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++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 59	95.06 1	94.23 3	78.38 35	92.78 4	95.74 6	82.45 3	97.49 4	89.42 16	96.68 2	94.95 11

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 66	93.57 7	94.06 10	77.24 56	93.10 1	95.72 8	82.99 1	97.44 7	89.07 21	96.63 4	94.88 15

DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 59	93.49 9	92.73 64	77.33 53	92.12 9	95.78 4	80.98 9	97.40 9	89.08 19	96.41 12	93.33 97
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		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 43	94.10 8	75.90 93	92.29 7	95.66 10	81.67 6	97.38 11	87.44 41	96.34 15	93.95 63
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 16	94.11 6	80.27 10	91.35 14	94.16 45	78.35 13	96.77 24	89.59 14	94.22 60	94.67 28
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
APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 97	91.06 16	96.03 1	76.84 14	97.03 17	89.09 18	95.65 27	94.47 38
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MM		89.16 6	89.23 7	88.97 4	90.79 95	73.65 10	92.66 23	91.17 127	86.57 1	87.39 49	94.97 19	71.70 55	97.68 1	92.19 1	95.63 28	95.57 1

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 123	92.29 7	95.97 2	74.28 29	97.24 13	88.58 29	96.91 1	94.87 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
HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 27	92.85 59	80.26 11	87.78 40	94.27 39	75.89 19	96.81 23	87.45 40	96.44 9	93.05 113

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 62	93.00 46	80.90 7	88.06 35	94.06 50	76.43 16	96.84 21	88.48 32	95.99 18	94.34 45

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 72	72.96 25	93.73 5	93.67 20	80.19 12	88.10 34	94.80 21	73.76 33	97.11 15	87.51 39	95.82 21	94.90 14
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		88.46 12	88.74 12	87.64 35	92.78 64	71.95 49	92.40 24	94.74 2	75.71 95	89.16 21	95.10 16	75.65 21	96.19 46	87.07 42	96.01 17	94.79 22

DeepPCF-MVS	80.84 1	88.10 13	88.56 13	86.73 53	92.24 71	69.03 103	89.57 90	93.39 30	77.53 49	89.79 19	94.12 47	78.98 12	96.58 35	85.66 49	95.72 24	94.58 33

SD-MVS		88.06 14	88.50 14	86.71 54	92.60 69	72.71 29	91.81 41	93.19 35	77.87 39	90.32 17	94.00 54	74.83 23	93.78 142	87.63 38	94.27 59	93.65 81
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
9.14			88.26 15		92.84 63		91.52 48	94.75 1	73.93 144	88.57 27	94.67 23	75.57 22	95.79 58	86.77 43	95.76 23

TSAR-MVS + MP.		88.02 17	88.11 16	87.72 30	93.68 43	72.13 46	91.41 50	92.35 82	74.62 127	88.90 24	93.85 62	75.75 20	96.00 54	87.80 36	94.63 48	95.04 9
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMMP_NAP		88.05 16	88.08 17	87.94 19	93.70 41	73.05 22	90.86 57	93.59 23	76.27 87	88.14 33	95.09 17	71.06 65	96.67 29	87.67 37	96.37 14	94.09 55

NCCC		88.06 14	88.01 18	88.24 11	94.41 22	73.62 11	91.22 54	92.83 60	81.50 5	85.79 63	93.47 71	73.02 41	97.00 18	84.90 55	94.94 40	94.10 54

ZNCC-MVS		87.94 18	87.85 19	88.20 12	94.39 24	73.33 19	93.03 14	93.81 17	76.81 69	85.24 68	94.32 37	71.76 53	96.93 19	85.53 52	95.79 22	94.32 46

MP-MVS-pluss		87.67 21	87.72 20	87.54 36	93.64 44	72.04 48	89.80 81	93.50 25	75.17 112	86.34 59	95.29 15	70.86 67	96.00 54	88.78 27	96.04 16	94.58 33
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		87.71 19	87.64 21	87.93 21	94.36 26	73.88 6	92.71 22	92.65 70	77.57 45	83.84 98	94.40 34	72.24 47	96.28 43	85.65 50	95.30 35	93.62 84
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
reproduce-ours		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 115	88.96 22	95.54 12	71.20 63	96.54 36	86.28 46	93.49 65	93.06 111

our_new_method		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 115	88.96 22	95.54 12	71.20 63	96.54 36	86.28 46	93.49 65	93.06 111

MVS_0304		87.69 20	87.55 24	88.12 13	89.45 130	71.76 51	91.47 49	89.54 179	82.14 3	86.65 57	94.28 38	68.28 101	97.46 6	90.81 5	95.31 34	95.15 7

APD-MVS		87.44 25	87.52 25	87.19 42	94.24 32	72.39 39	91.86 40	92.83 60	73.01 169	88.58 26	94.52 25	73.36 34	96.49 38	84.26 66	95.01 37	92.70 123
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HFP-MVS		87.58 22	87.47 26	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 71	84.91 73	94.44 32	70.78 68	96.61 32	84.53 63	94.89 42	93.66 77

fmvsm_s_conf0.5_n_3		86.36 47	87.46 27	83.09 176	87.08 231	65.21 200	89.09 113	90.21 158	79.67 18	89.98 18	95.02 18	73.17 38	91.71 236	91.30 2	91.60 89	92.34 138

reproduce_model		87.28 30	87.39 28	86.95 48	93.10 56	71.24 63	91.60 42	93.19 35	74.69 124	88.80 25	95.61 11	70.29 74	96.44 39	86.20 48	93.08 69	93.16 106

GST-MVS		87.42 27	87.26 29	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 67	84.68 77	93.99 56	70.67 70	96.82 22	84.18 70	95.01 37	93.90 66

MCST-MVS		87.37 29	87.25 30	87.73 28	94.53 17	72.46 38	89.82 79	93.82 16	73.07 167	84.86 76	92.89 86	76.22 17	96.33 41	84.89 57	95.13 36	94.40 41

ACMMPR		87.44 25	87.23 31	88.08 15	94.64 13	73.59 12	93.04 12	93.20 34	76.78 71	84.66 80	94.52 25	68.81 94	96.65 30	84.53 63	94.90 41	94.00 60

region2R		87.42 27	87.20 32	88.09 14	94.63 14	73.55 13	93.03 14	93.12 40	76.73 74	84.45 85	94.52 25	69.09 88	96.70 27	84.37 65	94.83 45	94.03 58

fmvsm_s_conf0.5_n_8		86.56 42	87.17 33	84.73 103	87.76 208	65.62 191	89.20 104	92.21 89	79.94 16	89.74 20	94.86 20	68.63 96	94.20 122	90.83 4	91.39 94	94.38 42

MTAPA		87.23 31	87.00 34	87.90 22	94.18 35	74.25 5	86.58 201	92.02 94	79.45 21	85.88 61	94.80 21	68.07 102	96.21 45	86.69 44	95.34 32	93.23 100

balanced_conf03		86.78 37	86.99 35	86.15 63	91.24 83	67.61 146	90.51 62	92.90 56	77.26 55	87.44 48	91.63 114	71.27 62	96.06 49	85.62 51	95.01 37	94.78 23

HPM-MVS		87.11 33	86.98 36	87.50 38	93.88 39	72.16 45	92.19 33	93.33 31	76.07 90	83.81 99	93.95 59	69.77 80	96.01 53	85.15 53	94.66 47	94.32 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CS-MVS		86.69 39	86.95 37	85.90 71	90.76 96	67.57 148	92.83 17	93.30 32	79.67 18	84.57 84	92.27 98	71.47 58	95.02 93	84.24 68	93.46 67	95.13 8

CP-MVS		87.11 33	86.92 38	87.68 34	94.20 34	73.86 7	93.98 3	92.82 63	76.62 77	83.68 101	94.46 29	67.93 104	95.95 57	84.20 69	94.39 55	93.23 100

XVS		87.18 32	86.91 39	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 23	83.67 102	94.17 44	67.45 109	96.60 33	83.06 78	94.50 51	94.07 56

DeepC-MVS	79.81 2	87.08 35	86.88 40	87.69 33	91.16 84	72.32 43	90.31 71	93.94 14	77.12 61	82.82 113	94.23 42	72.13 49	97.09 16	84.83 58	95.37 31	93.65 81
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS		86.73 38	86.67 41	86.91 49	94.11 37	72.11 47	92.37 28	92.56 75	74.50 128	86.84 56	94.65 24	67.31 111	95.77 59	84.80 59	92.85 72	92.84 121

DeepC-MVS_fast	79.65 3	86.91 36	86.62 42	87.76 27	93.52 46	72.37 41	91.26 51	93.04 41	76.62 77	84.22 89	93.36 75	71.44 59	96.76 25	80.82 103	95.33 33	94.16 51
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		86.29 48	86.48 43	85.71 73	91.02 88	67.21 162	92.36 29	93.78 18	78.97 30	83.51 105	91.20 129	70.65 71	95.15 84	81.96 92	94.89 42	94.77 24

EC-MVSNet		86.01 50	86.38 44	84.91 97	89.31 139	66.27 175	92.32 30	93.63 21	79.37 22	84.17 91	91.88 106	69.04 92	95.43 70	83.93 72	93.77 63	93.01 116

fmvsm_l_conf0.5_n_3		86.02 49	86.32 45	85.14 85	87.20 227	68.54 123	89.57 90	90.44 147	75.31 106	87.49 46	94.39 35	72.86 42	92.72 194	89.04 23	90.56 107	94.16 51

mPP-MVS		86.67 41	86.32 45	87.72 30	94.41 22	73.55 13	92.74 20	92.22 88	76.87 68	82.81 114	94.25 41	66.44 120	96.24 44	82.88 83	94.28 58	93.38 93

PGM-MVS		86.68 40	86.27 47	87.90 22	94.22 33	73.38 18	90.22 73	93.04 41	75.53 99	83.86 97	94.42 33	67.87 106	96.64 31	82.70 88	94.57 50	93.66 77

fmvsm_s_conf0.5_n_6		85.55 63	86.20 48	83.60 155	87.32 224	65.13 203	88.86 120	91.63 112	75.41 102	88.23 32	93.45 72	68.56 97	92.47 204	89.52 15	92.78 73	93.20 104

train_agg		86.43 44	86.20 48	87.13 44	93.26 52	72.96 25	88.75 126	91.89 102	68.69 258	85.00 71	93.10 79	74.43 26	95.41 73	84.97 54	95.71 25	93.02 115

CSCG		86.41 46	86.19 50	87.07 45	92.91 61	72.48 37	90.81 58	93.56 24	73.95 142	83.16 108	91.07 134	75.94 18	95.19 82	79.94 112	94.38 56	93.55 88

PHI-MVS		86.43 44	86.17 51	87.24 41	90.88 92	70.96 68	92.27 32	94.07 9	72.45 175	85.22 69	91.90 105	69.47 83	96.42 40	83.28 77	95.94 19	94.35 44

dcpmvs_2		85.63 61	86.15 52	84.06 137	91.71 78	64.94 210	86.47 204	91.87 104	73.63 150	86.60 58	93.02 84	76.57 15	91.87 230	83.36 75	92.15 81	95.35 3

CANet		86.45 43	86.10 53	87.51 37	90.09 108	70.94 70	89.70 85	92.59 74	81.78 4	81.32 130	91.43 122	70.34 72	97.23 14	84.26 66	93.36 68	94.37 43

casdiffmvs_mvg		85.99 51	86.09 54	85.70 74	87.65 212	67.22 161	88.69 130	93.04 41	79.64 20	85.33 67	92.54 95	73.30 35	94.50 112	83.49 74	91.14 98	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvsmconf_n		85.92 54	86.04 55	85.57 76	85.03 274	69.51 93	89.62 89	90.58 142	73.42 158	87.75 42	94.02 52	72.85 43	93.24 167	90.37 6	90.75 104	93.96 61

MVSMamba_PlusPlus		85.99 51	85.96 56	86.05 66	91.09 85	67.64 145	89.63 88	92.65 70	72.89 172	84.64 81	91.71 110	71.85 51	96.03 50	84.77 60	94.45 54	94.49 37

APD-MVS_3200maxsize		85.97 53	85.88 57	86.22 60	92.69 66	69.53 92	91.93 37	92.99 49	73.54 154	85.94 60	94.51 28	65.80 130	95.61 62	83.04 80	92.51 77	93.53 90

sasdasda		85.91 55	85.87 58	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 75	88.01 37	91.23 126	73.28 36	93.91 136	81.50 95	88.80 134	94.77 24

canonicalmvs		85.91 55	85.87 58	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 75	88.01 37	91.23 126	73.28 36	93.91 136	81.50 95	88.80 134	94.77 24

MSLP-MVS++		85.43 66	85.76 60	84.45 111	91.93 75	70.24 79	90.71 59	92.86 58	77.46 51	84.22 89	92.81 90	67.16 113	92.94 188	80.36 107	94.35 57	90.16 214

fmvsm_s_conf0.5_n_4		85.39 68	85.75 61	84.30 118	86.70 239	65.83 184	88.77 124	89.78 170	75.46 101	88.35 28	93.73 65	69.19 87	93.06 183	91.30 2	88.44 143	94.02 59

test_fmvsmconf0.1_n		85.61 62	85.65 62	85.50 77	82.99 321	69.39 100	89.65 86	90.29 156	73.31 161	87.77 41	94.15 46	71.72 54	93.23 168	90.31 7	90.67 106	93.89 67

SR-MVS-dyc-post		85.77 58	85.61 63	86.23 59	93.06 58	70.63 76	91.88 38	92.27 84	73.53 155	85.69 64	94.45 30	65.00 138	95.56 63	82.75 84	91.87 85	92.50 132

fmvsm_s_conf0.5_n_5		85.22 71	85.55 64	84.25 125	86.26 245	67.40 153	89.18 105	89.31 187	72.50 174	88.31 29	93.86 61	69.66 81	91.96 224	89.81 10	91.05 99	93.38 93

MGCFI-Net		85.06 75	85.51 65	83.70 153	89.42 131	63.01 252	89.43 94	92.62 73	76.43 79	87.53 45	91.34 124	72.82 44	93.42 162	81.28 98	88.74 137	94.66 31

RE-MVS-def			85.48 66		93.06 58	70.63 76	91.88 38	92.27 84	73.53 155	85.69 64	94.45 30	63.87 144		82.75 84	91.87 85	92.50 132

ACMMP		85.89 57	85.39 67	87.38 39	93.59 45	72.63 33	92.74 20	93.18 39	76.78 71	80.73 139	93.82 63	64.33 140	96.29 42	82.67 89	90.69 105	93.23 100
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
test_fmvsm_n_1920		85.29 70	85.34 68	85.13 88	86.12 250	69.93 86	88.65 132	90.78 138	69.97 226	88.27 30	93.98 57	71.39 60	91.54 243	88.49 31	90.45 109	93.91 64

TSAR-MVS + GP.		85.71 60	85.33 69	86.84 50	91.34 81	72.50 36	89.07 114	87.28 244	76.41 80	85.80 62	90.22 153	74.15 31	95.37 78	81.82 93	91.88 84	92.65 127

alignmvs		85.48 64	85.32 70	85.96 70	89.51 127	69.47 95	89.74 83	92.47 76	76.17 88	87.73 44	91.46 121	70.32 73	93.78 142	81.51 94	88.95 131	94.63 32

DELS-MVS		85.41 67	85.30 71	85.77 72	88.49 170	67.93 138	85.52 234	93.44 27	78.70 31	83.63 104	89.03 181	74.57 24	95.71 61	80.26 109	94.04 61	93.66 77
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
CDPH-MVS		85.76 59	85.29 72	87.17 43	93.49 47	71.08 64	88.58 134	92.42 80	68.32 265	84.61 82	93.48 69	72.32 46	96.15 48	79.00 115	95.43 30	94.28 48

casdiffmvs		85.11 73	85.14 73	85.01 91	87.20 227	65.77 188	87.75 163	92.83 60	77.84 40	84.36 88	92.38 97	72.15 48	93.93 135	81.27 99	90.48 108	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		84.93 76	84.98 74	84.80 101	87.30 225	65.39 197	87.30 177	92.88 57	77.62 43	84.04 94	92.26 99	71.81 52	93.96 129	81.31 97	90.30 111	95.03 10

UA-Net		85.08 74	84.96 75	85.45 78	92.07 73	68.07 135	89.78 82	90.86 137	82.48 2	84.60 83	93.20 78	69.35 84	95.22 81	71.39 192	90.88 103	93.07 110

HPM-MVS_fast		85.35 69	84.95 76	86.57 56	93.69 42	70.58 78	92.15 35	91.62 113	73.89 145	82.67 116	94.09 48	62.60 159	95.54 65	80.93 101	92.93 71	93.57 86

MVS_111021_HR		85.14 72	84.75 77	86.32 58	91.65 79	72.70 30	85.98 217	90.33 153	76.11 89	82.08 120	91.61 116	71.36 61	94.17 125	81.02 100	92.58 76	92.08 151

ETV-MVS		84.90 78	84.67 78	85.59 75	89.39 134	68.66 120	88.74 128	92.64 72	79.97 15	84.10 92	85.71 271	69.32 85	95.38 75	80.82 103	91.37 95	92.72 122

fmvsm_l_conf0.5_n		84.47 80	84.54 79	84.27 122	85.42 263	68.81 109	88.49 136	87.26 246	68.08 267	88.03 36	93.49 68	72.04 50	91.77 232	88.90 25	89.14 130	92.24 145

patch_mono-2		83.65 92	84.54 79	80.99 235	90.06 113	65.83 184	84.21 264	88.74 214	71.60 190	85.01 70	92.44 96	74.51 25	83.50 356	82.15 91	92.15 81	93.64 83

test_fmvsmconf0.01_n		84.73 79	84.52 81	85.34 80	80.25 362	69.03 103	89.47 92	89.65 176	73.24 165	86.98 54	94.27 39	66.62 116	93.23 168	90.26 8	89.95 119	93.78 74

3Dnovator+	77.84 4	85.48 64	84.47 82	88.51 7	91.08 86	73.49 16	93.18 11	93.78 18	80.79 8	76.66 212	93.37 74	60.40 205	96.75 26	77.20 134	93.73 64	95.29 5

DPM-MVS		84.93 76	84.29 83	86.84 50	90.20 106	73.04 23	87.12 181	93.04 41	69.80 230	82.85 112	91.22 128	73.06 40	96.02 52	76.72 142	94.63 48	91.46 168

fmvsm_l_conf0.5_n_a		84.13 83	84.16 84	84.06 137	85.38 264	68.40 126	88.34 143	86.85 256	67.48 274	87.48 47	93.40 73	70.89 66	91.61 237	88.38 33	89.22 128	92.16 149

fmvsm_s_conf0.5_n_2		84.04 84	84.11 85	83.81 151	86.17 248	65.00 208	86.96 186	87.28 244	74.35 132	88.25 31	94.23 42	61.82 173	92.60 197	89.85 9	88.09 148	93.84 70

fmvsm_s_conf0.5_n_7		83.34 103	84.03 86	81.28 226	85.73 256	65.13 203	85.40 235	89.90 168	74.96 117	82.13 119	93.89 60	66.65 115	87.92 314	86.56 45	91.05 99	90.80 186

test_fmvsmvis_n_1920		84.02 85	83.87 87	84.49 110	84.12 290	69.37 101	88.15 151	87.96 228	70.01 224	83.95 96	93.23 77	68.80 95	91.51 246	88.61 28	89.96 118	92.57 128

EI-MVSNet-Vis-set		84.19 82	83.81 88	85.31 81	88.18 182	67.85 139	87.66 165	89.73 174	80.05 14	82.95 109	89.59 166	70.74 69	94.82 101	80.66 106	84.72 191	93.28 99

fmvsm_s_conf0.1_n_2		83.80 88	83.79 89	83.83 150	85.62 259	64.94 210	87.03 184	86.62 260	74.32 133	87.97 39	94.33 36	60.67 197	92.60 197	89.72 11	87.79 150	93.96 61

BP-MVS1		84.32 81	83.71 90	86.17 61	87.84 201	67.85 139	89.38 99	89.64 177	77.73 41	83.98 95	92.12 102	56.89 229	95.43 70	84.03 71	91.75 88	95.24 6

fmvsm_s_conf0.5_n		83.80 88	83.71 90	84.07 135	86.69 240	67.31 156	89.46 93	83.07 312	71.09 200	86.96 55	93.70 66	69.02 93	91.47 248	88.79 26	84.62 193	93.44 92

nrg030		83.88 86	83.53 92	84.96 93	86.77 237	69.28 102	90.46 67	92.67 67	74.79 122	82.95 109	91.33 125	72.70 45	93.09 181	80.79 105	79.28 271	92.50 132

MG-MVS		83.41 100	83.45 93	83.28 166	92.74 65	62.28 264	88.17 149	89.50 181	75.22 107	81.49 129	92.74 94	66.75 114	95.11 87	72.85 180	91.58 91	92.45 135

fmvsm_s_conf0.5_n_a		83.63 94	83.41 94	84.28 120	86.14 249	68.12 133	89.43 94	82.87 317	70.27 219	87.27 51	93.80 64	69.09 88	91.58 239	88.21 34	83.65 213	93.14 108

fmvsm_s_conf0.1_n		83.56 96	83.38 95	84.10 129	84.86 276	67.28 157	89.40 98	83.01 313	70.67 208	87.08 52	93.96 58	68.38 99	91.45 249	88.56 30	84.50 194	93.56 87

EI-MVSNet-UG-set		83.81 87	83.38 95	85.09 89	87.87 199	67.53 149	87.44 173	89.66 175	79.74 17	82.23 118	89.41 175	70.24 75	94.74 104	79.95 111	83.92 205	92.99 118

CPTT-MVS		83.73 90	83.33 97	84.92 96	93.28 49	70.86 72	92.09 36	90.38 149	68.75 257	79.57 151	92.83 88	60.60 201	93.04 186	80.92 102	91.56 92	90.86 185

HQP_MVS		83.64 93	83.14 98	85.14 85	90.08 109	68.71 116	91.25 52	92.44 77	79.12 25	78.92 160	91.00 139	60.42 203	95.38 75	78.71 119	86.32 172	91.33 169

Effi-MVS+		83.62 95	83.08 99	85.24 83	88.38 176	67.45 150	88.89 119	89.15 196	75.50 100	82.27 117	88.28 202	69.61 82	94.45 114	77.81 128	87.84 149	93.84 70

MVS_Test		83.15 106	83.06 100	83.41 163	86.86 233	63.21 248	86.11 215	92.00 96	74.31 134	82.87 111	89.44 174	70.03 76	93.21 170	77.39 133	88.50 142	93.81 72

EPP-MVSNet		83.40 101	83.02 101	84.57 106	90.13 107	64.47 221	92.32 30	90.73 139	74.45 131	79.35 154	91.10 132	69.05 91	95.12 85	72.78 181	87.22 159	94.13 53

fmvsm_s_conf0.1_n_a		83.32 104	82.99 102	84.28 120	83.79 298	68.07 135	89.34 101	82.85 318	69.80 230	87.36 50	94.06 50	68.34 100	91.56 241	87.95 35	83.46 219	93.21 103

OPM-MVS		83.50 98	82.95 103	85.14 85	88.79 160	70.95 69	89.13 111	91.52 116	77.55 48	80.96 137	91.75 109	60.71 195	94.50 112	79.67 114	86.51 170	89.97 230
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EPNet		83.72 91	82.92 104	86.14 65	84.22 288	69.48 94	91.05 56	85.27 277	81.30 6	76.83 207	91.65 112	66.09 125	95.56 63	76.00 148	93.85 62	93.38 93
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IS-MVSNet		83.15 106	82.81 105	84.18 127	89.94 116	63.30 246	91.59 43	88.46 220	79.04 27	79.49 152	92.16 100	65.10 135	94.28 117	67.71 228	91.86 87	94.95 11

EIA-MVS		83.31 105	82.80 106	84.82 99	89.59 123	65.59 192	88.21 147	92.68 66	74.66 126	78.96 158	86.42 258	69.06 90	95.26 80	75.54 154	90.09 115	93.62 84

Vis-MVSNet		83.46 99	82.80 106	85.43 79	90.25 105	68.74 114	90.30 72	90.13 161	76.33 86	80.87 138	92.89 86	61.00 192	94.20 122	72.45 186	90.97 101	93.35 96
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GDP-MVS		83.52 97	82.64 108	86.16 62	88.14 185	68.45 125	89.13 111	92.69 65	72.82 173	83.71 100	91.86 108	55.69 234	95.35 79	80.03 110	89.74 122	94.69 27

FIs		82.07 122	82.42 109	81.04 234	88.80 159	58.34 306	88.26 146	93.49 26	76.93 66	78.47 171	91.04 135	69.92 78	92.34 212	69.87 209	84.97 188	92.44 136

VNet		82.21 119	82.41 110	81.62 215	90.82 93	60.93 279	84.47 255	89.78 170	76.36 85	84.07 93	91.88 106	64.71 139	90.26 273	70.68 199	88.89 132	93.66 77

PAPM_NR		83.02 110	82.41 110	84.82 99	92.47 70	66.37 173	87.93 158	91.80 107	73.82 146	77.32 195	90.66 144	67.90 105	94.90 97	70.37 202	89.48 125	93.19 105

VDD-MVS		83.01 111	82.36 112	84.96 93	91.02 88	66.40 172	88.91 118	88.11 223	77.57 45	84.39 87	93.29 76	52.19 267	93.91 136	77.05 137	88.70 138	94.57 35

3Dnovator	76.31 5	83.38 102	82.31 113	86.59 55	87.94 196	72.94 28	90.64 60	92.14 93	77.21 58	75.47 238	92.83 88	58.56 212	94.72 105	73.24 177	92.71 75	92.13 150

h-mvs33		83.15 106	82.19 114	86.02 69	90.56 98	70.85 73	88.15 151	89.16 195	76.02 91	84.67 78	91.39 123	61.54 178	95.50 66	82.71 86	75.48 320	91.72 158

MVS_111021_LR		82.61 115	82.11 115	84.11 128	88.82 157	71.58 55	85.15 238	86.16 268	74.69 124	80.47 141	91.04 135	62.29 166	90.55 271	80.33 108	90.08 116	90.20 213

RRT-MVS		82.60 117	82.10 116	84.10 129	87.98 195	62.94 257	87.45 172	91.27 123	77.42 52	79.85 147	90.28 149	56.62 231	94.70 107	79.87 113	88.15 147	94.67 28

DP-MVS Recon		83.11 109	82.09 117	86.15 63	94.44 19	70.92 71	88.79 123	92.20 90	70.53 213	79.17 156	91.03 137	64.12 142	96.03 50	68.39 225	90.14 114	91.50 164

MVSFormer		82.85 112	82.05 118	85.24 83	87.35 218	70.21 80	90.50 64	90.38 149	68.55 260	81.32 130	89.47 169	61.68 175	93.46 159	78.98 116	90.26 112	92.05 152

FC-MVSNet-test		81.52 134	82.02 119	80.03 255	88.42 175	55.97 345	87.95 156	93.42 29	77.10 62	77.38 193	90.98 141	69.96 77	91.79 231	68.46 224	84.50 194	92.33 139

HQP-MVS		82.61 115	82.02 119	84.37 113	89.33 136	66.98 165	89.17 106	92.19 91	76.41 80	77.23 198	90.23 152	60.17 206	95.11 87	77.47 131	85.99 180	91.03 179

OMC-MVS		82.69 113	81.97 121	84.85 98	88.75 162	67.42 151	87.98 154	90.87 136	74.92 118	79.72 149	91.65 112	62.19 169	93.96 129	75.26 158	86.42 171	93.16 106

diffmvs		82.10 120	81.88 122	82.76 197	83.00 319	63.78 234	83.68 272	89.76 172	72.94 170	82.02 121	89.85 158	65.96 129	90.79 267	82.38 90	87.30 158	93.71 76
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		82.62 114	81.83 123	84.96 93	90.80 94	69.76 90	88.74 128	91.70 111	69.39 238	78.96 158	88.46 197	65.47 132	94.87 100	74.42 163	88.57 139	90.24 212

CLD-MVS		82.31 118	81.65 124	84.29 119	88.47 171	67.73 143	85.81 225	92.35 82	75.78 94	78.33 174	86.58 253	64.01 143	94.35 115	76.05 147	87.48 155	90.79 187
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_NR-MVSNet		81.88 125	81.54 125	82.92 186	88.46 172	63.46 242	87.13 180	92.37 81	80.19 12	78.38 172	89.14 177	71.66 57	93.05 184	70.05 205	76.46 303	92.25 143

PS-MVSNAJss		82.07 122	81.31 126	84.34 116	86.51 243	67.27 158	89.27 102	91.51 117	71.75 185	79.37 153	90.22 153	63.15 153	94.27 118	77.69 129	82.36 233	91.49 165

LPG-MVS_test		82.08 121	81.27 127	84.50 108	89.23 143	68.76 112	90.22 73	91.94 100	75.37 104	76.64 213	91.51 118	54.29 247	94.91 95	78.44 121	83.78 206	89.83 235

LFMVS		81.82 127	81.23 128	83.57 158	91.89 76	63.43 244	89.84 78	81.85 329	77.04 64	83.21 106	93.10 79	52.26 266	93.43 161	71.98 187	89.95 119	93.85 68

API-MVS		81.99 124	81.23 128	84.26 124	90.94 90	70.18 85	91.10 55	89.32 186	71.51 192	78.66 165	88.28 202	65.26 133	95.10 90	64.74 255	91.23 97	87.51 300

UniMVSNet (Re)		81.60 133	81.11 130	83.09 176	88.38 176	64.41 223	87.60 166	93.02 45	78.42 34	78.56 168	88.16 206	69.78 79	93.26 166	69.58 212	76.49 302	91.60 159

xiu_mvs_v2_base		81.69 130	81.05 131	83.60 155	89.15 146	68.03 137	84.46 257	90.02 163	70.67 208	81.30 133	86.53 256	63.17 152	94.19 124	75.60 153	88.54 140	88.57 279

PS-MVSNAJ		81.69 130	81.02 132	83.70 153	89.51 127	68.21 132	84.28 263	90.09 162	70.79 205	81.26 134	85.62 276	63.15 153	94.29 116	75.62 152	88.87 133	88.59 278

GeoE		81.71 129	81.01 133	83.80 152	89.51 127	64.45 222	88.97 116	88.73 215	71.27 196	78.63 166	89.76 160	66.32 122	93.20 173	69.89 208	86.02 179	93.74 75

hse-mvs2		81.72 128	80.94 134	84.07 135	88.72 163	67.68 144	85.87 221	87.26 246	76.02 91	84.67 78	88.22 205	61.54 178	93.48 157	82.71 86	73.44 348	91.06 177

PAPR		81.66 132	80.89 135	83.99 145	90.27 104	64.00 229	86.76 197	91.77 110	68.84 256	77.13 205	89.50 167	67.63 107	94.88 99	67.55 230	88.52 141	93.09 109

MAR-MVS		81.84 126	80.70 136	85.27 82	91.32 82	71.53 56	89.82 79	90.92 133	69.77 232	78.50 169	86.21 262	62.36 165	94.52 111	65.36 249	92.05 83	89.77 238
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
VDDNet		81.52 134	80.67 137	84.05 140	90.44 101	64.13 228	89.73 84	85.91 271	71.11 199	83.18 107	93.48 69	50.54 293	93.49 156	73.40 174	88.25 145	94.54 36

ACMP	74.13 6	81.51 136	80.57 138	84.36 114	89.42 131	68.69 119	89.97 77	91.50 120	74.46 130	75.04 260	90.41 148	53.82 252	94.54 109	77.56 130	82.91 225	89.86 234
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
VPA-MVSNet		80.60 155	80.55 139	80.76 241	88.07 190	60.80 282	86.86 191	91.58 115	75.67 98	80.24 143	89.45 173	63.34 147	90.25 274	70.51 201	79.22 272	91.23 172

DU-MVS		81.12 141	80.52 140	82.90 187	87.80 203	63.46 242	87.02 185	91.87 104	79.01 28	78.38 172	89.07 179	65.02 136	93.05 184	70.05 205	76.46 303	92.20 146

test_yl		81.17 139	80.47 141	83.24 169	89.13 147	63.62 235	86.21 212	89.95 166	72.43 178	81.78 126	89.61 164	57.50 222	93.58 150	70.75 197	86.90 163	92.52 130

DCV-MVSNet		81.17 139	80.47 141	83.24 169	89.13 147	63.62 235	86.21 212	89.95 166	72.43 178	81.78 126	89.61 164	57.50 222	93.58 150	70.75 197	86.90 163	92.52 130

PVSNet_Blended		80.98 142	80.34 143	82.90 187	88.85 154	65.40 195	84.43 259	92.00 96	67.62 271	78.11 179	85.05 291	66.02 127	94.27 118	71.52 189	89.50 124	89.01 259

TranMVSNet+NR-MVSNet		80.84 145	80.31 144	82.42 202	87.85 200	62.33 262	87.74 164	91.33 122	80.55 9	77.99 183	89.86 157	65.23 134	92.62 195	67.05 237	75.24 330	92.30 141

jason		81.39 137	80.29 145	84.70 104	86.63 242	69.90 88	85.95 218	86.77 257	63.24 325	81.07 136	89.47 169	61.08 191	92.15 218	78.33 124	90.07 117	92.05 152
jason: jason.
lupinMVS		81.39 137	80.27 146	84.76 102	87.35 218	70.21 80	85.55 230	86.41 262	62.85 332	81.32 130	88.61 192	61.68 175	92.24 216	78.41 123	90.26 112	91.83 155

SDMVSNet		80.38 161	80.18 147	80.99 235	89.03 152	64.94 210	80.45 321	89.40 183	75.19 110	76.61 215	89.98 155	60.61 200	87.69 318	76.83 140	83.55 215	90.33 208

PVSNet_BlendedMVS		80.60 155	80.02 148	82.36 204	88.85 154	65.40 195	86.16 214	92.00 96	69.34 240	78.11 179	86.09 266	66.02 127	94.27 118	71.52 189	82.06 236	87.39 302

EI-MVSNet		80.52 159	79.98 149	82.12 205	84.28 286	63.19 250	86.41 205	88.95 206	74.18 139	78.69 163	87.54 223	66.62 116	92.43 206	72.57 184	80.57 255	90.74 191

Fast-Effi-MVS+		80.81 147	79.92 150	83.47 159	88.85 154	64.51 218	85.53 232	89.39 184	70.79 205	78.49 170	85.06 290	67.54 108	93.58 150	67.03 238	86.58 168	92.32 140

FA-MVS(test-final)		80.96 143	79.91 151	84.10 129	88.30 179	65.01 207	84.55 254	90.01 164	73.25 164	79.61 150	87.57 220	58.35 214	94.72 105	71.29 193	86.25 174	92.56 129

CANet_DTU		80.61 154	79.87 152	82.83 189	85.60 260	63.17 251	87.36 174	88.65 216	76.37 84	75.88 231	88.44 198	53.51 255	93.07 182	73.30 175	89.74 122	92.25 143

ACMM	73.20 8	80.78 152	79.84 153	83.58 157	89.31 139	68.37 127	89.99 76	91.60 114	70.28 218	77.25 196	89.66 162	53.37 257	93.53 155	74.24 166	82.85 226	88.85 267
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVG-OURS-SEG-HR		80.81 147	79.76 154	83.96 147	85.60 260	68.78 111	83.54 278	90.50 145	70.66 211	76.71 211	91.66 111	60.69 196	91.26 254	76.94 138	81.58 241	91.83 155

xiu_mvs_v1_base_debu		80.80 149	79.72 155	84.03 142	87.35 218	70.19 82	85.56 227	88.77 210	69.06 250	81.83 122	88.16 206	50.91 287	92.85 190	78.29 125	87.56 152	89.06 254

xiu_mvs_v1_base		80.80 149	79.72 155	84.03 142	87.35 218	70.19 82	85.56 227	88.77 210	69.06 250	81.83 122	88.16 206	50.91 287	92.85 190	78.29 125	87.56 152	89.06 254

xiu_mvs_v1_base_debi		80.80 149	79.72 155	84.03 142	87.35 218	70.19 82	85.56 227	88.77 210	69.06 250	81.83 122	88.16 206	50.91 287	92.85 190	78.29 125	87.56 152	89.06 254

UGNet		80.83 146	79.59 158	84.54 107	88.04 191	68.09 134	89.42 96	88.16 222	76.95 65	76.22 224	89.46 171	49.30 308	93.94 132	68.48 223	90.31 110	91.60 159
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
114514_t		80.68 153	79.51 159	84.20 126	94.09 38	67.27 158	89.64 87	91.11 130	58.75 370	74.08 274	90.72 143	58.10 215	95.04 92	69.70 210	89.42 126	90.30 210

QAPM		80.88 144	79.50 160	85.03 90	88.01 194	68.97 107	91.59 43	92.00 96	66.63 286	75.15 256	92.16 100	57.70 219	95.45 68	63.52 261	88.76 136	90.66 194

AdaColmap		80.58 158	79.42 161	84.06 137	93.09 57	68.91 108	89.36 100	88.97 205	69.27 241	75.70 234	89.69 161	57.20 226	95.77 59	63.06 266	88.41 144	87.50 301

NR-MVSNet		80.23 165	79.38 162	82.78 195	87.80 203	63.34 245	86.31 209	91.09 131	79.01 28	72.17 300	89.07 179	67.20 112	92.81 193	66.08 244	75.65 316	92.20 146

mvsmamba		80.60 155	79.38 162	84.27 122	89.74 121	67.24 160	87.47 170	86.95 252	70.02 223	75.38 244	88.93 182	51.24 284	92.56 200	75.47 156	89.22 128	93.00 117

IterMVS-LS		80.06 168	79.38 162	82.11 206	85.89 253	63.20 249	86.79 194	89.34 185	74.19 138	75.45 241	86.72 243	66.62 116	92.39 208	72.58 183	76.86 297	90.75 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_djsdf		80.30 164	79.32 165	83.27 167	83.98 294	65.37 198	90.50 64	90.38 149	68.55 260	76.19 225	88.70 188	56.44 232	93.46 159	78.98 116	80.14 261	90.97 182

v2v482		80.23 165	79.29 166	83.05 180	83.62 302	64.14 227	87.04 183	89.97 165	73.61 151	78.18 178	87.22 231	61.10 190	93.82 140	76.11 145	76.78 300	91.18 173

ECVR-MVS		79.61 174	79.26 167	80.67 243	90.08 109	54.69 360	87.89 160	77.44 372	74.88 119	80.27 142	92.79 91	48.96 314	92.45 205	68.55 222	92.50 78	94.86 18

XVG-OURS		80.41 160	79.23 168	83.97 146	85.64 258	69.02 105	83.03 289	90.39 148	71.09 200	77.63 189	91.49 120	54.62 246	91.35 252	75.71 150	83.47 218	91.54 162

WR-MVS		79.49 178	79.22 169	80.27 251	88.79 160	58.35 305	85.06 241	88.61 218	78.56 32	77.65 188	88.34 200	63.81 146	90.66 270	64.98 253	77.22 292	91.80 157

test1111		79.43 181	79.18 170	80.15 253	89.99 114	53.31 373	87.33 176	77.05 376	75.04 113	80.23 144	92.77 93	48.97 313	92.33 213	68.87 219	92.40 80	94.81 21

mvs_anonymous		79.42 182	79.11 171	80.34 249	84.45 285	57.97 312	82.59 291	87.62 237	67.40 275	76.17 228	88.56 195	68.47 98	89.59 286	70.65 200	86.05 178	93.47 91

v1144		80.03 169	79.03 172	83.01 182	83.78 299	64.51 218	87.11 182	90.57 144	71.96 184	78.08 181	86.20 263	61.41 182	93.94 132	74.93 159	77.23 291	90.60 197

v8		79.97 171	79.02 173	82.80 192	84.09 291	64.50 220	87.96 155	90.29 156	74.13 141	75.24 253	86.81 240	62.88 158	93.89 139	74.39 164	75.40 325	90.00 226

ab-mvs		79.51 177	78.97 174	81.14 231	88.46 172	60.91 280	83.84 269	89.24 192	70.36 215	79.03 157	88.87 185	63.23 151	90.21 275	65.12 251	82.57 231	92.28 142

Anonymous20240529		80.19 167	78.89 175	84.10 129	90.60 97	64.75 215	88.95 117	90.90 134	65.97 294	80.59 140	91.17 131	49.97 298	93.73 148	69.16 216	82.70 230	93.81 72

PCF-MVS	73.52 7	80.38 161	78.84 176	85.01 91	87.71 209	68.99 106	83.65 273	91.46 121	63.00 329	77.77 187	90.28 149	66.10 124	95.09 91	61.40 285	88.22 146	90.94 183
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v10		79.74 173	78.67 177	82.97 185	84.06 292	64.95 209	87.88 161	90.62 141	73.11 166	75.11 257	86.56 254	61.46 181	94.05 128	73.68 169	75.55 318	89.90 232

VPNet		78.69 201	78.66 178	78.76 278	88.31 178	55.72 349	84.45 258	86.63 259	76.79 70	78.26 175	90.55 146	59.30 208	89.70 285	66.63 239	77.05 294	90.88 184

BH-untuned		79.47 179	78.60 179	82.05 207	89.19 145	65.91 182	86.07 216	88.52 219	72.18 180	75.42 242	87.69 217	61.15 189	93.54 154	60.38 292	86.83 165	86.70 321

Effi-MVS+-dtu		80.03 169	78.57 180	84.42 112	85.13 272	68.74 114	88.77 124	88.10 224	74.99 114	74.97 261	83.49 325	57.27 225	93.36 163	73.53 171	80.88 249	91.18 173

WR-MVS_H		78.51 205	78.49 181	78.56 283	88.02 192	56.38 339	88.43 137	92.67 67	77.14 60	73.89 276	87.55 222	66.25 123	89.24 293	58.92 306	73.55 346	90.06 224

Vis-MVSNet (Re-imp)		78.36 208	78.45 182	78.07 294	88.64 166	51.78 383	86.70 198	79.63 355	74.14 140	75.11 257	90.83 142	61.29 186	89.75 283	58.10 316	91.60 89	92.69 125

BH-RMVSNet		79.61 174	78.44 183	83.14 174	89.38 135	65.93 181	84.95 244	87.15 249	73.56 153	78.19 177	89.79 159	56.67 230	93.36 163	59.53 300	86.74 166	90.13 216

v1192		79.59 176	78.43 184	83.07 179	83.55 304	64.52 217	86.93 189	90.58 142	70.83 204	77.78 186	85.90 267	59.15 209	93.94 132	73.96 168	77.19 293	90.76 189

v144192		79.47 179	78.37 185	82.78 195	83.35 307	63.96 230	86.96 186	90.36 152	69.99 225	77.50 190	85.67 274	60.66 198	93.77 144	74.27 165	76.58 301	90.62 195

CP-MVSNet		78.22 210	78.34 186	77.84 296	87.83 202	54.54 362	87.94 157	91.17 127	77.65 42	73.48 282	88.49 196	62.24 168	88.43 308	62.19 276	74.07 339	90.55 199

Baseline_NR-MVSNet		78.15 214	78.33 187	77.61 301	85.79 254	56.21 343	86.78 195	85.76 273	73.60 152	77.93 184	87.57 220	65.02 136	88.99 297	67.14 236	75.33 327	87.63 296

OpenMVS	72.83 10	79.77 172	78.33 187	84.09 133	85.17 268	69.91 87	90.57 61	90.97 132	66.70 280	72.17 300	91.91 104	54.70 244	93.96 129	61.81 282	90.95 102	88.41 283

UniMVSNet_ETH3D		79.10 191	78.24 189	81.70 214	86.85 234	60.24 291	87.28 178	88.79 209	74.25 137	76.84 206	90.53 147	49.48 304	91.56 241	67.98 226	82.15 234	93.29 98

V42		79.38 185	78.24 189	82.83 189	81.10 354	65.50 194	85.55 230	89.82 169	71.57 191	78.21 176	86.12 265	60.66 198	93.18 176	75.64 151	75.46 322	89.81 237

mamv4		76.81 243	78.23 191	72.54 356	86.12 250	65.75 189	78.76 345	82.07 326	64.12 316	72.97 288	91.02 138	67.97 103	68.08 421	83.04 80	78.02 283	83.80 367

PS-CasMVS		78.01 219	78.09 192	77.77 298	87.71 209	54.39 364	88.02 153	91.22 124	77.50 50	73.26 284	88.64 191	60.73 194	88.41 309	61.88 280	73.88 343	90.53 200

v1921920		79.22 187	78.03 193	82.80 192	83.30 309	63.94 231	86.80 193	90.33 153	69.91 228	77.48 191	85.53 278	58.44 213	93.75 146	73.60 170	76.85 298	90.71 193

jajsoiax		79.29 186	77.96 194	83.27 167	84.68 279	66.57 171	89.25 103	90.16 160	69.20 246	75.46 240	89.49 168	45.75 339	93.13 179	76.84 139	80.80 251	90.11 218

TAPA-MVS	73.13 9	79.15 189	77.94 195	82.79 194	89.59 123	62.99 256	88.16 150	91.51 117	65.77 295	77.14 204	91.09 133	60.91 193	93.21 170	50.26 366	87.05 161	92.17 148
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tttt0517		79.40 183	77.91 196	83.90 149	88.10 188	63.84 232	88.37 142	84.05 294	71.45 193	76.78 209	89.12 178	49.93 301	94.89 98	70.18 204	83.18 223	92.96 119

c3_l		78.75 198	77.91 196	81.26 227	82.89 323	61.56 273	84.09 267	89.13 198	69.97 226	75.56 236	84.29 305	66.36 121	92.09 220	73.47 173	75.48 320	90.12 217

MVSTER		79.01 193	77.88 198	82.38 203	83.07 316	64.80 214	84.08 268	88.95 206	69.01 253	78.69 163	87.17 234	54.70 244	92.43 206	74.69 160	80.57 255	89.89 233

tt0805		78.73 199	77.83 199	81.43 220	85.17 268	60.30 290	89.41 97	90.90 134	71.21 197	77.17 203	88.73 187	46.38 328	93.21 170	72.57 184	78.96 273	90.79 187

X-MVStestdata		80.37 163	77.83 199	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 23	83.67 102	12.47 433	67.45 109	96.60 33	83.06 78	94.50 51	94.07 56

v148		78.72 200	77.80 201	81.47 219	82.73 326	61.96 268	86.30 210	88.08 225	73.26 163	76.18 226	85.47 280	62.46 163	92.36 210	71.92 188	73.82 344	90.09 220

v1240		78.99 194	77.78 202	82.64 198	83.21 311	63.54 239	86.62 200	90.30 155	69.74 235	77.33 194	85.68 273	57.04 227	93.76 145	73.13 178	76.92 295	90.62 195

mvs_tets		79.13 190	77.77 203	83.22 171	84.70 278	66.37 173	89.17 106	90.19 159	69.38 239	75.40 243	89.46 171	44.17 351	93.15 177	76.78 141	80.70 253	90.14 215

miper_ehance_all_eth		78.59 204	77.76 204	81.08 233	82.66 328	61.56 273	83.65 273	89.15 196	68.87 255	75.55 237	83.79 317	66.49 119	92.03 221	73.25 176	76.39 305	89.64 241

thisisatest0530		79.40 183	77.76 204	84.31 117	87.69 211	65.10 206	87.36 174	84.26 292	70.04 222	77.42 192	88.26 204	49.94 299	94.79 103	70.20 203	84.70 192	93.03 114

CDS-MVSNet		79.07 192	77.70 206	83.17 173	87.60 213	68.23 131	84.40 261	86.20 267	67.49 273	76.36 221	86.54 255	61.54 178	90.79 267	61.86 281	87.33 157	90.49 202
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Anonymous20231211		78.97 195	77.69 207	82.81 191	90.54 99	64.29 225	90.11 75	91.51 117	65.01 306	76.16 229	88.13 211	50.56 292	93.03 187	69.68 211	77.56 290	91.11 175

PEN-MVS		77.73 225	77.69 207	77.84 296	87.07 232	53.91 367	87.91 159	91.18 126	77.56 47	73.14 286	88.82 186	61.23 187	89.17 294	59.95 295	72.37 354	90.43 204

AUN-MVS		79.21 188	77.60 209	84.05 140	88.71 164	67.61 146	85.84 223	87.26 246	69.08 249	77.23 198	88.14 210	53.20 259	93.47 158	75.50 155	73.45 347	91.06 177

v7n		78.97 195	77.58 210	83.14 174	83.45 306	65.51 193	88.32 144	91.21 125	73.69 149	72.41 296	86.32 261	57.93 216	93.81 141	69.18 215	75.65 316	90.11 218

TAMVS		78.89 197	77.51 211	83.03 181	87.80 203	67.79 142	84.72 248	85.05 281	67.63 270	76.75 210	87.70 216	62.25 167	90.82 266	58.53 311	87.13 160	90.49 202

sd_testset		77.70 228	77.40 212	78.60 281	89.03 152	60.02 293	79.00 341	85.83 272	75.19 110	76.61 215	89.98 155	54.81 239	85.46 340	62.63 272	83.55 215	90.33 208

GBi-Net		78.40 206	77.40 212	81.40 222	87.60 213	63.01 252	88.39 139	89.28 188	71.63 187	75.34 246	87.28 227	54.80 240	91.11 257	62.72 268	79.57 265	90.09 220

test1		78.40 206	77.40 212	81.40 222	87.60 213	63.01 252	88.39 139	89.28 188	71.63 187	75.34 246	87.28 227	54.80 240	91.11 257	62.72 268	79.57 265	90.09 220

BH-w/o		78.21 211	77.33 215	80.84 239	88.81 158	65.13 203	84.87 245	87.85 233	69.75 233	74.52 269	84.74 297	61.34 184	93.11 180	58.24 315	85.84 182	84.27 359

FMVSNet2		78.20 212	77.21 216	81.20 229	87.60 213	62.89 258	87.47 170	89.02 201	71.63 187	75.29 252	87.28 227	54.80 240	91.10 260	62.38 273	79.38 269	89.61 242

anonymousdsp		78.60 203	77.15 217	82.98 184	80.51 360	67.08 163	87.24 179	89.53 180	65.66 297	75.16 255	87.19 233	52.52 261	92.25 215	77.17 135	79.34 270	89.61 242

HY-MVS	69.67 12	77.95 220	77.15 217	80.36 248	87.57 217	60.21 292	83.37 280	87.78 235	66.11 290	75.37 245	87.06 238	63.27 149	90.48 272	61.38 286	82.43 232	90.40 206

cl22		78.07 216	77.01 219	81.23 228	82.37 335	61.83 270	83.55 277	87.98 227	68.96 254	75.06 259	83.87 313	61.40 183	91.88 229	73.53 171	76.39 305	89.98 229

Anonymous202405211		78.25 209	77.01 219	81.99 209	91.03 87	60.67 284	84.77 247	83.90 296	70.65 212	80.00 146	91.20 129	41.08 371	91.43 250	65.21 250	85.26 186	93.85 68

MVS		78.19 213	76.99 221	81.78 212	85.66 257	66.99 164	84.66 249	90.47 146	55.08 390	72.02 302	85.27 283	63.83 145	94.11 127	66.10 243	89.80 121	84.24 360

LCM-MVSNet-Re		77.05 238	76.94 222	77.36 305	87.20 227	51.60 384	80.06 326	80.46 345	75.20 109	67.69 344	86.72 243	62.48 162	88.98 298	63.44 263	89.25 127	91.51 163

miper_enhance_ethall		77.87 223	76.86 223	80.92 238	81.65 342	61.38 275	82.68 290	88.98 203	65.52 299	75.47 238	82.30 345	65.76 131	92.00 223	72.95 179	76.39 305	89.39 247

FMVSNet3		77.88 222	76.85 224	80.97 237	86.84 235	62.36 261	86.52 203	88.77 210	71.13 198	75.34 246	86.66 249	54.07 250	91.10 260	62.72 268	79.57 265	89.45 246

DTE-MVSNet		76.99 239	76.80 225	77.54 304	86.24 246	53.06 376	87.52 168	90.66 140	77.08 63	72.50 294	88.67 190	60.48 202	89.52 287	57.33 323	70.74 366	90.05 225

CNLPA		78.08 215	76.79 226	81.97 210	90.40 102	71.07 65	87.59 167	84.55 286	66.03 293	72.38 297	89.64 163	57.56 221	86.04 332	59.61 299	83.35 220	88.79 270

cl____		77.72 226	76.76 227	80.58 244	82.49 332	60.48 287	83.09 285	87.87 231	69.22 244	74.38 272	85.22 286	62.10 170	91.53 244	71.09 194	75.41 324	89.73 240

DIV-MVS_self_test		77.72 226	76.76 227	80.58 244	82.48 333	60.48 287	83.09 285	87.86 232	69.22 244	74.38 272	85.24 284	62.10 170	91.53 244	71.09 194	75.40 325	89.74 239

baseline1		76.98 240	76.75 229	77.66 299	88.13 186	55.66 350	85.12 239	81.89 327	73.04 168	76.79 208	88.90 183	62.43 164	87.78 317	63.30 265	71.18 364	89.55 244

eth_miper_zixun_eth		77.92 221	76.69 230	81.61 217	83.00 319	61.98 267	83.15 283	89.20 194	69.52 237	74.86 263	84.35 304	61.76 174	92.56 200	71.50 191	72.89 352	90.28 211

pm-mvs1		77.25 237	76.68 231	78.93 276	84.22 288	58.62 303	86.41 205	88.36 221	71.37 194	73.31 283	88.01 212	61.22 188	89.15 295	64.24 259	73.01 351	89.03 258

ET-MVSNet_ETH3D		78.63 202	76.63 232	84.64 105	86.73 238	69.47 95	85.01 242	84.61 285	69.54 236	66.51 362	86.59 251	50.16 296	91.75 233	76.26 144	84.24 202	92.69 125

test2506		77.30 236	76.49 233	79.74 261	90.08 109	52.02 377	87.86 162	63.10 419	74.88 119	80.16 145	92.79 91	38.29 385	92.35 211	68.74 221	92.50 78	94.86 18

Fast-Effi-MVS+-dtu		78.02 218	76.49 233	82.62 199	83.16 315	66.96 167	86.94 188	87.45 242	72.45 175	71.49 308	84.17 310	54.79 243	91.58 239	67.61 229	80.31 258	89.30 250

1112_ss		77.40 234	76.43 235	80.32 250	89.11 151	60.41 289	83.65 273	87.72 236	62.13 342	73.05 287	86.72 243	62.58 161	89.97 279	62.11 279	80.80 251	90.59 198

PAPM		77.68 229	76.40 236	81.51 218	87.29 226	61.85 269	83.78 270	89.59 178	64.74 308	71.23 309	88.70 188	62.59 160	93.66 149	52.66 350	87.03 162	89.01 259

PLC	70.83 11	78.05 217	76.37 237	83.08 178	91.88 77	67.80 141	88.19 148	89.46 182	64.33 314	69.87 326	88.38 199	53.66 253	93.58 150	58.86 307	82.73 228	87.86 292
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TR-MVS		77.44 232	76.18 238	81.20 229	88.24 180	63.24 247	84.61 252	86.40 263	67.55 272	77.81 185	86.48 257	54.10 249	93.15 177	57.75 319	82.72 229	87.20 307

FMVSNet1		77.44 232	76.12 239	81.40 222	86.81 236	63.01 252	88.39 139	89.28 188	70.49 214	74.39 271	87.28 227	49.06 312	91.11 257	60.91 289	78.52 276	90.09 220

MonoMVSNet		76.49 251	75.80 240	78.58 282	81.55 345	58.45 304	86.36 208	86.22 266	74.87 121	74.73 265	83.73 319	51.79 279	88.73 303	70.78 196	72.15 357	88.55 280

test_vis1_n_1920		75.52 265	75.78 241	74.75 335	79.84 368	57.44 323	83.26 281	85.52 275	62.83 333	79.34 155	86.17 264	45.10 344	79.71 376	78.75 118	81.21 245	87.10 314

CHOSEN 1792x2688		77.63 230	75.69 242	83.44 160	89.98 115	68.58 122	78.70 346	87.50 240	56.38 385	75.80 233	86.84 239	58.67 211	91.40 251	61.58 284	85.75 184	90.34 207

FE-MVS		77.78 224	75.68 243	84.08 134	88.09 189	66.00 179	83.13 284	87.79 234	68.42 264	78.01 182	85.23 285	45.50 342	95.12 85	59.11 304	85.83 183	91.11 175

WTY-MVS		75.65 263	75.68 243	75.57 321	86.40 244	56.82 330	77.92 359	82.40 322	65.10 303	76.18 226	87.72 215	63.13 156	80.90 372	60.31 293	81.96 237	89.00 261

testing91		76.54 246	75.66 245	79.18 273	88.43 174	55.89 346	81.08 308	83.00 314	73.76 148	75.34 246	84.29 305	46.20 333	90.07 277	64.33 257	84.50 194	91.58 161

XXY-MVS		75.41 268	75.56 246	74.96 330	83.59 303	57.82 316	80.59 318	83.87 297	66.54 287	74.93 262	88.31 201	63.24 150	80.09 375	62.16 277	76.85 298	86.97 315

thres100view900		76.50 248	75.55 247	79.33 269	89.52 126	56.99 328	85.83 224	83.23 307	73.94 143	76.32 222	87.12 235	51.89 276	91.95 225	48.33 375	83.75 209	89.07 252

thres600view7		76.50 248	75.44 248	79.68 263	89.40 133	57.16 325	85.53 232	83.23 307	73.79 147	76.26 223	87.09 236	51.89 276	91.89 228	48.05 380	83.72 212	90.00 226

Test_1112_low_res		76.40 253	75.44 248	79.27 270	89.28 141	58.09 308	81.69 300	87.07 250	59.53 362	72.48 295	86.67 248	61.30 185	89.33 290	60.81 291	80.15 260	90.41 205

HyFIR lowres test		77.53 231	75.40 250	83.94 148	89.59 123	66.62 169	80.36 322	88.64 217	56.29 386	76.45 218	85.17 287	57.64 220	93.28 165	61.34 287	83.10 224	91.91 154

thisisatest0515		77.33 235	75.38 251	83.18 172	85.27 267	63.80 233	82.11 296	83.27 306	65.06 304	75.91 230	83.84 315	49.54 303	94.27 118	67.24 234	86.19 175	91.48 166

tfpn200view9		76.42 252	75.37 252	79.55 268	89.13 147	57.65 319	85.17 236	83.60 299	73.41 159	76.45 218	86.39 259	52.12 268	91.95 225	48.33 375	83.75 209	89.07 252

thres400		76.50 248	75.37 252	79.86 258	89.13 147	57.65 319	85.17 236	83.60 299	73.41 159	76.45 218	86.39 259	52.12 268	91.95 225	48.33 375	83.75 209	90.00 226

1314		76.53 247	75.30 254	80.21 252	83.93 295	62.32 263	84.66 249	88.81 208	60.23 355	70.16 320	84.07 312	55.30 237	90.73 269	67.37 232	83.21 222	87.59 299

testing3-2		75.12 273	75.19 255	74.91 331	90.40 102	45.09 412	80.29 324	78.42 364	78.37 37	76.54 217	87.75 214	44.36 349	87.28 321	57.04 326	83.49 217	92.37 137

GA-MVS		76.87 242	75.17 256	81.97 210	82.75 325	62.58 259	81.44 305	86.35 265	72.16 182	74.74 264	82.89 336	46.20 333	92.02 222	68.85 220	81.09 246	91.30 171

testing99		76.09 258	75.12 257	79.00 274	88.16 183	55.50 352	80.79 312	81.40 334	73.30 162	75.17 254	84.27 308	44.48 348	90.02 278	64.28 258	84.22 203	91.48 166

EPNet_dtu		75.46 266	74.86 258	77.23 308	82.57 330	54.60 361	86.89 190	83.09 311	71.64 186	66.25 364	85.86 269	55.99 233	88.04 313	54.92 338	86.55 169	89.05 257
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LS3D		76.95 241	74.82 259	83.37 164	90.45 100	67.36 155	89.15 110	86.94 253	61.87 345	69.52 329	90.61 145	51.71 280	94.53 110	46.38 387	86.71 167	88.21 286

cascas		76.72 245	74.64 260	82.99 183	85.78 255	65.88 183	82.33 293	89.21 193	60.85 351	72.74 290	81.02 356	47.28 321	93.75 146	67.48 231	85.02 187	89.34 249

DP-MVS		76.78 244	74.57 261	83.42 161	93.29 48	69.46 97	88.55 135	83.70 298	63.98 321	70.20 317	88.89 184	54.01 251	94.80 102	46.66 384	81.88 239	86.01 333

TransMVSNet (Re)		75.39 270	74.56 262	77.86 295	85.50 262	57.10 327	86.78 195	86.09 270	72.17 181	71.53 307	87.34 226	63.01 157	89.31 291	56.84 329	61.83 393	87.17 308

LTVRE_ROB	69.57 13	76.25 255	74.54 263	81.41 221	88.60 167	64.38 224	79.24 336	89.12 199	70.76 207	69.79 328	87.86 213	49.09 311	93.20 173	56.21 334	80.16 259	86.65 322
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
thres200		75.55 264	74.47 264	78.82 277	87.78 206	57.85 315	83.07 287	83.51 302	72.44 177	75.84 232	84.42 300	52.08 271	91.75 233	47.41 382	83.64 214	86.86 317

MVP-Stereo		76.12 256	74.46 265	81.13 232	85.37 265	69.79 89	84.42 260	87.95 229	65.03 305	67.46 347	85.33 282	53.28 258	91.73 235	58.01 317	83.27 221	81.85 386
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
reproduce_monomvs		75.40 269	74.38 266	78.46 288	83.92 296	57.80 317	83.78 270	86.94 253	73.47 157	72.25 299	84.47 299	38.74 381	89.27 292	75.32 157	70.53 367	88.31 284

F-COLMAP		76.38 254	74.33 267	82.50 201	89.28 141	66.95 168	88.41 138	89.03 200	64.05 319	66.83 354	88.61 192	46.78 325	92.89 189	57.48 320	78.55 275	87.67 295

XVG-ACMP-BASELINE		76.11 257	74.27 268	81.62 215	83.20 312	64.67 216	83.60 276	89.75 173	69.75 233	71.85 303	87.09 236	32.78 398	92.11 219	69.99 207	80.43 257	88.09 288

testing11		75.14 272	74.01 269	78.53 285	88.16 183	56.38 339	80.74 315	80.42 346	70.67 208	72.69 293	83.72 320	43.61 355	89.86 280	62.29 275	83.76 208	89.36 248

ACMH+	68.96 14	76.01 259	74.01 269	82.03 208	88.60 167	65.31 199	88.86 120	87.55 238	70.25 220	67.75 343	87.47 225	41.27 369	93.19 175	58.37 313	75.94 313	87.60 297

ACMH	67.68 16	75.89 260	73.93 271	81.77 213	88.71 164	66.61 170	88.62 133	89.01 202	69.81 229	66.78 355	86.70 247	41.95 367	91.51 246	55.64 335	78.14 282	87.17 308
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CostFormer		75.24 271	73.90 272	79.27 270	82.65 329	58.27 307	80.80 311	82.73 320	61.57 346	75.33 250	83.13 331	55.52 235	91.07 263	64.98 253	78.34 281	88.45 281

IterMVS-SCA-FT		75.43 267	73.87 273	80.11 254	82.69 327	64.85 213	81.57 302	83.47 303	69.16 247	70.49 314	84.15 311	51.95 274	88.15 311	69.23 214	72.14 358	87.34 304

baseline2		75.70 262	73.83 274	81.30 225	83.26 310	61.79 271	82.57 292	80.65 341	66.81 277	66.88 353	83.42 326	57.86 218	92.19 217	63.47 262	79.57 265	89.91 231

test_cas_vis1_n_1920		73.76 286	73.74 275	73.81 344	75.90 390	59.77 295	80.51 319	82.40 322	58.30 372	81.62 128	85.69 272	44.35 350	76.41 394	76.29 143	78.61 274	85.23 346

sss		73.60 288	73.64 276	73.51 346	82.80 324	55.01 358	76.12 367	81.69 330	62.47 338	74.68 266	85.85 270	57.32 224	78.11 383	60.86 290	80.93 247	87.39 302

myMVS_eth3d28		73.62 287	73.53 277	73.90 343	88.20 181	47.41 402	78.06 356	79.37 357	74.29 136	73.98 275	84.29 305	44.67 345	83.54 355	51.47 356	87.39 156	90.74 191

SSC-MVS3.2		73.35 294	73.39 278	73.23 347	85.30 266	49.01 398	74.58 382	81.57 331	75.21 108	73.68 279	85.58 277	52.53 260	82.05 365	54.33 342	77.69 288	88.63 277

pmmvs6		74.69 275	73.39 278	78.61 280	81.38 349	57.48 322	86.64 199	87.95 229	64.99 307	70.18 318	86.61 250	50.43 294	89.52 287	62.12 278	70.18 369	88.83 268

IB-MVS	68.01 15	75.85 261	73.36 280	83.31 165	84.76 277	66.03 177	83.38 279	85.06 280	70.21 221	69.40 330	81.05 355	45.76 338	94.66 108	65.10 252	75.49 319	89.25 251
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
D2MVS		74.82 274	73.21 281	79.64 265	79.81 369	62.56 260	80.34 323	87.35 243	64.37 313	68.86 335	82.66 340	46.37 329	90.10 276	67.91 227	81.24 244	86.25 326

tfpnnormal		74.39 276	73.16 282	78.08 293	86.10 252	58.05 309	84.65 251	87.53 239	70.32 217	71.22 310	85.63 275	54.97 238	89.86 280	43.03 398	75.02 332	86.32 325

miper_lstm_enhance		74.11 281	73.11 283	77.13 309	80.11 364	59.62 297	72.23 389	86.92 255	66.76 279	70.40 315	82.92 335	56.93 228	82.92 360	69.06 217	72.63 353	88.87 266

mmtdpeth		74.16 280	73.01 284	77.60 303	83.72 301	61.13 276	85.10 240	85.10 279	72.06 183	77.21 202	80.33 364	43.84 353	85.75 334	77.14 136	52.61 411	85.91 336

IterMVS		74.29 277	72.94 285	78.35 289	81.53 346	63.49 241	81.58 301	82.49 321	68.06 268	69.99 323	83.69 321	51.66 281	85.54 338	65.85 246	71.64 361	86.01 333
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		73.43 290	72.81 286	75.28 327	87.91 197	50.99 390	78.59 349	81.31 336	65.51 301	74.47 270	84.83 294	46.39 327	86.68 325	58.41 312	77.86 284	88.17 287

MS-PatchMatch		73.83 285	72.67 287	77.30 307	83.87 297	66.02 178	81.82 297	84.66 284	61.37 349	68.61 338	82.82 338	47.29 320	88.21 310	59.27 301	84.32 201	77.68 401

testing222		74.04 282	72.66 288	78.19 291	87.89 198	55.36 353	81.06 309	79.20 360	71.30 195	74.65 267	83.57 324	39.11 380	88.67 305	51.43 358	85.75 184	90.53 200

CVMVSNet		72.99 300	72.58 289	74.25 339	84.28 286	50.85 391	86.41 205	83.45 304	44.56 410	73.23 285	87.54 223	49.38 306	85.70 335	65.90 245	78.44 278	86.19 328

test-LLR		72.94 301	72.43 290	74.48 336	81.35 350	58.04 310	78.38 350	77.46 370	66.66 281	69.95 324	79.00 377	48.06 317	79.24 377	66.13 241	84.83 189	86.15 329

OurMVSNet-221017-0		74.26 278	72.42 291	79.80 260	83.76 300	59.59 298	85.92 220	86.64 258	66.39 288	66.96 352	87.58 219	39.46 377	91.60 238	65.76 247	69.27 372	88.22 285

SCA		74.22 279	72.33 292	79.91 257	84.05 293	62.17 265	79.96 329	79.29 359	66.30 289	72.38 297	80.13 366	51.95 274	88.60 306	59.25 302	77.67 289	88.96 263

UBG		73.08 298	72.27 293	75.51 323	88.02 192	51.29 388	78.35 353	77.38 373	65.52 299	73.87 277	82.36 343	45.55 340	86.48 328	55.02 337	84.39 200	88.75 272

tpmrst		72.39 303	72.13 294	73.18 351	80.54 359	49.91 395	79.91 330	79.08 361	63.11 327	71.69 305	79.95 368	55.32 236	82.77 361	65.66 248	73.89 342	86.87 316

pmmvs4		74.03 284	71.91 295	80.39 247	81.96 338	68.32 128	81.45 304	82.14 324	59.32 363	69.87 326	85.13 288	52.40 264	88.13 312	60.21 294	74.74 335	84.73 356

EG-PatchMatch MVS		74.04 282	71.82 296	80.71 242	84.92 275	67.42 151	85.86 222	88.08 225	66.04 292	64.22 376	83.85 314	35.10 394	92.56 200	57.44 321	80.83 250	82.16 385

tpm		72.37 305	71.71 297	74.35 338	82.19 336	52.00 378	79.22 337	77.29 374	64.56 310	72.95 289	83.68 322	51.35 282	83.26 359	58.33 314	75.80 314	87.81 293

WB-MVSnew		71.96 310	71.65 298	72.89 352	84.67 282	51.88 381	82.29 294	77.57 369	62.31 339	73.67 280	83.00 333	53.49 256	81.10 371	45.75 391	82.13 235	85.70 339

UWE-MVS		72.13 308	71.49 299	74.03 341	86.66 241	47.70 400	81.40 306	76.89 378	63.60 324	75.59 235	84.22 309	39.94 376	85.62 337	48.98 372	86.13 177	88.77 271

CL-MVSNet_self_test		72.37 305	71.46 300	75.09 329	79.49 375	53.53 369	80.76 314	85.01 282	69.12 248	70.51 313	82.05 349	57.92 217	84.13 350	52.27 352	66.00 385	87.60 297

tpm2		73.26 295	71.46 300	78.63 279	83.34 308	56.71 333	80.65 317	80.40 347	56.63 384	73.55 281	82.02 350	51.80 278	91.24 255	56.35 333	78.42 279	87.95 289

RPSCF		73.23 296	71.46 300	78.54 284	82.50 331	59.85 294	82.18 295	82.84 319	58.96 367	71.15 311	89.41 175	45.48 343	84.77 347	58.82 308	71.83 360	91.02 181

PatchmatchNet		73.12 297	71.33 303	78.49 287	83.18 313	60.85 281	79.63 331	78.57 363	64.13 315	71.73 304	79.81 371	51.20 285	85.97 333	57.40 322	76.36 310	88.66 275
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CR-MVSNet		73.37 291	71.27 304	79.67 264	81.32 352	65.19 201	75.92 369	80.30 348	59.92 358	72.73 291	81.19 353	52.50 262	86.69 324	59.84 296	77.71 286	87.11 312

SixPastTwentyTwo		73.37 291	71.26 305	79.70 262	85.08 273	57.89 314	85.57 226	83.56 301	71.03 202	65.66 366	85.88 268	42.10 365	92.57 199	59.11 304	63.34 391	88.65 276

ETVMVS		72.25 307	71.05 306	75.84 317	87.77 207	51.91 380	79.39 334	74.98 385	69.26 242	73.71 278	82.95 334	40.82 373	86.14 331	46.17 388	84.43 199	89.47 245

MSDG		73.36 293	70.99 307	80.49 246	84.51 284	65.80 186	80.71 316	86.13 269	65.70 296	65.46 367	83.74 318	44.60 346	90.91 265	51.13 359	76.89 296	84.74 355

PatchMatch-RL		72.38 304	70.90 308	76.80 312	88.60 167	67.38 154	79.53 332	76.17 382	62.75 335	69.36 331	82.00 351	45.51 341	84.89 346	53.62 345	80.58 254	78.12 400

PVSNet	64.34 18	72.08 309	70.87 309	75.69 319	86.21 247	56.44 337	74.37 383	80.73 340	62.06 343	70.17 319	82.23 347	42.86 359	83.31 358	54.77 339	84.45 198	87.32 305

dmvs_re		71.14 314	70.58 310	72.80 353	81.96 338	59.68 296	75.60 373	79.34 358	68.55 260	69.27 333	80.72 361	49.42 305	76.54 391	52.56 351	77.79 285	82.19 384

test_fmvs1		70.93 317	70.52 311	72.16 358	73.71 401	55.05 357	80.82 310	78.77 362	51.21 402	78.58 167	84.41 301	31.20 403	76.94 389	75.88 149	80.12 262	84.47 358

RPMNet		73.51 289	70.49 312	82.58 200	81.32 352	65.19 201	75.92 369	92.27 84	57.60 378	72.73 291	76.45 393	52.30 265	95.43 70	48.14 379	77.71 286	87.11 312

test_0402		72.79 302	70.44 313	79.84 259	88.13 186	65.99 180	85.93 219	84.29 290	65.57 298	67.40 349	85.49 279	46.92 324	92.61 196	35.88 412	74.38 338	80.94 391

COLMAP_ROB	66.92 17	73.01 299	70.41 314	80.81 240	87.13 230	65.63 190	88.30 145	84.19 293	62.96 330	63.80 381	87.69 217	38.04 386	92.56 200	46.66 384	74.91 333	84.24 360
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test-mter		71.41 312	70.39 315	74.48 336	81.35 350	58.04 310	78.38 350	77.46 370	60.32 354	69.95 324	79.00 377	36.08 392	79.24 377	66.13 241	84.83 189	86.15 329

test_fmvs1_n		70.86 318	70.24 316	72.73 354	72.51 412	55.28 355	81.27 307	79.71 354	51.49 401	78.73 162	84.87 293	27.54 408	77.02 388	76.06 146	79.97 263	85.88 337

pmmvs5		71.55 311	70.20 317	75.61 320	77.83 383	56.39 338	81.74 299	80.89 337	57.76 376	67.46 347	84.49 298	49.26 309	85.32 342	57.08 325	75.29 328	85.11 350

MDTV_nov1_ep13			69.97 318		83.18 313	53.48 370	77.10 365	80.18 351	60.45 352	69.33 332	80.44 362	48.89 315	86.90 323	51.60 355	78.51 277

MIMVSNet		70.69 320	69.30 319	74.88 332	84.52 283	56.35 341	75.87 371	79.42 356	64.59 309	67.76 342	82.41 342	41.10 370	81.54 368	46.64 386	81.34 242	86.75 320

tpmvs		71.09 315	69.29 320	76.49 313	82.04 337	56.04 344	78.92 343	81.37 335	64.05 319	67.18 351	78.28 383	49.74 302	89.77 282	49.67 369	72.37 354	83.67 368

test_vis1_n		69.85 330	69.21 321	71.77 360	72.66 411	55.27 356	81.48 303	76.21 381	52.03 398	75.30 251	83.20 330	28.97 406	76.22 396	74.60 161	78.41 280	83.81 366

Patchmtry		70.74 319	69.16 322	75.49 324	80.72 356	54.07 366	74.94 380	80.30 348	58.34 371	70.01 321	81.19 353	52.50 262	86.54 326	53.37 347	71.09 365	85.87 338

TESTMET0.1,1		69.89 329	69.00 323	72.55 355	79.27 378	56.85 329	78.38 350	74.71 389	57.64 377	68.09 341	77.19 390	37.75 387	76.70 390	63.92 260	84.09 204	84.10 363

PMMVS		69.34 333	68.67 324	71.35 365	75.67 392	62.03 266	75.17 375	73.46 392	50.00 403	68.68 336	79.05 375	52.07 272	78.13 382	61.16 288	82.77 227	73.90 407

K. test v3		71.19 313	68.51 325	79.21 272	83.04 318	57.78 318	84.35 262	76.91 377	72.90 171	62.99 384	82.86 337	39.27 378	91.09 262	61.65 283	52.66 410	88.75 272

USDC		70.33 324	68.37 326	76.21 315	80.60 358	56.23 342	79.19 338	86.49 261	60.89 350	61.29 389	85.47 280	31.78 401	89.47 289	53.37 347	76.21 311	82.94 378

tpm cat1		70.57 321	68.31 327	77.35 306	82.41 334	57.95 313	78.08 355	80.22 350	52.04 397	68.54 339	77.66 388	52.00 273	87.84 316	51.77 353	72.07 359	86.25 326

OpenMVS_ROB	64.09 19	70.56 322	68.19 328	77.65 300	80.26 361	59.41 300	85.01 242	82.96 316	58.76 369	65.43 368	82.33 344	37.63 388	91.23 256	45.34 394	76.03 312	82.32 382

EPMVS		69.02 335	68.16 329	71.59 361	79.61 373	49.80 397	77.40 362	66.93 410	62.82 334	70.01 321	79.05 375	45.79 337	77.86 385	56.58 331	75.26 329	87.13 311

CMPMVS	51.72 21	70.19 326	68.16 329	76.28 314	73.15 408	57.55 321	79.47 333	83.92 295	48.02 406	56.48 406	84.81 295	43.13 357	86.42 329	62.67 271	81.81 240	84.89 353
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
AllTest		70.96 316	68.09 331	79.58 266	85.15 270	63.62 235	84.58 253	79.83 352	62.31 339	60.32 393	86.73 241	32.02 399	88.96 300	50.28 364	71.57 362	86.15 329

gg-mvs-nofinetune		69.95 328	67.96 332	75.94 316	83.07 316	54.51 363	77.23 364	70.29 400	63.11 327	70.32 316	62.33 414	43.62 354	88.69 304	53.88 344	87.76 151	84.62 357

FMVSNet5		69.50 331	67.96 332	74.15 340	82.97 322	55.35 354	80.01 328	82.12 325	62.56 337	63.02 382	81.53 352	36.92 389	81.92 366	48.42 374	74.06 340	85.17 349

Syy-MVS		68.05 344	67.85 334	68.67 380	84.68 279	40.97 423	78.62 347	73.08 394	66.65 284	66.74 356	79.46 372	52.11 270	82.30 363	32.89 415	76.38 308	82.75 379

PatchT		68.46 342	67.85 334	70.29 371	80.70 357	43.93 415	72.47 388	74.88 386	60.15 356	70.55 312	76.57 392	49.94 299	81.59 367	50.58 360	74.83 334	85.34 344

pmmvs-eth3d		70.50 323	67.83 336	78.52 286	77.37 386	66.18 176	81.82 297	81.51 332	58.90 368	63.90 380	80.42 363	42.69 360	86.28 330	58.56 310	65.30 387	83.11 374

Anonymous20231206		68.60 338	67.80 337	71.02 368	80.23 363	50.75 392	78.30 354	80.47 344	56.79 383	66.11 365	82.63 341	46.35 330	78.95 379	43.62 397	75.70 315	83.36 371

Patchmatch-RL test		70.24 325	67.78 338	77.61 301	77.43 385	59.57 299	71.16 393	70.33 399	62.94 331	68.65 337	72.77 405	50.62 291	85.49 339	69.58 212	66.58 382	87.77 294

test0.0.03 1		68.00 345	67.69 339	68.90 377	77.55 384	47.43 401	75.70 372	72.95 396	66.66 281	66.56 358	82.29 346	48.06 317	75.87 400	44.97 395	74.51 337	83.41 370

testing3		68.56 340	67.67 340	71.22 367	87.33 223	42.87 417	83.06 288	71.54 397	70.36 215	69.08 334	84.38 302	30.33 405	85.69 336	37.50 410	75.45 323	85.09 351

EU-MVSNet		68.53 341	67.61 341	71.31 366	78.51 382	47.01 404	84.47 255	84.27 291	42.27 413	66.44 363	84.79 296	40.44 374	83.76 352	58.76 309	68.54 377	83.17 372

KD-MVS_self_test		68.81 336	67.59 342	72.46 357	74.29 398	45.45 407	77.93 358	87.00 251	63.12 326	63.99 379	78.99 379	42.32 362	84.77 347	56.55 332	64.09 390	87.16 310

test_fmvs2		68.35 343	67.48 343	70.98 369	69.50 415	51.95 379	80.05 327	76.38 380	49.33 404	74.65 267	84.38 302	23.30 417	75.40 405	74.51 162	75.17 331	85.60 340

mvs5depth		69.45 332	67.45 344	75.46 325	73.93 399	55.83 347	79.19 338	83.23 307	66.89 276	71.63 306	83.32 327	33.69 397	85.09 343	59.81 297	55.34 407	85.46 342

ppachtmachnet_test		70.04 327	67.34 345	78.14 292	79.80 370	61.13 276	79.19 338	80.59 342	59.16 365	65.27 369	79.29 374	46.75 326	87.29 320	49.33 370	66.72 380	86.00 335

Anonymous20240521		68.80 337	67.22 346	73.55 345	74.33 397	54.11 365	83.18 282	85.61 274	58.15 373	61.68 388	80.94 358	30.71 404	81.27 370	57.00 327	73.34 350	85.28 345

our_test_3		69.14 334	67.00 347	75.57 321	79.80 370	58.80 301	77.96 357	77.81 367	59.55 361	62.90 385	78.25 384	47.43 319	83.97 351	51.71 354	67.58 379	83.93 365

test20.03		67.45 347	66.95 348	68.94 376	75.48 394	44.84 413	77.50 361	77.67 368	66.66 281	63.01 383	83.80 316	47.02 323	78.40 381	42.53 401	68.86 376	83.58 369

MIMVSNet1		68.58 339	66.78 349	73.98 342	80.07 365	51.82 382	80.77 313	84.37 287	64.40 312	59.75 396	82.16 348	36.47 390	83.63 354	42.73 399	70.33 368	86.48 324

testgi		66.67 353	66.53 350	67.08 387	75.62 393	41.69 422	75.93 368	76.50 379	66.11 290	65.20 372	86.59 251	35.72 393	74.71 407	43.71 396	73.38 349	84.84 354

myMVS_eth3d		67.02 350	66.29 351	69.21 375	84.68 279	42.58 418	78.62 347	73.08 394	66.65 284	66.74 356	79.46 372	31.53 402	82.30 363	39.43 407	76.38 308	82.75 379

UnsupCasMVSNet_eth		67.33 348	65.99 352	71.37 363	73.48 404	51.47 386	75.16 376	85.19 278	65.20 302	60.78 391	80.93 360	42.35 361	77.20 387	57.12 324	53.69 409	85.44 343

dp		66.80 351	65.43 353	70.90 370	79.74 372	48.82 399	75.12 378	74.77 387	59.61 360	64.08 378	77.23 389	42.89 358	80.72 373	48.86 373	66.58 382	83.16 373

UWE-MVS-28		65.32 360	64.93 354	66.49 388	78.70 380	38.55 425	77.86 360	64.39 417	62.00 344	64.13 377	83.60 323	41.44 368	76.00 398	31.39 417	80.89 248	84.92 352

TinyColmap		67.30 349	64.81 355	74.76 334	81.92 340	56.68 334	80.29 324	81.49 333	60.33 353	56.27 407	83.22 328	24.77 413	87.66 319	45.52 392	69.47 371	79.95 396

CHOSEN 280x420		66.51 354	64.71 356	71.90 359	81.45 347	63.52 240	57.98 423	68.95 406	53.57 393	62.59 386	76.70 391	46.22 332	75.29 406	55.25 336	79.68 264	76.88 403

TDRefinement		67.49 346	64.34 357	76.92 310	73.47 405	61.07 278	84.86 246	82.98 315	59.77 359	58.30 400	85.13 288	26.06 409	87.89 315	47.92 381	60.59 398	81.81 387

PM-MVS		66.41 355	64.14 358	73.20 350	73.92 400	56.45 336	78.97 342	64.96 416	63.88 323	64.72 373	80.24 365	19.84 421	83.44 357	66.24 240	64.52 389	79.71 397

dmvs_testset		62.63 368	64.11 359	58.19 398	78.55 381	24.76 436	75.28 374	65.94 413	67.91 269	60.34 392	76.01 395	53.56 254	73.94 411	31.79 416	67.65 378	75.88 405

KD-MVS_2432*1600		66.22 357	63.89 360	73.21 348	75.47 395	53.42 371	70.76 396	84.35 288	64.10 317	66.52 360	78.52 381	34.55 395	84.98 344	50.40 362	50.33 414	81.23 389

miper_refine_blended		66.22 357	63.89 360	73.21 348	75.47 395	53.42 371	70.76 396	84.35 288	64.10 317	66.52 360	78.52 381	34.55 395	84.98 344	50.40 362	50.33 414	81.23 389

MDA-MVSNet-bldmvs		66.68 352	63.66 362	75.75 318	79.28 377	60.56 286	73.92 385	78.35 365	64.43 311	50.13 415	79.87 370	44.02 352	83.67 353	46.10 389	56.86 401	83.03 376

ADS-MVSNet2		66.20 359	63.33 363	74.82 333	79.92 366	58.75 302	67.55 408	75.19 384	53.37 394	65.25 370	75.86 396	42.32 362	80.53 374	41.57 402	68.91 374	85.18 347

Patchmatch-test		64.82 363	63.24 364	69.57 373	79.42 376	49.82 396	63.49 420	69.05 405	51.98 399	59.95 395	80.13 366	50.91 287	70.98 414	40.66 404	73.57 345	87.90 291

MDA-MVSNet_test_wron		65.03 361	62.92 365	71.37 363	75.93 389	56.73 331	69.09 405	74.73 388	57.28 381	54.03 410	77.89 385	45.88 335	74.39 409	49.89 368	61.55 394	82.99 377

YYNet1		65.03 361	62.91 366	71.38 362	75.85 391	56.60 335	69.12 404	74.66 390	57.28 381	54.12 409	77.87 386	45.85 336	74.48 408	49.95 367	61.52 395	83.05 375

ADS-MVSNet		64.36 364	62.88 367	68.78 379	79.92 366	47.17 403	67.55 408	71.18 398	53.37 394	65.25 370	75.86 396	42.32 362	73.99 410	41.57 402	68.91 374	85.18 347

JIA-IIPM		66.32 356	62.82 368	76.82 311	77.09 387	61.72 272	65.34 416	75.38 383	58.04 375	64.51 374	62.32 415	42.05 366	86.51 327	51.45 357	69.22 373	82.21 383

LF4IMVS		64.02 365	62.19 369	69.50 374	70.90 413	53.29 374	76.13 366	77.18 375	52.65 396	58.59 398	80.98 357	23.55 416	76.52 392	53.06 349	66.66 381	78.68 399

test_fmvs3		63.36 367	61.82 370	67.98 384	62.51 424	46.96 405	77.37 363	74.03 391	45.24 409	67.50 346	78.79 380	12.16 429	72.98 413	72.77 182	66.02 384	83.99 364

new-patchmatchnet		61.73 370	61.73 371	61.70 394	72.74 410	24.50 437	69.16 403	78.03 366	61.40 347	56.72 405	75.53 399	38.42 383	76.48 393	45.95 390	57.67 400	84.13 362

UnsupCasMVSNet_bld		63.70 366	61.53 372	70.21 372	73.69 402	51.39 387	72.82 387	81.89 327	55.63 388	57.81 402	71.80 407	38.67 382	78.61 380	49.26 371	52.21 412	80.63 393

mvsany_test1		62.30 369	61.26 373	65.41 390	69.52 414	54.86 359	66.86 410	49.78 430	46.65 407	68.50 340	83.21 329	49.15 310	66.28 422	56.93 328	60.77 396	75.11 406

PVSNet_0	57.27 20	61.67 371	59.27 374	68.85 378	79.61 373	57.44 323	68.01 406	73.44 393	55.93 387	58.54 399	70.41 410	44.58 347	77.55 386	47.01 383	35.91 422	71.55 410

test_vis1_rt		60.28 372	58.42 375	65.84 389	67.25 418	55.60 351	70.44 398	60.94 422	44.33 411	59.00 397	66.64 412	24.91 412	68.67 419	62.80 267	69.48 370	73.25 408

MVS-HIRNet		59.14 374	57.67 376	63.57 392	81.65 342	43.50 416	71.73 390	65.06 415	39.59 417	51.43 412	57.73 420	38.34 384	82.58 362	39.53 405	73.95 341	64.62 416

ttmdpeth		59.91 373	57.10 377	68.34 382	67.13 419	46.65 406	74.64 381	67.41 409	48.30 405	62.52 387	85.04 292	20.40 419	75.93 399	42.55 400	45.90 420	82.44 381

DSMNet-mixed		57.77 376	56.90 378	60.38 396	67.70 417	35.61 427	69.18 402	53.97 428	32.30 426	57.49 403	79.88 369	40.39 375	68.57 420	38.78 408	72.37 354	76.97 402

WB-MVS		54.94 378	54.72 379	55.60 404	73.50 403	20.90 438	74.27 384	61.19 421	59.16 365	50.61 413	74.15 401	47.19 322	75.78 401	17.31 429	35.07 423	70.12 411

pmmvs3		57.79 375	54.26 380	68.37 381	64.02 423	56.72 332	75.12 378	65.17 414	40.20 415	52.93 411	69.86 411	20.36 420	75.48 403	45.45 393	55.25 408	72.90 409

SSC-MVS		53.88 381	53.59 381	54.75 406	72.87 409	19.59 439	73.84 386	60.53 423	57.58 379	49.18 417	73.45 404	46.34 331	75.47 404	16.20 432	32.28 425	69.20 412

N_pmnet		52.79 384	53.26 382	51.40 408	78.99 379	7.68 442	69.52 400	3.89 441	51.63 400	57.01 404	74.98 400	40.83 372	65.96 423	37.78 409	64.67 388	80.56 395

MVStest1		56.63 377	52.76 383	68.25 383	61.67 425	53.25 375	71.67 391	68.90 407	38.59 418	50.59 414	83.05 332	25.08 411	70.66 415	36.76 411	38.56 421	80.83 392

FPMVS		53.68 382	51.64 384	59.81 397	65.08 421	51.03 389	69.48 401	69.58 403	41.46 414	40.67 421	72.32 406	16.46 425	70.00 418	24.24 425	65.42 386	58.40 421

mvsany_test3		53.99 380	51.45 385	61.61 395	55.51 429	44.74 414	63.52 419	45.41 434	43.69 412	58.11 401	76.45 393	17.99 422	63.76 425	54.77 339	47.59 416	76.34 404

test_f		52.09 385	50.82 386	55.90 402	53.82 432	42.31 421	59.42 422	58.31 426	36.45 421	56.12 408	70.96 409	12.18 428	57.79 428	53.51 346	56.57 403	67.60 413

new_pmnet		50.91 387	50.29 387	52.78 407	68.58 416	34.94 429	63.71 418	56.63 427	39.73 416	44.95 418	65.47 413	21.93 418	58.48 427	34.98 413	56.62 402	64.92 415

APD_test1		53.31 383	49.93 388	63.42 393	65.68 420	50.13 394	71.59 392	66.90 411	34.43 423	40.58 422	71.56 408	8.65 434	76.27 395	34.64 414	55.36 406	63.86 417

LCM-MVSNet		54.25 379	49.68 389	67.97 385	53.73 433	45.28 410	66.85 411	80.78 339	35.96 422	39.45 423	62.23 416	8.70 433	78.06 384	48.24 378	51.20 413	80.57 394

EGC-MVSNET		52.07 386	47.05 390	67.14 386	83.51 305	60.71 283	80.50 320	67.75 408	0.07 436	0.43 437	75.85 398	24.26 414	81.54 368	28.82 419	62.25 392	59.16 419

test_vis3_rt		49.26 389	47.02 391	56.00 401	54.30 430	45.27 411	66.76 412	48.08 431	36.83 420	44.38 419	53.20 424	7.17 436	64.07 424	56.77 330	55.66 404	58.65 420

ANet_high		50.57 388	46.10 392	63.99 391	48.67 436	39.13 424	70.99 395	80.85 338	61.39 348	31.18 425	57.70 421	17.02 424	73.65 412	31.22 418	15.89 433	79.18 398

dongtai		45.42 392	45.38 393	45.55 410	73.36 406	26.85 434	67.72 407	34.19 436	54.15 392	49.65 416	56.41 423	25.43 410	62.94 426	19.45 427	28.09 427	46.86 426

testf1		45.72 390	41.96 394	57.00 399	56.90 427	45.32 408	66.14 413	59.26 424	26.19 427	30.89 426	60.96 418	4.14 437	70.64 416	26.39 423	46.73 418	55.04 422

APD_test2		45.72 390	41.96 394	57.00 399	56.90 427	45.32 408	66.14 413	59.26 424	26.19 427	30.89 426	60.96 418	4.14 437	70.64 416	26.39 423	46.73 418	55.04 422

Gipuma		45.18 393	41.86 396	55.16 405	77.03 388	51.52 385	32.50 429	80.52 343	32.46 425	27.12 428	35.02 429	9.52 432	75.50 402	22.31 426	60.21 399	38.45 428
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		39.70 396	40.40 397	37.58 413	64.52 422	26.98 432	65.62 415	33.02 437	46.12 408	42.79 420	48.99 426	24.10 415	46.56 434	12.16 435	26.30 428	39.20 427

PMVS	37.38 22	44.16 394	40.28 398	55.82 403	40.82 438	42.54 420	65.12 417	63.99 418	34.43 423	24.48 429	57.12 422	3.92 439	76.17 397	17.10 430	55.52 405	48.75 424
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		40.82 395	38.86 399	46.69 409	53.84 431	16.45 440	48.61 426	49.92 429	37.49 419	31.67 424	60.97 417	8.14 435	56.42 429	28.42 420	30.72 426	67.19 414

E-PMN		31.77 397	30.64 400	35.15 414	52.87 434	27.67 431	57.09 424	47.86 432	24.64 429	16.40 434	33.05 430	11.23 430	54.90 430	14.46 433	18.15 431	22.87 430

EMVS		30.81 399	29.65 401	34.27 415	50.96 435	25.95 435	56.58 425	46.80 433	24.01 430	15.53 435	30.68 431	12.47 427	54.43 431	12.81 434	17.05 432	22.43 431

test_method		31.52 398	29.28 402	38.23 412	27.03 440	6.50 443	20.94 431	62.21 420	4.05 434	22.35 432	52.50 425	13.33 426	47.58 432	27.04 422	34.04 424	60.62 418

cdsmvs_eth3d_5k		19.96 401	26.61 403	0.00 421	0.00 444	0.00 446	0.00 432	89.26 191	0.00 439	0.00 440	88.61 192	61.62 177	0.00 440	0.00 439	0.00 438	0.00 436

MVE	26.22 23	30.37 400	25.89 404	43.81 411	44.55 437	35.46 428	28.87 430	39.07 435	18.20 431	18.58 433	40.18 428	2.68 440	47.37 433	17.07 431	23.78 430	48.60 425
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		18.61 402	21.40 405	10.23 418	4.82 441	10.11 441	34.70 428	30.74 439	1.48 435	23.91 431	26.07 432	28.42 407	13.41 437	27.12 421	15.35 434	7.17 432

wuyk23d		16.82 403	15.94 406	19.46 417	58.74 426	31.45 430	39.22 427	3.74 442	6.84 433	6.04 436	2.70 436	1.27 441	24.29 436	10.54 436	14.40 435	2.63 433

ab-mvs-re		7.23 404	9.64 407	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	86.72 243	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test123		6.12 405	8.11 408	0.14 419	0.06 443	0.09 444	71.05 394	0.03 444	0.04 438	0.25 439	1.30 438	0.05 442	0.03 439	0.21 438	0.01 437	0.29 434

testmvs		6.04 406	8.02 409	0.10 420	0.08 442	0.03 445	69.74 399	0.04 443	0.05 437	0.31 438	1.68 437	0.02 443	0.04 438	0.24 437	0.02 436	0.25 435

pcd_1.5k_mvsjas		5.26 407	7.02 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	63.15 153	0.00 440	0.00 439	0.00 438	0.00 436

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						42.58 418								39.46 406

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 129	91.30 15

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 12	96.44 9	94.41 39

PC_three_1452									68.21 266	92.02 12	94.00 54	82.09 5	95.98 56	84.58 62	96.68 2	94.95 11

No_MVS				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 12	96.44 9	94.41 39

test_one_0601					95.07 7	71.46 57		94.14 5	78.27 38	92.05 11	95.74 6	80.83 11

eth-test2					0.00 444

eth-test					0.00 444

ZD-MVS					94.38 25	72.22 44		92.67 67	70.98 203	87.75 42	94.07 49	74.01 32	96.70 27	84.66 61	94.84 44

IU-MVS					95.30 2	71.25 59		92.95 55	66.81 277	92.39 6				88.94 24	96.63 4	94.85 20

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 52	82.45 3	96.87 20	83.77 73	96.48 8	94.88 15

test_241102_TWO								94.06 10	77.24 56	92.78 4	95.72 8	81.26 8	97.44 7	89.07 21	96.58 6	94.26 49

test_241102_ONE					95.30 2	70.98 66		94.06 10	77.17 59	93.10 1	95.39 14	82.99 1	97.27 12

save fliter					93.80 40	72.35 42	90.47 66	91.17 127	74.31 134

test_0728_THIRD									78.38 35	92.12 9	95.78 4	81.46 7	97.40 9	89.42 16	96.57 7	94.67 28

test_0728_SECOND				87.71 32	95.34 1	71.43 58	93.49 9	94.23 3					97.49 4	89.08 19	96.41 12	94.21 50

test0726					95.27 5	71.25 59	93.60 6	94.11 6	77.33 53	92.81 3	95.79 3	80.98 9

GSMVS																88.96 263

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 283				88.96 263

sam_mvs												50.01 297

ambc				75.24 328	73.16 407	50.51 393	63.05 421	87.47 241		64.28 375	77.81 387	17.80 423	89.73 284	57.88 318	60.64 397	85.49 341

MTGPA								92.02 94

test_post1							78.90 344				5.43 435	48.81 316	85.44 341	59.25 302

test_post											5.46 434	50.36 295	84.24 349

patchmatchnet-post											74.00 402	51.12 286	88.60 306

GG-mvs-BLEND				75.38 326	81.59 344	55.80 348	79.32 335	69.63 402		67.19 350	73.67 403	43.24 356	88.90 302	50.41 361	84.50 194	81.45 388

MTMP							92.18 34	32.83 438

gm-plane-assit					81.40 348	53.83 368			62.72 336		80.94 358		92.39 208	63.40 264

test9_res														84.90 55	95.70 26	92.87 120

TEST9					93.26 52	72.96 25	88.75 126	91.89 102	68.44 263	85.00 71	93.10 79	74.36 28	95.41 73

test_8					93.13 54	72.57 35	88.68 131	91.84 106	68.69 258	84.87 75	93.10 79	74.43 26	95.16 83

agg_prior2														82.91 82	95.45 29	92.70 123

agg_prior					92.85 62	71.94 50		91.78 109		84.41 86			94.93 94

TestCases				79.58 266	85.15 270	63.62 235		79.83 352	62.31 339	60.32 393	86.73 241	32.02 399	88.96 300	50.28 364	71.57 362	86.15 329

test_prior4						72.60 34	89.01 115

test_prior2							88.85 122		75.41 102	84.91 73	93.54 67	74.28 29		83.31 76	95.86 20

test_prior				86.33 57	92.61 68	69.59 91		92.97 54					95.48 67			93.91 64

旧先验2							86.56 202		58.10 374	87.04 53			88.98 298	74.07 167

新几何2							86.29 211

新几何1				83.42 161	93.13 54	70.71 74		85.48 276	57.43 380	81.80 125	91.98 103	63.28 148	92.27 214	64.60 256	92.99 70	87.27 306

旧先验1					91.96 74	65.79 187		86.37 264			93.08 83	69.31 86			92.74 74	88.74 274

无先验							87.48 169	88.98 203	60.00 357				94.12 126	67.28 233		88.97 262

原ACMM2							86.86 191

原ACMM1				84.35 115	93.01 60	68.79 110		92.44 77	63.96 322	81.09 135	91.57 117	66.06 126	95.45 68	67.19 235	94.82 46	88.81 269

test222					91.50 80	68.26 130	84.16 265	83.20 310	54.63 391	79.74 148	91.63 114	58.97 210			91.42 93	86.77 319

testdata2													91.01 264	62.37 274

segment_acmp												73.08 39

testdata				79.97 256	90.90 91	64.21 226		84.71 283	59.27 364	85.40 66	92.91 85	62.02 172	89.08 296	68.95 218	91.37 95	86.63 323

testdata1							84.14 266		75.71 95

test12				86.80 52	92.63 67	70.70 75		91.79 108		82.71 115		71.67 56	96.16 47		94.50 51	93.54 89

plane_prior7					90.08 109	68.51 124

plane_prior6					89.84 118	68.70 118						60.42 203

plane_prior5								92.44 77					95.38 75	78.71 119	86.32 172	91.33 169

plane_prior4											91.00 139

plane_prior3						68.60 121			78.44 33	78.92 160

plane_prior2							91.25 52		79.12 25

plane_prior1					89.90 117

plane_prior						68.71 116	90.38 70		77.62 43						86.16 176

n2								0.00 445

nn								0.00 445

door-mid								69.98 401

lessismore_v0				78.97 275	81.01 355	57.15 326		65.99 412		61.16 390	82.82 338	39.12 379	91.34 253	59.67 298	46.92 417	88.43 282

LGP-MVS_train				84.50 108	89.23 143	68.76 112		91.94 100	75.37 104	76.64 213	91.51 118	54.29 247	94.91 95	78.44 121	83.78 206	89.83 235

test11								92.23 87

door								69.44 404

HQP5-MVS						66.98 165

HQP-NCC					89.33 136		89.17 106		76.41 80	77.23 198

ACMP_Plane					89.33 136		89.17 106		76.41 80	77.23 198

BP-MVS														77.47 131

HQP4-MVS										77.24 197			95.11 87			91.03 179

HQP3-MVS								92.19 91							85.99 180

HQP2-MVS												60.17 206

NP-MVS					89.62 122	68.32 128					90.24 151

MDTV_nov1_ep13_2view						37.79 426	75.16 376		55.10 389	66.53 359		49.34 307		53.98 343		87.94 290

ACMMP++_ref															81.95 238

ACMMP++															81.25 243

Test By Simon												64.33 140

ITE_SJBPF				78.22 290	81.77 341	60.57 285		83.30 305	69.25 243	67.54 345	87.20 232	36.33 391	87.28 321	54.34 341	74.62 336	86.80 318

DeepMVS_CX				27.40 416	40.17 439	26.90 433		24.59 440	17.44 432	23.95 430	48.61 427	9.77 431	26.48 435	18.06 428	24.47 429	28.83 429

High-resolution multi-view benchmark