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 19	99.01 16	99.63 9	99.66 3	99.27 2	99.68 119	97.75 38	99.89 24	99.62 28

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 42	99.77 5	96.34 65	99.18 5	99.20 26	99.67 2	99.73 3	99.65 5	99.15 3	99.86 24	97.22 55	99.92 13	99.77 11

XVG-OURS-SEG-HR		97.38 104	97.07 118	98.30 68	99.01 101	97.41 34	94.66 249	99.02 62	95.20 165	98.15 114	97.52 199	98.83 4	98.43 332	94.87 168	96.41 333	99.07 158

ACMH	93.61 9	98.44 24	98.76 13	97.51 124	99.43 40	93.54 175	98.23 46	99.05 53	97.40 73	99.37 18	99.08 44	98.79 5	99.47 185	97.74 39	99.71 60	99.50 50
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 23	96.23 115	99.71 4	99.48 9	98.77 6	99.93 3	98.89 4	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 10	99.02 15	99.62 10	99.36 18	98.53 7	99.52 170	98.58 16	99.95 5	99.66 23
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	93.39 180	98.20 51	98.87 98	98.23 36	99.48 12	99.27 25	98.47 8	99.55 162	96.52 77	99.53 110	99.60 30

pm-mvs1		98.47 23	98.67 17	97.86 101	99.52 30	94.58 136	98.28 42	99.00 71	97.57 62	99.27 24	99.22 28	98.32 9	99.50 175	97.09 62	99.75 51	99.50 50

jajsoiax		98.77 9	98.79 12	98.74 34	99.66 13	96.48 60	98.45 31	99.12 39	95.83 141	99.67 6	99.37 16	98.25 10	99.92 5	98.77 7	99.94 8	99.82 6

ACMH+	93.58 10	98.23 33	98.31 31	97.98 94	99.39 45	95.22 118	97.55 91	99.20 26	98.21 37	99.25 26	98.51 90	98.21 11	99.40 209	94.79 172	99.72 57	99.32 101

HPM-MVS_fast		98.32 28	98.13 34	98.88 23	99.54 26	97.48 30	98.35 35	99.03 60	95.88 137	97.88 143	98.22 128	98.15 12	99.74 75	96.50 78	99.62 78	99.42 84

wuyk23d		93.25 280	95.20 196	87.40 355	96.07 326	95.38 105	97.04 121	94.97 318	95.33 160	99.70 5	98.11 140	98.14 13	91.94 373	77.76 366	99.68 68	74.89 373

ACMM	93.33 11	98.05 43	97.79 61	98.85 24	99.15 79	97.55 26	96.68 144	98.83 114	95.21 164	98.36 89	98.13 136	98.13 14	99.62 142	96.04 96	99.54 106	99.39 90
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 40	97.83 59	98.92 21	99.42 42	97.46 31	98.57 20	99.05 53	95.43 158	97.41 168	97.50 201	97.98 15	99.79 43	95.58 126	99.57 94	99.50 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 170	96.50 153	94.80 274	99.26 56	87.69 291	95.96 180	98.58 165	95.08 171	98.02 130	96.25 281	97.92 16	97.60 355	88.68 309	98.74 246	99.11 151

LPG-MVS_test		97.94 55	97.67 73	98.74 34	99.15 79	97.02 42	97.09 118	99.02 62	95.15 168	98.34 92	98.23 125	97.91 17	99.70 107	94.41 187	99.73 53	99.50 50

LGP-MVS_train				98.74 34	99.15 79	97.02 42		99.02 62	95.15 168	98.34 92	98.23 125	97.91 17	99.70 107	94.41 187	99.73 53	99.50 50

SED-MVS		97.94 55	97.90 50	98.07 86	99.22 65	95.35 108	96.79 135	98.83 114	96.11 121	99.08 34	98.24 123	97.87 19	99.72 85	95.44 135	99.51 120	99.14 141

test_241102_ONE					99.22 65	95.35 108		98.83 114	96.04 126	99.08 34	98.13 136	97.87 19	99.33 228

testf1		98.57 17	98.45 26	98.93 18	99.79 3	98.78 2	97.69 80	99.42 16	97.69 58	98.92 43	98.77 68	97.80 21	99.25 247	96.27 86	99.69 64	98.76 206

APD_test2		98.57 17	98.45 26	98.93 18	99.79 3	98.78 2	97.69 80	99.42 16	97.69 58	98.92 43	98.77 68	97.80 21	99.25 247	96.27 86	99.69 64	98.76 206

SD-MVS		97.37 106	97.70 68	96.35 200	98.14 200	95.13 122	96.54 147	98.92 87	95.94 133	99.19 29	98.08 142	97.74 23	95.06 369	95.24 147	99.54 106	98.87 194
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 74	97.70 68	98.16 79	98.78 120	95.72 86	96.23 163	99.02 62	93.92 206	98.62 61	98.99 48	97.69 24	99.62 142	96.18 91	99.87 26	99.15 138
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 65	95.66 91	97.90 67	99.08 47	98.31 32	99.02 37	98.74 71	97.68 25	99.61 148	97.77 37	99.85 30	99.70 21

ANet_high		98.31 29	98.94 6	96.41 199	99.33 51	89.64 248	97.92 66	99.56 11	99.27 6	99.66 8	99.50 8	97.67 26	99.83 33	97.55 46	99.98 2	99.77 11

casdiffmvs_mvg		97.83 71	98.11 35	97.00 162	98.57 147	92.10 209	95.97 178	99.18 29	97.67 61	99.00 39	98.48 94	97.64 27	99.50 175	96.96 67	99.54 106	99.40 87
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		97.23 113	97.21 111	97.30 144	97.65 258	94.39 142	97.84 70	99.05 53	97.42 69	96.68 214	93.85 335	97.63 28	99.33 228	96.29 85	98.47 267	98.18 266

GeoE		97.75 79	97.70 68	97.89 99	98.88 111	94.53 137	97.10 117	98.98 77	95.75 145	97.62 154	97.59 194	97.61 29	99.77 55	96.34 84	99.44 140	99.36 98

TranMVSNet+NR-MVSNet		98.33 27	98.30 33	98.43 57	99.07 93	95.87 81	96.73 142	99.05 53	98.67 23	98.84 49	98.45 95	97.58 30	99.88 20	96.45 80	99.86 27	99.54 44

cdsmvs_eth3d_5k		24.22 344	32.30 347	0.00 362	0.00 385	0.00 386	0.00 373	98.10 223	0.00 380	0.00 381	95.06 316	97.54 31	0.00 381	0.00 379	0.00 379	0.00 377

ACMP	92.54 13	97.47 98	97.10 115	98.55 49	99.04 99	96.70 51	96.24 162	98.89 90	93.71 211	97.97 135	97.75 181	97.44 32	99.63 137	93.22 228	99.70 63	99.32 101
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 62	96.50 103	99.32 21	99.44 13	97.43 33	99.92 5	98.73 9	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 14	98.85 20	99.00 39	99.20 29	97.42 34	99.59 150	97.21 56	99.76 46	99.40 87

anonymousdsp		98.72 14	98.63 19	98.99 10	99.62 16	97.29 37	98.65 19	99.19 28	95.62 149	99.35 20	99.37 16	97.38 35	99.90 14	98.59 15	99.91 16	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 38	99.22 8	99.22 28	98.96 51	97.35 36	99.92 5	97.79 36	99.93 10	99.79 9

COLMAP_ROB	94.48 6	98.25 32	98.11 35	98.64 43	99.21 72	97.35 35	97.96 63	99.16 31	98.34 31	98.78 53	98.52 88	97.32 37	99.45 192	94.08 201	99.67 70	99.13 143
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 83	97.79 61	97.40 139	99.06 94	93.52 176	95.96 180	98.97 80	94.55 190	98.82 50	98.76 70	97.31 38	99.29 239	97.20 58	99.44 140	99.38 92

XXY-MVS		97.54 93	97.70 68	97.07 156	99.46 37	92.21 202	97.22 110	99.00 71	94.93 178	98.58 66	98.92 55	97.31 38	99.41 207	94.44 185	99.43 148	99.59 31

PEN-MVS		98.75 10	98.85 10	98.44 55	99.58 19	95.67 90	98.45 31	99.15 35	99.33 5	99.30 22	99.00 47	97.27 40	99.92 5	97.64 44	99.92 13	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 41	99.36 4	99.29 23	99.06 45	97.27 40	99.93 3	97.71 40	99.91 16	99.70 21

ZNCC-MVS		97.92 59	97.62 82	98.83 25	99.32 53	97.24 39	97.45 98	98.84 108	95.76 143	96.93 201	97.43 205	97.26 42	99.79 43	96.06 93	99.53 110	99.45 73

MP-MVS-pluss		97.69 83	97.36 102	98.70 38	99.50 34	96.84 47	95.38 213	98.99 74	92.45 248	98.11 117	98.31 108	97.25 43	99.77 55	96.60 74	99.62 78	99.48 64
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 65	97.63 80	98.67 40	99.35 49	96.84 47	96.36 154	98.79 124	95.07 172	97.88 143	98.35 104	97.24 44	99.72 85	96.05 95	99.58 91	99.45 73

Effi-MVS+		96.19 166	96.01 171	96.71 179	97.43 276	92.19 205	96.12 168	99.10 41	95.45 156	93.33 324	94.71 323	97.23 45	99.56 159	93.21 229	97.54 307	98.37 243

tt0805		97.44 100	97.56 89	97.11 153	99.55 23	96.36 63	98.66 18	95.66 306	98.31 32	97.09 189	95.45 310	97.17 46	98.50 329	98.67 12	97.45 313	96.48 338

PGM-MVS		97.88 66	97.52 93	98.96 13	99.20 73	97.62 21	97.09 118	99.06 51	95.45 156	97.55 156	97.94 162	97.11 47	99.78 46	94.77 175	99.46 136	99.48 64

test_0728_THIRD									96.62 93	98.40 83	98.28 117	97.10 48	99.71 100	95.70 114	99.62 78	99.58 32

APD-MVS_3200maxsize		98.13 39	97.90 50	98.79 29	98.79 118	97.31 36	97.55 91	98.92 87	97.72 54	98.25 103	98.13 136	97.10 48	99.75 66	95.44 135	99.24 192	99.32 101

OPM-MVS		97.54 93	97.25 108	98.41 59	99.11 88	96.61 56	95.24 224	98.46 174	94.58 189	98.10 119	98.07 144	97.09 50	99.39 213	95.16 153	99.44 140	99.21 126
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 55	97.64 78	98.83 25	99.15 79	97.50 29	97.59 88	98.84 108	96.05 124	97.49 161	97.54 197	97.07 51	99.70 107	95.61 123	99.46 136	99.30 106

DVP-MVS		97.78 77	97.65 75	98.16 79	99.24 60	95.51 97	96.74 138	98.23 202	95.92 134	98.40 83	98.28 117	97.06 52	99.71 100	95.48 131	99.52 115	99.26 118
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 60	95.51 97	96.89 128	98.89 90	95.92 134	98.64 60	98.31 108	97.06 52

casdiffmvs		97.50 95	97.81 60	96.56 189	98.51 156	91.04 227	95.83 188	99.09 46	97.23 79	98.33 95	98.30 112	97.03 54	99.37 219	96.58 76	99.38 158	99.28 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SteuartSystems-ACMMP		98.02 45	97.76 66	98.79 29	99.43 40	97.21 41	97.15 113	98.90 89	96.58 98	98.08 122	97.87 170	97.02 55	99.76 60	95.25 146	99.59 89	99.40 87
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 310	98.37 86	97.44 204	97.00 56	96.78 365	92.01 242	99.25 189	99.21 126

DROMVSNet		97.90 64	97.94 49	97.79 105	98.66 134	95.14 121	98.31 39	99.66 6	97.57 62	95.95 251	97.01 238	96.99 57	99.82 35	97.66 43	99.64 75	98.39 241

DVP-MVS++		97.96 47	97.90 50	98.12 84	97.75 247	95.40 103	99.03 7	98.89 90	96.62 93	98.62 61	98.30 112	96.97 58	99.75 66	95.70 114	99.25 189	99.21 126

OPU-MVS				97.64 116	98.01 209	95.27 113	96.79 135				97.35 216	96.97 58	98.51 328	91.21 259	99.25 189	99.14 141

RE-MVS-def			97.88 54		98.81 115	98.05 9	97.55 91	98.86 101	97.77 49	98.20 107	98.07 144	96.94 60		95.49 128	99.20 194	99.26 118

APDe-MVS		98.14 36	98.03 43	98.47 54	98.72 125	96.04 75	98.07 58	99.10 41	95.96 131	98.59 65	98.69 75	96.94 60	99.81 37	96.64 72	99.58 91	99.57 37

test_one_0601					99.05 98	95.50 100		98.87 98	97.21 80	98.03 129	98.30 112	96.93 62

GST-MVS		97.82 74	97.49 97	98.81 27	99.23 62	97.25 38	97.16 112	98.79 124	95.96 131	97.53 157	97.40 207	96.93 62	99.77 55	95.04 162	99.35 167	99.42 84

test_241102_TWO								98.83 114	96.11 121	98.62 61	98.24 123	96.92 64	99.72 85	95.44 135	99.49 127	99.49 58

LCM-MVSNet-Re		97.33 109	97.33 104	97.32 143	98.13 203	93.79 166	96.99 124	99.65 7	96.74 91	99.47 13	98.93 54	96.91 65	99.84 30	90.11 287	99.06 215	98.32 250

VPA-MVSNet		98.27 30	98.46 24	97.70 111	99.06 94	93.80 165	97.76 75	99.00 71	98.40 29	99.07 36	98.98 49	96.89 66	99.75 66	97.19 59	99.79 40	99.55 43

ACMMP		98.05 43	97.75 67	98.93 18	99.23 62	97.60 22	98.09 57	98.96 81	95.75 145	97.91 140	98.06 149	96.89 66	99.76 60	95.32 143	99.57 94	99.43 83
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 44	98.32 65	98.45 165	96.69 52	98.52 26	99.69 3	98.07 42	96.07 247	97.19 226	96.88 68	99.86 24	97.50 48	99.73 53	98.41 238

PMVS	89.60 17	96.71 144	96.97 123	95.95 219	99.51 31	97.81 16	97.42 102	97.49 261	97.93 46	95.95 251	98.58 82	96.88 68	96.91 362	89.59 295	99.36 162	93.12 365
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 59	97.59 86	98.92 21	99.22 65	97.55 26	97.60 86	98.84 108	96.00 129	97.22 173	97.62 192	96.87 70	99.76 60	95.48 131	99.43 148	99.46 69

CP-MVS		97.92 59	97.56 89	98.99 10	98.99 102	97.82 15	97.93 65	98.96 81	96.11 121	96.89 204	97.45 203	96.85 71	99.78 46	95.19 149	99.63 77	99.38 92

DPE-MVS		97.64 86	97.35 103	98.50 51	98.85 113	96.18 69	95.21 226	98.99 74	95.84 140	98.78 53	98.08 142	96.84 72	99.81 37	93.98 207	99.57 94	99.52 48
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 70	97.97 46	97.47 132	99.19 75	94.07 156	96.71 143	98.73 136	98.66 24	98.56 67	98.41 98	96.84 72	99.69 114	94.82 170	99.81 36	98.64 218

CS-MVS-test		97.91 62	97.84 56	98.14 82	98.52 154	96.03 77	98.38 34	99.67 4	98.11 40	95.50 268	96.92 244	96.81 74	99.87 22	96.87 70	99.76 46	98.51 231

ACMMPR		97.95 51	97.62 82	98.94 15	99.20 73	97.56 25	97.59 88	98.83 114	96.05 124	97.46 166	97.63 191	96.77 75	99.76 60	95.61 123	99.46 136	99.49 58

Vis-MVSNet		98.27 30	98.34 30	98.07 86	99.33 51	95.21 120	98.04 60	99.46 12	97.32 76	97.82 150	99.11 40	96.75 76	99.86 24	97.84 33	99.36 162	99.15 138
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 193	95.07 202	96.75 177	97.67 257	92.82 190	94.22 264	98.60 161	91.61 260	93.42 322	92.90 345	96.73 77	99.70 107	92.60 235	97.89 290	97.74 296

baseline		97.44 100	97.78 65	96.43 195	98.52 154	90.75 234	96.84 129	99.03 60	96.51 102	97.86 147	98.02 153	96.67 78	99.36 221	97.09 62	99.47 133	99.19 131

SR-MVS		98.00 46	97.66 74	99.01 8	98.77 121	97.93 11	97.38 103	98.83 114	97.32 76	98.06 125	97.85 171	96.65 79	99.77 55	95.00 165	99.11 206	99.32 101

tfpnnormal		97.72 81	97.97 46	96.94 164	99.26 56	92.23 201	97.83 71	98.45 175	98.25 35	99.13 33	98.66 77	96.65 79	99.69 114	93.92 209	99.62 78	98.91 184

DeepPCF-MVS	94.58 5	96.90 129	96.43 155	98.31 67	97.48 270	97.23 40	92.56 314	98.60 161	92.84 241	98.54 68	97.40 207	96.64 81	98.78 301	94.40 189	99.41 155	98.93 180

MVS_111021_LR		96.82 135	96.55 147	97.62 117	98.27 180	95.34 110	93.81 286	98.33 193	94.59 188	96.56 222	96.63 262	96.61 82	98.73 306	94.80 171	99.34 170	98.78 202

Gipuma		98.07 42	98.31 31	97.36 141	99.76 7	96.28 68	98.51 27	99.10 41	98.76 22	96.79 207	99.34 22	96.61 82	98.82 297	96.38 82	99.50 124	96.98 318
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 56	99.02 6	98.81 115	98.05 9	97.55 91	98.86 101	97.77 49	98.20 107	98.07 144	96.60 84	99.76 60	95.49 128	99.20 194	99.26 118

MVS_111021_HR		96.73 141	96.54 149	97.27 145	98.35 173	93.66 172	93.42 296	98.36 189	94.74 181	96.58 220	96.76 256	96.54 85	98.99 283	94.87 168	99.27 187	99.15 138

SMA-MVS		97.48 97	97.11 114	98.60 45	98.83 114	96.67 53	96.74 138	98.73 136	91.61 260	98.48 75	98.36 103	96.53 86	99.68 119	95.17 151	99.54 106	99.45 73
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 37	99.08 10	99.42 15	99.23 27	96.53 86	99.91 13	99.27 2	99.93 10	99.73 18

mPP-MVS		97.91 62	97.53 92	99.04 4	99.22 65	97.87 14	97.74 78	98.78 128	96.04 126	97.10 184	97.73 184	96.53 86	99.78 46	95.16 153	99.50 124	99.46 69

XVS		97.96 47	97.63 80	98.94 15	99.15 79	97.66 19	97.77 73	98.83 114	97.42 69	96.32 233	97.64 190	96.49 89	99.72 85	95.66 119	99.37 159	99.45 73

X-MVStestdata		92.86 285	90.83 309	98.94 15	99.15 79	97.66 19	97.77 73	98.83 114	97.42 69	96.32 233	36.50 375	96.49 89	99.72 85	95.66 119	99.37 159	99.45 73

9.14			96.69 139		98.53 153		96.02 174	98.98 77	93.23 223	97.18 178	97.46 202	96.47 91	99.62 142	92.99 232	99.32 178

UA-Net		98.88 7	98.76 13	99.22 2	99.11 88	97.89 13	99.47 3	99.32 18	99.08 10	97.87 146	99.67 2	96.47 91	99.92 5	97.88 30	99.98 2	99.85 3

SF-MVS		97.60 89	97.39 100	98.22 75	98.93 107	95.69 88	97.05 120	99.10 41	95.32 161	97.83 149	97.88 169	96.44 93	99.72 85	94.59 183	99.39 157	99.25 122

xiu_mvs_v1_base_debu		95.62 188	95.96 175	94.60 282	98.01 209	88.42 269	93.99 276	98.21 204	92.98 235	95.91 253	94.53 326	96.39 94	99.72 85	95.43 138	98.19 277	95.64 348

xiu_mvs_v1_base		95.62 188	95.96 175	94.60 282	98.01 209	88.42 269	93.99 276	98.21 204	92.98 235	95.91 253	94.53 326	96.39 94	99.72 85	95.43 138	98.19 277	95.64 348

xiu_mvs_v1_base_debi		95.62 188	95.96 175	94.60 282	98.01 209	88.42 269	93.99 276	98.21 204	92.98 235	95.91 253	94.53 326	96.39 94	99.72 85	95.43 138	98.19 277	95.64 348

ETV-MVS		96.13 169	95.90 179	96.82 173	97.76 245	93.89 161	95.40 211	98.95 83	95.87 138	95.58 267	91.00 366	96.36 97	99.72 85	93.36 222	98.83 238	96.85 325

MP-MVS		97.64 86	97.18 112	99.00 9	99.32 53	97.77 17	97.49 97	98.73 136	96.27 112	95.59 266	97.75 181	96.30 98	99.78 46	93.70 217	99.48 131	99.45 73
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 175	96.34 159	94.96 265	97.90 220	87.91 284	94.13 271	98.49 172	94.41 192	98.16 112	97.76 178	96.29 99	98.68 314	90.52 280	99.42 151	98.30 254

Fast-Effi-MVS+-dtu		96.44 157	96.12 166	97.39 140	97.18 292	94.39 142	95.46 205	98.73 136	96.03 128	94.72 284	94.92 320	96.28 100	99.69 114	93.81 212	97.98 285	98.09 268

APD_test1		97.95 51	97.68 72	98.75 31	99.60 17	98.60 5	97.21 111	99.08 47	96.57 101	98.07 124	98.38 102	96.22 101	99.14 263	94.71 178	99.31 181	98.52 230

OMC-MVS		96.48 155	96.00 172	97.91 97	98.30 175	96.01 78	94.86 243	98.60 161	91.88 257	97.18 178	97.21 225	96.11 102	99.04 277	90.49 283	99.34 170	98.69 215

xiu_mvs_v2_base		94.22 249	94.63 227	92.99 322	97.32 286	84.84 333	92.12 322	97.84 241	91.96 255	94.17 296	93.43 336	96.07 103	99.71 100	91.27 256	97.48 310	94.42 358

CSCG		97.40 103	97.30 105	97.69 113	98.95 104	94.83 128	97.28 106	98.99 74	96.35 111	98.13 116	95.95 296	95.99 104	99.66 130	94.36 192	99.73 53	98.59 224

PHI-MVS		96.96 125	96.53 150	98.25 73	97.48 270	96.50 59	96.76 137	98.85 105	93.52 214	96.19 243	96.85 247	95.94 105	99.42 198	93.79 213	99.43 148	98.83 197

TSAR-MVS + MP.		97.42 102	97.23 110	98.00 93	99.38 46	95.00 125	97.63 85	98.20 207	93.00 234	98.16 112	98.06 149	95.89 106	99.72 85	95.67 118	99.10 208	99.28 113
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 91	97.28 107	98.49 52	99.16 77	96.90 46	96.39 151	98.98 77	95.05 173	98.06 125	98.02 153	95.86 107	99.56 159	94.37 190	99.64 75	99.00 167

AllTest		97.20 114	96.92 128	98.06 88	99.08 91	96.16 70	97.14 115	99.16 31	94.35 194	97.78 151	98.07 144	95.84 108	99.12 266	91.41 253	99.42 151	98.91 184

TestCases				98.06 88	99.08 91	96.16 70		99.16 31	94.35 194	97.78 151	98.07 144	95.84 108	99.12 266	91.41 253	99.42 151	98.91 184

APD-MVS		97.00 120	96.53 150	98.41 59	98.55 150	96.31 66	96.32 157	98.77 129	92.96 239	97.44 167	97.58 196	95.84 108	99.74 75	91.96 243	99.35 167	99.19 131
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 347	10.65 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	95.82 111	0.00 381	0.00 379	0.00 379	0.00 377

PS-MVSNAJss		98.53 21	98.63 19	98.21 78	99.68 11	94.82 129	98.10 56	99.21 24	96.91 86	99.75 2	99.45 12	95.82 111	99.92 5	98.80 6	99.96 4	99.89 1

PS-MVSNAJ		94.10 255	94.47 237	93.00 321	97.35 281	84.88 331	91.86 326	97.84 241	91.96 255	94.17 296	92.50 352	95.82 111	99.71 100	91.27 256	97.48 310	94.40 359

3Dnovator	96.53 2	97.61 88	97.64 78	97.50 127	97.74 250	93.65 173	98.49 28	98.88 96	96.86 88	97.11 183	98.55 86	95.82 111	99.73 80	95.94 104	99.42 151	99.13 143

MTAPA		98.14 36	97.84 56	99.06 3	99.44 39	97.90 12	97.25 107	98.73 136	97.69 58	97.90 141	97.96 159	95.81 115	99.82 35	96.13 92	99.61 84	99.45 73

DP-MVS		97.87 67	97.89 53	97.81 104	98.62 141	94.82 129	97.13 116	98.79 124	98.98 17	98.74 57	98.49 91	95.80 116	99.49 179	95.04 162	99.44 140	99.11 151

Anonymous20240529		97.96 47	98.04 42	97.71 110	98.69 132	94.28 150	97.86 69	98.31 197	98.79 21	99.23 27	98.86 63	95.76 117	99.61 148	95.49 128	99.36 162	99.23 124

LS3D		97.77 78	97.50 96	98.57 47	96.24 315	97.58 24	98.45 31	98.85 105	98.58 26	97.51 159	97.94 162	95.74 118	99.63 137	95.19 149	98.97 220	98.51 231

EIA-MVS		96.04 172	95.77 185	96.85 170	97.80 235	92.98 188	96.12 168	99.16 31	94.65 184	93.77 308	91.69 360	95.68 119	99.67 124	94.18 197	98.85 235	97.91 288

CNVR-MVS		96.92 127	96.55 147	98.03 92	98.00 213	95.54 95	94.87 242	98.17 213	94.60 186	96.38 230	97.05 234	95.67 120	99.36 221	95.12 159	99.08 210	99.19 131

CLD-MVS		95.47 196	95.07 202	96.69 181	98.27 180	92.53 196	91.36 332	98.67 151	91.22 267	95.78 260	94.12 333	95.65 121	98.98 285	90.81 268	99.72 57	98.57 225
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	98.79 118	94.37 144	98.84 11	99.15 35	99.37 3	99.67 6	99.43 14	95.61 122	99.72 85	98.12 22	99.86 27	99.73 18

EGC-MVSNET		83.08 341	77.93 344	98.53 50	99.57 20	97.55 26	98.33 38	98.57 166	4.71 377	10.38 378	98.90 59	95.60 123	99.50 175	95.69 116	99.61 84	98.55 228

ITE_SJBPF				97.85 102	98.64 135	96.66 54		98.51 171	95.63 148	97.22 173	97.30 220	95.52 124	98.55 325	90.97 263	98.90 228	98.34 249

DeepC-MVS_fast	94.34 7	96.74 139	96.51 152	97.44 135	97.69 253	94.15 154	96.02 174	98.43 178	93.17 229	97.30 170	97.38 213	95.48 125	99.28 241	93.74 214	99.34 170	98.88 192
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 30	99.05 13	99.17 30	98.79 65	95.47 126	99.89 18	97.95 29	99.91 16	99.75 16

FMVSNet1		97.95 51	98.08 37	97.56 119	99.14 86	93.67 169	98.23 46	98.66 153	97.41 72	99.00 39	99.19 30	95.47 126	99.73 80	95.83 111	99.76 46	99.30 106

MIMVSNet1		98.51 22	98.45 26	98.67 40	99.72 8	96.71 50	98.76 12	98.89 90	98.49 27	99.38 17	99.14 39	95.44 128	99.84 30	96.47 79	99.80 39	99.47 67

CP-MVSNet		98.42 25	98.46 24	98.30 68	99.46 37	95.22 118	98.27 44	98.84 108	99.05 13	99.01 38	98.65 79	95.37 129	99.90 14	97.57 45	99.91 16	99.77 11

segment_acmp												95.34 130

CDPH-MVS		95.45 198	94.65 224	97.84 103	98.28 178	94.96 126	93.73 288	98.33 193	85.03 335	95.44 269	96.60 263	95.31 131	99.44 195	90.01 289	99.13 202	99.11 151

3Dnovator+	96.13 3	97.73 80	97.59 86	98.15 81	98.11 204	95.60 92	98.04 60	98.70 145	98.13 39	96.93 201	98.45 95	95.30 132	99.62 142	95.64 121	98.96 221	99.24 123

MVS_Test		96.27 163	96.79 136	94.73 278	96.94 301	86.63 309	96.18 165	98.33 193	94.94 176	96.07 247	98.28 117	95.25 133	99.26 245	97.21 56	97.90 289	98.30 254

XVG-OURS		97.12 115	96.74 137	98.26 70	98.99 102	97.45 32	93.82 284	99.05 53	95.19 166	98.32 96	97.70 186	95.22 134	98.41 333	94.27 194	98.13 280	98.93 180

dcpmvs_2		97.12 115	97.99 45	94.51 288	99.11 88	84.00 341	97.75 76	99.65 7	97.38 74	99.14 32	98.42 97	95.16 135	99.96 2	95.52 127	99.78 43	99.58 32

MCST-MVS		96.24 164	95.80 183	97.56 119	98.75 122	94.13 155	94.66 249	98.17 213	90.17 279	96.21 241	96.10 290	95.14 136	99.43 197	94.13 200	98.85 235	99.13 143

EI-MVSNet-Vis-set		97.32 110	97.39 100	97.11 153	97.36 280	92.08 210	95.34 217	97.65 254	97.74 52	98.29 101	98.11 140	95.05 137	99.68 119	97.50 48	99.50 124	99.56 41

EI-MVSNet-UG-set		97.32 110	97.40 99	97.09 155	97.34 283	92.01 212	95.33 218	97.65 254	97.74 52	98.30 100	98.14 134	95.04 138	99.69 114	97.55 46	99.52 115	99.58 32

KD-MVS_self_test		97.86 69	98.07 38	97.25 147	99.22 65	92.81 191	97.55 91	98.94 84	97.10 82	98.85 47	98.88 61	95.03 139	99.67 124	97.39 52	99.65 73	99.26 118

ZD-MVS					98.43 167	95.94 79		98.56 167	90.72 272	96.66 216	97.07 232	95.02 140	99.74 75	91.08 260	98.93 226

DELS-MVS		96.17 167	96.23 162	95.99 215	97.55 266	90.04 242	92.38 319	98.52 169	94.13 199	96.55 224	97.06 233	94.99 141	99.58 152	95.62 122	99.28 185	98.37 243
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		96.59 149	96.93 126	95.55 238	98.88 111	87.12 302	94.47 254	99.30 19	94.12 200	96.65 218	98.41 98	94.98 142	99.87 22	95.81 113	99.78 43	99.66 23

ab-mvs		96.59 149	96.59 143	96.60 184	98.64 135	92.21 202	98.35 35	97.67 250	94.45 191	96.99 196	98.79 65	94.96 143	99.49 179	90.39 284	99.07 212	98.08 269

MSLP-MVS++		96.42 159	96.71 138	95.57 235	97.82 230	90.56 238	95.71 191	98.84 108	94.72 182	96.71 213	97.39 211	94.91 144	98.10 347	95.28 144	99.02 217	98.05 278

QAPM		95.88 178	95.57 191	96.80 174	97.90 220	91.84 216	98.18 53	98.73 136	88.41 298	96.42 228	98.13 136	94.73 145	99.75 66	88.72 307	98.94 224	98.81 199

RPSCF		97.87 67	97.51 94	98.95 14	99.15 79	98.43 6	97.56 90	99.06 51	96.19 118	98.48 75	98.70 74	94.72 146	99.24 250	94.37 190	99.33 176	99.17 135

DU-MVS		97.79 76	97.60 85	98.36 63	98.73 123	95.78 84	95.65 198	98.87 98	97.57 62	98.31 98	97.83 172	94.69 147	99.85 27	97.02 65	99.71 60	99.46 69

Baseline_NR-MVSNet		97.72 81	97.79 61	97.50 127	99.56 21	93.29 181	95.44 206	98.86 101	98.20 38	98.37 86	99.24 26	94.69 147	99.55 162	95.98 102	99.79 40	99.65 25

TEST9					97.84 227	95.23 115	93.62 290	98.39 185	86.81 316	93.78 306	95.99 292	94.68 149	99.52 170

UniMVSNet (Re)		97.83 71	97.65 75	98.35 64	98.80 117	95.86 83	95.92 184	99.04 59	97.51 66	98.22 106	97.81 176	94.68 149	99.78 46	97.14 60	99.75 51	99.41 86

UniMVSNet_NR-MVSNet		97.83 71	97.65 75	98.37 62	98.72 125	95.78 84	95.66 196	99.02 62	98.11 40	98.31 98	97.69 188	94.65 151	99.85 27	97.02 65	99.71 60	99.48 64

VPNet		97.26 112	97.49 97	96.59 185	99.47 36	90.58 236	96.27 158	98.53 168	97.77 49	98.46 78	98.41 98	94.59 152	99.68 119	94.61 179	99.29 184	99.52 48

train_agg		95.46 197	94.66 223	97.88 100	97.84 227	95.23 115	93.62 290	98.39 185	87.04 312	93.78 306	95.99 292	94.58 153	99.52 170	91.76 250	98.90 228	98.89 188

test_8					97.81 231	95.07 124	93.54 293	98.38 187	87.04 312	93.71 310	95.96 295	94.58 153	99.52 170

API-MVS		95.09 213	95.01 206	95.31 248	96.61 306	94.02 158	96.83 130	97.18 270	95.60 150	95.79 258	94.33 331	94.54 155	98.37 338	85.70 335	98.52 264	93.52 362

Test By Simon												94.51 156

MSDG		95.33 201	95.13 199	95.94 221	97.40 278	91.85 215	91.02 343	98.37 188	95.30 162	96.31 235	95.99 292	94.51 156	98.38 336	89.59 295	97.65 304	97.60 302

TSAR-MVS + GP.		96.47 156	96.12 166	97.49 130	97.74 250	95.23 115	94.15 268	96.90 281	93.26 222	98.04 128	96.70 258	94.41 158	98.89 292	94.77 175	99.14 200	98.37 243

NR-MVSNet		97.96 47	97.86 55	98.26 70	98.73 123	95.54 95	98.14 54	98.73 136	97.79 48	99.42 15	97.83 172	94.40 159	99.78 46	95.91 106	99.76 46	99.46 69

AdaColmap		95.11 211	94.62 228	96.58 186	97.33 285	94.45 141	94.92 240	98.08 226	93.15 230	93.98 304	95.53 308	94.34 160	99.10 271	85.69 336	98.61 259	96.20 342

FC-MVSNet-test		98.16 34	98.37 29	97.56 119	99.49 35	93.10 186	98.35 35	99.21 24	98.43 28	98.89 45	98.83 64	94.30 161	99.81 37	97.87 31	99.91 16	99.77 11

Effi-MVS+-dtu		96.81 136	96.09 168	98.99 10	96.90 303	98.69 4	96.42 150	98.09 225	95.86 139	95.15 275	95.54 307	94.26 162	99.81 37	94.06 202	98.51 266	98.47 235

ambc				96.56 189	98.23 185	91.68 219	97.88 68	98.13 221		98.42 81	98.56 85	94.22 163	99.04 277	94.05 204	99.35 167	98.95 174

test20.03		96.58 151	96.61 142	96.48 193	98.49 160	91.72 218	95.68 195	97.69 249	96.81 89	98.27 102	97.92 165	94.18 164	98.71 309	90.78 270	99.66 72	99.00 167

HPM-MVS++		96.99 121	96.38 157	98.81 27	98.64 135	97.59 23	95.97 178	98.20 207	95.51 154	95.06 276	96.53 267	94.10 165	99.70 107	94.29 193	99.15 199	99.13 143

test_vis3_rt		97.04 118	96.98 122	97.23 149	98.44 166	95.88 80	96.82 131	99.67 4	90.30 276	99.27 24	99.33 23	94.04 166	96.03 368	97.14 60	97.83 291	99.78 10

test_fmvs3		97.38 104	97.56 89	96.84 171	98.63 139	92.81 191	97.60 86	99.61 9	90.87 270	98.76 56	99.66 3	94.03 167	97.90 349	99.24 3	99.68 68	99.81 8

PM-MVS		97.36 108	97.10 115	98.14 82	98.91 109	96.77 49	96.20 164	98.63 159	93.82 208	98.54 68	98.33 106	93.98 168	99.05 276	95.99 101	99.45 139	98.61 223

mvsany_test3		96.21 165	95.93 178	97.05 157	97.40 278	94.33 146	95.76 190	94.20 326	89.10 289	99.36 19	99.60 6	93.97 169	97.85 350	95.40 142	98.63 257	98.99 170

OpenMVS	94.22 8	95.48 195	95.20 196	96.32 202	97.16 293	91.96 213	97.74 78	98.84 108	87.26 309	94.36 293	98.01 155	93.95 170	99.67 124	90.70 276	98.75 245	97.35 312

v8		97.60 89	98.06 40	96.23 205	98.71 128	89.44 252	97.43 101	98.82 122	97.29 78	98.74 57	99.10 41	93.86 171	99.68 119	98.61 14	99.94 8	99.56 41

diffmvs		96.04 172	96.23 162	95.46 243	97.35 281	88.03 282	93.42 296	99.08 47	94.09 202	96.66 216	96.93 242	93.85 172	99.29 239	96.01 100	98.67 252	99.06 160
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		96.52 153	95.99 173	98.10 85	97.81 231	95.68 89	95.00 238	98.20 207	95.39 159	95.40 271	96.36 277	93.81 173	99.45 192	93.55 220	98.42 269	99.17 135

TAPA-MVS	93.32 12	94.93 218	94.23 244	97.04 159	98.18 191	94.51 138	95.22 225	98.73 136	81.22 354	96.25 239	95.95 296	93.80 174	98.98 285	89.89 291	98.87 232	97.62 300
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 58	98.07 38	97.48 131	99.38 46	92.95 189	98.03 62	99.11 40	98.04 44	98.62 61	98.66 77	93.75 175	99.78 46	97.23 54	99.84 31	99.73 18

OurMVSNet-221017-0		98.61 16	98.61 23	98.63 44	99.77 5	96.35 64	99.17 6	99.05 53	98.05 43	99.61 11	99.52 7	93.72 176	99.88 20	98.72 11	99.88 25	99.65 25

test_prior2							93.33 300		94.21 197	94.02 302	96.25 281	93.64 177		91.90 245	98.96 221

mvsany_test1		93.47 274	93.03 270	94.79 275	94.05 361	92.12 206	90.82 345	90.01 363	85.02 336	97.26 172	98.28 117	93.57 178	97.03 359	92.51 238	95.75 344	95.23 354

旧先验1					97.80 235	93.87 162		97.75 246			97.04 235	93.57 178			98.68 251	98.72 211

v10		97.55 92	97.97 46	96.31 203	98.60 143	89.64 248	97.44 99	99.02 62	96.60 95	98.72 59	99.16 36	93.48 180	99.72 85	98.76 8	99.92 13	99.58 32

v148		96.58 151	96.97 123	95.42 245	98.63 139	87.57 292	95.09 230	97.90 236	95.91 136	98.24 104	97.96 159	93.42 181	99.39 213	96.04 96	99.52 115	99.29 112

V42		97.04 118	97.16 113	96.68 182	98.59 145	91.05 226	96.33 156	98.36 189	94.60 186	97.99 131	98.30 112	93.32 182	99.62 142	97.40 51	99.53 110	99.38 92

new-patchmatchnet		95.67 186	96.58 144	92.94 324	97.48 270	80.21 359	92.96 305	98.19 212	94.83 179	98.82 50	98.79 65	93.31 183	99.51 174	95.83 111	99.04 216	99.12 148

test12				97.46 133	97.61 261	94.07 156		97.78 245		93.57 316		93.31 183	99.42 198		98.78 242	98.89 188

UGNet		96.81 136	96.56 146	97.58 118	96.64 305	93.84 164	97.75 76	97.12 273	96.47 106	93.62 313	98.88 61	93.22 185	99.53 167	95.61 123	99.69 64	99.36 98
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		96.49 154	96.18 165	97.42 137	98.25 182	94.29 147	94.77 246	98.07 230	89.81 283	97.97 135	98.33 106	93.11 186	99.08 273	95.46 134	99.84 31	98.89 188

v1144		96.84 131	97.08 117	96.13 212	98.42 168	89.28 255	95.41 210	98.67 151	94.21 197	97.97 135	98.31 108	93.06 187	99.65 132	98.06 26	99.62 78	99.45 73

PVSNet_BlendedMVS		95.02 217	94.93 209	95.27 249	97.79 240	87.40 297	94.14 270	98.68 148	88.94 293	94.51 289	98.01 155	93.04 188	99.30 235	89.77 293	99.49 127	99.11 151

PVSNet_Blended		93.96 260	93.65 259	94.91 266	97.79 240	87.40 297	91.43 331	98.68 148	84.50 342	94.51 289	94.48 329	93.04 188	99.30 235	89.77 293	98.61 259	98.02 281

mvs_anonymous		95.36 200	96.07 170	93.21 316	96.29 313	81.56 354	94.60 251	97.66 252	93.30 221	96.95 200	98.91 58	93.03 190	99.38 216	96.60 74	97.30 318	98.69 215

v1192		96.83 134	97.06 119	96.15 211	98.28 178	89.29 254	95.36 214	98.77 129	93.73 210	98.11 117	98.34 105	93.02 191	99.67 124	98.35 20	99.58 91	99.50 50

F-COLMAP		95.30 203	94.38 241	98.05 91	98.64 135	96.04 75	95.61 201	98.66 153	89.00 292	93.22 325	96.40 275	92.90 192	99.35 224	87.45 326	97.53 308	98.77 205

WR-MVS		96.90 129	96.81 133	97.16 150	98.56 149	92.20 204	94.33 257	98.12 222	97.34 75	98.20 107	97.33 218	92.81 193	99.75 66	94.79 172	99.81 36	99.54 44

v1240		96.74 139	97.02 121	95.91 222	98.18 191	88.52 268	95.39 212	98.88 96	93.15 230	98.46 78	98.40 101	92.80 194	99.71 100	98.45 18	99.49 127	99.49 58

MVE	73.61 22	86.48 339	85.92 341	88.18 353	96.23 317	85.28 325	81.78 371	75.79 377	86.01 322	82.53 373	91.88 357	92.74 195	87.47 376	71.42 373	94.86 352	91.78 367
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 191	95.13 199	96.80 174	98.51 156	93.99 160	94.60 251	98.69 146	90.20 278	95.78 260	96.21 283	92.73 196	98.98 285	90.58 279	98.86 234	97.42 309

CANet		95.86 179	95.65 188	96.49 192	96.41 311	90.82 231	94.36 256	98.41 182	94.94 176	92.62 339	96.73 257	92.68 197	99.71 100	95.12 159	99.60 87	98.94 176

v1921920		96.72 142	96.96 125	95.99 215	98.21 186	88.79 265	95.42 208	98.79 124	93.22 224	98.19 111	98.26 122	92.68 197	99.70 107	98.34 21	99.55 103	99.49 58

BH-untuned		94.69 230	94.75 221	94.52 287	97.95 218	87.53 293	94.07 273	97.01 277	93.99 204	97.10 184	95.65 303	92.65 199	98.95 290	87.60 322	96.74 327	97.09 315

LF4IMVS		96.07 170	95.63 189	97.36 141	98.19 188	95.55 94	95.44 206	98.82 122	92.29 251	95.70 264	96.55 265	92.63 200	98.69 311	91.75 251	99.33 176	97.85 291

v2v482		96.78 138	97.06 119	95.95 219	98.57 147	88.77 266	95.36 214	98.26 199	95.18 167	97.85 148	98.23 125	92.58 201	99.63 137	97.80 35	99.69 64	99.45 73

EI-MVSNet		96.63 148	96.93 126	95.74 228	97.26 288	88.13 279	95.29 222	97.65 254	96.99 83	97.94 138	98.19 130	92.55 202	99.58 152	96.91 68	99.56 97	99.50 50

IterMVS-LS		96.92 127	97.29 106	95.79 226	98.51 156	88.13 279	95.10 229	98.66 153	96.99 83	98.46 78	98.68 76	92.55 202	99.74 75	96.91 68	99.79 40	99.50 50
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 106	97.25 108	97.74 108	98.69 132	94.50 140	97.04 121	95.61 310	98.59 25	98.51 70	98.72 72	92.54 204	99.58 152	96.02 98	99.49 127	99.12 148

MVS		90.02 317	89.20 324	92.47 331	94.71 350	86.90 306	95.86 186	96.74 288	64.72 373	90.62 350	92.77 347	92.54 204	98.39 335	79.30 361	95.56 346	92.12 366

test_vis1_rt		94.03 259	93.65 259	95.17 254	95.76 335	93.42 178	93.97 279	98.33 193	84.68 339	93.17 326	95.89 298	92.53 206	94.79 370	93.50 221	94.97 350	97.31 313

v144192		96.69 145	96.90 130	96.03 214	98.25 182	88.92 260	95.49 204	98.77 129	93.05 232	98.09 120	98.29 116	92.51 207	99.70 107	98.11 23	99.56 97	99.47 67

原ACMM1				96.58 186	98.16 196	92.12 206		98.15 219	85.90 325	93.49 318	96.43 272	92.47 208	99.38 216	87.66 321	98.62 258	98.23 261

VNet		96.84 131	96.83 132	96.88 168	98.06 205	92.02 211	96.35 155	97.57 260	97.70 57	97.88 143	97.80 177	92.40 209	99.54 165	94.73 177	98.96 221	99.08 156

114514_t		93.96 260	93.22 267	96.19 208	99.06 94	90.97 229	95.99 176	98.94 84	73.88 371	93.43 321	96.93 242	92.38 210	99.37 219	89.09 302	99.28 185	98.25 260

CPTT-MVS		96.69 145	96.08 169	98.49 52	98.89 110	96.64 55	97.25 107	98.77 129	92.89 240	96.01 250	97.13 228	92.23 211	99.67 124	92.24 240	99.34 170	99.17 135

MSP-MVS		97.45 99	96.92 128	99.03 5	99.26 56	97.70 18	97.66 82	98.89 90	95.65 147	98.51 70	96.46 271	92.15 212	99.81 37	95.14 156	98.58 262	99.58 32
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		94.21 251	93.03 270	97.76 107	96.94 301	97.44 33	96.97 125	97.15 271	87.89 307	92.00 344	92.73 349	92.14 213	99.12 266	83.92 349	97.51 309	96.73 332
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		95.95 176	95.80 183	96.42 197	99.28 55	90.62 235	95.31 220	99.08 47	88.40 299	96.97 199	98.17 133	92.11 214	99.78 46	93.64 218	99.21 193	98.86 195

BH-RMVSNet		94.56 238	94.44 240	94.91 266	97.57 263	87.44 296	93.78 287	96.26 294	93.69 212	96.41 229	96.50 270	92.10 215	99.00 281	85.96 333	97.71 298	98.31 252

新几何1				97.25 147	98.29 176	94.70 133		97.73 247	77.98 365	94.83 283	96.67 260	92.08 216	99.45 192	88.17 316	98.65 256	97.61 301

testdata				95.70 231	98.16 196	90.58 236		97.72 248	80.38 357	95.62 265	97.02 236	92.06 217	98.98 285	89.06 304	98.52 264	97.54 304

YYNet1		94.73 225	94.84 215	94.41 291	97.47 274	85.09 329	90.29 350	95.85 304	92.52 245	97.53 157	97.76 178	91.97 218	99.18 256	93.31 225	96.86 323	98.95 174

Anonymous20231206		95.27 204	95.06 204	95.88 223	98.72 125	89.37 253	95.70 192	97.85 239	88.00 305	96.98 198	97.62 192	91.95 219	99.34 226	89.21 300	99.53 110	98.94 176

MS-PatchMatch		94.83 222	94.91 211	94.57 285	96.81 304	87.10 303	94.23 263	97.34 265	88.74 296	97.14 180	97.11 230	91.94 220	98.23 343	92.99 232	97.92 287	98.37 243

MDA-MVSNet_test_wron		94.73 225	94.83 217	94.42 290	97.48 270	85.15 327	90.28 351	95.87 303	92.52 245	97.48 163	97.76 178	91.92 221	99.17 260	93.32 224	96.80 326	98.94 176

HQP_MVS		96.66 147	96.33 160	97.68 114	98.70 130	94.29 147	96.50 148	98.75 133	96.36 109	96.16 244	96.77 254	91.91 222	99.46 188	92.59 236	99.20 194	99.28 113

plane_prior6					98.38 170	94.37 144						91.91 222

MVP-Stereo		95.69 184	95.28 194	96.92 165	98.15 198	93.03 187	95.64 200	98.20 207	90.39 275	96.63 219	97.73 184	91.63 224	99.10 271	91.84 248	97.31 317	98.63 220
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 236	93.81 257	97.02 161	98.19 188	95.72 86	93.66 289	97.23 267	88.17 303	94.94 281	95.62 305	91.43 225	98.57 322	87.36 327	97.68 301	96.76 331

MDA-MVSNet-bldmvs		95.69 184	95.67 187	95.74 228	98.48 162	88.76 267	92.84 306	97.25 266	96.00 129	97.59 155	97.95 161	91.38 226	99.46 188	93.16 230	96.35 334	98.99 170

mvsmamba		98.16 34	98.06 40	98.44 55	99.53 29	95.87 81	98.70 13	98.94 84	97.71 56	98.85 47	99.10 41	91.35 227	99.83 33	98.47 17	99.90 22	99.64 27

PAPR		92.22 295	91.27 301	95.07 258	95.73 337	88.81 264	91.97 325	97.87 238	85.80 326	90.91 349	92.73 349	91.16 228	98.33 340	79.48 360	95.76 343	98.08 269

1314		92.38 292	92.30 287	92.64 328	95.42 344	85.15 327	95.86 186	96.97 279	85.40 331	90.62 350	93.06 343	91.12 229	97.80 352	86.74 330	95.49 347	94.97 356

ppachtmachnet_test		94.49 243	94.84 215	93.46 310	96.16 321	82.10 350	90.59 347	97.48 262	90.53 274	97.01 195	97.59 194	91.01 230	99.36 221	93.97 208	99.18 198	98.94 176

PLC	91.02 16	94.05 258	92.90 273	97.51 124	98.00 213	95.12 123	94.25 261	98.25 200	86.17 321	91.48 347	95.25 312	91.01 230	99.19 255	85.02 344	96.69 328	98.22 262
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 194	93.24 183	92.74 311	97.61 259	75.17 369	94.65 286	96.69 259	90.96 232			98.66 254	97.66 299

CL-MVSNet_self_test		95.04 214	94.79 220	95.82 225	97.51 268	89.79 246	91.14 340	96.82 284	93.05 232	96.72 212	96.40 275	90.82 233	99.16 261	91.95 244	98.66 254	98.50 233

USDC		94.56 238	94.57 234	94.55 286	97.78 243	86.43 312	92.75 309	98.65 158	85.96 323	96.91 203	97.93 164	90.82 233	98.74 305	90.71 275	99.59 89	98.47 235

PCF-MVS	89.43 18	92.12 298	90.64 312	96.57 188	97.80 235	93.48 177	89.88 357	98.45 175	74.46 370	96.04 249	95.68 302	90.71 235	99.31 232	73.73 369	99.01 219	96.91 322
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 236	94.17 248	95.96 217	98.36 172	91.23 224	95.93 183	97.95 233	92.98 235	93.42 322	94.43 330	90.53 236	98.38 336	87.60 322	96.29 335	98.27 258

our_test_3		94.20 253	94.58 232	93.07 318	96.16 321	81.20 356	90.42 349	96.84 282	90.72 272	97.14 180	97.13 228	90.47 237	99.11 269	94.04 205	98.25 275	98.91 184

test_f		95.82 181	95.88 181	95.66 232	97.61 261	93.21 184	95.61 201	98.17 213	86.98 314	98.42 81	99.47 10	90.46 238	94.74 371	97.71 40	98.45 268	99.03 163

OpenMVS_ROB	91.80 14	93.64 270	93.05 268	95.42 245	97.31 287	91.21 225	95.08 232	96.68 291	81.56 351	96.88 205	96.41 273	90.44 239	99.25 247	85.39 340	97.67 302	95.80 346

HQP2-MVS												90.33 240

N_pmnet		95.18 208	94.23 244	98.06 88	97.85 222	96.55 58	92.49 315	91.63 350	89.34 286	98.09 120	97.41 206	90.33 240	99.06 275	91.58 252	99.31 181	98.56 226

HQP-MVS		95.17 210	94.58 232	96.92 165	97.85 222	92.47 197	94.26 258	98.43 178	93.18 226	92.86 331	95.08 314	90.33 240	99.23 252	90.51 281	98.74 246	99.05 162

CNLPA		95.04 214	94.47 237	96.75 177	97.81 231	95.25 114	94.12 272	97.89 237	94.41 192	94.57 287	95.69 301	90.30 243	98.35 339	86.72 331	98.76 244	96.64 333

PMMVS		92.39 291	91.08 303	96.30 204	93.12 368	92.81 191	90.58 348	95.96 301	79.17 362	91.85 346	92.27 353	90.29 244	98.66 316	89.85 292	96.68 329	97.43 308

TR-MVS		92.54 290	92.20 289	93.57 308	96.49 309	86.66 308	93.51 294	94.73 320	89.96 281	94.95 280	93.87 334	90.24 245	98.61 319	81.18 358	94.88 351	95.45 352

MVS_0304		95.50 192	95.05 205	96.84 171	96.28 314	93.12 185	97.00 123	96.16 295	95.03 174	89.22 361	97.70 186	90.16 246	99.48 182	94.51 184	99.34 170	97.93 287

TAMVS		95.49 193	94.94 207	97.16 150	98.31 174	93.41 179	95.07 233	96.82 284	91.09 268	97.51 159	97.82 175	89.96 247	99.42 198	88.42 312	99.44 140	98.64 218

DPM-MVS		93.68 267	92.77 280	96.42 197	97.91 219	92.54 195	91.17 339	97.47 263	84.99 337	93.08 328	94.74 322	89.90 248	99.00 281	87.54 324	98.09 282	97.72 297

PMMVS2		93.66 268	94.07 250	92.45 332	97.57 263	80.67 358	86.46 365	96.00 299	93.99 204	97.10 184	97.38 213	89.90 248	97.82 351	88.76 306	99.47 133	98.86 195

RRT_MVS		97.95 51	97.79 61	98.43 57	99.67 12	95.56 93	98.86 10	96.73 290	97.99 45	99.15 31	99.35 20	89.84 250	99.90 14	98.64 13	99.90 22	99.82 6

bld_raw_dy_0_64		97.69 83	97.61 84	97.91 97	99.54 26	94.27 151	98.06 59	98.60 161	96.60 95	98.79 52	98.95 52	89.62 251	99.84 30	98.43 19	99.91 16	99.62 28

BH-w/o		92.14 297	91.94 291	92.73 327	97.13 294	85.30 323	92.46 316	95.64 307	89.33 287	94.21 295	92.74 348	89.60 252	98.24 342	81.68 356	94.66 353	94.66 357

Anonymous20240521		97.07 117	97.51 94	95.76 227	99.35 49	88.18 276	97.78 72	98.40 184	97.11 81	98.34 92	99.04 46	89.58 253	99.79 43	98.09 24	99.93 10	99.30 106

UnsupCasMVSNet_bld		94.72 229	94.26 243	96.08 213	98.62 141	90.54 239	93.38 298	98.05 232	90.30 276	97.02 194	96.80 253	89.54 254	99.16 261	88.44 311	96.18 336	98.56 226

MG-MVS		94.08 257	94.00 252	94.32 293	97.09 295	85.89 317	93.19 303	95.96 301	92.52 245	94.93 282	97.51 200	89.54 254	98.77 302	87.52 325	97.71 298	98.31 252

UnsupCasMVSNet_eth		95.91 177	95.73 186	96.44 194	98.48 162	91.52 221	95.31 220	98.45 175	95.76 143	97.48 163	97.54 197	89.53 256	98.69 311	94.43 186	94.61 354	99.13 143

GBi-Net		96.99 121	96.80 134	97.56 119	97.96 215	93.67 169	98.23 46	98.66 153	95.59 151	97.99 131	99.19 30	89.51 257	99.73 80	94.60 180	99.44 140	99.30 106

test1		96.99 121	96.80 134	97.56 119	97.96 215	93.67 169	98.23 46	98.66 153	95.59 151	97.99 131	99.19 30	89.51 257	99.73 80	94.60 180	99.44 140	99.30 106

FMVSNet2		96.72 142	96.67 141	96.87 169	97.96 215	91.88 214	97.15 113	98.06 231	95.59 151	98.50 72	98.62 80	89.51 257	99.65 132	94.99 166	99.60 87	99.07 158

pmmvs4		94.82 223	94.19 247	96.70 180	97.42 277	92.75 194	92.09 324	96.76 286	86.80 317	95.73 263	97.22 224	89.28 260	98.89 292	93.28 226	99.14 200	98.46 237

cascas		91.89 301	91.35 299	93.51 309	94.27 356	85.60 319	88.86 362	98.61 160	79.32 361	92.16 343	91.44 362	89.22 261	98.12 346	90.80 269	97.47 312	96.82 328

DSMNet-mixed		92.19 296	91.83 293	93.25 314	96.18 320	83.68 344	96.27 158	93.68 330	76.97 368	92.54 340	99.18 33	89.20 262	98.55 325	83.88 350	98.60 261	97.51 305

c3_l		95.20 207	95.32 193	94.83 273	96.19 319	86.43 312	91.83 327	98.35 192	93.47 216	97.36 169	97.26 222	88.69 263	99.28 241	95.41 141	99.36 162	98.78 202

test_fmvs2		96.38 160	96.45 154	96.16 210	97.85 222	91.30 223	96.81 132	99.45 13	89.24 288	98.49 73	99.38 15	88.68 264	97.62 354	98.83 5	99.32 178	99.57 37

CANet_DTU		94.65 234	94.21 246	95.96 217	95.90 329	89.68 247	93.92 281	97.83 243	93.19 225	90.12 356	95.64 304	88.52 265	99.57 158	93.27 227	99.47 133	98.62 221

EPP-MVSNet		96.84 131	96.58 144	97.65 115	99.18 76	93.78 167	98.68 14	96.34 293	97.91 47	97.30 170	98.06 149	88.46 266	99.85 27	93.85 211	99.40 156	99.32 101

SixPastTwentyTwo		97.49 96	97.57 88	97.26 146	99.56 21	92.33 199	98.28 42	96.97 279	98.30 34	99.45 14	99.35 20	88.43 267	99.89 18	98.01 27	99.76 46	99.54 44

miper_ehance_all_eth		94.69 230	94.70 222	94.64 279	95.77 334	86.22 314	91.32 336	98.24 201	91.67 259	97.05 191	96.65 261	88.39 268	99.22 254	94.88 167	98.34 271	98.49 234

IS-MVSNet		96.93 126	96.68 140	97.70 111	99.25 59	94.00 159	98.57 20	96.74 288	98.36 30	98.14 115	97.98 158	88.23 269	99.71 100	93.10 231	99.72 57	99.38 92

jason		94.39 246	94.04 251	95.41 247	98.29 176	87.85 287	92.74 311	96.75 287	85.38 332	95.29 272	96.15 285	88.21 270	99.65 132	94.24 195	99.34 170	98.74 208
jason: jason.
IterMVS-SCA-FT		95.86 179	96.19 164	94.85 271	97.68 254	85.53 320	92.42 317	97.63 258	96.99 83	98.36 89	98.54 87	87.94 271	99.75 66	97.07 64	99.08 210	99.27 117

SCA		93.38 277	93.52 262	92.96 323	96.24 315	81.40 355	93.24 301	94.00 327	91.58 262	94.57 287	96.97 239	87.94 271	99.42 198	89.47 297	97.66 303	98.06 275

sss		94.22 249	93.72 258	95.74 228	97.71 252	89.95 244	93.84 283	96.98 278	88.38 300	93.75 309	95.74 300	87.94 271	98.89 292	91.02 262	98.10 281	98.37 243

IterMVS		95.42 199	95.83 182	94.20 297	97.52 267	83.78 343	92.41 318	97.47 263	95.49 155	98.06 125	98.49 91	87.94 271	99.58 152	96.02 98	99.02 217	99.23 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 255	93.41 264	96.18 209	99.16 77	90.04 242	92.15 321	98.68 148	79.90 359	96.22 240	97.83 172	87.92 275	99.42 198	89.18 301	99.65 73	99.08 156

VDDNet		96.98 124	96.84 131	97.41 138	99.40 44	93.26 182	97.94 64	95.31 316	99.26 7	98.39 85	99.18 33	87.85 276	99.62 142	95.13 158	99.09 209	99.35 100

pmmvs5		94.63 235	94.34 242	95.50 240	97.63 260	88.34 272	94.02 274	97.13 272	87.15 311	95.22 274	97.15 227	87.50 277	99.27 244	93.99 206	99.26 188	98.88 192

D2MVS		95.18 208	95.17 198	95.21 251	97.76 245	87.76 290	94.15 268	97.94 234	89.77 284	96.99 196	97.68 189	87.45 278	99.14 263	95.03 164	99.81 36	98.74 208

test_vis1_n_1920		95.77 182	96.41 156	93.85 301	98.55 150	84.86 332	95.91 185	99.71 2	92.72 243	97.67 153	98.90 59	87.44 279	98.73 306	97.96 28	98.85 235	97.96 284

PVSNet	86.72 19	91.10 309	90.97 306	91.49 338	97.56 265	78.04 363	87.17 364	94.60 322	84.65 340	92.34 341	92.20 354	87.37 280	98.47 330	85.17 343	97.69 300	97.96 284

Anonymous202405211		96.34 161	95.98 174	97.43 136	98.25 182	93.85 163	96.74 138	94.41 324	97.72 54	98.37 86	98.03 152	87.15 281	99.53 167	94.06 202	99.07 212	98.92 183

MVSFormer		96.14 168	96.36 158	95.49 241	97.68 254	87.81 288	98.67 15	99.02 62	96.50 103	94.48 291	96.15 285	86.90 282	99.92 5	98.73 9	99.13 202	98.74 208

lupinMVS		93.77 263	93.28 265	95.24 250	97.68 254	87.81 288	92.12 322	96.05 297	84.52 341	94.48 291	95.06 316	86.90 282	99.63 137	93.62 219	99.13 202	98.27 258

eth_miper_zixun_eth		94.89 220	94.93 209	94.75 277	95.99 327	86.12 315	91.35 333	98.49 172	93.40 217	97.12 182	97.25 223	86.87 284	99.35 224	95.08 161	98.82 239	98.78 202

test_vis1_n		95.67 186	95.89 180	95.03 260	98.18 191	89.89 245	96.94 126	99.28 21	88.25 302	98.20 107	98.92 55	86.69 285	97.19 357	97.70 42	98.82 239	98.00 283

WTY-MVS		93.55 272	93.00 272	95.19 252	97.81 231	87.86 285	93.89 282	96.00 299	89.02 291	94.07 300	95.44 311	86.27 286	99.33 228	87.69 320	96.82 324	98.39 241

CDS-MVSNet		94.88 221	94.12 249	97.14 152	97.64 259	93.57 174	93.96 280	97.06 276	90.05 280	96.30 236	96.55 265	86.10 287	99.47 185	90.10 288	99.31 181	98.40 239
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 254	93.42 263	96.23 205	98.59 145	90.85 230	94.24 262	98.85 105	85.49 328	92.97 329	94.94 318	86.01 288	99.64 135	91.78 249	97.92 287	98.20 264

miper_enhance_ethall		93.14 282	92.78 279	94.20 297	93.65 364	85.29 324	89.97 353	97.85 239	85.05 334	96.15 246	94.56 325	85.74 289	99.14 263	93.74 214	98.34 271	98.17 267

new_pmnet		92.34 293	91.69 296	94.32 293	96.23 317	89.16 257	92.27 320	92.88 339	84.39 344	95.29 272	96.35 278	85.66 290	96.74 366	84.53 347	97.56 306	97.05 316

alignmvs		96.01 174	95.52 192	97.50 127	97.77 244	94.71 131	96.07 170	96.84 282	97.48 67	96.78 211	94.28 332	85.50 291	99.40 209	96.22 88	98.73 249	98.40 239

lessismore_v0				97.05 157	99.36 48	92.12 206		84.07 373		98.77 55	98.98 49	85.36 292	99.74 75	97.34 53	99.37 159	99.30 106

HY-MVS	91.43 15	92.58 289	91.81 294	94.90 268	96.49 309	88.87 262	97.31 104	94.62 321	85.92 324	90.50 353	96.84 248	85.05 293	99.40 209	83.77 352	95.78 342	96.43 339

EPNet		93.72 265	92.62 284	97.03 160	87.61 380	92.25 200	96.27 158	91.28 351	96.74 91	87.65 366	97.39 211	85.00 294	99.64 135	92.14 241	99.48 131	99.20 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 224	94.80 219	94.85 271	96.16 321	86.45 311	91.14 340	98.20 207	93.49 215	97.03 193	97.37 215	84.97 295	99.26 245	95.28 144	99.56 97	98.83 197

Test_1112_low_res		93.53 273	92.86 274	95.54 239	98.60 143	88.86 263	92.75 309	98.69 146	82.66 348	92.65 336	96.92 244	84.75 296	99.56 159	90.94 264	97.76 294	98.19 265

MVS-HIRNet		88.40 332	90.20 317	82.99 356	97.01 297	60.04 380	93.11 304	85.61 372	84.45 343	88.72 363	99.09 43	84.72 297	98.23 343	82.52 355	96.59 331	90.69 371

K. test v3		96.44 157	96.28 161	96.95 163	99.41 43	91.53 220	97.65 83	90.31 360	98.89 19	98.93 42	99.36 18	84.57 298	99.92 5	97.81 34	99.56 97	99.39 90

h-mvs33		96.29 162	95.63 189	98.26 70	98.50 159	96.11 73	96.90 127	97.09 274	96.58 98	97.21 175	98.19 130	84.14 299	99.78 46	95.89 107	96.17 337	98.89 188

hse-mvs2		95.77 182	95.09 201	97.79 105	97.84 227	95.51 97	95.66 196	95.43 315	96.58 98	97.21 175	96.16 284	84.14 299	99.54 165	95.89 107	96.92 320	98.32 250

DIV-MVS_self_test		94.73 225	94.64 225	95.01 261	95.86 330	87.00 304	91.33 334	98.08 226	93.34 219	97.10 184	97.34 217	84.02 301	99.31 232	95.15 155	99.55 103	98.72 211

cl____		94.73 225	94.64 225	95.01 261	95.85 331	87.00 304	91.33 334	98.08 226	93.34 219	97.10 184	97.33 218	84.01 302	99.30 235	95.14 156	99.56 97	98.71 214

Vis-MVSNet (Re-imp)		95.11 211	94.85 214	95.87 224	99.12 87	89.17 256	97.54 96	94.92 319	96.50 103	96.58 220	97.27 221	83.64 303	99.48 182	88.42 312	99.67 70	98.97 172

FA-MVS(test-final)		94.91 219	94.89 212	94.99 263	97.51 268	88.11 281	98.27 44	95.20 317	92.40 250	96.68 214	98.60 81	83.44 304	99.28 241	93.34 223	98.53 263	97.59 303

PVSNet_0	81.89 21	84.49 340	83.21 343	88.34 352	95.76 335	74.97 374	83.49 368	92.70 343	78.47 364	87.94 365	86.90 372	83.38 305	96.63 367	73.44 370	66.86 376	93.40 363

test_fmvs1_n		95.21 206	95.28 194	94.99 263	98.15 198	89.13 259	96.81 132	99.43 15	86.97 315	97.21 175	98.92 55	83.00 306	97.13 358	98.09 24	98.94 224	98.72 211

CMPMVS	73.10 23	92.74 287	91.39 298	96.77 176	93.57 366	94.67 134	94.21 265	97.67 250	80.36 358	93.61 314	96.60 263	82.85 307	97.35 356	84.86 345	98.78 242	98.29 257
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs1		94.51 242	94.60 229	94.26 296	95.91 328	87.92 283	95.35 216	99.02 62	86.56 319	96.79 207	98.52 88	82.64 308	97.00 361	97.87 31	98.71 250	97.88 289

EU-MVSNet		94.25 248	94.47 237	93.60 307	98.14 200	82.60 348	97.24 109	92.72 342	85.08 333	98.48 75	98.94 53	82.59 309	98.76 304	97.47 50	99.53 110	99.44 82

baseline1		93.14 282	92.64 283	94.62 281	97.34 283	87.20 301	96.67 145	93.02 337	94.71 183	96.51 225	95.83 299	81.64 310	98.60 321	90.00 290	88.06 369	98.07 271

test1111		94.53 241	94.81 218	93.72 304	99.06 94	81.94 353	98.31 39	83.87 374	96.37 108	98.49 73	99.17 35	81.49 311	99.73 80	96.64 72	99.86 27	99.49 58

CVMVSNet		92.33 294	92.79 277	90.95 341	97.26 288	75.84 371	95.29 222	92.33 345	81.86 349	96.27 237	98.19 130	81.44 312	98.46 331	94.23 196	98.29 274	98.55 228

EPNet_dtu		91.39 307	90.75 310	93.31 312	90.48 377	82.61 347	94.80 244	92.88 339	93.39 218	81.74 374	94.90 321	81.36 313	99.11 269	88.28 314	98.87 232	98.21 263
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 247	94.48 236	94.05 300	98.95 104	83.10 345	98.31 39	82.48 375	96.20 116	98.23 105	99.16 36	81.18 314	99.66 130	95.95 103	99.83 33	99.38 92

test_yl		94.40 244	94.00 252	95.59 233	96.95 299	89.52 250	94.75 247	95.55 312	96.18 119	96.79 207	96.14 287	81.09 315	99.18 256	90.75 271	97.77 292	98.07 271

DCV-MVSNet		94.40 244	94.00 252	95.59 233	96.95 299	89.52 250	94.75 247	95.55 312	96.18 119	96.79 207	96.14 287	81.09 315	99.18 256	90.75 271	97.77 292	98.07 271

MIMVSNet		93.42 275	92.86 274	95.10 257	98.17 194	88.19 275	98.13 55	93.69 328	92.07 252	95.04 279	98.21 129	80.95 317	99.03 280	81.42 357	98.06 283	98.07 271

PAPM		87.64 337	85.84 342	93.04 319	96.54 307	84.99 330	88.42 363	95.57 311	79.52 360	83.82 371	93.05 344	80.57 318	98.41 333	62.29 375	92.79 360	95.71 347

HyFIR lowres test		93.72 265	92.65 282	96.91 167	98.93 107	91.81 217	91.23 338	98.52 169	82.69 347	96.46 227	96.52 269	80.38 319	99.90 14	90.36 285	98.79 241	99.03 163

FMVSNet3		95.26 205	94.94 207	96.22 207	96.53 308	90.06 241	95.99 176	97.66 252	94.11 201	97.99 131	97.91 166	80.22 320	99.63 137	94.60 180	99.44 140	98.96 173

RPMNet		94.68 232	94.60 229	94.90 268	95.44 342	88.15 277	96.18 165	98.86 101	97.43 68	94.10 298	98.49 91	79.40 321	99.76 60	95.69 116	95.81 339	96.81 329

LFMVS		95.32 202	94.88 213	96.62 183	98.03 206	91.47 222	97.65 83	90.72 357	99.11 9	97.89 142	98.31 108	79.20 322	99.48 182	93.91 210	99.12 205	98.93 180

ADS-MVSNet2		91.47 306	90.51 314	94.36 292	95.51 340	85.63 318	95.05 235	95.70 305	83.46 345	92.69 334	96.84 248	79.15 323	99.41 207	85.66 337	90.52 364	98.04 279

ADS-MVSNet		90.95 312	90.26 316	93.04 319	95.51 340	82.37 349	95.05 235	93.41 334	83.46 345	92.69 334	96.84 248	79.15 323	98.70 310	85.66 337	90.52 364	98.04 279

MDTV_nov1_ep13_2view						57.28 381	94.89 241		80.59 356	94.02 302		78.66 325		85.50 339		97.82 293

cl22		93.25 280	92.84 276	94.46 289	94.30 355	86.00 316	91.09 342	96.64 292	90.74 271	95.79 258	96.31 279	78.24 326	98.77 302	94.15 199	98.34 271	98.62 221

PatchmatchNet		91.98 300	91.87 292	92.30 334	94.60 352	79.71 360	95.12 228	93.59 333	89.52 285	93.61 314	97.02 236	77.94 327	99.18 256	90.84 267	94.57 356	98.01 282
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 328				98.06 275

CR-MVSNet		93.29 279	92.79 277	94.78 276	95.44 342	88.15 277	96.18 165	97.20 268	84.94 338	94.10 298	98.57 83	77.67 329	99.39 213	95.17 151	95.81 339	96.81 329

Patchmtry		95.03 216	94.59 231	96.33 201	94.83 349	90.82 231	96.38 153	97.20 268	96.59 97	97.49 161	98.57 83	77.67 329	99.38 216	92.95 234	99.62 78	98.80 200

tpmrst		90.31 315	90.61 313	89.41 348	94.06 360	72.37 377	95.06 234	93.69 328	88.01 304	92.32 342	96.86 246	77.45 331	98.82 297	91.04 261	87.01 370	97.04 317

sam_mvs												77.38 332

patchmatchnet-post											96.84 248	77.36 333	99.42 198

Patchmatch-RL test		94.66 233	94.49 235	95.19 252	98.54 152	88.91 261	92.57 313	98.74 135	91.46 263	98.32 96	97.75 181	77.31 334	98.81 299	96.06 93	99.61 84	97.85 291

tpmvs		90.79 313	90.87 307	90.57 344	92.75 372	76.30 369	95.79 189	93.64 332	91.04 269	91.91 345	96.26 280	77.19 335	98.86 296	89.38 299	89.85 367	96.56 336

test_post											10.87 378	76.83 336	99.07 274

Patchmatch-test		93.60 271	93.25 266	94.63 280	96.14 324	87.47 294	96.04 172	94.50 323	93.57 213	96.47 226	96.97 239	76.50 337	98.61 319	90.67 277	98.41 270	97.81 295

MDTV_nov1_ep13			91.28 300		94.31 354	73.51 375	94.80 244	93.16 336	86.75 318	93.45 320	97.40 207	76.37 338	98.55 325	88.85 305	96.43 332

EMVS		89.06 327	89.22 322	88.61 351	93.00 369	77.34 366	82.91 370	90.92 354	94.64 185	92.63 338	91.81 358	76.30 339	97.02 360	83.83 351	96.90 322	91.48 369

test_post1							94.98 239				10.37 379	76.21 340	99.04 277	89.47 297

GA-MVS		92.83 286	92.15 290	94.87 270	96.97 298	87.27 300	90.03 352	96.12 296	91.83 258	94.05 301	94.57 324	76.01 341	98.97 289	92.46 239	97.34 316	98.36 248

PatchT		93.75 264	93.57 261	94.29 295	95.05 347	87.32 299	96.05 171	92.98 338	97.54 65	94.25 294	98.72 72	75.79 342	99.24 250	95.92 105	95.81 339	96.32 340

E-PMN		89.52 325	89.78 319	88.73 350	93.14 367	77.61 365	83.26 369	92.02 346	94.82 180	93.71 310	93.11 338	75.31 343	96.81 363	85.81 334	96.81 325	91.77 368

DeepMVS_CX				77.17 357	90.94 376	85.28 325		74.08 380	52.51 374	80.87 375	88.03 371	75.25 344	70.63 377	59.23 376	84.94 372	75.62 372

AUN-MVS		93.95 262	92.69 281	97.74 108	97.80 235	95.38 105	95.57 203	95.46 314	91.26 266	92.64 337	96.10 290	74.67 345	99.55 162	93.72 216	96.97 319	98.30 254

CHOSEN 280x420		89.98 319	89.19 325	92.37 333	95.60 339	81.13 357	86.22 366	97.09 274	81.44 353	87.44 367	93.15 337	73.99 346	99.47 185	88.69 308	99.07 212	96.52 337

thres200		91.00 311	90.42 315	92.77 326	97.47 274	83.98 342	94.01 275	91.18 353	95.12 170	95.44 269	91.21 364	73.93 347	99.31 232	77.76 366	97.63 305	95.01 355

test-LLR		89.97 320	89.90 318	90.16 345	94.24 357	74.98 372	89.89 354	89.06 364	92.02 253	89.97 357	90.77 367	73.92 348	98.57 322	91.88 246	97.36 314	96.92 320

test0.0.03 1		90.11 316	89.21 323	92.83 325	93.89 362	86.87 307	91.74 328	88.74 366	92.02 253	94.71 285	91.14 365	73.92 348	94.48 372	83.75 353	92.94 359	97.16 314

tpm cat1		88.01 335	87.33 336	90.05 347	94.48 353	76.28 370	94.47 254	94.35 325	73.84 372	89.26 360	95.61 306	73.64 350	98.30 341	84.13 348	86.20 371	95.57 351

tfpn200view9		91.55 305	91.00 304	93.21 316	98.02 207	84.35 338	95.70 192	90.79 355	96.26 113	95.90 256	92.13 355	73.62 351	99.42 198	78.85 363	97.74 295	95.85 344

thres400		91.68 304	91.00 304	93.71 305	98.02 207	84.35 338	95.70 192	90.79 355	96.26 113	95.90 256	92.13 355	73.62 351	99.42 198	78.85 363	97.74 295	97.36 310

test_method		66.88 342	66.13 345	69.11 358	62.68 381	25.73 383	49.76 372	96.04 298	14.32 376	64.27 377	91.69 360	73.45 353	88.05 375	76.06 368	66.94 375	93.54 361

thres100view900		91.76 303	91.26 302	93.26 313	98.21 186	84.50 336	96.39 151	90.39 358	96.87 87	96.33 232	93.08 342	73.44 354	99.42 198	78.85 363	97.74 295	95.85 344

thres600view7		92.03 299	91.43 297	93.82 302	98.19 188	84.61 335	96.27 158	90.39 358	96.81 89	96.37 231	93.11 338	73.44 354	99.49 179	80.32 359	97.95 286	97.36 310

MVSTER		94.21 251	93.93 255	95.05 259	95.83 332	86.46 310	95.18 227	97.65 254	92.41 249	97.94 138	98.00 157	72.39 356	99.58 152	96.36 83	99.56 97	99.12 148

JIA-IIPM		91.79 302	90.69 311	95.11 255	93.80 363	90.98 228	94.16 267	91.78 349	96.38 107	90.30 355	99.30 24	72.02 357	98.90 291	88.28 314	90.17 366	95.45 352

tpm		91.08 310	90.85 308	91.75 337	95.33 345	78.09 362	95.03 237	91.27 352	88.75 295	93.53 317	97.40 207	71.24 358	99.30 235	91.25 258	93.87 357	97.87 290

baseline2		89.65 324	88.44 331	93.25 314	95.62 338	82.71 346	93.82 284	85.94 371	88.89 294	87.35 368	92.54 351	71.23 359	99.33 228	86.01 332	94.60 355	97.72 297

CostFormer		89.75 323	89.25 321	91.26 340	94.69 351	78.00 364	95.32 219	91.98 347	81.50 352	90.55 352	96.96 241	71.06 360	98.89 292	88.59 310	92.63 361	96.87 323

FPMVS		89.92 321	88.63 329	93.82 302	98.37 171	96.94 45	91.58 329	93.34 335	88.00 305	90.32 354	97.10 231	70.87 361	91.13 374	71.91 372	96.16 338	93.39 364

EPMVS		89.26 326	88.55 330	91.39 339	92.36 373	79.11 361	95.65 198	79.86 376	88.60 297	93.12 327	96.53 267	70.73 362	98.10 347	90.75 271	89.32 368	96.98 318

FE-MVS		92.95 284	92.22 288	95.11 255	97.21 291	88.33 273	98.54 23	93.66 331	89.91 282	96.21 241	98.14 134	70.33 363	99.50 175	87.79 318	98.24 276	97.51 305

tmp_tt		57.23 343	62.50 346	41.44 359	34.77 382	49.21 382	83.93 367	60.22 383	15.31 375	71.11 376	79.37 374	70.09 364	44.86 378	64.76 374	82.93 374	30.25 374

ET-MVSNet_ETH3D		91.12 308	89.67 320	95.47 242	96.41 311	89.15 258	91.54 330	90.23 361	89.07 290	86.78 370	92.84 346	69.39 365	99.44 195	94.16 198	96.61 330	97.82 293

dp		88.08 334	88.05 332	88.16 354	92.85 370	68.81 379	94.17 266	92.88 339	85.47 329	91.38 348	96.14 287	68.87 366	98.81 299	86.88 329	83.80 373	96.87 323

iter_conf_final		94.54 240	93.91 256	96.43 195	97.23 290	90.41 240	96.81 132	98.10 223	93.87 207	96.80 206	97.89 167	68.02 367	99.72 85	96.73 71	99.77 45	99.18 134

tpm2		88.47 331	87.69 335	90.79 342	94.98 348	77.34 366	95.09 230	91.83 348	77.51 367	89.40 359	96.41 273	67.83 368	98.73 306	83.58 354	92.60 362	96.29 341

pmmvs3		90.00 318	88.90 328	93.32 311	94.20 359	85.34 322	91.25 337	92.56 344	78.59 363	93.82 305	95.17 313	67.36 369	98.69 311	89.08 303	98.03 284	95.92 343

thisisatest0515		90.43 314	89.18 326	94.17 299	97.07 296	85.44 321	89.75 358	87.58 367	88.28 301	93.69 312	91.72 359	65.27 370	99.58 152	90.59 278	98.67 252	97.50 307

tttt0517		93.31 278	92.56 285	95.57 235	98.71 128	87.86 285	97.44 99	87.17 369	95.79 142	97.47 165	96.84 248	64.12 371	99.81 37	96.20 89	99.32 178	99.02 166

thisisatest0530		92.71 288	91.76 295	95.56 237	98.42 168	88.23 274	96.03 173	87.35 368	94.04 203	96.56 222	95.47 309	64.03 372	99.77 55	94.78 174	99.11 206	98.68 217

iter_conf05		93.65 269	93.05 268	95.46 243	96.13 325	87.45 295	95.95 182	98.22 203	92.66 244	97.04 192	97.89 167	63.52 373	99.72 85	96.19 90	99.82 35	99.21 126

FMVSNet5		93.39 276	92.35 286	96.50 191	95.83 332	90.81 233	97.31 104	98.27 198	92.74 242	96.27 237	98.28 117	62.23 374	99.67 124	90.86 266	99.36 162	99.03 163

IB-MVS	85.98 20	88.63 330	86.95 339	93.68 306	95.12 346	84.82 334	90.85 344	90.17 362	87.55 308	88.48 364	91.34 363	58.01 375	99.59 150	87.24 328	93.80 358	96.63 335
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		88.28 333	86.96 338	92.23 335	92.84 371	84.44 337	98.19 52	74.60 378	99.08 10	87.01 369	99.47 10	56.93 376	98.23 343	78.91 362	95.61 345	94.01 360

KD-MVS_2432*1600		88.93 328	87.74 333	92.49 329	88.04 378	81.99 351	89.63 359	95.62 308	91.35 264	95.06 276	93.11 338	56.58 377	98.63 317	85.19 341	95.07 348	96.85 325

miper_refine_blended		88.93 328	87.74 333	92.49 329	88.04 378	81.99 351	89.63 359	95.62 308	91.35 264	95.06 276	93.11 338	56.58 377	98.63 317	85.19 341	95.07 348	96.85 325

GG-mvs-BLEND				90.60 343	91.00 375	84.21 340	98.23 46	72.63 381		82.76 372	84.11 373	56.14 379	96.79 364	72.20 371	92.09 363	90.78 370

TESTMET0.1,1		87.20 338	86.57 340	89.07 349	93.62 365	72.84 376	89.89 354	87.01 370	85.46 330	89.12 362	90.20 369	56.00 380	97.72 353	90.91 265	96.92 320	96.64 333

test2506		89.86 322	89.16 327	91.97 336	98.95 104	76.83 368	98.54 23	61.07 382	96.20 116	97.07 190	99.16 36	55.19 381	99.69 114	96.43 81	99.83 33	99.38 92

test-mter		87.92 336	87.17 337	90.16 345	94.24 357	74.98 372	89.89 354	89.06 364	86.44 320	89.97 357	90.77 367	54.96 382	98.57 322	91.88 246	97.36 314	96.92 320

test123		12.59 345	15.49 348	3.87 360	6.07 383	2.55 384	90.75 346	2.59 385	2.52 378	5.20 380	13.02 377	4.96 383	1.85 380	5.20 377	9.09 377	7.23 375

testmvs		12.33 346	15.23 349	3.64 361	5.77 384	2.23 385	88.99 361	3.62 384	2.30 379	5.29 379	13.09 376	4.52 384	1.95 379	5.16 378	8.32 378	6.75 376

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		7.91 348	10.55 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	94.94 318	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

FOURS1					99.59 18	98.20 7	99.03 7	99.25 22	98.96 18	98.87 46

MSC_two_6792asdad				98.22 75	97.75 247	95.34 110		98.16 217					99.75 66	95.87 109	99.51 120	99.57 37

No_MVS				98.22 75	97.75 247	95.34 110		98.16 217					99.75 66	95.87 109	99.51 120	99.57 37

eth-test2					0.00 385

eth-test					0.00 385

IU-MVS					99.22 65	95.40 103		98.14 220	85.77 327	98.36 89				95.23 148	99.51 120	99.49 58

save fliter					98.48 162	94.71 131	94.53 253	98.41 182	95.02 175

test_0728_SECOND				98.25 73	99.23 62	95.49 101	96.74 138	98.89 90					99.75 66	95.48 131	99.52 115	99.53 47

GSMVS																98.06 275

test_part2					99.03 100	96.07 74				98.08 122

MTGPA								98.73 136

MTMP							96.55 146	74.60 378

gm-plane-assit					91.79 374	71.40 378			81.67 350		90.11 370		98.99 283	84.86 345

test9_res														91.29 255	98.89 231	99.00 167

agg_prior2														90.34 286	98.90 228	99.10 155

agg_prior					97.80 235	94.96 126		98.36 189		93.49 318			99.53 167

test_prior4						95.38 105	93.61 292

test_prior				97.46 133	97.79 240	94.26 152		98.42 181					99.34 226			98.79 201

旧先验2							93.35 299		77.95 366	95.77 262			98.67 315	90.74 274

新几何2							93.43 295

无先验							93.20 302	97.91 235	80.78 355				99.40 209	87.71 319		97.94 286

原ACMM2							92.82 307

testdata2													99.46 188	87.84 317

testdata1							92.77 308		93.78 209

plane_prior7					98.70 130	94.67 134

plane_prior5								98.75 133					99.46 188	92.59 236	99.20 194	99.28 113

plane_prior4											96.77 254

plane_prior3						94.51 138			95.29 163	96.16 244

plane_prior2							96.50 148		96.36 109

plane_prior1					98.49 160

plane_prior						94.29 147	95.42 208		94.31 196						98.93 226

n2								0.00 386

nn								0.00 386

door-mid								98.17 213

test11								98.08 226

door								97.81 244

HQP5-MVS						92.47 197

HQP-NCC					97.85 222		94.26 258		93.18 226	92.86 331

ACMP_Plane					97.85 222		94.26 258		93.18 226	92.86 331

BP-MVS														90.51 281

HQP4-MVS										92.87 330			99.23 252			99.06 160

HQP3-MVS								98.43 178							98.74 246

NP-MVS					98.14 200	93.72 168					95.08 314

ACMMP++_ref															99.52 115

ACMMP++															99.55 103

High-resolution multi-view benchmark