High-res multi-view results

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

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

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

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

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

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

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

test_fmvsmconf0.01_n		98.57 21	98.74 19	98.06 101	99.39 50	94.63 177	96.70 173	99.82 1	95.44 221	99.64 13	99.52 12	98.96 4	99.74 95	99.38 7	99.86 35	99.81 10

mvs5depth		98.06 60	98.58 29	96.51 252	98.97 133	89.65 356	99.43 4	99.81 2	99.30 9	98.36 145	99.86 2	93.15 269	99.88 22	98.50 44	99.84 50	99.99 1

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

mmtdpeth		98.33 36	98.53 31	97.71 128	99.07 111	93.44 230	98.80 15	99.78 4	99.10 15	96.61 325	99.63 10	95.42 187	99.73 101	98.53 43	99.86 35	99.95 2

test_fmvsmconf0.1_n		98.41 34	98.54 30	98.03 106	99.16 93	94.61 178	96.18 216	99.73 5	95.05 240	99.60 17	99.34 29	98.68 8	99.72 111	99.21 12	99.85 47	99.76 21

fmvsm_s_conf0.1_n_2		97.68 115	98.18 57	96.20 286	99.06 113	89.08 375	95.51 282	99.72 6	96.06 175	99.48 21	99.24 36	95.18 199	99.60 199	99.45 4	99.88 28	99.94 3

test_vis1_n_1920		95.77 273	96.41 237	93.85 433	98.55 218	84.86 478	95.91 249	99.71 7	92.72 354	97.67 235	98.90 85	87.44 393	98.73 428	97.96 61	98.85 341	97.96 407

CS-MVS		98.09 56	98.01 76	98.32 72	98.45 239	96.69 59	98.52 29	99.69 8	98.07 59	96.07 364	97.19 325	96.88 99	99.86 27	97.50 84	99.73 85	98.41 350

PDCNetPlus		89.44 479	88.28 483	92.93 473	91.75 540	85.02 474	87.69 531	99.67 9	82.69 513	95.89 379	97.02 342	51.15 551	95.27 517	88.79 439	99.86 35	98.50 342

test_vis3_rt		97.04 178	96.98 186	97.23 185	98.44 240	95.88 104	96.82 157	99.67 9	90.30 425	99.27 39	99.33 31	94.04 241	96.03 514	97.14 101	97.83 430	99.78 14

SPE-MVS-test		97.91 84	97.84 97	98.14 94	98.52 222	96.03 100	98.38 38	99.67 9	98.11 57	95.50 399	96.92 354	96.81 105	99.87 25	96.87 115	99.76 72	98.51 339

EC-MVSNet		97.90 86	97.94 88	97.79 121	98.66 195	95.14 158	98.31 43	99.66 12	97.57 79	95.95 370	97.01 346	96.99 84	99.82 38	97.66 78	99.64 117	98.39 353

test_fmvsmvis_n_1920		98.08 57	98.47 32	96.93 211	99.03 122	93.29 236	96.32 203	99.65 13	95.59 210	99.71 7	99.01 67	97.66 38	99.60 199	99.44 5	99.83 55	97.90 411

dcpmvs_2		97.12 174	97.99 78	94.51 406	99.11 105	84.00 491	97.75 87	99.65 13	97.38 96	99.14 49	98.42 151	95.16 201	99.96 2	95.52 197	99.78 69	99.58 51

LCM-MVSNet-Re		97.33 158	97.33 159	97.32 175	98.13 288	93.79 215	96.99 146	99.65 13	96.74 127	99.47 23	98.93 78	96.91 94	99.84 33	90.11 418	99.06 314	98.32 364

test_fmvsmconf_n		98.30 40	98.41 39	97.99 109	98.94 137	94.60 179	96.00 236	99.64 16	94.99 245	99.43 27	99.18 45	98.51 12	99.71 127	99.13 20	99.84 50	99.67 36

fmvsm_l_conf0.5_n_3		98.29 41	98.46 33	97.79 121	98.90 148	94.05 205	96.06 228	99.63 17	96.07 174	99.37 32	98.93 78	98.29 16	99.68 151	99.11 22	99.79 65	99.65 41

test_fmvs3		97.38 153	97.56 138	96.84 222	98.63 205	92.81 250	97.60 103	99.61 18	90.87 412	98.76 95	99.66 6	94.03 242	97.90 488	99.24 11	99.68 104	99.81 10

fmvsm_l_conf0.5_n_9		97.92 80	98.37 40	96.57 245	98.94 137	90.54 326	95.39 292	99.58 19	96.82 123	99.56 18	98.77 95	97.23 67	99.61 196	99.17 17	99.86 35	99.57 59

fmvsm_s_conf0.5_n_5		97.63 122	97.83 100	97.04 201	98.77 176	92.33 265	95.63 276	99.58 19	93.53 311	99.10 52	98.66 115	96.44 131	99.65 172	99.12 21	99.68 104	99.12 220

test_fmvsm_n_1920		98.08 57	98.29 52	97.43 165	98.88 150	93.95 209	96.17 220	99.57 21	95.66 205	99.52 20	98.71 109	97.04 80	99.64 178	99.21 12	99.87 33	98.69 315

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 40	99.71 10	96.99 48	99.69 2	99.57 21	99.02 21	99.62 15	99.36 26	98.53 11	99.52 226	98.58 42	99.95 5	99.66 38
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
fmvsm_s_conf0.5_n_11		97.90 86	98.34 45	96.60 240	98.75 178	90.50 330	96.28 205	99.56 23	97.05 110	99.15 48	99.11 54	96.31 138	99.69 144	98.97 29	99.84 50	99.62 45

ANet_high		98.31 39	98.94 9	96.41 268	99.33 60	89.64 357	97.92 74	99.56 23	99.27 10	99.66 12	99.50 14	97.67 36	99.83 35	97.55 82	99.98 2	99.77 15

tt0320-xc		99.10 4	99.31 3	98.49 57	99.57 20	96.09 93	98.91 11	99.55 25	99.67 3	99.78 3	99.69 4	98.63 10	99.77 69	98.02 58	99.93 11	99.60 47

fmvsm_s_conf0.5_n_2		97.59 128	98.07 68	96.17 290	98.78 173	89.10 374	95.33 300	99.55 25	95.96 184	99.41 30	99.10 56	95.18 199	99.59 201	99.43 6	99.86 35	99.81 10

fmvsm_s_conf0.5_n_9		97.98 65	98.32 48	96.96 208	98.92 143	91.45 300	95.87 252	99.53 27	97.44 87	99.56 18	99.05 62	95.34 190	99.67 161	99.52 2	99.70 97	99.77 15

tt0320		99.07 6	99.29 4	98.43 62	99.55 24	95.92 103	98.97 10	99.53 27	99.67 3	99.79 2	99.71 3	98.33 14	99.78 58	98.11 52	99.92 15	99.57 59

fmvsm_s_conf0.5_n_10		97.74 106	98.11 62	96.62 236	98.72 183	90.95 316	95.99 239	99.50 29	96.22 158	99.20 44	98.93 78	95.13 203	99.77 69	99.49 3	99.76 72	99.15 206

fmvsm_s_conf0.5_n_3		97.88 89	98.37 40	96.41 268	98.73 180	89.82 350	95.94 246	99.49 30	96.81 124	99.09 53	99.03 65	97.09 73	99.65 172	99.37 8	99.76 72	99.76 21

Vis-MVSNet		98.27 42	98.34 45	98.07 99	99.33 60	95.21 154	98.04 64	99.46 31	97.32 100	97.82 227	99.11 54	96.75 108	99.86 27	97.84 67	99.36 249	99.15 206
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvs2		96.38 238	96.45 234	96.16 292	97.85 313	91.30 303	96.81 158	99.45 32	89.24 444	98.49 126	99.38 23	88.68 370	97.62 493	98.83 31	99.32 267	99.57 59

TDRefinement		98.90 8	98.86 11	99.02 9	99.54 28	98.06 8	99.34 5	99.44 33	98.85 27	99.00 62	99.20 40	97.42 52	99.59 201	97.21 96	99.76 72	99.40 134

test_fmvs1_n		95.21 312	95.28 295	94.99 374	98.15 283	89.13 373	96.81 158	99.43 34	86.97 478	97.21 269	98.92 81	83.00 446	97.13 499	98.09 54	98.94 325	98.72 310

fmvsm_s_conf0.5_n_8		97.66 118	98.12 60	96.27 280	98.79 169	89.43 363	95.76 261	99.42 35	97.49 85	99.16 47	99.04 63	94.56 225	99.69 144	99.18 16	99.73 85	99.70 33

testf1		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 96	99.42 35	97.69 75	98.92 72	98.77 95	97.80 30	99.25 349	96.27 149	99.69 99	98.76 305

APD_test2		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 96	99.42 35	97.69 75	98.92 72	98.77 95	97.80 30	99.25 349	96.27 149	99.69 99	98.76 305

fmvsm_l_conf0.5_n		97.68 115	97.81 103	97.27 179	98.92 143	92.71 257	95.89 250	99.41 38	93.36 318	99.00 62	98.44 149	96.46 130	99.65 172	99.09 23	99.76 72	99.45 112

fmvsm_s_conf0.5_n_6		97.45 144	97.79 105	96.44 261	98.58 213	90.31 338	95.77 260	99.33 39	94.52 268	98.85 81	98.44 149	95.68 173	99.62 188	99.15 19	99.81 59	99.38 143

fmvsm_l_conf0.5_n_a		97.60 125	97.76 111	97.11 192	98.92 143	92.28 269	95.83 256	99.32 40	93.22 325	98.91 74	98.49 140	96.31 138	99.64 178	99.07 24	99.76 72	99.40 134

UA-Net		98.88 10	98.76 16	99.22 2	99.11 105	97.89 16	99.47 3	99.32 40	99.08 16	97.87 223	99.67 5	96.47 128	99.92 5	97.88 64	99.98 2	99.85 6

aaatest				98.17 88	99.36 54	95.35 137	97.75 87	99.30 42	94.02 294	98.88 77	97.54 289		99.73 101	95.36 216	99.53 176	99.44 122

MED-MVS		98.14 50	98.09 66	98.27 78	99.36 54	95.35 137	97.75 87	99.30 42	97.28 103	98.88 77	98.41 154	96.99 84	99.73 101	95.36 216	99.51 189	99.74 26

patch_mono-2		96.59 219	96.93 191	95.55 340	98.88 150	87.12 436	94.47 357	99.30 42	94.12 288	96.65 323	98.41 154	94.98 209	99.87 25	95.81 180	99.78 69	99.66 38

pmmvs6		99.07 6	99.24 7	98.56 51	99.81 2	96.38 74	98.87 12	99.30 42	99.01 22	99.63 14	99.66 6	99.27 2	99.68 151	97.75 73	99.89 26	99.62 45

GDP-MVS		95.39 301	94.89 318	96.90 215	98.26 265	91.91 287	96.48 189	99.28 46	95.06 239	96.54 333	97.12 335	74.83 494	99.82 38	97.19 99	99.27 278	98.96 260

test_vis1_n		95.67 283	95.89 272	95.03 370	98.18 276	89.89 348	96.94 148	99.28 46	88.25 461	98.20 173	98.92 81	86.69 406	97.19 498	97.70 77	98.82 347	98.00 405

fmvsm_s_conf0.5_n_4		97.43 148	97.77 110	96.39 272	98.48 234	89.89 348	95.65 271	99.26 48	94.73 257	98.72 100	98.58 128	95.58 179	99.57 210	99.28 9	99.67 108	99.73 28

test_cas_vis1_n_1920		95.34 306	95.67 283	94.35 416	98.21 270	86.83 443	95.61 277	99.26 48	90.45 419	98.17 179	98.96 74	84.43 432	98.31 473	96.74 119	99.17 295	97.90 411

FOURS1					99.59 18	98.20 7	99.03 8	99.25 50	98.96 24	98.87 79

Casviewmamba		97.95 72	98.20 56	97.18 186	98.85 157	92.74 255	96.71 171	99.23 51	98.07 59	98.55 118	98.47 145	97.38 54	99.44 265	96.95 112	99.62 123	99.38 143

E5new		97.59 128	97.96 86	96.45 257	99.01 124	90.45 332	96.50 183	99.23 51	96.19 163	98.27 160	98.72 102	97.49 46	99.47 247	96.64 122	99.62 123	99.42 127

E6new		97.59 128	97.97 80	96.45 257	99.01 124	90.45 332	96.50 183	99.23 51	96.20 159	98.27 160	98.72 102	97.49 46	99.47 247	96.64 122	99.62 123	99.42 127

E6		97.59 128	97.97 80	96.45 257	99.01 124	90.45 332	96.50 183	99.23 51	96.20 159	98.27 160	98.72 102	97.49 46	99.47 247	96.64 122	99.62 123	99.42 127

E5		97.59 128	97.96 86	96.45 257	99.01 124	90.45 332	96.50 183	99.23 51	96.19 163	98.27 160	98.72 102	97.49 46	99.47 247	96.64 122	99.62 123	99.42 127

mvs_tets		98.90 8	98.94 9	98.75 34	99.69 11	96.48 69	98.54 26	99.22 56	96.23 157	99.71 7	99.48 15	98.77 7	99.93 3	98.89 30	99.95 5	99.84 8

FC-MVSNet-test		98.16 49	98.37 40	97.56 142	99.49 36	93.10 242	98.35 39	99.21 57	98.43 42	98.89 75	98.83 90	94.30 236	99.81 43	97.87 65	99.91 19	99.77 15

PS-MVSNAJss		98.53 27	98.63 23	98.21 87	99.68 12	94.82 169	98.10 60	99.21 57	96.91 120	99.75 5	99.45 18	95.82 164	99.92 5	98.80 32	99.96 4	99.89 4

hybridcas		97.73 107	98.10 65	96.62 236	98.84 159	91.10 308	96.46 191	99.20 59	97.53 83	98.65 106	98.42 151	97.41 53	99.38 298	96.79 118	99.59 144	99.37 152

UniMVSNet_ETH3D		99.12 3	99.28 5	98.65 45	99.77 5	96.34 78	99.18 6	99.20 59	99.67 3	99.73 6	99.65 8	99.15 3	99.86 27	97.22 95	99.92 15	99.77 15

ACMH+	93.58 10	98.23 45	98.31 49	97.98 110	99.39 50	95.22 152	97.55 108	99.20 59	98.21 54	99.25 41	98.51 139	98.21 18	99.40 285	94.79 268	99.72 90	99.32 160

sc_t1		99.09 5	99.28 5	98.53 54	99.72 8	96.21 86	98.87 12	99.19 62	99.71 2	99.76 4	99.65 8	98.64 9	99.79 53	98.07 56	99.90 25	99.58 51

anonymousdsp		98.72 17	98.63 23	98.99 13	99.62 16	97.29 41	98.65 22	99.19 62	95.62 208	99.35 35	99.37 24	97.38 54	99.90 17	98.59 41	99.91 19	99.77 15

E4		97.28 161	97.55 141	96.46 256	98.86 155	90.53 328	95.28 308	99.18 64	95.82 198	98.01 201	98.59 127	96.78 106	99.46 254	95.86 176	99.56 159	99.38 143

viewmacassd2359aftdt		97.25 164	97.52 144	96.43 263	98.83 160	90.49 331	95.45 285	99.18 64	95.44 221	97.98 208	98.47 145	96.90 96	99.37 305	95.93 169	99.55 166	99.43 125

casdiffmvs_mvg		97.83 95	98.11 62	97.00 206	98.57 215	92.10 280	95.97 242	99.18 64	97.67 78	99.00 62	98.48 144	97.64 39	99.50 232	96.96 111	99.54 172	99.40 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffseed414692147		97.67 117	97.88 94	97.03 203	98.82 162	92.32 267	96.55 180	99.17 67	96.99 111	98.01 201	98.67 114	97.64 39	99.38 298	95.45 206	99.66 111	99.40 134

WR-MVS_H		98.65 18	98.62 25	98.75 34	99.51 32	96.61 64	98.55 25	99.17 67	99.05 19	99.17 46	98.79 91	95.47 184	99.89 20	97.95 62	99.91 19	99.75 24

SSM_0407		97.39 152	97.67 120	96.54 250	98.51 224	90.96 313	96.40 193	99.16 69	96.95 116	98.27 160	98.09 214	97.05 78	99.67 161	95.21 227	99.40 236	98.98 255

SSM_0404		97.47 142	97.75 113	96.64 235	98.81 163	91.26 305	96.57 177	99.16 69	96.95 116	98.44 134	98.09 214	97.05 78	99.72 111	95.21 227	99.44 217	98.95 263

EIA-MVS		96.04 257	95.77 280	96.85 219	97.80 333	92.98 244	96.12 223	99.16 69	94.65 261	93.77 452	91.69 508	95.68 173	99.67 161	94.18 295	98.85 341	97.91 410

AllTest		97.20 167	96.92 193	98.06 101	99.08 109	96.16 88	97.14 136	99.16 69	94.35 279	97.78 229	98.07 218	95.84 161	99.12 377	91.41 379	99.42 230	98.91 274

TestCases				98.06 101	99.08 109	96.16 88		99.16 69	94.35 279	97.78 229	98.07 218	95.84 161	99.12 377	91.41 379	99.42 230	98.91 274

COLMAP_ROB	94.48 6	98.25 44	98.11 62	98.64 46	99.21 85	97.35 39	97.96 68	99.16 69	98.34 46	98.78 89	98.52 136	97.32 57	99.45 262	94.08 299	99.67 108	99.13 214
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_s_conf0.1_n_a		97.80 101	98.01 76	97.18 186	99.17 92	92.51 260	96.57 177	99.15 75	93.68 307	98.89 75	99.30 32	96.42 133	99.37 305	99.03 25	99.83 55	99.66 38

Anonymous20231211		98.55 24	98.76 16	97.94 113	98.79 169	94.37 191	98.84 14	99.15 75	99.37 6	99.67 10	99.43 20	95.61 177	99.72 111	98.12 51	99.86 35	99.73 28

PEN-MVS		98.75 13	98.85 13	98.44 61	99.58 19	95.67 114	98.45 34	99.15 75	99.33 8	99.30 37	99.00 68	97.27 60	99.92 5	97.64 79	99.92 15	99.75 24

diffmvs_AUTHOR		96.50 225	96.81 201	95.57 334	98.03 292	88.26 401	93.73 403	99.14 78	94.92 250	97.24 266	97.84 253	94.62 221	99.33 318	96.44 137	99.37 244	99.13 214

v7n		98.73 14	98.99 8	97.95 112	99.64 14	94.20 200	98.67 18	99.14 78	99.08 16	99.42 28	99.23 38	96.53 123	99.91 13	99.27 10	99.93 11	99.73 28

PS-CasMVS		98.73 14	98.85 13	98.39 66	99.55 24	95.47 130	98.49 31	99.13 80	99.22 12	99.22 43	98.96 74	97.35 56	99.92 5	97.79 70	99.93 11	99.79 13

E2		96.97 185	97.19 172	96.33 274	98.64 196	90.34 336	95.07 323	99.12 81	95.00 243	97.66 236	98.31 172	96.19 148	99.43 269	95.35 219	99.35 255	99.23 190

E3		96.97 185	97.19 172	96.33 274	98.64 196	90.34 336	95.07 323	99.12 81	95.00 243	97.66 236	98.31 172	96.19 148	99.43 269	95.35 219	99.35 255	99.23 190

jajsoiax		98.77 12	98.79 15	98.74 37	99.66 13	96.48 69	98.45 34	99.12 81	95.83 197	99.67 10	99.37 24	98.25 17	99.92 5	98.77 33	99.94 8	99.82 9

FE-MVSNET2		97.69 112	97.97 80	96.85 219	99.19 89	91.46 299	97.04 142	99.11 84	95.85 195	98.73 99	99.02 66	96.66 111	99.68 151	96.31 145	99.86 35	99.40 134

viewdifsd2359ckpt07		97.10 176	97.55 141	95.76 317	98.64 196	88.58 390	94.54 355	99.11 84	96.96 115	98.54 119	98.18 202	96.91 94	99.44 265	95.58 195	99.49 200	99.26 180

fmvsm_s_conf0.1_n		97.73 107	98.02 74	96.85 219	99.09 108	91.43 302	96.37 199	99.11 84	94.19 285	99.01 60	99.25 35	96.30 141	99.38 298	99.00 26	99.88 28	99.73 28

FIs		97.93 79	98.07 68	97.48 159	99.38 52	92.95 246	98.03 66	99.11 84	98.04 62	98.62 109	98.66 115	93.75 253	99.78 58	97.23 94	99.84 50	99.73 28

RRT-MVS		95.78 272	96.25 247	94.35 416	96.68 421	84.47 484	97.72 95	99.11 84	97.23 105	97.27 263	98.72 102	86.39 411	99.79 53	95.49 198	97.67 443	98.80 291

SF-MVS		97.60 125	97.39 153	98.22 84	98.93 141	95.69 112	97.05 141	99.10 89	95.32 227	97.83 226	97.88 247	96.44 131	99.72 111	94.59 282	99.39 240	99.25 187

Effi-MVS+		96.19 250	96.01 260	96.71 231	97.43 387	92.19 276	96.12 223	99.10 89	95.45 218	93.33 471	94.71 461	97.23 67	99.56 212	93.21 341	97.54 450	98.37 356

APDe-MVS		98.14 50	98.03 73	98.47 60	98.72 183	96.04 96	98.07 63	99.10 89	95.96 184	98.59 114	98.69 112	96.94 88	99.81 43	96.64 122	99.58 150	99.57 59
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DTE-MVSNet		98.79 11	98.86 11	98.59 49	99.55 24	96.12 91	98.48 33	99.10 89	99.36 7	99.29 38	99.06 61	97.27 60	99.93 3	97.71 75	99.91 19	99.70 33

Gipuma		98.07 59	98.31 49	97.36 172	99.76 7	96.28 83	98.51 30	99.10 89	98.76 29	96.79 308	99.34 29	96.61 117	98.82 418	96.38 140	99.50 197	96.98 458
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
lecture		98.59 20	98.60 28	98.55 52	99.48 37	96.38 74	98.08 62	99.09 94	98.46 41	98.68 105	98.73 101	97.88 27	99.80 50	97.43 87	99.59 144	99.48 102

reproduce_model		98.54 25	98.33 47	99.15 3	99.06 113	98.04 11	97.04 142	99.09 94	98.42 43	99.03 57	98.71 109	96.93 90	99.83 35	97.09 103	99.63 120	99.56 67

MGCFI-Net		97.20 167	97.23 168	97.08 197	97.68 355	93.71 218	97.79 82	99.09 94	97.40 94	96.59 326	93.96 473	97.67 36	99.35 313	96.43 138	98.50 389	98.17 387

casdiffmvs		97.50 139	97.81 103	96.56 247	98.51 224	91.04 310	95.83 256	99.09 94	97.23 105	98.33 152	98.30 178	97.03 81	99.37 305	96.58 130	99.38 242	99.28 174
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
APD_test1		97.95 72	97.68 119	98.75 34	99.60 17	98.60 5	97.21 132	99.08 98	96.57 139	98.07 193	98.38 160	96.22 146	99.14 372	94.71 276	99.31 270	98.52 338

nrg030		98.54 25	98.62 25	98.32 72	99.22 78	95.66 115	97.90 76	99.08 98	98.31 47	99.02 59	98.74 100	97.68 35	99.61 196	97.77 72	99.85 47	99.70 33

diffmvs		96.04 257	96.23 248	95.46 346	97.35 392	88.03 412	93.42 418	99.08 98	94.09 291	96.66 321	96.93 351	93.85 249	99.29 336	96.01 164	98.67 372	99.06 238
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		95.95 263	95.80 278	96.42 265	99.28 64	90.62 322	95.31 303	99.08 98	88.40 458	96.97 297	98.17 204	92.11 305	99.78 58	93.64 325	99.21 286	98.86 285

viewcassd2359sk11		96.73 209	96.89 197	96.24 282	98.46 238	90.20 340	94.94 333	99.07 102	94.43 276	97.33 260	98.05 227	95.69 172	99.40 285	94.98 257	99.11 304	99.12 220

mamba_0408		97.17 169	97.38 155	96.55 249	98.51 224	90.96 313	95.19 313	99.06 103	96.60 132	98.27 160	97.78 262	96.58 120	99.72 111	95.04 243	99.40 236	98.98 255

SSM_04072		97.14 170	97.38 155	96.42 265	98.51 224	90.96 313	95.19 313	99.06 103	96.60 132	98.27 160	97.78 262	96.58 120	99.31 328	95.04 243	99.40 236	98.98 255

fmvsm_s_conf0.5_n_a		97.65 119	97.83 100	97.13 191	98.80 166	92.51 260	96.25 211	99.06 103	93.67 308	98.64 107	99.00 68	96.23 145	99.36 309	98.99 27	99.80 63	99.53 78

fmvsm_s_conf0.5_n		97.62 123	97.89 92	96.80 225	98.79 169	91.44 301	96.14 222	99.06 103	94.19 285	98.82 86	98.98 71	96.22 146	99.38 298	98.98 28	99.86 35	99.58 51

PGM-MVS		97.88 89	97.52 144	98.96 16	99.20 87	97.62 24	97.09 139	99.06 103	95.45 218	97.55 243	97.94 240	97.11 70	99.78 58	94.77 271	99.46 211	99.48 102

RPSCF		97.87 91	97.51 146	98.95 17	99.15 96	98.43 6	97.56 107	99.06 103	96.19 163	98.48 128	98.70 111	94.72 214	99.24 353	94.37 288	99.33 265	99.17 202

FE-MVSNET		96.59 219	96.65 212	96.41 268	98.94 137	90.51 329	96.07 226	99.05 109	92.94 347	98.03 198	98.00 234	93.08 273	99.42 273	94.04 303	99.74 84	99.30 166

sasdasda		97.23 165	97.21 170	97.30 176	97.65 362	94.39 188	97.84 79	99.05 109	97.42 89	96.68 317	93.85 476	97.63 41	99.33 318	96.29 147	98.47 392	98.18 385

canonicalmvs		97.23 165	97.21 170	97.30 176	97.65 362	94.39 188	97.84 79	99.05 109	97.42 89	96.68 317	93.85 476	97.63 41	99.33 318	96.29 147	98.47 392	98.18 385

TranMVSNet+NR-MVSNet		98.33 36	98.30 51	98.43 62	99.07 111	95.87 105	96.73 170	99.05 109	98.67 30	98.84 83	98.45 147	97.58 44	99.88 22	96.45 136	99.86 35	99.54 73

OurMVSNet-221017-0		98.61 19	98.61 27	98.63 47	99.77 5	96.35 77	99.17 7	99.05 109	98.05 61	99.61 16	99.52 12	93.72 254	99.88 22	98.72 38	99.88 28	99.65 41

HPM-MVS		98.11 55	97.83 100	98.92 24	99.42 45	97.46 35	98.57 23	99.05 109	95.43 223	97.41 257	97.50 295	97.98 23	99.79 53	95.58 195	99.57 154	99.50 88
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
XVG-OURS		97.12 174	96.74 207	98.26 79	98.99 129	97.45 36	93.82 397	99.05 109	95.19 232	98.32 153	97.70 275	95.22 197	98.41 465	94.27 292	98.13 410	98.93 270

ACMH	93.61 9	98.44 32	98.76 16	97.51 148	99.43 43	93.54 225	98.23 50	99.05 109	97.40 94	99.37 32	99.08 60	98.79 6	99.47 247	97.74 74	99.71 93	99.50 88
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet (Re)		97.83 95	97.65 123	98.35 70	98.80 166	95.86 106	95.92 248	99.04 117	97.51 84	98.22 172	97.81 259	94.68 218	99.78 58	97.14 101	99.75 82	99.41 133

viewdifsd2359ckpt09		96.23 247	96.04 258	96.82 223	98.29 257	92.06 283	95.25 309	99.03 118	91.51 391	96.19 358	97.01 346	94.41 229	99.40 285	93.76 318	98.90 333	99.00 248

viewmanbaseed2359cas		96.77 205	96.94 190	96.27 280	98.41 247	90.24 339	95.11 318	99.03 118	94.28 282	97.45 255	97.85 251	95.92 158	99.32 326	95.18 231	99.19 291	99.24 188

HPM-MVS_fast		98.32 38	98.13 59	98.88 26	99.54 28	97.48 34	98.35 39	99.03 118	95.88 192	97.88 220	98.22 196	98.15 20	99.74 95	96.50 132	99.62 123	99.42 127

baseline		97.44 146	97.78 109	96.43 263	98.52 222	90.75 321	96.84 155	99.03 118	96.51 140	97.86 224	98.02 230	96.67 110	99.36 309	97.09 103	99.47 208	99.19 198

E3new		96.50 225	96.61 215	96.17 290	98.28 260	90.09 341	94.85 339	99.02 122	93.95 298	97.01 291	97.74 270	95.19 198	99.39 294	94.70 277	98.77 360	99.04 242

reproduce-ours		98.48 29	98.27 53	99.12 4	98.99 129	98.02 12	96.81 158	99.02 122	98.29 50	98.97 66	98.61 122	97.27 60	99.82 38	96.86 116	99.61 134	99.51 85

our_new_method		98.48 29	98.27 53	99.12 4	98.99 129	98.02 12	96.81 158	99.02 122	98.29 50	98.97 66	98.61 122	97.27 60	99.82 38	96.86 116	99.61 134	99.51 85

test_fmvs1		94.51 354	94.60 338	94.26 421	95.91 461	87.92 413	95.35 298	99.02 122	86.56 482	96.79 308	98.52 136	82.64 448	97.00 503	97.87 65	98.71 367	97.88 413

v10		97.55 134	97.97 80	96.31 278	98.60 209	89.64 357	97.44 117	99.02 122	96.60 132	98.72 100	99.16 49	93.48 260	99.72 111	98.76 34	99.92 15	99.58 51

UniMVSNet_NR-MVSNet		97.83 95	97.65 123	98.37 67	98.72 183	95.78 108	95.66 269	99.02 122	98.11 57	98.31 155	97.69 276	94.65 220	99.85 30	97.02 109	99.71 93	99.48 102

XVG-OURS-SEG-HR		97.38 153	97.07 180	98.30 75	99.01 124	97.41 38	94.66 350	99.02 122	95.20 231	98.15 182	97.52 293	98.83 5	98.43 464	94.87 261	96.41 488	99.07 235

MVSFormer		96.14 252	96.36 241	95.49 344	97.68 355	87.81 420	98.67 18	99.02 122	96.50 141	94.48 430	96.15 405	86.90 402	99.92 5	98.73 36	99.13 300	98.74 307

test_djsdf		98.73 14	98.74 19	98.69 42	99.63 15	96.30 82	98.67 18	99.02 122	96.50 141	99.32 36	99.44 19	97.43 51	99.92 5	98.73 36	99.95 5	99.86 5

LPG-MVS_test		97.94 76	97.67 120	98.74 37	99.15 96	97.02 46	97.09 139	99.02 122	95.15 234	98.34 149	98.23 193	97.91 25	99.70 136	94.41 285	99.73 85	99.50 88

LGP-MVS_train				98.74 37	99.15 96	97.02 46		99.02 122	95.15 234	98.34 149	98.23 193	97.91 25	99.70 136	94.41 285	99.73 85	99.50 88

DeepC-MVS	95.41 4	97.82 98	97.70 115	98.16 90	98.78 173	95.72 110	96.23 214	99.02 122	93.92 299	98.62 109	98.99 70	97.69 34	99.62 188	96.18 154	99.87 33	99.15 206
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
viewmamba		96.62 218	96.92 193	95.74 319	97.85 313	88.83 383	94.25 367	99.00 134	95.69 204	97.18 273	97.90 246	95.34 190	99.29 336	96.20 152	98.85 341	99.11 225

fmvsm_s_conf0.5_n_7		97.13 171	97.50 148	96.04 298	98.43 243	89.03 378	94.92 334	99.00 134	94.51 269	98.42 136	98.96 74	94.97 210	99.54 220	98.42 46	99.85 47	99.56 67

pm-mvs1		98.47 31	98.67 21	97.86 117	99.52 31	94.58 180	98.28 46	99.00 134	97.57 79	99.27 39	99.22 39	98.32 15	99.50 232	97.09 103	99.75 82	99.50 88

VPA-MVSNet		98.27 42	98.46 33	97.70 130	99.06 113	93.80 214	97.76 86	99.00 134	98.40 44	99.07 56	98.98 71	96.89 97	99.75 85	97.19 99	99.79 65	99.55 71

XXY-MVS		97.54 135	97.70 115	97.07 198	99.46 40	92.21 272	97.22 131	99.00 134	94.93 249	98.58 115	98.92 81	97.31 58	99.41 283	94.44 283	99.43 227	99.59 50

DPE-MVS		97.64 120	97.35 158	98.50 56	98.85 157	96.18 87	95.21 312	98.99 139	95.84 196	98.78 89	98.08 216	96.84 103	99.81 43	93.98 307	99.57 154	99.52 81
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		97.69 112	97.36 157	98.70 41	99.50 35	96.84 52	95.38 294	98.99 139	92.45 359	98.11 186	98.31 172	97.25 65	99.77 69	96.60 128	99.62 123	99.48 102
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CSCG		97.40 151	97.30 161	97.69 132	98.95 134	94.83 168	97.28 127	98.99 139	96.35 151	98.13 185	95.95 421	95.99 155	99.66 169	94.36 290	99.73 85	98.59 327

GeoE		97.75 105	97.70 115	97.89 115	98.88 150	94.53 183	97.10 138	98.98 142	95.75 202	97.62 238	97.59 285	97.61 43	99.77 69	96.34 143	99.44 217	99.36 153

9.14			96.69 209		98.53 221		96.02 234	98.98 142	93.23 324	97.18 273	97.46 298	96.47 128	99.62 188	92.99 345	99.32 267

XVG-ACMP-BASELINE		97.58 133	97.28 164	98.49 57	99.16 93	96.90 51	96.39 195	98.98 142	95.05 240	98.06 194	98.02 230	95.86 160	99.56 212	94.37 288	99.64 117	99.00 248

EG-PatchMatch MVS		97.69 112	97.79 105	97.40 169	99.06 113	93.52 226	95.96 244	98.97 145	94.55 267	98.82 86	98.76 99	97.31 58	99.29 336	97.20 98	99.44 217	99.38 143

CP-MVS		97.92 80	97.56 138	98.99 13	98.99 129	97.82 18	97.93 73	98.96 146	96.11 169	96.89 303	97.45 299	96.85 102	99.78 58	95.19 229	99.63 120	99.38 143

ACMMP		98.05 61	97.75 113	98.93 21	99.23 75	97.60 25	98.09 61	98.96 146	95.75 202	97.91 217	98.06 224	96.89 97	99.76 77	95.32 221	99.57 154	99.43 125
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
viewdifsd2359ckpt11		97.13 171	97.62 130	95.67 327	98.64 196	88.36 397	94.84 340	98.95 148	96.24 155	98.70 102	98.61 122	96.66 111	99.29 336	96.46 134	99.45 214	99.36 153

viewmsd2359difaftdt		97.13 171	97.62 130	95.67 327	98.64 196	88.36 397	94.84 340	98.95 148	96.24 155	98.70 102	98.61 122	96.66 111	99.29 336	96.46 134	99.45 214	99.36 153

ETV-MVS		96.13 253	95.90 271	96.82 223	97.76 343	93.89 210	95.40 291	98.95 148	95.87 193	95.58 394	91.00 515	96.36 137	99.72 111	93.36 333	98.83 345	96.85 465

KD-MVS_self_test		97.86 93	98.07 68	97.25 182	99.22 78	92.81 250	97.55 108	98.94 151	97.10 109	98.85 81	98.88 87	95.03 206	99.67 161	97.39 90	99.65 113	99.26 180

114514_t		93.96 375	93.22 389	96.19 288	99.06 113	90.97 312	95.99 239	98.94 151	73.88 545	93.43 468	96.93 351	92.38 300	99.37 305	89.09 435	99.28 276	98.25 376

hybridnocas07		96.00 261	96.21 250	95.39 352	97.56 372	87.89 415	93.70 405	98.93 153	93.96 297	96.48 335	97.65 279	93.38 263	99.19 361	95.39 215	98.81 349	99.08 232

usedtu_blend_shiyan5		93.74 381	93.08 393	95.71 325	94.99 500	89.17 367	97.38 121	98.93 153	96.40 146	94.75 420	87.24 536	80.36 464	99.40 285	91.84 369	95.85 501	98.55 332

SD-MVS		97.37 155	97.70 115	96.35 273	98.14 285	95.13 159	96.54 182	98.92 155	95.94 187	99.19 45	98.08 216	97.74 33	95.06 522	95.24 225	99.54 172	98.87 284
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
APD-MVS_3200maxsize		98.13 54	97.90 89	98.79 32	98.79 169	97.31 40	97.55 108	98.92 155	97.72 72	98.25 168	98.13 207	97.10 71	99.75 85	95.44 207	99.24 285	99.32 160

NormalMVS		96.87 194	96.39 238	98.30 75	99.48 37	95.57 119	96.87 153	98.90 157	96.94 118	96.85 305	97.88 247	85.36 422	99.76 77	95.63 189	99.59 144	99.57 59

Elysia		98.19 47	98.37 40	97.66 134	99.28 64	93.52 226	97.35 123	98.90 157	98.63 32	99.45 24	98.32 170	94.31 234	99.91 13	99.19 14	99.88 28	99.54 73

StellarMVS		98.19 47	98.37 40	97.66 134	99.28 64	93.52 226	97.35 123	98.90 157	98.63 32	99.45 24	98.32 170	94.31 234	99.91 13	99.19 14	99.88 28	99.54 73

SteuartSystems-ACMMP		98.02 63	97.76 111	98.79 32	99.43 43	97.21 45	97.15 134	98.90 157	96.58 136	98.08 191	97.87 250	97.02 82	99.76 77	95.25 224	99.59 144	99.40 134
Skip Steuart: Steuart Systems R&D Blog.
BridgeMVS		96.88 193	97.29 162	95.63 330	97.66 360	89.47 361	97.95 70	98.89 161	95.94 187	97.77 231	98.55 133	92.23 301	99.68 151	97.05 108	99.61 134	97.73 426

DVP-MVS++		97.96 68	97.90 89	98.12 96	97.75 345	95.40 132	99.03 8	98.89 161	96.62 130	98.62 109	98.30 178	96.97 86	99.75 85	95.70 181	99.25 282	99.21 194

test_0728_SECOND				98.25 82	99.23 75	95.49 128	96.74 166	98.89 161					99.75 85	95.48 202	99.52 183	99.53 78

test0726					99.24 72	95.51 124	96.89 152	98.89 161	95.92 189	98.64 107	98.31 172	97.06 76

MSP-MVS		97.45 144	96.92 193	99.03 8	99.26 68	97.70 21	97.66 99	98.89 161	95.65 206	98.51 123	96.46 383	92.15 303	99.81 43	95.14 237	98.58 382	99.58 51
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
MIMVSNet1		98.51 28	98.45 36	98.67 43	99.72 8	96.71 57	98.76 16	98.89 161	98.49 40	99.38 31	99.14 52	95.44 186	99.84 33	96.47 133	99.80 63	99.47 106

ACMP	92.54 13	97.47 142	97.10 177	98.55 52	99.04 121	96.70 58	96.24 213	98.89 161	93.71 303	97.97 210	97.75 267	97.44 50	99.63 183	93.22 340	99.70 97	99.32 160
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v1240		96.74 207	97.02 185	95.91 309	98.18 276	88.52 391	95.39 292	98.88 168	93.15 336	98.46 131	98.40 159	92.80 282	99.71 127	98.45 45	99.49 200	99.49 96

3Dnovator	96.53 2	97.61 124	97.64 126	97.50 154	97.74 348	93.65 223	98.49 31	98.88 168	96.86 122	97.11 279	98.55 133	95.82 164	99.73 101	95.94 168	99.42 230	99.13 214

ALIKED-LG		94.42 356	93.57 379	96.97 207	96.80 418	97.51 32	96.56 179	98.87 170	90.23 429	96.16 360	96.93 351	83.76 439	97.07 500	84.00 505	98.80 350	96.33 484

test_one_0601					99.05 119	95.50 127		98.87 170	97.21 107	98.03 198	98.30 178	96.93 90

TransMVSNet (Re)		98.38 35	98.67 21	97.51 148	99.51 32	93.39 234	98.20 55	98.87 170	98.23 53	99.48 21	99.27 34	98.47 13	99.55 217	96.52 131	99.53 176	99.60 47

DU-MVS		97.79 102	97.60 134	98.36 69	98.73 180	95.78 108	95.65 271	98.87 170	97.57 79	98.31 155	97.83 254	94.69 216	99.85 30	97.02 109	99.71 93	99.46 108

hybrid		95.77 273	95.95 268	95.23 358	97.54 375	87.44 427	93.65 407	98.86 174	93.17 334	96.06 366	97.65 279	93.14 270	99.20 359	94.94 259	98.57 383	99.04 242

TestfortrainingZip a		98.22 46	98.18 57	98.33 71	99.36 54	95.49 128	97.75 87	98.86 174	97.28 103	98.87 79	98.41 154	96.31 138	99.77 69	97.40 88	99.38 242	99.74 26

SR-MVS-dyc-post		98.14 50	97.84 97	99.02 9	98.81 163	98.05 9	97.55 108	98.86 174	97.77 67	98.20 173	98.07 218	96.60 119	99.76 77	95.49 198	99.20 287	99.26 180

RE-MVS-def			97.88 94		98.81 163	98.05 9	97.55 108	98.86 174	97.77 67	98.20 173	98.07 218	96.94 88		95.49 198	99.20 287	99.26 180

Baseline_NR-MVSNet		97.72 110	97.79 105	97.50 154	99.56 22	93.29 236	95.44 286	98.86 174	98.20 55	98.37 142	99.24 36	94.69 216	99.55 217	95.98 166	99.79 65	99.65 41

RPMNet		94.68 342	94.60 338	94.90 381	95.44 485	88.15 407	96.18 216	98.86 174	97.43 88	94.10 441	98.49 140	79.40 469	99.76 77	95.69 183	95.81 505	96.81 469

MVSMamba_PlusPlus		97.43 148	97.98 79	95.78 316	98.88 150	89.70 353	98.03 66	98.85 180	99.18 13	96.84 307	99.12 53	93.04 275	99.91 13	98.38 47	99.55 166	97.73 426

1112_ss		94.12 368	93.42 385	96.23 283	98.59 211	90.85 317	94.24 369	98.85 180	85.49 492	92.97 477	94.94 455	86.01 414	99.64 178	91.78 373	97.92 422	98.20 382

PHI-MVS		96.96 187	96.53 229	98.25 82	97.48 381	96.50 67	96.76 164	98.85 180	93.52 312	96.19 358	96.85 357	95.94 156	99.42 273	93.79 317	99.43 227	98.83 288

LS3D		97.77 104	97.50 148	98.57 50	96.24 439	97.58 27	98.45 34	98.85 180	98.58 36	97.51 246	97.94 240	95.74 171	99.63 183	95.19 229	98.97 319	98.51 339

viewdifsd2359ckpt13		96.47 229	96.42 236	96.61 239	98.35 252	91.50 297	95.31 303	98.84 184	93.21 327	96.73 314	97.58 287	95.28 195	99.26 346	94.02 305	98.45 394	99.07 235

ZNCC-MVS		97.92 80	97.62 130	98.83 28	99.32 62	97.24 43	97.45 116	98.84 184	95.76 200	96.93 299	97.43 301	97.26 64	99.79 53	96.06 157	99.53 176	99.45 112

HFP-MVS		97.94 76	97.64 126	98.83 28	99.15 96	97.50 33	97.59 105	98.84 184	96.05 176	97.49 248	97.54 289	97.07 75	99.70 136	95.61 192	99.46 211	99.30 166

region2R		97.92 80	97.59 135	98.92 24	99.22 78	97.55 29	97.60 103	98.84 184	96.00 181	97.22 267	97.62 283	96.87 101	99.76 77	95.48 202	99.43 227	99.46 108

MSLP-MVS++		96.42 235	96.71 208	95.57 334	97.82 327	90.56 325	95.71 263	98.84 184	94.72 258	96.71 316	97.39 308	94.91 212	98.10 482	95.28 222	99.02 316	98.05 400

CP-MVSNet		98.42 33	98.46 33	98.30 75	99.46 40	95.22 152	98.27 48	98.84 184	99.05 19	99.01 60	98.65 119	95.37 189	99.90 17	97.57 81	99.91 19	99.77 15

OpenMVS	94.22 8	95.48 295	95.20 297	96.32 277	97.16 404	91.96 286	97.74 93	98.84 184	87.26 471	94.36 432	98.01 232	93.95 246	99.67 161	90.70 405	98.75 362	97.35 447

SED-MVS		97.94 76	97.90 89	98.07 99	99.22 78	95.35 137	96.79 162	98.83 191	96.11 169	99.08 54	98.24 191	97.87 28	99.72 111	95.44 207	99.51 189	99.14 212

test_241102_TWO								98.83 191	96.11 169	98.62 109	98.24 191	96.92 93	99.72 111	95.44 207	99.49 200	99.49 96

test_241102_ONE					99.22 78	95.35 137		98.83 191	96.04 178	99.08 54	98.13 207	97.87 28	99.33 318

SR-MVS		98.00 64	97.66 122	99.01 11	98.77 176	97.93 14	97.38 121	98.83 191	97.32 100	98.06 194	97.85 251	96.65 114	99.77 69	95.00 249	99.11 304	99.32 160

XVS		97.96 68	97.63 128	98.94 18	99.15 96	97.66 22	97.77 84	98.83 191	97.42 89	96.32 344	97.64 281	96.49 126	99.72 111	95.66 186	99.37 244	99.45 112

X-MVStestdata		92.86 415	90.83 454	98.94 18	99.15 96	97.66 22	97.77 84	98.83 191	97.42 89	96.32 344	36.50 553	96.49 126	99.72 111	95.66 186	99.37 244	99.45 112

ACMMPR		97.95 72	97.62 130	98.94 18	99.20 87	97.56 28	97.59 105	98.83 191	96.05 176	97.46 254	97.63 282	96.77 107	99.76 77	95.61 192	99.46 211	99.49 96

ACMM	93.33 11	98.05 61	97.79 105	98.85 27	99.15 96	97.55 29	96.68 174	98.83 191	95.21 230	98.36 145	98.13 207	98.13 22	99.62 188	96.04 160	99.54 172	99.39 141
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
icg_test_0407_2		95.88 267	96.39 238	94.36 413	97.83 323	86.11 454	91.82 469	98.82 199	94.48 270	97.57 241	97.14 329	96.08 152	98.20 480	95.00 249	98.78 353	98.78 294

IMVS_0407		96.35 239	96.88 198	94.74 392	97.83 323	86.11 454	96.25 211	98.82 199	94.48 270	97.57 241	97.14 329	96.08 152	99.33 318	95.00 249	98.78 353	98.78 294

IMVS_0404		95.66 285	96.03 259	94.55 403	97.83 323	86.11 454	93.24 425	98.82 199	94.48 270	95.51 398	97.14 329	93.49 259	98.78 422	95.00 249	98.78 353	98.78 294

IMVS_0403		96.27 243	96.77 206	94.76 390	97.83 323	86.11 454	96.00 236	98.82 199	94.48 270	97.49 248	97.14 329	95.38 188	99.40 285	95.00 249	98.78 353	98.78 294

v8		97.60 125	98.06 71	96.23 283	98.71 187	89.44 362	97.43 119	98.82 199	97.29 102	98.74 97	99.10 56	93.86 248	99.68 151	98.61 40	99.94 8	99.56 67

LF4IMVS		96.07 254	95.63 286	97.36 172	98.19 273	95.55 121	95.44 286	98.82 199	92.29 364	95.70 389	96.55 377	92.63 288	98.69 436	91.75 375	99.33 265	97.85 415

GST-MVS		97.82 98	97.49 150	98.81 30	99.23 75	97.25 42	97.16 133	98.79 205	95.96 184	97.53 244	97.40 303	96.93 90	99.77 69	95.04 243	99.35 255	99.42 127

ACMMP_NAP		97.89 88	97.63 128	98.67 43	99.35 58	96.84 52	96.36 200	98.79 205	95.07 238	97.88 220	98.35 164	97.24 66	99.72 111	96.05 159	99.58 150	99.45 112

v1921920		96.72 211	96.96 189	95.99 301	98.21 270	88.79 385	95.42 288	98.79 205	93.22 325	98.19 177	98.26 189	92.68 285	99.70 136	98.34 49	99.55 166	99.49 96

DP-MVS		97.87 91	97.89 92	97.81 120	98.62 207	94.82 169	97.13 137	98.79 205	98.98 23	98.74 97	98.49 140	95.80 169	99.49 238	95.04 243	99.44 217	99.11 225

PMatch-Up-SfM		95.95 263	95.43 292	97.51 148	97.90 310	95.17 156	93.40 420	98.78 209	92.45 359	98.24 169	98.07 218	87.10 400	99.18 364	94.87 261	98.10 411	98.19 383

mPP-MVS		97.91 84	97.53 143	99.04 7	99.22 78	97.87 17	97.74 93	98.78 209	96.04 178	97.10 280	97.73 272	96.53 123	99.78 58	95.16 234	99.50 197	99.46 108

onestephybrid01		96.25 245	96.31 244	96.07 297	97.54 375	90.01 346	94.06 384	98.77 211	94.74 254	96.32 344	97.74 270	94.03 242	99.20 359	94.81 266	98.79 351	98.98 255

v144192		96.69 214	96.90 196	96.03 299	98.25 266	88.92 379	95.49 283	98.77 211	93.05 339	98.09 189	98.29 182	92.51 297	99.70 136	98.11 52	99.56 159	99.47 106

v1192		96.83 200	97.06 181	96.15 293	98.28 260	89.29 365	95.36 295	98.77 211	93.73 302	98.11 186	98.34 166	93.02 279	99.67 161	98.35 48	99.58 150	99.50 88

APD-MVS		97.00 180	96.53 229	98.41 64	98.55 218	96.31 80	96.32 203	98.77 211	92.96 346	97.44 256	97.58 287	95.84 161	99.74 95	91.96 364	99.35 255	99.19 198
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CPTT-MVS		96.69 214	96.08 256	98.49 57	98.89 149	96.64 62	97.25 128	98.77 211	92.89 348	96.01 368	97.13 333	92.23 301	99.67 161	92.24 360	99.34 260	99.17 202

test-260524					98.88 150	95.35 137		98.76 216		98.18 178		95.58 179	99.73 101	96.66 121	99.51 189

HQP_MVS		96.66 216	96.33 243	97.68 133	98.70 189	94.29 195	96.50 183	98.75 217	96.36 149	96.16 360	96.77 364	91.91 313	99.46 254	92.59 353	99.20 287	99.28 174

plane_prior5								98.75 217					99.46 254	92.59 353	99.20 287	99.28 174

PRO-TEST		95.35 305	95.48 291	94.95 378	96.49 428	87.11 437	95.86 253	98.74 219	93.21 327	95.07 409	95.57 437	93.10 272	99.51 230	92.89 350	98.37 399	98.24 377

Patchmatch-RL test		94.66 343	94.49 345	95.19 360	98.54 220	88.91 380	92.57 443	98.74 219	91.46 397	98.32 153	97.75 267	77.31 482	98.81 420	96.06 157	99.61 134	97.85 415

SMA-MVS		97.48 141	97.11 176	98.60 48	98.83 160	96.67 60	96.74 166	98.73 221	91.61 383	98.48 128	98.36 162	96.53 123	99.68 151	95.17 232	99.54 172	99.45 112
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
Fast-Effi-MVS+-dtu		96.44 232	96.12 253	97.39 170	97.18 403	94.39 188	95.46 284	98.73 221	96.03 180	94.72 423	94.92 457	96.28 144	99.69 144	93.81 316	97.98 418	98.09 390

MTGPA								98.73 221

MTAPA		98.14 50	97.84 97	99.06 6	99.44 42	97.90 15	97.25 128	98.73 221	97.69 75	97.90 218	97.96 237	95.81 168	99.82 38	96.13 156	99.61 134	99.45 112

MP-MVS		97.64 120	97.18 174	99.00 12	99.32 62	97.77 20	97.49 114	98.73 221	96.27 152	95.59 393	97.75 267	96.30 141	99.78 58	93.70 324	99.48 205	99.45 112
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NR-MVSNet		97.96 68	97.86 96	98.26 79	98.73 180	95.54 122	98.14 58	98.73 221	97.79 66	99.42 28	97.83 254	94.40 231	99.78 58	95.91 171	99.76 72	99.46 108

QAPM		95.88 267	95.57 288	96.80 225	97.90 310	91.84 290	98.18 57	98.73 221	88.41 457	96.42 339	98.13 207	94.73 213	99.75 85	88.72 441	98.94 325	98.81 290

test_0402		97.84 94	97.97 80	97.47 161	99.19 89	94.07 203	96.71 171	98.73 221	98.66 31	98.56 117	98.41 154	96.84 103	99.69 144	94.82 265	99.81 59	98.64 319

TAPA-MVS	93.32 12	94.93 327	94.23 357	97.04 201	98.18 276	94.51 184	95.22 311	98.73 221	81.22 524	96.25 353	95.95 421	93.80 251	98.98 400	89.89 423	98.87 338	97.62 434
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
3Dnovator+	96.13 3	97.73 107	97.59 135	98.15 93	98.11 289	95.60 117	98.04 64	98.70 230	98.13 56	96.93 299	98.45 147	95.30 194	99.62 188	95.64 188	98.96 322	99.24 188

Test_1112_low_res		93.53 393	92.86 401	95.54 341	98.60 209	88.86 382	92.75 437	98.69 231	82.66 515	92.65 488	96.92 354	84.75 428	99.56 212	90.94 391	97.76 435	98.19 383

DP-MVS Recon		95.55 291	95.13 302	96.80 225	98.51 224	93.99 208	94.60 352	98.69 231	90.20 430	95.78 385	96.21 401	92.73 284	98.98 400	90.58 409	98.86 340	97.42 444

CHOSEN 1792x2688		94.10 369	93.41 386	96.18 289	99.16 93	90.04 344	92.15 458	98.68 233	79.90 529	96.22 355	97.83 254	87.92 385	99.42 273	89.18 434	99.65 113	99.08 232

PVSNet_BlendedMVS		95.02 326	94.93 315	95.27 356	97.79 338	87.40 430	94.14 379	98.68 233	88.94 449	94.51 428	98.01 232	93.04 275	99.30 332	89.77 425	99.49 200	99.11 225

PVSNet_Blended		93.96 375	93.65 377	94.91 379	97.79 338	87.40 430	91.43 476	98.68 233	84.50 506	94.51 428	94.48 467	93.04 275	99.30 332	89.77 425	98.61 379	98.02 403

VortexMVS		96.04 257	96.56 222	94.49 408	97.60 369	84.36 486	96.05 229	98.67 236	94.74 254	98.95 70	98.78 94	87.13 399	99.50 232	97.37 92	99.76 72	99.60 47

v1144		96.84 197	97.08 179	96.13 294	98.42 245	89.28 366	95.41 290	98.67 236	94.21 283	97.97 210	98.31 172	93.06 274	99.65 172	98.06 57	99.62 123	99.45 112

CLD-MVS		95.47 296	95.07 305	96.69 233	98.27 263	92.53 259	91.36 477	98.67 236	91.22 404	95.78 385	94.12 471	95.65 176	98.98 400	90.81 396	99.72 90	98.57 328
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GBi-Net		96.99 181	96.80 203	97.56 142	97.96 302	93.67 219	98.23 50	98.66 239	95.59 210	97.99 203	99.19 41	89.51 354	99.73 101	94.60 279	99.44 217	99.30 166

test1		96.99 181	96.80 203	97.56 142	97.96 302	93.67 219	98.23 50	98.66 239	95.59 210	97.99 203	99.19 41	89.51 354	99.73 101	94.60 279	99.44 217	99.30 166

FMVSNet1		97.95 72	98.08 67	97.56 142	99.14 103	93.67 219	98.23 50	98.66 239	97.41 93	99.00 62	99.19 41	95.47 184	99.73 101	95.83 178	99.76 72	99.30 166

IterMVS-LS		96.92 189	97.29 162	95.79 315	98.51 224	88.13 409	95.10 319	98.66 239	96.99 111	98.46 131	98.68 113	92.55 292	99.74 95	96.91 113	99.79 65	99.50 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		95.30 309	94.38 352	98.05 105	98.64 196	96.04 96	95.61 277	98.66 239	89.00 448	93.22 472	96.40 388	92.90 280	99.35 313	87.45 465	97.53 451	98.77 303

USDC		94.56 351	94.57 343	94.55 403	97.78 341	86.43 448	92.75 437	98.65 244	85.96 486	96.91 302	97.93 242	90.82 327	98.74 427	90.71 404	99.59 144	98.47 345

PM-MVS		97.36 157	97.10 177	98.14 94	98.91 146	96.77 54	96.20 215	98.63 245	93.82 300	98.54 119	98.33 167	93.98 244	99.05 389	95.99 165	99.45 214	98.61 326

cascas		91.89 443	91.35 441	93.51 445	94.27 517	85.60 461	88.86 528	98.61 246	79.32 532	92.16 495	91.44 510	89.22 362	98.12 481	90.80 397	97.47 455	96.82 468

dtuplus		95.73 278	95.86 274	95.33 354	97.72 350	87.82 419	93.74 401	98.60 247	92.12 367	97.27 263	97.92 243	94.35 232	99.13 376	92.24 360	98.83 345	99.05 240

aaEdge-Enhanced		97.53 138	97.32 160	98.16 90	98.70 189	95.35 137	96.04 231	98.60 247	96.16 168	97.99 203	97.54 289	95.94 156	99.70 136	95.36 216	99.53 176	99.44 122

SDMVSNet		97.97 66	98.26 55	97.11 192	99.41 46	92.21 272	96.92 149	98.60 247	98.58 36	98.78 89	99.39 21	97.80 30	99.62 188	94.98 257	99.86 35	99.52 81

Fast-Effi-MVS+		95.49 293	95.07 305	96.75 229	97.67 359	92.82 248	94.22 372	98.60 247	91.61 383	93.42 469	92.90 489	96.73 109	99.70 136	92.60 352	97.89 427	97.74 425

DeepPCF-MVS	94.58 5	96.90 191	96.43 235	98.31 74	97.48 381	97.23 44	92.56 444	98.60 247	92.84 349	98.54 119	97.40 303	96.64 116	98.78 422	94.40 287	99.41 235	98.93 270

OMC-MVS		96.48 228	96.00 261	97.91 114	98.30 256	96.01 101	94.86 338	98.60 247	91.88 375	97.18 273	97.21 324	96.11 151	99.04 392	90.49 413	99.34 260	98.69 315

viewmambaseed2359dif		95.68 282	95.85 275	95.17 362	97.51 378	87.41 429	93.61 411	98.58 253	91.06 407	96.68 317	97.66 278	94.71 215	99.11 380	93.93 309	98.94 325	98.99 252

testgi		96.07 254	96.50 232	94.80 387	99.26 68	87.69 423	95.96 244	98.58 253	95.08 237	98.02 200	96.25 399	97.92 24	97.60 494	88.68 443	98.74 363	99.11 225

EGC-MVSNET		83.08 509	77.93 514	98.53 54	99.57 20	97.55 29	98.33 42	98.57 255	4.71 555	10.38 558	98.90 85	95.60 178	99.50 232	95.69 183	99.61 134	98.55 332

DKM-HiRes		96.47 229	95.93 269	98.09 98	98.86 155	96.41 73	94.38 360	98.56 256	94.05 292	96.93 299	97.48 296	87.73 388	98.55 452	95.86 176	99.48 205	99.31 165

ZD-MVS					98.43 243	95.94 102		98.56 256	90.72 414	96.66 321	97.07 338	95.02 207	99.74 95	91.08 386	98.93 330

VPNet		97.26 163	97.49 150	96.59 242	99.47 39	90.58 323	96.27 207	98.53 258	97.77 67	98.46 131	98.41 154	94.59 222	99.68 151	94.61 278	99.29 275	99.52 81

DELS-MVS		96.17 251	96.23 248	95.99 301	97.55 374	90.04 344	92.38 453	98.52 259	94.13 287	96.55 332	97.06 339	94.99 208	99.58 204	95.62 191	99.28 276	98.37 356
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
HyFIR lowres test		93.72 384	92.65 410	96.91 214	98.93 141	91.81 291	91.23 485	98.52 259	82.69 513	96.46 338	96.52 381	80.38 463	99.90 17	90.36 415	98.79 351	99.03 244

PMatch-SfM		95.65 286	95.03 308	97.51 148	97.96 302	95.00 162	93.49 416	98.51 261	92.24 365	97.80 228	98.03 228	83.97 438	99.19 361	94.77 271	98.50 389	98.35 362

DKM		96.39 237	95.99 262	97.59 140	98.44 240	96.42 72	94.42 359	98.51 261	92.81 350	98.15 182	97.47 297	89.37 360	97.26 497	95.02 248	99.68 104	99.09 231

ITE_SJBPF				97.85 118	98.64 196	96.66 61		98.51 261	95.63 207	97.22 267	97.30 318	95.52 181	98.55 452	90.97 390	98.90 333	98.34 363

eth_miper_zixun_eth		94.89 330	94.93 315	94.75 391	95.99 458	86.12 453	91.35 478	98.49 264	93.40 316	97.12 278	97.25 322	86.87 404	99.35 313	95.08 242	98.82 347	98.78 294

TinyColmap		96.00 261	96.34 242	94.96 377	97.90 310	87.91 414	94.13 380	98.49 264	94.41 277	98.16 180	97.76 264	96.29 143	98.68 439	90.52 410	99.42 230	98.30 369

dtuonlycased		95.11 319	95.70 282	93.35 448	99.05 119	81.45 511	91.13 491	98.48 266	93.11 338	97.98 208	97.27 319	96.15 150	99.32 326	89.61 427	98.50 389	99.27 178

RoMa-HiRes		97.28 161	97.05 183	97.98 110	98.78 173	96.22 85	96.48 189	98.47 267	93.69 305	98.97 66	97.73 272	93.48 260	98.47 461	96.31 145	99.51 189	99.26 180

SP-LightGlue		95.19 314	94.96 312	95.89 311	95.10 497	94.93 166	94.29 363	98.47 267	94.91 251	94.92 418	95.51 441	86.69 406	95.61 516	97.08 106	97.67 443	97.12 453

OPM-MVS		97.54 135	97.25 166	98.41 64	99.11 105	96.61 64	95.24 310	98.46 269	94.58 266	98.10 188	98.07 218	97.09 73	99.39 294	95.16 234	99.44 217	99.21 194
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
RoMa-SfM		96.87 194	96.56 222	97.79 121	98.50 230	96.46 71	95.89 250	98.45 270	91.48 394	98.84 83	97.40 303	93.93 247	97.96 485	94.99 255	99.58 150	98.96 260

tfpnnormal		97.72 110	97.97 80	96.94 210	99.26 68	92.23 271	97.83 81	98.45 270	98.25 52	99.13 50	98.66 115	96.65 114	99.69 144	93.92 310	99.62 123	98.91 274

UnsupCasMVSNet_eth		95.91 266	95.73 281	96.44 261	98.48 234	91.52 296	95.31 303	98.45 270	95.76 200	97.48 251	97.54 289	89.53 353	98.69 436	94.43 284	94.61 521	99.13 214

PCF-MVS	89.43 18	92.12 437	90.64 458	96.57 245	97.80 333	93.48 229	89.88 514	98.45 270	74.46 544	96.04 367	95.68 432	90.71 330	99.31 328	73.73 540	99.01 318	96.91 462
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
balanced_ft_v1		96.29 241	96.60 217	95.38 353	96.77 419	88.73 388	98.44 37	98.44 274	94.97 246	95.91 372	98.77 95	91.03 322	99.75 85	96.16 155	98.91 332	97.65 431

HQP3-MVS								98.43 275							98.74 363

HQP-MVS		95.17 317	94.58 341	96.92 212	97.85 313	92.47 262	94.26 364	98.43 275	93.18 331	92.86 482	95.08 451	90.33 336	99.23 355	90.51 411	98.74 363	99.05 240

DeepC-MVS_fast	94.34 7	96.74 207	96.51 231	97.44 164	97.69 354	94.15 201	96.02 234	98.43 275	93.17 334	97.30 261	97.38 310	95.48 183	99.28 341	93.74 319	99.34 260	98.88 282
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_prior				97.46 162	97.79 338	94.26 199		98.42 278					99.34 316			98.79 293

ArgMatch-SfM		95.74 277	95.15 301	97.49 157	97.82 327	95.16 157	94.03 385	98.41 279	89.33 440	97.58 240	96.65 372	90.07 343	98.89 409	93.17 342	99.30 274	98.44 349

save fliter					98.48 234	94.71 171	94.53 356	98.41 279	95.02 242

CANet		95.86 269	95.65 285	96.49 254	96.41 434	90.82 318	94.36 361	98.41 279	94.94 247	92.62 491	96.73 367	92.68 285	99.71 127	95.12 240	99.60 141	98.94 266

Anonymous20240521		97.07 177	97.51 146	95.76 317	99.35 58	88.18 406	97.78 83	98.40 282	97.11 108	98.34 149	99.04 63	89.58 349	99.79 53	98.09 54	99.93 11	99.30 166

TEST9					97.84 320	95.23 149	93.62 409	98.39 283	86.81 479	93.78 450	95.99 417	94.68 218	99.52 226

train_agg		95.46 297	94.66 332	97.88 116	97.84 320	95.23 149	93.62 409	98.39 283	87.04 475	93.78 450	95.99 417	94.58 223	99.52 226	91.76 374	98.90 333	98.89 278

KinetiMVS		97.82 98	98.02 74	97.24 184	99.24 72	92.32 267	96.92 149	98.38 285	98.56 39	99.03 57	98.33 167	93.22 267	99.83 35	98.74 35	99.71 93	99.57 59

test_8					97.81 329	95.07 161	93.54 414	98.38 285	87.04 475	93.71 455	95.96 420	94.58 223	99.52 226

MSDG		95.33 307	95.13 302	95.94 308	97.40 389	91.85 289	91.02 493	98.37 287	95.30 228	96.31 349	95.99 417	94.51 227	98.38 468	89.59 428	97.65 447	97.60 436

agg_prior					97.80 333	94.96 164		98.36 288		93.49 465			99.53 223

V42		97.04 178	97.16 175	96.68 234	98.59 211	91.05 309	96.33 202	98.36 288	94.60 263	97.99 203	98.30 178	93.32 264	99.62 188	97.40 88	99.53 176	99.38 143

MVS_111021_HR		96.73 209	96.54 228	97.27 179	98.35 252	93.66 222	93.42 418	98.36 288	94.74 254	96.58 327	96.76 366	96.54 122	98.99 398	94.87 261	99.27 278	99.15 206

c3_l		95.20 313	95.32 294	94.83 386	96.19 444	86.43 448	91.83 468	98.35 291	93.47 315	97.36 259	97.26 321	88.69 369	99.28 341	95.41 213	99.36 249	98.78 294

test_vis1_rt		94.03 374	93.65 377	95.17 362	95.76 474	93.42 232	93.97 391	98.33 292	84.68 503	93.17 473	95.89 424	92.53 296	94.79 524	93.50 330	94.97 517	97.31 450

MVS_Test		96.27 243	96.79 205	94.73 393	96.94 414	86.63 445	96.18 216	98.33 292	94.94 247	96.07 364	98.28 184	95.25 196	99.26 346	97.21 96	97.90 426	98.30 369

CDPH-MVS		95.45 298	94.65 333	97.84 119	98.28 260	94.96 164	93.73 403	98.33 292	85.03 499	95.44 400	96.60 375	95.31 193	99.44 265	90.01 420	99.13 300	99.11 225

MVS_111021_LR		96.82 201	96.55 226	97.62 138	98.27 263	95.34 143	93.81 399	98.33 292	94.59 265	96.56 330	96.63 374	96.61 117	98.73 428	94.80 267	99.34 260	98.78 294

Anonymous20240529		97.96 68	98.04 72	97.71 128	98.69 192	94.28 198	97.86 78	98.31 296	98.79 28	99.23 42	98.86 89	95.76 170	99.61 196	95.49 198	99.36 249	99.23 190

FMVSNet5		93.39 396	92.35 417	96.50 253	95.83 467	90.81 320	97.31 125	98.27 297	92.74 352	96.27 351	98.28 184	62.23 524	99.67 161	90.86 394	99.36 249	99.03 244

v2v482		96.78 204	97.06 181	95.95 306	98.57 215	88.77 386	95.36 295	98.26 298	95.18 233	97.85 225	98.23 193	92.58 289	99.63 183	97.80 69	99.69 99	99.45 112

sd_testset		97.97 66	98.12 60	97.51 148	99.41 46	93.44 230	97.96 68	98.25 299	98.58 36	98.78 89	99.39 21	98.21 18	99.56 212	92.65 351	99.86 35	99.52 81

PLC	91.02 16	94.05 372	92.90 400	97.51 148	98.00 300	95.12 160	94.25 367	98.25 299	86.17 484	91.48 502	95.25 449	91.01 323	99.19 361	85.02 497	96.69 481	98.22 380
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
miper_ehance_all_eth		94.69 340	94.70 331	94.64 395	95.77 473	86.22 451	91.32 481	98.24 301	91.67 380	97.05 287	96.65 372	88.39 374	99.22 357	94.88 260	98.34 401	98.49 344

DVP-MVS		97.78 103	97.65 123	98.16 90	99.24 72	95.51 124	96.74 166	98.23 302	95.92 189	98.40 139	98.28 184	97.06 76	99.71 127	95.48 202	99.52 183	99.26 180
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
xiu_mvs_v1_base_debu		95.62 287	95.96 265	94.60 399	98.01 296	88.42 394	93.99 388	98.21 303	92.98 342	95.91 372	94.53 464	96.39 134	99.72 111	95.43 210	98.19 407	95.64 498

xiu_mvs_v1_base		95.62 287	95.96 265	94.60 399	98.01 296	88.42 394	93.99 388	98.21 303	92.98 342	95.91 372	94.53 464	96.39 134	99.72 111	95.43 210	98.19 407	95.64 498

xiu_mvs_v1_base_debi		95.62 287	95.96 265	94.60 399	98.01 296	88.42 394	93.99 388	98.21 303	92.98 342	95.91 372	94.53 464	96.39 134	99.72 111	95.43 210	98.19 407	95.64 498

ALIKED-MNN		93.09 411	92.12 424	96.00 300	96.50 427	96.72 56	95.52 281	98.20 306	82.37 517	90.90 505	96.15 405	87.02 401	96.30 512	83.03 514	99.42 230	94.99 506

miper_lstm_enhance		94.81 334	94.80 328	94.85 384	96.16 447	86.45 447	91.14 489	98.20 306	93.49 314	97.03 288	97.37 312	84.97 427	99.26 346	95.28 222	99.56 159	98.83 288

TSAR-MVS + MP.		97.42 150	97.23 168	98.00 108	99.38 52	95.00 162	97.63 102	98.20 306	93.00 341	98.16 180	98.06 224	95.89 159	99.72 111	95.67 185	99.10 307	99.28 174
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MVP-Stereo		95.69 280	95.28 295	96.92 212	98.15 283	93.03 243	95.64 275	98.20 306	90.39 422	96.63 324	97.73 272	91.63 315	99.10 384	91.84 369	97.31 461	98.63 321
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS++		96.99 181	96.38 240	98.81 30	98.64 196	97.59 26	95.97 242	98.20 306	95.51 215	95.06 411	96.53 379	94.10 240	99.70 136	94.29 291	99.15 297	99.13 214

NCCC		96.52 224	95.99 262	98.10 97	97.81 329	95.68 113	95.00 330	98.20 306	95.39 224	95.40 403	96.36 390	93.81 250	99.45 262	93.55 329	98.42 397	99.17 202

new-patchmatchnet		95.67 283	96.58 219	92.94 472	97.48 381	80.21 520	92.96 432	98.19 312	94.83 252	98.82 86	98.79 91	93.31 265	99.51 230	95.83 178	99.04 315	99.12 220

test_f		95.82 271	95.88 273	95.66 329	97.61 367	93.21 241	95.61 277	98.17 313	86.98 477	98.42 136	99.47 16	90.46 333	94.74 526	97.71 75	98.45 394	99.03 244

MCST-MVS		96.24 246	95.80 278	97.56 142	98.75 178	94.13 202	94.66 350	98.17 313	90.17 431	96.21 356	96.10 411	95.14 202	99.43 269	94.13 298	98.85 341	99.13 214

door-mid								98.17 313

CNVR-MVS		96.92 189	96.55 226	98.03 106	98.00 300	95.54 122	94.87 337	98.17 313	94.60 263	96.38 341	97.05 340	95.67 175	99.36 309	95.12 240	99.08 309	99.19 198

MSC_two_6792asdad				98.22 84	97.75 345	95.34 143		98.16 317					99.75 85	95.87 174	99.51 189	99.57 59

No_MVS				98.22 84	97.75 345	95.34 143		98.16 317					99.75 85	95.87 174	99.51 189	99.57 59

原ACMM1				96.58 243	98.16 281	92.12 277		98.15 319	85.90 488	93.49 465	96.43 385	92.47 298	99.38 298	87.66 458	98.62 378	98.23 378

DenseAffine		96.06 256	95.57 288	97.53 147	98.44 240	95.79 107	94.20 374	98.14 320	92.44 361	97.95 213	97.18 327	88.87 367	97.96 485	93.41 331	99.52 183	98.85 287

IU-MVS					99.22 78	95.40 132		98.14 320	85.77 490	98.36 145				95.23 226	99.51 189	99.49 96

ambc				96.56 247	98.23 269	91.68 294	97.88 77	98.13 322		98.42 136	98.56 132	94.22 238	99.04 392	94.05 302	99.35 255	98.95 263

WR-MVS		96.90 191	96.81 201	97.16 188	98.56 217	92.20 275	94.33 362	98.12 323	97.34 99	98.20 173	97.33 315	92.81 281	99.75 85	94.79 268	99.81 59	99.54 73

cdsmvs_eth3d_5k		24.22 519	32.30 522	0.00 541	0.00 565	0.00 568	0.00 553	98.10 324	0.00 560	0.00 561	95.06 453	97.54 45	0.00 561	0.00 560	0.00 560	0.00 557

dtuonly		92.30 432	93.44 383	88.89 518	95.60 481	69.49 554	89.18 525	98.09 325	88.17 462	94.19 436	96.35 391	88.98 365	98.72 431	91.74 376	98.69 370	98.45 348

Effi-MVS+-dtu		96.81 202	96.09 255	98.99 13	96.90 416	98.69 4	96.42 192	98.09 325	95.86 194	95.15 408	95.54 438	94.26 237	99.81 43	94.06 300	98.51 388	98.47 345

cl____		94.73 335	94.64 334	95.01 372	95.85 466	87.00 439	91.33 479	98.08 327	93.34 320	97.10 280	97.33 315	84.01 437	99.30 332	95.14 237	99.56 159	98.71 314

DIV-MVS_self_test		94.73 335	94.64 334	95.01 372	95.86 465	87.00 439	91.33 479	98.08 327	93.34 320	97.10 280	97.34 314	84.02 436	99.31 328	95.15 236	99.55 166	98.72 310

test11								98.08 327

AdaColmap		95.11 319	94.62 337	96.58 243	97.33 396	94.45 187	94.92 334	98.08 327	93.15 336	93.98 448	95.53 440	94.34 233	99.10 384	85.69 485	98.61 379	96.20 488

pmmvs-eth3d		96.49 227	96.18 252	97.42 167	98.25 266	94.29 195	94.77 345	98.07 331	89.81 435	97.97 210	98.33 167	93.11 271	99.08 386	95.46 205	99.84 50	98.89 278

usedtu_dtu_shiyan2		97.54 135	97.26 165	98.37 67	99.54 28	96.04 96	97.94 71	98.06 332	97.36 98	98.62 109	98.20 198	95.52 181	99.73 101	90.90 393	99.18 292	99.33 158

FMVSNet2		96.72 211	96.67 211	96.87 218	97.96 302	91.88 288	97.15 134	98.06 332	95.59 210	98.50 125	98.62 121	89.51 354	99.65 172	94.99 255	99.60 141	99.07 235

UnsupCasMVSNet_bld		94.72 339	94.26 356	96.08 296	98.62 207	90.54 326	93.38 421	98.05 334	90.30 425	97.02 289	96.80 363	89.54 350	99.16 370	88.44 446	96.18 495	98.56 329

PAPM_NR		94.61 347	94.17 362	95.96 304	98.36 251	91.23 306	95.93 247	97.95 335	92.98 342	93.42 469	94.43 468	90.53 331	98.38 468	87.60 459	96.29 493	98.27 373

SD_0403		93.73 383	93.43 384	94.64 395	97.85 313	86.35 450	97.47 115	97.94 336	93.50 313	93.71 455	96.73 367	93.77 252	98.84 416	73.48 541	96.39 489	98.72 310

D2MVS		95.18 315	95.17 300	95.21 359	97.76 343	87.76 422	94.15 377	97.94 336	89.77 436	96.99 293	97.68 277	87.45 391	99.14 372	95.03 247	99.81 59	98.74 307

SP-SuperGlue		95.41 300	95.38 293	95.51 342	94.92 505	94.67 174	94.09 382	97.93 338	95.45 218	95.62 390	96.26 397	89.54 350	95.26 518	96.70 120	97.92 422	96.61 476

无先验							93.20 427	97.91 339	80.78 525				99.40 285	87.71 455		97.94 409

v148		96.58 222	96.97 187	95.42 347	98.63 205	87.57 424	95.09 320	97.90 340	95.91 191	98.24 169	97.96 237	93.42 262	99.39 294	96.04 160	99.52 183	99.29 173

ArgMatch-Sym		95.60 290	94.97 311	97.48 159	97.70 353	95.41 131	93.60 413	97.89 341	89.33 440	97.70 233	96.03 416	91.00 325	98.66 441	92.25 359	99.18 292	98.39 353

CNLPA		95.04 323	94.47 347	96.75 229	97.81 329	95.25 148	94.12 381	97.89 341	94.41 277	94.57 426	95.69 431	90.30 339	98.35 471	86.72 472	98.76 361	96.64 473

PAPR		92.22 434	91.27 444	95.07 367	95.73 476	88.81 384	91.97 464	97.87 343	85.80 489	90.91 504	92.73 495	91.16 319	98.33 472	79.48 526	95.76 510	98.08 391

miper_enhance_ethall		93.14 408	92.78 406	94.20 422	93.65 526	85.29 468	89.97 510	97.85 344	85.05 498	96.15 363	94.56 463	85.74 416	99.14 372	93.74 319	98.34 401	98.17 387

Anonymous20231206		95.27 310	95.06 307	95.88 312	98.72 183	89.37 364	95.70 264	97.85 344	88.00 465	96.98 296	97.62 283	91.95 310	99.34 316	89.21 433	99.53 176	98.94 266

SP-DiffGlue		94.64 345	94.54 344	94.97 376	93.53 529	94.33 193	93.94 393	97.84 346	93.35 319	96.58 327	95.54 438	88.87 367	94.71 527	93.73 321	97.44 457	95.87 493

xiu_mvs_v2_base		94.22 363	94.63 336	92.99 470	97.32 397	84.84 479	92.12 460	97.84 346	91.96 373	94.17 438	93.43 478	96.07 154	99.71 127	91.27 382	97.48 453	94.42 512

PS-MVSNAJ		94.10 369	94.47 347	93.00 469	97.35 392	84.88 476	91.86 467	97.84 346	91.96 373	94.17 438	92.50 499	95.82 164	99.71 127	91.27 382	97.48 453	94.40 513

CANet_DTU		94.65 344	94.21 360	95.96 304	95.90 462	89.68 355	93.92 394	97.83 349	93.19 330	90.12 518	95.64 434	88.52 371	99.57 210	93.27 338	99.47 208	98.62 322

door								97.81 350

test12				97.46 162	97.61 367	94.07 203		97.78 351		93.57 463		93.31 265	99.42 273		98.78 353	98.89 278

旧先验1					97.80 333	93.87 211		97.75 352			97.04 341	93.57 257			98.68 371	98.72 310

新几何1				97.25 182	98.29 257	94.70 173		97.73 353	77.98 538	94.83 419	96.67 371	92.08 307	99.45 262	88.17 452	98.65 376	97.61 435

testdata				95.70 326	98.16 281	90.58 323		97.72 354	80.38 527	95.62 390	97.02 342	92.06 308	98.98 400	89.06 437	98.52 385	97.54 439

test20.03		96.58 222	96.61 215	96.48 255	98.49 232	91.72 292	95.68 267	97.69 355	96.81 124	98.27 160	97.92 243	94.18 239	98.71 433	90.78 398	99.66 111	99.00 248

ab-mvs		96.59 219	96.59 218	96.60 240	98.64 196	92.21 272	98.35 39	97.67 356	94.45 275	96.99 293	98.79 91	94.96 211	99.49 238	90.39 414	99.07 311	98.08 391

CMPMVS	73.10 23	92.74 418	91.39 440	96.77 228	93.57 528	94.67 174	94.21 373	97.67 356	80.36 528	93.61 460	96.60 375	82.85 447	97.35 496	84.86 499	98.78 353	98.29 372
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
mvs_anonymous		95.36 303	96.07 257	93.21 460	96.29 438	81.56 509	94.60 352	97.66 358	93.30 322	96.95 298	98.91 84	93.03 278	99.38 298	96.60 128	97.30 462	98.69 315

FMVSNet3		95.26 311	94.94 313	96.22 285	96.53 426	90.06 342	95.99 239	97.66 358	94.11 289	97.99 203	97.91 245	80.22 468	99.63 183	94.60 279	99.44 217	98.96 260

EI-MVSNet-UG-set		97.32 159	97.40 152	97.09 196	97.34 394	92.01 285	95.33 300	97.65 360	97.74 70	98.30 157	98.14 205	95.04 205	99.69 144	97.55 82	99.52 183	99.58 51

EI-MVSNet-Vis-set		97.32 159	97.39 153	97.11 192	97.36 391	92.08 281	95.34 299	97.65 360	97.74 70	98.29 158	98.11 212	95.05 204	99.68 151	97.50 84	99.50 197	99.56 67

EI-MVSNet		96.63 217	96.93 191	95.74 319	97.26 399	88.13 409	95.29 306	97.65 360	96.99 111	97.94 215	98.19 199	92.55 292	99.58 204	96.91 113	99.56 159	99.50 88

MVSTER		94.21 365	93.93 371	95.05 369	95.83 467	86.46 446	95.18 315	97.65 360	92.41 362	97.94 215	98.00 234	72.39 507	99.58 204	96.36 141	99.56 159	99.12 220

usedtu_dtu_shiyan1		94.61 347	94.29 354	95.57 334	97.93 307	88.45 392	91.30 482	97.64 364	91.61 383	95.85 381	95.79 428	86.65 409	99.48 241	92.92 348	98.97 319	98.78 294

FE-MVSNET3		94.61 347	94.29 354	95.57 334	97.93 307	88.45 392	91.30 482	97.64 364	91.61 383	95.85 381	95.79 428	86.65 409	99.48 241	92.92 348	98.97 319	98.78 294

TestfortrainingZip				97.39 170	97.24 401	94.58 180	97.75 87	97.64 364	96.08 173	96.48 335	96.31 394	92.56 290	99.27 344		96.62 483	98.31 366

IterMVS-SCA-FT		95.86 269	96.19 251	94.85 384	97.68 355	85.53 462	92.42 450	97.63 367	96.99 111	98.36 145	98.54 135	87.94 381	99.75 85	97.07 107	99.08 309	99.27 178

test222					98.17 279	93.24 239	92.74 439	97.61 368	75.17 543	94.65 425	96.69 370	90.96 326			98.66 374	97.66 430

VNet		96.84 197	96.83 200	96.88 217	98.06 291	92.02 284	96.35 201	97.57 369	97.70 74	97.88 220	97.80 260	92.40 299	99.54 220	94.73 274	98.96 322	99.08 232

PMVS	89.60 17	96.71 213	96.97 187	95.95 306	99.51 32	97.81 19	97.42 120	97.49 370	97.93 63	95.95 370	98.58 128	96.88 99	96.91 504	89.59 428	99.36 249	93.12 522
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ppachtmachnet_test		94.49 355	94.84 324	93.46 446	96.16 447	82.10 504	90.59 500	97.48 371	90.53 418	97.01 291	97.59 285	91.01 323	99.36 309	93.97 308	99.18 292	98.94 266

DPM-MVS		93.68 387	92.77 407	96.42 265	97.91 309	92.54 258	91.17 488	97.47 372	84.99 501	93.08 475	94.74 460	89.90 345	99.00 396	87.54 461	98.09 413	97.72 428

IterMVS		95.42 299	95.83 277	94.20 422	97.52 377	83.78 494	92.41 451	97.47 372	95.49 217	98.06 194	98.49 140	87.94 381	99.58 204	96.02 162	99.02 316	99.23 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS3.2		95.75 276	96.56 222	93.34 449	98.69 192	80.75 517	91.60 472	97.43 374	97.37 97	96.99 293	97.02 342	93.69 255	99.71 127	96.32 144	99.89 26	99.55 71

MS-PatchMatch		94.83 332	94.91 317	94.57 402	96.81 417	87.10 438	94.23 371	97.34 375	88.74 452	97.14 276	97.11 336	91.94 311	98.23 477	92.99 345	97.92 422	98.37 356

ALIKED-NN		90.94 459	89.58 468	95.02 371	94.61 511	96.31 80	93.16 429	97.27 376	79.38 531	86.25 540	95.27 448	83.42 442	94.29 532	79.08 528	97.77 432	94.46 510

MDA-MVSNet-bldmvs		95.69 280	95.67 283	95.74 319	98.48 234	88.76 387	92.84 434	97.25 377	96.00 181	97.59 239	97.95 239	91.38 317	99.46 254	93.16 343	96.35 491	98.99 252

PatchMatch-RL		94.61 347	93.81 372	97.02 205	98.19 273	95.72 110	93.66 406	97.23 378	88.17 462	94.94 416	95.62 435	91.43 316	98.57 449	87.36 466	97.68 442	96.76 471

ELoFTR		95.12 318	94.86 321	95.91 309	98.39 248	93.23 240	94.57 354	97.21 379	87.26 471	98.53 122	98.52 136	86.67 408	97.37 495	93.24 339	99.36 249	97.12 453

CR-MVSNet		93.29 404	92.79 404	94.78 389	95.44 485	88.15 407	96.18 216	97.20 380	84.94 502	94.10 441	98.57 130	77.67 477	99.39 294	95.17 232	95.81 505	96.81 469

Patchmtry		95.03 325	94.59 340	96.33 274	94.83 508	90.82 318	96.38 198	97.20 380	96.59 135	97.49 248	98.57 130	77.67 477	99.38 298	92.95 347	99.62 123	98.80 291

API-MVS		95.09 322	95.01 309	95.31 355	96.61 423	94.02 206	96.83 156	97.18 382	95.60 209	95.79 383	94.33 469	94.54 226	98.37 470	85.70 484	98.52 385	93.52 518

MAR-MVS		94.21 365	93.03 395	97.76 125	96.94 414	97.44 37	96.97 147	97.15 383	87.89 467	92.00 496	92.73 495	92.14 304	99.12 377	83.92 506	97.51 452	96.73 472
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
pmmvs5		94.63 346	94.34 353	95.50 343	97.63 366	88.34 399	94.02 386	97.13 384	87.15 474	95.22 407	97.15 328	87.50 390	99.27 344	93.99 306	99.26 281	98.88 282

UGNet		96.81 202	96.56 222	97.58 141	96.64 422	93.84 213	97.75 87	97.12 385	96.47 145	93.62 459	98.88 87	93.22 267	99.53 223	95.61 192	99.69 99	99.36 153
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
blended_shiyan8		93.34 399	92.55 414	95.73 323	95.69 477	89.08 375	92.36 454	97.11 386	91.47 395	95.42 402	88.94 529	82.26 451	99.48 241	93.84 314	95.81 505	98.62 322

blended_shiyan6		93.34 399	92.54 415	95.73 323	95.68 478	89.08 375	92.35 455	97.10 387	91.47 395	95.37 404	88.96 528	82.26 451	99.48 241	93.83 315	95.85 501	98.62 322

blend_shiyan4		88.73 487	86.43 502	95.61 331	95.31 491	89.17 367	92.13 459	97.10 387	91.59 389	94.15 440	87.38 535	52.97 549	99.40 285	91.84 369	75.42 549	98.27 373

h-mvs33		96.29 241	95.63 286	98.26 79	98.50 230	96.11 92	96.90 151	97.09 389	96.58 136	97.21 269	98.19 199	84.14 433	99.78 58	95.89 172	96.17 496	98.89 278

CHOSEN 280x420		89.98 468	89.19 474	92.37 488	95.60 481	81.13 515	86.22 535	97.09 389	81.44 523	87.44 536	93.15 479	73.99 497	99.47 247	88.69 442	99.07 311	96.52 478

CDS-MVSNet		94.88 331	94.12 364	97.14 190	97.64 365	93.57 224	93.96 392	97.06 391	90.05 432	96.30 350	96.55 377	86.10 413	99.47 247	90.10 419	99.31 270	98.40 351
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
wanda-best-256-512		92.66 420	91.75 435	95.40 350	94.99 500	88.19 403	90.89 494	97.05 392	91.02 409	94.75 420	87.24 536	80.36 464	99.46 254	93.63 326	95.85 501	98.55 332

FE-blended-shiyan7		92.66 420	91.75 435	95.40 350	94.99 500	88.19 403	90.89 494	97.05 392	91.02 409	94.75 420	87.24 536	80.36 464	99.46 254	93.63 326	95.85 501	98.55 332

reproduce_monomvs		92.05 440	92.26 419	91.43 500	95.42 487	75.72 541	95.68 267	97.05 392	94.47 274	97.95 213	98.35 164	55.58 541	99.05 389	96.36 141	99.44 217	99.51 85

BH-untuned		94.69 340	94.75 330	94.52 405	97.95 306	87.53 425	94.07 383	97.01 395	93.99 295	97.10 280	95.65 433	92.65 287	98.95 405	87.60 459	96.74 477	97.09 455

sss		94.22 363	93.72 375	95.74 319	97.71 352	89.95 347	93.84 396	96.98 396	88.38 459	93.75 453	95.74 430	87.94 381	98.89 409	91.02 388	98.10 411	98.37 356

1314		92.38 428	92.30 418	92.64 482	95.42 487	85.15 471	95.86 253	96.97 397	85.40 495	90.62 507	93.06 485	91.12 320	97.80 491	86.74 471	95.49 514	94.97 507

SixPastTwentyTwo		97.49 140	97.57 137	97.26 181	99.56 22	92.33 265	98.28 46	96.97 397	98.30 49	99.45 24	99.35 28	88.43 373	99.89 20	98.01 59	99.76 72	99.54 73

LoFTR		95.39 301	95.01 309	96.52 251	97.16 404	95.19 155	94.77 345	96.95 399	90.31 424	98.78 89	98.29 182	86.71 405	97.91 487	92.56 355	99.57 154	96.46 482

TSAR-MVS + GP.		96.47 229	96.12 253	97.49 157	97.74 348	95.23 149	94.15 377	96.90 400	93.26 323	98.04 197	96.70 369	94.41 229	98.89 409	94.77 271	99.14 298	98.37 356

our_test_3		94.20 367	94.58 341	93.07 464	96.16 447	81.20 514	90.42 503	96.84 401	90.72 414	97.14 276	97.13 333	90.47 332	99.11 380	94.04 303	98.25 405	98.91 274

alignmvs		96.01 260	95.52 290	97.50 154	97.77 342	94.71 171	96.07 226	96.84 401	97.48 86	96.78 312	94.28 470	85.50 421	99.40 285	96.22 151	98.73 366	98.40 351

CL-MVSNet_self_test		95.04 323	94.79 329	95.82 314	97.51 378	89.79 351	91.14 489	96.82 403	93.05 339	96.72 315	96.40 388	90.82 327	99.16 370	91.95 365	98.66 374	98.50 342

TAMVS		95.49 293	94.94 313	97.16 188	98.31 255	93.41 233	95.07 323	96.82 403	91.09 406	97.51 246	97.82 257	89.96 344	99.42 273	88.42 447	99.44 217	98.64 319

pmmvs4		94.82 333	94.19 361	96.70 232	97.42 388	92.75 254	92.09 462	96.76 405	86.80 480	95.73 388	97.22 323	89.28 361	98.89 409	93.28 337	99.14 298	98.46 347

jason		94.39 359	94.04 366	95.41 349	98.29 257	87.85 418	92.74 439	96.75 406	85.38 496	95.29 405	96.15 405	88.21 380	99.65 172	94.24 293	99.34 260	98.74 307
jason: jason.
MVS		90.02 466	89.20 473	92.47 486	94.71 509	86.90 441	95.86 253	96.74 407	64.72 547	90.62 507	92.77 493	92.54 294	98.39 467	79.30 527	95.56 513	92.12 523

IS-MVSNet		96.93 188	96.68 210	97.70 130	99.25 71	94.00 207	98.57 23	96.74 407	98.36 45	98.14 184	97.98 236	88.23 379	99.71 127	93.10 344	99.72 90	99.38 143

MonoMVSNet		93.30 403	93.96 370	91.33 503	94.14 521	81.33 513	97.68 98	96.69 409	95.38 225	96.32 344	98.42 151	84.12 435	96.76 508	90.78 398	92.12 532	95.89 492

OpenMVS_ROB	91.80 14	93.64 390	93.05 394	95.42 347	97.31 398	91.21 307	95.08 322	96.68 410	81.56 521	96.88 304	96.41 386	90.44 335	99.25 349	85.39 490	97.67 443	95.80 496

SIFT-UM-Cal		93.74 381	93.73 373	93.78 437	95.97 460	96.07 94	89.78 516	96.67 411	91.69 379	97.77 231	96.09 413	89.51 354	94.75 525	86.68 473	99.39 240	90.52 540

cl22		93.25 405	92.84 403	94.46 410	94.30 516	86.00 458	91.09 492	96.64 412	90.74 413	95.79 383	96.31 394	78.24 474	98.77 424	94.15 297	98.34 401	98.62 322

gbinet_0.2-2-1-0.02		92.86 415	91.78 433	96.13 294	94.34 514	90.06 342	91.90 466	96.63 413	91.73 377	94.24 434	86.22 542	80.26 467	99.56 212	93.87 312	96.80 475	98.77 303

SP-MNN		94.33 361	94.22 359	94.67 394	94.94 504	92.73 256	93.74 401	96.59 414	92.73 353	93.75 453	95.38 446	88.24 377	95.08 521	94.86 264	97.78 431	96.20 488

EPP-MVSNet		96.84 197	96.58 219	97.65 136	99.18 91	93.78 216	98.68 17	96.34 415	97.91 64	97.30 261	98.06 224	88.46 372	99.85 30	93.85 313	99.40 236	99.32 160

BH-RMVSNet		94.56 351	94.44 350	94.91 379	97.57 370	87.44 427	93.78 400	96.26 416	93.69 305	96.41 340	96.50 382	92.10 306	99.00 396	85.96 482	97.71 439	98.31 366

LuminaMVS		96.76 206	96.58 219	97.30 176	98.94 137	92.96 245	96.17 220	96.15 417	95.54 214	98.96 69	98.18 202	87.73 388	99.80 50	97.98 60	99.61 134	99.15 206

GA-MVS		92.83 417	92.15 423	94.87 383	96.97 411	87.27 433	90.03 509	96.12 418	91.83 376	94.05 444	94.57 462	76.01 489	98.97 404	92.46 357	97.34 460	98.36 361

lupinMVS		93.77 379	93.28 387	95.24 357	97.68 355	87.81 420	92.12 460	96.05 419	84.52 505	94.48 430	95.06 453	86.90 402	99.63 183	93.62 328	99.13 300	98.27 373

test_method		66.88 513	66.13 516	69.11 531	62.68 557	25.73 563	49.76 548	96.04 420	14.32 554	64.27 553	91.69 508	73.45 504	88.05 548	76.06 537	66.94 550	93.54 517

PMMVS2		93.66 388	94.07 365	92.45 487	97.57 370	80.67 518	86.46 534	96.00 421	93.99 295	97.10 280	97.38 310	89.90 345	97.82 490	88.76 440	99.47 208	98.86 285

WTY-MVS		93.55 392	93.00 397	95.19 360	97.81 329	87.86 416	93.89 395	96.00 421	89.02 447	94.07 443	95.44 444	86.27 412	99.33 318	87.69 457	96.82 473	98.39 353

PMMVS		92.39 427	91.08 447	96.30 279	93.12 532	92.81 250	90.58 501	95.96 423	79.17 533	91.85 498	92.27 500	90.29 340	98.66 441	89.85 424	96.68 482	97.43 443

MG-MVS		94.08 371	94.00 367	94.32 418	97.09 408	85.89 459	93.19 428	95.96 423	92.52 356	94.93 417	97.51 294	89.54 350	98.77 424	87.52 463	97.71 439	98.31 366

WBMVS		91.11 454	90.72 456	92.26 491	95.99 458	77.98 531	91.47 475	95.90 425	91.63 381	95.90 376	96.45 384	59.60 527	99.46 254	89.97 422	99.59 144	99.33 158

MDA-MVSNet_test_wron		94.73 335	94.83 326	94.42 411	97.48 381	85.15 471	90.28 506	95.87 426	92.52 356	97.48 251	97.76 264	91.92 312	99.17 369	93.32 335	96.80 475	98.94 266

YYNet1		94.73 335	94.84 324	94.41 412	97.47 385	85.09 473	90.29 505	95.85 427	92.52 356	97.53 244	97.76 264	91.97 309	99.18 364	93.31 336	96.86 470	98.95 263

ADS-MVSNet2		91.47 450	90.51 460	94.36 413	95.51 483	85.63 460	95.05 327	95.70 428	83.46 511	92.69 486	96.84 358	79.15 471	99.41 283	85.66 486	90.52 534	98.04 401

tt0805		97.44 146	97.56 138	97.11 192	99.55 24	96.36 76	98.66 21	95.66 429	98.31 47	97.09 285	95.45 443	97.17 69	98.50 458	98.67 39	97.45 456	96.48 480

BH-w/o		92.14 436	91.94 426	92.73 479	97.13 407	85.30 467	92.46 447	95.64 430	89.33 440	94.21 435	92.74 494	89.60 348	98.24 476	81.68 519	94.66 520	94.66 509

KD-MVS_2432*1600		88.93 483	87.74 489	92.49 484	88.04 550	81.99 505	89.63 521	95.62 431	91.35 400	95.06 411	93.11 480	56.58 535	98.63 444	85.19 494	95.07 515	96.85 465

miper_refine_blended		88.93 483	87.74 489	92.49 484	88.04 550	81.99 505	89.63 521	95.62 431	91.35 400	95.06 411	93.11 480	56.58 535	98.63 444	85.19 494	95.07 515	96.85 465

VDD-MVS		97.37 155	97.25 166	97.74 126	98.69 192	94.50 186	97.04 142	95.61 433	98.59 35	98.51 123	98.72 102	92.54 294	99.58 204	96.02 162	99.49 200	99.12 220

SIFT-NCMNet		93.23 407	93.19 390	93.34 449	95.31 491	95.59 118	88.29 530	95.60 434	91.60 387	98.43 135	96.34 393	89.80 347	93.57 538	83.82 509	99.57 154	90.85 537

PAPM		87.64 497	85.84 504	93.04 466	96.54 425	84.99 475	88.42 529	95.57 435	79.52 530	83.82 542	93.05 486	80.57 462	98.41 465	62.29 547	92.79 529	95.71 497

test_yl		94.40 357	94.00 367	95.59 332	96.95 412	89.52 359	94.75 347	95.55 436	96.18 166	96.79 308	96.14 408	81.09 459	99.18 364	90.75 400	97.77 432	98.07 393

DCV-MVSNet		94.40 357	94.00 367	95.59 332	96.95 412	89.52 359	94.75 347	95.55 436	96.18 166	96.79 308	96.14 408	81.09 459	99.18 364	90.75 400	97.77 432	98.07 393

AUN-MVS		93.95 377	92.69 409	97.74 126	97.80 333	95.38 134	95.57 280	95.46 438	91.26 402	92.64 489	96.10 411	74.67 495	99.55 217	93.72 323	96.97 466	98.30 369

hse-mvs2		95.77 273	95.09 304	97.79 121	97.84 320	95.51 124	95.66 269	95.43 439	96.58 136	97.21 269	96.16 404	84.14 433	99.54 220	95.89 172	96.92 467	98.32 364

WB-MVS		95.50 292	96.62 213	92.11 494	99.21 85	77.26 536	96.12 223	95.40 440	98.62 34	98.84 83	98.26 189	91.08 321	99.50 232	93.37 332	98.70 369	99.58 51

mvsmamba		94.91 328	94.41 351	96.40 271	97.65 362	91.30 303	97.92 74	95.32 441	91.50 392	95.54 396	98.38 160	83.06 445	99.68 151	92.46 357	97.84 429	98.23 378

VDDNet		96.98 184	96.84 199	97.41 168	99.40 49	93.26 238	97.94 71	95.31 442	99.26 11	98.39 141	99.18 45	87.85 386	99.62 188	95.13 239	99.09 308	99.35 157

SymmetryMVS		96.43 234	95.85 275	98.17 88	98.58 213	95.57 119	96.87 153	95.29 443	96.94 118	96.85 305	97.88 247	85.36 422	99.76 77	95.63 189	99.27 278	99.19 198

BP-MVS1		95.36 303	94.86 321	96.89 216	98.35 252	91.72 292	96.76 164	95.21 444	96.48 144	96.23 354	97.19 325	75.97 490	99.80 50	97.91 63	99.60 141	99.15 206

FA-MVS(test-final)		94.91 328	94.89 318	94.99 374	97.51 378	88.11 411	98.27 48	95.20 445	92.40 363	96.68 317	98.60 126	83.44 441	99.28 341	93.34 334	98.53 384	97.59 437

SSC-MVS		95.92 265	97.03 184	92.58 483	99.28 64	78.39 526	96.68 174	95.12 446	98.90 25	99.11 51	98.66 115	91.36 318	99.68 151	95.00 249	99.16 296	99.67 36

MVStest1		91.89 443	91.45 438	93.21 460	89.01 546	84.87 477	95.82 258	95.05 447	91.50 392	98.75 96	99.19 41	57.56 530	95.11 520	97.78 71	98.37 399	99.64 44

wuyk23d		93.25 405	95.20 297	87.40 526	96.07 455	95.38 134	97.04 142	94.97 448	95.33 226	99.70 9	98.11 212	98.14 21	91.94 543	77.76 534	99.68 104	74.89 547

ttmdpeth		94.05 372	94.15 363	93.75 438	95.81 469	85.32 466	96.00 236	94.93 449	92.07 369	94.19 436	99.09 58	85.73 417	96.41 511	90.98 389	98.52 385	99.53 78

MatchFormer		93.37 398	93.14 391	94.07 426	96.06 456	92.91 247	94.24 369	94.92 450	85.51 491	98.29 158	97.79 261	85.70 418	96.13 513	86.23 477	99.51 189	93.18 521

Vis-MVSNet (Re-imp)		95.11 319	94.85 323	95.87 313	99.12 104	89.17 367	97.54 113	94.92 450	96.50 141	96.58 327	97.27 319	83.64 440	99.48 241	88.42 447	99.67 108	98.97 259

PatchmatchNet2					0.00 565	78.83 525	89.63 521	94.76 452	87.65 468
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TR-MVS		92.54 424	92.20 421	93.57 444	96.49 428	86.66 444	93.51 415	94.73 453	89.96 433	94.95 415	93.87 475	90.24 341	98.61 446	81.18 522	94.88 518	95.45 502

SIFT-PCN-Cal		93.02 413	92.95 398	93.23 458	95.63 479	94.57 182	89.68 520	94.71 454	90.40 421	97.02 289	95.84 426	88.33 376	93.66 535	85.26 492	99.65 113	91.45 531

HY-MVS	91.43 15	92.58 423	91.81 430	94.90 381	96.49 428	88.87 381	97.31 125	94.62 455	85.92 487	90.50 510	96.84 358	85.05 425	99.40 285	83.77 510	95.78 509	96.43 483

PVSNet	86.72 19	91.10 455	90.97 450	91.49 499	97.56 372	78.04 529	87.17 532	94.60 456	84.65 504	92.34 493	92.20 502	87.37 395	98.47 461	85.17 496	97.69 441	97.96 407

Patchmatch-test		93.60 391	93.25 388	94.63 397	96.14 451	87.47 426	96.04 231	94.50 457	93.57 309	96.47 337	96.97 348	76.50 485	98.61 446	90.67 407	98.41 398	97.81 419

SIFT-UMatch		93.66 388	93.67 376	93.63 442	96.30 437	96.15 90	90.62 499	94.47 458	92.12 367	97.39 258	96.18 402	87.74 387	93.63 536	88.59 444	99.64 117	91.12 533

Anonymous202405211		96.34 240	95.98 264	97.43 165	98.25 266	93.85 212	96.74 166	94.41 459	97.72 72	98.37 142	98.03 228	87.15 398	99.53 223	94.06 300	99.07 311	98.92 273

tpm cat1		88.01 495	87.33 494	90.05 514	94.48 513	76.28 539	94.47 357	94.35 460	73.84 546	89.26 525	95.61 436	73.64 501	98.30 474	84.13 503	86.20 542	95.57 501

guyue		96.21 248	96.29 245	95.98 303	98.80 166	89.14 372	96.40 193	94.34 461	95.99 183	98.58 115	98.13 207	87.42 394	99.64 178	97.39 90	99.55 166	99.16 205

SP-NN		92.63 422	92.38 416	93.37 447	93.30 530	92.36 264	92.04 463	94.24 462	91.60 387	89.19 526	93.92 474	87.21 397	91.28 544	93.73 321	96.17 496	96.48 480

mvsany_test3		96.21 248	95.93 269	97.05 199	97.40 389	94.33 193	95.76 261	94.20 463	89.10 445	99.36 34	99.60 11	93.97 245	97.85 489	95.40 214	98.63 377	98.99 252

SCA		93.38 397	93.52 381	92.96 471	96.24 439	81.40 512	93.24 425	94.00 464	91.58 390	94.57 426	96.97 348	87.94 381	99.42 273	89.47 430	97.66 446	98.06 397

SIFT-ConvMatch		93.72 384	93.47 382	94.48 409	96.22 443	96.63 63	90.58 501	93.91 465	91.70 378	97.70 233	96.17 403	89.03 364	95.12 519	86.29 476	99.65 113	91.69 528

SIFT-NCM-Cal		93.81 378	93.73 373	94.05 428	96.55 424	96.75 55	91.23 485	93.80 466	91.44 398	95.86 380	96.27 396	90.82 327	93.76 534	88.26 451	99.37 244	91.63 529

SIFT-MNN		93.13 410	92.91 399	93.79 436	96.42 432	96.49 68	91.23 485	93.73 467	92.18 366	95.52 397	96.08 414	84.66 430	93.04 541	87.49 464	98.94 325	91.84 525

testing91		89.67 475	88.55 480	93.04 466	95.90 462	81.80 508	92.71 441	93.71 468	93.71 303	90.18 516	90.15 521	57.11 533	99.22 357	87.17 469	96.32 492	98.12 389

tpmrst		90.31 463	90.61 459	89.41 515	94.06 522	72.37 550	95.06 326	93.69 469	88.01 464	92.32 494	96.86 356	77.45 479	98.82 418	91.04 387	87.01 541	97.04 457

MIMVSNet		93.42 395	92.86 401	95.10 366	98.17 279	88.19 403	98.13 59	93.69 469	92.07 369	95.04 414	98.21 197	80.95 461	99.03 395	81.42 520	98.06 414	98.07 393

DSMNet-mixed		92.19 435	91.83 429	93.25 456	96.18 446	83.68 495	96.27 207	93.68 471	76.97 542	92.54 492	99.18 45	89.20 363	98.55 452	83.88 507	98.60 381	97.51 440

FE-MVS		92.95 414	92.22 420	95.11 364	97.21 402	88.33 400	98.54 26	93.66 472	89.91 434	96.21 356	98.14 205	70.33 514	99.50 232	87.79 454	98.24 406	97.51 440

tpmvs		90.79 460	90.87 452	90.57 509	92.75 536	76.30 538	95.79 259	93.64 473	91.04 408	91.91 497	96.26 397	77.19 483	98.86 415	89.38 432	89.85 537	96.56 477

PatchmatchNet		91.98 442	91.87 428	92.30 490	94.60 512	79.71 521	95.12 316	93.59 474	89.52 438	93.61 460	97.02 342	77.94 475	99.18 364	90.84 395	94.57 523	98.01 404
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ADS-MVSNet		90.95 458	90.26 463	93.04 466	95.51 483	82.37 503	95.05 327	93.41 475	83.46 511	92.69 486	96.84 358	79.15 471	98.70 434	85.66 486	90.52 534	98.04 401

SIFT-CM-Cal		93.31 401	93.10 392	93.95 431	96.19 444	96.32 79	89.81 515	93.40 476	91.16 405	97.19 272	96.07 415	88.24 377	94.58 529	86.11 478	99.69 99	90.94 536

FPMVS		89.92 470	88.63 479	93.82 434	98.37 250	96.94 49	91.58 473	93.34 477	88.00 465	90.32 514	97.10 337	70.87 512	91.13 546	71.91 544	96.16 498	93.39 520

AstraMVS		96.41 236	96.48 233	96.20 286	98.91 146	89.69 354	96.28 205	93.29 478	96.11 169	98.70 102	98.36 162	89.41 358	99.66 169	97.60 80	99.63 120	99.26 180

MDTV_nov1_ep13			91.28 443		94.31 515	73.51 548	94.80 342	93.16 479	86.75 481	93.45 467	97.40 303	76.37 486	98.55 452	88.85 438	96.43 487

MASt3R-SfM		91.42 451	90.88 451	93.06 465	92.40 537	92.08 281	89.76 517	93.15 480	78.62 535	95.98 369	97.33 315	82.42 450	91.17 545	90.23 417	97.98 418	95.92 490

SIFT-NN-PointCN		92.48 426	92.19 422	93.33 452	95.40 489	95.65 116	90.19 507	93.07 481	88.67 454	92.90 478	95.95 421	89.38 359	93.20 539	85.21 493	98.94 325	91.15 532

baseline1		93.14 408	92.64 411	94.62 398	97.34 394	87.20 434	96.67 176	93.02 482	94.71 259	96.51 334	95.83 427	81.64 453	98.60 448	90.00 421	88.06 540	98.07 393

PatchT		93.75 380	93.57 379	94.29 420	95.05 498	87.32 432	96.05 229	92.98 483	97.54 82	94.25 433	98.72 102	75.79 491	99.24 353	95.92 170	95.81 505	96.32 485

FBQ-MVS		89.51 478	87.89 488	94.36 413	96.47 431	87.19 435	94.96 332	92.96 484	91.01 411	90.38 512	88.46 530	57.42 532	98.55 452	83.35 513	96.03 499	97.35 447

EPNet_dtu		91.39 452	90.75 455	93.31 454	90.48 544	82.61 501	94.80 342	92.88 485	93.39 317	81.74 545	94.90 458	81.36 457	99.11 380	88.28 449	98.87 338	98.21 381
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
new_pmnet		92.34 429	91.69 437	94.32 418	96.23 441	89.16 370	92.27 456	92.88 485	84.39 508	95.29 405	96.35 391	85.66 419	96.74 509	84.53 501	97.56 449	97.05 456

dp		88.08 494	88.05 486	88.16 524	92.85 534	68.81 555	94.17 375	92.88 485	85.47 493	91.38 503	96.14 408	68.87 518	98.81 420	86.88 470	83.80 544	96.87 463

EU-MVSNet		94.25 362	94.47 347	93.60 443	98.14 285	82.60 502	97.24 130	92.72 488	85.08 497	98.48 128	98.94 77	82.59 449	98.76 426	97.47 86	99.53 176	99.44 122

PVSNet_0	81.89 21	84.49 505	83.21 509	88.34 521	95.76 474	74.97 544	83.49 542	92.70 489	78.47 537	87.94 534	86.90 541	83.38 444	96.63 510	73.44 542	66.86 551	93.40 519

dmvs_re		92.08 439	91.27 444	94.51 406	97.16 404	92.79 253	95.65 271	92.64 490	94.11 289	92.74 485	90.98 516	83.41 443	94.44 531	80.72 523	94.07 525	96.29 486

MM		96.87 194	96.62 213	97.62 138	97.72 350	93.30 235	96.39 195	92.61 491	97.90 65	96.76 313	98.64 120	90.46 333	99.81 43	99.16 18	99.94 8	99.76 21

SIFT-PointCN		93.04 412	92.72 408	94.01 430	95.80 470	95.33 146	89.76 517	92.60 492	90.24 428	96.32 344	95.87 425	87.45 391	94.70 528	86.65 474	99.77 71	92.01 524

pmmvs3		90.00 467	88.90 477	93.32 453	94.20 520	85.34 465	91.25 484	92.56 493	78.59 536	93.82 449	95.17 450	67.36 520	98.69 436	89.08 436	98.03 416	95.92 490

myMVS_eth3d28		88.32 491	87.73 491	90.11 513	96.42 432	74.96 545	92.21 457	92.37 494	93.56 310	90.14 517	89.61 524	56.13 538	98.05 484	81.84 517	97.26 463	97.33 449

CVMVSNet		92.33 430	92.79 404	90.95 505	97.26 399	75.84 540	95.29 306	92.33 495	81.86 519	96.27 351	98.19 199	81.44 456	98.46 463	94.23 294	98.29 404	98.55 332

nomal-1		90.42 462	88.88 478	95.06 368	96.01 457	88.66 389	93.13 430	92.16 496	91.23 403	90.46 511	91.32 512	61.17 525	98.72 431	87.70 456	96.70 480	97.79 422

SIFT-NN-UMatch		92.28 433	91.93 427	93.34 449	96.13 452	96.04 96	90.05 508	92.08 497	90.41 420	92.88 480	95.29 447	87.36 396	93.63 536	85.33 491	97.87 428	90.34 542

testing99		89.21 481	88.04 487	92.70 480	95.78 472	81.00 516	92.65 442	92.03 498	93.20 329	89.90 521	90.08 523	55.25 542	99.14 372	87.54 461	95.95 500	97.97 406

E-PMN		89.52 477	89.78 466	88.73 519	93.14 531	77.61 532	83.26 543	92.02 499	94.82 253	93.71 455	93.11 480	75.31 492	96.81 505	85.81 483	96.81 474	91.77 527

CostFormer		89.75 473	89.25 469	91.26 504	94.69 510	78.00 530	95.32 302	91.98 500	81.50 522	90.55 509	96.96 350	71.06 511	98.89 409	88.59 444	92.63 530	96.87 463

tpm2		88.47 489	87.69 492	90.79 507	94.98 503	77.34 534	95.09 320	91.83 501	77.51 541	89.40 524	96.41 386	67.83 519	98.73 428	83.58 512	92.60 531	96.29 486

XFeat-MNN		88.85 486	88.16 485	90.91 506	88.38 548	89.73 352	84.46 539	91.81 502	83.72 509	95.56 395	92.95 488	74.60 496	92.68 542	84.01 504	97.99 417	90.32 543

JIA-IIPM		91.79 445	90.69 457	95.11 364	93.80 525	90.98 311	94.16 376	91.78 503	96.38 147	90.30 515	99.30 32	72.02 508	98.90 408	88.28 449	90.17 536	95.45 502

N_pmnet		95.18 315	94.23 357	98.06 101	97.85 313	96.55 66	92.49 445	91.63 504	89.34 439	98.09 189	97.41 302	90.33 336	99.06 388	91.58 377	99.31 270	98.56 329

testing11		88.93 483	87.63 493	92.80 477	95.87 464	81.49 510	92.48 446	91.54 505	91.62 382	88.27 533	90.24 519	55.12 545	99.11 380	87.30 467	96.28 494	97.81 419

UBG		88.29 492	87.17 495	91.63 498	96.08 453	78.21 527	91.61 471	91.50 506	89.67 437	89.71 522	88.97 527	59.01 528	98.91 406	81.28 521	96.72 479	97.77 423

Syy-MVS		92.09 438	91.80 431	92.93 473	95.19 494	82.65 500	92.46 447	91.35 507	90.67 416	91.76 499	87.61 533	85.64 420	98.50 458	94.73 274	96.84 471	97.65 431

myMVS_eth3d		87.16 503	85.61 506	91.82 496	95.19 494	79.32 522	92.46 447	91.35 507	90.67 416	91.76 499	87.61 533	41.96 554	98.50 458	82.66 515	96.84 471	97.65 431

EPNet		93.72 384	92.62 412	97.03 203	87.61 552	92.25 270	96.27 207	91.28 509	96.74 127	87.65 535	97.39 308	85.00 426	99.64 178	92.14 362	99.48 205	99.20 197
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		91.08 456	90.85 453	91.75 497	95.33 490	78.09 528	95.03 329	91.27 510	88.75 451	93.53 464	97.40 303	71.24 509	99.30 332	91.25 384	93.87 526	97.87 414

thres200		91.00 457	90.42 461	92.77 478	97.47 385	83.98 492	94.01 387	91.18 511	95.12 236	95.44 400	91.21 513	73.93 498	99.31 328	77.76 534	97.63 448	95.01 505

EMVS		89.06 482	89.22 471	88.61 520	93.00 533	77.34 534	82.91 544	90.92 512	94.64 262	92.63 490	91.81 506	76.30 487	97.02 502	83.83 508	96.90 469	91.48 530

SIFT-NN-CMatch		92.54 424	92.03 425	94.07 426	96.08 453	96.27 84	89.47 524	90.90 513	90.26 427	92.89 479	94.83 459	90.17 342	94.95 523	84.92 498	98.78 353	90.99 535

MGCNet		95.71 279	95.18 299	97.33 174	94.85 506	92.82 248	95.36 295	90.89 514	95.51 215	95.61 392	97.82 257	88.39 374	99.78 58	98.23 50	99.91 19	99.40 134

tfpn200view9		91.55 448	91.00 448	93.21 460	98.02 294	84.35 487	95.70 264	90.79 515	96.26 153	95.90 376	92.13 503	73.62 502	99.42 273	78.85 530	97.74 436	95.85 494

thres400		91.68 447	91.00 448	93.71 440	98.02 294	84.35 487	95.70 264	90.79 515	96.26 153	95.90 376	92.13 503	73.62 502	99.42 273	78.85 530	97.74 436	97.36 445

SIFT-NN		89.78 472	89.23 470	91.41 501	95.04 499	94.89 167	88.98 527	90.76 517	89.26 443	89.11 528	92.97 487	81.45 455	88.25 547	78.47 533	97.06 465	91.08 534

LFMVS		95.32 308	94.88 320	96.62 236	98.03 292	91.47 298	97.65 100	90.72 518	99.11 14	97.89 219	98.31 172	79.20 470	99.48 241	93.91 311	99.12 303	98.93 270

testing3-2		90.09 465	90.38 462	89.24 516	98.07 290	69.88 553	95.12 316	90.71 519	96.65 129	93.60 462	94.03 472	55.81 540	99.33 318	90.69 406	98.71 367	98.51 339

SIFT-NN-NCMNet		92.32 431	91.79 432	93.89 432	96.32 436	96.91 50	90.32 504	90.69 520	90.36 423	91.72 501	95.43 445	88.98 365	94.27 533	84.23 502	98.06 414	90.49 541

thres100view900		91.76 446	91.26 446	93.26 455	98.21 270	84.50 483	96.39 195	90.39 521	96.87 121	96.33 343	93.08 484	73.44 505	99.42 273	78.85 530	97.74 436	95.85 494

thres600view7		92.03 441	91.43 439	93.82 434	98.19 273	84.61 482	96.27 207	90.39 521	96.81 124	96.37 342	93.11 480	73.44 505	99.49 238	80.32 524	97.95 421	97.36 445

ETVMVS		87.62 498	85.75 505	93.22 459	96.15 450	83.26 496	92.94 433	90.37 523	91.39 399	90.37 513	88.45 531	51.93 550	98.64 443	73.76 539	96.38 490	97.75 424

K. test v3		96.44 232	96.28 246	96.95 209	99.41 46	91.53 295	97.65 100	90.31 524	98.89 26	98.93 71	99.36 26	84.57 431	99.92 5	97.81 68	99.56 159	99.39 141

ET-MVSNet_ETH3D		91.12 453	89.67 467	95.47 345	96.41 434	89.15 371	91.54 474	90.23 525	89.07 446	86.78 539	92.84 492	69.39 516	99.44 265	94.16 296	96.61 484	97.82 417

IB-MVS	85.98 20	88.63 488	86.95 499	93.68 441	95.12 496	84.82 480	90.85 496	90.17 526	87.55 470	88.48 532	91.34 511	58.01 529	99.59 201	87.24 468	93.80 527	96.63 475
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
testing222		87.35 500	85.50 507	92.93 473	95.79 471	82.83 498	92.40 452	90.10 527	92.80 351	88.87 529	89.02 526	48.34 553	98.70 434	75.40 538	96.74 477	97.27 451

mvsany_test1		93.47 394	93.03 395	94.79 388	94.05 523	92.12 277	90.82 497	90.01 528	85.02 500	97.26 265	98.28 184	93.57 257	97.03 501	92.51 356	95.75 511	95.23 504

test-LLR		89.97 469	89.90 465	90.16 510	94.24 518	74.98 542	89.89 511	89.06 529	92.02 371	89.97 519	90.77 517	73.92 499	98.57 449	91.88 367	97.36 458	96.92 460

test-mter		87.92 496	87.17 495	90.16 510	94.24 518	74.98 542	89.89 511	89.06 529	86.44 483	89.97 519	90.77 517	54.96 546	98.57 449	91.88 367	97.36 458	96.92 460

WB-MVSnew		91.50 449	91.29 442	92.14 493	94.85 506	80.32 519	93.29 424	88.77 531	88.57 456	94.03 445	92.21 501	92.56 290	98.28 475	80.21 525	97.08 464	97.81 419

test0.0.03 1		90.11 464	89.21 472	92.83 476	93.89 524	86.87 442	91.74 470	88.74 532	92.02 371	94.71 424	91.14 514	73.92 499	94.48 530	83.75 511	92.94 528	97.16 452

XFeat-NN		84.28 506	83.52 508	86.54 527	85.42 553	86.22 451	78.86 546	88.43 533	79.17 533	90.71 506	89.11 525	69.18 517	85.27 551	76.68 536	94.13 524	88.13 544

testing3		89.72 474	88.26 484	94.10 425	97.66 360	84.30 489	94.80 342	88.25 534	94.66 260	95.07 409	92.51 498	41.15 555	99.43 269	91.81 372	98.44 396	98.55 332

0.4-1-1-0.2		82.53 510	79.25 512	92.37 488	88.10 549	83.96 493	83.72 541	88.15 535	82.14 518	78.97 549	72.49 549	53.22 547	98.84 416	85.99 481	80.50 547	94.30 514

0.3-1-1-0.015		82.33 511	78.89 513	92.66 481	88.57 547	84.69 481	84.76 538	88.02 536	82.48 516	77.55 550	72.96 548	49.60 552	98.87 414	86.05 479	80.02 548	94.43 511

0.4-1-1-0.1		83.64 508	80.50 511	93.08 463	90.32 545	85.42 464	86.48 533	87.71 537	83.60 510	80.38 548	75.45 547	53.19 548	98.91 406	86.46 475	80.88 546	94.93 508

thisisatest0515		90.43 461	89.18 475	94.17 424	97.07 409	85.44 463	89.75 519	87.58 538	88.28 460	93.69 458	91.72 507	65.27 521	99.58 204	90.59 408	98.67 372	97.50 442

thisisatest0530		92.71 419	91.76 434	95.56 339	98.42 245	88.23 402	96.03 233	87.35 539	94.04 293	96.56 330	95.47 442	64.03 523	99.77 69	94.78 270	99.11 304	98.68 318

tttt0517		93.31 401	92.56 413	95.57 334	98.71 187	87.86 416	97.44 117	87.17 540	95.79 199	97.47 253	96.84 358	64.12 522	99.81 43	96.20 152	99.32 267	99.02 247

TESTMET0.1,1		87.20 502	86.57 501	89.07 517	93.62 527	72.84 549	89.89 511	87.01 541	85.46 494	89.12 527	90.20 520	56.00 539	97.72 492	90.91 392	96.92 467	96.64 473

dmvs_testset		87.30 501	86.99 497	88.24 522	96.71 420	77.48 533	94.68 349	86.81 542	92.64 355	89.61 523	87.01 539	85.91 415	93.12 540	61.04 548	88.49 539	94.13 515

baseline2		89.65 476	88.44 482	93.25 456	95.62 480	82.71 499	93.82 397	85.94 543	88.89 450	87.35 537	92.54 497	71.23 510	99.33 318	86.01 480	94.60 522	97.72 428

MVS-HIRNet		88.40 490	90.20 464	82.99 528	97.01 410	60.04 556	93.11 431	85.61 544	84.45 507	88.72 530	99.09 58	84.72 429	98.23 477	82.52 516	96.59 485	90.69 539

lessismore_v0				97.05 199	99.36 54	92.12 277		84.07 545		98.77 94	98.98 71	85.36 422	99.74 95	97.34 93	99.37 244	99.30 166

test1111		94.53 353	94.81 327	93.72 439	99.06 113	81.94 507	98.31 43	83.87 546	96.37 148	98.49 126	99.17 48	81.49 454	99.73 101	96.64 122	99.86 35	99.49 96

UWE-MVS		87.57 499	86.72 500	90.13 512	95.21 493	73.56 547	91.94 465	83.78 547	88.73 453	93.00 476	92.87 491	55.22 543	99.25 349	81.74 518	97.96 420	97.59 437

ECVR-MVS		94.37 360	94.48 346	94.05 428	98.95 134	83.10 497	98.31 43	82.48 548	96.20 159	98.23 171	99.16 49	81.18 458	99.66 169	95.95 167	99.83 55	99.38 143

EPMVS		89.26 480	88.55 480	91.39 502	92.36 538	79.11 524	95.65 271	79.86 549	88.60 455	93.12 474	96.53 379	70.73 513	98.10 482	90.75 400	89.32 538	96.98 458

UWE-MVS-28		83.78 507	82.36 510	88.03 525	90.72 543	71.58 551	93.64 408	77.87 550	87.62 469	85.91 541	92.89 490	59.94 526	95.99 515	56.06 550	96.56 486	96.52 478

GLUNet-SfM		74.13 512	71.69 515	81.46 529	63.16 556	74.17 546	66.80 547	76.03 551	58.10 549	88.60 531	86.99 540	57.56 530	86.25 550	50.03 551	97.91 425	83.95 545

MVE	73.61 22	86.48 504	85.92 503	88.18 523	96.23 441	85.28 469	81.78 545	75.79 552	86.01 485	82.53 544	91.88 505	92.74 283	87.47 549	71.42 545	94.86 519	91.78 526
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MTMP							96.55 180	74.60 553

gg-mvs-nofinetune		88.28 493	86.96 498	92.23 492	92.84 535	84.44 485	98.19 56	74.60 553	99.08 16	87.01 538	99.47 16	56.93 534	98.23 477	78.91 529	95.61 512	94.01 516

DeepMVS_CX				77.17 530	90.94 542	85.28 469		74.08 555	52.51 550	80.87 547	88.03 532	75.25 493	70.63 553	59.23 549	84.94 543	75.62 546

GG-mvs-BLEND				90.60 508	91.00 541	84.21 490	98.23 50	72.63 556		82.76 543	84.11 543	56.14 537	96.79 506	72.20 543	92.09 533	90.78 538

test2506		89.86 471	89.16 476	91.97 495	98.95 134	76.83 537	98.54 26	61.07 557	96.20 159	97.07 286	99.16 49	55.19 544	99.69 144	96.43 138	99.83 55	99.38 143

tmp_tt		57.23 515	62.50 518	41.44 534	34.77 560	49.21 560	83.93 540	60.22 558	15.31 553	71.11 552	79.37 545	70.09 515	44.86 556	64.76 546	82.93 545	30.25 550

VLMVS_CLIP		41.19 518	42.85 521	36.20 535	35.69 559	29.96 562	41.27 550	59.71 559	20.51 551	51.77 555	61.89 551	24.86 559	51.47 555	37.87 554	52.12 553	27.15 552

kuosan		54.81 516	54.94 519	54.42 533	74.43 555	50.03 559	84.98 537	44.27 560	61.80 548	62.49 554	70.43 550	35.16 557	58.04 554	19.30 555	41.61 555	55.19 549

dongtai		63.43 514	63.37 517	63.60 532	83.91 554	53.17 558	85.14 536	43.40 561	77.91 540	80.96 546	79.17 546	36.36 556	77.10 552	37.88 553	45.63 554	60.54 548

MVS_clip		42.92 517	47.56 520	28.98 536	56.50 558	40.01 561	44.33 549	12.68 562	16.97 552	74.98 551	81.47 544	34.48 558	17.21 557	43.66 552	63.00 552	29.72 551

VLMVS		16.27 521	17.60 524	12.26 537	17.44 562	14.02 564	13.33 551	7.39 563	0.97 558	23.14 557	32.55 554	21.01 560	8.58 558	7.93 557	34.66 557	14.18 553

testmvs		12.33 523	15.23 526	3.64 540	5.77 564	2.23 566	88.99 526	3.62 564	2.30 557	5.29 559	13.09 555	4.52 563	1.95 559	5.16 559	8.32 559	6.75 556

MVS_baseline		16.43 520	20.39 523	4.55 538	19.03 561	1.35 567	10.44 552	3.04 565	0.59 559	41.63 556	49.56 552	10.52 561	0.00 561	9.18 556	39.56 556	12.29 554

test123		12.59 522	15.49 525	3.87 539	6.07 563	2.55 565	90.75 498	2.59 566	2.52 556	5.20 560	13.02 556	4.96 562	1.85 560	5.20 558	9.09 558	7.23 555

mmdepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

monomultidepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

test_blank		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uanet_test		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

DCPMVS		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

pcd_1.5k_mvsjas		7.98 524	10.65 527	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	95.82 164	0.00 561	0.00 560	0.00 560	0.00 557

sosnet-low-res		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

sosnet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uncertanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

Regformer		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

n2								0.00 567

nn								0.00 567

ab-mvs-re		7.91 525	10.55 528	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	94.94 455	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

PatchmatchNet1														91.55 378	99.31 270	98.56 329
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.05 389
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						79.32 522								85.41 489

PC_three_1452									87.24 473	98.37 142	97.44 300	97.00 83	96.78 507	92.01 363	99.25 282	99.21 194

eth-test2					0.00 565

eth-test					0.00 565

OPU-MVS				97.64 137	98.01 296	95.27 147	96.79 162				97.35 313	96.97 86	98.51 457	91.21 385	99.25 282	99.14 212

test_0728_THIRD									96.62 130	98.40 139	98.28 184	97.10 71	99.71 127	95.70 181	99.62 123	99.58 51

GSMVS																98.06 397

test_part2					99.03 122	96.07 94				98.08 191

sam_mvs1												77.80 476				98.06 397

sam_mvs												77.38 480

test_post1							94.98 331				10.37 558	76.21 488	99.04 392	89.47 430

test_post											10.87 557	76.83 484	99.07 387

patchmatchnet-post											96.84 358	77.36 481	99.42 273

gm-plane-assit					91.79 539	71.40 552			81.67 520		90.11 522		98.99 398	84.86 499

test9_res														91.29 381	98.89 337	99.00 248

agg_prior2														90.34 416	98.90 333	99.10 230

test_prior4						95.38 134	93.61 411

test_prior2							93.33 423		94.21 283	94.02 446	96.25 399	93.64 256		91.90 366	98.96 322

旧先验2							93.35 422		77.95 539	95.77 387			98.67 440	90.74 403

新几何2							93.43 417

原ACMM2							92.82 435

testdata2													99.46 254	87.84 453

segment_acmp												95.34 190

testdata1							92.77 436		93.78 301

plane_prior7					98.70 189	94.67 174

plane_prior6					98.38 249	94.37 191						91.91 313

plane_prior4											96.77 364

plane_prior3						94.51 184			95.29 229	96.16 360

plane_prior2							96.50 183		96.36 149

plane_prior1					98.49 232

plane_prior						94.29 195	95.42 288		94.31 281						98.93 330

HQP5-MVS						92.47 262

HQP-NCC					97.85 313		94.26 364		93.18 331	92.86 482

ACMP_Plane					97.85 313		94.26 364		93.18 331	92.86 482

BP-MVS														90.51 411

HQP4-MVS										92.87 481			99.23 355			99.06 238

HQP2-MVS												90.33 336

NP-MVS					98.14 285	93.72 217					95.08 451

MDTV_nov1_ep13_2view						57.28 557	94.89 336		80.59 526	94.02 446		78.66 473		85.50 488		97.82 417

ACMMP++_ref															99.52 183

ACMMP++															99.55 166

Test By Simon												94.51 227

High-resolution multi-view benchmark