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.

DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 54	86.00 50	98.29 1	97.49 6	90.75 21	97.62 5	98.06 16	92.59 2	99.61 4	95.64 25	99.02 12	98.86 11

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 52	97.13 14	97.44 15	90.31 32	97.71 1	98.07 14	92.31 4	99.58 10	95.66 23	99.13 3	98.84 14

DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 55	97.09 16	96.73 86	90.27 36	97.04 14	98.05 18	91.47 8	99.55 16	95.62 27	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
DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 25	87.28 18	95.56 105	97.51 5	89.13 76	97.14 10	97.91 25	91.64 7	99.62 2	94.61 39	99.17 2	98.86 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 28	86.29 46	97.46 6	97.40 20	89.03 81	96.20 25	98.10 10	89.39 16	99.34 37	95.88 22	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 25	97.47 11	91.73 11	96.10 26	96.69 75	89.90 12	99.30 43	94.70 37	98.04 71	99.13 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
CNVR-MVS		95.40 7	95.37 7	95.50 8	98.11 36	88.51 7	95.29 115	96.96 58	92.09 7	95.32 38	97.08 58	89.49 15	99.33 40	95.10 34	98.85 20	98.66 21

SMA-MVS		95.20 8	95.07 12	95.59 6	98.14 35	88.48 8	96.26 46	97.28 32	85.90 171	97.67 3	98.10 10	88.41 20	99.56 12	94.66 38	99.19 1	98.71 20
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
SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 25	96.99 75	86.33 42	97.33 7	97.30 30	91.38 13	95.39 37	97.46 38	88.98 19	99.40 30	94.12 43	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		95.14 10	94.91 18	95.83 4	98.25 29	89.65 4	95.92 78	96.96 58	91.75 10	94.02 59	96.83 70	88.12 24	99.55 16	93.41 54	98.94 16	98.28 55

MM		95.10 11	94.91 18	95.68 5	96.09 107	88.34 9	96.68 33	94.37 250	95.08 1	94.68 46	97.72 32	82.94 92	99.64 1	97.85 2	98.76 29	99.06 7

SF-MVS		94.97 12	94.90 20	95.20 12	97.84 50	87.76 10	96.65 34	97.48 10	87.76 127	95.71 33	97.70 33	88.28 23	99.35 36	93.89 47	98.78 26	98.48 30

SD-MVS		94.96 13	95.33 8	93.88 63	97.25 72	86.69 28	96.19 49	97.11 48	90.42 29	96.95 16	97.27 46	89.53 14	96.91 268	94.38 41	98.85 20	98.03 78
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
TSAR-MVS + MP.		94.85 14	94.94 16	94.58 42	98.25 29	86.33 42	96.11 59	96.62 95	88.14 111	96.10 26	96.96 64	89.09 18	98.94 83	94.48 40	98.68 37	98.48 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
reproduce-ours		94.82 15	94.97 14	94.38 50	97.91 47	85.46 68	95.86 81	97.15 43	89.82 48	95.23 41	98.10 10	87.09 37	99.37 33	95.30 31	98.25 60	98.30 50

our_new_method		94.82 15	94.97 14	94.38 50	97.91 47	85.46 68	95.86 81	97.15 43	89.82 48	95.23 41	98.10 10	87.09 37	99.37 33	95.30 31	98.25 60	98.30 50

NCCC		94.81 17	94.69 23	95.17 14	97.83 51	87.46 17	95.66 96	96.93 62	92.34 5	93.94 60	96.58 85	87.74 27	99.44 29	92.83 63	98.40 54	98.62 22

fmvsm_l_conf0.5_n_3		94.80 18	95.01 13	94.15 57	95.64 130	85.08 75	96.09 60	97.36 22	90.98 16	97.09 12	98.12 7	84.98 67	98.94 83	97.07 12	97.80 79	98.43 38

reproduce_model		94.76 19	94.92 17	94.29 54	97.92 43	85.18 74	95.95 76	97.19 36	89.67 58	95.27 40	98.16 3	86.53 43	99.36 35	95.42 30	98.15 64	98.33 45

ACMMP_NAP		94.74 20	94.56 24	95.28 10	98.02 41	87.70 11	95.68 93	97.34 24	88.28 105	95.30 39	97.67 34	85.90 50	99.54 20	93.91 46	98.95 15	98.60 23

test_fmvsm_n_1920		94.71 21	95.11 11	93.50 77	95.79 121	84.62 85	96.15 54	97.64 2	89.85 47	97.19 9	97.89 26	86.28 46	98.71 108	97.11 11	98.08 70	97.17 123

test_fmvsmconf_n		94.60 22	94.81 21	93.98 59	94.62 185	84.96 78	96.15 54	97.35 23	89.37 67	96.03 29	98.11 8	86.36 44	99.01 66	97.45 7	97.83 78	97.96 81

HFP-MVS		94.52 23	94.40 28	94.86 24	98.61 10	86.81 25	96.94 20	97.34 24	88.63 93	93.65 65	97.21 50	86.10 48	99.49 26	92.35 76	98.77 28	98.30 50

fmvsm_s_conf0.5_n_3		94.49 24	95.13 10	92.56 122	95.49 138	81.10 196	95.93 77	97.16 42	92.96 2	97.39 7	98.13 4	83.63 81	98.80 98	97.89 1	97.61 86	97.78 95

ZNCC-MVS		94.47 25	94.28 35	95.03 16	98.52 15	86.96 20	96.85 28	97.32 28	88.24 106	93.15 75	97.04 61	86.17 47	99.62 2	92.40 73	98.81 23	98.52 26

XVS		94.45 26	94.32 31	94.85 25	98.54 13	86.60 34	96.93 22	97.19 36	90.66 26	92.85 83	97.16 56	85.02 63	99.49 26	91.99 90	98.56 50	98.47 33

MCST-MVS		94.45 26	94.20 41	95.19 13	98.46 19	87.50 16	95.00 136	97.12 46	87.13 140	92.51 98	96.30 92	89.24 17	99.34 37	93.46 51	98.62 46	98.73 18

region2R		94.43 28	94.27 37	94.92 20	98.65 8	86.67 30	96.92 24	97.23 35	88.60 96	93.58 67	97.27 46	85.22 58	99.54 20	92.21 80	98.74 31	98.56 25

ACMMPR		94.43 28	94.28 35	94.91 21	98.63 9	86.69 28	96.94 20	97.32 28	88.63 93	93.53 70	97.26 48	85.04 62	99.54 20	92.35 76	98.78 26	98.50 27

MTAPA		94.42 30	94.22 38	95.00 18	98.42 21	86.95 21	94.36 183	96.97 55	91.07 14	93.14 76	97.56 35	84.30 74	99.56 12	93.43 52	98.75 30	98.47 33

CP-MVS		94.34 31	94.21 40	94.74 37	98.39 23	86.64 32	97.60 4	97.24 33	88.53 98	92.73 91	97.23 49	85.20 59	99.32 41	92.15 83	98.83 22	98.25 62

fmvsm_l_conf0.5_n		94.29 32	94.46 26	93.79 69	95.28 145	85.43 70	95.68 93	96.43 108	86.56 155	96.84 18	97.81 30	87.56 32	98.77 102	97.14 10	96.82 105	97.16 127

MP-MVS		94.25 33	94.07 46	94.77 35	98.47 18	86.31 44	96.71 31	96.98 54	89.04 79	91.98 108	97.19 53	85.43 56	99.56 12	92.06 89	98.79 24	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APD-MVS		94.24 34	94.07 46	94.75 36	98.06 39	86.90 23	95.88 80	96.94 61	85.68 177	95.05 44	97.18 54	87.31 35	99.07 56	91.90 96	98.61 48	98.28 55
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SR-MVS		94.23 35	94.17 44	94.43 47	98.21 32	85.78 63	96.40 38	96.90 65	88.20 109	94.33 50	97.40 41	84.75 70	99.03 61	93.35 55	97.99 72	98.48 30

GST-MVS		94.21 36	93.97 50	94.90 23	98.41 22	86.82 24	96.54 36	97.19 36	88.24 106	93.26 72	96.83 70	85.48 55	99.59 8	91.43 104	98.40 54	98.30 50

MP-MVS-pluss		94.21 36	94.00 49	94.85 25	98.17 33	86.65 31	94.82 148	97.17 41	86.26 163	92.83 85	97.87 27	85.57 54	99.56 12	94.37 42	98.92 17	98.34 43
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_l_conf0.5_n_a		94.20 38	94.40 28	93.60 75	95.29 144	84.98 77	95.61 101	96.28 121	86.31 161	96.75 20	97.86 28	87.40 33	98.74 105	97.07 12	97.02 98	97.07 130

test_fmvsmconf0.1_n		94.20 38	94.31 33	93.88 63	92.46 275	84.80 81	96.18 51	96.82 74	89.29 70	95.68 34	98.11 8	85.10 60	98.99 73	97.38 8	97.75 83	97.86 89

DeepPCF-MVS	89.96 1	94.20 38	94.77 22	92.49 126	96.52 91	80.00 231	94.00 208	97.08 49	90.05 40	95.65 35	97.29 45	89.66 13	98.97 78	93.95 45	98.71 32	98.50 27

MVS_0304		94.18 41	93.80 54	95.34 9	94.91 168	87.62 14	95.97 73	93.01 291	92.58 4	94.22 51	97.20 52	80.56 122	99.59 8	97.04 14	98.68 37	98.81 17

CS-MVS		94.12 42	94.44 27	93.17 86	96.55 88	83.08 139	97.63 3	96.95 60	91.71 12	93.50 71	96.21 95	85.61 52	98.24 152	93.64 49	98.17 62	98.19 65

DeepC-MVS_fast	89.43 2	94.04 43	93.79 55	94.80 33	97.48 64	86.78 26	95.65 98	96.89 66	89.40 66	92.81 86	96.97 63	85.37 57	99.24 46	90.87 113	98.69 35	98.38 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SPE-MVS-test		94.02 44	94.29 34	93.24 83	96.69 81	83.24 129	97.49 5	96.92 63	92.14 6	92.90 81	95.77 119	85.02 63	98.33 147	93.03 60	98.62 46	98.13 69

HPM-MVS		94.02 44	93.88 51	94.43 47	98.39 23	85.78 63	97.25 10	97.07 50	86.90 148	92.62 95	96.80 74	84.85 69	99.17 50	92.43 71	98.65 44	98.33 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		93.99 46	93.78 56	94.63 40	98.50 16	85.90 60	96.87 26	96.91 64	88.70 91	91.83 117	97.17 55	83.96 78	99.55 16	91.44 103	98.64 45	98.43 38

balanced_conf03		93.98 47	94.22 38	93.26 82	96.13 101	83.29 128	96.27 45	96.52 103	89.82 48	95.56 36	95.51 128	84.50 72	98.79 100	94.83 36	98.86 19	97.72 98

fmvsm_s_conf0.5_n_5		93.96 48	94.18 43	93.30 79	94.79 175	83.81 111	95.77 88	96.74 85	88.02 114	96.23 24	97.84 29	83.36 86	98.83 96	97.49 5	97.34 92	97.25 118

PGM-MVS		93.96 48	93.72 59	94.68 38	98.43 20	86.22 47	95.30 113	97.78 1	87.45 134	93.26 72	97.33 44	84.62 71	99.51 24	90.75 115	98.57 49	98.32 49

PHI-MVS		93.89 50	93.65 63	94.62 41	96.84 78	86.43 39	96.69 32	97.49 6	85.15 190	93.56 69	96.28 93	85.60 53	99.31 42	92.45 70	98.79 24	98.12 72

fmvsm_s_conf0.5_n_4		93.86 51	94.37 30	92.33 136	95.13 156	80.95 201	95.64 99	96.97 55	89.60 60	96.85 17	97.77 31	83.08 90	98.92 86	97.49 5	96.78 106	97.13 128

SR-MVS-dyc-post		93.82 52	93.82 53	93.82 66	97.92 43	84.57 87	96.28 43	96.76 81	87.46 132	93.75 63	97.43 39	84.24 75	99.01 66	92.73 64	97.80 79	97.88 87

APD-MVS_3200maxsize		93.78 53	93.77 57	93.80 68	97.92 43	84.19 102	96.30 41	96.87 68	86.96 144	93.92 61	97.47 37	83.88 79	98.96 80	92.71 67	97.87 76	98.26 61

fmvsm_s_conf0.5_n		93.76 54	94.06 48	92.86 105	95.62 132	83.17 132	96.14 56	96.12 137	88.13 112	95.82 32	98.04 21	83.43 82	98.48 127	96.97 15	96.23 118	96.92 143

patch_mono-2		93.74 55	94.32 31	92.01 146	97.54 60	78.37 268	93.40 233	97.19 36	88.02 114	94.99 45	97.21 50	88.35 21	98.44 137	94.07 44	98.09 68	99.23 1

MSLP-MVS++		93.72 56	94.08 45	92.65 117	97.31 68	83.43 123	95.79 87	97.33 26	90.03 41	93.58 67	96.96 64	84.87 68	97.76 190	92.19 82	98.66 41	96.76 150

TSAR-MVS + GP.		93.66 57	93.41 67	94.41 49	96.59 85	86.78 26	94.40 175	93.93 267	89.77 55	94.21 52	95.59 126	87.35 34	98.61 119	92.72 66	96.15 121	97.83 92

fmvsm_s_conf0.5_n_a		93.57 58	93.76 58	93.00 97	95.02 158	83.67 115	96.19 49	96.10 139	87.27 137	95.98 30	98.05 18	83.07 91	98.45 135	96.68 17	95.51 130	96.88 146

CANet		93.54 59	93.20 72	94.55 43	95.65 129	85.73 65	94.94 139	96.69 91	91.89 9	90.69 133	95.88 113	81.99 113	99.54 20	93.14 58	97.95 74	98.39 40

dcpmvs_2		93.49 60	94.19 42	91.38 180	97.69 57	76.78 301	94.25 186	96.29 118	88.33 102	94.46 48	96.88 67	88.07 25	98.64 114	93.62 50	98.09 68	98.73 18

fmvsm_s_conf0.5_n_2		93.47 61	93.83 52	92.39 132	95.36 141	81.19 192	95.20 125	96.56 100	90.37 31	97.13 11	98.03 22	77.47 160	98.96 80	97.79 3	96.58 111	97.03 134

fmvsm_s_conf0.1_n		93.46 62	93.66 62	92.85 106	93.75 235	83.13 134	96.02 69	95.74 170	87.68 129	95.89 31	98.17 2	82.78 95	98.46 131	96.71 16	96.17 120	96.98 139

MVS_111021_HR		93.45 63	93.31 68	93.84 65	96.99 75	84.84 79	93.24 246	97.24 33	88.76 88	91.60 122	95.85 114	86.07 49	98.66 110	91.91 94	98.16 63	98.03 78

MVSMamba_PlusPlus		93.44 64	93.54 65	93.14 88	96.58 87	83.05 140	96.06 65	96.50 105	84.42 210	94.09 55	95.56 127	85.01 66	98.69 109	94.96 35	98.66 41	97.67 101

test_fmvsmvis_n_1920		93.44 64	93.55 64	93.10 90	93.67 239	84.26 101	95.83 85	96.14 133	89.00 83	92.43 100	97.50 36	83.37 85	98.72 106	96.61 18	97.44 88	96.32 167

train_agg		93.44 64	93.08 73	94.52 44	97.53 61	86.49 37	94.07 200	96.78 78	81.86 272	92.77 88	96.20 96	87.63 29	99.12 54	92.14 84	98.69 35	97.94 82

EC-MVSNet		93.44 64	93.71 60	92.63 118	95.21 150	82.43 160	97.27 9	96.71 89	90.57 28	92.88 82	95.80 117	83.16 87	98.16 158	93.68 48	98.14 65	97.31 114

DELS-MVS		93.43 68	93.25 70	93.97 60	95.42 140	85.04 76	93.06 253	97.13 45	90.74 23	91.84 115	95.09 147	86.32 45	99.21 48	91.22 105	98.45 52	97.65 102
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
HPM-MVS_fast		93.40 69	93.22 71	93.94 62	98.36 25	84.83 80	97.15 13	96.80 77	85.77 174	92.47 99	97.13 57	82.38 99	99.07 56	90.51 118	98.40 54	97.92 85

DeepC-MVS	88.79 3	93.31 70	92.99 76	94.26 55	96.07 109	85.83 61	94.89 142	96.99 53	89.02 82	89.56 148	97.37 43	82.51 98	99.38 31	92.20 81	98.30 57	97.57 107
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
sasdasda		93.27 71	92.75 80	94.85 25	95.70 126	87.66 12	96.33 39	96.41 110	90.00 42	94.09 55	94.60 168	82.33 101	98.62 117	92.40 73	92.86 190	98.27 57

canonicalmvs		93.27 71	92.75 80	94.85 25	95.70 126	87.66 12	96.33 39	96.41 110	90.00 42	94.09 55	94.60 168	82.33 101	98.62 117	92.40 73	92.86 190	98.27 57

ACMMP		93.24 73	92.88 78	94.30 53	98.09 38	85.33 72	96.86 27	97.45 14	88.33 102	90.15 143	97.03 62	81.44 116	99.51 24	90.85 114	95.74 126	98.04 77
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
CSCG		93.23 74	93.05 74	93.76 70	98.04 40	84.07 104	96.22 48	97.37 21	84.15 213	90.05 144	95.66 123	87.77 26	99.15 53	89.91 123	98.27 58	98.07 74

fmvsm_s_conf0.1_n_a		93.19 75	93.26 69	92.97 99	92.49 273	83.62 118	96.02 69	95.72 173	86.78 150	96.04 28	98.19 1	82.30 103	98.43 139	96.38 19	95.42 136	96.86 147

test_fmvsmconf0.01_n		93.19 75	93.02 75	93.71 73	89.25 369	84.42 98	96.06 65	96.29 118	89.06 77	94.68 46	98.13 4	79.22 140	98.98 77	97.22 9	97.24 93	97.74 97

fmvsm_s_conf0.1_n_2		93.16 77	93.42 66	92.37 133	94.62 185	81.13 194	95.23 120	95.89 159	90.30 34	96.74 21	98.02 23	76.14 172	98.95 82	97.64 4	96.21 119	97.03 134

alignmvs		93.08 78	92.50 86	94.81 32	95.62 132	87.61 15	95.99 71	96.07 142	89.77 55	94.12 54	94.87 154	80.56 122	98.66 110	92.42 72	93.10 186	98.15 68

MGCFI-Net		93.03 79	92.63 83	94.23 56	95.62 132	85.92 57	96.08 61	96.33 116	89.86 46	93.89 62	94.66 165	82.11 108	98.50 125	92.33 78	92.82 193	98.27 57

EI-MVSNet-Vis-set		93.01 80	92.92 77	93.29 80	95.01 159	83.51 122	94.48 167	95.77 167	90.87 17	92.52 97	96.67 77	84.50 72	99.00 71	91.99 90	94.44 160	97.36 113

casdiffmvs_mvg		92.96 81	92.83 79	93.35 78	94.59 187	83.40 125	95.00 136	96.34 115	90.30 34	92.05 106	96.05 104	83.43 82	98.15 159	92.07 86	95.67 127	98.49 29
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UA-Net		92.83 82	92.54 85	93.68 74	96.10 106	84.71 83	95.66 96	96.39 112	91.92 8	93.22 74	96.49 88	83.16 87	98.87 89	84.47 190	95.47 133	97.45 112

CDPH-MVS		92.83 82	92.30 88	94.44 45	97.79 52	86.11 49	94.06 202	96.66 92	80.09 303	92.77 88	96.63 82	86.62 40	99.04 60	87.40 151	98.66 41	98.17 67

ETV-MVS		92.74 84	92.66 82	92.97 99	95.20 151	84.04 106	95.07 132	96.51 104	90.73 24	92.96 80	91.19 289	84.06 76	98.34 145	91.72 99	96.54 112	96.54 162

EI-MVSNet-UG-set		92.74 84	92.62 84	93.12 89	94.86 171	83.20 131	94.40 175	95.74 170	90.71 25	92.05 106	96.60 84	84.00 77	98.99 73	91.55 101	93.63 170	97.17 123

DPM-MVS		92.58 86	91.74 96	95.08 15	96.19 99	89.31 5	92.66 265	96.56 100	83.44 231	91.68 121	95.04 148	86.60 42	98.99 73	85.60 176	97.92 75	96.93 142

casdiffmvs		92.51 87	92.43 87	92.74 112	94.41 202	81.98 170	94.54 165	96.23 127	89.57 61	91.96 110	96.17 100	82.58 97	98.01 177	90.95 111	95.45 135	98.23 63
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BP-MVS1		92.48 88	92.07 91	93.72 72	94.50 195	84.39 99	95.90 79	94.30 253	90.39 30	92.67 93	95.94 109	74.46 198	98.65 112	93.14 58	97.35 91	98.13 69

MVS_111021_LR		92.47 89	92.29 89	92.98 98	95.99 115	84.43 96	93.08 251	96.09 140	88.20 109	91.12 129	95.72 122	81.33 118	97.76 190	91.74 98	97.37 90	96.75 151

3Dnovator+	87.14 4	92.42 90	91.37 100	95.55 7	95.63 131	88.73 6	97.07 18	96.77 80	90.84 18	84.02 284	96.62 83	75.95 177	99.34 37	87.77 146	97.68 84	98.59 24

baseline		92.39 91	92.29 89	92.69 116	94.46 198	81.77 174	94.14 192	96.27 122	89.22 72	91.88 113	96.00 105	82.35 100	97.99 179	91.05 107	95.27 141	98.30 50

VNet		92.24 92	91.91 93	93.24 83	96.59 85	83.43 123	94.84 147	96.44 107	89.19 74	94.08 58	95.90 111	77.85 159	98.17 157	88.90 133	93.38 179	98.13 69

GDP-MVS		92.04 93	91.46 99	93.75 71	94.55 192	84.69 84	95.60 104	96.56 100	87.83 124	93.07 79	95.89 112	73.44 218	98.65 112	90.22 121	96.03 123	97.91 86

CPTT-MVS		91.99 94	91.80 94	92.55 123	98.24 31	81.98 170	96.76 30	96.49 106	81.89 271	90.24 138	96.44 90	78.59 148	98.61 119	89.68 124	97.85 77	97.06 131

EIA-MVS		91.95 95	91.94 92	91.98 150	95.16 153	80.01 230	95.36 108	96.73 86	88.44 99	89.34 153	92.16 253	83.82 80	98.45 135	89.35 127	97.06 96	97.48 110

DP-MVS Recon		91.95 95	91.28 102	93.96 61	98.33 27	85.92 57	94.66 159	96.66 92	82.69 251	90.03 145	95.82 116	82.30 103	99.03 61	84.57 188	96.48 115	96.91 144

EPNet		91.79 97	91.02 108	94.10 58	90.10 356	85.25 73	96.03 68	92.05 317	92.83 3	87.39 191	95.78 118	79.39 138	99.01 66	88.13 142	97.48 87	98.05 76
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MG-MVS		91.77 98	91.70 97	92.00 149	97.08 74	80.03 229	93.60 226	95.18 210	87.85 123	90.89 131	96.47 89	82.06 111	98.36 142	85.07 180	97.04 97	97.62 103

Vis-MVSNet		91.75 99	91.23 103	93.29 80	95.32 143	83.78 112	96.14 56	95.98 149	89.89 44	90.45 135	96.58 85	75.09 189	98.31 150	84.75 186	96.90 101	97.78 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator	86.66 5	91.73 100	90.82 112	94.44 45	94.59 187	86.37 41	97.18 12	97.02 52	89.20 73	84.31 279	96.66 78	73.74 214	99.17 50	86.74 161	97.96 73	97.79 94

EPP-MVSNet		91.70 101	91.56 98	92.13 145	95.88 118	80.50 214	97.33 7	95.25 206	86.15 166	89.76 147	95.60 125	83.42 84	98.32 149	87.37 153	93.25 183	97.56 108

MVSFormer		91.68 102	91.30 101	92.80 108	93.86 229	83.88 109	95.96 74	95.90 157	84.66 206	91.76 118	94.91 151	77.92 156	97.30 235	89.64 125	97.11 94	97.24 119

Effi-MVS+		91.59 103	91.11 105	93.01 96	94.35 207	83.39 126	94.60 161	95.10 214	87.10 141	90.57 134	93.10 224	81.43 117	98.07 173	89.29 129	94.48 158	97.59 106

IS-MVSNet		91.43 104	91.09 107	92.46 127	95.87 120	81.38 186	96.95 19	93.69 278	89.72 57	89.50 151	95.98 107	78.57 149	97.77 189	83.02 208	96.50 114	98.22 64

PVSNet_Blended_VisFu		91.38 105	90.91 110	92.80 108	96.39 94	83.17 132	94.87 144	96.66 92	83.29 236	89.27 155	94.46 173	80.29 125	99.17 50	87.57 149	95.37 137	96.05 185

diffmvs		91.37 106	91.23 103	91.77 166	93.09 256	80.27 218	92.36 274	95.52 189	87.03 143	91.40 126	94.93 150	80.08 127	97.44 219	92.13 85	94.56 155	97.61 104
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		91.31 107	91.11 105	91.93 154	94.37 203	80.14 222	93.46 231	95.80 165	86.46 158	91.35 127	93.77 203	82.21 106	98.09 170	87.57 149	94.95 145	97.55 109

OMC-MVS		91.23 108	90.62 115	93.08 92	96.27 97	84.07 104	93.52 228	95.93 153	86.95 145	89.51 149	96.13 102	78.50 150	98.35 144	85.84 174	92.90 189	96.83 149

PAPM_NR		91.22 109	90.78 113	92.52 125	97.60 59	81.46 183	94.37 181	96.24 126	86.39 160	87.41 188	94.80 159	82.06 111	98.48 127	82.80 214	95.37 137	97.61 104

PS-MVSNAJ		91.18 110	90.92 109	91.96 152	95.26 148	82.60 159	92.09 286	95.70 174	86.27 162	91.84 115	92.46 243	79.70 133	98.99 73	89.08 131	95.86 125	94.29 257

xiu_mvs_v2_base		91.13 111	90.89 111	91.86 160	94.97 162	82.42 161	92.24 280	95.64 181	86.11 170	91.74 120	93.14 222	79.67 136	98.89 88	89.06 132	95.46 134	94.28 258

nrg030		91.08 112	90.39 116	93.17 86	93.07 257	86.91 22	96.41 37	96.26 123	88.30 104	88.37 169	94.85 157	82.19 107	97.64 200	91.09 106	82.95 315	94.96 225

mamv4		90.92 113	91.78 95	88.33 294	95.67 128	70.75 377	92.92 258	96.02 148	81.90 269	88.11 170	95.34 134	85.88 51	96.97 263	95.22 33	95.01 144	97.26 117

lupinMVS		90.92 113	90.21 119	93.03 95	93.86 229	83.88 109	92.81 262	93.86 271	79.84 306	91.76 118	94.29 178	77.92 156	98.04 175	90.48 119	97.11 94	97.17 123

RRT-MVS		90.85 115	90.70 114	91.30 183	94.25 209	76.83 300	94.85 146	96.13 136	89.04 79	90.23 139	94.88 153	70.15 259	98.72 106	91.86 97	94.88 146	98.34 43

h-mvs33		90.80 116	90.15 122	92.75 111	96.01 111	82.66 156	95.43 107	95.53 188	89.80 51	93.08 77	95.64 124	75.77 178	99.00 71	92.07 86	78.05 372	96.60 157

jason		90.80 116	90.10 123	92.90 103	93.04 260	83.53 121	93.08 251	94.15 260	80.22 300	91.41 125	94.91 151	76.87 164	97.93 184	90.28 120	96.90 101	97.24 119
jason: jason.
VDD-MVS		90.74 118	89.92 130	93.20 85	96.27 97	83.02 142	95.73 90	93.86 271	88.42 101	92.53 96	96.84 69	62.09 333	98.64 114	90.95 111	92.62 195	97.93 84

PVSNet_Blended		90.73 119	90.32 118	91.98 150	96.12 102	81.25 188	92.55 269	96.83 72	82.04 264	89.10 157	92.56 241	81.04 120	98.85 93	86.72 163	95.91 124	95.84 192

test_yl		90.69 120	90.02 128	92.71 113	95.72 124	82.41 163	94.11 195	95.12 212	85.63 178	91.49 123	94.70 161	74.75 193	98.42 140	86.13 169	92.53 197	97.31 114

DCV-MVSNet		90.69 120	90.02 128	92.71 113	95.72 124	82.41 163	94.11 195	95.12 212	85.63 178	91.49 123	94.70 161	74.75 193	98.42 140	86.13 169	92.53 197	97.31 114

API-MVS		90.66 122	90.07 124	92.45 128	96.36 95	84.57 87	96.06 65	95.22 209	82.39 254	89.13 156	94.27 181	80.32 124	98.46 131	80.16 265	96.71 108	94.33 256

xiu_mvs_v1_base_debu		90.64 123	90.05 125	92.40 129	93.97 226	84.46 93	93.32 237	95.46 191	85.17 187	92.25 101	94.03 185	70.59 250	98.57 122	90.97 108	94.67 150	94.18 259

xiu_mvs_v1_base		90.64 123	90.05 125	92.40 129	93.97 226	84.46 93	93.32 237	95.46 191	85.17 187	92.25 101	94.03 185	70.59 250	98.57 122	90.97 108	94.67 150	94.18 259

xiu_mvs_v1_base_debi		90.64 123	90.05 125	92.40 129	93.97 226	84.46 93	93.32 237	95.46 191	85.17 187	92.25 101	94.03 185	70.59 250	98.57 122	90.97 108	94.67 150	94.18 259

HQP_MVS		90.60 126	90.19 120	91.82 163	94.70 181	82.73 152	95.85 83	96.22 128	90.81 19	86.91 197	94.86 155	74.23 202	98.12 160	88.15 140	89.99 229	94.63 237

FIs		90.51 127	90.35 117	90.99 200	93.99 225	80.98 199	95.73 90	97.54 4	89.15 75	86.72 204	94.68 163	81.83 115	97.24 243	85.18 179	88.31 262	94.76 235

mvsmamba		90.33 128	89.69 133	92.25 143	95.17 152	81.64 176	95.27 118	93.36 283	84.88 197	89.51 149	94.27 181	69.29 274	97.42 221	89.34 128	96.12 122	97.68 100

MAR-MVS		90.30 129	89.37 141	93.07 94	96.61 84	84.48 92	95.68 93	95.67 176	82.36 256	87.85 178	92.85 229	76.63 170	98.80 98	80.01 266	96.68 109	95.91 188
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
FC-MVSNet-test		90.27 130	90.18 121	90.53 212	93.71 236	79.85 236	95.77 88	97.59 3	89.31 69	86.27 215	94.67 164	81.93 114	97.01 261	84.26 192	88.09 265	94.71 236

CANet_DTU		90.26 131	89.41 140	92.81 107	93.46 246	83.01 143	93.48 229	94.47 246	89.43 65	87.76 183	94.23 183	70.54 254	99.03 61	84.97 181	96.39 116	96.38 165

SDMVSNet		90.19 132	89.61 135	91.93 154	96.00 112	83.09 138	92.89 259	95.98 149	88.73 89	86.85 201	95.20 142	72.09 234	97.08 254	88.90 133	89.85 235	95.63 202

OPM-MVS		90.12 133	89.56 136	91.82 163	93.14 253	83.90 108	94.16 191	95.74 170	88.96 84	87.86 177	95.43 132	72.48 230	97.91 185	88.10 144	90.18 228	93.65 294
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LFMVS		90.08 134	89.13 147	92.95 101	96.71 80	82.32 165	96.08 61	89.91 371	86.79 149	92.15 105	96.81 72	62.60 331	98.34 145	87.18 155	93.90 166	98.19 65

GeoE		90.05 135	89.43 139	91.90 159	95.16 153	80.37 217	95.80 86	94.65 243	83.90 218	87.55 187	94.75 160	78.18 154	97.62 202	81.28 245	93.63 170	97.71 99

PAPR		90.02 136	89.27 146	92.29 140	95.78 122	80.95 201	92.68 264	96.22 128	81.91 268	86.66 205	93.75 205	82.23 105	98.44 137	79.40 277	94.79 148	97.48 110

PVSNet_BlendedMVS		89.98 137	89.70 132	90.82 205	96.12 102	81.25 188	93.92 213	96.83 72	83.49 230	89.10 157	92.26 251	81.04 120	98.85 93	86.72 163	87.86 269	92.35 342

PS-MVSNAJss		89.97 138	89.62 134	91.02 197	91.90 293	80.85 205	95.26 119	95.98 149	86.26 163	86.21 217	94.29 178	79.70 133	97.65 198	88.87 135	88.10 263	94.57 242

XVG-OURS-SEG-HR		89.95 139	89.45 137	91.47 177	94.00 224	81.21 191	91.87 290	96.06 144	85.78 173	88.55 165	95.73 121	74.67 197	97.27 239	88.71 136	89.64 240	95.91 188

UGNet		89.95 139	88.95 151	92.95 101	94.51 194	83.31 127	95.70 92	95.23 207	89.37 67	87.58 185	93.94 193	64.00 321	98.78 101	83.92 197	96.31 117	96.74 152
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
UniMVSNet_NR-MVSNet		89.92 141	89.29 144	91.81 165	93.39 248	83.72 113	94.43 173	97.12 46	89.80 51	86.46 208	93.32 213	83.16 87	97.23 244	84.92 182	81.02 345	94.49 250

AdaColmap		89.89 142	89.07 148	92.37 133	97.41 65	83.03 141	94.42 174	95.92 154	82.81 248	86.34 214	94.65 166	73.89 210	99.02 64	80.69 256	95.51 130	95.05 220

hse-mvs2		89.88 143	89.34 142	91.51 174	94.83 173	81.12 195	93.94 211	93.91 270	89.80 51	93.08 77	93.60 207	75.77 178	97.66 197	92.07 86	77.07 379	95.74 197

UniMVSNet (Re)		89.80 144	89.07 148	92.01 146	93.60 242	84.52 90	94.78 151	97.47 11	89.26 71	86.44 211	92.32 248	82.10 109	97.39 232	84.81 185	80.84 349	94.12 263

HQP-MVS		89.80 144	89.28 145	91.34 182	94.17 213	81.56 177	94.39 177	96.04 145	88.81 85	85.43 243	93.97 192	73.83 212	97.96 181	87.11 158	89.77 238	94.50 248

FA-MVS(test-final)		89.66 146	88.91 153	91.93 154	94.57 190	80.27 218	91.36 302	94.74 239	84.87 198	89.82 146	92.61 240	74.72 196	98.47 130	83.97 196	93.53 173	97.04 133

VPA-MVSNet		89.62 147	88.96 150	91.60 171	93.86 229	82.89 147	95.46 106	97.33 26	87.91 118	88.43 168	93.31 214	74.17 205	97.40 229	87.32 154	82.86 320	94.52 245

WTY-MVS		89.60 148	88.92 152	91.67 169	95.47 139	81.15 193	92.38 273	94.78 237	83.11 240	89.06 159	94.32 176	78.67 147	96.61 282	81.57 241	90.89 217	97.24 119

Vis-MVSNet (Re-imp)		89.59 149	89.44 138	90.03 237	95.74 123	75.85 315	95.61 101	90.80 355	87.66 131	87.83 180	95.40 133	76.79 166	96.46 296	78.37 283	96.73 107	97.80 93

VDDNet		89.56 150	88.49 166	92.76 110	95.07 157	82.09 167	96.30 41	93.19 286	81.05 294	91.88 113	96.86 68	61.16 349	98.33 147	88.43 139	92.49 199	97.84 91

114514_t		89.51 151	88.50 164	92.54 124	98.11 36	81.99 169	95.16 128	96.36 114	70.19 400	85.81 225	95.25 138	76.70 168	98.63 116	82.07 229	96.86 104	97.00 138

QAPM		89.51 151	88.15 175	93.59 76	94.92 166	84.58 86	96.82 29	96.70 90	78.43 330	83.41 300	96.19 99	73.18 222	99.30 43	77.11 299	96.54 112	96.89 145

CLD-MVS		89.47 153	88.90 154	91.18 188	94.22 211	82.07 168	92.13 284	96.09 140	87.90 119	85.37 249	92.45 244	74.38 200	97.56 206	87.15 156	90.43 223	93.93 272
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LPG-MVS_test		89.45 154	88.90 154	91.12 189	94.47 196	81.49 181	95.30 113	96.14 133	86.73 152	85.45 240	95.16 144	69.89 261	98.10 162	87.70 147	89.23 247	93.77 287

CDS-MVSNet		89.45 154	88.51 163	92.29 140	93.62 241	83.61 120	93.01 254	94.68 242	81.95 266	87.82 181	93.24 218	78.69 146	96.99 262	80.34 262	93.23 184	96.28 170
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		89.41 156	88.64 159	91.71 168	94.74 176	80.81 206	93.54 227	95.10 214	83.11 240	86.82 203	90.67 312	79.74 132	97.75 193	80.51 260	93.55 172	96.57 160

ab-mvs		89.41 156	88.35 168	92.60 119	95.15 155	82.65 157	92.20 282	95.60 183	83.97 217	88.55 165	93.70 206	74.16 206	98.21 156	82.46 219	89.37 243	96.94 141

XVG-OURS		89.40 158	88.70 158	91.52 173	94.06 218	81.46 183	91.27 306	96.07 142	86.14 167	88.89 161	95.77 119	68.73 283	97.26 241	87.39 152	89.96 231	95.83 193

test_vis1_n_1920		89.39 159	89.84 131	88.04 302	92.97 264	72.64 354	94.71 156	96.03 147	86.18 165	91.94 112	96.56 87	61.63 337	95.74 333	93.42 53	95.11 143	95.74 197

mvs_anonymous		89.37 160	89.32 143	89.51 263	93.47 245	74.22 333	91.65 297	94.83 233	82.91 246	85.45 240	93.79 201	81.23 119	96.36 303	86.47 165	94.09 163	97.94 82

DU-MVS		89.34 161	88.50 164	91.85 162	93.04 260	83.72 113	94.47 170	96.59 97	89.50 62	86.46 208	93.29 216	77.25 162	97.23 244	84.92 182	81.02 345	94.59 240

TAMVS		89.21 162	88.29 172	91.96 152	93.71 236	82.62 158	93.30 241	94.19 258	82.22 259	87.78 182	93.94 193	78.83 143	96.95 265	77.70 292	92.98 188	96.32 167

ACMM	84.12 9	89.14 163	88.48 167	91.12 189	94.65 184	81.22 190	95.31 111	96.12 137	85.31 186	85.92 223	94.34 174	70.19 258	98.06 174	85.65 175	88.86 252	94.08 267
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test1111		89.10 164	88.64 159	90.48 217	95.53 137	74.97 324	96.08 61	84.89 403	88.13 112	90.16 142	96.65 79	63.29 326	98.10 162	86.14 167	96.90 101	98.39 40

EI-MVSNet		89.10 164	88.86 156	89.80 250	91.84 295	78.30 270	93.70 223	95.01 218	85.73 175	87.15 192	95.28 136	79.87 130	97.21 246	83.81 199	87.36 277	93.88 276

ECVR-MVS		89.09 166	88.53 162	90.77 207	95.62 132	75.89 314	96.16 52	84.22 405	87.89 121	90.20 140	96.65 79	63.19 328	98.10 162	85.90 172	96.94 99	98.33 45

CNLPA		89.07 167	87.98 178	92.34 135	96.87 77	84.78 82	94.08 199	93.24 284	81.41 285	84.46 269	95.13 146	75.57 185	96.62 279	77.21 297	93.84 168	95.61 204

PLC	84.53 7	89.06 168	88.03 177	92.15 144	97.27 71	82.69 155	94.29 184	95.44 196	79.71 308	84.01 285	94.18 184	76.68 169	98.75 103	77.28 296	93.41 178	95.02 221
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_djsdf		89.03 169	88.64 159	90.21 228	90.74 342	79.28 251	95.96 74	95.90 157	84.66 206	85.33 251	92.94 228	74.02 208	97.30 235	89.64 125	88.53 255	94.05 269

HY-MVS	83.01 12	89.03 169	87.94 180	92.29 140	94.86 171	82.77 148	92.08 287	94.49 245	81.52 284	86.93 195	92.79 235	78.32 153	98.23 153	79.93 267	90.55 221	95.88 190

ACMP	84.23 8	89.01 171	88.35 168	90.99 200	94.73 177	81.27 187	95.07 132	95.89 159	86.48 156	83.67 293	94.30 177	69.33 270	97.99 179	87.10 160	88.55 254	93.72 292
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
sss		88.93 172	88.26 174	90.94 203	94.05 219	80.78 207	91.71 294	95.38 200	81.55 283	88.63 164	93.91 197	75.04 190	95.47 345	82.47 218	91.61 205	96.57 160

TranMVSNet+NR-MVSNet		88.84 173	87.95 179	91.49 175	92.68 271	83.01 143	94.92 141	96.31 117	89.88 45	85.53 234	93.85 200	76.63 170	96.96 264	81.91 233	79.87 362	94.50 248

CHOSEN 1792x2688		88.84 173	87.69 184	92.30 139	96.14 100	81.42 185	90.01 338	95.86 162	74.52 369	87.41 188	93.94 193	75.46 186	98.36 142	80.36 261	95.53 129	97.12 129

MVSTER		88.84 173	88.29 172	90.51 215	92.95 265	80.44 215	93.73 220	95.01 218	84.66 206	87.15 192	93.12 223	72.79 226	97.21 246	87.86 145	87.36 277	93.87 277

test_cas_vis1_n_1920		88.83 176	88.85 157	88.78 279	91.15 323	76.72 302	93.85 216	94.93 225	83.23 239	92.81 86	96.00 105	61.17 348	94.45 356	91.67 100	94.84 147	95.17 216

OpenMVS	83.78 11	88.74 177	87.29 194	93.08 92	92.70 270	85.39 71	96.57 35	96.43 108	78.74 325	80.85 332	96.07 103	69.64 265	99.01 66	78.01 290	96.65 110	94.83 232

thisisatest0530		88.67 178	87.61 186	91.86 160	94.87 170	80.07 225	94.63 160	89.90 372	84.00 216	88.46 167	93.78 202	66.88 298	98.46 131	83.30 204	92.65 194	97.06 131

Effi-MVS+-dtu		88.65 179	88.35 168	89.54 260	93.33 249	76.39 308	94.47 170	94.36 251	87.70 128	85.43 243	89.56 341	73.45 217	97.26 241	85.57 177	91.28 209	94.97 222

tttt0517		88.61 180	87.78 183	91.11 192	94.96 163	77.81 283	95.35 109	89.69 375	85.09 192	88.05 175	94.59 170	66.93 296	98.48 127	83.27 205	92.13 202	97.03 134

BH-untuned		88.60 181	88.13 176	90.01 240	95.24 149	78.50 264	93.29 242	94.15 260	84.75 203	84.46 269	93.40 210	75.76 180	97.40 229	77.59 293	94.52 157	94.12 263

sd_testset		88.59 182	87.85 182	90.83 204	96.00 112	80.42 216	92.35 275	94.71 240	88.73 89	86.85 201	95.20 142	67.31 290	96.43 298	79.64 271	89.85 235	95.63 202

NR-MVSNet		88.58 183	87.47 190	91.93 154	93.04 260	84.16 103	94.77 152	96.25 125	89.05 78	80.04 345	93.29 216	79.02 142	97.05 259	81.71 240	80.05 359	94.59 240

1112_ss		88.42 184	87.33 193	91.72 167	94.92 166	80.98 199	92.97 256	94.54 244	78.16 336	83.82 288	93.88 198	78.78 145	97.91 185	79.45 273	89.41 242	96.26 171

WR-MVS		88.38 185	87.67 185	90.52 214	93.30 250	80.18 220	93.26 244	95.96 152	88.57 97	85.47 239	92.81 233	76.12 173	96.91 268	81.24 246	82.29 325	94.47 253

BH-RMVSNet		88.37 186	87.48 189	91.02 197	95.28 145	79.45 243	92.89 259	93.07 289	85.45 183	86.91 197	94.84 158	70.35 255	97.76 190	73.97 329	94.59 154	95.85 191

IterMVS-LS		88.36 187	87.91 181	89.70 254	93.80 232	78.29 271	93.73 220	95.08 216	85.73 175	84.75 261	91.90 268	79.88 129	96.92 267	83.83 198	82.51 321	93.89 273
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
X-MVStestdata		88.31 188	86.13 236	94.85 25	98.54 13	86.60 34	96.93 22	97.19 36	90.66 26	92.85 83	23.41 430	85.02 63	99.49 26	91.99 90	98.56 50	98.47 33

LCM-MVSNet-Re		88.30 189	88.32 171	88.27 295	94.71 180	72.41 359	93.15 247	90.98 348	87.77 126	79.25 354	91.96 265	78.35 152	95.75 332	83.04 207	95.62 128	96.65 156

jajsoiax		88.24 190	87.50 188	90.48 217	90.89 336	80.14 222	95.31 111	95.65 180	84.97 195	84.24 280	94.02 188	65.31 314	97.42 221	88.56 137	88.52 256	93.89 273

VPNet		88.20 191	87.47 190	90.39 222	93.56 243	79.46 242	94.04 203	95.54 187	88.67 92	86.96 194	94.58 171	69.33 270	97.15 248	84.05 195	80.53 354	94.56 243

TAPA-MVS	84.62 6	88.16 192	87.01 202	91.62 170	96.64 83	80.65 209	94.39 177	96.21 131	76.38 349	86.19 218	95.44 130	79.75 131	98.08 172	62.75 393	95.29 139	96.13 177
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		88.10 193	87.28 195	90.57 210	94.96 163	80.07 225	94.27 185	91.29 341	86.74 151	87.41 188	94.00 190	76.77 167	96.20 309	80.77 254	79.31 368	95.44 206

Anonymous20240529		88.09 194	86.59 218	92.58 121	96.53 90	81.92 172	95.99 71	95.84 163	74.11 373	89.06 159	95.21 141	61.44 341	98.81 97	83.67 202	87.47 274	97.01 137

HyFIR lowres test		88.09 194	86.81 206	91.93 154	96.00 112	80.63 210	90.01 338	95.79 166	73.42 380	87.68 184	92.10 259	73.86 211	97.96 181	80.75 255	91.70 204	97.19 122

mvs_tets		88.06 196	87.28 195	90.38 224	90.94 332	79.88 234	95.22 122	95.66 178	85.10 191	84.21 281	93.94 193	63.53 324	97.40 229	88.50 138	88.40 260	93.87 277

F-COLMAP		87.95 197	86.80 207	91.40 179	96.35 96	80.88 204	94.73 154	95.45 194	79.65 309	82.04 319	94.61 167	71.13 241	98.50 125	76.24 309	91.05 215	94.80 234

LS3D		87.89 198	86.32 229	92.59 120	96.07 109	82.92 146	95.23 120	94.92 226	75.66 356	82.89 307	95.98 107	72.48 230	99.21 48	68.43 364	95.23 142	95.64 201

anonymousdsp		87.84 199	87.09 198	90.12 233	89.13 370	80.54 213	94.67 158	95.55 185	82.05 262	83.82 288	92.12 256	71.47 239	97.15 248	87.15 156	87.80 272	92.67 330

v2v482		87.84 199	87.06 199	90.17 229	90.99 328	79.23 254	94.00 208	95.13 211	84.87 198	85.53 234	92.07 262	74.45 199	97.45 216	84.71 187	81.75 333	93.85 280

WR-MVS_H		87.80 201	87.37 192	89.10 272	93.23 251	78.12 274	95.61 101	97.30 30	87.90 119	83.72 291	92.01 264	79.65 137	96.01 318	76.36 306	80.54 353	93.16 314

AUN-MVS		87.78 202	86.54 221	91.48 176	94.82 174	81.05 197	93.91 215	93.93 267	83.00 243	86.93 195	93.53 208	69.50 268	97.67 195	86.14 167	77.12 378	95.73 199

PCF-MVS	84.11 10	87.74 203	86.08 240	92.70 115	94.02 220	84.43 96	89.27 351	95.87 161	73.62 378	84.43 271	94.33 175	78.48 151	98.86 91	70.27 350	94.45 159	94.81 233
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Anonymous202405211		87.68 204	86.13 236	92.31 138	96.66 82	80.74 208	94.87 144	91.49 336	80.47 299	89.46 152	95.44 130	54.72 385	98.23 153	82.19 225	89.89 233	97.97 80

V42		87.68 204	86.86 204	90.15 231	90.58 347	80.14 222	94.24 188	95.28 205	83.66 224	85.67 229	91.33 284	74.73 195	97.41 227	84.43 191	81.83 331	92.89 324

thres600view7		87.65 206	86.67 213	90.59 209	96.08 108	78.72 257	94.88 143	91.58 332	87.06 142	88.08 173	92.30 249	68.91 280	98.10 162	70.05 357	91.10 210	94.96 225

XXY-MVS		87.65 206	86.85 205	90.03 237	92.14 283	80.60 212	93.76 219	95.23 207	82.94 245	84.60 264	94.02 188	74.27 201	95.49 344	81.04 248	83.68 307	94.01 271

Test_1112_low_res		87.65 206	86.51 222	91.08 193	94.94 165	79.28 251	91.77 292	94.30 253	76.04 354	83.51 298	92.37 246	77.86 158	97.73 194	78.69 282	89.13 249	96.22 172

thres100view900		87.63 209	86.71 210	90.38 224	96.12 102	78.55 261	95.03 135	91.58 332	87.15 139	88.06 174	92.29 250	68.91 280	98.10 162	70.13 354	91.10 210	94.48 251

CP-MVSNet		87.63 209	87.26 197	88.74 283	93.12 254	76.59 305	95.29 115	96.58 98	88.43 100	83.49 299	92.98 227	75.28 187	95.83 327	78.97 279	81.15 341	93.79 282

thres400		87.62 211	86.64 214	90.57 210	95.99 115	78.64 259	94.58 162	91.98 321	86.94 146	88.09 171	91.77 270	69.18 276	98.10 162	70.13 354	91.10 210	94.96 225

v1144		87.61 212	86.79 208	90.06 236	91.01 327	79.34 247	93.95 210	95.42 199	83.36 235	85.66 230	91.31 287	74.98 191	97.42 221	83.37 203	82.06 327	93.42 303

tfpn200view9		87.58 213	86.64 214	90.41 221	95.99 115	78.64 259	94.58 162	91.98 321	86.94 146	88.09 171	91.77 270	69.18 276	98.10 162	70.13 354	91.10 210	94.48 251

BH-w/o		87.57 214	87.05 200	89.12 271	94.90 169	77.90 279	92.41 271	93.51 280	82.89 247	83.70 292	91.34 283	75.75 181	97.07 256	75.49 313	93.49 175	92.39 340

UniMVSNet_ETH3D		87.53 215	86.37 226	91.00 199	92.44 276	78.96 256	94.74 153	95.61 182	84.07 215	85.36 250	94.52 172	59.78 357	97.34 234	82.93 209	87.88 268	96.71 153

ET-MVSNet_ETH3D		87.51 216	85.91 248	92.32 137	93.70 238	83.93 107	92.33 277	90.94 351	84.16 212	72.09 396	92.52 242	69.90 260	95.85 326	89.20 130	88.36 261	97.17 123

1314		87.51 216	86.57 219	90.34 226	92.42 277	79.74 238	92.63 266	95.35 204	78.35 331	80.14 342	91.62 278	74.05 207	97.15 248	81.05 247	93.53 173	94.12 263

v8		87.50 218	86.71 210	89.89 244	91.37 313	79.40 244	94.50 166	95.38 200	84.81 201	83.60 296	91.33 284	76.05 174	97.42 221	82.84 212	80.51 356	92.84 326

Fast-Effi-MVS+-dtu		87.44 219	86.72 209	89.63 258	92.04 287	77.68 289	94.03 204	93.94 266	85.81 172	82.42 312	91.32 286	70.33 256	97.06 257	80.33 263	90.23 227	94.14 262

MVS		87.44 219	86.10 239	91.44 178	92.61 272	83.62 118	92.63 266	95.66 178	67.26 405	81.47 324	92.15 254	77.95 155	98.22 155	79.71 269	95.48 132	92.47 336

FE-MVS		87.40 221	86.02 242	91.57 172	94.56 191	79.69 239	90.27 325	93.72 277	80.57 297	88.80 162	91.62 278	65.32 313	98.59 121	74.97 321	94.33 162	96.44 163

FMVSNet3		87.40 221	86.11 238	91.30 183	93.79 234	83.64 117	94.20 190	94.81 235	83.89 219	84.37 272	91.87 269	68.45 286	96.56 287	78.23 287	85.36 291	93.70 293

test_fmvs1		87.34 223	87.56 187	86.68 341	90.59 346	71.80 363	94.01 206	94.04 265	78.30 332	91.97 109	95.22 139	56.28 376	93.71 371	92.89 62	94.71 149	94.52 245

thisisatest0515		87.33 224	85.99 243	91.37 181	93.49 244	79.55 240	90.63 320	89.56 380	80.17 301	87.56 186	90.86 302	67.07 295	98.28 151	81.50 242	93.02 187	96.29 169

PS-CasMVS		87.32 225	86.88 203	88.63 286	92.99 263	76.33 310	95.33 110	96.61 96	88.22 108	83.30 304	93.07 225	73.03 224	95.79 331	78.36 284	81.00 347	93.75 289

GBi-Net		87.26 226	85.98 244	91.08 193	94.01 221	83.10 135	95.14 129	94.94 221	83.57 226	84.37 272	91.64 274	66.59 303	96.34 304	78.23 287	85.36 291	93.79 282

test1		87.26 226	85.98 244	91.08 193	94.01 221	83.10 135	95.14 129	94.94 221	83.57 226	84.37 272	91.64 274	66.59 303	96.34 304	78.23 287	85.36 291	93.79 282

v1192		87.25 228	86.33 228	90.00 241	90.76 341	79.04 255	93.80 217	95.48 190	82.57 252	85.48 238	91.18 291	73.38 221	97.42 221	82.30 222	82.06 327	93.53 297

v10		87.25 228	86.38 225	89.85 245	91.19 319	79.50 241	94.48 167	95.45 194	83.79 222	83.62 295	91.19 289	75.13 188	97.42 221	81.94 232	80.60 351	92.63 332

DP-MVS		87.25 228	85.36 265	92.90 103	97.65 58	83.24 129	94.81 149	92.00 319	74.99 364	81.92 321	95.00 149	72.66 227	99.05 58	66.92 376	92.33 200	96.40 164

miper_ehance_all_eth		87.22 231	86.62 217	89.02 275	92.13 284	77.40 293	90.91 315	94.81 235	81.28 288	84.32 277	90.08 328	79.26 139	96.62 279	83.81 199	82.94 316	93.04 319

test2506		87.21 232	86.28 231	90.02 239	95.62 132	73.64 340	96.25 47	71.38 428	87.89 121	90.45 135	96.65 79	55.29 382	98.09 170	86.03 171	96.94 99	98.33 45

thres200		87.21 232	86.24 233	90.12 233	95.36 141	78.53 262	93.26 244	92.10 315	86.42 159	88.00 176	91.11 295	69.24 275	98.00 178	69.58 358	91.04 216	93.83 281

v144192		87.19 234	86.35 227	89.74 251	90.64 345	78.24 272	93.92 213	95.43 197	81.93 267	85.51 236	91.05 298	74.21 204	97.45 216	82.86 211	81.56 335	93.53 297

FMVSNet2		87.19 234	85.82 251	91.30 183	94.01 221	83.67 115	94.79 150	94.94 221	83.57 226	83.88 287	92.05 263	66.59 303	96.51 291	77.56 294	85.01 294	93.73 291

c3_l		87.14 236	86.50 223	89.04 274	92.20 281	77.26 294	91.22 309	94.70 241	82.01 265	84.34 276	90.43 317	78.81 144	96.61 282	83.70 201	81.09 342	93.25 308

testing91		87.11 237	86.18 234	89.92 243	94.43 201	75.38 323	91.53 299	92.27 311	86.48 156	86.50 206	90.24 320	61.19 347	97.53 208	82.10 227	90.88 218	96.84 148

Baseline_NR-MVSNet		87.07 238	86.63 216	88.40 289	91.44 308	77.87 281	94.23 189	92.57 303	84.12 214	85.74 228	92.08 260	77.25 162	96.04 314	82.29 223	79.94 360	91.30 363

v148		87.04 239	86.32 229	89.21 268	90.94 332	77.26 294	93.71 222	94.43 247	84.84 200	84.36 275	90.80 306	76.04 175	97.05 259	82.12 226	79.60 365	93.31 305

test_fmvs1_n		87.03 240	87.04 201	86.97 332	89.74 364	71.86 361	94.55 164	94.43 247	78.47 328	91.95 111	95.50 129	51.16 396	93.81 369	93.02 61	94.56 155	95.26 213

v1921920		86.97 241	86.06 241	89.69 255	90.53 350	78.11 275	93.80 217	95.43 197	81.90 269	85.33 251	91.05 298	72.66 227	97.41 227	82.05 230	81.80 332	93.53 297

tt0805		86.92 242	85.74 257	90.48 217	92.22 280	79.98 232	95.63 100	94.88 229	83.83 221	84.74 262	92.80 234	57.61 371	97.67 195	85.48 178	84.42 298	93.79 282

miper_enhance_ethall		86.90 243	86.18 234	89.06 273	91.66 304	77.58 291	90.22 331	94.82 234	79.16 315	84.48 268	89.10 346	79.19 141	96.66 277	84.06 194	82.94 316	92.94 322

MonoMVSNet		86.89 244	86.55 220	87.92 306	89.46 368	73.75 337	94.12 193	93.10 287	87.82 125	85.10 254	90.76 308	69.59 266	94.94 354	86.47 165	82.50 322	95.07 219

v7n		86.81 245	85.76 255	89.95 242	90.72 343	79.25 253	95.07 132	95.92 154	84.45 209	82.29 313	90.86 302	72.60 229	97.53 208	79.42 276	80.52 355	93.08 318

PEN-MVS		86.80 246	86.27 232	88.40 289	92.32 279	75.71 318	95.18 126	96.38 113	87.97 116	82.82 308	93.15 221	73.39 220	95.92 322	76.15 310	79.03 370	93.59 295

cl22		86.78 247	85.98 244	89.18 270	92.34 278	77.62 290	90.84 316	94.13 262	81.33 287	83.97 286	90.15 325	73.96 209	96.60 284	84.19 193	82.94 316	93.33 304

v1240		86.78 247	85.85 250	89.56 259	90.45 351	77.79 285	93.61 225	95.37 202	81.65 278	85.43 243	91.15 293	71.50 238	97.43 220	81.47 243	82.05 329	93.47 301

TR-MVS		86.78 247	85.76 255	89.82 247	94.37 203	78.41 266	92.47 270	92.83 295	81.11 293	86.36 212	92.40 245	68.73 283	97.48 212	73.75 333	89.85 235	93.57 296

PatchMatch-RL		86.77 250	85.54 259	90.47 220	95.88 118	82.71 154	90.54 322	92.31 309	79.82 307	84.32 277	91.57 282	68.77 282	96.39 300	73.16 335	93.48 177	92.32 343

testing3-2		86.72 251	86.71 210	86.74 340	96.11 105	65.92 398	93.39 234	89.65 378	89.46 63	87.84 179	92.79 235	59.17 363	97.60 203	81.31 244	90.72 219	96.70 154

testing99		86.72 251	85.73 258	89.69 255	94.23 210	74.91 326	91.35 303	90.97 349	86.14 167	86.36 212	90.22 321	59.41 360	97.48 212	82.24 224	90.66 220	96.69 155

PAPM		86.68 253	85.39 263	90.53 212	93.05 259	79.33 250	89.79 341	94.77 238	78.82 322	81.95 320	93.24 218	76.81 165	97.30 235	66.94 374	93.16 185	94.95 228

pm-mvs1		86.61 254	85.54 259	89.82 247	91.44 308	80.18 220	95.28 117	94.85 231	83.84 220	81.66 322	92.62 239	72.45 232	96.48 293	79.67 270	78.06 371	92.82 327

GA-MVS		86.61 254	85.27 268	90.66 208	91.33 316	78.71 258	90.40 324	93.81 274	85.34 185	85.12 253	89.57 340	61.25 344	97.11 253	80.99 251	89.59 241	96.15 175

Anonymous20231211		86.59 256	85.13 271	90.98 202	96.52 91	81.50 179	96.14 56	96.16 132	73.78 376	83.65 294	92.15 254	63.26 327	97.37 233	82.82 213	81.74 334	94.06 268

test_vis1_n		86.56 257	86.49 224	86.78 339	88.51 375	72.69 351	94.68 157	93.78 276	79.55 310	90.70 132	95.31 135	48.75 401	93.28 377	93.15 57	93.99 164	94.38 255

DIV-MVS_self_test		86.53 258	85.78 252	88.75 281	92.02 289	76.45 307	90.74 317	94.30 253	81.83 274	83.34 302	90.82 305	75.75 181	96.57 285	81.73 239	81.52 337	93.24 309

cl____		86.52 259	85.78 252	88.75 281	92.03 288	76.46 306	90.74 317	94.30 253	81.83 274	83.34 302	90.78 307	75.74 183	96.57 285	81.74 238	81.54 336	93.22 310

eth_miper_zixun_eth		86.50 260	85.77 254	88.68 284	91.94 290	75.81 316	90.47 323	94.89 227	82.05 262	84.05 283	90.46 316	75.96 176	96.77 272	82.76 215	79.36 367	93.46 302

baseline2		86.50 260	85.39 263	89.84 246	91.12 324	76.70 303	91.88 289	88.58 383	82.35 257	79.95 346	90.95 300	73.42 219	97.63 201	80.27 264	89.95 232	95.19 215

EPNet_dtu		86.49 262	85.94 247	88.14 300	90.24 354	72.82 349	94.11 195	92.20 313	86.66 154	79.42 353	92.36 247	73.52 215	95.81 329	71.26 342	93.66 169	95.80 195
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing11		86.44 263	85.35 266	89.69 255	94.29 208	75.40 322	91.30 304	90.53 358	84.76 202	85.06 255	90.13 326	58.95 366	97.45 216	82.08 228	91.09 214	96.21 174

cascas		86.43 264	84.98 274	90.80 206	92.10 286	80.92 203	90.24 329	95.91 156	73.10 383	83.57 297	88.39 359	65.15 315	97.46 215	84.90 184	91.43 207	94.03 270

reproduce_monomvs		86.37 265	85.87 249	87.87 307	93.66 240	73.71 338	93.44 232	95.02 217	88.61 95	82.64 311	91.94 266	57.88 370	96.68 276	89.96 122	79.71 364	93.22 310

SCA		86.32 266	85.18 270	89.73 253	92.15 282	76.60 304	91.12 310	91.69 328	83.53 229	85.50 237	88.81 352	66.79 299	96.48 293	76.65 302	90.35 225	96.12 178

LTVRE_ROB	82.13 13	86.26 267	84.90 277	90.34 226	94.44 200	81.50 179	92.31 279	94.89 227	83.03 242	79.63 351	92.67 237	69.69 264	97.79 188	71.20 343	86.26 286	91.72 353
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
DTE-MVSNet		86.11 268	85.48 261	87.98 303	91.65 305	74.92 325	94.93 140	95.75 169	87.36 136	82.26 314	93.04 226	72.85 225	95.82 328	74.04 328	77.46 376	93.20 312

XVG-ACMP-BASELINE		86.00 269	84.84 279	89.45 264	91.20 318	78.00 276	91.70 295	95.55 185	85.05 193	82.97 306	92.25 252	54.49 386	97.48 212	82.93 209	87.45 276	92.89 324

MVP-Stereo		85.97 270	84.86 278	89.32 266	90.92 334	82.19 166	92.11 285	94.19 258	78.76 324	78.77 359	91.63 277	68.38 287	96.56 287	75.01 320	93.95 165	89.20 391
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
D2MVS		85.90 271	85.09 272	88.35 291	90.79 339	77.42 292	91.83 291	95.70 174	80.77 296	80.08 344	90.02 330	66.74 301	96.37 301	81.88 234	87.97 267	91.26 364

test-LLR		85.87 272	85.41 262	87.25 324	90.95 330	71.67 366	89.55 345	89.88 373	83.41 232	84.54 266	87.95 366	67.25 292	95.11 350	81.82 235	93.37 180	94.97 222

FMVSNet1		85.85 273	84.11 292	91.08 193	92.81 267	83.10 135	95.14 129	94.94 221	81.64 279	82.68 309	91.64 274	59.01 365	96.34 304	75.37 315	83.78 304	93.79 282

PatchmatchNet		85.85 273	84.70 281	89.29 267	91.76 299	75.54 319	88.49 363	91.30 340	81.63 280	85.05 256	88.70 356	71.71 235	96.24 308	74.61 325	89.05 250	96.08 181
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
myMVS_eth3d28		85.80 275	85.26 269	87.42 319	94.73 177	69.92 384	90.60 321	90.95 350	87.21 138	86.06 221	90.04 329	59.47 358	96.02 316	74.89 322	93.35 182	96.33 166

CostFormer		85.77 276	84.94 276	88.26 296	91.16 322	72.58 357	89.47 349	91.04 347	76.26 352	86.45 210	89.97 332	70.74 248	96.86 271	82.35 221	87.07 282	95.34 212

PMMVS		85.71 277	84.96 275	87.95 304	88.90 373	77.09 296	88.68 361	90.06 367	72.32 390	86.47 207	90.76 308	72.15 233	94.40 358	81.78 237	93.49 175	92.36 341

PVSNet	78.82 18	85.55 278	84.65 282	88.23 298	94.72 179	71.93 360	87.12 383	92.75 299	78.80 323	84.95 258	90.53 314	64.43 319	96.71 275	74.74 323	93.86 167	96.06 184

UBG		85.51 279	84.57 285	88.35 291	94.21 212	71.78 364	90.07 336	89.66 377	82.28 258	85.91 224	89.01 348	61.30 342	97.06 257	76.58 305	92.06 203	96.22 172

IterMVS-SCA-FT		85.45 280	84.53 286	88.18 299	91.71 301	76.87 299	90.19 333	92.65 302	85.40 184	81.44 325	90.54 313	66.79 299	95.00 353	81.04 248	81.05 343	92.66 331

pmmvs4		85.43 281	83.86 297	90.16 230	90.02 359	82.97 145	90.27 325	92.67 301	75.93 355	80.73 333	91.74 272	71.05 242	95.73 334	78.85 281	83.46 311	91.78 352

mvsany_test1		85.42 282	85.30 267	85.77 353	87.95 387	75.41 321	87.61 380	80.97 413	76.82 346	88.68 163	95.83 115	77.44 161	90.82 399	85.90 172	86.51 284	91.08 371

ACMH	80.38 17	85.36 283	83.68 299	90.39 222	94.45 199	80.63 210	94.73 154	94.85 231	82.09 261	77.24 368	92.65 238	60.01 355	97.58 204	72.25 339	84.87 295	92.96 321
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		85.35 284	84.64 283	87.49 316	90.77 340	72.59 356	94.01 206	94.40 249	84.72 204	79.62 352	93.17 220	61.91 335	96.72 273	81.99 231	81.16 339	93.16 314

CR-MVSNet		85.35 284	83.76 298	90.12 233	90.58 347	79.34 247	85.24 396	91.96 323	78.27 333	85.55 232	87.87 369	71.03 243	95.61 337	73.96 330	89.36 244	95.40 208

tpmrst		85.35 284	84.99 273	86.43 344	90.88 337	67.88 392	88.71 360	91.43 338	80.13 302	86.08 220	88.80 354	73.05 223	96.02 316	82.48 217	83.40 313	95.40 208

miper_lstm_enhance		85.27 287	84.59 284	87.31 321	91.28 317	74.63 328	87.69 377	94.09 264	81.20 292	81.36 327	89.85 335	74.97 192	94.30 361	81.03 250	79.84 363	93.01 320

IB-MVS	80.51 15	85.24 288	83.26 305	91.19 187	92.13 284	79.86 235	91.75 293	91.29 341	83.28 237	80.66 335	88.49 358	61.28 343	98.46 131	80.99 251	79.46 366	95.25 214
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
CHOSEN 280x420		85.15 289	83.99 295	88.65 285	92.47 274	78.40 267	79.68 418	92.76 298	74.90 366	81.41 326	89.59 339	69.85 263	95.51 341	79.92 268	95.29 139	92.03 348

RPSCF		85.07 290	84.27 287	87.48 317	92.91 266	70.62 379	91.69 296	92.46 304	76.20 353	82.67 310	95.22 139	63.94 322	97.29 238	77.51 295	85.80 288	94.53 244

MS-PatchMatch		85.05 291	84.16 290	87.73 309	91.42 311	78.51 263	91.25 307	93.53 279	77.50 339	80.15 341	91.58 280	61.99 334	95.51 341	75.69 312	94.35 161	89.16 392

ACMH+	81.04 14	85.05 291	83.46 302	89.82 247	94.66 183	79.37 245	94.44 172	94.12 263	82.19 260	78.04 362	92.82 232	58.23 368	97.54 207	73.77 332	82.90 319	92.54 333

mmtdpeth		85.04 293	84.15 291	87.72 310	93.11 255	75.74 317	94.37 181	92.83 295	84.98 194	89.31 154	86.41 383	61.61 339	97.14 251	92.63 69	62.11 411	90.29 379

WBMVS		84.97 294	84.18 289	87.34 320	94.14 217	71.62 368	90.20 332	92.35 306	81.61 281	84.06 282	90.76 308	61.82 336	96.52 290	78.93 280	83.81 303	93.89 273

IterMVS		84.88 295	83.98 296	87.60 312	91.44 308	76.03 312	90.18 334	92.41 305	83.24 238	81.06 331	90.42 318	66.60 302	94.28 362	79.46 272	80.98 348	92.48 335
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		84.86 296	83.09 308	90.14 232	93.80 232	80.05 227	89.18 354	93.09 288	78.89 319	78.19 360	91.91 267	65.86 312	97.27 239	68.47 363	88.45 258	93.11 316

testing222		84.84 297	83.32 303	89.43 265	94.15 216	75.94 313	91.09 311	89.41 381	84.90 196	85.78 226	89.44 342	52.70 393	96.28 307	70.80 349	91.57 206	96.07 182

tpm		84.73 298	84.02 294	86.87 337	90.33 352	68.90 387	89.06 356	89.94 370	80.85 295	85.75 227	89.86 334	68.54 285	95.97 319	77.76 291	84.05 302	95.75 196

tfpnnormal		84.72 299	83.23 306	89.20 269	92.79 268	80.05 227	94.48 167	95.81 164	82.38 255	81.08 330	91.21 288	69.01 279	96.95 265	61.69 395	80.59 352	90.58 378

CVMVSNet		84.69 300	84.79 280	84.37 366	91.84 295	64.92 404	93.70 223	91.47 337	66.19 407	86.16 219	95.28 136	67.18 294	93.33 376	80.89 253	90.42 224	94.88 230

SSC-MVS3.2		84.60 301	84.19 288	85.85 352	92.74 269	68.07 389	88.15 368	93.81 274	87.42 135	83.76 290	91.07 297	62.91 329	95.73 334	74.56 326	83.24 314	93.75 289

test-mter		84.54 302	83.64 300	87.25 324	90.95 330	71.67 366	89.55 345	89.88 373	79.17 314	84.54 266	87.95 366	55.56 378	95.11 350	81.82 235	93.37 180	94.97 222

ETVMVS		84.43 303	82.92 312	88.97 277	94.37 203	74.67 327	91.23 308	88.35 385	83.37 234	86.06 221	89.04 347	55.38 380	95.67 336	67.12 372	91.34 208	96.58 159

TransMVSNet (Re)		84.43 303	83.06 310	88.54 287	91.72 300	78.44 265	95.18 126	92.82 297	82.73 250	79.67 350	92.12 256	73.49 216	95.96 320	71.10 347	68.73 401	91.21 365

pmmvs5		84.21 305	82.84 315	88.34 293	88.95 372	76.94 298	92.41 271	91.91 325	75.63 357	80.28 339	91.18 291	64.59 318	95.57 338	77.09 300	83.47 310	92.53 334

dmvs_re		84.20 306	83.22 307	87.14 330	91.83 297	77.81 283	90.04 337	90.19 363	84.70 205	81.49 323	89.17 345	64.37 320	91.13 397	71.58 341	85.65 290	92.46 337

tpm2		84.08 307	82.94 311	87.48 317	91.39 312	71.27 369	89.23 353	90.37 360	71.95 392	84.64 263	89.33 343	67.30 291	96.55 289	75.17 317	87.09 281	94.63 237

test_fmvs2		83.98 308	84.03 293	83.83 371	87.16 390	67.53 396	93.93 212	92.89 293	77.62 338	86.89 200	93.53 208	47.18 405	92.02 389	90.54 116	86.51 284	91.93 350

COLMAP_ROB	80.39 16	83.96 309	82.04 318	89.74 251	95.28 145	79.75 237	94.25 186	92.28 310	75.17 362	78.02 363	93.77 203	58.60 367	97.84 187	65.06 385	85.92 287	91.63 355
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RPMNet		83.95 310	81.53 321	91.21 186	90.58 347	79.34 247	85.24 396	96.76 81	71.44 394	85.55 232	82.97 403	70.87 246	98.91 87	61.01 397	89.36 244	95.40 208

SixPastTwentyTwo		83.91 311	82.90 313	86.92 334	90.99 328	70.67 378	93.48 229	91.99 320	85.54 181	77.62 367	92.11 258	60.59 351	96.87 270	76.05 311	77.75 373	93.20 312

EPMVS		83.90 312	82.70 316	87.51 314	90.23 355	72.67 352	88.62 362	81.96 411	81.37 286	85.01 257	88.34 360	66.31 306	94.45 356	75.30 316	87.12 280	95.43 207

WB-MVSnew		83.77 313	83.28 304	85.26 360	91.48 307	71.03 373	91.89 288	87.98 386	78.91 317	84.78 260	90.22 321	69.11 278	94.02 365	64.70 386	90.44 222	90.71 373

TESTMET0.1,1		83.74 314	82.85 314	86.42 345	89.96 360	71.21 371	89.55 345	87.88 387	77.41 340	83.37 301	87.31 374	56.71 374	93.65 373	80.62 258	92.85 192	94.40 254

UWE-MVS		83.69 315	83.09 308	85.48 355	93.06 258	65.27 403	90.92 314	86.14 395	79.90 305	86.26 216	90.72 311	57.17 373	95.81 329	71.03 348	92.62 195	95.35 211

pmmvs6		83.42 316	81.60 320	88.87 278	88.01 385	77.87 281	94.96 138	94.24 257	74.67 368	78.80 358	91.09 296	60.17 354	96.49 292	77.06 301	75.40 385	92.23 345

AllTest		83.42 316	81.39 322	89.52 261	95.01 159	77.79 285	93.12 248	90.89 353	77.41 340	76.12 376	93.34 211	54.08 388	97.51 210	68.31 365	84.27 300	93.26 306

tpmvs		83.35 318	82.07 317	87.20 328	91.07 326	71.00 375	88.31 366	91.70 327	78.91 317	80.49 338	87.18 378	69.30 273	97.08 254	68.12 368	83.56 309	93.51 300

USDC		82.76 319	81.26 324	87.26 323	91.17 320	74.55 329	89.27 351	93.39 282	78.26 334	75.30 382	92.08 260	54.43 387	96.63 278	71.64 340	85.79 289	90.61 375

Patchmtry		82.71 320	80.93 326	88.06 301	90.05 358	76.37 309	84.74 401	91.96 323	72.28 391	81.32 328	87.87 369	71.03 243	95.50 343	68.97 360	80.15 358	92.32 343

PatchT		82.68 321	81.27 323	86.89 336	90.09 357	70.94 376	84.06 403	90.15 364	74.91 365	85.63 231	83.57 398	69.37 269	94.87 355	65.19 382	88.50 257	94.84 231

MIMVSNet		82.59 322	80.53 327	88.76 280	91.51 306	78.32 269	86.57 387	90.13 365	79.32 311	80.70 334	88.69 357	52.98 392	93.07 381	66.03 380	88.86 252	94.90 229

test0.0.03 1		82.41 323	81.69 319	84.59 364	88.23 381	72.89 348	90.24 329	87.83 388	83.41 232	79.86 348	89.78 336	67.25 292	88.99 409	65.18 383	83.42 312	91.90 351

EG-PatchMatch MVS		82.37 324	80.34 330	88.46 288	90.27 353	79.35 246	92.80 263	94.33 252	77.14 344	73.26 393	90.18 324	47.47 404	96.72 273	70.25 351	87.32 279	89.30 388

tpm cat1		81.96 325	80.27 331	87.01 331	91.09 325	71.02 374	87.38 381	91.53 335	66.25 406	80.17 340	86.35 385	68.22 288	96.15 312	69.16 359	82.29 325	93.86 279

our_test_3		81.93 326	80.46 329	86.33 346	88.46 378	73.48 342	88.46 364	91.11 343	76.46 347	76.69 372	88.25 362	66.89 297	94.36 359	68.75 361	79.08 369	91.14 367

ppachtmachnet_test		81.84 327	80.07 335	87.15 329	88.46 378	74.43 332	89.04 357	92.16 314	75.33 360	77.75 365	88.99 349	66.20 308	95.37 346	65.12 384	77.60 374	91.65 354

gg-mvs-nofinetune		81.77 328	79.37 343	88.99 276	90.85 338	77.73 288	86.29 388	79.63 416	74.88 367	83.19 305	69.05 419	60.34 352	96.11 313	75.46 314	94.64 153	93.11 316

CL-MVSNet_self_test		81.74 329	80.53 327	85.36 357	85.96 396	72.45 358	90.25 327	93.07 289	81.24 290	79.85 349	87.29 375	70.93 245	92.52 384	66.95 373	69.23 397	91.11 369

Patchmatch-RL test		81.67 330	79.96 336	86.81 338	85.42 401	71.23 370	82.17 411	87.50 391	78.47 328	77.19 369	82.50 405	70.81 247	93.48 374	82.66 216	72.89 389	95.71 200

ADS-MVSNet2		81.66 331	79.71 340	87.50 315	91.35 314	74.19 334	83.33 406	88.48 384	72.90 385	82.24 315	85.77 389	64.98 316	93.20 379	64.57 387	83.74 305	95.12 217

K. test v3		81.59 332	80.15 334	85.91 351	89.89 362	69.42 386	92.57 268	87.71 389	85.56 180	73.44 392	89.71 338	55.58 377	95.52 340	77.17 298	69.76 395	92.78 328

ADS-MVSNet		81.56 333	79.78 337	86.90 335	91.35 314	71.82 362	83.33 406	89.16 382	72.90 385	82.24 315	85.77 389	64.98 316	93.76 370	64.57 387	83.74 305	95.12 217

FMVSNet5		81.52 334	79.60 341	87.27 322	91.17 320	77.95 277	91.49 300	92.26 312	76.87 345	76.16 375	87.91 368	51.67 394	92.34 386	67.74 369	81.16 339	91.52 358

dp		81.47 335	80.23 332	85.17 361	89.92 361	65.49 401	86.74 385	90.10 366	76.30 351	81.10 329	87.12 379	62.81 330	95.92 322	68.13 367	79.88 361	94.09 266

Patchmatch-test		81.37 336	79.30 344	87.58 313	90.92 334	74.16 335	80.99 413	87.68 390	70.52 398	76.63 373	88.81 352	71.21 240	92.76 383	60.01 401	86.93 283	95.83 193

EU-MVSNet		81.32 337	80.95 325	82.42 379	88.50 377	63.67 408	93.32 237	91.33 339	64.02 410	80.57 337	92.83 231	61.21 346	92.27 387	76.34 307	80.38 357	91.32 362

test_0402		81.30 338	79.17 348	87.67 311	93.19 252	78.17 273	92.98 255	91.71 326	75.25 361	76.02 378	90.31 319	59.23 361	96.37 301	50.22 414	83.63 308	88.47 399

JIA-IIPM		81.04 339	78.98 352	87.25 324	88.64 374	73.48 342	81.75 412	89.61 379	73.19 382	82.05 318	73.71 415	66.07 311	95.87 325	71.18 345	84.60 297	92.41 339

Anonymous20231206		81.03 340	79.77 339	84.82 363	87.85 388	70.26 381	91.42 301	92.08 316	73.67 377	77.75 365	89.25 344	62.43 332	93.08 380	61.50 396	82.00 330	91.12 368

mvs5depth		80.98 341	79.15 349	86.45 343	84.57 404	73.29 344	87.79 373	91.67 329	80.52 298	82.20 317	89.72 337	55.14 383	95.93 321	73.93 331	66.83 403	90.12 381

pmmvs-eth3d		80.97 342	78.72 354	87.74 308	84.99 403	79.97 233	90.11 335	91.65 330	75.36 359	73.51 391	86.03 386	59.45 359	93.96 368	75.17 317	72.21 390	89.29 390

testgi		80.94 343	80.20 333	83.18 372	87.96 386	66.29 397	91.28 305	90.70 357	83.70 223	78.12 361	92.84 230	51.37 395	90.82 399	63.34 390	82.46 323	92.43 338

CMPMVS	59.16 21	80.52 344	79.20 347	84.48 365	83.98 405	67.63 395	89.95 340	93.84 273	64.79 409	66.81 407	91.14 294	57.93 369	95.17 348	76.25 308	88.10 263	90.65 374
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing3		80.46 345	79.59 342	83.06 374	93.44 247	64.64 405	93.33 236	85.47 400	84.34 211	79.93 347	90.84 304	44.35 411	92.39 385	57.06 408	87.56 273	92.16 347

Anonymous20240521		80.44 346	79.21 346	84.11 369	85.75 399	67.89 391	92.86 261	93.23 285	75.61 358	75.59 381	87.47 373	50.03 397	94.33 360	71.14 346	81.21 338	90.12 381

LF4IMVS		80.37 347	79.07 351	84.27 368	86.64 392	69.87 385	89.39 350	91.05 346	76.38 349	74.97 384	90.00 331	47.85 403	94.25 363	74.55 327	80.82 350	88.69 397

KD-MVS_self_test		80.20 348	79.24 345	83.07 373	85.64 400	65.29 402	91.01 313	93.93 267	78.71 326	76.32 374	86.40 384	59.20 362	92.93 382	72.59 337	69.35 396	91.00 372

Syy-MVS		80.07 349	79.78 337	80.94 383	91.92 291	59.93 415	89.75 343	87.40 392	81.72 276	78.82 356	87.20 376	66.29 307	91.29 395	47.06 416	87.84 270	91.60 356

UnsupCasMVSNet_eth		80.07 349	78.27 356	85.46 356	85.24 402	72.63 355	88.45 365	94.87 230	82.99 244	71.64 399	88.07 365	56.34 375	91.75 392	73.48 334	63.36 409	92.01 349

test20.03		79.95 351	79.08 350	82.55 376	85.79 398	67.74 394	91.09 311	91.08 344	81.23 291	74.48 388	89.96 333	61.63 337	90.15 401	60.08 399	76.38 381	89.76 383

TDRefinement		79.81 352	77.34 358	87.22 327	79.24 418	75.48 320	93.12 248	92.03 318	76.45 348	75.01 383	91.58 280	49.19 400	96.44 297	70.22 353	69.18 398	89.75 384

TinyColmap		79.76 353	77.69 357	85.97 348	91.71 301	73.12 345	89.55 345	90.36 361	75.03 363	72.03 397	90.19 323	46.22 408	96.19 311	63.11 391	81.03 344	88.59 398

myMVS_eth3d		79.67 354	78.79 353	82.32 380	91.92 291	64.08 406	89.75 343	87.40 392	81.72 276	78.82 356	87.20 376	45.33 409	91.29 395	59.09 403	87.84 270	91.60 356

OpenMVS_ROB	74.94 19	79.51 355	77.03 363	86.93 333	87.00 391	76.23 311	92.33 277	90.74 356	68.93 402	74.52 387	88.23 363	49.58 399	96.62 279	57.64 406	84.29 299	87.94 402

MIMVSNet1		79.38 356	77.28 359	85.69 354	86.35 393	73.67 339	91.61 298	92.75 299	78.11 337	72.64 395	88.12 364	48.16 402	91.97 391	60.32 398	77.49 375	91.43 361

YYNet1		79.22 357	77.20 360	85.28 359	88.20 383	72.66 353	85.87 390	90.05 369	74.33 371	62.70 410	87.61 371	66.09 310	92.03 388	66.94 374	72.97 388	91.15 366

MDA-MVSNet_test_wron		79.21 358	77.19 361	85.29 358	88.22 382	72.77 350	85.87 390	90.06 367	74.34 370	62.62 412	87.56 372	66.14 309	91.99 390	66.90 377	73.01 387	91.10 370

UWE-MVS-28		78.98 359	78.38 355	80.80 384	88.18 384	60.66 414	90.65 319	78.51 418	78.84 321	77.93 364	90.93 301	59.08 364	89.02 408	50.96 413	90.33 226	92.72 329

MDA-MVSNet-bldmvs		78.85 360	76.31 365	86.46 342	89.76 363	73.88 336	88.79 359	90.42 359	79.16 315	59.18 415	88.33 361	60.20 353	94.04 364	62.00 394	68.96 399	91.48 360

KD-MVS_2432*1600		78.50 361	76.02 368	85.93 349	86.22 394	74.47 330	84.80 399	92.33 307	79.29 312	76.98 370	85.92 387	53.81 390	93.97 366	67.39 370	57.42 416	89.36 386

miper_refine_blended		78.50 361	76.02 368	85.93 349	86.22 394	74.47 330	84.80 399	92.33 307	79.29 312	76.98 370	85.92 387	53.81 390	93.97 366	67.39 370	57.42 416	89.36 386

PM-MVS		78.11 363	76.12 367	84.09 370	83.54 407	70.08 382	88.97 358	85.27 402	79.93 304	74.73 386	86.43 382	34.70 419	93.48 374	79.43 275	72.06 391	88.72 396

test_vis1_rt		77.96 364	76.46 364	82.48 378	85.89 397	71.74 365	90.25 327	78.89 417	71.03 397	71.30 400	81.35 407	42.49 413	91.05 398	84.55 189	82.37 324	84.65 405

test_fmvs3		77.67 365	77.16 362	79.22 387	79.52 417	61.14 412	92.34 276	91.64 331	73.98 374	78.86 355	86.59 380	27.38 423	87.03 411	88.12 143	75.97 383	89.50 385

PVSNet_0	73.20 20	77.22 366	74.83 372	84.37 366	90.70 344	71.10 372	83.09 408	89.67 376	72.81 387	73.93 390	83.13 400	60.79 350	93.70 372	68.54 362	50.84 421	88.30 400

DSMNet-mixed		76.94 367	76.29 366	78.89 388	83.10 409	56.11 424	87.78 374	79.77 415	60.65 414	75.64 380	88.71 355	61.56 340	88.34 410	60.07 400	89.29 246	92.21 346

ttmdpeth		76.55 368	74.64 373	82.29 381	82.25 412	67.81 393	89.76 342	85.69 398	70.35 399	75.76 379	91.69 273	46.88 406	89.77 403	66.16 379	63.23 410	89.30 388

new-patchmatchnet		76.41 369	75.17 371	80.13 385	82.65 411	59.61 416	87.66 378	91.08 344	78.23 335	69.85 403	83.22 399	54.76 384	91.63 394	64.14 389	64.89 407	89.16 392

UnsupCasMVSNet_bld		76.23 370	73.27 374	85.09 362	83.79 406	72.92 347	85.65 393	93.47 281	71.52 393	68.84 405	79.08 410	49.77 398	93.21 378	66.81 378	60.52 413	89.13 394

mvsany_test3		74.95 371	73.26 375	80.02 386	74.61 422	63.16 410	85.53 394	78.42 419	74.16 372	74.89 385	86.46 381	36.02 418	89.09 407	82.39 220	66.91 402	87.82 403

dmvs_testset		74.57 372	75.81 370	70.86 398	87.72 389	40.47 433	87.05 384	77.90 423	82.75 249	71.15 401	85.47 391	67.98 289	84.12 420	45.26 417	76.98 380	88.00 401

MVS-HIRNet		73.70 373	72.20 376	78.18 391	91.81 298	56.42 423	82.94 409	82.58 409	55.24 417	68.88 404	66.48 420	55.32 381	95.13 349	58.12 405	88.42 259	83.01 408

MVStest1		72.91 374	69.70 379	82.54 377	78.14 419	73.05 346	88.21 367	86.21 394	60.69 413	64.70 408	90.53 314	46.44 407	85.70 416	58.78 404	53.62 418	88.87 395

new_pmnet		72.15 375	70.13 378	78.20 390	82.95 410	65.68 399	83.91 404	82.40 410	62.94 412	64.47 409	79.82 409	42.85 412	86.26 415	57.41 407	74.44 386	82.65 410

test_f		71.95 376	70.87 377	75.21 394	74.21 424	59.37 417	85.07 398	85.82 397	65.25 408	70.42 402	83.13 400	23.62 424	82.93 422	78.32 285	71.94 392	83.33 407

pmmvs3		71.81 377	68.71 380	81.11 382	75.86 421	70.42 380	86.74 385	83.66 406	58.95 416	68.64 406	80.89 408	36.93 417	89.52 405	63.10 392	63.59 408	83.39 406

APD_test1		69.04 378	66.26 384	77.36 393	80.51 415	62.79 411	85.46 395	83.51 407	54.11 419	59.14 416	84.79 394	23.40 426	89.61 404	55.22 409	70.24 394	79.68 414

N_pmnet		68.89 379	68.44 381	70.23 399	89.07 371	28.79 438	88.06 369	19.50 438	69.47 401	71.86 398	84.93 392	61.24 345	91.75 392	54.70 410	77.15 377	90.15 380

WB-MVS		67.92 380	67.49 382	69.21 402	81.09 413	41.17 432	88.03 370	78.00 422	73.50 379	62.63 411	83.11 402	63.94 322	86.52 413	25.66 428	51.45 420	79.94 413

SSC-MVS		67.06 381	66.56 383	68.56 404	80.54 414	40.06 434	87.77 375	77.37 425	72.38 389	61.75 413	82.66 404	63.37 325	86.45 414	24.48 429	48.69 423	79.16 415

LCM-MVSNet		66.00 382	62.16 387	77.51 392	64.51 432	58.29 418	83.87 405	90.90 352	48.17 421	54.69 418	73.31 416	16.83 432	86.75 412	65.47 381	61.67 412	87.48 404

test_vis3_rt		65.12 383	62.60 385	72.69 396	71.44 425	60.71 413	87.17 382	65.55 429	63.80 411	53.22 419	65.65 422	14.54 433	89.44 406	76.65 302	65.38 405	67.91 420

FPMVS		64.63 384	62.55 386	70.88 397	70.80 426	56.71 419	84.42 402	84.42 404	51.78 420	49.57 420	81.61 406	23.49 425	81.48 423	40.61 423	76.25 382	74.46 416

EGC-MVSNET		61.97 385	56.37 390	78.77 389	89.63 366	73.50 341	89.12 355	82.79 408	0.21 435	1.24 436	84.80 393	39.48 414	90.04 402	44.13 418	75.94 384	72.79 417

PMMVS2		59.60 386	56.40 389	69.21 402	68.83 429	46.58 428	73.02 423	77.48 424	55.07 418	49.21 421	72.95 417	17.43 431	80.04 424	49.32 415	44.33 424	80.99 412

testf1		59.54 387	56.11 391	69.85 400	69.28 427	56.61 421	80.37 415	76.55 426	42.58 424	45.68 423	75.61 411	11.26 434	84.18 418	43.20 420	60.44 414	68.75 418

APD_test2		59.54 387	56.11 391	69.85 400	69.28 427	56.61 421	80.37 415	76.55 426	42.58 424	45.68 423	75.61 411	11.26 434	84.18 418	43.20 420	60.44 414	68.75 418

ANet_high		58.88 389	54.22 394	72.86 395	56.50 435	56.67 420	80.75 414	86.00 396	73.09 384	37.39 427	64.63 423	22.17 427	79.49 425	43.51 419	23.96 429	82.43 411

dongtai		58.82 390	58.24 388	60.56 407	83.13 408	45.09 431	82.32 410	48.22 437	67.61 404	61.70 414	69.15 418	38.75 415	76.05 426	32.01 425	41.31 425	60.55 422

Gipuma		57.99 391	54.91 393	67.24 405	88.51 375	65.59 400	52.21 426	90.33 362	43.58 423	42.84 426	51.18 427	20.29 429	85.07 417	34.77 424	70.45 393	51.05 426
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		53.51 392	53.30 395	54.13 411	76.06 420	45.36 430	80.11 417	48.36 436	59.63 415	54.84 417	63.43 424	37.41 416	62.07 431	20.73 431	39.10 426	54.96 425

PMVS	47.18 22	52.22 393	48.46 397	63.48 406	45.72 437	46.20 429	73.41 422	78.31 420	41.03 426	30.06 429	65.68 421	6.05 436	83.43 421	30.04 426	65.86 404	60.80 421
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		50.52 394	48.47 396	56.66 409	52.26 436	18.98 440	41.51 428	81.40 412	10.10 430	44.59 425	75.01 414	28.51 421	68.16 427	53.54 411	49.31 422	82.83 409

MVE	39.65 23	43.39 395	38.59 401	57.77 408	56.52 434	48.77 427	55.38 425	58.64 433	29.33 429	28.96 430	52.65 426	4.68 437	64.62 430	28.11 427	33.07 427	59.93 423
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		43.23 396	42.29 398	46.03 412	65.58 431	37.41 435	73.51 421	64.62 430	33.99 427	28.47 431	47.87 428	19.90 430	67.91 428	22.23 430	24.45 428	32.77 427

EMVS		42.07 397	41.12 399	44.92 413	63.45 433	35.56 437	73.65 420	63.48 431	33.05 428	26.88 432	45.45 429	21.27 428	67.14 429	19.80 432	23.02 430	32.06 428

tmp_tt		35.64 398	39.24 400	24.84 414	14.87 438	23.90 439	62.71 424	51.51 435	6.58 432	36.66 428	62.08 425	44.37 410	30.34 434	52.40 412	22.00 431	20.27 429

cdsmvs_eth3d_5k		22.14 399	29.52 402	0.00 418	0.00 441	0.00 443	0.00 429	95.76 168	0.00 436	0.00 437	94.29 178	75.66 184	0.00 437	0.00 436	0.00 435	0.00 433

wuyk23d		21.27 400	20.48 403	23.63 415	68.59 430	36.41 436	49.57 427	6.85 439	9.37 431	7.89 433	4.46 435	4.03 438	31.37 433	17.47 433	16.07 432	3.12 430

testmvs		8.92 401	11.52 404	1.12 417	1.06 439	0.46 442	86.02 389	0.65 440	0.62 433	2.74 434	9.52 433	0.31 440	0.45 436	2.38 434	0.39 433	2.46 432

test123		8.76 402	11.22 405	1.39 416	0.85 440	0.97 441	85.76 392	0.35 441	0.54 434	2.45 435	8.14 434	0.60 439	0.48 435	2.16 435	0.17 434	2.71 431

ab-mvs-re		7.82 403	10.43 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	93.88 198	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		6.64 404	8.86 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	79.70 133	0.00 437	0.00 436	0.00 435	0.00 433

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

WAC-MVS						64.08 406								59.14 402

FOURS1					98.86 1	85.54 67	98.29 1	97.49 6	89.79 54	96.29 23

MSC_two_6792asdad				96.52 1	97.78 54	90.86 1		96.85 69					99.61 4	96.03 20	99.06 9	99.07 5

PC_three_1452									82.47 253	97.09 12	97.07 60	92.72 1	98.04 175	92.70 68	99.02 12	98.86 11

No_MVS				96.52 1	97.78 54	90.86 1		96.85 69					99.61 4	96.03 20	99.06 9	99.07 5

test_one_0601					98.58 11	85.83 61		97.44 15	91.05 15	96.78 19	98.06 16	91.45 11

eth-test2					0.00 441

eth-test					0.00 441

ZD-MVS					98.15 34	86.62 33		97.07 50	83.63 225	94.19 53	96.91 66	87.57 31	99.26 45	91.99 90	98.44 53

RE-MVS-def			93.68 61		97.92 43	84.57 87	96.28 43	96.76 81	87.46 132	93.75 63	97.43 39	82.94 92		92.73 64	97.80 79	97.88 87

IU-MVS					98.77 5	86.00 50		96.84 71	81.26 289	97.26 8				95.50 29	99.13 3	99.03 8

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 58	92.59 2	98.94 83	92.25 79	98.99 14	98.84 14

test_241102_TWO								97.44 15	90.31 32	97.62 5	98.07 14	91.46 10	99.58 10	95.66 23	99.12 6	98.98 10

test_241102_ONE					98.77 5	85.99 52		97.44 15	90.26 38	97.71 1	97.96 24	92.31 4	99.38 31

9.14			94.47 25		97.79 52		96.08 61	97.44 15	86.13 169	95.10 43	97.40 41	88.34 22	99.22 47	93.25 56	98.70 34

save fliter					97.85 49	85.63 66	95.21 123	96.82 74	89.44 64

test_0728_THIRD									90.75 21	97.04 14	98.05 18	92.09 6	99.55 16	95.64 25	99.13 3	99.13 2

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 16	97.49 6					99.61 4	95.62 27	99.08 7	98.99 9

test0726					98.78 3	85.93 55	97.19 11	97.47 11	90.27 36	97.64 4	98.13 4	91.47 8

GSMVS																96.12 178

test_part2					98.55 12	87.22 19				96.40 22

sam_mvs1												71.70 236				96.12 178

sam_mvs												70.60 249

ambc				83.06 374	79.99 416	63.51 409	77.47 419	92.86 294		74.34 389	84.45 395	28.74 420	95.06 352	73.06 336	68.89 400	90.61 375

MTGPA								96.97 55

test_post1							88.00 371				9.81 432	69.31 272	95.53 339	76.65 302

test_post											10.29 431	70.57 253	95.91 324

patchmatchnet-post											83.76 397	71.53 237	96.48 293

GG-mvs-BLEND				87.94 305	89.73 365	77.91 278	87.80 372	78.23 421		80.58 336	83.86 396	59.88 356	95.33 347	71.20 343	92.22 201	90.60 377

MTMP							96.16 52	60.64 432

gm-plane-assit					89.60 367	68.00 390			77.28 343		88.99 349		97.57 205	79.44 274

test9_res														91.91 94	98.71 32	98.07 74

TEST9					97.53 61	86.49 37	94.07 200	96.78 78	81.61 281	92.77 88	96.20 96	87.71 28	99.12 54

test_8					97.49 63	86.30 45	94.02 205	96.76 81	81.86 272	92.70 92	96.20 96	87.63 29	99.02 64

agg_prior2														90.54 116	98.68 37	98.27 57

agg_prior					97.38 66	85.92 57		96.72 88		92.16 104			98.97 78

TestCases				89.52 261	95.01 159	77.79 285		90.89 353	77.41 340	76.12 376	93.34 211	54.08 388	97.51 210	68.31 365	84.27 300	93.26 306

test_prior4						85.96 54	94.11 195

test_prior2							94.12 193		87.67 130	92.63 94	96.39 91	86.62 40		91.50 102	98.67 40

test_prior				93.82 66	97.29 70	84.49 91		96.88 67					98.87 89			98.11 73

旧先验2							93.36 235		71.25 395	94.37 49			97.13 252	86.74 161

新几何2							93.11 250

新几何1				93.10 90	97.30 69	84.35 100		95.56 184	71.09 396	91.26 128	96.24 94	82.87 94	98.86 91	79.19 278	98.10 67	96.07 182

旧先验1					96.79 79	81.81 173		95.67 176			96.81 72	86.69 39			97.66 85	96.97 140

无先验							93.28 243	96.26 123	73.95 375				99.05 58	80.56 259		96.59 158

原ACMM2							92.94 257

原ACMM1				92.01 146	97.34 67	81.05 197		96.81 76	78.89 319	90.45 135	95.92 110	82.65 96	98.84 95	80.68 257	98.26 59	96.14 176

test222					96.55 88	81.70 175	92.22 281	95.01 218	68.36 403	90.20 140	96.14 101	80.26 126			97.80 79	96.05 185

testdata2													98.75 103	78.30 286

segment_acmp												87.16 36

testdata				90.49 216	96.40 93	77.89 280		95.37 202	72.51 388	93.63 66	96.69 75	82.08 110	97.65 198	83.08 206	97.39 89	95.94 187

testdata1							92.15 283		87.94 117

test12				94.34 52	97.13 73	86.15 48		96.29 118		91.04 130		85.08 61	99.01 66		98.13 66	97.86 89

plane_prior7					94.70 181	82.74 151

plane_prior6					94.52 193	82.75 149						74.23 202

plane_prior5								96.22 128					98.12 160	88.15 140	89.99 229	94.63 237

plane_prior4											94.86 155

plane_prior3						82.75 149			90.26 38	86.91 197

plane_prior2							95.85 83		90.81 19

plane_prior1					94.59 187

plane_prior						82.73 152	95.21 123		89.66 59						89.88 234

n2								0.00 442

nn								0.00 442

door-mid								85.49 399

lessismore_v0				86.04 347	88.46 378	68.78 388		80.59 414		73.01 394	90.11 327	55.39 379	96.43 298	75.06 319	65.06 406	92.90 323

LGP-MVS_train				91.12 189	94.47 196	81.49 181		96.14 133	86.73 152	85.45 240	95.16 144	69.89 261	98.10 162	87.70 147	89.23 247	93.77 287

test11								96.57 99

door								85.33 401

HQP5-MVS						81.56 177

HQP-NCC					94.17 213		94.39 177		88.81 85	85.43 243

ACMP_Plane					94.17 213		94.39 177		88.81 85	85.43 243

BP-MVS														87.11 158

HQP4-MVS										85.43 243			97.96 181			94.51 247

HQP3-MVS								96.04 145							89.77 238

HQP2-MVS												73.83 212

NP-MVS					94.37 203	82.42 161					93.98 191

MDTV_nov1_ep13_2view						55.91 425	87.62 379		73.32 381	84.59 265		70.33 256		74.65 324		95.50 205

MDTV_nov1_ep13			83.56 301		91.69 303	69.93 383	87.75 376	91.54 334	78.60 327	84.86 259	88.90 351	69.54 267	96.03 315	70.25 351	88.93 251

ACMMP++_ref															87.47 274

ACMMP++															88.01 266

Test By Simon												80.02 128

ITE_SJBPF				88.24 297	91.88 294	77.05 297		92.92 292	85.54 181	80.13 343	93.30 215	57.29 372	96.20 309	72.46 338	84.71 296	91.49 359

DeepMVS_CX				56.31 410	74.23 423	51.81 426		56.67 434	44.85 422	48.54 422	75.16 413	27.87 422	58.74 432	40.92 422	52.22 419	58.39 424

High-resolution multi-view benchmark