High-res multi-view results

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

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

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

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

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

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

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

test_fmvs3		99.12 49	99.41 19	98.25 229	99.76 32	95.07 280	99.05 65	99.94 2	97.78 174	99.82 21	99.84 2	98.56 50	99.71 245	99.96 1	99.96 25	99.97 3

test_fmvs2		98.70 102	98.97 64	97.89 254	99.54 97	94.05 307	98.55 107	99.92 6	96.78 253	99.72 29	99.78 8	96.60 185	99.67 264	99.91 2	99.90 68	99.94 7

test_fmvsmvis_n_1920		99.26 32	99.49 12	98.54 202	99.66 65	96.97 217	98.00 174	99.85 15	99.24 60	99.92 8	99.50 59	99.39 11	99.95 23	99.89 3	99.98 12	98.71 306

test_fmvsm_n_1920		99.33 26	99.45 18	98.99 135	99.57 80	97.73 178	97.93 181	99.83 20	99.22 61	99.93 6	99.30 95	99.42 10	99.96 12	99.85 4	99.99 5	99.29 212

MVS_0304		98.10 179	97.88 194	98.76 169	98.82 256	96.50 233	97.90 186	91.35 389	99.56 26	98.32 238	99.13 131	96.06 206	99.93 39	99.84 5	99.97 20	99.85 19

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 64	99.87 12	98.13 132	98.08 160	99.95 1	99.45 36	99.98 2	99.75 11	99.80 1	99.97 4	99.82 6	99.99 5	99.99 1

test_fmvs1_n		98.09 182	98.28 153	97.52 287	99.68 59	93.47 328	98.63 98	99.93 4	95.41 301	99.68 37	99.64 32	91.88 304	99.48 329	99.82 6	99.87 76	99.62 66

test_f		98.67 113	98.87 70	98.05 246	99.72 45	95.59 258	98.51 116	99.81 23	96.30 273	99.78 25	99.82 4	96.14 202	98.63 384	99.82 6	99.93 42	99.95 6

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 10	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 9	100.00 1	99.85 19

MM				98.91 146		96.97 217	97.89 188	94.44 372	99.54 27	98.95 155	99.14 130	93.50 280	99.92 49	99.80 10	99.96 25	99.85 19

test_fmvsmconf0.1_n		99.49 12	99.54 10	99.34 73	99.78 26	98.11 133	97.77 202	99.90 9	99.33 50	99.97 3	99.66 27	99.71 3	99.96 12	99.79 11	99.99 5	99.96 5

test_vis1_n		98.31 160	98.50 119	97.73 270	99.76 32	94.17 305	98.68 95	99.91 7	96.31 271	99.79 24	99.57 42	92.85 292	99.42 340	99.79 11	99.84 84	99.60 73

test_fmvs1		97.72 211	97.94 188	97.07 310	98.66 290	92.39 345	97.68 213	99.81 23	95.20 305	99.54 54	99.44 71	91.56 306	99.41 341	99.78 13	99.77 122	99.40 172

test_vis1_n_1920		98.40 149	98.92 67	96.81 323	99.74 38	90.76 369	98.15 152	99.91 7	98.33 128	99.89 15	99.55 48	95.07 242	99.88 82	99.76 14	99.93 42	99.79 28

test_vis3_rt		99.14 44	99.17 41	99.07 121	99.78 26	98.38 109	98.92 76	99.94 2	97.80 172	99.91 11	99.67 25	97.15 152	98.91 379	99.76 14	99.56 208	99.92 9

test_fmvsmconf_n		99.44 15	99.48 14	99.31 83	99.64 70	98.10 135	97.68 213	99.84 18	99.29 56	99.92 8	99.57 42	99.60 5	99.96 12	99.74 16	99.98 12	99.89 11

fmvsm_s_conf0.1_n_a		99.17 40	99.30 32	98.80 159	99.75 36	96.59 231	97.97 180	99.86 13	98.22 139	99.88 17	99.71 17	98.59 47	99.84 137	99.73 17	99.98 12	99.98 2

v7n		99.53 9	99.57 9	99.41 60	99.88 9	98.54 100	99.45 10	99.61 48	99.66 13	99.68 37	99.66 27	98.44 57	99.95 23	99.73 17	99.96 25	99.75 41

fmvsm_s_conf0.1_n		99.16 43	99.33 26	98.64 180	99.71 48	96.10 242	97.87 192	99.85 15	98.56 120	99.90 12	99.68 20	98.69 39	99.85 120	99.72 19	99.98 12	99.97 3

fmvsm_s_conf0.5_n_a		99.10 51	99.20 39	98.78 165	99.55 92	96.59 231	97.79 199	99.82 22	98.21 140	99.81 22	99.53 54	98.46 56	99.84 137	99.70 20	99.97 20	99.90 10

v10		98.97 65	99.11 50	98.55 199	99.44 128	96.21 241	98.90 77	99.55 70	98.73 107	99.48 66	99.60 39	96.63 184	99.83 154	99.70 20	99.99 5	99.61 72

fmvsm_s_conf0.5_n		99.09 52	99.26 35	98.61 188	99.55 92	96.09 245	97.74 207	99.81 23	98.55 121	99.85 19	99.55 48	98.60 46	99.84 137	99.69 22	99.98 12	99.89 11

v1240		98.55 131	98.62 103	98.32 223	99.22 170	95.58 260	97.51 236	99.45 105	97.16 236	99.45 72	99.24 106	96.12 204	99.85 120	99.60 23	99.88 73	99.55 103

v8		99.01 59	99.16 43	98.57 194	99.47 123	96.31 239	98.90 77	99.47 100	99.03 88	99.52 60	99.57 42	96.93 164	99.81 177	99.60 23	99.98 12	99.60 73

v1921920		98.54 133	98.60 108	98.38 219	99.20 176	95.76 257	97.56 230	99.36 134	97.23 231	99.38 85	99.17 121	96.02 208	99.84 137	99.57 25	99.90 68	99.54 107

v1192		98.60 123	98.66 97	98.41 216	99.27 160	95.88 252	97.52 234	99.36 134	97.41 209	99.33 95	99.20 113	96.37 196	99.82 164	99.57 25	99.92 53	99.55 103

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 9	98.61 92	99.34 20	99.71 31	99.27 58	99.90 12	99.74 13	99.68 4	99.97 4	99.55 27	99.99 5	99.88 14

PS-MVSNAJss		99.46 14	99.49 12	99.35 70	99.90 4	98.15 129	99.20 45	99.65 43	99.48 32	99.92 8	99.71 17	98.07 84	99.96 12	99.53 28	100.00 1	99.93 8

test_cas_vis1_n_1920		98.33 157	98.68 94	97.27 301	99.69 57	92.29 348	98.03 168	99.85 15	97.62 184	99.96 4	99.62 34	93.98 273	99.74 232	99.52 29	99.86 79	99.79 28

v144192		98.54 133	98.57 111	98.45 211	99.21 172	95.98 249	97.63 221	99.36 134	97.15 238	99.32 101	99.18 117	95.84 221	99.84 137	99.50 30	99.91 61	99.54 107

jajsoiax		99.58 6	99.61 8	99.48 51	99.87 12	98.61 92	99.28 37	99.66 42	99.09 82	99.89 15	99.68 20	99.53 7	99.97 4	99.50 30	99.99 5	99.87 16

v1144		98.60 123	98.66 97	98.41 216	99.36 146	95.90 251	97.58 228	99.34 145	97.51 196	99.27 106	99.15 127	96.34 198	99.80 184	99.47 32	99.93 42	99.51 119

RRT_MVS		99.09 52	98.94 65	99.55 23	99.87 12	98.82 78	99.48 9	98.16 315	99.49 31	99.59 50	99.65 30	94.79 254	99.95 23	99.45 33	99.96 25	99.88 14

OurMVSNet-221017-0		99.37 24	99.31 30	99.53 34	99.91 3	98.98 65	99.63 6	99.58 52	99.44 38	99.78 25	99.76 10	96.39 193	99.92 49	99.44 34	99.92 53	99.68 53

tt0805		98.69 105	98.62 103	98.90 149	99.75 36	99.30 17	99.15 53	96.97 345	98.86 102	98.87 176	97.62 323	98.63 43	98.96 376	99.41 35	98.29 332	98.45 325

pmmvs6		99.67 3	99.70 3	99.60 11	99.90 4	99.27 22	99.53 7	99.76 28	99.64 15	99.84 20	99.83 3	99.50 8	99.87 99	99.36 36	99.92 53	99.64 62

v2v482		98.56 127	98.62 103	98.37 220	99.42 134	95.81 255	97.58 228	99.16 211	97.90 165	99.28 104	99.01 160	95.98 214	99.79 197	99.33 37	99.90 68	99.51 119

mvsmamba		99.24 37	99.15 48	99.49 48	99.83 20	98.85 74	99.41 13	99.55 70	99.54 27	99.40 81	99.52 57	95.86 220	99.91 58	99.32 38	99.95 30	99.70 50

bld_raw_dy_0_64		99.07 56	99.00 60	99.29 84	99.85 17	98.18 126	99.11 58	99.40 121	99.33 50	99.38 85	99.44 71	95.21 237	99.97 4	99.31 39	99.98 12	99.73 43

ANet_high		99.57 7	99.67 5	99.28 86	99.89 6	98.09 136	99.14 54	99.93 4	99.82 3	99.93 6	99.81 5	99.17 18	99.94 34	99.31 39	100.00 1	99.82 23

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 21	99.85 17	99.11 59	99.90 1	99.78 26	99.63 17	99.78 25	99.67 25	99.48 9	99.81 177	99.30 41	99.97 20	99.77 33
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
MVSFormer		98.26 167	98.43 132	97.77 262	98.88 245	93.89 319	99.39 17	99.56 66	99.11 72	98.16 247	98.13 288	93.81 276	99.97 4	99.26 42	99.57 205	99.43 157

test_djsdf		99.52 10	99.51 11	99.53 34	99.86 15	98.74 82	99.39 17	99.56 66	99.11 72	99.70 33	99.73 15	99.00 22	99.97 4	99.26 42	99.98 12	99.89 11

Anonymous20240521		98.69 105	98.87 70	98.16 237	99.77 29	95.11 279	99.08 59	99.44 109	99.34 49	99.33 95	99.55 48	94.10 272	99.94 34	99.25 44	99.96 25	99.42 160

K. test v3		98.00 188	97.66 210	99.03 131	99.79 25	97.56 186	99.19 49	92.47 383	99.62 20	99.52 60	99.66 27	89.61 318	99.96 12	99.25 44	99.81 98	99.56 96

KD-MVS_self_test		99.25 33	99.18 40	99.44 57	99.63 73	99.06 64	98.69 94	99.54 75	99.31 53	99.62 49	99.53 54	97.36 140	99.86 108	99.24 46	99.71 152	99.39 175

Anonymous20231211		99.27 30	99.27 34	99.26 91	99.29 157	98.18 126	99.49 8	99.51 82	99.70 8	99.80 23	99.68 20	96.84 168	99.83 154	99.21 47	99.91 61	99.77 33

V42		98.78 89	98.78 80	98.76 169	99.44 128	97.04 214	98.27 140	99.19 200	97.87 167	99.25 114	99.16 123	96.84 168	99.78 208	99.21 47	99.84 84	99.46 145

MIMVSNet1		99.38 23	99.32 28	99.55 23	99.86 15	99.19 37	99.41 13	99.59 50	99.59 23	99.71 31	99.57 42	97.12 153	99.90 63	99.21 47	99.87 76	99.54 107

nrg030		99.40 21	99.35 23	99.54 27	99.58 76	99.13 55	98.98 72	99.48 93	99.68 11	99.46 69	99.26 101	98.62 44	99.73 237	99.17 50	99.92 53	99.76 37

SSC-MVS		98.71 98	98.74 82	98.62 185	99.72 45	96.08 247	98.74 86	98.64 293	99.74 6	99.67 39	99.24 106	94.57 258	99.95 23	99.11 51	99.24 265	99.82 23

anonymousdsp		99.51 11	99.47 16	99.62 6	99.88 9	99.08 63	99.34 20	99.69 34	98.93 97	99.65 43	99.72 16	98.93 26	99.95 23	99.11 51	100.00 1	99.82 23

VPA-MVSNet		99.30 28	99.30 32	99.28 86	99.49 114	98.36 114	99.00 69	99.45 105	99.63 17	99.52 60	99.44 71	98.25 67	99.88 82	99.09 53	99.84 84	99.62 66

pm-mvs1		99.44 15	99.48 14	99.33 78	99.80 23	98.63 89	99.29 33	99.63 44	99.30 55	99.65 43	99.60 39	99.16 20	99.82 164	99.07 54	99.83 91	99.56 96

TransMVSNet (Re)		99.44 15	99.47 16	99.36 64	99.80 23	98.58 95	99.27 39	99.57 59	99.39 43	99.75 28	99.62 34	99.17 18	99.83 154	99.06 55	99.62 185	99.66 57

EC-MVSNet		99.09 52	99.05 57	99.20 100	99.28 158	98.93 71	99.24 41	99.84 18	99.08 84	98.12 252	98.37 270	98.72 36	99.90 63	99.05 56	99.77 122	98.77 300

SixPastTwentyTwo		98.75 94	98.62 103	99.16 106	99.83 20	97.96 156	99.28 37	98.20 312	99.37 45	99.70 33	99.65 30	92.65 295	99.93 39	99.04 57	99.84 84	99.60 73

CS-MVS		99.13 47	99.10 52	99.24 96	99.06 211	99.15 47	99.36 19	99.88 11	99.36 48	98.21 244	98.46 262	98.68 40	99.93 39	99.03 58	99.85 80	98.64 315

FC-MVSNet-test		99.27 30	99.25 36	99.34 73	99.77 29	98.37 111	99.30 32	99.57 59	99.61 22	99.40 81	99.50 59	97.12 153	99.85 120	99.02 59	99.94 38	99.80 27

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 19	99.34 15	99.69 4	99.58 52	99.90 2	99.86 18	99.78 8	99.58 6	99.95 23	99.00 60	99.95 30	99.78 31

lessismore_v0				98.97 138	99.73 39	97.53 188		86.71 396		99.37 88	99.52 57	89.93 316	99.92 49	98.99 61	99.72 147	99.44 153

mvsany_test3		98.87 77	98.92 67	98.74 176	99.38 139	96.94 221	98.58 104	99.10 223	96.49 264	99.96 4	99.81 5	98.18 76	99.45 335	98.97 62	99.79 113	99.83 22

Vis-MVSNet		99.34 25	99.36 22	99.27 89	99.73 39	98.26 118	99.17 50	99.78 26	99.11 72	99.27 106	99.48 64	98.82 31	99.95 23	98.94 63	99.93 42	99.59 79
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS-test		99.13 47	99.09 53	99.26 91	99.13 196	98.97 66	99.31 27	99.88 11	99.44 38	98.16 247	98.51 254	98.64 41	99.93 39	98.91 64	99.85 80	98.88 283

mvs_anonymous		97.83 207	98.16 168	96.87 319	98.18 333	91.89 352	97.31 250	98.90 255	97.37 213	98.83 181	99.46 66	96.28 199	99.79 197	98.90 65	98.16 339	98.95 270

WR-MVS_H		99.33 26	99.22 38	99.65 5	99.71 48	99.24 25	99.32 23	99.55 70	99.46 35	99.50 65	99.34 88	97.30 142	99.93 39	98.90 65	99.93 42	99.77 33

PS-CasMVS		99.40 21	99.33 26	99.62 6	99.71 48	99.10 60	99.29 33	99.53 78	99.53 29	99.46 69	99.41 77	98.23 69	99.95 23	98.89 67	99.95 30	99.81 26

UA-Net		99.47 13	99.40 20	99.70 2	99.49 114	99.29 19	99.80 3	99.72 30	99.82 3	99.04 141	99.81 5	98.05 87	99.96 12	98.85 68	99.99 5	99.86 18

new-patchmatchnet		98.35 155	98.74 82	97.18 304	99.24 165	92.23 350	96.42 299	99.48 93	98.30 131	99.69 35	99.53 54	97.44 136	99.82 164	98.84 69	99.77 122	99.49 126

test1111		96.49 286	96.82 258	95.52 350	99.42 134	87.08 383	99.22 42	87.14 395	99.11 72	99.46 69	99.58 41	88.69 324	99.86 108	98.80 70	99.95 30	99.62 66

PEN-MVS		99.41 20	99.34 25	99.62 6	99.73 39	99.14 52	99.29 33	99.54 75	99.62 20	99.56 51	99.42 74	98.16 80	99.96 12	98.78 71	99.93 42	99.77 33

DTE-MVSNet		99.43 18	99.35 23	99.66 4	99.71 48	99.30 17	99.31 27	99.51 82	99.64 15	99.56 51	99.46 66	98.23 69	99.97 4	98.78 71	99.93 42	99.72 44

EG-PatchMatch MVS		98.99 61	99.01 59	98.94 142	99.50 107	97.47 190	98.04 167	99.59 50	98.15 151	99.40 81	99.36 83	98.58 49	99.76 220	98.78 71	99.68 165	99.59 79

EI-MVSNet-UG-set		98.69 105	98.71 88	98.62 185	99.10 200	96.37 236	97.23 256	98.87 260	99.20 65	99.19 120	98.99 164	97.30 142	99.85 120	98.77 74	99.79 113	99.65 61

test_vis1_rt		97.75 209	97.72 205	97.83 257	98.81 259	96.35 237	97.30 251	99.69 34	94.61 316	97.87 268	98.05 297	96.26 200	98.32 387	98.74 75	98.18 336	98.82 288

CP-MVSNet		99.21 39	99.09 53	99.56 21	99.65 66	98.96 70	99.13 55	99.34 145	99.42 41	99.33 95	99.26 101	97.01 161	99.94 34	98.74 75	99.93 42	99.79 28

EI-MVSNet-Vis-set		98.68 110	98.70 91	98.63 184	99.09 203	96.40 235	97.23 256	98.86 265	99.20 65	99.18 124	98.97 170	97.29 144	99.85 120	98.72 77	99.78 118	99.64 62

test2506		92.39 352	91.89 355	93.89 367	99.38 139	82.28 397	99.32 23	66.03 403	99.08 84	98.77 190	99.57 42	66.26 398	99.84 137	98.71 78	99.95 30	99.54 107

baseline		98.96 67	99.02 58	98.76 169	99.38 139	97.26 202	98.49 119	99.50 84	98.86 102	99.19 120	99.06 139	98.23 69	99.69 252	98.71 78	99.76 133	99.33 201

FIs		99.14 44	99.09 53	99.29 84	99.70 55	98.28 117	99.13 55	99.52 81	99.48 32	99.24 115	99.41 77	96.79 174	99.82 164	98.69 80	99.88 73	99.76 37

iter_conf_final		97.10 255	96.65 272	98.45 211	98.53 307	96.08 247	98.30 137	99.11 221	98.10 152	98.85 177	98.95 177	79.38 378	99.87 99	98.68 81	99.91 61	99.40 172

casdiffmvs_mvg		99.12 49	99.16 43	98.99 135	99.43 133	97.73 178	98.00 174	99.62 45	99.22 61	99.55 53	99.22 110	98.93 26	99.75 227	98.66 82	99.81 98	99.50 122
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WB-MVS		98.52 138	98.55 112	98.43 214	99.65 66	95.59 258	98.52 111	98.77 280	99.65 14	99.52 60	99.00 163	94.34 264	99.93 39	98.65 83	98.83 309	99.76 37

IterMVS-SCA-FT		97.85 204	98.18 164	96.87 319	99.27 160	91.16 365	95.53 337	99.25 185	99.10 79	99.41 78	99.35 84	93.10 285	99.96 12	98.65 83	99.94 38	99.49 126

UniMVSNet (Re)		98.87 77	98.71 88	99.35 70	99.24 165	98.73 85	97.73 209	99.38 126	98.93 97	99.12 126	98.73 219	96.77 175	99.86 108	98.63 85	99.80 108	99.46 145

EI-MVSNet		98.40 149	98.51 117	98.04 247	99.10 200	94.73 288	97.20 260	98.87 260	98.97 93	99.06 134	99.02 151	96.00 210	99.80 184	98.58 86	99.82 94	99.60 73

IterMVS-LS		98.55 131	98.70 91	98.09 239	99.48 121	94.73 288	97.22 259	99.39 124	98.97 93	99.38 85	99.31 94	96.00 210	99.93 39	98.58 86	99.97 20	99.60 73
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_Test		98.18 175	98.36 143	97.67 272	98.48 311	94.73 288	98.18 148	99.02 239	97.69 179	98.04 260	99.11 134	97.22 149	99.56 308	98.57 88	98.90 307	98.71 306

UniMVSNet_NR-MVSNet		98.86 80	98.68 94	99.40 62	99.17 187	98.74 82	97.68 213	99.40 121	99.14 71	99.06 134	98.59 246	96.71 181	99.93 39	98.57 88	99.77 122	99.53 114

DU-MVS		98.82 83	98.63 101	99.39 63	99.16 189	98.74 82	97.54 232	99.25 185	98.84 105	99.06 134	98.76 216	96.76 177	99.93 39	98.57 88	99.77 122	99.50 122

UGNet		98.53 135	98.45 129	98.79 162	97.94 344	96.96 219	99.08 59	98.54 297	99.10 79	96.82 329	99.47 65	96.55 187	99.84 137	98.56 91	99.94 38	99.55 103
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
ECVR-MVS		96.42 288	96.61 273	95.85 342	99.38 139	88.18 379	99.22 42	86.00 397	99.08 84	99.36 90	99.57 42	88.47 329	99.82 164	98.52 92	99.95 30	99.54 107

iter_conf05		96.54 282	96.07 288	97.92 251	97.90 347	94.50 295	97.87 192	99.14 217	97.73 176	98.89 168	98.95 177	75.75 388	99.87 99	98.50 93	99.92 53	99.40 172

IterMVS		97.73 210	98.11 173	96.57 327	99.24 165	90.28 370	95.52 339	99.21 194	98.86 102	99.33 95	99.33 90	93.11 284	99.94 34	98.49 94	99.94 38	99.48 136
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
casdiffmvs		98.95 68	99.00 60	98.81 157	99.38 139	97.33 198	97.82 197	99.57 59	99.17 70	99.35 92	99.17 121	98.35 64	99.69 252	98.46 95	99.73 140	99.41 163
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSTER		96.86 270	96.55 277	97.79 260	97.91 346	94.21 303	97.56 230	98.87 260	97.49 199	99.06 134	99.05 146	80.72 370	99.80 184	98.44 96	99.82 94	99.37 184

ACMH	96.65 7	99.25 33	99.24 37	99.26 91	99.72 45	98.38 109	99.07 62	99.55 70	98.30 131	99.65 43	99.45 70	99.22 15	99.76 220	98.44 96	99.77 122	99.64 62
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet1		99.17 40	99.17 41	99.17 103	99.55 92	98.24 120	99.20 45	99.44 109	99.21 63	99.43 74	99.55 48	97.82 103	99.86 108	98.42 98	99.89 72	99.41 163

v148		98.45 144	98.60 108	98.00 249	99.44 128	94.98 281	97.44 242	99.06 228	98.30 131	99.32 101	98.97 170	96.65 183	99.62 288	98.37 99	99.85 80	99.39 175

GeoE		99.05 57	98.99 63	99.25 94	99.44 128	98.35 115	98.73 89	99.56 66	98.42 124	98.91 165	98.81 208	98.94 25	99.91 58	98.35 100	99.73 140	99.49 126

VDD-MVS		98.56 127	98.39 139	99.07 121	99.13 196	98.07 142	98.59 103	97.01 343	99.59 23	99.11 127	99.27 99	94.82 249	99.79 197	98.34 101	99.63 182	99.34 196

TranMVSNet+NR-MVSNet		99.17 40	99.07 56	99.46 56	99.37 145	98.87 73	98.39 131	99.42 118	99.42 41	99.36 90	99.06 139	98.38 60	99.95 23	98.34 101	99.90 68	99.57 90

pmmvs5		97.64 217	97.49 221	98.08 242	99.14 194	95.12 278	96.70 287	99.05 231	93.77 335	98.62 206	98.83 203	93.23 281	99.75 227	98.33 103	99.76 133	99.36 190

patch_mono-2		98.51 139	98.63 101	98.17 235	99.38 139	94.78 285	97.36 246	99.69 34	98.16 150	98.49 225	99.29 96	97.06 156	99.97 4	98.29 104	99.91 61	99.76 37

EU-MVSNet		97.66 216	98.50 119	95.13 356	99.63 73	85.84 386	98.35 135	98.21 311	98.23 138	99.54 54	99.46 66	95.02 243	99.68 261	98.24 105	99.87 76	99.87 16

TDRefinement		99.42 19	99.38 21	99.55 23	99.76 32	99.33 16	99.68 5	99.71 31	99.38 44	99.53 58	99.61 37	98.64 41	99.80 184	98.24 105	99.84 84	99.52 117

DELS-MVS		98.27 165	98.20 161	98.48 208	98.86 247	96.70 229	95.60 335	99.20 196	97.73 176	98.45 228	98.71 222	97.50 131	99.82 164	98.21 107	99.59 196	98.93 275
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
XXY-MVS		99.14 44	99.15 48	99.10 115	99.76 32	97.74 176	98.85 82	99.62 45	98.48 123	99.37 88	99.49 63	98.75 34	99.86 108	98.20 108	99.80 108	99.71 45

alignmvs		97.35 236	96.88 253	98.78 165	98.54 305	98.09 136	97.71 210	97.69 328	99.20 65	97.59 287	95.90 365	88.12 332	99.55 311	98.18 109	98.96 302	98.70 309

Syy-MVS		96.04 297	95.56 301	97.49 290	97.10 375	94.48 296	96.18 312	96.58 354	95.65 291	94.77 372	92.29 392	91.27 308	99.36 347	98.17 110	98.05 347	98.63 316

VNet		98.42 146	98.30 151	98.79 162	98.79 263	97.29 200	98.23 143	98.66 290	99.31 53	98.85 177	98.80 209	94.80 252	99.78 208	98.13 111	99.13 282	99.31 207

h-mvs33		97.77 208	97.33 232	99.10 115	99.21 172	97.84 165	98.35 135	98.57 296	99.11 72	98.58 214	99.02 151	88.65 327	99.96 12	98.11 112	96.34 374	99.49 126

hse-mvs2		97.46 228	97.07 243	98.64 180	98.73 268	97.33 198	97.45 241	97.64 331	99.11 72	98.58 214	97.98 301	88.65 327	99.79 197	98.11 112	97.39 358	98.81 292

VPNet		98.87 77	98.83 75	99.01 133	99.70 55	97.62 185	98.43 127	99.35 139	99.47 34	99.28 104	99.05 146	96.72 180	99.82 164	98.09 114	99.36 245	99.59 79

canonicalmvs		98.34 156	98.26 156	98.58 192	98.46 313	97.82 169	98.96 73	99.46 102	99.19 69	97.46 299	95.46 374	98.59 47	99.46 334	98.08 115	98.71 317	98.46 323

Baseline_NR-MVSNet		98.98 64	98.86 73	99.36 64	99.82 22	98.55 97	97.47 240	99.57 59	99.37 45	99.21 118	99.61 37	96.76 177	99.83 154	98.06 116	99.83 91	99.71 45

DeepC-MVS	97.60 4	98.97 65	98.93 66	99.10 115	99.35 150	97.98 152	98.01 173	99.46 102	97.56 192	99.54 54	99.50 59	98.97 23	99.84 137	98.06 116	99.92 53	99.49 126
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
xiu_mvs_v1_base_debu		97.86 199	98.17 165	96.92 316	98.98 224	93.91 316	96.45 296	99.17 208	97.85 169	98.41 232	97.14 344	98.47 53	99.92 49	98.02 118	99.05 288	96.92 373

xiu_mvs_v1_base		97.86 199	98.17 165	96.92 316	98.98 224	93.91 316	96.45 296	99.17 208	97.85 169	98.41 232	97.14 344	98.47 53	99.92 49	98.02 118	99.05 288	96.92 373

xiu_mvs_v1_base_debi		97.86 199	98.17 165	96.92 316	98.98 224	93.91 316	96.45 296	99.17 208	97.85 169	98.41 232	97.14 344	98.47 53	99.92 49	98.02 118	99.05 288	96.92 373

dcpmvs_2		98.78 89	99.11 50	97.78 261	99.56 88	93.67 325	99.06 63	99.86 13	99.50 30	99.66 40	99.26 101	97.21 150	99.99 2	98.00 121	99.91 61	99.68 53

NR-MVSNet		98.95 68	98.82 76	99.36 64	99.16 189	98.72 87	99.22 42	99.20 196	99.10 79	99.72 29	98.76 216	96.38 195	99.86 108	98.00 121	99.82 94	99.50 122

SDMVSNet		99.23 38	99.32 28	98.96 139	99.68 59	97.35 197	98.84 84	99.48 93	99.69 9	99.63 46	99.68 20	99.03 21	99.96 12	97.97 123	99.92 53	99.57 90

FMVSNet2		98.49 140	98.40 136	98.75 172	98.90 239	97.14 213	98.61 101	99.13 218	98.59 115	99.19 120	99.28 97	94.14 268	99.82 164	97.97 123	99.80 108	99.29 212

diffmvs		98.22 171	98.24 158	98.17 235	99.00 220	95.44 266	96.38 301	99.58 52	97.79 173	98.53 222	98.50 258	96.76 177	99.74 232	97.95 125	99.64 179	99.34 196
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Anonymous20240529		98.93 70	98.87 70	99.12 111	99.19 179	98.22 125	99.01 67	98.99 245	99.25 59	99.54 54	99.37 80	97.04 157	99.80 184	97.89 126	99.52 220	99.35 194

pmmvs-eth3d		98.47 142	98.34 146	98.86 151	99.30 156	97.76 174	97.16 263	99.28 176	95.54 294	99.42 77	99.19 114	97.27 145	99.63 286	97.89 126	99.97 20	99.20 229

Patchmatch-RL test		97.26 243	97.02 246	97.99 250	99.52 102	95.53 262	96.13 314	99.71 31	97.47 200	99.27 106	99.16 123	84.30 357	99.62 288	97.89 126	99.77 122	98.81 292

VDDNet		98.21 172	97.95 186	99.01 133	99.58 76	97.74 176	99.01 67	97.29 338	99.67 12	98.97 152	99.50 59	90.45 313	99.80 184	97.88 129	99.20 271	99.48 136

APDe-MVS		98.99 61	98.79 79	99.60 11	99.21 172	99.15 47	98.87 79	99.48 93	97.57 190	99.35 92	99.24 106	97.83 100	99.89 73	97.88 129	99.70 157	99.75 41
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CANet		97.87 198	97.76 200	98.19 234	97.75 352	95.51 263	96.76 283	99.05 231	97.74 175	96.93 318	98.21 284	95.59 227	99.89 73	97.86 131	99.93 42	99.19 234

testf1		99.25 33	99.16 43	99.51 43	99.89 6	99.63 3	98.71 92	99.69 34	98.90 99	99.43 74	99.35 84	98.86 28	99.67 264	97.81 132	99.81 98	99.24 222

APD_test2		99.25 33	99.16 43	99.51 43	99.89 6	99.63 3	98.71 92	99.69 34	98.90 99	99.43 74	99.35 84	98.86 28	99.67 264	97.81 132	99.81 98	99.24 222

PM-MVS		98.82 83	98.72 86	99.12 111	99.64 70	98.54 100	97.98 177	99.68 39	97.62 184	99.34 94	99.18 117	97.54 125	99.77 214	97.79 134	99.74 137	99.04 255

tttt0517		95.64 309	94.98 318	97.64 276	99.36 146	93.81 321	98.72 90	90.47 391	98.08 154	98.67 199	98.34 274	73.88 390	99.92 49	97.77 135	99.51 222	99.20 229

GBi-Net		98.65 115	98.47 126	99.17 103	98.90 239	98.24 120	99.20 45	99.44 109	98.59 115	98.95 155	99.55 48	94.14 268	99.86 108	97.77 135	99.69 160	99.41 163

test1		98.65 115	98.47 126	99.17 103	98.90 239	98.24 120	99.20 45	99.44 109	98.59 115	98.95 155	99.55 48	94.14 268	99.86 108	97.77 135	99.69 160	99.41 163

FMVSNet3		97.50 224	97.24 235	98.29 227	98.08 339	95.83 254	97.86 194	98.91 254	97.89 166	98.95 155	98.95 177	87.06 333	99.81 177	97.77 135	99.69 160	99.23 224

UnsupCasMVSNet_eth		97.89 195	97.60 215	98.75 172	99.31 153	97.17 210	97.62 222	99.35 139	98.72 108	98.76 192	98.68 228	92.57 296	99.74 232	97.76 139	95.60 382	99.34 196

test20.03		98.78 89	98.77 81	98.78 165	99.46 124	97.20 207	97.78 200	99.24 190	99.04 87	99.41 78	98.90 187	97.65 113	99.76 220	97.70 140	99.79 113	99.39 175

Gipuma		99.03 58	99.16 43	98.64 180	99.94 2	98.51 102	99.32 23	99.75 29	99.58 25	98.60 210	99.62 34	98.22 72	99.51 324	97.70 140	99.73 140	97.89 349
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PatchT		96.65 278	96.35 281	97.54 285	97.40 368	95.32 270	97.98 177	96.64 353	99.33 50	96.89 325	99.42 74	84.32 356	99.81 177	97.69 142	97.49 354	97.48 367

mvsany_test1		97.60 219	97.54 217	97.77 262	97.72 353	95.35 269	95.36 344	97.13 341	94.13 329	99.71 31	99.33 90	97.93 96	99.30 357	97.60 143	98.94 304	98.67 314

D2MVS		97.84 205	97.84 197	97.83 257	99.14 194	94.74 287	96.94 272	98.88 258	95.84 287	98.89 168	98.96 173	94.40 262	99.69 252	97.55 144	99.95 30	99.05 251

MSLP-MVS++		98.02 186	98.14 171	97.64 276	98.58 300	95.19 275	97.48 238	99.23 192	97.47 200	97.90 266	98.62 242	97.04 157	98.81 382	97.55 144	99.41 239	98.94 274

WR-MVS		98.40 149	98.19 163	99.03 131	99.00 220	97.65 182	96.85 278	98.94 247	98.57 118	98.89 168	98.50 258	95.60 226	99.85 120	97.54 146	99.85 80	99.59 79

HPM-MVS_fast		99.01 59	98.82 76	99.57 16	99.71 48	99.35 12	99.00 69	99.50 84	97.33 216	98.94 162	98.86 197	98.75 34	99.82 164	97.53 147	99.71 152	99.56 96

RPMNet		97.02 262	96.93 248	97.30 299	97.71 355	94.22 301	98.11 156	99.30 165	99.37 45	96.91 321	99.34 88	86.72 335	99.87 99	97.53 147	97.36 361	97.81 354

PMMVS2		98.07 184	98.08 177	98.04 247	99.41 136	94.59 294	94.59 366	99.40 121	97.50 197	98.82 184	98.83 203	96.83 170	99.84 137	97.50 149	99.81 98	99.71 45

LFMVS		97.20 249	96.72 264	98.64 180	98.72 270	96.95 220	98.93 75	94.14 378	99.74 6	98.78 187	99.01 160	84.45 354	99.73 237	97.44 150	99.27 260	99.25 219

ACMM	96.08 12	98.91 72	98.73 84	99.48 51	99.55 92	99.14 52	98.07 162	99.37 130	97.62 184	99.04 141	98.96 173	98.84 30	99.79 197	97.43 151	99.65 177	99.49 126
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		95.51 313	95.47 302	95.65 348	98.25 328	88.27 378	93.25 383	98.88 258	93.53 338	94.65 374	97.15 343	86.17 340	99.93 39	97.41 152	99.93 42	98.73 305

CR-MVSNet		96.28 292	95.95 290	97.28 300	97.71 355	94.22 301	98.11 156	98.92 252	92.31 354	96.91 321	99.37 80	85.44 348	99.81 177	97.39 153	97.36 361	97.81 354

Anonymous202405211		97.90 193	97.50 220	99.08 119	98.90 239	98.25 119	98.53 110	96.16 359	98.87 101	99.11 127	98.86 197	90.40 314	99.78 208	97.36 154	99.31 253	99.19 234

CANet_DTU		97.26 243	97.06 244	97.84 256	97.57 360	94.65 292	96.19 311	98.79 277	97.23 231	95.14 369	98.24 281	93.22 282	99.84 137	97.34 155	99.84 84	99.04 255

Anonymous20231206		98.21 172	98.21 160	98.20 233	99.51 104	95.43 267	98.13 153	99.32 152	96.16 276	98.93 163	98.82 206	96.00 210	99.83 154	97.32 156	99.73 140	99.36 190

MP-MVS-pluss		98.57 126	98.23 159	99.60 11	99.69 57	99.35 12	97.16 263	99.38 126	94.87 312	98.97 152	98.99 164	98.01 89	99.88 82	97.29 157	99.70 157	99.58 85
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FMVSNet5		96.01 298	95.20 314	98.41 216	97.53 363	96.10 242	98.74 86	99.50 84	97.22 234	98.03 261	99.04 148	69.80 392	99.88 82	97.27 158	99.71 152	99.25 219

our_test_3		97.39 234	97.73 204	96.34 331	98.70 277	89.78 372	94.61 365	98.97 246	96.50 263	99.04 141	98.85 200	95.98 214	99.84 137	97.26 159	99.67 171	99.41 163

sd_testset		99.28 29	99.31 30	99.19 102	99.68 59	98.06 145	99.41 13	99.30 165	99.69 9	99.63 46	99.68 20	99.25 14	99.96 12	97.25 160	99.92 53	99.57 90

jason		97.45 230	97.35 230	97.76 265	99.24 165	93.93 315	95.86 326	98.42 303	94.24 326	98.50 224	98.13 288	94.82 249	99.91 58	97.22 161	99.73 140	99.43 157
jason: jason.
miper_lstm_enhance		97.18 251	97.16 239	97.25 303	98.16 334	92.85 337	95.15 350	99.31 157	97.25 225	98.74 195	98.78 212	90.07 315	99.78 208	97.19 162	99.80 108	99.11 246

DP-MVS		98.93 70	98.81 78	99.28 86	99.21 172	98.45 106	98.46 124	99.33 150	99.63 17	99.48 66	99.15 127	97.23 148	99.75 227	97.17 163	99.66 176	99.63 65

MTAPA		98.88 76	98.64 100	99.61 9	99.67 63	99.36 11	98.43 127	99.20 196	98.83 106	98.89 168	98.90 187	96.98 163	99.92 49	97.16 164	99.70 157	99.56 96

TSAR-MVS + GP.		98.18 175	97.98 184	98.77 168	98.71 273	97.88 161	96.32 304	98.66 290	96.33 269	99.23 117	98.51 254	97.48 135	99.40 342	97.16 164	99.46 232	99.02 258

3Dnovator	98.27 2	98.81 85	98.73 84	99.05 128	98.76 264	97.81 171	99.25 40	99.30 165	98.57 118	98.55 219	99.33 90	97.95 95	99.90 63	97.16 164	99.67 171	99.44 153

MSC_two_6792asdad				99.32 80	98.43 316	98.37 111		98.86 265					99.89 73	97.14 167	99.60 192	99.71 45

No_MVS				99.32 80	98.43 316	98.37 111		98.86 265					99.89 73	97.14 167	99.60 192	99.71 45

ACMMP_NAP		98.75 94	98.48 124	99.57 16	99.58 76	99.29 19	97.82 197	99.25 185	96.94 246	98.78 187	99.12 133	98.02 88	99.84 137	97.13 169	99.67 171	99.59 79

PVSNet_Blended_VisFu		98.17 177	98.15 169	98.22 232	99.73 39	95.15 276	97.36 246	99.68 39	94.45 322	98.99 147	99.27 99	96.87 167	99.94 34	97.13 169	99.91 61	99.57 90

HyFIR lowres test		97.19 250	96.60 275	98.96 139	99.62 75	97.28 201	95.17 348	99.50 84	94.21 327	99.01 145	98.32 277	86.61 336	99.99 2	97.10 171	99.84 84	99.60 73

EGC-MVSNET		85.24 360	80.54 363	99.34 73	99.77 29	99.20 34	99.08 59	99.29 173	12.08 397	20.84 398	99.42 74	97.55 124	99.85 120	97.08 172	99.72 147	98.96 269

DVP-MVS++		98.90 74	98.70 91	99.51 43	98.43 316	99.15 47	99.43 11	99.32 152	98.17 147	99.26 110	99.02 151	98.18 76	99.88 82	97.07 173	99.45 234	99.49 126

test_0728_THIRD									98.17 147	99.08 132	99.02 151	97.89 97	99.88 82	97.07 173	99.71 152	99.70 50

eth_miper_zixun_eth		97.23 247	97.25 234	97.17 305	98.00 342	92.77 339	94.71 359	99.18 204	97.27 223	98.56 217	98.74 218	91.89 303	99.69 252	97.06 175	99.81 98	99.05 251

MDA-MVSNet_test_wron		97.60 219	97.66 210	97.41 296	99.04 215	93.09 331	95.27 345	98.42 303	97.26 224	98.88 172	98.95 177	95.43 233	99.73 237	97.02 176	98.72 315	99.41 163

cl____		97.02 262	96.83 257	97.58 280	97.82 350	94.04 309	94.66 362	99.16 211	97.04 241	98.63 204	98.71 222	88.68 326	99.69 252	97.00 177	99.81 98	99.00 262

DIV-MVS_self_test		97.02 262	96.84 256	97.58 280	97.82 350	94.03 310	94.66 362	99.16 211	97.04 241	98.63 204	98.71 222	88.69 324	99.69 252	97.00 177	99.81 98	99.01 259

DVP-MVS		98.77 92	98.52 116	99.52 39	99.50 107	99.21 28	98.02 170	98.84 269	97.97 158	99.08 132	99.02 151	97.61 119	99.88 82	96.99 179	99.63 182	99.48 136
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.60 11	99.50 107	99.23 26	98.02 170	99.32 152					99.88 82	96.99 179	99.63 182	99.68 53

YYNet1		97.60 219	97.67 207	97.39 297	99.04 215	93.04 335	95.27 345	98.38 306	97.25 225	98.92 164	98.95 177	95.48 232	99.73 237	96.99 179	98.74 313	99.41 163

pmmvs4		97.58 222	97.28 233	98.51 205	98.84 251	96.93 222	95.40 343	98.52 299	93.60 337	98.61 208	98.65 235	95.10 241	99.60 295	96.97 182	99.79 113	98.99 263

TAMVS		98.24 170	98.05 179	98.80 159	99.07 207	97.18 209	97.88 189	98.81 274	96.66 259	99.17 125	99.21 111	94.81 251	99.77 214	96.96 183	99.88 73	99.44 153

c3_l		97.36 235	97.37 228	97.31 298	98.09 338	93.25 330	95.01 353	99.16 211	97.05 240	98.77 190	98.72 221	92.88 290	99.64 283	96.93 184	99.76 133	99.05 251

SED-MVS		98.91 72	98.72 86	99.49 48	99.49 114	99.17 39	98.10 158	99.31 157	98.03 155	99.66 40	99.02 151	98.36 61	99.88 82	96.91 185	99.62 185	99.41 163

test_241102_TWO								99.30 165	98.03 155	99.26 110	99.02 151	97.51 130	99.88 82	96.91 185	99.60 192	99.66 57

ET-MVSNet_ETH3D		94.30 330	93.21 340	97.58 280	98.14 335	94.47 297	94.78 358	93.24 382	94.72 314	89.56 392	95.87 366	78.57 383	99.81 177	96.91 185	97.11 366	98.46 323

N_pmnet		97.63 218	97.17 238	98.99 135	99.27 160	97.86 163	95.98 317	93.41 380	95.25 303	99.47 68	98.90 187	95.63 225	99.85 120	96.91 185	99.73 140	99.27 215

1112_ss		97.29 242	96.86 254	98.58 192	99.34 152	96.32 238	96.75 284	99.58 52	93.14 343	96.89 325	97.48 330	92.11 301	99.86 108	96.91 185	99.54 213	99.57 90

thisisatest0530		95.27 316	94.45 325	97.74 268	99.19 179	94.37 299	97.86 194	90.20 392	97.17 235	98.22 243	97.65 320	73.53 391	99.90 63	96.90 190	99.35 247	98.95 270

Fast-Effi-MVS+-dtu		98.27 165	98.09 174	98.81 157	98.43 316	98.11 133	97.61 224	99.50 84	98.64 109	97.39 304	97.52 328	98.12 83	99.95 23	96.90 190	98.71 317	98.38 330

TSAR-MVS + MP.		98.63 119	98.49 123	99.06 127	99.64 70	97.90 160	98.51 116	98.94 247	96.96 244	99.24 115	98.89 193	97.83 100	99.81 177	96.88 192	99.49 230	99.48 136
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MVS_111021_HR		98.25 169	98.08 177	98.75 172	99.09 203	97.46 191	95.97 318	99.27 179	97.60 188	97.99 262	98.25 280	98.15 82	99.38 346	96.87 193	99.57 205	99.42 160

EPP-MVSNet		98.30 161	98.04 180	99.07 121	99.56 88	97.83 166	99.29 33	98.07 319	99.03 88	98.59 212	99.13 131	92.16 300	99.90 63	96.87 193	99.68 165	99.49 126

ZNCC-MVS		98.68 110	98.40 136	99.54 27	99.57 80	99.21 28	98.46 124	99.29 173	97.28 222	98.11 253	98.39 267	98.00 90	99.87 99	96.86 195	99.64 179	99.55 103

MS-PatchMatch		97.68 214	97.75 201	97.45 293	98.23 331	93.78 322	97.29 252	98.84 269	96.10 278	98.64 203	98.65 235	96.04 207	99.36 347	96.84 196	99.14 280	99.20 229

3Dnovator+	97.89 3	98.69 105	98.51 117	99.24 96	98.81 259	98.40 107	99.02 66	99.19 200	98.99 91	98.07 256	99.28 97	97.11 155	99.84 137	96.84 196	99.32 251	99.47 143

miper_ehance_all_eth		97.06 259	97.03 245	97.16 307	97.83 349	93.06 332	94.66 362	99.09 225	95.99 283	98.69 197	98.45 263	92.73 294	99.61 294	96.79 198	99.03 292	98.82 288

XVS		98.72 97	98.45 129	99.53 34	99.46 124	99.21 28	98.65 96	99.34 145	98.62 113	97.54 292	98.63 240	97.50 131	99.83 154	96.79 198	99.53 217	99.56 96

X-MVStestdata		94.32 328	92.59 346	99.53 34	99.46 124	99.21 28	98.65 96	99.34 145	98.62 113	97.54 292	45.85 395	97.50 131	99.83 154	96.79 198	99.53 217	99.56 96

lupinMVS		97.06 259	96.86 254	97.65 274	98.88 245	93.89 319	95.48 340	97.97 321	93.53 338	98.16 247	97.58 324	93.81 276	99.91 58	96.77 201	99.57 205	99.17 240

IU-MVS					99.49 114	99.15 47		98.87 260	92.97 345	99.41 78				96.76 202	99.62 185	99.66 57

CHOSEN 1792x2688		97.49 226	97.14 242	98.54 202	99.68 59	96.09 245	96.50 294	99.62 45	91.58 360	98.84 180	98.97 170	92.36 297	99.88 82	96.76 202	99.95 30	99.67 56

ppachtmachnet_test		97.50 224	97.74 202	96.78 325	98.70 277	91.23 364	94.55 367	99.05 231	96.36 268	99.21 118	98.79 211	96.39 193	99.78 208	96.74 204	99.82 94	99.34 196

DeepPCF-MVS	96.93 5	98.32 158	98.01 182	99.23 98	98.39 321	98.97 66	95.03 352	99.18 204	96.88 249	99.33 95	98.78 212	98.16 80	99.28 361	96.74 204	99.62 185	99.44 153

EIA-MVS		98.00 188	97.74 202	98.80 159	98.72 270	98.09 136	98.05 165	99.60 49	97.39 211	96.63 335	95.55 370	97.68 110	99.80 184	96.73 206	99.27 260	98.52 321

CDS-MVSNet		97.69 213	97.35 230	98.69 177	98.73 268	97.02 216	96.92 276	98.75 284	95.89 286	98.59 212	98.67 230	92.08 302	99.74 232	96.72 207	99.81 98	99.32 203
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CSCG		98.68 110	98.50 119	99.20 100	99.45 127	98.63 89	98.56 106	99.57 59	97.87 167	98.85 177	98.04 298	97.66 112	99.84 137	96.72 207	99.81 98	99.13 244

ACMH+	96.62 9	99.08 55	99.00 60	99.33 78	99.71 48	98.83 76	98.60 102	99.58 52	99.11 72	99.53 58	99.18 117	98.81 32	99.67 264	96.71 209	99.77 122	99.50 122

MVS_111021_LR		98.30 161	98.12 172	98.83 154	99.16 189	98.03 147	96.09 315	99.30 165	97.58 189	98.10 254	98.24 281	98.25 67	99.34 351	96.69 210	99.65 177	99.12 245

OPM-MVS		98.56 127	98.32 150	99.25 94	99.41 136	98.73 85	97.13 265	99.18 204	97.10 239	98.75 193	98.92 183	98.18 76	99.65 280	96.68 211	99.56 208	99.37 184
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Effi-MVS+-dtu		98.26 167	97.90 192	99.35 70	98.02 341	99.49 5	98.02 170	99.16 211	98.29 134	97.64 283	97.99 300	96.44 192	99.95 23	96.66 212	98.93 305	98.60 318

Effi-MVS+		98.02 186	97.82 198	98.62 185	98.53 307	97.19 208	97.33 248	99.68 39	97.30 220	96.68 333	97.46 332	98.56 50	99.80 184	96.63 213	98.20 335	98.86 285

MDA-MVSNet-bldmvs		97.94 192	97.91 191	98.06 244	99.44 128	94.96 282	96.63 290	99.15 216	98.35 126	98.83 181	99.11 134	94.31 265	99.85 120	96.60 214	98.72 315	99.37 184

Test_1112_low_res		96.99 266	96.55 277	98.31 225	99.35 150	95.47 265	95.84 329	99.53 78	91.51 362	96.80 330	98.48 261	91.36 307	99.83 154	96.58 215	99.53 217	99.62 66

LS3D		98.63 119	98.38 141	99.36 64	97.25 372	99.38 8	99.12 57	99.32 152	99.21 63	98.44 229	98.88 194	97.31 141	99.80 184	96.58 215	99.34 249	98.92 276

APD_test1		98.83 82	98.66 97	99.34 73	99.78 26	99.47 6	98.42 129	99.45 105	98.28 136	98.98 148	99.19 114	97.76 106	99.58 303	96.57 217	99.55 211	98.97 267

HFP-MVS		98.71 98	98.44 131	99.51 43	99.49 114	99.16 43	98.52 111	99.31 157	97.47 200	98.58 214	98.50 258	97.97 94	99.85 120	96.57 217	99.59 196	99.53 114

ACMMPR		98.70 102	98.42 134	99.54 27	99.52 102	99.14 52	98.52 111	99.31 157	97.47 200	98.56 217	98.54 250	97.75 107	99.88 82	96.57 217	99.59 196	99.58 85

sss		97.21 248	96.93 248	98.06 244	98.83 253	95.22 274	96.75 284	98.48 301	94.49 318	97.27 307	97.90 307	92.77 293	99.80 184	96.57 217	99.32 251	99.16 243

SR-MVS-dyc-post		98.81 85	98.55 112	99.57 16	99.20 176	99.38 8	98.48 122	99.30 165	98.64 109	98.95 155	98.96 173	97.49 134	99.86 108	96.56 221	99.39 241	99.45 149

RE-MVS-def			98.58 110		99.20 176	99.38 8	98.48 122	99.30 165	98.64 109	98.95 155	98.96 173	97.75 107		96.56 221	99.39 241	99.45 149

SD-MVS		98.40 149	98.68 94	97.54 285	98.96 227	97.99 149	97.88 189	99.36 134	98.20 144	99.63 46	99.04 148	98.76 33	95.33 396	96.56 221	99.74 137	99.31 207
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
ambc				98.24 231	98.82 256	95.97 250	98.62 100	99.00 244		99.27 106	99.21 111	96.99 162	99.50 325	96.55 224	99.50 229	99.26 218

APD-MVS_3200maxsize		98.84 81	98.61 107	99.53 34	99.19 179	99.27 22	98.49 119	99.33 150	98.64 109	99.03 144	98.98 168	97.89 97	99.85 120	96.54 225	99.42 238	99.46 145

CP-MVS		98.70 102	98.42 134	99.52 39	99.36 146	99.12 57	98.72 90	99.36 134	97.54 195	98.30 239	98.40 266	97.86 99	99.89 73	96.53 226	99.72 147	99.56 96

MVP-Stereo		98.08 183	97.92 190	98.57 194	98.96 227	96.79 225	97.90 186	99.18 204	96.41 267	98.46 227	98.95 177	95.93 217	99.60 295	96.51 227	98.98 300	99.31 207
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
testgi		98.32 158	98.39 139	98.13 238	99.57 80	95.54 261	97.78 200	99.49 91	97.37 213	99.19 120	97.65 320	98.96 24	99.49 326	96.50 228	98.99 298	99.34 196

HPM-MVS		98.79 87	98.53 115	99.59 15	99.65 66	99.29 19	99.16 51	99.43 115	96.74 255	98.61 208	98.38 269	98.62 44	99.87 99	96.47 229	99.67 171	99.59 79
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
region2R		98.69 105	98.40 136	99.54 27	99.53 100	99.17 39	98.52 111	99.31 157	97.46 205	98.44 229	98.51 254	97.83 100	99.88 82	96.46 230	99.58 201	99.58 85

SMA-MVS		98.40 149	98.03 181	99.51 43	99.16 189	99.21 28	98.05 165	99.22 193	94.16 328	98.98 148	99.10 136	97.52 129	99.79 197	96.45 231	99.64 179	99.53 114
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
CNVR-MVS		98.17 177	97.87 195	99.07 121	98.67 285	98.24 120	97.01 268	98.93 249	97.25 225	97.62 284	98.34 274	97.27 145	99.57 305	96.42 232	99.33 250	99.39 175

CL-MVSNet_self_test		97.44 231	97.22 236	98.08 242	98.57 302	95.78 256	94.30 372	98.79 277	96.58 262	98.60 210	98.19 286	94.74 256	99.64 283	96.41 233	98.84 308	98.82 288

cl22		95.79 305	95.39 308	96.98 313	96.77 382	92.79 338	94.40 370	98.53 298	94.59 317	97.89 267	98.17 287	82.82 366	99.24 363	96.37 234	99.03 292	98.92 276

PS-MVSNAJ		97.08 258	97.39 226	96.16 339	98.56 303	92.46 343	95.24 347	98.85 268	97.25 225	97.49 297	95.99 362	98.07 84	99.90 63	96.37 234	98.67 321	96.12 385

CVMVSNet		96.25 293	97.21 237	93.38 373	99.10 200	80.56 400	97.20 260	98.19 314	96.94 246	99.00 146	99.02 151	89.50 320	99.80 184	96.36 236	99.59 196	99.78 31

xiu_mvs_v2_base		97.16 253	97.49 221	96.17 337	98.54 305	92.46 343	95.45 341	98.84 269	97.25 225	97.48 298	96.49 353	98.31 66	99.90 63	96.34 237	98.68 320	96.15 384

AUN-MVS		96.24 294	95.45 304	98.60 190	98.70 277	97.22 205	97.38 244	97.65 329	95.95 284	95.53 364	97.96 305	82.11 369	99.79 197	96.31 238	97.44 356	98.80 297

miper_enhance_ethall		96.01 298	95.74 293	96.81 323	96.41 387	92.27 349	93.69 381	98.89 257	91.14 367	98.30 239	97.35 339	90.58 312	99.58 303	96.31 238	99.03 292	98.60 318

ACMMP		98.75 94	98.50 119	99.52 39	99.56 88	99.16 43	98.87 79	99.37 130	97.16 236	98.82 184	99.01 160	97.71 109	99.87 99	96.29 240	99.69 160	99.54 107
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
ETV-MVS		98.03 185	97.86 196	98.56 198	98.69 282	98.07 142	97.51 236	99.50 84	98.10 152	97.50 296	95.51 371	98.41 58	99.88 82	96.27 241	99.24 265	97.71 361

XVG-OURS-SEG-HR		98.49 140	98.28 153	99.14 109	99.49 114	98.83 76	96.54 292	99.48 93	97.32 218	99.11 127	98.61 244	99.33 13	99.30 357	96.23 242	98.38 329	99.28 214

GA-MVS		95.86 303	95.32 311	97.49 290	98.60 295	94.15 306	93.83 379	97.93 322	95.49 296	96.68 333	97.42 334	83.21 362	99.30 357	96.22 243	98.55 327	99.01 259

mPP-MVS		98.64 117	98.34 146	99.54 27	99.54 97	99.17 39	98.63 98	99.24 190	97.47 200	98.09 255	98.68 228	97.62 118	99.89 73	96.22 243	99.62 185	99.57 90

Fast-Effi-MVS+		97.67 215	97.38 227	98.57 194	98.71 273	97.43 194	97.23 256	99.45 105	94.82 313	96.13 348	96.51 352	98.52 52	99.91 58	96.19 245	98.83 309	98.37 332

pmmvs3		95.03 320	94.40 326	96.93 315	97.70 357	92.53 342	95.08 351	97.71 327	88.57 380	97.71 279	98.08 295	79.39 377	99.82 164	96.19 245	99.11 286	98.43 328

MCST-MVS		98.00 188	97.63 213	99.10 115	99.24 165	98.17 128	96.89 277	98.73 287	95.66 290	97.92 264	97.70 318	97.17 151	99.66 275	96.18 247	99.23 267	99.47 143

SteuartSystems-ACMMP		98.79 87	98.54 114	99.54 27	99.73 39	99.16 43	98.23 143	99.31 157	97.92 163	98.90 166	98.90 187	98.00 90	99.88 82	96.15 248	99.72 147	99.58 85
Skip Steuart: Steuart Systems R&D Blog.
SR-MVS		98.71 98	98.43 132	99.57 16	99.18 186	99.35 12	98.36 134	99.29 173	98.29 134	98.88 172	98.85 200	97.53 127	99.87 99	96.14 249	99.31 253	99.48 136

MSP-MVS		98.40 149	98.00 183	99.61 9	99.57 80	99.25 24	98.57 105	99.35 139	97.55 194	99.31 103	97.71 316	94.61 257	99.88 82	96.14 249	99.19 274	99.70 50
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
FA-MVS(test-final)		96.99 266	96.82 258	97.50 289	98.70 277	94.78 285	99.34 20	96.99 344	95.07 306	98.48 226	99.33 90	88.41 330	99.65 280	96.13 251	98.92 306	98.07 343

DeepC-MVS_fast	96.85 6	98.30 161	98.15 169	98.75 172	98.61 293	97.23 203	97.76 205	99.09 225	97.31 219	98.75 193	98.66 233	97.56 123	99.64 283	96.10 252	99.55 211	99.39 175
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
GST-MVS		98.61 122	98.30 151	99.52 39	99.51 104	99.20 34	98.26 141	99.25 185	97.44 208	98.67 199	98.39 267	97.68 110	99.85 120	96.00 253	99.51 222	99.52 117

EPNet		96.14 295	95.44 305	98.25 229	90.76 399	95.50 264	97.92 183	94.65 370	98.97 93	92.98 386	98.85 200	89.12 322	99.87 99	95.99 254	99.68 165	99.39 175
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
COLMAP_ROB	96.50 10	98.99 61	98.85 74	99.41 60	99.58 76	99.10 60	98.74 86	99.56 66	99.09 82	99.33 95	99.19 114	98.40 59	99.72 244	95.98 255	99.76 133	99.42 160
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Patchmtry		97.35 236	96.97 247	98.50 207	97.31 371	96.47 234	98.18 148	98.92 252	98.95 96	98.78 187	99.37 80	85.44 348	99.85 120	95.96 256	99.83 91	99.17 240

tfpnnormal		98.90 74	98.90 69	98.91 146	99.67 63	97.82 169	99.00 69	99.44 109	99.45 36	99.51 64	99.24 106	98.20 75	99.86 108	95.92 257	99.69 160	99.04 255

XVG-ACMP-BASELINE		98.56 127	98.34 146	99.22 99	99.54 97	98.59 94	97.71 210	99.46 102	97.25 225	98.98 148	98.99 164	97.54 125	99.84 137	95.88 258	99.74 137	99.23 224

tpm		94.67 324	94.34 328	95.66 347	97.68 359	88.42 376	97.88 189	94.90 369	94.46 320	96.03 353	98.56 249	78.66 381	99.79 197	95.88 258	95.01 385	98.78 299

ab-mvs		98.41 147	98.36 143	98.59 191	99.19 179	97.23 203	99.32 23	98.81 274	97.66 181	98.62 206	99.40 79	96.82 171	99.80 184	95.88 258	99.51 222	98.75 303

test-LLR		93.90 337	93.85 331	94.04 364	96.53 384	84.62 391	94.05 376	92.39 384	96.17 274	94.12 379	95.07 376	82.30 367	99.67 264	95.87 261	98.18 336	97.82 352

test-mter		92.33 354	91.76 357	94.04 364	96.53 384	84.62 391	94.05 376	92.39 384	94.00 333	94.12 379	95.07 376	65.63 400	99.67 264	95.87 261	98.18 336	97.82 352

PGM-MVS		98.66 114	98.37 142	99.55 23	99.53 100	99.18 38	98.23 143	99.49 91	97.01 243	98.69 197	98.88 194	98.00 90	99.89 73	95.87 261	99.59 196	99.58 85

USDC		97.41 233	97.40 225	97.44 294	98.94 229	93.67 325	95.17 348	99.53 78	94.03 332	98.97 152	99.10 136	95.29 235	99.34 351	95.84 264	99.73 140	99.30 210

HPM-MVS++		98.10 179	97.64 212	99.48 51	99.09 203	99.13 55	97.52 234	98.75 284	97.46 205	96.90 324	97.83 311	96.01 209	99.84 137	95.82 265	99.35 247	99.46 145

TESTMET0.1,1		92.19 356	91.77 356	93.46 371	96.48 386	82.80 396	94.05 376	91.52 388	94.45 322	94.00 382	94.88 382	66.65 397	99.56 308	95.78 266	98.11 342	98.02 345

DSMNet-mixed		97.42 232	97.60 215	96.87 319	99.15 193	91.46 356	98.54 109	99.12 219	92.87 348	97.58 288	99.63 33	96.21 201	99.90 63	95.74 267	99.54 213	99.27 215

XVG-OURS		98.53 135	98.34 146	99.11 113	99.50 107	98.82 78	95.97 318	99.50 84	97.30 220	99.05 139	98.98 168	99.35 12	99.32 354	95.72 268	99.68 165	99.18 236

RPSCF		98.62 121	98.36 143	99.42 58	99.65 66	99.42 7	98.55 107	99.57 59	97.72 178	98.90 166	99.26 101	96.12 204	99.52 320	95.72 268	99.71 152	99.32 203

PHI-MVS		98.29 164	97.95 186	99.34 73	98.44 315	99.16 43	98.12 155	99.38 126	96.01 282	98.06 257	98.43 264	97.80 104	99.67 264	95.69 270	99.58 201	99.20 229

SF-MVS		98.53 135	98.27 155	99.32 80	99.31 153	98.75 81	98.19 147	99.41 119	96.77 254	98.83 181	98.90 187	97.80 104	99.82 164	95.68 271	99.52 220	99.38 182

test_0402		98.76 93	98.71 88	98.93 143	99.56 88	98.14 131	98.45 126	99.34 145	99.28 57	98.95 155	98.91 184	98.34 65	99.79 197	95.63 272	99.91 61	98.86 285

tpmrst		95.07 319	95.46 303	93.91 366	97.11 374	84.36 393	97.62 222	96.96 346	94.98 308	96.35 346	98.80 209	85.46 347	99.59 299	95.60 273	96.23 376	97.79 357

PMMVS		96.51 283	95.98 289	98.09 239	97.53 363	95.84 253	94.92 355	98.84 269	91.58 360	96.05 352	95.58 369	95.68 224	99.66 275	95.59 274	98.09 343	98.76 302

LPG-MVS_test		98.71 98	98.46 128	99.47 54	99.57 80	98.97 66	98.23 143	99.48 93	96.60 260	99.10 130	99.06 139	98.71 37	99.83 154	95.58 275	99.78 118	99.62 66

LGP-MVS_train				99.47 54	99.57 80	98.97 66		99.48 93	96.60 260	99.10 130	99.06 139	98.71 37	99.83 154	95.58 275	99.78 118	99.62 66

IS-MVSNet		98.19 174	97.90 192	99.08 119	99.57 80	97.97 153	99.31 27	98.32 307	99.01 90	98.98 148	99.03 150	91.59 305	99.79 197	95.49 277	99.80 108	99.48 136

baseline1		95.96 301	95.44 305	97.52 287	98.51 310	93.99 313	98.39 131	96.09 361	98.21 140	98.40 236	97.76 314	86.88 334	99.63 286	95.42 278	89.27 394	98.95 270

DPE-MVS		98.59 125	98.26 156	99.57 16	99.27 160	99.15 47	97.01 268	99.39 124	97.67 180	99.44 73	98.99 164	97.53 127	99.89 73	95.40 279	99.68 165	99.66 57
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
NCCC		97.86 199	97.47 224	99.05 128	98.61 293	98.07 142	96.98 270	98.90 255	97.63 183	97.04 315	97.93 306	95.99 213	99.66 275	95.31 280	98.82 311	99.43 157

testing3		93.51 342	92.09 350	97.75 266	98.60 295	94.40 298	97.32 249	95.26 368	97.56 192	96.79 331	95.50 372	53.57 402	99.77 214	95.26 281	98.97 301	99.08 247

PC_three_1452									93.27 341	99.40 81	98.54 250	98.22 72	97.00 392	95.17 282	99.45 234	99.49 126

Patchmatch-test		96.55 281	96.34 282	97.17 305	98.35 322	93.06 332	98.40 130	97.79 324	97.33 216	98.41 232	98.67 230	83.68 361	99.69 252	95.16 283	99.31 253	98.77 300

EPMVS		93.72 340	93.27 339	95.09 358	96.04 391	87.76 380	98.13 153	85.01 398	94.69 315	96.92 319	98.64 238	78.47 385	99.31 355	95.04 284	96.46 373	98.20 336

UnsupCasMVSNet_bld		97.30 240	96.92 250	98.45 211	99.28 158	96.78 228	96.20 310	99.27 179	95.42 298	98.28 241	98.30 278	93.16 283	99.71 245	94.99 285	97.37 359	98.87 284

PatchmatchNet		95.58 310	95.67 297	95.30 355	97.34 370	87.32 382	97.65 219	96.65 352	95.30 302	97.07 313	98.69 226	84.77 351	99.75 227	94.97 286	98.64 322	98.83 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPNet_dtu		94.93 322	94.78 323	95.38 354	93.58 396	87.68 381	96.78 281	95.69 366	97.35 215	89.14 393	98.09 294	88.15 331	99.49 326	94.95 287	99.30 256	98.98 264
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_yl		96.69 275	96.29 284	97.90 252	98.28 326	95.24 272	97.29 252	97.36 334	98.21 140	98.17 245	97.86 308	86.27 338	99.55 311	94.87 288	98.32 330	98.89 280

DCV-MVSNet		96.69 275	96.29 284	97.90 252	98.28 326	95.24 272	97.29 252	97.36 334	98.21 140	98.17 245	97.86 308	86.27 338	99.55 311	94.87 288	98.32 330	98.89 280

ACMP	95.32 15	98.41 147	98.09 174	99.36 64	99.51 104	98.79 80	97.68 213	99.38 126	95.76 289	98.81 186	98.82 206	98.36 61	99.82 164	94.75 290	99.77 122	99.48 136
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PVSNet_BlendedMVS		97.55 223	97.53 218	97.60 278	98.92 235	93.77 323	96.64 289	99.43 115	94.49 318	97.62 284	99.18 117	96.82 171	99.67 264	94.73 291	99.93 42	99.36 190

PVSNet_Blended		96.88 269	96.68 267	97.47 292	98.92 235	93.77 323	94.71 359	99.43 115	90.98 368	97.62 284	97.36 338	96.82 171	99.67 264	94.73 291	99.56 208	98.98 264

MP-MVS		98.46 143	98.09 174	99.54 27	99.57 80	99.22 27	98.50 118	99.19 200	97.61 187	97.58 288	98.66 233	97.40 138	99.88 82	94.72 293	99.60 192	99.54 107
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
OPU-MVS				98.82 155	98.59 298	98.30 116	98.10 158				98.52 253	98.18 76	98.75 383	94.62 294	99.48 231	99.41 163

LF4IMVS		97.90 193	97.69 206	98.52 204	99.17 187	97.66 181	97.19 262	99.47 100	96.31 271	97.85 271	98.20 285	96.71 181	99.52 320	94.62 294	99.72 147	98.38 330

CostFormer		93.97 336	93.78 333	94.51 361	97.53 363	85.83 387	97.98 177	95.96 363	89.29 378	94.99 371	98.63 240	78.63 382	99.62 288	94.54 296	96.50 372	98.09 342

thisisatest0515		94.12 334	93.16 341	96.97 314	98.60 295	92.90 336	93.77 380	90.61 390	94.10 330	96.91 321	95.87 366	74.99 389	99.80 184	94.52 297	99.12 285	98.20 336

旧先验2							95.76 330		88.56 381	97.52 294			99.66 275	94.48 298

CLD-MVS		97.49 226	97.16 239	98.48 208	99.07 207	97.03 215	94.71 359	99.21 194	94.46 320	98.06 257	97.16 342	97.57 122	99.48 329	94.46 299	99.78 118	98.95 270
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
AllTest		98.44 145	98.20 161	99.16 106	99.50 107	98.55 97	98.25 142	99.58 52	96.80 251	98.88 172	99.06 139	97.65 113	99.57 305	94.45 300	99.61 190	99.37 184

TestCases				99.16 106	99.50 107	98.55 97		99.58 52	96.80 251	98.88 172	99.06 139	97.65 113	99.57 305	94.45 300	99.61 190	99.37 184

HQP_MVS		97.99 191	97.67 207	98.93 143	99.19 179	97.65 182	97.77 202	99.27 179	98.20 144	97.79 275	97.98 301	94.90 245	99.70 248	94.42 302	99.51 222	99.45 149

plane_prior5								99.27 179					99.70 248	94.42 302	99.51 222	99.45 149

JIA-IIPM		95.52 312	95.03 317	97.00 311	96.85 380	94.03 310	96.93 274	95.82 364	99.20 65	94.63 375	99.71 17	83.09 363	99.60 295	94.42 302	94.64 386	97.36 370

cascas		94.79 323	94.33 329	96.15 340	96.02 392	92.36 347	92.34 388	99.26 184	85.34 387	95.08 370	94.96 381	92.96 289	98.53 385	94.41 305	98.59 325	97.56 366

TinyColmap		97.89 195	97.98 184	97.60 278	98.86 247	94.35 300	96.21 309	99.44 109	97.45 207	99.06 134	98.88 194	97.99 93	99.28 361	94.38 306	99.58 201	99.18 236

9.14			97.78 199		99.07 207		97.53 233	99.32 152	95.53 295	98.54 221	98.70 225	97.58 121	99.76 220	94.32 307	99.46 232

test_post1							97.59 227				20.48 399	83.07 364	99.66 275	94.16 308

SCA		96.41 289	96.66 270	95.67 346	98.24 329	88.35 377	95.85 328	96.88 350	96.11 277	97.67 282	98.67 230	93.10 285	99.85 120	94.16 308	99.22 268	98.81 292

test_prior2							95.74 331		96.48 265	96.11 349	97.63 322	95.92 218		94.16 308	99.20 271

tpmvs		95.02 321	95.25 312	94.33 362	96.39 388	85.87 385	98.08 160	96.83 351	95.46 297	95.51 365	98.69 226	85.91 343	99.53 316	94.16 308	96.23 376	97.58 365

LCM-MVSNet-Re		98.64 117	98.48 124	99.11 113	98.85 250	98.51 102	98.49 119	99.83 20	98.37 125	99.69 35	99.46 66	98.21 74	99.92 49	94.13 312	99.30 256	98.91 279

MSDG		97.71 212	97.52 219	98.28 228	98.91 238	96.82 224	94.42 369	99.37 130	97.65 182	98.37 237	98.29 279	97.40 138	99.33 353	94.09 313	99.22 268	98.68 313

MVS-HIRNet		94.32 328	95.62 298	90.42 377	98.46 313	75.36 401	96.29 305	89.13 394	95.25 303	95.38 366	99.75 11	92.88 290	99.19 367	94.07 314	99.39 241	96.72 378

DP-MVS Recon		97.33 238	96.92 250	98.57 194	99.09 203	97.99 149	96.79 280	99.35 139	93.18 342	97.71 279	98.07 296	95.00 244	99.31 355	93.97 315	99.13 282	98.42 329

new_pmnet		96.99 266	96.76 262	97.67 272	98.72 270	94.89 283	95.95 322	98.20 312	92.62 351	98.55 219	98.54 250	94.88 248	99.52 320	93.96 316	99.44 237	98.59 320

MDTV_nov1_ep13			95.22 313		97.06 377	83.20 395	97.74 207	96.16 359	94.37 324	96.99 317	98.83 203	83.95 359	99.53 316	93.90 317	97.95 350

WTY-MVS		96.67 277	96.27 286	97.87 255	98.81 259	94.61 293	96.77 282	97.92 323	94.94 310	97.12 310	97.74 315	91.11 309	99.82 164	93.89 318	98.15 340	99.18 236

Vis-MVSNet (Re-imp)		97.46 228	97.16 239	98.34 222	99.55 92	96.10 242	98.94 74	98.44 302	98.32 130	98.16 247	98.62 242	88.76 323	99.73 237	93.88 319	99.79 113	99.18 236

ITE_SJBPF				98.87 150	99.22 170	98.48 104		99.35 139	97.50 197	98.28 241	98.60 245	97.64 116	99.35 350	93.86 320	99.27 260	98.79 298

CPTT-MVS		97.84 205	97.36 229	99.27 89	99.31 153	98.46 105	98.29 138	99.27 179	94.90 311	97.83 272	98.37 270	94.90 245	99.84 137	93.85 321	99.54 213	99.51 119

APD-MVS		98.10 179	97.67 207	99.42 58	99.11 198	98.93 71	97.76 205	99.28 176	94.97 309	98.72 196	98.77 214	97.04 157	99.85 120	93.79 322	99.54 213	99.49 126
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
train_agg		97.10 255	96.45 280	99.07 121	98.71 273	98.08 140	95.96 320	99.03 236	91.64 358	95.85 354	97.53 326	96.47 190	99.76 220	93.67 323	99.16 277	99.36 190

PVSNet	93.40 17	95.67 307	95.70 295	95.57 349	98.83 253	88.57 375	92.50 386	97.72 326	92.69 350	96.49 344	96.44 356	93.72 279	99.43 338	93.61 324	99.28 259	98.71 306

test0.0.03 1		94.51 325	93.69 334	96.99 312	96.05 390	93.61 327	94.97 354	93.49 379	96.17 274	97.57 290	94.88 382	82.30 367	99.01 375	93.60 325	94.17 389	98.37 332

testdata				98.09 239	98.93 231	95.40 268		98.80 276	90.08 374	97.45 300	98.37 270	95.26 236	99.70 248	93.58 326	98.95 303	99.17 240

MDTV_nov1_ep13_2view						74.92 402	97.69 212		90.06 375	97.75 278		85.78 344		93.52 327		98.69 310

TAPA-MVS	96.21 11	96.63 279	95.95 290	98.65 179	98.93 231	98.09 136	96.93 274	99.28 176	83.58 389	98.13 251	97.78 312	96.13 203	99.40 342	93.52 327	99.29 258	98.45 325
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OMC-MVS		97.88 197	97.49 221	99.04 130	98.89 244	98.63 89	96.94 272	99.25 185	95.02 307	98.53 222	98.51 254	97.27 145	99.47 332	93.50 329	99.51 222	99.01 259

PatchMatch-RL		97.24 246	96.78 261	98.61 188	99.03 218	97.83 166	96.36 302	99.06 228	93.49 340	97.36 306	97.78 312	95.75 222	99.49 326	93.44 330	98.77 312	98.52 321

114514_t		96.50 285	95.77 292	98.69 177	99.48 121	97.43 194	97.84 196	99.55 70	81.42 391	96.51 341	98.58 247	95.53 228	99.67 264	93.41 331	99.58 201	98.98 264

dp		93.47 343	93.59 336	93.13 375	96.64 383	81.62 399	97.66 217	96.42 357	92.80 349	96.11 349	98.64 238	78.55 384	99.59 299	93.31 332	92.18 393	98.16 338

test9_res														93.28 333	99.15 279	99.38 182

IB-MVS	91.63 19	92.24 355	90.90 359	96.27 334	97.22 373	91.24 363	94.36 371	93.33 381	92.37 353	92.24 388	94.58 385	66.20 399	99.89 73	93.16 334	94.63 387	97.66 362
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
baseline2		93.73 339	92.83 345	96.42 330	97.70 357	91.28 362	96.84 279	89.77 393	93.96 334	92.44 387	95.93 364	79.14 379	99.77 214	92.94 335	96.76 371	98.21 335

OpenMVS	96.65 7	97.09 257	96.68 267	98.32 223	98.32 324	97.16 211	98.86 81	99.37 130	89.48 376	96.29 347	99.15 127	96.56 186	99.90 63	92.90 336	99.20 271	97.89 349

ADS-MVSNet2		95.43 314	94.98 318	96.76 326	98.14 335	91.74 353	97.92 183	97.76 325	90.23 370	96.51 341	98.91 184	85.61 345	99.85 120	92.88 337	96.90 367	98.69 310

ADS-MVSNet		95.24 317	94.93 321	96.18 336	98.14 335	90.10 371	97.92 183	97.32 337	90.23 370	96.51 341	98.91 184	85.61 345	99.74 232	92.88 337	96.90 367	98.69 310

BP-MVS														92.82 339

HQP-MVS		97.00 265	96.49 279	98.55 199	98.67 285	96.79 225	96.29 305	99.04 234	96.05 279	95.55 360	96.84 347	93.84 274	99.54 314	92.82 339	99.26 263	99.32 203

testdata2													99.79 197	92.80 341

CDPH-MVS		97.26 243	96.66 270	99.07 121	99.00 220	98.15 129	96.03 316	99.01 242	91.21 366	97.79 275	97.85 310	96.89 166	99.69 252	92.75 342	99.38 244	99.39 175

新几何1				98.91 146	98.94 229	97.76 174		98.76 281	87.58 383	96.75 332	98.10 292	94.80 252	99.78 208	92.73 343	99.00 297	99.20 229

ZD-MVS					99.01 219	98.84 75		99.07 227	94.10 330	98.05 259	98.12 290	96.36 197	99.86 108	92.70 344	99.19 274

F-COLMAP		97.30 240	96.68 267	99.14 109	99.19 179	98.39 108	97.27 255	99.30 165	92.93 346	96.62 336	98.00 299	95.73 223	99.68 261	92.62 345	98.46 328	99.35 194

原ACMM1				98.35 221	98.90 239	96.25 240		98.83 273	92.48 352	96.07 351	98.10 292	95.39 234	99.71 245	92.61 346	98.99 298	99.08 247

agg_prior2														92.50 347	99.16 277	99.37 184

FE-MVS		95.66 308	94.95 320	97.77 262	98.53 307	95.28 271	99.40 16	96.09 361	93.11 344	97.96 263	99.26 101	79.10 380	99.77 214	92.40 348	98.71 317	98.27 334

无先验							95.74 331	98.74 286	89.38 377				99.73 237	92.38 349		99.22 228

CMPMVS	75.91 23	96.29 291	95.44 305	98.84 153	96.25 389	98.69 88	97.02 267	99.12 219	88.90 379	97.83 272	98.86 197	89.51 319	98.90 380	91.92 350	99.51 222	98.92 276
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
BH-untuned		96.83 271	96.75 263	97.08 308	98.74 267	93.33 329	96.71 286	98.26 309	96.72 256	98.44 229	97.37 337	95.20 238	99.47 332	91.89 351	97.43 357	98.44 327

gm-plane-assit					94.83 394	81.97 398			88.07 382		94.99 379		99.60 295	91.76 352

CNLPA		97.17 252	96.71 265	98.55 199	98.56 303	98.05 146	96.33 303	98.93 249	96.91 248	97.06 314	97.39 335	94.38 263	99.45 335	91.66 353	99.18 276	98.14 339

MIMVSNet		96.62 280	96.25 287	97.71 271	99.04 215	94.66 291	99.16 51	96.92 349	97.23 231	97.87 268	99.10 136	86.11 342	99.65 280	91.65 354	99.21 270	98.82 288

1314		95.74 306	95.60 299	96.17 337	97.53 363	92.75 340	98.07 162	98.31 308	91.22 365	94.25 377	96.68 350	95.53 228	99.03 372	91.64 355	97.18 364	96.74 377

PMVS	91.26 20	97.86 199	97.94 188	97.65 274	99.71 48	97.94 158	98.52 111	98.68 289	98.99 91	97.52 294	99.35 84	97.41 137	98.18 388	91.59 356	99.67 171	96.82 376
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tpm cat1		93.29 345	93.13 343	93.75 368	97.39 369	84.74 390	97.39 243	97.65 329	83.39 390	94.16 378	98.41 265	82.86 365	99.39 344	91.56 357	95.35 384	97.14 372

test_method		79.78 361	79.50 364	80.62 378	80.21 400	45.76 404	70.82 392	98.41 305	31.08 396	80.89 397	97.71 316	84.85 350	97.37 391	91.51 358	80.03 395	98.75 303

DPM-MVS		96.32 290	95.59 300	98.51 205	98.76 264	97.21 206	94.54 368	98.26 309	91.94 357	96.37 345	97.25 340	93.06 287	99.43 338	91.42 359	98.74 313	98.89 280

WAC-MVS						90.90 367								91.37 360

KD-MVS_2432*1600		92.87 349	91.99 352	95.51 351	91.37 397	89.27 373	94.07 374	98.14 316	95.42 298	97.25 308	96.44 356	67.86 394	99.24 363	91.28 361	96.08 379	98.02 345

miper_refine_blended		92.87 349	91.99 352	95.51 351	91.37 397	89.27 373	94.07 374	98.14 316	95.42 298	97.25 308	96.44 356	67.86 394	99.24 363	91.28 361	96.08 379	98.02 345

HY-MVS	95.94 13	95.90 302	95.35 310	97.55 284	97.95 343	94.79 284	98.81 85	96.94 348	92.28 355	95.17 368	98.57 248	89.90 317	99.75 227	91.20 363	97.33 363	98.10 341

MG-MVS		96.77 274	96.61 273	97.26 302	98.31 325	93.06 332	95.93 323	98.12 318	96.45 266	97.92 264	98.73 219	93.77 278	99.39 344	91.19 364	99.04 291	99.33 201

AdaColmap		97.14 254	96.71 265	98.46 210	98.34 323	97.80 172	96.95 271	98.93 249	95.58 293	96.92 319	97.66 319	95.87 219	99.53 316	90.97 365	99.14 280	98.04 344

PLC	94.65 16	96.51 283	95.73 294	98.85 152	98.75 266	97.91 159	96.42 299	99.06 228	90.94 369	95.59 357	97.38 336	94.41 261	99.59 299	90.93 366	98.04 349	99.05 251
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm2		93.09 347	92.58 347	94.62 360	97.56 361	86.53 384	97.66 217	95.79 365	86.15 385	94.07 381	98.23 283	75.95 386	99.53 316	90.91 367	96.86 370	97.81 354

QAPM		97.31 239	96.81 260	98.82 155	98.80 262	97.49 189	99.06 63	99.19 200	90.22 372	97.69 281	99.16 123	96.91 165	99.90 63	90.89 368	99.41 239	99.07 249

PAPM_NR		96.82 273	96.32 283	98.30 226	99.07 207	96.69 230	97.48 238	98.76 281	95.81 288	96.61 337	96.47 355	94.12 271	99.17 368	90.82 369	97.78 351	99.06 250

BH-RMVSNet		96.83 271	96.58 276	97.58 280	98.47 312	94.05 307	96.67 288	97.36 334	96.70 258	97.87 268	97.98 301	95.14 240	99.44 337	90.47 370	98.58 326	99.25 219

API-MVS		97.04 261	96.91 252	97.42 295	97.88 348	98.23 124	98.18 148	98.50 300	97.57 190	97.39 304	96.75 349	96.77 175	99.15 370	90.16 371	99.02 295	94.88 390

E-PMN		94.17 332	94.37 327	93.58 370	96.86 379	85.71 388	90.11 390	97.07 342	98.17 147	97.82 274	97.19 341	84.62 353	98.94 377	89.77 372	97.68 353	96.09 386

MAR-MVS		96.47 287	95.70 295	98.79 162	97.92 345	99.12 57	98.28 139	98.60 295	92.16 356	95.54 363	96.17 360	94.77 255	99.52 320	89.62 373	98.23 333	97.72 360
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
myMVS_eth3d		91.92 357	90.45 360	96.30 332	97.10 375	90.90 367	96.18 312	96.58 354	95.65 291	94.77 372	92.29 392	53.88 401	99.36 347	89.59 374	98.05 347	98.63 316

wuyk23d		96.06 296	97.62 214	91.38 376	98.65 292	98.57 96	98.85 82	96.95 347	96.86 250	99.90 12	99.16 123	99.18 17	98.40 386	89.23 375	99.77 122	77.18 394

OpenMVS_ROB	95.38 14	95.84 304	95.18 315	97.81 259	98.41 320	97.15 212	97.37 245	98.62 294	83.86 388	98.65 202	98.37 270	94.29 266	99.68 261	88.41 376	98.62 324	96.60 379

dmvs_re		95.98 300	95.39 308	97.74 268	98.86 247	97.45 192	98.37 133	95.69 366	97.95 160	96.56 338	95.95 363	90.70 311	97.68 390	88.32 377	96.13 378	98.11 340

BH-w/o		95.13 318	94.89 322	95.86 341	98.20 332	91.31 360	95.65 333	97.37 333	93.64 336	96.52 340	95.70 368	93.04 288	99.02 373	88.10 378	95.82 381	97.24 371

EMVS		93.83 338	94.02 330	93.23 374	96.83 381	84.96 389	89.77 391	96.32 358	97.92 163	97.43 302	96.36 359	86.17 340	98.93 378	87.68 379	97.73 352	95.81 387

gg-mvs-nofinetune		92.37 353	91.20 358	95.85 342	95.80 393	92.38 346	99.31 27	81.84 400	99.75 5	91.83 389	99.74 13	68.29 393	99.02 373	87.15 380	97.12 365	96.16 383

TR-MVS		95.55 311	95.12 316	96.86 322	97.54 362	93.94 314	96.49 295	96.53 356	94.36 325	97.03 316	96.61 351	94.26 267	99.16 369	86.91 381	96.31 375	97.47 368

PVSNet_0	89.98 21	91.15 359	90.30 362	93.70 369	97.72 353	84.34 394	90.24 389	97.42 332	90.20 373	93.79 384	93.09 390	90.90 310	98.89 381	86.57 382	72.76 396	97.87 351

tmp_tt		78.77 362	78.73 365	78.90 379	58.45 401	74.76 403	94.20 373	78.26 402	39.16 395	86.71 395	92.82 391	80.50 371	75.19 398	86.16 383	92.29 392	86.74 393

PAPR		95.29 315	94.47 324	97.75 266	97.50 367	95.14 277	94.89 356	98.71 288	91.39 364	95.35 367	95.48 373	94.57 258	99.14 371	84.95 384	97.37 359	98.97 267

thres600view7		94.45 326	93.83 332	96.29 333	99.06 211	91.53 355	97.99 176	94.24 376	98.34 127	97.44 301	95.01 378	79.84 373	99.67 264	84.33 385	98.23 333	97.66 362

MVS		93.19 346	92.09 350	96.50 329	96.91 378	94.03 310	98.07 162	98.06 320	68.01 393	94.56 376	96.48 354	95.96 216	99.30 357	83.84 386	96.89 369	96.17 382

thres100view900		94.19 331	93.67 335	95.75 345	99.06 211	91.35 359	98.03 168	94.24 376	98.33 128	97.40 303	94.98 380	79.84 373	99.62 288	83.05 387	98.08 344	96.29 380

tfpn200view9		94.03 335	93.44 337	95.78 344	98.93 231	91.44 357	97.60 225	94.29 374	97.94 161	97.10 311	94.31 386	79.67 375	99.62 288	83.05 387	98.08 344	96.29 380

thres400		94.14 333	93.44 337	96.24 335	98.93 231	91.44 357	97.60 225	94.29 374	97.94 161	97.10 311	94.31 386	79.67 375	99.62 288	83.05 387	98.08 344	97.66 362

thres200		93.72 340	93.14 342	95.46 353	98.66 290	91.29 361	96.61 291	94.63 371	97.39 211	96.83 328	93.71 388	79.88 372	99.56 308	82.40 390	98.13 341	95.54 389

GG-mvs-BLEND				94.76 359	94.54 395	92.13 351	99.31 27	80.47 401		88.73 394	91.01 394	67.59 396	98.16 389	82.30 391	94.53 388	93.98 391

MVE	83.40 22	92.50 351	91.92 354	94.25 363	98.83 253	91.64 354	92.71 385	83.52 399	95.92 285	86.46 396	95.46 374	95.20 238	95.40 395	80.51 392	98.64 322	95.73 388
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PCF-MVS	92.86 18	94.36 327	93.00 344	98.42 215	98.70 277	97.56 186	93.16 384	99.11 221	79.59 392	97.55 291	97.43 333	92.19 299	99.73 237	79.85 393	99.45 234	97.97 348
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
FPMVS		93.44 344	92.23 348	97.08 308	99.25 164	97.86 163	95.61 334	97.16 340	92.90 347	93.76 385	98.65 235	75.94 387	95.66 394	79.30 394	97.49 354	97.73 359

DeepMVS_CX				93.44 372	98.24 329	94.21 303		94.34 373	64.28 394	91.34 390	94.87 384	89.45 321	92.77 397	77.54 395	93.14 390	93.35 392

dmvs_testset		92.94 348	92.21 349	95.13 356	98.59 298	90.99 366	97.65 219	92.09 386	96.95 245	94.00 382	93.55 389	92.34 298	96.97 393	72.20 396	92.52 391	97.43 369

PAPM		91.88 358	90.34 361	96.51 328	98.06 340	92.56 341	92.44 387	97.17 339	86.35 384	90.38 391	96.01 361	86.61 336	99.21 366	70.65 397	95.43 383	97.75 358

test123		17.04 365	20.11 368	7.82 380	10.25 403	4.91 405	94.80 357	4.47 405	4.93 398	10.00 400	24.28 397	9.69 403	3.64 399	10.14 398	12.43 398	14.92 395

testmvs		17.12 364	20.53 367	6.87 381	12.05 402	4.20 406	93.62 382	6.73 404	4.62 399	10.41 399	24.33 396	8.28 404	3.56 400	9.69 399	15.07 397	12.86 396

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

cdsmvs_eth3d_5k		24.66 363	32.88 366	0.00 382	0.00 404	0.00 407	0.00 393	99.10 223	0.00 400	0.00 401	97.58 324	99.21 16	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		8.17 366	10.90 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	98.07 84	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

ab-mvs-re		8.12 367	10.83 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	97.48 330	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

FOURS1					99.73 39	99.67 2	99.43 11	99.54 75	99.43 40	99.26 110

test_one_0601					99.39 138	99.20 34		99.31 157	98.49 122	98.66 201	99.02 151	97.64 116

eth-test2					0.00 404

eth-test					0.00 404

test_241102_ONE					99.49 114	99.17 39		99.31 157	97.98 157	99.66 40	98.90 187	98.36 61	99.48 329

save fliter					99.11 198	97.97 153	96.53 293	99.02 239	98.24 137

test0726					99.50 107	99.21 28	98.17 151	99.35 139	97.97 158	99.26 110	99.06 139	97.61 119

GSMVS																98.81 292

test_part2					99.36 146	99.10 60				99.05 139

sam_mvs1												84.74 352				98.81 292

sam_mvs												84.29 358

MTGPA								99.20 196

test_post											21.25 398	83.86 360	99.70 248

patchmatchnet-post											98.77 214	84.37 355	99.85 120

MTMP							97.93 181	91.91 387

TEST9					98.71 273	98.08 140	95.96 320	99.03 236	91.40 363	95.85 354	97.53 326	96.52 188	99.76 220

test_8					98.67 285	98.01 148	95.91 325	99.02 239	91.64 358	95.79 356	97.50 329	96.47 190	99.76 220

agg_prior					98.68 284	97.99 149		99.01 242		95.59 357			99.77 214

test_prior4						97.97 153	95.86 326

test_prior				98.95 141	98.69 282	97.95 157		99.03 236					99.59 299			99.30 210

新几何2							95.93 323

旧先验1					98.82 256	97.45 192		98.76 281			98.34 274	95.50 231			99.01 296	99.23 224

原ACMM2							95.53 337

test222					98.92 235	96.93 222	95.54 336	98.78 279	85.72 386	96.86 327	98.11 291	94.43 260			99.10 287	99.23 224

segment_acmp												97.02 160

testdata1							95.44 342		96.32 270

test12				98.93 143	98.58 300	97.83 166		98.66 290		96.53 339		95.51 230	99.69 252		99.13 282	99.27 215

plane_prior7					99.19 179	97.87 162

plane_prior6					98.99 223	97.70 180						94.90 245

plane_prior4											97.98 301

plane_prior3						97.78 173			97.41 209	97.79 275

plane_prior2							97.77 202		98.20 144

plane_prior1					99.05 214

plane_prior						97.65 182	97.07 266		96.72 256						99.36 245

n2								0.00 406

nn								0.00 406

door-mid								99.57 59

test11								98.87 260

door								99.41 119

HQP5-MVS						96.79 225

HQP-NCC					98.67 285		96.29 305		96.05 279	95.55 360

ACMP_Plane					98.67 285		96.29 305		96.05 279	95.55 360

HQP4-MVS										95.56 359			99.54 314			99.32 203

HQP3-MVS								99.04 234							99.26 263

HQP2-MVS												93.84 274

NP-MVS					98.84 251	97.39 196					96.84 347

ACMMP++_ref															99.77 122

ACMMP++															99.68 165

Test By Simon												96.52 188

High-resolution multi-view benchmark