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 1	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 3

pmmvs6		99.07 4	99.24 4	98.56 48	99.81 2	96.38 62	98.87 9	99.30 21	99.01 16	99.63 10	99.66 3	99.27 2	99.68 120	97.75 41	99.89 25	99.62 29

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 42	99.77 5	96.34 65	99.18 5	99.20 29	99.67 2	99.73 3	99.65 5	99.15 3	99.86 24	97.22 58	99.92 14	99.77 11

XVG-OURS-SEG-HR		97.38 108	97.07 122	98.30 68	99.01 104	97.41 34	94.66 256	99.02 65	95.20 170	98.15 119	97.52 204	98.83 4	98.43 336	94.87 173	96.41 338	99.07 161

ACMH	93.61 9	98.44 24	98.76 13	97.51 124	99.43 40	93.54 176	98.23 46	99.05 56	97.40 76	99.37 20	99.08 46	98.79 5	99.47 189	97.74 42	99.71 65	99.50 53
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_tets		98.90 5	98.94 6	98.75 31	99.69 10	96.48 60	98.54 23	99.22 26	96.23 118	99.71 4	99.48 9	98.77 6	99.93 3	98.89 7	99.95 5	99.84 5

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 37	99.71 9	96.99 44	99.69 2	99.57 11	99.02 15	99.62 11	99.36 20	98.53 7	99.52 175	98.58 19	99.95 5	99.66 24
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
TransMVSNet (Re)		98.38 26	98.67 17	97.51 124	99.51 31	93.39 182	98.20 51	98.87 101	98.23 38	99.48 14	99.27 27	98.47 8	99.55 167	96.52 81	99.53 115	99.60 31

pm-mvs1		98.47 23	98.67 17	97.86 101	99.52 30	94.58 136	98.28 42	99.00 74	97.57 64	99.27 26	99.22 30	98.32 9	99.50 180	97.09 65	99.75 56	99.50 53

jajsoiax		98.77 9	98.79 12	98.74 34	99.66 13	96.48 60	98.45 31	99.12 42	95.83 144	99.67 7	99.37 18	98.25 10	99.92 5	98.77 10	99.94 8	99.82 6

sd_testset		97.97 49	98.12 38	97.51 124	99.41 43	93.44 179	97.96 63	98.25 204	98.58 26	98.78 55	99.39 15	98.21 11	99.56 163	92.65 239	99.86 29	99.52 49

ACMH+	93.58 10	98.23 33	98.31 32	97.98 94	99.39 47	95.22 118	97.55 92	99.20 29	98.21 39	99.25 28	98.51 96	98.21 11	99.40 213	94.79 177	99.72 62	99.32 104

HPM-MVS_fast		98.32 28	98.13 37	98.88 23	99.54 26	97.48 30	98.35 35	99.03 63	95.88 140	97.88 148	98.22 134	98.15 13	99.74 76	96.50 82	99.62 83	99.42 87

wuyk23d		93.25 285	95.20 202	87.40 362	96.07 333	95.38 105	97.04 122	94.97 322	95.33 165	99.70 6	98.11 146	98.14 14	91.94 380	77.76 372	99.68 73	74.89 380

ACMM	93.33 11	98.05 45	97.79 65	98.85 24	99.15 81	97.55 26	96.68 145	98.83 117	95.21 169	98.36 93	98.13 142	98.13 15	99.62 144	96.04 100	99.54 111	99.39 93
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 40	97.83 63	98.92 21	99.42 42	97.46 31	98.57 20	99.05 56	95.43 163	97.41 173	97.50 206	97.98 16	99.79 44	95.58 130	99.57 99	99.50 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 175	96.50 157	94.80 278	99.26 58	87.69 296	95.96 184	98.58 169	95.08 176	98.02 135	96.25 286	97.92 17	97.60 360	88.68 314	98.74 251	99.11 154

LPG-MVS_test		97.94 59	97.67 77	98.74 34	99.15 81	97.02 42	97.09 119	99.02 65	95.15 173	98.34 96	98.23 131	97.91 18	99.70 108	94.41 191	99.73 58	99.50 53

LGP-MVS_train				98.74 34	99.15 81	97.02 42		99.02 65	95.15 173	98.34 96	98.23 131	97.91 18	99.70 108	94.41 191	99.73 58	99.50 53

SED-MVS		97.94 59	97.90 54	98.07 86	99.22 67	95.35 108	96.79 136	98.83 117	96.11 124	99.08 36	98.24 129	97.87 20	99.72 86	95.44 139	99.51 125	99.14 144

test_241102_ONE					99.22 67	95.35 108		98.83 117	96.04 129	99.08 36	98.13 142	97.87 20	99.33 232

SDMVSNet		97.97 49	98.26 36	97.11 156	99.41 43	92.21 206	96.92 127	98.60 164	98.58 26	98.78 55	99.39 15	97.80 22	99.62 144	94.98 171	99.86 29	99.52 49

testf1		98.57 17	98.45 27	98.93 18	99.79 3	98.78 2	97.69 81	99.42 18	97.69 60	98.92 45	98.77 72	97.80 22	99.25 251	96.27 90	99.69 69	98.76 209

APD_test2		98.57 17	98.45 27	98.93 18	99.79 3	98.78 2	97.69 81	99.42 18	97.69 60	98.92 45	98.77 72	97.80 22	99.25 251	96.27 90	99.69 69	98.76 209

SD-MVS		97.37 110	97.70 72	96.35 204	98.14 205	95.13 122	96.54 148	98.92 90	95.94 136	99.19 31	98.08 148	97.74 25	95.06 374	95.24 151	99.54 111	98.87 197
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 78	97.70 72	98.16 79	98.78 124	95.72 86	96.23 166	99.02 65	93.92 211	98.62 65	98.99 51	97.69 26	99.62 144	96.18 95	99.87 27	99.15 141
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 20	98.62 21	98.32 65	99.22 67	95.66 91	97.90 68	99.08 50	98.31 34	99.02 39	98.74 75	97.68 27	99.61 151	97.77 40	99.85 34	99.70 22

ANet_high		98.31 29	98.94 6	96.41 203	99.33 53	89.64 253	97.92 67	99.56 13	99.27 6	99.66 9	99.50 8	97.67 28	99.83 33	97.55 49	99.98 2	99.77 11

test_fmvsmvis_n_1920		98.08 42	98.47 24	96.93 169	99.03 102	93.29 183	96.32 159	99.65 7	95.59 155	99.71 4	99.01 49	97.66 29	99.60 153	99.44 2	99.83 37	97.90 292

casdiffmvs_mvg		97.83 75	98.11 39	97.00 166	98.57 151	92.10 214	95.97 182	99.18 32	97.67 63	99.00 41	98.48 100	97.64 30	99.50 180	96.96 70	99.54 111	99.40 90
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
canonicalmvs		97.23 117	97.21 115	97.30 146	97.65 264	94.39 142	97.84 71	99.05 56	97.42 72	96.68 219	93.85 340	97.63 31	99.33 232	96.29 89	98.47 272	98.18 270

GeoE		97.75 83	97.70 72	97.89 99	98.88 114	94.53 137	97.10 118	98.98 80	95.75 148	97.62 159	97.59 199	97.61 32	99.77 56	96.34 88	99.44 145	99.36 101

TranMVSNet+NR-MVSNet		98.33 27	98.30 34	98.43 57	99.07 95	95.87 81	96.73 143	99.05 56	98.67 23	98.84 51	98.45 101	97.58 33	99.88 20	96.45 84	99.86 29	99.54 45

cdsmvs_eth3d_5k		24.22 351	32.30 354	0.00 369	0.00 392	0.00 393	0.00 380	98.10 228	0.00 387	0.00 388	95.06 321	97.54 34	0.00 388	0.00 386	0.00 386	0.00 384

ACMP	92.54 13	97.47 102	97.10 119	98.55 49	99.04 101	96.70 51	96.24 165	98.89 93	93.71 216	97.97 140	97.75 187	97.44 35	99.63 139	93.22 232	99.70 68	99.32 104
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 11	98.74 16	98.69 39	99.63 15	96.30 67	98.67 15	99.02 65	96.50 106	99.32 23	99.44 13	97.43 36	99.92 5	98.73 12	99.95 5	99.86 2

TDRefinement		98.90 5	98.86 8	99.02 6	99.54 26	98.06 8	99.34 4	99.44 16	98.85 20	99.00 41	99.20 31	97.42 37	99.59 154	97.21 59	99.76 51	99.40 90

anonymousdsp		98.72 14	98.63 19	98.99 10	99.62 16	97.29 37	98.65 19	99.19 31	95.62 153	99.35 22	99.37 18	97.38 38	99.90 14	98.59 18	99.91 17	99.77 11

PS-CasMVS		98.73 11	98.85 10	98.39 61	99.55 23	95.47 102	98.49 28	99.13 41	99.22 8	99.22 30	98.96 54	97.35 39	99.92 5	97.79 39	99.93 10	99.79 9

COLMAP_ROB	94.48 6	98.25 32	98.11 39	98.64 43	99.21 74	97.35 35	97.96 63	99.16 34	98.34 33	98.78 55	98.52 94	97.32 40	99.45 196	94.08 205	99.67 75	99.13 146
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 87	97.79 65	97.40 141	99.06 96	93.52 177	95.96 184	98.97 83	94.55 194	98.82 52	98.76 74	97.31 41	99.29 243	97.20 61	99.44 145	99.38 95

XXY-MVS		97.54 97	97.70 72	97.07 160	99.46 37	92.21 206	97.22 111	99.00 74	94.93 182	98.58 70	98.92 59	97.31 41	99.41 211	94.44 189	99.43 153	99.59 32

PEN-MVS		98.75 10	98.85 10	98.44 55	99.58 19	95.67 90	98.45 31	99.15 38	99.33 5	99.30 24	99.00 50	97.27 43	99.92 5	97.64 47	99.92 14	99.75 16

DTE-MVSNet		98.79 8	98.86 8	98.59 46	99.55 23	96.12 72	98.48 30	99.10 44	99.36 4	99.29 25	99.06 47	97.27 43	99.93 3	97.71 43	99.91 17	99.70 22

ZNCC-MVS		97.92 63	97.62 86	98.83 25	99.32 55	97.24 39	97.45 99	98.84 111	95.76 146	96.93 206	97.43 210	97.26 45	99.79 44	96.06 97	99.53 115	99.45 76

MP-MVS-pluss		97.69 87	97.36 106	98.70 38	99.50 34	96.84 47	95.38 219	98.99 77	92.45 254	98.11 122	98.31 114	97.25 46	99.77 56	96.60 78	99.62 83	99.48 67
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 69	97.63 84	98.67 40	99.35 51	96.84 47	96.36 156	98.79 127	95.07 177	97.88 148	98.35 110	97.24 47	99.72 86	96.05 99	99.58 96	99.45 76

Effi-MVS+		96.19 171	96.01 176	96.71 183	97.43 282	92.19 210	96.12 172	99.10 44	95.45 161	93.33 330	94.71 328	97.23 48	99.56 163	93.21 233	97.54 312	98.37 247

tt0805		97.44 104	97.56 93	97.11 156	99.55 23	96.36 63	98.66 18	95.66 310	98.31 34	97.09 194	95.45 315	97.17 49	98.50 333	98.67 15	97.45 318	96.48 343

PGM-MVS		97.88 70	97.52 97	98.96 13	99.20 75	97.62 21	97.09 119	99.06 54	95.45 161	97.55 161	97.94 168	97.11 50	99.78 47	94.77 180	99.46 141	99.48 67

test_0728_THIRD									96.62 96	98.40 87	98.28 123	97.10 51	99.71 101	95.70 118	99.62 83	99.58 33

APD-MVS_3200maxsize		98.13 39	97.90 54	98.79 29	98.79 122	97.31 36	97.55 92	98.92 90	97.72 56	98.25 107	98.13 142	97.10 51	99.75 67	95.44 139	99.24 196	99.32 104

OPM-MVS		97.54 97	97.25 112	98.41 59	99.11 90	96.61 56	95.24 230	98.46 178	94.58 193	98.10 124	98.07 150	97.09 53	99.39 217	95.16 157	99.44 145	99.21 129
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 59	97.64 82	98.83 25	99.15 81	97.50 29	97.59 89	98.84 111	96.05 127	97.49 166	97.54 202	97.07 54	99.70 108	95.61 127	99.46 141	99.30 109

DVP-MVS		97.78 81	97.65 79	98.16 79	99.24 62	95.51 97	96.74 139	98.23 207	95.92 137	98.40 87	98.28 123	97.06 55	99.71 101	95.48 135	99.52 120	99.26 121
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 62	95.51 97	96.89 129	98.89 93	95.92 137	98.64 64	98.31 114	97.06 55

test_fmvsm_n_1920		98.08 42	98.29 35	97.43 137	98.88 114	93.95 161	96.17 171	99.57 11	95.66 150	99.52 13	98.71 78	97.04 57	99.64 136	99.21 6	99.87 27	98.69 218

casdiffmvs		97.50 99	97.81 64	96.56 193	98.51 160	91.04 232	95.83 192	99.09 49	97.23 82	98.33 99	98.30 118	97.03 58	99.37 223	96.58 80	99.38 163	99.28 116
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 47	97.76 70	98.79 29	99.43 40	97.21 41	97.15 114	98.90 92	96.58 101	98.08 127	97.87 176	97.02 59	99.76 61	95.25 150	99.59 94	99.40 90
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 317	98.37 90	97.44 209	97.00 60	96.78 370	92.01 247	99.25 193	99.21 129

EC-MVSNet		97.90 68	97.94 53	97.79 105	98.66 138	95.14 121	98.31 39	99.66 6	97.57 64	95.95 256	97.01 243	96.99 61	99.82 35	97.66 46	99.64 80	98.39 245

DVP-MVS++		97.96 51	97.90 54	98.12 84	97.75 253	95.40 103	99.03 7	98.89 93	96.62 96	98.62 65	98.30 118	96.97 62	99.75 67	95.70 118	99.25 193	99.21 129

OPU-MVS				97.64 116	98.01 214	95.27 113	96.79 136				97.35 221	96.97 62	98.51 332	91.21 264	99.25 193	99.14 144

RE-MVS-def			97.88 58		98.81 119	98.05 9	97.55 92	98.86 104	97.77 51	98.20 111	98.07 150	96.94 64		95.49 132	99.20 198	99.26 121

APDe-MVS		98.14 36	98.03 47	98.47 54	98.72 129	96.04 75	98.07 58	99.10 44	95.96 134	98.59 69	98.69 80	96.94 64	99.81 37	96.64 76	99.58 96	99.57 38

test_one_0601					99.05 100	95.50 100		98.87 101	97.21 83	98.03 134	98.30 118	96.93 66

GST-MVS		97.82 78	97.49 101	98.81 27	99.23 64	97.25 38	97.16 113	98.79 127	95.96 134	97.53 162	97.40 212	96.93 66	99.77 56	95.04 166	99.35 172	99.42 87

test_241102_TWO								98.83 117	96.11 124	98.62 65	98.24 129	96.92 68	99.72 86	95.44 139	99.49 132	99.49 61

LCM-MVSNet-Re		97.33 113	97.33 108	97.32 145	98.13 208	93.79 167	96.99 124	99.65 7	96.74 94	99.47 15	98.93 58	96.91 69	99.84 30	90.11 292	99.06 220	98.32 254

VPA-MVSNet		98.27 30	98.46 25	97.70 111	99.06 96	93.80 166	97.76 76	99.00 74	98.40 31	99.07 38	98.98 52	96.89 70	99.75 67	97.19 62	99.79 45	99.55 44

ACMMP		98.05 45	97.75 71	98.93 18	99.23 64	97.60 22	98.09 57	98.96 84	95.75 148	97.91 145	98.06 155	96.89 70	99.76 61	95.32 147	99.57 99	99.43 86
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 41	98.01 48	98.32 65	98.45 169	96.69 52	98.52 26	99.69 3	98.07 44	96.07 252	97.19 231	96.88 72	99.86 24	97.50 51	99.73 58	98.41 242

PMVS	89.60 17	96.71 148	96.97 127	95.95 223	99.51 31	97.81 16	97.42 103	97.49 266	97.93 48	95.95 256	98.58 88	96.88 72	96.91 367	89.59 300	99.36 167	93.12 372
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 63	97.59 90	98.92 21	99.22 67	97.55 26	97.60 87	98.84 111	96.00 132	97.22 178	97.62 197	96.87 74	99.76 61	95.48 135	99.43 153	99.46 72

CP-MVS		97.92 63	97.56 93	98.99 10	98.99 105	97.82 15	97.93 66	98.96 84	96.11 124	96.89 209	97.45 208	96.85 75	99.78 47	95.19 153	99.63 82	99.38 95

DPE-MVS		97.64 90	97.35 107	98.50 51	98.85 117	96.18 69	95.21 232	98.99 77	95.84 143	98.78 55	98.08 148	96.84 76	99.81 37	93.98 211	99.57 99	99.52 49
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 74	97.97 50	97.47 133	99.19 77	94.07 156	96.71 144	98.73 139	98.66 24	98.56 71	98.41 104	96.84 76	99.69 115	94.82 175	99.81 41	98.64 222

CS-MVS-test		97.91 66	97.84 60	98.14 82	98.52 158	96.03 77	98.38 34	99.67 4	98.11 42	95.50 273	96.92 249	96.81 78	99.87 22	96.87 73	99.76 51	98.51 235

ACMMPR		97.95 55	97.62 86	98.94 15	99.20 75	97.56 25	97.59 89	98.83 117	96.05 127	97.46 171	97.63 196	96.77 79	99.76 61	95.61 127	99.46 141	99.49 61

Vis-MVSNet		98.27 30	98.34 31	98.07 86	99.33 53	95.21 120	98.04 60	99.46 14	97.32 79	97.82 155	99.11 42	96.75 80	99.86 24	97.84 36	99.36 167	99.15 141
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 197	95.07 208	96.75 181	97.67 263	92.82 192	94.22 271	98.60 164	91.61 266	93.42 328	92.90 350	96.73 81	99.70 108	92.60 240	97.89 295	97.74 301

baseline		97.44 104	97.78 69	96.43 199	98.52 158	90.75 239	96.84 130	99.03 63	96.51 105	97.86 152	98.02 159	96.67 82	99.36 225	97.09 65	99.47 138	99.19 134

SR-MVS		98.00 48	97.66 78	99.01 8	98.77 125	97.93 11	97.38 104	98.83 117	97.32 79	98.06 130	97.85 177	96.65 83	99.77 56	95.00 169	99.11 211	99.32 104

tfpnnormal		97.72 85	97.97 50	96.94 168	99.26 58	92.23 205	97.83 72	98.45 179	98.25 37	99.13 35	98.66 82	96.65 83	99.69 115	93.92 213	99.62 83	98.91 187

DeepPCF-MVS	94.58 5	96.90 133	96.43 159	98.31 67	97.48 276	97.23 40	92.56 321	98.60 164	92.84 246	98.54 72	97.40 212	96.64 85	98.78 305	94.40 193	99.41 160	98.93 183

MVS_111021_LR		96.82 139	96.55 151	97.62 117	98.27 184	95.34 110	93.81 293	98.33 197	94.59 192	96.56 227	96.63 267	96.61 86	98.73 310	94.80 176	99.34 175	98.78 205

Gipuma		98.07 44	98.31 32	97.36 143	99.76 7	96.28 68	98.51 27	99.10 44	98.76 22	96.79 212	99.34 24	96.61 86	98.82 301	96.38 86	99.50 129	96.98 323
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SR-MVS-dyc-post		98.14 36	97.84 60	99.02 6	98.81 119	98.05 9	97.55 92	98.86 104	97.77 51	98.20 111	98.07 150	96.60 88	99.76 61	95.49 132	99.20 198	99.26 121

MVS_111021_HR		96.73 145	96.54 153	97.27 148	98.35 177	93.66 173	93.42 303	98.36 193	94.74 185	96.58 225	96.76 261	96.54 89	98.99 287	94.87 173	99.27 191	99.15 141

SMA-MVS		97.48 101	97.11 118	98.60 45	98.83 118	96.67 53	96.74 139	98.73 139	91.61 266	98.48 79	98.36 109	96.53 90	99.68 120	95.17 155	99.54 111	99.45 76
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 11	98.99 5	97.95 95	99.64 14	94.20 153	98.67 15	99.14 40	99.08 10	99.42 17	99.23 29	96.53 90	99.91 13	99.27 4	99.93 10	99.73 19

mPP-MVS		97.91 66	97.53 96	99.04 4	99.22 67	97.87 14	97.74 79	98.78 131	96.04 129	97.10 189	97.73 190	96.53 90	99.78 47	95.16 157	99.50 129	99.46 72

XVS		97.96 51	97.63 84	98.94 15	99.15 81	97.66 19	97.77 74	98.83 117	97.42 72	96.32 238	97.64 195	96.49 93	99.72 86	95.66 123	99.37 164	99.45 76

X-MVStestdata		92.86 290	90.83 315	98.94 15	99.15 81	97.66 19	97.77 74	98.83 117	97.42 72	96.32 238	36.50 382	96.49 93	99.72 86	95.66 123	99.37 164	99.45 76

9.14			96.69 143		98.53 157		96.02 178	98.98 80	93.23 228	97.18 183	97.46 207	96.47 95	99.62 144	92.99 236	99.32 182

UA-Net		98.88 7	98.76 13	99.22 2	99.11 90	97.89 13	99.47 3	99.32 20	99.08 10	97.87 151	99.67 2	96.47 95	99.92 5	97.88 33	99.98 2	99.85 3

SF-MVS		97.60 93	97.39 104	98.22 75	98.93 110	95.69 88	97.05 121	99.10 44	95.32 166	97.83 154	97.88 175	96.44 97	99.72 86	94.59 188	99.39 162	99.25 125

xiu_mvs_v1_base_debu		95.62 193	95.96 180	94.60 286	98.01 214	88.42 274	93.99 283	98.21 209	92.98 240	95.91 258	94.53 331	96.39 98	99.72 86	95.43 142	98.19 282	95.64 354

xiu_mvs_v1_base		95.62 193	95.96 180	94.60 286	98.01 214	88.42 274	93.99 283	98.21 209	92.98 240	95.91 258	94.53 331	96.39 98	99.72 86	95.43 142	98.19 282	95.64 354

xiu_mvs_v1_base_debi		95.62 193	95.96 180	94.60 286	98.01 214	88.42 274	93.99 283	98.21 209	92.98 240	95.91 258	94.53 331	96.39 98	99.72 86	95.43 142	98.19 282	95.64 354

ETV-MVS		96.13 174	95.90 184	96.82 177	97.76 251	93.89 162	95.40 217	98.95 86	95.87 141	95.58 272	91.00 371	96.36 101	99.72 86	93.36 226	98.83 243	96.85 330

MP-MVS		97.64 90	97.18 116	99.00 9	99.32 55	97.77 17	97.49 98	98.73 139	96.27 115	95.59 271	97.75 187	96.30 102	99.78 47	93.70 221	99.48 136	99.45 76
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 180	96.34 164	94.96 269	97.90 226	87.91 289	94.13 278	98.49 176	94.41 196	98.16 117	97.76 184	96.29 103	98.68 318	90.52 285	99.42 156	98.30 258

Fast-Effi-MVS+-dtu		96.44 162	96.12 171	97.39 142	97.18 298	94.39 142	95.46 211	98.73 139	96.03 131	94.72 290	94.92 325	96.28 104	99.69 115	93.81 216	97.98 290	98.09 272

APD_test1		97.95 55	97.68 76	98.75 31	99.60 17	98.60 5	97.21 112	99.08 50	96.57 104	98.07 129	98.38 108	96.22 105	99.14 267	94.71 183	99.31 185	98.52 234

OMC-MVS		96.48 160	96.00 177	97.91 97	98.30 179	96.01 78	94.86 249	98.60 164	91.88 263	97.18 183	97.21 230	96.11 106	99.04 281	90.49 288	99.34 175	98.69 218

xiu_mvs_v2_base		94.22 254	94.63 232	92.99 328	97.32 292	84.84 339	92.12 329	97.84 246	91.96 261	94.17 302	93.43 341	96.07 107	99.71 101	91.27 261	97.48 315	94.42 364

CSCG		97.40 107	97.30 109	97.69 113	98.95 107	94.83 128	97.28 107	98.99 77	96.35 114	98.13 121	95.95 301	95.99 108	99.66 131	94.36 196	99.73 58	98.59 228

PHI-MVS		96.96 129	96.53 154	98.25 73	97.48 276	96.50 59	96.76 138	98.85 108	93.52 219	96.19 248	96.85 252	95.94 109	99.42 202	93.79 217	99.43 153	98.83 200

TSAR-MVS + MP.		97.42 106	97.23 114	98.00 93	99.38 48	95.00 125	97.63 86	98.20 212	93.00 239	98.16 117	98.06 155	95.89 110	99.72 86	95.67 122	99.10 213	99.28 116
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 95	97.28 111	98.49 52	99.16 79	96.90 46	96.39 153	98.98 80	95.05 178	98.06 130	98.02 159	95.86 111	99.56 163	94.37 194	99.64 80	99.00 170

AllTest		97.20 118	96.92 132	98.06 88	99.08 93	96.16 70	97.14 116	99.16 34	94.35 198	97.78 156	98.07 150	95.84 112	99.12 270	91.41 258	99.42 156	98.91 187

TestCases				98.06 88	99.08 93	96.16 70		99.16 34	94.35 198	97.78 156	98.07 150	95.84 112	99.12 270	91.41 258	99.42 156	98.91 187

APD-MVS		97.00 124	96.53 154	98.41 59	98.55 154	96.31 66	96.32 159	98.77 132	92.96 244	97.44 172	97.58 201	95.84 112	99.74 76	91.96 248	99.35 172	99.19 134
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 354	10.65 357	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	95.82 115	0.00 388	0.00 386	0.00 386	0.00 384

PS-MVSNAJss		98.53 21	98.63 19	98.21 78	99.68 11	94.82 129	98.10 56	99.21 27	96.91 89	99.75 2	99.45 12	95.82 115	99.92 5	98.80 9	99.96 4	99.89 1

PS-MVSNAJ		94.10 260	94.47 242	93.00 327	97.35 287	84.88 337	91.86 333	97.84 246	91.96 261	94.17 302	92.50 357	95.82 115	99.71 101	91.27 261	97.48 315	94.40 365

3Dnovator	96.53 2	97.61 92	97.64 82	97.50 128	97.74 256	93.65 174	98.49 28	98.88 99	96.86 91	97.11 188	98.55 92	95.82 115	99.73 81	95.94 108	99.42 156	99.13 146

MTAPA		98.14 36	97.84 60	99.06 3	99.44 39	97.90 12	97.25 108	98.73 139	97.69 60	97.90 146	97.96 165	95.81 119	99.82 35	96.13 96	99.61 89	99.45 76

DP-MVS		97.87 71	97.89 57	97.81 104	98.62 145	94.82 129	97.13 117	98.79 127	98.98 17	98.74 61	98.49 97	95.80 120	99.49 184	95.04 166	99.44 145	99.11 154

Anonymous20240529		97.96 51	98.04 46	97.71 110	98.69 136	94.28 150	97.86 70	98.31 201	98.79 21	99.23 29	98.86 67	95.76 121	99.61 151	95.49 132	99.36 167	99.23 127

LS3D		97.77 82	97.50 100	98.57 47	96.24 322	97.58 24	98.45 31	98.85 108	98.58 26	97.51 164	97.94 168	95.74 122	99.63 139	95.19 153	98.97 225	98.51 235

EIA-MVS		96.04 177	95.77 190	96.85 175	97.80 241	92.98 190	96.12 172	99.16 34	94.65 188	93.77 314	91.69 365	95.68 123	99.67 125	94.18 201	98.85 240	97.91 291

CNVR-MVS		96.92 131	96.55 151	98.03 92	98.00 218	95.54 95	94.87 248	98.17 218	94.60 190	96.38 235	97.05 239	95.67 124	99.36 225	95.12 163	99.08 215	99.19 134

CLD-MVS		95.47 200	95.07 208	96.69 185	98.27 184	92.53 199	91.36 339	98.67 154	91.22 273	95.78 265	94.12 338	95.65 125	98.98 289	90.81 273	99.72 62	98.57 229
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 19	98.76 13	97.94 96	98.79 122	94.37 144	98.84 11	99.15 38	99.37 3	99.67 7	99.43 14	95.61 126	99.72 86	98.12 25	99.86 29	99.73 19

EGC-MVSNET		83.08 348	77.93 351	98.53 50	99.57 20	97.55 26	98.33 38	98.57 170	4.71 384	10.38 385	98.90 63	95.60 127	99.50 180	95.69 120	99.61 89	98.55 232

ITE_SJBPF				97.85 102	98.64 139	96.66 54		98.51 175	95.63 152	97.22 178	97.30 225	95.52 128	98.55 329	90.97 268	98.90 233	98.34 253

DeepC-MVS_fast	94.34 7	96.74 143	96.51 156	97.44 136	97.69 259	94.15 154	96.02 178	98.43 182	93.17 234	97.30 175	97.38 218	95.48 129	99.28 245	93.74 218	99.34 175	98.88 195
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 15	98.62 21	98.75 31	99.51 31	96.61 56	98.55 22	99.17 33	99.05 13	99.17 32	98.79 69	95.47 130	99.89 18	97.95 32	99.91 17	99.75 16

FMVSNet1		97.95 55	98.08 41	97.56 119	99.14 88	93.67 170	98.23 46	98.66 156	97.41 75	99.00 41	99.19 32	95.47 130	99.73 81	95.83 115	99.76 51	99.30 109

MIMVSNet1		98.51 22	98.45 27	98.67 40	99.72 8	96.71 50	98.76 12	98.89 93	98.49 29	99.38 19	99.14 41	95.44 132	99.84 30	96.47 83	99.80 44	99.47 70

CP-MVSNet		98.42 25	98.46 25	98.30 68	99.46 37	95.22 118	98.27 44	98.84 111	99.05 13	99.01 40	98.65 84	95.37 133	99.90 14	97.57 48	99.91 17	99.77 11

segment_acmp												95.34 134

CDPH-MVS		95.45 202	94.65 229	97.84 103	98.28 182	94.96 126	93.73 295	98.33 197	85.03 342	95.44 274	96.60 268	95.31 135	99.44 199	90.01 294	99.13 207	99.11 154

3Dnovator+	96.13 3	97.73 84	97.59 90	98.15 81	98.11 209	95.60 92	98.04 60	98.70 148	98.13 41	96.93 206	98.45 101	95.30 136	99.62 144	95.64 125	98.96 226	99.24 126

MVS_Test		96.27 168	96.79 140	94.73 282	96.94 308	86.63 315	96.18 168	98.33 197	94.94 180	96.07 252	98.28 123	95.25 137	99.26 249	97.21 59	97.90 294	98.30 258

XVG-OURS		97.12 119	96.74 141	98.26 70	98.99 105	97.45 32	93.82 291	99.05 56	95.19 171	98.32 100	97.70 192	95.22 138	98.41 337	94.27 198	98.13 285	98.93 183

dcpmvs_2		97.12 119	97.99 49	94.51 292	99.11 90	84.00 347	97.75 77	99.65 7	97.38 77	99.14 34	98.42 103	95.16 139	99.96 2	95.52 131	99.78 48	99.58 33

MCST-MVS		96.24 169	95.80 188	97.56 119	98.75 126	94.13 155	94.66 256	98.17 218	90.17 286	96.21 246	96.10 295	95.14 140	99.43 201	94.13 204	98.85 240	99.13 146

EI-MVSNet-Vis-set		97.32 114	97.39 104	97.11 156	97.36 286	92.08 215	95.34 223	97.65 259	97.74 54	98.29 105	98.11 146	95.05 141	99.68 120	97.50 51	99.50 129	99.56 42

EI-MVSNet-UG-set		97.32 114	97.40 103	97.09 159	97.34 289	92.01 217	95.33 224	97.65 259	97.74 54	98.30 104	98.14 140	95.04 142	99.69 115	97.55 49	99.52 120	99.58 33

KD-MVS_self_test		97.86 73	98.07 42	97.25 150	99.22 67	92.81 193	97.55 92	98.94 87	97.10 85	98.85 49	98.88 65	95.03 143	99.67 125	97.39 55	99.65 78	99.26 121

ZD-MVS					98.43 171	95.94 79		98.56 171	90.72 278	96.66 221	97.07 237	95.02 144	99.74 76	91.08 265	98.93 231

DELS-MVS		96.17 172	96.23 167	95.99 219	97.55 272	90.04 247	92.38 326	98.52 173	94.13 203	96.55 229	97.06 238	94.99 145	99.58 156	95.62 126	99.28 189	98.37 247
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		96.59 154	96.93 130	95.55 242	98.88 114	87.12 307	94.47 261	99.30 21	94.12 204	96.65 223	98.41 104	94.98 146	99.87 22	95.81 117	99.78 48	99.66 24

ab-mvs		96.59 154	96.59 147	96.60 188	98.64 139	92.21 206	98.35 35	97.67 255	94.45 195	96.99 201	98.79 69	94.96 147	99.49 184	90.39 289	99.07 217	98.08 273

MSLP-MVS++		96.42 164	96.71 142	95.57 239	97.82 236	90.56 243	95.71 195	98.84 111	94.72 186	96.71 218	97.39 216	94.91 148	98.10 352	95.28 148	99.02 222	98.05 282

QAPM		95.88 183	95.57 197	96.80 178	97.90 226	91.84 221	98.18 53	98.73 139	88.41 305	96.42 233	98.13 142	94.73 149	99.75 67	88.72 312	98.94 229	98.81 202

RPSCF		97.87 71	97.51 98	98.95 14	99.15 81	98.43 6	97.56 91	99.06 54	96.19 121	98.48 79	98.70 79	94.72 150	99.24 254	94.37 194	99.33 180	99.17 138

DU-MVS		97.79 80	97.60 89	98.36 63	98.73 127	95.78 84	95.65 202	98.87 101	97.57 64	98.31 102	97.83 178	94.69 151	99.85 27	97.02 68	99.71 65	99.46 72

Baseline_NR-MVSNet		97.72 85	97.79 65	97.50 128	99.56 21	93.29 183	95.44 212	98.86 104	98.20 40	98.37 90	99.24 28	94.69 151	99.55 167	95.98 106	99.79 45	99.65 26

TEST9					97.84 233	95.23 115	93.62 297	98.39 189	86.81 323	93.78 312	95.99 297	94.68 153	99.52 175

UniMVSNet (Re)		97.83 75	97.65 79	98.35 64	98.80 121	95.86 83	95.92 188	99.04 62	97.51 69	98.22 110	97.81 182	94.68 153	99.78 47	97.14 63	99.75 56	99.41 89

UniMVSNet_NR-MVSNet		97.83 75	97.65 79	98.37 62	98.72 129	95.78 84	95.66 200	99.02 65	98.11 42	98.31 102	97.69 193	94.65 155	99.85 27	97.02 68	99.71 65	99.48 67

VPNet		97.26 116	97.49 101	96.59 189	99.47 36	90.58 241	96.27 161	98.53 172	97.77 51	98.46 82	98.41 104	94.59 156	99.68 120	94.61 184	99.29 188	99.52 49

train_agg		95.46 201	94.66 228	97.88 100	97.84 233	95.23 115	93.62 297	98.39 189	87.04 319	93.78 312	95.99 297	94.58 157	99.52 175	91.76 255	98.90 233	98.89 191

test_8					97.81 237	95.07 124	93.54 300	98.38 191	87.04 319	93.71 316	95.96 300	94.58 157	99.52 175

API-MVS		95.09 218	95.01 211	95.31 252	96.61 314	94.02 158	96.83 131	97.18 275	95.60 154	95.79 263	94.33 336	94.54 159	98.37 342	85.70 340	98.52 269	93.52 369

Test By Simon												94.51 160

MSDG		95.33 206	95.13 205	95.94 225	97.40 284	91.85 220	91.02 350	98.37 192	95.30 167	96.31 240	95.99 297	94.51 160	98.38 340	89.59 300	97.65 309	97.60 307

TSAR-MVS + GP.		96.47 161	96.12 171	97.49 131	97.74 256	95.23 115	94.15 275	96.90 286	93.26 227	98.04 133	96.70 263	94.41 162	98.89 296	94.77 180	99.14 205	98.37 247

NR-MVSNet		97.96 51	97.86 59	98.26 70	98.73 127	95.54 95	98.14 54	98.73 139	97.79 50	99.42 17	97.83 178	94.40 163	99.78 47	95.91 110	99.76 51	99.46 72

AdaColmap		95.11 216	94.62 233	96.58 190	97.33 291	94.45 141	94.92 246	98.08 231	93.15 235	93.98 310	95.53 313	94.34 164	99.10 275	85.69 341	98.61 264	96.20 348

FC-MVSNet-test		98.16 34	98.37 30	97.56 119	99.49 35	93.10 188	98.35 35	99.21 27	98.43 30	98.89 47	98.83 68	94.30 165	99.81 37	97.87 34	99.91 17	99.77 11

Effi-MVS+-dtu		96.81 140	96.09 173	98.99 10	96.90 310	98.69 4	96.42 152	98.09 230	95.86 142	95.15 281	95.54 312	94.26 166	99.81 37	94.06 206	98.51 271	98.47 239

ambc				96.56 193	98.23 189	91.68 224	97.88 69	98.13 226		98.42 85	98.56 91	94.22 167	99.04 281	94.05 208	99.35 172	98.95 177

test20.03		96.58 156	96.61 146	96.48 197	98.49 164	91.72 223	95.68 199	97.69 254	96.81 92	98.27 106	97.92 171	94.18 168	98.71 313	90.78 275	99.66 77	99.00 170

HPM-MVS++		96.99 125	96.38 162	98.81 27	98.64 139	97.59 23	95.97 182	98.20 212	95.51 159	95.06 282	96.53 272	94.10 169	99.70 108	94.29 197	99.15 204	99.13 146

test_vis3_rt		97.04 122	96.98 126	97.23 152	98.44 170	95.88 80	96.82 132	99.67 4	90.30 283	99.27 26	99.33 25	94.04 170	96.03 373	97.14 63	97.83 296	99.78 10

test_fmvs3		97.38 108	97.56 93	96.84 176	98.63 143	92.81 193	97.60 87	99.61 10	90.87 276	98.76 60	99.66 3	94.03 171	97.90 354	99.24 5	99.68 73	99.81 8

PM-MVS		97.36 112	97.10 119	98.14 82	98.91 112	96.77 49	96.20 167	98.63 162	93.82 213	98.54 72	98.33 112	93.98 172	99.05 280	95.99 105	99.45 144	98.61 227

mvsany_test3		96.21 170	95.93 183	97.05 161	97.40 284	94.33 146	95.76 194	94.20 330	89.10 296	99.36 21	99.60 6	93.97 173	97.85 355	95.40 146	98.63 262	98.99 173

OpenMVS	94.22 8	95.48 199	95.20 202	96.32 206	97.16 299	91.96 218	97.74 79	98.84 111	87.26 316	94.36 299	98.01 161	93.95 174	99.67 125	90.70 281	98.75 250	97.35 317

v8		97.60 93	98.06 44	96.23 209	98.71 132	89.44 257	97.43 102	98.82 125	97.29 81	98.74 61	99.10 43	93.86 175	99.68 120	98.61 17	99.94 8	99.56 42

diffmvs		96.04 177	96.23 167	95.46 247	97.35 287	88.03 287	93.42 303	99.08 50	94.09 207	96.66 221	96.93 247	93.85 176	99.29 243	96.01 104	98.67 257	99.06 163
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		96.52 158	95.99 178	98.10 85	97.81 237	95.68 89	95.00 244	98.20 212	95.39 164	95.40 276	96.36 282	93.81 177	99.45 196	93.55 224	98.42 274	99.17 138

TAPA-MVS	93.32 12	94.93 223	94.23 249	97.04 163	98.18 196	94.51 138	95.22 231	98.73 139	81.22 361	96.25 244	95.95 301	93.80 178	98.98 289	89.89 296	98.87 237	97.62 305
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 62	98.07 42	97.48 132	99.38 48	92.95 191	98.03 62	99.11 43	98.04 46	98.62 65	98.66 82	93.75 179	99.78 47	97.23 57	99.84 35	99.73 19

OurMVSNet-221017-0		98.61 16	98.61 23	98.63 44	99.77 5	96.35 64	99.17 6	99.05 56	98.05 45	99.61 12	99.52 7	93.72 180	99.88 20	98.72 14	99.88 26	99.65 26

test_prior2							93.33 307		94.21 201	94.02 308	96.25 286	93.64 181		91.90 250	98.96 226

mvsany_test1		93.47 279	93.03 275	94.79 279	94.05 368	92.12 211	90.82 352	90.01 368	85.02 343	97.26 177	98.28 123	93.57 182	97.03 364	92.51 243	95.75 349	95.23 360

旧先验1					97.80 241	93.87 163		97.75 251			97.04 240	93.57 182			98.68 256	98.72 214

v10		97.55 96	97.97 50	96.31 207	98.60 147	89.64 253	97.44 100	99.02 65	96.60 98	98.72 63	99.16 38	93.48 184	99.72 86	98.76 11	99.92 14	99.58 33

v148		96.58 156	96.97 127	95.42 249	98.63 143	87.57 297	95.09 236	97.90 241	95.91 139	98.24 108	97.96 165	93.42 185	99.39 217	96.04 100	99.52 120	99.29 115

V42		97.04 122	97.16 117	96.68 186	98.59 149	91.05 231	96.33 158	98.36 193	94.60 190	97.99 136	98.30 118	93.32 186	99.62 144	97.40 54	99.53 115	99.38 95

new-patchmatchnet		95.67 191	96.58 148	92.94 330	97.48 276	80.21 365	92.96 312	98.19 217	94.83 183	98.82 52	98.79 69	93.31 187	99.51 179	95.83 115	99.04 221	99.12 151

test12				97.46 134	97.61 267	94.07 156		97.78 250		93.57 322		93.31 187	99.42 202		98.78 247	98.89 191

UGNet		96.81 140	96.56 150	97.58 118	96.64 313	93.84 165	97.75 77	97.12 278	96.47 109	93.62 319	98.88 65	93.22 189	99.53 172	95.61 127	99.69 69	99.36 101
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
pmmvs-eth3d		96.49 159	96.18 170	97.42 139	98.25 186	94.29 147	94.77 252	98.07 235	89.81 290	97.97 140	98.33 112	93.11 190	99.08 277	95.46 138	99.84 35	98.89 191

v1144		96.84 135	97.08 121	96.13 216	98.42 172	89.28 260	95.41 216	98.67 154	94.21 201	97.97 140	98.31 114	93.06 191	99.65 133	98.06 29	99.62 83	99.45 76

PVSNet_BlendedMVS		95.02 222	94.93 214	95.27 253	97.79 246	87.40 302	94.14 277	98.68 151	88.94 300	94.51 295	98.01 161	93.04 192	99.30 239	89.77 298	99.49 132	99.11 154

PVSNet_Blended		93.96 265	93.65 264	94.91 270	97.79 246	87.40 302	91.43 338	98.68 151	84.50 349	94.51 295	94.48 334	93.04 192	99.30 239	89.77 298	98.61 264	98.02 285

mvs_anonymous		95.36 204	96.07 175	93.21 322	96.29 321	81.56 360	94.60 258	97.66 257	93.30 226	96.95 205	98.91 62	93.03 194	99.38 220	96.60 78	97.30 323	98.69 218

v1192		96.83 138	97.06 123	96.15 215	98.28 182	89.29 259	95.36 220	98.77 132	93.73 215	98.11 122	98.34 111	93.02 195	99.67 125	98.35 23	99.58 96	99.50 53

F-COLMAP		95.30 208	94.38 246	98.05 91	98.64 139	96.04 75	95.61 206	98.66 156	89.00 299	93.22 331	96.40 280	92.90 196	99.35 228	87.45 331	97.53 313	98.77 208

WR-MVS		96.90 133	96.81 137	97.16 153	98.56 153	92.20 209	94.33 264	98.12 227	97.34 78	98.20 111	97.33 223	92.81 197	99.75 67	94.79 177	99.81 41	99.54 45

v1240		96.74 143	97.02 125	95.91 226	98.18 196	88.52 273	95.39 218	98.88 99	93.15 235	98.46 82	98.40 107	92.80 198	99.71 101	98.45 21	99.49 132	99.49 61

MVS_0304		96.62 153	96.40 161	97.28 147	97.91 224	92.30 203	96.47 151	89.74 369	97.52 68	95.38 277	98.63 85	92.76 199	99.81 37	99.28 3	99.93 10	99.75 16

MVE	73.61 22	86.48 346	85.92 348	88.18 360	96.23 324	85.28 331	81.78 378	75.79 384	86.01 329	82.53 380	91.88 362	92.74 200	87.47 383	71.42 379	94.86 357	91.78 374
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 196	95.13 205	96.80 178	98.51 160	93.99 160	94.60 258	98.69 149	90.20 285	95.78 265	96.21 288	92.73 201	98.98 289	90.58 284	98.86 239	97.42 314

CANet		95.86 184	95.65 194	96.49 196	96.41 319	90.82 236	94.36 263	98.41 186	94.94 180	92.62 346	96.73 262	92.68 202	99.71 101	95.12 163	99.60 92	98.94 179

v1921920		96.72 146	96.96 129	95.99 219	98.21 190	88.79 270	95.42 214	98.79 127	93.22 229	98.19 115	98.26 128	92.68 202	99.70 108	98.34 24	99.55 108	99.49 61

BH-untuned		94.69 235	94.75 226	94.52 291	97.95 223	87.53 298	94.07 280	97.01 282	93.99 209	97.10 189	95.65 308	92.65 204	98.95 294	87.60 327	96.74 332	97.09 320

LF4IMVS		96.07 175	95.63 195	97.36 143	98.19 193	95.55 94	95.44 212	98.82 125	92.29 257	95.70 269	96.55 270	92.63 205	98.69 315	91.75 256	99.33 180	97.85 296

v2v482		96.78 142	97.06 123	95.95 223	98.57 151	88.77 271	95.36 220	98.26 203	95.18 172	97.85 153	98.23 131	92.58 206	99.63 139	97.80 38	99.69 69	99.45 76

EI-MVSNet		96.63 152	96.93 130	95.74 232	97.26 294	88.13 284	95.29 228	97.65 259	96.99 86	97.94 143	98.19 136	92.55 207	99.58 156	96.91 71	99.56 102	99.50 53

IterMVS-LS		96.92 131	97.29 110	95.79 230	98.51 160	88.13 284	95.10 235	98.66 156	96.99 86	98.46 82	98.68 81	92.55 207	99.74 76	96.91 71	99.79 45	99.50 53
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 110	97.25 112	97.74 108	98.69 136	94.50 140	97.04 122	95.61 314	98.59 25	98.51 74	98.72 76	92.54 209	99.58 156	96.02 102	99.49 132	99.12 151

MVS		90.02 323	89.20 330	92.47 337	94.71 357	86.90 311	95.86 190	96.74 293	64.72 380	90.62 357	92.77 352	92.54 209	98.39 339	79.30 367	95.56 351	92.12 373

test_vis1_rt		94.03 264	93.65 264	95.17 258	95.76 342	93.42 180	93.97 286	98.33 197	84.68 346	93.17 332	95.89 303	92.53 211	94.79 375	93.50 225	94.97 355	97.31 318

v144192		96.69 149	96.90 134	96.03 218	98.25 186	88.92 265	95.49 210	98.77 132	93.05 237	98.09 125	98.29 122	92.51 212	99.70 108	98.11 26	99.56 102	99.47 70

原ACMM1				96.58 190	98.16 201	92.12 211		98.15 224	85.90 332	93.49 324	96.43 277	92.47 213	99.38 220	87.66 326	98.62 263	98.23 265

VNet		96.84 135	96.83 136	96.88 173	98.06 210	92.02 216	96.35 157	97.57 265	97.70 59	97.88 148	97.80 183	92.40 214	99.54 170	94.73 182	98.96 226	99.08 159

114514_t		93.96 265	93.22 272	96.19 212	99.06 96	90.97 234	95.99 180	98.94 87	73.88 378	93.43 327	96.93 247	92.38 215	99.37 223	89.09 307	99.28 189	98.25 264

CPTT-MVS		96.69 149	96.08 174	98.49 52	98.89 113	96.64 55	97.25 108	98.77 132	92.89 245	96.01 255	97.13 233	92.23 216	99.67 125	92.24 245	99.34 175	99.17 138

MSP-MVS		97.45 103	96.92 132	99.03 5	99.26 58	97.70 18	97.66 83	98.89 93	95.65 151	98.51 74	96.46 276	92.15 217	99.81 37	95.14 160	98.58 267	99.58 33
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		94.21 256	93.03 275	97.76 107	96.94 308	97.44 33	96.97 125	97.15 276	87.89 314	92.00 351	92.73 354	92.14 218	99.12 270	83.92 354	97.51 314	96.73 337
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		95.95 181	95.80 188	96.42 201	99.28 57	90.62 240	95.31 226	99.08 50	88.40 306	96.97 204	98.17 139	92.11 219	99.78 47	93.64 222	99.21 197	98.86 198

BH-RMVSNet		94.56 243	94.44 245	94.91 270	97.57 269	87.44 301	93.78 294	96.26 299	93.69 217	96.41 234	96.50 275	92.10 220	99.00 285	85.96 338	97.71 303	98.31 256

新几何1				97.25 150	98.29 180	94.70 133		97.73 252	77.98 372	94.83 289	96.67 265	92.08 221	99.45 196	88.17 321	98.65 261	97.61 306

testdata				95.70 235	98.16 201	90.58 241		97.72 253	80.38 364	95.62 270	97.02 241	92.06 222	98.98 289	89.06 309	98.52 269	97.54 309

YYNet1		94.73 230	94.84 220	94.41 296	97.47 280	85.09 335	90.29 357	95.85 308	92.52 251	97.53 162	97.76 184	91.97 223	99.18 260	93.31 229	96.86 328	98.95 177

Anonymous20231206		95.27 209	95.06 210	95.88 227	98.72 129	89.37 258	95.70 196	97.85 244	88.00 312	96.98 203	97.62 197	91.95 224	99.34 230	89.21 305	99.53 115	98.94 179

MS-PatchMatch		94.83 227	94.91 216	94.57 289	96.81 311	87.10 308	94.23 270	97.34 270	88.74 303	97.14 185	97.11 235	91.94 225	98.23 348	92.99 236	97.92 292	98.37 247

MDA-MVSNet_test_wron		94.73 230	94.83 222	94.42 295	97.48 276	85.15 333	90.28 358	95.87 307	92.52 251	97.48 168	97.76 184	91.92 226	99.17 264	93.32 228	96.80 331	98.94 179

HQP_MVS		96.66 151	96.33 165	97.68 114	98.70 134	94.29 147	96.50 149	98.75 136	96.36 112	96.16 249	96.77 259	91.91 227	99.46 192	92.59 241	99.20 198	99.28 116

plane_prior6					98.38 174	94.37 144						91.91 227

MVP-Stereo		95.69 189	95.28 200	96.92 170	98.15 203	93.03 189	95.64 205	98.20 212	90.39 282	96.63 224	97.73 190	91.63 229	99.10 275	91.84 253	97.31 322	98.63 224
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 241	93.81 262	97.02 165	98.19 193	95.72 86	93.66 296	97.23 272	88.17 310	94.94 287	95.62 310	91.43 230	98.57 326	87.36 332	97.68 306	96.76 336

MDA-MVSNet-bldmvs		95.69 189	95.67 192	95.74 232	98.48 166	88.76 272	92.84 313	97.25 271	96.00 132	97.59 160	97.95 167	91.38 231	99.46 192	93.16 234	96.35 339	98.99 173

mvsmamba		98.16 34	98.06 44	98.44 55	99.53 29	95.87 81	98.70 13	98.94 87	97.71 58	98.85 49	99.10 43	91.35 232	99.83 33	98.47 20	99.90 23	99.64 28

PAPR		92.22 300	91.27 306	95.07 262	95.73 344	88.81 269	91.97 332	97.87 243	85.80 333	90.91 356	92.73 354	91.16 233	98.33 344	79.48 366	95.76 348	98.08 273

1314		92.38 297	92.30 292	92.64 334	95.42 351	85.15 333	95.86 190	96.97 284	85.40 338	90.62 357	93.06 348	91.12 234	97.80 357	86.74 335	95.49 352	94.97 362

ppachtmachnet_test		94.49 248	94.84 220	93.46 316	96.16 328	82.10 356	90.59 354	97.48 267	90.53 280	97.01 200	97.59 199	91.01 235	99.36 225	93.97 212	99.18 202	98.94 179

PLC	91.02 16	94.05 263	92.90 278	97.51 124	98.00 218	95.12 123	94.25 268	98.25 204	86.17 328	91.48 354	95.25 317	91.01 235	99.19 259	85.02 349	96.69 333	98.22 266
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 199	93.24 186	92.74 318	97.61 264	75.17 376	94.65 292	96.69 264	90.96 237			98.66 259	97.66 304

CL-MVSNet_self_test		95.04 219	94.79 225	95.82 229	97.51 274	89.79 251	91.14 347	96.82 289	93.05 237	96.72 217	96.40 280	90.82 238	99.16 265	91.95 249	98.66 259	98.50 237

USDC		94.56 243	94.57 239	94.55 290	97.78 249	86.43 318	92.75 316	98.65 161	85.96 330	96.91 208	97.93 170	90.82 238	98.74 309	90.71 280	99.59 94	98.47 239

PCF-MVS	89.43 18	92.12 303	90.64 318	96.57 192	97.80 241	93.48 178	89.88 364	98.45 179	74.46 377	96.04 254	95.68 307	90.71 240	99.31 236	73.73 375	99.01 224	96.91 327
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 241	94.17 253	95.96 221	98.36 176	91.23 229	95.93 187	97.95 238	92.98 240	93.42 328	94.43 335	90.53 241	98.38 340	87.60 327	96.29 340	98.27 262

our_test_3		94.20 258	94.58 237	93.07 324	96.16 328	81.20 362	90.42 356	96.84 287	90.72 278	97.14 185	97.13 233	90.47 242	99.11 273	94.04 209	98.25 280	98.91 187

test_f		95.82 186	95.88 186	95.66 236	97.61 267	93.21 187	95.61 206	98.17 218	86.98 321	98.42 85	99.47 10	90.46 243	94.74 376	97.71 43	98.45 273	99.03 166

OpenMVS_ROB	91.80 14	93.64 275	93.05 273	95.42 249	97.31 293	91.21 230	95.08 238	96.68 296	81.56 358	96.88 210	96.41 278	90.44 244	99.25 251	85.39 345	97.67 307	95.80 352

HQP2-MVS												90.33 245

N_pmnet		95.18 213	94.23 249	98.06 88	97.85 228	96.55 58	92.49 322	91.63 355	89.34 293	98.09 125	97.41 211	90.33 245	99.06 279	91.58 257	99.31 185	98.56 230

HQP-MVS		95.17 215	94.58 237	96.92 170	97.85 228	92.47 200	94.26 265	98.43 182	93.18 231	92.86 337	95.08 319	90.33 245	99.23 256	90.51 286	98.74 251	99.05 165

CNLPA		95.04 219	94.47 242	96.75 181	97.81 237	95.25 114	94.12 279	97.89 242	94.41 196	94.57 293	95.69 306	90.30 248	98.35 343	86.72 336	98.76 249	96.64 338

PMMVS		92.39 296	91.08 309	96.30 208	93.12 375	92.81 193	90.58 355	95.96 305	79.17 369	91.85 353	92.27 358	90.29 249	98.66 320	89.85 297	96.68 334	97.43 313

TR-MVS		92.54 295	92.20 294	93.57 314	96.49 317	86.66 314	93.51 301	94.73 324	89.96 288	94.95 286	93.87 339	90.24 250	98.61 323	81.18 363	94.88 356	95.45 358

TAMVS		95.49 197	94.94 212	97.16 153	98.31 178	93.41 181	95.07 239	96.82 289	91.09 274	97.51 164	97.82 181	89.96 251	99.42 202	88.42 317	99.44 145	98.64 222

DPM-MVS		93.68 272	92.77 285	96.42 201	97.91 224	92.54 198	91.17 346	97.47 268	84.99 344	93.08 334	94.74 327	89.90 252	99.00 285	87.54 329	98.09 287	97.72 302

PMMVS2		93.66 273	94.07 255	92.45 338	97.57 269	80.67 364	86.46 372	96.00 303	93.99 209	97.10 189	97.38 218	89.90 252	97.82 356	88.76 311	99.47 138	98.86 198

RRT_MVS		97.95 55	97.79 65	98.43 57	99.67 12	95.56 93	98.86 10	96.73 295	97.99 47	99.15 33	99.35 22	89.84 254	99.90 14	98.64 16	99.90 23	99.82 6

bld_raw_dy_0_64		97.69 87	97.61 88	97.91 97	99.54 26	94.27 151	98.06 59	98.60 164	96.60 98	98.79 54	98.95 56	89.62 255	99.84 30	98.43 22	99.91 17	99.62 29

BH-w/o		92.14 302	91.94 296	92.73 333	97.13 301	85.30 329	92.46 323	95.64 311	89.33 294	94.21 301	92.74 353	89.60 256	98.24 347	81.68 361	94.66 358	94.66 363

Anonymous20240521		97.07 121	97.51 98	95.76 231	99.35 51	88.18 281	97.78 73	98.40 188	97.11 84	98.34 96	99.04 48	89.58 257	99.79 44	98.09 27	99.93 10	99.30 109

UnsupCasMVSNet_bld		94.72 234	94.26 248	96.08 217	98.62 145	90.54 244	93.38 305	98.05 237	90.30 283	97.02 199	96.80 258	89.54 258	99.16 265	88.44 316	96.18 341	98.56 230

MG-MVS		94.08 262	94.00 257	94.32 299	97.09 302	85.89 323	93.19 310	95.96 305	92.52 251	94.93 288	97.51 205	89.54 258	98.77 306	87.52 330	97.71 303	98.31 256

UnsupCasMVSNet_eth		95.91 182	95.73 191	96.44 198	98.48 166	91.52 226	95.31 226	98.45 179	95.76 146	97.48 168	97.54 202	89.53 260	98.69 315	94.43 190	94.61 359	99.13 146

GBi-Net		96.99 125	96.80 138	97.56 119	97.96 220	93.67 170	98.23 46	98.66 156	95.59 155	97.99 136	99.19 32	89.51 261	99.73 81	94.60 185	99.44 145	99.30 109

test1		96.99 125	96.80 138	97.56 119	97.96 220	93.67 170	98.23 46	98.66 156	95.59 155	97.99 136	99.19 32	89.51 261	99.73 81	94.60 185	99.44 145	99.30 109

FMVSNet2		96.72 146	96.67 145	96.87 174	97.96 220	91.88 219	97.15 114	98.06 236	95.59 155	98.50 76	98.62 86	89.51 261	99.65 133	94.99 170	99.60 92	99.07 161

pmmvs4		94.82 228	94.19 252	96.70 184	97.42 283	92.75 197	92.09 331	96.76 291	86.80 324	95.73 268	97.22 229	89.28 264	98.89 296	93.28 230	99.14 205	98.46 241

cascas		91.89 307	91.35 304	93.51 315	94.27 363	85.60 325	88.86 369	98.61 163	79.32 368	92.16 350	91.44 367	89.22 265	98.12 351	90.80 274	97.47 317	96.82 333

DSMNet-mixed		92.19 301	91.83 298	93.25 320	96.18 327	83.68 350	96.27 161	93.68 334	76.97 375	92.54 347	99.18 35	89.20 266	98.55 329	83.88 355	98.60 266	97.51 310

c3_l		95.20 212	95.32 199	94.83 277	96.19 326	86.43 318	91.83 334	98.35 196	93.47 221	97.36 174	97.26 227	88.69 267	99.28 245	95.41 145	99.36 167	98.78 205

test_fmvs2		96.38 165	96.45 158	96.16 214	97.85 228	91.30 228	96.81 133	99.45 15	89.24 295	98.49 77	99.38 17	88.68 268	97.62 359	98.83 8	99.32 182	99.57 38

CANet_DTU		94.65 239	94.21 251	95.96 221	95.90 336	89.68 252	93.92 288	97.83 248	93.19 230	90.12 363	95.64 309	88.52 269	99.57 162	93.27 231	99.47 138	98.62 225

EPP-MVSNet		96.84 135	96.58 148	97.65 115	99.18 78	93.78 168	98.68 14	96.34 298	97.91 49	97.30 175	98.06 155	88.46 270	99.85 27	93.85 215	99.40 161	99.32 104

SixPastTwentyTwo		97.49 100	97.57 92	97.26 149	99.56 21	92.33 202	98.28 42	96.97 284	98.30 36	99.45 16	99.35 22	88.43 271	99.89 18	98.01 30	99.76 51	99.54 45

miper_ehance_all_eth		94.69 235	94.70 227	94.64 283	95.77 341	86.22 320	91.32 343	98.24 206	91.67 265	97.05 196	96.65 266	88.39 272	99.22 258	94.88 172	98.34 276	98.49 238

IS-MVSNet		96.93 130	96.68 144	97.70 111	99.25 61	94.00 159	98.57 20	96.74 293	98.36 32	98.14 120	97.98 164	88.23 273	99.71 101	93.10 235	99.72 62	99.38 95

jason		94.39 251	94.04 256	95.41 251	98.29 180	87.85 292	92.74 318	96.75 292	85.38 339	95.29 278	96.15 290	88.21 274	99.65 133	94.24 199	99.34 175	98.74 211
jason: jason.
IterMVS-SCA-FT		95.86 184	96.19 169	94.85 275	97.68 260	85.53 326	92.42 324	97.63 263	96.99 86	98.36 93	98.54 93	87.94 275	99.75 67	97.07 67	99.08 215	99.27 120

SCA		93.38 282	93.52 267	92.96 329	96.24 322	81.40 361	93.24 308	94.00 331	91.58 268	94.57 293	96.97 244	87.94 275	99.42 202	89.47 302	97.66 308	98.06 279

sss		94.22 254	93.72 263	95.74 232	97.71 258	89.95 249	93.84 290	96.98 283	88.38 307	93.75 315	95.74 305	87.94 275	98.89 296	91.02 267	98.10 286	98.37 247

IterMVS		95.42 203	95.83 187	94.20 303	97.52 273	83.78 349	92.41 325	97.47 268	95.49 160	98.06 130	98.49 97	87.94 275	99.58 156	96.02 102	99.02 222	99.23 127
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 260	93.41 269	96.18 213	99.16 79	90.04 247	92.15 328	98.68 151	79.90 366	96.22 245	97.83 178	87.92 279	99.42 202	89.18 306	99.65 78	99.08 159

VDDNet		96.98 128	96.84 135	97.41 140	99.40 46	93.26 185	97.94 65	95.31 320	99.26 7	98.39 89	99.18 35	87.85 280	99.62 144	95.13 162	99.09 214	99.35 103

pmmvs5		94.63 240	94.34 247	95.50 244	97.63 266	88.34 277	94.02 281	97.13 277	87.15 318	95.22 280	97.15 232	87.50 281	99.27 248	93.99 210	99.26 192	98.88 195

D2MVS		95.18 213	95.17 204	95.21 255	97.76 251	87.76 295	94.15 275	97.94 239	89.77 291	96.99 201	97.68 194	87.45 282	99.14 267	95.03 168	99.81 41	98.74 211

test_vis1_n_1920		95.77 187	96.41 160	93.85 307	98.55 154	84.86 338	95.91 189	99.71 2	92.72 248	97.67 158	98.90 63	87.44 283	98.73 310	97.96 31	98.85 240	97.96 288

PVSNet	86.72 19	91.10 315	90.97 312	91.49 344	97.56 271	78.04 369	87.17 371	94.60 326	84.65 347	92.34 348	92.20 359	87.37 284	98.47 334	85.17 348	97.69 305	97.96 288

Anonymous202405211		96.34 166	95.98 179	97.43 137	98.25 186	93.85 164	96.74 139	94.41 328	97.72 56	98.37 90	98.03 158	87.15 285	99.53 172	94.06 206	99.07 217	98.92 186

MVSFormer		96.14 173	96.36 163	95.49 245	97.68 260	87.81 293	98.67 15	99.02 65	96.50 106	94.48 297	96.15 290	86.90 286	99.92 5	98.73 12	99.13 207	98.74 211

lupinMVS		93.77 268	93.28 270	95.24 254	97.68 260	87.81 293	92.12 329	96.05 301	84.52 348	94.48 297	95.06 321	86.90 286	99.63 139	93.62 223	99.13 207	98.27 262

eth_miper_zixun_eth		94.89 225	94.93 214	94.75 281	95.99 334	86.12 321	91.35 340	98.49 176	93.40 222	97.12 187	97.25 228	86.87 288	99.35 228	95.08 165	98.82 244	98.78 205

test_vis1_n		95.67 191	95.89 185	95.03 264	98.18 196	89.89 250	96.94 126	99.28 23	88.25 309	98.20 111	98.92 59	86.69 289	97.19 362	97.70 45	98.82 244	98.00 287

WTY-MVS		93.55 277	93.00 277	95.19 256	97.81 237	87.86 290	93.89 289	96.00 303	89.02 298	94.07 306	95.44 316	86.27 290	99.33 232	87.69 325	96.82 329	98.39 245

CDS-MVSNet		94.88 226	94.12 254	97.14 155	97.64 265	93.57 175	93.96 287	97.06 281	90.05 287	96.30 241	96.55 270	86.10 291	99.47 189	90.10 293	99.31 185	98.40 243
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 259	93.42 268	96.23 209	98.59 149	90.85 235	94.24 269	98.85 108	85.49 335	92.97 335	94.94 323	86.01 292	99.64 136	91.78 254	97.92 292	98.20 268

dmvs_testset		87.30 344	86.99 344	88.24 359	96.71 312	77.48 372	94.68 255	86.81 377	92.64 250	89.61 366	87.01 378	85.91 293	93.12 379	61.04 382	88.49 375	94.13 366

miper_enhance_ethall		93.14 287	92.78 284	94.20 303	93.65 371	85.29 330	89.97 360	97.85 244	85.05 341	96.15 251	94.56 330	85.74 294	99.14 267	93.74 218	98.34 276	98.17 271

new_pmnet		92.34 298	91.69 301	94.32 299	96.23 324	89.16 262	92.27 327	92.88 343	84.39 351	95.29 278	96.35 283	85.66 295	96.74 371	84.53 352	97.56 311	97.05 321

alignmvs		96.01 179	95.52 198	97.50 128	97.77 250	94.71 131	96.07 174	96.84 287	97.48 70	96.78 216	94.28 337	85.50 296	99.40 213	96.22 92	98.73 254	98.40 243

lessismore_v0				97.05 161	99.36 50	92.12 211		84.07 380		98.77 59	98.98 52	85.36 297	99.74 76	97.34 56	99.37 164	99.30 109

HY-MVS	91.43 15	92.58 294	91.81 299	94.90 272	96.49 317	88.87 267	97.31 105	94.62 325	85.92 331	90.50 360	96.84 253	85.05 298	99.40 213	83.77 357	95.78 347	96.43 344

EPNet		93.72 270	92.62 289	97.03 164	87.61 387	92.25 204	96.27 161	91.28 356	96.74 94	87.65 373	97.39 216	85.00 299	99.64 136	92.14 246	99.48 136	99.20 133
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 229	94.80 224	94.85 275	96.16 328	86.45 317	91.14 347	98.20 212	93.49 220	97.03 198	97.37 220	84.97 300	99.26 249	95.28 148	99.56 102	98.83 200

Test_1112_low_res		93.53 278	92.86 279	95.54 243	98.60 147	88.86 268	92.75 316	98.69 149	82.66 355	92.65 343	96.92 249	84.75 301	99.56 163	90.94 269	97.76 299	98.19 269

MVS-HIRNet		88.40 338	90.20 323	82.99 363	97.01 304	60.04 387	93.11 311	85.61 379	84.45 350	88.72 370	99.09 45	84.72 302	98.23 348	82.52 360	96.59 336	90.69 378

K. test v3		96.44 162	96.28 166	96.95 167	99.41 43	91.53 225	97.65 84	90.31 365	98.89 19	98.93 44	99.36 20	84.57 303	99.92 5	97.81 37	99.56 102	99.39 93

test_cas_vis1_n_1920		95.34 205	95.67 192	94.35 298	98.21 190	86.83 313	95.61 206	99.26 24	90.45 281	98.17 116	98.96 54	84.43 304	98.31 345	96.74 74	99.17 203	97.90 292

h-mvs33		96.29 167	95.63 195	98.26 70	98.50 163	96.11 73	96.90 128	97.09 279	96.58 101	97.21 180	98.19 136	84.14 305	99.78 47	95.89 111	96.17 342	98.89 191

hse-mvs2		95.77 187	95.09 207	97.79 105	97.84 233	95.51 97	95.66 200	95.43 319	96.58 101	97.21 180	96.16 289	84.14 305	99.54 170	95.89 111	96.92 325	98.32 254

DIV-MVS_self_test		94.73 230	94.64 230	95.01 265	95.86 337	87.00 309	91.33 341	98.08 231	93.34 224	97.10 189	97.34 222	84.02 307	99.31 236	95.15 159	99.55 108	98.72 214

cl____		94.73 230	94.64 230	95.01 265	95.85 338	87.00 309	91.33 341	98.08 231	93.34 224	97.10 189	97.33 223	84.01 308	99.30 239	95.14 160	99.56 102	98.71 217

Vis-MVSNet (Re-imp)		95.11 216	94.85 219	95.87 228	99.12 89	89.17 261	97.54 97	94.92 323	96.50 106	96.58 225	97.27 226	83.64 309	99.48 187	88.42 317	99.67 75	98.97 175

FA-MVS(test-final)		94.91 224	94.89 217	94.99 267	97.51 274	88.11 286	98.27 44	95.20 321	92.40 256	96.68 219	98.60 87	83.44 310	99.28 245	93.34 227	98.53 268	97.59 308

dmvs_re		92.08 304	91.27 306	94.51 292	97.16 299	92.79 196	95.65 202	92.64 348	94.11 205	92.74 340	90.98 372	83.41 311	94.44 378	80.72 364	94.07 362	96.29 346

PVSNet_0	81.89 21	84.49 347	83.21 350	88.34 358	95.76 342	74.97 381	83.49 375	92.70 347	78.47 371	87.94 372	86.90 379	83.38 312	96.63 372	73.44 376	66.86 383	93.40 370

test_fmvs1_n		95.21 211	95.28 200	94.99 267	98.15 203	89.13 264	96.81 133	99.43 17	86.97 322	97.21 180	98.92 59	83.00 313	97.13 363	98.09 27	98.94 229	98.72 214

CMPMVS	73.10 23	92.74 292	91.39 303	96.77 180	93.57 373	94.67 134	94.21 272	97.67 255	80.36 365	93.61 320	96.60 268	82.85 314	97.35 361	84.86 350	98.78 247	98.29 261
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs1		94.51 247	94.60 234	94.26 302	95.91 335	87.92 288	95.35 222	99.02 65	86.56 326	96.79 212	98.52 94	82.64 315	97.00 366	97.87 34	98.71 255	97.88 294

EU-MVSNet		94.25 253	94.47 242	93.60 313	98.14 205	82.60 354	97.24 110	92.72 346	85.08 340	98.48 79	98.94 57	82.59 316	98.76 308	97.47 53	99.53 115	99.44 85

baseline1		93.14 287	92.64 288	94.62 285	97.34 289	87.20 306	96.67 146	93.02 341	94.71 187	96.51 230	95.83 304	81.64 317	98.60 325	90.00 295	88.06 376	98.07 275

test1111		94.53 246	94.81 223	93.72 310	99.06 96	81.94 359	98.31 39	83.87 381	96.37 111	98.49 77	99.17 37	81.49 318	99.73 81	96.64 76	99.86 29	99.49 61

CVMVSNet		92.33 299	92.79 282	90.95 347	97.26 294	75.84 378	95.29 228	92.33 350	81.86 356	96.27 242	98.19 136	81.44 319	98.46 335	94.23 200	98.29 279	98.55 232

EPNet_dtu		91.39 313	90.75 316	93.31 318	90.48 384	82.61 353	94.80 250	92.88 343	93.39 223	81.74 381	94.90 326	81.36 320	99.11 273	88.28 319	98.87 237	98.21 267
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 252	94.48 241	94.05 306	98.95 107	83.10 351	98.31 39	82.48 382	96.20 119	98.23 109	99.16 38	81.18 321	99.66 131	95.95 107	99.83 37	99.38 95

test_yl		94.40 249	94.00 257	95.59 237	96.95 306	89.52 255	94.75 253	95.55 316	96.18 122	96.79 212	96.14 292	81.09 322	99.18 260	90.75 276	97.77 297	98.07 275

DCV-MVSNet		94.40 249	94.00 257	95.59 237	96.95 306	89.52 255	94.75 253	95.55 316	96.18 122	96.79 212	96.14 292	81.09 322	99.18 260	90.75 276	97.77 297	98.07 275

MIMVSNet		93.42 280	92.86 279	95.10 261	98.17 199	88.19 280	98.13 55	93.69 332	92.07 258	95.04 285	98.21 135	80.95 324	99.03 284	81.42 362	98.06 288	98.07 275

PAPM		87.64 343	85.84 349	93.04 325	96.54 315	84.99 336	88.42 370	95.57 315	79.52 367	83.82 378	93.05 349	80.57 325	98.41 337	62.29 381	92.79 366	95.71 353

HyFIR lowres test		93.72 270	92.65 287	96.91 172	98.93 110	91.81 222	91.23 345	98.52 173	82.69 354	96.46 232	96.52 274	80.38 326	99.90 14	90.36 290	98.79 246	99.03 166

FMVSNet3		95.26 210	94.94 212	96.22 211	96.53 316	90.06 246	95.99 180	97.66 257	94.11 205	97.99 136	97.91 172	80.22 327	99.63 139	94.60 185	99.44 145	98.96 176

RPMNet		94.68 237	94.60 234	94.90 272	95.44 349	88.15 282	96.18 168	98.86 104	97.43 71	94.10 304	98.49 97	79.40 328	99.76 61	95.69 120	95.81 344	96.81 334

LFMVS		95.32 207	94.88 218	96.62 187	98.03 211	91.47 227	97.65 84	90.72 362	99.11 9	97.89 147	98.31 114	79.20 329	99.48 187	93.91 214	99.12 210	98.93 183

ADS-MVSNet2		91.47 312	90.51 320	94.36 297	95.51 347	85.63 324	95.05 241	95.70 309	83.46 352	92.69 341	96.84 253	79.15 330	99.41 211	85.66 342	90.52 370	98.04 283

ADS-MVSNet		90.95 318	90.26 322	93.04 325	95.51 347	82.37 355	95.05 241	93.41 338	83.46 352	92.69 341	96.84 253	79.15 330	98.70 314	85.66 342	90.52 370	98.04 283

MDTV_nov1_ep13_2view						57.28 388	94.89 247		80.59 363	94.02 308		78.66 332		85.50 344		97.82 298

cl22		93.25 285	92.84 281	94.46 294	94.30 362	86.00 322	91.09 349	96.64 297	90.74 277	95.79 263	96.31 284	78.24 333	98.77 306	94.15 203	98.34 276	98.62 225

PatchmatchNet		91.98 306	91.87 297	92.30 340	94.60 359	79.71 366	95.12 234	93.59 337	89.52 292	93.61 320	97.02 241	77.94 334	99.18 260	90.84 272	94.57 361	98.01 286
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 335				98.06 279

CR-MVSNet		93.29 284	92.79 282	94.78 280	95.44 349	88.15 282	96.18 168	97.20 273	84.94 345	94.10 304	98.57 89	77.67 336	99.39 217	95.17 155	95.81 344	96.81 334

Patchmtry		95.03 221	94.59 236	96.33 205	94.83 356	90.82 236	96.38 155	97.20 273	96.59 100	97.49 166	98.57 89	77.67 336	99.38 220	92.95 238	99.62 83	98.80 203

tpmrst		90.31 321	90.61 319	89.41 354	94.06 367	72.37 384	95.06 240	93.69 332	88.01 311	92.32 349	96.86 251	77.45 338	98.82 301	91.04 266	87.01 377	97.04 322

sam_mvs												77.38 339

patchmatchnet-post											96.84 253	77.36 340	99.42 202

Patchmatch-RL test		94.66 238	94.49 240	95.19 256	98.54 156	88.91 266	92.57 320	98.74 138	91.46 269	98.32 100	97.75 187	77.31 341	98.81 303	96.06 97	99.61 89	97.85 296

tpmvs		90.79 319	90.87 313	90.57 350	92.75 379	76.30 376	95.79 193	93.64 336	91.04 275	91.91 352	96.26 285	77.19 342	98.86 300	89.38 304	89.85 373	96.56 341

test_post											10.87 385	76.83 343	99.07 278

Patchmatch-test		93.60 276	93.25 271	94.63 284	96.14 331	87.47 299	96.04 176	94.50 327	93.57 218	96.47 231	96.97 244	76.50 344	98.61 323	90.67 282	98.41 275	97.81 300

MDTV_nov1_ep13			91.28 305		94.31 361	73.51 382	94.80 250	93.16 340	86.75 325	93.45 326	97.40 212	76.37 345	98.55 329	88.85 310	96.43 337

EMVS		89.06 333	89.22 328	88.61 357	93.00 376	77.34 373	82.91 377	90.92 359	94.64 189	92.63 345	91.81 363	76.30 346	97.02 365	83.83 356	96.90 327	91.48 376

test_post1							94.98 245				10.37 386	76.21 347	99.04 281	89.47 302

GA-MVS		92.83 291	92.15 295	94.87 274	96.97 305	87.27 305	90.03 359	96.12 300	91.83 264	94.05 307	94.57 329	76.01 348	98.97 293	92.46 244	97.34 321	98.36 252

PatchT		93.75 269	93.57 266	94.29 301	95.05 354	87.32 304	96.05 175	92.98 342	97.54 67	94.25 300	98.72 76	75.79 349	99.24 254	95.92 109	95.81 344	96.32 345

E-PMN		89.52 331	89.78 325	88.73 356	93.14 374	77.61 371	83.26 376	92.02 351	94.82 184	93.71 316	93.11 343	75.31 350	96.81 368	85.81 339	96.81 330	91.77 375

DeepMVS_CX				77.17 364	90.94 383	85.28 331		74.08 387	52.51 381	80.87 382	88.03 377	75.25 351	70.63 384	59.23 383	84.94 379	75.62 379

AUN-MVS		93.95 267	92.69 286	97.74 108	97.80 241	95.38 105	95.57 209	95.46 318	91.26 272	92.64 344	96.10 295	74.67 352	99.55 167	93.72 220	96.97 324	98.30 258

CHOSEN 280x420		89.98 325	89.19 331	92.37 339	95.60 346	81.13 363	86.22 373	97.09 279	81.44 360	87.44 374	93.15 342	73.99 353	99.47 189	88.69 313	99.07 217	96.52 342

thres200		91.00 317	90.42 321	92.77 332	97.47 280	83.98 348	94.01 282	91.18 358	95.12 175	95.44 274	91.21 369	73.93 354	99.31 236	77.76 372	97.63 310	95.01 361

test-LLR		89.97 326	89.90 324	90.16 351	94.24 364	74.98 379	89.89 361	89.06 370	92.02 259	89.97 364	90.77 373	73.92 355	98.57 326	91.88 251	97.36 319	96.92 325

test0.0.03 1		90.11 322	89.21 329	92.83 331	93.89 369	86.87 312	91.74 335	88.74 372	92.02 259	94.71 291	91.14 370	73.92 355	94.48 377	83.75 358	92.94 365	97.16 319

tpm cat1		88.01 341	87.33 342	90.05 353	94.48 360	76.28 377	94.47 261	94.35 329	73.84 379	89.26 368	95.61 311	73.64 357	98.30 346	84.13 353	86.20 378	95.57 357

tfpn200view9		91.55 311	91.00 310	93.21 322	98.02 212	84.35 344	95.70 196	90.79 360	96.26 116	95.90 261	92.13 360	73.62 358	99.42 202	78.85 369	97.74 300	95.85 350

thres400		91.68 310	91.00 310	93.71 311	98.02 212	84.35 344	95.70 196	90.79 360	96.26 116	95.90 261	92.13 360	73.62 358	99.42 202	78.85 369	97.74 300	97.36 315

test_method		66.88 349	66.13 352	69.11 365	62.68 388	25.73 390	49.76 379	96.04 302	14.32 383	64.27 384	91.69 365	73.45 360	88.05 382	76.06 374	66.94 382	93.54 368

thres100view900		91.76 309	91.26 308	93.26 319	98.21 190	84.50 342	96.39 153	90.39 363	96.87 90	96.33 237	93.08 347	73.44 361	99.42 202	78.85 369	97.74 300	95.85 350

thres600view7		92.03 305	91.43 302	93.82 308	98.19 193	84.61 341	96.27 161	90.39 363	96.81 92	96.37 236	93.11 343	73.44 361	99.49 184	80.32 365	97.95 291	97.36 315

MVSTER		94.21 256	93.93 260	95.05 263	95.83 339	86.46 316	95.18 233	97.65 259	92.41 255	97.94 143	98.00 163	72.39 363	99.58 156	96.36 87	99.56 102	99.12 151

JIA-IIPM		91.79 308	90.69 317	95.11 259	93.80 370	90.98 233	94.16 274	91.78 354	96.38 110	90.30 362	99.30 26	72.02 364	98.90 295	88.28 319	90.17 372	95.45 358

tpm		91.08 316	90.85 314	91.75 343	95.33 352	78.09 368	95.03 243	91.27 357	88.75 302	93.53 323	97.40 212	71.24 365	99.30 239	91.25 263	93.87 363	97.87 295

baseline2		89.65 330	88.44 337	93.25 320	95.62 345	82.71 352	93.82 291	85.94 378	88.89 301	87.35 375	92.54 356	71.23 366	99.33 232	86.01 337	94.60 360	97.72 302

CostFormer		89.75 329	89.25 327	91.26 346	94.69 358	78.00 370	95.32 225	91.98 352	81.50 359	90.55 359	96.96 246	71.06 367	98.89 296	88.59 315	92.63 367	96.87 328

FPMVS		89.92 327	88.63 335	93.82 308	98.37 175	96.94 45	91.58 336	93.34 339	88.00 312	90.32 361	97.10 236	70.87 368	91.13 381	71.91 378	96.16 343	93.39 371

EPMVS		89.26 332	88.55 336	91.39 345	92.36 380	79.11 367	95.65 202	79.86 383	88.60 304	93.12 333	96.53 272	70.73 369	98.10 352	90.75 276	89.32 374	96.98 323

FE-MVS		92.95 289	92.22 293	95.11 259	97.21 297	88.33 278	98.54 23	93.66 335	89.91 289	96.21 246	98.14 140	70.33 370	99.50 180	87.79 323	98.24 281	97.51 310

tmp_tt		57.23 350	62.50 353	41.44 366	34.77 389	49.21 389	83.93 374	60.22 390	15.31 382	71.11 383	79.37 381	70.09 371	44.86 385	64.76 380	82.93 381	30.25 381

ET-MVSNet_ETH3D		91.12 314	89.67 326	95.47 246	96.41 319	89.15 263	91.54 337	90.23 366	89.07 297	86.78 377	92.84 351	69.39 372	99.44 199	94.16 202	96.61 335	97.82 298

dp		88.08 340	88.05 338	88.16 361	92.85 377	68.81 386	94.17 273	92.88 343	85.47 336	91.38 355	96.14 292	68.87 373	98.81 303	86.88 334	83.80 380	96.87 328

iter_conf_final		94.54 245	93.91 261	96.43 199	97.23 296	90.41 245	96.81 133	98.10 228	93.87 212	96.80 211	97.89 173	68.02 374	99.72 86	96.73 75	99.77 50	99.18 137

tpm2		88.47 337	87.69 341	90.79 348	94.98 355	77.34 373	95.09 236	91.83 353	77.51 374	89.40 367	96.41 278	67.83 375	98.73 310	83.58 359	92.60 368	96.29 346

pmmvs3		90.00 324	88.90 334	93.32 317	94.20 366	85.34 328	91.25 344	92.56 349	78.59 370	93.82 311	95.17 318	67.36 376	98.69 315	89.08 308	98.03 289	95.92 349

thisisatest0515		90.43 320	89.18 332	94.17 305	97.07 303	85.44 327	89.75 365	87.58 373	88.28 308	93.69 318	91.72 364	65.27 377	99.58 156	90.59 283	98.67 257	97.50 312

tttt0517		93.31 283	92.56 290	95.57 239	98.71 132	87.86 290	97.44 100	87.17 375	95.79 145	97.47 170	96.84 253	64.12 378	99.81 37	96.20 93	99.32 182	99.02 169

thisisatest0530		92.71 293	91.76 300	95.56 241	98.42 172	88.23 279	96.03 177	87.35 374	94.04 208	96.56 227	95.47 314	64.03 379	99.77 56	94.78 179	99.11 211	98.68 221

iter_conf05		93.65 274	93.05 273	95.46 247	96.13 332	87.45 300	95.95 186	98.22 208	92.66 249	97.04 197	97.89 173	63.52 380	99.72 86	96.19 94	99.82 40	99.21 129

FMVSNet5		93.39 281	92.35 291	96.50 195	95.83 339	90.81 238	97.31 105	98.27 202	92.74 247	96.27 242	98.28 123	62.23 381	99.67 125	90.86 271	99.36 167	99.03 166

IB-MVS	85.98 20	88.63 336	86.95 346	93.68 312	95.12 353	84.82 340	90.85 351	90.17 367	87.55 315	88.48 371	91.34 368	58.01 382	99.59 154	87.24 333	93.80 364	96.63 340
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
gg-mvs-nofinetune		88.28 339	86.96 345	92.23 341	92.84 378	84.44 343	98.19 52	74.60 385	99.08 10	87.01 376	99.47 10	56.93 383	98.23 348	78.91 368	95.61 350	94.01 367

KD-MVS_2432*1600		88.93 334	87.74 339	92.49 335	88.04 385	81.99 357	89.63 366	95.62 312	91.35 270	95.06 282	93.11 343	56.58 384	98.63 321	85.19 346	95.07 353	96.85 330

miper_refine_blended		88.93 334	87.74 339	92.49 335	88.04 385	81.99 357	89.63 366	95.62 312	91.35 270	95.06 282	93.11 343	56.58 384	98.63 321	85.19 346	95.07 353	96.85 330

GG-mvs-BLEND				90.60 349	91.00 382	84.21 346	98.23 46	72.63 388		82.76 379	84.11 380	56.14 386	96.79 369	72.20 377	92.09 369	90.78 377

TESTMET0.1,1		87.20 345	86.57 347	89.07 355	93.62 372	72.84 383	89.89 361	87.01 376	85.46 337	89.12 369	90.20 375	56.00 387	97.72 358	90.91 270	96.92 325	96.64 338

test2506		89.86 328	89.16 333	91.97 342	98.95 107	76.83 375	98.54 23	61.07 389	96.20 119	97.07 195	99.16 38	55.19 388	99.69 115	96.43 85	99.83 37	99.38 95

test-mter		87.92 342	87.17 343	90.16 351	94.24 364	74.98 379	89.89 361	89.06 370	86.44 327	89.97 364	90.77 373	54.96 389	98.57 326	91.88 251	97.36 319	96.92 325

test123		12.59 352	15.49 355	3.87 367	6.07 390	2.55 391	90.75 353	2.59 392	2.52 385	5.20 387	13.02 384	4.96 390	1.85 387	5.20 384	9.09 384	7.23 382

testmvs		12.33 353	15.23 356	3.64 368	5.77 391	2.23 392	88.99 368	3.62 391	2.30 386	5.29 386	13.09 383	4.52 391	1.95 386	5.16 385	8.32 385	6.75 383

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

ab-mvs-re		7.91 355	10.55 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	94.94 323	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

FOURS1					99.59 18	98.20 7	99.03 7	99.25 25	98.96 18	98.87 48

MSC_two_6792asdad				98.22 75	97.75 253	95.34 110		98.16 222					99.75 67	95.87 113	99.51 125	99.57 38

No_MVS				98.22 75	97.75 253	95.34 110		98.16 222					99.75 67	95.87 113	99.51 125	99.57 38

eth-test2					0.00 392

eth-test					0.00 392

IU-MVS					99.22 67	95.40 103		98.14 225	85.77 334	98.36 93				95.23 152	99.51 125	99.49 61

save fliter					98.48 166	94.71 131	94.53 260	98.41 186	95.02 179

test_0728_SECOND				98.25 73	99.23 64	95.49 101	96.74 139	98.89 93					99.75 67	95.48 135	99.52 120	99.53 48

GSMVS																98.06 279

test_part2					99.03 102	96.07 74				98.08 127

MTGPA								98.73 139

MTMP							96.55 147	74.60 385

gm-plane-assit					91.79 381	71.40 385			81.67 357		90.11 376		98.99 287	84.86 350

test9_res														91.29 260	98.89 236	99.00 170

agg_prior2														90.34 291	98.90 233	99.10 158

agg_prior					97.80 241	94.96 126		98.36 193		93.49 324			99.53 172

test_prior4						95.38 105	93.61 299

test_prior				97.46 134	97.79 246	94.26 152		98.42 185					99.34 230			98.79 204

旧先验2							93.35 306		77.95 373	95.77 267			98.67 319	90.74 279

新几何2							93.43 302

无先验							93.20 309	97.91 240	80.78 362				99.40 213	87.71 324		97.94 290

原ACMM2							92.82 314

testdata2													99.46 192	87.84 322

testdata1							92.77 315		93.78 214

plane_prior7					98.70 134	94.67 134

plane_prior5								98.75 136					99.46 192	92.59 241	99.20 198	99.28 116

plane_prior4											96.77 259

plane_prior3						94.51 138			95.29 168	96.16 249

plane_prior2							96.50 149		96.36 112

plane_prior1					98.49 164

plane_prior						94.29 147	95.42 214		94.31 200						98.93 231

n2								0.00 393

nn								0.00 393

door-mid								98.17 218

test11								98.08 231

door								97.81 249

HQP5-MVS						92.47 200

HQP-NCC					97.85 228		94.26 265		93.18 231	92.86 337

ACMP_Plane					97.85 228		94.26 265		93.18 231	92.86 337

BP-MVS														90.51 286

HQP4-MVS										92.87 336			99.23 256			99.06 163

HQP3-MVS								98.43 182							98.74 251

NP-MVS					98.14 205	93.72 169					95.08 319

ACMMP++_ref															99.52 120

ACMMP++															99.55 108

High-resolution multi-view benchmark