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

fmvsm_s_conf0.1_n_2		97.68 100	98.18 48	96.20 233	99.06 100	89.08 289	95.51 238	99.72 6	96.06 141	99.48 17	99.24 33	95.18 159	99.60 171	99.45 2	99.88 25	99.94 3

test_fmvsmvis_n_1920		98.08 50	98.47 29	96.93 183	99.03 108	93.29 192	96.32 174	99.65 13	95.59 172	99.71 5	99.01 61	97.66 34	99.60 171	99.44 3	99.83 45	97.90 326

fmvsm_s_conf0.5_n_2		97.59 111	98.07 54	96.17 236	98.78 141	89.10 288	95.33 254	99.55 23	95.96 149	99.41 24	99.10 53	95.18 159	99.59 173	99.43 4	99.86 30	99.81 10

test_fmvsmconf0.01_n		98.57 18	98.74 17	98.06 90	99.39 44	94.63 138	96.70 155	99.82 1	95.44 181	99.64 11	99.52 9	98.96 4	99.74 83	99.38 5	99.86 30	99.81 10

fmvsm_s_conf0.5_n_3		97.88 78	98.37 37	96.41 221	98.73 146	89.82 270	95.94 208	99.49 24	96.81 103	99.09 44	99.03 60	97.09 61	99.65 147	99.37 6	99.76 61	99.76 20

mamv4		99.05 5	98.91 8	99.46 2	98.94 119	99.62 2	97.98 63	99.70 8	99.49 3	99.78 2	99.22 36	95.92 127	99.95 3	99.31 7	99.83 45	98.83 225

fmvsm_s_conf0.5_n_4		97.43 123	97.77 88	96.39 224	98.48 187	89.89 268	95.65 228	99.26 38	94.73 209	98.72 80	98.58 108	95.58 146	99.57 182	99.28 8	99.67 89	99.73 25

v7n		98.73 12	98.99 5	97.95 100	99.64 13	94.20 158	98.67 15	99.14 56	99.08 14	99.42 22	99.23 35	96.53 100	99.91 14	99.27 9	99.93 11	99.73 25

test_fmvs3		97.38 127	97.56 112	96.84 193	98.63 164	92.81 203	97.60 94	99.61 18	90.87 317	98.76 76	99.66 4	94.03 193	97.90 397	99.24 10	99.68 86	99.81 10

test_fmvsmconf0.1_n		98.41 31	98.54 27	98.03 95	99.16 80	94.61 139	96.18 184	99.73 5	95.05 199	99.60 15	99.34 26	98.68 8	99.72 95	99.21 11	99.85 39	99.76 20

test_fmvsm_n_1920		98.08 50	98.29 44	97.43 144	98.88 128	93.95 167	96.17 188	99.57 20	95.66 167	99.52 16	98.71 93	97.04 66	99.64 153	99.21 11	99.87 28	98.69 245

MM		96.87 157	96.62 169	97.62 123	97.72 282	93.30 191	96.39 166	92.61 382	97.90 58	96.76 240	98.64 103	90.46 270	99.81 41	99.16 13	99.94 8	99.76 20

test_fmvsmconf_n		98.30 37	98.41 36	97.99 98	98.94 119	94.60 140	96.00 200	99.64 16	94.99 202	99.43 21	99.18 43	98.51 10	99.71 109	99.13 14	99.84 41	99.67 32

fmvsm_s_conf0.5_n_5		97.63 105	97.83 79	97.04 176	98.77 143	92.33 215	95.63 233	99.58 19	93.53 250	99.10 43	98.66 98	96.44 108	99.65 147	99.12 15	99.68 86	99.12 174

fmvsm_l_conf0.5_n_3		98.29 38	98.46 30	97.79 109	98.90 126	94.05 163	96.06 194	99.63 17	96.07 140	99.37 26	98.93 71	98.29 13	99.68 130	99.11 16	99.79 55	99.65 37

fmvsm_l_conf0.5_n		97.68 100	97.81 82	97.27 156	98.92 123	92.71 208	95.89 212	99.41 31	93.36 256	99.00 52	98.44 126	96.46 107	99.65 147	99.09 17	99.76 61	99.45 96

fmvsm_l_conf0.5_n_a		97.60 108	97.76 89	97.11 167	98.92 123	92.28 217	95.83 215	99.32 32	93.22 262	98.91 61	98.49 119	96.31 115	99.64 153	99.07 18	99.76 61	99.40 111

fmvsm_s_conf0.1_n_a		97.80 89	98.01 61	97.18 162	99.17 79	92.51 211	96.57 159	99.15 53	93.68 246	98.89 62	99.30 29	96.42 110	99.37 249	99.03 19	99.83 45	99.66 34

fmvsm_s_conf0.1_n		97.73 94	98.02 60	96.85 191	99.09 95	91.43 245	96.37 170	99.11 59	94.19 229	99.01 50	99.25 32	96.30 116	99.38 244	99.00 20	99.88 25	99.73 25

fmvsm_s_conf0.5_n_a		97.65 102	97.83 79	97.13 166	98.80 136	92.51 211	96.25 180	99.06 74	93.67 247	98.64 82	99.00 62	96.23 120	99.36 252	98.99 21	99.80 53	99.53 63

fmvsm_s_conf0.5_n		97.62 106	97.89 72	96.80 195	98.79 138	91.44 244	96.14 189	99.06 74	94.19 229	98.82 68	98.98 65	96.22 121	99.38 244	98.98 22	99.86 30	99.58 44

mvs_tets		98.90 6	98.94 6	98.75 35	99.69 10	96.48 64	98.54 23	99.22 41	96.23 131	99.71 5	99.48 12	98.77 7	99.93 4	98.89 23	99.95 5	99.84 8

test_fmvs2		96.38 187	96.45 184	96.16 237	97.85 252	91.30 246	96.81 141	99.45 26	89.24 339	98.49 96	99.38 20	88.68 294	97.62 402	98.83 24	99.32 205	99.57 51

PS-MVSNAJss		98.53 24	98.63 21	98.21 80	99.68 11	94.82 131	98.10 56	99.21 42	96.91 100	99.75 3	99.45 15	95.82 133	99.92 6	98.80 25	99.96 4	99.89 4

jajsoiax		98.77 10	98.79 13	98.74 38	99.66 12	96.48 64	98.45 31	99.12 58	95.83 161	99.67 8	99.37 21	98.25 14	99.92 6	98.77 26	99.94 8	99.82 9

v10		97.55 113	97.97 65	96.31 228	98.60 168	89.64 275	97.44 107	99.02 88	96.60 111	98.72 80	99.16 47	93.48 207	99.72 95	98.76 27	99.92 14	99.58 44

MVSFormer		96.14 195	96.36 188	95.49 270	97.68 285	87.81 318	98.67 15	99.02 88	96.50 118	94.48 330	96.15 321	86.90 313	99.92 6	98.73 28	99.13 232	98.74 238

test_djsdf		98.73 12	98.74 17	98.69 43	99.63 14	96.30 71	98.67 15	99.02 88	96.50 118	99.32 30	99.44 16	97.43 42	99.92 6	98.73 28	99.95 5	99.86 5

OurMVSNet-221017-0		98.61 17	98.61 25	98.63 48	99.77 5	96.35 68	99.17 7	99.05 78	98.05 54	99.61 14	99.52 9	93.72 202	99.88 21	98.72 30	99.88 25	99.65 37

tt0805		97.44 121	97.56 112	97.11 167	99.55 22	96.36 67	98.66 18	95.66 336	98.31 41	97.09 217	95.45 346	97.17 57	98.50 372	98.67 31	97.45 353	96.48 389

v8		97.60 108	98.06 57	96.23 230	98.71 152	89.44 280	97.43 109	98.82 151	97.29 91	98.74 78	99.10 53	93.86 197	99.68 130	98.61 32	99.94 8	99.56 55

anonymousdsp		98.72 15	98.63 21	98.99 14	99.62 15	97.29 41	98.65 19	99.19 46	95.62 170	99.35 29	99.37 21	97.38 44	99.90 16	98.59 33	99.91 17	99.77 15

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 41	99.71 9	96.99 48	99.69 2	99.57 20	99.02 19	99.62 13	99.36 23	98.53 9	99.52 196	98.58 34	99.95 5	99.66 34
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
mmtdpeth		98.33 33	98.53 28	97.71 115	99.07 98	93.44 186	98.80 12	99.78 4	99.10 13	96.61 250	99.63 7	95.42 152	99.73 89	98.53 35	99.86 30	99.95 2

mvs5depth		98.06 53	98.58 26	96.51 213	98.97 115	89.65 274	99.43 4	99.81 2	99.30 7	98.36 112	99.86 2	93.15 213	99.88 21	98.50 36	99.84 41	99.99 1

v1240		96.74 166	97.02 148	95.91 249	98.18 220	88.52 298	95.39 247	98.88 124	93.15 270	98.46 101	98.40 132	92.80 223	99.71 109	98.45 37	99.49 154	99.49 81

MVSMamba_PlusPlus		97.43 123	97.98 64	95.78 254	98.88 128	89.70 272	98.03 61	98.85 133	99.18 11	96.84 234	99.12 51	93.04 216	99.91 14	98.38 38	99.55 129	97.73 340

v1192		96.83 161	97.06 145	96.15 238	98.28 205	89.29 282	95.36 249	98.77 158	93.73 242	98.11 142	98.34 138	93.02 220	99.67 139	98.35 39	99.58 117	99.50 73

v1921920		96.72 169	96.96 152	95.99 242	98.21 214	88.79 295	95.42 243	98.79 153	93.22 262	98.19 135	98.26 155	92.68 226	99.70 118	98.34 40	99.55 129	99.49 81

MVS_0304		95.71 214	95.18 230	97.33 152	94.85 398	92.82 201	95.36 249	90.89 400	95.51 176	95.61 302	97.82 207	88.39 298	99.78 53	98.23 41	99.91 17	99.40 111

Anonymous20231211		98.55 21	98.76 14	97.94 101	98.79 138	94.37 150	98.84 11	99.15 53	99.37 4	99.67 8	99.43 17	95.61 144	99.72 95	98.12 42	99.86 30	99.73 25

v144192		96.69 172	96.90 157	96.03 241	98.25 210	88.92 290	95.49 239	98.77 158	93.05 272	98.09 145	98.29 149	92.51 237	99.70 118	98.11 43	99.56 123	99.47 90

test_fmvs1_n		95.21 240	95.28 226	94.99 291	98.15 227	89.13 287	96.81 141	99.43 28	86.97 369	97.21 203	98.92 73	83.00 345	97.13 406	98.09 44	98.94 254	98.72 241

Anonymous20240521		97.07 142	97.51 117	95.76 255	99.35 49	88.18 306	97.78 78	98.40 213	97.11 95	98.34 116	99.04 59	89.58 283	99.79 49	98.09 44	99.93 11	99.30 133

v1144		96.84 158	97.08 143	96.13 239	98.42 194	89.28 283	95.41 245	98.67 180	94.21 227	97.97 160	98.31 141	93.06 215	99.65 147	98.06 46	99.62 99	99.45 96

SixPastTwentyTwo		97.49 117	97.57 111	97.26 158	99.56 20	92.33 215	98.28 42	96.97 309	98.30 43	99.45 20	99.35 25	88.43 297	99.89 19	98.01 47	99.76 61	99.54 60

test_vis1_n_1920		95.77 211	96.41 186	93.85 333	98.55 175	84.86 364	95.91 211	99.71 7	92.72 284	97.67 180	98.90 77	87.44 310	98.73 347	97.96 48	98.85 265	97.96 322

WR-MVS_H		98.65 16	98.62 23	98.75 35	99.51 28	96.61 60	98.55 22	99.17 48	99.05 17	99.17 39	98.79 83	95.47 149	99.89 19	97.95 49	99.91 17	99.75 23

BP-MVS1		95.36 232	94.86 247	96.89 188	98.35 199	91.72 238	96.76 147	95.21 349	96.48 121	96.23 274	97.19 258	75.97 381	99.80 48	97.91 50	99.60 111	99.15 163

UA-Net		98.88 8	98.76 14	99.22 3	99.11 92	97.89 17	99.47 3	99.32 32	99.08 14	97.87 172	99.67 3	96.47 105	99.92 6	97.88 51	99.98 2	99.85 6

test_fmvs1		94.51 276	94.60 263	94.26 327	95.91 368	87.92 313	95.35 252	99.02 88	86.56 373	96.79 235	98.52 116	82.64 347	97.00 409	97.87 52	98.71 280	97.88 328

FC-MVSNet-test		98.16 43	98.37 37	97.56 126	99.49 32	93.10 197	98.35 35	99.21 42	98.43 36	98.89 62	98.83 82	94.30 187	99.81 41	97.87 52	99.91 17	99.77 15

Vis-MVSNet		98.27 39	98.34 39	98.07 88	99.33 51	95.21 122	98.04 59	99.46 25	97.32 89	97.82 176	99.11 52	96.75 90	99.86 26	97.84 54	99.36 190	99.15 163
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
K. test v3		96.44 184	96.28 191	96.95 181	99.41 40	91.53 241	97.65 91	90.31 408	98.89 24	98.93 58	99.36 23	84.57 333	99.92 6	97.81 55	99.56 123	99.39 116

v2v482		96.78 165	97.06 145	95.95 246	98.57 172	88.77 296	95.36 249	98.26 228	95.18 192	97.85 174	98.23 159	92.58 230	99.63 157	97.80 56	99.69 82	99.45 96

PS-CasMVS		98.73 12	98.85 11	98.39 63	99.55 22	95.47 104	98.49 28	99.13 57	99.22 10	99.22 37	98.96 68	97.35 45	99.92 6	97.79 57	99.93 11	99.79 13

MVStest1		91.89 339	91.45 334	93.21 351	89.01 431	84.87 363	95.82 217	95.05 352	91.50 307	98.75 77	99.19 39	57.56 418	95.11 420	97.78 58	98.37 307	99.64 40

nrg030		98.54 22	98.62 23	98.32 67	99.22 66	95.66 94	97.90 71	99.08 70	98.31 41	99.02 49	98.74 89	97.68 31	99.61 169	97.77 59	99.85 39	99.70 30

pmmvs6		99.07 4	99.24 4	98.56 52	99.81 2	96.38 66	98.87 10	99.30 34	99.01 20	99.63 12	99.66 4	99.27 2	99.68 130	97.75 60	99.89 23	99.62 41

ACMH	93.61 9	98.44 29	98.76 14	97.51 131	99.43 37	93.54 183	98.23 46	99.05 78	97.40 84	99.37 26	99.08 57	98.79 6	99.47 211	97.74 61	99.71 78	99.50 73
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_f		95.82 209	95.88 212	95.66 260	97.61 297	93.21 196	95.61 234	98.17 242	86.98 368	98.42 104	99.47 13	90.46 270	94.74 423	97.71 62	98.45 303	99.03 190

DTE-MVSNet		98.79 9	98.86 9	98.59 50	99.55 22	96.12 76	98.48 30	99.10 62	99.36 5	99.29 32	99.06 58	97.27 49	99.93 4	97.71 62	99.91 17	99.70 30

test_vis1_n		95.67 217	95.89 211	95.03 288	98.18 220	89.89 268	96.94 134	99.28 36	88.25 355	98.20 131	98.92 73	86.69 316	97.19 405	97.70 64	98.82 269	98.00 320

EC-MVSNet		97.90 76	97.94 68	97.79 109	98.66 159	95.14 123	98.31 39	99.66 12	97.57 72	95.95 286	97.01 273	96.99 70	99.82 36	97.66 65	99.64 95	98.39 274

PEN-MVS		98.75 11	98.85 11	98.44 59	99.58 18	95.67 93	98.45 31	99.15 53	99.33 6	99.30 31	99.00 62	97.27 49	99.92 6	97.64 66	99.92 14	99.75 23

CP-MVSNet		98.42 30	98.46 30	98.30 70	99.46 34	95.22 120	98.27 44	98.84 137	99.05 17	99.01 50	98.65 102	95.37 153	99.90 16	97.57 67	99.91 17	99.77 15

EI-MVSNet-UG-set		97.32 133	97.40 122	97.09 171	97.34 319	92.01 231	95.33 254	97.65 282	97.74 63	98.30 124	98.14 168	95.04 164	99.69 125	97.55 68	99.52 142	99.58 44

ANet_high		98.31 36	98.94 6	96.41 221	99.33 51	89.64 275	97.92 69	99.56 22	99.27 8	99.66 10	99.50 11	97.67 32	99.83 34	97.55 68	99.98 2	99.77 15

CS-MVS		98.09 49	98.01 61	98.32 67	98.45 191	96.69 56	98.52 26	99.69 9	98.07 53	96.07 282	97.19 258	96.88 82	99.86 26	97.50 70	99.73 71	98.41 271

EI-MVSNet-Vis-set		97.32 133	97.39 123	97.11 167	97.36 316	92.08 229	95.34 253	97.65 282	97.74 63	98.29 125	98.11 174	95.05 163	99.68 130	97.50 70	99.50 151	99.56 55

EU-MVSNet		94.25 282	94.47 271	93.60 340	98.14 229	82.60 385	97.24 117	92.72 379	85.08 387	98.48 98	98.94 70	82.59 348	98.76 345	97.47 72	99.53 137	99.44 106

V42		97.04 143	97.16 139	96.68 204	98.59 170	91.05 250	96.33 173	98.36 218	94.60 215	97.99 156	98.30 145	93.32 209	99.62 162	97.40 73	99.53 137	99.38 118

KD-MVS_self_test		97.86 82	98.07 54	97.25 159	99.22 66	92.81 203	97.55 99	98.94 112	97.10 96	98.85 65	98.88 79	95.03 165	99.67 139	97.39 74	99.65 93	99.26 145

lessismore_v0				97.05 174	99.36 48	92.12 225		84.07 425		98.77 75	98.98 65	85.36 327	99.74 83	97.34 75	99.37 187	99.30 133

FIs		97.93 70	98.07 54	97.48 139	99.38 46	92.95 200	98.03 61	99.11 59	98.04 55	98.62 84	98.66 98	93.75 201	99.78 53	97.23 76	99.84 41	99.73 25

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 46	99.77 5	96.34 69	99.18 6	99.20 44	99.67 2	99.73 4	99.65 6	99.15 3	99.86 26	97.22 77	99.92 14	99.77 15

MVS_Test		96.27 190	96.79 163	94.73 306	96.94 337	86.63 339	96.18 184	98.33 222	94.94 203	96.07 282	98.28 150	95.25 157	99.26 280	97.21 78	97.90 327	98.30 287

TDRefinement		98.90 6	98.86 9	99.02 10	99.54 25	98.06 9	99.34 5	99.44 27	98.85 25	99.00 52	99.20 38	97.42 43	99.59 173	97.21 78	99.76 61	99.40 111

EG-PatchMatch MVS		97.69 98	97.79 84	97.40 148	99.06 100	93.52 184	95.96 206	98.97 108	94.55 219	98.82 68	98.76 88	97.31 47	99.29 274	97.20 80	99.44 167	99.38 118

GDP-MVS		95.39 231	94.89 244	96.90 187	98.26 209	91.91 233	96.48 164	99.28 36	95.06 198	96.54 257	97.12 263	74.83 385	99.82 36	97.19 81	99.27 214	98.96 200

VPA-MVSNet		98.27 39	98.46 30	97.70 117	99.06 100	93.80 172	97.76 81	99.00 99	98.40 38	99.07 47	98.98 65	96.89 80	99.75 74	97.19 81	99.79 55	99.55 58

test_vis3_rt		97.04 143	96.98 149	97.23 161	98.44 192	95.88 84	96.82 140	99.67 10	90.30 326	99.27 33	99.33 28	94.04 192	96.03 418	97.14 83	97.83 330	99.78 14

UniMVSNet (Re)		97.83 84	97.65 99	98.35 66	98.80 136	95.86 86	95.92 210	99.04 85	97.51 76	98.22 130	97.81 209	94.68 175	99.78 53	97.14 83	99.75 69	99.41 110

reproduce_model		98.54 22	98.33 40	99.15 4	99.06 100	98.04 12	97.04 129	99.09 67	98.42 37	99.03 48	98.71 93	96.93 75	99.83 34	97.09 85	99.63 97	99.56 55

pm-mvs1		98.47 28	98.67 19	97.86 105	99.52 27	94.58 141	98.28 42	99.00 99	97.57 72	99.27 33	99.22 36	98.32 12	99.50 201	97.09 85	99.75 69	99.50 73

baseline		97.44 121	97.78 87	96.43 218	98.52 179	90.75 258	96.84 138	99.03 86	96.51 117	97.86 173	98.02 187	96.67 92	99.36 252	97.09 85	99.47 160	99.19 157

IterMVS-SCA-FT		95.86 207	96.19 195	94.85 299	97.68 285	85.53 350	92.42 365	97.63 286	96.99 97	98.36 112	98.54 115	87.94 302	99.75 74	97.07 88	99.08 240	99.27 144

balanced_conf03		96.88 156	97.29 129	95.63 261	97.66 290	89.47 279	97.95 66	98.89 117	95.94 152	97.77 179	98.55 113	92.23 241	99.68 130	97.05 89	99.61 105	97.73 340

UniMVSNet_NR-MVSNet		97.83 84	97.65 99	98.37 64	98.72 149	95.78 87	95.66 226	99.02 88	98.11 51	98.31 122	97.69 220	94.65 177	99.85 29	97.02 90	99.71 78	99.48 87

DU-MVS		97.79 90	97.60 108	98.36 65	98.73 146	95.78 87	95.65 228	98.87 126	97.57 72	98.31 122	97.83 204	94.69 173	99.85 29	97.02 90	99.71 78	99.46 92

casdiffmvs_mvg		97.83 84	98.11 51	97.00 180	98.57 172	92.10 228	95.97 204	99.18 47	97.67 71	99.00 52	98.48 123	97.64 35	99.50 201	96.96 92	99.54 133	99.40 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet		96.63 175	96.93 153	95.74 256	97.26 324	88.13 309	95.29 259	97.65 282	96.99 97	97.94 164	98.19 164	92.55 232	99.58 176	96.91 93	99.56 123	99.50 73

IterMVS-LS		96.92 152	97.29 129	95.79 253	98.51 181	88.13 309	95.10 267	98.66 182	96.99 97	98.46 101	98.68 97	92.55 232	99.74 83	96.91 93	99.79 55	99.50 73
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SPE-MVS-test		97.91 74	97.84 76	98.14 84	98.52 179	96.03 81	98.38 34	99.67 10	98.11 51	95.50 306	96.92 279	96.81 88	99.87 24	96.87 95	99.76 61	98.51 263

reproduce-ours		98.48 26	98.27 45	99.12 5	98.99 111	98.02 13	96.81 141	99.02 88	98.29 44	98.97 56	98.61 105	97.27 49	99.82 36	96.86 96	99.61 105	99.51 70

our_new_method		98.48 26	98.27 45	99.12 5	98.99 111	98.02 13	96.81 141	99.02 88	98.29 44	98.97 56	98.61 105	97.27 49	99.82 36	96.86 96	99.61 105	99.51 70

test_cas_vis1_n_1920		95.34 234	95.67 218	94.35 322	98.21 214	86.83 337	95.61 234	99.26 38	90.45 324	98.17 136	98.96 68	84.43 334	98.31 386	96.74 98	99.17 227	97.90 326

test1111		94.53 275	94.81 252	93.72 337	99.06 100	81.94 390	98.31 39	83.87 426	96.37 124	98.49 96	99.17 46	81.49 350	99.73 89	96.64 99	99.86 30	99.49 81

APDe-MVS		98.14 44	98.03 59	98.47 58	98.72 149	96.04 79	98.07 58	99.10 62	95.96 149	98.59 88	98.69 96	96.94 73	99.81 41	96.64 99	99.58 117	99.57 51
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS-pluss		97.69 98	97.36 125	98.70 42	99.50 31	96.84 51	95.38 248	98.99 102	92.45 289	98.11 142	98.31 141	97.25 54	99.77 63	96.60 101	99.62 99	99.48 87
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mvs_anonymous		95.36 232	96.07 201	93.21 351	96.29 352	81.56 392	94.60 291	97.66 280	93.30 259	96.95 228	98.91 76	93.03 219	99.38 244	96.60 101	97.30 358	98.69 245

casdiffmvs		97.50 116	97.81 82	96.56 211	98.51 181	91.04 251	95.83 215	99.09 67	97.23 92	98.33 119	98.30 145	97.03 67	99.37 249	96.58 103	99.38 186	99.28 140
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TransMVSNet (Re)		98.38 32	98.67 19	97.51 131	99.51 28	93.39 190	98.20 51	98.87 126	98.23 47	99.48 17	99.27 31	98.47 11	99.55 188	96.52 104	99.53 137	99.60 42

HPM-MVS_fast		98.32 35	98.13 49	98.88 27	99.54 25	97.48 34	98.35 35	99.03 86	95.88 157	97.88 169	98.22 162	98.15 17	99.74 83	96.50 105	99.62 99	99.42 108

MIMVSNet1		98.51 25	98.45 33	98.67 44	99.72 8	96.71 54	98.76 13	98.89 117	98.49 35	99.38 25	99.14 50	95.44 151	99.84 32	96.47 106	99.80 53	99.47 90

TranMVSNet+NR-MVSNet		98.33 33	98.30 43	98.43 60	99.07 98	95.87 85	96.73 153	99.05 78	98.67 28	98.84 66	98.45 124	97.58 39	99.88 21	96.45 107	99.86 30	99.54 60

MGCFI-Net		97.20 138	97.23 134	97.08 172	97.68 285	93.71 176	97.79 77	99.09 67	97.40 84	96.59 251	93.96 371	97.67 32	99.35 256	96.43 108	98.50 300	98.17 302

test2506		89.86 364	89.16 369	91.97 381	98.95 116	76.83 418	98.54 23	61.07 436	96.20 132	97.07 218	99.16 47	55.19 430	99.69 125	96.43 108	99.83 45	99.38 118

Gipuma		98.07 52	98.31 41	97.36 150	99.76 7	96.28 72	98.51 27	99.10 62	98.76 27	96.79 235	99.34 26	96.61 96	98.82 338	96.38 110	99.50 151	96.98 368
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
reproduce_monomvs		92.05 336	92.26 323	91.43 386	95.42 389	75.72 422	95.68 224	97.05 306	94.47 220	97.95 163	98.35 136	55.58 427	99.05 315	96.36 111	99.44 167	99.51 70

MVSTER		94.21 285	93.93 292	95.05 287	95.83 374	86.46 340	95.18 264	97.65 282	92.41 290	97.94 164	98.00 191	72.39 397	99.58 176	96.36 111	99.56 123	99.12 174

GeoE		97.75 93	97.70 92	97.89 103	98.88 128	94.53 142	97.10 125	98.98 105	95.75 165	97.62 181	97.59 226	97.61 38	99.77 63	96.34 113	99.44 167	99.36 124

SSC-MVS3.2		95.75 213	96.56 175	93.34 344	98.69 156	80.75 399	91.60 381	97.43 293	97.37 87	96.99 223	97.02 270	93.69 203	99.71 109	96.32 114	99.89 23	99.55 58

sasdasda		97.23 136	97.21 136	97.30 154	97.65 292	94.39 147	97.84 74	99.05 78	97.42 79	96.68 243	93.85 373	97.63 36	99.33 261	96.29 115	98.47 301	98.18 300

canonicalmvs		97.23 136	97.21 136	97.30 154	97.65 292	94.39 147	97.84 74	99.05 78	97.42 79	96.68 243	93.85 373	97.63 36	99.33 261	96.29 115	98.47 301	98.18 300

testf1		98.57 18	98.45 33	98.93 22	99.79 3	98.78 3	97.69 87	99.42 29	97.69 68	98.92 59	98.77 86	97.80 26	99.25 282	96.27 117	99.69 82	98.76 236

APD_test2		98.57 18	98.45 33	98.93 22	99.79 3	98.78 3	97.69 87	99.42 29	97.69 68	98.92 59	98.77 86	97.80 26	99.25 282	96.27 117	99.69 82	98.76 236

alignmvs		96.01 201	95.52 224	97.50 135	97.77 274	94.71 133	96.07 193	96.84 312	97.48 77	96.78 239	94.28 368	85.50 326	99.40 237	96.22 119	98.73 279	98.40 272

tttt0517		93.31 312	92.56 320	95.57 264	98.71 152	87.86 315	97.44 107	87.17 420	95.79 162	97.47 192	96.84 283	64.12 411	99.81 41	96.20 120	99.32 205	99.02 193

DeepC-MVS	95.41 4	97.82 87	97.70 92	98.16 81	98.78 141	95.72 89	96.23 182	99.02 88	93.92 239	98.62 84	98.99 64	97.69 30	99.62 162	96.18 121	99.87 28	99.15 163
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MTAPA		98.14 44	97.84 76	99.06 7	99.44 36	97.90 16	97.25 115	98.73 165	97.69 68	97.90 167	97.96 193	95.81 137	99.82 36	96.13 122	99.61 105	99.45 96

ZNCC-MVS		97.92 71	97.62 106	98.83 29	99.32 53	97.24 43	97.45 106	98.84 137	95.76 163	96.93 229	97.43 237	97.26 53	99.79 49	96.06 123	99.53 137	99.45 96

Patchmatch-RL test		94.66 268	94.49 269	95.19 280	98.54 177	88.91 291	92.57 358	98.74 164	91.46 309	98.32 120	97.75 214	77.31 373	98.81 340	96.06 123	99.61 105	97.85 330

ACMMP_NAP		97.89 77	97.63 104	98.67 44	99.35 49	96.84 51	96.36 171	98.79 153	95.07 197	97.88 169	98.35 136	97.24 55	99.72 95	96.05 125	99.58 117	99.45 96

v148		96.58 178	96.97 150	95.42 273	98.63 164	87.57 322	95.09 268	97.90 264	95.91 156	98.24 128	97.96 193	93.42 208	99.39 241	96.04 126	99.52 142	99.29 139

ACMM	93.33 11	98.05 54	97.79 84	98.85 28	99.15 83	97.55 30	96.68 156	98.83 143	95.21 189	98.36 112	98.13 170	98.13 19	99.62 162	96.04 126	99.54 133	99.39 116
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VDD-MVS		97.37 129	97.25 132	97.74 113	98.69 156	94.50 145	97.04 129	95.61 340	98.59 31	98.51 93	98.72 90	92.54 234	99.58 176	96.02 128	99.49 154	99.12 174

IterMVS		95.42 230	95.83 213	94.20 328	97.52 303	83.78 377	92.41 366	97.47 291	95.49 178	98.06 150	98.49 119	87.94 302	99.58 176	96.02 128	99.02 247	99.23 151
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs		96.04 199	96.23 193	95.46 272	97.35 317	88.03 312	93.42 337	99.08 70	94.09 235	96.66 246	96.93 277	93.85 198	99.29 274	96.01 130	98.67 284	99.06 187
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PM-MVS		97.36 131	97.10 141	98.14 84	98.91 125	96.77 53	96.20 183	98.63 188	93.82 240	98.54 91	98.33 139	93.98 194	99.05 315	95.99 131	99.45 166	98.61 254

Baseline_NR-MVSNet		97.72 96	97.79 84	97.50 135	99.56 20	93.29 192	95.44 241	98.86 129	98.20 49	98.37 109	99.24 33	94.69 173	99.55 188	95.98 132	99.79 55	99.65 37

ECVR-MVS		94.37 281	94.48 270	94.05 332	98.95 116	83.10 380	98.31 39	82.48 428	96.20 132	98.23 129	99.16 47	81.18 353	99.66 145	95.95 133	99.83 45	99.38 118

3Dnovator	96.53 2	97.61 107	97.64 102	97.50 135	97.74 280	93.65 181	98.49 28	98.88 124	96.86 102	97.11 211	98.55 113	95.82 133	99.73 89	95.94 134	99.42 179	99.13 169

PatchT		93.75 299	93.57 297	94.29 326	95.05 396	87.32 328	96.05 195	92.98 375	97.54 75	94.25 333	98.72 90	75.79 382	99.24 286	95.92 135	95.81 390	96.32 391

NR-MVSNet		97.96 60	97.86 75	98.26 72	98.73 146	95.54 97	98.14 54	98.73 165	97.79 59	99.42 22	97.83 204	94.40 185	99.78 53	95.91 136	99.76 61	99.46 92

h-mvs33		96.29 189	95.63 221	98.26 72	98.50 184	96.11 77	96.90 136	97.09 303	96.58 113	97.21 203	98.19 164	84.14 335	99.78 53	95.89 137	96.17 387	98.89 216

hse-mvs2		95.77 211	95.09 234	97.79 109	97.84 257	95.51 99	95.66 226	95.43 345	96.58 113	97.21 203	96.16 320	84.14 335	99.54 191	95.89 137	96.92 362	98.32 283

MSC_two_6792asdad				98.22 77	97.75 277	95.34 112		98.16 246					99.75 74	95.87 139	99.51 147	99.57 51

No_MVS				98.22 77	97.75 277	95.34 112		98.16 246					99.75 74	95.87 139	99.51 147	99.57 51

new-patchmatchnet		95.67 217	96.58 173	92.94 361	97.48 306	80.21 402	92.96 347	98.19 241	94.83 206	98.82 68	98.79 83	93.31 210	99.51 200	95.83 141	99.04 246	99.12 174

FMVSNet1		97.95 64	98.08 53	97.56 126	99.14 90	93.67 177	98.23 46	98.66 182	97.41 83	99.00 52	99.19 39	95.47 149	99.73 89	95.83 141	99.76 61	99.30 133

patch_mono-2		96.59 176	96.93 153	95.55 267	98.88 128	87.12 331	94.47 294	99.30 34	94.12 232	96.65 248	98.41 129	94.98 168	99.87 24	95.81 143	99.78 59	99.66 34

DVP-MVS++		97.96 60	97.90 69	98.12 86	97.75 277	95.40 105	99.03 8	98.89 117	96.62 109	98.62 84	98.30 145	96.97 71	99.75 74	95.70 144	99.25 217	99.21 153

test_0728_THIRD									96.62 109	98.40 106	98.28 150	97.10 59	99.71 109	95.70 144	99.62 99	99.58 44

EGC-MVSNET		83.08 395	77.93 398	98.53 54	99.57 19	97.55 30	98.33 38	98.57 195	4.71 433	10.38 434	98.90 77	95.60 145	99.50 201	95.69 146	99.61 105	98.55 259

RPMNet		94.68 267	94.60 263	94.90 296	95.44 387	88.15 307	96.18 184	98.86 129	97.43 78	94.10 338	98.49 119	79.40 360	99.76 68	95.69 146	95.81 390	96.81 379

TSAR-MVS + MP.		97.42 125	97.23 134	98.00 97	99.38 46	95.00 127	97.63 93	98.20 236	93.00 274	98.16 137	98.06 183	95.89 128	99.72 95	95.67 148	99.10 238	99.28 140
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVS		97.96 60	97.63 104	98.94 19	99.15 83	97.66 23	97.77 79	98.83 143	97.42 79	96.32 266	97.64 222	96.49 103	99.72 95	95.66 149	99.37 187	99.45 96

X-MVStestdata		92.86 320	90.83 349	98.94 19	99.15 83	97.66 23	97.77 79	98.83 143	97.42 79	96.32 266	36.50 431	96.49 103	99.72 95	95.66 149	99.37 187	99.45 96

3Dnovator+	96.13 3	97.73 94	97.59 109	98.15 83	98.11 233	95.60 95	98.04 59	98.70 174	98.13 50	96.93 229	98.45 124	95.30 156	99.62 162	95.64 151	98.96 251	99.24 150

DELS-MVS		96.17 194	96.23 193	95.99 242	97.55 302	90.04 265	92.38 368	98.52 198	94.13 231	96.55 256	97.06 267	94.99 167	99.58 176	95.62 152	99.28 212	98.37 276
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
HFP-MVS		97.94 67	97.64 102	98.83 29	99.15 83	97.50 33	97.59 96	98.84 137	96.05 142	97.49 188	97.54 229	97.07 63	99.70 118	95.61 153	99.46 163	99.30 133

ACMMPR		97.95 64	97.62 106	98.94 19	99.20 75	97.56 29	97.59 96	98.83 143	96.05 142	97.46 193	97.63 223	96.77 89	99.76 68	95.61 153	99.46 163	99.49 81

UGNet		96.81 163	96.56 175	97.58 125	96.64 343	93.84 171	97.75 82	97.12 302	96.47 122	93.62 354	98.88 79	93.22 212	99.53 193	95.61 153	99.69 82	99.36 124
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
HPM-MVS		98.11 48	97.83 79	98.92 25	99.42 39	97.46 35	98.57 20	99.05 78	95.43 182	97.41 195	97.50 233	97.98 20	99.79 49	95.58 156	99.57 120	99.50 73
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
dcpmvs_2		97.12 140	97.99 63	94.51 316	99.11 92	84.00 375	97.75 82	99.65 13	97.38 86	99.14 40	98.42 127	95.16 161	99.96 2	95.52 157	99.78 59	99.58 44

SR-MVS-dyc-post		98.14 44	97.84 76	99.02 10	98.81 134	98.05 10	97.55 99	98.86 129	97.77 60	98.20 131	98.07 178	96.60 98	99.76 68	95.49 158	99.20 222	99.26 145

RE-MVS-def			97.88 74		98.81 134	98.05 10	97.55 99	98.86 129	97.77 60	98.20 131	98.07 178	96.94 73		95.49 158	99.20 222	99.26 145

Anonymous20240529		97.96 60	98.04 58	97.71 115	98.69 156	94.28 156	97.86 73	98.31 226	98.79 26	99.23 36	98.86 81	95.76 139	99.61 169	95.49 158	99.36 190	99.23 151

RRT-MVS		95.78 210	96.25 192	94.35 322	96.68 342	84.47 369	97.72 86	99.11 59	97.23 92	97.27 199	98.72 90	86.39 317	99.79 49	95.49 158	97.67 341	98.80 229

DVP-MVS		97.78 91	97.65 99	98.16 81	99.24 61	95.51 99	96.74 149	98.23 232	95.92 154	98.40 106	98.28 150	97.06 64	99.71 109	95.48 162	99.52 142	99.26 145
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				98.25 75	99.23 63	95.49 103	96.74 149	98.89 117					99.75 74	95.48 162	99.52 142	99.53 63

region2R		97.92 71	97.59 109	98.92 25	99.22 66	97.55 30	97.60 94	98.84 137	96.00 147	97.22 201	97.62 224	96.87 84	99.76 68	95.48 162	99.43 176	99.46 92

pmmvs-eth3d		96.49 181	96.18 196	97.42 146	98.25 210	94.29 153	94.77 285	98.07 258	89.81 333	97.97 160	98.33 139	93.11 214	99.08 312	95.46 165	99.84 41	98.89 216

SED-MVS		97.94 67	97.90 69	98.07 88	99.22 66	95.35 110	96.79 145	98.83 143	96.11 137	99.08 45	98.24 157	97.87 24	99.72 95	95.44 166	99.51 147	99.14 167

test_241102_TWO								98.83 143	96.11 137	98.62 84	98.24 157	96.92 78	99.72 95	95.44 166	99.49 154	99.49 81

APD-MVS_3200maxsize		98.13 47	97.90 69	98.79 33	98.79 138	97.31 40	97.55 99	98.92 114	97.72 65	98.25 127	98.13 170	97.10 59	99.75 74	95.44 166	99.24 220	99.32 128

xiu_mvs_v1_base_debu		95.62 219	95.96 206	94.60 310	98.01 239	88.42 299	93.99 316	98.21 233	92.98 275	95.91 288	94.53 362	96.39 111	99.72 95	95.43 169	98.19 314	95.64 401

xiu_mvs_v1_base		95.62 219	95.96 206	94.60 310	98.01 239	88.42 299	93.99 316	98.21 233	92.98 275	95.91 288	94.53 362	96.39 111	99.72 95	95.43 169	98.19 314	95.64 401

xiu_mvs_v1_base_debi		95.62 219	95.96 206	94.60 310	98.01 239	88.42 299	93.99 316	98.21 233	92.98 275	95.91 288	94.53 362	96.39 111	99.72 95	95.43 169	98.19 314	95.64 401

c3_l		95.20 241	95.32 225	94.83 301	96.19 357	86.43 342	91.83 378	98.35 221	93.47 253	97.36 196	97.26 254	88.69 293	99.28 276	95.41 172	99.36 190	98.78 232

mvsany_test3		96.21 192	95.93 209	97.05 174	97.40 314	94.33 152	95.76 219	94.20 362	89.10 340	99.36 28	99.60 8	93.97 195	97.85 398	95.40 173	98.63 289	98.99 197

ACMMP		98.05 54	97.75 91	98.93 22	99.23 63	97.60 26	98.09 57	98.96 109	95.75 165	97.91 166	98.06 183	96.89 80	99.76 68	95.32 174	99.57 120	99.43 107
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
miper_lstm_enhance		94.81 259	94.80 253	94.85 299	96.16 359	86.45 341	91.14 394	98.20 236	93.49 252	97.03 220	97.37 247	84.97 330	99.26 280	95.28 175	99.56 123	98.83 225

MSLP-MVS++		96.42 186	96.71 165	95.57 264	97.82 260	90.56 262	95.71 220	98.84 137	94.72 210	96.71 242	97.39 243	94.91 170	98.10 394	95.28 175	99.02 247	98.05 315

SteuartSystems-ACMMP		98.02 56	97.76 89	98.79 33	99.43 37	97.21 45	97.15 121	98.90 116	96.58 113	98.08 147	97.87 202	97.02 68	99.76 68	95.25 177	99.59 114	99.40 111
Skip Steuart: Steuart Systems R&D Blog.
SD-MVS		97.37 129	97.70 92	96.35 225	98.14 229	95.13 124	96.54 161	98.92 114	95.94 152	99.19 38	98.08 176	97.74 29	95.06 421	95.24 178	99.54 133	98.87 222
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
IU-MVS					99.22 66	95.40 105		98.14 249	85.77 381	98.36 112				95.23 179	99.51 147	99.49 81

CP-MVS		97.92 71	97.56 112	98.99 14	98.99 111	97.82 19	97.93 68	98.96 109	96.11 137	96.89 232	97.45 235	96.85 85	99.78 53	95.19 180	99.63 97	99.38 118

LS3D		97.77 92	97.50 119	98.57 51	96.24 353	97.58 28	98.45 31	98.85 133	98.58 32	97.51 186	97.94 196	95.74 140	99.63 157	95.19 180	98.97 250	98.51 263

SMA-MVS		97.48 118	97.11 140	98.60 49	98.83 133	96.67 57	96.74 149	98.73 165	91.61 304	98.48 98	98.36 135	96.53 100	99.68 130	95.17 182	99.54 133	99.45 96
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
CR-MVSNet		93.29 314	92.79 312	94.78 304	95.44 387	88.15 307	96.18 184	97.20 297	84.94 392	94.10 338	98.57 110	77.67 368	99.39 241	95.17 182	95.81 390	96.81 379

OPM-MVS		97.54 114	97.25 132	98.41 61	99.11 92	96.61 60	95.24 261	98.46 203	94.58 218	98.10 144	98.07 178	97.09 61	99.39 241	95.16 184	99.44 167	99.21 153
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
mPP-MVS		97.91 74	97.53 115	99.04 8	99.22 66	97.87 18	97.74 84	98.78 157	96.04 144	97.10 212	97.73 217	96.53 100	99.78 53	95.16 184	99.50 151	99.46 92

DIV-MVS_self_test		94.73 260	94.64 259	95.01 289	95.86 372	87.00 333	91.33 388	98.08 254	93.34 257	97.10 212	97.34 249	84.02 338	99.31 267	95.15 186	99.55 129	98.72 241

cl____		94.73 260	94.64 259	95.01 289	95.85 373	87.00 333	91.33 388	98.08 254	93.34 257	97.10 212	97.33 250	84.01 339	99.30 270	95.14 187	99.56 123	98.71 244

MSP-MVS		97.45 120	96.92 155	99.03 9	99.26 57	97.70 22	97.66 90	98.89 117	95.65 168	98.51 93	96.46 306	92.15 243	99.81 41	95.14 187	98.58 294	99.58 44
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
VDDNet		96.98 149	96.84 158	97.41 147	99.40 43	93.26 194	97.94 67	95.31 348	99.26 9	98.39 108	99.18 43	87.85 307	99.62 162	95.13 189	99.09 239	99.35 126

CANet		95.86 207	95.65 220	96.49 215	96.41 350	90.82 255	94.36 296	98.41 211	94.94 203	92.62 383	96.73 292	92.68 226	99.71 109	95.12 190	99.60 111	98.94 204

CNVR-MVS		96.92 152	96.55 177	98.03 95	98.00 243	95.54 97	94.87 280	98.17 242	94.60 215	96.38 263	97.05 268	95.67 142	99.36 252	95.12 190	99.08 240	99.19 157

eth_miper_zixun_eth		94.89 255	94.93 241	94.75 305	95.99 366	86.12 345	91.35 387	98.49 201	93.40 254	97.12 210	97.25 255	86.87 315	99.35 256	95.08 192	98.82 269	98.78 232

GST-MVS		97.82 87	97.49 120	98.81 31	99.23 63	97.25 42	97.16 120	98.79 153	95.96 149	97.53 184	97.40 239	96.93 75	99.77 63	95.04 193	99.35 195	99.42 108

DP-MVS		97.87 80	97.89 72	97.81 108	98.62 166	94.82 131	97.13 124	98.79 153	98.98 21	98.74 78	98.49 119	95.80 138	99.49 206	95.04 193	99.44 167	99.11 178

D2MVS		95.18 242	95.17 231	95.21 279	97.76 275	87.76 320	94.15 308	97.94 262	89.77 334	96.99 223	97.68 221	87.45 309	99.14 300	95.03 195	99.81 50	98.74 238

SSC-MVS		95.92 204	97.03 147	92.58 370	99.28 55	78.39 407	96.68 156	95.12 351	98.90 23	99.11 42	98.66 98	91.36 258	99.68 130	95.00 196	99.16 228	99.67 32

SR-MVS		98.00 57	97.66 98	99.01 12	98.77 143	97.93 15	97.38 111	98.83 143	97.32 89	98.06 150	97.85 203	96.65 93	99.77 63	95.00 196	99.11 236	99.32 128

FMVSNet2		96.72 169	96.67 168	96.87 190	97.96 245	91.88 234	97.15 121	98.06 259	95.59 172	98.50 95	98.62 104	89.51 287	99.65 147	94.99 198	99.60 111	99.07 185

SDMVSNet		97.97 58	98.26 47	97.11 167	99.41 40	92.21 220	96.92 135	98.60 190	98.58 32	98.78 71	99.39 18	97.80 26	99.62 162	94.98 199	99.86 30	99.52 66

miper_ehance_all_eth		94.69 265	94.70 256	94.64 307	95.77 379	86.22 344	91.32 390	98.24 231	91.67 301	97.05 219	96.65 296	88.39 298	99.22 290	94.88 200	98.34 308	98.49 267

XVG-OURS-SEG-HR		97.38 127	97.07 144	98.30 70	99.01 110	97.41 38	94.66 289	99.02 88	95.20 190	98.15 139	97.52 231	98.83 5	98.43 377	94.87 201	96.41 380	99.07 185

MVS_111021_HR		96.73 168	96.54 179	97.27 156	98.35 199	93.66 180	93.42 337	98.36 218	94.74 208	96.58 252	96.76 291	96.54 99	98.99 323	94.87 201	99.27 214	99.15 163

test_0402		97.84 83	97.97 65	97.47 140	99.19 77	94.07 161	96.71 154	98.73 165	98.66 29	98.56 90	98.41 129	96.84 86	99.69 125	94.82 203	99.81 50	98.64 249

MVS_111021_LR		96.82 162	96.55 177	97.62 123	98.27 207	95.34 112	93.81 326	98.33 222	94.59 217	96.56 254	96.63 297	96.61 96	98.73 347	94.80 204	99.34 198	98.78 232

WR-MVS		96.90 154	96.81 160	97.16 163	98.56 174	92.20 223	94.33 297	98.12 251	97.34 88	98.20 131	97.33 250	92.81 222	99.75 74	94.79 205	99.81 50	99.54 60

ACMH+	93.58 10	98.23 42	98.31 41	97.98 99	99.39 44	95.22 120	97.55 99	99.20 44	98.21 48	99.25 35	98.51 118	98.21 15	99.40 237	94.79 205	99.72 75	99.32 128

thisisatest0530		92.71 323	91.76 332	95.56 266	98.42 194	88.23 304	96.03 197	87.35 419	94.04 236	96.56 254	95.47 345	64.03 412	99.77 63	94.78 207	99.11 236	98.68 248

PGM-MVS		97.88 78	97.52 116	98.96 17	99.20 75	97.62 25	97.09 126	99.06 74	95.45 179	97.55 183	97.94 196	97.11 58	99.78 53	94.77 208	99.46 163	99.48 87

TSAR-MVS + GP.		96.47 183	96.12 197	97.49 138	97.74 280	95.23 117	94.15 308	96.90 311	93.26 260	98.04 153	96.70 293	94.41 184	98.89 333	94.77 208	99.14 230	98.37 276

Syy-MVS		92.09 334	91.80 331	92.93 362	95.19 393	82.65 383	92.46 362	91.35 394	90.67 321	91.76 391	87.61 423	85.64 325	98.50 372	94.73 210	96.84 366	97.65 345

VNet		96.84 158	96.83 159	96.88 189	98.06 235	92.02 230	96.35 172	97.57 288	97.70 67	97.88 169	97.80 210	92.40 239	99.54 191	94.73 210	98.96 251	99.08 183

APD_test1		97.95 64	97.68 96	98.75 35	99.60 16	98.60 6	97.21 119	99.08 70	96.57 116	98.07 149	98.38 133	96.22 121	99.14 300	94.71 212	99.31 208	98.52 262

VPNet		97.26 135	97.49 120	96.59 207	99.47 33	90.58 260	96.27 176	98.53 197	97.77 60	98.46 101	98.41 129	94.59 178	99.68 130	94.61 213	99.29 211	99.52 66

GBi-Net		96.99 146	96.80 161	97.56 126	97.96 245	93.67 177	98.23 46	98.66 182	95.59 172	97.99 156	99.19 39	89.51 287	99.73 89	94.60 214	99.44 167	99.30 133

test1		96.99 146	96.80 161	97.56 126	97.96 245	93.67 177	98.23 46	98.66 182	95.59 172	97.99 156	99.19 39	89.51 287	99.73 89	94.60 214	99.44 167	99.30 133

FMVSNet3		95.26 239	94.94 239	96.22 232	96.53 346	90.06 264	95.99 202	97.66 280	94.11 233	97.99 156	97.91 200	80.22 359	99.63 157	94.60 214	99.44 167	98.96 200

SF-MVS		97.60 108	97.39 123	98.22 77	98.93 121	95.69 91	97.05 128	99.10 62	95.32 186	97.83 175	97.88 201	96.44 108	99.72 95	94.59 217	99.39 185	99.25 149

XXY-MVS		97.54 114	97.70 92	97.07 173	99.46 34	92.21 220	97.22 118	99.00 99	94.93 205	98.58 89	98.92 73	97.31 47	99.41 235	94.44 218	99.43 176	99.59 43

UnsupCasMVSNet_eth		95.91 205	95.73 217	96.44 217	98.48 187	91.52 242	95.31 257	98.45 204	95.76 163	97.48 190	97.54 229	89.53 286	98.69 353	94.43 219	94.61 405	99.13 169

LPG-MVS_test		97.94 67	97.67 97	98.74 38	99.15 83	97.02 46	97.09 126	99.02 88	95.15 193	98.34 116	98.23 159	97.91 22	99.70 118	94.41 220	99.73 71	99.50 73

LGP-MVS_train				98.74 38	99.15 83	97.02 46		99.02 88	95.15 193	98.34 116	98.23 159	97.91 22	99.70 118	94.41 220	99.73 71	99.50 73

DeepPCF-MVS	94.58 5	96.90 154	96.43 185	98.31 69	97.48 306	97.23 44	92.56 359	98.60 190	92.84 281	98.54 91	97.40 239	96.64 95	98.78 342	94.40 222	99.41 183	98.93 208

XVG-ACMP-BASELINE		97.58 112	97.28 131	98.49 56	99.16 80	96.90 50	96.39 166	98.98 105	95.05 199	98.06 150	98.02 187	95.86 129	99.56 184	94.37 223	99.64 95	99.00 194

RPSCF		97.87 80	97.51 117	98.95 18	99.15 83	98.43 7	97.56 98	99.06 74	96.19 134	98.48 98	98.70 95	94.72 172	99.24 286	94.37 223	99.33 203	99.17 160

CSCG		97.40 126	97.30 128	97.69 119	98.95 116	94.83 130	97.28 114	98.99 102	96.35 127	98.13 141	95.95 332	95.99 125	99.66 145	94.36 225	99.73 71	98.59 255

HPM-MVS++		96.99 146	96.38 187	98.81 31	98.64 160	97.59 27	95.97 204	98.20 236	95.51 176	95.06 315	96.53 302	94.10 191	99.70 118	94.29 226	99.15 229	99.13 169

XVG-OURS		97.12 140	96.74 164	98.26 72	98.99 111	97.45 36	93.82 324	99.05 78	95.19 191	98.32 120	97.70 219	95.22 158	98.41 378	94.27 227	98.13 317	98.93 208

jason		94.39 280	94.04 287	95.41 275	98.29 203	87.85 317	92.74 354	96.75 317	85.38 386	95.29 310	96.15 321	88.21 301	99.65 147	94.24 228	99.34 198	98.74 238
jason: jason.
CVMVSNet		92.33 329	92.79 312	90.95 390	97.26 324	75.84 421	95.29 259	92.33 385	81.86 403	96.27 271	98.19 164	81.44 351	98.46 376	94.23 229	98.29 311	98.55 259

EIA-MVS		96.04 199	95.77 216	96.85 191	97.80 265	92.98 199	96.12 190	99.16 49	94.65 213	93.77 349	91.69 403	95.68 141	99.67 139	94.18 230	98.85 265	97.91 325

ET-MVSNet_ETH3D		91.12 348	89.67 362	95.47 271	96.41 350	89.15 286	91.54 383	90.23 409	89.07 341	86.78 423	92.84 387	69.39 406	99.44 222	94.16 231	96.61 376	97.82 332

cl22		93.25 315	92.84 311	94.46 318	94.30 406	86.00 346	91.09 396	96.64 322	90.74 318	95.79 294	96.31 315	78.24 365	98.77 343	94.15 232	98.34 308	98.62 252

MCST-MVS		96.24 191	95.80 214	97.56 126	98.75 145	94.13 160	94.66 289	98.17 242	90.17 329	96.21 276	96.10 326	95.14 162	99.43 224	94.13 233	98.85 265	99.13 169

COLMAP_ROB	94.48 6	98.25 41	98.11 51	98.64 47	99.21 73	97.35 39	97.96 64	99.16 49	98.34 40	98.78 71	98.52 116	97.32 46	99.45 219	94.08 234	99.67 89	99.13 169
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous202405211		96.34 188	95.98 205	97.43 144	98.25 210	93.85 170	96.74 149	94.41 360	97.72 65	98.37 109	98.03 186	87.15 312	99.53 193	94.06 235	99.07 242	98.92 211

Effi-MVS+-dtu		96.81 163	96.09 199	98.99 14	96.90 339	98.69 5	96.42 165	98.09 253	95.86 159	95.15 313	95.54 343	94.26 188	99.81 41	94.06 235	98.51 299	98.47 268

ambc				96.56 211	98.23 213	91.68 240	97.88 72	98.13 250		98.42 104	98.56 112	94.22 189	99.04 317	94.05 237	99.35 195	98.95 202

our_test_3		94.20 287	94.58 266	93.07 354	96.16 359	81.20 396	90.42 403	96.84 312	90.72 319	97.14 208	97.13 261	90.47 269	99.11 307	94.04 238	98.25 312	98.91 212

pmmvs5		94.63 270	94.34 277	95.50 269	97.63 296	88.34 302	94.02 314	97.13 301	87.15 365	95.22 312	97.15 260	87.50 308	99.27 279	93.99 239	99.26 216	98.88 220

DPE-MVS		97.64 103	97.35 126	98.50 55	98.85 132	96.18 73	95.21 263	98.99 102	95.84 160	98.78 71	98.08 176	96.84 86	99.81 41	93.98 240	99.57 120	99.52 66
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ppachtmachnet_test		94.49 277	94.84 249	93.46 343	96.16 359	82.10 387	90.59 401	97.48 290	90.53 323	97.01 222	97.59 226	91.01 262	99.36 252	93.97 241	99.18 226	98.94 204

tfpnnormal		97.72 96	97.97 65	96.94 182	99.26 57	92.23 219	97.83 76	98.45 204	98.25 46	99.13 41	98.66 98	96.65 93	99.69 125	93.92 242	99.62 99	98.91 212

LFMVS		95.32 236	94.88 246	96.62 205	98.03 236	91.47 243	97.65 91	90.72 403	99.11 12	97.89 168	98.31 141	79.20 361	99.48 209	93.91 243	99.12 235	98.93 208

EPP-MVSNet		96.84 158	96.58 173	97.65 121	99.18 78	93.78 174	98.68 14	96.34 323	97.91 57	97.30 197	98.06 183	88.46 296	99.85 29	93.85 244	99.40 184	99.32 128

Fast-Effi-MVS+-dtu		96.44 184	96.12 197	97.39 149	97.18 327	94.39 147	95.46 240	98.73 165	96.03 146	94.72 323	94.92 356	96.28 119	99.69 125	93.81 245	97.98 322	98.09 305

PHI-MVS		96.96 150	96.53 180	98.25 75	97.48 306	96.50 63	96.76 147	98.85 133	93.52 251	96.19 278	96.85 282	95.94 126	99.42 226	93.79 246	99.43 176	98.83 225

miper_enhance_ethall		93.14 317	92.78 314	94.20 328	93.65 416	85.29 355	89.97 407	97.85 267	85.05 388	96.15 281	94.56 361	85.74 322	99.14 300	93.74 247	98.34 308	98.17 302

DeepC-MVS_fast	94.34 7	96.74 166	96.51 182	97.44 143	97.69 284	94.15 159	96.02 198	98.43 207	93.17 269	97.30 197	97.38 245	95.48 148	99.28 276	93.74 247	99.34 198	98.88 220
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AUN-MVS		93.95 297	92.69 316	97.74 113	97.80 265	95.38 107	95.57 237	95.46 344	91.26 313	92.64 381	96.10 326	74.67 386	99.55 188	93.72 249	96.97 361	98.30 287

MP-MVS		97.64 103	97.18 138	99.00 13	99.32 53	97.77 21	97.49 105	98.73 165	96.27 128	95.59 303	97.75 214	96.30 116	99.78 53	93.70 250	99.48 158	99.45 96
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PVSNet_Blended_VisFu		95.95 203	95.80 214	96.42 219	99.28 55	90.62 259	95.31 257	99.08 70	88.40 352	96.97 227	98.17 167	92.11 245	99.78 53	93.64 251	99.21 221	98.86 223

lupinMVS		93.77 298	93.28 301	95.24 278	97.68 285	87.81 318	92.12 372	96.05 326	84.52 395	94.48 330	95.06 352	86.90 313	99.63 157	93.62 252	99.13 232	98.27 291

NCCC		96.52 180	95.99 204	98.10 87	97.81 261	95.68 92	95.00 276	98.20 236	95.39 183	95.40 309	96.36 313	93.81 199	99.45 219	93.55 253	98.42 305	99.17 160

test_vis1_rt		94.03 294	93.65 295	95.17 282	95.76 380	93.42 188	93.97 319	98.33 222	84.68 393	93.17 368	95.89 334	92.53 236	94.79 422	93.50 254	94.97 401	97.31 362

WB-MVS		95.50 223	96.62 169	92.11 380	99.21 73	77.26 417	96.12 190	95.40 346	98.62 30	98.84 66	98.26 155	91.08 261	99.50 201	93.37 255	98.70 282	99.58 44

ETV-MVS		96.13 196	95.90 210	96.82 194	97.76 275	93.89 168	95.40 246	98.95 111	95.87 158	95.58 304	91.00 409	96.36 114	99.72 95	93.36 256	98.83 268	96.85 375

FA-MVS(test-final)		94.91 253	94.89 244	94.99 291	97.51 304	88.11 311	98.27 44	95.20 350	92.40 291	96.68 243	98.60 107	83.44 341	99.28 276	93.34 257	98.53 295	97.59 350

MDA-MVSNet_test_wron		94.73 260	94.83 251	94.42 319	97.48 306	85.15 358	90.28 405	95.87 333	92.52 286	97.48 190	97.76 211	91.92 252	99.17 297	93.32 258	96.80 370	98.94 204

YYNet1		94.73 260	94.84 249	94.41 320	97.47 310	85.09 360	90.29 404	95.85 334	92.52 286	97.53 184	97.76 211	91.97 249	99.18 293	93.31 259	96.86 365	98.95 202

pmmvs4		94.82 258	94.19 282	96.70 202	97.42 313	92.75 207	92.09 374	96.76 316	86.80 371	95.73 299	97.22 256	89.28 290	98.89 333	93.28 260	99.14 230	98.46 270

CANet_DTU		94.65 269	94.21 281	95.96 244	95.90 369	89.68 273	93.92 321	97.83 271	93.19 265	90.12 405	95.64 340	88.52 295	99.57 182	93.27 261	99.47 160	98.62 252

ACMP	92.54 13	97.47 119	97.10 141	98.55 53	99.04 107	96.70 55	96.24 181	98.89 117	93.71 243	97.97 160	97.75 214	97.44 41	99.63 157	93.22 262	99.70 81	99.32 128
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Effi-MVS+		96.19 193	96.01 202	96.71 201	97.43 312	92.19 224	96.12 190	99.10 62	95.45 179	93.33 366	94.71 359	97.23 56	99.56 184	93.21 263	97.54 347	98.37 276

MDA-MVSNet-bldmvs		95.69 215	95.67 218	95.74 256	98.48 187	88.76 297	92.84 349	97.25 295	96.00 147	97.59 182	97.95 195	91.38 257	99.46 214	93.16 264	96.35 382	98.99 197

IS-MVSNet		96.93 151	96.68 167	97.70 117	99.25 60	94.00 165	98.57 20	96.74 318	98.36 39	98.14 140	97.98 192	88.23 300	99.71 109	93.10 265	99.72 75	99.38 118

9.14			96.69 166		98.53 178		96.02 198	98.98 105	93.23 261	97.18 206	97.46 234	96.47 105	99.62 162	92.99 266	99.32 205

MS-PatchMatch		94.83 257	94.91 243	94.57 313	96.81 340	87.10 332	94.23 303	97.34 294	88.74 347	97.14 208	97.11 264	91.94 251	98.23 390	92.99 266	97.92 325	98.37 276

Patchmtry		95.03 250	94.59 265	96.33 226	94.83 400	90.82 255	96.38 169	97.20 297	96.59 112	97.49 188	98.57 110	77.67 368	99.38 244	92.95 268	99.62 99	98.80 229

sd_testset		97.97 58	98.12 50	97.51 131	99.41 40	93.44 186	97.96 64	98.25 229	98.58 32	98.78 71	99.39 18	98.21 15	99.56 184	92.65 269	99.86 30	99.52 66

Fast-Effi-MVS+		95.49 224	95.07 235	96.75 199	97.67 289	92.82 201	94.22 304	98.60 190	91.61 304	93.42 364	92.90 384	96.73 91	99.70 118	92.60 270	97.89 328	97.74 339

HQP_MVS		96.66 174	96.33 190	97.68 120	98.70 154	94.29 153	96.50 162	98.75 162	96.36 125	96.16 279	96.77 289	91.91 253	99.46 214	92.59 271	99.20 222	99.28 140

plane_prior5								98.75 162					99.46 214	92.59 271	99.20 222	99.28 140

mvsany_test1		93.47 308	93.03 305	94.79 303	94.05 413	92.12 225	90.82 399	90.01 412	85.02 390	97.26 200	98.28 150	93.57 205	97.03 407	92.51 273	95.75 395	95.23 407

GA-MVS		92.83 321	92.15 326	94.87 298	96.97 334	87.27 329	90.03 406	96.12 325	91.83 300	94.05 341	94.57 360	76.01 380	98.97 329	92.46 274	97.34 356	98.36 281

mvsmamba		94.91 253	94.41 275	96.40 223	97.65 292	91.30 246	97.92 69	95.32 347	91.50 307	95.54 305	98.38 133	83.06 344	99.68 130	92.46 274	97.84 329	98.23 294

CPTT-MVS		96.69 172	96.08 200	98.49 56	98.89 127	96.64 59	97.25 115	98.77 158	92.89 280	96.01 285	97.13 261	92.23 241	99.67 139	92.24 276	99.34 198	99.17 160

EPNet		93.72 300	92.62 319	97.03 178	87.61 434	92.25 218	96.27 176	91.28 396	96.74 106	87.65 419	97.39 243	85.00 329	99.64 153	92.14 277	99.48 158	99.20 156
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PC_three_1452									87.24 364	98.37 109	97.44 236	97.00 69	96.78 413	92.01 278	99.25 217	99.21 153

APD-MVS		97.00 145	96.53 180	98.41 61	98.55 175	96.31 70	96.32 174	98.77 158	92.96 279	97.44 194	97.58 228	95.84 130	99.74 83	91.96 279	99.35 195	99.19 157
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CL-MVSNet_self_test		95.04 248	94.79 254	95.82 252	97.51 304	89.79 271	91.14 394	96.82 314	93.05 272	96.72 241	96.40 311	90.82 265	99.16 298	91.95 280	98.66 286	98.50 266

test_prior2							93.33 341		94.21 227	94.02 343	96.25 317	93.64 204		91.90 281	98.96 251

test-LLR		89.97 362	89.90 360	90.16 394	94.24 408	74.98 423	89.89 408	89.06 413	92.02 295	89.97 406	90.77 411	73.92 389	98.57 365	91.88 282	97.36 354	96.92 370

test-mter		87.92 384	87.17 384	90.16 394	94.24 408	74.98 423	89.89 408	89.06 413	86.44 374	89.97 406	90.77 411	54.96 432	98.57 365	91.88 282	97.36 354	96.92 370

MVP-Stereo		95.69 215	95.28 226	96.92 184	98.15 227	93.03 198	95.64 232	98.20 236	90.39 325	96.63 249	97.73 217	91.63 255	99.10 310	91.84 284	97.31 357	98.63 251
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
testing3		89.72 366	88.26 375	94.10 331	97.66 290	84.30 373	94.80 282	88.25 417	94.66 212	95.07 314	92.51 393	41.15 436	99.43 224	91.81 285	98.44 304	98.55 259

1112_ss		94.12 288	93.42 299	96.23 230	98.59 170	90.85 254	94.24 302	98.85 133	85.49 382	92.97 372	94.94 354	86.01 320	99.64 153	91.78 286	97.92 325	98.20 298

train_agg		95.46 228	94.66 257	97.88 104	97.84 257	95.23 117	93.62 331	98.39 214	87.04 366	93.78 347	95.99 328	94.58 179	99.52 196	91.76 287	98.90 258	98.89 216

LF4IMVS		96.07 197	95.63 221	97.36 150	98.19 217	95.55 96	95.44 241	98.82 151	92.29 292	95.70 300	96.55 300	92.63 229	98.69 353	91.75 288	99.33 203	97.85 330

N_pmnet		95.18 242	94.23 279	98.06 90	97.85 252	96.55 62	92.49 360	91.63 391	89.34 337	98.09 145	97.41 238	90.33 273	99.06 314	91.58 289	99.31 208	98.56 257

AllTest		97.20 138	96.92 155	98.06 90	99.08 96	96.16 74	97.14 123	99.16 49	94.35 224	97.78 177	98.07 178	95.84 130	99.12 304	91.41 290	99.42 179	98.91 212

TestCases				98.06 90	99.08 96	96.16 74		99.16 49	94.35 224	97.78 177	98.07 178	95.84 130	99.12 304	91.41 290	99.42 179	98.91 212

test9_res														91.29 292	98.89 261	99.00 194

xiu_mvs_v2_base		94.22 283	94.63 261	92.99 359	97.32 322	84.84 365	92.12 372	97.84 269	91.96 297	94.17 336	93.43 375	96.07 124	99.71 109	91.27 293	97.48 350	94.42 411

PS-MVSNAJ		94.10 289	94.47 271	93.00 358	97.35 317	84.88 362	91.86 377	97.84 269	91.96 297	94.17 336	92.50 394	95.82 133	99.71 109	91.27 293	97.48 350	94.40 412

tpm		91.08 351	90.85 348	91.75 383	95.33 391	78.09 409	95.03 275	91.27 397	88.75 346	93.53 359	97.40 239	71.24 399	99.30 270	91.25 295	93.87 409	97.87 329

OPU-MVS				97.64 122	98.01 239	95.27 115	96.79 145				97.35 248	96.97 71	98.51 371	91.21 296	99.25 217	99.14 167

ZD-MVS					98.43 193	95.94 83		98.56 196	90.72 319	96.66 246	97.07 266	95.02 166	99.74 83	91.08 297	98.93 256

tpmrst		90.31 356	90.61 354	89.41 399	94.06 412	72.37 430	95.06 272	93.69 365	88.01 357	92.32 386	96.86 281	77.45 370	98.82 338	91.04 298	87.01 424	97.04 367

sss		94.22 283	93.72 294	95.74 256	97.71 283	89.95 267	93.84 323	96.98 308	88.38 353	93.75 350	95.74 336	87.94 302	98.89 333	91.02 299	98.10 318	98.37 276

ttmdpeth		94.05 292	94.15 284	93.75 336	95.81 376	85.32 353	96.00 200	94.93 354	92.07 293	94.19 335	99.09 55	85.73 323	96.41 417	90.98 300	98.52 296	99.53 63

ITE_SJBPF				97.85 106	98.64 160	96.66 58		98.51 200	95.63 169	97.22 201	97.30 252	95.52 147	98.55 368	90.97 301	98.90 258	98.34 282

Test_1112_low_res		93.53 307	92.86 309	95.54 268	98.60 168	88.86 293	92.75 352	98.69 175	82.66 402	92.65 380	96.92 279	84.75 331	99.56 184	90.94 302	97.76 333	98.19 299

TESTMET0.1,1		87.20 390	86.57 390	89.07 401	93.62 417	72.84 429	89.89 408	87.01 421	85.46 384	89.12 413	90.20 414	56.00 425	97.72 401	90.91 303	96.92 362	96.64 383

FMVSNet5		93.39 310	92.35 321	96.50 214	95.83 374	90.81 257	97.31 112	98.27 227	92.74 283	96.27 271	98.28 150	62.23 413	99.67 139	90.86 304	99.36 190	99.03 190

PatchmatchNet		91.98 338	91.87 328	92.30 376	94.60 403	79.71 403	95.12 265	93.59 370	89.52 336	93.61 355	97.02 270	77.94 366	99.18 293	90.84 305	94.57 407	98.01 319
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CLD-MVS		95.47 227	95.07 235	96.69 203	98.27 207	92.53 210	91.36 386	98.67 180	91.22 314	95.78 296	94.12 369	95.65 143	98.98 325	90.81 306	99.72 75	98.57 256
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
cascas		91.89 339	91.35 337	93.51 342	94.27 407	85.60 349	88.86 416	98.61 189	79.32 415	92.16 387	91.44 405	89.22 291	98.12 393	90.80 307	97.47 352	96.82 378

MonoMVSNet		93.30 313	93.96 291	91.33 388	94.14 411	81.33 395	97.68 89	96.69 320	95.38 184	96.32 266	98.42 127	84.12 337	96.76 414	90.78 308	92.12 415	95.89 396

test20.03		96.58 178	96.61 171	96.48 216	98.49 185	91.72 238	95.68 224	97.69 277	96.81 103	98.27 126	97.92 199	94.18 190	98.71 350	90.78 308	99.66 92	99.00 194

test_yl		94.40 278	94.00 288	95.59 262	96.95 335	89.52 277	94.75 286	95.55 342	96.18 135	96.79 235	96.14 323	81.09 354	99.18 293	90.75 310	97.77 331	98.07 308

DCV-MVSNet		94.40 278	94.00 288	95.59 262	96.95 335	89.52 277	94.75 286	95.55 342	96.18 135	96.79 235	96.14 323	81.09 354	99.18 293	90.75 310	97.77 331	98.07 308

EPMVS		89.26 370	88.55 372	91.39 387	92.36 425	79.11 406	95.65 228	79.86 429	88.60 349	93.12 369	96.53 302	70.73 403	98.10 394	90.75 310	89.32 421	96.98 368

旧先验2							93.35 340		77.95 420	95.77 298			98.67 357	90.74 313

USDC		94.56 273	94.57 268	94.55 314	97.78 273	86.43 342	92.75 352	98.65 187	85.96 377	96.91 231	97.93 198	90.82 265	98.74 346	90.71 314	99.59 114	98.47 268

OpenMVS	94.22 8	95.48 226	95.20 228	96.32 227	97.16 328	91.96 232	97.74 84	98.84 137	87.26 363	94.36 332	98.01 189	93.95 196	99.67 139	90.70 315	98.75 275	97.35 360

testing3-2		90.09 358	90.38 357	89.24 400	98.07 234	69.88 433	95.12 265	90.71 404	96.65 108	93.60 357	94.03 370	55.81 426	99.33 261	90.69 316	98.71 280	98.51 263

Patchmatch-test		93.60 305	93.25 302	94.63 308	96.14 363	87.47 324	96.04 196	94.50 359	93.57 248	96.47 259	96.97 274	76.50 376	98.61 362	90.67 317	98.41 306	97.81 334

thisisatest0515		90.43 355	89.18 368	94.17 330	97.07 332	85.44 351	89.75 412	87.58 418	88.28 354	93.69 353	91.72 402	65.27 410	99.58 176	90.59 318	98.67 284	97.50 355

DP-MVS Recon		95.55 222	95.13 232	96.80 195	98.51 181	93.99 166	94.60 291	98.69 175	90.20 328	95.78 296	96.21 319	92.73 225	98.98 325	90.58 319	98.86 264	97.42 357

TinyColmap		96.00 202	96.34 189	94.96 293	97.90 250	87.91 314	94.13 311	98.49 201	94.41 222	98.16 137	97.76 211	96.29 118	98.68 356	90.52 320	99.42 179	98.30 287

BP-MVS														90.51 321

HQP-MVS		95.17 244	94.58 266	96.92 184	97.85 252	92.47 213	94.26 298	98.43 207	93.18 266	92.86 374	95.08 350	90.33 273	99.23 288	90.51 321	98.74 276	99.05 189

OMC-MVS		96.48 182	96.00 203	97.91 102	98.30 202	96.01 82	94.86 281	98.60 190	91.88 299	97.18 206	97.21 257	96.11 123	99.04 317	90.49 323	99.34 198	98.69 245

ab-mvs		96.59 176	96.59 172	96.60 206	98.64 160	92.21 220	98.35 35	97.67 278	94.45 221	96.99 223	98.79 83	94.96 169	99.49 206	90.39 324	99.07 242	98.08 306

HyFIR lowres test		93.72 300	92.65 317	96.91 186	98.93 121	91.81 237	91.23 392	98.52 198	82.69 401	96.46 260	96.52 304	80.38 358	99.90 16	90.36 325	98.79 271	99.03 190

agg_prior2														90.34 326	98.90 258	99.10 182

LCM-MVSNet-Re		97.33 132	97.33 127	97.32 153	98.13 232	93.79 173	96.99 132	99.65 13	96.74 106	99.47 19	98.93 71	96.91 79	99.84 32	90.11 327	99.06 245	98.32 283

CDS-MVSNet		94.88 256	94.12 285	97.14 165	97.64 295	93.57 182	93.96 320	97.06 305	90.05 330	96.30 270	96.55 300	86.10 319	99.47 211	90.10 328	99.31 208	98.40 272
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CDPH-MVS		95.45 229	94.65 258	97.84 107	98.28 205	94.96 128	93.73 328	98.33 222	85.03 389	95.44 307	96.60 298	95.31 155	99.44 222	90.01 329	99.13 232	99.11 178

baseline1		93.14 317	92.64 318	94.62 309	97.34 319	87.20 330	96.67 158	93.02 374	94.71 211	96.51 258	95.83 335	81.64 349	98.60 364	90.00 330	88.06 423	98.07 308

WBMVS		91.11 349	90.72 351	92.26 377	95.99 366	77.98 412	91.47 384	95.90 332	91.63 302	95.90 291	96.45 307	59.60 415	99.46 214	89.97 331	99.59 114	99.33 127

TAPA-MVS	93.32 12	94.93 252	94.23 279	97.04 176	98.18 220	94.51 143	95.22 262	98.73 165	81.22 408	96.25 273	95.95 332	93.80 200	98.98 325	89.89 332	98.87 262	97.62 347
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PMMVS		92.39 326	91.08 343	96.30 229	93.12 420	92.81 203	90.58 402	95.96 330	79.17 416	91.85 390	92.27 395	90.29 277	98.66 358	89.85 333	96.68 375	97.43 356

PVSNet_BlendedMVS		95.02 251	94.93 241	95.27 277	97.79 270	87.40 326	94.14 310	98.68 177	88.94 344	94.51 328	98.01 189	93.04 216	99.30 270	89.77 334	99.49 154	99.11 178

PVSNet_Blended		93.96 295	93.65 295	94.91 294	97.79 270	87.40 326	91.43 385	98.68 177	84.50 396	94.51 328	94.48 365	93.04 216	99.30 270	89.77 334	98.61 291	98.02 318

MSDG		95.33 235	95.13 232	95.94 248	97.40 314	91.85 235	91.02 397	98.37 217	95.30 187	96.31 269	95.99 328	94.51 182	98.38 381	89.59 336	97.65 344	97.60 349

PMVS	89.60 17	96.71 171	96.97 150	95.95 246	99.51 28	97.81 20	97.42 110	97.49 289	97.93 56	95.95 286	98.58 108	96.88 82	96.91 410	89.59 336	99.36 190	93.12 419
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_post1							94.98 277				10.37 435	76.21 379	99.04 317	89.47 338

SCA		93.38 311	93.52 298	92.96 360	96.24 353	81.40 394	93.24 343	94.00 363	91.58 306	94.57 326	96.97 274	87.94 302	99.42 226	89.47 338	97.66 343	98.06 312

tpmvs		90.79 354	90.87 347	90.57 393	92.75 424	76.30 419	95.79 218	93.64 369	91.04 316	91.91 389	96.26 316	77.19 374	98.86 337	89.38 340	89.85 420	96.56 386

Anonymous20231206		95.27 238	95.06 237	95.88 250	98.72 149	89.37 281	95.70 221	97.85 267	88.00 358	96.98 226	97.62 224	91.95 250	99.34 259	89.21 341	99.53 137	98.94 204

CHOSEN 1792x2688		94.10 289	93.41 300	96.18 235	99.16 80	90.04 265	92.15 371	98.68 177	79.90 413	96.22 275	97.83 204	87.92 306	99.42 226	89.18 342	99.65 93	99.08 183

114514_t		93.96 295	93.22 303	96.19 234	99.06 100	90.97 253	95.99 202	98.94 112	73.88 426	93.43 363	96.93 277	92.38 240	99.37 249	89.09 343	99.28 212	98.25 293

pmmvs3		90.00 360	88.90 370	93.32 345	94.20 410	85.34 352	91.25 391	92.56 383	78.59 417	93.82 346	95.17 349	67.36 409	98.69 353	89.08 344	98.03 321	95.92 395

testdata				95.70 259	98.16 225	90.58 260		97.72 276	80.38 411	95.62 301	97.02 270	92.06 248	98.98 325	89.06 345	98.52 296	97.54 352

MDTV_nov1_ep13			91.28 339		94.31 405	73.51 428	94.80 282	93.16 373	86.75 372	93.45 362	97.40 239	76.37 377	98.55 368	88.85 346	96.43 379

PMMVS2		93.66 303	94.07 286	92.45 374	97.57 299	80.67 400	86.46 419	96.00 328	93.99 237	97.10 212	97.38 245	89.90 280	97.82 399	88.76 347	99.47 160	98.86 223

QAPM		95.88 206	95.57 223	96.80 195	97.90 250	91.84 236	98.18 53	98.73 165	88.41 351	96.42 261	98.13 170	94.73 171	99.75 74	88.72 348	98.94 254	98.81 228

CHOSEN 280x420		89.98 361	89.19 367	92.37 375	95.60 384	81.13 397	86.22 420	97.09 303	81.44 407	87.44 420	93.15 376	73.99 387	99.47 211	88.69 349	99.07 242	96.52 387

testgi		96.07 197	96.50 183	94.80 302	99.26 57	87.69 321	95.96 206	98.58 194	95.08 196	98.02 155	96.25 317	97.92 21	97.60 403	88.68 350	98.74 276	99.11 178

CostFormer		89.75 365	89.25 363	91.26 389	94.69 402	78.00 411	95.32 256	91.98 388	81.50 406	90.55 398	96.96 276	71.06 401	98.89 333	88.59 351	92.63 413	96.87 373

UnsupCasMVSNet_bld		94.72 264	94.26 278	96.08 240	98.62 166	90.54 263	93.38 339	98.05 260	90.30 326	97.02 221	96.80 288	89.54 284	99.16 298	88.44 352	96.18 386	98.56 257

TAMVS		95.49 224	94.94 239	97.16 163	98.31 201	93.41 189	95.07 271	96.82 314	91.09 315	97.51 186	97.82 207	89.96 279	99.42 226	88.42 353	99.44 167	98.64 249

Vis-MVSNet (Re-imp)		95.11 245	94.85 248	95.87 251	99.12 91	89.17 284	97.54 104	94.92 355	96.50 118	96.58 252	97.27 253	83.64 340	99.48 209	88.42 353	99.67 89	98.97 199

EPNet_dtu		91.39 347	90.75 350	93.31 346	90.48 430	82.61 384	94.80 282	92.88 376	93.39 255	81.74 428	94.90 357	81.36 352	99.11 307	88.28 355	98.87 262	98.21 297
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
JIA-IIPM		91.79 341	90.69 352	95.11 283	93.80 415	90.98 252	94.16 307	91.78 390	96.38 123	90.30 402	99.30 29	72.02 398	98.90 332	88.28 355	90.17 419	95.45 405

新几何1				97.25 159	98.29 203	94.70 135		97.73 275	77.98 419	94.83 322	96.67 295	92.08 247	99.45 219	88.17 357	98.65 288	97.61 348

testdata2													99.46 214	87.84 358

FE-MVS		92.95 319	92.22 324	95.11 283	97.21 326	88.33 303	98.54 23	93.66 368	89.91 332	96.21 276	98.14 168	70.33 404	99.50 201	87.79 359	98.24 313	97.51 353

无先验							93.20 344	97.91 263	80.78 409				99.40 237	87.71 360		97.94 324

WTY-MVS		93.55 306	93.00 307	95.19 280	97.81 261	87.86 315	93.89 322	96.00 328	89.02 342	94.07 340	95.44 347	86.27 318	99.33 261	87.69 361	96.82 368	98.39 274

原ACMM1				96.58 208	98.16 225	92.12 225		98.15 248	85.90 379	93.49 360	96.43 308	92.47 238	99.38 244	87.66 362	98.62 290	98.23 294

BH-untuned		94.69 265	94.75 255	94.52 315	97.95 248	87.53 323	94.07 313	97.01 307	93.99 237	97.10 212	95.65 339	92.65 228	98.95 330	87.60 363	96.74 371	97.09 365

PAPM_NR		94.61 271	94.17 283	95.96 244	98.36 198	91.23 248	95.93 209	97.95 261	92.98 275	93.42 364	94.43 366	90.53 268	98.38 381	87.60 363	96.29 384	98.27 291

testing99		89.21 371	88.04 377	92.70 368	95.78 378	81.00 398	92.65 357	92.03 386	93.20 264	89.90 408	90.08 417	55.25 428	99.14 300	87.54 365	95.95 389	97.97 321

DPM-MVS		93.68 302	92.77 315	96.42 219	97.91 249	92.54 209	91.17 393	97.47 291	84.99 391	93.08 370	94.74 358	89.90 280	99.00 321	87.54 365	98.09 319	97.72 342

MG-MVS		94.08 291	94.00 288	94.32 324	97.09 331	85.89 347	93.19 345	95.96 330	92.52 286	94.93 321	97.51 232	89.54 284	98.77 343	87.52 367	97.71 337	98.31 285

F-COLMAP		95.30 237	94.38 276	98.05 94	98.64 160	96.04 79	95.61 234	98.66 182	89.00 343	93.22 367	96.40 311	92.90 221	99.35 256	87.45 368	97.53 348	98.77 235

PatchMatch-RL		94.61 271	93.81 293	97.02 179	98.19 217	95.72 89	93.66 329	97.23 296	88.17 356	94.94 320	95.62 341	91.43 256	98.57 365	87.36 369	97.68 340	96.76 381

testing11		88.93 373	87.63 382	92.80 365	95.87 371	81.49 393	92.48 361	91.54 392	91.62 303	88.27 417	90.24 413	55.12 431	99.11 307	87.30 370	96.28 385	97.81 334

IB-MVS	85.98 20	88.63 376	86.95 388	93.68 339	95.12 395	84.82 366	90.85 398	90.17 410	87.55 362	88.48 416	91.34 406	58.01 417	99.59 173	87.24 371	93.80 410	96.63 385
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
testing91		89.67 367	88.55 372	93.04 355	95.90 369	81.80 391	92.71 356	93.71 364	93.71 243	90.18 403	90.15 415	57.11 419	99.22 290	87.17 372	96.32 383	98.12 304

dp		88.08 382	88.05 376	88.16 407	92.85 422	68.81 434	94.17 306	92.88 376	85.47 383	91.38 394	96.14 323	68.87 407	98.81 340	86.88 373	83.80 427	96.87 373

1314		92.38 327	92.30 322	92.64 369	95.42 389	85.15 358	95.86 213	96.97 309	85.40 385	90.62 396	93.06 382	91.12 260	97.80 400	86.74 374	95.49 398	94.97 409

CNLPA		95.04 248	94.47 271	96.75 199	97.81 261	95.25 116	94.12 312	97.89 265	94.41 222	94.57 326	95.69 337	90.30 276	98.35 384	86.72 375	98.76 274	96.64 383

baseline2		89.65 368	88.44 374	93.25 348	95.62 383	82.71 382	93.82 324	85.94 423	88.89 345	87.35 421	92.54 392	71.23 400	99.33 261	86.01 376	94.60 406	97.72 342

BH-RMVSNet		94.56 273	94.44 274	94.91 294	97.57 299	87.44 325	93.78 327	96.26 324	93.69 245	96.41 262	96.50 305	92.10 246	99.00 321	85.96 377	97.71 337	98.31 285

E-PMN		89.52 369	89.78 361	88.73 402	93.14 419	77.61 413	83.26 425	92.02 387	94.82 207	93.71 351	93.11 377	75.31 383	96.81 411	85.81 378	96.81 369	91.77 422

API-MVS		95.09 247	95.01 238	95.31 276	96.61 344	94.02 164	96.83 139	97.18 299	95.60 171	95.79 294	94.33 367	94.54 181	98.37 383	85.70 379	98.52 296	93.52 416

AdaColmap		95.11 245	94.62 262	96.58 208	97.33 321	94.45 146	94.92 278	98.08 254	93.15 270	93.98 345	95.53 344	94.34 186	99.10 310	85.69 380	98.61 291	96.20 394

ADS-MVSNet2		91.47 346	90.51 355	94.36 321	95.51 385	85.63 348	95.05 273	95.70 335	83.46 399	92.69 378	96.84 283	79.15 362	99.41 235	85.66 381	90.52 417	98.04 316

ADS-MVSNet		90.95 353	90.26 358	93.04 355	95.51 385	82.37 386	95.05 273	93.41 371	83.46 399	92.69 378	96.84 283	79.15 362	98.70 351	85.66 381	90.52 417	98.04 316

MDTV_nov1_ep13_2view						57.28 436	94.89 279		80.59 410	94.02 343		78.66 364		85.50 383		97.82 332

WAC-MVS						79.32 404								85.41 384

OpenMVS_ROB	91.80 14	93.64 304	93.05 304	95.42 273	97.31 323	91.21 249	95.08 270	96.68 321	81.56 405	96.88 233	96.41 309	90.44 272	99.25 282	85.39 385	97.67 341	95.80 399

KD-MVS_2432*1600		88.93 373	87.74 378	92.49 371	88.04 432	81.99 388	89.63 413	95.62 338	91.35 311	95.06 315	93.11 377	56.58 421	98.63 360	85.19 386	95.07 399	96.85 375

miper_refine_blended		88.93 373	87.74 378	92.49 371	88.04 432	81.99 388	89.63 413	95.62 338	91.35 311	95.06 315	93.11 377	56.58 421	98.63 360	85.19 386	95.07 399	96.85 375

PVSNet	86.72 19	91.10 350	90.97 346	91.49 385	97.56 301	78.04 410	87.17 418	94.60 358	84.65 394	92.34 385	92.20 397	87.37 311	98.47 375	85.17 388	97.69 339	97.96 322

PLC	91.02 16	94.05 292	92.90 308	97.51 131	98.00 243	95.12 125	94.25 301	98.25 229	86.17 375	91.48 393	95.25 348	91.01 262	99.19 292	85.02 389	96.69 374	98.22 296
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
gm-plane-assit					91.79 426	71.40 432			81.67 404		90.11 416		98.99 323	84.86 390

CMPMVS	73.10 23	92.74 322	91.39 336	96.77 198	93.57 418	94.67 136	94.21 305	97.67 278	80.36 412	93.61 355	96.60 298	82.85 346	97.35 404	84.86 390	98.78 272	98.29 290
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		92.34 328	91.69 333	94.32 324	96.23 355	89.16 285	92.27 369	92.88 376	84.39 398	95.29 310	96.35 314	85.66 324	96.74 415	84.53 392	97.56 346	97.05 366

tpm cat1		88.01 383	87.33 383	90.05 398	94.48 404	76.28 420	94.47 294	94.35 361	73.84 427	89.26 412	95.61 342	73.64 391	98.30 387	84.13 393	86.20 425	95.57 404

MAR-MVS		94.21 285	93.03 305	97.76 112	96.94 337	97.44 37	96.97 133	97.15 300	87.89 360	92.00 388	92.73 390	92.14 244	99.12 304	83.92 394	97.51 349	96.73 382
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
DSMNet-mixed		92.19 331	91.83 329	93.25 348	96.18 358	83.68 378	96.27 176	93.68 367	76.97 423	92.54 384	99.18 43	89.20 292	98.55 368	83.88 395	98.60 293	97.51 353

EMVS		89.06 372	89.22 364	88.61 403	93.00 421	77.34 415	82.91 426	90.92 399	94.64 214	92.63 382	91.81 401	76.30 378	97.02 408	83.83 396	96.90 364	91.48 423

HY-MVS	91.43 15	92.58 324	91.81 330	94.90 296	96.49 347	88.87 292	97.31 112	94.62 357	85.92 378	90.50 399	96.84 283	85.05 328	99.40 237	83.77 397	95.78 393	96.43 390

test0.0.03 1		90.11 357	89.21 365	92.83 364	93.89 414	86.87 336	91.74 379	88.74 416	92.02 295	94.71 324	91.14 408	73.92 389	94.48 424	83.75 398	92.94 411	97.16 364

tpm2		88.47 377	87.69 381	90.79 391	94.98 397	77.34 415	95.09 268	91.83 389	77.51 422	89.40 411	96.41 309	67.83 408	98.73 347	83.58 399	92.60 414	96.29 392

myMVS_eth3d		87.16 391	85.61 394	91.82 382	95.19 393	79.32 404	92.46 362	91.35 394	90.67 321	91.76 391	87.61 423	41.96 435	98.50 372	82.66 400	96.84 366	97.65 345

MVS-HIRNet		88.40 378	90.20 359	82.99 410	97.01 333	60.04 435	93.11 346	85.61 424	84.45 397	88.72 415	99.09 55	84.72 332	98.23 390	82.52 401	96.59 377	90.69 425

myMVS_eth3d28		88.32 379	87.73 380	90.11 397	96.42 349	74.96 426	92.21 370	92.37 384	93.56 249	90.14 404	89.61 418	56.13 424	98.05 396	81.84 402	97.26 359	97.33 361

UWE-MVS		87.57 387	86.72 389	90.13 396	95.21 392	73.56 427	91.94 376	83.78 427	88.73 348	93.00 371	92.87 386	55.22 429	99.25 282	81.74 403	97.96 323	97.59 350

BH-w/o		92.14 332	91.94 327	92.73 367	97.13 330	85.30 354	92.46 362	95.64 337	89.33 338	94.21 334	92.74 389	89.60 282	98.24 389	81.68 404	94.66 404	94.66 410

MIMVSNet		93.42 309	92.86 309	95.10 285	98.17 223	88.19 305	98.13 55	93.69 365	92.07 293	95.04 318	98.21 163	80.95 356	99.03 320	81.42 405	98.06 320	98.07 308

UBG		88.29 380	87.17 384	91.63 384	96.08 364	78.21 408	91.61 380	91.50 393	89.67 335	89.71 409	88.97 420	59.01 416	98.91 331	81.28 406	96.72 373	97.77 337

TR-MVS		92.54 325	92.20 325	93.57 341	96.49 347	86.66 338	93.51 335	94.73 356	89.96 331	94.95 319	93.87 372	90.24 278	98.61 362	81.18 407	94.88 402	95.45 405

dmvs_re		92.08 335	91.27 340	94.51 316	97.16 328	92.79 206	95.65 228	92.64 381	94.11 233	92.74 377	90.98 410	83.41 342	94.44 425	80.72 408	94.07 408	96.29 392

thres600view7		92.03 337	91.43 335	93.82 334	98.19 217	84.61 367	96.27 176	90.39 405	96.81 103	96.37 264	93.11 377	73.44 395	99.49 206	80.32 409	97.95 324	97.36 358

WB-MVSnew		91.50 345	91.29 338	92.14 379	94.85 398	80.32 401	93.29 342	88.77 415	88.57 350	94.03 342	92.21 396	92.56 231	98.28 388	80.21 410	97.08 360	97.81 334

PAPR		92.22 330	91.27 340	95.07 286	95.73 382	88.81 294	91.97 375	97.87 266	85.80 380	90.91 395	92.73 390	91.16 259	98.33 385	79.48 411	95.76 394	98.08 306

MVS		90.02 359	89.20 366	92.47 373	94.71 401	86.90 335	95.86 213	96.74 318	64.72 428	90.62 396	92.77 388	92.54 234	98.39 380	79.30 412	95.56 397	92.12 420

gg-mvs-nofinetune		88.28 381	86.96 387	92.23 378	92.84 423	84.44 370	98.19 52	74.60 432	99.08 14	87.01 422	99.47 13	56.93 420	98.23 390	78.91 413	95.61 396	94.01 414

thres100view900		91.76 342	91.26 342	93.26 347	98.21 214	84.50 368	96.39 166	90.39 405	96.87 101	96.33 265	93.08 381	73.44 395	99.42 226	78.85 414	97.74 334	95.85 397

tfpn200view9		91.55 344	91.00 344	93.21 351	98.02 237	84.35 371	95.70 221	90.79 401	96.26 129	95.90 291	92.13 398	73.62 392	99.42 226	78.85 414	97.74 334	95.85 397

thres400		91.68 343	91.00 344	93.71 338	98.02 237	84.35 371	95.70 221	90.79 401	96.26 129	95.90 291	92.13 398	73.62 392	99.42 226	78.85 414	97.74 334	97.36 358

thres200		91.00 352	90.42 356	92.77 366	97.47 310	83.98 376	94.01 315	91.18 398	95.12 195	95.44 307	91.21 407	73.93 388	99.31 267	77.76 417	97.63 345	95.01 408

wuyk23d		93.25 315	95.20 228	87.40 409	96.07 365	95.38 107	97.04 129	94.97 353	95.33 185	99.70 7	98.11 174	98.14 18	91.94 427	77.76 417	99.68 86	74.89 427

test_method		66.88 396	66.13 399	69.11 412	62.68 437	25.73 440	49.76 428	96.04 327	14.32 432	64.27 432	91.69 403	73.45 394	88.05 429	76.06 419	66.94 429	93.54 415

testing222		87.35 388	85.50 395	92.93 362	95.79 377	82.83 381	92.40 367	90.10 411	92.80 282	88.87 414	89.02 419	48.34 434	98.70 351	75.40 420	96.74 371	97.27 363

ETVMVS		87.62 386	85.75 393	93.22 350	96.15 362	83.26 379	92.94 348	90.37 407	91.39 310	90.37 400	88.45 421	51.93 433	98.64 359	73.76 421	96.38 381	97.75 338

PCF-MVS	89.43 18	92.12 333	90.64 353	96.57 210	97.80 265	93.48 185	89.88 411	98.45 204	74.46 425	96.04 284	95.68 338	90.71 267	99.31 267	73.73 422	99.01 249	96.91 372
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	81.89 21	84.49 393	83.21 396	88.34 404	95.76 380	74.97 425	83.49 424	92.70 380	78.47 418	87.94 418	86.90 426	83.38 343	96.63 416	73.44 423	66.86 430	93.40 417

GG-mvs-BLEND				90.60 392	91.00 427	84.21 374	98.23 46	72.63 435		82.76 426	84.11 427	56.14 423	96.79 412	72.20 424	92.09 416	90.78 424

FPMVS		89.92 363	88.63 371	93.82 334	98.37 197	96.94 49	91.58 382	93.34 372	88.00 358	90.32 401	97.10 265	70.87 402	91.13 428	71.91 425	96.16 388	93.39 418

MVE	73.61 22	86.48 392	85.92 391	88.18 406	96.23 355	85.28 356	81.78 427	75.79 431	86.01 376	82.53 427	91.88 400	92.74 224	87.47 430	71.42 426	94.86 403	91.78 421
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		57.23 398	62.50 401	41.44 415	34.77 438	49.21 439	83.93 423	60.22 437	15.31 431	71.11 431	79.37 428	70.09 405	44.86 434	64.76 427	82.93 428	30.25 430

PAPM		87.64 385	85.84 392	93.04 355	96.54 345	84.99 361	88.42 417	95.57 341	79.52 414	83.82 425	93.05 383	80.57 357	98.41 378	62.29 428	92.79 412	95.71 400

dmvs_testset		87.30 389	86.99 386	88.24 405	96.71 341	77.48 414	94.68 288	86.81 422	92.64 285	89.61 410	87.01 425	85.91 321	93.12 426	61.04 429	88.49 422	94.13 413

DeepMVS_CX				77.17 411	90.94 428	85.28 356		74.08 434	52.51 430	80.87 430	88.03 422	75.25 384	70.63 432	59.23 430	84.94 426	75.62 426

UWE-MVS-28		83.78 394	82.36 397	88.03 408	90.72 429	71.58 431	93.64 330	77.87 430	87.62 361	85.91 424	92.89 385	59.94 414	95.99 419	56.06 431	96.56 378	96.52 387

dongtai		63.43 397	63.37 400	63.60 413	83.91 435	53.17 437	85.14 421	43.40 439	77.91 421	80.96 429	79.17 429	36.36 437	77.10 431	37.88 432	45.63 431	60.54 428

kuosan		54.81 399	54.94 402	54.42 414	74.43 436	50.03 438	84.98 422	44.27 438	61.80 429	62.49 433	70.43 430	35.16 438	58.04 433	19.30 433	41.61 432	55.19 429

test123		12.59 401	15.49 404	3.87 416	6.07 439	2.55 441	90.75 400	2.59 441	2.52 434	5.20 436	13.02 433	4.96 439	1.85 436	5.20 434	9.09 433	7.23 431

testmvs		12.33 402	15.23 405	3.64 417	5.77 440	2.23 442	88.99 415	3.62 440	2.30 435	5.29 435	13.09 432	4.52 440	1.95 435	5.16 435	8.32 434	6.75 432

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

cdsmvs_eth3d_5k		24.22 400	32.30 403	0.00 418	0.00 441	0.00 443	0.00 429	98.10 252	0.00 436	0.00 437	95.06 352	97.54 40	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		7.98 403	10.65 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	95.82 133	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

ab-mvs-re		7.91 404	10.55 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	94.94 354	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

FOURS1					99.59 17	98.20 8	99.03 8	99.25 40	98.96 22	98.87 64

test_one_0601					99.05 106	95.50 102		98.87 126	97.21 94	98.03 154	98.30 145	96.93 75

eth-test2					0.00 441

eth-test					0.00 441

test_241102_ONE					99.22 66	95.35 110		98.83 143	96.04 144	99.08 45	98.13 170	97.87 24	99.33 261

save fliter					98.48 187	94.71 133	94.53 293	98.41 211	95.02 201

test0726					99.24 61	95.51 99	96.89 137	98.89 117	95.92 154	98.64 82	98.31 141	97.06 64

GSMVS																98.06 312

test_part2					99.03 108	96.07 78				98.08 147

sam_mvs1												77.80 367				98.06 312

sam_mvs												77.38 371

MTGPA								98.73 165

test_post											10.87 434	76.83 375	99.07 313

patchmatchnet-post											96.84 283	77.36 372	99.42 226

MTMP							96.55 160	74.60 432

TEST9					97.84 257	95.23 117	93.62 331	98.39 214	86.81 370	93.78 347	95.99 328	94.68 175	99.52 196

test_8					97.81 261	95.07 126	93.54 334	98.38 216	87.04 366	93.71 351	95.96 331	94.58 179	99.52 196

agg_prior					97.80 265	94.96 128		98.36 218		93.49 360			99.53 193

test_prior4						95.38 107	93.61 333

test_prior				97.46 141	97.79 270	94.26 157		98.42 210					99.34 259			98.79 231

新几何2							93.43 336

旧先验1					97.80 265	93.87 169		97.75 274			97.04 269	93.57 205			98.68 283	98.72 241

原ACMM2							92.82 350

test222					98.17 223	93.24 195	92.74 354	97.61 287	75.17 424	94.65 325	96.69 294	90.96 264			98.66 286	97.66 344

segment_acmp												95.34 154

testdata1							92.77 351		93.78 241

test12				97.46 141	97.61 297	94.07 161		97.78 273		93.57 358		93.31 210	99.42 226		98.78 272	98.89 216

plane_prior7					98.70 154	94.67 136

plane_prior6					98.38 196	94.37 150						91.91 253

plane_prior4											96.77 289

plane_prior3						94.51 143			95.29 188	96.16 279

plane_prior2							96.50 162		96.36 125

plane_prior1					98.49 185

plane_prior						94.29 153	95.42 243		94.31 226						98.93 256

n2								0.00 442

nn								0.00 442

door-mid								98.17 242

test11								98.08 254

door								97.81 272

HQP5-MVS						92.47 213

HQP-NCC					97.85 252		94.26 298		93.18 266	92.86 374

ACMP_Plane					97.85 252		94.26 298		93.18 266	92.86 374

HQP4-MVS										92.87 373			99.23 288			99.06 187

HQP3-MVS								98.43 207							98.74 276

HQP2-MVS												90.33 273

NP-MVS					98.14 229	93.72 175					95.08 350

ACMMP++_ref															99.52 142

ACMMP++															99.55 129

Test By Simon												94.51 182

High-resolution multi-view benchmark