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.

PC_three_1452									90.77 158	98.89 8	98.28 51	96.24 1	98.35 198	95.76 59	99.58 21	99.59 19

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 58	95.39 11	99.29 1	98.28 27	94.78 31	98.93 6	98.87 6	96.04 2	99.86 8	97.45 13	99.58 21	99.59 19

OPU-MVS				98.55 3	98.82 52	96.86 3	98.25 36				98.26 52	96.04 2	99.24 111	95.36 75	99.59 17	99.56 25

test_0728_THIRD									94.78 31	98.73 10	98.87 6	95.87 4	99.84 21	97.45 13	99.72 2	99.77 1

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 30	95.13 16	99.19 1	98.89 4	95.54 5	99.85 16	97.52 9	99.66 10	99.56 25

test_241102_ONE					99.42 7	95.30 17		98.27 30	95.09 19	99.19 1	98.81 10	95.54 5	99.65 49

test_one_0601					99.32 22	95.20 20		98.25 35	95.13 16	98.48 16	98.87 6	95.16 7

DVP-MVS		97.91 3	97.81 3	98.22 12	99.45 3	95.36 13	98.21 43	97.85 105	94.92 22	98.73 10	98.87 6	95.08 8	99.84 21	97.52 9	99.67 6	99.48 39
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					99.45 3	95.36 13	98.31 29	98.29 25	94.92 22	98.99 4	98.92 2	95.08 8

DPE-MVS		97.86 4	97.65 5	98.47 5	99.17 32	95.78 7	97.21 144	98.35 20	95.16 15	98.71 12	98.80 11	95.05 10	99.89 3	96.70 27	99.73 1	99.73 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_241102_TWO								98.27 30	95.13 16	98.93 6	98.89 4	94.99 11	99.85 16	97.52 9	99.65 12	99.74 7

SteuartSystems-ACMMP		97.62 7	97.53 7	97.87 22	98.39 76	94.25 36	98.43 24	98.27 30	95.34 10	98.11 19	98.56 18	94.53 12	99.71 37	96.57 31	99.62 15	99.65 12
Skip Steuart: Steuart Systems R&D Blog.
CNVR-MVS		97.68 6	97.44 9	98.37 7	98.90 50	95.86 6	97.27 136	98.08 63	95.81 4	97.87 27	98.31 46	94.26 13	99.68 45	97.02 20	99.49 36	99.57 22

SD-MVS		97.41 10	97.53 7	97.06 60	98.57 69	94.46 30	97.92 65	98.14 53	94.82 28	99.01 3	98.55 20	94.18 14	97.41 303	96.94 21	99.64 13	99.32 55
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
MSP-MVS		97.59 8	97.54 6	97.73 34	99.40 11	93.77 52	98.53 15	98.29 25	95.55 6	98.56 14	97.81 85	93.90 15	99.65 49	96.62 28	99.21 64	99.77 1
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
MCST-MVS		97.18 16	96.84 25	98.20 13	99.30 24	95.35 15	97.12 151	98.07 68	93.54 70	96.08 80	97.69 92	93.86 16	99.71 37	96.50 32	99.39 48	99.55 28

APDe-MVS		97.82 5	97.73 4	98.08 17	99.15 33	94.82 26	98.81 7	98.30 24	94.76 33	98.30 17	98.90 3	93.77 17	99.68 45	97.93 1	99.69 3	99.75 5

TSAR-MVS + MP.		97.42 9	97.33 11	97.69 38	99.25 27	94.24 37	98.07 52	97.85 105	93.72 62	98.57 13	98.35 37	93.69 18	99.40 97	97.06 19	99.46 39	99.44 43
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
patch_mono-2		96.83 33	97.44 9	95.01 157	99.05 39	85.39 282	96.98 160	98.77 5	94.70 35	97.99 23	98.66 14	93.61 19	99.91 1	97.67 5	99.50 33	99.72 10

DeepPCF-MVS	93.97 1	96.61 42	97.09 13	95.15 149	98.09 98	86.63 262	96.00 237	98.15 51	95.43 7	97.95 24	98.56 18	93.40 20	99.36 101	96.77 25	99.48 37	99.45 41

SF-MVS		97.39 11	97.13 12	98.17 14	99.02 42	95.28 19	98.23 40	98.27 30	92.37 113	98.27 18	98.65 16	93.33 21	99.72 36	96.49 33	99.52 28	99.51 33

SMA-MVS		97.35 12	97.03 18	98.30 8	99.06 38	95.42 10	97.94 63	98.18 46	90.57 173	98.85 9	98.94 1	93.33 21	99.83 24	96.72 26	99.68 4	99.63 14
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
NCCC		97.30 14	97.03 18	98.11 16	98.77 53	95.06 24	97.34 129	98.04 78	95.96 2	97.09 43	97.88 78	93.18 23	99.71 37	95.84 57	99.17 67	99.56 25

9.14			96.75 31		98.93 47		97.73 82	98.23 40	91.28 145	97.88 26	98.44 31	93.00 24	99.65 49	95.76 59	99.47 38

segment_acmp												92.89 25

TSAR-MVS + GP.		96.69 39	96.49 41	97.27 52	98.31 80	93.39 58	96.79 173	96.72 221	94.17 50	97.44 31	97.66 96	92.76 26	99.33 102	96.86 24	97.76 117	99.08 76

dcpmvs_2		96.37 48	97.05 16	94.31 196	98.96 46	84.11 299	97.56 105	97.51 139	93.92 56	97.43 33	98.52 22	92.75 27	99.32 104	97.32 17	99.50 33	99.51 33

TEST9					98.70 56	94.19 38	96.41 206	98.02 83	88.17 237	96.03 81	97.56 107	92.74 28	99.59 61

train_agg		96.30 50	95.83 56	97.72 35	98.70 56	94.19 38	96.41 206	98.02 83	88.58 226	96.03 81	97.56 107	92.73 29	99.59 61	95.04 81	99.37 52	99.39 49

test_8					98.67 58	94.06 45	96.37 214	98.01 86	88.58 226	95.98 85	97.55 109	92.73 29	99.58 64

CSCG		96.05 54	95.91 54	96.46 81	99.24 28	90.47 152	98.30 30	98.57 12	89.01 209	93.97 131	97.57 105	92.62 31	99.76 31	94.66 93	99.27 57	99.15 68

HPM-MVS++		97.34 13	96.97 20	98.47 5	99.08 36	96.16 4	97.55 108	97.97 90	95.59 5	96.61 60	97.89 76	92.57 32	99.84 21	95.95 52	99.51 31	99.40 48

ZD-MVS					99.05 39	94.59 28		98.08 63	89.22 204	97.03 45	98.10 59	92.52 33	99.65 49	94.58 96	99.31 55

PHI-MVS		96.77 36	96.46 44	97.71 37	98.40 74	94.07 44	98.21 43	98.45 16	89.86 185	97.11 42	98.01 69	92.52 33	99.69 43	96.03 50	99.53 27	99.36 53

APD-MVS		96.95 25	96.60 36	98.01 18	99.03 41	94.93 25	97.72 85	98.10 61	91.50 135	98.01 22	98.32 45	92.33 35	99.58 64	94.85 86	99.51 31	99.53 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		96.68 41	96.58 38	96.99 61	98.46 70	92.31 86	96.20 228	98.90 2	94.30 48	95.86 88	97.74 90	92.33 35	99.38 100	96.04 49	99.42 44	99.28 58

MSLP-MVS++		96.94 26	97.06 14	96.59 70	98.72 55	91.86 99	97.67 90	98.49 13	94.66 38	97.24 37	98.41 34	92.31 37	98.94 145	96.61 29	99.46 39	98.96 87

旧先验1					98.38 77	93.38 59		97.75 111			98.09 61	92.30 38			99.01 76	99.16 66

HFP-MVS		97.14 18	96.92 22	97.83 24	99.42 7	94.12 42	98.52 16	98.32 22	93.21 82	97.18 38	98.29 49	92.08 39	99.83 24	95.63 66	99.59 17	99.54 29

test_prior2							96.35 215		92.80 103	96.03 81	97.59 104	92.01 40		95.01 83	99.38 49

CDPH-MVS		95.97 57	95.38 65	97.77 31	98.93 47	94.44 31	96.35 215	97.88 98	86.98 268	96.65 58	97.89 76	91.99 41	99.47 89	92.26 134	99.46 39	99.39 49

CP-MVS		97.02 22	96.81 28	97.64 41	99.33 21	93.54 55	98.80 8	98.28 27	92.99 91	96.45 70	98.30 48	91.90 42	99.85 16	95.61 68	99.68 4	99.54 29

CS-MVS		96.86 30	97.06 14	96.26 97	98.16 95	91.16 130	99.09 3	97.87 100	95.30 11	97.06 44	98.03 66	91.72 43	98.71 167	97.10 18	99.17 67	98.90 95

DPM-MVS		95.69 62	94.92 75	98.01 18	98.08 99	95.71 9	95.27 268	97.62 127	90.43 176	95.55 99	97.07 128	91.72 43	99.50 86	89.62 189	98.94 79	98.82 104

XVS		97.18 16	96.96 21	97.81 26	99.38 14	94.03 46	98.59 12	98.20 42	94.85 24	96.59 62	98.29 49	91.70 45	99.80 28	95.66 61	99.40 46	99.62 15

X-MVStestdata		91.71 198	89.67 257	97.81 26	99.38 14	94.03 46	98.59 12	98.20 42	94.85 24	96.59 62	32.69 374	91.70 45	99.80 28	95.66 61	99.40 46	99.62 15

ZNCC-MVS		96.96 24	96.67 34	97.85 23	99.37 16	94.12 42	98.49 20	98.18 46	92.64 108	96.39 72	98.18 56	91.61 47	99.88 4	95.59 71	99.55 24	99.57 22

ACMMP_NAP		97.20 15	96.86 23	98.23 11	99.09 34	95.16 22	97.60 101	98.19 44	92.82 102	97.93 25	98.74 13	91.60 48	99.86 8	96.26 36	99.52 28	99.67 11

region2R		97.07 20	96.84 25	97.77 31	99.46 2	93.79 50	98.52 16	98.24 37	93.19 85	97.14 40	98.34 40	91.59 49	99.87 7	95.46 73	99.59 17	99.64 13

DELS-MVS		96.61 42	96.38 47	97.30 49	97.79 113	93.19 65	95.96 239	98.18 46	95.23 12	95.87 87	97.65 97	91.45 50	99.70 42	95.87 53	99.44 43	99.00 85
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
SR-MVS		97.01 23	96.86 23	97.47 44	99.09 34	93.27 64	97.98 57	98.07 68	93.75 61	97.45 30	98.48 28	91.43 51	99.59 61	96.22 39	99.27 57	99.54 29

SR-MVS-dyc-post		96.88 29	96.80 29	97.11 59	99.02 42	92.34 84	97.98 57	98.03 80	93.52 72	97.43 33	98.51 23	91.40 52	99.56 72	96.05 47	99.26 59	99.43 45

GST-MVS		96.85 32	96.52 40	97.82 25	99.36 18	94.14 41	98.29 31	98.13 54	92.72 105	96.70 54	98.06 63	91.35 53	99.86 8	94.83 87	99.28 56	99.47 40

ACMMPR		97.07 20	96.84 25	97.79 28	99.44 6	93.88 48	98.52 16	98.31 23	93.21 82	97.15 39	98.33 43	91.35 53	99.86 8	95.63 66	99.59 17	99.62 15

CS-MVS-test		96.89 28	97.04 17	96.45 82	98.29 81	91.66 104	99.03 4	97.85 105	95.84 3	96.90 47	97.97 72	91.24 55	98.75 161	96.92 22	99.33 53	98.94 90

DeepC-MVS_fast	93.89 2	96.93 27	96.64 35	97.78 29	98.64 64	94.30 33	97.41 120	98.04 78	94.81 29	96.59 62	98.37 36	91.24 55	99.64 56	95.16 79	99.52 28	99.42 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ETV-MVS		96.02 55	95.89 55	96.40 85	97.16 138	92.44 82	97.47 117	97.77 110	94.55 40	96.48 67	94.51 257	91.23 57	98.92 146	95.65 64	98.19 104	97.82 165

PGM-MVS		96.81 34	96.53 39	97.65 39	99.35 20	93.53 56	97.65 93	98.98 1	92.22 115	97.14 40	98.44 31	91.17 58	99.85 16	94.35 98	99.46 39	99.57 22

MP-MVS-pluss		96.70 38	96.27 49	97.98 20	99.23 30	94.71 27	96.96 162	98.06 71	90.67 164	95.55 99	98.78 12	91.07 59	99.86 8	96.58 30	99.55 24	99.38 51
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mPP-MVS		96.86 30	96.60 36	97.64 41	99.40 11	93.44 57	98.50 19	98.09 62	93.27 81	95.95 86	98.33 43	91.04 60	99.88 4	95.20 78	99.57 23	99.60 18

HPM-MVS		96.69 39	96.45 45	97.40 46	99.36 18	93.11 67	98.87 6	98.06 71	91.17 150	96.40 71	97.99 70	90.99 61	99.58 64	95.61 68	99.61 16	99.49 37
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
APD-MVS_3200maxsize		96.81 34	96.71 33	97.12 58	99.01 45	92.31 86	97.98 57	98.06 71	93.11 88	97.44 31	98.55 20	90.93 62	99.55 74	96.06 46	99.25 61	99.51 33

test12				97.65 39	98.46 70	94.26 35		97.66 122		95.52 102		90.89 63	99.46 90		99.25 61	99.22 63

MTAPA		97.08 19	96.78 30	97.97 21	99.37 16	94.42 32	97.24 138	98.08 63	95.07 20	96.11 79	98.59 17	90.88 64	99.90 2	96.18 45	99.50 33	99.58 21

EI-MVSNet-Vis-set		96.51 44	96.47 42	96.63 67	98.24 85	91.20 125	96.89 166	97.73 114	94.74 34	96.49 66	98.49 25	90.88 64	99.58 64	96.44 34	98.32 100	99.13 70

RE-MVS-def			96.72 32		99.02 42	92.34 84	97.98 57	98.03 80	93.52 72	97.43 33	98.51 23	90.71 66		96.05 47	99.26 59	99.43 45

EIA-MVS		95.53 68	95.47 61	95.71 124	97.06 147	89.63 172	97.82 74	97.87 100	93.57 66	93.92 132	95.04 234	90.61 67	98.95 144	94.62 95	98.68 87	98.54 118

MP-MVS		96.77 36	96.45 45	97.72 35	99.39 13	93.80 49	98.41 25	98.06 71	93.37 78	95.54 101	98.34 40	90.59 68	99.88 4	94.83 87	99.54 26	99.49 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EI-MVSNet-UG-set		96.34 49	96.30 48	96.47 79	98.20 90	90.93 137	96.86 167	97.72 116	94.67 37	96.16 78	98.46 29	90.43 69	99.58 64	96.23 38	97.96 111	98.90 95

原ACMM1				96.38 88	98.59 66	91.09 132		97.89 96	87.41 260	95.22 106	97.68 93	90.25 70	99.54 76	87.95 219	99.12 72	98.49 125

HPM-MVS_fast		96.51 44	96.27 49	97.22 54	99.32 22	92.74 74	98.74 9	98.06 71	90.57 173	96.77 51	98.35 37	90.21 71	99.53 78	94.80 90	99.63 14	99.38 51

testdata				95.46 141	98.18 94	88.90 203		97.66 122	82.73 327	97.03 45	98.07 62	90.06 72	98.85 151	89.67 187	98.98 77	98.64 115

新几何1				97.32 48	98.60 65	93.59 54		97.75 111	81.58 334	95.75 92	97.85 82	90.04 73	99.67 47	86.50 251	99.13 71	98.69 112

DP-MVS Recon		95.68 63	95.12 73	97.37 47	99.19 31	94.19 38	97.03 153	98.08 63	88.35 233	95.09 109	97.65 97	89.97 74	99.48 88	92.08 143	98.59 90	98.44 133

MVS_111021_LR		96.24 52	96.19 51	96.39 87	98.23 89	91.35 117	96.24 226	98.79 4	93.99 54	95.80 90	97.65 97	89.92 75	99.24 111	95.87 53	99.20 65	98.58 116

EPP-MVSNet		95.22 76	95.04 74	95.76 117	97.49 130	89.56 176	98.67 10	97.00 199	90.69 162	94.24 123	97.62 102	89.79 76	98.81 154	93.39 119	96.49 150	98.92 93

DROMVSNet		96.42 46	96.47 42	96.26 97	97.01 152	91.52 110	98.89 5	97.75 111	94.42 43	96.64 59	97.68 93	89.32 77	98.60 176	97.45 13	99.11 73	98.67 114

PAPR		94.18 99	93.42 118	96.48 78	97.64 122	91.42 116	95.55 254	97.71 120	88.99 210	92.34 166	95.82 198	89.19 78	99.11 125	86.14 257	97.38 126	98.90 95

MG-MVS		95.61 65	95.38 65	96.31 92	98.42 73	90.53 150	96.04 234	97.48 142	93.47 74	95.67 96	98.10 59	89.17 79	99.25 110	91.27 161	98.77 84	99.13 70

PAPM_NR		95.01 80	94.59 83	96.26 97	98.89 51	90.68 147	97.24 138	97.73 114	91.80 129	92.93 157	96.62 161	89.13 80	99.14 122	89.21 201	97.78 115	98.97 86

mvsany_test1		93.93 113	93.98 97	93.78 225	94.94 260	86.80 255	94.62 280	92.55 345	88.77 223	96.85 48	98.49 25	88.98 81	98.08 227	95.03 82	95.62 166	96.46 209

ACMMP		96.27 51	95.93 53	97.28 51	99.24 28	92.62 77	98.25 36	98.81 3	92.99 91	94.56 117	98.39 35	88.96 82	99.85 16	94.57 97	97.63 118	99.36 53
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
UA-Net		95.95 58	95.53 59	97.20 56	97.67 118	92.98 70	97.65 93	98.13 54	94.81 29	96.61 60	98.35 37	88.87 83	99.51 83	90.36 174	97.35 128	99.11 74

API-MVS		94.84 89	94.49 89	95.90 113	97.90 108	92.00 96	97.80 76	97.48 142	89.19 205	94.81 112	96.71 144	88.84 84	99.17 118	88.91 207	98.76 85	96.53 204

test222					98.24 85	92.21 89	95.33 263	97.60 128	79.22 347	95.25 104	97.84 84	88.80 85			99.15 69	98.72 109

Test By Simon												88.73 86

pcd_1.5k_mvsjas		7.39 348	9.85 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	88.65 87	0.00 381	0.00 379	0.00 379	0.00 377

PS-MVSNAJss		93.74 121	93.51 111	94.44 188	93.91 301	89.28 193	97.75 79	97.56 135	92.50 110	89.94 223	96.54 164	88.65 87	98.18 212	93.83 111	90.90 240	95.86 224

PS-MVSNAJ		95.37 70	95.33 67	95.49 137	97.35 132	90.66 148	95.31 265	97.48 142	93.85 59	96.51 65	95.70 208	88.65 87	99.65 49	94.80 90	98.27 101	96.17 214

xiu_mvs_v2_base		95.32 72	95.29 68	95.40 142	97.22 134	90.50 151	95.44 259	97.44 156	93.70 64	96.46 69	96.18 180	88.59 90	99.53 78	94.79 92	97.81 114	96.17 214

PLC	91.00 6	94.11 105	93.43 116	96.13 103	98.58 68	91.15 131	96.69 184	97.39 162	87.29 263	91.37 186	96.71 144	88.39 91	99.52 82	87.33 238	97.13 137	97.73 167
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UniMVSNet_NR-MVSNet		93.37 133	92.67 143	95.47 140	95.34 235	92.83 72	97.17 147	98.58 11	92.98 96	90.13 214	95.80 199	88.37 92	97.85 263	91.71 151	83.93 316	95.73 240

PVSNet_BlendedMVS		94.06 107	93.92 98	94.47 187	98.27 82	89.46 183	96.73 178	98.36 17	90.17 179	94.36 120	95.24 228	88.02 93	99.58 64	93.44 116	90.72 243	94.36 310

PVSNet_Blended		94.87 88	94.56 85	95.81 116	98.27 82	89.46 183	95.47 258	98.36 17	88.84 217	94.36 120	96.09 188	88.02 93	99.58 64	93.44 116	98.18 105	98.40 136

TAPA-MVS	90.10 7	92.30 179	91.22 196	95.56 131	98.33 79	89.60 174	96.79 173	97.65 124	81.83 332	91.52 182	97.23 120	87.94 95	98.91 148	71.31 355	98.37 99	98.17 147
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
casdiffmvs_mvg		95.81 61	95.57 58	96.51 75	96.87 157	91.49 111	97.50 111	97.56 135	93.99 54	95.13 108	97.92 75	87.89 96	98.78 156	95.97 51	97.33 129	99.26 60
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		94.89 87	94.62 82	95.68 125	96.83 161	89.55 177	96.70 182	97.17 179	91.17 150	95.60 98	96.11 187	87.87 97	98.76 160	93.01 129	97.17 136	98.72 109

UniMVSNet (Re)		93.31 135	92.55 149	95.61 129	95.39 229	93.34 62	97.39 125	98.71 6	93.14 87	90.10 218	94.83 244	87.71 98	98.03 238	91.67 154	83.99 315	95.46 251

FC-MVSNet-test		93.94 112	93.57 105	95.04 154	95.48 226	91.45 115	98.12 48	98.71 6	93.37 78	90.23 209	96.70 146	87.66 99	97.85 263	91.49 156	90.39 248	95.83 228

canonicalmvs		96.02 55	95.45 62	97.75 33	97.59 126	95.15 23	98.28 32	97.60 128	94.52 41	96.27 75	96.12 184	87.65 100	99.18 117	96.20 44	94.82 179	98.91 94

FIs		94.09 106	93.70 102	95.27 145	95.70 217	92.03 95	98.10 49	98.68 8	93.36 80	90.39 206	96.70 146	87.63 101	97.94 253	92.25 136	90.50 247	95.84 227

CDS-MVSNet		94.14 104	93.54 107	95.93 112	96.18 198	91.46 114	96.33 217	97.04 195	88.97 212	93.56 137	96.51 165	87.55 102	97.89 261	89.80 183	95.95 157	98.44 133
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+		94.93 85	94.45 91	96.36 90	96.61 171	91.47 113	96.41 206	97.41 161	91.02 155	94.50 118	95.92 192	87.53 103	98.78 156	93.89 108	96.81 141	98.84 103

casdiffmvs		95.64 64	95.49 60	96.08 104	96.76 168	90.45 153	97.29 135	97.44 156	94.00 53	95.46 103	97.98 71	87.52 104	98.73 163	95.64 65	97.33 129	99.08 76
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		95.27 73	94.91 76	96.38 88	98.20 90	90.86 139	97.27 136	98.25 35	90.21 178	94.18 125	97.27 117	87.48 105	99.73 33	93.53 113	97.77 116	98.55 117

mvs_anonymous		93.82 118	93.74 101	94.06 205	96.44 186	85.41 280	95.81 245	97.05 193	89.85 187	90.09 219	96.36 173	87.44 106	97.75 273	93.97 104	96.69 146	99.02 79

CANet		96.39 47	96.02 52	97.50 43	97.62 123	93.38 59	97.02 155	97.96 91	95.42 8	94.86 111	97.81 85	87.38 107	99.82 26	96.88 23	99.20 65	99.29 56

baseline		95.58 66	95.42 64	96.08 104	96.78 164	90.41 155	97.16 148	97.45 152	93.69 65	95.65 97	97.85 82	87.29 108	98.68 169	95.66 61	97.25 133	99.13 70

TAMVS		94.01 110	93.46 113	95.64 126	96.16 200	90.45 153	96.71 181	96.89 211	89.27 203	93.46 142	96.92 137	87.29 108	97.94 253	88.70 211	95.74 162	98.53 119

nrg030		94.05 108	93.31 120	96.27 96	95.22 246	94.59 28	98.34 27	97.46 147	92.93 99	91.21 196	96.64 152	87.23 110	98.22 207	94.99 84	85.80 288	95.98 223

CPTT-MVS		95.57 67	95.19 70	96.70 64	99.27 26	91.48 112	98.33 28	98.11 59	87.79 249	95.17 107	98.03 66	87.09 111	99.61 57	93.51 114	99.42 44	99.02 79

OMC-MVS		95.09 79	94.70 81	96.25 100	98.46 70	91.28 119	96.43 204	97.57 132	92.04 124	94.77 113	97.96 73	87.01 112	99.09 129	91.31 160	96.77 142	98.36 140

DeepC-MVS	93.07 3	96.06 53	95.66 57	97.29 50	97.96 102	93.17 66	97.30 134	98.06 71	93.92 56	93.38 144	98.66 14	86.83 113	99.73 33	95.60 70	99.22 63	98.96 87
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
IterMVS-LS		92.29 180	91.94 168	93.34 244	96.25 194	86.97 253	96.57 200	97.05 193	90.67 164	89.50 239	94.80 246	86.59 114	97.64 281	89.91 180	86.11 286	95.40 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		93.03 149	92.88 132	93.48 239	95.77 215	86.98 252	96.44 202	97.12 183	90.66 166	91.30 190	97.64 100	86.56 115	98.05 234	89.91 180	90.55 245	95.41 253

miper_enhance_ethall		91.54 208	91.01 201	93.15 251	95.35 234	87.07 251	93.97 303	96.90 209	86.79 272	89.17 249	93.43 306	86.55 116	97.64 281	89.97 179	86.93 278	94.74 299

1112_ss		93.37 133	92.42 155	96.21 101	97.05 149	90.99 133	96.31 219	96.72 221	86.87 271	89.83 227	96.69 148	86.51 117	99.14 122	88.12 216	93.67 194	98.50 123

diffmvs		95.25 74	95.13 72	95.63 127	96.43 187	89.34 188	95.99 238	97.35 168	92.83 101	96.31 73	97.37 114	86.44 118	98.67 170	96.26 36	97.19 135	98.87 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 93	94.02 96	96.79 63	97.71 117	92.05 94	96.59 197	97.35 168	90.61 170	94.64 115	96.93 134	86.41 119	99.39 98	91.20 163	94.71 183	98.94 90

EPNet		95.20 77	94.56 85	97.14 57	92.80 329	92.68 76	97.85 71	94.87 315	96.64 1	92.46 160	97.80 87	86.23 120	99.65 49	93.72 112	98.62 89	99.10 75
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		91.59 203	91.13 199	92.97 257	95.55 223	86.57 263	94.47 285	96.88 212	87.77 250	88.88 254	94.01 284	86.22 121	97.54 290	89.49 191	86.93 278	94.79 295

Fast-Effi-MVS+		93.46 130	92.75 139	95.59 130	96.77 165	90.03 159	96.81 172	97.13 182	88.19 236	91.30 190	94.27 273	86.21 122	98.63 173	87.66 230	96.46 152	98.12 149

MVSFormer		95.37 70	95.16 71	95.99 111	96.34 191	91.21 123	98.22 41	97.57 132	91.42 139	96.22 76	97.32 115	86.20 123	97.92 257	94.07 102	99.05 74	98.85 101

lupinMVS		94.99 84	94.56 85	96.29 95	96.34 191	91.21 123	95.83 244	96.27 248	88.93 214	96.22 76	96.88 139	86.20 123	98.85 151	95.27 77	99.05 74	98.82 104

114514_t		93.95 111	93.06 126	96.63 67	99.07 37	91.61 105	97.46 119	97.96 91	77.99 351	93.00 152	97.57 105	86.14 125	99.33 102	89.22 200	99.15 69	98.94 90

alignmvs		95.87 60	95.23 69	97.78 29	97.56 129	95.19 21	97.86 68	97.17 179	94.39 45	96.47 68	96.40 171	85.89 126	99.20 114	96.21 43	95.11 175	98.95 89

WR-MVS_H		92.00 191	91.35 187	93.95 214	95.09 253	89.47 181	98.04 54	98.68 8	91.46 137	88.34 265	94.68 251	85.86 127	97.56 288	85.77 265	84.24 313	94.82 290

Test_1112_low_res		92.84 160	91.84 171	95.85 115	97.04 150	89.97 165	95.53 256	96.64 229	85.38 294	89.65 233	95.18 229	85.86 127	99.10 126	87.70 226	93.58 199	98.49 125

HY-MVS	89.66 9	93.87 115	92.95 129	96.63 67	97.10 143	92.49 81	95.64 252	96.64 229	89.05 208	93.00 152	95.79 202	85.77 129	99.45 92	89.16 204	94.35 185	97.96 155

c3_l		91.38 215	90.89 203	92.88 261	95.58 221	86.30 266	94.68 279	96.84 216	88.17 237	88.83 257	94.23 276	85.65 130	97.47 297	89.36 194	84.63 306	94.89 285

IS-MVSNet		94.90 86	94.52 88	96.05 107	97.67 118	90.56 149	98.44 23	96.22 251	93.21 82	93.99 129	97.74 90	85.55 131	98.45 188	89.98 178	97.86 112	99.14 69

MVS		91.71 198	90.44 222	95.51 135	95.20 248	91.59 107	96.04 234	97.45 152	73.44 359	87.36 288	95.60 213	85.42 132	99.10 126	85.97 262	97.46 121	95.83 228

VNet		95.89 59	95.45 62	97.21 55	98.07 100	92.94 71	97.50 111	98.15 51	93.87 58	97.52 29	97.61 103	85.29 133	99.53 78	95.81 58	95.27 171	99.16 66

CNLPA		94.28 97	93.53 108	96.52 72	98.38 77	92.55 79	96.59 197	96.88 212	90.13 181	91.91 175	97.24 119	85.21 134	99.09 129	87.64 231	97.83 113	97.92 157

F-COLMAP		93.58 126	92.98 128	95.37 143	98.40 74	88.98 201	97.18 146	97.29 173	87.75 252	90.49 203	97.10 127	85.21 134	99.50 86	86.70 248	96.72 145	97.63 171

LCM-MVSNet-Re		92.50 167	92.52 152	92.44 272	96.82 163	81.89 320	96.92 164	93.71 334	92.41 112	84.30 319	94.60 255	85.08 136	97.03 316	91.51 155	97.36 127	98.40 136

NR-MVSNet		92.34 176	91.27 193	95.53 134	94.95 258	93.05 68	97.39 125	98.07 68	92.65 107	84.46 317	95.71 206	85.00 137	97.77 272	89.71 185	83.52 322	95.78 233

PAPM		91.52 209	90.30 228	95.20 147	95.30 241	89.83 168	93.38 323	96.85 215	86.26 282	88.59 261	95.80 199	84.88 138	98.15 214	75.67 341	95.93 158	97.63 171

MAR-MVS		94.22 98	93.46 113	96.51 75	98.00 101	92.19 91	97.67 90	97.47 145	88.13 240	93.00 152	95.84 196	84.86 139	99.51 83	87.99 218	98.17 106	97.83 164
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
jason		94.84 89	94.39 93	96.18 102	95.52 224	90.93 137	96.09 232	96.52 237	89.28 202	96.01 84	97.32 115	84.70 140	98.77 159	95.15 80	98.91 81	98.85 101
jason: jason.
sss		94.51 94	93.80 100	96.64 65	97.07 144	91.97 97	96.32 218	98.06 71	88.94 213	94.50 118	96.78 141	84.60 141	99.27 109	91.90 144	96.02 155	98.68 113

LS3D		93.57 127	92.61 147	96.47 79	97.59 126	91.61 105	97.67 90	97.72 116	85.17 299	90.29 208	98.34 40	84.60 141	99.73 33	83.85 291	98.27 101	98.06 154

Vis-MVSNet (Re-imp)		94.15 101	93.88 99	94.95 163	97.61 124	87.92 232	98.10 49	95.80 267	92.22 115	93.02 151	97.45 110	84.53 143	97.91 260	88.24 215	97.97 110	99.02 79

GeoE		93.89 114	93.28 121	95.72 123	96.96 155	89.75 170	98.24 39	96.92 208	89.47 197	92.12 171	97.21 121	84.42 144	98.39 195	87.71 225	96.50 149	99.01 82

cdsmvs_eth3d_5k		23.24 344	30.99 346	0.00 362	0.00 385	0.00 386	0.00 373	97.63 126	0.00 380	0.00 381	96.88 139	84.38 145	0.00 381	0.00 379	0.00 379	0.00 377

test_yl		94.78 91	94.23 94	96.43 83	97.74 115	91.22 121	96.85 168	97.10 185	91.23 147	95.71 93	96.93 134	84.30 146	99.31 106	93.10 122	95.12 173	98.75 106

DCV-MVSNet		94.78 91	94.23 94	96.43 83	97.74 115	91.22 121	96.85 168	97.10 185	91.23 147	95.71 93	96.93 134	84.30 146	99.31 106	93.10 122	95.12 173	98.75 106

CHOSEN 280x420		93.12 144	92.72 142	94.34 194	96.71 169	87.27 243	90.29 350	97.72 116	86.61 275	91.34 187	95.29 224	84.29 148	98.41 190	93.25 120	98.94 79	97.35 185

baseline1		92.82 161	91.90 169	95.55 133	97.20 136	90.77 144	97.19 145	94.58 320	92.20 117	92.36 164	96.34 174	84.16 149	98.21 208	89.20 202	83.90 319	97.68 170

eth_miper_zixun_eth		91.02 234	90.59 218	92.34 275	95.33 238	84.35 295	94.10 300	96.90 209	88.56 228	88.84 256	94.33 268	84.08 150	97.60 286	88.77 210	84.37 312	95.06 274

PCF-MVS	89.48 11	91.56 206	89.95 245	96.36 90	96.60 172	92.52 80	92.51 336	97.26 174	79.41 346	88.90 252	96.56 163	84.04 151	99.55 74	77.01 337	97.30 131	97.01 191
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
1314		92.81 162	92.03 164	95.14 150	95.33 238	89.52 180	96.04 234	97.44 156	87.72 253	86.25 303	95.33 223	83.84 152	98.79 155	89.26 198	97.05 138	97.11 190

DP-MVS		92.76 163	91.51 185	96.52 72	98.77 53	90.99 133	97.38 127	96.08 257	82.38 328	89.29 245	97.87 79	83.77 153	99.69 43	81.37 311	96.69 146	98.89 98

3Dnovator+	91.43 4	95.40 69	94.48 90	98.16 15	96.90 156	95.34 16	98.48 21	97.87 100	94.65 39	88.53 263	98.02 68	83.69 154	99.71 37	93.18 121	98.96 78	99.44 43

h-mvs33		94.15 101	93.52 110	96.04 108	97.81 112	90.22 157	97.62 100	97.58 131	95.19 13	96.74 52	97.45 110	83.67 155	99.61 57	95.85 55	79.73 338	98.29 143

hse-mvs2		93.45 131	92.99 127	94.81 171	97.02 151	88.59 209	96.69 184	96.47 240	95.19 13	96.74 52	96.16 183	83.67 155	98.48 187	95.85 55	79.13 342	97.35 185

AdaColmap		94.34 96	93.68 103	96.31 92	98.59 66	91.68 103	96.59 197	97.81 109	89.87 184	92.15 169	97.06 129	83.62 157	99.54 76	89.34 195	98.07 108	97.70 169

DU-MVS		92.90 156	92.04 163	95.49 137	94.95 258	92.83 72	97.16 148	98.24 37	93.02 90	90.13 214	95.71 206	83.47 158	97.85 263	91.71 151	83.93 316	95.78 233

Baseline_NR-MVSNet		91.20 226	90.62 216	92.95 258	93.83 304	88.03 229	97.01 158	95.12 301	88.42 231	89.70 230	95.13 232	83.47 158	97.44 300	89.66 188	83.24 324	93.37 328

miper_lstm_enhance		90.50 253	90.06 243	91.83 287	95.33 238	83.74 303	93.86 309	96.70 225	87.56 257	87.79 279	93.81 292	83.45 160	96.92 322	87.39 236	84.62 307	94.82 290

EPNet_dtu		91.71 198	91.28 192	92.99 256	93.76 306	83.71 305	96.69 184	95.28 292	93.15 86	87.02 295	95.95 191	83.37 161	97.38 305	79.46 323	96.84 140	97.88 160
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FA-MVS(test-final)		93.52 129	92.92 130	95.31 144	96.77 165	88.54 212	94.82 276	96.21 253	89.61 192	94.20 124	95.25 227	83.24 162	99.14 122	90.01 177	96.16 154	98.25 144

BH-untuned		92.94 154	92.62 146	93.92 219	97.22 134	86.16 271	96.40 210	96.25 250	90.06 182	89.79 228	96.17 182	83.19 163	98.35 198	87.19 241	97.27 132	97.24 187

TranMVSNet+NR-MVSNet		92.50 167	91.63 178	95.14 150	94.76 270	92.07 93	97.53 109	98.11 59	92.90 100	89.56 236	96.12 184	83.16 164	97.60 286	89.30 196	83.20 325	95.75 238

CHOSEN 1792x2688		94.15 101	93.51 111	96.06 106	98.27 82	89.38 186	95.18 272	98.48 15	85.60 291	93.76 135	97.11 126	83.15 165	99.61 57	91.33 159	98.72 86	99.19 64

PMMVS		92.86 158	92.34 156	94.42 190	94.92 261	86.73 258	94.53 284	96.38 244	84.78 306	94.27 122	95.12 233	83.13 166	98.40 191	91.47 157	96.49 150	98.12 149

Effi-MVS+-dtu		93.08 146	93.21 123	92.68 269	96.02 208	83.25 309	97.14 150	96.72 221	93.85 59	91.20 197	93.44 304	83.08 167	98.30 202	91.69 153	95.73 163	96.50 206

v8		91.29 223	90.53 221	93.57 236	94.15 294	88.12 227	97.34 129	97.06 192	88.99 210	88.32 266	94.26 275	83.08 167	98.01 240	87.62 232	83.92 318	94.57 304

mvsmamba		93.83 117	93.46 113	94.93 166	94.88 265	90.85 140	98.55 14	95.49 283	94.24 49	91.29 193	96.97 133	83.04 169	98.14 215	95.56 72	91.17 233	95.78 233

DIV-MVS_self_test		90.97 237	90.33 225	92.88 261	95.36 233	86.19 270	94.46 287	96.63 232	87.82 246	88.18 272	94.23 276	82.99 170	97.53 292	87.72 223	85.57 290	94.93 281

cl____		90.96 238	90.32 226	92.89 260	95.37 232	86.21 269	94.46 287	96.64 229	87.82 246	88.15 273	94.18 279	82.98 171	97.54 290	87.70 226	85.59 289	94.92 283

BH-w/o		92.14 188	91.75 173	93.31 245	96.99 154	85.73 275	95.67 249	95.69 272	88.73 224	89.26 247	94.82 245	82.97 172	98.07 231	85.26 272	96.32 153	96.13 218

v148		90.99 235	90.38 224	92.81 264	93.83 304	85.80 274	96.78 175	96.68 226	89.45 198	88.75 259	93.93 288	82.96 173	97.82 267	87.83 221	83.25 323	94.80 293

HyFIR lowres test		93.66 123	92.92 130	95.87 114	98.24 85	89.88 167	94.58 282	98.49 13	85.06 301	93.78 134	95.78 203	82.86 174	98.67 170	91.77 149	95.71 164	99.07 78

test_djsdf		93.07 147	92.76 137	94.00 209	93.49 315	88.70 207	98.22 41	97.57 132	91.42 139	90.08 220	95.55 216	82.85 175	97.92 257	94.07 102	91.58 223	95.40 256

PatchmatchNet		91.91 193	91.35 187	93.59 234	95.38 230	84.11 299	93.15 327	95.39 285	89.54 194	92.10 172	93.68 297	82.82 176	98.13 216	84.81 276	95.32 170	98.52 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												82.76 177				98.45 130

xiu_mvs_v1_base_debu		95.01 80	94.76 78	95.75 119	96.58 174	91.71 100	96.25 223	97.35 168	92.99 91	96.70 54	96.63 158	82.67 178	99.44 93	96.22 39	97.46 121	96.11 219

xiu_mvs_v1_base		95.01 80	94.76 78	95.75 119	96.58 174	91.71 100	96.25 223	97.35 168	92.99 91	96.70 54	96.63 158	82.67 178	99.44 93	96.22 39	97.46 121	96.11 219

xiu_mvs_v1_base_debi		95.01 80	94.76 78	95.75 119	96.58 174	91.71 100	96.25 223	97.35 168	92.99 91	96.70 54	96.63 158	82.67 178	99.44 93	96.22 39	97.46 121	96.11 219

patchmatchnet-post											90.45 337	82.65 181	98.10 223

V42		91.58 205	90.87 204	93.73 226	94.05 298	88.50 214	97.32 132	96.97 200	88.80 222	89.71 229	94.33 268	82.54 182	98.05 234	89.01 205	85.07 300	94.64 303

WR-MVS		92.34 176	91.53 182	94.77 176	95.13 251	90.83 141	96.40 210	97.98 89	91.88 128	89.29 245	95.54 217	82.50 183	97.80 268	89.79 184	85.27 296	95.69 242

tpmrst		91.44 212	91.32 189	91.79 290	95.15 249	79.20 346	93.42 322	95.37 287	88.55 229	93.49 141	93.67 298	82.49 184	98.27 204	90.41 172	89.34 257	97.90 158

MDTV_nov1_ep13_2view						70.35 362	93.10 329		83.88 316	93.55 138		82.47 185		86.25 254		98.38 138

XVG-OURS-SEG-HR		93.86 116	93.55 106	94.81 171	97.06 147	88.53 213	95.28 266	97.45 152	91.68 132	94.08 128	97.68 93	82.41 186	98.90 149	93.84 110	92.47 208	96.98 192

QAPM		93.45 131	92.27 158	96.98 62	96.77 165	92.62 77	98.39 26	98.12 56	84.50 309	88.27 269	97.77 88	82.39 187	99.81 27	85.40 270	98.81 83	98.51 122

Patchmatch-test		89.42 272	87.99 279	93.70 229	95.27 242	85.11 286	88.98 357	94.37 325	81.11 335	87.10 293	93.69 295	82.28 188	97.50 295	74.37 345	94.76 180	98.48 127

Vis-MVSNet		95.23 75	94.81 77	96.51 75	97.18 137	91.58 108	98.26 35	98.12 56	94.38 46	94.90 110	98.15 58	82.28 188	98.92 146	91.45 158	98.58 91	99.01 82
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator	91.36 5	95.19 78	94.44 92	97.44 45	96.56 177	93.36 61	98.65 11	98.36 17	94.12 51	89.25 248	98.06 63	82.20 190	99.77 30	93.41 118	99.32 54	99.18 65

v10		91.04 233	90.23 233	93.49 238	94.12 295	88.16 226	97.32 132	97.08 188	88.26 235	88.29 268	94.22 278	82.17 191	97.97 245	86.45 252	84.12 314	94.33 311

v1144		91.37 217	90.60 217	93.68 231	93.89 302	88.23 222	96.84 170	97.03 197	88.37 232	89.69 231	94.39 264	82.04 192	97.98 242	87.80 222	85.37 293	94.84 287

MVSTER		93.20 139	92.81 136	94.37 192	96.56 177	89.59 175	97.06 152	97.12 183	91.24 146	91.30 190	95.96 190	82.02 193	98.05 234	93.48 115	90.55 245	95.47 250

CP-MVSNet		91.89 194	91.24 194	93.82 222	95.05 254	88.57 210	97.82 74	98.19 44	91.70 131	88.21 271	95.76 204	81.96 194	97.52 294	87.86 220	84.65 305	95.37 259

Patchmatch-RL test		87.38 293	86.24 294	90.81 309	88.74 358	78.40 350	88.12 361	93.17 339	87.11 267	82.17 336	89.29 346	81.95 195	95.60 342	88.64 212	77.02 346	98.41 135

sam_mvs												81.94 196

pmmvs4		90.93 239	89.85 249	94.17 200	93.34 320	90.79 143	94.60 281	96.02 258	84.62 307	87.45 284	95.15 230	81.88 197	97.45 299	87.70 226	87.87 270	94.27 315

test_post											17.58 377	81.76 198	98.08 227

XVG-OURS		93.72 122	93.35 119	94.80 174	97.07 144	88.61 208	94.79 277	97.46 147	91.97 127	93.99 129	97.86 81	81.74 199	98.88 150	92.64 133	92.67 206	96.92 196

v2v482		91.59 203	90.85 207	93.80 223	93.87 303	88.17 225	96.94 163	96.88 212	89.54 194	89.53 237	94.90 240	81.70 200	98.02 239	89.25 199	85.04 302	95.20 270

baseline2		91.63 201	90.86 205	93.94 216	94.33 289	86.32 265	95.92 241	91.64 352	89.37 200	86.94 296	94.69 250	81.62 201	98.69 168	88.64 212	94.57 184	96.81 199

v144192		91.06 232	90.28 229	93.39 242	93.66 310	87.23 246	96.83 171	97.07 190	87.43 259	89.69 231	94.28 272	81.48 202	98.00 241	87.18 242	84.92 304	94.93 281

MDTV_nov1_ep13			90.76 211		95.22 246	80.33 335	93.03 330	95.28 292	88.14 239	92.84 158	93.83 289	81.34 203	98.08 227	82.86 296	94.34 186

HQP_MVS		93.78 120	93.43 116	94.82 169	96.21 195	89.99 162	97.74 80	97.51 139	94.85 24	91.34 187	96.64 152	81.32 204	98.60 176	93.02 127	92.23 211	95.86 224

plane_prior6					96.10 205	90.00 160						81.32 204

v7n		90.76 243	89.86 248	93.45 241	93.54 312	87.60 240	97.70 89	97.37 165	88.85 216	87.65 282	94.08 283	81.08 206	98.10 223	84.68 278	83.79 320	94.66 302

HQP2-MVS												80.95 207

HQP-MVS		93.19 140	92.74 140	94.54 186	95.86 210	89.33 189	96.65 188	97.39 162	93.55 67	90.14 210	95.87 194	80.95 207	98.50 184	92.13 140	92.10 216	95.78 233

CR-MVSNet		90.82 242	89.77 253	93.95 214	94.45 285	87.19 247	90.23 351	95.68 274	86.89 270	92.40 161	92.36 321	80.91 209	97.05 315	81.09 313	93.95 192	97.60 176

Patchmtry		88.64 283	87.25 286	92.78 265	94.09 296	86.64 259	89.82 354	95.68 274	80.81 339	87.63 283	92.36 321	80.91 209	97.03 316	78.86 326	85.12 299	94.67 301

v1192		91.07 231	90.23 233	93.58 235	93.70 307	87.82 236	96.73 178	97.07 190	87.77 250	89.58 234	94.32 270	80.90 211	97.97 245	86.52 250	85.48 291	94.95 277

cl22		91.21 225	90.56 220	93.14 252	96.09 206	86.80 255	94.41 289	96.58 235	87.80 248	88.58 262	93.99 286	80.85 212	97.62 284	89.87 182	86.93 278	94.99 276

anonymousdsp		92.16 186	91.55 181	93.97 212	92.58 333	89.55 177	97.51 110	97.42 160	89.42 199	88.40 264	94.84 243	80.66 213	97.88 262	91.87 146	91.28 231	94.48 305

RRT_MVS		93.10 145	92.83 134	93.93 218	94.76 270	88.04 228	98.47 22	96.55 236	93.44 75	90.01 222	97.04 130	80.64 214	97.93 256	94.33 99	90.21 250	95.83 228

CLD-MVS		92.98 151	92.53 151	94.32 195	96.12 204	89.20 195	95.28 266	97.47 145	92.66 106	89.90 224	95.62 212	80.58 215	98.40 191	92.73 132	92.40 209	95.38 258
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_post1							92.81 333				16.58 378	80.53 216	97.68 277	86.20 255

VPA-MVSNet		93.24 137	92.48 154	95.51 135	95.70 217	92.39 83	97.86 68	98.66 10	92.30 114	92.09 173	95.37 222	80.49 217	98.40 191	93.95 105	85.86 287	95.75 238

tpmvs		89.83 268	89.15 267	91.89 285	94.92 261	80.30 336	93.11 328	95.46 284	86.28 281	88.08 274	92.65 312	80.44 218	98.52 183	81.47 307	89.92 252	96.84 198

PatchMatch-RL		92.90 156	92.02 165	95.56 131	98.19 92	90.80 142	95.27 268	97.18 177	87.96 242	91.86 177	95.68 209	80.44 218	98.99 142	84.01 287	97.54 120	96.89 197

PEN-MVS		91.20 226	90.44 222	93.48 239	94.49 283	87.91 234	97.76 78	98.18 46	91.29 142	87.78 280	95.74 205	80.35 220	97.33 307	85.46 269	82.96 326	95.19 271

Fast-Effi-MVS+-dtu		92.29 180	91.99 166	93.21 250	95.27 242	85.52 278	97.03 153	96.63 232	92.09 122	89.11 251	95.14 231	80.33 221	98.08 227	87.54 234	94.74 182	96.03 222

MSDG		91.42 213	90.24 232	94.96 162	97.15 140	88.91 202	93.69 315	96.32 246	85.72 290	86.93 297	96.47 167	80.24 222	98.98 143	80.57 314	95.05 176	96.98 192

v1921920		90.85 241	90.03 244	93.29 246	93.55 311	86.96 254	96.74 177	97.04 195	87.36 261	89.52 238	94.34 267	80.23 223	97.97 245	86.27 253	85.21 297	94.94 279

RPMNet		88.98 275	87.05 290	94.77 176	94.45 285	87.19 247	90.23 351	98.03 80	77.87 353	92.40 161	87.55 356	80.17 224	99.51 83	68.84 360	93.95 192	97.60 176

ET-MVSNet_ETH3D		91.49 210	90.11 238	95.63 127	96.40 188	91.57 109	95.34 262	93.48 337	90.60 172	75.58 355	95.49 219	80.08 225	96.79 325	94.25 100	89.76 254	98.52 120

PatchT		88.87 279	87.42 284	93.22 249	94.08 297	85.10 287	89.51 355	94.64 319	81.92 331	92.36 164	88.15 352	80.05 226	97.01 319	72.43 351	93.65 195	97.54 179

our_test_3		88.78 281	87.98 280	91.20 304	92.45 336	82.53 313	93.61 319	95.69 272	85.77 289	84.88 314	93.71 294	79.99 227	96.78 326	79.47 322	86.24 283	94.28 314

DTE-MVSNet		90.56 250	89.75 255	93.01 255	93.95 299	87.25 244	97.64 97	97.65 124	90.74 159	87.12 291	95.68 209	79.97 228	97.00 320	83.33 292	81.66 331	94.78 297

D2MVS		91.30 222	90.95 202	92.35 274	94.71 275	85.52 278	96.18 229	98.21 41	88.89 215	86.60 300	93.82 291	79.92 229	97.95 252	89.29 197	90.95 239	93.56 324

TransMVSNet (Re)		88.94 276	87.56 283	93.08 254	94.35 288	88.45 216	97.73 82	95.23 296	87.47 258	84.26 320	95.29 224	79.86 230	97.33 307	79.44 324	74.44 353	93.45 327

ACMM	89.79 8	92.96 152	92.50 153	94.35 193	96.30 193	88.71 206	97.58 103	97.36 167	91.40 141	90.53 202	96.65 151	79.77 231	98.75 161	91.24 162	91.64 221	95.59 245
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		92.16 186	91.23 195	94.95 163	94.75 272	90.94 136	97.47 117	97.43 159	89.14 206	88.90 252	96.43 169	79.71 232	98.24 205	89.56 190	87.68 271	95.67 244

PS-CasMVS		91.55 207	90.84 208	93.69 230	94.96 257	88.28 219	97.84 72	98.24 37	91.46 137	88.04 275	95.80 199	79.67 233	97.48 296	87.02 245	84.54 310	95.31 262

ab-mvs		93.57 127	92.55 149	96.64 65	97.28 133	91.96 98	95.40 260	97.45 152	89.81 189	93.22 150	96.28 176	79.62 234	99.46 90	90.74 169	93.11 200	98.50 123

v1240		90.70 247	89.85 249	93.23 248	93.51 314	86.80 255	96.61 194	97.02 198	87.16 266	89.58 234	94.31 271	79.55 235	97.98 242	85.52 268	85.44 292	94.90 284

CostFormer		91.18 229	90.70 214	92.62 270	94.84 267	81.76 321	94.09 301	94.43 322	84.15 312	92.72 159	93.77 293	79.43 236	98.20 209	90.70 170	92.18 214	97.90 158

CANet_DTU		94.37 95	93.65 104	96.55 71	96.46 185	92.13 92	96.21 227	96.67 228	94.38 46	93.53 140	97.03 131	79.34 237	99.71 37	90.76 168	98.45 97	97.82 165

OPM-MVS		93.28 136	92.76 137	94.82 169	94.63 279	90.77 144	96.65 188	97.18 177	93.72 62	91.68 178	97.26 118	79.33 238	98.63 173	92.13 140	92.28 210	95.07 273
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
iter_conf_final		93.60 124	93.11 124	95.04 154	97.13 141	91.30 118	97.92 65	95.65 276	92.98 96	91.60 179	96.64 152	79.28 239	98.13 216	95.34 76	91.49 225	95.70 241

JIA-IIPM		88.26 287	87.04 291	91.91 284	93.52 313	81.42 323	89.38 356	94.38 324	80.84 338	90.93 199	80.74 363	79.22 240	97.92 257	82.76 298	91.62 222	96.38 210

CVMVSNet		91.23 224	91.75 173	89.67 323	95.77 215	74.69 356	96.44 202	94.88 312	85.81 288	92.18 168	97.64 100	79.07 241	95.58 343	88.06 217	95.86 160	98.74 108

LPG-MVS_test		92.94 154	92.56 148	94.10 203	96.16 200	88.26 220	97.65 93	97.46 147	91.29 142	90.12 216	97.16 123	79.05 242	98.73 163	92.25 136	91.89 219	95.31 262

LGP-MVS_train				94.10 203	96.16 200	88.26 220		97.46 147	91.29 142	90.12 216	97.16 123	79.05 242	98.73 163	92.25 136	91.89 219	95.31 262

test-LLR		91.42 213	91.19 197	92.12 280	94.59 280	80.66 329	94.29 295	92.98 340	91.11 152	90.76 200	92.37 318	79.02 244	98.07 231	88.81 208	96.74 143	97.63 171

test0.0.03 1		89.37 273	88.70 271	91.41 300	92.47 335	85.63 276	95.22 271	92.70 343	91.11 152	86.91 298	93.65 299	79.02 244	93.19 360	78.00 330	89.18 258	95.41 253

ADS-MVSNet2		89.45 271	88.59 273	92.03 282	95.86 210	82.26 317	90.93 346	94.32 327	83.23 324	91.28 194	91.81 328	79.01 246	95.99 333	79.52 320	91.39 229	97.84 162

ADS-MVSNet		89.89 265	88.68 272	93.53 237	95.86 210	84.89 291	90.93 346	95.07 303	83.23 324	91.28 194	91.81 328	79.01 246	97.85 263	79.52 320	91.39 229	97.84 162

ppachtmachnet_test		88.35 286	87.29 285	91.53 296	92.45 336	83.57 307	93.75 312	95.97 259	84.28 310	85.32 312	94.18 279	79.00 248	96.93 321	75.71 340	84.99 303	94.10 317

OpenMVS	89.19 12	92.86 158	91.68 177	96.40 85	95.34 235	92.73 75	98.27 33	98.12 56	84.86 304	85.78 306	97.75 89	78.89 249	99.74 32	87.50 235	98.65 88	96.73 201

LTVRE_ROB	88.41 13	90.99 235	89.92 247	94.19 199	96.18 198	89.55 177	96.31 219	97.09 187	87.88 245	85.67 307	95.91 193	78.79 250	98.57 180	81.50 306	89.98 251	94.44 308
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
AUN-MVS		91.76 197	90.75 212	94.81 171	97.00 153	88.57 210	96.65 188	96.49 239	89.63 191	92.15 169	96.12 184	78.66 251	98.50 184	90.83 166	79.18 341	97.36 183

pm-mvs1		90.72 246	89.65 259	93.96 213	94.29 292	89.63 172	97.79 77	96.82 217	89.07 207	86.12 305	95.48 220	78.61 252	97.78 270	86.97 246	81.67 330	94.46 306

PVSNet	86.66 18	92.24 183	91.74 175	93.73 226	97.77 114	83.69 306	92.88 331	96.72 221	87.91 244	93.00 152	94.86 242	78.51 253	99.05 137	86.53 249	97.45 125	98.47 128

ACMP	89.59 10	92.62 166	92.14 161	94.05 206	96.40 188	88.20 223	97.36 128	97.25 176	91.52 134	88.30 267	96.64 152	78.46 254	98.72 166	91.86 147	91.48 226	95.23 269
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
BH-RMVSNet		92.72 165	91.97 167	94.97 161	97.16 138	87.99 230	96.15 230	95.60 277	90.62 169	91.87 176	97.15 125	78.41 255	98.57 180	83.16 293	97.60 119	98.36 140

thres200		92.23 184	91.39 186	94.75 178	97.61 124	89.03 200	96.60 196	95.09 302	92.08 123	93.28 147	94.00 285	78.39 256	99.04 140	81.26 312	94.18 187	96.19 213

MDA-MVSNet_test_wron		85.87 308	84.23 312	90.80 311	92.38 338	82.57 312	93.17 325	95.15 299	82.15 329	67.65 360	92.33 324	78.20 257	95.51 344	77.33 332	79.74 337	94.31 313

tfpn200view9		92.38 173	91.52 183	94.95 163	97.85 110	89.29 191	97.41 120	94.88 312	92.19 119	93.27 148	94.46 262	78.17 258	99.08 131	81.40 308	94.08 188	96.48 207

thres400		92.42 171	91.52 183	95.12 152	97.85 110	89.29 191	97.41 120	94.88 312	92.19 119	93.27 148	94.46 262	78.17 258	99.08 131	81.40 308	94.08 188	96.98 192

YYNet1		85.87 308	84.23 312	90.78 312	92.38 338	82.46 315	93.17 325	95.14 300	82.12 330	67.69 359	92.36 321	78.16 260	95.50 345	77.31 333	79.73 338	94.39 309

CL-MVSNet_self_test		86.31 302	85.15 304	89.80 322	88.83 357	81.74 322	93.93 306	96.22 251	86.67 273	85.03 313	90.80 335	78.09 261	94.50 350	74.92 342	71.86 358	93.15 329

thres100view900		92.43 170	91.58 180	94.98 160	97.92 106	89.37 187	97.71 87	94.66 317	92.20 117	93.31 146	94.90 240	78.06 262	99.08 131	81.40 308	94.08 188	96.48 207

thres600view7		92.49 169	91.60 179	95.18 148	97.91 107	89.47 181	97.65 93	94.66 317	92.18 121	93.33 145	94.91 239	78.06 262	99.10 126	81.61 305	94.06 191	96.98 192

tpm cat1		88.36 285	87.21 288	91.81 289	95.13 251	80.55 332	92.58 335	95.70 270	74.97 356	87.45 284	91.96 326	78.01 264	98.17 213	80.39 316	88.74 263	96.72 202

MVP-Stereo		90.74 245	90.08 239	92.71 267	93.19 323	88.20 223	95.86 243	96.27 248	86.07 285	84.86 315	94.76 247	77.84 265	97.75 273	83.88 290	98.01 109	92.17 344
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EPMVS		90.70 247	89.81 251	93.37 243	94.73 274	84.21 297	93.67 316	88.02 364	89.50 196	92.38 163	93.49 302	77.82 266	97.78 270	86.03 261	92.68 205	98.11 152

tfpnnormal		89.70 270	88.40 275	93.60 233	95.15 249	90.10 158	97.56 105	98.16 50	87.28 264	86.16 304	94.63 254	77.57 267	98.05 234	74.48 343	84.59 308	92.65 336

tpm		90.25 257	89.74 256	91.76 293	93.92 300	79.73 342	93.98 302	93.54 336	88.28 234	91.99 174	93.25 307	77.51 268	97.44 300	87.30 239	87.94 269	98.12 149

thisisatest0515		92.29 180	91.30 191	95.25 146	96.60 172	88.90 203	94.36 291	92.32 346	87.92 243	93.43 143	94.57 256	77.28 269	99.00 141	89.42 193	95.86 160	97.86 161

FMVSNet3		91.78 196	90.69 215	95.03 156	96.53 180	92.27 88	97.02 155	96.93 204	89.79 190	89.35 242	94.65 253	77.01 270	97.47 297	86.12 258	88.82 260	95.35 260

TR-MVS		91.48 211	90.59 218	94.16 201	96.40 188	87.33 241	95.67 249	95.34 291	87.68 254	91.46 184	95.52 218	76.77 271	98.35 198	82.85 297	93.61 197	96.79 200

FE-MVS		92.05 190	91.05 200	95.08 153	96.83 161	87.93 231	93.91 308	95.70 270	86.30 280	94.15 126	94.97 235	76.59 272	99.21 113	84.10 285	96.86 139	98.09 153

tttt0517		92.96 152	92.33 157	94.87 167	97.11 142	87.16 249	97.97 62	92.09 348	90.63 168	93.88 133	97.01 132	76.50 273	99.06 136	90.29 176	95.45 168	98.38 138

RPSCF		90.75 244	90.86 205	90.42 316	96.84 159	76.29 354	95.61 253	96.34 245	83.89 315	91.38 185	97.87 79	76.45 274	98.78 156	87.16 243	92.23 211	96.20 212

tpm2		89.96 263	89.21 265	92.23 279	94.91 263	81.25 324	93.78 311	94.42 323	80.62 341	91.56 181	93.44 304	76.44 275	97.94 253	85.60 267	92.08 218	97.49 180

thisisatest0530		93.03 149	92.21 160	95.49 137	97.07 144	89.11 199	97.49 116	92.19 347	90.16 180	94.09 127	96.41 170	76.43 276	99.05 137	90.38 173	95.68 165	98.31 142

iter_conf05		93.18 143	92.63 144	94.83 168	96.64 170	90.69 146	97.60 101	95.53 282	92.52 109	91.58 180	96.64 152	76.35 277	98.13 216	95.43 74	91.42 228	95.68 243

EU-MVSNet		88.72 282	88.90 269	88.20 330	93.15 324	74.21 357	96.63 193	94.22 328	85.18 298	87.32 289	95.97 189	76.16 278	94.98 348	85.27 271	86.17 284	95.41 253

bld_raw_dy_0_64		92.37 174	91.69 176	94.39 191	94.28 293	89.73 171	97.71 87	93.65 335	92.78 104	90.46 204	96.67 150	75.88 279	97.97 245	92.92 131	90.89 241	95.48 247

dp		88.90 278	88.26 278	90.81 309	94.58 282	76.62 352	92.85 332	94.93 309	85.12 300	90.07 221	93.07 308	75.81 280	98.12 221	80.53 315	87.42 275	97.71 168

IterMVS-SCA-FT		90.31 255	89.81 251	91.82 288	95.52 224	84.20 298	94.30 294	96.15 255	90.61 170	87.39 287	94.27 273	75.80 281	96.44 328	87.34 237	86.88 282	94.82 290

SCA		91.84 195	91.18 198	93.83 221	95.59 220	84.95 290	94.72 278	95.58 279	90.82 156	92.25 167	93.69 295	75.80 281	98.10 223	86.20 255	95.98 156	98.45 130

IterMVS		90.15 261	89.67 257	91.61 295	95.48 226	83.72 304	94.33 293	96.12 256	89.99 183	87.31 290	94.15 281	75.78 283	96.27 331	86.97 246	86.89 281	94.83 288
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
jajsoiax		92.42 171	91.89 170	94.03 208	93.33 321	88.50 214	97.73 82	97.53 137	92.00 126	88.85 255	96.50 166	75.62 284	98.11 222	93.88 109	91.56 224	95.48 247

cascas		91.20 226	90.08 239	94.58 184	94.97 256	89.16 198	93.65 317	97.59 130	79.90 344	89.40 240	92.92 310	75.36 285	98.36 197	92.14 139	94.75 181	96.23 211

VPNet		92.23 184	91.31 190	94.99 158	95.56 222	90.96 135	97.22 143	97.86 104	92.96 98	90.96 198	96.62 161	75.06 286	98.20 209	91.90 144	83.65 321	95.80 231

N_pmnet		78.73 327	78.71 328	78.79 346	92.80 329	46.50 379	94.14 299	43.71 382	78.61 349	80.83 339	91.66 331	74.94 287	96.36 329	67.24 361	84.45 311	93.50 325

mvs_tets		92.31 178	91.76 172	93.94 216	93.41 318	88.29 218	97.63 99	97.53 137	92.04 124	88.76 258	96.45 168	74.62 288	98.09 226	93.91 107	91.48 226	95.45 252

DSMNet-mixed		86.34 301	86.12 297	87.00 336	89.88 351	70.43 361	94.93 275	90.08 360	77.97 352	85.42 311	92.78 311	74.44 289	93.96 355	74.43 344	95.14 172	96.62 203

pmmvs5		89.86 267	88.87 270	92.82 263	92.86 327	86.23 268	96.26 222	95.39 285	84.24 311	87.12 291	94.51 257	74.27 290	97.36 306	87.61 233	87.57 272	94.86 286

OurMVSNet-221017-0		90.51 252	90.19 237	91.44 299	93.41 318	81.25 324	96.98 160	96.28 247	91.68 132	86.55 301	96.30 175	74.20 291	97.98 242	88.96 206	87.40 276	95.09 272

GBi-Net		91.35 218	90.27 230	94.59 180	96.51 181	91.18 127	97.50 111	96.93 204	88.82 219	89.35 242	94.51 257	73.87 292	97.29 309	86.12 258	88.82 260	95.31 262

test1		91.35 218	90.27 230	94.59 180	96.51 181	91.18 127	97.50 111	96.93 204	88.82 219	89.35 242	94.51 257	73.87 292	97.29 309	86.12 258	88.82 260	95.31 262

FMVSNet2		91.31 221	90.08 239	94.99 158	96.51 181	92.21 89	97.41 120	96.95 202	88.82 219	88.62 260	94.75 248	73.87 292	97.42 302	85.20 273	88.55 265	95.35 260

COLMAP_ROB	87.81 15	90.40 254	89.28 264	93.79 224	97.95 103	87.13 250	96.92 164	95.89 264	82.83 326	86.88 299	97.18 122	73.77 295	99.29 108	78.44 328	93.62 196	94.95 277
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20231206		87.09 295	86.14 296	89.93 321	91.22 343	80.35 334	96.11 231	95.35 288	83.57 321	84.16 321	93.02 309	73.54 296	95.61 341	72.16 352	86.14 285	93.84 322

UGNet		94.04 109	93.28 121	96.31 92	96.85 158	91.19 126	97.88 67	97.68 121	94.40 44	93.00 152	96.18 180	73.39 297	99.61 57	91.72 150	98.46 96	98.13 148
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
test1111		93.19 140	92.82 135	94.30 197	97.58 128	84.56 294	98.21 43	89.02 362	93.53 71	94.58 116	98.21 53	72.69 298	99.05 137	93.06 125	98.48 95	99.28 58

ECVR-MVS		93.19 140	92.73 141	94.57 185	97.66 120	85.41 280	98.21 43	88.23 363	93.43 76	94.70 114	98.21 53	72.57 299	99.07 134	93.05 126	98.49 93	99.25 61

Anonymous20231211		90.63 249	89.42 261	94.27 198	98.24 85	89.19 197	98.05 53	97.89 96	79.95 343	88.25 270	94.96 236	72.56 300	98.13 216	89.70 186	85.14 298	95.49 246

ACMH	87.59 16	90.53 251	89.42 261	93.87 220	96.21 195	87.92 232	97.24 138	96.94 203	88.45 230	83.91 327	96.27 177	71.92 301	98.62 175	84.43 282	89.43 256	95.05 275
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		91.38 215	90.31 227	94.59 180	94.65 277	87.62 239	94.34 292	96.19 254	90.73 160	90.35 207	93.83 289	71.84 302	97.96 250	87.22 240	93.61 197	98.21 146

SixPastTwentyTwo		89.15 274	88.54 274	90.98 306	93.49 315	80.28 337	96.70 182	94.70 316	90.78 157	84.15 322	95.57 214	71.78 303	97.71 276	84.63 279	85.07 300	94.94 279

gg-mvs-nofinetune		87.82 290	85.61 299	94.44 188	94.46 284	89.27 194	91.21 345	84.61 372	80.88 337	89.89 226	74.98 365	71.50 304	97.53 292	85.75 266	97.21 134	96.51 205

test20.03		86.14 305	85.40 302	88.35 328	90.12 348	80.06 339	95.90 242	95.20 297	88.59 225	81.29 338	93.62 300	71.43 305	92.65 361	71.26 356	81.17 333	92.34 340

MS-PatchMatch		90.27 256	89.77 253	91.78 291	94.33 289	84.72 293	95.55 254	96.73 220	86.17 284	86.36 302	95.28 226	71.28 306	97.80 268	84.09 286	98.14 107	92.81 333

PVSNet_0	82.17 19	85.46 311	83.64 314	90.92 307	95.27 242	79.49 343	90.55 349	95.60 277	83.76 318	83.00 333	89.95 341	71.09 307	97.97 245	82.75 299	60.79 369	95.31 262

GG-mvs-BLEND				93.62 232	93.69 308	89.20 195	92.39 338	83.33 373		87.98 278	89.84 343	71.00 308	96.87 323	82.08 304	95.40 169	94.80 293

ITE_SJBPF				92.43 273	95.34 235	85.37 283		95.92 260	91.47 136	87.75 281	96.39 172	71.00 308	97.96 250	82.36 302	89.86 253	93.97 320

IB-MVS	87.33 17	89.91 264	88.28 277	94.79 175	95.26 245	87.70 238	95.12 274	93.95 332	89.35 201	87.03 294	92.49 316	70.74 310	99.19 115	89.18 203	81.37 332	97.49 180
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
MDA-MVSNet-bldmvs		85.00 312	82.95 317	91.17 305	93.13 325	83.33 308	94.56 283	95.00 305	84.57 308	65.13 364	92.65 312	70.45 311	95.85 336	73.57 348	77.49 345	94.33 311

AllTest		90.23 258	88.98 268	93.98 210	97.94 104	86.64 259	96.51 201	95.54 280	85.38 294	85.49 309	96.77 142	70.28 312	99.15 120	80.02 318	92.87 201	96.15 216

TestCases				93.98 210	97.94 104	86.64 259		95.54 280	85.38 294	85.49 309	96.77 142	70.28 312	99.15 120	80.02 318	92.87 201	96.15 216

ACMH+	87.92 14	90.20 259	89.18 266	93.25 247	96.48 184	86.45 264	96.99 159	96.68 226	88.83 218	84.79 316	96.22 179	70.16 314	98.53 182	84.42 283	88.04 268	94.77 298

test_vis1_n_1920		94.17 100	94.58 84	92.91 259	97.42 131	82.02 319	97.83 73	97.85 105	94.68 36	98.10 20	98.49 25	70.15 315	99.32 104	97.91 2	98.82 82	97.40 182

KD-MVS_self_test		85.95 307	84.95 306	88.96 327	89.55 354	79.11 347	95.13 273	96.42 242	85.91 287	84.07 325	90.48 336	70.03 316	94.82 349	80.04 317	72.94 356	92.94 331

Anonymous20240529		91.98 192	90.73 213	95.73 122	98.14 96	89.40 185	97.99 56	97.72 116	79.63 345	93.54 139	97.41 113	69.94 317	99.56 72	91.04 165	91.11 235	98.22 145

pmmvs-eth3d		86.22 303	84.45 310	91.53 296	88.34 359	87.25 244	94.47 285	95.01 304	83.47 322	79.51 348	89.61 344	69.75 318	95.71 339	83.13 294	76.73 349	91.64 345

test_fmvs1		93.21 138	93.53 108	92.25 278	96.55 179	81.20 326	97.40 124	96.96 201	90.68 163	96.80 49	98.04 65	69.25 319	98.40 191	97.58 8	98.50 92	97.16 189

LFMVS		93.60 124	92.63 144	96.52 72	98.13 97	91.27 120	97.94 63	93.39 338	90.57 173	96.29 74	98.31 46	69.00 320	99.16 119	94.18 101	95.87 159	99.12 73

TESTMET0.1,1		90.06 262	89.42 261	91.97 283	94.41 287	80.62 331	94.29 295	91.97 350	87.28 264	90.44 205	92.47 317	68.79 321	97.67 278	88.50 214	96.60 148	97.61 175

XVG-ACMP-BASELINE		90.93 239	90.21 236	93.09 253	94.31 291	85.89 273	95.33 263	97.26 174	91.06 154	89.38 241	95.44 221	68.61 322	98.60 176	89.46 192	91.05 236	94.79 295

MVS-HIRNet		82.47 322	81.21 324	86.26 338	95.38 230	69.21 364	88.96 358	89.49 361	66.28 362	80.79 340	74.08 367	68.48 323	97.39 304	71.93 353	95.47 167	92.18 343

VDD-MVS		93.82 118	93.08 125	96.02 109	97.88 109	89.96 166	97.72 85	95.85 265	92.43 111	95.86 88	98.44 31	68.42 324	99.39 98	96.31 35	94.85 177	98.71 111

test_0402		86.46 299	84.79 308	91.45 298	95.02 255	85.55 277	96.29 221	94.89 311	80.90 336	82.21 335	93.97 287	68.21 325	97.29 309	62.98 364	88.68 264	91.51 348

test-mter		90.19 260	89.54 260	92.12 280	94.59 280	80.66 329	94.29 295	92.98 340	87.68 254	90.76 200	92.37 318	67.67 326	98.07 231	88.81 208	96.74 143	97.63 171

VDDNet		93.05 148	92.07 162	96.02 109	96.84 159	90.39 156	98.08 51	95.85 265	86.22 283	95.79 91	98.46 29	67.59 327	99.19 115	94.92 85	94.85 177	98.47 128

USDC		88.94 276	87.83 281	92.27 277	94.66 276	84.96 289	93.86 309	95.90 262	87.34 262	83.40 329	95.56 215	67.43 328	98.19 211	82.64 301	89.67 255	93.66 323

pmmvs6		87.81 291	86.19 295	92.69 268	91.32 342	86.30 266	97.34 129	96.41 243	80.59 342	84.05 326	94.37 266	67.37 329	97.67 278	84.75 277	79.51 340	94.09 319

test2506		91.60 202	90.78 210	94.04 207	97.66 120	83.81 302	98.27 33	75.53 377	93.43 76	95.23 105	98.21 53	67.21 330	99.07 134	93.01 129	98.49 93	99.25 61

KD-MVS_2432*1600		84.81 314	82.64 318	91.31 301	91.07 344	85.34 284	91.22 343	95.75 268	85.56 292	83.09 331	90.21 339	67.21 330	95.89 334	77.18 335	62.48 367	92.69 334

miper_refine_blended		84.81 314	82.64 318	91.31 301	91.07 344	85.34 284	91.22 343	95.75 268	85.56 292	83.09 331	90.21 339	67.21 330	95.89 334	77.18 335	62.48 367	92.69 334

K. test v3		87.64 292	86.75 293	90.32 317	93.02 326	79.48 344	96.61 194	92.08 349	90.66 166	80.25 345	94.09 282	67.21 330	96.65 327	85.96 263	80.83 334	94.83 288

tt0805		91.09 230	90.07 242	94.16 201	95.61 219	88.31 217	97.56 105	96.51 238	89.56 193	89.17 249	95.64 211	67.08 334	98.38 196	91.07 164	88.44 266	95.80 231

CMPMVS	62.92 21	85.62 310	84.92 307	87.74 332	89.14 355	73.12 360	94.17 298	96.80 218	73.98 357	73.65 358	94.93 238	66.36 335	97.61 285	83.95 289	91.28 231	92.48 339
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UniMVSNet_ETH3D		91.34 220	90.22 235	94.68 179	94.86 266	87.86 235	97.23 142	97.46 147	87.99 241	89.90 224	96.92 137	66.35 336	98.23 206	90.30 175	90.99 238	97.96 155

lessismore_v0				90.45 315	91.96 341	79.09 348		87.19 367		80.32 344	94.39 264	66.31 337	97.55 289	84.00 288	76.84 347	94.70 300

Anonymous202405211		92.07 189	90.83 209	95.76 117	98.19 92	88.75 205	97.58 103	95.00 305	86.00 286	93.64 136	97.45 110	66.24 338	99.53 78	90.68 171	92.71 204	99.01 82

new-patchmatchnet		83.18 320	81.87 322	87.11 334	86.88 362	75.99 355	93.70 313	95.18 298	85.02 302	77.30 353	88.40 349	65.99 339	93.88 356	74.19 347	70.18 360	91.47 350

FMVSNet1		89.88 266	88.31 276	94.59 180	95.41 228	91.18 127	97.50 111	96.93 204	86.62 274	87.41 286	94.51 257	65.94 340	97.29 309	83.04 295	87.43 274	95.31 262

TDRefinement		86.53 298	84.76 309	91.85 286	82.23 368	84.25 296	96.38 213	95.35 288	84.97 303	84.09 324	94.94 237	65.76 341	98.34 201	84.60 280	74.52 352	92.97 330

UnsupCasMVSNet_eth		85.99 306	84.45 310	90.62 313	89.97 350	82.40 316	93.62 318	97.37 165	89.86 185	78.59 351	92.37 318	65.25 342	95.35 347	82.27 303	70.75 359	94.10 317

LF4IMVS		87.94 289	87.25 286	89.98 320	92.38 338	80.05 340	94.38 290	95.25 295	87.59 256	84.34 318	94.74 249	64.31 343	97.66 280	84.83 275	87.45 273	92.23 341

Anonymous20240521		86.42 300	85.44 300	89.34 325	90.33 347	79.79 341	96.73 178	95.92 260	83.71 319	83.25 330	91.36 333	63.92 344	96.01 332	78.39 329	85.36 294	92.22 342

MIMVSNet		88.50 284	86.76 292	93.72 228	94.84 267	87.77 237	91.39 341	94.05 329	86.41 279	87.99 277	92.59 315	63.27 345	95.82 338	77.44 331	92.84 203	97.57 178

test_fmvs1_n		92.73 164	92.88 132	92.29 276	96.08 207	81.05 327	97.98 57	97.08 188	90.72 161	96.79 50	98.18 56	63.07 346	98.45 188	97.62 7	98.42 98	97.36 183

FMVSNet5		87.29 294	85.79 298	91.78 291	94.80 269	87.28 242	95.49 257	95.28 292	84.09 313	83.85 328	91.82 327	62.95 347	94.17 354	78.48 327	85.34 295	93.91 321

testgi		87.97 288	87.21 288	90.24 318	92.86 327	80.76 328	96.67 187	94.97 307	91.74 130	85.52 308	95.83 197	62.66 348	94.47 352	76.25 338	88.36 267	95.48 247

TinyColmap		86.82 297	85.35 303	91.21 303	94.91 263	82.99 310	93.94 305	94.02 331	83.58 320	81.56 337	94.68 251	62.34 349	98.13 216	75.78 339	87.35 277	92.52 338

new_pmnet		82.89 321	81.12 325	88.18 331	89.63 352	80.18 338	91.77 340	92.57 344	76.79 355	75.56 356	88.23 351	61.22 350	94.48 351	71.43 354	82.92 327	89.87 357

OpenMVS_ROB	81.14 20	84.42 316	82.28 321	90.83 308	90.06 349	84.05 301	95.73 248	94.04 330	73.89 358	80.17 346	91.53 332	59.15 351	97.64 281	66.92 362	89.05 259	90.80 354

test_fmvs2		89.77 269	89.93 246	89.31 326	93.68 309	76.37 353	97.64 97	95.90 262	89.84 188	91.49 183	96.26 178	58.77 352	97.10 313	94.65 94	91.13 234	94.46 306

test_vis1_n		92.37 174	92.26 159	92.72 266	94.75 272	82.64 311	98.02 55	96.80 218	91.18 149	97.77 28	97.93 74	58.02 353	98.29 203	97.63 6	98.21 103	97.23 188

MIMVSNet1		84.93 313	83.05 315	90.56 314	89.56 353	84.84 292	95.40 260	95.35 288	83.91 314	80.38 343	92.21 325	57.23 354	93.34 359	70.69 358	82.75 329	93.50 325

EG-PatchMatch MVS		87.02 296	85.44 300	91.76 293	92.67 331	85.00 288	96.08 233	96.45 241	83.41 323	79.52 347	93.49 302	57.10 355	97.72 275	79.34 325	90.87 242	92.56 337

MVS_0304		88.79 280	87.57 282	92.46 271	94.65 277	86.15 272	96.40 210	97.17 179	86.44 277	88.02 276	91.71 330	56.68 356	97.03 316	84.47 281	92.58 207	94.19 316

UnsupCasMVSNet_bld		82.13 323	79.46 327	90.14 319	88.00 360	82.47 314	90.89 348	96.62 234	78.94 348	75.61 354	84.40 361	56.63 357	96.31 330	77.30 334	66.77 365	91.63 346

EGC-MVSNET		68.77 334	63.01 339	86.07 339	92.49 334	82.24 318	93.96 304	90.96 357	0.71 379	2.62 380	90.89 334	53.66 358	93.46 357	57.25 368	84.55 309	82.51 362

tmp_tt		51.94 342	53.82 342	46.29 358	33.73 382	45.30 381	78.32 368	67.24 381	18.02 375	50.93 371	87.05 358	52.99 359	53.11 377	70.76 357	25.29 375	40.46 373

test_vis1_rt		86.16 304	85.06 305	89.46 324	93.47 317	80.46 333	96.41 206	86.61 369	85.22 297	79.15 349	88.64 347	52.41 360	97.06 314	93.08 124	90.57 244	90.87 353

pmmvs3		79.97 325	77.50 330	87.39 333	82.80 367	79.38 345	92.70 334	90.75 359	70.69 360	78.66 350	87.47 357	51.34 361	93.40 358	73.39 349	69.65 361	89.38 358

DeepMVS_CX				74.68 352	90.84 346	64.34 372		81.61 375	65.34 363	67.47 361	88.01 354	48.60 362	80.13 373	62.33 365	73.68 355	79.58 364

mvsany_test3		83.59 317	82.44 320	87.03 335	83.80 364	73.82 358	93.70 313	90.92 358	86.42 278	82.51 334	90.26 338	46.76 363	95.71 339	90.82 167	76.76 348	91.57 347

PM-MVS		83.48 318	81.86 323	88.31 329	87.83 361	77.59 351	93.43 321	91.75 351	86.91 269	80.63 341	89.91 342	44.42 364	95.84 337	85.17 274	76.73 349	91.50 349

test_method		66.11 336	64.89 338	69.79 353	72.62 376	35.23 383	65.19 371	92.83 342	20.35 374	65.20 363	88.08 353	43.14 365	82.70 371	73.12 350	63.46 366	91.45 351

APD_test1		79.31 326	77.70 329	84.14 340	89.11 356	69.07 365	92.36 339	91.50 353	69.07 361	73.87 357	92.63 314	39.93 366	94.32 353	70.54 359	80.25 336	89.02 359

ambc				86.56 337	83.60 365	70.00 363	85.69 363	94.97 307		80.60 342	88.45 348	37.42 367	96.84 324	82.69 300	75.44 351	92.86 332

test_fmvs3		83.21 319	83.02 316	83.78 341	86.77 363	68.34 366	96.76 176	94.91 310	86.49 276	84.14 323	89.48 345	36.04 368	91.73 363	91.86 147	80.77 335	91.26 352

test_f		80.57 324	79.62 326	83.41 342	83.38 366	67.80 368	93.57 320	93.72 333	80.80 340	77.91 352	87.63 355	33.40 369	92.08 362	87.14 244	79.04 343	90.34 356

Gipuma		67.86 335	65.41 337	75.18 351	92.66 332	73.45 359	66.50 370	94.52 321	53.33 369	57.80 370	66.07 370	30.81 370	89.20 367	48.15 371	78.88 344	62.90 370
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		52.08 341	51.31 344	54.39 357	72.62 376	45.39 380	83.84 365	75.51 378	41.13 372	40.77 374	59.65 373	30.08 371	73.60 375	28.31 375	29.90 374	44.18 372

FPMVS		71.27 330	69.85 332	75.50 350	74.64 373	59.03 375	91.30 342	91.50 353	58.80 365	57.92 369	88.28 350	29.98 372	85.53 370	53.43 369	82.84 328	81.95 363

E-PMN		53.28 339	52.56 343	55.43 356	74.43 374	47.13 378	83.63 366	76.30 376	42.23 371	42.59 373	62.22 372	28.57 373	74.40 374	31.53 374	31.51 372	44.78 371

PMMVS2		70.19 331	66.92 334	80.01 344	76.35 372	65.67 370	86.22 362	87.58 366	64.83 364	62.38 365	80.29 364	26.78 374	88.49 368	63.79 363	54.07 370	85.88 360

ANet_high		63.94 337	59.58 340	77.02 347	61.24 380	66.06 369	85.66 364	87.93 365	78.53 350	42.94 372	71.04 369	25.42 375	80.71 372	52.60 370	30.83 373	84.28 361

LCM-MVSNet		72.55 329	69.39 333	82.03 343	70.81 378	65.42 371	90.12 353	94.36 326	55.02 368	65.88 362	81.72 362	24.16 376	89.96 364	74.32 346	68.10 364	90.71 355

test_vis3_rt		72.73 328	70.55 331	79.27 345	80.02 369	68.13 367	93.92 307	74.30 379	76.90 354	58.99 368	73.58 368	20.29 377	95.37 346	84.16 284	72.80 357	74.31 367

testf1		69.31 332	66.76 335	76.94 348	78.61 370	61.93 373	88.27 359	86.11 370	55.62 366	59.69 366	85.31 359	20.19 378	89.32 365	57.62 366	69.44 362	79.58 364

APD_test2		69.31 332	66.76 335	76.94 348	78.61 370	61.93 373	88.27 359	86.11 370	55.62 366	59.69 366	85.31 359	20.19 378	89.32 365	57.62 366	69.44 362	79.58 364

PMVS	53.92 22	58.58 338	55.40 341	68.12 354	51.00 381	48.64 377	78.86 367	87.10 368	46.77 370	35.84 376	74.28 366	8.76 380	86.34 369	42.07 372	73.91 354	69.38 368
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		25.11 343	24.57 347	26.74 359	73.98 375	39.89 382	57.88 372	9.80 383	12.27 376	10.39 377	6.97 379	7.03 381	36.44 378	25.43 376	17.39 376	3.89 376

MVE	50.73 23	53.25 340	48.81 345	66.58 355	65.34 379	57.50 376	72.49 369	70.94 380	40.15 373	39.28 375	63.51 371	6.89 382	73.48 376	38.29 373	42.38 371	68.76 369
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test123		13.04 346	15.66 349	5.18 360	4.51 384	3.45 384	92.50 337	1.81 385	2.50 378	7.58 379	20.15 376	3.67 383	2.18 380	7.13 378	1.07 378	9.90 374

testmvs		13.36 345	16.33 348	4.48 361	5.04 383	2.26 385	93.18 324	3.28 384	2.70 377	8.24 378	21.66 375	2.29 384	2.19 379	7.58 377	2.96 377	9.00 375

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		8.06 347	10.74 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	96.69 148	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					99.55 1	93.34 62	99.29 1	98.35 20	94.98 21	98.49 15

MSC_two_6792asdad				98.86 1	98.67 58	96.94 1		97.93 94					99.86 8	97.68 3	99.67 6	99.77 1

No_MVS				98.86 1	98.67 58	96.94 1		97.93 94					99.86 8	97.68 3	99.67 6	99.77 1

eth-test2					0.00 385

eth-test					0.00 385

IU-MVS					99.42 7	95.39 11		97.94 93	90.40 177	98.94 5				97.41 16	99.66 10	99.74 7

save fliter					98.91 49	94.28 34	97.02 155	98.02 83	95.35 9

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 27					99.86 8	97.52 9	99.67 6	99.75 5

GSMVS																98.45 130

test_part2					99.28 25	95.74 8				98.10 20

MTGPA								98.08 63

MTMP							97.86 68	82.03 374

gm-plane-assit					93.22 322	78.89 349			84.82 305		93.52 301		98.64 172	87.72 223

test9_res														94.81 89	99.38 49	99.45 41

agg_prior2														93.94 106	99.38 49	99.50 36

agg_prior					98.67 58	93.79 50		98.00 87		95.68 95			99.57 71

test_prior4						93.66 53	96.42 205

test_prior				97.23 53	98.67 58	92.99 69		98.00 87					99.41 96			99.29 56

旧先验2							95.94 240		81.66 333	97.34 36			98.82 153	92.26 134

新几何2							95.79 246

无先验							95.79 246	97.87 100	83.87 317				99.65 49	87.68 229		98.89 98

原ACMM2							95.67 249

testdata2													99.67 47	85.96 263

testdata1							95.26 270		93.10 89

plane_prior7					96.21 195	89.98 164

plane_prior5								97.51 139					98.60 176	93.02 127	92.23 211	95.86 224

plane_prior4											96.64 152

plane_prior3						90.00 160			94.46 42	91.34 187

plane_prior2							97.74 80		94.85 24

plane_prior1					96.14 203

plane_prior						89.99 162	97.24 138		94.06 52						92.16 215

n2								0.00 386

nn								0.00 386

door-mid								91.06 356

test11								97.88 98

door								91.13 355

HQP5-MVS						89.33 189

HQP-NCC					95.86 210		96.65 188		93.55 67	90.14 210

ACMP_Plane					95.86 210		96.65 188		93.55 67	90.14 210

BP-MVS														92.13 140

HQP4-MVS										90.14 210			98.50 184			95.78 233

HQP3-MVS								97.39 162							92.10 216

NP-MVS					95.99 209	89.81 169					95.87 194

ACMMP++_ref															90.30 249

ACMMP++															91.02 237

High-resolution multi-view benchmark