High-res multi-view results

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

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

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

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

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

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

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

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

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 41	99.71 9	96.99 48	99.69 2	99.57 20	99.02 19	99.62 13	99.36 23	98.53 9	99.52 199	98.58 36	99.95 5	99.66 35
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UA-Net		98.88 8	98.76 14	99.22 3	99.11 92	97.89 17	99.47 3	99.32 34	99.08 14	97.87 175	99.67 3	96.47 105	99.92 6	97.88 54	99.98 2	99.85 6

mvs5depth		98.06 53	98.58 26	96.51 213	98.97 115	89.65 275	99.43 4	99.81 2	99.30 7	98.36 115	99.86 2	93.15 216	99.88 21	98.50 38	99.84 42	99.99 1

TDRefinement		98.90 6	98.86 9	99.02 10	99.54 25	98.06 9	99.34 5	99.44 27	98.85 25	99.00 53	99.20 38	97.42 43	99.59 175	97.21 81	99.76 63	99.40 113

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 46	99.77 5	96.34 69	99.18 6	99.20 46	99.67 2	99.73 4	99.65 6	99.15 3	99.86 26	97.22 80	99.92 14	99.77 15

OurMVSNet-221017-0		98.61 17	98.61 25	98.63 48	99.77 5	96.35 68	99.17 7	99.05 80	98.05 54	99.61 14	99.52 9	93.72 205	99.88 21	98.72 32	99.88 25	99.65 38

DVP-MVS++		97.96 60	97.90 70	98.12 86	97.75 280	95.40 105	99.03 8	98.89 120	96.62 110	98.62 86	98.30 148	96.97 71	99.75 74	95.70 147	99.25 220	99.21 156

FOURS1					99.59 17	98.20 8	99.03 8	99.25 42	98.96 22	98.87 65

pmmvs6		99.07 4	99.24 4	98.56 52	99.81 2	96.38 66	98.87 10	99.30 36	99.01 20	99.63 12	99.66 4	99.27 2	99.68 131	97.75 63	99.89 23	99.62 42

Anonymous20231211		98.55 21	98.76 14	97.94 101	98.79 138	94.37 150	98.84 11	99.15 55	99.37 4	99.67 8	99.43 17	95.61 145	99.72 95	98.12 45	99.86 30	99.73 25

mmtdpeth		98.33 33	98.53 28	97.71 115	99.07 98	93.44 186	98.80 12	99.78 4	99.10 13	96.61 253	99.63 7	95.42 153	99.73 89	98.53 37	99.86 30	99.95 2

MIMVSNet1		98.51 25	98.45 33	98.67 44	99.72 8	96.71 54	98.76 13	98.89 120	98.49 35	99.38 25	99.14 50	95.44 152	99.84 32	96.47 109	99.80 55	99.47 92

EPP-MVSNet		96.84 161	96.58 176	97.65 121	99.18 78	93.78 174	98.68 14	96.34 326	97.91 57	97.30 200	98.06 186	88.46 299	99.85 29	93.85 247	99.40 187	99.32 131

v7n		98.73 12	98.99 5	97.95 100	99.64 13	94.20 158	98.67 15	99.14 58	99.08 14	99.42 22	99.23 35	96.53 100	99.91 14	99.27 9	99.93 11	99.73 25

MVSFormer		96.14 198	96.36 191	95.49 273	97.68 288	87.81 321	98.67 15	99.02 90	96.50 119	94.48 333	96.15 324	86.90 316	99.92 6	98.73 30	99.13 235	98.74 241

test_djsdf		98.73 12	98.74 17	98.69 43	99.63 14	96.30 71	98.67 15	99.02 90	96.50 119	99.32 30	99.44 16	97.43 42	99.92 6	98.73 30	99.95 5	99.86 5

tt0805		97.44 123	97.56 114	97.11 167	99.55 22	96.36 67	98.66 18	95.66 339	98.31 41	97.09 220	95.45 349	97.17 57	98.50 375	98.67 33	97.45 356	96.48 392

anonymousdsp		98.72 15	98.63 21	98.99 14	99.62 15	97.29 41	98.65 19	99.19 48	95.62 171	99.35 29	99.37 21	97.38 44	99.90 16	98.59 35	99.91 17	99.77 15

HPM-MVS		98.11 48	97.83 80	98.92 25	99.42 39	97.46 35	98.57 20	99.05 80	95.43 183	97.41 198	97.50 236	97.98 20	99.79 49	95.58 159	99.57 123	99.50 75
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
IS-MVSNet		96.93 154	96.68 170	97.70 117	99.25 60	94.00 165	98.57 20	96.74 321	98.36 39	98.14 143	97.98 195	88.23 303	99.71 109	93.10 268	99.72 78	99.38 120

WR-MVS_H		98.65 16	98.62 23	98.75 35	99.51 28	96.61 60	98.55 22	99.17 50	99.05 17	99.17 39	98.79 85	95.47 150	99.89 19	97.95 52	99.91 17	99.75 23

FE-MVS		92.95 322	92.22 327	95.11 286	97.21 329	88.33 306	98.54 23	93.66 371	89.91 335	96.21 279	98.14 171	70.33 407	99.50 204	87.79 362	98.24 316	97.51 356

test2506		89.86 367	89.16 372	91.97 384	98.95 116	76.83 421	98.54 23	61.07 439	96.20 133	97.07 221	99.16 47	55.19 433	99.69 125	96.43 111	99.83 46	99.38 120

mvs_tets		98.90 6	98.94 6	98.75 35	99.69 10	96.48 64	98.54 23	99.22 43	96.23 132	99.71 5	99.48 12	98.77 7	99.93 4	98.89 25	99.95 5	99.84 8

CS-MVS		98.09 49	98.01 62	98.32 67	98.45 193	96.69 56	98.52 26	99.69 9	98.07 53	96.07 285	97.19 261	96.88 82	99.86 26	97.50 73	99.73 73	98.41 274

Gipuma		98.07 52	98.31 41	97.36 150	99.76 7	96.28 72	98.51 27	99.10 64	98.76 27	96.79 238	99.34 26	96.61 96	98.82 341	96.38 113	99.50 154	96.98 371
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PS-CasMVS		98.73 12	98.85 11	98.39 63	99.55 22	95.47 104	98.49 28	99.13 59	99.22 10	99.22 37	98.96 69	97.35 45	99.92 6	97.79 60	99.93 11	99.79 13

3Dnovator	96.53 2	97.61 108	97.64 104	97.50 135	97.74 283	93.65 181	98.49 28	98.88 127	96.86 103	97.11 214	98.55 115	95.82 133	99.73 89	95.94 137	99.42 182	99.13 172

DTE-MVSNet		98.79 9	98.86 9	98.59 50	99.55 22	96.12 76	98.48 30	99.10 64	99.36 5	99.29 32	99.06 58	97.27 49	99.93 4	97.71 65	99.91 17	99.70 30

jajsoiax		98.77 10	98.79 13	98.74 38	99.66 12	96.48 64	98.45 31	99.12 60	95.83 162	99.67 8	99.37 21	98.25 14	99.92 6	98.77 28	99.94 8	99.82 9

PEN-MVS		98.75 11	98.85 11	98.44 59	99.58 18	95.67 93	98.45 31	99.15 55	99.33 6	99.30 31	99.00 63	97.27 49	99.92 6	97.64 69	99.92 14	99.75 23

LS3D		97.77 92	97.50 121	98.57 51	96.24 356	97.58 28	98.45 31	98.85 136	98.58 32	97.51 189	97.94 199	95.74 140	99.63 158	95.19 183	98.97 253	98.51 266

SPE-MVS-test		97.91 74	97.84 77	98.14 84	98.52 181	96.03 81	98.38 34	99.67 10	98.11 51	95.50 309	96.92 282	96.81 88	99.87 24	96.87 98	99.76 63	98.51 266

FC-MVSNet-test		98.16 43	98.37 37	97.56 126	99.49 32	93.10 197	98.35 35	99.21 44	98.43 36	98.89 63	98.83 84	94.30 190	99.81 41	97.87 55	99.91 17	99.77 15

HPM-MVS_fast		98.32 35	98.13 49	98.88 27	99.54 25	97.48 34	98.35 35	99.03 88	95.88 158	97.88 172	98.22 165	98.15 17	99.74 83	96.50 108	99.62 102	99.42 110

ab-mvs		96.59 179	96.59 175	96.60 206	98.64 161	92.21 220	98.35 35	97.67 281	94.45 224	96.99 226	98.79 85	94.96 171	99.49 209	90.39 327	99.07 245	98.08 309

EGC-MVSNET		83.08 398	77.93 401	98.53 54	99.57 19	97.55 30	98.33 38	98.57 198	4.71 436	10.38 437	98.90 79	95.60 146	99.50 204	95.69 149	99.61 108	98.55 262

test1111		94.53 278	94.81 255	93.72 340	99.06 100	81.94 393	98.31 39	83.87 429	96.37 125	98.49 98	99.17 46	81.49 353	99.73 89	96.64 102	99.86 30	99.49 83

ECVR-MVS		94.37 284	94.48 273	94.05 335	98.95 116	83.10 383	98.31 39	82.48 431	96.20 133	98.23 132	99.16 47	81.18 356	99.66 146	95.95 136	99.83 46	99.38 120

EC-MVSNet		97.90 76	97.94 69	97.79 109	98.66 160	95.14 123	98.31 39	99.66 12	97.57 72	95.95 289	97.01 276	96.99 70	99.82 36	97.66 68	99.64 98	98.39 277

pm-mvs1		98.47 28	98.67 19	97.86 105	99.52 27	94.58 141	98.28 42	99.00 101	97.57 72	99.27 33	99.22 36	98.32 12	99.50 204	97.09 88	99.75 71	99.50 75

SixPastTwentyTwo		97.49 118	97.57 113	97.26 158	99.56 20	92.33 215	98.28 42	96.97 312	98.30 43	99.45 20	99.35 25	88.43 300	99.89 19	98.01 50	99.76 63	99.54 62

FA-MVS(test-final)		94.91 256	94.89 247	94.99 294	97.51 307	88.11 314	98.27 44	95.20 353	92.40 294	96.68 246	98.60 109	83.44 344	99.28 279	93.34 260	98.53 298	97.59 353

CP-MVSNet		98.42 30	98.46 30	98.30 70	99.46 34	95.22 120	98.27 44	98.84 140	99.05 17	99.01 51	98.65 104	95.37 154	99.90 16	97.57 70	99.91 17	99.77 15

GG-mvs-BLEND				90.60 395	91.00 430	84.21 377	98.23 46	72.63 438		82.76 429	84.11 430	56.14 426	96.79 415	72.20 427	92.09 419	90.78 427

GBi-Net		96.99 149	96.80 164	97.56 126	97.96 248	93.67 177	98.23 46	98.66 185	95.59 173	97.99 159	99.19 39	89.51 290	99.73 89	94.60 217	99.44 170	99.30 136

test1		96.99 149	96.80 164	97.56 126	97.96 248	93.67 177	98.23 46	98.66 185	95.59 173	97.99 159	99.19 39	89.51 290	99.73 89	94.60 217	99.44 170	99.30 136

FMVSNet1		97.95 64	98.08 54	97.56 126	99.14 90	93.67 177	98.23 46	98.66 185	97.41 84	99.00 53	99.19 39	95.47 150	99.73 89	95.83 144	99.76 63	99.30 136

ACMH	93.61 9	98.44 29	98.76 14	97.51 131	99.43 37	93.54 183	98.23 46	99.05 80	97.40 85	99.37 26	99.08 57	98.79 6	99.47 214	97.74 64	99.71 81	99.50 75
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TransMVSNet (Re)		98.38 32	98.67 19	97.51 131	99.51 28	93.39 190	98.20 51	98.87 129	98.23 47	99.48 17	99.27 31	98.47 11	99.55 190	96.52 107	99.53 140	99.60 43

gg-mvs-nofinetune		88.28 384	86.96 390	92.23 381	92.84 426	84.44 373	98.19 52	74.60 435	99.08 14	87.01 425	99.47 13	56.93 423	98.23 393	78.91 416	95.61 399	94.01 417

QAPM		95.88 209	95.57 226	96.80 195	97.90 253	91.84 236	98.18 53	98.73 168	88.41 354	96.42 264	98.13 173	94.73 173	99.75 74	88.72 351	98.94 257	98.81 231

NR-MVSNet		97.96 60	97.86 76	98.26 72	98.73 147	95.54 97	98.14 54	98.73 168	97.79 59	99.42 22	97.83 207	94.40 188	99.78 53	95.91 139	99.76 63	99.46 94

MIMVSNet		93.42 312	92.86 312	95.10 288	98.17 226	88.19 308	98.13 55	93.69 368	92.07 296	95.04 321	98.21 166	80.95 359	99.03 323	81.42 408	98.06 323	98.07 311

PS-MVSNAJss		98.53 24	98.63 21	98.21 80	99.68 11	94.82 131	98.10 56	99.21 44	96.91 101	99.75 3	99.45 15	95.82 133	99.92 6	98.80 27	99.96 4	99.89 4

ACMMP		98.05 54	97.75 93	98.93 22	99.23 63	97.60 26	98.09 57	98.96 112	95.75 166	97.91 169	98.06 186	96.89 80	99.76 68	95.32 177	99.57 123	99.43 109
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
APDe-MVS		98.14 44	98.03 60	98.47 58	98.72 150	96.04 79	98.07 58	99.10 64	95.96 150	98.59 90	98.69 98	96.94 73	99.81 41	96.64 102	99.58 120	99.57 52
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
Vis-MVSNet		98.27 39	98.34 39	98.07 88	99.33 51	95.21 122	98.04 59	99.46 25	97.32 90	97.82 179	99.11 52	96.75 90	99.86 26	97.84 57	99.36 193	99.15 166
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	96.13 3	97.73 94	97.59 111	98.15 83	98.11 236	95.60 95	98.04 59	98.70 177	98.13 50	96.93 232	98.45 126	95.30 157	99.62 163	95.64 154	98.96 254	99.24 153

MVSMamba_PlusPlus		97.43 125	97.98 65	95.78 257	98.88 128	89.70 273	98.03 61	98.85 136	99.18 11	96.84 237	99.12 51	93.04 219	99.91 14	98.38 41	99.55 132	97.73 343

FIs		97.93 70	98.07 55	97.48 139	99.38 46	92.95 200	98.03 61	99.11 61	98.04 55	98.62 86	98.66 100	93.75 204	99.78 53	97.23 79	99.84 42	99.73 25

mamv4		99.05 5	98.91 8	99.46 2	98.94 119	99.62 2	97.98 63	99.70 8	99.49 3	99.78 2	99.22 36	95.92 127	99.95 3	99.31 7	99.83 46	98.83 228

sd_testset		97.97 58	98.12 50	97.51 131	99.41 40	93.44 186	97.96 64	98.25 232	98.58 32	98.78 73	99.39 18	98.21 15	99.56 186	92.65 272	99.86 30	99.52 68

COLMAP_ROB	94.48 6	98.25 41	98.11 52	98.64 47	99.21 73	97.35 39	97.96 64	99.16 51	98.34 40	98.78 73	98.52 118	97.32 46	99.45 222	94.08 237	99.67 92	99.13 172
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
balanced_conf03		96.88 159	97.29 132	95.63 264	97.66 293	89.47 280	97.95 66	98.89 120	95.94 153	97.77 182	98.55 115	92.23 244	99.68 131	97.05 92	99.61 108	97.73 343

VDDNet		96.98 152	96.84 161	97.41 147	99.40 43	93.26 194	97.94 67	95.31 351	99.26 9	98.39 111	99.18 43	87.85 310	99.62 163	95.13 192	99.09 242	99.35 129

CP-MVS		97.92 71	97.56 114	98.99 14	98.99 111	97.82 19	97.93 68	98.96 112	96.11 138	96.89 235	97.45 238	96.85 85	99.78 53	95.19 183	99.63 100	99.38 120

mvsmamba		94.91 256	94.41 278	96.40 224	97.65 295	91.30 246	97.92 69	95.32 350	91.50 310	95.54 308	98.38 136	83.06 347	99.68 131	92.46 277	97.84 332	98.23 297

ANet_high		98.31 36	98.94 6	96.41 222	99.33 51	89.64 276	97.92 69	99.56 22	99.27 8	99.66 10	99.50 11	97.67 32	99.83 34	97.55 71	99.98 2	99.77 15

nrg030		98.54 22	98.62 23	98.32 67	99.22 66	95.66 94	97.90 71	99.08 72	98.31 41	99.02 50	98.74 91	97.68 31	99.61 171	97.77 62	99.85 39	99.70 30

ambc				96.56 211	98.23 216	91.68 240	97.88 72	98.13 253		98.42 106	98.56 114	94.22 192	99.04 320	94.05 240	99.35 198	98.95 205

Anonymous20240529		97.96 60	98.04 59	97.71 115	98.69 157	94.28 156	97.86 73	98.31 229	98.79 26	99.23 36	98.86 83	95.76 139	99.61 171	95.49 161	99.36 193	99.23 154

sasdasda		97.23 138	97.21 139	97.30 154	97.65 295	94.39 147	97.84 74	99.05 80	97.42 80	96.68 246	93.85 376	97.63 36	99.33 264	96.29 118	98.47 304	98.18 303

canonicalmvs		97.23 138	97.21 139	97.30 154	97.65 295	94.39 147	97.84 74	99.05 80	97.42 80	96.68 246	93.85 376	97.63 36	99.33 264	96.29 118	98.47 304	98.18 303

tfpnnormal		97.72 96	97.97 66	96.94 182	99.26 57	92.23 219	97.83 76	98.45 207	98.25 46	99.13 42	98.66 100	96.65 93	99.69 125	93.92 245	99.62 102	98.91 215

MGCFI-Net		97.20 140	97.23 137	97.08 172	97.68 288	93.71 176	97.79 77	99.09 69	97.40 85	96.59 254	93.96 374	97.67 32	99.35 259	96.43 111	98.50 303	98.17 305

Anonymous20240521		97.07 145	97.51 119	95.76 258	99.35 49	88.18 309	97.78 78	98.40 216	97.11 96	98.34 119	99.04 59	89.58 286	99.79 49	98.09 47	99.93 11	99.30 136

XVS		97.96 60	97.63 106	98.94 19	99.15 83	97.66 23	97.77 79	98.83 146	97.42 80	96.32 269	97.64 225	96.49 103	99.72 95	95.66 152	99.37 190	99.45 98

X-MVStestdata		92.86 323	90.83 352	98.94 19	99.15 83	97.66 23	97.77 79	98.83 146	97.42 80	96.32 269	36.50 434	96.49 103	99.72 95	95.66 152	99.37 190	99.45 98

VPA-MVSNet		98.27 39	98.46 30	97.70 117	99.06 100	93.80 172	97.76 81	99.00 101	98.40 38	99.07 48	98.98 66	96.89 80	99.75 74	97.19 84	99.79 57	99.55 60

dcpmvs_2		97.12 143	97.99 64	94.51 319	99.11 92	84.00 378	97.75 82	99.65 13	97.38 87	99.14 41	98.42 130	95.16 162	99.96 2	95.52 160	99.78 61	99.58 45

UGNet		96.81 166	96.56 178	97.58 125	96.64 346	93.84 171	97.75 82	97.12 305	96.47 123	93.62 357	98.88 81	93.22 215	99.53 196	95.61 156	99.69 85	99.36 127
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
mPP-MVS		97.91 74	97.53 117	99.04 8	99.22 66	97.87 18	97.74 84	98.78 160	96.04 145	97.10 215	97.73 220	96.53 100	99.78 53	95.16 187	99.50 154	99.46 94

OpenMVS	94.22 8	95.48 229	95.20 231	96.32 228	97.16 331	91.96 232	97.74 84	98.84 140	87.26 366	94.36 335	98.01 192	93.95 199	99.67 140	90.70 318	98.75 278	97.35 363

RRT-MVS		95.78 213	96.25 195	94.35 325	96.68 345	84.47 372	97.72 86	99.11 61	97.23 93	97.27 202	98.72 92	86.39 320	99.79 49	95.49 161	97.67 344	98.80 232

testf1		98.57 18	98.45 33	98.93 22	99.79 3	98.78 3	97.69 87	99.42 29	97.69 68	98.92 60	98.77 88	97.80 26	99.25 285	96.27 120	99.69 85	98.76 239

APD_test2		98.57 18	98.45 33	98.93 22	99.79 3	98.78 3	97.69 87	99.42 29	97.69 68	98.92 60	98.77 88	97.80 26	99.25 285	96.27 120	99.69 85	98.76 239

MonoMVSNet		93.30 316	93.96 294	91.33 391	94.14 414	81.33 398	97.68 89	96.69 323	95.38 185	96.32 269	98.42 130	84.12 340	96.76 417	90.78 311	92.12 418	95.89 399

MSP-MVS		97.45 121	96.92 158	99.03 9	99.26 57	97.70 22	97.66 90	98.89 120	95.65 169	98.51 95	96.46 309	92.15 246	99.81 41	95.14 190	98.58 297	99.58 45
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
LFMVS		95.32 239	94.88 249	96.62 205	98.03 239	91.47 243	97.65 91	90.72 406	99.11 12	97.89 171	98.31 144	79.20 364	99.48 212	93.91 246	99.12 238	98.93 211

K. test v3		96.44 187	96.28 194	96.95 181	99.41 40	91.53 241	97.65 91	90.31 411	98.89 24	98.93 59	99.36 23	84.57 336	99.92 6	97.81 58	99.56 126	99.39 118

TSAR-MVS + MP.		97.42 127	97.23 137	98.00 97	99.38 46	95.00 127	97.63 93	98.20 239	93.00 277	98.16 140	98.06 186	95.89 128	99.72 95	95.67 151	99.10 241	99.28 143
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_fmvs3		97.38 129	97.56 114	96.84 193	98.63 165	92.81 203	97.60 94	99.61 18	90.87 320	98.76 78	99.66 4	94.03 196	97.90 400	99.24 10	99.68 89	99.81 10

region2R		97.92 71	97.59 111	98.92 25	99.22 66	97.55 30	97.60 94	98.84 140	96.00 148	97.22 204	97.62 227	96.87 84	99.76 68	95.48 165	99.43 179	99.46 94

HFP-MVS		97.94 67	97.64 104	98.83 29	99.15 83	97.50 33	97.59 96	98.84 140	96.05 143	97.49 191	97.54 232	97.07 63	99.70 118	95.61 156	99.46 166	99.30 136

ACMMPR		97.95 64	97.62 108	98.94 19	99.20 75	97.56 29	97.59 96	98.83 146	96.05 143	97.46 196	97.63 226	96.77 89	99.76 68	95.61 156	99.46 166	99.49 83

RPSCF		97.87 80	97.51 119	98.95 18	99.15 83	98.43 7	97.56 98	99.06 76	96.19 135	98.48 100	98.70 97	94.72 174	99.24 289	94.37 226	99.33 206	99.17 163

KD-MVS_self_test		97.86 82	98.07 55	97.25 159	99.22 66	92.81 203	97.55 99	98.94 115	97.10 97	98.85 66	98.88 81	95.03 166	99.67 140	97.39 77	99.65 96	99.26 148

SR-MVS-dyc-post		98.14 44	97.84 77	99.02 10	98.81 134	98.05 10	97.55 99	98.86 132	97.77 60	98.20 134	98.07 181	96.60 98	99.76 68	95.49 161	99.20 225	99.26 148

RE-MVS-def			97.88 75		98.81 134	98.05 10	97.55 99	98.86 132	97.77 60	98.20 134	98.07 181	96.94 73		95.49 161	99.20 225	99.26 148

APD-MVS_3200maxsize		98.13 47	97.90 70	98.79 33	98.79 138	97.31 40	97.55 99	98.92 117	97.72 65	98.25 130	98.13 173	97.10 59	99.75 74	95.44 169	99.24 223	99.32 131

ACMH+	93.58 10	98.23 42	98.31 41	97.98 99	99.39 44	95.22 120	97.55 99	99.20 46	98.21 48	99.25 35	98.51 120	98.21 15	99.40 240	94.79 208	99.72 78	99.32 131

Vis-MVSNet (Re-imp)		95.11 248	94.85 251	95.87 254	99.12 91	89.17 286	97.54 104	94.92 358	96.50 119	96.58 255	97.27 256	83.64 343	99.48 212	88.42 356	99.67 92	98.97 202

MP-MVS		97.64 104	97.18 141	99.00 13	99.32 53	97.77 21	97.49 105	98.73 168	96.27 129	95.59 306	97.75 217	96.30 116	99.78 53	93.70 253	99.48 161	99.45 98
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		97.92 71	97.62 108	98.83 29	99.32 53	97.24 43	97.45 106	98.84 140	95.76 164	96.93 232	97.43 240	97.26 53	99.79 49	96.06 126	99.53 140	99.45 98

tttt0517		93.31 315	92.56 323	95.57 267	98.71 153	87.86 318	97.44 107	87.17 423	95.79 163	97.47 195	96.84 286	64.12 414	99.81 41	96.20 123	99.32 208	99.02 196

v10		97.55 114	97.97 66	96.31 229	98.60 169	89.64 276	97.44 107	99.02 90	96.60 112	98.72 82	99.16 47	93.48 210	99.72 95	98.76 29	99.92 14	99.58 45

v8		97.60 109	98.06 58	96.23 232	98.71 153	89.44 281	97.43 109	98.82 154	97.29 92	98.74 80	99.10 53	93.86 200	99.68 131	98.61 34	99.94 8	99.56 56

PMVS	89.60 17	96.71 174	96.97 153	95.95 249	99.51 28	97.81 20	97.42 110	97.49 292	97.93 56	95.95 289	98.58 110	96.88 82	96.91 413	89.59 339	99.36 193	93.12 422
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SR-MVS		98.00 57	97.66 100	99.01 12	98.77 144	97.93 15	97.38 111	98.83 146	97.32 90	98.06 153	97.85 206	96.65 93	99.77 63	95.00 199	99.11 239	99.32 131

FMVSNet5		93.39 313	92.35 324	96.50 214	95.83 377	90.81 257	97.31 112	98.27 230	92.74 286	96.27 274	98.28 153	62.23 416	99.67 140	90.86 307	99.36 193	99.03 193

HY-MVS	91.43 15	92.58 327	91.81 333	94.90 299	96.49 350	88.87 295	97.31 112	94.62 360	85.92 381	90.50 402	96.84 286	85.05 331	99.40 240	83.77 400	95.78 396	96.43 393

CSCG		97.40 128	97.30 131	97.69 119	98.95 116	94.83 130	97.28 114	98.99 105	96.35 128	98.13 144	95.95 335	95.99 125	99.66 146	94.36 228	99.73 73	98.59 258

MTAPA		98.14 44	97.84 77	99.06 7	99.44 36	97.90 16	97.25 115	98.73 168	97.69 68	97.90 170	97.96 196	95.81 137	99.82 36	96.13 125	99.61 108	99.45 98

CPTT-MVS		96.69 175	96.08 203	98.49 56	98.89 127	96.64 59	97.25 115	98.77 161	92.89 283	96.01 288	97.13 264	92.23 244	99.67 140	92.24 279	99.34 201	99.17 163

EU-MVSNet		94.25 285	94.47 274	93.60 343	98.14 232	82.60 388	97.24 117	92.72 382	85.08 390	98.48 100	98.94 72	82.59 351	98.76 348	97.47 75	99.53 140	99.44 108

XXY-MVS		97.54 115	97.70 94	97.07 173	99.46 34	92.21 220	97.22 118	99.00 101	94.93 206	98.58 91	98.92 75	97.31 47	99.41 238	94.44 221	99.43 179	99.59 44

APD_test1		97.95 64	97.68 98	98.75 35	99.60 16	98.60 6	97.21 119	99.08 72	96.57 117	98.07 152	98.38 136	96.22 121	99.14 303	94.71 215	99.31 211	98.52 265

GST-MVS		97.82 87	97.49 123	98.81 31	99.23 63	97.25 42	97.16 120	98.79 156	95.96 150	97.53 187	97.40 242	96.93 75	99.77 63	95.04 196	99.35 198	99.42 110

SteuartSystems-ACMMP		98.02 56	97.76 91	98.79 33	99.43 37	97.21 45	97.15 121	98.90 119	96.58 114	98.08 150	97.87 205	97.02 68	99.76 68	95.25 180	99.59 117	99.40 113
Skip Steuart: Steuart Systems R&D Blog.
FMVSNet2		96.72 172	96.67 171	96.87 190	97.96 248	91.88 234	97.15 121	98.06 262	95.59 173	98.50 97	98.62 106	89.51 290	99.65 148	94.99 201	99.60 114	99.07 188

AllTest		97.20 140	96.92 158	98.06 90	99.08 96	96.16 74	97.14 123	99.16 51	94.35 227	97.78 180	98.07 181	95.84 130	99.12 307	91.41 293	99.42 182	98.91 215

DP-MVS		97.87 80	97.89 73	97.81 108	98.62 167	94.82 131	97.13 124	98.79 156	98.98 21	98.74 80	98.49 121	95.80 138	99.49 209	95.04 196	99.44 170	99.11 181

GeoE		97.75 93	97.70 94	97.89 103	98.88 128	94.53 142	97.10 125	98.98 108	95.75 166	97.62 184	97.59 229	97.61 38	99.77 63	96.34 116	99.44 170	99.36 127

PGM-MVS		97.88 78	97.52 118	98.96 17	99.20 75	97.62 25	97.09 126	99.06 76	95.45 180	97.55 186	97.94 199	97.11 58	99.78 53	94.77 211	99.46 166	99.48 89

LPG-MVS_test		97.94 67	97.67 99	98.74 38	99.15 83	97.02 46	97.09 126	99.02 90	95.15 194	98.34 119	98.23 162	97.91 22	99.70 118	94.41 223	99.73 73	99.50 75

SF-MVS		97.60 109	97.39 126	98.22 77	98.93 121	95.69 91	97.05 128	99.10 64	95.32 187	97.83 178	97.88 204	96.44 108	99.72 95	94.59 220	99.39 188	99.25 152

reproduce_model		98.54 22	98.33 40	99.15 4	99.06 100	98.04 12	97.04 129	99.09 69	98.42 37	99.03 49	98.71 95	96.93 75	99.83 34	97.09 88	99.63 100	99.56 56

VDD-MVS		97.37 131	97.25 135	97.74 113	98.69 157	94.50 145	97.04 129	95.61 343	98.59 31	98.51 95	98.72 92	92.54 237	99.58 178	96.02 131	99.49 157	99.12 177

wuyk23d		93.25 318	95.20 231	87.40 412	96.07 368	95.38 107	97.04 129	94.97 356	95.33 186	99.70 7	98.11 177	98.14 18	91.94 430	77.76 420	99.68 89	74.89 430

LCM-MVSNet-Re		97.33 134	97.33 130	97.32 153	98.13 235	93.79 173	96.99 132	99.65 13	96.74 107	99.47 19	98.93 73	96.91 79	99.84 32	90.11 330	99.06 248	98.32 286

MAR-MVS		94.21 288	93.03 308	97.76 112	96.94 340	97.44 37	96.97 133	97.15 303	87.89 363	92.00 391	92.73 393	92.14 247	99.12 307	83.92 397	97.51 352	96.73 385
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
test_vis1_n		95.67 220	95.89 214	95.03 291	98.18 223	89.89 269	96.94 134	99.28 38	88.25 358	98.20 134	98.92 75	86.69 319	97.19 408	97.70 67	98.82 272	98.00 323

SDMVSNet		97.97 58	98.26 47	97.11 167	99.41 40	92.21 220	96.92 135	98.60 193	98.58 32	98.78 73	99.39 18	97.80 26	99.62 163	94.98 202	99.86 30	99.52 68

h-mvs33		96.29 192	95.63 224	98.26 72	98.50 186	96.11 77	96.90 136	97.09 306	96.58 114	97.21 206	98.19 167	84.14 338	99.78 53	95.89 140	96.17 390	98.89 219

test0726					99.24 61	95.51 99	96.89 137	98.89 120	95.92 155	98.64 84	98.31 144	97.06 64

baseline		97.44 123	97.78 89	96.43 219	98.52 181	90.75 258	96.84 138	99.03 88	96.51 118	97.86 176	98.02 190	96.67 92	99.36 255	97.09 88	99.47 163	99.19 160

API-MVS		95.09 250	95.01 241	95.31 279	96.61 347	94.02 164	96.83 139	97.18 302	95.60 172	95.79 297	94.33 370	94.54 184	98.37 386	85.70 382	98.52 299	93.52 419

test_vis3_rt		97.04 146	96.98 152	97.23 161	98.44 194	95.88 84	96.82 140	99.67 10	90.30 329	99.27 33	99.33 28	94.04 195	96.03 421	97.14 86	97.83 333	99.78 14

reproduce-ours		98.48 26	98.27 45	99.12 5	98.99 111	98.02 13	96.81 141	99.02 90	98.29 44	98.97 57	98.61 107	97.27 49	99.82 36	96.86 99	99.61 108	99.51 72

our_new_method		98.48 26	98.27 45	99.12 5	98.99 111	98.02 13	96.81 141	99.02 90	98.29 44	98.97 57	98.61 107	97.27 49	99.82 36	96.86 99	99.61 108	99.51 72

test_fmvs1_n		95.21 243	95.28 229	94.99 294	98.15 230	89.13 289	96.81 141	99.43 28	86.97 372	97.21 206	98.92 75	83.00 348	97.13 409	98.09 47	98.94 257	98.72 244

test_fmvs2		96.38 190	96.45 187	96.16 239	97.85 255	91.30 246	96.81 141	99.45 26	89.24 342	98.49 98	99.38 20	88.68 297	97.62 405	98.83 26	99.32 208	99.57 52

SED-MVS		97.94 67	97.90 70	98.07 88	99.22 66	95.35 110	96.79 145	98.83 146	96.11 138	99.08 46	98.24 160	97.87 24	99.72 95	95.44 169	99.51 150	99.14 170

OPU-MVS				97.64 122	98.01 242	95.27 115	96.79 145				97.35 251	96.97 71	98.51 374	91.21 299	99.25 220	99.14 170

BP-MVS1		95.36 235	94.86 250	96.89 188	98.35 202	91.72 238	96.76 147	95.21 352	96.48 122	96.23 277	97.19 261	75.97 384	99.80 48	97.91 53	99.60 114	99.15 166

PHI-MVS		96.96 153	96.53 183	98.25 75	97.48 309	96.50 63	96.76 147	98.85 136	93.52 254	96.19 281	96.85 285	95.94 126	99.42 229	93.79 249	99.43 179	98.83 228

DVP-MVS		97.78 91	97.65 101	98.16 81	99.24 61	95.51 99	96.74 149	98.23 235	95.92 155	98.40 109	98.28 153	97.06 64	99.71 109	95.48 165	99.52 145	99.26 148
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				98.25 75	99.23 63	95.49 103	96.74 149	98.89 120					99.75 74	95.48 165	99.52 145	99.53 65

Anonymous202405211		96.34 191	95.98 208	97.43 144	98.25 213	93.85 170	96.74 149	94.41 363	97.72 65	98.37 112	98.03 189	87.15 315	99.53 196	94.06 238	99.07 245	98.92 214

SMA-MVS		97.48 119	97.11 143	98.60 49	98.83 133	96.67 57	96.74 149	98.73 168	91.61 307	98.48 100	98.36 138	96.53 100	99.68 131	95.17 185	99.54 136	99.45 98
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
TranMVSNet+NR-MVSNet		98.33 33	98.30 43	98.43 60	99.07 98	95.87 85	96.73 153	99.05 80	98.67 28	98.84 68	98.45 126	97.58 39	99.88 21	96.45 110	99.86 30	99.54 62

test_0402		97.84 83	97.97 66	97.47 140	99.19 77	94.07 161	96.71 154	98.73 168	98.66 29	98.56 92	98.41 132	96.84 86	99.69 125	94.82 206	99.81 51	98.64 252

test_fmvsmconf0.01_n		98.57 18	98.74 17	98.06 90	99.39 44	94.63 138	96.70 155	99.82 1	95.44 182	99.64 11	99.52 9	98.96 4	99.74 83	99.38 5	99.86 30	99.81 10

SSC-MVS		95.92 207	97.03 150	92.58 373	99.28 55	78.39 410	96.68 156	95.12 354	98.90 23	99.11 43	98.66 100	91.36 261	99.68 131	95.00 199	99.16 231	99.67 33

ACMM	93.33 11	98.05 54	97.79 85	98.85 28	99.15 83	97.55 30	96.68 156	98.83 146	95.21 190	98.36 115	98.13 173	98.13 19	99.62 163	96.04 129	99.54 136	99.39 118
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		93.14 320	92.64 321	94.62 312	97.34 322	87.20 333	96.67 158	93.02 377	94.71 212	96.51 261	95.83 338	81.64 352	98.60 367	90.00 333	88.06 426	98.07 311

fmvsm_s_conf0.1_n_a		97.80 89	98.01 62	97.18 162	99.17 79	92.51 211	96.57 159	99.15 55	93.68 249	98.89 63	99.30 29	96.42 110	99.37 252	99.03 21	99.83 46	99.66 35

MTMP							96.55 160	74.60 435

SD-MVS		97.37 131	97.70 94	96.35 226	98.14 232	95.13 124	96.54 161	98.92 117	95.94 153	99.19 38	98.08 179	97.74 29	95.06 424	95.24 181	99.54 136	98.87 225
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
HQP_MVS		96.66 177	96.33 193	97.68 120	98.70 155	94.29 153	96.50 162	98.75 165	96.36 126	96.16 282	96.77 292	91.91 256	99.46 217	92.59 274	99.20 225	99.28 143

plane_prior2							96.50 162		96.36 126

GDP-MVS		95.39 234	94.89 247	96.90 187	98.26 212	91.91 233	96.48 164	99.28 38	95.06 199	96.54 260	97.12 266	74.83 388	99.82 36	97.19 84	99.27 217	98.96 203

Effi-MVS+-dtu		96.81 166	96.09 202	98.99 14	96.90 342	98.69 5	96.42 165	98.09 256	95.86 160	95.15 316	95.54 346	94.26 191	99.81 41	94.06 238	98.51 302	98.47 271

MM		96.87 160	96.62 172	97.62 123	97.72 285	93.30 191	96.39 166	92.61 385	97.90 58	96.76 243	98.64 105	90.46 273	99.81 41	99.16 14	99.94 8	99.76 20

thres100view900		91.76 345	91.26 345	93.26 350	98.21 217	84.50 371	96.39 166	90.39 408	96.87 102	96.33 268	93.08 384	73.44 398	99.42 229	78.85 417	97.74 337	95.85 400

XVG-ACMP-BASELINE		97.58 113	97.28 134	98.49 56	99.16 80	96.90 50	96.39 166	98.98 108	95.05 200	98.06 153	98.02 190	95.86 129	99.56 186	94.37 226	99.64 98	99.00 197

Patchmtry		95.03 253	94.59 268	96.33 227	94.83 403	90.82 255	96.38 169	97.20 300	96.59 113	97.49 191	98.57 112	77.67 371	99.38 247	92.95 271	99.62 102	98.80 232

fmvsm_s_conf0.1_n		97.73 94	98.02 61	96.85 191	99.09 95	91.43 245	96.37 170	99.11 61	94.19 232	99.01 51	99.25 32	96.30 116	99.38 247	99.00 22	99.88 25	99.73 25

ACMMP_NAP		97.89 77	97.63 106	98.67 44	99.35 49	96.84 51	96.36 171	98.79 156	95.07 198	97.88 172	98.35 139	97.24 55	99.72 95	96.05 128	99.58 120	99.45 98

VNet		96.84 161	96.83 162	96.88 189	98.06 238	92.02 230	96.35 172	97.57 291	97.70 67	97.88 172	97.80 213	92.40 242	99.54 193	94.73 213	98.96 254	99.08 186

V42		97.04 146	97.16 142	96.68 204	98.59 171	91.05 250	96.33 173	98.36 221	94.60 216	97.99 159	98.30 148	93.32 212	99.62 163	97.40 76	99.53 140	99.38 120

test_fmvsmvis_n_1920		98.08 50	98.47 29	96.93 183	99.03 108	93.29 192	96.32 174	99.65 13	95.59 173	99.71 5	99.01 62	97.66 34	99.60 173	99.44 3	99.83 46	97.90 329

APD-MVS		97.00 148	96.53 183	98.41 61	98.55 177	96.31 70	96.32 174	98.77 161	92.96 282	97.44 197	97.58 231	95.84 130	99.74 83	91.96 282	99.35 198	99.19 160
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPNet		97.26 137	97.49 123	96.59 207	99.47 33	90.58 260	96.27 176	98.53 200	97.77 60	98.46 103	98.41 132	94.59 180	99.68 131	94.61 216	99.29 214	99.52 68

thres600view7		92.03 340	91.43 338	93.82 337	98.19 220	84.61 370	96.27 176	90.39 408	96.81 104	96.37 267	93.11 380	73.44 398	99.49 209	80.32 412	97.95 327	97.36 361

EPNet		93.72 303	92.62 322	97.03 178	87.61 437	92.25 218	96.27 176	91.28 399	96.74 107	87.65 422	97.39 246	85.00 332	99.64 154	92.14 280	99.48 161	99.20 159
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DSMNet-mixed		92.19 334	91.83 332	93.25 351	96.18 361	83.68 381	96.27 176	93.68 370	76.97 426	92.54 387	99.18 43	89.20 295	98.55 371	83.88 398	98.60 296	97.51 356

fmvsm_s_conf0.5_n_a		97.65 103	97.83 80	97.13 166	98.80 136	92.51 211	96.25 180	99.06 76	93.67 250	98.64 84	99.00 63	96.23 120	99.36 255	98.99 23	99.80 55	99.53 65

ACMP	92.54 13	97.47 120	97.10 144	98.55 53	99.04 107	96.70 55	96.24 181	98.89 120	93.71 246	97.97 163	97.75 217	97.44 41	99.63 158	93.22 265	99.70 84	99.32 131
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS	95.41 4	97.82 87	97.70 94	98.16 81	98.78 142	95.72 89	96.23 182	99.02 90	93.92 242	98.62 86	98.99 65	97.69 30	99.62 163	96.18 124	99.87 28	99.15 166
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PM-MVS		97.36 133	97.10 144	98.14 84	98.91 125	96.77 53	96.20 183	98.63 191	93.82 243	98.54 93	98.33 142	93.98 197	99.05 318	95.99 134	99.45 169	98.61 257

test_fmvsmconf0.1_n		98.41 31	98.54 27	98.03 95	99.16 80	94.61 139	96.18 184	99.73 5	95.05 200	99.60 15	99.34 26	98.68 8	99.72 95	99.21 11	99.85 39	99.76 20

MVS_Test		96.27 193	96.79 166	94.73 309	96.94 340	86.63 342	96.18 184	98.33 225	94.94 204	96.07 285	98.28 153	95.25 158	99.26 283	97.21 81	97.90 330	98.30 290

CR-MVSNet		93.29 317	92.79 315	94.78 307	95.44 390	88.15 310	96.18 184	97.20 300	84.94 395	94.10 341	98.57 112	77.67 371	99.39 244	95.17 185	95.81 393	96.81 382

RPMNet		94.68 270	94.60 266	94.90 299	95.44 390	88.15 310	96.18 184	98.86 132	97.43 79	94.10 341	98.49 121	79.40 363	99.76 68	95.69 149	95.81 393	96.81 382

test_fmvsm_n_1920		98.08 50	98.29 44	97.43 144	98.88 128	93.95 167	96.17 188	99.57 20	95.66 168	99.52 16	98.71 95	97.04 66	99.64 154	99.21 11	99.87 28	98.69 248

fmvsm_s_conf0.5_n		97.62 107	97.89 73	96.80 195	98.79 138	91.44 244	96.14 189	99.06 76	94.19 232	98.82 70	98.98 66	96.22 121	99.38 247	98.98 24	99.86 30	99.58 45

WB-MVS		95.50 226	96.62 172	92.11 383	99.21 73	77.26 420	96.12 190	95.40 349	98.62 30	98.84 68	98.26 158	91.08 264	99.50 204	93.37 258	98.70 285	99.58 45

EIA-MVS		96.04 202	95.77 219	96.85 191	97.80 268	92.98 199	96.12 190	99.16 51	94.65 214	93.77 352	91.69 406	95.68 141	99.67 140	94.18 233	98.85 268	97.91 328

Effi-MVS+		96.19 196	96.01 205	96.71 201	97.43 315	92.19 224	96.12 190	99.10 64	95.45 180	93.33 369	94.71 362	97.23 56	99.56 186	93.21 266	97.54 350	98.37 279

alignmvs		96.01 204	95.52 227	97.50 135	97.77 277	94.71 133	96.07 193	96.84 315	97.48 78	96.78 242	94.28 371	85.50 329	99.40 240	96.22 122	98.73 282	98.40 275

fmvsm_l_conf0.5_n_3		98.29 38	98.46 30	97.79 109	98.90 126	94.05 163	96.06 194	99.63 17	96.07 141	99.37 26	98.93 73	98.29 13	99.68 131	99.11 18	99.79 57	99.65 38

PatchT		93.75 302	93.57 300	94.29 329	95.05 399	87.32 331	96.05 195	92.98 378	97.54 75	94.25 336	98.72 92	75.79 385	99.24 289	95.92 138	95.81 393	96.32 394

Patchmatch-test		93.60 308	93.25 305	94.63 311	96.14 366	87.47 327	96.04 196	94.50 362	93.57 251	96.47 262	96.97 277	76.50 379	98.61 365	90.67 320	98.41 309	97.81 337

thisisatest0530		92.71 326	91.76 335	95.56 269	98.42 197	88.23 307	96.03 197	87.35 422	94.04 239	96.56 257	95.47 348	64.03 415	99.77 63	94.78 210	99.11 239	98.68 251

9.14			96.69 169		98.53 180		96.02 198	98.98 108	93.23 264	97.18 209	97.46 237	96.47 105	99.62 163	92.99 269	99.32 208

DeepC-MVS_fast	94.34 7	96.74 169	96.51 185	97.44 143	97.69 287	94.15 159	96.02 198	98.43 210	93.17 272	97.30 200	97.38 248	95.48 149	99.28 279	93.74 250	99.34 201	98.88 223
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ttmdpeth		94.05 295	94.15 287	93.75 339	95.81 379	85.32 356	96.00 200	94.93 357	92.07 296	94.19 338	99.09 55	85.73 326	96.41 420	90.98 303	98.52 299	99.53 65

test_fmvsmconf_n		98.30 37	98.41 36	97.99 98	98.94 119	94.60 140	96.00 200	99.64 16	94.99 203	99.43 21	99.18 43	98.51 10	99.71 109	99.13 16	99.84 42	99.67 33

114514_t		93.96 298	93.22 306	96.19 236	99.06 100	90.97 253	95.99 202	98.94 115	73.88 429	93.43 366	96.93 280	92.38 243	99.37 252	89.09 346	99.28 215	98.25 296

FMVSNet3		95.26 242	94.94 242	96.22 234	96.53 349	90.06 265	95.99 202	97.66 283	94.11 236	97.99 159	97.91 203	80.22 362	99.63 158	94.60 217	99.44 170	98.96 203

HPM-MVS++		96.99 149	96.38 190	98.81 31	98.64 161	97.59 27	95.97 204	98.20 239	95.51 177	95.06 318	96.53 305	94.10 194	99.70 118	94.29 229	99.15 232	99.13 172

casdiffmvs_mvg		97.83 84	98.11 52	97.00 180	98.57 174	92.10 228	95.97 204	99.18 49	97.67 71	99.00 53	98.48 125	97.64 35	99.50 204	96.96 95	99.54 136	99.40 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
testgi		96.07 200	96.50 186	94.80 305	99.26 57	87.69 324	95.96 206	98.58 197	95.08 197	98.02 158	96.25 320	97.92 21	97.60 406	88.68 353	98.74 279	99.11 181

EG-PatchMatch MVS		97.69 98	97.79 85	97.40 148	99.06 100	93.52 184	95.96 206	98.97 111	94.55 220	98.82 70	98.76 90	97.31 47	99.29 277	97.20 83	99.44 170	99.38 120

fmvsm_s_conf0.5_n_3		97.88 78	98.37 37	96.41 222	98.73 147	89.82 271	95.94 208	99.49 24	96.81 104	99.09 45	99.03 61	97.09 61	99.65 148	99.37 6	99.76 63	99.76 20

PAPM_NR		94.61 274	94.17 286	95.96 247	98.36 201	91.23 248	95.93 209	97.95 264	92.98 278	93.42 367	94.43 369	90.53 271	98.38 384	87.60 366	96.29 387	98.27 294

UniMVSNet (Re)		97.83 84	97.65 101	98.35 66	98.80 136	95.86 86	95.92 210	99.04 87	97.51 76	98.22 133	97.81 212	94.68 177	99.78 53	97.14 86	99.75 71	99.41 112

test_vis1_n_1920		95.77 214	96.41 189	93.85 336	98.55 177	84.86 367	95.91 211	99.71 7	92.72 287	97.67 183	98.90 79	87.44 313	98.73 350	97.96 51	98.85 268	97.96 325

fmvsm_l_conf0.5_n		97.68 100	97.81 83	97.27 156	98.92 123	92.71 208	95.89 212	99.41 32	93.36 259	99.00 53	98.44 128	96.46 107	99.65 148	99.09 19	99.76 63	99.45 98

1314		92.38 330	92.30 325	92.64 372	95.42 392	85.15 361	95.86 213	96.97 312	85.40 388	90.62 399	93.06 385	91.12 263	97.80 403	86.74 377	95.49 401	94.97 412

MVS		90.02 362	89.20 369	92.47 376	94.71 404	86.90 338	95.86 213	96.74 321	64.72 431	90.62 399	92.77 391	92.54 237	98.39 383	79.30 415	95.56 400	92.12 423

fmvsm_l_conf0.5_n_a		97.60 109	97.76 91	97.11 167	98.92 123	92.28 217	95.83 215	99.32 34	93.22 265	98.91 62	98.49 121	96.31 115	99.64 154	99.07 20	99.76 63	99.40 113

casdiffmvs		97.50 117	97.81 83	96.56 211	98.51 183	91.04 251	95.83 215	99.09 69	97.23 93	98.33 122	98.30 148	97.03 67	99.37 252	96.58 106	99.38 189	99.28 143
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVStest1		91.89 342	91.45 337	93.21 354	89.01 434	84.87 366	95.82 217	95.05 355	91.50 310	98.75 79	99.19 39	57.56 421	95.11 423	97.78 61	98.37 310	99.64 41

tpmvs		90.79 357	90.87 350	90.57 396	92.75 427	76.30 422	95.79 218	93.64 372	91.04 319	91.91 392	96.26 319	77.19 377	98.86 340	89.38 343	89.85 423	96.56 389

fmvsm_s_conf0.5_n_6		97.45 121	97.79 85	96.44 217	98.58 173	90.31 264	95.77 219	99.33 33	94.52 221	98.85 66	98.44 128	95.68 141	99.62 163	99.15 15	99.81 51	99.38 120

fmvsm_s_conf0.5_n_8		97.66 102	98.12 50	96.27 231	98.79 138	89.43 282	95.76 220	99.42 29	97.49 77	99.16 40	99.04 59	94.56 183	99.69 125	99.18 13	99.73 73	99.70 30

mvsany_test3		96.21 195	95.93 212	97.05 174	97.40 317	94.33 152	95.76 220	94.20 365	89.10 343	99.36 28	99.60 8	93.97 198	97.85 401	95.40 176	98.63 292	98.99 200

MSLP-MVS++		96.42 189	96.71 168	95.57 267	97.82 263	90.56 262	95.71 222	98.84 140	94.72 211	96.71 245	97.39 246	94.91 172	98.10 397	95.28 178	99.02 250	98.05 318

tfpn200view9		91.55 347	91.00 347	93.21 354	98.02 240	84.35 374	95.70 223	90.79 404	96.26 130	95.90 294	92.13 401	73.62 395	99.42 229	78.85 417	97.74 337	95.85 400

Anonymous20231206		95.27 241	95.06 240	95.88 253	98.72 150	89.37 283	95.70 223	97.85 270	88.00 361	96.98 229	97.62 227	91.95 253	99.34 262	89.21 344	99.53 140	98.94 207

thres400		91.68 346	91.00 347	93.71 341	98.02 240	84.35 374	95.70 223	90.79 404	96.26 130	95.90 294	92.13 401	73.62 395	99.42 229	78.85 417	97.74 337	97.36 361

reproduce_monomvs		92.05 339	92.26 326	91.43 389	95.42 392	75.72 425	95.68 226	97.05 309	94.47 223	97.95 166	98.35 139	55.58 430	99.05 318	96.36 114	99.44 170	99.51 72

test20.03		96.58 181	96.61 174	96.48 216	98.49 187	91.72 238	95.68 226	97.69 280	96.81 104	98.27 129	97.92 202	94.18 193	98.71 353	90.78 311	99.66 95	99.00 197

hse-mvs2		95.77 214	95.09 237	97.79 109	97.84 260	95.51 99	95.66 228	95.43 348	96.58 114	97.21 206	96.16 323	84.14 338	99.54 193	95.89 140	96.92 365	98.32 286

UniMVSNet_NR-MVSNet		97.83 84	97.65 101	98.37 64	98.72 150	95.78 87	95.66 228	99.02 90	98.11 51	98.31 125	97.69 223	94.65 179	99.85 29	97.02 93	99.71 81	99.48 89

fmvsm_s_conf0.5_n_4		97.43 125	97.77 90	96.39 225	98.48 189	89.89 269	95.65 230	99.26 40	94.73 210	98.72 82	98.58 110	95.58 147	99.57 184	99.28 8	99.67 92	99.73 25

dmvs_re		92.08 338	91.27 343	94.51 319	97.16 331	92.79 206	95.65 230	92.64 384	94.11 236	92.74 380	90.98 413	83.41 345	94.44 428	80.72 411	94.07 411	96.29 395

DU-MVS		97.79 90	97.60 110	98.36 65	98.73 147	95.78 87	95.65 230	98.87 129	97.57 72	98.31 125	97.83 207	94.69 175	99.85 29	97.02 93	99.71 81	99.46 94

EPMVS		89.26 373	88.55 375	91.39 390	92.36 428	79.11 409	95.65 230	79.86 432	88.60 352	93.12 372	96.53 305	70.73 406	98.10 397	90.75 313	89.32 424	96.98 371

MVP-Stereo		95.69 218	95.28 229	96.92 184	98.15 230	93.03 198	95.64 234	98.20 239	90.39 328	96.63 252	97.73 220	91.63 258	99.10 313	91.84 287	97.31 360	98.63 254
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
fmvsm_s_conf0.5_n_5		97.63 106	97.83 80	97.04 176	98.77 144	92.33 215	95.63 235	99.58 19	93.53 253	99.10 44	98.66 100	96.44 108	99.65 148	99.12 17	99.68 89	99.12 177

test_cas_vis1_n_1920		95.34 237	95.67 221	94.35 325	98.21 217	86.83 340	95.61 236	99.26 40	90.45 327	98.17 139	98.96 69	84.43 337	98.31 389	96.74 101	99.17 230	97.90 329

test_f		95.82 212	95.88 215	95.66 263	97.61 300	93.21 196	95.61 236	98.17 245	86.98 371	98.42 106	99.47 13	90.46 273	94.74 426	97.71 65	98.45 306	99.03 193

F-COLMAP		95.30 240	94.38 279	98.05 94	98.64 161	96.04 79	95.61 236	98.66 185	89.00 346	93.22 370	96.40 314	92.90 224	99.35 259	87.45 371	97.53 351	98.77 238

AUN-MVS		93.95 300	92.69 319	97.74 113	97.80 268	95.38 107	95.57 239	95.46 347	91.26 316	92.64 384	96.10 329	74.67 389	99.55 190	93.72 252	96.97 364	98.30 290

fmvsm_s_conf0.1_n_2		97.68 100	98.18 48	96.20 235	99.06 100	89.08 291	95.51 240	99.72 6	96.06 142	99.48 17	99.24 33	95.18 160	99.60 173	99.45 2	99.88 25	99.94 3

v144192		96.69 175	96.90 160	96.03 244	98.25 213	88.92 293	95.49 241	98.77 161	93.05 275	98.09 148	98.29 152	92.51 240	99.70 118	98.11 46	99.56 126	99.47 92

Fast-Effi-MVS+-dtu		96.44 187	96.12 200	97.39 149	97.18 330	94.39 147	95.46 242	98.73 168	96.03 147	94.72 326	94.92 359	96.28 119	99.69 125	93.81 248	97.98 325	98.09 308

Baseline_NR-MVSNet		97.72 96	97.79 85	97.50 135	99.56 20	93.29 192	95.44 243	98.86 132	98.20 49	98.37 112	99.24 33	94.69 175	99.55 190	95.98 135	99.79 57	99.65 38

LF4IMVS		96.07 200	95.63 224	97.36 150	98.19 220	95.55 96	95.44 243	98.82 154	92.29 295	95.70 303	96.55 303	92.63 232	98.69 356	91.75 291	99.33 206	97.85 333

v1921920		96.72 172	96.96 155	95.99 245	98.21 217	88.79 298	95.42 245	98.79 156	93.22 265	98.19 138	98.26 158	92.68 229	99.70 118	98.34 43	99.55 132	99.49 83

plane_prior						94.29 153	95.42 245		94.31 229						98.93 259

v1144		96.84 161	97.08 146	96.13 241	98.42 197	89.28 285	95.41 247	98.67 183	94.21 230	97.97 163	98.31 144	93.06 218	99.65 148	98.06 49	99.62 102	99.45 98

ETV-MVS		96.13 199	95.90 213	96.82 194	97.76 278	93.89 168	95.40 248	98.95 114	95.87 159	95.58 307	91.00 412	96.36 114	99.72 95	93.36 259	98.83 271	96.85 378

v1240		96.74 169	97.02 151	95.91 252	98.18 223	88.52 301	95.39 249	98.88 127	93.15 273	98.46 103	98.40 135	92.80 226	99.71 109	98.45 39	99.49 157	99.49 83

MP-MVS-pluss		97.69 98	97.36 128	98.70 42	99.50 31	96.84 51	95.38 250	98.99 105	92.45 292	98.11 145	98.31 144	97.25 54	99.77 63	96.60 104	99.62 102	99.48 89
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MVS_0304		95.71 217	95.18 233	97.33 152	94.85 401	92.82 201	95.36 251	90.89 403	95.51 177	95.61 305	97.82 210	88.39 301	99.78 53	98.23 44	99.91 17	99.40 113

v1192		96.83 164	97.06 148	96.15 240	98.28 208	89.29 284	95.36 251	98.77 161	93.73 245	98.11 145	98.34 141	93.02 223	99.67 140	98.35 42	99.58 120	99.50 75

v2v482		96.78 168	97.06 148	95.95 249	98.57 174	88.77 299	95.36 251	98.26 231	95.18 193	97.85 177	98.23 162	92.58 233	99.63 158	97.80 59	99.69 85	99.45 98

test_fmvs1		94.51 279	94.60 266	94.26 330	95.91 371	87.92 316	95.35 254	99.02 90	86.56 376	96.79 238	98.52 118	82.64 350	97.00 412	97.87 55	98.71 283	97.88 331

EI-MVSNet-Vis-set		97.32 135	97.39 126	97.11 167	97.36 319	92.08 229	95.34 255	97.65 285	97.74 63	98.29 128	98.11 177	95.05 164	99.68 131	97.50 73	99.50 154	99.56 56

fmvsm_s_conf0.5_n_2		97.59 112	98.07 55	96.17 238	98.78 142	89.10 290	95.33 256	99.55 23	95.96 150	99.41 24	99.10 53	95.18 160	99.59 175	99.43 4	99.86 30	99.81 10

EI-MVSNet-UG-set		97.32 135	97.40 125	97.09 171	97.34 322	92.01 231	95.33 256	97.65 285	97.74 63	98.30 127	98.14 171	95.04 165	99.69 125	97.55 71	99.52 145	99.58 45

CostFormer		89.75 368	89.25 366	91.26 392	94.69 405	78.00 414	95.32 258	91.98 391	81.50 409	90.55 401	96.96 279	71.06 404	98.89 336	88.59 354	92.63 416	96.87 376

PVSNet_Blended_VisFu		95.95 206	95.80 217	96.42 220	99.28 55	90.62 259	95.31 259	99.08 72	88.40 355	96.97 230	98.17 170	92.11 248	99.78 53	93.64 254	99.21 224	98.86 226

UnsupCasMVSNet_eth		95.91 208	95.73 220	96.44 217	98.48 189	91.52 242	95.31 259	98.45 207	95.76 164	97.48 193	97.54 232	89.53 289	98.69 356	94.43 222	94.61 408	99.13 172

EI-MVSNet		96.63 178	96.93 156	95.74 259	97.26 327	88.13 312	95.29 261	97.65 285	96.99 98	97.94 167	98.19 167	92.55 235	99.58 178	96.91 96	99.56 126	99.50 75

CVMVSNet		92.33 332	92.79 315	90.95 393	97.26 327	75.84 424	95.29 261	92.33 388	81.86 406	96.27 274	98.19 167	81.44 354	98.46 379	94.23 232	98.29 314	98.55 262

OPM-MVS		97.54 115	97.25 135	98.41 61	99.11 92	96.61 60	95.24 263	98.46 206	94.58 219	98.10 147	98.07 181	97.09 61	99.39 244	95.16 187	99.44 170	99.21 156
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TAPA-MVS	93.32 12	94.93 255	94.23 282	97.04 176	98.18 223	94.51 143	95.22 264	98.73 168	81.22 411	96.25 276	95.95 335	93.80 203	98.98 328	89.89 335	98.87 265	97.62 350
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPE-MVS		97.64 104	97.35 129	98.50 55	98.85 132	96.18 73	95.21 265	98.99 105	95.84 161	98.78 73	98.08 179	96.84 86	99.81 41	93.98 243	99.57 123	99.52 68
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MVSTER		94.21 288	93.93 295	95.05 290	95.83 377	86.46 343	95.18 266	97.65 285	92.41 293	97.94 167	98.00 194	72.39 400	99.58 178	96.36 114	99.56 126	99.12 177

testing3-2		90.09 361	90.38 360	89.24 403	98.07 237	69.88 436	95.12 267	90.71 407	96.65 109	93.60 360	94.03 373	55.81 429	99.33 264	90.69 319	98.71 283	98.51 266

PatchmatchNet		91.98 341	91.87 331	92.30 379	94.60 406	79.71 406	95.12 267	93.59 373	89.52 339	93.61 358	97.02 273	77.94 369	99.18 296	90.84 308	94.57 410	98.01 322
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
IterMVS-LS		96.92 155	97.29 132	95.79 256	98.51 183	88.13 312	95.10 269	98.66 185	96.99 98	98.46 103	98.68 99	92.55 235	99.74 83	96.91 96	99.79 57	99.50 75
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v148		96.58 181	96.97 153	95.42 276	98.63 165	87.57 325	95.09 270	97.90 267	95.91 157	98.24 131	97.96 196	93.42 211	99.39 244	96.04 129	99.52 145	99.29 142

tpm2		88.47 380	87.69 384	90.79 394	94.98 400	77.34 418	95.09 270	91.83 392	77.51 425	89.40 414	96.41 312	67.83 411	98.73 350	83.58 402	92.60 417	96.29 395

OpenMVS_ROB	91.80 14	93.64 307	93.05 307	95.42 276	97.31 326	91.21 249	95.08 272	96.68 324	81.56 408	96.88 236	96.41 312	90.44 275	99.25 285	85.39 388	97.67 344	95.80 402

TAMVS		95.49 227	94.94 242	97.16 163	98.31 204	93.41 189	95.07 273	96.82 317	91.09 318	97.51 189	97.82 210	89.96 282	99.42 229	88.42 356	99.44 170	98.64 252

tpmrst		90.31 359	90.61 357	89.41 402	94.06 415	72.37 433	95.06 274	93.69 368	88.01 360	92.32 389	96.86 284	77.45 373	98.82 341	91.04 301	87.01 427	97.04 370

ADS-MVSNet2		91.47 349	90.51 358	94.36 324	95.51 388	85.63 351	95.05 275	95.70 338	83.46 402	92.69 381	96.84 286	79.15 365	99.41 238	85.66 384	90.52 420	98.04 319

ADS-MVSNet		90.95 356	90.26 361	93.04 358	95.51 388	82.37 389	95.05 275	93.41 374	83.46 402	92.69 381	96.84 286	79.15 365	98.70 354	85.66 384	90.52 420	98.04 319

tpm		91.08 354	90.85 351	91.75 386	95.33 394	78.09 412	95.03 277	91.27 400	88.75 349	93.53 362	97.40 242	71.24 402	99.30 273	91.25 298	93.87 412	97.87 332

NCCC		96.52 183	95.99 207	98.10 87	97.81 264	95.68 92	95.00 278	98.20 239	95.39 184	95.40 312	96.36 316	93.81 202	99.45 222	93.55 256	98.42 308	99.17 163

test_post1							94.98 279				10.37 438	76.21 382	99.04 320	89.47 341

fmvsm_s_conf0.5_n_7		97.13 142	97.50 121	96.04 243	98.43 195	89.03 292	94.92 280	99.00 101	94.51 222	98.42 106	98.96 69	94.97 170	99.54 193	98.42 40	99.85 39	99.56 56

AdaColmap		95.11 248	94.62 265	96.58 208	97.33 324	94.45 146	94.92 280	98.08 257	93.15 273	93.98 348	95.53 347	94.34 189	99.10 313	85.69 383	98.61 294	96.20 397

MDTV_nov1_ep13_2view						57.28 439	94.89 282		80.59 413	94.02 346		78.66 367		85.50 386		97.82 335

CNVR-MVS		96.92 155	96.55 180	98.03 95	98.00 246	95.54 97	94.87 283	98.17 245	94.60 216	96.38 266	97.05 271	95.67 143	99.36 255	95.12 193	99.08 243	99.19 160

OMC-MVS		96.48 185	96.00 206	97.91 102	98.30 205	96.01 82	94.86 284	98.60 193	91.88 302	97.18 209	97.21 260	96.11 123	99.04 320	90.49 326	99.34 201	98.69 248

testing3		89.72 369	88.26 378	94.10 334	97.66 293	84.30 376	94.80 285	88.25 420	94.66 213	95.07 317	92.51 396	41.15 439	99.43 227	91.81 288	98.44 307	98.55 262

EPNet_dtu		91.39 350	90.75 353	93.31 349	90.48 433	82.61 387	94.80 285	92.88 379	93.39 258	81.74 431	94.90 360	81.36 355	99.11 310	88.28 358	98.87 265	98.21 300
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13			91.28 342		94.31 408	73.51 431	94.80 285	93.16 376	86.75 375	93.45 365	97.40 242	76.37 380	98.55 371	88.85 349	96.43 382

pmmvs-eth3d		96.49 184	96.18 199	97.42 146	98.25 213	94.29 153	94.77 288	98.07 261	89.81 336	97.97 163	98.33 142	93.11 217	99.08 315	95.46 168	99.84 42	98.89 219

test_yl		94.40 281	94.00 291	95.59 265	96.95 338	89.52 278	94.75 289	95.55 345	96.18 136	96.79 238	96.14 326	81.09 357	99.18 296	90.75 313	97.77 334	98.07 311

DCV-MVSNet		94.40 281	94.00 291	95.59 265	96.95 338	89.52 278	94.75 289	95.55 345	96.18 136	96.79 238	96.14 326	81.09 357	99.18 296	90.75 313	97.77 334	98.07 311

dmvs_testset		87.30 392	86.99 389	88.24 408	96.71 344	77.48 417	94.68 291	86.81 425	92.64 288	89.61 413	87.01 428	85.91 324	93.12 429	61.04 432	88.49 425	94.13 416

MCST-MVS		96.24 194	95.80 217	97.56 126	98.75 146	94.13 160	94.66 292	98.17 245	90.17 332	96.21 279	96.10 329	95.14 163	99.43 227	94.13 236	98.85 268	99.13 172

XVG-OURS-SEG-HR		97.38 129	97.07 147	98.30 70	99.01 110	97.41 38	94.66 292	99.02 90	95.20 191	98.15 142	97.52 234	98.83 5	98.43 380	94.87 204	96.41 383	99.07 188

mvs_anonymous		95.36 235	96.07 204	93.21 354	96.29 355	81.56 395	94.60 294	97.66 283	93.30 262	96.95 231	98.91 78	93.03 222	99.38 247	96.60 104	97.30 361	98.69 248

DP-MVS Recon		95.55 225	95.13 235	96.80 195	98.51 183	93.99 166	94.60 294	98.69 178	90.20 331	95.78 299	96.21 322	92.73 228	98.98 328	90.58 322	98.86 267	97.42 360

save fliter					98.48 189	94.71 133	94.53 296	98.41 214	95.02 202

patch_mono-2		96.59 179	96.93 156	95.55 270	98.88 128	87.12 334	94.47 297	99.30 36	94.12 235	96.65 251	98.41 132	94.98 169	99.87 24	95.81 146	99.78 61	99.66 35

tpm cat1		88.01 386	87.33 386	90.05 401	94.48 407	76.28 423	94.47 297	94.35 364	73.84 430	89.26 415	95.61 345	73.64 394	98.30 390	84.13 396	86.20 428	95.57 407

CANet		95.86 210	95.65 223	96.49 215	96.41 353	90.82 255	94.36 299	98.41 214	94.94 204	92.62 386	96.73 295	92.68 229	99.71 109	95.12 193	99.60 114	98.94 207

WR-MVS		96.90 157	96.81 163	97.16 163	98.56 176	92.20 223	94.33 300	98.12 254	97.34 89	98.20 134	97.33 253	92.81 225	99.75 74	94.79 208	99.81 51	99.54 62

HQP-NCC					97.85 255		94.26 301		93.18 269	92.86 377

ACMP_Plane					97.85 255		94.26 301		93.18 269	92.86 377

HQP-MVS		95.17 247	94.58 269	96.92 184	97.85 255	92.47 213	94.26 301	98.43 210	93.18 269	92.86 377	95.08 353	90.33 276	99.23 291	90.51 324	98.74 279	99.05 192

PLC	91.02 16	94.05 295	92.90 311	97.51 131	98.00 246	95.12 125	94.25 304	98.25 232	86.17 378	91.48 396	95.25 351	91.01 265	99.19 295	85.02 392	96.69 377	98.22 299
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
1112_ss		94.12 291	93.42 302	96.23 232	98.59 171	90.85 254	94.24 305	98.85 136	85.49 385	92.97 375	94.94 357	86.01 323	99.64 154	91.78 289	97.92 328	98.20 301

MS-PatchMatch		94.83 260	94.91 246	94.57 316	96.81 343	87.10 335	94.23 306	97.34 297	88.74 350	97.14 211	97.11 267	91.94 254	98.23 393	92.99 269	97.92 328	98.37 279

Fast-Effi-MVS+		95.49 227	95.07 238	96.75 199	97.67 292	92.82 201	94.22 307	98.60 193	91.61 307	93.42 367	92.90 387	96.73 91	99.70 118	92.60 273	97.89 331	97.74 342

CMPMVS	73.10 23	92.74 325	91.39 339	96.77 198	93.57 421	94.67 136	94.21 308	97.67 281	80.36 415	93.61 358	96.60 301	82.85 349	97.35 407	84.86 393	98.78 275	98.29 293
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dp		88.08 385	88.05 379	88.16 410	92.85 425	68.81 437	94.17 309	92.88 379	85.47 386	91.38 397	96.14 326	68.87 410	98.81 343	86.88 376	83.80 430	96.87 376

JIA-IIPM		91.79 344	90.69 355	95.11 286	93.80 418	90.98 252	94.16 310	91.78 393	96.38 124	90.30 405	99.30 29	72.02 401	98.90 335	88.28 358	90.17 422	95.45 408

D2MVS		95.18 245	95.17 234	95.21 282	97.76 278	87.76 323	94.15 311	97.94 265	89.77 337	96.99 226	97.68 224	87.45 312	99.14 303	95.03 198	99.81 51	98.74 241

TSAR-MVS + GP.		96.47 186	96.12 200	97.49 138	97.74 283	95.23 117	94.15 311	96.90 314	93.26 263	98.04 156	96.70 296	94.41 187	98.89 336	94.77 211	99.14 233	98.37 279

PVSNet_BlendedMVS		95.02 254	94.93 244	95.27 280	97.79 273	87.40 329	94.14 313	98.68 180	88.94 347	94.51 331	98.01 192	93.04 219	99.30 273	89.77 337	99.49 157	99.11 181

TinyColmap		96.00 205	96.34 192	94.96 296	97.90 253	87.91 317	94.13 314	98.49 204	94.41 225	98.16 140	97.76 214	96.29 118	98.68 359	90.52 323	99.42 182	98.30 290

CNLPA		95.04 251	94.47 274	96.75 199	97.81 264	95.25 116	94.12 315	97.89 268	94.41 225	94.57 329	95.69 340	90.30 279	98.35 387	86.72 378	98.76 277	96.64 386

BH-untuned		94.69 268	94.75 258	94.52 318	97.95 251	87.53 326	94.07 316	97.01 310	93.99 240	97.10 215	95.65 342	92.65 231	98.95 333	87.60 366	96.74 374	97.09 368

pmmvs5		94.63 273	94.34 280	95.50 272	97.63 299	88.34 305	94.02 317	97.13 304	87.15 368	95.22 315	97.15 263	87.50 311	99.27 282	93.99 242	99.26 219	98.88 223

thres200		91.00 355	90.42 359	92.77 369	97.47 313	83.98 379	94.01 318	91.18 401	95.12 196	95.44 310	91.21 410	73.93 391	99.31 270	77.76 420	97.63 348	95.01 411

xiu_mvs_v1_base_debu		95.62 222	95.96 209	94.60 313	98.01 242	88.42 302	93.99 319	98.21 236	92.98 278	95.91 291	94.53 365	96.39 111	99.72 95	95.43 172	98.19 317	95.64 404

xiu_mvs_v1_base		95.62 222	95.96 209	94.60 313	98.01 242	88.42 302	93.99 319	98.21 236	92.98 278	95.91 291	94.53 365	96.39 111	99.72 95	95.43 172	98.19 317	95.64 404

xiu_mvs_v1_base_debi		95.62 222	95.96 209	94.60 313	98.01 242	88.42 302	93.99 319	98.21 236	92.98 278	95.91 291	94.53 365	96.39 111	99.72 95	95.43 172	98.19 317	95.64 404

test_vis1_rt		94.03 297	93.65 298	95.17 285	95.76 383	93.42 188	93.97 322	98.33 225	84.68 396	93.17 371	95.89 337	92.53 239	94.79 425	93.50 257	94.97 404	97.31 365

CDS-MVSNet		94.88 259	94.12 288	97.14 165	97.64 298	93.57 182	93.96 323	97.06 308	90.05 333	96.30 273	96.55 303	86.10 322	99.47 214	90.10 331	99.31 211	98.40 275
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		94.65 272	94.21 284	95.96 247	95.90 372	89.68 274	93.92 324	97.83 274	93.19 268	90.12 408	95.64 343	88.52 298	99.57 184	93.27 264	99.47 163	98.62 255

WTY-MVS		93.55 309	93.00 310	95.19 283	97.81 264	87.86 318	93.89 325	96.00 331	89.02 345	94.07 343	95.44 350	86.27 321	99.33 264	87.69 364	96.82 371	98.39 277

sss		94.22 286	93.72 297	95.74 259	97.71 286	89.95 268	93.84 326	96.98 311	88.38 356	93.75 353	95.74 339	87.94 305	98.89 336	91.02 302	98.10 321	98.37 279

baseline2		89.65 371	88.44 377	93.25 351	95.62 386	82.71 385	93.82 327	85.94 426	88.89 348	87.35 424	92.54 395	71.23 403	99.33 264	86.01 379	94.60 409	97.72 345

XVG-OURS		97.12 143	96.74 167	98.26 72	98.99 111	97.45 36	93.82 327	99.05 80	95.19 192	98.32 123	97.70 222	95.22 159	98.41 381	94.27 230	98.13 320	98.93 211

MVS_111021_LR		96.82 165	96.55 180	97.62 123	98.27 210	95.34 112	93.81 329	98.33 225	94.59 218	96.56 257	96.63 300	96.61 96	98.73 350	94.80 207	99.34 201	98.78 235

BH-RMVSNet		94.56 276	94.44 277	94.91 297	97.57 302	87.44 328	93.78 330	96.26 327	93.69 248	96.41 265	96.50 308	92.10 249	99.00 324	85.96 380	97.71 340	98.31 288

CDPH-MVS		95.45 232	94.65 261	97.84 107	98.28 208	94.96 128	93.73 331	98.33 225	85.03 392	95.44 310	96.60 301	95.31 156	99.44 225	90.01 332	99.13 235	99.11 181

PatchMatch-RL		94.61 274	93.81 296	97.02 179	98.19 220	95.72 89	93.66 332	97.23 299	88.17 359	94.94 323	95.62 344	91.43 259	98.57 368	87.36 372	97.68 343	96.76 384

UWE-MVS-28		83.78 397	82.36 400	88.03 411	90.72 432	71.58 434	93.64 333	77.87 433	87.62 364	85.91 427	92.89 388	59.94 417	95.99 422	56.06 434	96.56 381	96.52 390

TEST9					97.84 260	95.23 117	93.62 334	98.39 217	86.81 373	93.78 350	95.99 331	94.68 177	99.52 199

train_agg		95.46 231	94.66 260	97.88 104	97.84 260	95.23 117	93.62 334	98.39 217	87.04 369	93.78 350	95.99 331	94.58 181	99.52 199	91.76 290	98.90 261	98.89 219

test_prior4						95.38 107	93.61 336

test_8					97.81 264	95.07 126	93.54 337	98.38 219	87.04 369	93.71 354	95.96 334	94.58 181	99.52 199

TR-MVS		92.54 328	92.20 328	93.57 344	96.49 350	86.66 341	93.51 338	94.73 359	89.96 334	94.95 322	93.87 375	90.24 281	98.61 365	81.18 410	94.88 405	95.45 408

新几何2							93.43 339

diffmvs		96.04 202	96.23 196	95.46 275	97.35 320	88.03 315	93.42 340	99.08 72	94.09 238	96.66 249	96.93 280	93.85 201	99.29 277	96.01 133	98.67 287	99.06 190
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_111021_HR		96.73 171	96.54 182	97.27 156	98.35 202	93.66 180	93.42 340	98.36 221	94.74 209	96.58 255	96.76 294	96.54 99	98.99 326	94.87 204	99.27 217	99.15 166

UnsupCasMVSNet_bld		94.72 267	94.26 281	96.08 242	98.62 167	90.54 263	93.38 342	98.05 263	90.30 329	97.02 224	96.80 291	89.54 287	99.16 301	88.44 355	96.18 389	98.56 260

旧先验2							93.35 343		77.95 423	95.77 301			98.67 360	90.74 316

test_prior2							93.33 344		94.21 230	94.02 346	96.25 320	93.64 207		91.90 284	98.96 254

WB-MVSnew		91.50 348	91.29 341	92.14 382	94.85 401	80.32 404	93.29 345	88.77 418	88.57 353	94.03 345	92.21 399	92.56 234	98.28 391	80.21 413	97.08 363	97.81 337

SCA		93.38 314	93.52 301	92.96 363	96.24 356	81.40 397	93.24 346	94.00 366	91.58 309	94.57 329	96.97 277	87.94 305	99.42 229	89.47 341	97.66 346	98.06 315

无先验							93.20 347	97.91 266	80.78 412				99.40 240	87.71 363		97.94 327

MG-MVS		94.08 294	94.00 291	94.32 327	97.09 334	85.89 350	93.19 348	95.96 333	92.52 289	94.93 324	97.51 235	89.54 287	98.77 346	87.52 370	97.71 340	98.31 288

MVS-HIRNet		88.40 381	90.20 362	82.99 413	97.01 336	60.04 438	93.11 349	85.61 427	84.45 400	88.72 418	99.09 55	84.72 335	98.23 393	82.52 404	96.59 380	90.69 428

new-patchmatchnet		95.67 220	96.58 176	92.94 364	97.48 309	80.21 405	92.96 350	98.19 244	94.83 207	98.82 70	98.79 85	93.31 213	99.51 203	95.83 144	99.04 249	99.12 177

ETVMVS		87.62 389	85.75 396	93.22 353	96.15 365	83.26 382	92.94 351	90.37 410	91.39 313	90.37 403	88.45 424	51.93 436	98.64 362	73.76 424	96.38 384	97.75 341

MDA-MVSNet-bldmvs		95.69 218	95.67 221	95.74 259	98.48 189	88.76 300	92.84 352	97.25 298	96.00 148	97.59 185	97.95 198	91.38 260	99.46 217	93.16 267	96.35 385	98.99 200

原ACMM2							92.82 353

testdata1							92.77 354		93.78 244

Test_1112_low_res		93.53 310	92.86 312	95.54 271	98.60 169	88.86 296	92.75 355	98.69 178	82.66 405	92.65 383	96.92 282	84.75 334	99.56 186	90.94 305	97.76 336	98.19 302

USDC		94.56 276	94.57 271	94.55 317	97.78 276	86.43 345	92.75 355	98.65 190	85.96 380	96.91 234	97.93 201	90.82 268	98.74 349	90.71 317	99.59 117	98.47 271

test222					98.17 226	93.24 195	92.74 357	97.61 290	75.17 427	94.65 328	96.69 297	90.96 267			98.66 289	97.66 347

jason		94.39 283	94.04 290	95.41 278	98.29 206	87.85 320	92.74 357	96.75 320	85.38 389	95.29 313	96.15 324	88.21 304	99.65 148	94.24 231	99.34 201	98.74 241
jason: jason.
testing91		89.67 370	88.55 375	93.04 358	95.90 372	81.80 394	92.71 359	93.71 367	93.71 246	90.18 406	90.15 418	57.11 422	99.22 293	87.17 375	96.32 386	98.12 307

testing99		89.21 374	88.04 380	92.70 371	95.78 381	81.00 401	92.65 360	92.03 389	93.20 267	89.90 411	90.08 420	55.25 431	99.14 303	87.54 368	95.95 392	97.97 324

Patchmatch-RL test		94.66 271	94.49 272	95.19 283	98.54 179	88.91 294	92.57 361	98.74 167	91.46 312	98.32 123	97.75 217	77.31 376	98.81 343	96.06 126	99.61 108	97.85 333

DeepPCF-MVS	94.58 5	96.90 157	96.43 188	98.31 69	97.48 309	97.23 44	92.56 362	98.60 193	92.84 284	98.54 93	97.40 242	96.64 95	98.78 345	94.40 225	99.41 186	98.93 211

N_pmnet		95.18 245	94.23 282	98.06 90	97.85 255	96.55 62	92.49 363	91.63 394	89.34 340	98.09 148	97.41 241	90.33 276	99.06 317	91.58 292	99.31 211	98.56 260

testing11		88.93 376	87.63 385	92.80 368	95.87 374	81.49 396	92.48 364	91.54 395	91.62 306	88.27 420	90.24 416	55.12 434	99.11 310	87.30 373	96.28 388	97.81 337

Syy-MVS		92.09 337	91.80 334	92.93 365	95.19 396	82.65 386	92.46 365	91.35 397	90.67 324	91.76 394	87.61 426	85.64 328	98.50 375	94.73 213	96.84 369	97.65 348

myMVS_eth3d		87.16 394	85.61 397	91.82 385	95.19 396	79.32 407	92.46 365	91.35 397	90.67 324	91.76 394	87.61 426	41.96 438	98.50 375	82.66 403	96.84 369	97.65 348

BH-w/o		92.14 335	91.94 330	92.73 370	97.13 333	85.30 357	92.46 365	95.64 340	89.33 341	94.21 337	92.74 392	89.60 285	98.24 392	81.68 407	94.66 407	94.66 413

IterMVS-SCA-FT		95.86 210	96.19 198	94.85 302	97.68 288	85.53 353	92.42 368	97.63 289	96.99 98	98.36 115	98.54 117	87.94 305	99.75 74	97.07 91	99.08 243	99.27 147

IterMVS		95.42 233	95.83 216	94.20 331	97.52 306	83.78 380	92.41 369	97.47 294	95.49 179	98.06 153	98.49 121	87.94 305	99.58 178	96.02 131	99.02 250	99.23 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing222		87.35 391	85.50 398	92.93 365	95.79 380	82.83 384	92.40 370	90.10 414	92.80 285	88.87 417	89.02 422	48.34 437	98.70 354	75.40 423	96.74 374	97.27 366

DELS-MVS		96.17 197	96.23 196	95.99 245	97.55 305	90.04 266	92.38 371	98.52 201	94.13 234	96.55 259	97.06 270	94.99 168	99.58 178	95.62 155	99.28 215	98.37 279
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
new_pmnet		92.34 331	91.69 336	94.32 327	96.23 358	89.16 287	92.27 372	92.88 379	84.39 401	95.29 313	96.35 317	85.66 327	96.74 418	84.53 395	97.56 349	97.05 369

myMVS_eth3d28		88.32 382	87.73 383	90.11 400	96.42 352	74.96 429	92.21 373	92.37 387	93.56 252	90.14 407	89.61 421	56.13 427	98.05 399	81.84 405	97.26 362	97.33 364

CHOSEN 1792x2688		94.10 292	93.41 303	96.18 237	99.16 80	90.04 266	92.15 374	98.68 180	79.90 416	96.22 278	97.83 207	87.92 309	99.42 229	89.18 345	99.65 96	99.08 186

xiu_mvs_v2_base		94.22 286	94.63 264	92.99 362	97.32 325	84.84 368	92.12 375	97.84 272	91.96 300	94.17 339	93.43 378	96.07 124	99.71 109	91.27 296	97.48 353	94.42 414

lupinMVS		93.77 301	93.28 304	95.24 281	97.68 288	87.81 321	92.12 375	96.05 329	84.52 398	94.48 333	95.06 355	86.90 316	99.63 158	93.62 255	99.13 235	98.27 294

pmmvs4		94.82 261	94.19 285	96.70 202	97.42 316	92.75 207	92.09 377	96.76 319	86.80 374	95.73 302	97.22 259	89.28 293	98.89 336	93.28 263	99.14 233	98.46 273

PAPR		92.22 333	91.27 343	95.07 289	95.73 385	88.81 297	91.97 378	97.87 269	85.80 383	90.91 398	92.73 393	91.16 262	98.33 388	79.48 414	95.76 397	98.08 309

UWE-MVS		87.57 390	86.72 392	90.13 399	95.21 395	73.56 430	91.94 379	83.78 430	88.73 351	93.00 374	92.87 389	55.22 432	99.25 285	81.74 406	97.96 326	97.59 353

PS-MVSNAJ		94.10 292	94.47 274	93.00 361	97.35 320	84.88 365	91.86 380	97.84 272	91.96 300	94.17 339	92.50 397	95.82 133	99.71 109	91.27 296	97.48 353	94.40 415

c3_l		95.20 244	95.32 228	94.83 304	96.19 360	86.43 345	91.83 381	98.35 224	93.47 256	97.36 199	97.26 257	88.69 296	99.28 279	95.41 175	99.36 193	98.78 235

test0.0.03 1		90.11 360	89.21 368	92.83 367	93.89 417	86.87 339	91.74 382	88.74 419	92.02 298	94.71 327	91.14 411	73.92 392	94.48 427	83.75 401	92.94 414	97.16 367

UBG		88.29 383	87.17 387	91.63 387	96.08 367	78.21 411	91.61 383	91.50 396	89.67 338	89.71 412	88.97 423	59.01 419	98.91 334	81.28 409	96.72 376	97.77 340

SSC-MVS3.2		95.75 216	96.56 178	93.34 347	98.69 157	80.75 402	91.60 384	97.43 296	97.37 88	96.99 226	97.02 273	93.69 206	99.71 109	96.32 117	99.89 23	99.55 60

FPMVS		89.92 366	88.63 374	93.82 337	98.37 200	96.94 49	91.58 385	93.34 375	88.00 361	90.32 404	97.10 268	70.87 405	91.13 431	71.91 428	96.16 391	93.39 421

ET-MVSNet_ETH3D		91.12 351	89.67 365	95.47 274	96.41 353	89.15 288	91.54 386	90.23 412	89.07 344	86.78 426	92.84 390	69.39 409	99.44 225	94.16 234	96.61 379	97.82 335

WBMVS		91.11 352	90.72 354	92.26 380	95.99 369	77.98 415	91.47 387	95.90 335	91.63 305	95.90 294	96.45 310	59.60 418	99.46 217	89.97 334	99.59 117	99.33 130

PVSNet_Blended		93.96 298	93.65 298	94.91 297	97.79 273	87.40 329	91.43 388	98.68 180	84.50 399	94.51 331	94.48 368	93.04 219	99.30 273	89.77 337	98.61 294	98.02 321

CLD-MVS		95.47 230	95.07 238	96.69 203	98.27 210	92.53 210	91.36 389	98.67 183	91.22 317	95.78 299	94.12 372	95.65 144	98.98 328	90.81 309	99.72 78	98.57 259
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
eth_miper_zixun_eth		94.89 258	94.93 244	94.75 308	95.99 369	86.12 348	91.35 390	98.49 204	93.40 257	97.12 213	97.25 258	86.87 318	99.35 259	95.08 195	98.82 272	98.78 235

cl____		94.73 263	94.64 262	95.01 292	95.85 376	87.00 336	91.33 391	98.08 257	93.34 260	97.10 215	97.33 253	84.01 342	99.30 273	95.14 190	99.56 126	98.71 247

DIV-MVS_self_test		94.73 263	94.64 262	95.01 292	95.86 375	87.00 336	91.33 391	98.08 257	93.34 260	97.10 215	97.34 252	84.02 341	99.31 270	95.15 189	99.55 132	98.72 244

miper_ehance_all_eth		94.69 268	94.70 259	94.64 310	95.77 382	86.22 347	91.32 393	98.24 234	91.67 304	97.05 222	96.65 299	88.39 301	99.22 293	94.88 203	98.34 311	98.49 270

pmmvs3		90.00 363	88.90 373	93.32 348	94.20 413	85.34 355	91.25 394	92.56 386	78.59 420	93.82 349	95.17 352	67.36 412	98.69 356	89.08 347	98.03 324	95.92 398

HyFIR lowres test		93.72 303	92.65 320	96.91 186	98.93 121	91.81 237	91.23 395	98.52 201	82.69 404	96.46 263	96.52 307	80.38 361	99.90 16	90.36 328	98.79 274	99.03 193

DPM-MVS		93.68 305	92.77 318	96.42 220	97.91 252	92.54 209	91.17 396	97.47 294	84.99 394	93.08 373	94.74 361	89.90 283	99.00 324	87.54 368	98.09 322	97.72 345

CL-MVSNet_self_test		95.04 251	94.79 257	95.82 255	97.51 307	89.79 272	91.14 397	96.82 317	93.05 275	96.72 244	96.40 314	90.82 268	99.16 301	91.95 283	98.66 289	98.50 269

miper_lstm_enhance		94.81 262	94.80 256	94.85 302	96.16 362	86.45 344	91.14 397	98.20 239	93.49 255	97.03 223	97.37 250	84.97 333	99.26 283	95.28 178	99.56 126	98.83 228

cl22		93.25 318	92.84 314	94.46 321	94.30 409	86.00 349	91.09 399	96.64 325	90.74 321	95.79 297	96.31 318	78.24 368	98.77 346	94.15 235	98.34 311	98.62 255

MSDG		95.33 238	95.13 235	95.94 251	97.40 317	91.85 235	91.02 400	98.37 220	95.30 188	96.31 272	95.99 331	94.51 185	98.38 384	89.59 339	97.65 347	97.60 352

IB-MVS	85.98 20	88.63 379	86.95 391	93.68 342	95.12 398	84.82 369	90.85 401	90.17 413	87.55 365	88.48 419	91.34 409	58.01 420	99.59 175	87.24 374	93.80 413	96.63 388
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
mvsany_test1		93.47 311	93.03 308	94.79 306	94.05 416	92.12 225	90.82 402	90.01 415	85.02 393	97.26 203	98.28 153	93.57 208	97.03 410	92.51 276	95.75 398	95.23 410

test123		12.59 404	15.49 407	3.87 419	6.07 442	2.55 444	90.75 403	2.59 444	2.52 437	5.20 439	13.02 436	4.96 442	1.85 439	5.20 437	9.09 436	7.23 434

ppachtmachnet_test		94.49 280	94.84 252	93.46 346	96.16 362	82.10 390	90.59 404	97.48 293	90.53 326	97.01 225	97.59 229	91.01 265	99.36 255	93.97 244	99.18 229	98.94 207

PMMVS		92.39 329	91.08 346	96.30 230	93.12 423	92.81 203	90.58 405	95.96 333	79.17 419	91.85 393	92.27 398	90.29 280	98.66 361	89.85 336	96.68 378	97.43 359

our_test_3		94.20 290	94.58 269	93.07 357	96.16 362	81.20 399	90.42 406	96.84 315	90.72 322	97.14 211	97.13 264	90.47 272	99.11 310	94.04 241	98.25 315	98.91 215

YYNet1		94.73 263	94.84 252	94.41 323	97.47 313	85.09 363	90.29 407	95.85 337	92.52 289	97.53 187	97.76 214	91.97 252	99.18 296	93.31 262	96.86 368	98.95 205

MDA-MVSNet_test_wron		94.73 263	94.83 254	94.42 322	97.48 309	85.15 361	90.28 408	95.87 336	92.52 289	97.48 193	97.76 214	91.92 255	99.17 300	93.32 261	96.80 373	98.94 207

GA-MVS		92.83 324	92.15 329	94.87 301	96.97 337	87.27 332	90.03 409	96.12 328	91.83 303	94.05 344	94.57 363	76.01 383	98.97 332	92.46 277	97.34 359	98.36 284

miper_enhance_ethall		93.14 320	92.78 317	94.20 331	93.65 419	85.29 358	89.97 410	97.85 270	85.05 391	96.15 284	94.56 364	85.74 325	99.14 303	93.74 250	98.34 311	98.17 305

test-LLR		89.97 365	89.90 363	90.16 397	94.24 411	74.98 426	89.89 411	89.06 416	92.02 298	89.97 409	90.77 414	73.92 392	98.57 368	91.88 285	97.36 357	96.92 373

TESTMET0.1,1		87.20 393	86.57 393	89.07 404	93.62 420	72.84 432	89.89 411	87.01 424	85.46 387	89.12 416	90.20 417	56.00 428	97.72 404	90.91 306	96.92 365	96.64 386

test-mter		87.92 387	87.17 387	90.16 397	94.24 411	74.98 426	89.89 411	89.06 416	86.44 377	89.97 409	90.77 414	54.96 435	98.57 368	91.88 285	97.36 357	96.92 373

PCF-MVS	89.43 18	92.12 336	90.64 356	96.57 210	97.80 268	93.48 185	89.88 414	98.45 207	74.46 428	96.04 287	95.68 341	90.71 270	99.31 270	73.73 425	99.01 252	96.91 375
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thisisatest0515		90.43 358	89.18 371	94.17 333	97.07 335	85.44 354	89.75 415	87.58 421	88.28 357	93.69 356	91.72 405	65.27 413	99.58 178	90.59 321	98.67 287	97.50 358

KD-MVS_2432*1600		88.93 376	87.74 381	92.49 374	88.04 435	81.99 391	89.63 416	95.62 341	91.35 314	95.06 318	93.11 380	56.58 424	98.63 363	85.19 389	95.07 402	96.85 378

miper_refine_blended		88.93 376	87.74 381	92.49 374	88.04 435	81.99 391	89.63 416	95.62 341	91.35 314	95.06 318	93.11 380	56.58 424	98.63 363	85.19 389	95.07 402	96.85 378

testmvs		12.33 405	15.23 408	3.64 420	5.77 443	2.23 445	88.99 418	3.62 443	2.30 438	5.29 438	13.09 435	4.52 443	1.95 438	5.16 438	8.32 437	6.75 435

cascas		91.89 342	91.35 340	93.51 345	94.27 410	85.60 352	88.86 419	98.61 192	79.32 418	92.16 390	91.44 408	89.22 294	98.12 396	90.80 310	97.47 355	96.82 381

PAPM		87.64 388	85.84 395	93.04 358	96.54 348	84.99 364	88.42 420	95.57 344	79.52 417	83.82 428	93.05 386	80.57 360	98.41 381	62.29 431	92.79 415	95.71 403

PVSNet	86.72 19	91.10 353	90.97 349	91.49 388	97.56 304	78.04 413	87.17 421	94.60 361	84.65 397	92.34 388	92.20 400	87.37 314	98.47 378	85.17 391	97.69 342	97.96 325

PMMVS2		93.66 306	94.07 289	92.45 377	97.57 302	80.67 403	86.46 422	96.00 331	93.99 240	97.10 215	97.38 248	89.90 283	97.82 402	88.76 350	99.47 163	98.86 226

CHOSEN 280x420		89.98 364	89.19 370	92.37 378	95.60 387	81.13 400	86.22 423	97.09 306	81.44 410	87.44 423	93.15 379	73.99 390	99.47 214	88.69 352	99.07 245	96.52 390

dongtai		63.43 400	63.37 403	63.60 416	83.91 438	53.17 440	85.14 424	43.40 442	77.91 424	80.96 432	79.17 432	36.36 440	77.10 434	37.88 435	45.63 434	60.54 431

kuosan		54.81 402	54.94 405	54.42 417	74.43 439	50.03 441	84.98 425	44.27 441	61.80 432	62.49 436	70.43 433	35.16 441	58.04 436	19.30 436	41.61 435	55.19 432

tmp_tt		57.23 401	62.50 404	41.44 418	34.77 441	49.21 442	83.93 426	60.22 440	15.31 434	71.11 434	79.37 431	70.09 408	44.86 437	64.76 430	82.93 431	30.25 433

PVSNet_0	81.89 21	84.49 396	83.21 399	88.34 407	95.76 383	74.97 428	83.49 427	92.70 383	78.47 421	87.94 421	86.90 429	83.38 346	96.63 419	73.44 426	66.86 433	93.40 420

E-PMN		89.52 372	89.78 364	88.73 405	93.14 422	77.61 416	83.26 428	92.02 390	94.82 208	93.71 354	93.11 380	75.31 386	96.81 414	85.81 381	96.81 372	91.77 425

EMVS		89.06 375	89.22 367	88.61 406	93.00 424	77.34 418	82.91 429	90.92 402	94.64 215	92.63 385	91.81 404	76.30 381	97.02 411	83.83 399	96.90 367	91.48 426

MVE	73.61 22	86.48 395	85.92 394	88.18 409	96.23 358	85.28 359	81.78 430	75.79 434	86.01 379	82.53 430	91.88 403	92.74 227	87.47 433	71.42 429	94.86 406	91.78 424
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		66.88 399	66.13 402	69.11 415	62.68 440	25.73 443	49.76 431	96.04 330	14.32 435	64.27 435	91.69 406	73.45 397	88.05 432	76.06 422	66.94 432	93.54 418

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

cdsmvs_eth3d_5k		24.22 403	32.30 406	0.00 421	0.00 444	0.00 446	0.00 432	98.10 255	0.00 439	0.00 440	95.06 355	97.54 40	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		7.98 406	10.65 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	95.82 133	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

ab-mvs-re		7.91 407	10.55 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	94.94 357	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						79.32 407								85.41 387

MSC_two_6792asdad				98.22 77	97.75 280	95.34 112		98.16 249					99.75 74	95.87 142	99.51 150	99.57 52

PC_three_1452									87.24 367	98.37 112	97.44 239	97.00 69	96.78 416	92.01 281	99.25 220	99.21 156

No_MVS				98.22 77	97.75 280	95.34 112		98.16 249					99.75 74	95.87 142	99.51 150	99.57 52

test_one_0601					99.05 106	95.50 102		98.87 129	97.21 95	98.03 157	98.30 148	96.93 75

eth-test2					0.00 444

eth-test					0.00 444

ZD-MVS					98.43 195	95.94 83		98.56 199	90.72 322	96.66 249	97.07 269	95.02 167	99.74 83	91.08 300	98.93 259

IU-MVS					99.22 66	95.40 105		98.14 252	85.77 384	98.36 115				95.23 182	99.51 150	99.49 83

test_241102_TWO								98.83 146	96.11 138	98.62 86	98.24 160	96.92 78	99.72 95	95.44 169	99.49 157	99.49 83

test_241102_ONE					99.22 66	95.35 110		98.83 146	96.04 145	99.08 46	98.13 173	97.87 24	99.33 264

test_0728_THIRD									96.62 110	98.40 109	98.28 153	97.10 59	99.71 109	95.70 147	99.62 102	99.58 45

GSMVS																98.06 315

test_part2					99.03 108	96.07 78				98.08 150

sam_mvs1												77.80 370				98.06 315

sam_mvs												77.38 374

MTGPA								98.73 168

test_post											10.87 437	76.83 378	99.07 316

patchmatchnet-post											96.84 286	77.36 375	99.42 229

gm-plane-assit					91.79 429	71.40 435			81.67 407		90.11 419		98.99 326	84.86 393

test9_res														91.29 295	98.89 264	99.00 197

agg_prior2														90.34 329	98.90 261	99.10 185

agg_prior					97.80 268	94.96 128		98.36 221		93.49 363			99.53 196

TestCases				98.06 90	99.08 96	96.16 74		99.16 51	94.35 227	97.78 180	98.07 181	95.84 130	99.12 307	91.41 293	99.42 182	98.91 215

test_prior				97.46 141	97.79 273	94.26 157		98.42 213					99.34 262			98.79 234

新几何1				97.25 159	98.29 206	94.70 135		97.73 278	77.98 422	94.83 325	96.67 298	92.08 250	99.45 222	88.17 360	98.65 291	97.61 351

旧先验1					97.80 268	93.87 169		97.75 277			97.04 272	93.57 208			98.68 286	98.72 244

原ACMM1				96.58 208	98.16 228	92.12 225		98.15 251	85.90 382	93.49 363	96.43 311	92.47 241	99.38 247	87.66 365	98.62 293	98.23 297

testdata2													99.46 217	87.84 361

segment_acmp												95.34 155

testdata				95.70 262	98.16 228	90.58 260		97.72 279	80.38 414	95.62 304	97.02 273	92.06 251	98.98 328	89.06 348	98.52 299	97.54 355

test12				97.46 141	97.61 300	94.07 161		97.78 276		93.57 361		93.31 213	99.42 229		98.78 275	98.89 219

plane_prior7					98.70 155	94.67 136

plane_prior6					98.38 199	94.37 150						91.91 256

plane_prior5								98.75 165					99.46 217	92.59 274	99.20 225	99.28 143

plane_prior4											96.77 292

plane_prior3						94.51 143			95.29 189	96.16 282

plane_prior1					98.49 187

n2								0.00 445

nn								0.00 445

door-mid								98.17 245

lessismore_v0				97.05 174	99.36 48	92.12 225		84.07 428		98.77 77	98.98 66	85.36 330	99.74 83	97.34 78	99.37 190	99.30 136

LGP-MVS_train				98.74 38	99.15 83	97.02 46		99.02 90	95.15 194	98.34 119	98.23 162	97.91 22	99.70 118	94.41 223	99.73 73	99.50 75

test11								98.08 257

door								97.81 275

HQP5-MVS						92.47 213

BP-MVS														90.51 324

HQP4-MVS										92.87 376			99.23 291			99.06 190

HQP3-MVS								98.43 210							98.74 279

HQP2-MVS												90.33 276

NP-MVS					98.14 232	93.72 175					95.08 353

ACMMP++_ref															99.52 145

ACMMP++															99.55 132

Test By Simon												94.51 185

ITE_SJBPF				97.85 106	98.64 161	96.66 58		98.51 203	95.63 170	97.22 204	97.30 255	95.52 148	98.55 371	90.97 304	98.90 261	98.34 285

DeepMVS_CX				77.17 414	90.94 431	85.28 359		74.08 437	52.51 433	80.87 433	88.03 425	75.25 387	70.63 435	59.23 433	84.94 429	75.62 429

High-resolution multi-view benchmark