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

pmmvs6		99.07 6	99.24 7	98.56 52	99.81 2	96.38 66	98.87 12	99.30 40	99.01 23	99.63 15	99.66 6	99.27 2	99.68 143	97.75 72	99.89 26	99.62 43

UniMVSNet_ETH3D		99.12 3	99.28 5	98.65 46	99.77 5	96.34 70	99.18 6	99.20 50	99.67 3	99.73 7	99.65 8	99.15 3	99.86 28	97.22 93	99.92 15	99.77 15

test_fmvsmconf0.01_n		98.57 22	98.74 20	98.06 96	99.39 49	94.63 144	96.70 165	99.82 1	95.44 201	99.64 14	99.52 12	98.96 4	99.74 93	99.38 6	99.86 35	99.81 10

XVG-OURS-SEG-HR		97.38 140	97.07 162	98.30 74	99.01 118	97.41 38	94.66 317	99.02 103	95.20 211	98.15 160	97.52 258	98.83 5	98.43 408	94.87 231	96.41 411	99.07 207

ACMH	93.61 9	98.44 33	98.76 17	97.51 139	99.43 42	93.54 189	98.23 49	99.05 92	97.40 93	99.37 33	99.08 60	98.79 6	99.47 232	97.74 73	99.71 88	99.50 85
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_tets		98.90 9	98.94 9	98.75 35	99.69 11	96.48 64	98.54 26	99.22 47	96.23 148	99.71 8	99.48 15	98.77 7	99.93 4	98.89 29	99.95 5	99.84 8

test_fmvsmconf0.1_n		98.41 35	98.54 31	98.03 101	99.16 88	94.61 145	96.18 199	99.73 5	95.05 220	99.60 18	99.34 29	98.68 8	99.72 105	99.21 12	99.85 45	99.76 21

sc_t1		99.09 5	99.28 5	98.53 55	99.72 8	96.21 74	98.87 12	99.19 52	99.71 2	99.76 5	99.65 8	98.64 9	99.79 54	98.07 55	99.90 25	99.58 48

tt0320-xc		99.10 4	99.31 3	98.49 58	99.57 20	96.09 80	98.91 11	99.55 24	99.67 3	99.78 3	99.69 4	98.63 10	99.77 70	98.02 57	99.93 11	99.60 44

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 41	99.71 10	96.99 48	99.69 2	99.57 21	99.02 22	99.62 16	99.36 26	98.53 11	99.52 216	98.58 41	99.95 5	99.66 36
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
test_fmvsmconf_n		98.30 41	98.41 40	97.99 104	98.94 127	94.60 146	96.00 217	99.64 16	94.99 223	99.43 28	99.18 46	98.51 12	99.71 121	99.13 20	99.84 48	99.67 34

TransMVSNet (Re)		98.38 36	98.67 22	97.51 139	99.51 31	93.39 198	98.20 54	98.87 146	98.23 54	99.48 22	99.27 34	98.47 13	99.55 207	96.52 120	99.53 155	99.60 44

tt0320		99.07 6	99.29 4	98.43 63	99.55 24	95.92 87	98.97 10	99.53 26	99.67 3	99.79 2	99.71 3	98.33 14	99.78 59	98.11 51	99.92 15	99.57 56

pm-mvs1		98.47 32	98.67 22	97.86 111	99.52 30	94.58 147	98.28 45	99.00 114	97.57 79	99.27 40	99.22 39	98.32 15	99.50 221	97.09 101	99.75 78	99.50 85

fmvsm_l_conf0.5_n_3		98.29 42	98.46 34	97.79 115	98.90 138	94.05 169	96.06 210	99.63 17	96.07 158	99.37 33	98.93 77	98.29 16	99.68 143	99.11 22	99.79 63	99.65 39

jajsoiax		98.77 13	98.79 16	98.74 38	99.66 13	96.48 64	98.45 34	99.12 69	95.83 180	99.67 11	99.37 24	98.25 17	99.92 6	98.77 32	99.94 8	99.82 9

sd_testset		97.97 65	98.12 58	97.51 139	99.41 45	93.44 194	97.96 68	98.25 256	98.58 37	98.78 83	99.39 21	98.21 18	99.56 203	92.65 300	99.86 35	99.52 78

ACMH+	93.58 10	98.23 46	98.31 49	97.98 105	99.39 49	95.22 126	97.55 103	99.20 50	98.21 55	99.25 42	98.51 128	98.21 18	99.40 258	94.79 235	99.72 85	99.32 144

HPM-MVS_fast		98.32 39	98.13 57	98.88 27	99.54 28	97.48 34	98.35 38	99.03 100	95.88 176	97.88 191	98.22 178	98.15 20	99.74 93	96.50 121	99.62 112	99.42 122

wuyk23d		93.25 347	95.20 259	87.40 441	96.07 397	95.38 113	97.04 136	94.97 383	95.33 206	99.70 10	98.11 192	98.14 21	91.94 459	77.76 448	99.68 98	74.89 459

ACMM	93.33 11	98.05 60	97.79 94	98.85 28	99.15 91	97.55 30	96.68 166	98.83 163	95.21 210	98.36 130	98.13 187	98.13 22	99.62 179	96.04 144	99.54 151	99.39 130
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 54	97.83 89	98.92 25	99.42 44	97.46 35	98.57 23	99.05 92	95.43 203	97.41 221	97.50 260	97.98 23	99.79 54	95.58 177	99.57 136	99.50 85
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 224	96.50 207	94.80 328	99.26 64	87.69 346	95.96 224	98.58 219	95.08 217	98.02 176	96.25 349	97.92 24	97.60 435	88.68 381	98.74 307	99.11 200

LPG-MVS_test		97.94 74	97.67 109	98.74 38	99.15 91	97.02 46	97.09 133	99.02 103	95.15 214	98.34 134	98.23 175	97.91 25	99.70 130	94.41 250	99.73 80	99.50 85

LGP-MVS_train				98.74 38	99.15 91	97.02 46		99.02 103	95.15 214	98.34 134	98.23 175	97.91 25	99.70 130	94.41 250	99.73 80	99.50 85

lecture		98.59 21	98.60 29	98.55 53	99.48 36	96.38 66	98.08 61	99.09 78	98.46 42	98.68 96	98.73 98	97.88 27	99.80 51	97.43 86	99.59 128	99.48 99

SED-MVS		97.94 74	97.90 79	98.07 94	99.22 74	95.35 116	96.79 155	98.83 163	96.11 154	99.08 53	98.24 173	97.87 28	99.72 105	95.44 187	99.51 165	99.14 188

test_241102_ONE					99.22 74	95.35 116		98.83 163	96.04 162	99.08 53	98.13 187	97.87 28	99.33 284

SDMVSNet		97.97 65	98.26 55	97.11 177	99.41 45	92.21 230	96.92 142	98.60 215	98.58 37	98.78 83	99.39 21	97.80 30	99.62 179	94.98 229	99.86 35	99.52 78

testf1		98.57 22	98.45 37	98.93 22	99.79 3	98.78 3	97.69 91	99.42 33	97.69 75	98.92 70	98.77 93	97.80 30	99.25 310	96.27 135	99.69 94	98.76 267

APD_test2		98.57 22	98.45 37	98.93 22	99.79 3	98.78 3	97.69 91	99.42 33	97.69 75	98.92 70	98.77 93	97.80 30	99.25 310	96.27 135	99.69 94	98.76 267

SD-MVS		97.37 142	97.70 104	96.35 243	98.14 253	95.13 130	96.54 172	98.92 131	95.94 171	99.19 45	98.08 196	97.74 33	95.06 453	95.24 199	99.54 151	98.87 249
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
DeepC-MVS	95.41 4	97.82 95	97.70 104	98.16 87	98.78 157	95.72 93	96.23 197	99.02 103	93.92 269	98.62 99	98.99 69	97.69 34	99.62 179	96.18 139	99.87 33	99.15 183
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		98.54 26	98.62 26	98.32 71	99.22 74	95.66 98	97.90 75	99.08 82	98.31 48	99.02 58	98.74 97	97.68 35	99.61 187	97.77 71	99.85 45	99.70 31

MGCFI-Net		97.20 152	97.23 152	97.08 182	97.68 315	93.71 182	97.79 81	99.09 78	97.40 93	96.59 281	93.96 403	97.67 36	99.35 279	96.43 126	98.50 331	98.17 334

ANet_high		98.31 40	98.94 9	96.41 239	99.33 56	89.64 295	97.92 73	99.56 23	99.27 11	99.66 13	99.50 14	97.67 36	99.83 36	97.55 81	99.98 2	99.77 15

test_fmvsmvis_n_1920		98.08 56	98.47 33	96.93 194	99.03 116	93.29 200	96.32 187	99.65 13	95.59 191	99.71 8	99.01 66	97.66 38	99.60 190	99.44 4	99.83 52	97.90 358

casdiffmvs_mvg		97.83 92	98.11 60	97.00 190	98.57 191	92.10 238	95.97 222	99.18 54	97.67 78	99.00 61	98.48 133	97.64 39	99.50 221	96.96 108	99.54 151	99.40 125
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
sasdasda		97.23 150	97.21 154	97.30 162	97.65 322	94.39 153	97.84 78	99.05 92	97.42 88	96.68 272	93.85 405	97.63 40	99.33 284	96.29 133	98.47 332	98.18 332

canonicalmvs		97.23 150	97.21 154	97.30 162	97.65 322	94.39 153	97.84 78	99.05 92	97.42 88	96.68 272	93.85 405	97.63 40	99.33 284	96.29 133	98.47 332	98.18 332

GeoE		97.75 102	97.70 104	97.89 109	98.88 140	94.53 148	97.10 132	98.98 121	95.75 184	97.62 203	97.59 253	97.61 42	99.77 70	96.34 131	99.44 186	99.36 139

TranMVSNet+NR-MVSNet		98.33 37	98.30 51	98.43 63	99.07 106	95.87 89	96.73 163	99.05 92	98.67 31	98.84 78	98.45 135	97.58 43	99.88 23	96.45 124	99.86 35	99.54 70

cdsmvs_eth3d_5k		24.22 432	32.30 435	0.00 450	0.00 473	0.00 475	0.00 461	98.10 279	0.00 468	0.00 469	95.06 384	97.54 44	0.00 469	0.00 468	0.00 467	0.00 465

ACMP	92.54 13	97.47 129	97.10 159	98.55 53	99.04 115	96.70 55	96.24 196	98.89 137	93.71 273	97.97 182	97.75 240	97.44 45	99.63 174	93.22 293	99.70 92	99.32 144
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 15	98.74 20	98.69 43	99.63 15	96.30 72	98.67 18	99.02 103	96.50 134	99.32 37	99.44 19	97.43 46	99.92 6	98.73 35	99.95 5	99.86 5

TDRefinement		98.90 9	98.86 12	99.02 10	99.54 28	98.06 9	99.34 5	99.44 31	98.85 28	99.00 61	99.20 41	97.42 47	99.59 192	97.21 94	99.76 69	99.40 125

anonymousdsp		98.72 18	98.63 24	98.99 14	99.62 16	97.29 41	98.65 22	99.19 52	95.62 189	99.35 36	99.37 24	97.38 48	99.90 18	98.59 40	99.91 19	99.77 15

PS-CasMVS		98.73 15	98.85 14	98.39 67	99.55 24	95.47 110	98.49 31	99.13 68	99.22 13	99.22 44	98.96 73	97.35 49	99.92 6	97.79 69	99.93 11	99.79 13

COLMAP_ROB	94.48 6	98.25 45	98.11 60	98.64 47	99.21 81	97.35 39	97.96 68	99.16 57	98.34 47	98.78 83	98.52 126	97.32 50	99.45 240	94.08 264	99.67 101	99.13 190
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EG-PatchMatch MVS		97.69 107	97.79 94	97.40 156	99.06 108	93.52 190	95.96 224	98.97 124	94.55 242	98.82 80	98.76 96	97.31 51	99.29 301	97.20 96	99.44 186	99.38 132

XXY-MVS		97.54 124	97.70 104	97.07 183	99.46 39	92.21 230	97.22 125	99.00 114	94.93 226	98.58 104	98.92 79	97.31 51	99.41 256	94.44 248	99.43 196	99.59 47

reproduce-ours		98.48 30	98.27 53	99.12 5	98.99 119	98.02 13	96.81 151	99.02 103	98.29 51	98.97 65	98.61 114	97.27 53	99.82 39	96.86 112	99.61 118	99.51 82

our_new_method		98.48 30	98.27 53	99.12 5	98.99 119	98.02 13	96.81 151	99.02 103	98.29 51	98.97 65	98.61 114	97.27 53	99.82 39	96.86 112	99.61 118	99.51 82

PEN-MVS		98.75 14	98.85 14	98.44 62	99.58 19	95.67 97	98.45 34	99.15 63	99.33 9	99.30 38	99.00 67	97.27 53	99.92 6	97.64 78	99.92 15	99.75 24

DTE-MVSNet		98.79 12	98.86 12	98.59 50	99.55 24	96.12 78	98.48 33	99.10 73	99.36 8	99.29 39	99.06 61	97.27 53	99.93 4	97.71 74	99.91 19	99.70 31

ZNCC-MVS		97.92 78	97.62 119	98.83 29	99.32 58	97.24 43	97.45 111	98.84 157	95.76 182	96.93 256	97.43 264	97.26 57	99.79 54	96.06 141	99.53 155	99.45 109

MP-MVS-pluss		97.69 107	97.36 143	98.70 42	99.50 34	96.84 51	95.38 271	98.99 118	92.45 320	98.11 163	98.31 157	97.25 58	99.77 70	96.60 117	99.62 112	99.48 99
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 85	97.63 117	98.67 44	99.35 54	96.84 51	96.36 184	98.79 177	95.07 218	97.88 191	98.35 149	97.24 59	99.72 105	96.05 143	99.58 133	99.45 109

fmvsm_l_conf0.5_n_9		97.92 78	98.37 41	96.57 222	98.94 127	90.54 278	95.39 269	99.58 19	96.82 116	99.56 19	98.77 93	97.23 60	99.61 187	99.17 17	99.86 35	99.57 56

Effi-MVS+		96.19 220	96.01 231	96.71 212	97.43 344	92.19 234	96.12 206	99.10 73	95.45 199	93.33 398	94.71 391	97.23 60	99.56 203	93.21 294	97.54 378	98.37 308

tt0805		97.44 133	97.56 126	97.11 177	99.55 24	96.36 68	98.66 21	95.66 365	98.31 48	97.09 244	95.45 378	97.17 62	98.50 403	98.67 38	97.45 384	96.48 421

PGM-MVS		97.88 86	97.52 130	98.96 17	99.20 83	97.62 25	97.09 133	99.06 86	95.45 199	97.55 207	97.94 216	97.11 63	99.78 59	94.77 238	99.46 181	99.48 99

test_0728_THIRD									96.62 123	98.40 124	98.28 166	97.10 64	99.71 121	95.70 163	99.62 112	99.58 48

APD-MVS_3200maxsize		98.13 53	97.90 79	98.79 33	98.79 153	97.31 40	97.55 103	98.92 131	97.72 72	98.25 148	98.13 187	97.10 64	99.75 84	95.44 187	99.24 245	99.32 144

fmvsm_s_conf0.5_n_3		97.88 86	98.37 41	96.41 239	98.73 162	89.82 289	95.94 226	99.49 28	96.81 117	99.09 52	99.03 65	97.09 66	99.65 163	99.37 7	99.76 69	99.76 21

OPM-MVS		97.54 124	97.25 150	98.41 65	99.11 100	96.61 60	95.24 284	98.46 229	94.58 241	98.10 165	98.07 198	97.09 66	99.39 263	95.16 208	99.44 186	99.21 171
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 74	97.64 115	98.83 29	99.15 91	97.50 33	97.59 100	98.84 157	96.05 160	97.49 212	97.54 256	97.07 68	99.70 130	95.61 174	99.46 181	99.30 149

DVP-MVS		97.78 100	97.65 112	98.16 87	99.24 68	95.51 105	96.74 159	98.23 259	95.92 173	98.40 124	98.28 166	97.06 69	99.71 121	95.48 183	99.52 160	99.26 161
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
test0726					99.24 68	95.51 105	96.89 145	98.89 137	95.92 173	98.64 97	98.31 157	97.06 69

SSM_0407		97.39 139	97.67 109	96.54 227	98.51 200	90.96 266	96.40 177	99.16 57	96.95 109	98.27 144	98.09 194	97.05 71	99.67 152	95.21 201	99.40 204	98.98 222

SSM_0404		97.47 129	97.75 102	96.64 216	98.81 147	91.26 259	96.57 169	99.16 57	96.95 109	98.44 120	98.09 194	97.05 71	99.72 105	95.21 201	99.44 186	98.95 228

test_fmvsm_n_1920		98.08 56	98.29 52	97.43 152	98.88 140	93.95 173	96.17 203	99.57 21	95.66 186	99.52 21	98.71 102	97.04 73	99.64 169	99.21 12	99.87 33	98.69 277

casdiffmvs		97.50 126	97.81 92	96.56 224	98.51 200	91.04 263	95.83 234	99.09 78	97.23 101	98.33 137	98.30 161	97.03 74	99.37 271	96.58 119	99.38 209	99.28 156
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SteuartSystems-ACMMP		98.02 62	97.76 100	98.79 33	99.43 42	97.21 45	97.15 128	98.90 133	96.58 129	98.08 168	97.87 224	97.02 75	99.76 76	95.25 198	99.59 128	99.40 125
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 396	98.37 127	97.44 263	97.00 76	96.78 445	92.01 309	99.25 242	99.21 171

EC-MVSNet		97.90 84	97.94 78	97.79 115	98.66 175	95.14 129	98.31 42	99.66 12	97.57 79	95.95 316	97.01 304	96.99 77	99.82 39	97.66 77	99.64 107	98.39 306

DVP-MVS++		97.96 67	97.90 79	98.12 92	97.75 307	95.40 111	99.03 8	98.89 137	96.62 123	98.62 99	98.30 161	96.97 78	99.75 84	95.70 163	99.25 242	99.21 171

OPU-MVS				97.64 130	98.01 264	95.27 121	96.79 155				97.35 275	96.97 78	98.51 402	91.21 327	99.25 242	99.14 188

RE-MVS-def			97.88 84		98.81 147	98.05 10	97.55 103	98.86 149	97.77 67	98.20 152	98.07 198	96.94 80		95.49 179	99.20 247	99.26 161

APDe-MVS		98.14 50	98.03 68	98.47 61	98.72 165	96.04 82	98.07 62	99.10 73	95.96 168	98.59 103	98.69 105	96.94 80	99.81 44	96.64 115	99.58 133	99.57 56
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
reproduce_model		98.54 26	98.33 47	99.15 4	99.06 108	98.04 12	97.04 136	99.09 78	98.42 44	99.03 56	98.71 102	96.93 82	99.83 36	97.09 101	99.63 109	99.56 64

test_one_0601					99.05 114	95.50 108		98.87 146	97.21 103	98.03 175	98.30 161	96.93 82

GST-MVS		97.82 95	97.49 136	98.81 31	99.23 71	97.25 42	97.16 127	98.79 177	95.96 168	97.53 208	97.40 266	96.93 82	99.77 70	95.04 217	99.35 219	99.42 122

test_241102_TWO								98.83 163	96.11 154	98.62 99	98.24 173	96.92 85	99.72 105	95.44 187	99.49 172	99.49 93

LCM-MVSNet-Re		97.33 145	97.33 145	97.32 161	98.13 256	93.79 179	96.99 139	99.65 13	96.74 120	99.47 24	98.93 77	96.91 86	99.84 34	90.11 358	99.06 271	98.32 315

viewmacassd2359aftdt		97.25 149	97.52 130	96.43 234	98.83 145	90.49 280	95.45 262	99.18 54	95.44 201	97.98 181	98.47 134	96.90 87	99.37 271	95.93 153	99.55 145	99.43 120

VPA-MVSNet		98.27 43	98.46 34	97.70 123	99.06 108	93.80 178	97.76 85	99.00 114	98.40 45	99.07 55	98.98 70	96.89 88	99.75 84	97.19 97	99.79 63	99.55 68

ACMMP		98.05 60	97.75 102	98.93 22	99.23 71	97.60 26	98.09 60	98.96 125	95.75 184	97.91 188	98.06 203	96.89 88	99.76 76	95.32 195	99.57 136	99.43 120
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
CS-MVS		98.09 55	98.01 71	98.32 71	98.45 213	96.69 56	98.52 29	99.69 9	98.07 60	96.07 312	97.19 285	96.88 90	99.86 28	97.50 83	99.73 80	98.41 303

PMVS	89.60 17	96.71 192	96.97 168	95.95 269	99.51 31	97.81 20	97.42 115	97.49 317	97.93 63	95.95 316	98.58 118	96.88 90	96.91 442	89.59 367	99.36 214	93.12 451
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 78	97.59 123	98.92 25	99.22 74	97.55 30	97.60 98	98.84 157	96.00 165	97.22 228	97.62 251	96.87 92	99.76 76	95.48 183	99.43 196	99.46 105

CP-MVS		97.92 78	97.56 126	98.99 14	98.99 119	97.82 19	97.93 72	98.96 125	96.11 154	96.89 259	97.45 262	96.85 93	99.78 59	95.19 203	99.63 109	99.38 132

DPE-MVS		97.64 113	97.35 144	98.50 57	98.85 144	96.18 75	95.21 286	98.99 118	95.84 179	98.78 83	98.08 196	96.84 94	99.81 44	93.98 270	99.57 136	99.52 78
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 91	97.97 75	97.47 148	99.19 85	94.07 167	96.71 164	98.73 189	98.66 32	98.56 106	98.41 141	96.84 94	99.69 137	94.82 233	99.81 57	98.64 281

SPE-MVS-test		97.91 82	97.84 86	98.14 90	98.52 198	96.03 84	98.38 37	99.67 10	98.11 58	95.50 337	96.92 310	96.81 96	99.87 26	96.87 111	99.76 69	98.51 295

ACMMPR		97.95 71	97.62 119	98.94 19	99.20 83	97.56 29	97.59 100	98.83 163	96.05 160	97.46 218	97.63 250	96.77 97	99.76 76	95.61 174	99.46 181	99.49 93

Vis-MVSNet		98.27 43	98.34 46	98.07 94	99.33 56	95.21 128	98.04 63	99.46 29	97.32 98	97.82 198	99.11 55	96.75 98	99.86 28	97.84 66	99.36 214	99.15 183
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 255	95.07 266	96.75 210	97.67 319	92.82 210	94.22 332	98.60 215	91.61 335	93.42 396	92.90 416	96.73 99	99.70 130	92.60 301	97.89 359	97.74 371

baseline		97.44 133	97.78 98	96.43 234	98.52 198	90.75 273	96.84 148	99.03 100	96.51 133	97.86 195	98.02 207	96.67 100	99.36 275	97.09 101	99.47 178	99.19 175

viewmsd2359difaftdt		97.13 156	97.62 119	95.67 283	98.64 176	88.36 325	94.84 309	98.95 127	96.24 147	98.70 94	98.61 114	96.66 101	99.29 301	96.46 123	99.45 184	99.36 139

SR-MVS		98.00 63	97.66 111	99.01 12	98.77 159	97.93 15	97.38 116	98.83 163	97.32 98	98.06 171	97.85 225	96.65 102	99.77 70	95.00 222	99.11 262	99.32 144

tfpnnormal		97.72 105	97.97 75	96.94 193	99.26 64	92.23 229	97.83 80	98.45 230	98.25 53	99.13 49	98.66 107	96.65 102	99.69 137	93.92 273	99.62 112	98.91 239

DeepPCF-MVS	94.58 5	96.90 172	96.43 210	98.31 73	97.48 338	97.23 44	92.56 390	98.60 215	92.84 312	98.54 107	97.40 266	96.64 104	98.78 372	94.40 252	99.41 203	98.93 235

MVS_111021_LR		96.82 181	96.55 201	97.62 131	98.27 231	95.34 118	93.81 354	98.33 249	94.59 240	96.56 284	96.63 329	96.61 105	98.73 378	94.80 234	99.34 222	98.78 259

Gipuma		98.07 58	98.31 49	97.36 158	99.76 7	96.28 73	98.51 30	99.10 73	98.76 30	96.79 264	99.34 29	96.61 105	98.82 368	96.38 128	99.50 169	96.98 400
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SR-MVS-dyc-post		98.14 50	97.84 86	99.02 10	98.81 147	98.05 10	97.55 103	98.86 149	97.77 67	98.20 152	98.07 198	96.60 107	99.76 76	95.49 179	99.20 247	99.26 161

mamba_0408		97.17 154	97.38 141	96.55 226	98.51 200	90.96 266	95.19 287	99.06 86	96.60 125	98.27 144	97.78 235	96.58 108	99.72 105	95.04 217	99.40 204	98.98 222

SSM_04072		97.14 155	97.38 141	96.42 236	98.51 200	90.96 266	95.19 287	99.06 86	96.60 125	98.27 144	97.78 235	96.58 108	99.31 293	95.04 217	99.40 204	98.98 222

MVS_111021_HR		96.73 189	96.54 203	97.27 165	98.35 223	93.66 186	93.42 367	98.36 245	94.74 230	96.58 282	96.76 322	96.54 110	98.99 352	94.87 231	99.27 238	99.15 183

SMA-MVS		97.48 128	97.11 158	98.60 49	98.83 145	96.67 57	96.74 159	98.73 189	91.61 335	98.48 114	98.36 147	96.53 111	99.68 143	95.17 206	99.54 151	99.45 109
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
v7n		98.73 15	98.99 8	97.95 106	99.64 14	94.20 164	98.67 18	99.14 66	99.08 17	99.42 29	99.23 38	96.53 111	99.91 14	99.27 10	99.93 11	99.73 26

mPP-MVS		97.91 82	97.53 129	99.04 8	99.22 74	97.87 18	97.74 88	98.78 181	96.04 162	97.10 239	97.73 243	96.53 111	99.78 59	95.16 208	99.50 169	99.46 105

XVS		97.96 67	97.63 117	98.94 19	99.15 91	97.66 23	97.77 83	98.83 163	97.42 88	96.32 296	97.64 249	96.49 114	99.72 105	95.66 168	99.37 210	99.45 109

X-MVStestdata		92.86 352	90.83 381	98.94 19	99.15 91	97.66 23	97.77 83	98.83 163	97.42 88	96.32 296	36.50 463	96.49 114	99.72 105	95.66 168	99.37 210	99.45 109

9.14			96.69 188		98.53 197		96.02 215	98.98 121	93.23 292	97.18 233	97.46 261	96.47 116	99.62 179	92.99 297	99.32 229

UA-Net		98.88 11	98.76 17	99.22 3	99.11 100	97.89 17	99.47 3	99.32 38	99.08 17	97.87 194	99.67 5	96.47 116	99.92 6	97.88 63	99.98 2	99.85 6

fmvsm_l_conf0.5_n		97.68 109	97.81 92	97.27 165	98.92 133	92.71 217	95.89 230	99.41 36	93.36 287	99.00 61	98.44 137	96.46 118	99.65 163	99.09 23	99.76 69	99.45 109

fmvsm_s_conf0.5_n_5		97.63 115	97.83 89	97.04 186	98.77 159	92.33 224	95.63 254	99.58 19	93.53 280	99.10 51	98.66 107	96.44 119	99.65 163	99.12 21	99.68 98	99.12 196

SF-MVS		97.60 118	97.39 139	98.22 82	98.93 131	95.69 95	97.05 135	99.10 73	95.32 207	97.83 197	97.88 221	96.44 119	99.72 105	94.59 247	99.39 208	99.25 166

fmvsm_s_conf0.1_n_a		97.80 98	98.01 71	97.18 172	99.17 87	92.51 220	96.57 169	99.15 63	93.68 276	98.89 73	99.30 32	96.42 121	99.37 271	99.03 25	99.83 52	99.66 36

xiu_mvs_v1_base_debu		95.62 250	95.96 235	94.60 339	98.01 264	88.42 322	93.99 344	98.21 260	92.98 306	95.91 318	94.53 394	96.39 122	99.72 105	95.43 190	98.19 345	95.64 433

xiu_mvs_v1_base		95.62 250	95.96 235	94.60 339	98.01 264	88.42 322	93.99 344	98.21 260	92.98 306	95.91 318	94.53 394	96.39 122	99.72 105	95.43 190	98.19 345	95.64 433

xiu_mvs_v1_base_debi		95.62 250	95.96 235	94.60 339	98.01 264	88.42 322	93.99 344	98.21 260	92.98 306	95.91 318	94.53 394	96.39 122	99.72 105	95.43 190	98.19 345	95.64 433

ETV-MVS		96.13 223	95.90 239	96.82 205	97.76 305	93.89 174	95.40 268	98.95 127	95.87 177	95.58 334	91.00 441	96.36 125	99.72 105	93.36 287	98.83 295	96.85 407

fmvsm_l_conf0.5_n_a		97.60 118	97.76 100	97.11 177	98.92 133	92.28 227	95.83 234	99.32 38	93.22 293	98.91 72	98.49 129	96.31 126	99.64 169	99.07 24	99.76 69	99.40 125

fmvsm_s_conf0.1_n		97.73 103	98.02 69	96.85 202	99.09 103	91.43 256	96.37 183	99.11 70	94.19 259	99.01 59	99.25 35	96.30 127	99.38 266	99.00 26	99.88 28	99.73 26

MP-MVS		97.64 113	97.18 156	99.00 13	99.32 58	97.77 21	97.49 109	98.73 189	96.27 144	95.59 333	97.75 240	96.30 127	99.78 59	93.70 281	99.48 176	99.45 109
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 230	96.34 216	94.96 319	97.90 275	87.91 339	94.13 339	98.49 227	94.41 251	98.16 158	97.76 237	96.29 129	98.68 387	90.52 351	99.42 199	98.30 319

Fast-Effi-MVS+-dtu		96.44 206	96.12 225	97.39 157	97.18 359	94.39 153	95.46 261	98.73 189	96.03 164	94.72 354	94.92 388	96.28 130	99.69 137	93.81 276	97.98 353	98.09 337

fmvsm_s_conf0.5_n_a		97.65 112	97.83 89	97.13 176	98.80 150	92.51 220	96.25 194	99.06 86	93.67 277	98.64 97	99.00 67	96.23 131	99.36 275	98.99 27	99.80 61	99.53 75

fmvsm_s_conf0.5_n		97.62 116	97.89 82	96.80 206	98.79 153	91.44 255	96.14 205	99.06 86	94.19 259	98.82 80	98.98 70	96.22 132	99.38 266	98.98 28	99.86 35	99.58 48

APD_test1		97.95 71	97.68 108	98.75 35	99.60 17	98.60 6	97.21 126	99.08 82	96.57 132	98.07 170	98.38 145	96.22 132	99.14 328	94.71 242	99.31 232	98.52 294

OMC-MVS		96.48 204	96.00 232	97.91 108	98.30 226	96.01 85	94.86 308	98.60 215	91.88 330	97.18 233	97.21 284	96.11 134	99.04 346	90.49 354	99.34 222	98.69 277

icg_test_0407_2		95.88 234	96.39 212	94.36 352	97.83 286	86.11 373	91.82 410	98.82 171	94.48 245	97.57 205	97.14 288	96.08 135	98.20 424	95.00 222	98.78 299	98.78 259

IMVS_0407		96.35 212	96.88 177	94.74 333	97.83 286	86.11 373	96.25 194	98.82 171	94.48 245	97.57 205	97.14 288	96.08 135	99.33 284	95.00 222	98.78 299	98.78 259

xiu_mvs_v2_base		94.22 314	94.63 292	92.99 391	97.32 354	84.84 396	92.12 403	97.84 297	91.96 328	94.17 367	93.43 407	96.07 137	99.71 121	91.27 324	97.48 381	94.42 443

CSCG		97.40 138	97.30 146	97.69 125	98.95 124	94.83 136	97.28 121	98.99 118	96.35 143	98.13 162	95.95 364	95.99 138	99.66 160	94.36 255	99.73 80	98.59 287

PHI-MVS		96.96 168	96.53 204	98.25 80	97.48 338	96.50 63	96.76 157	98.85 153	93.52 281	96.19 308	96.85 313	95.94 139	99.42 247	93.79 277	99.43 196	98.83 252

viewmanbaseed2359cas		96.77 185	96.94 171	96.27 248	98.41 219	90.24 282	95.11 292	99.03 100	94.28 256	97.45 219	97.85 225	95.92 140	99.32 292	95.18 205	99.19 251	99.24 167

mamv4		99.05 8	98.91 11	99.46 2	98.94 127	99.62 2	97.98 67	99.70 8	99.49 6	99.78 3	99.22 39	95.92 140	99.95 3	99.31 8	99.83 52	98.83 252

TSAR-MVS + MP.		97.42 137	97.23 152	98.00 103	99.38 51	95.00 133	97.63 97	98.20 263	93.00 305	98.16 158	98.06 203	95.89 142	99.72 105	95.67 167	99.10 264	99.28 156
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVG-ACMP-BASELINE		97.58 122	97.28 149	98.49 58	99.16 88	96.90 50	96.39 179	98.98 121	95.05 220	98.06 171	98.02 207	95.86 143	99.56 203	94.37 253	99.64 107	99.00 216

AllTest		97.20 152	96.92 174	98.06 96	99.08 104	96.16 76	97.14 130	99.16 57	94.35 253	97.78 199	98.07 198	95.84 144	99.12 332	91.41 321	99.42 199	98.91 239

TestCases				98.06 96	99.08 104	96.16 76		99.16 57	94.35 253	97.78 199	98.07 198	95.84 144	99.12 332	91.41 321	99.42 199	98.91 239

APD-MVS		97.00 163	96.53 204	98.41 65	98.55 194	96.31 71	96.32 187	98.77 182	92.96 310	97.44 220	97.58 255	95.84 144	99.74 93	91.96 310	99.35 219	99.19 175
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 435	10.65 438	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	95.82 147	0.00 469	0.00 468	0.00 467	0.00 465

PS-MVSNAJss		98.53 28	98.63 24	98.21 85	99.68 12	94.82 137	98.10 59	99.21 48	96.91 113	99.75 6	99.45 18	95.82 147	99.92 6	98.80 31	99.96 4	99.89 4

PS-MVSNAJ		94.10 320	94.47 302	93.00 390	97.35 349	84.88 393	91.86 408	97.84 297	91.96 328	94.17 367	92.50 426	95.82 147	99.71 121	91.27 324	97.48 381	94.40 444

3Dnovator	96.53 2	97.61 117	97.64 115	97.50 143	97.74 310	93.65 187	98.49 31	98.88 144	96.86 115	97.11 238	98.55 123	95.82 147	99.73 99	95.94 152	99.42 199	99.13 190

MTAPA		98.14 50	97.84 86	99.06 7	99.44 41	97.90 16	97.25 122	98.73 189	97.69 75	97.90 189	97.96 213	95.81 151	99.82 39	96.13 140	99.61 118	99.45 109

DP-MVS		97.87 88	97.89 82	97.81 114	98.62 183	94.82 137	97.13 131	98.79 177	98.98 24	98.74 90	98.49 129	95.80 152	99.49 227	95.04 217	99.44 186	99.11 200

Anonymous20240529		97.96 67	98.04 67	97.71 121	98.69 172	94.28 162	97.86 77	98.31 253	98.79 29	99.23 43	98.86 87	95.76 153	99.61 187	95.49 179	99.36 214	99.23 169

LS3D		97.77 101	97.50 134	98.57 51	96.24 385	97.58 28	98.45 34	98.85 153	98.58 37	97.51 210	97.94 216	95.74 154	99.63 174	95.19 203	98.97 276	98.51 295

fmvsm_s_conf0.5_n_6		97.45 131	97.79 94	96.44 232	98.58 189	90.31 281	95.77 238	99.33 37	94.52 243	98.85 76	98.44 137	95.68 155	99.62 179	99.15 19	99.81 57	99.38 132

EIA-MVS		96.04 226	95.77 247	96.85 202	97.80 295	92.98 207	96.12 206	99.16 57	94.65 236	93.77 380	91.69 435	95.68 155	99.67 152	94.18 260	98.85 292	97.91 357

CNVR-MVS		96.92 170	96.55 201	98.03 101	98.00 268	95.54 103	94.87 307	98.17 269	94.60 238	96.38 293	97.05 299	95.67 157	99.36 275	95.12 214	99.08 266	99.19 175

CLD-MVS		95.47 258	95.07 266	96.69 214	98.27 231	92.53 219	91.36 418	98.67 204	91.22 345	95.78 326	94.12 401	95.65 158	98.98 354	90.81 337	99.72 85	98.57 288
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous20231211		98.55 25	98.76 17	97.94 107	98.79 153	94.37 156	98.84 14	99.15 63	99.37 7	99.67 11	99.43 20	95.61 159	99.72 105	98.12 50	99.86 35	99.73 26

EGC-MVSNET		83.08 427	77.93 430	98.53 55	99.57 20	97.55 30	98.33 41	98.57 221	4.71 465	10.38 466	98.90 83	95.60 160	99.50 221	95.69 165	99.61 118	98.55 291

fmvsm_s_conf0.5_n_4		97.43 135	97.77 99	96.39 242	98.48 209	89.89 287	95.65 249	99.26 44	94.73 232	98.72 92	98.58 118	95.58 161	99.57 201	99.28 9	99.67 101	99.73 26

ITE_SJBPF				97.85 112	98.64 176	96.66 58		98.51 226	95.63 188	97.22 228	97.30 279	95.52 162	98.55 399	90.97 332	98.90 285	98.34 314

DeepC-MVS_fast	94.34 7	96.74 187	96.51 206	97.44 151	97.69 314	94.15 165	96.02 215	98.43 233	93.17 300	97.30 223	97.38 272	95.48 163	99.28 304	93.74 278	99.34 222	98.88 247
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
WR-MVS_H		98.65 19	98.62 26	98.75 35	99.51 31	96.61 60	98.55 25	99.17 56	99.05 20	99.17 46	98.79 89	95.47 164	99.89 21	97.95 61	99.91 19	99.75 24

FMVSNet1		97.95 71	98.08 62	97.56 134	99.14 98	93.67 183	98.23 49	98.66 207	97.41 92	99.00 61	99.19 42	95.47 164	99.73 99	95.83 160	99.76 69	99.30 149

MIMVSNet1		98.51 29	98.45 37	98.67 44	99.72 8	96.71 54	98.76 16	98.89 137	98.49 41	99.38 32	99.14 53	95.44 166	99.84 34	96.47 122	99.80 61	99.47 103

mmtdpeth		98.33 37	98.53 32	97.71 121	99.07 106	93.44 194	98.80 15	99.78 4	99.10 16	96.61 280	99.63 10	95.42 167	99.73 99	98.53 42	99.86 35	99.95 2

IMVS_0403		96.27 215	96.77 185	94.76 331	97.83 286	86.11 373	96.00 217	98.82 171	94.48 245	97.49 212	97.14 288	95.38 168	99.40 258	95.00 222	98.78 299	98.78 259

CP-MVSNet		98.42 34	98.46 34	98.30 74	99.46 39	95.22 126	98.27 47	98.84 157	99.05 20	99.01 59	98.65 111	95.37 169	99.90 18	97.57 80	99.91 19	99.77 15

fmvsm_s_conf0.5_n_9		97.98 64	98.32 48	96.96 191	98.92 133	91.45 254	95.87 231	99.53 26	97.44 86	99.56 19	99.05 62	95.34 170	99.67 152	99.52 2	99.70 92	99.77 15

segment_acmp												95.34 170

CDPH-MVS		95.45 260	94.65 289	97.84 113	98.28 229	94.96 134	93.73 356	98.33 249	85.03 421	95.44 338	96.60 330	95.31 172	99.44 243	90.01 360	99.13 258	99.11 200

3Dnovator+	96.13 3	97.73 103	97.59 123	98.15 89	98.11 257	95.60 99	98.04 63	98.70 198	98.13 57	96.93 256	98.45 135	95.30 173	99.62 179	95.64 170	98.96 277	99.24 167

MVS_Test		96.27 215	96.79 184	94.73 334	96.94 369	86.63 365	96.18 199	98.33 249	94.94 224	96.07 312	98.28 166	95.25 174	99.26 308	97.21 94	97.90 358	98.30 319

XVG-OURS		97.12 158	96.74 186	98.26 77	98.99 119	97.45 36	93.82 352	99.05 92	95.19 212	98.32 138	97.70 245	95.22 175	98.41 409	94.27 257	98.13 348	98.93 235

fmvsm_s_conf0.5_n_2		97.59 121	98.07 63	96.17 257	98.78 157	89.10 310	95.33 277	99.55 24	95.96 168	99.41 31	99.10 56	95.18 176	99.59 192	99.43 5	99.86 35	99.81 10

fmvsm_s_conf0.1_n_2		97.68 109	98.18 56	96.20 253	99.06 108	89.08 311	95.51 259	99.72 6	96.06 159	99.48 22	99.24 36	95.18 176	99.60 190	99.45 3	99.88 28	99.94 3

dcpmvs_2		97.12 158	97.99 73	94.51 346	99.11 100	84.00 407	97.75 86	99.65 13	97.38 95	99.14 48	98.42 139	95.16 178	99.96 2	95.52 178	99.78 67	99.58 48

MCST-MVS		96.24 217	95.80 245	97.56 134	98.75 161	94.13 166	94.66 317	98.17 269	90.17 361	96.21 306	96.10 358	95.14 179	99.43 245	94.13 263	98.85 292	99.13 190

EI-MVSNet-Vis-set		97.32 146	97.39 139	97.11 177	97.36 348	92.08 239	95.34 276	97.65 310	97.74 70	98.29 143	98.11 192	95.05 180	99.68 143	97.50 83	99.50 169	99.56 64

EI-MVSNet-UG-set		97.32 146	97.40 138	97.09 181	97.34 351	92.01 241	95.33 277	97.65 310	97.74 70	98.30 142	98.14 185	95.04 181	99.69 137	97.55 81	99.52 160	99.58 48

KD-MVS_self_test		97.86 90	98.07 63	97.25 168	99.22 74	92.81 212	97.55 103	98.94 129	97.10 105	98.85 76	98.88 85	95.03 182	99.67 152	97.39 88	99.65 105	99.26 161

ZD-MVS					98.43 215	95.94 86		98.56 222	90.72 351	96.66 276	97.07 297	95.02 183	99.74 93	91.08 328	98.93 283

DELS-MVS		96.17 221	96.23 221	95.99 264	97.55 333	90.04 284	92.38 399	98.52 224	94.13 261	96.55 286	97.06 298	94.99 184	99.58 195	95.62 173	99.28 236	98.37 308
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
patch_mono-2		96.59 197	96.93 172	95.55 292	98.88 140	87.12 357	94.47 322	99.30 40	94.12 262	96.65 278	98.41 141	94.98 185	99.87 26	95.81 162	99.78 67	99.66 36

fmvsm_s_conf0.5_n_7		97.13 156	97.50 134	96.04 262	98.43 215	89.03 312	94.92 304	99.00 114	94.51 244	98.42 121	98.96 73	94.97 186	99.54 210	98.42 45	99.85 45	99.56 64

ab-mvs		96.59 197	96.59 194	96.60 218	98.64 176	92.21 230	98.35 38	97.67 306	94.45 250	96.99 250	98.79 89	94.96 187	99.49 227	90.39 355	99.07 268	98.08 338

MSLP-MVS++		96.42 209	96.71 187	95.57 288	97.82 290	90.56 277	95.71 241	98.84 157	94.72 233	96.71 271	97.39 270	94.91 188	98.10 426	95.28 196	99.02 273	98.05 347

QAPM		95.88 234	95.57 254	96.80 206	97.90 275	91.84 246	98.18 56	98.73 189	88.41 383	96.42 291	98.13 187	94.73 189	99.75 84	88.72 379	98.94 280	98.81 255

RPSCF		97.87 88	97.51 132	98.95 18	99.15 91	98.43 7	97.56 102	99.06 86	96.19 151	98.48 114	98.70 104	94.72 190	99.24 314	94.37 253	99.33 227	99.17 179

viewmambaseed2359dif		95.68 246	95.85 242	95.17 307	97.51 335	87.41 351	93.61 362	98.58 219	91.06 347	96.68 272	97.66 248	94.71 191	99.11 335	93.93 272	98.94 280	98.99 219

DU-MVS		97.79 99	97.60 122	98.36 69	98.73 162	95.78 91	95.65 249	98.87 146	97.57 79	98.31 140	97.83 228	94.69 192	99.85 31	97.02 106	99.71 88	99.46 105

Baseline_NR-MVSNet		97.72 105	97.79 94	97.50 143	99.56 22	93.29 200	95.44 263	98.86 149	98.20 56	98.37 127	99.24 36	94.69 192	99.55 207	95.98 150	99.79 63	99.65 39

TEST9					97.84 283	95.23 123	93.62 360	98.39 240	86.81 402	93.78 378	95.99 360	94.68 194	99.52 216

UniMVSNet (Re)		97.83 92	97.65 112	98.35 70	98.80 150	95.86 90	95.92 228	99.04 99	97.51 83	98.22 151	97.81 233	94.68 194	99.78 59	97.14 99	99.75 78	99.41 124

UniMVSNet_NR-MVSNet		97.83 92	97.65 112	98.37 68	98.72 165	95.78 91	95.66 247	99.02 103	98.11 58	98.31 140	97.69 246	94.65 196	99.85 31	97.02 106	99.71 88	99.48 99

diffmvs_AUTHOR		96.50 202	96.81 180	95.57 288	98.03 260	88.26 328	93.73 356	99.14 66	94.92 227	97.24 227	97.84 227	94.62 197	99.33 284	96.44 125	99.37 210	99.13 190

VPNet		97.26 148	97.49 136	96.59 219	99.47 38	90.58 275	96.27 190	98.53 223	97.77 67	98.46 117	98.41 141	94.59 198	99.68 143	94.61 243	99.29 235	99.52 78

train_agg		95.46 259	94.66 288	97.88 110	97.84 283	95.23 123	93.62 360	98.39 240	87.04 398	93.78 378	95.99 360	94.58 199	99.52 216	91.76 318	98.90 285	98.89 243

test_8					97.81 291	95.07 132	93.54 364	98.38 242	87.04 398	93.71 382	95.96 363	94.58 199	99.52 216

fmvsm_s_conf0.5_n_8		97.66 111	98.12 58	96.27 248	98.79 153	89.43 301	95.76 239	99.42 33	97.49 84	99.16 47	99.04 63	94.56 201	99.69 137	99.18 16	99.73 80	99.70 31

API-MVS		95.09 278	95.01 269	95.31 301	96.61 376	94.02 170	96.83 149	97.18 327	95.60 190	95.79 324	94.33 399	94.54 202	98.37 414	85.70 410	98.52 327	93.52 448

Test By Simon												94.51 203

MSDG		95.33 266	95.13 263	95.94 271	97.40 346	91.85 245	91.02 429	98.37 244	95.30 208	96.31 299	95.99 360	94.51 203	98.38 412	89.59 367	97.65 375	97.60 381

TSAR-MVS + GP.		96.47 205	96.12 225	97.49 146	97.74 310	95.23 123	94.15 336	96.90 339	93.26 291	98.04 174	96.70 325	94.41 205	98.89 362	94.77 238	99.14 256	98.37 308

NR-MVSNet		97.96 67	97.86 85	98.26 77	98.73 162	95.54 103	98.14 57	98.73 189	97.79 66	99.42 29	97.83 228	94.40 206	99.78 59	95.91 155	99.76 69	99.46 105

AdaColmap		95.11 276	94.62 293	96.58 220	97.33 353	94.45 152	94.92 304	98.08 281	93.15 301	93.98 376	95.53 376	94.34 207	99.10 339	85.69 411	98.61 322	96.20 426

Elysia		98.19 47	98.37 41	97.66 127	99.28 60	93.52 190	97.35 117	98.90 133	98.63 33	99.45 25	98.32 155	94.31 208	99.91 14	99.19 14	99.88 28	99.54 70

StellarMVS		98.19 47	98.37 41	97.66 127	99.28 60	93.52 190	97.35 117	98.90 133	98.63 33	99.45 25	98.32 155	94.31 208	99.91 14	99.19 14	99.88 28	99.54 70

FC-MVSNet-test		98.16 49	98.37 41	97.56 134	99.49 35	93.10 205	98.35 38	99.21 48	98.43 43	98.89 73	98.83 88	94.30 210	99.81 44	97.87 64	99.91 19	99.77 15

Effi-MVS+-dtu		96.81 182	96.09 227	98.99 14	96.90 371	98.69 5	96.42 176	98.09 280	95.86 178	95.15 344	95.54 375	94.26 211	99.81 44	94.06 265	98.51 330	98.47 300

ambc				96.56 224	98.23 237	91.68 250	97.88 76	98.13 277		98.42 121	98.56 122	94.22 212	99.04 346	94.05 267	99.35 219	98.95 228

test20.03		96.58 199	96.61 193	96.48 231	98.49 207	91.72 248	95.68 245	97.69 305	96.81 117	98.27 144	97.92 219	94.18 213	98.71 381	90.78 339	99.66 104	99.00 216

HPM-MVS++		96.99 164	96.38 214	98.81 31	98.64 176	97.59 27	95.97 222	98.20 263	95.51 196	95.06 346	96.53 334	94.10 214	99.70 130	94.29 256	99.15 255	99.13 190

test_vis3_rt		97.04 161	96.98 167	97.23 171	98.44 214	95.88 88	96.82 150	99.67 10	90.30 358	99.27 40	99.33 31	94.04 215	96.03 450	97.14 99	97.83 361	99.78 14

test_fmvs3		97.38 140	97.56 126	96.84 204	98.63 181	92.81 212	97.60 98	99.61 18	90.87 349	98.76 88	99.66 6	94.03 216	97.90 429	99.24 11	99.68 98	99.81 10

PM-MVS		97.36 144	97.10 159	98.14 90	98.91 136	96.77 53	96.20 198	98.63 213	93.82 270	98.54 107	98.33 152	93.98 217	99.05 344	95.99 149	99.45 184	98.61 286

mvsany_test3		96.21 218	95.93 238	97.05 184	97.40 346	94.33 158	95.76 239	94.20 393	89.10 372	99.36 35	99.60 11	93.97 218	97.85 430	95.40 194	98.63 320	98.99 219

OpenMVS	94.22 8	95.48 257	95.20 259	96.32 245	97.16 360	91.96 242	97.74 88	98.84 157	87.26 395	94.36 363	98.01 209	93.95 219	99.67 152	90.70 346	98.75 306	97.35 392

v8		97.60 118	98.06 66	96.23 250	98.71 168	89.44 300	97.43 114	98.82 171	97.29 100	98.74 90	99.10 56	93.86 220	99.68 143	98.61 39	99.94 8	99.56 64

diffmvs		96.04 226	96.23 221	95.46 297	97.35 349	88.03 337	93.42 367	99.08 82	94.09 265	96.66 276	96.93 308	93.85 221	99.29 301	96.01 148	98.67 315	99.06 209
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NCCC		96.52 201	95.99 233	98.10 93	97.81 291	95.68 96	95.00 302	98.20 263	95.39 204	95.40 340	96.36 345	93.81 222	99.45 240	93.55 284	98.42 336	99.17 179

TAPA-MVS	93.32 12	94.93 283	94.23 310	97.04 186	98.18 244	94.51 149	95.22 285	98.73 189	81.22 440	96.25 303	95.95 364	93.80 223	98.98 354	89.89 363	98.87 289	97.62 379
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SD_0403		93.73 331	93.43 330	94.64 335	97.85 277	86.35 370	97.47 110	97.94 289	93.50 282	93.71 382	96.73 323	93.77 224	98.84 367	73.48 454	96.39 412	98.72 272

FIs		97.93 77	98.07 63	97.48 147	99.38 51	92.95 209	98.03 65	99.11 70	98.04 62	98.62 99	98.66 107	93.75 225	99.78 59	97.23 92	99.84 48	99.73 26

OurMVSNet-221017-0		98.61 20	98.61 28	98.63 48	99.77 5	96.35 69	99.17 7	99.05 92	98.05 61	99.61 17	99.52 12	93.72 226	99.88 23	98.72 37	99.88 28	99.65 39

SSC-MVS3.2		95.75 242	96.56 198	93.34 376	98.69 172	80.75 431	91.60 413	97.43 321	97.37 96	96.99 250	97.02 301	93.69 227	99.71 121	96.32 132	99.89 26	99.55 68

test_prior2							93.33 371		94.21 257	94.02 374	96.25 349	93.64 228		91.90 312	98.96 277

mvsany_test1		93.47 340	93.03 337	94.79 329	94.05 445	92.12 235	90.82 431	90.01 444	85.02 422	97.26 226	98.28 166	93.57 229	97.03 439	92.51 304	95.75 427	95.23 439

旧先验1					97.80 295	93.87 175		97.75 302			97.04 300	93.57 229			98.68 314	98.72 272

IMVS_0404		95.66 249	96.03 230	94.55 343	97.83 286	86.11 373	93.24 373	98.82 171	94.48 245	95.51 336	97.14 288	93.49 231	98.78 372	95.00 222	98.78 299	98.78 259

v10		97.55 123	97.97 75	96.31 246	98.60 185	89.64 295	97.44 112	99.02 103	96.60 125	98.72 92	99.16 50	93.48 232	99.72 105	98.76 33	99.92 15	99.58 48

v148		96.58 199	96.97 168	95.42 298	98.63 181	87.57 347	95.09 294	97.90 292	95.91 175	98.24 149	97.96 213	93.42 233	99.39 263	96.04 144	99.52 160	99.29 155

V42		97.04 161	97.16 157	96.68 215	98.59 187	91.05 262	96.33 186	98.36 245	94.60 238	97.99 177	98.30 161	93.32 234	99.62 179	97.40 87	99.53 155	99.38 132

new-patchmatchnet		95.67 247	96.58 195	92.94 393	97.48 338	80.21 434	92.96 378	98.19 268	94.83 228	98.82 80	98.79 89	93.31 235	99.51 220	95.83 160	99.04 272	99.12 196

test12				97.46 149	97.61 327	94.07 167		97.78 301		93.57 390		93.31 235	99.42 247		98.78 299	98.89 243

KinetiMVS		97.82 95	98.02 69	97.24 170	99.24 68	92.32 226	96.92 142	98.38 242	98.56 40	99.03 56	98.33 152	93.22 237	99.83 36	98.74 34	99.71 88	99.57 56

UGNet		96.81 182	96.56 198	97.58 133	96.64 375	93.84 177	97.75 86	97.12 330	96.47 138	93.62 386	98.88 85	93.22 237	99.53 213	95.61 174	99.69 94	99.36 139
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
mvs5depth		98.06 59	98.58 30	96.51 228	98.97 123	89.65 294	99.43 4	99.81 2	99.30 10	98.36 130	99.86 2	93.15 239	99.88 23	98.50 43	99.84 48	99.99 1

pmmvs-eth3d		96.49 203	96.18 224	97.42 154	98.25 234	94.29 159	94.77 313	98.07 285	89.81 365	97.97 182	98.33 152	93.11 240	99.08 341	95.46 186	99.84 48	98.89 243

v1144		96.84 177	97.08 161	96.13 260	98.42 217	89.28 304	95.41 267	98.67 204	94.21 257	97.97 182	98.31 157	93.06 241	99.65 163	98.06 56	99.62 112	99.45 109

MVSMamba_PlusPlus		97.43 135	97.98 74	95.78 277	98.88 140	89.70 291	98.03 65	98.85 153	99.18 14	96.84 263	99.12 54	93.04 242	99.91 14	98.38 46	99.55 145	97.73 372

PVSNet_BlendedMVS		95.02 282	94.93 272	95.27 302	97.79 300	87.40 352	94.14 338	98.68 201	88.94 376	94.51 359	98.01 209	93.04 242	99.30 297	89.77 365	99.49 172	99.11 200

PVSNet_Blended		93.96 326	93.65 326	94.91 320	97.79 300	87.40 352	91.43 417	98.68 201	84.50 428	94.51 359	94.48 397	93.04 242	99.30 297	89.77 365	98.61 322	98.02 350

mvs_anonymous		95.36 263	96.07 229	93.21 383	96.29 384	81.56 424	94.60 319	97.66 308	93.30 290	96.95 255	98.91 82	93.03 245	99.38 266	96.60 117	97.30 389	98.69 277

v1192		96.83 180	97.06 163	96.15 259	98.28 229	89.29 303	95.36 272	98.77 182	93.73 272	98.11 163	98.34 151	93.02 246	99.67 152	98.35 47	99.58 133	99.50 85

F-COLMAP		95.30 268	94.38 307	98.05 100	98.64 176	96.04 82	95.61 255	98.66 207	89.00 375	93.22 399	96.40 343	92.90 247	99.35 279	87.45 399	97.53 379	98.77 266

WR-MVS		96.90 172	96.81 180	97.16 173	98.56 193	92.20 233	94.33 325	98.12 278	97.34 97	98.20 152	97.33 277	92.81 248	99.75 84	94.79 235	99.81 57	99.54 70

v1240		96.74 187	97.02 166	95.91 272	98.18 244	88.52 321	95.39 269	98.88 144	93.15 301	98.46 117	98.40 144	92.80 249	99.71 121	98.45 44	99.49 172	99.49 93

MVE	73.61 22	86.48 424	85.92 423	88.18 438	96.23 387	85.28 387	81.78 459	75.79 463	86.01 408	82.53 459	91.88 432	92.74 250	87.47 462	71.42 458	94.86 435	91.78 453
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 253	95.13 263	96.80 206	98.51 200	93.99 172	94.60 319	98.69 199	90.20 360	95.78 326	96.21 351	92.73 251	98.98 354	90.58 350	98.86 291	97.42 389

CANet		95.86 236	95.65 251	96.49 230	96.41 382	90.82 270	94.36 324	98.41 237	94.94 224	92.62 415	96.73 323	92.68 252	99.71 121	95.12 214	99.60 125	98.94 231

v1921920		96.72 190	96.96 170	95.99 264	98.21 238	88.79 318	95.42 265	98.79 177	93.22 293	98.19 156	98.26 171	92.68 252	99.70 130	98.34 48	99.55 145	99.49 93

BH-untuned		94.69 296	94.75 286	94.52 345	97.95 273	87.53 348	94.07 341	97.01 335	93.99 267	97.10 239	95.65 371	92.65 254	98.95 359	87.60 394	96.74 402	97.09 397

LF4IMVS		96.07 224	95.63 252	97.36 158	98.19 241	95.55 102	95.44 263	98.82 171	92.29 323	95.70 330	96.55 332	92.63 255	98.69 384	91.75 319	99.33 227	97.85 362

v2v482		96.78 184	97.06 163	95.95 269	98.57 191	88.77 319	95.36 272	98.26 255	95.18 213	97.85 196	98.23 175	92.58 256	99.63 174	97.80 68	99.69 94	99.45 109

WB-MVSnew		91.50 377	91.29 370	92.14 411	94.85 430	80.32 433	93.29 372	88.77 447	88.57 382	94.03 373	92.21 428	92.56 257	98.28 419	80.21 441	97.08 391	97.81 366

EI-MVSNet		96.63 196	96.93 172	95.74 279	97.26 356	88.13 334	95.29 282	97.65 310	96.99 106	97.94 186	98.19 180	92.55 258	99.58 195	96.91 109	99.56 139	99.50 85

IterMVS-LS		96.92 170	97.29 147	95.79 276	98.51 200	88.13 334	95.10 293	98.66 207	96.99 106	98.46 117	98.68 106	92.55 258	99.74 93	96.91 109	99.79 63	99.50 85
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 142	97.25 150	97.74 119	98.69 172	94.50 151	97.04 136	95.61 369	98.59 36	98.51 109	98.72 99	92.54 260	99.58 195	96.02 146	99.49 172	99.12 196

MVS		90.02 391	89.20 398	92.47 405	94.71 433	86.90 361	95.86 232	96.74 346	64.72 460	90.62 428	92.77 420	92.54 260	98.39 411	79.30 443	95.56 429	92.12 452

test_vis1_rt		94.03 325	93.65 326	95.17 307	95.76 412	93.42 196	93.97 347	98.33 249	84.68 425	93.17 400	95.89 366	92.53 262	94.79 454	93.50 285	94.97 433	97.31 394

v144192		96.69 193	96.90 176	96.03 263	98.25 234	88.92 313	95.49 260	98.77 182	93.05 303	98.09 166	98.29 165	92.51 263	99.70 130	98.11 51	99.56 139	99.47 103

原ACMM1				96.58 220	98.16 249	92.12 235		98.15 275	85.90 411	93.49 392	96.43 340	92.47 264	99.38 266	87.66 393	98.62 321	98.23 326

VNet		96.84 177	96.83 179	96.88 200	98.06 259	92.02 240	96.35 185	97.57 316	97.70 74	97.88 191	97.80 234	92.40 265	99.54 210	94.73 240	98.96 277	99.08 205

114514_t		93.96 326	93.22 335	96.19 255	99.06 108	90.97 265	95.99 220	98.94 129	73.88 458	93.43 395	96.93 308	92.38 266	99.37 271	89.09 374	99.28 236	98.25 325

balanced_conf03		96.88 174	97.29 147	95.63 285	97.66 320	89.47 299	97.95 70	98.89 137	95.94 171	97.77 201	98.55 123	92.23 267	99.68 143	97.05 105	99.61 118	97.73 372

CPTT-MVS		96.69 193	96.08 228	98.49 58	98.89 139	96.64 59	97.25 122	98.77 182	92.89 311	96.01 315	97.13 292	92.23 267	99.67 152	92.24 307	99.34 222	99.17 179

MSP-MVS		97.45 131	96.92 174	99.03 9	99.26 64	97.70 22	97.66 94	98.89 137	95.65 187	98.51 109	96.46 338	92.15 269	99.81 44	95.14 211	98.58 325	99.58 48
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
MAR-MVS		94.21 316	93.03 337	97.76 118	96.94 369	97.44 37	96.97 140	97.15 328	87.89 392	92.00 420	92.73 422	92.14 270	99.12 332	83.92 425	97.51 380	96.73 414
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
PVSNet_Blended_VisFu		95.95 231	95.80 245	96.42 236	99.28 60	90.62 274	95.31 280	99.08 82	88.40 384	96.97 254	98.17 184	92.11 271	99.78 59	93.64 282	99.21 246	98.86 250

BH-RMVSNet		94.56 304	94.44 305	94.91 320	97.57 330	87.44 350	93.78 355	96.26 352	93.69 275	96.41 292	96.50 337	92.10 272	99.00 350	85.96 408	97.71 368	98.31 317

新几何1				97.25 168	98.29 227	94.70 141		97.73 303	77.98 451	94.83 353	96.67 327	92.08 273	99.45 240	88.17 388	98.65 319	97.61 380

testdata				95.70 282	98.16 249	90.58 275		97.72 304	80.38 443	95.62 331	97.02 301	92.06 274	98.98 354	89.06 376	98.52 327	97.54 384

YYNet1		94.73 291	94.84 280	94.41 351	97.47 342	85.09 391	90.29 436	95.85 363	92.52 317	97.53 208	97.76 237	91.97 275	99.18 321	93.31 290	96.86 396	98.95 228

Anonymous20231206		95.27 269	95.06 268	95.88 273	98.72 165	89.37 302	95.70 242	97.85 295	88.00 390	96.98 253	97.62 251	91.95 276	99.34 282	89.21 372	99.53 155	98.94 231

MS-PatchMatch		94.83 288	94.91 274	94.57 342	96.81 372	87.10 358	94.23 331	97.34 322	88.74 379	97.14 235	97.11 295	91.94 277	98.23 421	92.99 297	97.92 356	98.37 308

MDA-MVSNet_test_wron		94.73 291	94.83 282	94.42 350	97.48 338	85.15 389	90.28 437	95.87 362	92.52 317	97.48 215	97.76 237	91.92 278	99.17 325	93.32 289	96.80 401	98.94 231

HQP_MVS		96.66 195	96.33 217	97.68 126	98.70 170	94.29 159	96.50 173	98.75 186	96.36 141	96.16 309	96.77 320	91.91 279	99.46 235	92.59 302	99.20 247	99.28 156

plane_prior6					98.38 220	94.37 156						91.91 279

MVP-Stereo		95.69 244	95.28 257	96.92 195	98.15 251	93.03 206	95.64 253	98.20 263	90.39 357	96.63 279	97.73 243	91.63 281	99.10 339	91.84 315	97.31 388	98.63 283
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 302	93.81 324	97.02 189	98.19 241	95.72 93	93.66 358	97.23 324	88.17 388	94.94 351	95.62 373	91.43 282	98.57 396	87.36 400	97.68 371	96.76 413

MDA-MVSNet-bldmvs		95.69 244	95.67 249	95.74 279	98.48 209	88.76 320	92.84 380	97.25 323	96.00 165	97.59 204	97.95 215	91.38 283	99.46 235	93.16 295	96.35 414	98.99 219

SSC-MVS		95.92 232	97.03 165	92.58 402	99.28 60	78.39 439	96.68 166	95.12 381	98.90 26	99.11 50	98.66 107	91.36 284	99.68 143	95.00 222	99.16 254	99.67 34

PAPR		92.22 362	91.27 372	95.07 312	95.73 414	88.81 317	91.97 406	97.87 294	85.80 412	90.91 427	92.73 422	91.16 285	98.33 416	79.48 442	95.76 426	98.08 338

1314		92.38 359	92.30 354	92.64 401	95.42 421	85.15 389	95.86 232	96.97 337	85.40 417	90.62 428	93.06 414	91.12 286	97.80 432	86.74 405	95.49 430	94.97 441

WB-MVS		95.50 254	96.62 191	92.11 412	99.21 81	77.26 449	96.12 206	95.40 375	98.62 35	98.84 78	98.26 171	91.08 287	99.50 221	93.37 286	98.70 313	99.58 48

ppachtmachnet_test		94.49 308	94.84 280	93.46 375	96.16 391	82.10 419	90.59 433	97.48 318	90.53 355	97.01 249	97.59 253	91.01 288	99.36 275	93.97 271	99.18 252	98.94 231

PLC	91.02 16	94.05 323	92.90 340	97.51 139	98.00 268	95.12 131	94.25 329	98.25 256	86.17 407	91.48 425	95.25 380	91.01 288	99.19 320	85.02 420	96.69 405	98.22 328
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 247	93.24 203	92.74 385	97.61 315	75.17 456	94.65 356	96.69 326	90.96 290			98.66 317	97.66 376

CL-MVSNet_self_test		95.04 279	94.79 285	95.82 275	97.51 335	89.79 290	91.14 426	96.82 342	93.05 303	96.72 270	96.40 343	90.82 291	99.16 326	91.95 311	98.66 317	98.50 298

USDC		94.56 304	94.57 299	94.55 343	97.78 303	86.43 368	92.75 383	98.65 212	85.96 409	96.91 258	97.93 218	90.82 291	98.74 377	90.71 345	99.59 128	98.47 300

PCF-MVS	89.43 18	92.12 365	90.64 385	96.57 222	97.80 295	93.48 193	89.88 443	98.45 230	74.46 457	96.04 314	95.68 370	90.71 293	99.31 293	73.73 453	99.01 275	96.91 404
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 302	94.17 314	95.96 267	98.36 222	91.23 260	95.93 227	97.95 288	92.98 306	93.42 396	94.43 398	90.53 294	98.38 412	87.60 394	96.29 416	98.27 323

our_test_3		94.20 318	94.58 297	93.07 386	96.16 391	81.20 428	90.42 435	96.84 340	90.72 351	97.14 235	97.13 292	90.47 295	99.11 335	94.04 268	98.25 343	98.91 239

MM		96.87 175	96.62 191	97.62 131	97.72 312	93.30 199	96.39 179	92.61 414	97.90 65	96.76 269	98.64 112	90.46 296	99.81 44	99.16 18	99.94 8	99.76 21

test_f		95.82 238	95.88 241	95.66 284	97.61 327	93.21 204	95.61 255	98.17 269	86.98 400	98.42 121	99.47 16	90.46 296	94.74 455	97.71 74	98.45 334	99.03 212

OpenMVS_ROB	91.80 14	93.64 336	93.05 336	95.42 298	97.31 355	91.21 261	95.08 296	96.68 349	81.56 437	96.88 260	96.41 341	90.44 298	99.25 310	85.39 416	97.67 372	95.80 431

HQP2-MVS												90.33 299

N_pmnet		95.18 273	94.23 310	98.06 96	97.85 277	96.55 62	92.49 391	91.63 423	89.34 369	98.09 166	97.41 265	90.33 299	99.06 343	91.58 320	99.31 232	98.56 289

HQP-MVS		95.17 275	94.58 297	96.92 195	97.85 277	92.47 222	94.26 326	98.43 233	93.18 297	92.86 406	95.08 382	90.33 299	99.23 316	90.51 352	98.74 307	99.05 211

CNLPA		95.04 279	94.47 302	96.75 210	97.81 291	95.25 122	94.12 340	97.89 293	94.41 251	94.57 357	95.69 369	90.30 302	98.35 415	86.72 406	98.76 305	96.64 415

PMMVS		92.39 358	91.08 375	96.30 247	93.12 452	92.81 212	90.58 434	95.96 359	79.17 448	91.85 422	92.27 427	90.29 303	98.66 389	89.85 364	96.68 406	97.43 388

TR-MVS		92.54 357	92.20 357	93.57 373	96.49 379	86.66 364	93.51 365	94.73 386	89.96 363	94.95 350	93.87 404	90.24 304	98.61 393	81.18 438	94.88 434	95.45 437

TAMVS		95.49 255	94.94 270	97.16 173	98.31 225	93.41 197	95.07 297	96.82 342	91.09 346	97.51 210	97.82 231	89.96 305	99.42 247	88.42 384	99.44 186	98.64 281

DPM-MVS		93.68 334	92.77 347	96.42 236	97.91 274	92.54 218	91.17 425	97.47 319	84.99 423	93.08 402	94.74 390	89.90 306	99.00 350	87.54 396	98.09 350	97.72 374

PMMVS2		93.66 335	94.07 317	92.45 406	97.57 330	80.67 432	86.46 451	96.00 357	93.99 267	97.10 239	97.38 272	89.90 306	97.82 431	88.76 378	99.47 178	98.86 250

BH-w/o		92.14 364	91.94 359	92.73 399	97.13 362	85.30 385	92.46 393	95.64 366	89.33 370	94.21 365	92.74 421	89.60 308	98.24 420	81.68 435	94.66 436	94.66 442

Anonymous20240521		97.07 160	97.51 132	95.76 278	99.35 54	88.18 331	97.78 82	98.40 239	97.11 104	98.34 134	99.04 63	89.58 309	99.79 54	98.09 53	99.93 11	99.30 149

UnsupCasMVSNet_bld		94.72 295	94.26 309	96.08 261	98.62 183	90.54 278	93.38 369	98.05 287	90.30 358	97.02 248	96.80 319	89.54 310	99.16 326	88.44 383	96.18 418	98.56 289

MG-MVS		94.08 322	94.00 319	94.32 356	97.09 363	85.89 378	93.19 376	95.96 359	92.52 317	94.93 352	97.51 259	89.54 310	98.77 374	87.52 398	97.71 368	98.31 317

UnsupCasMVSNet_eth		95.91 233	95.73 248	96.44 232	98.48 209	91.52 252	95.31 280	98.45 230	95.76 182	97.48 215	97.54 256	89.53 312	98.69 384	94.43 249	94.61 437	99.13 190

GBi-Net		96.99 164	96.80 182	97.56 134	97.96 270	93.67 183	98.23 49	98.66 207	95.59 191	97.99 177	99.19 42	89.51 313	99.73 99	94.60 244	99.44 186	99.30 149

test1		96.99 164	96.80 182	97.56 134	97.96 270	93.67 183	98.23 49	98.66 207	95.59 191	97.99 177	99.19 42	89.51 313	99.73 99	94.60 244	99.44 186	99.30 149

FMVSNet2		96.72 190	96.67 190	96.87 201	97.96 270	91.88 244	97.15 128	98.06 286	95.59 191	98.50 111	98.62 113	89.51 313	99.65 163	94.99 228	99.60 125	99.07 207

AstraMVS		96.41 210	96.48 208	96.20 253	98.91 136	89.69 292	96.28 189	93.29 404	96.11 154	98.70 94	98.36 147	89.41 316	99.66 160	97.60 79	99.63 109	99.26 161

pmmvs4		94.82 289	94.19 313	96.70 213	97.42 345	92.75 216	92.09 405	96.76 344	86.80 403	95.73 329	97.22 283	89.28 317	98.89 362	93.28 291	99.14 256	98.46 302

cascas		91.89 371	91.35 369	93.51 374	94.27 439	85.60 380	88.86 448	98.61 214	79.32 447	92.16 419	91.44 437	89.22 318	98.12 425	90.80 338	97.47 383	96.82 410

DSMNet-mixed		92.19 363	91.83 361	93.25 380	96.18 390	83.68 410	96.27 190	93.68 398	76.97 455	92.54 416	99.18 46	89.20 319	98.55 399	83.88 426	98.60 324	97.51 385

c3_l		95.20 272	95.32 256	94.83 327	96.19 389	86.43 368	91.83 409	98.35 248	93.47 284	97.36 222	97.26 281	88.69 320	99.28 304	95.41 193	99.36 214	98.78 259

test_fmvs2		96.38 211	96.45 209	96.16 258	97.85 277	91.30 257	96.81 151	99.45 30	89.24 371	98.49 112	99.38 23	88.68 321	97.62 434	98.83 30	99.32 229	99.57 56

CANet_DTU		94.65 300	94.21 312	95.96 267	95.90 401	89.68 293	93.92 349	97.83 299	93.19 296	90.12 437	95.64 372	88.52 322	99.57 201	93.27 292	99.47 178	98.62 284

EPP-MVSNet		96.84 177	96.58 195	97.65 129	99.18 86	93.78 180	98.68 17	96.34 351	97.91 64	97.30 223	98.06 203	88.46 323	99.85 31	93.85 275	99.40 204	99.32 144

SixPastTwentyTwo		97.49 127	97.57 125	97.26 167	99.56 22	92.33 224	98.28 45	96.97 337	98.30 50	99.45 25	99.35 28	88.43 324	99.89 21	98.01 58	99.76 69	99.54 70

miper_ehance_all_eth		94.69 296	94.70 287	94.64 335	95.77 411	86.22 371	91.32 422	98.24 258	91.67 332	97.05 246	96.65 328	88.39 325	99.22 318	94.88 230	98.34 339	98.49 299

MVS_0304		95.71 243	95.18 261	97.33 160	94.85 430	92.82 210	95.36 272	90.89 432	95.51 196	95.61 332	97.82 231	88.39 325	99.78 59	98.23 49	99.91 19	99.40 125

IS-MVSNet		96.93 169	96.68 189	97.70 123	99.25 67	94.00 171	98.57 23	96.74 346	98.36 46	98.14 161	97.98 212	88.23 327	99.71 121	93.10 296	99.72 85	99.38 132

jason		94.39 311	94.04 318	95.41 300	98.29 227	87.85 342	92.74 385	96.75 345	85.38 418	95.29 341	96.15 353	88.21 328	99.65 163	94.24 258	99.34 222	98.74 269
jason: jason.
IterMVS-SCA-FT		95.86 236	96.19 223	94.85 325	97.68 315	85.53 381	92.42 396	97.63 314	96.99 106	98.36 130	98.54 125	87.94 329	99.75 84	97.07 104	99.08 266	99.27 160

SCA		93.38 343	93.52 329	92.96 392	96.24 385	81.40 426	93.24 373	94.00 394	91.58 337	94.57 357	96.97 305	87.94 329	99.42 247	89.47 369	97.66 374	98.06 344

sss		94.22 314	93.72 325	95.74 279	97.71 313	89.95 286	93.84 351	96.98 336	88.38 385	93.75 381	95.74 368	87.94 329	98.89 362	91.02 330	98.10 349	98.37 308

IterMVS		95.42 261	95.83 244	94.20 360	97.52 334	83.78 409	92.41 397	97.47 319	95.49 198	98.06 171	98.49 129	87.94 329	99.58 195	96.02 146	99.02 273	99.23 169
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 320	93.41 332	96.18 256	99.16 88	90.04 284	92.15 402	98.68 201	79.90 445	96.22 305	97.83 228	87.92 333	99.42 247	89.18 373	99.65 105	99.08 205

VDDNet		96.98 167	96.84 178	97.41 155	99.40 48	93.26 202	97.94 71	95.31 377	99.26 12	98.39 126	99.18 46	87.85 334	99.62 179	95.13 213	99.09 265	99.35 142

LuminaMVS		96.76 186	96.58 195	97.30 162	98.94 127	92.96 208	96.17 203	96.15 353	95.54 195	98.96 67	98.18 183	87.73 335	99.80 51	97.98 59	99.61 118	99.15 183

pmmvs5		94.63 301	94.34 308	95.50 294	97.63 326	88.34 326	94.02 342	97.13 329	87.15 397	95.22 343	97.15 287	87.50 336	99.27 307	93.99 269	99.26 241	98.88 247

D2MVS		95.18 273	95.17 262	95.21 304	97.76 305	87.76 345	94.15 336	97.94 289	89.77 366	96.99 250	97.68 247	87.45 337	99.14 328	95.03 221	99.81 57	98.74 269

test_vis1_n_1920		95.77 240	96.41 211	93.85 365	98.55 194	84.86 395	95.91 229	99.71 7	92.72 315	97.67 202	98.90 83	87.44 338	98.73 378	97.96 60	98.85 292	97.96 354

guyue		96.21 218	96.29 218	95.98 266	98.80 150	89.14 308	96.40 177	94.34 392	95.99 167	98.58 104	98.13 187	87.42 339	99.64 169	97.39 88	99.55 145	99.16 182

PVSNet	86.72 19	91.10 382	90.97 378	91.49 417	97.56 332	78.04 442	87.17 450	94.60 388	84.65 426	92.34 417	92.20 429	87.37 340	98.47 406	85.17 419	97.69 370	97.96 354

Anonymous202405211		96.34 213	95.98 234	97.43 152	98.25 234	93.85 176	96.74 159	94.41 390	97.72 72	98.37 127	98.03 206	87.15 341	99.53 213	94.06 265	99.07 268	98.92 238

VortexMVS		96.04 226	96.56 198	94.49 348	97.60 329	84.36 402	96.05 211	98.67 204	94.74 230	98.95 68	98.78 92	87.13 342	99.50 221	97.37 90	99.76 69	99.60 44

MVSFormer		96.14 222	96.36 215	95.49 295	97.68 315	87.81 343	98.67 18	99.02 103	96.50 134	94.48 361	96.15 353	86.90 343	99.92 6	98.73 35	99.13 258	98.74 269

lupinMVS		93.77 329	93.28 333	95.24 303	97.68 315	87.81 343	92.12 403	96.05 355	84.52 427	94.48 361	95.06 384	86.90 343	99.63 174	93.62 283	99.13 258	98.27 323

eth_miper_zixun_eth		94.89 286	94.93 272	94.75 332	95.99 398	86.12 372	91.35 419	98.49 227	93.40 285	97.12 237	97.25 282	86.87 345	99.35 279	95.08 216	98.82 296	98.78 259

test_vis1_n		95.67 247	95.89 240	95.03 314	98.18 244	89.89 287	96.94 141	99.28 42	88.25 387	98.20 152	98.92 79	86.69 346	97.19 437	97.70 76	98.82 296	98.00 352

RRT-MVS		95.78 239	96.25 220	94.35 354	96.68 374	84.47 400	97.72 90	99.11 70	97.23 101	97.27 225	98.72 99	86.39 347	99.79 54	95.49 179	97.67 372	98.80 256

WTY-MVS		93.55 338	93.00 339	95.19 305	97.81 291	87.86 340	93.89 350	96.00 357	89.02 374	94.07 371	95.44 379	86.27 348	99.33 284	87.69 392	96.82 399	98.39 306

CDS-MVSNet		94.88 287	94.12 316	97.14 175	97.64 325	93.57 188	93.96 348	97.06 333	90.05 362	96.30 300	96.55 332	86.10 349	99.47 232	90.10 359	99.31 232	98.40 304
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 319	93.42 331	96.23 250	98.59 187	90.85 269	94.24 330	98.85 153	85.49 414	92.97 404	94.94 386	86.01 350	99.64 169	91.78 317	97.92 356	98.20 330

dmvs_testset		87.30 421	86.99 418	88.24 437	96.71 373	77.48 446	94.68 316	86.81 454	92.64 316	89.61 442	87.01 457	85.91 351	93.12 458	61.04 461	88.49 454	94.13 445

miper_enhance_ethall		93.14 349	92.78 346	94.20 360	93.65 448	85.29 386	89.97 439	97.85 295	85.05 420	96.15 311	94.56 393	85.74 352	99.14 328	93.74 278	98.34 339	98.17 334

ttmdpeth		94.05 323	94.15 315	93.75 368	95.81 408	85.32 384	96.00 217	94.93 384	92.07 324	94.19 366	99.09 58	85.73 353	96.41 449	90.98 331	98.52 327	99.53 75

new_pmnet		92.34 360	91.69 365	94.32 356	96.23 387	89.16 306	92.27 400	92.88 408	84.39 430	95.29 341	96.35 346	85.66 354	96.74 447	84.53 423	97.56 377	97.05 398

Syy-MVS		92.09 366	91.80 363	92.93 394	95.19 425	82.65 415	92.46 393	91.35 426	90.67 353	91.76 423	87.61 455	85.64 355	98.50 403	94.73 240	96.84 397	97.65 377

alignmvs		96.01 229	95.52 255	97.50 143	97.77 304	94.71 139	96.07 209	96.84 340	97.48 85	96.78 268	94.28 400	85.50 356	99.40 258	96.22 137	98.73 310	98.40 304

NormalMVS		96.87 175	96.39 212	98.30 74	99.48 36	95.57 100	96.87 146	98.90 133	96.94 111	96.85 261	97.88 221	85.36 357	99.76 76	95.63 171	99.59 128	99.57 56

SymmetryMVS		96.43 208	95.85 242	98.17 86	98.58 189	95.57 100	96.87 146	95.29 378	96.94 111	96.85 261	97.88 221	85.36 357	99.76 76	95.63 171	99.27 238	99.19 175

lessismore_v0				97.05 184	99.36 53	92.12 235		84.07 457		98.77 87	98.98 70	85.36 357	99.74 93	97.34 91	99.37 210	99.30 149

HY-MVS	91.43 15	92.58 356	91.81 362	94.90 322	96.49 379	88.87 315	97.31 119	94.62 387	85.92 410	90.50 431	96.84 314	85.05 360	99.40 258	83.77 428	95.78 425	96.43 422

EPNet		93.72 332	92.62 351	97.03 188	87.61 466	92.25 228	96.27 190	91.28 428	96.74 120	87.65 451	97.39 270	85.00 361	99.64 169	92.14 308	99.48 176	99.20 174
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 290	94.80 284	94.85 325	96.16 391	86.45 367	91.14 426	98.20 263	93.49 283	97.03 247	97.37 274	84.97 362	99.26 308	95.28 196	99.56 139	98.83 252

Test_1112_low_res		93.53 339	92.86 341	95.54 293	98.60 185	88.86 316	92.75 383	98.69 199	82.66 434	92.65 412	96.92 310	84.75 363	99.56 203	90.94 333	97.76 364	98.19 331

MVS-HIRNet		88.40 410	90.20 391	82.99 442	97.01 365	60.04 467	93.11 377	85.61 456	84.45 429	88.72 447	99.09 58	84.72 364	98.23 421	82.52 432	96.59 408	90.69 457

K. test v3		96.44 206	96.28 219	96.95 192	99.41 45	91.53 251	97.65 95	90.31 440	98.89 27	98.93 69	99.36 26	84.57 365	99.92 6	97.81 67	99.56 139	99.39 130

test_cas_vis1_n_1920		95.34 265	95.67 249	94.35 354	98.21 238	86.83 363	95.61 255	99.26 44	90.45 356	98.17 157	98.96 73	84.43 366	98.31 417	96.74 114	99.17 253	97.90 358

h-mvs33		96.29 214	95.63 252	98.26 77	98.50 206	96.11 79	96.90 144	97.09 331	96.58 129	97.21 230	98.19 180	84.14 367	99.78 59	95.89 156	96.17 419	98.89 243

hse-mvs2		95.77 240	95.09 265	97.79 115	97.84 283	95.51 105	95.66 247	95.43 374	96.58 129	97.21 230	96.16 352	84.14 367	99.54 210	95.89 156	96.92 393	98.32 315

MonoMVSNet		93.30 345	93.96 322	91.33 420	94.14 443	81.33 427	97.68 93	96.69 348	95.38 205	96.32 296	98.42 139	84.12 369	96.76 446	90.78 339	92.12 447	95.89 428

DIV-MVS_self_test		94.73 291	94.64 290	95.01 315	95.86 404	87.00 359	91.33 420	98.08 281	93.34 288	97.10 239	97.34 276	84.02 370	99.31 293	95.15 210	99.55 145	98.72 272

cl____		94.73 291	94.64 290	95.01 315	95.85 405	87.00 359	91.33 420	98.08 281	93.34 288	97.10 239	97.33 277	84.01 371	99.30 297	95.14 211	99.56 139	98.71 276

Vis-MVSNet (Re-imp)		95.11 276	94.85 279	95.87 274	99.12 99	89.17 305	97.54 108	94.92 385	96.50 134	96.58 282	97.27 280	83.64 372	99.48 230	88.42 384	99.67 101	98.97 225

FA-MVS(test-final)		94.91 284	94.89 275	94.99 317	97.51 335	88.11 336	98.27 47	95.20 380	92.40 322	96.68 272	98.60 117	83.44 373	99.28 304	93.34 288	98.53 326	97.59 382

dmvs_re		92.08 367	91.27 372	94.51 346	97.16 360	92.79 215	95.65 249	92.64 413	94.11 263	92.74 409	90.98 442	83.41 374	94.44 457	80.72 439	94.07 440	96.29 424

PVSNet_0	81.89 21	84.49 425	83.21 428	88.34 436	95.76 412	74.97 457	83.49 456	92.70 412	78.47 450	87.94 450	86.90 458	83.38 375	96.63 448	73.44 455	66.86 462	93.40 449

mvsmamba		94.91 284	94.41 306	96.40 241	97.65 322	91.30 257	97.92 73	95.32 376	91.50 338	95.54 335	98.38 145	83.06 376	99.68 143	92.46 305	97.84 360	98.23 326

test_fmvs1_n		95.21 271	95.28 257	94.99 317	98.15 251	89.13 309	96.81 151	99.43 32	86.97 401	97.21 230	98.92 79	83.00 377	97.13 438	98.09 53	98.94 280	98.72 272

CMPMVS	73.10 23	92.74 354	91.39 368	96.77 209	93.57 450	94.67 142	94.21 333	97.67 306	80.36 444	93.61 387	96.60 330	82.85 378	97.35 436	84.86 421	98.78 299	98.29 322
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs1		94.51 307	94.60 294	94.26 359	95.91 400	87.92 338	95.35 275	99.02 103	86.56 405	96.79 264	98.52 126	82.64 379	97.00 441	97.87 64	98.71 311	97.88 360

EU-MVSNet		94.25 313	94.47 302	93.60 372	98.14 253	82.60 417	97.24 124	92.72 411	85.08 419	98.48 114	98.94 76	82.59 380	98.76 376	97.47 85	99.53 155	99.44 119

baseline1		93.14 349	92.64 350	94.62 338	97.34 351	87.20 356	96.67 168	93.02 406	94.71 234	96.51 288	95.83 367	81.64 381	98.60 395	90.00 361	88.06 455	98.07 340

test1111		94.53 306	94.81 283	93.72 369	99.06 108	81.94 422	98.31 42	83.87 458	96.37 140	98.49 112	99.17 49	81.49 382	99.73 99	96.64 115	99.86 35	99.49 93

CVMVSNet		92.33 361	92.79 344	90.95 422	97.26 356	75.84 453	95.29 282	92.33 417	81.86 435	96.27 301	98.19 180	81.44 383	98.46 407	94.23 259	98.29 342	98.55 291

EPNet_dtu		91.39 379	90.75 382	93.31 378	90.48 462	82.61 416	94.80 310	92.88 408	93.39 286	81.74 460	94.90 389	81.36 384	99.11 335	88.28 386	98.87 289	98.21 329
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 312	94.48 301	94.05 364	98.95 124	83.10 412	98.31 42	82.48 460	96.20 149	98.23 150	99.16 50	81.18 385	99.66 160	95.95 151	99.83 52	99.38 132

test_yl		94.40 309	94.00 319	95.59 286	96.95 367	89.52 297	94.75 314	95.55 371	96.18 152	96.79 264	96.14 355	81.09 386	99.18 321	90.75 341	97.77 362	98.07 340

DCV-MVSNet		94.40 309	94.00 319	95.59 286	96.95 367	89.52 297	94.75 314	95.55 371	96.18 152	96.79 264	96.14 355	81.09 386	99.18 321	90.75 341	97.77 362	98.07 340

MIMVSNet		93.42 341	92.86 341	95.10 311	98.17 247	88.19 330	98.13 58	93.69 396	92.07 324	95.04 349	98.21 179	80.95 388	99.03 349	81.42 436	98.06 351	98.07 340

PAPM		87.64 417	85.84 424	93.04 387	96.54 377	84.99 392	88.42 449	95.57 370	79.52 446	83.82 457	93.05 415	80.57 389	98.41 409	62.29 460	92.79 444	95.71 432

HyFIR lowres test		93.72 332	92.65 349	96.91 197	98.93 131	91.81 247	91.23 424	98.52 224	82.69 433	96.46 290	96.52 336	80.38 390	99.90 18	90.36 356	98.79 298	99.03 212

FMVSNet3		95.26 270	94.94 270	96.22 252	96.53 378	90.06 283	95.99 220	97.66 308	94.11 263	97.99 177	97.91 220	80.22 391	99.63 174	94.60 244	99.44 186	98.96 226

RPMNet		94.68 298	94.60 294	94.90 322	95.44 419	88.15 332	96.18 199	98.86 149	97.43 87	94.10 369	98.49 129	79.40 392	99.76 76	95.69 165	95.81 422	96.81 411

LFMVS		95.32 267	94.88 277	96.62 217	98.03 260	91.47 253	97.65 95	90.72 435	99.11 15	97.89 190	98.31 157	79.20 393	99.48 230	93.91 274	99.12 261	98.93 235

ADS-MVSNet2		91.47 378	90.51 387	94.36 352	95.51 417	85.63 379	95.05 299	95.70 364	83.46 431	92.69 410	96.84 314	79.15 394	99.41 256	85.66 412	90.52 449	98.04 348

ADS-MVSNet		90.95 385	90.26 390	93.04 387	95.51 417	82.37 418	95.05 299	93.41 402	83.46 431	92.69 410	96.84 314	79.15 394	98.70 382	85.66 412	90.52 449	98.04 348

MDTV_nov1_ep13_2view						57.28 468	94.89 306		80.59 442	94.02 374		78.66 396		85.50 414		97.82 364

cl22		93.25 347	92.84 343	94.46 349	94.30 438	86.00 377	91.09 428	96.64 350	90.74 350	95.79 324	96.31 347	78.24 397	98.77 374	94.15 262	98.34 339	98.62 284

PatchmatchNet		91.98 370	91.87 360	92.30 408	94.60 435	79.71 435	95.12 290	93.59 401	89.52 368	93.61 387	97.02 301	77.94 398	99.18 321	90.84 336	94.57 439	98.01 351
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 399				98.06 344

CR-MVSNet		93.29 346	92.79 344	94.78 330	95.44 419	88.15 332	96.18 199	97.20 325	84.94 424	94.10 369	98.57 120	77.67 400	99.39 263	95.17 206	95.81 422	96.81 411

Patchmtry		95.03 281	94.59 296	96.33 244	94.83 432	90.82 270	96.38 182	97.20 325	96.59 128	97.49 212	98.57 120	77.67 400	99.38 266	92.95 299	99.62 112	98.80 256

tpmrst		90.31 388	90.61 386	89.41 431	94.06 444	72.37 462	95.06 298	93.69 396	88.01 389	92.32 418	96.86 312	77.45 402	98.82 368	91.04 329	87.01 456	97.04 399

sam_mvs												77.38 403

patchmatchnet-post											96.84 314	77.36 404	99.42 247

Patchmatch-RL test		94.66 299	94.49 300	95.19 305	98.54 196	88.91 314	92.57 389	98.74 188	91.46 340	98.32 138	97.75 240	77.31 405	98.81 370	96.06 141	99.61 118	97.85 362

tpmvs		90.79 386	90.87 379	90.57 425	92.75 456	76.30 451	95.79 237	93.64 400	91.04 348	91.91 421	96.26 348	77.19 406	98.86 366	89.38 371	89.85 452	96.56 418

test_post											10.87 466	76.83 407	99.07 342

Patchmatch-test		93.60 337	93.25 334	94.63 337	96.14 395	87.47 349	96.04 213	94.50 389	93.57 278	96.47 289	96.97 305	76.50 408	98.61 393	90.67 348	98.41 337	97.81 366

MDTV_nov1_ep13			91.28 371		94.31 437	73.51 460	94.80 310	93.16 405	86.75 404	93.45 394	97.40 266	76.37 409	98.55 399	88.85 377	96.43 410

EMVS		89.06 404	89.22 396	88.61 435	93.00 453	77.34 447	82.91 458	90.92 431	94.64 237	92.63 414	91.81 433	76.30 410	97.02 440	83.83 427	96.90 395	91.48 455

test_post1							94.98 303				10.37 467	76.21 411	99.04 346	89.47 369

GA-MVS		92.83 353	92.15 358	94.87 324	96.97 366	87.27 355	90.03 438	96.12 354	91.83 331	94.05 372	94.57 392	76.01 412	98.97 358	92.46 305	97.34 387	98.36 313

BP-MVS1		95.36 263	94.86 278	96.89 199	98.35 223	91.72 248	96.76 157	95.21 379	96.48 137	96.23 304	97.19 285	75.97 413	99.80 51	97.91 62	99.60 125	99.15 183

PatchT		93.75 330	93.57 328	94.29 358	95.05 428	87.32 354	96.05 211	92.98 407	97.54 82	94.25 364	98.72 99	75.79 414	99.24 314	95.92 154	95.81 422	96.32 423

E-PMN		89.52 401	89.78 393	88.73 434	93.14 451	77.61 445	83.26 457	92.02 419	94.82 229	93.71 382	93.11 409	75.31 415	96.81 443	85.81 409	96.81 400	91.77 454

DeepMVS_CX				77.17 443	90.94 460	85.28 387		74.08 466	52.51 462	80.87 462	88.03 454	75.25 416	70.63 464	59.23 462	84.94 458	75.62 458

GDP-MVS		95.39 262	94.89 275	96.90 198	98.26 233	91.91 243	96.48 175	99.28 42	95.06 219	96.54 287	97.12 294	74.83 417	99.82 39	97.19 97	99.27 238	98.96 226

AUN-MVS		93.95 328	92.69 348	97.74 119	97.80 295	95.38 113	95.57 258	95.46 373	91.26 344	92.64 413	96.10 358	74.67 418	99.55 207	93.72 280	96.97 392	98.30 319

CHOSEN 280x420		89.98 393	89.19 399	92.37 407	95.60 416	81.13 429	86.22 452	97.09 331	81.44 439	87.44 452	93.15 408	73.99 419	99.47 232	88.69 380	99.07 268	96.52 419

thres200		91.00 384	90.42 388	92.77 398	97.47 342	83.98 408	94.01 343	91.18 430	95.12 216	95.44 338	91.21 439	73.93 420	99.31 293	77.76 448	97.63 376	95.01 440

test-LLR		89.97 394	89.90 392	90.16 426	94.24 440	74.98 455	89.89 440	89.06 445	92.02 326	89.97 438	90.77 443	73.92 421	98.57 396	91.88 313	97.36 385	96.92 402

test0.0.03 1		90.11 389	89.21 397	92.83 396	93.89 446	86.87 362	91.74 411	88.74 448	92.02 326	94.71 355	91.14 440	73.92 421	94.48 456	83.75 429	92.94 443	97.16 396

tpm cat1		88.01 415	87.33 415	90.05 430	94.48 436	76.28 452	94.47 322	94.35 391	73.84 459	89.26 444	95.61 374	73.64 423	98.30 418	84.13 424	86.20 457	95.57 436

tfpn200view9		91.55 376	91.00 376	93.21 383	98.02 262	84.35 403	95.70 242	90.79 433	96.26 145	95.90 321	92.13 430	73.62 424	99.42 247	78.85 445	97.74 365	95.85 429

thres400		91.68 375	91.00 376	93.71 370	98.02 262	84.35 403	95.70 242	90.79 433	96.26 145	95.90 321	92.13 430	73.62 424	99.42 247	78.85 445	97.74 365	97.36 390

test_method		66.88 428	66.13 431	69.11 444	62.68 469	25.73 472	49.76 460	96.04 356	14.32 464	64.27 464	91.69 435	73.45 426	88.05 461	76.06 450	66.94 461	93.54 447

thres100view900		91.76 374	91.26 374	93.26 379	98.21 238	84.50 399	96.39 179	90.39 437	96.87 114	96.33 295	93.08 413	73.44 427	99.42 247	78.85 445	97.74 365	95.85 429

thres600view7		92.03 369	91.43 367	93.82 366	98.19 241	84.61 398	96.27 190	90.39 437	96.81 117	96.37 294	93.11 409	73.44 427	99.49 227	80.32 440	97.95 355	97.36 390

MVSTER		94.21 316	93.93 323	95.05 313	95.83 406	86.46 366	95.18 289	97.65 310	92.41 321	97.94 186	98.00 211	72.39 429	99.58 195	96.36 129	99.56 139	99.12 196

JIA-IIPM		91.79 373	90.69 384	95.11 309	93.80 447	90.98 264	94.16 335	91.78 422	96.38 139	90.30 434	99.30 32	72.02 430	98.90 361	88.28 386	90.17 451	95.45 437

tpm		91.08 383	90.85 380	91.75 415	95.33 423	78.09 441	95.03 301	91.27 429	88.75 378	93.53 391	97.40 266	71.24 431	99.30 297	91.25 326	93.87 441	97.87 361

baseline2		89.65 400	88.44 406	93.25 380	95.62 415	82.71 414	93.82 352	85.94 455	88.89 377	87.35 453	92.54 424	71.23 432	99.33 284	86.01 407	94.60 438	97.72 374

CostFormer		89.75 397	89.25 395	91.26 421	94.69 434	78.00 443	95.32 279	91.98 420	81.50 438	90.55 430	96.96 307	71.06 433	98.89 362	88.59 382	92.63 445	96.87 405

FPMVS		89.92 395	88.63 403	93.82 366	98.37 221	96.94 49	91.58 414	93.34 403	88.00 390	90.32 433	97.10 296	70.87 434	91.13 460	71.91 457	96.16 420	93.39 450

EPMVS		89.26 402	88.55 404	91.39 419	92.36 457	79.11 438	95.65 249	79.86 461	88.60 381	93.12 401	96.53 334	70.73 435	98.10 426	90.75 341	89.32 453	96.98 400

FE-MVS		92.95 351	92.22 356	95.11 309	97.21 358	88.33 327	98.54 26	93.66 399	89.91 364	96.21 306	98.14 185	70.33 436	99.50 221	87.79 390	98.24 344	97.51 385

tmp_tt		57.23 430	62.50 433	41.44 447	34.77 470	49.21 471	83.93 455	60.22 469	15.31 463	71.11 463	79.37 460	70.09 437	44.86 466	64.76 459	82.93 460	30.25 462

ET-MVSNet_ETH3D		91.12 380	89.67 394	95.47 296	96.41 382	89.15 307	91.54 415	90.23 441	89.07 373	86.78 455	92.84 419	69.39 438	99.44 243	94.16 261	96.61 407	97.82 364

dp		88.08 414	88.05 408	88.16 439	92.85 454	68.81 466	94.17 334	92.88 408	85.47 415	91.38 426	96.14 355	68.87 439	98.81 370	86.88 404	83.80 459	96.87 405

tpm2		88.47 409	87.69 413	90.79 423	94.98 429	77.34 447	95.09 294	91.83 421	77.51 454	89.40 443	96.41 341	67.83 440	98.73 378	83.58 430	92.60 446	96.29 424

pmmvs3		90.00 392	88.90 402	93.32 377	94.20 442	85.34 383	91.25 423	92.56 415	78.59 449	93.82 377	95.17 381	67.36 441	98.69 384	89.08 375	98.03 352	95.92 427

thisisatest0515		90.43 387	89.18 400	94.17 362	97.07 364	85.44 382	89.75 444	87.58 450	88.28 386	93.69 385	91.72 434	65.27 442	99.58 195	90.59 349	98.67 315	97.50 387

tttt0517		93.31 344	92.56 352	95.57 288	98.71 168	87.86 340	97.44 112	87.17 452	95.79 181	97.47 217	96.84 314	64.12 443	99.81 44	96.20 138	99.32 229	99.02 215

thisisatest0530		92.71 355	91.76 364	95.56 291	98.42 217	88.23 329	96.03 214	87.35 451	94.04 266	96.56 284	95.47 377	64.03 444	99.77 70	94.78 237	99.11 262	98.68 280

FMVSNet5		93.39 342	92.35 353	96.50 229	95.83 406	90.81 272	97.31 119	98.27 254	92.74 314	96.27 301	98.28 166	62.23 445	99.67 152	90.86 335	99.36 214	99.03 212

UWE-MVS-28		83.78 426	82.36 429	88.03 440	90.72 461	71.58 463	93.64 359	77.87 462	87.62 393	85.91 456	92.89 417	59.94 446	95.99 451	56.06 463	96.56 409	96.52 419

WBMVS		91.11 381	90.72 383	92.26 409	95.99 398	77.98 444	91.47 416	95.90 361	91.63 333	95.90 321	96.45 339	59.60 447	99.46 235	89.97 362	99.59 128	99.33 143

UBG		88.29 412	87.17 416	91.63 416	96.08 396	78.21 440	91.61 412	91.50 425	89.67 367	89.71 441	88.97 452	59.01 448	98.91 360	81.28 437	96.72 404	97.77 369

IB-MVS	85.98 20	88.63 408	86.95 420	93.68 371	95.12 427	84.82 397	90.85 430	90.17 442	87.55 394	88.48 448	91.34 438	58.01 449	99.59 192	87.24 402	93.80 442	96.63 417
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
MVStest1		91.89 371	91.45 366	93.21 383	89.01 463	84.87 394	95.82 236	95.05 382	91.50 338	98.75 89	99.19 42	57.56 450	95.11 452	97.78 70	98.37 338	99.64 42

testing91		89.67 399	88.55 404	93.04 387	95.90 401	81.80 423	92.71 387	93.71 395	93.71 273	90.18 435	90.15 447	57.11 451	99.22 318	87.17 403	96.32 415	98.12 336

gg-mvs-nofinetune		88.28 413	86.96 419	92.23 410	92.84 455	84.44 401	98.19 55	74.60 464	99.08 17	87.01 454	99.47 16	56.93 452	98.23 421	78.91 444	95.61 428	94.01 446

KD-MVS_2432*1600		88.93 405	87.74 410	92.49 403	88.04 464	81.99 420	89.63 445	95.62 367	91.35 342	95.06 346	93.11 409	56.58 453	98.63 391	85.19 417	95.07 431	96.85 407

miper_refine_blended		88.93 405	87.74 410	92.49 403	88.04 464	81.99 420	89.63 445	95.62 367	91.35 342	95.06 346	93.11 409	56.58 453	98.63 391	85.19 417	95.07 431	96.85 407

GG-mvs-BLEND				90.60 424	91.00 459	84.21 406	98.23 49	72.63 467		82.76 458	84.11 459	56.14 455	96.79 444	72.20 456	92.09 448	90.78 456

myMVS_eth3d28		88.32 411	87.73 412	90.11 429	96.42 381	74.96 458	92.21 401	92.37 416	93.56 279	90.14 436	89.61 450	56.13 456	98.05 428	81.84 433	97.26 390	97.33 393

TESTMET0.1,1		87.20 422	86.57 422	89.07 433	93.62 449	72.84 461	89.89 440	87.01 453	85.46 416	89.12 445	90.20 446	56.00 457	97.72 433	90.91 334	96.92 393	96.64 415

testing3-2		90.09 390	90.38 389	89.24 432	98.07 258	69.88 465	95.12 290	90.71 436	96.65 122	93.60 389	94.03 402	55.81 458	99.33 284	90.69 347	98.71 311	98.51 295

reproduce_monomvs		92.05 368	92.26 355	91.43 418	95.42 421	75.72 454	95.68 245	97.05 334	94.47 249	97.95 185	98.35 149	55.58 459	99.05 344	96.36 129	99.44 186	99.51 82

testing99		89.21 403	88.04 409	92.70 400	95.78 410	81.00 430	92.65 388	92.03 418	93.20 295	89.90 440	90.08 449	55.25 460	99.14 328	87.54 396	95.95 421	97.97 353

UWE-MVS		87.57 419	86.72 421	90.13 428	95.21 424	73.56 459	91.94 407	83.78 459	88.73 380	93.00 403	92.87 418	55.22 461	99.25 310	81.74 434	97.96 354	97.59 382

test2506		89.86 396	89.16 401	91.97 413	98.95 124	76.83 450	98.54 26	61.07 468	96.20 149	97.07 245	99.16 50	55.19 462	99.69 137	96.43 126	99.83 52	99.38 132

testing11		88.93 405	87.63 414	92.80 397	95.87 403	81.49 425	92.48 392	91.54 424	91.62 334	88.27 449	90.24 445	55.12 463	99.11 335	87.30 401	96.28 417	97.81 366

test-mter		87.92 416	87.17 416	90.16 426	94.24 440	74.98 455	89.89 440	89.06 445	86.44 406	89.97 438	90.77 443	54.96 464	98.57 396	91.88 313	97.36 385	96.92 402

ETVMVS		87.62 418	85.75 425	93.22 382	96.15 394	83.26 411	92.94 379	90.37 439	91.39 341	90.37 432	88.45 453	51.93 465	98.64 390	73.76 452	96.38 413	97.75 370

testing222		87.35 420	85.50 427	92.93 394	95.79 409	82.83 413	92.40 398	90.10 443	92.80 313	88.87 446	89.02 451	48.34 466	98.70 382	75.40 451	96.74 402	97.27 395

myMVS_eth3d		87.16 423	85.61 426	91.82 414	95.19 425	79.32 436	92.46 393	91.35 426	90.67 353	91.76 423	87.61 455	41.96 467	98.50 403	82.66 431	96.84 397	97.65 377

testing3		89.72 398	88.26 407	94.10 363	97.66 320	84.30 405	94.80 310	88.25 449	94.66 235	95.07 345	92.51 425	41.15 468	99.43 245	91.81 316	98.44 335	98.55 291

dongtai		63.43 429	63.37 432	63.60 445	83.91 467	53.17 469	85.14 453	43.40 471	77.91 453	80.96 461	79.17 461	36.36 469	77.10 463	37.88 464	45.63 463	60.54 460

kuosan		54.81 431	54.94 434	54.42 446	74.43 468	50.03 470	84.98 454	44.27 470	61.80 461	62.49 465	70.43 462	35.16 470	58.04 465	19.30 465	41.61 464	55.19 461

test123		12.59 433	15.49 436	3.87 448	6.07 471	2.55 473	90.75 432	2.59 473	2.52 466	5.20 468	13.02 465	4.96 471	1.85 468	5.20 466	9.09 465	7.23 463

testmvs		12.33 434	15.23 437	3.64 449	5.77 472	2.23 474	88.99 447	3.62 472	2.30 467	5.29 467	13.09 464	4.52 472	1.95 467	5.16 467	8.32 466	6.75 464

mmdepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

monomultidepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

test_blank		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet_test		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

DCPMVS		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet-low-res		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uncertanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

Regformer		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

ab-mvs-re		7.91 436	10.55 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	94.94 386	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

WAC-MVS						79.32 436								85.41 415

FOURS1					99.59 18	98.20 8	99.03 8	99.25 46	98.96 25	98.87 75

MSC_two_6792asdad				98.22 82	97.75 307	95.34 118		98.16 273					99.75 84	95.87 158	99.51 165	99.57 56

No_MVS				98.22 82	97.75 307	95.34 118		98.16 273					99.75 84	95.87 158	99.51 165	99.57 56

eth-test2					0.00 473

eth-test					0.00 473

IU-MVS					99.22 74	95.40 111		98.14 276	85.77 413	98.36 130				95.23 200	99.51 165	99.49 93

save fliter					98.48 209	94.71 139	94.53 321	98.41 237	95.02 222

test_0728_SECOND				98.25 80	99.23 71	95.49 109	96.74 159	98.89 137					99.75 84	95.48 183	99.52 160	99.53 75

GSMVS																98.06 344

test_part2					99.03 116	96.07 81				98.08 168

MTGPA								98.73 189

MTMP							96.55 171	74.60 464

gm-plane-assit					91.79 458	71.40 464			81.67 436		90.11 448		98.99 352	84.86 421

test9_res														91.29 323	98.89 288	99.00 216

agg_prior2														90.34 357	98.90 285	99.10 204

agg_prior					97.80 295	94.96 134		98.36 245		93.49 392			99.53 213

test_prior4						95.38 113	93.61 362

test_prior				97.46 149	97.79 300	94.26 163		98.42 236					99.34 282			98.79 258

旧先验2							93.35 370		77.95 452	95.77 328			98.67 388	90.74 344

新几何2							93.43 366

无先验							93.20 375	97.91 291	80.78 441				99.40 258	87.71 391		97.94 356

原ACMM2							92.82 381

testdata2													99.46 235	87.84 389

testdata1							92.77 382		93.78 271

plane_prior7					98.70 170	94.67 142

plane_prior5								98.75 186					99.46 235	92.59 302	99.20 247	99.28 156

plane_prior4											96.77 320

plane_prior3						94.51 149			95.29 209	96.16 309

plane_prior2							96.50 173		96.36 141

plane_prior1					98.49 207

plane_prior						94.29 159	95.42 265		94.31 255						98.93 283

n2								0.00 474

nn								0.00 474

door-mid								98.17 269

test11								98.08 281

door								97.81 300

HQP5-MVS						92.47 222

HQP-NCC					97.85 277		94.26 326		93.18 297	92.86 406

ACMP_Plane					97.85 277		94.26 326		93.18 297	92.86 406

BP-MVS														90.51 352

HQP4-MVS										92.87 405			99.23 316			99.06 209

HQP3-MVS								98.43 233							98.74 307

NP-MVS					98.14 253	93.72 181					95.08 382

ACMMP++_ref															99.52 160

ACMMP++															99.55 145

High-resolution multi-view benchmark