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.

fmvsm_l_mol_unc0.5_1		99.77 1	99.70 1	99.97 1	99.88 13	99.92 2	99.36 303	99.67 27	99.51 2	99.96 27	99.97 1	99.01 19	99.99 4	99.98 1	99.99 1	99.99 1

fmvsm_s_conf0.1_n_a		99.26 92	99.06 112	99.85 44	99.52 237	99.62 85	99.54 176	99.62 53	98.69 109	99.99 2	99.96 2	94.47 307	99.94 92	99.88 27	99.92 39	99.98 3

UA-Net		99.42 56	99.29 66	99.80 65	99.62 185	99.55 99	99.50 208	99.70 18	98.79 97	99.77 91	99.96 2	97.45 126	99.96 42	98.92 164	99.90 57	99.89 31

fmvsm_s_conf0.1_n		99.29 85	99.10 100	99.86 35	99.70 124	99.65 77	99.53 185	99.62 53	98.74 103	99.99 2	99.95 4	94.53 305	99.94 92	99.89 26	99.96 18	99.97 5

test_fmvs1_n		98.41 242	98.14 255	99.21 232	99.82 54	97.71 329	99.74 49	99.49 203	99.32 31	99.99 2	99.95 4	85.32 476	99.97 30	99.82 30	99.84 103	99.96 8

DeepC-MVS	98.35 2	99.30 83	99.19 88	99.64 103	99.82 54	99.23 151	99.62 110	99.55 101	98.94 80	99.63 156	99.95 4	95.82 227	99.94 92	99.37 82	99.97 10	99.73 130
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.1_n_2		99.37 69	99.22 83	99.81 61	99.77 80	99.75 53	99.46 247	99.60 69	99.47 7	99.98 13	99.94 7	94.98 263	99.95 77	99.97 3	99.79 134	99.73 130

test_cas_vis1_n_1920		99.16 114	99.01 139	99.61 111	99.81 59	98.86 232	99.65 91	99.64 43	99.39 25	99.97 25	99.94 7	93.20 349	99.98 21	99.55 51	99.91 46	99.99 1

test_vis1_n		97.92 305	97.44 347	99.34 203	99.53 231	98.08 304	99.74 49	99.49 203	99.15 39	100.00 1	99.94 7	79.51 502	99.98 21	99.88 27	99.76 142	99.97 5

OurMVSNet-221017-0		97.88 310	97.77 301	98.19 377	98.71 441	96.53 397	99.88 4	99.00 417	97.79 261	98.78 358	99.94 7	91.68 391	99.35 378	97.21 369	96.99 378	98.69 371

fmvsm_s_conf0.5_n_11		99.32 79	99.16 92	99.80 65	99.83 48	99.70 62	99.57 148	99.56 91	99.45 14	99.99 2	99.93 11	94.18 320	99.99 4	99.96 14	99.98 5	99.73 130

fmvsm_s_conf0.5_n_3		99.37 69	99.20 86	99.87 23	99.75 94	99.70 62	99.48 233	99.66 33	99.45 14	99.99 2	99.93 11	94.64 297	99.97 30	99.94 22	99.97 10	99.95 12

fmvsm_s_conf0.5_n_2		99.32 79	99.13 95	99.89 13	99.80 65	99.77 50	99.44 258	99.58 79	99.47 7	99.99 2	99.93 11	94.04 325	99.96 42	99.96 14	99.93 33	99.93 23

test_fmvsmconf0.01_n		99.22 100	99.03 120	99.79 69	98.42 467	99.48 114	99.55 171	99.51 163	99.39 25	99.78 87	99.93 11	94.80 278	99.95 77	99.93 24	99.95 23	99.94 18

test2506		96.81 401	96.65 397	97.29 444	99.74 102	92.21 492	99.60 119	85.06 550	99.13 42	99.77 91	99.93 11	87.82 455	99.85 193	99.38 81	99.38 186	99.80 90

test1111		98.04 285	98.11 259	97.83 415	99.74 102	93.82 475	99.58 140	95.40 526	99.12 47	99.65 148	99.93 11	90.73 413	99.84 203	99.43 72	99.38 186	99.82 74

ECVR-MVS		98.04 285	98.05 268	98.00 393	99.74 102	94.37 470	99.59 130	94.98 527	99.13 42	99.66 138	99.93 11	90.67 414	99.84 203	99.40 75	99.38 186	99.80 90

SixPastTwentyTwo		97.50 369	97.33 365	98.03 388	98.65 449	96.23 410	99.77 36	98.68 470	97.14 337	97.90 436	99.93 11	90.45 415	99.18 415	97.00 384	96.43 388	98.67 384

fmvsm_s_conf0.5_n_10		99.41 60	99.24 78	99.92 2	99.83 48	99.84 21	99.53 185	99.56 91	99.45 14	99.99 2	99.92 19	94.92 269	99.99 4	99.97 3	99.97 10	99.95 12

fmvsm_s_conf0.5_n_9		99.41 60	99.28 69	99.81 61	99.84 39	99.52 108	99.48 233	99.62 53	99.46 10	99.99 2	99.92 19	95.24 256	99.96 42	99.97 3	99.97 10	99.96 8

MVSMamba_PlusPlus		99.46 43	99.41 37	99.64 103	99.68 137	99.50 111	99.75 44	99.50 188	98.27 161	99.87 49	99.92 19	98.09 110	99.94 92	99.65 42	99.95 23	99.47 260

fmvsm_s_conf0.5_n_a		99.56 22	99.47 25	99.85 44	99.83 48	99.64 83	99.52 187	99.65 40	99.10 49	99.98 13	99.92 19	97.35 131	99.96 42	99.94 22	99.92 39	99.95 12

fmvsm_s_conf0.5_n		99.51 30	99.40 38	99.85 44	99.84 39	99.65 77	99.51 197	99.67 27	99.13 42	99.98 13	99.92 19	96.60 176	99.96 42	99.95 17	99.96 18	99.95 12

test_fmvsmconf0.1_n		99.55 24	99.45 31	99.86 35	99.44 271	99.65 77	99.50 208	99.61 62	99.45 14	99.87 49	99.92 19	97.31 132	99.97 30	99.95 17	99.99 1	99.97 5

test_fmvsmconf_n		99.70 4	99.64 5	99.87 23	99.80 65	99.66 73	99.48 233	99.64 43	99.45 14	99.92 31	99.92 19	98.62 78	99.99 4	99.96 14	99.99 1	99.96 8

test_fmvsmvis_n_1920		99.65 9	99.61 9	99.77 75	99.38 290	99.37 126	99.58 140	99.62 53	99.41 24	99.87 49	99.92 19	98.81 50	100.00 1	99.97 3	99.93 33	99.94 18

E5new		99.14 127	99.02 131	99.50 155	99.69 130	98.91 213	99.60 119	99.53 126	98.13 193	99.72 109	99.91 27	96.26 200	99.84 203	99.30 98	99.10 235	99.76 109

E6new		99.15 119	99.03 120	99.50 155	99.66 153	98.90 218	99.60 119	99.53 126	98.13 193	99.72 109	99.91 27	96.31 194	99.84 203	99.30 98	99.10 235	99.76 109

E6		99.15 119	99.03 120	99.50 155	99.66 153	98.90 218	99.60 119	99.53 126	98.13 193	99.72 109	99.91 27	96.31 194	99.84 203	99.30 98	99.10 235	99.76 109

E5		99.14 127	99.02 131	99.50 155	99.69 130	98.91 213	99.60 119	99.53 126	98.13 193	99.72 109	99.91 27	96.26 200	99.84 203	99.30 98	99.10 235	99.76 109

test_fmvsm_n_1920		99.69 7	99.66 4	99.78 72	99.84 39	99.44 119	99.58 140	99.69 22	99.43 20	99.98 13	99.91 27	98.62 78	100.00 1	99.97 3	99.95 23	99.90 28

test_vis1_n_1920		98.63 230	98.40 238	99.31 211	99.86 26	97.94 317	99.67 78	99.62 53	99.43 20	99.99 2	99.91 27	87.29 457	100.00 1	99.92 25	99.92 39	99.98 3

mvsany_test1		99.50 32	99.46 29	99.62 110	99.61 196	99.09 171	98.94 434	99.48 215	99.10 49	99.96 27	99.91 27	98.85 44	99.96 42	99.72 33	99.58 171	99.82 74

test_fmvs1		98.88 188	98.79 191	99.16 237	99.69 130	97.61 333	99.55 171	99.49 203	99.32 31	99.98 13	99.91 27	91.41 400	99.96 42	99.82 30	99.92 39	99.90 28

SD-MVS		99.41 60	99.52 15	99.05 249	99.74 102	99.68 66	99.46 247	99.52 135	99.11 48	99.88 43	99.91 27	99.43 1	97.70 500	98.72 200	99.93 33	99.77 102
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
ACMH	97.28 8	98.10 272	97.99 274	98.44 352	99.41 279	96.96 372	99.60 119	99.56 91	98.09 208	98.15 424	99.91 27	90.87 412	99.70 303	98.88 168	97.45 359	98.67 384
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E4		99.13 131	99.01 139	99.49 162	99.68 137	98.90 218	99.52 187	99.52 135	98.13 193	99.71 119	99.90 37	96.32 192	99.84 203	99.21 117	99.11 226	99.75 115

viewdifsd2359ckpt11		98.78 213	98.74 197	98.89 278	99.67 140	97.04 362	99.50 208	99.58 79	98.26 164	99.56 178	99.90 37	94.36 310	99.87 178	99.49 62	98.32 303	99.77 102

viewmsd2359difaftdt		98.78 213	98.74 197	98.90 274	99.67 140	97.04 362	99.50 208	99.58 79	98.26 164	99.56 178	99.90 37	94.36 310	99.87 178	99.49 62	98.32 303	99.77 102

fmvsm_s_conf0.5_n_8		99.54 25	99.42 33	99.89 13	99.83 48	99.74 56	99.51 197	99.62 53	99.46 10	99.99 2	99.90 37	96.60 176	99.98 21	99.95 17	99.95 23	99.96 8

reproduce_model		99.63 10	99.54 14	99.90 9	99.78 72	99.88 11	99.56 156	99.55 101	99.15 39	99.90 35	99.90 37	99.00 24	99.97 30	99.11 133	99.91 46	99.86 44

patch_mono-2		99.26 92	99.62 8	98.16 379	99.81 59	94.59 466	99.52 187	99.64 43	99.33 30	99.73 104	99.90 37	99.00 24	99.99 4	99.69 35	99.98 5	99.89 31

VDDNet		97.55 363	97.02 387	99.16 237	99.49 254	98.12 302	99.38 293	99.30 358	95.35 435	99.68 127	99.90 37	82.62 492	99.93 110	99.31 95	98.13 320	99.42 274

QAPM		98.67 225	98.30 245	99.80 65	99.20 342	99.67 70	99.77 36	99.72 14	94.74 451	98.73 362	99.90 37	95.78 231	99.98 21	96.96 388	99.88 74	99.76 109

3Dnovator	97.25 9	99.24 97	99.05 115	99.81 61	99.12 364	99.66 73	99.84 12	99.74 13	99.09 56	98.92 331	99.90 37	95.94 220	99.98 21	98.95 158	99.92 39	99.79 94

MED-MVS		99.70 4	99.63 6	99.90 9	99.88 13	99.81 35	99.69 64	99.87 6	99.48 4	99.90 35	99.89 46	99.30 4	99.95 77	98.83 184	99.88 74	99.93 23

TestfortrainingZip a		99.70 4	99.63 6	99.92 2	99.88 13	99.90 3	99.69 64	99.79 11	99.48 4	99.93 30	99.89 46	98.78 54	99.93 110	99.32 93	99.88 74	99.93 23

viewmacassd2359aftdt		99.08 156	98.94 160	99.50 155	99.66 153	98.96 195	99.51 197	99.54 110	98.27 161	99.42 212	99.89 46	95.88 225	99.80 247	99.20 118	99.11 226	99.76 109

fmvsm_l_conf0.5_n_9		99.58 17	99.47 25	99.92 2	99.85 32	99.82 30	99.47 243	99.63 47	99.45 14	99.98 13	99.89 46	97.02 150	99.99 4	99.98 1	99.96 18	99.95 12

LuminaMVS		99.23 98	99.10 100	99.61 111	99.35 298	99.31 138	99.46 247	99.13 397	98.61 115	99.86 53	99.89 46	96.41 190	99.91 137	99.67 38	99.51 177	99.63 198

fmvsm_l_conf0.5_n_3		99.61 11	99.51 19	99.92 2	99.84 39	99.82 30	99.54 176	99.66 33	99.46 10	99.98 13	99.89 46	97.27 135	99.99 4	99.97 3	99.95 23	99.95 12

reproduce-ours		99.61 11	99.52 15	99.90 9	99.76 84	99.88 11	99.52 187	99.54 110	99.13 42	99.89 40	99.89 46	98.96 27	99.96 42	99.04 144	99.90 57	99.85 48

our_new_method		99.61 11	99.52 15	99.90 9	99.76 84	99.88 11	99.52 187	99.54 110	99.13 42	99.89 40	99.89 46	98.96 27	99.96 42	99.04 144	99.90 57	99.85 48

Anonymous20240529		98.09 273	97.68 313	99.34 203	99.66 153	98.44 285	99.40 284	99.43 281	93.67 463	99.22 271	99.89 46	90.23 420	99.93 110	99.26 113	98.33 299	99.66 179

CHOSEN 1792x2688		99.19 102	99.10 100	99.45 177	99.89 8	98.52 275	99.39 288	99.94 1	98.73 104	99.11 294	99.89 46	95.50 242	99.94 92	99.50 58	99.97 10	99.89 31

RPSCF		98.22 258	98.62 218	96.99 451	99.82 54	91.58 494	99.72 55	99.44 270	96.61 383	99.66 138	99.89 46	95.92 221	99.82 234	97.46 349	99.10 235	99.57 224

3Dnovator+	97.12 13	99.18 105	98.97 150	99.82 58	99.17 356	99.68 66	99.81 20	99.51 163	99.20 35	98.72 363	99.89 46	95.68 236	99.97 30	98.86 176	99.86 88	99.81 81

COLMAP_ROB	97.56 6	98.86 194	98.75 195	99.17 236	99.88 13	98.53 271	99.34 315	99.59 74	97.55 292	98.70 370	99.89 46	95.83 226	99.90 150	98.10 278	99.90 57	99.08 316
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
dtuplus		99.03 168	98.92 163	99.36 199	99.60 203	98.62 262	99.35 309	99.51 163	97.99 235	99.38 226	99.88 59	96.04 211	99.79 254	99.37 82	99.17 208	99.68 165

hybridcas		99.13 131	99.00 143	99.51 149	99.70 124	99.04 180	99.65 91	99.52 135	98.20 179	99.75 101	99.88 59	95.78 231	99.78 262	99.41 73	99.16 209	99.71 152

casdiffseed414692147		98.97 181	98.78 192	99.53 137	99.66 153	99.16 159	99.61 117	99.52 135	98.01 233	99.21 274	99.88 59	94.82 275	99.70 303	99.29 104	99.04 247	99.74 120

E2		99.15 119	99.03 120	99.49 162	99.65 165	98.93 210	99.49 225	99.52 135	98.14 190	99.72 109	99.88 59	96.57 180	99.84 203	99.17 125	99.13 219	99.72 140

E3		99.15 119	99.03 120	99.49 162	99.62 185	98.91 213	99.49 225	99.52 135	98.13 193	99.72 109	99.88 59	96.61 175	99.84 203	99.17 125	99.13 219	99.72 140

AstraMVS		99.09 154	99.03 120	99.25 226	99.66 153	98.13 300	99.57 148	98.24 490	98.82 91	99.91 32	99.88 59	95.81 228	99.90 150	99.72 33	99.67 160	99.74 120

fmvsm_s_conf0.5_n_7		99.34 76	99.29 66	99.48 167	99.70 124	98.63 260	99.42 271	99.63 47	99.46 10	99.98 13	99.88 59	95.59 239	99.96 42	99.97 3	99.98 5	99.85 48

SDMVSNet		99.11 147	98.90 169	99.75 78	99.81 59	99.59 91	99.81 20	99.65 40	98.78 100	99.64 153	99.88 59	94.56 300	99.93 110	99.67 38	98.26 307	99.72 140

sd_testset		98.75 218	98.57 226	99.29 219	99.81 59	98.26 293	99.56 156	99.62 53	98.78 100	99.64 153	99.88 59	92.02 382	99.88 171	99.54 52	98.26 307	99.72 140

dcpmvs_2		99.23 98	99.58 10	98.16 379	99.83 48	94.68 462	99.76 39	99.52 135	99.07 59	99.98 13	99.88 59	98.56 82	99.93 110	99.67 38	99.98 5	99.87 42

RRT-MVS		98.91 186	98.75 195	99.39 197	99.46 264	98.61 265	99.76 39	99.50 188	98.06 217	99.81 73	99.88 59	93.91 332	99.94 92	99.11 133	99.27 197	99.61 203

test_djsdf		98.67 225	98.57 226	98.98 257	98.70 442	98.91 213	99.88 4	99.46 250	97.55 292	99.22 271	99.88 59	95.73 234	99.28 388	99.03 146	97.62 342	98.75 354

DP-MVS		99.16 114	98.95 158	99.78 72	99.77 80	99.53 104	99.41 276	99.50 188	97.03 352	99.04 311	99.88 59	97.39 127	99.92 125	98.66 209	99.90 57	99.87 42

TDRefinement		95.42 433	94.57 443	97.97 396	89.83 550	96.11 414	99.48 233	98.75 457	96.74 371	96.68 467	99.88 59	88.65 441	99.71 295	98.37 252	82.74 519	98.09 467

EPP-MVSNet		99.13 131	98.99 145	99.53 137	99.65 165	99.06 177	99.81 20	99.33 338	97.43 310	99.60 168	99.88 59	97.14 140	99.84 203	99.13 130	98.94 254	99.69 159

OpenMVS	96.50 16	98.47 236	98.12 258	99.52 144	99.04 387	99.53 104	99.82 16	99.72 14	94.56 454	98.08 426	99.88 59	94.73 288	99.98 21	97.47 348	99.76 142	99.06 322

onestephybrid01		99.17 110	99.06 112	99.49 162	99.60 203	98.98 187	99.38 293	99.50 188	98.52 125	99.81 73	99.87 75	96.27 197	99.81 239	99.47 67	99.10 235	99.67 172

Casviewmamba		99.16 114	99.02 131	99.59 115	99.66 153	99.21 153	99.68 74	99.52 135	98.31 155	99.60 168	99.87 75	95.96 216	99.85 193	99.40 75	99.16 209	99.72 140

viewcassd2359sk11		99.18 105	99.08 106	99.49 162	99.65 165	98.95 201	99.48 233	99.51 163	98.10 207	99.72 109	99.87 75	97.13 141	99.84 203	99.13 130	99.14 216	99.69 159

Elysia		98.88 188	98.65 210	99.58 119	99.58 209	99.34 130	99.65 91	99.52 135	98.26 164	99.83 67	99.87 75	93.37 343	99.90 150	97.81 307	99.91 46	99.49 251

StellarMVS		98.88 188	98.65 210	99.58 119	99.58 209	99.34 130	99.65 91	99.52 135	98.26 164	99.83 67	99.87 75	93.37 343	99.90 150	97.81 307	99.91 46	99.49 251

guyue		99.16 114	99.04 117	99.52 144	99.69 130	98.92 212	99.59 130	98.81 449	98.73 104	99.90 35	99.87 75	95.34 249	99.88 171	99.66 41	99.81 122	99.74 120

balanced_ft_v1		99.02 170	98.98 148	99.15 241	99.39 287	98.12 302	99.79 32	99.51 163	98.20 179	99.66 138	99.87 75	94.84 274	99.93 110	99.69 35	99.84 103	99.41 277

lessismore_v0				97.79 419	98.69 445	95.44 441		94.75 530		95.71 477	99.87 75	88.69 439	99.32 383	95.89 422	94.93 430	98.62 406

casdiffmvs_mvg		99.15 119	99.02 131	99.55 128	99.66 153	99.09 171	99.64 99	99.56 91	98.26 164	99.45 201	99.87 75	96.03 213	99.81 239	99.54 52	99.15 215	99.73 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		99.12 141	98.97 150	99.56 125	99.78 72	99.10 170	99.68 74	99.66 33	98.49 129	99.86 53	99.87 75	94.77 283	99.84 203	99.19 119	99.41 185	99.74 120
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMH+	97.24 10	97.92 305	97.78 299	98.32 364	99.46 264	96.68 392	99.56 156	99.54 110	98.41 140	97.79 442	99.87 75	90.18 423	99.66 315	98.05 287	97.18 374	98.62 406

fmvsm_s_conf0.5_n_5		99.37 69	99.21 84	99.86 35	99.80 65	99.68 66	99.42 271	99.61 62	99.37 27	99.97 25	99.86 86	94.96 264	99.99 4	99.97 3	99.93 33	99.92 26

fmvsm_s_conf0.5_n_4		99.36 73	99.24 78	99.73 84	99.78 72	99.53 104	99.49 225	99.60 69	99.42 23	99.99 2	99.86 86	95.15 259	99.95 77	99.95 17	99.89 68	99.73 130

ACMMP_NAP		99.47 41	99.34 50	99.88 17	99.87 21	99.86 19	99.47 243	99.48 215	98.05 220	99.76 97	99.86 86	98.82 49	99.93 110	98.82 191	99.91 46	99.84 56

casdiffmvs		99.13 131	98.98 148	99.56 125	99.65 165	99.16 159	99.56 156	99.50 188	98.33 151	99.41 217	99.86 86	95.92 221	99.83 225	99.45 71	99.16 209	99.70 156
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		99.36 73	99.28 69	99.61 111	99.86 26	99.07 176	99.47 243	99.93 2	97.66 280	99.71 119	99.86 86	97.73 121	99.96 42	99.47 67	99.82 119	99.79 94

IS-MVSNet		99.05 165	98.87 177	99.57 123	99.73 109	99.32 134	99.75 44	99.20 387	98.02 232	99.56 178	99.86 86	96.54 181	99.67 312	98.09 279	99.13 219	99.73 130

USDC		97.34 382	97.20 377	97.75 422	99.07 378	95.20 446	98.51 488	99.04 410	97.99 235	98.31 412	99.86 86	89.02 433	99.55 341	95.67 431	97.36 367	98.49 437

SSM_0407		99.13 131	99.03 120	99.43 187	99.62 185	98.88 224	99.51 197	99.50 188	98.14 190	99.37 229	99.85 93	96.85 157	99.83 225	99.19 119	99.25 200	99.60 206

viewmambaseed2359dif		99.01 175	98.90 169	99.32 209	99.58 209	98.51 277	99.33 317	99.54 110	97.85 251	99.44 206	99.85 93	96.01 214	99.79 254	99.41 73	99.13 219	99.67 172

SSM_0404		99.16 114	99.06 112	99.44 183	99.65 165	98.96 195	99.49 225	99.50 188	98.14 190	99.62 160	99.85 93	96.85 157	99.85 193	99.19 119	99.26 199	99.52 237

lecture		99.60 15	99.50 20	99.89 13	99.89 8	99.90 3	99.75 44	99.59 74	99.06 62	99.88 43	99.85 93	98.41 95	99.96 42	99.28 107	99.84 103	99.83 66

sc_t1		95.75 424	95.05 432	97.87 405	98.83 421	94.61 465	99.21 368	99.45 261	87.45 508	97.97 433	99.85 93	81.19 498	99.43 360	98.27 262	93.20 463	99.57 224

APD_test1		95.87 421	96.49 401	94.00 480	99.53 231	84.01 515	99.54 176	99.32 349	95.91 429	97.99 431	99.85 93	85.49 474	99.88 171	91.96 484	98.84 268	98.12 465

TSAR-MVS + MP.		99.58 17	99.50 20	99.81 61	99.91 1	99.66 73	99.63 105	99.39 296	98.91 84	99.78 87	99.85 93	99.36 2	99.94 92	98.84 181	99.88 74	99.82 74
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
tmp_tt		82.80 495	81.52 499	86.66 513	66.61 561	68.44 545	92.79 543	97.92 496	68.96 531	80.04 539	99.85 93	85.77 470	96.15 517	97.86 300	43.89 553	95.39 522

AllTest		98.87 191	98.72 199	99.31 211	99.86 26	98.48 282	99.56 156	99.61 62	97.85 251	99.36 235	99.85 93	95.95 218	99.85 193	96.66 404	99.83 115	99.59 217

TestCases				99.31 211	99.86 26	98.48 282		99.61 62	97.85 251	99.36 235	99.85 93	95.95 218	99.85 193	96.66 404	99.83 115	99.59 217

VDD-MVS		97.73 342	97.35 359	98.88 283	99.47 262	97.12 352	99.34 315	98.85 444	98.19 181	99.67 133	99.85 93	82.98 490	99.92 125	99.49 62	98.32 303	99.60 206

APDe-MVS		99.66 8	99.57 11	99.92 2	99.77 80	99.89 7	99.75 44	99.56 91	99.02 63	99.88 43	99.85 93	99.18 11	99.96 42	99.22 115	99.92 39	99.90 28
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DeepPCF-MVS	98.18 3	98.81 208	99.37 44	97.12 448	99.60 203	91.75 493	98.61 476	99.44 270	99.35 28	99.83 67	99.85 93	98.70 71	99.81 239	99.02 148	99.91 46	99.81 81

ACMM	97.58 5	98.37 248	98.34 241	98.48 341	99.41 279	97.10 353	99.56 156	99.45 261	98.53 124	99.04 311	99.85 93	93.00 352	99.71 295	98.74 197	97.45 359	98.64 397
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		99.27 89	99.12 97	99.74 81	99.18 348	99.75 53	99.56 156	99.57 86	98.45 134	99.49 195	99.85 93	97.77 120	99.94 92	98.33 257	99.84 103	99.52 237

viewmamba		99.20 101	99.12 97	99.44 183	99.61 196	98.87 228	99.42 271	99.52 135	98.42 138	99.84 57	99.84 108	96.85 157	99.78 262	99.46 69	99.11 226	99.67 172

hybridnocas07		99.13 131	99.03 120	99.46 175	99.63 175	98.90 218	99.38 293	99.52 135	98.41 140	99.82 71	99.84 108	96.09 208	99.80 247	99.40 75	99.16 209	99.68 165

hybrid		99.11 147	99.01 139	99.41 190	99.64 170	98.76 248	99.35 309	99.52 135	98.31 155	99.80 79	99.84 108	96.16 204	99.79 254	99.40 75	99.06 244	99.68 165

E3new		99.18 105	99.08 106	99.48 167	99.63 175	98.94 205	99.46 247	99.50 188	98.06 217	99.72 109	99.84 108	97.27 135	99.84 203	99.10 136	99.13 219	99.67 172

BridgeMVS		99.46 43	99.39 40	99.67 92	99.55 223	99.58 96	99.74 49	99.51 163	98.42 138	99.87 49	99.84 108	98.05 113	99.91 137	99.58 48	99.94 31	99.52 237

DPE-MVS		99.46 43	99.32 54	99.91 7	99.78 72	99.88 11	99.36 303	99.51 163	98.73 104	99.88 43	99.84 108	98.72 69	99.96 42	98.16 272	99.87 80	99.88 37
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
XVG-OURS		98.73 221	98.68 204	98.88 283	99.70 124	97.73 325	98.92 436	99.55 101	98.52 125	99.45 201	99.84 108	95.27 252	99.91 137	98.08 283	98.84 268	99.00 328

baseline		99.15 119	99.02 131	99.53 137	99.66 153	99.14 165	99.72 55	99.48 215	98.35 148	99.42 212	99.84 108	96.07 209	99.79 254	99.51 57	99.14 216	99.67 172

ACMMP		99.45 47	99.32 54	99.82 58	99.89 8	99.67 70	99.62 110	99.69 22	98.12 201	99.63 156	99.84 108	98.73 68	99.96 42	98.55 232	99.83 115	99.81 81
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
aaatest				99.87 23	99.88 13	99.81 35	99.69 64	99.87 6	99.34 29	99.90 35	99.83 117		99.95 77	98.83 184	99.89 68	99.83 66

aaEdge-Enhanced		99.56 22	99.46 29	99.86 35	99.80 65	99.81 35	99.37 297	99.70 18	99.18 36	99.83 67	99.83 117	98.74 67	99.93 110	98.83 184	99.89 68	99.83 66

fmvsm_l_conf0.5_n_a		99.71 2	99.67 2	99.85 44	99.86 26	99.61 88	99.56 156	99.63 47	99.48 4	99.98 13	99.83 117	98.75 62	99.99 4	99.97 3	99.96 18	99.94 18

EI-MVSNet-UG-set		99.58 17	99.57 11	99.64 103	99.78 72	99.14 165	99.60 119	99.45 261	99.01 65	99.90 35	99.83 117	98.98 26	99.93 110	99.59 46	99.95 23	99.86 44

EI-MVSNet		98.67 225	98.67 205	98.68 316	99.35 298	97.97 310	99.50 208	99.38 306	96.93 361	99.20 278	99.83 117	97.87 116	99.36 375	98.38 250	97.56 347	98.71 362

CVMVSNet		98.57 232	98.67 205	98.30 366	99.35 298	95.59 432	99.50 208	99.55 101	98.60 117	99.39 224	99.83 117	94.48 306	99.45 351	98.75 195	98.56 286	99.85 48

mvsmamba		99.06 161	98.96 154	99.36 199	99.47 262	98.64 259	99.70 60	99.05 409	97.61 285	99.65 148	99.83 117	96.54 181	99.92 125	99.19 119	99.62 167	99.51 246

LPG-MVS_test		98.22 258	98.13 257	98.49 339	99.33 304	97.05 359	99.58 140	99.55 101	97.46 303	99.24 266	99.83 117	92.58 368	99.72 288	98.09 279	97.51 352	98.68 376

LGP-MVS_train				98.49 339	99.33 304	97.05 359		99.55 101	97.46 303	99.24 266	99.83 117	92.58 368	99.72 288	98.09 279	97.51 352	98.68 376

SteuartSystems-ACMMP		99.54 25	99.42 33	99.87 23	99.82 54	99.81 35	99.59 130	99.51 163	98.62 114	99.79 82	99.83 117	99.28 5	99.97 30	98.48 236	99.90 57	99.84 56
Skip Steuart: Steuart Systems R&D Blog.
XXY-MVS		98.38 246	98.09 263	99.24 229	99.26 327	99.32 134	99.56 156	99.55 101	97.45 306	98.71 364	99.83 117	93.23 346	99.63 330	98.88 168	96.32 391	98.76 352

viewmanbaseed2359cas		99.18 105	99.07 111	99.50 155	99.62 185	99.01 184	99.50 208	99.52 135	98.25 169	99.68 127	99.82 128	96.93 155	99.80 247	99.15 129	99.11 226	99.70 156

fmvsm_l_conf0.5_n		99.71 2	99.67 2	99.85 44	99.84 39	99.63 84	99.56 156	99.63 47	99.47 7	99.98 13	99.82 128	98.75 62	99.99 4	99.97 3	99.97 10	99.94 18

SR-MVS-dyc-post		99.45 47	99.31 60	99.85 44	99.76 84	99.82 30	99.63 105	99.52 135	98.38 143	99.76 97	99.82 128	98.53 85	99.95 77	98.61 217	99.81 122	99.77 102

RE-MVS-def			99.34 50		99.76 84	99.82 30	99.63 105	99.52 135	98.38 143	99.76 97	99.82 128	98.75 62		98.61 217	99.81 122	99.77 102

test0726					99.85 32	99.89 7	99.62 110	99.50 188	99.10 49	99.86 53	99.82 128	98.94 34

SMA-MVS		99.44 51	99.30 62	99.85 44	99.73 109	99.83 24	99.56 156	99.47 237	97.45 306	99.78 87	99.82 128	99.18 11	99.91 137	98.79 192	99.89 68	99.81 81
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
nrg030		98.64 229	98.42 236	99.28 223	99.05 385	99.69 65	99.81 20	99.46 250	98.04 227	99.01 314	99.82 128	96.69 171	99.38 368	99.34 89	94.59 437	98.78 346

FC-MVSNet-test		98.75 218	98.62 218	99.15 241	99.08 375	99.45 118	99.86 11	99.60 69	98.23 174	98.70 370	99.82 128	96.80 165	99.22 406	99.07 140	96.38 389	98.79 344

EI-MVSNet-Vis-set		99.58 17	99.56 13	99.64 103	99.78 72	99.15 164	99.61 117	99.45 261	99.01 65	99.89 40	99.82 128	99.01 19	99.92 125	99.56 50	99.95 23	99.85 48

APD-MVS_3200maxsize		99.48 38	99.35 48	99.85 44	99.76 84	99.83 24	99.63 105	99.54 110	98.36 147	99.79 82	99.82 128	98.86 43	99.95 77	98.62 214	99.81 122	99.78 100

EU-MVSNet		97.98 296	98.03 270	97.81 418	98.72 438	96.65 393	99.66 85	99.66 33	98.09 208	98.35 409	99.82 128	95.25 255	98.01 492	97.41 355	95.30 421	98.78 346

APD-MVS		99.27 89	99.08 106	99.84 56	99.75 94	99.79 43	99.50 208	99.50 188	97.16 336	99.77 91	99.82 128	98.78 54	99.94 92	97.56 337	99.86 88	99.80 90
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TAMVS		99.12 141	99.08 106	99.24 229	99.46 264	98.55 269	99.51 197	99.46 250	98.09 208	99.45 201	99.82 128	98.34 99	99.51 344	98.70 202	98.93 255	99.67 172

DeepC-MVS_fast	98.69 1	99.49 34	99.39 40	99.77 75	99.63 175	99.59 91	99.36 303	99.46 250	99.07 59	99.79 82	99.82 128	98.85 44	99.92 125	98.68 207	99.87 80	99.82 74
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		99.13 131	99.02 131	99.45 177	99.57 215	98.63 260	99.07 399	99.34 330	98.99 70	99.61 165	99.82 128	97.98 115	99.87 178	97.00 384	99.80 127	99.85 48

viewdifsd2359ckpt07		99.11 147	99.00 143	99.43 187	99.63 175	98.73 250	99.45 251	99.54 110	98.33 151	99.62 160	99.81 143	96.17 203	99.87 178	99.27 110	99.14 216	99.69 159

diffmvs_AUTHOR		99.19 102	99.10 100	99.48 167	99.64 170	98.85 233	99.32 320	99.48 215	98.50 128	99.81 73	99.81 143	96.82 163	99.88 171	99.40 75	99.12 224	99.71 152

mamba_0408		99.08 156	98.96 154	99.44 183	99.62 185	98.88 224	99.25 354	99.47 237	98.05 220	99.37 229	99.81 143	96.85 157	99.85 193	98.98 151	99.25 200	99.60 206

SSM_04072		99.06 161	98.96 154	99.35 202	99.62 185	98.88 224	99.25 354	99.47 237	98.05 220	99.37 229	99.81 143	96.85 157	99.58 336	98.98 151	99.25 200	99.60 206

KinetiMVS		99.12 141	98.92 163	99.70 88	99.67 140	99.40 124	99.67 78	99.63 47	98.73 104	99.94 29	99.81 143	94.54 303	99.96 42	98.40 248	99.93 33	99.74 120

DVP-MVS++		99.59 16	99.50 20	99.88 17	99.51 240	99.88 11	99.87 8	99.51 163	98.99 70	99.88 43	99.81 143	99.27 6	99.96 42	98.85 178	99.80 127	99.81 81

test_one_0601					99.81 59	99.88 11		99.49 203	98.97 77	99.65 148	99.81 143	99.09 15

SED-MVS		99.61 11	99.52 15	99.88 17	99.84 39	99.90 3	99.60 119	99.48 215	99.08 57	99.91 32	99.81 143	99.20 8	99.96 42	98.91 165	99.85 95	99.79 94

test_241102_TWO								99.48 215	99.08 57	99.88 43	99.81 143	98.94 34	99.96 42	98.91 165	99.84 103	99.88 37

OPM-MVS		98.19 262	98.10 260	98.45 349	98.88 411	97.07 357	99.28 338	99.38 306	98.57 120	99.22 271	99.81 143	92.12 380	99.66 315	98.08 283	97.54 349	98.61 415
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MTAPA		99.52 29	99.39 40	99.89 13	99.90 4	99.86 19	99.66 85	99.47 237	98.79 97	99.68 127	99.81 143	98.43 92	99.97 30	98.88 168	99.90 57	99.83 66

FIs		98.78 213	98.63 213	99.23 231	99.18 348	99.54 101	99.83 15	99.59 74	98.28 159	98.79 357	99.81 143	96.75 168	99.37 371	99.08 139	96.38 389	98.78 346

mvs_tets		98.40 245	98.23 249	98.91 272	98.67 447	98.51 277	99.66 85	99.53 126	98.19 181	98.65 379	99.81 143	92.75 358	99.44 356	99.31 95	97.48 358	98.77 350

mvs_anonymous		99.03 168	98.99 145	99.16 237	99.38 290	98.52 275	99.51 197	99.38 306	97.79 261	99.38 226	99.81 143	97.30 133	99.45 351	99.35 84	98.99 252	99.51 246

TSAR-MVS + GP.		99.36 73	99.36 46	99.36 199	99.67 140	98.61 265	99.07 399	99.33 338	99.00 68	99.82 71	99.81 143	99.06 17	99.84 203	99.09 138	99.42 184	99.65 186

EPNet		98.86 194	98.71 201	99.30 216	97.20 497	98.18 296	99.62 110	98.91 433	99.28 33	98.63 382	99.81 143	95.96 216	99.99 4	99.24 114	99.72 150	99.73 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ab-mvs		98.86 194	98.63 213	99.54 129	99.64 170	99.19 154	99.44 258	99.54 110	97.77 264	99.30 249	99.81 143	94.20 317	99.93 110	99.17 125	98.82 270	99.49 251

OMC-MVS		99.08 156	99.04 117	99.20 233	99.67 140	98.22 295	99.28 338	99.52 135	98.07 213	99.66 138	99.81 143	97.79 119	99.78 262	97.79 309	99.81 122	99.60 206

viewdifsd2359ckpt13		99.06 161	98.93 162	99.45 177	99.63 175	98.96 195	99.50 208	99.51 163	97.83 255	99.28 253	99.80 161	96.68 173	99.71 295	99.05 143	99.12 224	99.68 165

icg_test_0407_2		98.79 212	98.86 180	98.57 327	99.55 223	96.93 373	99.07 399	99.44 270	98.05 220	99.66 138	99.80 161	97.13 141	99.18 415	98.15 274	98.92 257	99.60 206

IMVS_0407		98.86 194	98.91 167	98.72 309	99.55 223	96.93 373	99.50 208	99.44 270	98.05 220	99.66 138	99.80 161	97.13 141	99.65 320	98.15 274	98.92 257	99.60 206

IMVS_0404		98.53 233	98.52 231	98.55 333	99.55 223	96.93 373	99.20 371	99.44 270	98.05 220	98.96 325	99.80 161	94.66 295	99.13 423	98.15 274	98.92 257	99.60 206

IMVS_0403		98.86 194	98.89 173	98.78 304	99.55 223	96.93 373	99.58 140	99.44 270	98.05 220	99.68 127	99.80 161	96.81 164	99.80 247	98.15 274	98.92 257	99.60 206

MM		99.40 65	99.28 69	99.74 81	99.67 140	99.31 138	99.52 187	98.87 441	99.55 1	99.74 102	99.80 161	96.47 184	99.98 21	99.97 3	99.97 10	99.94 18

test_fmvs2		97.25 387	97.30 369	97.09 449	99.43 272	93.31 484	99.73 53	98.87 441	98.83 90	99.28 253	99.80 161	84.45 482	99.66 315	97.88 297	97.45 359	98.30 454

tt0805		97.97 299	97.77 301	98.57 327	99.59 207	96.61 395	99.45 251	99.08 403	98.21 177	98.88 339	99.80 161	88.66 440	99.70 303	98.58 223	97.72 337	99.39 281

SF-MVS		99.38 68	99.24 78	99.79 69	99.79 70	99.68 66	99.57 148	99.54 110	97.82 260	99.71 119	99.80 161	98.95 32	99.93 110	98.19 268	99.84 103	99.74 120

DVP-MVS		99.57 21	99.47 25	99.88 17	99.85 32	99.89 7	99.57 148	99.37 316	99.10 49	99.81 73	99.80 161	98.94 34	99.96 42	98.93 162	99.86 88	99.81 81
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									98.99 70	99.81 73	99.80 161	99.09 15	99.96 42	98.85 178	99.90 57	99.88 37

jajsoiax		98.43 239	98.28 246	98.88 283	98.60 456	98.43 286	99.82 16	99.53 126	98.19 181	98.63 382	99.80 161	93.22 348	99.44 356	99.22 115	97.50 354	98.77 350

PGM-MVS		99.45 47	99.31 60	99.86 35	99.87 21	99.78 49	99.58 140	99.65 40	97.84 254	99.71 119	99.80 161	99.12 14	99.97 30	98.33 257	99.87 80	99.83 66

TransMVSNet (Re)		97.15 391	96.58 398	98.86 290	99.12 364	98.85 233	99.49 225	98.91 433	95.48 434	97.16 458	99.80 161	93.38 342	99.11 430	94.16 457	91.73 479	98.62 406

K. test v3		97.10 393	96.79 394	98.01 391	98.72 438	96.33 405	99.87 8	97.05 511	97.59 286	96.16 473	99.80 161	88.71 438	99.04 441	96.69 402	96.55 386	98.65 395

DELS-MVS		99.48 38	99.42 33	99.65 97	99.72 113	99.40 124	99.05 406	99.66 33	99.14 41	99.57 176	99.80 161	98.46 90	99.94 92	99.57 49	99.84 103	99.60 206
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
CSCG		99.32 79	99.32 54	99.32 209	99.85 32	98.29 291	99.71 59	99.66 33	98.11 203	99.41 217	99.80 161	98.37 98	99.96 42	98.99 150	99.96 18	99.72 140

mvs5depth		96.66 403	96.22 408	97.97 396	97.00 502	96.28 407	98.66 472	99.03 413	96.61 383	96.93 464	99.79 178	87.20 458	99.47 347	96.65 406	94.13 447	98.16 463

SR-MVS		99.43 54	99.29 66	99.86 35	99.75 94	99.83 24	99.59 130	99.62 53	98.21 177	99.73 104	99.79 178	98.68 72	99.96 42	98.44 243	99.77 139	99.79 94

MP-MVS-pluss		99.37 69	99.20 86	99.88 17	99.90 4	99.87 18	99.30 327	99.52 135	97.18 334	99.60 168	99.79 178	98.79 53	99.95 77	98.83 184	99.91 46	99.83 66
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
pm-mvs1		97.68 352	97.28 372	98.88 283	99.06 381	98.62 262	99.50 208	99.45 261	96.32 404	97.87 438	99.79 178	92.47 372	99.35 378	97.54 339	93.54 457	98.67 384

LFMVS		97.90 308	97.35 359	99.54 129	99.52 237	99.01 184	99.39 288	98.24 490	97.10 344	99.65 148	99.79 178	84.79 480	99.91 137	99.28 107	98.38 296	99.69 159

TinyColmap		97.12 392	96.89 392	97.83 415	99.07 378	95.52 436	98.57 480	98.74 461	97.58 288	97.81 441	99.79 178	88.16 448	99.56 339	95.10 442	97.21 372	98.39 450

ACMP	97.20 11	98.06 279	97.94 281	98.45 349	99.37 293	97.01 366	99.44 258	99.49 203	97.54 296	98.45 400	99.79 178	91.95 384	99.72 288	97.91 295	97.49 357	98.62 406
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
fmvsm_s_conf0.5_n_6		99.54 25	99.44 32	99.85 44	99.51 240	99.67 70	99.50 208	99.64 43	99.43 20	99.98 13	99.78 185	97.26 138	99.95 77	99.95 17	99.93 33	99.92 26

GeoE		98.85 203	98.62 218	99.53 137	99.61 196	99.08 174	99.80 25	99.51 163	97.10 344	99.31 245	99.78 185	95.23 257	99.77 267	98.21 266	99.03 248	99.75 115

9.14			99.10 100		99.72 113		99.40 284	99.51 163	97.53 297	99.64 153	99.78 185	98.84 46	99.91 137	97.63 328	99.82 119

MGCNet		99.15 119	98.96 154	99.73 84	98.92 405	99.37 126	99.37 297	96.92 513	99.51 2	99.66 138	99.78 185	96.69 171	99.97 30	99.84 29	99.97 10	99.84 56

pmmvs6		96.53 407	96.09 412	97.82 417	98.69 445	95.47 437	99.37 297	99.47 237	93.46 468	97.41 448	99.78 185	87.06 462	99.33 381	96.92 393	92.70 473	98.65 395

MSLP-MVS++		99.46 43	99.47 25	99.44 183	99.60 203	99.16 159	99.41 276	99.71 16	98.98 73	99.45 201	99.78 185	99.19 10	99.54 342	99.28 107	99.84 103	99.63 198

VNet		99.11 147	98.90 169	99.73 84	99.52 237	99.56 97	99.41 276	99.39 296	99.01 65	99.74 102	99.78 185	95.56 240	99.92 125	99.52 56	98.18 316	99.72 140

114514_t		98.93 184	98.67 205	99.72 87	99.85 32	99.53 104	99.62 110	99.59 74	92.65 480	99.71 119	99.78 185	98.06 112	99.90 150	98.84 181	99.91 46	99.74 120

Vis-MVSNet (Re-imp)		98.87 191	98.72 199	99.31 211	99.71 119	98.88 224	99.80 25	99.44 270	97.91 243	99.36 235	99.78 185	95.49 243	99.43 360	97.91 295	99.11 226	99.62 201

UniMVSNet_ETH3D		97.32 384	96.81 393	98.87 287	99.40 284	97.46 337	99.51 197	99.53 126	95.86 430	98.54 392	99.77 194	82.44 493	99.66 315	98.68 207	97.52 351	99.50 250

anonymousdsp		98.44 238	98.28 246	98.94 264	98.50 463	98.96 195	99.77 36	99.50 188	97.07 346	98.87 342	99.77 194	94.76 284	99.28 388	98.66 209	97.60 343	98.57 428

CDS-MVSNet		99.09 154	99.03 120	99.25 226	99.42 274	98.73 250	99.45 251	99.46 250	98.11 203	99.46 199	99.77 194	98.01 114	99.37 371	98.70 202	98.92 257	99.66 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MSDG		98.98 179	98.80 188	99.53 137	99.76 84	99.19 154	98.75 462	99.55 101	97.25 327	99.47 197	99.77 194	97.82 118	99.87 178	96.93 391	99.90 57	99.54 231

NormalMVS		99.27 89	99.19 88	99.52 144	99.89 8	98.83 238	99.65 91	99.52 135	99.10 49	99.84 57	99.76 198	95.80 229	99.99 4	99.30 98	99.84 103	99.74 120

SymmetryMVS		99.15 119	99.02 131	99.52 144	99.72 113	98.83 238	99.65 91	99.34 330	99.10 49	99.84 57	99.76 198	95.80 229	99.99 4	99.30 98	98.72 276	99.73 130

CHOSEN 280x420		99.12 141	99.13 95	99.08 245	99.66 153	97.89 318	98.43 494	99.71 16	98.88 85	99.62 160	99.76 198	96.63 174	99.70 303	99.46 69	99.99 1	99.66 179

PS-MVSNAJss		98.92 185	98.92 163	98.90 274	98.78 427	98.53 271	99.78 34	99.54 110	98.07 213	99.00 318	99.76 198	99.01 19	99.37 371	99.13 130	97.23 371	98.81 343

MVS_Test		99.10 153	98.97 150	99.48 167	99.49 254	99.14 165	99.67 78	99.34 330	97.31 322	99.58 173	99.76 198	97.65 123	99.82 234	98.87 171	99.07 243	99.46 265

TestfortrainingZip				99.69 90	99.58 209	99.62 85	99.69 64	99.38 306	98.98 73	99.84 57	99.75 203	98.84 46	99.78 262		99.21 204	99.66 179

CANet_DTU		98.97 181	98.87 177	99.25 226	99.33 304	98.42 288	99.08 398	99.30 358	99.16 38	99.43 209	99.75 203	95.27 252	99.97 30	98.56 229	99.95 23	99.36 286

mPP-MVS		99.44 51	99.30 62	99.86 35	99.88 13	99.79 43	99.69 64	99.48 215	98.12 201	99.50 192	99.75 203	98.78 54	99.97 30	98.57 226	99.89 68	99.83 66

HPM-MVS_fast		99.51 30	99.40 38	99.85 44	99.91 1	99.79 43	99.76 39	99.56 91	97.72 271	99.76 97	99.75 203	99.13 13	99.92 125	99.07 140	99.92 39	99.85 48

HyFIR lowres test		99.11 147	98.92 163	99.65 97	99.90 4	99.37 126	99.02 414	99.91 3	97.67 279	99.59 172	99.75 203	95.90 223	99.73 284	99.53 54	99.02 250	99.86 44

ITE_SJBPF				98.08 386	99.29 317	96.37 403		98.92 428	98.34 149	98.83 350	99.75 203	91.09 409	99.62 331	95.82 423	97.40 365	98.25 458

test_241102_ONE					99.84 39	99.90 3		99.48 215	99.07 59	99.91 32	99.74 209	99.20 8	99.76 271

Anonymous202405211		98.30 254	97.98 275	99.26 225	99.57 215	98.16 297	99.41 276	98.55 480	96.03 427	99.19 281	99.74 209	91.87 385	99.92 125	99.16 128	98.29 306	99.70 156

tttt0517		98.42 240	98.14 255	99.28 223	99.66 153	98.38 289	99.74 49	96.85 514	97.68 277	99.79 82	99.74 209	91.39 401	99.89 165	98.83 184	99.56 173	99.57 224

XVS		99.53 28	99.42 33	99.87 23	99.85 32	99.83 24	99.69 64	99.68 24	98.98 73	99.37 229	99.74 209	98.81 50	99.94 92	98.79 192	99.86 88	99.84 56

MP-MVS		99.33 78	99.15 93	99.87 23	99.88 13	99.82 30	99.66 85	99.46 250	98.09 208	99.48 196	99.74 209	98.29 101	99.96 42	97.93 294	99.87 80	99.82 74
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVS_111021_LR		99.41 60	99.33 52	99.65 97	99.77 80	99.51 110	98.94 434	99.85 8	98.82 91	99.65 148	99.74 209	98.51 87	99.80 247	98.83 184	99.89 68	99.64 193

VPNet		97.84 319	97.44 347	99.01 253	99.21 340	98.94 205	99.48 233	99.57 86	98.38 143	99.28 253	99.73 215	88.89 435	99.39 366	99.19 119	93.27 461	98.71 362

MVSTER		98.49 234	98.32 243	99.00 255	99.35 298	99.02 182	99.54 176	99.38 306	97.41 314	99.20 278	99.73 215	93.86 334	99.36 375	98.87 171	97.56 347	98.62 406

MVS_111021_HR		99.41 60	99.32 54	99.66 93	99.72 113	99.47 116	98.95 432	99.85 8	98.82 91	99.54 185	99.73 215	98.51 87	99.74 278	98.91 165	99.88 74	99.77 102

PHI-MVS		99.30 83	99.17 91	99.70 88	99.56 219	99.52 108	99.58 140	99.80 10	97.12 340	99.62 160	99.73 215	98.58 80	99.90 150	98.61 217	99.91 46	99.68 165

tt0320-xc		95.31 437	94.59 441	97.45 437	98.92 405	94.73 459	99.20 371	99.31 353	86.74 510	97.23 454	99.72 219	81.14 499	98.95 465	97.08 380	91.98 478	98.67 384

tt0320		95.71 426	95.07 431	97.62 429	99.05 385	95.02 452	99.25 354	99.52 135	86.81 509	97.97 433	99.72 219	83.58 487	99.15 418	96.38 414	93.35 458	98.68 376

IterMVS-SCA-FT		97.82 325	97.75 306	98.06 387	99.57 215	96.36 404	99.02 414	99.49 203	97.18 334	98.71 364	99.72 219	92.72 361	99.14 420	97.44 353	95.86 406	98.67 384

diffmvs		99.14 127	99.02 131	99.51 149	99.61 196	98.96 195	99.28 338	99.49 203	98.46 132	99.72 109	99.71 222	96.50 183	99.88 171	99.31 95	99.11 226	99.67 172
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XVG-OURS-SEG-HR		98.69 223	98.62 218	98.89 278	99.71 119	97.74 324	99.12 389	99.54 110	98.44 137	99.42 212	99.71 222	94.20 317	99.92 125	98.54 233	98.90 263	99.00 328

EPNet_dtu		98.03 287	97.96 277	98.23 375	98.27 470	95.54 435	99.23 362	98.75 457	99.02 63	97.82 440	99.71 222	96.11 207	99.48 345	93.04 474	99.65 163	99.69 159
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		99.42 56	99.30 62	99.78 72	99.62 185	99.71 60	99.26 352	99.52 135	98.82 91	99.39 224	99.71 222	98.96 27	99.85 193	98.59 222	99.80 127	99.77 102

VortexMVS		98.67 225	98.66 208	98.68 316	99.62 185	97.96 312	99.59 130	99.41 286	98.13 193	99.31 245	99.70 226	95.48 244	99.27 391	99.40 75	97.32 368	98.79 344

FE-MVS		98.48 235	98.17 251	99.40 192	99.54 230	98.96 195	99.68 74	98.81 449	95.54 433	99.62 160	99.70 226	93.82 335	99.93 110	97.35 359	99.46 181	99.32 292

PC_three_1452									98.18 184	99.84 57	99.70 226	99.31 3	98.52 482	98.30 261	99.80 127	99.81 81

OPU-MVS				99.64 103	99.56 219	99.72 58	99.60 119				99.70 226	99.27 6	99.42 363	98.24 265	99.80 127	99.79 94

CS-MVS		99.50 32	99.48 23	99.54 129	99.76 84	99.42 121	99.90 1	99.55 101	98.56 121	99.78 87	99.70 226	98.65 76	99.79 254	99.65 42	99.78 136	99.41 277

tfpnnormal		97.84 319	97.47 339	98.98 257	99.20 342	99.22 152	99.64 99	99.61 62	96.32 404	98.27 416	99.70 226	93.35 345	99.44 356	95.69 429	95.40 419	98.27 456

v7n		97.87 312	97.52 330	98.92 268	98.76 434	98.58 267	99.84 12	99.46 250	96.20 413	98.91 333	99.70 226	94.89 272	99.44 356	96.03 419	93.89 453	98.75 354

testdata				99.54 129	99.75 94	98.95 201		99.51 163	97.07 346	99.43 209	99.70 226	98.87 42	99.94 92	97.76 314	99.64 164	99.72 140

IterMVS		97.83 322	97.77 301	98.02 390	99.58 209	96.27 408	99.02 414	99.48 215	97.22 331	98.71 364	99.70 226	92.75 358	99.13 423	97.46 349	96.00 400	98.67 384
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PCF-MVS	97.08 14	97.66 356	97.06 386	99.47 173	99.61 196	99.09 171	98.04 512	99.25 376	91.24 494	98.51 394	99.70 226	94.55 302	99.91 137	92.76 479	99.85 95	99.42 274
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LTVRE_ROB	97.16 12	98.02 289	97.90 284	98.40 357	99.23 335	96.80 386	99.70 60	99.60 69	97.12 340	98.18 422	99.70 226	91.73 390	99.72 288	98.39 249	97.45 359	98.68 376
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
viewdifsd2359ckpt09		99.01 175	98.87 177	99.40 192	99.62 185	98.79 244	99.44 258	99.51 163	97.76 266	99.35 238	99.69 237	96.42 189	99.75 275	98.97 156	99.11 226	99.66 179

BP-MVS1		99.12 141	98.94 160	99.65 97	99.51 240	99.30 141	99.67 78	98.92 428	98.48 130	99.84 57	99.69 237	94.96 264	99.92 125	99.62 45	99.79 134	99.71 152

SPE-MVS-test		99.49 34	99.48 23	99.54 129	99.78 72	99.30 141	99.89 2	99.58 79	98.56 121	99.73 104	99.69 237	98.55 83	99.82 234	99.69 35	99.85 95	99.48 254

HFP-MVS		99.49 34	99.37 44	99.86 35	99.87 21	99.80 40	99.66 85	99.67 27	98.15 186	99.68 127	99.69 237	99.06 17	99.96 42	98.69 205	99.87 80	99.84 56

旧先验1					99.74 102	99.59 91		99.54 110			99.69 237	98.47 89			99.68 158	99.73 130

ACMMPR		99.49 34	99.36 46	99.86 35	99.87 21	99.79 43	99.66 85	99.67 27	98.15 186	99.67 133	99.69 237	98.95 32	99.96 42	98.69 205	99.87 80	99.84 56

CPTT-MVS		99.11 147	98.90 169	99.74 81	99.80 65	99.46 117	99.59 130	99.49 203	97.03 352	99.63 156	99.69 237	97.27 135	99.96 42	97.82 305	99.84 103	99.81 81

EC-MVSNet		99.44 51	99.39 40	99.58 119	99.56 219	99.49 112	99.88 4	99.58 79	98.38 143	99.73 104	99.69 237	98.20 105	99.70 303	99.64 44	99.82 119	99.54 231

dtuonly		98.37 248	98.26 248	98.69 314	99.07 378	96.81 385	98.51 488	98.75 457	97.77 264	99.57 176	99.68 245	96.12 206	99.71 295	95.76 426	99.11 226	99.57 224

GST-MVS		99.40 65	99.24 78	99.85 44	99.86 26	99.79 43	99.60 119	99.67 27	97.97 238	99.63 156	99.68 245	98.52 86	99.95 77	98.38 250	99.86 88	99.81 81

Anonymous20231211		97.88 310	97.54 328	98.90 274	99.71 119	98.53 271	99.48 233	99.57 86	94.16 457	98.81 353	99.68 245	93.23 346	99.42 363	98.84 181	94.42 441	98.76 352

region2R		99.48 38	99.35 48	99.87 23	99.88 13	99.80 40	99.65 91	99.66 33	98.13 193	99.66 138	99.68 245	98.96 27	99.96 42	98.62 214	99.87 80	99.84 56

PS-CasMVS		97.93 302	97.59 324	98.95 262	98.99 395	99.06 177	99.68 74	99.52 135	97.13 338	98.31 412	99.68 245	92.44 376	99.05 440	98.51 234	94.08 450	98.75 354

HY-MVS	97.30 7	98.85 203	98.64 212	99.47 173	99.42 274	99.08 174	99.62 110	99.36 318	97.39 316	99.28 253	99.68 245	96.44 187	99.92 125	98.37 252	98.22 310	99.40 280

DP-MVS Recon		99.12 141	98.95 158	99.65 97	99.74 102	99.70 62	99.27 343	99.57 86	96.40 402	99.42 212	99.68 245	98.75 62	99.80 247	97.98 291	99.72 150	99.44 270

ADS-MVSNet2		98.02 289	98.07 267	97.87 405	99.33 304	95.19 447	99.23 362	99.08 403	96.24 410	99.10 297	99.67 252	94.11 322	98.93 467	96.81 396	99.05 245	99.48 254

ADS-MVSNet		98.20 261	98.08 264	98.56 331	99.33 304	96.48 399	99.23 362	99.15 394	96.24 410	99.10 297	99.67 252	94.11 322	99.71 295	96.81 396	99.05 245	99.48 254

DTE-MVSNet		97.51 368	97.19 378	98.46 347	98.63 451	98.13 300	99.84 12	99.48 215	96.68 375	97.97 433	99.67 252	92.92 354	98.56 481	96.88 395	92.60 475	98.70 367

Baseline_NR-MVSNet		97.76 334	97.45 342	98.68 316	99.09 372	98.29 291	99.41 276	98.85 444	95.65 432	98.63 382	99.67 252	94.82 275	99.10 433	98.07 286	92.89 470	98.64 397

CMPMVS	69.68 23	94.13 456	94.90 434	91.84 492	97.24 496	80.01 530	98.52 486	99.48 215	89.01 503	91.99 506	99.67 252	85.67 471	99.13 423	95.44 435	97.03 377	96.39 517
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GDP-MVS		99.08 156	98.89 173	99.64 103	99.53 231	99.34 130	99.64 99	99.48 215	98.32 153	99.77 91	99.66 257	95.14 260	99.93 110	98.97 156	99.50 179	99.64 193

原ACMM1				99.65 97	99.73 109	99.33 133		99.47 237	97.46 303	99.12 292	99.66 257	98.67 74	99.91 137	97.70 324	99.69 155	99.71 152

thisisatest0530		98.35 250	98.03 270	99.31 211	99.63 175	98.56 268	99.54 176	96.75 516	97.53 297	99.73 104	99.65 259	91.25 405	99.89 165	98.62 214	99.56 173	99.48 254

test222					99.75 94	99.49 112	98.91 439	99.49 203	96.42 400	99.34 242	99.65 259	98.28 102			99.69 155	99.72 140

MVSFormer		99.17 110	99.12 97	99.29 219	99.51 240	98.94 205	99.88 4	99.46 250	97.55 292	99.80 79	99.65 259	97.39 127	99.28 388	99.03 146	99.85 95	99.65 186

jason		99.13 131	99.03 120	99.45 177	99.46 264	98.87 228	99.12 389	99.26 373	98.03 229	99.79 82	99.65 259	97.02 150	99.85 193	99.02 148	99.90 57	99.65 186
jason: jason.
BH-RMVSNet		98.41 242	98.08 264	99.40 192	99.41 279	98.83 238	99.30 327	98.77 456	97.70 275	98.94 329	99.65 259	92.91 356	99.74 278	96.52 408	99.55 175	99.64 193

sss		99.17 110	99.05 115	99.53 137	99.62 185	98.97 191	99.36 303	99.62 53	97.83 255	99.67 133	99.65 259	97.37 130	99.95 77	99.19 119	99.19 207	99.68 165

h-mvs33		97.70 348	97.28 372	98.97 259	99.70 124	97.27 344	99.36 303	99.45 261	98.94 80	99.66 138	99.64 265	94.93 267	99.99 4	99.48 65	84.36 509	99.65 186

ZNCC-MVS		99.47 41	99.33 52	99.87 23	99.87 21	99.81 35	99.64 99	99.67 27	98.08 212	99.55 184	99.64 265	98.91 39	99.96 42	98.72 200	99.90 57	99.82 74

新几何1				99.75 78	99.75 94	99.59 91		99.54 110	96.76 370	99.29 252	99.64 265	98.43 92	99.94 92	96.92 393	99.66 161	99.72 140

PEN-MVS		97.76 334	97.44 347	98.72 309	98.77 432	98.54 270	99.78 34	99.51 163	97.06 348	98.29 415	99.64 265	92.63 367	98.89 471	98.09 279	93.16 464	98.72 360

CP-MVSNet		98.09 273	97.78 299	99.01 253	98.97 400	99.24 150	99.67 78	99.46 250	97.25 327	98.48 397	99.64 265	93.79 336	99.06 439	98.63 213	94.10 449	98.74 358

LF4IMVS		97.52 366	97.46 341	97.70 426	98.98 398	95.55 433	99.29 332	98.82 447	98.07 213	98.66 373	99.64 265	89.97 424	99.61 333	97.01 383	96.68 381	97.94 482

HPM-MVS		99.42 56	99.28 69	99.83 57	99.90 4	99.72 58	99.81 20	99.54 110	97.59 286	99.68 127	99.63 271	98.91 39	99.94 92	98.58 223	99.91 46	99.84 56
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
NCCC		99.34 76	99.19 88	99.79 69	99.61 196	99.65 77	99.30 327	99.48 215	98.86 86	99.21 274	99.63 271	98.72 69	99.90 150	98.25 264	99.63 166	99.80 90

CP-MVS		99.45 47	99.32 54	99.85 44	99.83 48	99.75 53	99.69 64	99.52 135	98.07 213	99.53 187	99.63 271	98.93 38	99.97 30	98.74 197	99.91 46	99.83 66

AdaColmap		99.01 175	98.80 188	99.66 93	99.56 219	99.54 101	99.18 376	99.70 18	98.18 184	99.35 238	99.63 271	96.32 192	99.90 150	97.48 346	99.77 139	99.55 229

TAPA-MVS	97.07 15	97.74 340	97.34 362	98.94 264	99.70 124	97.53 334	99.25 354	99.51 163	91.90 489	99.30 249	99.63 271	98.78 54	99.64 324	88.09 505	99.87 80	99.65 186
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ppachtmachnet_test		97.49 374	97.45 342	97.61 432	98.62 452	95.24 445	98.80 454	99.46 250	96.11 422	98.22 419	99.62 276	96.45 186	98.97 462	93.77 461	95.97 404	98.61 415

MCST-MVS		99.43 54	99.30 62	99.82 58	99.79 70	99.74 56	99.29 332	99.40 293	98.79 97	99.52 189	99.62 276	98.91 39	99.90 150	98.64 211	99.75 144	99.82 74

WTY-MVS		99.06 161	98.88 176	99.61 111	99.62 185	99.16 159	99.37 297	99.56 91	98.04 227	99.53 187	99.62 276	96.84 162	99.94 92	98.85 178	98.49 291	99.72 140

MDTV_nov1_ep13			98.32 243		99.11 366	94.44 468	99.27 343	98.74 461	97.51 300	99.40 222	99.62 276	94.78 280	99.76 271	97.59 331	98.81 272

CANet		99.25 96	99.14 94	99.59 115	99.41 279	99.16 159	99.35 309	99.57 86	98.82 91	99.51 191	99.61 280	96.46 185	99.95 77	99.59 46	99.98 5	99.65 186

HQP_MVS		98.27 257	98.22 250	98.44 352	99.29 317	96.97 370	99.39 288	99.47 237	98.97 77	99.11 294	99.61 280	92.71 363	99.69 309	97.78 310	97.63 340	98.67 384

plane_prior4											99.61 280

baseline1		98.31 252	97.95 279	99.38 198	99.50 252	98.74 249	99.59 130	98.93 425	98.41 140	99.14 289	99.60 283	94.59 298	99.79 254	98.48 236	93.29 460	99.61 203

TranMVSNet+NR-MVSNet		97.93 302	97.66 315	98.76 306	98.78 427	98.62 262	99.65 91	99.49 203	97.76 266	98.49 396	99.60 283	94.23 316	98.97 462	98.00 290	92.90 469	98.70 367

FA-MVS(test-final)		98.75 218	98.53 230	99.41 190	99.55 223	99.05 179	99.80 25	99.01 416	96.59 388	99.58 173	99.59 285	95.39 246	99.90 150	97.78 310	99.49 180	99.28 296

tpmrst		98.33 251	98.48 233	97.90 403	99.16 358	94.78 458	99.31 325	99.11 399	97.27 325	99.45 201	99.59 285	95.33 250	99.84 203	98.48 236	98.61 280	99.09 315

IterMVS-LS		98.46 237	98.42 236	98.58 326	99.59 207	98.00 308	99.37 297	99.43 281	96.94 360	99.07 303	99.59 285	97.87 116	99.03 443	98.32 259	95.62 413	98.71 362
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		99.19 102	99.04 117	99.64 103	99.78 72	99.27 146	99.42 271	99.54 110	97.29 324	99.41 217	99.59 285	98.42 94	99.93 110	98.19 268	99.69 155	99.73 130

PRO-TEST		99.17 110	99.08 106	99.45 177	99.37 293	99.14 165	99.62 110	99.50 188	98.59 119	99.69 126	99.58 289	96.72 170	99.76 271	99.06 142	99.58 171	99.44 270

ttmdpeth		97.80 329	97.63 320	98.29 367	98.77 432	97.38 340	99.64 99	99.36 318	98.78 100	96.30 471	99.58 289	92.34 379	99.39 366	98.36 254	95.58 414	98.10 466

pmmvs4		98.13 269	97.90 284	98.81 299	98.61 454	98.87 228	98.99 422	99.21 386	96.44 398	99.06 308	99.58 289	95.90 223	99.11 430	97.18 375	96.11 397	98.46 443

1112_ss		98.98 179	98.77 193	99.59 115	99.68 137	99.02 182	99.25 354	99.48 215	97.23 330	99.13 290	99.58 289	96.93 155	99.90 150	98.87 171	98.78 273	99.84 56

ab-mvs-re		8.30 526	11.06 529	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	99.58 289	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

PatchmatchNet		98.31 252	98.36 239	98.19 377	99.16 358	95.32 444	99.27 343	98.92 428	97.37 317	99.37 229	99.58 289	94.90 271	99.70 303	97.43 354	99.21 204	99.54 231
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		98.19 262	98.16 252	98.27 372	99.30 313	95.55 433	99.07 399	98.97 421	97.57 289	99.43 209	99.57 295	92.72 361	99.74 278	97.58 332	99.20 206	99.52 237

Patchmatch-test		97.93 302	97.65 316	98.77 305	99.18 348	97.07 357	99.03 411	99.14 396	96.16 417	98.74 361	99.57 295	94.56 300	99.72 288	93.36 469	99.11 226	99.52 237

PVSNet	96.02 17	98.85 203	98.84 185	98.89 278	99.73 109	97.28 343	98.32 500	99.60 69	97.86 248	99.50 192	99.57 295	96.75 168	99.86 185	98.56 229	99.70 154	99.54 231

cdsmvs_eth3d_5k		24.64 525	32.85 528	0.00 543	0.00 567	0.00 570	0.00 555	99.51 163	0.00 562	0.00 563	99.56 298	96.58 178	0.00 564	0.00 562	0.00 562	0.00 559

1314		98.68 224	98.54 229	99.11 244	98.89 409	98.65 257	99.27 343	99.49 203	96.89 362	97.99 431	99.56 298	97.72 122	99.83 225	97.74 317	99.27 197	98.84 342

lupinMVS		99.13 131	99.01 139	99.46 175	99.51 240	98.94 205	99.05 406	99.16 393	97.86 248	99.80 79	99.56 298	97.39 127	99.86 185	98.94 159	99.85 95	99.58 221

miper_lstm_enhance		98.00 294	97.91 283	98.28 371	99.34 303	97.43 338	98.88 441	99.36 318	96.48 395	98.80 355	99.55 301	95.98 215	98.91 468	97.27 365	95.50 418	98.51 436

DPM-MVS		98.95 183	98.71 201	99.66 93	99.63 175	99.55 99	98.64 474	99.10 400	97.93 241	99.42 212	99.55 301	98.67 74	99.80 247	95.80 425	99.68 158	99.61 203

CDPH-MVS		99.13 131	98.91 167	99.80 65	99.75 94	99.71 60	99.15 382	99.41 286	96.60 386	99.60 168	99.55 301	98.83 48	99.90 150	97.48 346	99.83 115	99.78 100

dp		97.75 338	97.80 295	97.59 433	99.10 369	93.71 478	99.32 320	98.88 439	96.48 395	99.08 302	99.55 301	92.67 366	99.82 234	96.52 408	98.58 283	99.24 302

CLD-MVS		98.16 266	98.10 260	98.33 362	99.29 317	96.82 384	98.75 462	99.44 270	97.83 255	99.13 290	99.55 301	92.92 354	99.67 312	98.32 259	97.69 338	98.48 438
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ArgMatch-SfM		96.18 415	95.78 420	97.38 441	99.08 375	94.64 464	99.20 371	99.33 338	98.01 233	98.54 392	99.54 306	83.13 489	99.43 360	93.86 460	91.29 481	98.08 468

ZD-MVS					99.71 119	99.79 43		99.61 62	96.84 365	99.56 178	99.54 306	98.58 80	99.96 42	96.93 391	99.75 144

cl____		98.01 292	97.84 292	98.55 333	99.25 331	97.97 310	98.71 467	99.34 330	96.47 397	98.59 389	99.54 306	95.65 237	99.21 411	97.21 369	95.77 407	98.46 443

DIV-MVS_self_test		98.01 292	97.85 291	98.48 341	99.24 333	97.95 315	98.71 467	99.35 325	96.50 391	98.60 388	99.54 306	95.72 235	99.03 443	97.21 369	95.77 407	98.46 443

MVS		97.28 385	96.55 399	99.48 167	98.78 427	98.95 201	99.27 343	99.39 296	83.53 517	98.08 426	99.54 306	96.97 153	99.87 178	94.23 455	99.16 209	99.63 198

ArgMatch-Sym		96.59 405	96.31 405	97.42 438	98.89 409	94.84 457	99.16 378	99.39 296	98.11 203	98.35 409	99.53 311	84.38 483	99.40 365	94.16 457	94.85 434	98.03 473

SSC-MVS3.2		97.34 382	97.15 379	97.93 400	99.02 389	95.76 427	99.48 233	99.58 79	97.62 284	99.09 300	99.53 311	87.95 451	99.27 391	96.42 411	95.66 412	98.75 354

pmmvs5		97.52 366	97.30 369	98.16 379	98.57 459	96.73 387	99.27 343	98.90 435	96.14 420	98.37 405	99.53 311	91.54 397	99.14 420	97.51 343	95.87 405	98.63 404

HPM-MVS++		99.39 67	99.23 82	99.87 23	99.75 94	99.84 21	99.43 264	99.51 163	98.68 111	99.27 259	99.53 311	98.64 77	99.96 42	98.44 243	99.80 127	99.79 94

PatchMatch-RL		98.84 206	98.62 218	99.52 144	99.71 119	99.28 144	99.06 403	99.77 12	97.74 270	99.50 192	99.53 311	95.41 245	99.84 203	97.17 376	99.64 164	99.44 270

MonoMVSNet		98.38 246	98.47 234	98.12 384	98.59 458	96.19 412	99.72 55	98.79 454	97.89 245	99.44 206	99.52 316	96.13 205	98.90 470	98.64 211	97.54 349	99.28 296

eth_miper_zixun_eth		98.05 284	97.96 277	98.33 362	99.26 327	97.38 340	98.56 484	99.31 353	96.65 378	98.88 339	99.52 316	96.58 178	99.12 429	97.39 356	95.53 417	98.47 440

test_prior2							98.96 429		98.34 149	99.01 314	99.52 316	98.68 72		97.96 292	99.74 147

test_0402		96.64 404	96.24 407	97.85 409	98.85 418	96.43 402	99.44 258	99.26 373	93.52 466	96.98 462	99.52 316	88.52 444	99.20 413	92.58 482	97.50 354	97.93 483

test_yl		98.86 194	98.63 213	99.54 129	99.49 254	99.18 156	99.50 208	99.07 406	98.22 175	99.61 165	99.51 320	95.37 247	99.84 203	98.60 220	98.33 299	99.59 217

DCV-MVSNet		98.86 194	98.63 213	99.54 129	99.49 254	99.18 156	99.50 208	99.07 406	98.22 175	99.61 165	99.51 320	95.37 247	99.84 203	98.60 220	98.33 299	99.59 217

v148		97.79 331	97.55 325	98.50 338	98.74 435	97.72 326	99.54 176	99.33 338	96.26 409	98.90 335	99.51 320	94.68 292	99.14 420	97.83 304	93.15 465	98.63 404

testing915		98.83 207	98.59 224	99.56 125	99.67 140	98.93 210	99.80 25	99.39 296	98.30 157	99.46 199	99.50 323	93.05 350	99.89 165	99.29 104	98.88 264	99.85 48

DU-MVS		98.08 277	97.79 296	98.96 260	98.87 414	98.98 187	99.41 276	99.45 261	97.87 247	98.71 364	99.50 323	94.82 275	99.22 406	98.57 226	92.87 471	98.68 376

NR-MVSNet		97.97 299	97.61 322	99.02 252	98.87 414	99.26 147	99.47 243	99.42 283	97.63 282	97.08 460	99.50 323	95.07 262	99.13 423	97.86 300	93.59 456	98.68 376

XVG-ACMP-BASELINE		97.83 322	97.71 310	98.20 376	99.11 366	96.33 405	99.41 276	99.52 135	98.06 217	99.05 310	99.50 323	89.64 429	99.73 284	97.73 318	97.38 366	98.53 432

dtuonlycased		97.04 395	97.33 365	96.16 467	99.08 375	90.59 499	98.79 456	99.38 306	97.19 333	96.91 465	99.49 327	90.22 422	98.75 476	97.04 382	97.89 329	99.14 307

RoMa-SfM		94.36 454	93.86 455	95.88 471	98.61 454	90.62 498	98.85 445	99.04 410	91.63 491	94.14 490	99.49 327	77.16 503	99.09 435	92.66 480	93.13 466	97.91 485

reproduce_monomvs		97.89 309	97.87 289	97.96 398	99.51 240	95.45 439	99.60 119	99.25 376	99.17 37	98.85 349	99.49 327	89.29 432	99.64 324	99.35 84	96.31 392	98.78 346

MSP-MVS		99.42 56	99.27 73	99.88 17	99.89 8	99.80 40	99.67 78	99.50 188	98.70 108	99.77 91	99.49 327	98.21 104	99.95 77	98.46 241	99.77 139	99.88 37
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
TEST9					99.67 140	99.65 77	99.05 406	99.41 286	96.22 412	98.95 327	99.49 327	98.77 58	99.91 137

train_agg		99.02 170	98.77 193	99.77 75	99.67 140	99.65 77	99.05 406	99.41 286	96.28 406	98.95 327	99.49 327	98.76 59	99.91 137	97.63 328	99.72 150	99.75 115

PVSNet_Blended		99.08 156	98.97 150	99.42 189	99.76 84	98.79 244	98.78 457	99.91 3	96.74 371	99.67 133	99.49 327	97.53 124	99.88 171	98.98 151	99.85 95	99.60 206

CNLPA		99.14 127	98.99 145	99.59 115	99.58 209	99.41 123	99.16 378	99.44 270	98.45 134	99.19 281	99.49 327	98.08 111	99.89 165	97.73 318	99.75 144	99.48 254

test_8					99.67 140	99.61 88	99.03 411	99.41 286	96.28 406	98.93 330	99.48 335	98.76 59	99.91 137

EPMVS		97.82 325	97.65 316	98.35 361	98.88 411	95.98 415	99.49 225	94.71 532	97.57 289	99.26 264	99.48 335	92.46 375	99.71 295	97.87 299	99.08 242	99.35 287

PLC	97.94 4	99.02 170	98.85 183	99.53 137	99.66 153	99.01 184	99.24 359	99.52 135	96.85 364	99.27 259	99.48 335	98.25 103	99.91 137	97.76 314	99.62 167	99.65 186
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
xiu_mvs_v1_base_debu		99.29 85	99.27 73	99.34 203	99.63 175	98.97 191	99.12 389	99.51 163	98.86 86	99.84 57	99.47 338	98.18 106	99.99 4	99.50 58	99.31 194	99.08 316

xiu_mvs_v1_base		99.29 85	99.27 73	99.34 203	99.63 175	98.97 191	99.12 389	99.51 163	98.86 86	99.84 57	99.47 338	98.18 106	99.99 4	99.50 58	99.31 194	99.08 316

xiu_mvs_v1_base_debi		99.29 85	99.27 73	99.34 203	99.63 175	98.97 191	99.12 389	99.51 163	98.86 86	99.84 57	99.47 338	98.18 106	99.99 4	99.50 58	99.31 194	99.08 316

v1921920		97.80 329	97.45 342	98.84 294	98.80 423	98.53 271	99.52 187	99.34 330	96.15 419	99.24 266	99.47 338	93.98 328	99.29 387	95.40 437	95.13 425	98.69 371

MVStest1		96.08 419	95.48 424	97.89 404	98.93 403	96.70 388	99.56 156	99.35 325	92.69 479	91.81 507	99.46 342	89.90 425	98.96 464	95.00 445	92.61 474	98.00 478

UniMVSNet_NR-MVSNet		98.22 258	97.97 276	98.96 260	98.92 405	98.98 187	99.48 233	99.53 126	97.76 266	98.71 364	99.46 342	96.43 188	99.22 406	98.57 226	92.87 471	98.69 371

testgi		97.65 357	97.50 334	98.13 383	99.36 297	96.45 401	99.42 271	99.48 215	97.76 266	97.87 438	99.45 344	91.09 409	98.81 473	94.53 450	98.52 289	99.13 310

EIA-MVS		99.18 105	99.09 105	99.45 177	99.49 254	99.18 156	99.67 78	99.53 126	97.66 280	99.40 222	99.44 345	98.10 109	99.81 239	98.94 159	99.62 167	99.35 287

tpm2		97.44 377	97.34 362	97.74 424	99.15 362	94.36 471	99.45 251	98.94 424	93.45 469	98.90 335	99.44 345	91.35 402	99.59 335	97.31 360	98.07 322	99.29 295

thisisatest0515		98.14 268	97.79 296	99.19 234	99.50 252	98.50 279	98.61 476	96.82 515	96.95 358	99.54 185	99.43 347	91.66 394	99.86 185	98.08 283	99.51 177	99.22 304

WR-MVS		98.06 279	97.73 308	99.06 247	98.86 417	99.25 149	99.19 374	99.35 325	97.30 323	98.66 373	99.43 347	93.94 329	99.21 411	98.58 223	94.28 444	98.71 362

hse-mvs2		97.50 369	97.14 380	98.59 322	99.49 254	97.05 359	99.28 338	99.22 382	98.94 80	99.66 138	99.42 349	94.93 267	99.65 320	99.48 65	83.80 513	99.08 316

v8		97.95 301	97.63 320	98.93 266	98.95 402	98.81 243	99.80 25	99.41 286	96.03 427	99.10 297	99.42 349	94.92 269	99.30 386	96.94 390	94.08 450	98.66 393

tpmvs		97.98 296	98.02 272	97.84 412	99.04 387	94.73 459	99.31 325	99.20 387	96.10 426	98.76 360	99.42 349	94.94 266	99.81 239	96.97 387	98.45 292	98.97 334

UGNet		98.87 191	98.69 203	99.40 192	99.22 339	98.72 252	99.44 258	99.68 24	99.24 34	99.18 285	99.42 349	92.74 360	99.96 42	99.34 89	99.94 31	99.53 236
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
RoMa-HiRes		92.56 467	92.07 470	94.02 479	97.77 487	87.59 507	98.87 443	98.46 483	89.82 498	92.47 502	99.41 353	71.58 514	97.29 505	90.47 493	89.79 496	97.17 504

WBMVS		97.74 340	97.50 334	98.46 347	99.24 333	97.43 338	99.21 368	99.42 283	97.45 306	98.96 325	99.41 353	88.83 436	99.23 399	98.94 159	96.02 398	98.71 362

AUN-MVS		96.88 399	96.31 405	98.59 322	99.48 261	97.04 362	99.27 343	99.22 382	97.44 309	98.51 394	99.41 353	91.97 383	99.66 315	97.71 321	83.83 512	99.07 321

Effi-MVS+		98.81 208	98.59 224	99.48 167	99.46 264	99.12 169	98.08 511	99.50 188	97.50 301	99.38 226	99.41 353	96.37 191	99.81 239	99.11 133	98.54 288	99.51 246

v10		97.85 315	97.52 330	98.86 290	98.99 395	98.67 255	99.75 44	99.41 286	95.70 431	98.98 321	99.41 353	94.75 285	99.23 399	96.01 421	94.63 436	98.67 384

v144192		97.92 305	97.60 323	98.87 287	98.83 421	98.65 257	99.55 171	99.34 330	96.20 413	99.32 244	99.40 358	94.36 310	99.26 394	96.37 415	95.03 427	98.70 367

NP-MVS					99.23 335	96.92 377					99.40 358

HQP-MVS		98.02 289	97.90 284	98.37 360	99.19 345	96.83 382	98.98 425	99.39 296	98.24 171	98.66 373	99.40 358	92.47 372	99.64 324	97.19 373	97.58 345	98.64 397

MAR-MVS		98.86 194	98.63 213	99.54 129	99.37 293	99.66 73	99.45 251	99.54 110	96.61 383	99.01 314	99.40 358	97.09 145	99.86 185	97.68 326	99.53 176	99.10 311
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
SD_0403		97.55 363	97.53 329	97.62 429	99.61 196	93.64 481	99.72 55	99.44 270	98.03 229	98.62 385	99.39 362	96.06 210	99.57 337	87.88 507	99.01 251	99.66 179

dongtai		93.26 461	92.93 465	94.25 478	99.39 287	85.68 511	97.68 519	93.27 536	92.87 477	96.85 466	99.39 362	82.33 494	97.48 503	76.78 530	97.80 334	99.58 221

API-MVS		99.04 166	99.03 120	99.06 247	99.40 284	99.31 138	99.55 171	99.56 91	98.54 123	99.33 243	99.39 362	98.76 59	99.78 262	96.98 386	99.78 136	98.07 469

CR-MVSNet		98.17 265	97.93 282	98.87 287	99.18 348	98.49 280	99.22 366	99.33 338	96.96 356	99.56 178	99.38 365	94.33 313	99.00 452	94.83 448	98.58 283	99.14 307

Patchmtry		97.75 338	97.40 354	98.81 299	99.10 369	98.87 228	99.11 395	99.33 338	94.83 449	98.81 353	99.38 365	94.33 313	99.02 447	96.10 417	95.57 415	98.53 432

BH-untuned		98.42 240	98.36 239	98.59 322	99.49 254	96.70 388	99.27 343	99.13 397	97.24 329	98.80 355	99.38 365	95.75 233	99.74 278	97.07 381	99.16 209	99.33 291

V42		98.06 279	97.79 296	98.86 290	98.98 398	98.84 235	99.69 64	99.34 330	96.53 390	99.30 249	99.37 368	94.67 293	99.32 383	97.57 336	94.66 435	98.42 446

VPA-MVSNet		98.29 255	97.95 279	99.30 216	99.16 358	99.54 101	99.50 208	99.58 79	98.27 161	99.35 238	99.37 368	92.53 370	99.65 320	99.35 84	94.46 438	98.72 360

PVSNet_BlendedMVS		98.86 194	98.80 188	99.03 251	99.76 84	98.79 244	99.28 338	99.91 3	97.42 313	99.67 133	99.37 368	97.53 124	99.88 171	98.98 151	97.29 369	98.42 446

D2MVS		98.41 242	98.50 232	98.15 382	99.26 327	96.62 394	99.40 284	99.61 62	97.71 272	98.98 321	99.36 371	96.04 211	99.67 312	98.70 202	97.41 364	98.15 464

MVP-Stereo		97.81 327	97.75 306	97.99 394	97.53 489	96.60 396	98.96 429	98.85 444	97.22 331	97.23 454	99.36 371	95.28 251	99.46 349	95.51 433	99.78 136	97.92 484
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1240		97.69 349	97.32 367	98.79 302	98.85 418	98.43 286	99.48 233	99.36 318	96.11 422	99.27 259	99.36 371	93.76 338	99.24 398	94.46 451	95.23 422	98.70 367

dmvs_re		98.08 277	98.16 252	97.85 409	99.55 223	94.67 463	99.70 60	98.92 428	98.15 186	99.06 308	99.35 374	93.67 340	99.25 396	97.77 313	97.25 370	99.64 193

v1144		97.98 296	97.69 312	98.85 293	98.87 414	98.66 256	99.54 176	99.35 325	96.27 408	99.23 270	99.35 374	94.67 293	99.23 399	96.73 399	95.16 424	98.68 376

v2v482		98.06 279	97.77 301	98.92 268	98.90 408	98.82 241	99.57 148	99.36 318	96.65 378	99.19 281	99.35 374	94.20 317	99.25 396	97.72 320	94.97 428	98.69 371

CostFormer		97.72 344	97.73 308	97.71 425	99.15 362	94.02 474	99.54 176	99.02 414	94.67 452	99.04 311	99.35 374	92.35 378	99.77 267	98.50 235	97.94 326	99.34 290

testing3-2		97.84 319	97.70 311	98.24 374	99.53 231	95.37 443	99.55 171	98.67 473	98.46 132	99.27 259	99.34 378	86.58 464	99.83 225	99.32 93	98.63 279	99.52 237

our_test_3		97.65 357	97.68 313	97.55 434	98.62 452	94.97 454	98.84 449	99.30 358	96.83 367	98.19 421	99.34 378	97.01 152	99.02 447	95.00 445	96.01 399	98.64 397

c3_l		98.12 271	98.04 269	98.38 359	99.30 313	97.69 330	98.81 453	99.33 338	96.67 376	98.83 350	99.34 378	97.11 144	98.99 454	97.58 332	95.34 420	98.48 438

Fast-Effi-MVS+-dtu		98.77 217	98.83 187	98.60 321	99.41 279	96.99 368	99.52 187	99.49 203	98.11 203	99.24 266	99.34 378	96.96 154	99.79 254	97.95 293	99.45 182	99.02 327

Fast-Effi-MVS+		98.70 222	98.43 235	99.51 149	99.51 240	99.28 144	99.52 187	99.47 237	96.11 422	99.01 314	99.34 378	96.20 202	99.84 203	97.88 297	98.82 270	99.39 281

v1192		97.81 327	97.44 347	98.91 272	98.88 411	98.68 254	99.51 197	99.34 330	96.18 415	99.20 278	99.34 378	94.03 326	99.36 375	95.32 439	95.18 423	98.69 371

tpm		97.67 355	97.55 325	98.03 388	99.02 389	95.01 453	99.43 264	98.54 481	96.44 398	99.12 292	99.34 378	91.83 387	99.60 334	97.75 316	96.46 387	99.48 254

PAPM		97.59 361	97.09 384	99.07 246	99.06 381	98.26 293	98.30 501	99.10 400	94.88 447	98.08 426	99.34 378	96.27 197	99.64 324	89.87 496	98.92 257	99.31 294

GBi-Net		97.68 352	97.48 336	98.29 367	99.51 240	97.26 346	99.43 264	99.48 215	96.49 392	99.07 303	99.32 386	90.26 417	98.98 455	97.10 377	96.65 382	98.62 406

test1		97.68 352	97.48 336	98.29 367	99.51 240	97.26 346	99.43 264	99.48 215	96.49 392	99.07 303	99.32 386	90.26 417	98.98 455	97.10 377	96.65 382	98.62 406

FMVSNet1		96.84 400	96.36 404	98.29 367	99.32 311	97.26 346	99.43 264	99.48 215	95.11 440	98.55 391	99.32 386	83.95 485	98.98 455	95.81 424	96.26 393	98.62 406

MS-PatchMatch		97.24 389	97.32 367	96.99 451	98.45 466	93.51 483	98.82 452	99.32 349	97.41 314	98.13 425	99.30 389	88.99 434	99.56 339	95.68 430	99.80 127	97.90 486

GA-MVS		97.85 315	97.47 339	99.00 255	99.38 290	97.99 309	98.57 480	99.15 394	97.04 351	98.90 335	99.30 389	89.83 426	99.38 368	96.70 401	98.33 299	99.62 201

miper_ehance_all_eth		98.18 264	98.10 260	98.41 355	99.23 335	97.72 326	98.72 466	99.31 353	96.60 386	98.88 339	99.29 391	97.29 134	99.13 423	97.60 330	95.99 401	98.38 451

FMVSNet2		97.72 344	97.36 357	98.80 301	99.51 240	98.84 235	99.45 251	99.42 283	96.49 392	98.86 348	99.29 391	90.26 417	98.98 455	96.44 410	96.56 385	98.58 426

TESTMET0.1,1		97.55 363	97.27 375	98.40 357	98.93 403	96.53 397	98.67 469	97.61 504	96.96 356	98.64 380	99.28 393	88.63 443	99.45 351	97.30 363	99.38 186	99.21 305

FMVSNet3		98.03 287	97.76 305	98.84 294	99.39 287	98.98 187	99.40 284	99.38 306	96.67 376	99.07 303	99.28 393	92.93 353	98.98 455	97.10 377	96.65 382	98.56 429

PAPM_NR		99.04 166	98.84 185	99.66 93	99.74 102	99.44 119	99.39 288	99.38 306	97.70 275	99.28 253	99.28 393	98.34 99	99.85 193	96.96 388	99.45 182	99.69 159

EGC-MVSNET		82.80 495	77.86 502	97.62 429	97.91 478	96.12 413	99.33 317	99.28 364	8.40 560	25.05 562	99.27 396	84.11 484	99.33 381	89.20 499	98.22 310	97.42 500

ETV-MVS		99.26 92	99.21 84	99.40 192	99.46 264	99.30 141	99.56 156	99.52 135	98.52 125	99.44 206	99.27 396	98.41 95	99.86 185	99.10 136	99.59 170	99.04 324

xiu_mvs_v2_base		99.26 92	99.25 77	99.29 219	99.53 231	98.91 213	99.02 414	99.45 261	98.80 96	99.71 119	99.26 398	98.94 34	99.98 21	99.34 89	99.23 203	98.98 332

test20.03		96.12 417	95.96 415	96.63 460	97.44 490	95.45 439	99.51 197	99.38 306	96.55 389	96.16 473	99.25 399	93.76 338	96.17 516	87.35 511	94.22 445	98.27 456

PS-MVSNAJ		99.32 79	99.32 54	99.30 216	99.57 215	98.94 205	98.97 428	99.46 250	98.92 83	99.71 119	99.24 400	99.01 19	99.98 21	99.35 84	99.66 161	98.97 334

Test_1112_low_res		98.89 187	98.66 208	99.57 123	99.69 130	98.95 201	99.03 411	99.47 237	96.98 354	99.15 288	99.23 401	96.77 167	99.89 165	98.83 184	98.78 273	99.86 44

cl22		97.85 315	97.64 319	98.48 341	99.09 372	97.87 319	98.60 479	99.33 338	97.11 343	98.87 342	99.22 402	92.38 377	99.17 417	98.21 266	95.99 401	98.42 446

EG-PatchMatch MVS		95.97 420	95.69 421	96.81 458	97.78 484	92.79 487	99.16 378	98.93 425	96.16 417	94.08 492	99.22 402	82.72 491	99.47 347	95.67 431	97.50 354	98.17 462

TR-MVS		97.76 334	97.41 353	98.82 296	99.06 381	97.87 319	98.87 443	98.56 477	96.63 382	98.68 372	99.22 402	92.49 371	99.65 320	95.40 437	97.79 335	98.95 338

ET-MVSNet_ETH3D		96.49 408	95.64 423	99.05 249	99.53 231	98.82 241	98.84 449	97.51 507	97.63 282	84.77 524	99.21 405	92.09 381	98.91 468	98.98 151	92.21 477	99.41 277

WR-MVS_H		98.13 269	97.87 289	98.90 274	99.02 389	98.84 235	99.70 60	99.59 74	97.27 325	98.40 403	99.19 406	95.53 241	99.23 399	98.34 256	93.78 455	98.61 415

miper_enhance_ethall		98.16 266	98.08 264	98.41 355	98.96 401	97.72 326	98.45 493	99.32 349	96.95 358	98.97 323	99.17 407	97.06 148	99.22 406	97.86 300	95.99 401	98.29 455

baseline2		97.87 312	97.55 325	98.82 296	99.18 348	98.02 307	99.41 276	96.58 520	96.97 355	96.51 468	99.17 407	93.43 341	99.57 337	97.71 321	99.03 248	98.86 340

MIMVSNet1		95.51 429	95.04 433	96.92 456	97.38 492	95.60 431	99.52 187	99.50 188	93.65 464	96.97 463	99.17 407	85.28 478	96.56 513	88.36 504	95.55 416	98.60 418

gm-plane-assit					98.54 461	92.96 486			94.65 453		99.15 410		99.64 324	97.56 337

MIMVSNet		97.73 342	97.45 342	98.57 327	99.45 270	97.50 336	99.02 414	98.98 420	96.11 422	99.41 217	99.14 411	90.28 416	98.74 477	95.74 427	98.93 255	99.47 260

MASt3R-SfM		94.79 447	95.11 430	93.81 483	97.96 477	85.14 513	98.52 486	98.99 418	95.33 436	97.53 446	99.13 412	79.99 501	99.48 345	93.66 464	94.90 432	96.80 510

LCM-MVSNet-Re		97.83 322	98.15 254	96.87 457	99.30 313	92.25 491	99.59 130	98.26 488	97.43 310	96.20 472	99.13 412	96.27 197	98.73 478	98.17 271	98.99 252	99.64 193

UniMVSNet (Re)		98.29 255	98.00 273	99.13 243	99.00 392	99.36 129	99.49 225	99.51 163	97.95 239	98.97 323	99.13 412	96.30 196	99.38 368	98.36 254	93.34 459	98.66 393

N_pmnet		94.95 445	95.83 418	92.31 491	98.47 464	79.33 533	99.12 389	92.81 540	93.87 459	97.68 443	99.13 412	93.87 333	99.01 450	91.38 489	96.19 395	98.59 424

PAPR		98.63 230	98.34 241	99.51 149	99.40 284	99.03 181	98.80 454	99.36 318	96.33 403	99.00 318	99.12 416	98.46 90	99.84 203	95.23 441	99.37 193	99.66 179

tpm cat1		97.39 379	97.36 357	97.50 436	99.17 356	93.73 477	99.43 264	99.31 353	91.27 493	98.71 364	99.08 417	94.31 315	99.77 267	96.41 413	98.50 290	99.00 328

FMVSNet5		96.43 410	96.19 409	97.15 445	99.11 366	95.89 422	99.32 320	99.52 135	94.47 456	98.34 411	99.07 418	87.54 456	97.07 507	92.61 481	95.72 410	98.47 440

PMMVS		98.80 211	98.62 218	99.34 203	99.27 322	98.70 253	98.76 461	99.31 353	97.34 319	99.21 274	99.07 418	97.20 139	99.82 234	98.56 229	98.87 265	99.52 237

DKM		93.17 463	92.50 467	95.21 475	98.53 462	90.26 501	98.74 465	98.90 435	93.00 475	92.61 501	99.06 420	70.06 518	97.74 499	91.92 485	89.65 498	97.62 493

Anonymous20231206		96.22 412	96.03 413	96.79 459	97.31 495	94.14 473	99.63 105	99.08 403	96.17 416	97.04 461	99.06 420	93.94 329	97.76 498	86.96 514	95.06 426	98.47 440

usedtu_dtu_shiyan1		98.09 273	97.82 293	98.89 278	98.70 442	98.90 218	98.57 480	99.47 237	96.78 368	98.87 342	99.05 422	94.75 285	99.23 399	97.45 351	96.74 379	98.53 432

FE-MVSNET3		98.09 273	97.82 293	98.89 278	98.70 442	98.90 218	98.57 480	99.47 237	96.78 368	98.87 342	99.05 422	94.75 285	99.23 399	97.45 351	96.74 379	98.53 432

DeepMVS_CX				93.34 486	99.29 317	82.27 519		99.22 382	85.15 515	96.33 470	99.05 422	90.97 411	99.73 284	93.57 466	97.77 336	98.01 475

YYNet1		95.36 435	94.51 444	97.92 401	97.89 480	97.10 353	99.10 397	99.23 380	93.26 471	80.77 536	99.04 425	92.81 357	98.02 491	94.30 452	94.18 446	98.64 397

Anonymous20240521		96.20 414	95.89 417	97.13 447	97.72 488	94.96 455	99.79 32	99.29 362	93.01 474	97.20 457	99.03 426	89.69 428	98.36 485	91.16 490	96.13 396	98.07 469

MDA-MVSNet-bldmvs		94.96 444	93.98 452	97.92 401	98.24 471	97.27 344	99.15 382	99.33 338	93.80 462	80.09 538	99.03 426	88.31 446	97.86 496	93.49 467	94.36 442	98.62 406

test_method		91.10 473	91.36 473	90.31 502	95.85 516	73.72 542	94.89 530	99.25 376	68.39 532	95.82 476	99.02 428	80.50 500	98.95 465	93.64 465	94.89 433	98.25 458

DenseAffine		94.28 455	93.53 461	96.52 463	98.72 438	92.31 490	98.78 457	99.02 414	93.14 473	94.45 488	99.01 429	74.73 507	99.20 413	90.98 491	92.94 468	98.04 472

UWE-MVS		97.58 362	97.29 371	98.48 341	99.09 372	96.25 409	99.01 419	96.61 519	97.86 248	99.19 281	99.01 429	88.72 437	99.90 150	97.38 357	98.69 277	99.28 296

UWE-MVS-28		97.36 380	97.24 376	97.75 422	98.84 420	94.44 468	99.24 359	97.58 506	97.98 237	99.00 318	99.00 431	91.35 402	99.53 343	93.75 462	98.39 294	99.27 300

BH-w/o		98.00 294	97.89 288	98.32 364	99.35 298	96.20 411	99.01 419	98.90 435	96.42 400	98.38 404	99.00 431	95.26 254	99.72 288	96.06 418	98.61 280	99.03 325

Effi-MVS+-dtu		98.78 213	98.89 173	98.47 346	99.33 304	96.91 378	99.57 148	99.30 358	98.47 131	99.41 217	98.99 433	96.78 166	99.74 278	98.73 199	99.38 186	98.74 358

UnsupCasMVSNet_eth		96.44 409	96.12 410	97.40 440	98.65 449	95.65 430	99.36 303	99.51 163	97.13 338	96.04 475	98.99 433	88.40 445	98.17 488	96.71 400	90.27 491	98.40 449

test0.0.03 1		97.71 347	97.42 352	98.56 331	98.41 468	97.82 322	98.78 457	98.63 475	97.34 319	98.05 430	98.98 435	94.45 308	98.98 455	95.04 444	97.15 375	98.89 339

MDA-MVSNet_test_wron		95.45 430	94.60 440	98.01 391	98.16 475	97.21 349	99.11 395	99.24 379	93.49 467	80.73 537	98.98 435	93.02 351	98.18 487	94.22 456	94.45 440	98.64 397

FPMVS		84.93 492	85.65 492	82.75 518	86.77 554	63.39 547	98.35 496	98.92 428	74.11 524	83.39 529	98.98 435	50.85 538	92.40 534	84.54 521	94.97 428	92.46 527

testing3		97.28 385	96.76 395	98.82 296	99.37 293	98.07 305	99.45 251	99.36 318	97.56 291	97.89 437	98.95 438	83.70 486	98.82 472	96.03 419	98.56 286	99.58 221

WB-MVSnew		97.65 357	97.65 316	97.63 428	98.78 427	97.62 332	99.13 386	98.33 486	97.36 318	99.07 303	98.94 439	95.64 238	99.15 418	92.95 475	98.68 278	96.12 520

SSC-MVS		92.73 466	93.73 456	89.72 508	95.02 527	81.38 524	99.76 39	99.23 380	94.87 448	92.80 500	98.93 440	94.71 290	91.37 537	74.49 536	93.80 454	96.42 516

testf1		90.42 477	90.68 477	89.65 509	97.78 484	73.97 540	99.13 386	98.81 449	89.62 500	91.80 508	98.93 440	62.23 529	98.80 474	86.61 516	91.17 482	96.19 518

APD_test2		90.42 477	90.68 477	89.65 509	97.78 484	73.97 540	99.13 386	98.81 449	89.62 500	91.80 508	98.93 440	62.23 529	98.80 474	86.61 516	91.17 482	96.19 518

alignmvs		98.81 208	98.56 228	99.58 119	99.43 272	99.42 121	99.51 197	98.96 423	98.61 115	99.35 238	98.92 443	94.78 280	99.77 267	99.35 84	98.11 321	99.54 231

nomal-1		97.78 332	97.52 330	98.54 337	99.27 322	96.47 400	99.32 320	98.56 477	97.43 310	98.92 331	98.91 444	88.14 450	99.72 288	98.75 195	98.39 294	99.44 270

WB-MVS		93.10 464	94.10 449	90.12 505	95.51 523	81.88 521	99.73 53	99.27 371	95.05 443	93.09 499	98.91 444	94.70 291	91.89 535	76.62 531	94.02 452	96.58 515

DKM-HiRes		92.13 468	91.58 472	93.78 484	98.24 471	88.09 505	98.61 476	98.68 470	91.39 492	90.36 511	98.90 446	67.97 523	96.01 518	91.39 488	88.65 500	97.24 502

test-LLR		98.06 279	97.90 284	98.55 333	98.79 424	97.10 353	98.67 469	97.75 499	97.34 319	98.61 386	98.85 447	94.45 308	99.45 351	97.25 367	99.38 186	99.10 311

test-mter		97.49 374	97.13 382	98.55 333	98.79 424	97.10 353	98.67 469	97.75 499	96.65 378	98.61 386	98.85 447	88.23 447	99.45 351	97.25 367	99.38 186	99.10 311

dmvs_testset		95.02 442	96.12 410	91.72 493	99.10 369	80.43 529	99.58 140	97.87 498	97.47 302	95.22 479	98.82 449	93.99 327	95.18 523	88.09 505	94.91 431	99.56 228

MGCFI-Net		99.01 175	98.85 183	99.50 155	99.42 274	99.26 147	99.82 16	99.48 215	98.60 117	99.28 253	98.81 450	97.04 149	99.76 271	99.29 104	97.87 331	99.47 260

sasdasda		99.02 170	98.86 180	99.51 149	99.42 274	99.32 134	99.80 25	99.48 215	98.63 112	99.31 245	98.81 450	97.09 145	99.75 275	99.27 110	97.90 327	99.47 260

canonicalmvs		99.02 170	98.86 180	99.51 149	99.42 274	99.32 134	99.80 25	99.48 215	98.63 112	99.31 245	98.81 450	97.09 145	99.75 275	99.27 110	97.90 327	99.47 260

new_pmnet		96.38 411	96.03 413	97.41 439	98.13 476	95.16 449	99.05 406	99.20 387	93.94 458	97.39 451	98.79 453	91.61 396	99.04 441	90.43 494	95.77 407	98.05 471

cascas		97.69 349	97.43 351	98.48 341	98.60 456	97.30 342	98.18 506	99.39 296	92.96 476	98.41 402	98.78 454	93.77 337	99.27 391	98.16 272	98.61 280	98.86 340

PVSNet_0	94.43 19	96.09 418	95.47 425	97.94 399	99.31 312	94.34 472	97.81 517	99.70 18	97.12 340	97.46 447	98.75 455	89.71 427	99.79 254	97.69 325	81.69 522	99.68 165

patchmatchnet-post											98.70 456	94.79 279	99.74 278

Patchmatch-RL test		95.84 422	95.81 419	95.95 470	95.61 519	90.57 500	98.24 502	98.39 484	95.10 442	95.20 480	98.67 457	94.78 280	97.77 497	96.28 416	90.02 492	99.51 246

thres100view900		97.76 334	97.45 342	98.69 314	99.72 113	97.86 321	99.59 130	98.74 461	97.93 241	99.26 264	98.62 458	91.75 388	99.83 225	93.22 471	98.18 316	98.37 452

thres600view7		97.86 314	97.51 333	98.92 268	99.72 113	97.95 315	99.59 130	98.74 461	97.94 240	99.27 259	98.62 458	91.75 388	99.86 185	93.73 463	98.19 315	98.96 336

FBQ-MVS		97.45 376	97.07 385	98.59 322	99.27 322	96.84 381	99.35 309	98.81 449	97.55 292	98.89 338	98.61 460	85.29 477	99.62 331	97.67 327	98.21 314	99.32 292

DSMNet-mixed		97.25 387	97.35 359	96.95 454	97.84 482	93.61 482	99.57 148	96.63 518	96.13 421	98.87 342	98.61 460	94.59 298	97.70 500	95.08 443	98.86 266	99.55 229

mmtdpeth		96.95 397	96.71 396	97.67 427	99.33 304	94.90 456	99.89 2	99.28 364	98.15 186	99.72 109	98.57 462	86.56 465	99.90 150	99.82 30	89.02 499	98.20 461

MVS_clip		71.06 511	74.26 510	61.45 536	84.42 558	45.51 564	79.78 551	56.58 563	40.80 555	90.25 512	98.55 463	61.46 531	49.70 559	80.63 527	75.89 539	89.13 537

IB-MVS	95.67 18	96.22 412	95.44 427	98.57 327	99.21 340	96.70 388	98.65 473	97.74 501	96.71 373	97.27 453	98.54 464	86.03 469	99.92 125	98.47 239	86.30 506	99.10 311
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
myMVS_eth3d28		97.69 349	97.34 362	98.73 307	99.27 322	97.52 335	99.33 317	98.78 455	98.03 229	98.82 352	98.49 465	86.64 463	99.46 349	98.44 243	98.24 309	99.23 303

GG-mvs-BLEND				98.45 349	98.55 460	98.16 297	99.43 264	93.68 535		97.23 454	98.46 466	89.30 431	99.22 406	95.43 436	98.22 310	97.98 480

tfpn200view9		97.72 344	97.38 355	98.72 309	99.69 130	97.96 312	99.50 208	98.73 467	97.83 255	99.17 286	98.45 467	91.67 392	99.83 225	93.22 471	98.18 316	98.37 452

thres400		97.77 333	97.38 355	98.92 268	99.69 130	97.96 312	99.50 208	98.73 467	97.83 255	99.17 286	98.45 467	91.67 392	99.83 225	93.22 471	98.18 316	98.96 336

testing11		97.50 369	97.10 383	98.71 312	99.20 342	96.91 378	99.29 332	98.82 447	97.89 245	98.21 420	98.40 469	85.63 472	99.83 225	98.45 242	98.04 323	99.37 285

kuosan		90.92 475	90.11 480	93.34 486	98.78 427	85.59 512	98.15 509	93.16 538	89.37 502	92.07 505	98.38 470	81.48 497	95.19 522	62.54 543	97.04 376	99.25 301

KD-MVS_2432*1600		94.62 449	93.72 457	97.31 442	97.19 498	95.82 425	98.34 497	99.20 387	95.00 445	97.57 444	98.35 471	87.95 451	98.10 489	92.87 477	77.00 537	98.01 475

miper_refine_blended		94.62 449	93.72 457	97.31 442	97.19 498	95.82 425	98.34 497	99.20 387	95.00 445	97.57 444	98.35 471	87.95 451	98.10 489	92.87 477	77.00 537	98.01 475

thres200		97.61 360	97.28 372	98.62 320	99.64 170	98.03 306	99.26 352	98.74 461	97.68 277	99.09 300	98.32 473	91.66 394	99.81 239	92.88 476	98.22 310	98.03 473

testing91		97.44 377	97.02 387	98.71 312	99.18 348	96.89 380	99.19 374	99.04 410	97.78 263	98.31 412	98.29 474	85.41 475	99.85 193	98.01 289	97.95 325	99.39 281

usedtu_dtu_shiyan2		91.34 472	89.96 481	95.47 474	93.61 537	90.81 497	99.15 382	98.68 470	86.37 512	95.19 481	98.27 475	72.64 510	97.05 508	85.40 519	80.32 532	98.54 430

testing99		97.36 380	96.94 390	98.63 319	99.18 348	96.70 388	99.30 327	98.93 425	97.71 272	98.23 417	98.26 476	84.92 479	99.84 203	98.04 288	97.85 333	99.35 287

OpenMVS_ROB	92.34 20	94.38 453	93.70 459	96.41 464	97.38 492	93.17 485	99.06 403	98.75 457	86.58 511	94.84 487	98.26 476	81.53 496	99.32 383	89.01 501	97.87 331	96.76 511

UBG		97.85 315	97.48 336	98.95 262	99.25 331	97.64 331	99.24 359	98.74 461	97.90 244	98.64 380	98.20 478	88.65 441	99.81 239	98.27 262	98.40 293	99.42 274

LoFTR		93.25 462	92.33 468	95.99 469	97.91 478	90.83 496	99.06 403	98.56 477	92.19 482	90.24 513	98.18 479	72.97 508	99.26 394	89.37 498	92.52 476	97.89 487

testing222		97.16 390	96.50 400	99.16 237	99.16 358	98.47 284	99.27 343	98.66 474	97.71 272	98.23 417	98.15 480	82.28 495	99.84 203	97.36 358	97.66 339	99.18 306

Syy-MVS		97.09 394	97.14 380	96.95 454	99.00 392	92.73 488	99.29 332	99.39 296	97.06 348	97.41 448	98.15 480	93.92 331	98.68 479	91.71 486	98.34 297	99.45 268

myMVS_eth3d		96.89 398	96.37 403	98.43 354	99.00 392	97.16 350	99.29 332	99.39 296	97.06 348	97.41 448	98.15 480	83.46 488	98.68 479	95.27 440	98.34 297	99.45 268

CL-MVSNet_self_test		94.49 451	93.97 453	96.08 468	96.16 512	93.67 480	98.33 499	99.38 306	95.13 438	97.33 452	98.15 480	92.69 365	96.57 512	88.67 502	79.87 534	97.99 479

test_vis1_rt		95.81 423	95.65 422	96.32 465	99.67 140	91.35 495	99.49 225	96.74 517	98.25 169	95.24 478	98.10 484	74.96 504	99.90 150	99.53 54	98.85 267	97.70 492

ETVMVS		97.50 369	96.90 391	99.29 219	99.23 335	98.78 247	99.32 320	98.90 435	97.52 299	98.56 390	98.09 485	84.72 481	99.69 309	97.86 300	97.88 330	99.39 281

pmmvs3		94.09 457	93.25 464	96.60 461	94.76 529	94.49 467	98.92 436	98.18 494	89.66 499	96.48 469	98.06 486	86.28 467	97.33 504	89.68 497	87.20 505	97.97 481

mvsany_test3		93.77 459	93.45 462	94.74 477	95.78 517	88.01 506	99.64 99	98.25 489	98.28 159	94.31 489	97.97 487	68.89 521	98.51 483	97.50 344	90.37 489	97.71 489

PMatch-Up-SfM		86.75 491	85.43 493	90.73 500	94.97 528	81.39 523	97.55 522	94.92 528	86.33 513	83.10 530	97.95 488	46.03 547	93.97 530	87.59 508	80.39 531	96.83 509

PMatch-SfM		88.28 484	86.92 489	92.38 490	95.93 514	84.56 514	97.84 516	96.01 522	88.80 505	84.11 526	97.95 488	49.73 541	95.66 521	89.15 500	82.72 520	96.91 508

blended_shiyan6		95.54 428	94.78 436	97.84 412	96.60 506	95.89 422	98.85 445	99.28 364	92.17 486	98.43 401	97.95 488	91.44 398	99.02 447	97.30 363	80.97 526	98.60 418

blended_shiyan8		95.56 427	94.79 435	97.87 405	96.60 506	95.90 421	98.85 445	99.27 371	92.19 482	98.47 398	97.94 491	91.43 399	99.11 430	97.26 366	81.09 525	98.60 418

MatchFormer		91.94 470	90.72 475	95.58 473	97.82 483	89.79 504	98.92 436	98.87 441	88.24 507	88.03 518	97.92 492	70.39 516	99.23 399	85.21 520	91.12 484	97.72 488

blend_shiyan4		95.25 438	94.39 446	97.84 412	96.70 505	95.92 419	98.84 449	99.28 364	92.21 481	98.16 423	97.84 493	87.10 461	99.07 436	97.53 340	81.87 521	98.54 430

ELoFTR		89.95 479	88.65 484	93.85 481	95.93 514	85.85 510	98.64 474	98.31 487	90.34 497	85.03 523	97.76 494	60.28 532	99.01 450	87.27 512	84.26 510	96.71 514

PM-MVS		92.96 465	92.23 469	95.14 476	95.61 519	89.98 503	99.37 297	98.21 492	94.80 450	95.04 484	97.69 495	65.06 525	97.90 495	94.30 452	89.98 493	97.54 498

wanda-best-256-512		95.43 431	94.66 438	97.77 420	96.45 508	95.68 428	98.48 490	99.28 364	92.18 484	98.36 406	97.68 496	91.20 406	99.03 443	97.31 360	80.97 526	98.60 418

FE-blended-shiyan7		95.43 431	94.66 438	97.77 420	96.45 508	95.68 428	98.48 490	99.28 364	92.18 484	98.36 406	97.68 496	91.20 406	99.03 443	97.31 360	80.97 526	98.60 418

usedtu_blend_shiyan5		95.04 441	94.10 449	97.86 408	96.45 508	95.92 419	99.29 332	99.22 382	86.17 514	98.36 406	97.68 496	91.20 406	99.07 436	97.53 340	80.97 526	98.60 418

FE-MVSNET2		95.10 440	94.44 445	97.08 450	95.08 525	95.97 416	99.51 197	99.37 316	95.02 444	94.10 491	97.57 499	86.18 468	97.66 502	93.28 470	89.86 494	97.61 494

FE-MVSNET		94.07 458	93.36 463	96.22 466	94.05 533	94.71 461	99.56 156	98.36 485	93.15 472	93.76 495	97.55 500	86.47 466	96.49 514	87.48 509	89.83 495	97.48 499

pmmvs-eth3d		95.34 436	94.73 437	97.15 445	95.53 521	95.94 418	99.35 309	99.10 400	95.13 438	93.55 496	97.54 501	88.15 449	97.91 494	94.58 449	89.69 497	97.61 494

gbinet_0.2-2-1-0.02		95.40 434	94.58 442	97.85 409	96.11 513	95.97 416	98.56 484	99.26 373	92.12 488	98.47 398	97.49 502	90.23 420	99.00 452	97.71 321	81.25 523	98.58 426

ambc				93.06 489	92.68 541	82.36 518	98.47 492	98.73 467		95.09 483	97.41 503	55.55 533	99.10 433	96.42 411	91.32 480	97.71 489

RPMNet		96.72 402	95.90 416	99.19 234	99.18 348	98.49 280	99.22 366	99.52 135	88.72 506	99.56 178	97.38 504	94.08 324	99.95 77	86.87 515	98.58 283	99.14 307

new-patchmatchnet		94.48 452	94.08 451	95.67 472	95.08 525	92.41 489	99.18 376	99.28 364	94.55 455	93.49 497	97.37 505	87.86 454	97.01 509	91.57 487	88.36 501	97.61 494

PDCNetPlus		84.77 493	83.24 496	89.36 511	94.33 532	83.93 516	98.13 510	76.80 555	83.26 518	86.31 520	97.33 506	62.90 527	92.65 532	87.20 513	62.90 543	91.50 530

KD-MVS_self_test		95.00 443	94.34 447	96.96 453	97.07 501	95.39 442	99.56 156	99.44 270	95.11 440	97.13 459	97.32 507	91.86 386	97.27 506	90.35 495	81.23 524	98.23 460

PatchT		97.03 396	96.44 402	98.79 302	98.99 395	98.34 290	99.16 378	99.07 406	92.13 487	99.52 189	97.31 508	94.54 303	98.98 455	88.54 503	98.73 275	99.03 325

ALIKED-LG		88.17 486	87.32 488	90.75 499	98.67 447	81.68 522	98.16 507	94.72 531	78.63 521	86.08 522	97.07 509	70.16 517	96.62 511	71.97 539	90.37 489	93.95 525

0.4-1-1-0.1		95.23 439	94.22 448	98.26 373	97.39 491	95.86 424	97.59 521	97.62 502	93.85 460	94.97 485	97.03 510	87.20 458	99.87 178	98.47 239	83.84 511	99.05 323

ALIKED-NN		88.27 485	87.61 487	90.24 503	98.46 465	79.97 531	97.04 525	94.61 533	75.25 522	86.99 519	96.90 511	72.78 509	95.78 520	75.45 534	91.01 486	94.97 523

test_fmvs3		92.10 469	91.77 471	93.08 488	96.19 511	86.25 508	99.82 16	98.62 476	96.65 378	95.19 481	96.90 511	55.05 535	95.93 519	96.63 407	90.92 488	97.06 507

UnsupCasMVSNet_bld		93.53 460	92.51 466	96.58 462	97.38 492	93.82 475	98.24 502	99.48 215	91.10 495	93.10 498	96.66 513	74.89 506	98.37 484	94.03 459	87.71 504	97.56 497

0.4-1-1-0.2		94.94 446	93.92 454	97.99 394	96.84 504	95.13 451	96.64 528	97.62 502	93.45 469	94.92 486	96.56 514	87.14 460	99.86 185	98.43 246	83.69 515	98.98 332

0.3-1-1-0.015		94.79 447	93.69 460	98.10 385	96.99 503	95.46 438	97.02 526	97.61 504	93.53 465	94.03 493	96.54 515	85.60 473	99.86 185	98.43 246	83.45 516	98.99 331

LCM-MVSNet		86.80 490	85.22 495	91.53 494	87.81 553	80.96 526	98.23 504	98.99 418	71.05 529	90.13 514	96.51 516	48.45 546	96.88 510	90.51 492	85.30 508	96.76 511

test_f		91.90 471	91.26 474	93.84 482	95.52 522	85.92 509	99.69 64	98.53 482	95.31 437	93.87 494	96.37 517	55.33 534	98.27 486	95.70 428	90.98 487	97.32 501

SP-DiffGlue		90.78 476	90.71 476	90.98 497	95.45 524	81.30 525	97.92 515	97.30 509	75.18 523	92.09 504	95.93 518	74.93 505	94.89 526	93.46 468	94.12 448	96.74 513

VLMVS_CLIP		71.76 508	73.17 511	67.54 533	63.66 563	40.57 566	82.57 550	89.67 545	44.24 554	82.97 532	95.88 519	37.85 555	71.58 556	83.87 522	77.80 535	90.48 532

ALIKED-MNN		86.97 488	85.90 490	90.16 504	99.06 381	79.59 532	97.93 514	94.82 529	72.37 527	84.41 525	95.46 520	68.55 522	96.43 515	72.40 537	88.11 503	94.47 524

PMMVS2		86.87 489	85.37 494	91.35 495	90.21 547	83.80 517	98.89 440	97.45 508	83.13 519	91.67 510	95.03 521	48.49 545	94.70 528	85.86 518	77.62 536	95.54 521

Gipuma		90.99 474	90.15 479	93.51 485	98.73 436	90.12 502	93.98 535	99.45 261	79.32 520	92.28 503	94.91 522	69.61 519	97.98 493	87.42 510	95.67 411	92.45 528
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
JIA-IIPM		97.50 369	97.02 387	98.93 266	98.73 436	97.80 323	99.30 327	98.97 421	91.73 490	98.91 333	94.86 523	95.10 261	99.71 295	97.58 332	97.98 324	99.28 296

SP-SuperGlue		89.23 481	88.68 482	90.88 498	98.23 473	80.60 528	98.16 507	97.30 509	73.08 525	89.64 515	94.62 524	71.80 513	94.91 525	82.11 525	93.22 462	97.14 506

SP-LightGlue		89.28 480	88.68 482	91.06 496	98.21 474	80.90 527	98.19 505	96.96 512	72.38 526	89.60 516	94.43 525	72.44 511	95.06 524	82.91 523	93.03 467	97.22 503

VLMVS		64.83 516	67.01 517	58.30 538	65.95 562	42.53 565	76.90 553	66.20 561	29.52 556	82.93 533	94.37 526	42.34 549	55.19 558	72.39 538	72.45 540	77.18 541

SP-MNN		88.33 483	87.78 486	89.95 507	98.28 469	77.92 535	98.01 513	95.69 525	70.61 530	86.18 521	94.36 527	71.09 515	94.76 527	81.51 526	94.32 443	97.17 504

XFeat-MNN		82.40 497	82.10 498	83.31 516	93.04 539	68.49 544	95.39 529	90.86 542	60.29 539	81.56 534	94.09 528	66.79 524	91.70 536	76.62 531	80.26 533	89.74 534

SP-NN		88.62 482	88.17 485	89.96 506	97.89 480	78.51 534	97.19 524	96.09 521	71.28 528	88.29 517	94.00 529	71.98 512	93.65 531	82.37 524	94.46 438	97.71 489

PMVS	70.75 22	75.98 504	74.97 507	79.01 521	70.98 560	55.18 559	93.37 538	98.21 492	65.08 537	61.78 550	93.83 530	21.74 563	92.53 533	78.59 529	91.12 484	89.34 536
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
XFeat-NN		82.84 494	83.12 497	82.00 520	94.35 531	67.14 546	93.32 540	89.27 546	62.21 538	84.06 527	93.50 531	69.15 520	89.40 538	78.92 528	83.33 517	89.46 535

GLUNet-SfM		78.99 500	76.32 504	86.99 512	89.16 552	73.30 543	93.36 539	90.45 543	66.38 535	74.95 544	93.30 532	52.29 537	94.61 529	75.35 535	51.65 550	93.07 526

MVS-HIRNet		95.75 424	95.16 429	97.51 435	99.30 313	93.69 479	98.88 441	95.78 523	85.09 516	98.78 358	92.65 533	91.29 404	99.37 371	94.85 447	99.85 95	99.46 265

E-PMN		80.61 498	79.88 500	82.81 517	90.75 545	76.38 538	97.69 518	95.76 524	66.44 534	83.52 528	92.25 534	62.54 528	87.16 546	68.53 541	61.40 544	84.89 539

test_vis3_rt		87.04 487	85.81 491	90.73 500	93.99 534	81.96 520	99.76 39	90.23 544	92.81 478	81.35 535	91.56 535	40.06 553	99.07 436	94.27 454	88.23 502	91.15 531

EMVS		80.02 499	79.22 501	82.43 519	91.19 544	76.40 537	97.55 522	92.49 541	66.36 536	83.01 531	91.27 536	64.63 526	85.79 549	65.82 542	60.65 545	85.08 538

MVS_baseline		35.35 524	39.65 527	22.45 542	47.29 564	11.23 569	38.03 554	9.90 568	5.09 561	58.24 553	91.18 537	16.48 565	0.13 563	42.28 555	48.39 551	55.99 555

gg-mvs-nofinetune		96.17 416	95.32 428	98.73 307	98.79 424	98.14 299	99.38 293	94.09 534	91.07 496	98.07 429	91.04 538	89.62 430	99.35 378	96.75 398	99.09 241	98.68 376

SIFT-MNN		75.73 505	75.71 505	75.77 523	95.65 518	60.92 550	94.36 532	87.62 547	58.67 541	75.90 542	90.94 539	49.64 543	89.04 540	44.85 550	83.80 513	77.35 540

SIFT-NN		76.99 502	77.37 503	75.84 522	97.10 500	62.39 548	94.15 534	87.21 548	59.41 540	79.90 540	90.73 540	54.60 536	88.56 541	47.22 545	86.03 507	76.57 542

SIFT-ConvMatch		69.43 513	68.09 516	73.45 528	93.86 536	60.02 554	92.57 544	77.69 554	57.58 545	62.69 548	90.53 541	42.14 550	86.65 548	43.98 551	51.72 549	73.67 547

SIFT-NN-NCMNet		75.53 506	75.57 506	75.42 524	93.93 535	61.35 549	94.41 531	86.44 549	58.51 542	76.23 541	90.44 542	50.56 539	89.34 539	46.60 546	83.04 518	75.58 544

SIFT-UMatch		68.14 514	66.40 518	73.38 529	92.20 543	59.42 555	92.84 542	76.01 557	56.87 547	58.37 552	90.35 543	41.97 551	87.16 546	42.64 552	46.35 552	73.55 549

SIFT-NN-CMatch		72.61 507	71.92 512	74.68 525	92.79 540	60.24 552	93.28 541	81.57 553	58.24 544	75.18 543	90.26 544	49.66 542	87.35 545	46.02 547	60.26 546	76.45 543

SIFT-CM-Cal		66.94 515	65.48 519	71.33 531	93.05 538	58.77 556	91.46 547	70.45 559	56.64 550	61.97 549	89.98 545	40.72 552	83.32 552	42.57 553	42.47 554	71.90 550

SIFT-UM-Cal		64.60 517	62.65 520	70.42 532	92.22 542	58.07 558	92.29 545	66.92 560	56.70 548	50.16 556	89.97 546	37.90 554	82.95 553	42.33 554	35.40 557	70.24 552

SIFT-NN-UMatch		71.65 509	70.86 513	74.00 527	90.69 546	60.53 551	93.59 536	81.89 551	58.42 543	60.99 551	89.71 547	50.18 540	87.89 543	45.77 548	66.55 542	73.57 548

SIFT-NCM-Cal		71.65 509	70.76 514	74.34 526	94.61 530	60.18 553	94.16 533	81.72 552	57.21 546	55.36 554	89.56 548	42.48 548	88.45 542	41.31 556	80.41 530	74.39 546

ANet_high		77.30 501	74.86 508	84.62 515	75.88 559	77.61 536	97.63 520	93.15 539	88.81 504	64.27 547	89.29 549	36.51 557	83.93 550	75.89 533	52.31 548	92.33 529

SIFT-NN-PointCN		70.32 512	69.71 515	72.13 530	90.01 548	58.29 557	93.45 537	76.20 556	56.66 549	70.25 546	89.20 550	48.94 544	83.41 551	45.45 549	57.26 547	74.70 545

MVE	76.82 21	76.91 503	74.31 509	84.70 514	85.38 557	76.05 539	96.88 527	93.17 537	67.39 533	71.28 545	89.01 551	21.66 564	87.69 544	71.74 540	72.29 541	90.35 533
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-PCN-Cal		61.29 519	60.21 522	64.54 535	89.88 549	50.56 561	91.21 548	65.73 562	53.15 552	48.59 557	87.20 552	36.60 556	76.52 554	37.37 559	32.17 558	66.54 553

SIFT-PointCN		62.71 518	61.56 521	66.18 534	89.53 551	50.88 560	91.81 546	72.35 558	53.65 551	50.49 555	86.32 553	33.30 558	76.23 555	35.91 560	40.66 555	71.43 551

SIFT-NCMNet		55.02 520	53.54 523	59.46 537	86.55 555	47.35 563	87.85 549	46.22 564	51.77 553	44.11 558	83.50 554	27.88 561	68.75 557	32.81 561	21.14 561	62.27 554

testmvs		39.17 522	43.78 524	25.37 541	36.04 566	16.84 568	98.36 495	26.56 565	20.06 558	38.51 560	67.32 555	29.64 560	15.30 562	37.59 557	39.90 556	43.98 557

test123		39.01 523	42.50 525	28.53 540	39.17 565	20.91 567	98.75 462	19.17 567	19.83 559	38.57 559	66.67 556	33.16 559	15.42 561	37.50 558	29.66 559	49.26 556

test_post											65.99 557	94.65 296	99.73 284

test_post1							99.23 362				65.14 558	94.18 320	99.71 295	97.58 332

X-MVStestdata		96.55 406	95.45 426	99.87 23	99.85 32	99.83 24	99.69 64	99.68 24	98.98 73	99.37 229	64.01 559	98.81 50	99.94 92	98.79 192	99.86 88	99.84 56

wuyk23d		40.18 521	41.29 526	36.84 539	86.18 556	49.12 562	79.73 552	22.81 566	27.64 557	25.46 561	28.45 560	21.98 562	48.89 560	55.80 544	23.56 560	12.51 558

test_blank		0.13 528	0.17 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	1.57 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

mmdepth		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

monomultidepth		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uanet_test		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

DCPMVS		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

pcd_1.5k_mvsjas		8.27 527	11.03 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	99.01 19	0.00 564	0.00 562	0.00 562	0.00 559

sosnet-low-res		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

sosnet		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uncertanet		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

Regformer		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uanet		0.02 529	0.03 532	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.27 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet2					0.00 567	95.16 449	98.77 460	99.17 392	93.82 461
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														91.97 483	96.20 394	98.59 424
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.13 423
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					99.82 54	99.84 21		99.63 47		99.85 56		98.54 84	99.94 92	99.34 89	99.88 74

WAC-MVS						97.16 350								95.47 434

FOURS1					99.91 1	99.93 1	99.87 8	99.56 91	99.10 49	99.81 73

MSC_two_6792asdad				99.87 23	99.51 240	99.76 51		99.33 338					99.96 42	98.87 171	99.84 103	99.89 31

No_MVS				99.87 23	99.51 240	99.76 51		99.33 338					99.96 42	98.87 171	99.84 103	99.89 31

eth-test2					0.00 567

eth-test					0.00 567

IU-MVS					99.84 39	99.88 11		99.32 349	98.30 157	99.84 57				98.86 176	99.85 95	99.89 31

save fliter					99.76 84	99.59 91	99.14 385	99.40 293	99.00 68

test_0728_SECOND				99.91 7	99.84 39	99.89 7	99.57 148	99.51 163					99.96 42	98.93 162	99.86 88	99.88 37

GSMVS																99.52 237

test_part2					99.81 59	99.83 24				99.77 91

sam_mvs1												94.86 273				99.52 237

sam_mvs												94.72 289

MTGPA								99.47 237

MTMP							99.54 176	98.88 439

test9_res														97.49 345	99.72 150	99.75 115

agg_prior2														97.21 369	99.73 149	99.75 115

agg_prior					99.67 140	99.62 85		99.40 293		98.87 342			99.91 137

test_prior4						99.56 97	98.99 422

test_prior				99.68 91	99.67 140	99.48 114		99.56 91					99.83 225			99.74 120

旧先验2							98.96 429		96.70 374	99.47 197			99.94 92	98.19 268

新几何2							99.01 419

无先验							98.99 422	99.51 163	96.89 362				99.93 110	97.53 340		99.72 140

原ACMM2							98.95 432

testdata2													99.95 77	96.67 403

segment_acmp												98.96 27

testdata1							98.85 445		98.32 153

test12				99.75 78	99.64 170	99.61 88		99.29 362		99.21 274		98.38 97	99.89 165		99.74 147	99.74 120

plane_prior7					99.29 317	97.03 365

plane_prior6					99.27 322	96.98 369						92.71 363

plane_prior5								99.47 237					99.69 309	97.78 310	97.63 340	98.67 384

plane_prior3						97.00 367			98.69 109	99.11 294

plane_prior2							99.39 288		98.97 77

plane_prior1					99.26 327

plane_prior						96.97 370	99.21 368		98.45 134						97.60 343

n2								0.00 569

nn								0.00 569

door-mid								98.05 495

test11								99.35 325

door								97.92 496

HQP5-MVS						96.83 382

HQP-NCC					99.19 345		98.98 425		98.24 171	98.66 373

ACMP_Plane					99.19 345		98.98 425		98.24 171	98.66 373

BP-MVS														97.19 373

HQP4-MVS										98.66 373			99.64 324			98.64 397

HQP3-MVS								99.39 296							97.58 345

HQP2-MVS												92.47 372

MDTV_nov1_ep13_2view						95.18 448	99.35 309		96.84 365	99.58 173		95.19 258		97.82 305		99.46 265

ACMMP++_ref															97.19 373

ACMMP++															97.43 363

Test By Simon												98.75 62

High-resolution multi-view benchmark