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									90.77 175	98.89 14	98.28 65	96.24 1	98.35 214	95.76 73	99.58 21	99.59 22

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 58	95.39 11	99.29 1	98.28 36	94.78 41	98.93 9	98.87 15	96.04 2	99.86 8	97.45 26	99.58 21	99.59 22

OPU-MVS				98.55 3	98.82 52	96.86 3	98.25 36				98.26 66	96.04 2	99.24 124	95.36 89	99.59 17	99.56 29

test_0728_THIRD									94.78 41	98.73 18	98.87 15	95.87 4	99.84 23	97.45 26	99.72 2	99.77 2

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 39	95.13 23	99.19 4	98.89 13	95.54 5	99.85 18	97.52 22	99.66 10	99.56 29

test_241102_ONE					99.42 7	95.30 17		98.27 39	95.09 26	99.19 4	98.81 21	95.54 5	99.65 58

test_one_0601					99.32 22	95.20 20		98.25 45	95.13 23	98.48 24	98.87 15	95.16 7

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 116	94.92 32	98.73 18	98.87 15	95.08 8	99.84 23	97.52 22	99.67 6	99.48 44
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 34	94.92 32	98.99 7	98.92 10	95.08 8

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 159	98.35 27	95.16 22	98.71 20	98.80 22	95.05 10	99.89 3	96.70 41	99.73 1	99.73 10
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 39	95.13 23	98.93 9	98.89 13	94.99 11	99.85 18	97.52 22	99.65 12	99.74 8

SteuartSystems-ACMMP		97.62 9	97.53 11	97.87 24	98.39 77	94.25 38	98.43 24	98.27 39	95.34 17	98.11 28	98.56 31	94.53 12	99.71 46	96.57 45	99.62 15	99.65 15
Skip Steuart: Steuart Systems R&D Blog.
CNVR-MVS		97.68 6	97.44 13	98.37 7	98.90 50	95.86 6	97.27 151	98.08 74	95.81 9	97.87 36	98.31 60	94.26 13	99.68 54	97.02 33	99.49 36	99.57 26

SD-MVS		97.41 14	97.53 11	97.06 66	98.57 69	94.46 31	97.92 73	98.14 64	94.82 38	99.01 6	98.55 33	94.18 14	97.41 319	96.94 34	99.64 13	99.32 62
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 10	97.54 10	97.73 36	99.40 11	93.77 54	98.53 15	98.29 34	95.55 13	98.56 22	97.81 99	93.90 15	99.65 58	96.62 42	99.21 69	99.77 2
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 20	96.84 32	98.20 14	99.30 24	95.35 15	97.12 166	98.07 79	93.54 83	96.08 94	97.69 106	93.86 16	99.71 46	96.50 46	99.39 52	99.55 32

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 27	98.81 7	98.30 32	94.76 43	98.30 26	98.90 12	93.77 17	99.68 54	97.93 14	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TSAR-MVS + MP.		97.42 13	97.33 15	97.69 40	99.25 27	94.24 39	98.07 52	97.85 116	93.72 75	98.57 21	98.35 51	93.69 18	99.40 110	97.06 32	99.46 39	99.44 49
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 40	97.44 13	95.01 172	99.05 39	85.39 297	96.98 176	98.77 7	94.70 45	97.99 32	98.66 27	93.61 19	99.91 1	97.67 18	99.50 33	99.72 11

fmvsm_l_conf0.5_n_a		97.63 8	97.76 5	97.26 57	98.25 86	92.59 82	97.81 88	98.68 13	94.93 30	99.24 3	98.87 15	93.52 20	99.79 33	99.32 3	99.21 69	99.40 54

DeepPCF-MVS	93.97 1	96.61 51	97.09 18	95.15 163	98.09 101	86.63 277	96.00 253	98.15 62	95.43 14	97.95 33	98.56 31	93.40 21	99.36 114	96.77 38	99.48 37	99.45 47

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 50	98.21 92	92.75 76	97.83 84	98.73 9	95.04 28	99.30 1	98.84 20	93.34 22	99.78 35	99.32 3	99.13 77	99.50 40

SF-MVS		97.39 15	97.13 16	98.17 15	99.02 42	95.28 19	98.23 40	98.27 39	92.37 129	98.27 27	98.65 29	93.33 23	99.72 45	96.49 47	99.52 28	99.51 37

SMA-MVS		97.35 16	97.03 24	98.30 8	99.06 38	95.42 10	97.94 71	98.18 57	90.57 190	98.85 15	98.94 9	93.33 23	99.83 26	96.72 40	99.68 4	99.63 17
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 18	97.03 24	98.11 17	98.77 53	95.06 24	97.34 144	98.04 89	95.96 6	97.09 55	97.88 92	93.18 25	99.71 46	95.84 71	99.17 73	99.56 29

9.14			96.75 40		98.93 47		97.73 95	98.23 50	91.28 161	97.88 35	98.44 44	93.00 26	99.65 58	95.76 73	99.47 38

segment_acmp												92.89 27

TSAR-MVS + GP.		96.69 48	96.49 51	97.27 56	98.31 81	93.39 60	96.79 190	96.72 234	94.17 62	97.44 43	97.66 110	92.76 28	99.33 115	96.86 37	97.76 131	99.08 83

dcpmvs_2		96.37 59	97.05 22	94.31 211	98.96 46	84.11 315	97.56 119	97.51 153	93.92 69	97.43 45	98.52 35	92.75 29	99.32 117	97.32 30	99.50 33	99.51 37

TEST9					98.70 56	94.19 40	96.41 223	98.02 94	88.17 258	96.03 95	97.56 121	92.74 30	99.59 74

train_agg		96.30 61	95.83 68	97.72 37	98.70 56	94.19 40	96.41 223	98.02 94	88.58 245	96.03 95	97.56 121	92.73 31	99.59 74	95.04 95	99.37 56	99.39 56

test_8					98.67 58	94.06 47	96.37 230	98.01 97	88.58 245	95.98 99	97.55 123	92.73 31	99.58 77

CSCG		96.05 66	95.91 65	96.46 89	99.24 28	90.47 164	98.30 30	98.57 18	89.01 228	93.97 145	97.57 119	92.62 33	99.76 38	94.66 107	99.27 62	99.15 75

HPM-MVS++		97.34 17	96.97 26	98.47 5	99.08 36	96.16 4	97.55 122	97.97 101	95.59 11	96.61 72	97.89 90	92.57 34	99.84 23	95.95 66	99.51 31	99.40 54

ZD-MVS					99.05 39	94.59 29		98.08 74	89.22 222	97.03 57	98.10 73	92.52 35	99.65 58	94.58 111	99.31 60

PHI-MVS		96.77 43	96.46 55	97.71 39	98.40 75	94.07 46	98.21 43	98.45 22	89.86 203	97.11 54	98.01 83	92.52 35	99.69 52	96.03 64	99.53 27	99.36 60

test_fmvsm_n_1920		97.55 11	97.89 3	96.53 79	98.41 74	91.73 107	98.01 57	99.02 1	96.37 4	99.30 1	98.92 10	92.39 37	99.79 33	99.16 5	99.46 39	98.08 165

APD-MVS		96.95 31	96.60 46	98.01 19	99.03 41	94.93 26	97.72 98	98.10 72	91.50 151	98.01 31	98.32 59	92.33 38	99.58 77	94.85 100	99.51 31	99.53 36
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		96.68 50	96.58 48	96.99 68	98.46 70	92.31 91	96.20 244	98.90 3	94.30 60	95.86 102	97.74 104	92.33 38	99.38 113	96.04 63	99.42 46	99.28 65

MSLP-MVS++		96.94 32	97.06 19	96.59 77	98.72 55	91.86 105	97.67 103	98.49 19	94.66 48	97.24 49	98.41 47	92.31 40	98.94 159	96.61 43	99.46 39	98.96 94

旧先验1					98.38 78	93.38 61		97.75 123			98.09 75	92.30 41			99.01 86	99.16 73

HFP-MVS		97.14 22	96.92 29	97.83 26	99.42 7	94.12 44	98.52 16	98.32 30	93.21 96	97.18 50	98.29 63	92.08 42	99.83 26	95.63 80	99.59 17	99.54 33

test_prior2							96.35 231		92.80 119	96.03 95	97.59 118	92.01 43		95.01 97	99.38 53

CDPH-MVS		95.97 69	95.38 77	97.77 33	98.93 47	94.44 32	96.35 231	97.88 109	86.98 289	96.65 70	97.89 90	91.99 44	99.47 102	92.26 149	99.46 39	99.39 56

CP-MVS		97.02 28	96.81 36	97.64 43	99.33 21	93.54 57	98.80 8	98.28 36	92.99 107	96.45 82	98.30 62	91.90 45	99.85 18	95.61 82	99.68 4	99.54 33

CS-MVS		96.86 36	97.06 19	96.26 106	98.16 98	91.16 140	99.09 3	97.87 111	95.30 18	97.06 56	98.03 80	91.72 46	98.71 182	97.10 31	99.17 73	98.90 102

DPM-MVS		95.69 74	94.92 87	98.01 19	98.08 104	95.71 9	95.27 285	97.62 141	90.43 193	95.55 113	97.07 144	91.72 46	99.50 99	89.62 204	98.94 89	98.82 111

XVS		97.18 20	96.96 27	97.81 28	99.38 14	94.03 48	98.59 12	98.20 52	94.85 34	96.59 74	98.29 63	91.70 48	99.80 30	95.66 75	99.40 50	99.62 18

X-MVStestdata		91.71 213	89.67 272	97.81 28	99.38 14	94.03 48	98.59 12	98.20 52	94.85 34	96.59 74	32.69 396	91.70 48	99.80 30	95.66 75	99.40 50	99.62 18

ZNCC-MVS		96.96 30	96.67 44	97.85 25	99.37 16	94.12 44	98.49 20	98.18 57	92.64 124	96.39 84	98.18 70	91.61 50	99.88 4	95.59 85	99.55 24	99.57 26

ACMMP_NAP		97.20 19	96.86 30	98.23 11	99.09 34	95.16 22	97.60 115	98.19 55	92.82 118	97.93 34	98.74 26	91.60 51	99.86 8	96.26 50	99.52 28	99.67 13

region2R		97.07 25	96.84 32	97.77 33	99.46 2	93.79 52	98.52 16	98.24 47	93.19 99	97.14 52	98.34 54	91.59 52	99.87 7	95.46 87	99.59 17	99.64 16

test_fmvsmconf_n		97.49 12	97.56 9	97.29 53	97.44 139	92.37 88	97.91 75	98.88 4	95.83 8	98.92 12	99.05 5	91.45 53	99.80 30	99.12 6	99.46 39	99.69 12

DELS-MVS		96.61 51	96.38 58	97.30 52	97.79 119	93.19 67	95.96 255	98.18 57	95.23 19	95.87 101	97.65 111	91.45 53	99.70 51	95.87 67	99.44 45	99.00 92
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 29	96.86 30	97.47 46	99.09 34	93.27 66	97.98 61	98.07 79	93.75 74	97.45 42	98.48 41	91.43 55	99.59 74	96.22 53	99.27 62	99.54 33

SR-MVS-dyc-post		96.88 35	96.80 37	97.11 65	99.02 42	92.34 89	97.98 61	98.03 91	93.52 85	97.43 45	98.51 36	91.40 56	99.56 85	96.05 61	99.26 64	99.43 51

GST-MVS		96.85 38	96.52 50	97.82 27	99.36 18	94.14 43	98.29 31	98.13 65	92.72 121	96.70 66	98.06 77	91.35 57	99.86 8	94.83 101	99.28 61	99.47 46

ACMMPR		97.07 25	96.84 32	97.79 30	99.44 6	93.88 50	98.52 16	98.31 31	93.21 96	97.15 51	98.33 57	91.35 57	99.86 8	95.63 80	99.59 17	99.62 18

CS-MVS-test		96.89 34	97.04 23	96.45 90	98.29 82	91.66 113	99.03 4	97.85 116	95.84 7	96.90 59	97.97 86	91.24 59	98.75 176	96.92 35	99.33 58	98.94 97

DeepC-MVS_fast	93.89 2	96.93 33	96.64 45	97.78 31	98.64 64	94.30 35	97.41 134	98.04 89	94.81 39	96.59 74	98.37 49	91.24 59	99.64 66	95.16 93	99.52 28	99.42 53
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 67	95.89 66	96.40 93	97.16 147	92.44 86	97.47 131	97.77 122	94.55 50	96.48 79	94.51 274	91.23 61	98.92 161	95.65 78	98.19 118	97.82 177

PGM-MVS		96.81 41	96.53 49	97.65 41	99.35 20	93.53 58	97.65 106	98.98 2	92.22 131	97.14 52	98.44 44	91.17 62	99.85 18	94.35 113	99.46 39	99.57 26

MP-MVS-pluss		96.70 46	96.27 60	97.98 21	99.23 30	94.71 28	96.96 178	98.06 82	90.67 181	95.55 113	98.78 25	91.07 63	99.86 8	96.58 44	99.55 24	99.38 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mPP-MVS		96.86 36	96.60 46	97.64 43	99.40 11	93.44 59	98.50 19	98.09 73	93.27 95	95.95 100	98.33 57	91.04 64	99.88 4	95.20 92	99.57 23	99.60 21

HPM-MVS		96.69 48	96.45 56	97.40 48	99.36 18	93.11 69	98.87 6	98.06 82	91.17 166	96.40 83	97.99 84	90.99 65	99.58 77	95.61 82	99.61 16	99.49 42
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
APD-MVS_3200maxsize		96.81 41	96.71 43	97.12 64	99.01 45	92.31 91	97.98 61	98.06 82	93.11 104	97.44 43	98.55 33	90.93 66	99.55 87	96.06 60	99.25 66	99.51 37

test12				97.65 41	98.46 70	94.26 37		97.66 134		95.52 116		90.89 67	99.46 103		99.25 66	99.22 70

MTAPA		97.08 24	96.78 38	97.97 22	99.37 16	94.42 33	97.24 153	98.08 74	95.07 27	96.11 92	98.59 30	90.88 68	99.90 2	96.18 59	99.50 33	99.58 25

EI-MVSNet-Vis-set		96.51 54	96.47 52	96.63 74	98.24 87	91.20 135	96.89 182	97.73 126	94.74 44	96.49 78	98.49 38	90.88 68	99.58 77	96.44 48	98.32 113	99.13 77

RE-MVS-def			96.72 42		99.02 42	92.34 89	97.98 61	98.03 91	93.52 85	97.43 45	98.51 36	90.71 70		96.05 61	99.26 64	99.43 51

EIA-MVS		95.53 80	95.47 73	95.71 138	97.06 156	89.63 186	97.82 86	97.87 111	93.57 79	93.92 146	95.04 250	90.61 71	98.95 158	94.62 109	98.68 97	98.54 125

MP-MVS		96.77 43	96.45 56	97.72 37	99.39 13	93.80 51	98.41 25	98.06 82	93.37 91	95.54 115	98.34 54	90.59 72	99.88 4	94.83 101	99.54 26	99.49 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EI-MVSNet-UG-set		96.34 60	96.30 59	96.47 87	98.20 93	90.93 147	96.86 184	97.72 128	94.67 47	96.16 91	98.46 42	90.43 73	99.58 77	96.23 52	97.96 125	98.90 102

原ACMM1				96.38 96	98.59 66	91.09 142		97.89 107	87.41 281	95.22 120	97.68 107	90.25 74	99.54 89	87.95 235	99.12 79	98.49 132

HPM-MVS_fast		96.51 54	96.27 60	97.22 59	99.32 22	92.74 77	98.74 9	98.06 82	90.57 190	96.77 63	98.35 51	90.21 75	99.53 91	94.80 104	99.63 14	99.38 58

testdata				95.46 155	98.18 97	88.90 218		97.66 134	82.73 347	97.03 57	98.07 76	90.06 76	98.85 166	89.67 202	98.98 87	98.64 122

新几何1				97.32 51	98.60 65	93.59 56		97.75 123	81.58 356	95.75 106	97.85 96	90.04 77	99.67 56	86.50 267	99.13 77	98.69 119

test_fmvsmconf0.1_n		97.09 23	97.06 19	97.19 62	95.67 232	92.21 94	97.95 70	98.27 39	95.78 10	98.40 25	99.00 6	89.99 78	99.78 35	99.06 7	99.41 49	99.59 22

DP-MVS Recon		95.68 75	95.12 85	97.37 49	99.19 31	94.19 40	97.03 169	98.08 74	88.35 254	95.09 123	97.65 111	89.97 79	99.48 101	92.08 158	98.59 102	98.44 140

MVS_111021_LR		96.24 63	96.19 62	96.39 95	98.23 91	91.35 127	96.24 242	98.79 6	93.99 67	95.80 104	97.65 111	89.92 80	99.24 124	95.87 67	99.20 71	98.58 123

EPP-MVSNet		95.22 88	95.04 86	95.76 131	97.49 138	89.56 190	98.67 10	97.00 212	90.69 179	94.24 137	97.62 116	89.79 81	98.81 169	93.39 134	96.49 164	98.92 100

MVS_0304		97.04 27	96.73 41	97.96 23	97.60 133	94.36 34	98.01 57	94.09 344	97.33 2	96.29 86	98.79 24	89.73 82	99.86 8	99.36 2	99.42 46	99.67 13

test_fmvsmvis_n_1920		96.70 46	96.84 32	96.31 100	96.62 182	91.73 107	97.98 61	98.30 32	96.19 5	96.10 93	98.95 8	89.42 83	99.76 38	98.90 10	99.08 81	97.43 194

EC-MVSNet		96.42 56	96.47 52	96.26 106	97.01 161	91.52 119	98.89 5	97.75 123	94.42 55	96.64 71	97.68 107	89.32 84	98.60 192	97.45 26	99.11 80	98.67 121

PAPR		94.18 112	93.42 132	96.48 86	97.64 128	91.42 125	95.55 271	97.71 132	88.99 229	92.34 180	95.82 214	89.19 85	99.11 138	86.14 273	97.38 140	98.90 102

MG-MVS		95.61 77	95.38 77	96.31 100	98.42 73	90.53 162	96.04 250	97.48 156	93.47 87	95.67 110	98.10 73	89.17 86	99.25 123	91.27 176	98.77 94	99.13 77

PAPM_NR		95.01 92	94.59 95	96.26 106	98.89 51	90.68 159	97.24 153	97.73 126	91.80 145	92.93 171	96.62 177	89.13 87	99.14 135	89.21 216	97.78 129	98.97 93

mvsany_test1		93.93 127	93.98 110	93.78 241	94.94 278	86.80 270	94.62 299	92.55 364	88.77 242	96.85 60	98.49 38	88.98 88	98.08 243	95.03 96	95.62 180	96.46 225

ACMMP		96.27 62	95.93 64	97.28 55	99.24 28	92.62 80	98.25 36	98.81 5	92.99 107	94.56 131	98.39 48	88.96 89	99.85 18	94.57 112	97.63 132	99.36 60
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 70	95.53 71	97.20 61	97.67 124	92.98 72	97.65 106	98.13 65	94.81 39	96.61 72	98.35 51	88.87 90	99.51 96	90.36 189	97.35 142	99.11 81

API-MVS		94.84 101	94.49 102	95.90 126	97.90 114	92.00 102	97.80 89	97.48 156	89.19 223	94.81 126	96.71 160	88.84 91	99.17 131	88.91 223	98.76 95	96.53 220

fmvsm_s_conf0.5_n		96.85 38	97.13 16	96.04 119	98.07 105	90.28 169	97.97 67	98.76 8	94.93 30	98.84 16	99.06 4	88.80 92	99.65 58	99.06 7	98.63 99	98.18 155

test222					98.24 87	92.21 94	95.33 280	97.60 142	79.22 369	95.25 118	97.84 98	88.80 92			99.15 75	98.72 116

Test By Simon												88.73 94

pcd_1.5k_mvsjas		7.39 369	9.85 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	88.65 95	0.00 403	0.00 402	0.00 401	0.00 399

PS-MVSNAJss		93.74 135	93.51 125	94.44 203	93.91 318	89.28 207	97.75 92	97.56 149	92.50 126	89.94 239	96.54 180	88.65 95	98.18 228	93.83 126	90.90 258	95.86 241

PS-MVSNAJ		95.37 82	95.33 79	95.49 151	97.35 141	90.66 160	95.31 282	97.48 156	93.85 72	96.51 77	95.70 224	88.65 95	99.65 58	94.80 104	98.27 115	96.17 231

xiu_mvs_v2_base		95.32 84	95.29 80	95.40 156	97.22 143	90.50 163	95.44 276	97.44 170	93.70 77	96.46 81	96.18 196	88.59 98	99.53 91	94.79 106	97.81 128	96.17 231

PLC	91.00 6	94.11 119	93.43 130	96.13 114	98.58 68	91.15 141	96.69 201	97.39 176	87.29 284	91.37 202	96.71 160	88.39 99	99.52 95	87.33 254	97.13 151	97.73 179
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UniMVSNet_NR-MVSNet		93.37 147	92.67 157	95.47 154	95.34 251	92.83 74	97.17 162	98.58 17	92.98 112	90.13 230	95.80 215	88.37 100	97.85 279	91.71 166	83.93 335	95.73 257

fmvsm_s_conf0.5_n_a		96.75 45	96.93 28	96.20 111	97.64 128	90.72 156	98.00 59	98.73 9	94.55 50	98.91 13	99.08 3	88.22 101	99.63 67	98.91 9	98.37 111	98.25 151

MM				98.23 11		95.03 25	98.07 52	95.76 281	97.78 1	97.52 40	98.80 22	88.09 102	99.86 8	99.44 1	99.37 56	99.80 1

fmvsm_s_conf0.1_n		96.58 53	96.77 39	96.01 123	96.67 180	90.25 170	97.91 75	98.38 23	94.48 53	98.84 16	99.14 1	88.06 103	99.62 68	98.82 11	98.60 101	98.15 158

PVSNet_BlendedMVS		94.06 121	93.92 111	94.47 202	98.27 83	89.46 197	96.73 195	98.36 24	90.17 196	94.36 134	95.24 244	88.02 104	99.58 77	93.44 131	90.72 261	94.36 330

PVSNet_Blended		94.87 100	94.56 97	95.81 130	98.27 83	89.46 197	95.47 275	98.36 24	88.84 236	94.36 134	96.09 204	88.02 104	99.58 77	93.44 131	98.18 119	98.40 143

TAPA-MVS	90.10 7	92.30 194	91.22 211	95.56 145	98.33 80	89.60 188	96.79 190	97.65 136	81.83 353	91.52 198	97.23 136	87.94 106	98.91 163	71.31 374	98.37 111	98.17 157
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
casdiffmvs_mvg		95.81 73	95.57 70	96.51 83	96.87 166	91.49 120	97.50 125	97.56 149	93.99 67	95.13 122	97.92 89	87.89 107	98.78 171	95.97 65	97.33 143	99.26 67
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 99	94.62 94	95.68 139	96.83 170	89.55 191	96.70 199	97.17 193	91.17 166	95.60 112	96.11 203	87.87 108	98.76 175	93.01 144	97.17 150	98.72 116

UniMVSNet (Re)		93.31 149	92.55 163	95.61 143	95.39 245	93.34 64	97.39 139	98.71 11	93.14 103	90.10 234	94.83 260	87.71 109	98.03 254	91.67 169	83.99 334	95.46 268

FC-MVSNet-test		93.94 126	93.57 119	95.04 169	95.48 240	91.45 124	98.12 48	98.71 11	93.37 91	90.23 225	96.70 162	87.66 110	97.85 279	91.49 171	90.39 266	95.83 245

canonicalmvs		96.02 67	95.45 74	97.75 35	97.59 134	95.15 23	98.28 32	97.60 142	94.52 52	96.27 88	96.12 200	87.65 111	99.18 130	96.20 58	94.82 193	98.91 101

FIs		94.09 120	93.70 115	95.27 159	95.70 230	92.03 101	98.10 49	98.68 13	93.36 93	90.39 222	96.70 162	87.63 112	97.94 269	92.25 151	90.50 265	95.84 244

CDS-MVSNet		94.14 118	93.54 121	95.93 125	96.18 210	91.46 123	96.33 233	97.04 208	88.97 231	93.56 151	96.51 181	87.55 113	97.89 277	89.80 198	95.95 171	98.44 140
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+		94.93 97	94.45 104	96.36 98	96.61 183	91.47 122	96.41 223	97.41 175	91.02 171	94.50 132	95.92 208	87.53 114	98.78 171	93.89 123	96.81 155	98.84 110

casdiffmvs		95.64 76	95.49 72	96.08 115	96.76 178	90.45 165	97.29 150	97.44 170	94.00 66	95.46 117	97.98 85	87.52 115	98.73 178	95.64 79	97.33 143	99.08 83
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 85	94.91 88	96.38 96	98.20 93	90.86 149	97.27 151	98.25 45	90.21 195	94.18 139	97.27 133	87.48 116	99.73 42	93.53 128	97.77 130	98.55 124

fmvsm_s_conf0.1_n_a		96.40 57	96.47 52	96.16 113	95.48 240	90.69 157	97.91 75	98.33 29	94.07 64	98.93 9	99.14 1	87.44 117	99.61 69	98.63 13	98.32 113	98.18 155

mvs_anonymous		93.82 132	93.74 114	94.06 221	96.44 198	85.41 295	95.81 261	97.05 206	89.85 205	90.09 235	96.36 189	87.44 117	97.75 289	93.97 119	96.69 160	99.02 86

CANet		96.39 58	96.02 63	97.50 45	97.62 130	93.38 61	97.02 171	97.96 102	95.42 15	94.86 125	97.81 99	87.38 119	99.82 28	96.88 36	99.20 71	99.29 63

baseline		95.58 78	95.42 76	96.08 115	96.78 173	90.41 167	97.16 163	97.45 166	93.69 78	95.65 111	97.85 96	87.29 120	98.68 184	95.66 75	97.25 147	99.13 77

TAMVS		94.01 124	93.46 127	95.64 140	96.16 212	90.45 165	96.71 198	96.89 224	89.27 221	93.46 156	96.92 153	87.29 120	97.94 269	88.70 227	95.74 176	98.53 126

nrg030		94.05 122	93.31 134	96.27 105	95.22 262	94.59 29	98.34 27	97.46 161	92.93 115	91.21 212	96.64 168	87.23 122	98.22 223	94.99 98	85.80 307	95.98 240

CPTT-MVS		95.57 79	95.19 82	96.70 71	99.27 26	91.48 121	98.33 28	98.11 70	87.79 270	95.17 121	98.03 80	87.09 123	99.61 69	93.51 129	99.42 46	99.02 86

OMC-MVS		95.09 91	94.70 93	96.25 109	98.46 70	91.28 129	96.43 221	97.57 146	92.04 140	94.77 127	97.96 87	87.01 124	99.09 142	91.31 175	96.77 156	98.36 147

DeepC-MVS	93.07 3	96.06 65	95.66 69	97.29 53	97.96 108	93.17 68	97.30 149	98.06 82	93.92 69	93.38 158	98.66 27	86.83 125	99.73 42	95.60 84	99.22 68	98.96 94
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
IterMVS-LS		92.29 195	91.94 183	93.34 260	96.25 206	86.97 268	96.57 217	97.05 206	90.67 181	89.50 255	94.80 262	86.59 126	97.64 297	89.91 195	86.11 305	95.40 273
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		93.03 164	92.88 146	93.48 255	95.77 228	86.98 267	96.44 219	97.12 196	90.66 183	91.30 206	97.64 114	86.56 127	98.05 250	89.91 195	90.55 263	95.41 270

miper_enhance_ethall		91.54 223	91.01 216	93.15 267	95.35 250	87.07 266	93.97 324	96.90 222	86.79 293	89.17 265	93.43 324	86.55 128	97.64 297	89.97 194	86.93 297	94.74 319

1112_ss		93.37 147	92.42 170	96.21 110	97.05 158	90.99 143	96.31 235	96.72 234	86.87 292	89.83 243	96.69 164	86.51 129	99.14 135	88.12 232	93.67 211	98.50 130

diffmvs		95.25 86	95.13 84	95.63 141	96.43 199	89.34 202	95.99 254	97.35 182	92.83 117	96.31 85	97.37 128	86.44 130	98.67 185	96.26 50	97.19 149	98.87 107
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		94.71 105	94.02 109	96.79 70	97.71 123	92.05 100	96.59 214	97.35 182	90.61 187	94.64 129	96.93 150	86.41 131	99.39 111	91.20 178	94.71 197	98.94 97

EPNet		95.20 89	94.56 97	97.14 63	92.80 346	92.68 79	97.85 82	94.87 329	96.64 3	92.46 174	97.80 101	86.23 132	99.65 58	93.72 127	98.62 100	99.10 82
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		91.59 218	91.13 214	92.97 273	95.55 237	86.57 278	94.47 305	96.88 225	87.77 271	88.88 270	94.01 301	86.22 133	97.54 306	89.49 206	86.93 297	94.79 315

Fast-Effi-MVS+		93.46 144	92.75 153	95.59 144	96.77 175	90.03 173	96.81 189	97.13 195	88.19 257	91.30 206	94.27 290	86.21 134	98.63 189	87.66 246	96.46 166	98.12 160

MVSFormer		95.37 82	95.16 83	95.99 124	96.34 203	91.21 133	98.22 41	97.57 146	91.42 155	96.22 89	97.32 129	86.20 135	97.92 273	94.07 117	99.05 83	98.85 108

lupinMVS		94.99 96	94.56 97	96.29 104	96.34 203	91.21 133	95.83 260	96.27 261	88.93 233	96.22 89	96.88 155	86.20 135	98.85 166	95.27 91	99.05 83	98.82 111

114514_t		93.95 125	93.06 140	96.63 74	99.07 37	91.61 114	97.46 133	97.96 102	77.99 373	93.00 166	97.57 119	86.14 137	99.33 115	89.22 215	99.15 75	98.94 97

alignmvs		95.87 72	95.23 81	97.78 31	97.56 137	95.19 21	97.86 79	97.17 193	94.39 57	96.47 80	96.40 187	85.89 138	99.20 127	96.21 57	95.11 189	98.95 96

WR-MVS_H		92.00 206	91.35 202	93.95 230	95.09 271	89.47 195	98.04 55	98.68 13	91.46 153	88.34 282	94.68 267	85.86 139	97.56 304	85.77 281	84.24 332	94.82 310

Test_1112_low_res		92.84 175	91.84 186	95.85 129	97.04 159	89.97 179	95.53 273	96.64 242	85.38 314	89.65 249	95.18 245	85.86 139	99.10 139	87.70 242	93.58 216	98.49 132

HY-MVS	89.66 9	93.87 129	92.95 143	96.63 74	97.10 152	92.49 85	95.64 269	96.64 242	89.05 227	93.00 166	95.79 218	85.77 141	99.45 105	89.16 219	94.35 199	97.96 167

c3_l		91.38 230	90.89 218	92.88 277	95.58 235	86.30 282	94.68 298	96.84 229	88.17 258	88.83 273	94.23 293	85.65 142	97.47 313	89.36 209	84.63 325	94.89 305

IS-MVSNet		94.90 98	94.52 101	96.05 118	97.67 124	90.56 161	98.44 23	96.22 264	93.21 96	93.99 143	97.74 104	85.55 143	98.45 204	89.98 193	97.86 126	99.14 76

MVS		91.71 213	90.44 237	95.51 149	95.20 264	91.59 116	96.04 250	97.45 166	73.44 381	87.36 305	95.60 229	85.42 144	99.10 139	85.97 278	97.46 135	95.83 245

VNet		95.89 71	95.45 74	97.21 60	98.07 105	92.94 73	97.50 125	98.15 62	93.87 71	97.52 40	97.61 117	85.29 145	99.53 91	95.81 72	95.27 185	99.16 73

CNLPA		94.28 110	93.53 122	96.52 80	98.38 78	92.55 83	96.59 214	96.88 225	90.13 199	91.91 189	97.24 135	85.21 146	99.09 142	87.64 247	97.83 127	97.92 169

F-COLMAP		93.58 140	92.98 142	95.37 157	98.40 75	88.98 216	97.18 161	97.29 187	87.75 273	90.49 219	97.10 143	85.21 146	99.50 99	86.70 264	96.72 159	97.63 183

LCM-MVSNet-Re		92.50 182	92.52 166	92.44 287	96.82 172	81.89 336	96.92 180	93.71 352	92.41 128	84.30 338	94.60 271	85.08 148	97.03 332	91.51 170	97.36 141	98.40 143

NR-MVSNet		92.34 191	91.27 208	95.53 148	94.95 276	93.05 70	97.39 139	98.07 79	92.65 123	84.46 336	95.71 222	85.00 149	97.77 288	89.71 200	83.52 341	95.78 250

PAPM		91.52 224	90.30 243	95.20 161	95.30 257	89.83 182	93.38 344	96.85 228	86.26 302	88.59 277	95.80 215	84.88 150	98.15 230	75.67 357	95.93 172	97.63 183

MAR-MVS		94.22 111	93.46 127	96.51 83	98.00 107	92.19 97	97.67 103	97.47 159	88.13 261	93.00 166	95.84 212	84.86 151	99.51 96	87.99 234	98.17 120	97.83 176
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		94.84 101	94.39 106	96.18 112	95.52 238	90.93 147	96.09 248	96.52 250	89.28 220	96.01 98	97.32 129	84.70 152	98.77 174	95.15 94	98.91 91	98.85 108
jason: jason.
sss		94.51 106	93.80 113	96.64 72	97.07 153	91.97 103	96.32 234	98.06 82	88.94 232	94.50 132	96.78 157	84.60 153	99.27 122	91.90 159	96.02 169	98.68 120

LS3D		93.57 141	92.61 161	96.47 87	97.59 134	91.61 114	97.67 103	97.72 128	85.17 319	90.29 224	98.34 54	84.60 153	99.73 42	83.85 306	98.27 115	98.06 166

Vis-MVSNet (Re-imp)		94.15 115	93.88 112	94.95 178	97.61 131	87.92 247	98.10 49	95.80 280	92.22 131	93.02 165	97.45 124	84.53 155	97.91 276	88.24 231	97.97 124	99.02 86

GeoE		93.89 128	93.28 135	95.72 137	96.96 164	89.75 184	98.24 39	96.92 221	89.47 215	92.12 185	97.21 137	84.42 156	98.39 211	87.71 241	96.50 163	99.01 89

cdsmvs_eth3d_5k		23.24 365	30.99 367	0.00 384	0.00 406	0.00 409	0.00 395	97.63 140	0.00 402	0.00 403	96.88 155	84.38 157	0.00 403	0.00 402	0.00 401	0.00 399

test_yl		94.78 103	94.23 107	96.43 91	97.74 121	91.22 131	96.85 185	97.10 198	91.23 163	95.71 107	96.93 150	84.30 158	99.31 119	93.10 137	95.12 187	98.75 113

DCV-MVSNet		94.78 103	94.23 107	96.43 91	97.74 121	91.22 131	96.85 185	97.10 198	91.23 163	95.71 107	96.93 150	84.30 158	99.31 119	93.10 137	95.12 187	98.75 113

CHOSEN 280x420		93.12 158	92.72 156	94.34 209	96.71 179	87.27 258	90.29 372	97.72 128	86.61 296	91.34 203	95.29 240	84.29 160	98.41 206	93.25 135	98.94 89	97.35 198

test_fmvsmconf0.01_n		96.15 64	95.85 67	97.03 67	92.66 349	91.83 106	97.97 67	97.84 120	95.57 12	97.53 39	99.00 6	84.20 161	99.76 38	98.82 11	99.08 81	99.48 44

baseline1		92.82 176	91.90 184	95.55 147	97.20 145	90.77 154	97.19 160	94.58 334	92.20 133	92.36 178	96.34 190	84.16 162	98.21 224	89.20 217	83.90 338	97.68 182

eth_miper_zixun_eth		91.02 249	90.59 233	92.34 291	95.33 254	84.35 311	94.10 321	96.90 222	88.56 247	88.84 272	94.33 285	84.08 163	97.60 302	88.77 226	84.37 331	95.06 294

PCF-MVS	89.48 11	91.56 221	89.95 260	96.36 98	96.60 184	92.52 84	92.51 358	97.26 188	79.41 368	88.90 268	96.56 179	84.04 164	99.55 87	77.01 353	97.30 145	97.01 207
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
1314		92.81 177	92.03 179	95.14 164	95.33 254	89.52 194	96.04 250	97.44 170	87.72 274	86.25 322	95.33 239	83.84 165	98.79 170	89.26 213	97.05 152	97.11 206

DP-MVS		92.76 178	91.51 200	96.52 80	98.77 53	90.99 143	97.38 141	96.08 270	82.38 349	89.29 261	97.87 93	83.77 166	99.69 52	81.37 327	96.69 160	98.89 105

3Dnovator+	91.43 4	95.40 81	94.48 103	98.16 16	96.90 165	95.34 16	98.48 21	97.87 111	94.65 49	88.53 279	98.02 82	83.69 167	99.71 46	93.18 136	98.96 88	99.44 49

h-mvs33		94.15 115	93.52 124	96.04 119	97.81 118	90.22 171	97.62 114	97.58 145	95.19 20	96.74 64	97.45 124	83.67 168	99.61 69	95.85 69	79.73 358	98.29 150

hse-mvs2		93.45 145	92.99 141	94.81 186	97.02 160	88.59 224	96.69 201	96.47 253	95.19 20	96.74 64	96.16 199	83.67 168	98.48 203	95.85 69	79.13 362	97.35 198

AdaColmap		94.34 109	93.68 116	96.31 100	98.59 66	91.68 112	96.59 214	97.81 121	89.87 202	92.15 183	97.06 145	83.62 170	99.54 89	89.34 210	98.07 122	97.70 181

DU-MVS		92.90 171	92.04 178	95.49 151	94.95 276	92.83 74	97.16 163	98.24 47	93.02 106	90.13 230	95.71 222	83.47 171	97.85 279	91.71 166	83.93 335	95.78 250

Baseline_NR-MVSNet		91.20 241	90.62 231	92.95 274	93.83 321	88.03 244	97.01 174	95.12 315	88.42 252	89.70 246	95.13 248	83.47 171	97.44 316	89.66 203	83.24 343	93.37 347

miper_lstm_enhance		90.50 268	90.06 258	91.83 303	95.33 254	83.74 319	93.86 330	96.70 238	87.56 278	87.79 295	93.81 309	83.45 173	96.92 337	87.39 252	84.62 326	94.82 310

EPNet_dtu		91.71 213	91.28 207	92.99 272	93.76 323	83.71 321	96.69 201	95.28 306	93.15 102	87.02 312	95.95 207	83.37 174	97.38 321	79.46 339	96.84 154	97.88 172
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FA-MVS(test-final)		93.52 143	92.92 144	95.31 158	96.77 175	88.54 227	94.82 295	96.21 266	89.61 210	94.20 138	95.25 243	83.24 175	99.14 135	90.01 192	96.16 168	98.25 151

BH-untuned		92.94 169	92.62 160	93.92 235	97.22 143	86.16 287	96.40 227	96.25 263	90.06 200	89.79 244	96.17 198	83.19 176	98.35 214	87.19 257	97.27 146	97.24 203

TranMVSNet+NR-MVSNet		92.50 182	91.63 193	95.14 164	94.76 288	92.07 99	97.53 123	98.11 70	92.90 116	89.56 252	96.12 200	83.16 177	97.60 302	89.30 211	83.20 344	95.75 255

CHOSEN 1792x2688		94.15 115	93.51 125	96.06 117	98.27 83	89.38 200	95.18 289	98.48 21	85.60 311	93.76 149	97.11 142	83.15 178	99.61 69	91.33 174	98.72 96	99.19 71

PMMVS		92.86 173	92.34 171	94.42 205	94.92 279	86.73 273	94.53 303	96.38 257	84.78 326	94.27 136	95.12 249	83.13 179	98.40 207	91.47 172	96.49 164	98.12 160

Effi-MVS+-dtu		93.08 161	93.21 137	92.68 285	96.02 221	83.25 325	97.14 165	96.72 234	93.85 72	91.20 213	93.44 322	83.08 180	98.30 218	91.69 168	95.73 177	96.50 222

v8		91.29 238	90.53 236	93.57 252	94.15 311	88.12 242	97.34 144	97.06 205	88.99 229	88.32 283	94.26 292	83.08 180	98.01 256	87.62 248	83.92 337	94.57 324

mvsmamba		93.83 131	93.46 127	94.93 181	94.88 283	90.85 150	98.55 14	95.49 297	94.24 61	91.29 209	96.97 149	83.04 182	98.14 231	95.56 86	91.17 251	95.78 250

DIV-MVS_self_test		90.97 252	90.33 240	92.88 277	95.36 249	86.19 286	94.46 307	96.63 245	87.82 267	88.18 289	94.23 293	82.99 183	97.53 308	87.72 239	85.57 309	94.93 301

cl____		90.96 253	90.32 241	92.89 276	95.37 248	86.21 285	94.46 307	96.64 242	87.82 267	88.15 290	94.18 296	82.98 184	97.54 306	87.70 242	85.59 308	94.92 303

BH-w/o		92.14 203	91.75 188	93.31 261	96.99 163	85.73 290	95.67 266	95.69 286	88.73 243	89.26 263	94.82 261	82.97 185	98.07 247	85.26 288	96.32 167	96.13 235

v148		90.99 250	90.38 239	92.81 280	93.83 321	85.80 289	96.78 192	96.68 239	89.45 216	88.75 275	93.93 305	82.96 186	97.82 283	87.83 237	83.25 342	94.80 313

HyFIR lowres test		93.66 137	92.92 144	95.87 127	98.24 87	89.88 181	94.58 301	98.49 19	85.06 321	93.78 148	95.78 219	82.86 187	98.67 185	91.77 164	95.71 178	99.07 85

test_djsdf		93.07 162	92.76 151	94.00 225	93.49 332	88.70 222	98.22 41	97.57 146	91.42 155	90.08 236	95.55 232	82.85 188	97.92 273	94.07 117	91.58 241	95.40 273

PatchmatchNet		91.91 208	91.35 202	93.59 250	95.38 246	84.11 315	93.15 348	95.39 299	89.54 212	92.10 186	93.68 314	82.82 189	98.13 232	84.81 292	95.32 184	98.52 127
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												82.76 190				98.45 137

xiu_mvs_v1_base_debu		95.01 92	94.76 90	95.75 133	96.58 186	91.71 109	96.25 239	97.35 182	92.99 107	96.70 66	96.63 174	82.67 191	99.44 106	96.22 53	97.46 135	96.11 236

xiu_mvs_v1_base		95.01 92	94.76 90	95.75 133	96.58 186	91.71 109	96.25 239	97.35 182	92.99 107	96.70 66	96.63 174	82.67 191	99.44 106	96.22 53	97.46 135	96.11 236

xiu_mvs_v1_base_debi		95.01 92	94.76 90	95.75 133	96.58 186	91.71 109	96.25 239	97.35 182	92.99 107	96.70 66	96.63 174	82.67 191	99.44 106	96.22 53	97.46 135	96.11 236

patchmatchnet-post											90.45 357	82.65 194	98.10 239

V42		91.58 220	90.87 219	93.73 242	94.05 315	88.50 229	97.32 147	96.97 213	88.80 241	89.71 245	94.33 285	82.54 195	98.05 250	89.01 220	85.07 319	94.64 323

WR-MVS		92.34 191	91.53 197	94.77 191	95.13 269	90.83 151	96.40 227	97.98 100	91.88 144	89.29 261	95.54 233	82.50 196	97.80 284	89.79 199	85.27 315	95.69 259

tpmrst		91.44 227	91.32 204	91.79 306	95.15 267	79.20 365	93.42 343	95.37 301	88.55 248	93.49 155	93.67 315	82.49 197	98.27 220	90.41 187	89.34 276	97.90 170

MDTV_nov1_ep13_2view						70.35 382	93.10 350		83.88 336	93.55 152		82.47 198		86.25 270		98.38 145

XVG-OURS-SEG-HR		93.86 130	93.55 120	94.81 186	97.06 156	88.53 228	95.28 283	97.45 166	91.68 148	94.08 142	97.68 107	82.41 199	98.90 164	93.84 125	92.47 226	96.98 208

QAPM		93.45 145	92.27 173	96.98 69	96.77 175	92.62 80	98.39 26	98.12 67	84.50 329	88.27 286	97.77 102	82.39 200	99.81 29	85.40 286	98.81 93	98.51 129

Patchmatch-test		89.42 288	87.99 295	93.70 245	95.27 258	85.11 302	88.98 379	94.37 339	81.11 357	87.10 310	93.69 312	82.28 201	97.50 311	74.37 363	94.76 194	98.48 134

Vis-MVSNet		95.23 87	94.81 89	96.51 83	97.18 146	91.58 117	98.26 35	98.12 67	94.38 58	94.90 124	98.15 72	82.28 201	98.92 161	91.45 173	98.58 103	99.01 89
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator	91.36 5	95.19 90	94.44 105	97.44 47	96.56 189	93.36 63	98.65 11	98.36 24	94.12 63	89.25 264	98.06 77	82.20 203	99.77 37	93.41 133	99.32 59	99.18 72

v10		91.04 248	90.23 248	93.49 254	94.12 312	88.16 241	97.32 147	97.08 201	88.26 256	88.29 285	94.22 295	82.17 204	97.97 261	86.45 268	84.12 333	94.33 331

v1144		91.37 232	90.60 232	93.68 247	93.89 319	88.23 237	96.84 187	97.03 210	88.37 253	89.69 247	94.39 281	82.04 205	97.98 258	87.80 238	85.37 312	94.84 307

MVSTER		93.20 153	92.81 150	94.37 207	96.56 189	89.59 189	97.06 168	97.12 196	91.24 162	91.30 206	95.96 206	82.02 206	98.05 250	93.48 130	90.55 263	95.47 267

CP-MVSNet		91.89 209	91.24 209	93.82 238	95.05 272	88.57 225	97.82 86	98.19 55	91.70 147	88.21 288	95.76 220	81.96 207	97.52 310	87.86 236	84.65 324	95.37 276

Patchmatch-RL test		87.38 309	86.24 312	90.81 325	88.74 377	78.40 369	88.12 383	93.17 357	87.11 288	82.17 355	89.29 366	81.95 208	95.60 358	88.64 228	77.02 366	98.41 142

sam_mvs												81.94 209

pmmvs4		90.93 254	89.85 264	94.17 216	93.34 337	90.79 153	94.60 300	96.02 271	84.62 327	87.45 301	95.15 246	81.88 210	97.45 315	87.70 242	87.87 289	94.27 335

test_post											17.58 399	81.76 211	98.08 243

XVG-OURS		93.72 136	93.35 133	94.80 189	97.07 153	88.61 223	94.79 296	97.46 161	91.97 143	93.99 143	97.86 95	81.74 212	98.88 165	92.64 148	92.67 225	96.92 212

v2v482		91.59 218	90.85 222	93.80 239	93.87 320	88.17 240	96.94 179	96.88 225	89.54 212	89.53 253	94.90 256	81.70 213	98.02 255	89.25 214	85.04 321	95.20 288

baseline2		91.63 216	90.86 220	93.94 232	94.33 306	86.32 281	95.92 257	91.64 371	89.37 218	86.94 315	94.69 266	81.62 214	98.69 183	88.64 228	94.57 198	96.81 215

v144192		91.06 247	90.28 244	93.39 258	93.66 327	87.23 261	96.83 188	97.07 203	87.43 280	89.69 247	94.28 289	81.48 215	98.00 257	87.18 258	84.92 323	94.93 301

MDTV_nov1_ep13			90.76 226		95.22 262	80.33 352	93.03 351	95.28 306	88.14 260	92.84 172	93.83 306	81.34 216	98.08 243	82.86 311	94.34 200

HQP_MVS		93.78 134	93.43 130	94.82 184	96.21 207	89.99 176	97.74 93	97.51 153	94.85 34	91.34 203	96.64 168	81.32 217	98.60 192	93.02 142	92.23 229	95.86 241

plane_prior6					96.10 218	90.00 174						81.32 217

v7n		90.76 258	89.86 263	93.45 257	93.54 329	87.60 255	97.70 102	97.37 179	88.85 235	87.65 298	94.08 300	81.08 219	98.10 239	84.68 294	83.79 339	94.66 322

HQP2-MVS												80.95 220

HQP-MVS		93.19 154	92.74 154	94.54 201	95.86 223	89.33 203	96.65 205	97.39 176	93.55 80	90.14 226	95.87 210	80.95 220	98.50 200	92.13 155	92.10 234	95.78 250

CR-MVSNet		90.82 257	89.77 268	93.95 230	94.45 302	87.19 262	90.23 373	95.68 288	86.89 291	92.40 175	92.36 339	80.91 222	97.05 331	81.09 329	93.95 209	97.60 188

Patchmtry		88.64 298	87.25 301	92.78 281	94.09 313	86.64 274	89.82 376	95.68 288	80.81 361	87.63 299	92.36 339	80.91 222	97.03 332	78.86 342	85.12 318	94.67 321

v1192		91.07 246	90.23 248	93.58 251	93.70 324	87.82 251	96.73 195	97.07 203	87.77 271	89.58 250	94.32 287	80.90 224	97.97 261	86.52 266	85.48 310	94.95 297

cl22		91.21 240	90.56 235	93.14 268	96.09 219	86.80 270	94.41 309	96.58 248	87.80 269	88.58 278	93.99 303	80.85 225	97.62 300	89.87 197	86.93 297	94.99 296

anonymousdsp		92.16 201	91.55 196	93.97 228	92.58 351	89.55 191	97.51 124	97.42 174	89.42 217	88.40 281	94.84 259	80.66 226	97.88 278	91.87 161	91.28 249	94.48 325

RRT_MVS		93.10 159	92.83 148	93.93 234	94.76 288	88.04 243	98.47 22	96.55 249	93.44 88	90.01 238	97.04 146	80.64 227	97.93 272	94.33 114	90.21 268	95.83 245

CLD-MVS		92.98 166	92.53 165	94.32 210	96.12 217	89.20 210	95.28 283	97.47 159	92.66 122	89.90 240	95.62 228	80.58 228	98.40 207	92.73 147	92.40 227	95.38 275
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_post1							92.81 355				16.58 400	80.53 229	97.68 293	86.20 271

VPA-MVSNet		93.24 151	92.48 168	95.51 149	95.70 230	92.39 87	97.86 79	98.66 16	92.30 130	92.09 187	95.37 238	80.49 230	98.40 207	93.95 120	85.86 306	95.75 255

tpmvs		89.83 284	89.15 283	91.89 301	94.92 279	80.30 353	93.11 349	95.46 298	86.28 301	88.08 291	92.65 330	80.44 231	98.52 199	81.47 323	89.92 270	96.84 214

PatchMatch-RL		92.90 171	92.02 180	95.56 145	98.19 95	90.80 152	95.27 285	97.18 191	87.96 263	91.86 191	95.68 225	80.44 231	98.99 156	84.01 302	97.54 134	96.89 213

PEN-MVS		91.20 241	90.44 237	93.48 255	94.49 300	87.91 249	97.76 91	98.18 57	91.29 158	87.78 296	95.74 221	80.35 233	97.33 323	85.46 285	82.96 345	95.19 291

Fast-Effi-MVS+-dtu		92.29 195	91.99 181	93.21 266	95.27 258	85.52 293	97.03 169	96.63 245	92.09 138	89.11 267	95.14 247	80.33 234	98.08 243	87.54 250	94.74 196	96.03 239

MSDG		91.42 228	90.24 247	94.96 177	97.15 149	88.91 217	93.69 336	96.32 259	85.72 310	86.93 316	96.47 183	80.24 235	98.98 157	80.57 330	95.05 190	96.98 208

v1921920		90.85 256	90.03 259	93.29 262	93.55 328	86.96 269	96.74 194	97.04 208	87.36 282	89.52 254	94.34 284	80.23 236	97.97 261	86.27 269	85.21 316	94.94 299

RPMNet		88.98 291	87.05 305	94.77 191	94.45 302	87.19 262	90.23 373	98.03 91	77.87 375	92.40 175	87.55 378	80.17 237	99.51 96	68.84 379	93.95 209	97.60 188

ET-MVSNet_ETH3D		91.49 225	90.11 253	95.63 141	96.40 200	91.57 118	95.34 279	93.48 355	90.60 189	75.58 375	95.49 235	80.08 238	96.79 340	94.25 115	89.76 272	98.52 127

PatchT		88.87 295	87.42 299	93.22 265	94.08 314	85.10 303	89.51 377	94.64 333	81.92 352	92.36 178	88.15 374	80.05 239	97.01 334	72.43 370	93.65 212	97.54 191

our_test_3		88.78 296	87.98 296	91.20 320	92.45 354	82.53 329	93.61 340	95.69 286	85.77 309	84.88 333	93.71 311	79.99 240	96.78 341	79.47 338	86.24 302	94.28 334

DTE-MVSNet		90.56 265	89.75 270	93.01 271	93.95 316	87.25 259	97.64 110	97.65 136	90.74 176	87.12 308	95.68 225	79.97 241	97.00 335	83.33 307	81.66 351	94.78 317

D2MVS		91.30 237	90.95 217	92.35 289	94.71 293	85.52 293	96.18 245	98.21 51	88.89 234	86.60 319	93.82 308	79.92 242	97.95 268	89.29 212	90.95 257	93.56 343

TransMVSNet (Re)		88.94 292	87.56 298	93.08 270	94.35 305	88.45 231	97.73 95	95.23 310	87.47 279	84.26 339	95.29 240	79.86 243	97.33 323	79.44 340	74.44 373	93.45 346

ACMM	89.79 8	92.96 167	92.50 167	94.35 208	96.30 205	88.71 221	97.58 117	97.36 181	91.40 157	90.53 218	96.65 167	79.77 244	98.75 176	91.24 177	91.64 239	95.59 262
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		92.16 201	91.23 210	94.95 178	94.75 290	90.94 146	97.47 131	97.43 173	89.14 224	88.90 268	96.43 185	79.71 245	98.24 221	89.56 205	87.68 290	95.67 261

PS-CasMVS		91.55 222	90.84 223	93.69 246	94.96 275	88.28 234	97.84 83	98.24 47	91.46 153	88.04 292	95.80 215	79.67 246	97.48 312	87.02 261	84.54 329	95.31 280

ab-mvs		93.57 141	92.55 163	96.64 72	97.28 142	91.96 104	95.40 277	97.45 166	89.81 207	93.22 164	96.28 192	79.62 247	99.46 103	90.74 184	93.11 217	98.50 130

v1240		90.70 262	89.85 264	93.23 264	93.51 331	86.80 270	96.61 211	97.02 211	87.16 287	89.58 250	94.31 288	79.55 248	97.98 258	85.52 284	85.44 311	94.90 304

CostFormer		91.18 244	90.70 229	92.62 286	94.84 285	81.76 337	94.09 322	94.43 336	84.15 332	92.72 173	93.77 310	79.43 249	98.20 225	90.70 185	92.18 232	97.90 170

CANet_DTU		94.37 108	93.65 117	96.55 78	96.46 197	92.13 98	96.21 243	96.67 241	94.38 58	93.53 154	97.03 147	79.34 250	99.71 46	90.76 183	98.45 109	97.82 177

OPM-MVS		93.28 150	92.76 151	94.82 184	94.63 296	90.77 154	96.65 205	97.18 191	93.72 75	91.68 194	97.26 134	79.33 251	98.63 189	92.13 155	92.28 228	95.07 293
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
iter_conf_final		93.60 138	93.11 138	95.04 169	97.13 150	91.30 128	97.92 73	95.65 290	92.98 112	91.60 195	96.64 168	79.28 252	98.13 232	95.34 90	91.49 243	95.70 258

JIA-IIPM		88.26 302	87.04 306	91.91 300	93.52 330	81.42 339	89.38 378	94.38 338	80.84 360	90.93 215	80.74 385	79.22 253	97.92 273	82.76 314	91.62 240	96.38 226

SDMVSNet		94.17 113	93.61 118	95.86 128	98.09 101	91.37 126	97.35 143	98.20 52	93.18 100	91.79 192	97.28 131	79.13 254	98.93 160	94.61 110	92.84 220	97.28 201

CVMVSNet		91.23 239	91.75 188	89.67 340	95.77 228	74.69 375	96.44 219	94.88 326	85.81 308	92.18 182	97.64 114	79.07 255	95.58 359	88.06 233	95.86 174	98.74 115

LPG-MVS_test		92.94 169	92.56 162	94.10 219	96.16 212	88.26 235	97.65 106	97.46 161	91.29 158	90.12 232	97.16 139	79.05 256	98.73 178	92.25 151	91.89 237	95.31 280

LGP-MVS_train				94.10 219	96.16 212	88.26 235		97.46 161	91.29 158	90.12 232	97.16 139	79.05 256	98.73 178	92.25 151	91.89 237	95.31 280

test-LLR		91.42 228	91.19 212	92.12 296	94.59 297	80.66 346	94.29 316	92.98 358	91.11 168	90.76 216	92.37 336	79.02 258	98.07 247	88.81 224	96.74 157	97.63 183

test0.0.03 1		89.37 289	88.70 287	91.41 316	92.47 353	85.63 291	95.22 288	92.70 362	91.11 168	86.91 317	93.65 316	79.02 258	93.19 379	78.00 346	89.18 277	95.41 270

ADS-MVSNet2		89.45 287	88.59 289	92.03 298	95.86 223	82.26 333	90.93 368	94.32 342	83.23 344	91.28 210	91.81 348	79.01 260	95.99 348	79.52 336	91.39 247	97.84 174

ADS-MVSNet		89.89 281	88.68 288	93.53 253	95.86 223	84.89 307	90.93 368	95.07 317	83.23 344	91.28 210	91.81 348	79.01 260	97.85 279	79.52 336	91.39 247	97.84 174

ppachtmachnet_test		88.35 301	87.29 300	91.53 312	92.45 354	83.57 323	93.75 333	95.97 272	84.28 330	85.32 331	94.18 296	79.00 262	96.93 336	75.71 356	84.99 322	94.10 336

OpenMVS	89.19 12	92.86 173	91.68 192	96.40 93	95.34 251	92.73 78	98.27 33	98.12 67	84.86 324	85.78 325	97.75 103	78.89 263	99.74 41	87.50 251	98.65 98	96.73 217

LTVRE_ROB	88.41 13	90.99 250	89.92 262	94.19 215	96.18 210	89.55 191	96.31 235	97.09 200	87.88 266	85.67 326	95.91 209	78.79 264	98.57 196	81.50 322	89.98 269	94.44 328
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		91.76 212	90.75 227	94.81 186	97.00 162	88.57 225	96.65 205	96.49 252	89.63 209	92.15 183	96.12 200	78.66 265	98.50 200	90.83 181	79.18 361	97.36 196

pm-mvs1		90.72 261	89.65 274	93.96 229	94.29 309	89.63 186	97.79 90	96.82 230	89.07 225	86.12 324	95.48 236	78.61 266	97.78 286	86.97 262	81.67 350	94.46 326

PVSNet	86.66 18	92.24 198	91.74 190	93.73 242	97.77 120	83.69 322	92.88 353	96.72 234	87.91 265	93.00 166	94.86 258	78.51 267	99.05 151	86.53 265	97.45 139	98.47 135

ACMP	89.59 10	92.62 181	92.14 176	94.05 222	96.40 200	88.20 238	97.36 142	97.25 190	91.52 150	88.30 284	96.64 168	78.46 268	98.72 181	91.86 162	91.48 244	95.23 287
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
BH-RMVSNet		92.72 180	91.97 182	94.97 176	97.16 147	87.99 245	96.15 246	95.60 291	90.62 186	91.87 190	97.15 141	78.41 269	98.57 196	83.16 308	97.60 133	98.36 147

thres200		92.23 199	91.39 201	94.75 193	97.61 131	89.03 215	96.60 213	95.09 316	92.08 139	93.28 161	94.00 302	78.39 270	99.04 154	81.26 328	94.18 201	96.19 230

MDA-MVSNet_test_wron		85.87 326	84.23 330	90.80 327	92.38 356	82.57 328	93.17 346	95.15 313	82.15 350	67.65 382	92.33 342	78.20 271	95.51 360	77.33 348	79.74 357	94.31 333

tfpn200view9		92.38 188	91.52 198	94.95 178	97.85 116	89.29 205	97.41 134	94.88 326	92.19 135	93.27 162	94.46 279	78.17 272	99.08 144	81.40 324	94.08 205	96.48 223

thres400		92.42 186	91.52 198	95.12 166	97.85 116	89.29 205	97.41 134	94.88 326	92.19 135	93.27 162	94.46 279	78.17 272	99.08 144	81.40 324	94.08 205	96.98 208

YYNet1		85.87 326	84.23 330	90.78 328	92.38 356	82.46 331	93.17 346	95.14 314	82.12 351	67.69 381	92.36 339	78.16 274	95.50 361	77.31 349	79.73 358	94.39 329

CL-MVSNet_self_test		86.31 320	85.15 322	89.80 339	88.83 376	81.74 338	93.93 327	96.22 264	86.67 294	85.03 332	90.80 355	78.09 275	94.50 366	74.92 360	71.86 378	93.15 349

thres100view900		92.43 185	91.58 195	94.98 175	97.92 112	89.37 201	97.71 100	94.66 331	92.20 133	93.31 160	94.90 256	78.06 276	99.08 144	81.40 324	94.08 205	96.48 223

thres600view7		92.49 184	91.60 194	95.18 162	97.91 113	89.47 195	97.65 106	94.66 331	92.18 137	93.33 159	94.91 255	78.06 276	99.10 139	81.61 321	94.06 208	96.98 208

tpm cat1		88.36 300	87.21 303	91.81 305	95.13 269	80.55 349	92.58 357	95.70 284	74.97 378	87.45 301	91.96 346	78.01 278	98.17 229	80.39 332	88.74 282	96.72 218

MVP-Stereo		90.74 260	90.08 254	92.71 283	93.19 340	88.20 238	95.86 259	96.27 261	86.07 305	84.86 334	94.76 263	77.84 279	97.75 289	83.88 305	98.01 123	92.17 364
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EPMVS		90.70 262	89.81 266	93.37 259	94.73 292	84.21 313	93.67 337	88.02 385	89.50 214	92.38 177	93.49 320	77.82 280	97.78 286	86.03 277	92.68 224	98.11 163

tfpnnormal		89.70 286	88.40 291	93.60 249	95.15 267	90.10 172	97.56 119	98.16 61	87.28 285	86.16 323	94.63 270	77.57 281	98.05 250	74.48 361	84.59 327	92.65 356

tpm		90.25 272	89.74 271	91.76 309	93.92 317	79.73 359	93.98 323	93.54 354	88.28 255	91.99 188	93.25 325	77.51 282	97.44 316	87.30 255	87.94 288	98.12 160

thisisatest0515		92.29 195	91.30 206	95.25 160	96.60 184	88.90 218	94.36 311	92.32 365	87.92 264	93.43 157	94.57 272	77.28 283	99.00 155	89.42 208	95.86 174	97.86 173

FMVSNet3		91.78 211	90.69 230	95.03 171	96.53 192	92.27 93	97.02 171	96.93 217	89.79 208	89.35 258	94.65 269	77.01 284	97.47 313	86.12 274	88.82 279	95.35 277

dmvs_testset		81.38 342	82.60 338	77.73 366	91.74 360	51.49 399	93.03 351	84.21 394	89.07 225	78.28 371	91.25 353	76.97 285	88.53 389	56.57 389	82.24 349	93.16 348

TR-MVS		91.48 226	90.59 233	94.16 217	96.40 200	87.33 256	95.67 266	95.34 305	87.68 275	91.46 200	95.52 234	76.77 286	98.35 214	82.85 312	93.61 214	96.79 216

FE-MVS		92.05 205	91.05 215	95.08 167	96.83 170	87.93 246	93.91 329	95.70 284	86.30 300	94.15 140	94.97 251	76.59 287	99.21 126	84.10 300	96.86 153	98.09 164

tttt0517		92.96 167	92.33 172	94.87 182	97.11 151	87.16 264	97.97 67	92.09 367	90.63 185	93.88 147	97.01 148	76.50 288	99.06 150	90.29 191	95.45 182	98.38 145

RPSCF		90.75 259	90.86 220	90.42 332	96.84 168	76.29 373	95.61 270	96.34 258	83.89 335	91.38 201	97.87 93	76.45 289	98.78 171	87.16 259	92.23 229	96.20 229

tpm2		89.96 279	89.21 281	92.23 295	94.91 281	81.25 340	93.78 332	94.42 337	80.62 363	91.56 197	93.44 322	76.44 290	97.94 269	85.60 283	92.08 236	97.49 192

thisisatest0530		93.03 164	92.21 175	95.49 151	97.07 153	89.11 214	97.49 130	92.19 366	90.16 197	94.09 141	96.41 186	76.43 291	99.05 151	90.38 188	95.68 179	98.31 149

iter_conf05		93.18 157	92.63 158	94.83 183	96.64 181	90.69 157	97.60 115	95.53 296	92.52 125	91.58 196	96.64 168	76.35 292	98.13 232	95.43 88	91.42 246	95.68 260

EU-MVSNet		88.72 297	88.90 285	88.20 348	93.15 341	74.21 376	96.63 210	94.22 343	85.18 318	87.32 306	95.97 205	76.16 293	94.98 364	85.27 287	86.17 303	95.41 270

Syy-MVS		87.13 312	87.02 307	87.47 351	95.16 265	73.21 379	95.00 292	93.93 349	88.55 248	86.96 313	91.99 344	75.90 294	94.00 372	61.59 385	94.11 202	95.20 288

bld_raw_dy_0_64		92.37 189	91.69 191	94.39 206	94.28 310	89.73 185	97.71 100	93.65 353	92.78 120	90.46 220	96.67 166	75.88 295	97.97 261	92.92 146	90.89 259	95.48 264

dp		88.90 294	88.26 294	90.81 325	94.58 299	76.62 371	92.85 354	94.93 323	85.12 320	90.07 237	93.07 326	75.81 296	98.12 237	80.53 331	87.42 294	97.71 180

IterMVS-SCA-FT		90.31 270	89.81 266	91.82 304	95.52 238	84.20 314	94.30 315	96.15 268	90.61 187	87.39 304	94.27 290	75.80 297	96.44 343	87.34 253	86.88 301	94.82 310

SCA		91.84 210	91.18 213	93.83 237	95.59 234	84.95 306	94.72 297	95.58 293	90.82 173	92.25 181	93.69 312	75.80 297	98.10 239	86.20 271	95.98 170	98.45 137

IterMVS		90.15 277	89.67 272	91.61 311	95.48 240	83.72 320	94.33 313	96.12 269	89.99 201	87.31 307	94.15 298	75.78 299	96.27 346	86.97 262	86.89 300	94.83 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
jajsoiax		92.42 186	91.89 185	94.03 224	93.33 338	88.50 229	97.73 95	97.53 151	92.00 142	88.85 271	96.50 182	75.62 300	98.11 238	93.88 124	91.56 242	95.48 264

cascas		91.20 241	90.08 254	94.58 199	94.97 274	89.16 213	93.65 338	97.59 144	79.90 366	89.40 256	92.92 328	75.36 301	98.36 213	92.14 154	94.75 195	96.23 227

sd_testset		93.10 159	92.45 169	95.05 168	98.09 101	89.21 209	96.89 182	97.64 138	93.18 100	91.79 192	97.28 131	75.35 302	98.65 187	88.99 221	92.84 220	97.28 201

VPNet		92.23 199	91.31 205	94.99 173	95.56 236	90.96 145	97.22 158	97.86 115	92.96 114	90.96 214	96.62 177	75.06 303	98.20 225	91.90 159	83.65 340	95.80 248

WB-MVS		76.77 347	76.63 350	77.18 367	85.32 383	56.82 397	94.53 303	89.39 381	82.66 348	71.35 379	89.18 367	75.03 304	88.88 387	35.42 395	66.79 385	85.84 381

N_pmnet		78.73 346	78.71 347	78.79 365	92.80 346	46.50 402	94.14 320	43.71 404	78.61 371	80.83 358	91.66 350	74.94 305	96.36 344	67.24 380	84.45 330	93.50 344

SSC-MVS		76.05 348	75.83 351	76.72 371	84.77 384	56.22 398	94.32 314	88.96 383	81.82 354	70.52 380	88.91 368	74.79 306	88.71 388	33.69 396	64.71 387	85.23 382

dmvs_re		90.21 274	89.50 276	92.35 289	95.47 243	85.15 301	95.70 265	94.37 339	90.94 172	88.42 280	93.57 318	74.63 307	95.67 356	82.80 313	89.57 274	96.22 228

mvs_tets		92.31 193	91.76 187	93.94 232	93.41 335	88.29 233	97.63 112	97.53 151	92.04 140	88.76 274	96.45 184	74.62 308	98.09 242	93.91 122	91.48 244	95.45 269

DSMNet-mixed		86.34 319	86.12 315	87.00 355	89.88 370	70.43 381	94.93 294	90.08 379	77.97 374	85.42 330	92.78 329	74.44 309	93.96 374	74.43 362	95.14 186	96.62 219

pmmvs5		89.86 283	88.87 286	92.82 279	92.86 344	86.23 284	96.26 238	95.39 299	84.24 331	87.12 308	94.51 274	74.27 310	97.36 322	87.61 249	87.57 291	94.86 306

OurMVSNet-221017-0		90.51 267	90.19 252	91.44 315	93.41 335	81.25 340	96.98 176	96.28 260	91.68 148	86.55 320	96.30 191	74.20 311	97.98 258	88.96 222	87.40 295	95.09 292

GBi-Net		91.35 233	90.27 245	94.59 195	96.51 193	91.18 137	97.50 125	96.93 217	88.82 238	89.35 258	94.51 274	73.87 312	97.29 325	86.12 274	88.82 279	95.31 280

test1		91.35 233	90.27 245	94.59 195	96.51 193	91.18 137	97.50 125	96.93 217	88.82 238	89.35 258	94.51 274	73.87 312	97.29 325	86.12 274	88.82 279	95.31 280

FMVSNet2		91.31 236	90.08 254	94.99 173	96.51 193	92.21 94	97.41 134	96.95 215	88.82 238	88.62 276	94.75 264	73.87 312	97.42 318	85.20 289	88.55 284	95.35 277

COLMAP_ROB	87.81 15	90.40 269	89.28 280	93.79 240	97.95 109	87.13 265	96.92 180	95.89 277	82.83 346	86.88 318	97.18 138	73.77 315	99.29 121	78.44 344	93.62 213	94.95 297
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_cas_vis1_n_1920		94.48 107	94.55 100	94.28 213	96.78 173	86.45 279	97.63 112	97.64 138	93.32 94	97.68 38	98.36 50	73.75 316	99.08 144	96.73 39	99.05 83	97.31 200

Anonymous20231206		87.09 313	86.14 314	89.93 338	91.22 362	80.35 351	96.11 247	95.35 302	83.57 341	84.16 340	93.02 327	73.54 317	95.61 357	72.16 371	86.14 304	93.84 341

UGNet		94.04 123	93.28 135	96.31 100	96.85 167	91.19 136	97.88 78	97.68 133	94.40 56	93.00 166	96.18 196	73.39 318	99.61 69	91.72 165	98.46 108	98.13 159
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		93.19 154	92.82 149	94.30 212	97.58 136	84.56 310	98.21 43	89.02 382	93.53 84	94.58 130	98.21 67	72.69 319	99.05 151	93.06 140	98.48 107	99.28 65

ECVR-MVS		93.19 154	92.73 155	94.57 200	97.66 126	85.41 295	98.21 43	88.23 384	93.43 89	94.70 128	98.21 67	72.57 320	99.07 148	93.05 141	98.49 105	99.25 68

Anonymous20231211		90.63 264	89.42 277	94.27 214	98.24 87	89.19 212	98.05 54	97.89 107	79.95 365	88.25 287	94.96 252	72.56 321	98.13 232	89.70 201	85.14 317	95.49 263

ACMH	87.59 16	90.53 266	89.42 277	93.87 236	96.21 207	87.92 247	97.24 153	96.94 216	88.45 251	83.91 346	96.27 193	71.92 322	98.62 191	84.43 297	89.43 275	95.05 295
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		91.38 230	90.31 242	94.59 195	94.65 295	87.62 254	94.34 312	96.19 267	90.73 177	90.35 223	93.83 306	71.84 323	97.96 266	87.22 256	93.61 214	98.21 154

SixPastTwentyTwo		89.15 290	88.54 290	90.98 322	93.49 332	80.28 354	96.70 199	94.70 330	90.78 174	84.15 341	95.57 230	71.78 324	97.71 292	84.63 295	85.07 319	94.94 299

gg-mvs-nofinetune		87.82 305	85.61 317	94.44 203	94.46 301	89.27 208	91.21 367	84.61 393	80.88 359	89.89 242	74.98 387	71.50 325	97.53 308	85.75 282	97.21 148	96.51 221

test20.03		86.14 323	85.40 320	88.35 346	90.12 367	80.06 356	95.90 258	95.20 311	88.59 244	81.29 357	93.62 317	71.43 326	92.65 380	71.26 375	81.17 353	92.34 360

MS-PatchMatch		90.27 271	89.77 268	91.78 307	94.33 306	84.72 309	95.55 271	96.73 233	86.17 304	86.36 321	95.28 242	71.28 327	97.80 284	84.09 301	98.14 121	92.81 353

PVSNet_0	82.17 19	85.46 329	83.64 332	90.92 323	95.27 258	79.49 362	90.55 371	95.60 291	83.76 338	83.00 352	89.95 361	71.09 328	97.97 261	82.75 315	60.79 391	95.31 280

GG-mvs-BLEND				93.62 248	93.69 325	89.20 210	92.39 360	83.33 395		87.98 294	89.84 363	71.00 329	96.87 338	82.08 320	95.40 183	94.80 313

ITE_SJBPF				92.43 288	95.34 251	85.37 298		95.92 273	91.47 152	87.75 297	96.39 188	71.00 329	97.96 266	82.36 318	89.86 271	93.97 339

IB-MVS	87.33 17	89.91 280	88.28 293	94.79 190	95.26 261	87.70 253	95.12 291	93.95 348	89.35 219	87.03 311	92.49 334	70.74 331	99.19 128	89.18 218	81.37 352	97.49 192
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		85.00 330	82.95 335	91.17 321	93.13 342	83.33 324	94.56 302	95.00 319	84.57 328	65.13 386	92.65 330	70.45 332	95.85 351	73.57 367	77.49 365	94.33 331

AllTest		90.23 273	88.98 284	93.98 226	97.94 110	86.64 274	96.51 218	95.54 294	85.38 314	85.49 328	96.77 158	70.28 333	99.15 133	80.02 334	92.87 218	96.15 233

TestCases				93.98 226	97.94 110	86.64 274		95.54 294	85.38 314	85.49 328	96.77 158	70.28 333	99.15 133	80.02 334	92.87 218	96.15 233

ACMH+	87.92 14	90.20 275	89.18 282	93.25 263	96.48 196	86.45 279	96.99 175	96.68 239	88.83 237	84.79 335	96.22 195	70.16 335	98.53 198	84.42 298	88.04 287	94.77 318

test_vis1_n_1920		94.17 113	94.58 96	92.91 275	97.42 140	82.02 335	97.83 84	97.85 116	94.68 46	98.10 29	98.49 38	70.15 336	99.32 117	97.91 15	98.82 92	97.40 195

KD-MVS_self_test		85.95 325	84.95 324	88.96 345	89.55 373	79.11 366	95.13 290	96.42 255	85.91 307	84.07 344	90.48 356	70.03 337	94.82 365	80.04 333	72.94 376	92.94 351

Anonymous20240529		91.98 207	90.73 228	95.73 136	98.14 99	89.40 199	97.99 60	97.72 128	79.63 367	93.54 153	97.41 127	69.94 338	99.56 85	91.04 180	91.11 253	98.22 153

pmmvs-eth3d		86.22 321	84.45 328	91.53 312	88.34 378	87.25 259	94.47 305	95.01 318	83.47 342	79.51 367	89.61 364	69.75 339	95.71 354	83.13 309	76.73 369	91.64 365

test_fmvs1		93.21 152	93.53 122	92.25 294	96.55 191	81.20 342	97.40 138	96.96 214	90.68 180	96.80 61	98.04 79	69.25 340	98.40 207	97.58 21	98.50 104	97.16 205

LFMVS		93.60 138	92.63 158	96.52 80	98.13 100	91.27 130	97.94 71	93.39 356	90.57 190	96.29 86	98.31 60	69.00 341	99.16 132	94.18 116	95.87 173	99.12 80

TESTMET0.1,1		90.06 278	89.42 277	91.97 299	94.41 304	80.62 348	94.29 316	91.97 369	87.28 285	90.44 221	92.47 335	68.79 342	97.67 294	88.50 230	96.60 162	97.61 187

XVG-ACMP-BASELINE		90.93 254	90.21 251	93.09 269	94.31 308	85.89 288	95.33 280	97.26 188	91.06 170	89.38 257	95.44 237	68.61 343	98.60 192	89.46 207	91.05 254	94.79 315

MVS-HIRNet		82.47 340	81.21 343	86.26 357	95.38 246	69.21 384	88.96 380	89.49 380	66.28 384	80.79 359	74.08 389	68.48 344	97.39 320	71.93 372	95.47 181	92.18 363

VDD-MVS		93.82 132	93.08 139	96.02 121	97.88 115	89.96 180	97.72 98	95.85 278	92.43 127	95.86 102	98.44 44	68.42 345	99.39 111	96.31 49	94.85 191	98.71 118

test_0402		86.46 317	84.79 326	91.45 314	95.02 273	85.55 292	96.29 237	94.89 325	80.90 358	82.21 354	93.97 304	68.21 346	97.29 325	62.98 383	88.68 283	91.51 368

test-mter		90.19 276	89.54 275	92.12 296	94.59 297	80.66 346	94.29 316	92.98 358	87.68 275	90.76 216	92.37 336	67.67 347	98.07 247	88.81 224	96.74 157	97.63 183

VDDNet		93.05 163	92.07 177	96.02 121	96.84 168	90.39 168	98.08 51	95.85 278	86.22 303	95.79 105	98.46 42	67.59 348	99.19 128	94.92 99	94.85 191	98.47 135

USDC		88.94 292	87.83 297	92.27 293	94.66 294	84.96 305	93.86 330	95.90 275	87.34 283	83.40 348	95.56 231	67.43 349	98.19 227	82.64 317	89.67 273	93.66 342

pmmvs6		87.81 306	86.19 313	92.69 284	91.32 361	86.30 282	97.34 144	96.41 256	80.59 364	84.05 345	94.37 283	67.37 350	97.67 294	84.75 293	79.51 360	94.09 338

test2506		91.60 217	90.78 225	94.04 223	97.66 126	83.81 318	98.27 33	75.53 399	93.43 89	95.23 119	98.21 67	67.21 351	99.07 148	93.01 144	98.49 105	99.25 68

KD-MVS_2432*1600		84.81 332	82.64 336	91.31 317	91.07 363	85.34 299	91.22 365	95.75 282	85.56 312	83.09 350	90.21 359	67.21 351	95.89 349	77.18 351	62.48 389	92.69 354

miper_refine_blended		84.81 332	82.64 336	91.31 317	91.07 363	85.34 299	91.22 365	95.75 282	85.56 312	83.09 350	90.21 359	67.21 351	95.89 349	77.18 351	62.48 389	92.69 354

K. test v3		87.64 308	86.75 310	90.32 333	93.02 343	79.48 363	96.61 211	92.08 368	90.66 183	80.25 364	94.09 299	67.21 351	96.65 342	85.96 279	80.83 354	94.83 308

tt0805		91.09 245	90.07 257	94.16 217	95.61 233	88.31 232	97.56 119	96.51 251	89.56 211	89.17 265	95.64 227	67.08 355	98.38 212	91.07 179	88.44 285	95.80 248

CMPMVS	62.92 21	85.62 328	84.92 325	87.74 350	89.14 374	73.12 380	94.17 319	96.80 231	73.98 379	73.65 378	94.93 254	66.36 356	97.61 301	83.95 304	91.28 249	92.48 359
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UniMVSNet_ETH3D		91.34 235	90.22 250	94.68 194	94.86 284	87.86 250	97.23 157	97.46 161	87.99 262	89.90 240	96.92 153	66.35 357	98.23 222	90.30 190	90.99 256	97.96 167

lessismore_v0				90.45 331	91.96 359	79.09 367		87.19 388		80.32 363	94.39 281	66.31 358	97.55 305	84.00 303	76.84 367	94.70 320

Anonymous202405211		92.07 204	90.83 224	95.76 131	98.19 95	88.75 220	97.58 117	95.00 319	86.00 306	93.64 150	97.45 124	66.24 359	99.53 91	90.68 186	92.71 223	99.01 89

new-patchmatchnet		83.18 338	81.87 341	87.11 353	86.88 381	75.99 374	93.70 334	95.18 312	85.02 322	77.30 373	88.40 371	65.99 360	93.88 375	74.19 365	70.18 380	91.47 370

FMVSNet1		89.88 282	88.31 292	94.59 195	95.41 244	91.18 137	97.50 125	96.93 217	86.62 295	87.41 303	94.51 274	65.94 361	97.29 325	83.04 310	87.43 293	95.31 280

TDRefinement		86.53 316	84.76 327	91.85 302	82.23 389	84.25 312	96.38 229	95.35 302	84.97 323	84.09 343	94.94 253	65.76 362	98.34 217	84.60 296	74.52 372	92.97 350

UnsupCasMVSNet_eth		85.99 324	84.45 328	90.62 329	89.97 369	82.40 332	93.62 339	97.37 179	89.86 203	78.59 370	92.37 336	65.25 363	95.35 363	82.27 319	70.75 379	94.10 336

LF4IMVS		87.94 304	87.25 301	89.98 337	92.38 356	80.05 357	94.38 310	95.25 309	87.59 277	84.34 337	94.74 265	64.31 364	97.66 296	84.83 291	87.45 292	92.23 361

Anonymous20240521		86.42 318	85.44 318	89.34 343	90.33 366	79.79 358	96.73 195	95.92 273	83.71 339	83.25 349	91.36 352	63.92 365	96.01 347	78.39 345	85.36 313	92.22 362

MIMVSNet		88.50 299	86.76 309	93.72 244	94.84 285	87.77 252	91.39 363	94.05 345	86.41 299	87.99 293	92.59 333	63.27 366	95.82 353	77.44 347	92.84 220	97.57 190

test_fmvs1_n		92.73 179	92.88 146	92.29 292	96.08 220	81.05 343	97.98 61	97.08 201	90.72 178	96.79 62	98.18 70	63.07 367	98.45 204	97.62 20	98.42 110	97.36 196

FMVSNet5		87.29 310	85.79 316	91.78 307	94.80 287	87.28 257	95.49 274	95.28 306	84.09 333	83.85 347	91.82 347	62.95 368	94.17 370	78.48 343	85.34 314	93.91 340

testgi		87.97 303	87.21 303	90.24 334	92.86 344	80.76 344	96.67 204	94.97 321	91.74 146	85.52 327	95.83 213	62.66 369	94.47 368	76.25 354	88.36 286	95.48 264

TinyColmap		86.82 315	85.35 321	91.21 319	94.91 281	82.99 326	93.94 326	94.02 347	83.58 340	81.56 356	94.68 267	62.34 370	98.13 232	75.78 355	87.35 296	92.52 358

new_pmnet		82.89 339	81.12 344	88.18 349	89.63 371	80.18 355	91.77 362	92.57 363	76.79 377	75.56 376	88.23 373	61.22 371	94.48 367	71.43 373	82.92 346	89.87 377

OpenMVS_ROB	81.14 20	84.42 334	82.28 340	90.83 324	90.06 368	84.05 317	95.73 264	94.04 346	73.89 380	80.17 365	91.53 351	59.15 372	97.64 297	66.92 381	89.05 278	90.80 374

test_fmvs2		89.77 285	89.93 261	89.31 344	93.68 326	76.37 372	97.64 110	95.90 275	89.84 206	91.49 199	96.26 194	58.77 373	97.10 329	94.65 108	91.13 252	94.46 326

test_vis1_n		92.37 189	92.26 174	92.72 282	94.75 290	82.64 327	98.02 56	96.80 231	91.18 165	97.77 37	97.93 88	58.02 374	98.29 219	97.63 19	98.21 117	97.23 204

MIMVSNet1		84.93 331	83.05 333	90.56 330	89.56 372	84.84 308	95.40 277	95.35 302	83.91 334	80.38 362	92.21 343	57.23 375	93.34 378	70.69 377	82.75 348	93.50 344

EG-PatchMatch MVS		87.02 314	85.44 318	91.76 309	92.67 348	85.00 304	96.08 249	96.45 254	83.41 343	79.52 366	93.49 320	57.10 376	97.72 291	79.34 341	90.87 260	92.56 357

UnsupCasMVSNet_bld		82.13 341	79.46 346	90.14 335	88.00 379	82.47 330	90.89 370	96.62 247	78.94 370	75.61 374	84.40 383	56.63 377	96.31 345	77.30 350	66.77 386	91.63 366

myMVS_eth3d		87.18 311	86.38 311	89.58 341	95.16 265	79.53 360	95.00 292	93.93 349	88.55 248	86.96 313	91.99 344	56.23 378	94.00 372	75.47 359	94.11 202	95.20 288

testing3		87.67 307	86.88 308	90.05 336	96.14 215	80.71 345	97.10 167	92.85 360	90.15 198	87.54 300	94.55 273	55.70 379	94.10 371	73.77 366	94.10 204	95.35 277

EGC-MVSNET		68.77 355	63.01 360	86.07 358	92.49 352	82.24 334	93.96 325	90.96 376	0.71 401	2.62 402	90.89 354	53.66 380	93.46 376	57.25 388	84.55 328	82.51 384

tmp_tt		51.94 363	53.82 363	46.29 380	33.73 403	45.30 404	78.32 390	67.24 403	18.02 397	50.93 393	87.05 380	52.99 381	53.11 399	70.76 376	25.29 397	40.46 395

test_vis1_rt		86.16 322	85.06 323	89.46 342	93.47 334	80.46 350	96.41 223	86.61 390	85.22 317	79.15 368	88.64 369	52.41 382	97.06 330	93.08 139	90.57 262	90.87 373

pmmvs3		79.97 344	77.50 349	87.39 352	82.80 388	79.38 364	92.70 356	90.75 378	70.69 382	78.66 369	87.47 379	51.34 383	93.40 377	73.39 368	69.65 381	89.38 378

DeepMVS_CX				74.68 374	90.84 365	64.34 392		81.61 397	65.34 385	67.47 383	88.01 376	48.60 384	80.13 395	62.33 384	73.68 375	79.58 386

mvsany_test3		83.59 335	82.44 339	87.03 354	83.80 385	73.82 377	93.70 334	90.92 377	86.42 298	82.51 353	90.26 358	46.76 385	95.71 354	90.82 182	76.76 368	91.57 367

PM-MVS		83.48 336	81.86 342	88.31 347	87.83 380	77.59 370	93.43 342	91.75 370	86.91 290	80.63 360	89.91 362	44.42 386	95.84 352	85.17 290	76.73 369	91.50 369

test_method		66.11 357	64.89 359	69.79 375	72.62 397	35.23 406	65.19 393	92.83 361	20.35 396	65.20 385	88.08 375	43.14 387	82.70 393	73.12 369	63.46 388	91.45 371

APD_test1		79.31 345	77.70 348	84.14 359	89.11 375	69.07 385	92.36 361	91.50 372	69.07 383	73.87 377	92.63 332	39.93 388	94.32 369	70.54 378	80.25 356	89.02 379

ambc				86.56 356	83.60 386	70.00 383	85.69 385	94.97 321		80.60 361	88.45 370	37.42 389	96.84 339	82.69 316	75.44 371	92.86 352

test_fmvs3		83.21 337	83.02 334	83.78 360	86.77 382	68.34 386	96.76 193	94.91 324	86.49 297	84.14 342	89.48 365	36.04 390	91.73 382	91.86 162	80.77 355	91.26 372

test_f		80.57 343	79.62 345	83.41 361	83.38 387	67.80 388	93.57 341	93.72 351	80.80 362	77.91 372	87.63 377	33.40 391	92.08 381	87.14 260	79.04 363	90.34 376

Gipuma		67.86 356	65.41 358	75.18 373	92.66 349	73.45 378	66.50 392	94.52 335	53.33 391	57.80 392	66.07 392	30.81 392	89.20 386	48.15 392	78.88 364	62.90 392
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		52.08 362	51.31 365	54.39 379	72.62 397	45.39 403	83.84 387	75.51 400	41.13 394	40.77 396	59.65 395	30.08 393	73.60 397	28.31 398	29.90 396	44.18 394

FPMVS		71.27 351	69.85 353	75.50 372	74.64 394	59.03 395	91.30 364	91.50 372	58.80 387	57.92 391	88.28 372	29.98 394	85.53 392	53.43 390	82.84 347	81.95 385

E-PMN		53.28 360	52.56 364	55.43 378	74.43 395	47.13 401	83.63 388	76.30 398	42.23 393	42.59 395	62.22 394	28.57 395	74.40 396	31.53 397	31.51 394	44.78 393

PMMVS2		70.19 352	66.92 355	80.01 363	76.35 393	65.67 390	86.22 384	87.58 387	64.83 386	62.38 387	80.29 386	26.78 396	88.49 390	63.79 382	54.07 392	85.88 380

ANet_high		63.94 358	59.58 361	77.02 368	61.24 401	66.06 389	85.66 386	87.93 386	78.53 372	42.94 394	71.04 391	25.42 397	80.71 394	52.60 391	30.83 395	84.28 383

LCM-MVSNet		72.55 350	69.39 354	82.03 362	70.81 399	65.42 391	90.12 375	94.36 341	55.02 390	65.88 384	81.72 384	24.16 398	89.96 383	74.32 364	68.10 384	90.71 375

test_vis3_rt		72.73 349	70.55 352	79.27 364	80.02 390	68.13 387	93.92 328	74.30 401	76.90 376	58.99 390	73.58 390	20.29 399	95.37 362	84.16 299	72.80 377	74.31 389

testf1		69.31 353	66.76 356	76.94 369	78.61 391	61.93 393	88.27 381	86.11 391	55.62 388	59.69 388	85.31 381	20.19 400	89.32 384	57.62 386	69.44 382	79.58 386

APD_test2		69.31 353	66.76 356	76.94 369	78.61 391	61.93 393	88.27 381	86.11 391	55.62 388	59.69 388	85.31 381	20.19 400	89.32 384	57.62 386	69.44 382	79.58 386

PMVS	53.92 22	58.58 359	55.40 362	68.12 376	51.00 402	48.64 400	78.86 389	87.10 389	46.77 392	35.84 398	74.28 388	8.76 402	86.34 391	42.07 393	73.91 374	69.38 390
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		25.11 364	24.57 368	26.74 381	73.98 396	39.89 405	57.88 394	9.80 405	12.27 398	10.39 399	6.97 401	7.03 403	36.44 400	25.43 399	17.39 398	3.89 398

MVE	50.73 23	53.25 361	48.81 366	66.58 377	65.34 400	57.50 396	72.49 391	70.94 402	40.15 395	39.28 397	63.51 393	6.89 404	73.48 398	38.29 394	42.38 393	68.76 391
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test123		13.04 367	15.66 370	5.18 382	4.51 405	3.45 407	92.50 359	1.81 407	2.50 400	7.58 401	20.15 398	3.67 405	2.18 402	7.13 401	1.07 400	9.90 396

testmvs		13.36 366	16.33 369	4.48 383	5.04 404	2.26 408	93.18 345	3.28 406	2.70 399	8.24 400	21.66 397	2.29 406	2.19 401	7.58 400	2.96 399	9.00 397

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

ab-mvs-re		8.06 368	10.74 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	96.69 164	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						79.53 360								75.56 358

FOURS1					99.55 1	93.34 64	99.29 1	98.35 27	94.98 29	98.49 23

MSC_two_6792asdad				98.86 1	98.67 58	96.94 1		97.93 105					99.86 8	97.68 16	99.67 6	99.77 2

No_MVS				98.86 1	98.67 58	96.94 1		97.93 105					99.86 8	97.68 16	99.67 6	99.77 2

eth-test2					0.00 406

eth-test					0.00 406

IU-MVS					99.42 7	95.39 11		97.94 104	90.40 194	98.94 8				97.41 29	99.66 10	99.74 8

save fliter					98.91 49	94.28 36	97.02 171	98.02 94	95.35 16

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 36					99.86 8	97.52 22	99.67 6	99.75 6

GSMVS																98.45 137

test_part2					99.28 25	95.74 8				98.10 29

MTGPA								98.08 74

MTMP							97.86 79	82.03 396

gm-plane-assit					93.22 339	78.89 368			84.82 325		93.52 319		98.64 188	87.72 239

test9_res														94.81 103	99.38 53	99.45 47

agg_prior2														93.94 121	99.38 53	99.50 40

agg_prior					98.67 58	93.79 52		98.00 98		95.68 109			99.57 84

test_prior4						93.66 55	96.42 222

test_prior				97.23 58	98.67 58	92.99 71		98.00 98					99.41 109			99.29 63

旧先验2							95.94 256		81.66 355	97.34 48			98.82 168	92.26 149

新几何2							95.79 262

无先验							95.79 262	97.87 111	83.87 337				99.65 58	87.68 245		98.89 105

原ACMM2							95.67 266

testdata2													99.67 56	85.96 279

testdata1							95.26 287		93.10 105

plane_prior7					96.21 207	89.98 178

plane_prior5								97.51 153					98.60 192	93.02 142	92.23 229	95.86 241

plane_prior4											96.64 168

plane_prior3						90.00 174			94.46 54	91.34 203

plane_prior2							97.74 93		94.85 34

plane_prior1					96.14 215

plane_prior						89.99 176	97.24 153		94.06 65						92.16 233

n2								0.00 408

nn								0.00 408

door-mid								91.06 375

test11								97.88 109

door								91.13 374

HQP5-MVS						89.33 203

HQP-NCC					95.86 223		96.65 205		93.55 80	90.14 226

ACMP_Plane					95.86 223		96.65 205		93.55 80	90.14 226

BP-MVS														92.13 155

HQP4-MVS										90.14 226			98.50 200			95.78 250

HQP3-MVS								97.39 176							92.10 234

NP-MVS					95.99 222	89.81 183					95.87 210

ACMMP++_ref															90.30 267

ACMMP++															91.02 255

High-resolution multi-view benchmark