MVSNAJ		94.10 304	94.47 286	93.00 373	97.35 332	84.88 376	91.86 392	97.84 280	91.96 312	94.17 351	92.50 409	95.82 137	99.71 118	91.27 308	97.48 365	94.40 427

CR-MVSNet		93.29 329	92.79 327	94.78 318	95.44 402	88.15 321	96.18 194	97.20 308	84.94 407	94.10 353	98.57 117	77.67 383	99.39 256	95.17 197	95.81 405	96.81 394

RPMNet		94.68 282	94.60 278	94.90 310	95.44 402	88.15 321	96.18 194	98.86 138	97.43 86	94.10 353	98.49 126	79.40 375	99.76 76	95.69 160	95.81 405	96.81 394

WTY-MVS		93.55 321	93.00 322	95.19 294	97.81 275	87.86 329	93.89 337	96.00 340	89.02 357	94.07 355	95.44 362	86.27 332	99.33 276	87.69 376	96.82 383	98.39 289

GA-MVS		92.83 336	92.15 341	94.87 312	96.97 349	87.27 343	90.03 421	96.12 337	91.83 315	94.05 356	94.57 375	76.01 395	98.97 344	92.46 289	97.34 371	98.36 296

WB-MVSnew		91.50 360	91.29 353	92.14 394	94.85 413	80.32 416	93.29 357	88.77 430	88.57 365	94.03 357	92.21 411	92.56 241	98.28 403	80.21 425	97.08 375	97.81 349

test_prior2							93.33 356		94.21 242	94.02 358	96.25 332	93.64 213		91.90 296	98.96 266

MDTV_nov1_ep13_2view						57.28 451	94.89 294		80.59 425	94.02 358		78.66 379		85.50 398		97.82 347

AdaColmap		95.11 260	94.62 277	96.58 217	97.33 336	94.45 151	94.92 292	98.08 265	93.15 285	93.98 360	95.53 359	94.34 193	99.10 325	85.69 395	98.61 306	96.20 409

pmmvs3		90.00 375	88.90 385	93.32 360	94.20 425	85.34 366	91.25 406	92.56 398	78.59 432	93.82 361	95.17 364	67.36 424	98.69 368	89.08 359	98.03 336	95.92 410

TEST9					97.84 271	95.23 122	93.62 346	98.39 224	86.81 385	93.78 362	95.99 343	94.68 181	99.52 210

train_agg		95.46 243	94.66 272	97.88 109	97.84 271	95.23 122	93.62 346	98.39 224	87.04 381	93.78 362	95.99 343	94.58 185	99.52 210	91.76 302	98.90 273	98.89 231

EIA-MVS		96.04 213	95.77 231	96.85 200	97.80 279	92.98 206	96.12 201	99.16 54	94.65 226	93.77 364	91.69 418	95.68 145	99.67 149	94.18 245	98.85 280	97.91 340

sss		94.22 298	93.72 309	95.74 270	97.71 297	89.95 277	93.84 338	96.98 319	88.38 368	93.75 365	95.74 351	87.94 313	98.89 348	91.02 314	98.10 333	98.37 291

test_8					97.81 275	95.07 131	93.54 349	98.38 226	87.04 381	93.71 366	95.96 346	94.58 185	99.52 210

E-PMN		89.52 384	89.78 376	88.73 417	93.14 434	77.61 428	83.26 440	92.02 402	94.82 219	93.71 366	93.11 392	75.31 398	96.81 426	85.81 393	96.81 384	91.77 437

thisisatest0515		90.43 370	89.18 383	94.17 345	97.07 347	85.44 365	89.75 427	87.58 433	88.28 369	93.69 368	91.72 417	65.27 425	99.58 189	90.59 333	98.67 299	97.50 370

UGNet		96.81 173	96.56 186	97.58 132	96.64 358	93.84 176	97.75 86	97.12 313	96.47 131	93.62 369	98.88 84	93.22 221	99.53 207	95.61 168	99.69 92	99.36 135
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
PatchmatchNet		91.98 353	91.87 343	92.30 391	94.60 418	79.71 418	95.12 279	93.59 384	89.52 351	93.61 370	97.02 285	77.94 381	99.18 308	90.84 320	94.57 422	98.01 334
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CMPMVS	73.10 23	92.74 337	91.39 351	96.77 207	93.57 433	94.67 141	94.21 320	97.67 289	80.36 427	93.61 370	96.60 313	82.85 361	97.35 419	84.86 405	98.78 287	98.29 305
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing3-2		90.09 373	90.38 372	89.24 415	98.07 248	69.88 448	95.12 279	90.71 419	96.65 117	93.60 372	94.03 385	55.81 441	99.33 276	90.69 331	98.71 295	98.51 278

test12				97.46 148	97.61 311	94.07 166		97.78 284		93.57 373		93.31 219	99.42 241		98.78 287	98.89 231

tpm		91.08 366	90.85 363	91.75 398	95.33 406	78.09 424	95.03 289	91.27 412	88.75 361	93.53 374	97.40 254	71.24 414	99.30 285	91.25 310	93.87 424	97.87 344

agg_prior					97.80 279	94.96 133		98.36 229		93.49 375			99.53 207

原ACMM1				96.58 217	98.16 239	92.12 234		98.15 259	85.90 394	93.49 375	96.43 323	92.47 248	99.38 259	87.66 377	98.62 305	98.23 309

MDTV_nov1_ep13			91.28 354		94.31 420	73.51 443	94.80 297	93.16 388	86.75 387	93.45 377	97.40 254	76.37 392	98.55 383	88.85 361	96.43 394

114514_t		93.96 310	93.22 318	96.19 246	99.06 107	90.97 262	95.99 214	98.94 119	73.88 441	93.43 378	96.93 292	92.38 250	99.37 264	89.09 358	99.28 226	98.25 308

Fast-Effi-MVS+		95.49 239	95.07 250	96.75 208	97.67 303	92.82 209	94.22 319	98.60 200	91.61 319	93.42 379	92.90 399	96.73 95	99.70 127	92.60 285	97.89 343	97.74 354

PAPM_NR		94.61 286	94.17 298	95.96 258	98.36 212	91.23 257	95.93 221	97.95 272	92.98 290	93.42 379	94.43 381	90.53 278	98.38 396	87.60 378	96.29 399	98.27 306

Effi-MVS+		96.19 207	96.01 216	96.71 210	97.43 327	92.19 233	96.12 201	99.10 67	95.45 191	93.33 381	94.71 374	97.23 60	99.56 197	93.21 278	97.54 362	98.37 291

F-COLMAP		95.30 252	94.38 291	98.05 99	98.64 171	96.04 82	95.61 248	98.66 192	89.00 358	93.22 382	96.40 326	92.90 231	99.35 271	87.45 383	97.53 363	98.77 250

test_vis1_rt		94.03 309	93.65 310	95.17 296	95.76 395	93.42 195	93.97 334	98.33 233	84.68 408	93.17 383	95.89 349	92.53 246	94.79 437	93.50 269	94.97 416	97.31 377

EPMVS		89.26 385	88.55 387	91.39 402	92.36 440	79.11 421	95.65 242	79.86 444	88.60 364	93.12 384	96.53 317	70.73 418	98.10 409	90.75 325	89.32 436	96.98 383

DPM-MVS		93.68 317	92.77 330	96.42 229	97.91 263	92.54 217	91.17 408	97.47 302	84.99 406	93.08 385	94.74 373	89.90 290	99.00 336	87.54 380	98.09 334	97.72 357

UWE-MVS		87.57 402	86.72 404	90.13 411	95.21 407	73.56 442	91.94 391	83.78 442	88.73 363	93.00 386	92.87 401	55.22 444	99.25 297	81.74 418	97.96 338	97.59 365

1112_ss		94.12 303	93.42 314	96.23 241	98.59 181	90.85 263	94.24 317	98.85 142	85.49 397	92.97 387	94.94 369	86.01 334	99.64 164	91.78 301	97.92 340	98.20 313

HQP4-MVS										92.87 388			99.23 303			99.06 202

HQP-NCC					97.85 266		94.26 313		93.18 281	92.86 389

ACMP_Plane					97.85 266		94.26 313		93.18 281	92.86 389

HQP-MVS		95.17 259	94.58 281	96.92 193	97.85 266	92.47 221	94.26 313	98.43 217	93.18 281	92.86 389	95.08 365	90.33 283	99.23 303	90.51 336	98.74 291	99.05 204

dmvs_re		92.08 350	91.27 355	94.51 330	97.16 343	92.79 214	95.65 242	92.64 396	94.11 248	92.74 392	90.98 425	83.41 357	94.44 440	80.72 423	94.07 423	96.29 407

ADS-MVSNet2		91.47 361	90.51 370	94.36 336	95.51 400	85.63 362	95.05 287	95.70 347	83.46 414	92.69 393	96.84 298	79.15 377	99.41 250	85.66 396	90.52 432	98.04 331

ADS-MVSNet		90.95 368	90.26 373	93.04 370	95.51 400	82.37 401	95.05 287	93.41 385	83.46 414	92.69 393	96.84 298	79.15 377	98.70 366	85.66 396	90.52 432	98.04 331

Test_1112_low_res		93.53 322	92.86 324	95.54 282	98.60 179	88.86 307	92.75 367	98.69 184	82.66 417	92.65 395	96.92 294	84.75 346	99.56 197	90.94 317	97.76 348	98.19 314

AUN-MVS		93.95 312	92.69 331	97.74 118	97.80 279	95.38 112	95.57 251	95.46 356	91.26 328	92.64 396	96.10 341	74.67 401	99.55 201	93.72 264	96.97 376	98.30 302

EMVS		89.06 387	89.22 379	88.61 418	93.00 436	77.34 430	82.91 441	90.92 414	94.64 227	92.63 397	91.81 416	76.30 393	97.02 423	83.83 411	96.90 379	91.48 438

CANet		95.86 222	95.65 235	96.49 224	96.41 365	90.82 264	94.36 311	98.41 221	94.94 215	92.62 398	96.73 307	92.68 236	99.71 118	95.12 205	99.60 123	98.94 219

DSMNet-mixed		92.19 346	91.83 344	93.25 363	96.18 373	83.68 393	96.27 186	93.68 381	76.97 438	92.54 399	99.18 46	89.20 303	98.55 383	83.88 410	98.60 308	97.51 368

PVSNet	86.72 19	91.10 365	90.97 361	91.49 400	97.56 316	78.04 425	87.17 433	94.60 371	84.65 409	92.34 400	92.20 412	87.37 324	98.47 390	85.17 403	97.69 354	97.96 337

tpmrst		90.31 371	90.61 369	89.41 414	94.06 427	72.37 445	95.06 286	93.69 379	88.01 372	92.32 401	96.86 296	77.45 385	98.82 353	91.04 313	87.01 439	97.04 382

cascas		91.89 354	91.35 352	93.51 357	94.27 422	85.60 363	88.86 431	98.61 199	79.32 430	92.16 402	91.44 420	89.22 302	98.12 408	90.80 322	97.47 367	96.82 393

MAR-MVS		94.21 300	93.03 320	97.76 117	96.94 352	97.44 37	96.97 139	97.15 311	87.89 375	92.00 403	92.73 405	92.14 254	99.12 319	83.92 409	97.51 364	96.73 397
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
tpmvs		90.79 369	90.87 362	90.57 408	92.75 439	76.30 434	95.79 230	93.64 383	91.04 331	91.91 404	96.26 331	77.19 389	98.86 352	89.38 355	89.85 435	96.56 401

PMMVS		92.39 341	91.08 358	96.30 239	93.12 435	92.81 211	90.58 417	95.96 342	79.17 431	91.85 405	92.27 410	90.29 287	98.66 373	89.85 348	96.68 390	97.43 371

Syy-MVS		92.09 349	91.80 346	92.93 377	95.19 408	82.65 398	92.46 377	91.35 409	90.67 336	91.76 406	87.61 438	85.64 339	98.50 387	94.73 225	96.84 381	97.65 360

myMVS_eth3d		87.16 406	85.61 409	91.82 397	95.19 408	79.32 419	92.46 377	91.35 409	90.67 336	91.76 406	87.61 438	41.96 450	98.50 387	82.66 415	96.84 381	97.65 360

PLC	91.02 16	94.05 307	92.90 323	97.51 138	98.00 257	95.12 130	94.25 316	98.25 240	86.17 390	91.48 408	95.25 363	91.01 272	99.19 307	85.02 404	96.69 389	98.22 311
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dp		88.08 397	88.05 391	88.16 422	92.85 437	68.81 449	94.17 321	92.88 391	85.47 398	91.38 409	96.14 338	68.87 422	98.81 355	86.88 388	83.80 442	96.87 388

PAPR		92.22 345	91.27 355	95.07 300	95.73 397	88.81 308	91.97 390	97.87 277	85.80 395	90.91 410	92.73 405	91.16 269	98.33 400	79.48 426	95.76 409	98.08 321

1314		92.38 342	92.30 337	92.64 384	95.42 404	85.15 372	95.86 225	96.97 320	85.40 400	90.62 411	93.06 397	91.12 270	97.80 415	86.74 389	95.49 413	94.97 424

MVS		90.02 374	89.20 381	92.47 388	94.71 416	86.90 349	95.86 225	96.74 329	64.72 443	90.62 411	92.77 403	92.54 244	98.39 395	79.30 427	95.56 412	92.12 435

CostFormer		89.75 380	89.25 378	91.26 404	94.69 417	78.00 426	95.32 270	91.98 403	81.50 421	90.55 413	96.96 291	71.06 416	98.89 348	88.59 366	92.63 428	96.87 388

HY-MVS	91.43 15	92.58 339	91.81 345	94.90 310	96.49 362	88.87 306	97.31 118	94.62 370	85.92 393	90.50 414	96.84 298	85.05 343	99.40 252	83.77 412	95.78 408	96.43 405

ETVMVS		87.62 401	85.75 408	93.22 365	96.15 377	83.26 394	92.94 363	90.37 422	91.39 325	90.37 415	88.45 436	51.93 448	98.64 374	73.76 436	96.38 396	97.75 353

FPMVS		89.92 378	88.63 386	93.82 349	98.37 211	96.94 49	91.58 397	93.34 386	88.00 373	90.32 416	97.10 280	70.87 417	91.13 443	71.91 440	96.16 403	93.39 433

JIA-IIPM		91.79 356	90.69 367	95.11 297	93.80 430	90.98 261	94.16 322	91.78 405	96.38 132	90.30 417	99.30 32	72.02 413	98.90 347	88.28 370	90.17 434	95.45 420

testing91		89.67 382	88.55 387	93.04 370	95.90 384	81.80 406	92.71 371	93.71 378	93.71 258	90.18 418	90.15 430	57.11 434	99.22 305	87.17 387	96.32 398	98.12 319

myMVS_eth3d28		88.32 394	87.73 395	90.11 412	96.42 364	74.96 441	92.21 385	92.37 399	93.56 264	90.14 419	89.61 433	56.13 439	98.05 411	81.84 417	97.26 374	97.33 376

CANet_DTU		94.65 284	94.21 296	95.96 258	95.90 384	89.68 284	93.92 336	97.83 282	93.19 280	90.12 420	95.64 355	88.52 306	99.57 195	93.27 276	99.47 174	98.62 267

test-LLR		89.97 377	89.90 375	90.16 409	94.24 423	74.98 438	89.89 423	89.06 428	92.02 310	89.97 421	90.77 426	73.92 404	98.57 380	91.88 297	97.36 369	96.92 385

test-mter		87.92 399	87.17 399	90.16 409	94.24 423	74.98 438	89.89 423	89.06 428	86.44 389	89.97 421	90.77 426	54.96 447	98.57 380	91.88 297	97.36 369	96.92 385

testing99		89.21 386	88.04 392	92.70 383	95.78 393	81.00 413	92.65 372	92.03 401	93.20 279	89.90 423	90.08 432	55.25 443	99.14 315	87.54 380	95.95 404	97.97 336

UBG		88.29 395	87.17 399	91.63 399	96.08 379	78.21 423	91.61 395	91.50 408	89.67 350	89.71 424	88.97 435	59.01 431	98.91 346	81.28 421	96.72 388	97.77 352

dmvs_testset		87.30 404	86.99 401	88.24 420	96.71 356	77.48 429	94.68 303	86.81 437	92.64 300	89.61 425	87.01 440	85.91 335	93.12 441	61.04 444	88.49 437	94.13 428

tpm2		88.47 392	87.69 396	90.79 406	94.98 412	77.34 430	95.09 282	91.83 404	77.51 437	89.40 426	96.41 324	67.83 423	98.73 362	83.58 414	92.60 429	96.29 407

tpm cat1		88.01 398	87.33 398	90.05 413	94.48 419	76.28 435	94.47 309	94.35 374	73.84 442	89.26 427	95.61 357	73.64 406	98.30 402	84.13 408	86.20 440	95.57 419

TESTMET0.1,1		87.20 405	86.57 405	89.07 416	93.62 432	72.84 444	89.89 423	87.01 436	85.46 399	89.12 428	90.20 429	56.00 440	97.72 416	90.91 318	96.92 377	96.64 398

testing222		87.35 403	85.50 410	92.93 377	95.79 392	82.83 396	92.40 382	90.10 426	92.80 297	88.87 429	89.02 434	48.34 449	98.70 366	75.40 435	96.74 386	97.27 378

MVS-HIRNet		88.40 393	90.20 374	82.99 425	97.01 348	60.04 450	93.11 361	85.61 439	84.45 412	88.72 430	99.09 58	84.72 347	98.23 405	82.52 416	96.59 392	90.69 440

IB-MVS	85.98 20	88.63 391	86.95 403	93.68 354	95.12 410	84.82 380	90.85 413	90.17 425	87.55 377	88.48 431	91.34 421	58.01 432	99.59 186	87.24 386	93.80 425	96.63 400
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
testing11		88.93 388	87.63 397	92.80 380	95.87 386	81.49 408	92.48 376	91.54 407	91.62 318	88.27 432	90.24 428	55.12 446	99.11 322	87.30 385	96.28 400	97.81 349

PVSNet_0	81.89 21	84.49 408	83.21 411	88.34 419	95.76 395	74.97 440	83.49 439	92.70 395	78.47 433	87.94 433	86.90 441	83.38 358	96.63 431	73.44 438	66.86 445	93.40 432

EPNet		93.72 315	92.62 334	97.03 187	87.61 449	92.25 227	96.27 186	91.28 411	96.74 115	87.65 434	97.39 258	85.00 344	99.64 164	92.14 292	99.48 172	99.20 168
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CHOSEN 280x420		89.98 376	89.19 382	92.37 390	95.60 399	81.13 412	86.22 435	97.09 314	81.44 422	87.44 435	93.15 391	73.99 402	99.47 226	88.69 364	99.07 257	96.52 402

baseline2		89.65 383	88.44 389	93.25 363	95.62 398	82.71 397	93.82 339	85.94 438	88.89 360	87.35 436	92.54 407	71.23 415	99.33 276	86.01 391	94.60 421	97.72 357

gg-mvs-nofinetune		88.28 396	86.96 402	92.23 393	92.84 438	84.44 384	98.19 55	74.60 447	99.08 17	87.01 437	99.47 16	56.93 435	98.23 405	78.91 428	95.61 411	94.01 429

ET-MVSNet_ETH3D		91.12 363	89.67 377	95.47 285	96.41 365	89.15 298	91.54 398	90.23 424	89.07 356	86.78 438	92.84 402	69.39 421	99.44 237	94.16 246	96.61 391	97.82 347

UWE-MVS-28		83.78 409	82.36 412	88.03 423	90.72 444	71.58 446	93.64 345	77.87 445	87.62 376	85.91 439	92.89 400	59.94 429	95.99 434	56.06 446	96.56 393	96.52 402

PAPM		87.64 400	85.84 407	93.04 370	96.54 360	84.99 375	88.42 432	95.57 353	79.52 429	83.82 440	93.05 398	80.57 372	98.41 393	62.29 443	92.79 427	95.71 415

GG-mvs-BLEND				90.60 407	91.00 442	84.21 389	98.23 49	72.63 450		82.76 441	84.11 442	56.14 438	96.79 427	72.20 439	92.09 431	90.78 439

MVE	73.61 22	86.48 407	85.92 406	88.18 421	96.23 370	85.28 370	81.78 442	75.79 446	86.01 391	82.53 442	91.88 415	92.74 234	87.47 445	71.42 441	94.86 418	91.78 436
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EPNet_dtu		91.39 362	90.75 365	93.31 361	90.48 445	82.61 399	94.80 297	92.88 391	93.39 270	81.74 443	94.90 372	81.36 367	99.11 322	88.28 370	98.87 277	98.21 312
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		63.43 412	63.37 415	63.60 428	83.91 450	53.17 452	85.14 436	43.40 454	77.91 436	80.96 444	79.17 444	36.36 452	77.10 446	37.88 447	45.63 446	60.54 443

DeepMVS_CX				77.17 426	90.94 443	85.28 370		74.08 449	52.51 445	80.87 445	88.03 437	75.25 399	70.63 447	59.23 445	84.94 441	75.62 441

tmp_tt		57.23 413	62.50 416	41.44 430	34.77 453	49.21 454	83.93 438	60.22 452	15.31 446	71.11 446	79.37 443	70.09 420	44.86 449	64.76 442	82.93 443	30.25 445

test_method		66.88 411	66.13 414	69.11 427	62.68 452	25.73 455	49.76 443	96.04 339	14.32 447	64.27 447	91.69 418	73.45 409	88.05 444	76.06 434	66.94 444	93.54 430

kuosan		54.81 414	54.94 417	54.42 429	74.43 451	50.03 453	84.98 437	44.27 453	61.80 444	62.49 448	70.43 445	35.16 453	58.04 448	19.30 448	41.61 447	55.19 444

EGC-MVSNET		83.08 410	77.93 413	98.53 55	99.57 20	97.55 30	98.33 41	98.57 205	4.71 448	10.38 449	98.90 82	95.60 150	99.50 215	95.69 160	99.61 116	98.55 274

testmvs		12.33 417	15.23 420	3.64 432	5.77 455	2.23 457	88.99 430	3.62 455	2.30 450	5.29 450	13.09 447	4.52 455	1.95 450	5.16 450	8.32 449	6.75 447

test123		12.59 416	15.49 419	3.87 431	6.07 454	2.55 456	90.75 415	2.59 456	2.52 449	5.20 451	13.02 448	4.96 454	1.85 451	5.20 449	9.09 448	7.23 446

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		24.22 415	32.30 418	0.00 433	0.00 456	0.00 458	0.00 444	98.10 263	0.00 451	0.00 452	95.06 367	97.54 44	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		7.98 418	10.65 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	95.82 137	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		7.91 419	10.55 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	94.94 369	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						79.32 419								85.41 399

MSC_two_6792asdad				98.22 81	97.75 291	95.34 117		98.16 257					99.75 83	95.87 153	99.51 161	99.57 55

No_MVS				98.22 81	97.75 291	95.34 117		98.16 257					99.75 83	95.87 153	99.51 161	99.57 55

eth-test2					0.00 456

eth-test					0.00 456

OPU-MVS				97.64 129	98.01 253	95.27 120	96.79 153				97.35 263	96.97 75	98.51 386	91.21 311	99.25 232	99.14 182

save fliter					98.48 200	94.71 138	94.53 308	98.41 221	95.02 213

test_0728_SECOND				98.25 79	99.23 70	95.49 108	96.74 157	98.89 126					99.75 83	95.48 177	99.52 156	99.53 72

GSMVS																98.06 327

sam_mvs1												77.80 382				98.06 327

sam_mvs												77.38 386

MTGPA								98.73 174

test_post1							94.98 291				10.37 450	76.21 394	99.04 332	89.47 353

test_post											10.87 449	76.83 390	99.07 328

patchmatchnet-post											96.84 298	77.36 387	99.42 241

MTMP							96.55 168	74.60 447

gm-plane-assit					91.79 441	71.40 447			81.67 419		90.11 431		98.99 338	84.86 405

test9_res														91.29 307	98.89 276	99.00 209

agg_prior2														90.34 341	98.90 273	99.10 197

test_prior4						95.38 112	93.61 348

test_prior				97.46 148	97.79 284	94.26 162		98.42 220					99.34 274			98.79 246

新几何2							93.43 351

旧先验1					97.80 279	93.87 174		97.75 285			97.04 284	93.57 214			98.68 298	98.72 256

无先验							93.20 359	97.91 274	80.78 424				99.40 252	87.71 375		97.94 339

原ACMM2							92.82 365

testdata2													99.46 229	87.84 373

segment_acmp												95.34 159

testdata1							92.77 366		93.78 256

plane_prior7					98.70 165	94.67 141

plane_prior6					98.38 210	94.37 155						91.91 263

plane_prior5								98.75 171					99.46 229	92.59 286	99.20 237	99.28 151

plane_prior4											96.77 304

plane_prior2							96.50 170		96.36 134

plane_prior1					98.49 198

plane_prior						94.29 158	95.42 257		94.31 241						98.93 271

n2								0.00 457

nn								0.00 457

door-mid								98.17 253

test11								98.08 265

door								97.81 283

HQP5-MVS						92.47 221

BP-MVS														90.51 336

HQP3-MVS								98.43 217							98.74 291

HQP2-MVS												90.33 283

NP-MVS					98.14 243	93.72 180					95.08 365

ACMMP++_ref															99.52 156

ACMMP++															99.55 142

Test By Simon												94.51 189

High-resolution multi-view benchmark