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.

FOURS1					98.86 1	85.54 74	98.29 1	97.49 5	89.79 43	96.29 15

test_0728_SECOND				95.01 17	98.79 2	86.43 43	97.09 14	97.49 5					99.61 3	95.62 8	99.08 7	98.99 7

DVP-MVS		95.67 3	96.02 3	94.64 43	98.78 3	85.93 61	97.09 14	96.73 81	90.27 31	97.04 10	98.05 8	91.47 8	99.55 15	95.62 8	99.08 7	98.45 36
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					98.78 3	85.93 61	97.19 9	97.47 10	90.27 31	97.64 4	98.13 1	91.47 8

SED-MVS		95.91 2	96.28 2	94.80 36	98.77 5	85.99 58	97.13 12	97.44 14	90.31 29	97.71 1	98.07 4	92.31 4	99.58 8	95.66 4	99.13 3	98.84 12

IU-MVS					98.77 5	86.00 56		96.84 67	81.26 248	97.26 7				95.50 10	99.13 3	99.03 6

test_241102_ONE					98.77 5	85.99 58		97.44 14	90.26 33	97.71 1	97.96 10	92.31 4	99.38 32

region2R		94.43 23	94.27 25	94.92 22	98.65 8	86.67 34	96.92 22	97.23 35	88.60 76	93.58 51	97.27 29	85.22 59	99.54 19	92.21 52	98.74 33	98.56 23

ACMMPR		94.43 23	94.28 23	94.91 24	98.63 9	86.69 32	96.94 18	97.32 27	88.63 74	93.53 54	97.26 31	85.04 62	99.54 19	92.35 49	98.78 25	98.50 26

HFP-MVS		94.52 18	94.40 20	94.86 27	98.61 10	86.81 26	96.94 18	97.34 22	88.63 74	93.65 47	97.21 34	86.10 48	99.49 26	92.35 49	98.77 28	98.30 45

#test#		94.32 29	94.14 32	94.86 27	98.61 10	86.81 26	96.43 34	97.34 22	87.51 107	93.65 47	97.21 34	86.10 48	99.49 26	91.68 73	98.77 28	98.30 45

test_one_0601					98.58 12	85.83 67		97.44 14	91.05 15	96.78 13	98.06 6	91.45 11

test_part2					98.55 13	87.22 18				96.40 14

XVS		94.45 21	94.32 21	94.85 29	98.54 14	86.60 38	96.93 20	97.19 38	90.66 25	92.85 66	97.16 39	85.02 63	99.49 26	91.99 61	98.56 51	98.47 32

X-MVStestdata		88.31 166	86.13 208	94.85 29	98.54 14	86.60 38	96.93 20	97.19 38	90.66 25	92.85 66	23.41 367	85.02 63	99.49 26	91.99 61	98.56 51	98.47 32

ZNCC-MVS		94.47 19	94.28 23	95.03 16	98.52 16	86.96 19	96.85 26	97.32 27	88.24 86	93.15 59	97.04 45	86.17 47	99.62 1	92.40 47	98.81 22	98.52 24

mPP-MVS		93.99 39	93.78 44	94.63 44	98.50 17	85.90 66	96.87 24	96.91 59	88.70 72	91.83 96	97.17 38	83.96 77	99.55 15	91.44 78	98.64 47	98.43 38

MSP-MVS		95.42 6	95.56 6	94.98 21	98.49 18	86.52 40	96.91 23	97.47 10	91.73 8	96.10 17	96.69 61	89.90 12	99.30 42	94.70 12	98.04 70	99.13 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
MP-MVS		94.25 30	94.07 35	94.77 38	98.47 19	86.31 49	96.71 29	96.98 51	89.04 63	91.98 90	97.19 36	85.43 57	99.56 10	92.06 60	98.79 23	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		94.45 21	94.20 29	95.19 11	98.46 20	87.50 15	95.00 112	97.12 43	87.13 114	92.51 80	96.30 77	89.24 17	99.34 36	93.46 25	98.62 48	98.73 15

PGM-MVS		93.96 41	93.72 46	94.68 41	98.43 21	86.22 52	95.30 89	97.78 1	87.45 110	93.26 55	97.33 26	84.62 68	99.51 24	90.75 91	98.57 50	98.32 44

zzz-MVS		94.47 19	94.30 22	95.00 18	98.42 22	86.95 20	95.06 110	96.97 52	91.07 13	93.14 60	97.56 16	84.30 70	99.56 10	93.43 26	98.75 31	98.47 32

MTAPA		94.42 25	94.22 26	95.00 18	98.42 22	86.95 20	94.36 160	96.97 52	91.07 13	93.14 60	97.56 16	84.30 70	99.56 10	93.43 26	98.75 31	98.47 32

GST-MVS		94.21 34	93.97 39	94.90 26	98.41 24	86.82 25	96.54 33	97.19 38	88.24 86	93.26 55	96.83 54	85.48 56	99.59 7	91.43 79	98.40 57	98.30 45

HPM-MVS		94.02 38	93.88 40	94.43 53	98.39 25	85.78 69	97.25 8	97.07 47	86.90 122	92.62 77	96.80 58	84.85 66	99.17 53	92.43 45	98.65 46	98.33 43
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		94.34 27	94.21 28	94.74 40	98.39 25	86.64 36	97.60 3	97.24 33	88.53 78	92.73 73	97.23 32	85.20 60	99.32 40	92.15 55	98.83 21	98.25 54

DPE-MVS		95.57 4	95.67 4	95.25 9	98.36 27	87.28 17	95.56 79	97.51 4	89.13 61	97.14 8	97.91 11	91.64 7	99.62 1	94.61 14	99.17 2	98.86 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
HPM-MVS_fast		93.40 57	93.22 56	93.94 64	98.36 27	84.83 81	97.15 11	96.80 73	85.77 144	92.47 81	97.13 40	82.38 91	99.07 61	90.51 93	98.40 57	97.92 79

DP-MVS Recon		91.95 79	91.28 85	93.96 63	98.33 29	85.92 63	94.66 135	96.66 91	82.69 213	90.03 121	95.82 98	82.30 94	99.03 67	84.57 158	96.48 106	96.91 122

APDe-MVS		95.46 5	95.64 5	94.91 24	98.26 30	86.29 51	97.46 4	97.40 20	89.03 65	96.20 16	98.10 2	89.39 16	99.34 36	95.88 3	99.03 11	99.10 3

TSAR-MVS + MP.		94.85 13	94.94 11	94.58 46	98.25 31	86.33 47	96.11 52	96.62 94	88.14 92	96.10 17	96.96 49	89.09 18	98.94 87	94.48 15	98.68 39	98.48 28
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		95.14 10	94.91 12	95.83 4	98.25 31	89.65 4	95.92 62	96.96 55	91.75 7	94.02 39	96.83 54	88.12 24	99.55 15	93.41 28	98.94 16	98.28 49

testtj		94.39 26	94.18 30	95.00 18	98.24 33	86.77 30	96.16 47	97.23 35	87.28 112	94.85 28	97.04 45	86.99 40	99.52 23	91.54 75	98.33 60	98.71 16

CPTT-MVS		91.99 78	91.80 79	92.55 111	98.24 33	81.98 160	96.76 28	96.49 102	81.89 233	90.24 117	96.44 74	78.59 136	98.61 110	89.68 98	97.85 77	97.06 114

SR-MVS		94.23 32	94.17 31	94.43 53	98.21 35	85.78 69	96.40 37	96.90 60	88.20 89	94.33 31	97.40 23	84.75 67	99.03 67	93.35 29	97.99 71	98.48 28

MP-MVS-pluss		94.21 34	94.00 38	94.85 29	98.17 36	86.65 35	94.82 124	97.17 41	86.26 135	92.83 68	97.87 12	85.57 55	99.56 10	94.37 17	98.92 17	98.34 42
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ZD-MVS					98.15 37	86.62 37		97.07 47	83.63 190	94.19 34	96.91 51	87.57 32	99.26 46	91.99 61	98.44 55

SMA-MVS		95.20 8	95.07 10	95.59 5	98.14 38	88.48 8	96.26 43	97.28 31	85.90 141	97.67 3	98.10 2	88.41 20	99.56 10	94.66 13	99.19 1	98.71 16
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
test1172		93.97 40	94.07 35	93.66 74	98.11 39	83.45 120	96.26 43	96.84 67	88.33 82	94.19 34	97.43 20	84.24 72	99.01 73	93.26 31	97.98 72	98.52 24

CNVR-MVS		95.40 7	95.37 7	95.50 7	98.11 39	88.51 7	95.29 92	96.96 55	92.09 3	95.32 23	97.08 42	89.49 15	99.33 39	95.10 11	98.85 19	98.66 18

114514_t		89.51 131	88.50 141	92.54 112	98.11 39	81.99 159	95.16 103	96.36 110	70.19 346	85.81 187	95.25 114	76.70 154	98.63 108	82.07 193	96.86 96	97.00 118

ACMMP		93.24 61	92.88 65	94.30 57	98.09 42	85.33 77	96.86 25	97.45 13	88.33 82	90.15 119	97.03 47	81.44 105	99.51 24	90.85 89	95.74 112	98.04 70
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
APD-MVS		94.24 31	94.07 35	94.75 39	98.06 43	86.90 23	95.88 63	96.94 57	85.68 147	95.05 27	97.18 37	87.31 34	99.07 61	91.90 69	98.61 49	98.28 49
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CSCG		93.23 62	93.05 60	93.76 72	98.04 44	84.07 103	96.22 45	97.37 21	84.15 179	90.05 120	95.66 104	87.77 26	99.15 56	89.91 96	98.27 62	98.07 67

ACMMP_NAP		94.74 15	94.56 17	95.28 8	98.02 45	87.70 12	95.68 72	97.34 22	88.28 85	95.30 24	97.67 15	85.90 52	99.54 19	93.91 20	98.95 15	98.60 21

OPU-MVS				96.21 3	98.00 46	90.85 3	97.13 12				97.08 42	92.59 2	98.94 87	92.25 51	98.99 14	98.84 12

SR-MVS-dyc-post		93.82 45	93.82 41	93.82 67	97.92 47	84.57 86	96.28 41	96.76 77	87.46 108	93.75 44	97.43 20	84.24 72	99.01 73	92.73 38	97.80 78	97.88 81

RE-MVS-def			93.68 48		97.92 47	84.57 86	96.28 41	96.76 77	87.46 108	93.75 44	97.43 20	82.94 85		92.73 38	97.80 78	97.88 81

APD-MVS_3200maxsize		93.78 46	93.77 45	93.80 71	97.92 47	84.19 101	96.30 39	96.87 64	86.96 118	93.92 41	97.47 18	83.88 78	98.96 86	92.71 41	97.87 76	98.26 53

xxxxxxxxxxxxxcwj		94.65 16	94.70 15	94.48 50	97.85 50	85.63 72	95.21 98	95.47 176	89.44 50	95.71 19	97.70 13	88.28 22	99.35 34	93.89 21	98.78 25	98.48 28

save fliter					97.85 50	85.63 72	95.21 98	96.82 71	89.44 50

SF-MVS		94.97 11	94.90 13	95.20 10	97.84 52	87.76 10	96.65 31	97.48 9	87.76 101	95.71 19	97.70 13	88.28 22	99.35 34	93.89 21	98.78 25	98.48 28

NCCC		94.81 14	94.69 16	95.17 12	97.83 53	87.46 16	95.66 74	96.93 58	92.34 2	93.94 40	96.58 68	87.74 27	99.44 30	92.83 37	98.40 57	98.62 20

ETH3 D test6400		93.64 50	93.22 56	94.92 22	97.79 54	86.84 24	95.31 86	97.26 32	82.67 214	93.81 43	96.29 78	87.29 35	99.27 45	89.87 97	98.67 41	98.65 19

9.14			94.47 18		97.79 54		96.08 53	97.44 14	86.13 139	95.10 26	97.40 23	88.34 21	99.22 49	93.25 32	98.70 36

CDPH-MVS		92.83 66	92.30 74	94.44 51	97.79 54	86.11 54	94.06 179	96.66 91	80.09 261	92.77 70	96.63 65	86.62 42	99.04 66	87.40 125	98.66 44	98.17 58

DVP-MVS++.		95.98 1	96.36 1	94.82 34	97.78 57	86.00 56	98.29 1	97.49 5	90.75 20	97.62 5	98.06 6	92.59 2	99.61 3	95.64 6	99.02 12	98.86 9

MSC_two_6792asdad				96.52 1	97.78 57	90.86 1		96.85 65					99.61 3	96.03 1	99.06 9	99.07 4

No_MVS				96.52 1	97.78 57	90.86 1		96.85 65					99.61 3	96.03 1	99.06 9	99.07 4

ETH3D-3000-0.1		94.61 17	94.44 19	95.12 13	97.70 60	87.71 11	95.98 59	97.44 14	86.67 127	95.25 25	97.31 27	87.73 28	99.24 47	93.11 35	98.76 30	98.40 39

DP-MVS		87.25 204	85.36 234	92.90 94	97.65 61	83.24 125	94.81 125	92.00 289	74.99 315	81.92 278	95.00 122	72.66 210	99.05 63	66.92 329	92.33 171	96.40 136

PAPM_NR		91.22 93	90.78 96	92.52 113	97.60 62	81.46 173	94.37 159	96.24 117	86.39 133	87.41 157	94.80 131	82.06 100	98.48 116	82.80 182	95.37 120	97.61 92

TEST9					97.53 63	86.49 41	94.07 177	96.78 74	81.61 241	92.77 70	96.20 83	87.71 29	99.12 58

train_agg		93.44 54	93.08 59	94.52 48	97.53 63	86.49 41	94.07 177	96.78 74	81.86 234	92.77 70	96.20 83	87.63 30	99.12 58	92.14 56	98.69 37	97.94 76

abl_6		93.18 63	93.05 60	93.57 76	97.52 65	84.27 100	95.53 80	96.67 90	87.85 98	93.20 58	97.22 33	80.35 112	99.18 52	91.91 66	97.21 89	97.26 105

test_8					97.49 66	86.30 50	94.02 182	96.76 77	81.86 234	92.70 74	96.20 83	87.63 30	99.02 71

DeepC-MVS_fast	89.43 2	94.04 37	93.79 43	94.80 36	97.48 67	86.78 28	95.65 76	96.89 61	89.40 53	92.81 69	96.97 48	85.37 58	99.24 47	90.87 88	98.69 37	98.38 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		89.89 123	89.07 129	92.37 121	97.41 68	83.03 131	94.42 151	95.92 140	82.81 211	86.34 180	94.65 137	73.89 193	99.02 71	80.69 219	95.51 115	95.05 184

agg_prior1		93.29 59	92.97 63	94.26 58	97.38 69	85.92 63	93.92 188	96.72 83	81.96 228	92.16 85	96.23 81	87.85 25	98.97 83	91.95 65	98.55 53	97.90 80

agg_prior					97.38 69	85.92 63		96.72 83		92.16 85			98.97 83

原ACMM1				92.01 133	97.34 71	81.05 185		96.81 72	78.89 275	90.45 115	95.92 94	82.65 88	98.84 99	80.68 220	98.26 63	96.14 145

MSLP-MVS++		93.72 47	94.08 34	92.65 106	97.31 72	83.43 121	95.79 67	97.33 25	90.03 36	93.58 51	96.96 49	84.87 65	97.76 170	92.19 54	98.66 44	96.76 125

新几何1				93.10 84	97.30 73	84.35 99		95.56 168	71.09 343	91.26 107	96.24 80	82.87 87	98.86 94	79.19 241	98.10 68	96.07 152

test_prior3		93.60 51	93.53 51	93.82 67	97.29 74	84.49 90	94.12 170	96.88 62	87.67 104	92.63 75	96.39 75	86.62 42	98.87 91	91.50 76	98.67 41	98.11 65

test_prior				93.82 67	97.29 74	84.49 90		96.88 62					98.87 91			98.11 65

1121		90.42 110	89.49 116	93.20 80	97.27 76	84.46 93	92.63 236	95.51 174	71.01 344	91.20 108	96.21 82	82.92 86	99.05 63	80.56 222	98.07 69	96.10 150

PLC	84.53 7	89.06 146	88.03 154	92.15 129	97.27 76	82.69 145	94.29 162	95.44 182	79.71 266	84.01 244	94.18 155	76.68 155	98.75 103	77.28 258	93.41 152	95.02 185
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SD-MVS		94.96 12	95.33 8	93.88 65	97.25 78	86.69 32	96.19 46	97.11 45	90.42 28	96.95 12	97.27 29	89.53 14	96.91 243	94.38 16	98.85 19	98.03 71
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
test12				94.34 56	97.13 79	86.15 53		96.29 112		91.04 111		85.08 61	99.01 73		98.13 67	97.86 83

MG-MVS		91.77 82	91.70 81	92.00 135	97.08 80	80.03 215	93.60 201	95.18 196	87.85 98	90.89 112	96.47 73	82.06 100	98.36 125	85.07 150	97.04 93	97.62 91

SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 29	96.99 81	86.33 47	97.33 5	97.30 29	91.38 11	95.39 22	97.46 19	88.98 19	99.40 31	94.12 18	98.89 18	98.82 14
Skip Steuart: Steuart Systems R&D Blog.
MVS_111021_HR		93.45 53	93.31 54	93.84 66	96.99 81	84.84 80	93.24 218	97.24 33	88.76 71	91.60 101	95.85 97	86.07 50	98.66 105	91.91 66	98.16 65	98.03 71

CNLPA		89.07 145	87.98 156	92.34 122	96.87 83	84.78 82	94.08 176	93.24 260	81.41 244	84.46 228	95.13 119	75.57 170	96.62 253	77.21 259	93.84 143	95.61 170

PHI-MVS		93.89 44	93.65 49	94.62 45	96.84 84	86.43 43	96.69 30	97.49 5	85.15 163	93.56 53	96.28 79	85.60 54	99.31 41	92.45 44	98.79 23	98.12 63

旧先验1					96.79 85	81.81 163		95.67 160			96.81 56	86.69 41			97.66 82	96.97 119

ETH3D cwj APD-0.16		93.91 42	93.53 51	95.06 15	96.76 86	87.78 9	94.92 117	97.21 37	84.33 177	93.89 42	97.09 41	87.20 36	99.29 44	91.90 69	98.44 55	98.12 63

LFMVS		90.08 115	89.13 128	92.95 92	96.71 87	82.32 155	96.08 53	89.91 337	86.79 123	92.15 87	96.81 56	62.60 302	98.34 128	87.18 129	93.90 141	98.19 57

Anonymous202405211		87.68 182	86.13 208	92.31 124	96.66 88	80.74 195	94.87 121	91.49 304	80.47 257	89.46 126	95.44 108	54.72 340	98.23 134	82.19 191	89.89 195	97.97 74

TAPA-MVS	84.62 6	88.16 170	87.01 178	91.62 154	96.64 89	80.65 196	94.39 154	96.21 122	76.38 300	86.19 183	95.44 108	79.75 120	98.08 150	62.75 344	95.29 122	96.13 146
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MAR-MVS		90.30 111	89.37 121	93.07 87	96.61 90	84.48 92	95.68 72	95.67 160	82.36 219	87.85 148	92.85 202	76.63 156	98.80 101	80.01 230	96.68 99	95.91 157
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
VNet		92.24 77	91.91 78	93.24 79	96.59 91	83.43 121	94.84 123	96.44 103	89.19 59	94.08 38	95.90 95	77.85 147	98.17 138	88.90 107	93.38 153	98.13 62

TSAR-MVS + GP.		93.66 49	93.41 53	94.41 55	96.59 91	86.78 28	94.40 152	93.93 246	89.77 44	94.21 33	95.59 107	87.35 33	98.61 110	92.72 40	96.15 109	97.83 85

test222					96.55 93	81.70 165	92.22 250	95.01 203	68.36 349	90.20 118	96.14 88	80.26 115			97.80 78	96.05 154

Anonymous20240529		88.09 172	86.59 193	92.58 110	96.53 94	81.92 162	95.99 57	95.84 148	74.11 323	89.06 132	95.21 116	61.44 310	98.81 100	83.67 170	87.47 232	97.01 117

Anonymous20231211		86.59 227	85.13 237	90.98 184	96.52 95	81.50 169	96.14 49	96.16 123	73.78 325	83.65 253	92.15 225	63.26 300	97.37 209	82.82 181	81.74 288	94.06 232

DeepPCF-MVS	89.96 1	94.20 36	94.77 14	92.49 114	96.52 95	80.00 217	94.00 184	97.08 46	90.05 35	95.65 21	97.29 28	89.66 13	98.97 83	93.95 19	98.71 34	98.50 26

testdata				90.49 197	96.40 97	77.89 263		95.37 188	72.51 336	93.63 49	96.69 61	82.08 99	97.65 179	83.08 174	97.39 87	95.94 156

PVSNet_Blended_VisFu		91.38 89	90.91 93	92.80 97	96.39 98	83.17 127	94.87 121	96.66 91	83.29 200	89.27 128	94.46 144	80.29 114	99.17 53	87.57 123	95.37 120	96.05 154

API-MVS		90.66 104	90.07 106	92.45 116	96.36 99	84.57 86	96.06 55	95.22 195	82.39 217	89.13 129	94.27 153	80.32 113	98.46 118	80.16 229	96.71 98	94.33 220

F-COLMAP		87.95 175	86.80 183	91.40 163	96.35 100	80.88 191	94.73 130	95.45 180	79.65 267	82.04 276	94.61 138	71.13 224	98.50 115	76.24 269	91.05 182	94.80 198

VDD-MVS		90.74 100	89.92 112	93.20 80	96.27 101	83.02 132	95.73 69	93.86 250	88.42 81	92.53 78	96.84 53	62.09 305	98.64 107	90.95 86	92.62 167	97.93 78

OMC-MVS		91.23 92	90.62 97	93.08 85	96.27 101	84.07 103	93.52 203	95.93 139	86.95 119	89.51 124	96.13 89	78.50 138	98.35 127	85.84 143	92.90 163	96.83 124

DPM-MVS		92.58 70	91.74 80	95.08 14	96.19 103	89.31 5	92.66 235	96.56 100	83.44 196	91.68 100	95.04 121	86.60 45	98.99 80	85.60 146	97.92 75	96.93 121

CHOSEN 1792x2688		88.84 153	87.69 161	92.30 125	96.14 104	81.42 175	90.01 293	95.86 147	74.52 320	87.41 157	93.94 164	75.46 171	98.36 125	80.36 225	95.53 114	97.12 113

thres100view900		87.63 187	86.71 186	90.38 203	96.12 105	78.55 245	95.03 111	91.58 300	87.15 113	88.06 144	92.29 221	68.91 259	98.10 142	70.13 308	91.10 178	94.48 216

PVSNet_BlendedMVS		89.98 118	89.70 113	90.82 186	96.12 105	81.25 179	93.92 188	96.83 69	83.49 195	89.10 130	92.26 222	81.04 109	98.85 97	86.72 137	87.86 230	92.35 302

PVSNet_Blended		90.73 101	90.32 100	91.98 136	96.12 105	81.25 179	92.55 240	96.83 69	82.04 226	89.10 130	92.56 212	81.04 109	98.85 97	86.72 137	95.91 110	95.84 161

UA-Net		92.83 66	92.54 71	93.68 73	96.10 108	84.71 83	95.66 74	96.39 108	91.92 4	93.22 57	96.49 72	83.16 82	98.87 91	84.47 159	95.47 117	97.45 100

thres600view7		87.65 184	86.67 188	90.59 190	96.08 109	78.72 241	94.88 120	91.58 300	87.06 116	88.08 143	92.30 220	68.91 259	98.10 142	70.05 311	91.10 178	94.96 189

DeepC-MVS	88.79 3	93.31 58	92.99 62	94.26 58	96.07 110	85.83 67	94.89 119	96.99 50	89.02 66	89.56 123	97.37 25	82.51 90	99.38 32	92.20 53	98.30 61	97.57 95
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		87.89 176	86.32 203	92.59 109	96.07 110	82.92 136	95.23 96	94.92 211	75.66 307	82.89 266	95.98 92	72.48 213	99.21 50	68.43 318	95.23 125	95.64 169

hse-mvs3		90.80 98	90.15 104	92.75 100	96.01 112	82.66 146	95.43 82	95.53 172	89.80 40	93.08 62	95.64 105	75.77 163	99.00 78	92.07 58	78.05 326	96.60 131

HyFIR lowres test		88.09 172	86.81 182	91.93 140	96.00 113	80.63 197	90.01 293	95.79 152	73.42 328	87.68 153	92.10 230	73.86 194	97.96 161	80.75 218	91.70 174	97.19 109

tfpn200view9		87.58 191	86.64 189	90.41 200	95.99 114	78.64 243	94.58 138	91.98 291	86.94 120	88.09 141	91.77 240	69.18 256	98.10 142	70.13 308	91.10 178	94.48 216

thres400		87.62 189	86.64 189	90.57 191	95.99 114	78.64 243	94.58 138	91.98 291	86.94 120	88.09 141	91.77 240	69.18 256	98.10 142	70.13 308	91.10 178	94.96 189

MVS_111021_LR		92.47 74	92.29 75	92.98 90	95.99 114	84.43 97	93.08 223	96.09 127	88.20 89	91.12 109	95.72 103	81.33 107	97.76 170	91.74 71	97.37 88	96.75 126

test_part1		89.00 150	87.99 155	92.04 131	95.94 117	83.81 110	96.14 49	96.05 132	86.44 131	85.69 190	93.73 178	71.57 219	97.66 177	85.80 144	80.54 307	94.66 201

PatchMatch-RL		86.77 223	85.54 228	90.47 199	95.88 118	82.71 144	90.54 282	92.31 280	79.82 265	84.32 236	91.57 250	68.77 261	96.39 272	73.16 292	93.48 151	92.32 303

EPP-MVSNet		91.70 85	91.56 82	92.13 130	95.88 118	80.50 202	97.33 5	95.25 192	86.15 137	89.76 122	95.60 106	83.42 81	98.32 131	87.37 127	93.25 156	97.56 96

IS-MVSNet		91.43 88	91.09 90	92.46 115	95.87 120	81.38 176	96.95 17	93.69 255	89.72 46	89.50 125	95.98 92	78.57 137	97.77 169	83.02 176	96.50 105	98.22 56

PAPR		90.02 117	89.27 126	92.29 126	95.78 121	80.95 189	92.68 234	96.22 119	81.91 231	86.66 173	93.75 177	82.23 95	98.44 122	79.40 240	94.79 127	97.48 98

Vis-MVSNet (Re-imp)		89.59 129	89.44 118	90.03 217	95.74 122	75.85 294	95.61 77	90.80 322	87.66 106	87.83 149	95.40 111	76.79 152	96.46 269	78.37 246	96.73 97	97.80 86

test_yl		90.69 102	90.02 110	92.71 102	95.72 123	82.41 153	94.11 172	95.12 198	85.63 148	91.49 102	94.70 133	74.75 178	98.42 123	86.13 141	92.53 168	97.31 102

DCV-MVSNet		90.69 102	90.02 110	92.71 102	95.72 123	82.41 153	94.11 172	95.12 198	85.63 148	91.49 102	94.70 133	74.75 178	98.42 123	86.13 141	92.53 168	97.31 102

canonicalmvs		93.27 60	92.75 67	94.85 29	95.70 125	87.66 13	96.33 38	96.41 106	90.00 37	94.09 37	94.60 139	82.33 93	98.62 109	92.40 47	92.86 164	98.27 51

CANet		93.54 52	93.20 58	94.55 47	95.65 126	85.73 71	94.94 115	96.69 88	91.89 5	90.69 113	95.88 96	81.99 102	99.54 19	93.14 34	97.95 74	98.39 40

3Dnovator+	87.14 4	92.42 75	91.37 83	95.55 6	95.63 127	88.73 6	97.07 16	96.77 76	90.84 17	84.02 243	96.62 66	75.95 162	99.34 36	87.77 120	97.68 81	98.59 22

alignmvs		93.08 64	92.50 72	94.81 35	95.62 128	87.61 14	95.99 57	96.07 129	89.77 44	94.12 36	94.87 126	80.56 111	98.66 105	92.42 46	93.10 159	98.15 60

Regformer-1		94.22 33	94.13 33	94.51 49	95.54 129	86.36 46	94.57 140	96.44 103	91.69 9	94.32 32	96.56 70	87.05 39	99.03 67	93.35 29	97.65 83	98.15 60

Regformer-2		94.33 28	94.22 26	94.68 41	95.54 129	86.75 31	94.57 140	96.70 86	91.84 6	94.41 29	96.56 70	87.19 37	99.13 57	93.50 24	97.65 83	98.16 59

WTY-MVS		89.60 128	88.92 133	91.67 153	95.47 131	81.15 183	92.38 244	94.78 221	83.11 203	89.06 132	94.32 148	78.67 135	96.61 256	81.57 205	90.89 184	97.24 106

DELS-MVS		93.43 56	93.25 55	93.97 62	95.42 132	85.04 79	93.06 225	97.13 42	90.74 22	91.84 94	95.09 120	86.32 46	99.21 50	91.22 80	98.45 54	97.65 90
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
Regformer-3		93.68 48	93.64 50	93.81 70	95.36 133	84.61 84	94.68 132	95.83 149	91.27 12	93.60 50	96.71 59	85.75 53	98.86 94	92.87 36	96.65 100	97.96 75

Regformer-4		93.91 42	93.81 42	94.19 60	95.36 133	85.47 75	94.68 132	96.41 106	91.60 10	93.75 44	96.71 59	85.95 51	99.10 60	93.21 33	96.65 100	98.01 73

thres200		87.21 208	86.24 206	90.12 213	95.36 133	78.53 246	93.26 215	92.10 285	86.42 132	88.00 146	91.11 263	69.24 255	98.00 158	69.58 312	91.04 183	93.83 245

Vis-MVSNet		91.75 83	91.23 86	93.29 77	95.32 136	83.78 111	96.14 49	95.98 135	89.89 38	90.45 115	96.58 68	75.09 174	98.31 132	84.75 156	96.90 94	97.78 88
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
BH-RMVSNet		88.37 164	87.48 166	91.02 179	95.28 137	79.45 227	92.89 230	93.07 264	85.45 154	86.91 168	94.84 130	70.35 238	97.76 170	73.97 287	94.59 132	95.85 160

COLMAP_ROB	80.39 16	83.96 268	82.04 275	89.74 229	95.28 137	79.75 222	94.25 164	92.28 281	75.17 313	78.02 316	93.77 175	58.60 329	97.84 167	65.06 337	85.92 244	91.63 313
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PS-MVSNAJ		91.18 94	90.92 92	91.96 138	95.26 139	82.60 149	92.09 255	95.70 158	86.27 134	91.84 94	92.46 214	79.70 122	98.99 80	89.08 105	95.86 111	94.29 221

BH-untuned		88.60 160	88.13 153	90.01 219	95.24 140	78.50 248	93.29 213	94.15 240	84.75 171	84.46 228	93.40 182	75.76 165	97.40 205	77.59 255	94.52 134	94.12 227

DROMVSNet		93.44 54	93.71 47	92.63 107	95.21 141	82.43 150	97.27 7	96.71 85	90.57 27	92.88 65	95.80 99	83.16 82	98.16 139	93.68 23	98.14 66	97.31 102

ETV-MVS		92.74 68	92.66 69	92.97 91	95.20 142	84.04 105	95.07 107	96.51 101	90.73 23	92.96 64	91.19 257	84.06 74	98.34 128	91.72 72	96.54 103	96.54 135

GeoE		90.05 116	89.43 119	91.90 143	95.16 143	80.37 204	95.80 66	94.65 225	83.90 184	87.55 156	94.75 132	78.18 142	97.62 183	81.28 208	93.63 145	97.71 89

EIA-MVS		91.95 79	91.94 77	91.98 136	95.16 143	80.01 216	95.36 83	96.73 81	88.44 79	89.34 127	92.16 224	83.82 80	98.45 121	89.35 102	97.06 92	97.48 98

ab-mvs		89.41 137	88.35 145	92.60 108	95.15 145	82.65 147	92.20 251	95.60 167	83.97 183	88.55 136	93.70 179	74.16 189	98.21 137	82.46 187	89.37 203	96.94 120

VDDNet		89.56 130	88.49 143	92.76 99	95.07 146	82.09 157	96.30 39	93.19 262	81.05 253	91.88 92	96.86 52	61.16 315	98.33 130	88.43 113	92.49 170	97.84 84

AllTest		83.42 274	81.39 280	89.52 237	95.01 147	77.79 267	93.12 220	90.89 320	77.41 292	76.12 328	93.34 183	54.08 343	97.51 189	68.31 319	84.27 257	93.26 268

TestCases				89.52 237	95.01 147	77.79 267		90.89 320	77.41 292	76.12 328	93.34 183	54.08 343	97.51 189	68.31 319	84.27 257	93.26 268

EI-MVSNet-Vis-set		93.01 65	92.92 64	93.29 77	95.01 147	83.51 119	94.48 144	95.77 153	90.87 16	92.52 79	96.67 63	84.50 69	99.00 78	91.99 61	94.44 137	97.36 101

xiu_mvs_v2_base		91.13 95	90.89 94	91.86 144	94.97 150	82.42 151	92.24 249	95.64 165	86.11 140	91.74 99	93.14 194	79.67 125	98.89 90	89.06 106	95.46 118	94.28 222

tttt0517		88.61 159	87.78 160	91.11 174	94.96 151	77.81 266	95.35 84	89.69 341	85.09 165	88.05 145	94.59 140	66.93 274	98.48 116	83.27 173	92.13 173	97.03 116

baseline1		88.10 171	87.28 172	90.57 191	94.96 151	80.07 211	94.27 163	91.29 309	86.74 124	87.41 157	94.00 161	76.77 153	96.20 280	80.77 217	79.31 322	95.44 174

Test_1112_low_res		87.65 184	86.51 196	91.08 175	94.94 153	79.28 235	91.77 260	94.30 234	76.04 305	83.51 257	92.37 217	77.86 146	97.73 174	78.69 245	89.13 209	96.22 142

1112_ss		88.42 162	87.33 170	91.72 151	94.92 154	80.98 187	92.97 228	94.54 226	78.16 289	83.82 248	93.88 169	78.78 133	97.91 165	79.45 236	89.41 202	96.26 141

QAPM		89.51 131	88.15 152	93.59 75	94.92 154	84.58 85	96.82 27	96.70 86	78.43 284	83.41 259	96.19 86	73.18 205	99.30 42	77.11 261	96.54 103	96.89 123

BH-w/o		87.57 192	87.05 177	89.12 246	94.90 156	77.90 262	92.41 242	93.51 257	82.89 210	83.70 251	91.34 251	75.75 166	97.07 232	75.49 274	93.49 149	92.39 300

thisisatest0530		88.67 157	87.61 164	91.86 144	94.87 157	80.07 211	94.63 136	89.90 338	84.00 182	88.46 138	93.78 174	66.88 276	98.46 118	83.30 172	92.65 166	97.06 114

CS-MVS-test		92.55 71	92.72 68	92.02 132	94.87 157	81.34 177	96.43 34	96.57 98	89.04 63	91.05 110	94.41 145	83.85 79	98.09 148	90.83 90	97.47 86	96.64 130

EI-MVSNet-UG-set		92.74 68	92.62 70	93.12 83	94.86 159	83.20 126	94.40 152	95.74 156	90.71 24	92.05 89	96.60 67	84.00 76	98.99 80	91.55 74	93.63 145	97.17 110

HY-MVS	83.01 12	89.03 147	87.94 158	92.29 126	94.86 159	82.77 138	92.08 256	94.49 227	81.52 243	86.93 166	92.79 208	78.32 141	98.23 134	79.93 231	90.55 185	95.88 159

hse-mvs2		89.88 124	89.34 122	91.51 158	94.83 161	81.12 184	93.94 187	93.91 249	89.80 40	93.08 62	93.60 180	75.77 163	97.66 177	92.07 58	77.07 333	95.74 166

AUN-MVS		87.78 180	86.54 195	91.48 160	94.82 162	81.05 185	93.91 191	93.93 246	83.00 206	86.93 166	93.53 181	69.50 249	97.67 176	86.14 140	77.12 332	95.73 167

Fast-Effi-MVS+		89.41 137	88.64 138	91.71 152	94.74 163	80.81 193	93.54 202	95.10 200	83.11 203	86.82 171	90.67 275	79.74 121	97.75 173	80.51 224	93.55 147	96.57 133

ACMP	84.23 8	89.01 149	88.35 145	90.99 182	94.73 164	81.27 178	95.07 107	95.89 145	86.48 129	83.67 252	94.30 149	69.33 251	97.99 159	87.10 134	88.55 214	93.72 254
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PVSNet	78.82 18	85.55 245	84.65 248	88.23 271	94.72 165	71.93 326	87.12 328	92.75 271	78.80 278	84.95 219	90.53 277	64.43 296	96.71 250	74.74 282	93.86 142	96.06 153

LCM-MVSNet-Re		88.30 167	88.32 148	88.27 268	94.71 166	72.41 325	93.15 219	90.98 316	87.77 100	79.25 310	91.96 236	78.35 140	95.75 300	83.04 175	95.62 113	96.65 129

HQP_MVS		90.60 108	90.19 102	91.82 147	94.70 167	82.73 142	95.85 64	96.22 119	90.81 18	86.91 168	94.86 127	74.23 185	98.12 140	88.15 115	89.99 191	94.63 202

plane_prior7					94.70 167	82.74 141

ACMH+	81.04 14	85.05 256	83.46 264	89.82 225	94.66 169	79.37 229	94.44 149	94.12 243	82.19 222	78.04 315	92.82 205	58.23 330	97.54 187	73.77 289	82.90 274	92.54 294

ACMM	84.12 9	89.14 143	88.48 144	91.12 171	94.65 170	81.22 181	95.31 86	96.12 126	85.31 158	85.92 186	94.34 146	70.19 241	98.06 152	85.65 145	88.86 212	94.08 231
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
plane_prior1					94.59 171

3Dnovator	86.66 5	91.73 84	90.82 95	94.44 51	94.59 171	86.37 45	97.18 10	97.02 49	89.20 58	84.31 238	96.66 64	73.74 197	99.17 53	86.74 135	97.96 73	97.79 87

plane_prior6					94.52 173	82.75 139						74.23 185

UGNet		89.95 120	88.95 132	92.95 92	94.51 174	83.31 124	95.70 71	95.23 193	89.37 54	87.58 154	93.94 164	64.00 297	98.78 102	83.92 165	96.31 108	96.74 127
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
LPG-MVS_test		89.45 134	88.90 134	91.12 171	94.47 175	81.49 171	95.30 89	96.14 124	86.73 125	85.45 203	95.16 117	69.89 243	98.10 142	87.70 121	89.23 207	93.77 250

LGP-MVS_train				91.12 171	94.47 175	81.49 171		96.14 124	86.73 125	85.45 203	95.16 117	69.89 243	98.10 142	87.70 121	89.23 207	93.77 250

baseline		92.39 76	92.29 75	92.69 105	94.46 177	81.77 164	94.14 169	96.27 113	89.22 57	91.88 92	96.00 91	82.35 92	97.99 159	91.05 82	95.27 124	98.30 45

ACMH	80.38 17	85.36 248	83.68 260	90.39 201	94.45 178	80.63 197	94.73 130	94.85 215	82.09 223	77.24 320	92.65 210	60.01 322	97.58 184	72.25 296	84.87 252	92.96 283
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LTVRE_ROB	82.13 13	86.26 235	84.90 243	90.34 206	94.44 179	81.50 169	92.31 248	94.89 212	83.03 205	79.63 307	92.67 209	69.69 246	97.79 168	71.20 299	86.26 243	91.72 311
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
casdiffmvs		92.51 73	92.43 73	92.74 101	94.41 180	81.98 160	94.54 142	96.23 118	89.57 48	91.96 91	96.17 87	82.58 89	98.01 157	90.95 86	95.45 119	98.23 55

MVS_Test		91.31 91	91.11 88	91.93 140	94.37 181	80.14 208	93.46 206	95.80 151	86.46 130	91.35 106	93.77 175	82.21 96	98.09 148	87.57 123	94.95 126	97.55 97

NP-MVS					94.37 181	82.42 151					93.98 162

TR-MVS		86.78 220	85.76 225	89.82 225	94.37 181	78.41 250	92.47 241	92.83 268	81.11 252	86.36 179	92.40 216	68.73 262	97.48 191	73.75 290	89.85 197	93.57 258

Effi-MVS+		91.59 87	91.11 88	93.01 89	94.35 184	83.39 123	94.60 137	95.10 200	87.10 115	90.57 114	93.10 196	81.43 106	98.07 151	89.29 103	94.48 135	97.59 94

CLD-MVS		89.47 133	88.90 134	91.18 170	94.22 185	82.07 158	92.13 253	96.09 127	87.90 96	85.37 212	92.45 215	74.38 183	97.56 186	87.15 130	90.43 186	93.93 237
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		92.55 71	92.87 66	91.58 156	94.21 186	80.54 200	95.30 89	96.68 89	88.18 91	92.09 88	94.57 142	84.06 74	98.05 153	92.56 43	98.19 64	96.15 143

HQP-NCC					94.17 187		94.39 154		88.81 68	85.43 206

ACMP_Plane					94.17 187		94.39 154		88.81 68	85.43 206

HQP-MVS		89.80 125	89.28 125	91.34 165	94.17 187	81.56 167	94.39 154	96.04 133	88.81 68	85.43 206	93.97 163	73.83 195	97.96 161	87.11 132	89.77 198	94.50 213

XVG-OURS		89.40 139	88.70 137	91.52 157	94.06 190	81.46 173	91.27 271	96.07 129	86.14 138	88.89 134	95.77 101	68.73 262	97.26 217	87.39 126	89.96 193	95.83 162

sss		88.93 151	88.26 151	90.94 185	94.05 191	80.78 194	91.71 263	95.38 186	81.55 242	88.63 135	93.91 168	75.04 175	95.47 311	82.47 186	91.61 175	96.57 133

PCF-MVS	84.11 10	87.74 181	86.08 212	92.70 104	94.02 192	84.43 97	89.27 303	95.87 146	73.62 327	84.43 230	94.33 147	78.48 139	98.86 94	70.27 304	94.45 136	94.81 197
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
GBi-Net		87.26 202	85.98 215	91.08 175	94.01 193	83.10 128	95.14 104	94.94 206	83.57 191	84.37 231	91.64 243	66.59 281	96.34 276	78.23 249	85.36 248	93.79 246

test1		87.26 202	85.98 215	91.08 175	94.01 193	83.10 128	95.14 104	94.94 206	83.57 191	84.37 231	91.64 243	66.59 281	96.34 276	78.23 249	85.36 248	93.79 246

FMVSNet2		87.19 209	85.82 221	91.30 166	94.01 193	83.67 114	94.79 126	94.94 206	83.57 191	83.88 246	92.05 234	66.59 281	96.51 264	77.56 256	85.01 251	93.73 253

XVG-OURS-SEG-HR		89.95 120	89.45 117	91.47 161	94.00 196	81.21 182	91.87 258	96.06 131	85.78 143	88.55 136	95.73 102	74.67 181	97.27 215	88.71 110	89.64 200	95.91 157

FIs		90.51 109	90.35 99	90.99 182	93.99 197	80.98 187	95.73 69	97.54 3	89.15 60	86.72 172	94.68 135	81.83 104	97.24 219	85.18 149	88.31 222	94.76 199

xiu_mvs_v1_base_debu		90.64 105	90.05 107	92.40 117	93.97 198	84.46 93	93.32 208	95.46 177	85.17 160	92.25 82	94.03 156	70.59 233	98.57 112	90.97 83	94.67 128	94.18 223

xiu_mvs_v1_base		90.64 105	90.05 107	92.40 117	93.97 198	84.46 93	93.32 208	95.46 177	85.17 160	92.25 82	94.03 156	70.59 233	98.57 112	90.97 83	94.67 128	94.18 223

xiu_mvs_v1_base_debi		90.64 105	90.05 107	92.40 117	93.97 198	84.46 93	93.32 208	95.46 177	85.17 160	92.25 82	94.03 156	70.59 233	98.57 112	90.97 83	94.67 128	94.18 223

VPA-MVSNet		89.62 127	88.96 131	91.60 155	93.86 201	82.89 137	95.46 81	97.33 25	87.91 95	88.43 139	93.31 186	74.17 188	97.40 205	87.32 128	82.86 275	94.52 211

MVSFormer		91.68 86	91.30 84	92.80 97	93.86 201	83.88 108	95.96 60	95.90 143	84.66 173	91.76 97	94.91 124	77.92 144	97.30 211	89.64 99	97.11 90	97.24 106

lupinMVS		90.92 97	90.21 101	93.03 88	93.86 201	83.88 108	92.81 232	93.86 250	79.84 264	91.76 97	94.29 150	77.92 144	98.04 154	90.48 94	97.11 90	97.17 110

IterMVS-LS		88.36 165	87.91 159	89.70 232	93.80 204	78.29 254	93.73 195	95.08 202	85.73 145	84.75 221	91.90 238	79.88 118	96.92 242	83.83 166	82.51 276	93.89 238
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		84.86 260	83.09 267	90.14 212	93.80 204	80.05 213	89.18 306	93.09 263	78.89 275	78.19 313	91.91 237	65.86 290	97.27 215	68.47 317	88.45 218	93.11 278

FMVSNet3		87.40 199	86.11 210	91.30 166	93.79 206	83.64 115	94.20 167	94.81 219	83.89 185	84.37 231	91.87 239	68.45 265	96.56 261	78.23 249	85.36 248	93.70 255

FC-MVSNet-test		90.27 112	90.18 103	90.53 193	93.71 207	79.85 221	95.77 68	97.59 2	89.31 55	86.27 181	94.67 136	81.93 103	97.01 237	84.26 161	88.09 226	94.71 200

TAMVS		89.21 142	88.29 149	91.96 138	93.71 207	82.62 148	93.30 212	94.19 238	82.22 221	87.78 151	93.94 164	78.83 131	96.95 240	77.70 254	92.98 162	96.32 138

ET-MVSNet_ETH3D		87.51 194	85.91 219	92.32 123	93.70 209	83.93 106	92.33 246	90.94 318	84.16 178	72.09 346	92.52 213	69.90 242	95.85 295	89.20 104	88.36 221	97.17 110

CDS-MVSNet		89.45 134	88.51 140	92.29 126	93.62 210	83.61 117	93.01 226	94.68 224	81.95 229	87.82 150	93.24 190	78.69 134	96.99 238	80.34 226	93.23 157	96.28 140
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
UniMVSNet (Re)		89.80 125	89.07 129	92.01 133	93.60 211	84.52 89	94.78 127	97.47 10	89.26 56	86.44 178	92.32 219	82.10 98	97.39 208	84.81 155	80.84 303	94.12 227

VPNet		88.20 169	87.47 167	90.39 201	93.56 212	79.46 226	94.04 180	95.54 171	88.67 73	86.96 165	94.58 141	69.33 251	97.15 224	84.05 164	80.53 309	94.56 209

thisisatest0515		87.33 200	85.99 214	91.37 164	93.49 213	79.55 224	90.63 281	89.56 344	80.17 259	87.56 155	90.86 268	67.07 273	98.28 133	81.50 206	93.02 161	96.29 139

mvs_anonymous		89.37 140	89.32 123	89.51 239	93.47 214	74.22 305	91.65 266	94.83 217	82.91 209	85.45 203	93.79 173	81.23 108	96.36 275	86.47 139	94.09 139	97.94 76

CANet_DTU		90.26 113	89.41 120	92.81 96	93.46 215	83.01 133	93.48 204	94.47 228	89.43 52	87.76 152	94.23 154	70.54 237	99.03 67	84.97 151	96.39 107	96.38 137

UniMVSNet_NR-MVSNet		89.92 122	89.29 124	91.81 149	93.39 216	83.72 112	94.43 150	97.12 43	89.80 40	86.46 175	93.32 185	83.16 82	97.23 220	84.92 152	81.02 299	94.49 215

Effi-MVS+-dtu		88.65 158	88.35 145	89.54 236	93.33 217	76.39 289	94.47 147	94.36 231	87.70 102	85.43 206	89.56 297	73.45 200	97.26 217	85.57 147	91.28 177	94.97 186

mvs-test1		89.45 134	89.14 127	90.38 203	93.33 217	77.63 272	94.95 114	94.36 231	87.70 102	87.10 164	92.81 206	73.45 200	98.03 156	85.57 147	93.04 160	95.48 172

WR-MVS		88.38 163	87.67 163	90.52 195	93.30 219	80.18 206	93.26 215	95.96 137	88.57 77	85.47 202	92.81 206	76.12 158	96.91 243	81.24 209	82.29 278	94.47 218

WR-MVS_H		87.80 179	87.37 169	89.10 247	93.23 220	78.12 257	95.61 77	97.30 29	87.90 96	83.72 250	92.01 235	79.65 126	96.01 288	76.36 266	80.54 307	93.16 276

test_0402		81.30 296	79.17 304	87.67 281	93.19 221	78.17 256	92.98 227	91.71 296	75.25 312	76.02 330	90.31 281	59.23 326	96.37 273	50.22 359	83.63 264	88.47 349

OPM-MVS		90.12 114	89.56 115	91.82 147	93.14 222	83.90 107	94.16 168	95.74 156	88.96 67	87.86 147	95.43 110	72.48 213	97.91 165	88.10 118	90.18 190	93.65 256
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CP-MVSNet		87.63 187	87.26 174	88.74 257	93.12 223	76.59 286	95.29 92	96.58 97	88.43 80	83.49 258	92.98 199	75.28 172	95.83 296	78.97 242	81.15 295	93.79 246

diffmvs		91.37 90	91.23 86	91.77 150	93.09 224	80.27 205	92.36 245	95.52 173	87.03 117	91.40 105	94.93 123	80.08 116	97.44 196	92.13 57	94.56 133	97.61 92

nrg030		91.08 96	90.39 98	93.17 82	93.07 225	86.91 22	96.41 36	96.26 114	88.30 84	88.37 140	94.85 129	82.19 97	97.64 181	91.09 81	82.95 270	94.96 189

PAPM		86.68 224	85.39 232	90.53 193	93.05 226	79.33 234	89.79 296	94.77 222	78.82 277	81.95 277	93.24 190	76.81 151	97.30 211	66.94 327	93.16 158	94.95 192

DU-MVS		89.34 141	88.50 141	91.85 146	93.04 227	83.72 112	94.47 147	96.59 96	89.50 49	86.46 175	93.29 188	77.25 148	97.23 220	84.92 152	81.02 299	94.59 206

NR-MVSNet		88.58 161	87.47 167	91.93 140	93.04 227	84.16 102	94.77 128	96.25 116	89.05 62	80.04 302	93.29 188	79.02 130	97.05 234	81.71 204	80.05 314	94.59 206

jason		90.80 98	90.10 105	92.90 94	93.04 227	83.53 118	93.08 223	94.15 240	80.22 258	91.41 104	94.91 124	76.87 150	97.93 164	90.28 95	96.90 94	97.24 106
jason: jason.
RRT_test8_iter05		86.90 215	86.36 200	88.52 262	93.00 230	73.27 313	94.32 161	95.96 137	85.50 153	84.26 239	92.86 201	60.76 317	97.70 175	88.32 114	82.29 278	94.60 205

PS-CasMVS		87.32 201	86.88 179	88.63 260	92.99 231	76.33 291	95.33 85	96.61 95	88.22 88	83.30 263	93.07 197	73.03 207	95.79 299	78.36 247	81.00 301	93.75 252

MVSTER		88.84 153	88.29 149	90.51 196	92.95 232	80.44 203	93.73 195	95.01 203	84.66 173	87.15 161	93.12 195	72.79 209	97.21 222	87.86 119	87.36 235	93.87 241

RPSCF		85.07 255	84.27 252	87.48 287	92.91 233	70.62 338	91.69 265	92.46 276	76.20 304	82.67 269	95.22 115	63.94 298	97.29 214	77.51 257	85.80 246	94.53 210

FMVSNet1		85.85 241	84.11 254	91.08 175	92.81 234	83.10 128	95.14 104	94.94 206	81.64 239	82.68 268	91.64 243	59.01 328	96.34 276	75.37 276	83.78 260	93.79 246

tfpnnormal		84.72 262	83.23 266	89.20 244	92.79 235	80.05 213	94.48 144	95.81 150	82.38 218	81.08 286	91.21 256	69.01 258	96.95 240	61.69 346	80.59 306	90.58 333

OpenMVS	83.78 11	88.74 156	87.29 171	93.08 85	92.70 236	85.39 76	96.57 32	96.43 105	78.74 280	80.85 288	96.07 90	69.64 247	99.01 73	78.01 252	96.65 100	94.83 196

TranMVSNet+NR-MVSNet		88.84 153	87.95 157	91.49 159	92.68 237	83.01 133	94.92 117	96.31 111	89.88 39	85.53 196	93.85 171	76.63 156	96.96 239	81.91 197	79.87 317	94.50 213

MVS		87.44 197	86.10 211	91.44 162	92.61 238	83.62 116	92.63 236	95.66 162	67.26 350	81.47 280	92.15 225	77.95 143	98.22 136	79.71 233	95.48 116	92.47 297

CHOSEN 280x420		85.15 254	83.99 256	88.65 259	92.47 239	78.40 251	79.68 355	92.76 270	74.90 317	81.41 282	89.59 295	69.85 245	95.51 307	79.92 232	95.29 122	92.03 307

UniMVSNet_ETH3D		87.53 193	86.37 199	91.00 181	92.44 240	78.96 240	94.74 129	95.61 166	84.07 181	85.36 213	94.52 143	59.78 324	97.34 210	82.93 177	87.88 229	96.71 128

1314		87.51 194	86.57 194	90.34 206	92.42 241	79.74 223	92.63 236	95.35 190	78.35 285	80.14 299	91.62 247	74.05 190	97.15 224	81.05 210	93.53 148	94.12 227

cl-mvsnet2		86.78 220	85.98 215	89.18 245	92.34 242	77.62 273	90.84 278	94.13 242	81.33 246	83.97 245	90.15 284	73.96 192	96.60 258	84.19 162	82.94 271	93.33 266

PEN-MVS		86.80 219	86.27 205	88.40 264	92.32 243	75.71 296	95.18 101	96.38 109	87.97 93	82.82 267	93.15 193	73.39 203	95.92 291	76.15 270	79.03 324	93.59 257

cl_fuxian		87.14 211	86.50 197	89.04 249	92.20 244	77.26 278	91.22 273	94.70 223	82.01 227	84.34 235	90.43 279	78.81 132	96.61 256	83.70 169	81.09 296	93.25 270

SCA		86.32 234	85.18 236	89.73 231	92.15 245	76.60 285	91.12 274	91.69 298	83.53 194	85.50 199	88.81 304	66.79 277	96.48 266	76.65 264	90.35 188	96.12 147

XXY-MVS		87.65 184	86.85 181	90.03 217	92.14 246	80.60 199	93.76 194	95.23 193	82.94 208	84.60 223	94.02 159	74.27 184	95.49 310	81.04 211	83.68 263	94.01 235

miper_ehance_all_eth		87.22 207	86.62 192	89.02 250	92.13 247	77.40 277	90.91 277	94.81 219	81.28 247	84.32 236	90.08 286	79.26 128	96.62 253	83.81 167	82.94 271	93.04 281

IB-MVS	80.51 15	85.24 253	83.26 265	91.19 169	92.13 247	79.86 220	91.75 261	91.29 309	83.28 201	80.66 291	88.49 310	61.28 311	98.46 118	80.99 214	79.46 320	95.25 180
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
cascas		86.43 233	84.98 240	90.80 187	92.10 249	80.92 190	90.24 287	95.91 142	73.10 331	83.57 256	88.39 311	65.15 292	97.46 193	84.90 154	91.43 176	94.03 234

Fast-Effi-MVS+-dtu		87.44 197	86.72 185	89.63 234	92.04 250	77.68 271	94.03 181	93.94 245	85.81 142	82.42 270	91.32 254	70.33 239	97.06 233	80.33 227	90.23 189	94.14 226

cl-mvsnet____		86.52 229	85.78 222	88.75 255	92.03 251	76.46 287	90.74 279	94.30 234	81.83 236	83.34 261	90.78 272	75.74 168	96.57 259	81.74 202	81.54 290	93.22 273

cl-mvsnet1		86.53 228	85.78 222	88.75 255	92.02 252	76.45 288	90.74 279	94.30 234	81.83 236	83.34 261	90.82 270	75.75 166	96.57 259	81.73 203	81.52 291	93.24 271

RRT_MVS		88.86 152	87.68 162	92.39 120	92.02 252	86.09 55	94.38 158	94.94 206	85.45 154	87.14 163	93.84 172	65.88 289	97.11 228	88.73 109	86.77 242	93.98 236

eth_miper_zixun_eth		86.50 230	85.77 224	88.68 258	91.94 254	75.81 295	90.47 283	94.89 212	82.05 224	84.05 242	90.46 278	75.96 161	96.77 247	82.76 183	79.36 321	93.46 264

PS-MVSNAJss		89.97 119	89.62 114	91.02 179	91.90 255	80.85 192	95.26 95	95.98 135	86.26 135	86.21 182	94.29 150	79.70 122	97.65 179	88.87 108	88.10 224	94.57 208

ITE_SJBPF				88.24 270	91.88 256	77.05 281		92.92 266	85.54 151	80.13 300	93.30 187	57.29 332	96.20 280	72.46 295	84.71 253	91.49 315

EI-MVSNet		89.10 144	88.86 136	89.80 228	91.84 257	78.30 253	93.70 198	95.01 203	85.73 145	87.15 161	95.28 112	79.87 119	97.21 222	83.81 167	87.36 235	93.88 240

CVMVSNet		84.69 263	84.79 246	84.37 324	91.84 257	64.92 357	93.70 198	91.47 305	66.19 352	86.16 184	95.28 112	67.18 271	93.33 337	80.89 216	90.42 187	94.88 194

MVS-HIRNet		73.70 321	72.20 324	78.18 338	91.81 259	56.42 364	82.94 350	82.58 359	55.24 358	68.88 351	66.48 359	55.32 338	95.13 315	58.12 353	88.42 219	83.01 354

PatchmatchNet		85.85 241	84.70 247	89.29 242	91.76 260	75.54 297	88.49 315	91.30 308	81.63 240	85.05 217	88.70 308	71.71 217	96.24 279	74.61 284	89.05 210	96.08 151
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TransMVSNet (Re)		84.43 265	83.06 268	88.54 261	91.72 261	78.44 249	95.18 101	92.82 269	82.73 212	79.67 306	92.12 227	73.49 199	95.96 290	71.10 303	68.73 350	91.21 322

IterMVS-SCA-FT		85.45 246	84.53 251	88.18 272	91.71 262	76.87 283	90.19 290	92.65 274	85.40 156	81.44 281	90.54 276	66.79 277	95.00 319	81.04 211	81.05 297	92.66 292

TinyColmap		79.76 308	77.69 310	85.97 310	91.71 262	73.12 314	89.55 297	90.36 328	75.03 314	72.03 347	90.19 282	46.22 358	96.19 282	63.11 342	81.03 298	88.59 348

MDTV_nov1_ep13			83.56 263		91.69 264	69.93 342	87.75 323	91.54 302	78.60 282	84.86 220	88.90 303	69.54 248	96.03 286	70.25 305	88.93 211

miper_enhance_ethall		86.90 215	86.18 207	89.06 248	91.66 265	77.58 274	90.22 289	94.82 218	79.16 272	84.48 227	89.10 300	79.19 129	96.66 251	84.06 163	82.94 271	92.94 284

DTE-MVSNet		86.11 236	85.48 230	87.98 276	91.65 266	74.92 299	94.93 116	95.75 155	87.36 111	82.26 272	93.04 198	72.85 208	95.82 297	74.04 286	77.46 330	93.20 274

MIMVSNet		82.59 280	80.53 285	88.76 254	91.51 267	78.32 252	86.57 331	90.13 331	79.32 268	80.70 290	88.69 309	52.98 347	93.07 341	66.03 332	88.86 212	94.90 193

pm-mvs1		86.61 225	85.54 228	89.82 225	91.44 268	80.18 206	95.28 94	94.85 215	83.84 186	81.66 279	92.62 211	72.45 215	96.48 266	79.67 234	78.06 325	92.82 289

Baseline_NR-MVSNet		87.07 212	86.63 191	88.40 264	91.44 268	77.87 264	94.23 166	92.57 275	84.12 180	85.74 189	92.08 231	77.25 148	96.04 285	82.29 190	79.94 315	91.30 319

IterMVS		84.88 259	83.98 257	87.60 282	91.44 268	76.03 293	90.18 291	92.41 277	83.24 202	81.06 287	90.42 280	66.60 280	94.28 326	79.46 235	80.98 302	92.48 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DWT-MVSNet_test		84.95 258	83.68 260	88.77 253	91.43 271	73.75 309	91.74 262	90.98 316	80.66 256	83.84 247	87.36 326	62.44 303	97.11 228	78.84 244	85.81 245	95.46 173

MS-PatchMatch		85.05 256	84.16 253	87.73 280	91.42 272	78.51 247	91.25 272	93.53 256	77.50 291	80.15 298	91.58 248	61.99 306	95.51 307	75.69 273	94.35 138	89.16 343

tpm2		84.08 267	82.94 269	87.48 287	91.39 273	71.27 330	89.23 305	90.37 327	71.95 339	84.64 222	89.33 298	67.30 268	96.55 263	75.17 278	87.09 239	94.63 202

v8		87.50 196	86.71 186	89.89 222	91.37 274	79.40 228	94.50 143	95.38 186	84.81 170	83.60 255	91.33 252	76.05 159	97.42 198	82.84 180	80.51 311	92.84 288

ADS-MVSNet2		81.66 289	79.71 297	87.50 285	91.35 275	74.19 306	83.33 347	88.48 347	72.90 333	82.24 273	85.77 338	64.98 293	93.20 339	64.57 338	83.74 261	95.12 182

ADS-MVSNet		81.56 291	79.78 295	86.90 301	91.35 275	71.82 327	83.33 347	89.16 345	72.90 333	82.24 273	85.77 338	64.98 293	93.76 332	64.57 338	83.74 261	95.12 182

GA-MVS		86.61 225	85.27 235	90.66 188	91.33 277	78.71 242	90.40 284	93.81 253	85.34 157	85.12 216	89.57 296	61.25 312	97.11 228	80.99 214	89.59 201	96.15 143

miper_lstm_enhance		85.27 252	84.59 250	87.31 289	91.28 278	74.63 300	87.69 324	94.09 244	81.20 251	81.36 283	89.85 292	74.97 177	94.30 325	81.03 213	79.84 318	93.01 282

XVG-ACMP-BASELINE		86.00 237	84.84 245	89.45 240	91.20 279	78.00 259	91.70 264	95.55 169	85.05 166	82.97 265	92.25 223	54.49 341	97.48 191	82.93 177	87.45 234	92.89 286

v10		87.25 204	86.38 198	89.85 223	91.19 280	79.50 225	94.48 144	95.45 180	83.79 187	83.62 254	91.19 257	75.13 173	97.42 198	81.94 196	80.60 305	92.63 293

FMVSNet5		81.52 292	79.60 298	87.27 290	91.17 281	77.95 260	91.49 268	92.26 282	76.87 297	76.16 327	87.91 320	51.67 348	92.34 345	67.74 323	81.16 293	91.52 314

USDC		82.76 277	81.26 282	87.26 291	91.17 281	74.55 301	89.27 303	93.39 259	78.26 287	75.30 333	92.08 231	54.43 342	96.63 252	71.64 297	85.79 247	90.61 330

CostFormer		85.77 243	84.94 242	88.26 269	91.16 283	72.58 323	89.47 301	91.04 315	76.26 303	86.45 177	89.97 289	70.74 231	96.86 246	82.35 188	87.07 240	95.34 179

baseline2		86.50 230	85.39 232	89.84 224	91.12 284	76.70 284	91.88 257	88.58 346	82.35 220	79.95 303	90.95 267	73.42 202	97.63 182	80.27 228	89.95 194	95.19 181

tpm cat1		81.96 283	80.27 289	87.01 298	91.09 285	71.02 334	87.38 327	91.53 303	66.25 351	80.17 297	86.35 334	68.22 267	96.15 283	69.16 313	82.29 278	93.86 243

tpmvs		83.35 276	82.07 274	87.20 296	91.07 286	71.00 335	88.31 318	91.70 297	78.91 274	80.49 294	87.18 330	69.30 254	97.08 231	68.12 322	83.56 265	93.51 262

v1144		87.61 190	86.79 184	90.06 216	91.01 287	79.34 231	93.95 186	95.42 185	83.36 199	85.66 192	91.31 255	74.98 176	97.42 198	83.37 171	82.06 281	93.42 265

v2v482		87.84 177	87.06 176	90.17 209	90.99 288	79.23 238	94.00 184	95.13 197	84.87 168	85.53 196	92.07 233	74.45 182	97.45 194	84.71 157	81.75 287	93.85 244

SixPastTwentyTwo		83.91 270	82.90 270	86.92 300	90.99 288	70.67 337	93.48 204	91.99 290	85.54 151	77.62 319	92.11 229	60.59 318	96.87 245	76.05 271	77.75 327	93.20 274

test-LLR		85.87 240	85.41 231	87.25 292	90.95 290	71.67 328	89.55 297	89.88 339	83.41 197	84.54 225	87.95 318	67.25 269	95.11 316	81.82 199	93.37 154	94.97 186

test-mter		84.54 264	83.64 262	87.25 292	90.95 290	71.67 328	89.55 297	89.88 339	79.17 271	84.54 225	87.95 318	55.56 336	95.11 316	81.82 199	93.37 154	94.97 186

v148		87.04 213	86.32 203	89.21 243	90.94 292	77.26 278	93.71 197	94.43 229	84.84 169	84.36 234	90.80 271	76.04 160	97.05 234	82.12 192	79.60 319	93.31 267

mvs_tets		88.06 174	87.28 172	90.38 203	90.94 292	79.88 219	95.22 97	95.66 162	85.10 164	84.21 241	93.94 164	63.53 299	97.40 205	88.50 112	88.40 220	93.87 241

MVP-Stereo		85.97 238	84.86 244	89.32 241	90.92 294	82.19 156	92.11 254	94.19 238	78.76 279	78.77 312	91.63 246	68.38 266	96.56 261	75.01 281	93.95 140	89.20 342
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Patchmatch-test		81.37 294	79.30 300	87.58 283	90.92 294	74.16 307	80.99 353	87.68 351	70.52 345	76.63 325	88.81 304	71.21 223	92.76 343	60.01 352	86.93 241	95.83 162

jajsoiax		88.24 168	87.50 165	90.48 198	90.89 296	80.14 208	95.31 86	95.65 164	84.97 167	84.24 240	94.02 159	65.31 291	97.42 198	88.56 111	88.52 216	93.89 238

tpmrst		85.35 249	84.99 239	86.43 306	90.88 297	67.88 349	88.71 312	91.43 306	80.13 260	86.08 185	88.80 306	73.05 206	96.02 287	82.48 185	83.40 269	95.40 176

gg-mvs-nofinetune		81.77 286	79.37 299	88.99 251	90.85 298	77.73 270	86.29 332	79.63 365	74.88 318	83.19 264	69.05 358	60.34 319	96.11 284	75.46 275	94.64 131	93.11 278

D2MVS		85.90 239	85.09 238	88.35 266	90.79 299	77.42 276	91.83 259	95.70 158	80.77 255	80.08 301	90.02 287	66.74 279	96.37 273	81.88 198	87.97 228	91.26 320

OurMVSNet-221017-0		85.35 249	84.64 249	87.49 286	90.77 300	72.59 322	94.01 183	94.40 230	84.72 172	79.62 308	93.17 192	61.91 307	96.72 248	81.99 195	81.16 293	93.16 276

v1192		87.25 204	86.33 202	90.00 220	90.76 301	79.04 239	93.80 192	95.48 175	82.57 215	85.48 201	91.18 259	73.38 204	97.42 198	82.30 189	82.06 281	93.53 259

test_djsdf		89.03 147	88.64 138	90.21 208	90.74 302	79.28 235	95.96 60	95.90 143	84.66 173	85.33 214	92.94 200	74.02 191	97.30 211	89.64 99	88.53 215	94.05 233

v7n		86.81 218	85.76 225	89.95 221	90.72 303	79.25 237	95.07 107	95.92 140	84.45 176	82.29 271	90.86 268	72.60 212	97.53 188	79.42 239	80.52 310	93.08 280

PVSNet_0	73.20 20	77.22 317	74.83 322	84.37 324	90.70 304	71.10 333	83.09 349	89.67 342	72.81 335	73.93 340	83.13 346	60.79 316	93.70 333	68.54 316	50.84 361	88.30 350

v144192		87.19 209	86.35 201	89.74 229	90.64 305	78.24 255	93.92 188	95.43 183	81.93 230	85.51 198	91.05 265	74.21 187	97.45 194	82.86 179	81.56 289	93.53 259

MVS_0304		83.46 273	81.92 276	88.10 274	90.63 306	77.49 275	93.26 215	93.75 254	80.04 262	80.44 295	87.24 329	47.94 355	95.55 304	75.79 272	88.16 223	91.26 320

V42		87.68 182	86.86 180	90.15 211	90.58 307	80.14 208	94.24 165	95.28 191	83.66 189	85.67 191	91.33 252	74.73 180	97.41 203	84.43 160	81.83 285	92.89 286

CR-MVSNet		85.35 249	83.76 259	90.12 213	90.58 307	79.34 231	85.24 338	91.96 293	78.27 286	85.55 194	87.87 321	71.03 226	95.61 302	73.96 288	89.36 204	95.40 176

RPMNet		83.95 269	81.53 279	91.21 168	90.58 307	79.34 231	85.24 338	96.76 77	71.44 341	85.55 194	82.97 347	70.87 229	98.91 89	61.01 348	89.36 204	95.40 176

v1921920		86.97 214	86.06 213	89.69 233	90.53 310	78.11 258	93.80 192	95.43 183	81.90 232	85.33 214	91.05 265	72.66 210	97.41 203	82.05 194	81.80 286	93.53 259

v1240		86.78 220	85.85 220	89.56 235	90.45 311	77.79 267	93.61 200	95.37 188	81.65 238	85.43 206	91.15 261	71.50 221	97.43 197	81.47 207	82.05 283	93.47 263

tpm		84.73 261	84.02 255	86.87 303	90.33 312	68.90 345	89.06 307	89.94 336	80.85 254	85.75 188	89.86 291	68.54 264	95.97 289	77.76 253	84.05 259	95.75 165

EG-PatchMatch MVS		82.37 282	80.34 288	88.46 263	90.27 313	79.35 230	92.80 233	94.33 233	77.14 296	73.26 343	90.18 283	47.47 357	96.72 248	70.25 305	87.32 237	89.30 340

EPNet_dtu		86.49 232	85.94 218	88.14 273	90.24 314	72.82 317	94.11 172	92.20 283	86.66 128	79.42 309	92.36 218	73.52 198	95.81 298	71.26 298	93.66 144	95.80 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPMVS		83.90 271	82.70 273	87.51 284	90.23 315	72.67 319	88.62 314	81.96 361	81.37 245	85.01 218	88.34 312	66.31 284	94.45 321	75.30 277	87.12 238	95.43 175

EPNet		91.79 81	91.02 91	94.10 61	90.10 316	85.25 78	96.03 56	92.05 287	92.83 1	87.39 160	95.78 100	79.39 127	99.01 73	88.13 117	97.48 85	98.05 69
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PatchT		82.68 279	81.27 281	86.89 302	90.09 317	70.94 336	84.06 344	90.15 330	74.91 316	85.63 193	83.57 344	69.37 250	94.87 320	65.19 334	88.50 217	94.84 195

Patchmtry		82.71 278	80.93 284	88.06 275	90.05 318	76.37 290	84.74 342	91.96 293	72.28 338	81.32 284	87.87 321	71.03 226	95.50 309	68.97 314	80.15 313	92.32 303

pmmvs4		85.43 247	83.86 258	90.16 210	90.02 319	82.97 135	90.27 285	92.67 273	75.93 306	80.73 289	91.74 242	71.05 225	95.73 301	78.85 243	83.46 267	91.78 310

TESTMET0.1,1		83.74 272	82.85 271	86.42 307	89.96 320	71.21 332	89.55 297	87.88 348	77.41 292	83.37 260	87.31 327	56.71 333	93.65 334	80.62 221	92.85 165	94.40 219

dp		81.47 293	80.23 290	85.17 319	89.92 321	65.49 355	86.74 329	90.10 332	76.30 302	81.10 285	87.12 331	62.81 301	95.92 291	68.13 321	79.88 316	94.09 230

K. test v3		81.59 290	80.15 292	85.91 313	89.89 322	69.42 344	92.57 239	87.71 350	85.56 150	73.44 342	89.71 294	55.58 335	95.52 306	77.17 260	69.76 344	92.78 290

MDA-MVSNet-bldmvs		78.85 313	76.31 316	86.46 305	89.76 323	73.88 308	88.79 311	90.42 325	79.16 272	59.18 358	88.33 313	60.20 320	94.04 328	62.00 345	68.96 348	91.48 316

GG-mvs-BLEND				87.94 278	89.73 324	77.91 261	87.80 321	78.23 367		80.58 292	83.86 342	59.88 323	95.33 313	71.20 299	92.22 172	90.60 332

gm-plane-assit					89.60 325	68.00 347			77.28 295		88.99 301		97.57 185	79.44 237

anonymousdsp		87.84 177	87.09 175	90.12 213	89.13 326	80.54 200	94.67 134	95.55 169	82.05 224	83.82 248	92.12 227	71.47 222	97.15 224	87.15 130	87.80 231	92.67 291

N_pmnet		68.89 324	68.44 327	70.23 342	89.07 327	28.79 374	88.06 319	19.50 375	69.47 347	71.86 348	84.93 340	61.24 313	91.75 350	54.70 356	77.15 331	90.15 334

pmmvs5		84.21 266	82.84 272	88.34 267	88.95 328	76.94 282	92.41 242	91.91 295	75.63 308	80.28 296	91.18 259	64.59 295	95.57 303	77.09 262	83.47 266	92.53 295

PMMVS		85.71 244	84.96 241	87.95 277	88.90 329	77.09 280	88.68 313	90.06 333	72.32 337	86.47 174	90.76 273	72.15 216	94.40 322	81.78 201	93.49 149	92.36 301

JIA-IIPM		81.04 297	78.98 307	87.25 292	88.64 330	73.48 311	81.75 352	89.61 343	73.19 330	82.05 275	73.71 355	66.07 288	95.87 294	71.18 301	84.60 254	92.41 299

Gipuma		57.99 329	54.91 331	67.24 344	88.51 331	65.59 354	52.21 363	90.33 329	43.58 363	42.84 364	51.18 364	20.29 369	85.07 360	34.77 364	70.45 343	51.05 363
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EU-MVSNet		81.32 295	80.95 283	82.42 333	88.50 332	63.67 358	93.32 208	91.33 307	64.02 354	80.57 293	92.83 204	61.21 314	92.27 346	76.34 267	80.38 312	91.32 318

our_test_3		81.93 284	80.46 287	86.33 308	88.46 333	73.48 311	88.46 316	91.11 311	76.46 298	76.69 324	88.25 314	66.89 275	94.36 323	68.75 315	79.08 323	91.14 324

ppachtmachnet_test		81.84 285	80.07 293	87.15 297	88.46 333	74.43 304	89.04 308	92.16 284	75.33 311	77.75 317	88.99 301	66.20 285	95.37 312	65.12 336	77.60 328	91.65 312

lessismore_v0				86.04 309	88.46 333	68.78 346		80.59 363		73.01 344	90.11 285	55.39 337	96.43 271	75.06 280	65.06 352	92.90 285

test0.0.03 1		82.41 281	81.69 277	84.59 322	88.23 336	72.89 316	90.24 287	87.83 349	83.41 197	79.86 304	89.78 293	67.25 269	88.99 356	65.18 335	83.42 268	91.90 309

bset_n11_16_dypcd		86.83 217	85.55 227	90.65 189	88.22 337	81.70 165	88.88 310	90.42 325	85.26 159	85.49 200	90.69 274	67.11 272	97.02 236	89.51 101	84.39 255	93.23 272

MDA-MVSNet_test_wron		79.21 312	77.19 314	85.29 317	88.22 337	72.77 318	85.87 334	90.06 333	74.34 321	62.62 357	87.56 324	66.14 286	91.99 348	66.90 330	73.01 338	91.10 327

YYNet1		79.22 311	77.20 313	85.28 318	88.20 339	72.66 320	85.87 334	90.05 335	74.33 322	62.70 356	87.61 323	66.09 287	92.03 347	66.94 327	72.97 339	91.15 323

pmmvs6		83.42 274	81.60 278	88.87 252	88.01 340	77.87 264	94.96 113	94.24 237	74.67 319	78.80 311	91.09 264	60.17 321	96.49 265	77.06 263	75.40 336	92.23 305

testgi		80.94 300	80.20 291	83.18 329	87.96 341	66.29 352	91.28 270	90.70 324	83.70 188	78.12 314	92.84 203	51.37 349	90.82 353	63.34 341	82.46 277	92.43 298

Anonymous20231206		81.03 298	79.77 296	84.82 321	87.85 342	70.26 340	91.42 269	92.08 286	73.67 326	77.75 317	89.25 299	62.43 304	93.08 340	61.50 347	82.00 284	91.12 325

OpenMVS_ROB	74.94 19	79.51 309	77.03 315	86.93 299	87.00 343	76.23 292	92.33 246	90.74 323	68.93 348	74.52 337	88.23 315	49.58 352	96.62 253	57.64 354	84.29 256	87.94 351

LF4IMVS		80.37 303	79.07 306	84.27 326	86.64 344	69.87 343	89.39 302	91.05 314	76.38 300	74.97 335	90.00 288	47.85 356	94.25 327	74.55 285	80.82 304	88.69 347

MIMVSNet1		79.38 310	77.28 312	85.69 314	86.35 345	73.67 310	91.61 267	92.75 271	78.11 290	72.64 345	88.12 316	48.16 354	91.97 349	60.32 349	77.49 329	91.43 317

KD-MVS_2432*1600		78.50 314	76.02 319	85.93 311	86.22 346	74.47 302	84.80 340	92.33 278	79.29 269	76.98 322	85.92 336	53.81 345	93.97 329	67.39 324	57.42 358	89.36 338

miper_refine_blended		78.50 314	76.02 319	85.93 311	86.22 346	74.47 302	84.80 340	92.33 278	79.29 269	76.98 322	85.92 336	53.81 345	93.97 329	67.39 324	57.42 358	89.36 338

CL-MVSNet_2432*1600		81.74 287	80.53 285	85.36 316	85.96 348	72.45 324	90.25 286	93.07 264	81.24 249	79.85 305	87.29 328	70.93 228	92.52 344	66.95 326	69.23 346	91.11 326

test20.03		79.95 306	79.08 305	82.55 332	85.79 349	67.74 350	91.09 275	91.08 312	81.23 250	74.48 338	89.96 290	61.63 308	90.15 354	60.08 350	76.38 334	89.76 336

Anonymous20240521		80.44 302	79.21 302	84.11 327	85.75 350	67.89 348	92.86 231	93.23 261	75.61 309	75.59 332	87.47 325	50.03 350	94.33 324	71.14 302	81.21 292	90.12 335

DIV-MVS_2432*1600		80.20 304	79.24 301	83.07 330	85.64 351	65.29 356	91.01 276	93.93 246	78.71 281	76.32 326	86.40 333	59.20 327	92.93 342	72.59 294	69.35 345	91.00 328

Patchmatch-RL test		81.67 288	79.96 294	86.81 304	85.42 352	71.23 331	82.17 351	87.50 352	78.47 283	77.19 321	82.50 348	70.81 230	93.48 335	82.66 184	72.89 340	95.71 168

UnsupCasMVSNet_eth		80.07 305	78.27 309	85.46 315	85.24 353	72.63 321	88.45 317	94.87 214	82.99 207	71.64 349	88.07 317	56.34 334	91.75 350	73.48 291	63.36 355	92.01 308

pmmvs-eth3d		80.97 299	78.72 308	87.74 279	84.99 354	79.97 218	90.11 292	91.65 299	75.36 310	73.51 341	86.03 335	59.45 325	93.96 331	75.17 278	72.21 341	89.29 341

CMPMVS	59.16 21	80.52 301	79.20 303	84.48 323	83.98 355	67.63 351	89.95 295	93.84 252	64.79 353	66.81 354	91.14 262	57.93 331	95.17 314	76.25 268	88.10 224	90.65 329
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UnsupCasMVSNet_bld		76.23 320	73.27 323	85.09 320	83.79 356	72.92 315	85.65 337	93.47 258	71.52 340	68.84 352	79.08 352	49.77 351	93.21 338	66.81 331	60.52 357	89.13 345

PM-MVS		78.11 316	76.12 318	84.09 328	83.54 357	70.08 341	88.97 309	85.27 356	79.93 263	74.73 336	86.43 332	34.70 362	93.48 335	79.43 238	72.06 342	88.72 346

DSMNet-mixed		76.94 318	76.29 317	78.89 336	83.10 358	56.11 365	87.78 322	79.77 364	60.65 356	75.64 331	88.71 307	61.56 309	88.34 357	60.07 351	89.29 206	92.21 306

new_pmnet		72.15 322	70.13 325	78.20 337	82.95 359	65.68 353	83.91 345	82.40 360	62.94 355	64.47 355	79.82 351	42.85 360	86.26 359	57.41 355	74.44 337	82.65 356

new-patchmatchnet		76.41 319	75.17 321	80.13 335	82.65 360	59.61 360	87.66 325	91.08 312	78.23 288	69.85 350	83.22 345	54.76 339	91.63 352	64.14 340	64.89 353	89.16 343

ambc				83.06 331	79.99 361	63.51 359	77.47 356	92.86 267		74.34 339	84.45 341	28.74 363	95.06 318	73.06 293	68.89 349	90.61 330

TDRefinement		79.81 307	77.34 311	87.22 295	79.24 362	75.48 298	93.12 220	92.03 288	76.45 299	75.01 334	91.58 248	49.19 353	96.44 270	70.22 307	69.18 347	89.75 337

pmmvs3		71.81 323	68.71 326	81.11 334	75.86 363	70.42 339	86.74 329	83.66 358	58.95 357	68.64 353	80.89 350	36.93 361	89.52 355	63.10 343	63.59 354	83.39 353

DeepMVS_CX				56.31 348	74.23 364	51.81 367		56.67 373	44.85 362	48.54 362	75.16 353	27.87 365	58.74 369	40.92 362	52.22 360	58.39 362

FPMVS		64.63 326	62.55 328	70.88 341	70.80 365	56.71 362	84.42 343	84.42 357	51.78 360	49.57 360	81.61 349	23.49 366	81.48 362	40.61 363	76.25 335	74.46 359

PMMVS2		59.60 327	56.40 330	69.21 343	68.83 366	46.58 369	73.02 360	77.48 368	55.07 359	49.21 361	72.95 357	17.43 371	80.04 363	49.32 360	44.33 363	80.99 358

wuyk23d		21.27 337	20.48 340	23.63 352	68.59 367	36.41 372	49.57 364	6.85 376	9.37 369	7.89 371	4.46 372	4.03 375	31.37 370	17.47 369	16.07 369	3.12 367

E-PMN		43.23 333	42.29 335	46.03 349	65.58 368	37.41 371	73.51 358	64.62 369	33.99 365	28.47 369	47.87 365	19.90 370	67.91 366	22.23 367	24.45 365	32.77 364

LCM-MVSNet		66.00 325	62.16 329	77.51 339	64.51 369	58.29 361	83.87 346	90.90 319	48.17 361	54.69 359	73.31 356	16.83 372	86.75 358	65.47 333	61.67 356	87.48 352

EMVS		42.07 334	41.12 336	44.92 350	63.45 370	35.56 373	73.65 357	63.48 370	33.05 366	26.88 370	45.45 366	21.27 368	67.14 367	19.80 368	23.02 367	32.06 365

MVE	39.65 23	43.39 332	38.59 338	57.77 346	56.52 371	48.77 368	55.38 362	58.64 372	29.33 367	28.96 368	52.65 363	4.68 374	64.62 368	28.11 366	33.07 364	59.93 361
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		58.88 328	54.22 332	72.86 340	56.50 372	56.67 363	80.75 354	86.00 353	73.09 332	37.39 365	64.63 361	22.17 367	79.49 364	43.51 361	23.96 366	82.43 357

test_method		50.52 331	48.47 333	56.66 347	52.26 373	18.98 376	41.51 365	81.40 362	10.10 368	44.59 363	75.01 354	28.51 364	68.16 365	53.54 357	49.31 362	82.83 355

PMVS	47.18 22	52.22 330	48.46 334	63.48 345	45.72 374	46.20 370	73.41 359	78.31 366	41.03 364	30.06 367	65.68 360	6.05 373	83.43 361	30.04 365	65.86 351	60.80 360
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		35.64 335	39.24 337	24.84 351	14.87 375	23.90 375	62.71 361	51.51 374	6.58 370	36.66 366	62.08 362	44.37 359	30.34 371	52.40 358	22.00 368	20.27 366

testmvs		8.92 338	11.52 341	1.12 354	1.06 376	0.46 378	86.02 333	0.65 377	0.62 371	2.74 372	9.52 370	0.31 377	0.45 373	2.38 370	0.39 370	2.46 369

test123		8.76 339	11.22 342	1.39 353	0.85 377	0.97 377	85.76 336	0.35 378	0.54 372	2.45 373	8.14 371	0.60 376	0.48 372	2.16 371	0.17 371	2.71 368

eth-test2					0.00 378

eth-test					0.00 378

uanet_test		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

cdsmvs_eth3d_5k		22.14 336	29.52 339	0.00 355	0.00 378	0.00 379	0.00 366	95.76 154	0.00 373	0.00 374	94.29 150	75.66 169	0.00 374	0.00 372	0.00 372	0.00 370

pcd_1.5k_mvsjas		6.64 341	8.86 344	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	79.70 122	0.00 374	0.00 372	0.00 372	0.00 370

sosnet-low-res		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

sosnet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uncertanet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

Regformer		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

ab-mvs-re		7.82 340	10.43 343	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	93.88 169	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uanet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

PC_three_1452									82.47 216	97.09 9	97.07 44	92.72 1	98.04 154	92.70 42	99.02 12	98.86 9

test_241102_TWO								97.44 14	90.31 29	97.62 5	98.07 4	91.46 10	99.58 8	95.66 4	99.12 6	98.98 8

test_0728_THIRD									90.75 20	97.04 10	98.05 8	92.09 6	99.55 15	95.64 6	99.13 3	99.13 1

GSMVS																96.12 147

sam_mvs1												71.70 218				96.12 147

sam_mvs												70.60 232

MTGPA								96.97 52

test_post1							88.00 320				9.81 369	69.31 253	95.53 305	76.65 264

test_post											10.29 368	70.57 236	95.91 293

patchmatchnet-post											83.76 343	71.53 220	96.48 266

MTMP							96.16 47	60.64 371

test9_res														91.91 66	98.71 34	98.07 67

agg_prior2														90.54 92	98.68 39	98.27 51

test_prior4						85.96 60	94.11 172

test_prior2							94.12 170		87.67 104	92.63 75	96.39 75	86.62 42		91.50 76	98.67 41

旧先验2							93.36 207		71.25 342	94.37 30			97.13 227	86.74 135

新几何2							93.11 222

无先验							93.28 214	96.26 114	73.95 324				99.05 63	80.56 222		96.59 132

原ACMM2							92.94 229

testdata2													98.75 103	78.30 248

segment_acmp												87.16 38

testdata1							92.15 252		87.94 94

plane_prior5								96.22 119					98.12 140	88.15 115	89.99 191	94.63 202

plane_prior4											94.86 127

plane_prior3						82.75 139			90.26 33	86.91 168

plane_prior2							95.85 64		90.81 18

plane_prior						82.73 142	95.21 98		89.66 47						89.88 196

n2								0.00 379

nn								0.00 379

door-mid								85.49 354

test11								96.57 98

door								85.33 355

HQP5-MVS						81.56 167

BP-MVS														87.11 132

HQP4-MVS										85.43 206			97.96 161			94.51 212

HQP3-MVS								96.04 133							89.77 198

HQP2-MVS												73.83 195

MDTV_nov1_ep13_2view						55.91 366	87.62 326		73.32 329	84.59 224		70.33 239		74.65 283		95.50 171

ACMMP++_ref															87.47 232

ACMMP++															88.01 227

Test By Simon												80.02 117

High-resolution multi-view benchmark