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 5

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 17	99.02 19	99.62 13	99.36 23	98.53 9	99.52 187	98.58 28	99.95 5	99.66 30
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 27	99.08 14	97.87 166	99.67 3	96.47 103	99.92 6	97.88 44	99.98 2	99.85 5

mvs5depth		98.06 52	98.58 26	96.51 209	98.97 114	89.65 268	99.43 4	99.81 2	99.30 7	98.36 106	99.86 2	93.15 206	99.88 21	98.50 30	99.84 38	99.99 1

TDRefinement		98.90 6	98.86 9	99.02 10	99.54 25	98.06 9	99.34 5	99.44 22	98.85 25	99.00 47	99.20 37	97.42 42	99.59 166	97.21 71	99.76 57	99.40 105

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 46	99.77 5	96.34 69	99.18 6	99.20 37	99.67 2	99.73 4	99.65 6	99.15 3	99.86 26	97.22 70	99.92 14	99.77 13

OurMVSNet-221017-0		98.61 17	98.61 25	98.63 48	99.77 5	96.35 68	99.17 7	99.05 71	98.05 54	99.61 14	99.52 9	93.72 196	99.88 21	98.72 24	99.88 24	99.65 33

DVP-MVS++		97.96 59	97.90 65	98.12 86	97.75 267	95.40 105	99.03 8	98.89 110	96.62 106	98.62 78	98.30 139	96.97 69	99.75 72	95.70 135	99.25 208	99.21 147

FOURS1					99.59 17	98.20 8	99.03 8	99.25 33	98.96 22	98.87 59

pmmvs6		99.07 4	99.24 4	98.56 52	99.81 2	96.38 66	98.87 10	99.30 29	99.01 20	99.63 12	99.66 4	99.27 2	99.68 127	97.75 53	99.89 23	99.62 36

Anonymous20231211		98.55 21	98.76 14	97.94 101	98.79 136	94.37 150	98.84 11	99.15 46	99.37 4	99.67 8	99.43 17	95.61 141	99.72 93	98.12 36	99.86 28	99.73 22

mmtdpeth		98.33 33	98.53 28	97.71 114	99.07 98	93.44 185	98.80 12	99.78 4	99.10 13	96.61 243	99.63 7	95.42 148	99.73 87	98.53 29	99.86 28	99.95 2

MIMVSNet1		98.51 25	98.45 32	98.67 44	99.72 8	96.71 54	98.76 13	98.89 110	98.49 35	99.38 23	99.14 49	95.44 147	99.84 32	96.47 98	99.80 50	99.47 84

EPP-MVSNet		96.84 152	96.58 167	97.65 120	99.18 78	93.78 173	98.68 14	96.34 315	97.91 57	97.30 191	98.06 177	88.46 289	99.85 29	93.85 235	99.40 176	99.32 122

v7n		98.73 12	98.99 5	97.95 100	99.64 13	94.20 158	98.67 15	99.14 49	99.08 14	99.42 21	99.23 34	96.53 98	99.91 14	99.27 5	99.93 11	99.73 22

MVSFormer		96.14 189	96.36 181	95.49 262	97.68 275	87.81 310	98.67 15	99.02 81	96.50 115	94.48 321	96.15 312	86.90 306	99.92 6	98.73 22	99.13 223	98.74 229

test_djsdf		98.73 12	98.74 17	98.69 43	99.63 14	96.30 71	98.67 15	99.02 81	96.50 115	99.32 27	99.44 16	97.43 41	99.92 6	98.73 22	99.95 5	99.86 4

tt0805		97.44 116	97.56 106	97.11 166	99.55 22	96.36 67	98.66 18	95.66 328	98.31 41	97.09 211	95.45 337	97.17 56	98.50 362	98.67 25	97.45 343	96.48 377

anonymousdsp		98.72 15	98.63 21	98.99 14	99.62 15	97.29 41	98.65 19	99.19 39	95.62 163	99.35 26	99.37 21	97.38 43	99.90 16	98.59 27	99.91 17	99.77 13

HPM-MVS		98.11 47	97.83 75	98.92 25	99.42 39	97.46 35	98.57 20	99.05 71	95.43 175	97.41 189	97.50 227	97.98 19	99.79 47	95.58 147	99.57 112	99.50 67
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
IS-MVSNet		96.93 145	96.68 161	97.70 116	99.25 60	94.00 164	98.57 20	96.74 310	98.36 39	98.14 134	97.98 186	88.23 293	99.71 107	93.10 256	99.72 70	99.38 112

WR-MVS_H		98.65 16	98.62 23	98.75 35	99.51 28	96.61 60	98.55 22	99.17 41	99.05 17	99.17 36	98.79 79	95.47 145	99.89 19	97.95 43	99.91 17	99.75 20

FE-MVS		92.95 310	92.22 315	95.11 275	97.21 316	88.33 295	98.54 23	93.66 359	89.91 321	96.21 267	98.14 162	70.33 395	99.50 192	87.79 349	98.24 303	97.51 343

test2506		89.86 354	89.16 359	91.97 372	98.95 115	76.83 409	98.54 23	61.07 424	96.20 128	97.07 212	99.16 46	55.19 418	99.69 122	96.43 100	99.83 42	99.38 112

mvs_tets		98.90 6	98.94 6	98.75 35	99.69 10	96.48 64	98.54 23	99.22 34	96.23 127	99.71 5	99.48 12	98.77 7	99.93 4	98.89 17	99.95 5	99.84 7

CS-MVS		98.09 48	98.01 57	98.32 67	98.45 184	96.69 56	98.52 26	99.69 8	98.07 53	96.07 273	97.19 252	96.88 80	99.86 26	97.50 63	99.73 66	98.41 261

Gipuma		98.07 51	98.31 39	97.36 149	99.76 7	96.28 72	98.51 27	99.10 55	98.76 27	96.79 228	99.34 26	96.61 94	98.82 328	96.38 102	99.50 143	96.98 357
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 50	99.22 10	99.22 34	98.96 65	97.35 44	99.92 6	97.79 50	99.93 11	99.79 11

3Dnovator	96.53 2	97.61 103	97.64 96	97.50 134	97.74 270	93.65 180	98.49 28	98.88 117	96.86 101	97.11 205	98.55 107	95.82 130	99.73 87	95.94 125	99.42 171	99.13 162

DTE-MVSNet		98.79 9	98.86 9	98.59 50	99.55 22	96.12 76	98.48 30	99.10 55	99.36 5	99.29 29	99.06 56	97.27 48	99.93 4	97.71 55	99.91 17	99.70 26

jajsoiax		98.77 10	98.79 13	98.74 38	99.66 12	96.48 64	98.45 31	99.12 51	95.83 154	99.67 8	99.37 21	98.25 13	99.92 6	98.77 20	99.94 8	99.82 8

PEN-MVS		98.75 11	98.85 11	98.44 59	99.58 18	95.67 93	98.45 31	99.15 46	99.33 6	99.30 28	99.00 59	97.27 48	99.92 6	97.64 59	99.92 14	99.75 20

LS3D		97.77 90	97.50 113	98.57 51	96.24 342	97.58 28	98.45 31	98.85 126	98.58 32	97.51 180	97.94 190	95.74 137	99.63 151	95.19 171	98.97 241	98.51 254

SPE-MVS-test		97.91 73	97.84 72	98.14 84	98.52 173	96.03 81	98.38 34	99.67 9	98.11 51	95.50 297	96.92 270	96.81 86	99.87 24	96.87 87	99.76 57	98.51 254

FC-MVSNet-test		98.16 42	98.37 36	97.56 125	99.49 32	93.10 196	98.35 35	99.21 35	98.43 36	98.89 57	98.83 78	94.30 181	99.81 40	97.87 45	99.91 17	99.77 13

HPM-MVS_fast		98.32 35	98.13 46	98.88 27	99.54 25	97.48 34	98.35 35	99.03 79	95.88 150	97.88 163	98.22 156	98.15 16	99.74 81	96.50 97	99.62 92	99.42 102

ab-mvs		96.59 170	96.59 166	96.60 202	98.64 154	92.21 218	98.35 35	97.67 271	94.45 212	96.99 217	98.79 79	94.96 163	99.49 197	90.39 314	99.07 233	98.08 296

EGC-MVSNET		83.08 383	77.93 386	98.53 54	99.57 19	97.55 30	98.33 38	98.57 188	4.71 421	10.38 422	98.90 73	95.60 142	99.50 192	95.69 137	99.61 98	98.55 250

test1111		94.53 266	94.81 243	93.72 329	99.06 100	81.94 382	98.31 39	83.87 415	96.37 120	98.49 90	99.17 45	81.49 343	99.73 87	96.64 91	99.86 28	99.49 75

ECVR-MVS		94.37 272	94.48 261	94.05 324	98.95 115	83.10 372	98.31 39	82.48 417	96.20 128	98.23 123	99.16 46	81.18 346	99.66 141	95.95 124	99.83 42	99.38 112

EC-MVSNet		97.90 75	97.94 64	97.79 109	98.66 153	95.14 123	98.31 39	99.66 11	97.57 72	95.95 277	97.01 264	96.99 68	99.82 36	97.66 58	99.64 88	98.39 264

pm-mvs1		98.47 28	98.67 19	97.86 105	99.52 27	94.58 141	98.28 42	99.00 92	97.57 72	99.27 30	99.22 35	98.32 12	99.50 192	97.09 77	99.75 64	99.50 67

SixPastTwentyTwo		97.49 112	97.57 105	97.26 157	99.56 20	92.33 214	98.28 42	96.97 301	98.30 43	99.45 19	99.35 25	88.43 290	99.89 19	98.01 41	99.76 57	99.54 54

FA-MVS(test-final)		94.91 244	94.89 237	94.99 283	97.51 294	88.11 303	98.27 44	95.20 341	92.40 280	96.68 236	98.60 102	83.44 334	99.28 266	93.34 248	98.53 285	97.59 340

CP-MVSNet		98.42 30	98.46 30	98.30 70	99.46 34	95.22 120	98.27 44	98.84 130	99.05 17	99.01 45	98.65 97	95.37 149	99.90 16	97.57 60	99.91 17	99.77 13

GG-mvs-BLEND				90.60 383	91.00 416	84.21 366	98.23 46	72.63 423		82.76 414	84.11 415	56.14 413	96.79 401	72.20 413	92.09 404	90.78 412

GBi-Net		96.99 140	96.80 155	97.56 125	97.96 235	93.67 176	98.23 46	98.66 175	95.59 165	97.99 150	99.19 38	89.51 280	99.73 87	94.60 205	99.44 159	99.30 127

test1		96.99 140	96.80 155	97.56 125	97.96 235	93.67 176	98.23 46	98.66 175	95.59 165	97.99 150	99.19 38	89.51 280	99.73 87	94.60 205	99.44 159	99.30 127

FMVSNet1		97.95 63	98.08 50	97.56 125	99.14 90	93.67 176	98.23 46	98.66 175	97.41 83	99.00 47	99.19 38	95.47 145	99.73 87	95.83 132	99.76 57	99.30 127

ACMH	93.61 9	98.44 29	98.76 14	97.51 130	99.43 37	93.54 182	98.23 46	99.05 71	97.40 84	99.37 24	99.08 55	98.79 6	99.47 202	97.74 54	99.71 73	99.50 67
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TransMVSNet (Re)		98.38 32	98.67 19	97.51 130	99.51 28	93.39 189	98.20 51	98.87 119	98.23 47	99.48 17	99.27 31	98.47 11	99.55 179	96.52 96	99.53 129	99.60 37

gg-mvs-nofinetune		88.28 370	86.96 376	92.23 369	92.84 412	84.44 362	98.19 52	74.60 420	99.08 14	87.01 411	99.47 13	56.93 410	98.23 380	78.91 402	95.61 384	94.01 402

QAPM		95.88 200	95.57 216	96.80 191	97.90 240	91.84 233	98.18 53	98.73 158	88.41 340	96.42 253	98.13 164	94.73 165	99.75 72	88.72 338	98.94 245	98.81 219

NR-MVSNet		97.96 59	97.86 71	98.26 72	98.73 142	95.54 97	98.14 54	98.73 158	97.79 59	99.42 21	97.83 198	94.40 179	99.78 51	95.91 127	99.76 57	99.46 86

MIMVSNet		93.42 300	92.86 300	95.10 277	98.17 214	88.19 297	98.13 55	93.69 356	92.07 282	95.04 309	98.21 157	80.95 349	99.03 310	81.42 394	98.06 310	98.07 298

PS-MVSNAJss		98.53 24	98.63 21	98.21 80	99.68 11	94.82 131	98.10 56	99.21 35	96.91 99	99.75 3	99.45 15	95.82 130	99.92 6	98.80 19	99.96 4	99.89 3

ACMMP		98.05 53	97.75 85	98.93 22	99.23 63	97.60 26	98.09 57	98.96 102	95.75 158	97.91 160	98.06 177	96.89 78	99.76 66	95.32 165	99.57 112	99.43 101
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 43	98.03 55	98.47 58	98.72 144	96.04 79	98.07 58	99.10 55	95.96 143	98.59 82	98.69 92	96.94 71	99.81 40	96.64 91	99.58 109	99.57 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
Vis-MVSNet		98.27 38	98.34 37	98.07 88	99.33 51	95.21 122	98.04 59	99.46 20	97.32 88	97.82 170	99.11 51	96.75 88	99.86 26	97.84 47	99.36 182	99.15 157
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	96.13 3	97.73 92	97.59 103	98.15 83	98.11 224	95.60 95	98.04 59	98.70 167	98.13 50	96.93 222	98.45 118	95.30 152	99.62 156	95.64 142	98.96 242	99.24 144

MVSMamba_PlusPlus		97.43 118	97.98 60	95.78 246	98.88 126	89.70 266	98.03 61	98.85 126	99.18 11	96.84 227	99.12 50	93.04 209	99.91 14	98.38 32	99.55 121	97.73 330

FIs		97.93 69	98.07 51	97.48 138	99.38 46	92.95 199	98.03 61	99.11 52	98.04 55	98.62 78	98.66 94	93.75 195	99.78 51	97.23 69	99.84 38	99.73 22

mamv4		99.05 5	98.91 8	99.46 2	98.94 118	99.62 2	97.98 63	99.70 7	99.49 3	99.78 2	99.22 35	95.92 124	99.95 3	99.31 4	99.83 42	98.83 216

sd_testset		97.97 57	98.12 47	97.51 130	99.41 40	93.44 185	97.96 64	98.25 222	98.58 32	98.78 66	99.39 18	98.21 14	99.56 175	92.65 260	99.86 28	99.52 60

COLMAP_ROB	94.48 6	98.25 40	98.11 48	98.64 47	99.21 73	97.35 39	97.96 64	99.16 42	98.34 40	98.78 66	98.52 110	97.32 45	99.45 210	94.08 225	99.67 83	99.13 162
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
balanced_conf03		96.88 150	97.29 123	95.63 253	97.66 280	89.47 273	97.95 66	98.89 110	95.94 145	97.77 173	98.55 107	92.23 234	99.68 127	97.05 81	99.61 98	97.73 330

VDDNet		96.98 143	96.84 152	97.41 146	99.40 43	93.26 193	97.94 67	95.31 340	99.26 9	98.39 102	99.18 42	87.85 300	99.62 156	95.13 180	99.09 230	99.35 120

CP-MVS		97.92 70	97.56 106	98.99 14	98.99 110	97.82 19	97.93 68	98.96 102	96.11 133	96.89 225	97.45 229	96.85 83	99.78 51	95.19 171	99.63 90	99.38 112

mvsmamba		94.91 244	94.41 266	96.40 218	97.65 282	91.30 242	97.92 69	95.32 339	91.50 296	95.54 296	98.38 127	83.06 337	99.68 127	92.46 265	97.84 319	98.23 284

ANet_high		98.31 36	98.94 6	96.41 217	99.33 51	89.64 269	97.92 69	99.56 19	99.27 8	99.66 10	99.50 11	97.67 31	99.83 34	97.55 61	99.98 2	99.77 13

nrg030		98.54 22	98.62 23	98.32 67	99.22 66	95.66 94	97.90 71	99.08 63	98.31 41	99.02 44	98.74 85	97.68 30	99.61 163	97.77 52	99.85 36	99.70 26

ambc				96.56 207	98.23 204	91.68 236	97.88 72	98.13 243		98.42 98	98.56 106	94.22 183	99.04 307	94.05 228	99.35 187	98.95 193

Anonymous20240529		97.96 59	98.04 54	97.71 114	98.69 151	94.28 156	97.86 73	98.31 219	98.79 26	99.23 33	98.86 77	95.76 136	99.61 163	95.49 149	99.36 182	99.23 145

sasdasda		97.23 130	97.21 130	97.30 153	97.65 282	94.39 147	97.84 74	99.05 71	97.42 79	96.68 236	93.85 363	97.63 35	99.33 252	96.29 106	98.47 291	98.18 290

canonicalmvs		97.23 130	97.21 130	97.30 153	97.65 282	94.39 147	97.84 74	99.05 71	97.42 79	96.68 236	93.85 363	97.63 35	99.33 252	96.29 106	98.47 291	98.18 290

tfpnnormal		97.72 94	97.97 61	96.94 180	99.26 57	92.23 217	97.83 76	98.45 197	98.25 46	99.13 38	98.66 94	96.65 91	99.69 122	93.92 233	99.62 92	98.91 203

MGCFI-Net		97.20 132	97.23 128	97.08 171	97.68 275	93.71 175	97.79 77	99.09 60	97.40 84	96.59 244	93.96 361	97.67 31	99.35 247	96.43 100	98.50 290	98.17 292

Anonymous20240521		97.07 136	97.51 111	95.76 247	99.35 49	88.18 298	97.78 78	98.40 206	97.11 94	98.34 110	99.04 57	89.58 276	99.79 47	98.09 38	99.93 11	99.30 127

XVS		97.96 59	97.63 98	98.94 19	99.15 83	97.66 23	97.77 79	98.83 136	97.42 79	96.32 258	97.64 216	96.49 101	99.72 93	95.66 140	99.37 179	99.45 90

X-MVStestdata		92.86 311	90.83 340	98.94 19	99.15 83	97.66 23	97.77 79	98.83 136	97.42 79	96.32 258	36.50 419	96.49 101	99.72 93	95.66 140	99.37 179	99.45 90

VPA-MVSNet		98.27 38	98.46 30	97.70 116	99.06 100	93.80 171	97.76 81	99.00 92	98.40 38	99.07 42	98.98 62	96.89 78	99.75 72	97.19 74	99.79 52	99.55 53

dcpmvs_2		97.12 134	97.99 59	94.51 308	99.11 92	84.00 367	97.75 82	99.65 12	97.38 86	99.14 37	98.42 121	95.16 155	99.96 2	95.52 148	99.78 55	99.58 39

UGNet		96.81 157	96.56 169	97.58 124	96.64 333	93.84 170	97.75 82	97.12 294	96.47 118	93.62 345	98.88 75	93.22 205	99.53 184	95.61 144	99.69 77	99.36 118
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 73	97.53 109	99.04 8	99.22 66	97.87 18	97.74 84	98.78 150	96.04 138	97.10 206	97.73 211	96.53 98	99.78 51	95.16 175	99.50 143	99.46 86

OpenMVS	94.22 8	95.48 219	95.20 221	96.32 221	97.16 318	91.96 230	97.74 84	98.84 130	87.26 351	94.36 323	98.01 183	93.95 190	99.67 135	90.70 306	98.75 266	97.35 350

RRT-MVS		95.78 204	96.25 185	94.35 314	96.68 332	84.47 361	97.72 86	99.11 52	97.23 91	97.27 193	98.72 86	86.39 310	99.79 47	95.49 149	97.67 331	98.80 220

testf1		98.57 18	98.45 32	98.93 22	99.79 3	98.78 3	97.69 87	99.42 24	97.69 68	98.92 54	98.77 82	97.80 25	99.25 272	96.27 108	99.69 77	98.76 227

APD_test2		98.57 18	98.45 32	98.93 22	99.79 3	98.78 3	97.69 87	99.42 24	97.69 68	98.92 54	98.77 82	97.80 25	99.25 272	96.27 108	99.69 77	98.76 227

MonoMVSNet		93.30 304	93.96 282	91.33 379	94.14 400	81.33 387	97.68 89	96.69 312	95.38 177	96.32 258	98.42 121	84.12 330	96.76 403	90.78 299	92.12 403	95.89 384

MSP-MVS		97.45 115	96.92 149	99.03 9	99.26 57	97.70 22	97.66 90	98.89 110	95.65 161	98.51 87	96.46 297	92.15 236	99.81 40	95.14 178	98.58 284	99.58 39
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		95.32 227	94.88 238	96.62 201	98.03 226	91.47 239	97.65 91	90.72 393	99.11 12	97.89 162	98.31 135	79.20 354	99.48 200	93.91 234	99.12 226	98.93 199

K. test v3		96.44 178	96.28 184	96.95 179	99.41 40	91.53 237	97.65 91	90.31 397	98.89 24	98.93 53	99.36 23	84.57 326	99.92 6	97.81 48	99.56 115	99.39 110

TSAR-MVS + MP.		97.42 119	97.23 128	98.00 97	99.38 46	95.00 127	97.63 93	98.20 229	93.00 263	98.16 131	98.06 177	95.89 125	99.72 93	95.67 139	99.10 229	99.28 134
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_fmvs3		97.38 121	97.56 106	96.84 189	98.63 158	92.81 202	97.60 94	99.61 16	90.87 306	98.76 71	99.66 4	94.03 187	97.90 386	99.24 6	99.68 81	99.81 9

region2R		97.92 70	97.59 103	98.92 25	99.22 66	97.55 30	97.60 94	98.84 130	96.00 141	97.22 195	97.62 218	96.87 82	99.76 66	95.48 153	99.43 168	99.46 86

HFP-MVS		97.94 66	97.64 96	98.83 29	99.15 83	97.50 33	97.59 96	98.84 130	96.05 136	97.49 182	97.54 223	97.07 61	99.70 115	95.61 144	99.46 155	99.30 127

ACMMPR		97.95 63	97.62 100	98.94 19	99.20 75	97.56 29	97.59 96	98.83 136	96.05 136	97.46 187	97.63 217	96.77 87	99.76 66	95.61 144	99.46 155	99.49 75

RPSCF		97.87 78	97.51 111	98.95 18	99.15 83	98.43 7	97.56 98	99.06 67	96.19 130	98.48 92	98.70 91	94.72 166	99.24 276	94.37 214	99.33 195	99.17 154

KD-MVS_self_test		97.86 80	98.07 51	97.25 158	99.22 66	92.81 202	97.55 99	98.94 105	97.10 95	98.85 60	98.88 75	95.03 159	99.67 135	97.39 67	99.65 86	99.26 139

SR-MVS-dyc-post		98.14 43	97.84 72	99.02 10	98.81 132	98.05 10	97.55 99	98.86 122	97.77 60	98.20 125	98.07 172	96.60 96	99.76 66	95.49 149	99.20 213	99.26 139

RE-MVS-def			97.88 70		98.81 132	98.05 10	97.55 99	98.86 122	97.77 60	98.20 125	98.07 172	96.94 71		95.49 149	99.20 213	99.26 139

APD-MVS_3200maxsize		98.13 46	97.90 65	98.79 33	98.79 136	97.31 40	97.55 99	98.92 107	97.72 65	98.25 121	98.13 164	97.10 58	99.75 72	95.44 157	99.24 211	99.32 122

ACMH+	93.58 10	98.23 41	98.31 39	97.98 99	99.39 44	95.22 120	97.55 99	99.20 37	98.21 48	99.25 32	98.51 112	98.21 14	99.40 228	94.79 196	99.72 70	99.32 122

Vis-MVSNet (Re-imp)		95.11 236	94.85 239	95.87 243	99.12 91	89.17 278	97.54 104	94.92 346	96.50 115	96.58 245	97.27 247	83.64 333	99.48 200	88.42 343	99.67 83	98.97 191

MP-MVS		97.64 100	97.18 132	99.00 13	99.32 53	97.77 21	97.49 105	98.73 158	96.27 124	95.59 294	97.75 208	96.30 113	99.78 51	93.70 241	99.48 150	99.45 90
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		97.92 70	97.62 100	98.83 29	99.32 53	97.24 43	97.45 106	98.84 130	95.76 156	96.93 222	97.43 231	97.26 52	99.79 47	96.06 114	99.53 129	99.45 90

tttt0517		93.31 303	92.56 311	95.57 256	98.71 147	87.86 307	97.44 107	87.17 409	95.79 155	97.47 186	96.84 274	64.12 402	99.81 40	96.20 111	99.32 197	99.02 185

v10		97.55 108	97.97 61	96.31 222	98.60 162	89.64 269	97.44 107	99.02 81	96.60 108	98.72 75	99.16 46	93.48 200	99.72 93	98.76 21	99.92 14	99.58 39

v8		97.60 104	98.06 53	96.23 224	98.71 147	89.44 274	97.43 109	98.82 144	97.29 90	98.74 73	99.10 52	93.86 191	99.68 127	98.61 26	99.94 8	99.56 50

PMVS	89.60 17	96.71 165	96.97 144	95.95 238	99.51 28	97.81 20	97.42 110	97.49 282	97.93 56	95.95 277	98.58 103	96.88 80	96.91 399	89.59 326	99.36 182	93.12 407
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SR-MVS		98.00 56	97.66 92	99.01 12	98.77 140	97.93 15	97.38 111	98.83 136	97.32 88	98.06 144	97.85 197	96.65 91	99.77 61	95.00 187	99.11 227	99.32 122

FMVSNet5		93.39 301	92.35 312	96.50 210	95.83 363	90.81 253	97.31 112	98.27 220	92.74 272	96.27 263	98.28 144	62.23 404	99.67 135	90.86 295	99.36 182	99.03 182

HY-MVS	91.43 15	92.58 315	91.81 321	94.90 288	96.49 337	88.87 284	97.31 112	94.62 348	85.92 366	90.50 389	96.84 274	85.05 321	99.40 228	83.77 387	95.78 381	96.43 378

CSCG		97.40 120	97.30 122	97.69 118	98.95 115	94.83 130	97.28 114	98.99 95	96.35 123	98.13 135	95.95 323	95.99 122	99.66 141	94.36 216	99.73 66	98.59 246

MTAPA		98.14 43	97.84 72	99.06 7	99.44 36	97.90 16	97.25 115	98.73 158	97.69 68	97.90 161	97.96 187	95.81 134	99.82 36	96.13 113	99.61 98	99.45 90

CPTT-MVS		96.69 166	96.08 193	98.49 56	98.89 125	96.64 59	97.25 115	98.77 151	92.89 269	96.01 276	97.13 254	92.23 234	99.67 135	92.24 267	99.34 190	99.17 154

EU-MVSNet		94.25 273	94.47 262	93.60 332	98.14 220	82.60 377	97.24 117	92.72 370	85.08 375	98.48 92	98.94 67	82.59 341	98.76 335	97.47 65	99.53 129	99.44 100

XXY-MVS		97.54 109	97.70 86	97.07 172	99.46 34	92.21 218	97.22 118	99.00 92	94.93 197	98.58 83	98.92 69	97.31 46	99.41 226	94.44 209	99.43 168	99.59 38

APD_test1		97.95 63	97.68 90	98.75 35	99.60 16	98.60 6	97.21 119	99.08 63	96.57 113	98.07 143	98.38 127	96.22 118	99.14 290	94.71 203	99.31 200	98.52 253

GST-MVS		97.82 85	97.49 114	98.81 31	99.23 63	97.25 42	97.16 120	98.79 146	95.96 143	97.53 178	97.40 233	96.93 73	99.77 61	95.04 184	99.35 187	99.42 102

SteuartSystems-ACMMP		98.02 55	97.76 83	98.79 33	99.43 37	97.21 45	97.15 121	98.90 109	96.58 110	98.08 141	97.87 196	97.02 66	99.76 66	95.25 168	99.59 106	99.40 105
Skip Steuart: Steuart Systems R&D Blog.
FMVSNet2		96.72 163	96.67 162	96.87 186	97.96 235	91.88 231	97.15 121	98.06 252	95.59 165	98.50 89	98.62 99	89.51 280	99.65 143	94.99 189	99.60 104	99.07 177

AllTest		97.20 132	96.92 149	98.06 90	99.08 96	96.16 74	97.14 123	99.16 42	94.35 215	97.78 171	98.07 172	95.84 127	99.12 294	91.41 281	99.42 171	98.91 203

DP-MVS		97.87 78	97.89 68	97.81 108	98.62 160	94.82 131	97.13 124	98.79 146	98.98 21	98.74 73	98.49 113	95.80 135	99.49 197	95.04 184	99.44 159	99.11 170

GeoE		97.75 91	97.70 86	97.89 103	98.88 126	94.53 142	97.10 125	98.98 98	95.75 158	97.62 175	97.59 220	97.61 37	99.77 61	96.34 105	99.44 159	99.36 118

PGM-MVS		97.88 77	97.52 110	98.96 17	99.20 75	97.62 25	97.09 126	99.06 67	95.45 172	97.55 177	97.94 190	97.11 57	99.78 51	94.77 199	99.46 155	99.48 81

LPG-MVS_test		97.94 66	97.67 91	98.74 38	99.15 83	97.02 46	97.09 126	99.02 81	95.15 186	98.34 110	98.23 153	97.91 21	99.70 115	94.41 211	99.73 66	99.50 67

SF-MVS		97.60 104	97.39 117	98.22 77	98.93 120	95.69 91	97.05 128	99.10 55	95.32 179	97.83 169	97.88 195	96.44 106	99.72 93	94.59 208	99.39 177	99.25 143

reproduce_model		98.54 22	98.33 38	99.15 4	99.06 100	98.04 12	97.04 129	99.09 60	98.42 37	99.03 43	98.71 89	96.93 73	99.83 34	97.09 77	99.63 90	99.56 50

VDD-MVS		97.37 123	97.25 126	97.74 112	98.69 151	94.50 145	97.04 129	95.61 332	98.59 31	98.51 87	98.72 86	92.54 227	99.58 168	96.02 119	99.49 146	99.12 167

wuyk23d		93.25 306	95.20 221	87.40 397	96.07 354	95.38 107	97.04 129	94.97 344	95.33 178	99.70 7	98.11 168	98.14 17	91.94 415	77.76 406	99.68 81	74.89 415

LCM-MVSNet-Re		97.33 126	97.33 121	97.32 152	98.13 223	93.79 172	96.99 132	99.65 12	96.74 104	99.47 18	98.93 68	96.91 77	99.84 32	90.11 317	99.06 236	98.32 273

MAR-MVS		94.21 276	93.03 296	97.76 111	96.94 327	97.44 37	96.97 133	97.15 292	87.89 349	92.00 378	92.73 379	92.14 237	99.12 294	83.92 384	97.51 339	96.73 371
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		95.67 210	95.89 204	95.03 280	98.18 211	89.89 264	96.94 134	99.28 31	88.25 344	98.20 125	98.92 69	86.69 309	97.19 394	97.70 57	98.82 260	98.00 310

SDMVSNet		97.97 57	98.26 45	97.11 166	99.41 40	92.21 218	96.92 135	98.60 183	98.58 32	98.78 66	99.39 18	97.80 25	99.62 156	94.98 190	99.86 28	99.52 60

h-mvs33		96.29 183	95.63 214	98.26 72	98.50 178	96.11 77	96.90 136	97.09 295	96.58 110	97.21 197	98.19 158	84.14 328	99.78 51	95.89 128	96.17 375	98.89 207

test0726					99.24 61	95.51 99	96.89 137	98.89 110	95.92 147	98.64 76	98.31 135	97.06 62

baseline		97.44 116	97.78 82	96.43 214	98.52 173	90.75 254	96.84 138	99.03 79	96.51 114	97.86 167	98.02 181	96.67 90	99.36 243	97.09 77	99.47 152	99.19 151

API-MVS		95.09 238	95.01 231	95.31 268	96.61 334	94.02 163	96.83 139	97.18 291	95.60 164	95.79 285	94.33 358	94.54 175	98.37 373	85.70 369	98.52 286	93.52 404

test_vis3_rt		97.04 137	96.98 143	97.23 160	98.44 185	95.88 84	96.82 140	99.67 9	90.30 315	99.27 30	99.33 28	94.04 186	96.03 407	97.14 75	97.83 320	99.78 12

reproduce-ours		98.48 26	98.27 43	99.12 5	98.99 110	98.02 13	96.81 141	99.02 81	98.29 44	98.97 51	98.61 100	97.27 48	99.82 36	96.86 88	99.61 98	99.51 64

our_new_method		98.48 26	98.27 43	99.12 5	98.99 110	98.02 13	96.81 141	99.02 81	98.29 44	98.97 51	98.61 100	97.27 48	99.82 36	96.86 88	99.61 98	99.51 64

test_fmvs1_n		95.21 231	95.28 219	94.99 283	98.15 218	89.13 281	96.81 141	99.43 23	86.97 357	97.21 197	98.92 69	83.00 338	97.13 395	98.09 38	98.94 245	98.72 232

test_fmvs2		96.38 181	96.45 177	96.16 229	97.85 242	91.30 242	96.81 141	99.45 21	89.24 328	98.49 90	99.38 20	88.68 287	97.62 391	98.83 18	99.32 197	99.57 46

SED-MVS		97.94 66	97.90 65	98.07 88	99.22 66	95.35 110	96.79 145	98.83 136	96.11 133	99.08 40	98.24 151	97.87 23	99.72 93	95.44 157	99.51 139	99.14 160

OPU-MVS				97.64 121	98.01 229	95.27 115	96.79 145				97.35 242	96.97 69	98.51 361	91.21 287	99.25 208	99.14 160

PHI-MVS		96.96 144	96.53 173	98.25 75	97.48 296	96.50 63	96.76 147	98.85 126	93.52 240	96.19 269	96.85 273	95.94 123	99.42 217	93.79 237	99.43 168	98.83 216

DVP-MVS		97.78 89	97.65 93	98.16 81	99.24 61	95.51 99	96.74 148	98.23 225	95.92 147	98.40 100	98.28 144	97.06 62	99.71 107	95.48 153	99.52 134	99.26 139
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	96.74 148	98.89 110					99.75 72	95.48 153	99.52 134	99.53 57

Anonymous202405211		96.34 182	95.98 198	97.43 143	98.25 201	93.85 169	96.74 148	94.41 351	97.72 65	98.37 103	98.03 180	87.15 305	99.53 184	94.06 226	99.07 233	98.92 202

SMA-MVS		97.48 113	97.11 134	98.60 49	98.83 131	96.67 57	96.74 148	98.73 158	91.61 293	98.48 92	98.36 129	96.53 98	99.68 127	95.17 173	99.54 125	99.45 90
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 41	98.43 60	99.07 98	95.87 85	96.73 152	99.05 71	98.67 28	98.84 61	98.45 118	97.58 38	99.88 21	96.45 99	99.86 28	99.54 54

test_0402		97.84 81	97.97 61	97.47 139	99.19 77	94.07 161	96.71 153	98.73 158	98.66 29	98.56 84	98.41 123	96.84 84	99.69 122	94.82 194	99.81 47	98.64 240

test_fmvsmconf0.01_n		98.57 18	98.74 17	98.06 90	99.39 44	94.63 138	96.70 154	99.82 1	95.44 174	99.64 11	99.52 9	98.96 4	99.74 81	99.38 3	99.86 28	99.81 9

SSC-MVS		95.92 198	97.03 141	92.58 361	99.28 55	78.39 398	96.68 155	95.12 342	98.90 23	99.11 39	98.66 94	91.36 251	99.68 127	95.00 187	99.16 219	99.67 28

ACMM	93.33 11	98.05 53	97.79 79	98.85 28	99.15 83	97.55 30	96.68 155	98.83 136	95.21 182	98.36 106	98.13 164	98.13 18	99.62 156	96.04 117	99.54 125	99.39 110
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		93.14 308	92.64 309	94.62 301	97.34 309	87.20 322	96.67 157	93.02 365	94.71 202	96.51 250	95.83 326	81.64 342	98.60 354	90.00 320	88.06 411	98.07 298

fmvsm_s_conf0.1_n_a		97.80 87	98.01 57	97.18 161	99.17 79	92.51 210	96.57 158	99.15 46	93.68 237	98.89 57	99.30 29	96.42 107	99.37 240	99.03 13	99.83 42	99.66 30

MTMP							96.55 159	74.60 420

SD-MVS		97.37 123	97.70 86	96.35 219	98.14 220	95.13 124	96.54 160	98.92 107	95.94 145	99.19 35	98.08 170	97.74 28	95.06 409	95.24 169	99.54 125	98.87 213
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		96.66 168	96.33 183	97.68 119	98.70 149	94.29 153	96.50 161	98.75 155	96.36 121	96.16 270	96.77 280	91.91 246	99.46 205	92.59 262	99.20 213	99.28 134

plane_prior2							96.50 161		96.36 121

Effi-MVS+-dtu		96.81 157	96.09 192	98.99 14	96.90 329	98.69 5	96.42 163	98.09 246	95.86 152	95.15 304	95.54 334	94.26 182	99.81 40	94.06 226	98.51 289	98.47 258

MM		96.87 151	96.62 163	97.62 122	97.72 272	93.30 190	96.39 164	92.61 373	97.90 58	96.76 233	98.64 98	90.46 263	99.81 40	99.16 9	99.94 8	99.76 18

thres100view900		91.76 333	91.26 333	93.26 338	98.21 205	84.50 360	96.39 164	90.39 394	96.87 100	96.33 257	93.08 371	73.44 386	99.42 217	78.85 403	97.74 324	95.85 385

XVG-ACMP-BASELINE		97.58 107	97.28 125	98.49 56	99.16 80	96.90 50	96.39 164	98.98 98	95.05 191	98.06 144	98.02 181	95.86 126	99.56 175	94.37 214	99.64 88	99.00 186

Patchmtry		95.03 241	94.59 256	96.33 220	94.83 389	90.82 251	96.38 167	97.20 289	96.59 109	97.49 182	98.57 104	77.67 361	99.38 235	92.95 259	99.62 92	98.80 220

fmvsm_s_conf0.1_n		97.73 92	98.02 56	96.85 187	99.09 95	91.43 241	96.37 168	99.11 52	94.19 220	99.01 45	99.25 32	96.30 113	99.38 235	99.00 14	99.88 24	99.73 22

ACMMP_NAP		97.89 76	97.63 98	98.67 44	99.35 49	96.84 51	96.36 169	98.79 146	95.07 190	97.88 163	98.35 130	97.24 54	99.72 93	96.05 116	99.58 109	99.45 90

VNet		96.84 152	96.83 153	96.88 185	98.06 225	92.02 228	96.35 170	97.57 281	97.70 67	97.88 163	97.80 204	92.40 232	99.54 182	94.73 201	98.96 242	99.08 175

V42		97.04 137	97.16 133	96.68 200	98.59 164	91.05 246	96.33 171	98.36 211	94.60 206	97.99 150	98.30 139	93.32 202	99.62 156	97.40 66	99.53 129	99.38 112

test_fmvsmvis_n_1920		98.08 49	98.47 29	96.93 181	99.03 107	93.29 191	96.32 172	99.65 12	95.59 165	99.71 5	99.01 58	97.66 33	99.60 165	99.44 2	99.83 42	97.90 316

APD-MVS		97.00 139	96.53 173	98.41 61	98.55 169	96.31 70	96.32 172	98.77 151	92.96 268	97.44 188	97.58 222	95.84 127	99.74 81	91.96 270	99.35 187	99.19 151
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPNet		97.26 129	97.49 114	96.59 203	99.47 33	90.58 256	96.27 174	98.53 190	97.77 60	98.46 95	98.41 123	94.59 172	99.68 127	94.61 204	99.29 203	99.52 60

thres600view7		92.03 328	91.43 326	93.82 326	98.19 208	84.61 359	96.27 174	90.39 394	96.81 102	96.37 256	93.11 367	73.44 386	99.49 197	80.32 398	97.95 314	97.36 348

EPNet		93.72 291	92.62 310	97.03 176	87.61 422	92.25 216	96.27 174	91.28 386	96.74 104	87.65 408	97.39 237	85.00 322	99.64 147	92.14 268	99.48 150	99.20 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DSMNet-mixed		92.19 322	91.83 320	93.25 339	96.18 347	83.68 370	96.27 174	93.68 358	76.97 411	92.54 374	99.18 42	89.20 285	98.55 358	83.88 385	98.60 283	97.51 343

fmvsm_s_conf0.5_n_a		97.65 99	97.83 75	97.13 165	98.80 134	92.51 210	96.25 178	99.06 67	93.67 238	98.64 76	99.00 59	96.23 117	99.36 243	98.99 15	99.80 50	99.53 57

ACMP	92.54 13	97.47 114	97.10 135	98.55 53	99.04 106	96.70 55	96.24 179	98.89 110	93.71 234	97.97 154	97.75 208	97.44 40	99.63 151	93.22 253	99.70 76	99.32 122
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS	95.41 4	97.82 85	97.70 86	98.16 81	98.78 139	95.72 89	96.23 180	99.02 81	93.92 230	98.62 78	98.99 61	97.69 29	99.62 156	96.18 112	99.87 26	99.15 157
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PM-MVS		97.36 125	97.10 135	98.14 84	98.91 124	96.77 53	96.20 181	98.63 181	93.82 231	98.54 85	98.33 133	93.98 188	99.05 305	95.99 122	99.45 158	98.61 245

test_fmvsmconf0.1_n		98.41 31	98.54 27	98.03 95	99.16 80	94.61 139	96.18 182	99.73 5	95.05 191	99.60 15	99.34 26	98.68 8	99.72 93	99.21 7	99.85 36	99.76 18

MVS_Test		96.27 184	96.79 157	94.73 298	96.94 327	86.63 331	96.18 182	98.33 215	94.94 195	96.07 273	98.28 144	95.25 153	99.26 270	97.21 71	97.90 317	98.30 277

CR-MVSNet		93.29 305	92.79 303	94.78 296	95.44 376	88.15 299	96.18 182	97.20 289	84.94 380	94.10 329	98.57 104	77.67 361	99.39 232	95.17 173	95.81 378	96.81 368

RPMNet		94.68 258	94.60 254	94.90 288	95.44 376	88.15 299	96.18 182	98.86 122	97.43 78	94.10 329	98.49 113	79.40 353	99.76 66	95.69 137	95.81 378	96.81 368

test_fmvsm_n_1920		98.08 49	98.29 42	97.43 143	98.88 126	93.95 166	96.17 186	99.57 17	95.66 160	99.52 16	98.71 89	97.04 64	99.64 147	99.21 7	99.87 26	98.69 236

fmvsm_s_conf0.5_n		97.62 102	97.89 68	96.80 191	98.79 136	91.44 240	96.14 187	99.06 67	94.19 220	98.82 63	98.98 62	96.22 118	99.38 235	98.98 16	99.86 28	99.58 39

WB-MVS		95.50 216	96.62 163	92.11 371	99.21 73	77.26 408	96.12 188	95.40 338	98.62 30	98.84 61	98.26 149	91.08 254	99.50 192	93.37 246	98.70 272	99.58 39

EIA-MVS		96.04 193	95.77 209	96.85 187	97.80 255	92.98 198	96.12 188	99.16 42	94.65 204	93.77 340	91.69 392	95.68 138	99.67 135	94.18 221	98.85 256	97.91 315

Effi-MVS+		96.19 187	96.01 195	96.71 197	97.43 302	92.19 222	96.12 188	99.10 55	95.45 172	93.33 356	94.71 350	97.23 55	99.56 175	93.21 254	97.54 337	98.37 266

alignmvs		96.01 195	95.52 217	97.50 134	97.77 264	94.71 133	96.07 191	96.84 304	97.48 77	96.78 232	94.28 359	85.50 319	99.40 228	96.22 110	98.73 270	98.40 262

PatchT		93.75 290	93.57 288	94.29 318	95.05 385	87.32 320	96.05 192	92.98 366	97.54 75	94.25 324	98.72 86	75.79 374	99.24 276	95.92 126	95.81 378	96.32 379

Patchmatch-test		93.60 296	93.25 293	94.63 300	96.14 352	87.47 316	96.04 193	94.50 350	93.57 239	96.47 251	96.97 265	76.50 369	98.61 352	90.67 307	98.41 296	97.81 324

thisisatest0530		92.71 314	91.76 323	95.56 258	98.42 187	88.23 296	96.03 194	87.35 408	94.04 227	96.56 247	95.47 336	64.03 403	99.77 61	94.78 198	99.11 227	98.68 239

9.14			96.69 160		98.53 172		96.02 195	98.98 98	93.23 250	97.18 200	97.46 228	96.47 103	99.62 156	92.99 257	99.32 197

DeepC-MVS_fast	94.34 7	96.74 160	96.51 175	97.44 142	97.69 274	94.15 159	96.02 195	98.43 200	93.17 258	97.30 191	97.38 239	95.48 144	99.28 266	93.74 238	99.34 190	98.88 211
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ttmdpeth		94.05 283	94.15 275	93.75 328	95.81 365	85.32 345	96.00 197	94.93 345	92.07 282	94.19 326	99.09 53	85.73 316	96.41 406	90.98 291	98.52 286	99.53 57

test_fmvsmconf_n		98.30 37	98.41 35	97.99 98	98.94 118	94.60 140	96.00 197	99.64 15	94.99 194	99.43 20	99.18 42	98.51 10	99.71 107	99.13 10	99.84 38	99.67 28

114514_t		93.96 286	93.22 294	96.19 227	99.06 100	90.97 249	95.99 199	98.94 105	73.88 414	93.43 353	96.93 268	92.38 233	99.37 240	89.09 333	99.28 204	98.25 283

FMVSNet3		95.26 230	94.94 232	96.22 226	96.53 336	90.06 260	95.99 199	97.66 273	94.11 224	97.99 150	97.91 194	80.22 352	99.63 151	94.60 205	99.44 159	98.96 192

HPM-MVS++		96.99 140	96.38 180	98.81 31	98.64 154	97.59 27	95.97 201	98.20 229	95.51 169	95.06 306	96.53 293	94.10 185	99.70 115	94.29 217	99.15 220	99.13 162

casdiffmvs_mvg		97.83 82	98.11 48	97.00 178	98.57 166	92.10 226	95.97 201	99.18 40	97.67 71	99.00 47	98.48 117	97.64 34	99.50 192	96.96 84	99.54 125	99.40 105
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		96.07 191	96.50 176	94.80 294	99.26 57	87.69 313	95.96 203	98.58 187	95.08 189	98.02 149	96.25 308	97.92 20	97.60 392	88.68 340	98.74 267	99.11 170

EG-PatchMatch MVS		97.69 96	97.79 79	97.40 147	99.06 100	93.52 183	95.96 203	98.97 101	94.55 210	98.82 63	98.76 84	97.31 46	99.29 264	97.20 73	99.44 159	99.38 112

PAPM_NR		94.61 262	94.17 274	95.96 236	98.36 191	91.23 244	95.93 205	97.95 254	92.98 264	93.42 354	94.43 357	90.53 261	98.38 371	87.60 353	96.29 372	98.27 281

UniMVSNet (Re)		97.83 82	97.65 93	98.35 66	98.80 134	95.86 86	95.92 206	99.04 78	97.51 76	98.22 124	97.81 203	94.68 169	99.78 51	97.14 75	99.75 64	99.41 104

test_vis1_n_1920		95.77 205	96.41 179	93.85 325	98.55 169	84.86 356	95.91 207	99.71 6	92.72 273	97.67 174	98.90 73	87.44 303	98.73 337	97.96 42	98.85 256	97.96 312

fmvsm_l_conf0.5_n		97.68 98	97.81 77	97.27 155	98.92 122	92.71 207	95.89 208	99.41 26	93.36 245	99.00 47	98.44 120	96.46 105	99.65 143	99.09 11	99.76 57	99.45 90

1314		92.38 318	92.30 313	92.64 360	95.42 378	85.15 350	95.86 209	96.97 301	85.40 373	90.62 386	93.06 372	91.12 253	97.80 389	86.74 364	95.49 386	94.97 397

MVS		90.02 349	89.20 356	92.47 364	94.71 390	86.90 327	95.86 209	96.74 310	64.72 416	90.62 386	92.77 377	92.54 227	98.39 370	79.30 401	95.56 385	92.12 408

fmvsm_l_conf0.5_n_a		97.60 104	97.76 83	97.11 166	98.92 122	92.28 215	95.83 211	99.32 27	93.22 251	98.91 56	98.49 113	96.31 112	99.64 147	99.07 12	99.76 57	99.40 105

casdiffmvs		97.50 111	97.81 77	96.56 207	98.51 175	91.04 247	95.83 211	99.09 60	97.23 91	98.33 113	98.30 139	97.03 65	99.37 240	96.58 95	99.38 178	99.28 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVStest1		91.89 330	91.45 325	93.21 342	89.01 419	84.87 355	95.82 213	95.05 343	91.50 296	98.75 72	99.19 38	57.56 408	95.11 408	97.78 51	98.37 297	99.64 35

tpmvs		90.79 345	90.87 338	90.57 384	92.75 413	76.30 410	95.79 214	93.64 360	91.04 305	91.91 379	96.26 307	77.19 367	98.86 327	89.38 330	89.85 408	96.56 375

mvsany_test3		96.21 186	95.93 202	97.05 173	97.40 304	94.33 152	95.76 215	94.20 353	89.10 329	99.36 25	99.60 8	93.97 189	97.85 387	95.40 164	98.63 279	98.99 189

MSLP-MVS++		96.42 180	96.71 159	95.57 256	97.82 250	90.56 258	95.71 216	98.84 130	94.72 201	96.71 235	97.39 237	94.91 164	98.10 384	95.28 166	99.02 238	98.05 305

tfpn200view9		91.55 335	91.00 335	93.21 342	98.02 227	84.35 363	95.70 217	90.79 391	96.26 125	95.90 282	92.13 387	73.62 383	99.42 217	78.85 403	97.74 324	95.85 385

Anonymous20231206		95.27 229	95.06 230	95.88 242	98.72 144	89.37 275	95.70 217	97.85 260	88.00 347	96.98 219	97.62 218	91.95 243	99.34 250	89.21 331	99.53 129	98.94 195

thres400		91.68 334	91.00 335	93.71 330	98.02 227	84.35 363	95.70 217	90.79 391	96.26 125	95.90 282	92.13 387	73.62 383	99.42 217	78.85 403	97.74 324	97.36 348

reproduce_monomvs		92.05 327	92.26 314	91.43 377	95.42 378	75.72 413	95.68 220	97.05 298	94.47 211	97.95 157	98.35 130	55.58 415	99.05 305	96.36 103	99.44 159	99.51 64

test20.03		96.58 172	96.61 165	96.48 212	98.49 179	91.72 235	95.68 220	97.69 270	96.81 102	98.27 120	97.92 193	94.18 184	98.71 340	90.78 299	99.66 85	99.00 186

hse-mvs2		95.77 205	95.09 227	97.79 109	97.84 247	95.51 99	95.66 222	95.43 337	96.58 110	97.21 197	96.16 311	84.14 328	99.54 182	95.89 128	96.92 351	98.32 273

UniMVSNet_NR-MVSNet		97.83 82	97.65 93	98.37 64	98.72 144	95.78 87	95.66 222	99.02 81	98.11 51	98.31 116	97.69 214	94.65 171	99.85 29	97.02 82	99.71 73	99.48 81

dmvs_re		92.08 326	91.27 331	94.51 308	97.16 318	92.79 205	95.65 224	92.64 372	94.11 224	92.74 367	90.98 399	83.41 335	94.44 413	80.72 397	94.07 396	96.29 380

DU-MVS		97.79 88	97.60 102	98.36 65	98.73 142	95.78 87	95.65 224	98.87 119	97.57 72	98.31 116	97.83 198	94.69 167	99.85 29	97.02 82	99.71 73	99.46 86

EPMVS		89.26 360	88.55 362	91.39 378	92.36 414	79.11 397	95.65 224	79.86 418	88.60 338	93.12 359	96.53 293	70.73 394	98.10 384	90.75 301	89.32 409	96.98 357

MVP-Stereo		95.69 208	95.28 219	96.92 182	98.15 218	93.03 197	95.64 227	98.20 229	90.39 314	96.63 242	97.73 211	91.63 248	99.10 300	91.84 275	97.31 347	98.63 242
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_cas_vis1_n_1920		95.34 225	95.67 211	94.35 314	98.21 205	86.83 329	95.61 228	99.26 32	90.45 313	98.17 130	98.96 65	84.43 327	98.31 376	96.74 90	99.17 218	97.90 316

test_f		95.82 203	95.88 205	95.66 252	97.61 287	93.21 195	95.61 228	98.17 235	86.98 356	98.42 98	99.47 13	90.46 263	94.74 411	97.71 55	98.45 293	99.03 182

F-COLMAP		95.30 228	94.38 267	98.05 94	98.64 154	96.04 79	95.61 228	98.66 175	89.00 332	93.22 357	96.40 302	92.90 214	99.35 247	87.45 358	97.53 338	98.77 226

AUN-MVS		93.95 288	92.69 307	97.74 112	97.80 255	95.38 107	95.57 231	95.46 336	91.26 302	92.64 371	96.10 317	74.67 377	99.55 179	93.72 240	96.97 350	98.30 277

v144192		96.69 166	96.90 151	96.03 233	98.25 201	88.92 282	95.49 232	98.77 151	93.05 261	98.09 139	98.29 143	92.51 230	99.70 115	98.11 37	99.56 115	99.47 84

Fast-Effi-MVS+-dtu		96.44 178	96.12 190	97.39 148	97.18 317	94.39 147	95.46 233	98.73 158	96.03 140	94.72 314	94.92 347	96.28 116	99.69 122	93.81 236	97.98 312	98.09 295

Baseline_NR-MVSNet		97.72 94	97.79 79	97.50 134	99.56 20	93.29 191	95.44 234	98.86 122	98.20 49	98.37 103	99.24 33	94.69 167	99.55 179	95.98 123	99.79 52	99.65 33

LF4IMVS		96.07 191	95.63 214	97.36 149	98.19 208	95.55 96	95.44 234	98.82 144	92.29 281	95.70 291	96.55 291	92.63 222	98.69 343	91.75 279	99.33 195	97.85 320

v1921920		96.72 163	96.96 146	95.99 234	98.21 205	88.79 287	95.42 236	98.79 146	93.22 251	98.19 129	98.26 149	92.68 219	99.70 115	98.34 34	99.55 121	99.49 75

plane_prior						94.29 153	95.42 236		94.31 217						98.93 247

v1144		96.84 152	97.08 137	96.13 231	98.42 187	89.28 277	95.41 238	98.67 173	94.21 218	97.97 154	98.31 135	93.06 208	99.65 143	98.06 40	99.62 92	99.45 90

ETV-MVS		96.13 190	95.90 203	96.82 190	97.76 265	93.89 167	95.40 239	98.95 104	95.87 151	95.58 295	91.00 398	96.36 111	99.72 93	93.36 247	98.83 259	96.85 364

v1240		96.74 160	97.02 142	95.91 241	98.18 211	88.52 290	95.39 240	98.88 117	93.15 259	98.46 95	98.40 126	92.80 216	99.71 107	98.45 31	99.49 146	99.49 75

MP-MVS-pluss		97.69 96	97.36 119	98.70 42	99.50 31	96.84 51	95.38 241	98.99 95	92.45 278	98.11 136	98.31 135	97.25 53	99.77 61	96.60 93	99.62 92	99.48 81
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MVS_0304		95.71 207	95.18 223	97.33 151	94.85 387	92.82 200	95.36 242	90.89 390	95.51 169	95.61 293	97.82 201	88.39 291	99.78 51	98.23 35	99.91 17	99.40 105

v1192		96.83 155	97.06 139	96.15 230	98.28 197	89.29 276	95.36 242	98.77 151	93.73 233	98.11 136	98.34 132	93.02 213	99.67 135	98.35 33	99.58 109	99.50 67

v2v482		96.78 159	97.06 139	95.95 238	98.57 166	88.77 288	95.36 242	98.26 221	95.18 185	97.85 168	98.23 153	92.58 223	99.63 151	97.80 49	99.69 77	99.45 90

test_fmvs1		94.51 267	94.60 254	94.26 319	95.91 357	87.92 305	95.35 245	99.02 81	86.56 361	96.79 228	98.52 110	82.64 340	97.00 398	97.87 45	98.71 271	97.88 318

EI-MVSNet-Vis-set		97.32 127	97.39 117	97.11 166	97.36 306	92.08 227	95.34 246	97.65 275	97.74 63	98.29 119	98.11 168	95.05 157	99.68 127	97.50 63	99.50 143	99.56 50

EI-MVSNet-UG-set		97.32 127	97.40 116	97.09 170	97.34 309	92.01 229	95.33 247	97.65 275	97.74 63	98.30 118	98.14 162	95.04 158	99.69 122	97.55 61	99.52 134	99.58 39

CostFormer		89.75 355	89.25 353	91.26 380	94.69 391	78.00 402	95.32 248	91.98 378	81.50 394	90.55 388	96.96 267	71.06 392	98.89 323	88.59 341	92.63 401	96.87 362

PVSNet_Blended_VisFu		95.95 197	95.80 207	96.42 215	99.28 55	90.62 255	95.31 249	99.08 63	88.40 341	96.97 220	98.17 161	92.11 238	99.78 51	93.64 242	99.21 212	98.86 214

UnsupCasMVSNet_eth		95.91 199	95.73 210	96.44 213	98.48 181	91.52 238	95.31 249	98.45 197	95.76 156	97.48 184	97.54 223	89.53 279	98.69 343	94.43 210	94.61 393	99.13 162

EI-MVSNet		96.63 169	96.93 147	95.74 248	97.26 314	88.13 301	95.29 251	97.65 275	96.99 96	97.94 158	98.19 158	92.55 225	99.58 168	96.91 85	99.56 115	99.50 67

CVMVSNet		92.33 320	92.79 303	90.95 381	97.26 314	75.84 412	95.29 251	92.33 375	81.86 391	96.27 263	98.19 158	81.44 344	98.46 366	94.23 220	98.29 301	98.55 250

OPM-MVS		97.54 109	97.25 126	98.41 61	99.11 92	96.61 60	95.24 253	98.46 196	94.58 209	98.10 138	98.07 172	97.09 60	99.39 232	95.16 175	99.44 159	99.21 147
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TAPA-MVS	93.32 12	94.93 243	94.23 270	97.04 175	98.18 211	94.51 143	95.22 254	98.73 158	81.22 396	96.25 265	95.95 323	93.80 194	98.98 315	89.89 322	98.87 253	97.62 337
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPE-MVS		97.64 100	97.35 120	98.50 55	98.85 130	96.18 73	95.21 255	98.99 95	95.84 153	98.78 66	98.08 170	96.84 84	99.81 40	93.98 231	99.57 112	99.52 60
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MVSTER		94.21 276	93.93 283	95.05 279	95.83 363	86.46 332	95.18 256	97.65 275	92.41 279	97.94 158	98.00 185	72.39 388	99.58 168	96.36 103	99.56 115	99.12 167

PatchmatchNet		91.98 329	91.87 319	92.30 367	94.60 392	79.71 394	95.12 257	93.59 361	89.52 325	93.61 346	97.02 262	77.94 359	99.18 283	90.84 296	94.57 395	98.01 309
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
IterMVS-LS		96.92 146	97.29 123	95.79 245	98.51 175	88.13 301	95.10 258	98.66 175	96.99 96	98.46 95	98.68 93	92.55 225	99.74 81	96.91 85	99.79 52	99.50 67
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v148		96.58 172	96.97 144	95.42 265	98.63 158	87.57 314	95.09 259	97.90 257	95.91 149	98.24 122	97.96 187	93.42 201	99.39 232	96.04 117	99.52 134	99.29 133

tpm2		88.47 367	87.69 370	90.79 382	94.98 386	77.34 406	95.09 259	91.83 379	77.51 410	89.40 400	96.41 300	67.83 399	98.73 337	83.58 389	92.60 402	96.29 380

OpenMVS_ROB	91.80 14	93.64 295	93.05 295	95.42 265	97.31 313	91.21 245	95.08 261	96.68 313	81.56 393	96.88 226	96.41 300	90.44 265	99.25 272	85.39 375	97.67 331	95.80 387

TAMVS		95.49 217	94.94 232	97.16 162	98.31 193	93.41 188	95.07 262	96.82 306	91.09 304	97.51 180	97.82 201	89.96 272	99.42 217	88.42 343	99.44 159	98.64 240

tpmrst		90.31 347	90.61 345	89.41 389	94.06 401	72.37 420	95.06 263	93.69 356	88.01 346	92.32 376	96.86 272	77.45 363	98.82 328	91.04 289	87.01 412	97.04 356

ADS-MVSNet2		91.47 337	90.51 346	94.36 313	95.51 374	85.63 340	95.05 264	95.70 327	83.46 387	92.69 368	96.84 274	79.15 355	99.41 226	85.66 371	90.52 405	98.04 306

ADS-MVSNet		90.95 344	90.26 348	93.04 346	95.51 374	82.37 378	95.05 264	93.41 362	83.46 387	92.69 368	96.84 274	79.15 355	98.70 341	85.66 371	90.52 405	98.04 306

tpm		91.08 342	90.85 339	91.75 374	95.33 380	78.09 400	95.03 266	91.27 387	88.75 335	93.53 349	97.40 233	71.24 390	99.30 260	91.25 286	93.87 397	97.87 319

NCCC		96.52 174	95.99 197	98.10 87	97.81 251	95.68 92	95.00 267	98.20 229	95.39 176	95.40 300	96.36 304	93.81 193	99.45 210	93.55 244	98.42 295	99.17 154

test_post1							94.98 268				10.37 423	76.21 372	99.04 307	89.47 328

AdaColmap		95.11 236	94.62 253	96.58 204	97.33 311	94.45 146	94.92 269	98.08 247	93.15 259	93.98 336	95.53 335	94.34 180	99.10 300	85.69 370	98.61 281	96.20 382

MDTV_nov1_ep13_2view						57.28 424	94.89 270		80.59 398	94.02 334		78.66 357		85.50 373		97.82 322

CNVR-MVS		96.92 146	96.55 170	98.03 95	98.00 233	95.54 97	94.87 271	98.17 235	94.60 206	96.38 255	97.05 260	95.67 139	99.36 243	95.12 181	99.08 231	99.19 151

OMC-MVS		96.48 176	96.00 196	97.91 102	98.30 194	96.01 82	94.86 272	98.60 183	91.88 288	97.18 200	97.21 251	96.11 120	99.04 307	90.49 313	99.34 190	98.69 236

testing3		89.72 356	88.26 365	94.10 323	97.66 280	84.30 365	94.80 273	88.25 406	94.66 203	95.07 305	92.51 382	41.15 424	99.43 215	91.81 276	98.44 294	98.55 250

EPNet_dtu		91.39 338	90.75 341	93.31 337	90.48 418	82.61 376	94.80 273	92.88 367	93.39 244	81.74 416	94.90 348	81.36 345	99.11 297	88.28 345	98.87 253	98.21 287
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13			91.28 330		94.31 394	73.51 418	94.80 273	93.16 364	86.75 360	93.45 352	97.40 233	76.37 370	98.55 358	88.85 336	96.43 367

pmmvs-eth3d		96.49 175	96.18 189	97.42 145	98.25 201	94.29 153	94.77 276	98.07 251	89.81 322	97.97 154	98.33 133	93.11 207	99.08 302	95.46 156	99.84 38	98.89 207

test_yl		94.40 269	94.00 279	95.59 254	96.95 325	89.52 271	94.75 277	95.55 334	96.18 131	96.79 228	96.14 314	81.09 347	99.18 283	90.75 301	97.77 321	98.07 298

DCV-MVSNet		94.40 269	94.00 279	95.59 254	96.95 325	89.52 271	94.75 277	95.55 334	96.18 131	96.79 228	96.14 314	81.09 347	99.18 283	90.75 301	97.77 321	98.07 298

dmvs_testset		87.30 378	86.99 375	88.24 394	96.71 331	77.48 405	94.68 279	86.81 411	92.64 274	89.61 399	87.01 413	85.91 314	93.12 414	61.04 418	88.49 410	94.13 401

MCST-MVS		96.24 185	95.80 207	97.56 125	98.75 141	94.13 160	94.66 280	98.17 235	90.17 318	96.21 267	96.10 317	95.14 156	99.43 215	94.13 224	98.85 256	99.13 162

XVG-OURS-SEG-HR		97.38 121	97.07 138	98.30 70	99.01 109	97.41 38	94.66 280	99.02 81	95.20 183	98.15 133	97.52 225	98.83 5	98.43 367	94.87 192	96.41 368	99.07 177

mvs_anonymous		95.36 224	96.07 194	93.21 342	96.29 341	81.56 384	94.60 282	97.66 273	93.30 248	96.95 221	98.91 72	93.03 212	99.38 235	96.60 93	97.30 348	98.69 236

DP-MVS Recon		95.55 215	95.13 225	96.80 191	98.51 175	93.99 165	94.60 282	98.69 168	90.20 317	95.78 287	96.21 310	92.73 218	98.98 315	90.58 309	98.86 255	97.42 347

save fliter					98.48 181	94.71 133	94.53 284	98.41 204	95.02 193

patch_mono-2		96.59 170	96.93 147	95.55 259	98.88 126	87.12 323	94.47 285	99.30 29	94.12 223	96.65 241	98.41 123	94.98 162	99.87 24	95.81 134	99.78 55	99.66 30

tpm cat1		88.01 372	87.33 372	90.05 388	94.48 393	76.28 411	94.47 285	94.35 352	73.84 415	89.26 401	95.61 333	73.64 382	98.30 377	84.13 383	86.20 413	95.57 392

CANet		95.86 201	95.65 213	96.49 211	96.41 339	90.82 251	94.36 287	98.41 204	94.94 195	92.62 373	96.73 283	92.68 219	99.71 107	95.12 181	99.60 104	98.94 195

WR-MVS		96.90 148	96.81 154	97.16 162	98.56 168	92.20 221	94.33 288	98.12 244	97.34 87	98.20 125	97.33 244	92.81 215	99.75 72	94.79 196	99.81 47	99.54 54

HQP-NCC					97.85 242		94.26 289		93.18 255	92.86 364

ACMP_Plane					97.85 242		94.26 289		93.18 255	92.86 364

HQP-MVS		95.17 235	94.58 257	96.92 182	97.85 242	92.47 212	94.26 289	98.43 200	93.18 255	92.86 364	95.08 341	90.33 266	99.23 278	90.51 311	98.74 267	99.05 181

PLC	91.02 16	94.05 283	92.90 299	97.51 130	98.00 233	95.12 125	94.25 292	98.25 222	86.17 363	91.48 383	95.25 339	91.01 255	99.19 282	85.02 379	96.69 363	98.22 286
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
1112_ss		94.12 279	93.42 290	96.23 224	98.59 164	90.85 250	94.24 293	98.85 126	85.49 370	92.97 362	94.94 345	86.01 313	99.64 147	91.78 277	97.92 315	98.20 288

MS-PatchMatch		94.83 248	94.91 236	94.57 305	96.81 330	87.10 324	94.23 294	97.34 286	88.74 336	97.14 202	97.11 256	91.94 244	98.23 380	92.99 257	97.92 315	98.37 266

Fast-Effi-MVS+		95.49 217	95.07 228	96.75 195	97.67 279	92.82 200	94.22 295	98.60 183	91.61 293	93.42 354	92.90 374	96.73 89	99.70 115	92.60 261	97.89 318	97.74 329

CMPMVS	73.10 23	92.74 313	91.39 327	96.77 194	93.57 407	94.67 136	94.21 296	97.67 271	80.36 400	93.61 346	96.60 289	82.85 339	97.35 393	84.86 380	98.78 263	98.29 280
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dp		88.08 371	88.05 366	88.16 396	92.85 411	68.81 422	94.17 297	92.88 367	85.47 371	91.38 384	96.14 314	68.87 398	98.81 330	86.88 363	83.80 415	96.87 362

JIA-IIPM		91.79 332	90.69 343	95.11 275	93.80 404	90.98 248	94.16 298	91.78 380	96.38 119	90.30 392	99.30 29	72.02 389	98.90 322	88.28 345	90.17 407	95.45 393

D2MVS		95.18 233	95.17 224	95.21 271	97.76 265	87.76 312	94.15 299	97.94 255	89.77 323	96.99 217	97.68 215	87.45 302	99.14 290	95.03 186	99.81 47	98.74 229

TSAR-MVS + GP.		96.47 177	96.12 190	97.49 137	97.74 270	95.23 117	94.15 299	96.90 303	93.26 249	98.04 147	96.70 284	94.41 178	98.89 323	94.77 199	99.14 221	98.37 266

PVSNet_BlendedMVS		95.02 242	94.93 234	95.27 269	97.79 260	87.40 318	94.14 301	98.68 170	88.94 333	94.51 319	98.01 183	93.04 209	99.30 260	89.77 324	99.49 146	99.11 170

TinyColmap		96.00 196	96.34 182	94.96 285	97.90 240	87.91 306	94.13 302	98.49 194	94.41 213	98.16 131	97.76 205	96.29 115	98.68 346	90.52 310	99.42 171	98.30 277

CNLPA		95.04 239	94.47 262	96.75 195	97.81 251	95.25 116	94.12 303	97.89 258	94.41 213	94.57 317	95.69 328	90.30 269	98.35 374	86.72 365	98.76 265	96.64 372

BH-untuned		94.69 256	94.75 246	94.52 307	97.95 238	87.53 315	94.07 304	97.01 299	93.99 228	97.10 206	95.65 330	92.65 221	98.95 320	87.60 353	96.74 360	97.09 354

pmmvs5		94.63 261	94.34 268	95.50 261	97.63 286	88.34 294	94.02 305	97.13 293	87.15 353	95.22 303	97.15 253	87.50 301	99.27 269	93.99 230	99.26 207	98.88 211

thres200		91.00 343	90.42 347	92.77 357	97.47 300	83.98 368	94.01 306	91.18 388	95.12 188	95.44 298	91.21 396	73.93 379	99.31 257	77.76 406	97.63 335	95.01 396

xiu_mvs_v1_base_debu		95.62 212	95.96 199	94.60 302	98.01 229	88.42 291	93.99 307	98.21 226	92.98 264	95.91 279	94.53 353	96.39 108	99.72 93	95.43 160	98.19 304	95.64 389

xiu_mvs_v1_base		95.62 212	95.96 199	94.60 302	98.01 229	88.42 291	93.99 307	98.21 226	92.98 264	95.91 279	94.53 353	96.39 108	99.72 93	95.43 160	98.19 304	95.64 389

xiu_mvs_v1_base_debi		95.62 212	95.96 199	94.60 302	98.01 229	88.42 291	93.99 307	98.21 226	92.98 264	95.91 279	94.53 353	96.39 108	99.72 93	95.43 160	98.19 304	95.64 389

test_vis1_rt		94.03 285	93.65 286	95.17 274	95.76 369	93.42 187	93.97 310	98.33 215	84.68 381	93.17 358	95.89 325	92.53 229	94.79 410	93.50 245	94.97 389	97.31 351

CDS-MVSNet		94.88 247	94.12 276	97.14 164	97.64 285	93.57 181	93.96 311	97.06 297	90.05 319	96.30 262	96.55 291	86.10 312	99.47 202	90.10 318	99.31 200	98.40 262
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		94.65 260	94.21 272	95.96 236	95.90 358	89.68 267	93.92 312	97.83 264	93.19 254	90.12 394	95.64 331	88.52 288	99.57 174	93.27 252	99.47 152	98.62 243

WTY-MVS		93.55 297	93.00 298	95.19 272	97.81 251	87.86 307	93.89 313	96.00 320	89.02 331	94.07 331	95.44 338	86.27 311	99.33 252	87.69 351	96.82 357	98.39 264

sss		94.22 274	93.72 285	95.74 248	97.71 273	89.95 263	93.84 314	96.98 300	88.38 342	93.75 341	95.74 327	87.94 295	98.89 323	91.02 290	98.10 308	98.37 266

baseline2		89.65 358	88.44 364	93.25 339	95.62 372	82.71 374	93.82 315	85.94 412	88.89 334	87.35 410	92.54 381	71.23 391	99.33 252	86.01 366	94.60 394	97.72 332

XVG-OURS		97.12 134	96.74 158	98.26 72	98.99 110	97.45 36	93.82 315	99.05 71	95.19 184	98.32 114	97.70 213	95.22 154	98.41 368	94.27 218	98.13 307	98.93 199

MVS_111021_LR		96.82 156	96.55 170	97.62 122	98.27 199	95.34 112	93.81 317	98.33 215	94.59 208	96.56 247	96.63 288	96.61 94	98.73 337	94.80 195	99.34 190	98.78 223

BH-RMVSNet		94.56 264	94.44 265	94.91 286	97.57 289	87.44 317	93.78 318	96.26 316	93.69 236	96.41 254	96.50 296	92.10 239	99.00 311	85.96 367	97.71 327	98.31 275

CDPH-MVS		95.45 222	94.65 249	97.84 107	98.28 197	94.96 128	93.73 319	98.33 215	85.03 377	95.44 298	96.60 289	95.31 151	99.44 213	90.01 319	99.13 223	99.11 170

PatchMatch-RL		94.61 262	93.81 284	97.02 177	98.19 208	95.72 89	93.66 320	97.23 288	88.17 345	94.94 311	95.62 332	91.43 249	98.57 355	87.36 359	97.68 330	96.76 370

TEST9					97.84 247	95.23 117	93.62 321	98.39 207	86.81 358	93.78 338	95.99 319	94.68 169	99.52 187

train_agg		95.46 221	94.66 248	97.88 104	97.84 247	95.23 117	93.62 321	98.39 207	87.04 354	93.78 338	95.99 319	94.58 173	99.52 187	91.76 278	98.90 249	98.89 207

test_prior4						95.38 107	93.61 323

test_8					97.81 251	95.07 126	93.54 324	98.38 209	87.04 354	93.71 342	95.96 322	94.58 173	99.52 187

TR-MVS		92.54 316	92.20 316	93.57 333	96.49 337	86.66 330	93.51 325	94.73 347	89.96 320	94.95 310	93.87 362	90.24 271	98.61 352	81.18 396	94.88 390	95.45 393

新几何2							93.43 326

diffmvs		96.04 193	96.23 186	95.46 264	97.35 307	88.03 304	93.42 327	99.08 63	94.09 226	96.66 239	96.93 268	93.85 192	99.29 264	96.01 121	98.67 274	99.06 179
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		96.73 162	96.54 172	97.27 155	98.35 192	93.66 179	93.42 327	98.36 211	94.74 200	96.58 245	96.76 282	96.54 97	98.99 313	94.87 192	99.27 206	99.15 157

UnsupCasMVSNet_bld		94.72 255	94.26 269	96.08 232	98.62 160	90.54 259	93.38 329	98.05 253	90.30 315	97.02 215	96.80 279	89.54 277	99.16 288	88.44 342	96.18 374	98.56 248

旧先验2							93.35 330		77.95 408	95.77 289			98.67 347	90.74 304

test_prior2							93.33 331		94.21 218	94.02 334	96.25 308	93.64 197		91.90 272	98.96 242

WB-MVSnew		91.50 336	91.29 329	92.14 370	94.85 387	80.32 392	93.29 332	88.77 404	88.57 339	94.03 333	92.21 385	92.56 224	98.28 378	80.21 399	97.08 349	97.81 324

SCA		93.38 302	93.52 289	92.96 351	96.24 342	81.40 386	93.24 333	94.00 354	91.58 295	94.57 317	96.97 265	87.94 295	99.42 217	89.47 328	97.66 333	98.06 302

无先验							93.20 334	97.91 256	80.78 397				99.40 228	87.71 350		97.94 314

MG-MVS		94.08 282	94.00 279	94.32 316	97.09 321	85.89 339	93.19 335	95.96 322	92.52 275	94.93 312	97.51 226	89.54 277	98.77 333	87.52 357	97.71 327	98.31 275

MVS-HIRNet		88.40 368	90.20 349	82.99 398	97.01 323	60.04 423	93.11 336	85.61 413	84.45 385	88.72 404	99.09 53	84.72 325	98.23 380	82.52 391	96.59 366	90.69 413

new-patchmatchnet		95.67 210	96.58 167	92.94 352	97.48 296	80.21 393	92.96 337	98.19 234	94.83 198	98.82 63	98.79 79	93.31 203	99.51 191	95.83 132	99.04 237	99.12 167

ETVMVS		87.62 375	85.75 382	93.22 341	96.15 351	83.26 371	92.94 338	90.37 396	91.39 299	90.37 390	88.45 409	51.93 421	98.64 349	73.76 410	96.38 369	97.75 328

MDA-MVSNet-bldmvs		95.69 208	95.67 211	95.74 248	98.48 181	88.76 289	92.84 339	97.25 287	96.00 141	97.59 176	97.95 189	91.38 250	99.46 205	93.16 255	96.35 370	98.99 189

原ACMM2							92.82 340

testdata1							92.77 341		93.78 232

Test_1112_low_res		93.53 298	92.86 300	95.54 260	98.60 162	88.86 285	92.75 342	98.69 168	82.66 390	92.65 370	96.92 270	84.75 324	99.56 175	90.94 293	97.76 323	98.19 289

USDC		94.56 264	94.57 259	94.55 306	97.78 263	86.43 334	92.75 342	98.65 180	85.96 365	96.91 224	97.93 192	90.82 258	98.74 336	90.71 305	99.59 106	98.47 258

test222					98.17 214	93.24 194	92.74 344	97.61 280	75.17 412	94.65 316	96.69 285	90.96 257			98.66 276	97.66 334

jason		94.39 271	94.04 278	95.41 267	98.29 195	87.85 309	92.74 344	96.75 309	85.38 374	95.29 301	96.15 312	88.21 294	99.65 143	94.24 219	99.34 190	98.74 229
jason: jason.
testing91		89.67 357	88.55 362	93.04 346	95.90 358	81.80 383	92.71 346	93.71 355	93.71 234	90.18 393	90.15 404	57.11 409	99.22 280	87.17 362	96.32 371	98.12 294

testing99		89.21 361	88.04 367	92.70 359	95.78 367	81.00 390	92.65 347	92.03 376	93.20 253	89.90 397	90.08 406	55.25 416	99.14 290	87.54 355	95.95 377	97.97 311

Patchmatch-RL test		94.66 259	94.49 260	95.19 272	98.54 171	88.91 283	92.57 348	98.74 157	91.46 298	98.32 114	97.75 208	77.31 366	98.81 330	96.06 114	99.61 98	97.85 320

DeepPCF-MVS	94.58 5	96.90 148	96.43 178	98.31 69	97.48 296	97.23 44	92.56 349	98.60 183	92.84 270	98.54 85	97.40 233	96.64 93	98.78 332	94.40 213	99.41 175	98.93 199

N_pmnet		95.18 233	94.23 270	98.06 90	97.85 242	96.55 62	92.49 350	91.63 381	89.34 326	98.09 139	97.41 232	90.33 266	99.06 304	91.58 280	99.31 200	98.56 248

testing11		88.93 363	87.63 371	92.80 356	95.87 360	81.49 385	92.48 351	91.54 382	91.62 292	88.27 406	90.24 402	55.12 419	99.11 297	87.30 360	96.28 373	97.81 324

Syy-MVS		92.09 325	91.80 322	92.93 353	95.19 382	82.65 375	92.46 352	91.35 384	90.67 310	91.76 381	87.61 411	85.64 318	98.50 362	94.73 201	96.84 355	97.65 335

myMVS_eth3d		87.16 380	85.61 383	91.82 373	95.19 382	79.32 395	92.46 352	91.35 384	90.67 310	91.76 381	87.61 411	41.96 423	98.50 362	82.66 390	96.84 355	97.65 335

BH-w/o		92.14 323	91.94 318	92.73 358	97.13 320	85.30 346	92.46 352	95.64 329	89.33 327	94.21 325	92.74 378	89.60 275	98.24 379	81.68 393	94.66 392	94.66 398

IterMVS-SCA-FT		95.86 201	96.19 188	94.85 291	97.68 275	85.53 342	92.42 355	97.63 279	96.99 96	98.36 106	98.54 109	87.94 295	99.75 72	97.07 80	99.08 231	99.27 138

IterMVS		95.42 223	95.83 206	94.20 320	97.52 293	83.78 369	92.41 356	97.47 284	95.49 171	98.06 144	98.49 113	87.94 295	99.58 168	96.02 119	99.02 238	99.23 145
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing222		87.35 377	85.50 384	92.93 353	95.79 366	82.83 373	92.40 357	90.10 400	92.80 271	88.87 403	89.02 407	48.34 422	98.70 341	75.40 409	96.74 360	97.27 352

DELS-MVS		96.17 188	96.23 186	95.99 234	97.55 292	90.04 261	92.38 358	98.52 191	94.13 222	96.55 249	97.06 259	94.99 161	99.58 168	95.62 143	99.28 204	98.37 266
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		92.34 319	91.69 324	94.32 316	96.23 344	89.16 279	92.27 359	92.88 367	84.39 386	95.29 301	96.35 305	85.66 317	96.74 404	84.53 382	97.56 336	97.05 355

CHOSEN 1792x2688		94.10 280	93.41 291	96.18 228	99.16 80	90.04 261	92.15 360	98.68 170	79.90 401	96.22 266	97.83 198	87.92 299	99.42 217	89.18 332	99.65 86	99.08 175

xiu_mvs_v2_base		94.22 274	94.63 252	92.99 350	97.32 312	84.84 357	92.12 361	97.84 262	91.96 286	94.17 327	93.43 365	96.07 121	99.71 107	91.27 284	97.48 340	94.42 399

lupinMVS		93.77 289	93.28 292	95.24 270	97.68 275	87.81 310	92.12 361	96.05 318	84.52 383	94.48 321	95.06 343	86.90 306	99.63 151	93.62 243	99.13 223	98.27 281

pmmvs4		94.82 249	94.19 273	96.70 198	97.42 303	92.75 206	92.09 363	96.76 308	86.80 359	95.73 290	97.22 250	89.28 283	98.89 323	93.28 251	99.14 221	98.46 260

PAPR		92.22 321	91.27 331	95.07 278	95.73 371	88.81 286	91.97 364	97.87 259	85.80 368	90.91 385	92.73 379	91.16 252	98.33 375	79.48 400	95.76 382	98.08 296

UWE-MVS		87.57 376	86.72 378	90.13 387	95.21 381	73.56 417	91.94 365	83.78 416	88.73 337	93.00 361	92.87 375	55.22 417	99.25 272	81.74 392	97.96 313	97.59 340

PS-MVSNAJ		94.10 280	94.47 262	93.00 349	97.35 307	84.88 354	91.86 366	97.84 262	91.96 286	94.17 327	92.50 383	95.82 130	99.71 107	91.27 284	97.48 340	94.40 400

c3_l		95.20 232	95.32 218	94.83 293	96.19 346	86.43 334	91.83 367	98.35 214	93.47 242	97.36 190	97.26 248	88.69 286	99.28 266	95.41 163	99.36 182	98.78 223

test0.0.03 1		90.11 348	89.21 355	92.83 355	93.89 403	86.87 328	91.74 368	88.74 405	92.02 284	94.71 315	91.14 397	73.92 380	94.48 412	83.75 388	92.94 399	97.16 353

UBG		88.29 369	87.17 373	91.63 375	96.08 353	78.21 399	91.61 369	91.50 383	89.67 324	89.71 398	88.97 408	59.01 406	98.91 321	81.28 395	96.72 362	97.77 327

FPMVS		89.92 353	88.63 361	93.82 326	98.37 190	96.94 49	91.58 370	93.34 363	88.00 347	90.32 391	97.10 257	70.87 393	91.13 416	71.91 414	96.16 376	93.39 406

ET-MVSNet_ETH3D		91.12 339	89.67 352	95.47 263	96.41 339	89.15 280	91.54 371	90.23 398	89.07 330	86.78 412	92.84 376	69.39 397	99.44 213	94.16 222	96.61 365	97.82 322

WBMVS		91.11 340	90.72 342	92.26 368	95.99 355	77.98 403	91.47 372	95.90 324	91.63 291	95.90 282	96.45 298	59.60 405	99.46 205	89.97 321	99.59 106	99.33 121

PVSNet_Blended		93.96 286	93.65 286	94.91 286	97.79 260	87.40 318	91.43 373	98.68 170	84.50 384	94.51 319	94.48 356	93.04 209	99.30 260	89.77 324	98.61 281	98.02 308

CLD-MVS		95.47 220	95.07 228	96.69 199	98.27 199	92.53 209	91.36 374	98.67 173	91.22 303	95.78 287	94.12 360	95.65 140	98.98 315	90.81 297	99.72 70	98.57 247
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		94.89 246	94.93 234	94.75 297	95.99 355	86.12 337	91.35 375	98.49 194	93.40 243	97.12 204	97.25 249	86.87 308	99.35 247	95.08 183	98.82 260	98.78 223

cl____		94.73 251	94.64 250	95.01 281	95.85 362	87.00 325	91.33 376	98.08 247	93.34 246	97.10 206	97.33 244	84.01 332	99.30 260	95.14 178	99.56 115	98.71 235

DIV-MVS_self_test		94.73 251	94.64 250	95.01 281	95.86 361	87.00 325	91.33 376	98.08 247	93.34 246	97.10 206	97.34 243	84.02 331	99.31 257	95.15 177	99.55 121	98.72 232

miper_ehance_all_eth		94.69 256	94.70 247	94.64 299	95.77 368	86.22 336	91.32 378	98.24 224	91.67 290	97.05 213	96.65 287	88.39 291	99.22 280	94.88 191	98.34 298	98.49 257

pmmvs3		90.00 350	88.90 360	93.32 336	94.20 399	85.34 344	91.25 379	92.56 374	78.59 405	93.82 337	95.17 340	67.36 400	98.69 343	89.08 334	98.03 311	95.92 383

HyFIR lowres test		93.72 291	92.65 308	96.91 184	98.93 120	91.81 234	91.23 380	98.52 191	82.69 389	96.46 252	96.52 295	80.38 351	99.90 16	90.36 315	98.79 262	99.03 182

DPM-MVS		93.68 293	92.77 306	96.42 215	97.91 239	92.54 208	91.17 381	97.47 284	84.99 379	93.08 360	94.74 349	89.90 273	99.00 311	87.54 355	98.09 309	97.72 332

CL-MVSNet_self_test		95.04 239	94.79 245	95.82 244	97.51 294	89.79 265	91.14 382	96.82 306	93.05 261	96.72 234	96.40 302	90.82 258	99.16 288	91.95 271	98.66 276	98.50 256

miper_lstm_enhance		94.81 250	94.80 244	94.85 291	96.16 348	86.45 333	91.14 382	98.20 229	93.49 241	97.03 214	97.37 241	84.97 323	99.26 270	95.28 166	99.56 115	98.83 216

cl22		93.25 306	92.84 302	94.46 310	94.30 395	86.00 338	91.09 384	96.64 314	90.74 307	95.79 285	96.31 306	78.24 358	98.77 333	94.15 223	98.34 298	98.62 243

MSDG		95.33 226	95.13 225	95.94 240	97.40 304	91.85 232	91.02 385	98.37 210	95.30 180	96.31 261	95.99 319	94.51 176	98.38 371	89.59 326	97.65 334	97.60 339

IB-MVS	85.98 20	88.63 366	86.95 377	93.68 331	95.12 384	84.82 358	90.85 386	90.17 399	87.55 350	88.48 405	91.34 395	58.01 407	99.59 166	87.24 361	93.80 398	96.63 374
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		93.47 299	93.03 296	94.79 295	94.05 402	92.12 223	90.82 387	90.01 401	85.02 378	97.26 194	98.28 144	93.57 198	97.03 396	92.51 264	95.75 383	95.23 395

test123		12.59 389	15.49 392	3.87 404	6.07 427	2.55 429	90.75 388	2.59 429	2.52 422	5.20 424	13.02 421	4.96 427	1.85 424	5.20 422	9.09 421	7.23 419

ppachtmachnet_test		94.49 268	94.84 240	93.46 335	96.16 348	82.10 379	90.59 389	97.48 283	90.53 312	97.01 216	97.59 220	91.01 255	99.36 243	93.97 232	99.18 217	98.94 195

PMMVS		92.39 317	91.08 334	96.30 223	93.12 409	92.81 202	90.58 390	95.96 322	79.17 404	91.85 380	92.27 384	90.29 270	98.66 348	89.85 323	96.68 364	97.43 346

our_test_3		94.20 278	94.58 257	93.07 345	96.16 348	81.20 388	90.42 391	96.84 304	90.72 308	97.14 202	97.13 254	90.47 262	99.11 297	94.04 229	98.25 302	98.91 203

YYNet1		94.73 251	94.84 240	94.41 312	97.47 300	85.09 352	90.29 392	95.85 326	92.52 275	97.53 178	97.76 205	91.97 242	99.18 283	93.31 250	96.86 354	98.95 193

MDA-MVSNet_test_wron		94.73 251	94.83 242	94.42 311	97.48 296	85.15 350	90.28 393	95.87 325	92.52 275	97.48 184	97.76 205	91.92 245	99.17 287	93.32 249	96.80 359	98.94 195

GA-MVS		92.83 312	92.15 317	94.87 290	96.97 324	87.27 321	90.03 394	96.12 317	91.83 289	94.05 332	94.57 351	76.01 373	98.97 319	92.46 265	97.34 346	98.36 271

miper_enhance_ethall		93.14 308	92.78 305	94.20 320	93.65 405	85.29 347	89.97 395	97.85 260	85.05 376	96.15 272	94.56 352	85.74 315	99.14 290	93.74 238	98.34 298	98.17 292

test-LLR		89.97 352	89.90 350	90.16 385	94.24 397	74.98 414	89.89 396	89.06 402	92.02 284	89.97 395	90.77 400	73.92 380	98.57 355	91.88 273	97.36 344	96.92 359

TESTMET0.1,1		87.20 379	86.57 379	89.07 390	93.62 406	72.84 419	89.89 396	87.01 410	85.46 372	89.12 402	90.20 403	56.00 414	97.72 390	90.91 294	96.92 351	96.64 372

test-mter		87.92 373	87.17 373	90.16 385	94.24 397	74.98 414	89.89 396	89.06 402	86.44 362	89.97 395	90.77 400	54.96 420	98.57 355	91.88 273	97.36 344	96.92 359

PCF-MVS	89.43 18	92.12 324	90.64 344	96.57 206	97.80 255	93.48 184	89.88 399	98.45 197	74.46 413	96.04 275	95.68 329	90.71 260	99.31 257	73.73 411	99.01 240	96.91 361
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thisisatest0515		90.43 346	89.18 358	94.17 322	97.07 322	85.44 343	89.75 400	87.58 407	88.28 343	93.69 344	91.72 391	65.27 401	99.58 168	90.59 308	98.67 274	97.50 345

KD-MVS_2432*1600		88.93 363	87.74 368	92.49 362	88.04 420	81.99 380	89.63 401	95.62 330	91.35 300	95.06 306	93.11 367	56.58 411	98.63 350	85.19 376	95.07 387	96.85 364

miper_refine_blended		88.93 363	87.74 368	92.49 362	88.04 420	81.99 380	89.63 401	95.62 330	91.35 300	95.06 306	93.11 367	56.58 411	98.63 350	85.19 376	95.07 387	96.85 364

testmvs		12.33 390	15.23 393	3.64 405	5.77 428	2.23 430	88.99 403	3.62 428	2.30 423	5.29 423	13.09 420	4.52 428	1.95 423	5.16 423	8.32 422	6.75 420

cascas		91.89 330	91.35 328	93.51 334	94.27 396	85.60 341	88.86 404	98.61 182	79.32 403	92.16 377	91.44 394	89.22 284	98.12 383	90.80 298	97.47 342	96.82 367

PAPM		87.64 374	85.84 381	93.04 346	96.54 335	84.99 353	88.42 405	95.57 333	79.52 402	83.82 413	93.05 373	80.57 350	98.41 368	62.29 417	92.79 400	95.71 388

PVSNet	86.72 19	91.10 341	90.97 337	91.49 376	97.56 291	78.04 401	87.17 406	94.60 349	84.65 382	92.34 375	92.20 386	87.37 304	98.47 365	85.17 378	97.69 329	97.96 312

PMMVS2		93.66 294	94.07 277	92.45 365	97.57 289	80.67 391	86.46 407	96.00 320	93.99 228	97.10 206	97.38 239	89.90 273	97.82 388	88.76 337	99.47 152	98.86 214

CHOSEN 280x420		89.98 351	89.19 357	92.37 366	95.60 373	81.13 389	86.22 408	97.09 295	81.44 395	87.44 409	93.15 366	73.99 378	99.47 202	88.69 339	99.07 233	96.52 376

dongtai		63.43 385	63.37 388	63.60 401	83.91 423	53.17 425	85.14 409	43.40 427	77.91 409	80.96 417	79.17 417	36.36 425	77.10 419	37.88 420	45.63 419	60.54 416

kuosan		54.81 387	54.94 390	54.42 402	74.43 424	50.03 426	84.98 410	44.27 426	61.80 417	62.49 421	70.43 418	35.16 426	58.04 421	19.30 421	41.61 420	55.19 417

tmp_tt		57.23 386	62.50 389	41.44 403	34.77 426	49.21 427	83.93 411	60.22 425	15.31 419	71.11 419	79.37 416	70.09 396	44.86 422	64.76 416	82.93 416	30.25 418

PVSNet_0	81.89 21	84.49 382	83.21 385	88.34 393	95.76 369	74.97 416	83.49 412	92.70 371	78.47 406	87.94 407	86.90 414	83.38 336	96.63 405	73.44 412	66.86 418	93.40 405

E-PMN		89.52 359	89.78 351	88.73 391	93.14 408	77.61 404	83.26 413	92.02 377	94.82 199	93.71 342	93.11 367	75.31 375	96.81 400	85.81 368	96.81 358	91.77 410

EMVS		89.06 362	89.22 354	88.61 392	93.00 410	77.34 406	82.91 414	90.92 389	94.64 205	92.63 372	91.81 390	76.30 371	97.02 397	83.83 386	96.90 353	91.48 411

MVE	73.61 22	86.48 381	85.92 380	88.18 395	96.23 344	85.28 348	81.78 415	75.79 419	86.01 364	82.53 415	91.88 389	92.74 217	87.47 418	71.42 415	94.86 391	91.78 409
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		66.88 384	66.13 387	69.11 400	62.68 425	25.73 428	49.76 416	96.04 319	14.32 420	64.27 420	91.69 392	73.45 385	88.05 417	76.06 408	66.94 417	93.54 403

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

cdsmvs_eth3d_5k		24.22 388	32.30 391	0.00 406	0.00 429	0.00 431	0.00 417	98.10 245	0.00 424	0.00 425	95.06 343	97.54 39	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		7.98 391	10.65 394	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	95.82 130	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

ab-mvs-re		7.91 392	10.55 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	94.94 345	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						79.32 395								85.41 374

MSC_two_6792asdad				98.22 77	97.75 267	95.34 112		98.16 239					99.75 72	95.87 130	99.51 139	99.57 46

PC_three_1452									87.24 352	98.37 103	97.44 230	97.00 67	96.78 402	92.01 269	99.25 208	99.21 147

No_MVS				98.22 77	97.75 267	95.34 112		98.16 239					99.75 72	95.87 130	99.51 139	99.57 46

test_one_0601					99.05 105	95.50 102		98.87 119	97.21 93	98.03 148	98.30 139	96.93 73

eth-test2					0.00 429

eth-test					0.00 429

ZD-MVS					98.43 186	95.94 83		98.56 189	90.72 308	96.66 239	97.07 258	95.02 160	99.74 81	91.08 288	98.93 247

IU-MVS					99.22 66	95.40 105		98.14 242	85.77 369	98.36 106				95.23 170	99.51 139	99.49 75

test_241102_TWO								98.83 136	96.11 133	98.62 78	98.24 151	96.92 76	99.72 93	95.44 157	99.49 146	99.49 75

test_241102_ONE					99.22 66	95.35 110		98.83 136	96.04 138	99.08 40	98.13 164	97.87 23	99.33 252

test_0728_THIRD									96.62 106	98.40 100	98.28 144	97.10 58	99.71 107	95.70 135	99.62 92	99.58 39

GSMVS																98.06 302

test_part2					99.03 107	96.07 78				98.08 141

sam_mvs1												77.80 360				98.06 302

sam_mvs												77.38 364

MTGPA								98.73 158

test_post											10.87 422	76.83 368	99.07 303

patchmatchnet-post											96.84 274	77.36 365	99.42 217

gm-plane-assit					91.79 415	71.40 421			81.67 392		90.11 405		98.99 313	84.86 380

test9_res														91.29 283	98.89 252	99.00 186

agg_prior2														90.34 316	98.90 249	99.10 174

agg_prior					97.80 255	94.96 128		98.36 211		93.49 350			99.53 184

TestCases				98.06 90	99.08 96	96.16 74		99.16 42	94.35 215	97.78 171	98.07 172	95.84 127	99.12 294	91.41 281	99.42 171	98.91 203

test_prior				97.46 140	97.79 260	94.26 157		98.42 203					99.34 250			98.79 222

新几何1				97.25 158	98.29 195	94.70 135		97.73 268	77.98 407	94.83 313	96.67 286	92.08 240	99.45 210	88.17 347	98.65 278	97.61 338

旧先验1					97.80 255	93.87 168		97.75 267			97.04 261	93.57 198			98.68 273	98.72 232

原ACMM1				96.58 204	98.16 216	92.12 223		98.15 241	85.90 367	93.49 350	96.43 299	92.47 231	99.38 235	87.66 352	98.62 280	98.23 284

testdata2													99.46 205	87.84 348

segment_acmp												95.34 150

testdata				95.70 251	98.16 216	90.58 256		97.72 269	80.38 399	95.62 292	97.02 262	92.06 241	98.98 315	89.06 335	98.52 286	97.54 342

test12				97.46 140	97.61 287	94.07 161		97.78 266		93.57 348		93.31 203	99.42 217		98.78 263	98.89 207

plane_prior7					98.70 149	94.67 136

plane_prior6					98.38 189	94.37 150						91.91 246

plane_prior5								98.75 155					99.46 205	92.59 262	99.20 213	99.28 134

plane_prior4											96.77 280

plane_prior3						94.51 143			95.29 181	96.16 270

plane_prior1					98.49 179

n2								0.00 430

nn								0.00 430

door-mid								98.17 235

lessismore_v0				97.05 173	99.36 48	92.12 223		84.07 414		98.77 70	98.98 62	85.36 320	99.74 81	97.34 68	99.37 179	99.30 127

LGP-MVS_train				98.74 38	99.15 83	97.02 46		99.02 81	95.15 186	98.34 110	98.23 153	97.91 21	99.70 115	94.41 211	99.73 66	99.50 67

test11								98.08 247

door								97.81 265

HQP5-MVS						92.47 212

BP-MVS														90.51 311

HQP4-MVS										92.87 363			99.23 278			99.06 179

HQP3-MVS								98.43 200							98.74 267

HQP2-MVS												90.33 266

NP-MVS					98.14 220	93.72 174					95.08 341

ACMMP++_ref															99.52 134

ACMMP++															99.55 121

Test By Simon												94.51 176

ITE_SJBPF				97.85 106	98.64 154	96.66 58		98.51 193	95.63 162	97.22 195	97.30 246	95.52 143	98.55 358	90.97 292	98.90 249	98.34 272

DeepMVS_CX				77.17 399	90.94 417	85.28 348		74.08 422	52.51 418	80.87 418	88.03 410	75.25 376	70.63 420	59.23 419	84.94 414	75.62 414

High-resolution multi-view benchmark