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.

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 55	93.10 1	95.72 8	82.99 1	97.44 7	89.07 18	96.63 4	94.88 15

test_241102_ONE					95.30 2	70.98 66		94.06 10	77.17 58	93.10 1	95.39 14	82.99 1	97.27 12

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 34	92.78 4	95.74 6	82.45 3	97.49 4	89.42 13	96.68 2	94.95 11

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 51	82.45 3	96.87 20	83.77 69	96.48 8	94.88 15

PC_three_1452									68.21 262	92.02 12	94.00 53	82.09 5	95.98 56	84.58 58	96.68 2	94.95 11

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 92	92.29 7	95.66 10	81.67 6	97.38 11	87.44 38	96.34 15	93.95 62
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0728_THIRD									78.38 34	92.12 9	95.78 4	81.46 7	97.40 9	89.42 13	96.57 7	94.67 28

test_241102_TWO								94.06 10	77.24 55	92.78 4	95.72 8	81.26 8	97.44 7	89.07 18	96.58 6	94.26 48

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 52	92.12 9	95.78 4	80.98 9	97.40 9	89.08 16	96.41 12	93.33 95
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					95.27 5	71.25 59	93.60 6	94.11 6	77.33 52	92.81 3	95.79 3	80.98 9

test_one_0601					95.07 7	71.46 57		94.14 5	78.27 37	92.05 11	95.74 6	80.83 11

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 48	89.79 19	94.12 46	78.98 12	96.58 35	85.66 45	95.72 24	94.58 33

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 44	78.35 13	96.77 24	89.59 12	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 96	91.06 16	96.03 1	76.84 14	97.03 17	89.09 15	95.65 27	94.47 38
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
dcpmvs_2		85.63 60	86.15 50	84.06 135	91.71 78	64.94 206	86.47 201	91.87 103	73.63 147	86.60 55	93.02 80	76.57 15	91.87 227	83.36 71	92.15 80	95.35 3

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 32	94.06 49	76.43 16	96.84 21	88.48 29	95.99 18	94.34 44

MCST-MVS		87.37 29	87.25 30	87.73 28	94.53 17	72.46 38	89.82 79	93.82 16	73.07 164	84.86 73	92.89 82	76.22 17	96.33 41	84.89 53	95.13 36	94.40 41

CSCG		86.41 45	86.19 48	87.07 45	92.91 61	72.48 37	90.81 58	93.56 24	73.95 139	83.16 105	91.07 130	75.94 18	95.19 82	79.94 108	94.38 56	93.55 87

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 37	94.27 38	75.89 19	96.81 23	87.45 37	96.44 9	93.05 110

TSAR-MVS + MP.		88.02 17	88.11 16	87.72 30	93.68 43	72.13 46	91.41 50	92.35 82	74.62 124	88.90 23	93.85 59	75.75 20	96.00 54	87.80 33	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
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 94	89.16 20	95.10 16	75.65 21	96.19 46	87.07 39	96.01 17	94.79 22

9.14			88.26 15		92.84 63		91.52 48	94.75 1	73.93 141	88.57 26	94.67 22	75.57 22	95.79 58	86.77 40	95.76 23

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 38	90.32 17	94.00 53	74.83 23	93.78 141	87.63 35	94.27 59	93.65 80
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
DELS-MVS		85.41 65	85.30 68	85.77 72	88.49 170	67.93 138	85.52 231	93.44 27	78.70 30	83.63 101	89.03 177	74.57 24	95.71 61	80.26 105	94.04 61	93.66 76
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
patch_mono-2		83.65 89	84.54 76	80.99 231	90.06 113	65.83 183	84.21 260	88.74 210	71.60 186	85.01 67	92.44 92	74.51 25	83.50 352	82.15 87	92.15 80	93.64 82

train_agg		86.43 43	86.20 47	87.13 44	93.26 52	72.96 25	88.75 123	91.89 101	68.69 254	85.00 68	93.10 75	74.43 26	95.41 73	84.97 50	95.71 25	93.02 112

test_8					93.13 54	72.57 35	88.68 128	91.84 105	68.69 254	84.87 72	93.10 75	74.43 26	95.16 83

TEST9					93.26 52	72.96 25	88.75 123	91.89 101	68.44 259	85.00 68	93.10 75	74.36 28	95.41 73

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 120	92.29 7	95.97 2	74.28 29	97.24 13	88.58 26	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
test_prior2							88.85 119		75.41 101	84.91 70	93.54 64	74.28 29		83.31 72	95.86 20

TSAR-MVS + GP.		85.71 59	85.33 66	86.84 50	91.34 81	72.50 36	89.07 112	87.28 240	76.41 79	85.80 59	90.22 149	74.15 31	95.37 78	81.82 89	91.88 83	92.65 124

ZD-MVS					94.38 25	72.22 44		92.67 67	70.98 199	87.75 39	94.07 48	74.01 32	96.70 27	84.66 57	94.84 44

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 31	94.80 20	73.76 33	97.11 15	87.51 36	95.82 21	94.90 14
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		87.44 25	87.52 25	87.19 42	94.24 32	72.39 39	91.86 40	92.83 60	73.01 166	88.58 25	94.52 24	73.36 34	96.49 38	84.26 62	95.01 37	92.70 120
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
casdiffmvs_mvg		85.99 50	86.09 52	85.70 74	87.65 211	67.22 160	88.69 127	93.04 41	79.64 19	85.33 64	92.54 91	73.30 35	94.50 112	83.49 70	91.14 96	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
sasdasda		85.91 54	85.87 56	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 74	88.01 34	91.23 122	73.28 36	93.91 135	81.50 91	88.80 130	94.77 24

canonicalmvs		85.91 54	85.87 56	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 74	88.01 34	91.23 122	73.28 36	93.91 135	81.50 91	88.80 130	94.77 24

fmvsm_s_conf0.5_n_3		86.36 46	87.46 27	83.09 173	87.08 229	65.21 198	89.09 111	90.21 156	79.67 17	89.98 18	95.02 18	73.17 38	91.71 233	91.30 2	91.60 88	92.34 135

segment_acmp												73.08 39

DPM-MVS		84.93 73	84.29 80	86.84 50	90.20 106	73.04 23	87.12 178	93.04 41	69.80 226	82.85 109	91.22 124	73.06 40	96.02 52	76.72 138	94.63 48	91.46 165

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 60	93.47 68	73.02 41	97.00 18	84.90 51	94.94 40	94.10 53

fmvsm_l_conf0.5_n_3		86.02 48	86.32 44	85.14 85	87.20 225	68.54 123	89.57 90	90.44 145	75.31 104	87.49 43	94.39 34	72.86 42	92.72 193	89.04 20	90.56 103	94.16 50

test_fmvsmconf_n		85.92 53	86.04 53	85.57 76	85.03 270	69.51 93	89.62 89	90.58 140	73.42 155	87.75 39	94.02 51	72.85 43	93.24 166	90.37 5	90.75 100	93.96 60

MGCFI-Net		85.06 72	85.51 62	83.70 151	89.42 131	63.01 248	89.43 94	92.62 73	76.43 78	87.53 42	91.34 120	72.82 44	93.42 161	81.28 94	88.74 133	94.66 31

nrg030		83.88 83	83.53 88	84.96 93	86.77 235	69.28 102	90.46 67	92.67 67	74.79 119	82.95 106	91.33 121	72.70 45	93.09 180	80.79 101	79.28 267	92.50 129

CDPH-MVS		85.76 58	85.29 69	87.17 43	93.49 47	71.08 64	88.58 131	92.42 80	68.32 261	84.61 79	93.48 66	72.32 46	96.15 48	79.00 111	95.43 30	94.28 47

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 44	83.84 95	94.40 33	72.24 47	96.28 43	85.65 46	95.30 35	93.62 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffmvs		85.11 70	85.14 70	85.01 91	87.20 225	65.77 187	87.75 160	92.83 60	77.84 39	84.36 85	92.38 93	72.15 48	93.93 134	81.27 95	90.48 104	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
DeepC-MVS	79.81 2	87.08 35	86.88 39	87.69 33	91.16 84	72.32 43	90.31 71	93.94 14	77.12 60	82.82 110	94.23 41	72.13 49	97.09 16	84.83 54	95.37 31	93.65 80
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_l_conf0.5_n		84.47 77	84.54 76	84.27 121	85.42 259	68.81 109	88.49 133	87.26 242	68.08 263	88.03 33	93.49 65	72.04 50	91.77 229	88.90 22	89.14 126	92.24 142

MVSMamba_PlusPlus		85.99 50	85.96 54	86.05 66	91.09 85	67.64 145	89.63 88	92.65 70	72.89 169	84.64 78	91.71 106	71.85 51	96.03 50	84.77 56	94.45 54	94.49 37

baseline		84.93 73	84.98 71	84.80 101	87.30 223	65.39 195	87.30 174	92.88 57	77.62 42	84.04 91	92.26 95	71.81 52	93.96 128	81.31 93	90.30 107	95.03 10

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 68	85.24 65	94.32 36	71.76 53	96.93 19	85.53 48	95.79 22	94.32 45

test_fmvsmconf0.1_n		85.61 61	85.65 60	85.50 77	82.99 317	69.39 100	89.65 86	90.29 154	73.31 158	87.77 38	94.15 45	71.72 54	93.23 167	90.31 6	90.67 102	93.89 66

MM		89.16 6	89.23 7	88.97 4	90.79 95	73.65 10	92.66 23	91.17 125	86.57 1	87.39 46	94.97 19	71.70 55	97.68 1	92.19 1	95.63 28	95.57 1

test12				86.80 52	92.63 67	70.70 75		91.79 107		82.71 112		71.67 56	96.16 47		94.50 51	93.54 88

UniMVSNet_NR-MVSNet		81.88 121	81.54 121	82.92 183	88.46 172	63.46 238	87.13 177	92.37 81	80.19 12	78.38 168	89.14 173	71.66 57	93.05 183	70.05 201	76.46 299	92.25 140

CS-MVS		86.69 39	86.95 36	85.90 71	90.76 96	67.57 148	92.83 17	93.30 32	79.67 17	84.57 81	92.27 94	71.47 58	95.02 93	84.24 64	93.46 67	95.13 8

DeepC-MVS_fast	79.65 3	86.91 36	86.62 41	87.76 27	93.52 46	72.37 41	91.26 51	93.04 41	76.62 76	84.22 86	93.36 71	71.44 59	96.76 25	80.82 99	95.33 33	94.16 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsm_n_1920		85.29 68	85.34 65	85.13 88	86.12 247	69.93 86	88.65 129	90.78 136	69.97 222	88.27 28	93.98 56	71.39 60	91.54 240	88.49 28	90.45 105	93.91 63

MVS_111021_HR		85.14 69	84.75 74	86.32 58	91.65 79	72.70 30	85.98 214	90.33 151	76.11 88	82.08 116	91.61 112	71.36 61	94.17 124	81.02 96	92.58 75	92.08 148

balanced_conf03		86.78 37	86.99 34	86.15 63	91.24 83	67.61 146	90.51 62	92.90 56	77.26 54	87.44 45	91.63 110	71.27 62	96.06 49	85.62 47	95.01 37	94.78 23

reproduce-ours		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 113	88.96 21	95.54 12	71.20 63	96.54 36	86.28 42	93.49 65	93.06 108

our_new_method		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 113	88.96 21	95.54 12	71.20 63	96.54 36	86.28 42	93.49 65	93.06 108

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 86	88.14 30	95.09 17	71.06 65	96.67 29	87.67 34	96.37 14	94.09 54

fmvsm_l_conf0.5_n_a		84.13 80	84.16 81	84.06 135	85.38 260	68.40 126	88.34 140	86.85 252	67.48 270	87.48 44	93.40 69	70.89 66	91.61 234	88.38 30	89.22 124	92.16 146

MP-MVS-pluss		87.67 21	87.72 20	87.54 36	93.64 44	72.04 48	89.80 81	93.50 25	75.17 110	86.34 56	95.29 15	70.86 67	96.00 54	88.78 24	96.04 16	94.58 33
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
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 70	84.91 70	94.44 31	70.78 68	96.61 32	84.53 59	94.89 42	93.66 76

EI-MVSNet-Vis-set		84.19 79	83.81 84	85.31 81	88.18 182	67.85 139	87.66 162	89.73 171	80.05 14	82.95 106	89.59 162	70.74 69	94.82 101	80.66 102	84.72 187	93.28 97

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 66	84.68 74	93.99 55	70.67 70	96.82 22	84.18 66	95.01 37	93.90 65

SPE-MVS-test		86.29 47	86.48 42	85.71 73	91.02 88	67.21 161	92.36 29	93.78 18	78.97 29	83.51 102	91.20 125	70.65 71	95.15 84	81.96 88	94.89 42	94.77 24

CANet		86.45 42	86.10 51	87.51 37	90.09 108	70.94 70	89.70 85	92.59 74	81.78 4	81.32 126	91.43 118	70.34 72	97.23 14	84.26 62	93.36 68	94.37 42

alignmvs		85.48 62	85.32 67	85.96 70	89.51 127	69.47 95	89.74 83	92.47 76	76.17 87	87.73 41	91.46 117	70.32 73	93.78 141	81.51 90	88.95 127	94.63 32

reproduce_model		87.28 30	87.39 28	86.95 48	93.10 56	71.24 63	91.60 42	93.19 35	74.69 121	88.80 24	95.61 11	70.29 74	96.44 39	86.20 44	93.08 69	93.16 103

EI-MVSNet-UG-set		83.81 84	83.38 91	85.09 89	87.87 199	67.53 149	87.44 170	89.66 172	79.74 16	82.23 115	89.41 171	70.24 75	94.74 104	79.95 107	83.92 201	92.99 115

MVS_Test		83.15 102	83.06 96	83.41 160	86.86 231	63.21 244	86.11 212	92.00 95	74.31 131	82.87 108	89.44 170	70.03 76	93.21 169	77.39 129	88.50 138	93.81 71

FC-MVSNet-test		81.52 130	82.02 115	80.03 251	88.42 175	55.97 341	87.95 153	93.42 29	77.10 61	77.38 189	90.98 137	69.96 77	91.79 228	68.46 220	84.50 190	92.33 136

FIs		82.07 118	82.42 105	81.04 230	88.80 159	58.34 302	88.26 143	93.49 26	76.93 65	78.47 167	91.04 131	69.92 78	92.34 210	69.87 205	84.97 184	92.44 133

UniMVSNet (Re)		81.60 129	81.11 126	83.09 173	88.38 176	64.41 219	87.60 163	93.02 45	78.42 33	78.56 164	88.16 202	69.78 79	93.26 165	69.58 208	76.49 298	91.60 156

HPM-MVS		87.11 33	86.98 35	87.50 38	93.88 39	72.16 45	92.19 33	93.33 31	76.07 89	83.81 96	93.95 58	69.77 80	96.01 53	85.15 49	94.66 47	94.32 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
Effi-MVS+		83.62 92	83.08 95	85.24 83	88.38 176	67.45 150	88.89 117	89.15 192	75.50 99	82.27 114	88.28 198	69.61 81	94.45 114	77.81 124	87.84 145	93.84 69

PHI-MVS		86.43 43	86.17 49	87.24 41	90.88 92	70.96 68	92.27 32	94.07 9	72.45 171	85.22 66	91.90 101	69.47 82	96.42 40	83.28 73	95.94 19	94.35 43

UA-Net		85.08 71	84.96 72	85.45 78	92.07 73	68.07 135	89.78 82	90.86 135	82.48 2	84.60 80	93.20 74	69.35 83	95.22 81	71.39 188	90.88 99	93.07 107

ETV-MVS		84.90 75	84.67 75	85.59 75	89.39 134	68.66 120	88.74 125	92.64 72	79.97 15	84.10 89	85.71 267	69.32 84	95.38 75	80.82 99	91.37 93	92.72 119

旧先验1					91.96 74	65.79 186		86.37 260			93.08 79	69.31 85			92.74 73	88.74 270

fmvsm_s_conf0.5_n_4		85.39 66	85.75 59	84.30 117	86.70 237	65.83 183	88.77 121	89.78 167	75.46 100	88.35 27	93.73 62	69.19 86	93.06 182	91.30 2	88.44 139	94.02 58

fmvsm_s_conf0.5_n_a		83.63 91	83.41 90	84.28 119	86.14 246	68.12 133	89.43 94	82.87 313	70.27 215	87.27 48	93.80 61	69.09 87	91.58 236	88.21 31	83.65 209	93.14 105

region2R		87.42 27	87.20 32	88.09 14	94.63 14	73.55 13	93.03 14	93.12 40	76.73 73	84.45 82	94.52 24	69.09 87	96.70 27	84.37 61	94.83 45	94.03 57

EIA-MVS		83.31 101	82.80 102	84.82 99	89.59 123	65.59 190	88.21 144	92.68 66	74.66 123	78.96 154	86.42 254	69.06 89	95.26 80	75.54 150	90.09 111	93.62 83

EPP-MVSNet		83.40 98	83.02 97	84.57 105	90.13 107	64.47 217	92.32 30	90.73 137	74.45 128	79.35 150	91.10 128	69.05 90	95.12 85	72.78 177	87.22 155	94.13 52

EC-MVSNet		86.01 49	86.38 43	84.91 97	89.31 139	66.27 174	92.32 30	93.63 21	79.37 21	84.17 88	91.88 102	69.04 91	95.43 70	83.93 68	93.77 63	93.01 113

fmvsm_s_conf0.5_n		83.80 85	83.71 86	84.07 133	86.69 238	67.31 155	89.46 93	83.07 308	71.09 196	86.96 52	93.70 63	69.02 92	91.47 245	88.79 23	84.62 189	93.44 91

ACMMPR		87.44 25	87.23 31	88.08 15	94.64 13	73.59 12	93.04 12	93.20 34	76.78 70	84.66 77	94.52 24	68.81 93	96.65 30	84.53 59	94.90 41	94.00 59

test_fmvsmvis_n_1920		84.02 82	83.87 83	84.49 109	84.12 286	69.37 101	88.15 148	87.96 224	70.01 220	83.95 93	93.23 73	68.80 94	91.51 243	88.61 25	89.96 114	92.57 125

mvs_anonymous		79.42 178	79.11 167	80.34 245	84.45 281	57.97 308	82.59 287	87.62 233	67.40 271	76.17 224	88.56 191	68.47 95	89.59 283	70.65 196	86.05 174	93.47 90

fmvsm_s_conf0.1_n		83.56 93	83.38 91	84.10 127	84.86 272	67.28 156	89.40 98	83.01 309	70.67 204	87.08 49	93.96 57	68.38 96	91.45 246	88.56 27	84.50 190	93.56 86

fmvsm_s_conf0.1_n_a		83.32 100	82.99 98	84.28 119	83.79 294	68.07 135	89.34 101	82.85 314	69.80 226	87.36 47	94.06 49	68.34 97	91.56 238	87.95 32	83.46 215	93.21 101

MVS_0304		87.69 20	87.55 24	88.12 13	89.45 130	71.76 51	91.47 49	89.54 176	82.14 3	86.65 54	94.28 37	68.28 98	97.46 6	90.81 4	95.31 34	95.15 7

MTAPA		87.23 31	87.00 33	87.90 22	94.18 35	74.25 5	86.58 198	92.02 93	79.45 20	85.88 58	94.80 20	68.07 99	96.21 45	86.69 41	95.34 32	93.23 98

mamv4		76.81 239	78.23 187	72.54 352	86.12 247	65.75 188	78.76 341	82.07 322	64.12 312	72.97 284	91.02 134	67.97 100	68.08 417	83.04 76	78.02 279	83.80 363

CP-MVS		87.11 33	86.92 37	87.68 34	94.20 34	73.86 7	93.98 3	92.82 63	76.62 76	83.68 98	94.46 28	67.93 101	95.95 57	84.20 65	94.39 55	93.23 98

PAPM_NR		83.02 106	82.41 106	84.82 99	92.47 70	66.37 172	87.93 155	91.80 106	73.82 143	77.32 191	90.66 140	67.90 102	94.90 97	70.37 198	89.48 121	93.19 102

PGM-MVS		86.68 40	86.27 46	87.90 22	94.22 33	73.38 18	90.22 73	93.04 41	75.53 98	83.86 94	94.42 32	67.87 103	96.64 31	82.70 84	94.57 50	93.66 76

PAPR		81.66 128	80.89 131	83.99 143	90.27 104	64.00 225	86.76 194	91.77 109	68.84 252	77.13 201	89.50 163	67.63 104	94.88 99	67.55 226	88.52 137	93.09 106

Fast-Effi-MVS+		80.81 143	79.92 146	83.47 156	88.85 154	64.51 214	85.53 229	89.39 181	70.79 201	78.49 166	85.06 286	67.54 105	93.58 149	67.03 234	86.58 164	92.32 137

XVS		87.18 32	86.91 38	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 99	94.17 43	67.45 106	96.60 33	83.06 74	94.50 51	94.07 55

X-MVStestdata		80.37 159	77.83 195	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 99	12.47 429	67.45 106	96.60 33	83.06 74	94.50 51	94.07 55

SR-MVS		86.73 38	86.67 40	86.91 49	94.11 37	72.11 47	92.37 28	92.56 75	74.50 125	86.84 53	94.65 23	67.31 108	95.77 59	84.80 55	92.85 72	92.84 118

NR-MVSNet		80.23 161	79.38 158	82.78 192	87.80 203	63.34 241	86.31 206	91.09 129	79.01 27	72.17 296	89.07 175	67.20 109	92.81 192	66.08 240	75.65 312	92.20 143

MSLP-MVS++		85.43 64	85.76 58	84.45 110	91.93 75	70.24 79	90.71 59	92.86 58	77.46 50	84.22 86	92.81 86	67.16 110	92.94 187	80.36 103	94.35 57	90.16 210

MG-MVS		83.41 97	83.45 89	83.28 163	92.74 65	62.28 260	88.17 146	89.50 178	75.22 105	81.49 125	92.74 90	66.75 111	95.11 87	72.85 176	91.58 90	92.45 132

test_fmvsmconf0.01_n		84.73 76	84.52 78	85.34 80	80.25 358	69.03 103	89.47 92	89.65 173	73.24 162	86.98 51	94.27 38	66.62 112	93.23 167	90.26 7	89.95 115	93.78 73

EI-MVSNet		80.52 155	79.98 145	82.12 202	84.28 282	63.19 246	86.41 202	88.95 202	74.18 136	78.69 159	87.54 219	66.62 112	92.43 204	72.57 180	80.57 251	90.74 187

IterMVS-LS		80.06 164	79.38 158	82.11 203	85.89 250	63.20 245	86.79 191	89.34 182	74.19 135	75.45 237	86.72 239	66.62 112	92.39 206	72.58 179	76.86 293	90.75 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		78.59 200	77.76 200	81.08 229	82.66 324	61.56 269	83.65 269	89.15 192	68.87 251	75.55 233	83.79 313	66.49 115	92.03 219	73.25 172	76.39 301	89.64 237

mPP-MVS		86.67 41	86.32 44	87.72 30	94.41 22	73.55 13	92.74 20	92.22 88	76.87 67	82.81 111	94.25 40	66.44 116	96.24 44	82.88 79	94.28 58	93.38 92

c3_l		78.75 194	77.91 192	81.26 223	82.89 319	61.56 269	84.09 263	89.13 194	69.97 222	75.56 232	84.29 301	66.36 117	92.09 218	73.47 169	75.48 316	90.12 213

GeoE		81.71 125	81.01 129	83.80 150	89.51 127	64.45 218	88.97 114	88.73 211	71.27 192	78.63 162	89.76 156	66.32 118	93.20 172	69.89 204	86.02 175	93.74 74

WR-MVS_H		78.51 201	78.49 177	78.56 279	88.02 192	56.38 335	88.43 134	92.67 67	77.14 59	73.89 272	87.55 218	66.25 119	89.24 290	58.92 302	73.55 342	90.06 220

PCF-MVS	73.52 7	80.38 157	78.84 172	85.01 91	87.71 208	68.99 106	83.65 269	91.46 119	63.00 325	77.77 183	90.28 145	66.10 120	95.09 91	61.40 281	88.22 142	90.94 180
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EPNet		83.72 88	82.92 100	86.14 65	84.22 284	69.48 94	91.05 56	85.27 273	81.30 6	76.83 203	91.65 108	66.09 121	95.56 63	76.00 144	93.85 62	93.38 92
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM1				84.35 114	93.01 60	68.79 110		92.44 77	63.96 318	81.09 131	91.57 113	66.06 122	95.45 68	67.19 231	94.82 46	88.81 265

PVSNet_BlendedMVS		80.60 151	80.02 144	82.36 201	88.85 154	65.40 193	86.16 211	92.00 95	69.34 236	78.11 175	86.09 262	66.02 123	94.27 118	71.52 185	82.06 232	87.39 298

PVSNet_Blended		80.98 138	80.34 139	82.90 184	88.85 154	65.40 193	84.43 255	92.00 95	67.62 267	78.11 175	85.05 287	66.02 123	94.27 118	71.52 185	89.50 120	89.01 255

diffmvs		82.10 116	81.88 118	82.76 194	83.00 315	63.78 230	83.68 268	89.76 169	72.94 167	82.02 117	89.85 154	65.96 125	90.79 264	82.38 86	87.30 154	93.71 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
APD-MVS_3200maxsize		85.97 52	85.88 55	86.22 60	92.69 66	69.53 92	91.93 37	92.99 49	73.54 151	85.94 57	94.51 27	65.80 126	95.61 62	83.04 76	92.51 76	93.53 89

miper_enhance_ethall		77.87 219	76.86 219	80.92 234	81.65 338	61.38 271	82.68 286	88.98 199	65.52 295	75.47 234	82.30 341	65.76 127	92.00 221	72.95 175	76.39 301	89.39 243

PVSNet_Blended_VisFu		82.62 110	81.83 119	84.96 93	90.80 94	69.76 90	88.74 125	91.70 110	69.39 234	78.96 154	88.46 193	65.47 128	94.87 100	74.42 159	88.57 135	90.24 208

API-MVS		81.99 120	81.23 124	84.26 123	90.94 90	70.18 85	91.10 55	89.32 183	71.51 188	78.66 161	88.28 198	65.26 129	95.10 90	64.74 251	91.23 95	87.51 296

TranMVSNet+NR-MVSNet		80.84 141	80.31 140	82.42 199	87.85 200	62.33 258	87.74 161	91.33 120	80.55 9	77.99 179	89.86 153	65.23 130	92.62 194	67.05 233	75.24 326	92.30 138

IS-MVSNet		83.15 102	82.81 101	84.18 125	89.94 116	63.30 242	91.59 43	88.46 216	79.04 26	79.49 148	92.16 96	65.10 131	94.28 117	67.71 224	91.86 86	94.95 11

DU-MVS		81.12 137	80.52 136	82.90 184	87.80 203	63.46 238	87.02 182	91.87 103	79.01 27	78.38 168	89.07 175	65.02 132	93.05 183	70.05 201	76.46 299	92.20 143

Baseline_NR-MVSNet		78.15 210	78.33 183	77.61 297	85.79 251	56.21 339	86.78 192	85.76 269	73.60 149	77.93 180	87.57 216	65.02 132	88.99 294	67.14 232	75.33 323	87.63 292

SR-MVS-dyc-post		85.77 57	85.61 61	86.23 59	93.06 58	70.63 76	91.88 38	92.27 84	73.53 152	85.69 61	94.45 29	65.00 134	95.56 63	82.75 80	91.87 84	92.50 129

VNet		82.21 115	82.41 106	81.62 212	90.82 93	60.93 275	84.47 251	89.78 167	76.36 84	84.07 90	91.88 102	64.71 135	90.26 270	70.68 195	88.89 128	93.66 76

Test By Simon												64.33 136

ACMMP		85.89 56	85.39 64	87.38 39	93.59 45	72.63 33	92.74 20	93.18 39	76.78 70	80.73 135	93.82 60	64.33 136	96.29 42	82.67 85	90.69 101	93.23 98
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
DP-MVS Recon		83.11 105	82.09 113	86.15 63	94.44 19	70.92 71	88.79 120	92.20 89	70.53 209	79.17 152	91.03 133	64.12 138	96.03 50	68.39 221	90.14 110	91.50 161

CLD-MVS		82.31 114	81.65 120	84.29 118	88.47 171	67.73 143	85.81 222	92.35 82	75.78 93	78.33 170	86.58 249	64.01 139	94.35 115	76.05 143	87.48 151	90.79 183
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
RE-MVS-def			85.48 63		93.06 58	70.63 76	91.88 38	92.27 84	73.53 152	85.69 61	94.45 29	63.87 140		82.75 80	91.87 84	92.50 129

MVS		78.19 209	76.99 217	81.78 209	85.66 253	66.99 163	84.66 245	90.47 144	55.08 386	72.02 298	85.27 279	63.83 141	94.11 126	66.10 239	89.80 117	84.24 356

WR-MVS		79.49 174	79.22 165	80.27 247	88.79 160	58.35 301	85.06 237	88.61 214	78.56 31	77.65 184	88.34 196	63.81 142	90.66 267	64.98 249	77.22 288	91.80 154

VPA-MVSNet		80.60 151	80.55 135	80.76 237	88.07 190	60.80 278	86.86 188	91.58 113	75.67 97	80.24 139	89.45 169	63.34 143	90.25 271	70.51 197	79.22 268	91.23 169

新几何1				83.42 158	93.13 54	70.71 74		85.48 272	57.43 376	81.80 121	91.98 99	63.28 144	92.27 212	64.60 252	92.99 70	87.27 302

HY-MVS	69.67 12	77.95 216	77.15 213	80.36 244	87.57 216	60.21 288	83.37 276	87.78 231	66.11 286	75.37 241	87.06 234	63.27 145	90.48 269	61.38 282	82.43 228	90.40 202

XXY-MVS		75.41 264	75.56 242	74.96 326	83.59 299	57.82 312	80.59 314	83.87 293	66.54 283	74.93 258	88.31 197	63.24 146	80.09 371	62.16 273	76.85 294	86.97 311

ab-mvs		79.51 173	78.97 170	81.14 227	88.46 172	60.91 276	83.84 265	89.24 188	70.36 211	79.03 153	88.87 181	63.23 147	90.21 272	65.12 247	82.57 227	92.28 139

xiu_mvs_v2_base		81.69 126	81.05 127	83.60 153	89.15 146	68.03 137	84.46 253	90.02 161	70.67 204	81.30 129	86.53 252	63.17 148	94.19 123	75.60 149	88.54 136	88.57 275

pcd_1.5k_mvsjas		5.26 403	7.02 406	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	63.15 149	0.00 436	0.00 435	0.00 434	0.00 432

PS-MVSNAJss		82.07 118	81.31 122	84.34 115	86.51 241	67.27 157	89.27 102	91.51 115	71.75 181	79.37 149	90.22 149	63.15 149	94.27 118	77.69 125	82.36 229	91.49 162

PS-MVSNAJ		81.69 126	81.02 128	83.70 151	89.51 127	68.21 132	84.28 259	90.09 160	70.79 201	81.26 130	85.62 272	63.15 149	94.29 116	75.62 148	88.87 129	88.59 274

WTY-MVS		75.65 259	75.68 239	75.57 317	86.40 242	56.82 326	77.92 355	82.40 318	65.10 299	76.18 222	87.72 211	63.13 152	80.90 368	60.31 289	81.96 233	89.00 257

TransMVSNet (Re)		75.39 266	74.56 258	77.86 291	85.50 258	57.10 323	86.78 192	86.09 266	72.17 177	71.53 303	87.34 222	63.01 153	89.31 288	56.84 325	61.83 389	87.17 304

v8		79.97 167	79.02 169	82.80 189	84.09 287	64.50 216	87.96 152	90.29 154	74.13 138	75.24 249	86.81 236	62.88 154	93.89 138	74.39 160	75.40 321	90.00 222

HPM-MVS_fast		85.35 67	84.95 73	86.57 56	93.69 42	70.58 78	92.15 35	91.62 111	73.89 142	82.67 113	94.09 47	62.60 155	95.54 65	80.93 97	92.93 71	93.57 85

PAPM		77.68 225	76.40 232	81.51 215	87.29 224	61.85 265	83.78 266	89.59 175	64.74 304	71.23 305	88.70 184	62.59 156	93.66 148	52.66 346	87.03 158	89.01 255

1112_ss		77.40 230	76.43 231	80.32 246	89.11 151	60.41 285	83.65 269	87.72 232	62.13 338	73.05 283	86.72 239	62.58 157	89.97 276	62.11 275	80.80 247	90.59 194

LCM-MVSNet-Re		77.05 234	76.94 218	77.36 301	87.20 225	51.60 380	80.06 322	80.46 341	75.20 107	67.69 340	86.72 239	62.48 158	88.98 295	63.44 259	89.25 123	91.51 160

v148		78.72 196	77.80 197	81.47 216	82.73 322	61.96 264	86.30 207	88.08 221	73.26 160	76.18 222	85.47 276	62.46 159	92.36 208	71.92 184	73.82 340	90.09 216

baseline1		76.98 236	76.75 225	77.66 295	88.13 186	55.66 346	85.12 235	81.89 323	73.04 165	76.79 204	88.90 179	62.43 160	87.78 313	63.30 261	71.18 360	89.55 240

MAR-MVS		81.84 122	80.70 132	85.27 82	91.32 82	71.53 56	89.82 79	90.92 131	69.77 228	78.50 165	86.21 258	62.36 161	94.52 111	65.36 245	92.05 82	89.77 234
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
MVS_111021_LR		82.61 111	82.11 111	84.11 126	88.82 157	71.58 55	85.15 234	86.16 264	74.69 121	80.47 137	91.04 131	62.29 162	90.55 268	80.33 104	90.08 112	90.20 209

TAMVS		78.89 193	77.51 207	83.03 178	87.80 203	67.79 142	84.72 244	85.05 277	67.63 266	76.75 206	87.70 212	62.25 163	90.82 263	58.53 307	87.13 156	90.49 198

CP-MVSNet		78.22 206	78.34 182	77.84 292	87.83 202	54.54 358	87.94 154	91.17 125	77.65 41	73.48 278	88.49 192	62.24 164	88.43 305	62.19 272	74.07 335	90.55 195

OMC-MVS		82.69 109	81.97 117	84.85 98	88.75 162	67.42 151	87.98 151	90.87 134	74.92 115	79.72 145	91.65 108	62.19 165	93.96 128	75.26 154	86.42 167	93.16 103

cl____		77.72 222	76.76 223	80.58 240	82.49 328	60.48 283	83.09 281	87.87 227	69.22 240	74.38 268	85.22 282	62.10 166	91.53 241	71.09 190	75.41 320	89.73 236

DIV-MVS_self_test		77.72 222	76.76 223	80.58 240	82.48 329	60.48 283	83.09 281	87.86 228	69.22 240	74.38 268	85.24 280	62.10 166	91.53 241	71.09 190	75.40 321	89.74 235

testdata				79.97 252	90.90 91	64.21 222		84.71 279	59.27 360	85.40 63	92.91 81	62.02 168	89.08 293	68.95 214	91.37 93	86.63 319

fmvsm_s_conf0.5_n_2		84.04 81	84.11 82	83.81 149	86.17 245	65.00 204	86.96 183	87.28 240	74.35 129	88.25 29	94.23 41	61.82 169	92.60 196	89.85 8	88.09 144	93.84 69

eth_miper_zixun_eth		77.92 217	76.69 226	81.61 214	83.00 315	61.98 263	83.15 279	89.20 190	69.52 233	74.86 259	84.35 300	61.76 170	92.56 199	71.50 187	72.89 348	90.28 207

MVSFormer		82.85 108	82.05 114	85.24 83	87.35 217	70.21 80	90.50 64	90.38 147	68.55 256	81.32 126	89.47 165	61.68 171	93.46 158	78.98 112	90.26 108	92.05 149

lupinMVS		81.39 133	80.27 142	84.76 102	87.35 217	70.21 80	85.55 227	86.41 258	62.85 328	81.32 126	88.61 188	61.68 171	92.24 214	78.41 119	90.26 108	91.83 152

cdsmvs_eth3d_5k		19.96 397	26.61 399	0.00 417	0.00 440	0.00 442	0.00 428	89.26 187	0.00 435	0.00 436	88.61 188	61.62 173	0.00 436	0.00 435	0.00 434	0.00 432

h-mvs33		83.15 102	82.19 110	86.02 69	90.56 98	70.85 73	88.15 148	89.16 191	76.02 90	84.67 75	91.39 119	61.54 174	95.50 66	82.71 82	75.48 316	91.72 155

hse-mvs2		81.72 124	80.94 130	84.07 133	88.72 163	67.68 144	85.87 218	87.26 242	76.02 90	84.67 75	88.22 201	61.54 174	93.48 156	82.71 82	73.44 344	91.06 174

CDS-MVSNet		79.07 188	77.70 202	83.17 170	87.60 212	68.23 131	84.40 257	86.20 263	67.49 269	76.36 217	86.54 251	61.54 174	90.79 264	61.86 277	87.33 153	90.49 198
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v10		79.74 169	78.67 173	82.97 182	84.06 288	64.95 205	87.88 158	90.62 139	73.11 163	75.11 253	86.56 250	61.46 177	94.05 127	73.68 165	75.55 314	89.90 228

v1144		80.03 165	79.03 168	83.01 179	83.78 295	64.51 214	87.11 179	90.57 142	71.96 180	78.08 177	86.20 259	61.41 178	93.94 131	74.93 155	77.23 287	90.60 193

cl22		78.07 212	77.01 215	81.23 224	82.37 331	61.83 266	83.55 273	87.98 223	68.96 250	75.06 255	83.87 309	61.40 179	91.88 226	73.53 167	76.39 301	89.98 225

BH-w/o		78.21 207	77.33 211	80.84 235	88.81 158	65.13 201	84.87 241	87.85 229	69.75 229	74.52 265	84.74 293	61.34 180	93.11 179	58.24 311	85.84 178	84.27 355

Test_1112_low_res		76.40 249	75.44 244	79.27 266	89.28 141	58.09 304	81.69 296	87.07 246	59.53 358	72.48 291	86.67 244	61.30 181	89.33 287	60.81 287	80.15 256	90.41 201

Vis-MVSNet (Re-imp)		78.36 204	78.45 178	78.07 290	88.64 166	51.78 379	86.70 195	79.63 351	74.14 137	75.11 253	90.83 138	61.29 182	89.75 280	58.10 312	91.60 88	92.69 122

PEN-MVS		77.73 221	77.69 203	77.84 292	87.07 230	53.91 363	87.91 156	91.18 124	77.56 46	73.14 282	88.82 182	61.23 183	89.17 291	59.95 291	72.37 350	90.43 200

pm-mvs1		77.25 233	76.68 227	78.93 272	84.22 284	58.62 299	86.41 202	88.36 217	71.37 190	73.31 279	88.01 208	61.22 184	89.15 292	64.24 255	73.01 347	89.03 254

BH-untuned		79.47 175	78.60 175	82.05 204	89.19 145	65.91 181	86.07 213	88.52 215	72.18 176	75.42 238	87.69 213	61.15 185	93.54 153	60.38 288	86.83 161	86.70 317

v2v482		80.23 161	79.29 162	83.05 177	83.62 298	64.14 223	87.04 180	89.97 163	73.61 148	78.18 174	87.22 227	61.10 186	93.82 139	76.11 141	76.78 296	91.18 170

jason		81.39 133	80.29 141	84.70 103	86.63 240	69.90 88	85.95 215	86.77 253	63.24 321	81.07 132	89.47 165	61.08 187	92.15 216	78.33 120	90.07 113	92.05 149
jason: jason.
Vis-MVSNet		83.46 96	82.80 102	85.43 79	90.25 105	68.74 114	90.30 72	90.13 159	76.33 85	80.87 134	92.89 82	61.00 188	94.20 122	72.45 182	90.97 97	93.35 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAPA-MVS	73.13 9	79.15 185	77.94 191	82.79 191	89.59 123	62.99 252	88.16 147	91.51 115	65.77 291	77.14 200	91.09 129	60.91 189	93.21 169	50.26 362	87.05 157	92.17 145
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PS-CasMVS		78.01 215	78.09 188	77.77 294	87.71 208	54.39 360	88.02 150	91.22 122	77.50 49	73.26 280	88.64 187	60.73 190	88.41 306	61.88 276	73.88 339	90.53 196

OPM-MVS		83.50 95	82.95 99	85.14 85	88.79 160	70.95 69	89.13 109	91.52 114	77.55 47	80.96 133	91.75 105	60.71 191	94.50 112	79.67 110	86.51 166	89.97 226
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XVG-OURS-SEG-HR		80.81 143	79.76 150	83.96 145	85.60 256	68.78 111	83.54 274	90.50 143	70.66 207	76.71 207	91.66 107	60.69 192	91.26 251	76.94 134	81.58 237	91.83 152

fmvsm_s_conf0.1_n_2		83.80 85	83.79 85	83.83 148	85.62 255	64.94 206	87.03 181	86.62 256	74.32 130	87.97 36	94.33 35	60.67 193	92.60 196	89.72 9	87.79 146	93.96 60

v144192		79.47 175	78.37 181	82.78 192	83.35 303	63.96 226	86.96 183	90.36 150	69.99 221	77.50 186	85.67 270	60.66 194	93.77 143	74.27 161	76.58 297	90.62 191

V42		79.38 181	78.24 185	82.83 186	81.10 350	65.50 192	85.55 227	89.82 166	71.57 187	78.21 172	86.12 261	60.66 194	93.18 175	75.64 147	75.46 318	89.81 233

SDMVSNet		80.38 157	80.18 143	80.99 231	89.03 152	64.94 206	80.45 317	89.40 180	75.19 108	76.61 211	89.98 151	60.61 196	87.69 314	76.83 136	83.55 211	90.33 204

CPTT-MVS		83.73 87	83.33 93	84.92 96	93.28 49	70.86 72	92.09 36	90.38 147	68.75 253	79.57 147	92.83 84	60.60 197	93.04 185	80.92 98	91.56 91	90.86 182

DTE-MVSNet		76.99 235	76.80 221	77.54 300	86.24 243	53.06 372	87.52 165	90.66 138	77.08 62	72.50 290	88.67 186	60.48 198	89.52 284	57.33 319	70.74 362	90.05 221

HQP_MVS		83.64 90	83.14 94	85.14 85	90.08 109	68.71 116	91.25 52	92.44 77	79.12 24	78.92 156	91.00 135	60.42 199	95.38 75	78.71 115	86.32 168	91.33 166

plane_prior6					89.84 118	68.70 118						60.42 199

3Dnovator+	77.84 4	85.48 62	84.47 79	88.51 7	91.08 86	73.49 16	93.18 11	93.78 18	80.79 8	76.66 208	93.37 70	60.40 201	96.75 26	77.20 130	93.73 64	95.29 5

HQP2-MVS												60.17 202

HQP-MVS		82.61 111	82.02 115	84.37 112	89.33 136	66.98 164	89.17 104	92.19 90	76.41 79	77.23 194	90.23 148	60.17 202	95.11 87	77.47 127	85.99 176	91.03 176

VPNet		78.69 197	78.66 174	78.76 274	88.31 178	55.72 345	84.45 254	86.63 255	76.79 69	78.26 171	90.55 142	59.30 204	89.70 282	66.63 235	77.05 290	90.88 181

v1192		79.59 172	78.43 180	83.07 176	83.55 300	64.52 213	86.93 186	90.58 140	70.83 200	77.78 182	85.90 263	59.15 205	93.94 131	73.96 164	77.19 289	90.76 185

test222					91.50 80	68.26 130	84.16 261	83.20 306	54.63 387	79.74 144	91.63 110	58.97 206			91.42 92	86.77 315

CHOSEN 1792x2688		77.63 226	75.69 238	83.44 157	89.98 115	68.58 122	78.70 342	87.50 236	56.38 381	75.80 229	86.84 235	58.67 207	91.40 248	61.58 280	85.75 180	90.34 203

3Dnovator	76.31 5	83.38 99	82.31 109	86.59 55	87.94 196	72.94 28	90.64 60	92.14 92	77.21 57	75.47 234	92.83 84	58.56 208	94.72 105	73.24 173	92.71 74	92.13 147

v1921920		79.22 183	78.03 189	82.80 189	83.30 305	63.94 227	86.80 190	90.33 151	69.91 224	77.48 187	85.53 274	58.44 209	93.75 145	73.60 166	76.85 294	90.71 189

FA-MVS(test-final)		80.96 139	79.91 147	84.10 127	88.30 179	65.01 203	84.55 250	90.01 162	73.25 161	79.61 146	87.57 216	58.35 210	94.72 105	71.29 189	86.25 170	92.56 126

114514_t		80.68 149	79.51 155	84.20 124	94.09 38	67.27 157	89.64 87	91.11 128	58.75 366	74.08 270	90.72 139	58.10 211	95.04 92	69.70 206	89.42 122	90.30 206

v7n		78.97 191	77.58 206	83.14 171	83.45 302	65.51 191	88.32 141	91.21 123	73.69 146	72.41 292	86.32 257	57.93 212	93.81 140	69.18 211	75.65 312	90.11 214

CL-MVSNet_self_test		72.37 301	71.46 296	75.09 325	79.49 371	53.53 365	80.76 310	85.01 278	69.12 244	70.51 309	82.05 345	57.92 213	84.13 346	52.27 348	66.00 381	87.60 293

baseline2		75.70 258	73.83 270	81.30 222	83.26 306	61.79 267	82.57 288	80.65 337	66.81 273	66.88 349	83.42 322	57.86 214	92.19 215	63.47 258	79.57 261	89.91 227

QAPM		80.88 140	79.50 156	85.03 90	88.01 194	68.97 107	91.59 43	92.00 95	66.63 282	75.15 252	92.16 96	57.70 215	95.45 68	63.52 257	88.76 132	90.66 190

HyFIR lowres test		77.53 227	75.40 246	83.94 146	89.59 123	66.62 168	80.36 318	88.64 213	56.29 382	76.45 214	85.17 283	57.64 216	93.28 164	61.34 283	83.10 220	91.91 151

CNLPA		78.08 211	76.79 222	81.97 207	90.40 102	71.07 65	87.59 164	84.55 282	66.03 289	72.38 293	89.64 159	57.56 217	86.04 328	59.61 295	83.35 216	88.79 266

test_yl		81.17 135	80.47 137	83.24 166	89.13 147	63.62 231	86.21 209	89.95 164	72.43 174	81.78 122	89.61 160	57.50 218	93.58 149	70.75 193	86.90 159	92.52 127

DCV-MVSNet		81.17 135	80.47 137	83.24 166	89.13 147	63.62 231	86.21 209	89.95 164	72.43 174	81.78 122	89.61 160	57.50 218	93.58 149	70.75 193	86.90 159	92.52 127

sss		73.60 284	73.64 272	73.51 342	82.80 320	55.01 354	76.12 363	81.69 326	62.47 334	74.68 262	85.85 266	57.32 220	78.11 379	60.86 286	80.93 243	87.39 298

Effi-MVS+-dtu		80.03 165	78.57 176	84.42 111	85.13 268	68.74 114	88.77 121	88.10 220	74.99 112	74.97 257	83.49 321	57.27 221	93.36 162	73.53 167	80.88 245	91.18 170

AdaColmap		80.58 154	79.42 157	84.06 135	93.09 57	68.91 108	89.36 100	88.97 201	69.27 237	75.70 230	89.69 157	57.20 222	95.77 59	63.06 262	88.41 140	87.50 297

v1240		78.99 190	77.78 198	82.64 195	83.21 307	63.54 235	86.62 197	90.30 153	69.74 231	77.33 190	85.68 269	57.04 223	93.76 144	73.13 174	76.92 291	90.62 191

miper_lstm_enhance		74.11 277	73.11 279	77.13 305	80.11 360	59.62 293	72.23 385	86.92 251	66.76 275	70.40 311	82.92 331	56.93 224	82.92 356	69.06 213	72.63 349	88.87 262

BP-MVS1		84.32 78	83.71 86	86.17 61	87.84 201	67.85 139	89.38 99	89.64 174	77.73 40	83.98 92	92.12 98	56.89 225	95.43 70	84.03 67	91.75 87	95.24 6

BH-RMVSNet		79.61 170	78.44 179	83.14 171	89.38 135	65.93 180	84.95 240	87.15 245	73.56 150	78.19 173	89.79 155	56.67 226	93.36 162	59.53 296	86.74 162	90.13 212

RRT-MVS		82.60 113	82.10 112	84.10 127	87.98 195	62.94 253	87.45 169	91.27 121	77.42 51	79.85 143	90.28 145	56.62 227	94.70 107	79.87 109	88.15 143	94.67 28

test_djsdf		80.30 160	79.32 161	83.27 164	83.98 290	65.37 196	90.50 64	90.38 147	68.55 256	76.19 221	88.70 184	56.44 228	93.46 158	78.98 112	80.14 257	90.97 179

EPNet_dtu		75.46 262	74.86 254	77.23 304	82.57 326	54.60 357	86.89 187	83.09 307	71.64 182	66.25 360	85.86 265	55.99 229	88.04 310	54.92 334	86.55 165	89.05 253
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GDP-MVS		83.52 94	82.64 104	86.16 62	88.14 185	68.45 125	89.13 109	92.69 65	72.82 170	83.71 97	91.86 104	55.69 230	95.35 79	80.03 106	89.74 118	94.69 27

CostFormer		75.24 267	73.90 268	79.27 266	82.65 325	58.27 303	80.80 307	82.73 316	61.57 342	75.33 246	83.13 327	55.52 231	91.07 260	64.98 249	78.34 277	88.45 277

tpmrst		72.39 299	72.13 290	73.18 347	80.54 355	49.91 391	79.91 326	79.08 357	63.11 323	71.69 301	79.95 364	55.32 232	82.77 357	65.66 244	73.89 338	86.87 312

1314		76.53 243	75.30 250	80.21 248	83.93 291	62.32 259	84.66 245	88.81 204	60.23 351	70.16 316	84.07 308	55.30 233	90.73 266	67.37 228	83.21 218	87.59 295

tfpnnormal		74.39 272	73.16 278	78.08 289	86.10 249	58.05 305	84.65 247	87.53 235	70.32 213	71.22 306	85.63 271	54.97 234	89.86 277	43.03 394	75.02 328	86.32 321

sd_testset		77.70 224	77.40 208	78.60 277	89.03 152	60.02 289	79.00 337	85.83 268	75.19 108	76.61 211	89.98 151	54.81 235	85.46 336	62.63 268	83.55 211	90.33 204

GBi-Net		78.40 202	77.40 208	81.40 219	87.60 212	63.01 248	88.39 136	89.28 184	71.63 183	75.34 242	87.28 223	54.80 236	91.11 254	62.72 264	79.57 261	90.09 216

test1		78.40 202	77.40 208	81.40 219	87.60 212	63.01 248	88.39 136	89.28 184	71.63 183	75.34 242	87.28 223	54.80 236	91.11 254	62.72 264	79.57 261	90.09 216

FMVSNet2		78.20 208	77.21 212	81.20 225	87.60 212	62.89 254	87.47 167	89.02 197	71.63 183	75.29 248	87.28 223	54.80 236	91.10 257	62.38 269	79.38 265	89.61 238

Fast-Effi-MVS+-dtu		78.02 214	76.49 229	82.62 196	83.16 311	66.96 166	86.94 185	87.45 238	72.45 171	71.49 304	84.17 306	54.79 239	91.58 236	67.61 225	80.31 254	89.30 246

MVSTER		79.01 189	77.88 194	82.38 200	83.07 312	64.80 210	84.08 264	88.95 202	69.01 249	78.69 159	87.17 230	54.70 240	92.43 204	74.69 156	80.57 251	89.89 229

OpenMVS	72.83 10	79.77 168	78.33 183	84.09 131	85.17 264	69.91 87	90.57 61	90.97 130	66.70 276	72.17 296	91.91 100	54.70 240	93.96 128	61.81 278	90.95 98	88.41 279

XVG-OURS		80.41 156	79.23 164	83.97 144	85.64 254	69.02 105	83.03 285	90.39 146	71.09 196	77.63 185	91.49 116	54.62 242	91.35 249	75.71 146	83.47 214	91.54 159

LPG-MVS_test		82.08 117	81.27 123	84.50 107	89.23 143	68.76 112	90.22 73	91.94 99	75.37 102	76.64 209	91.51 114	54.29 243	94.91 95	78.44 117	83.78 202	89.83 231

LGP-MVS_train				84.50 107	89.23 143	68.76 112		91.94 99	75.37 102	76.64 209	91.51 114	54.29 243	94.91 95	78.44 117	83.78 202	89.83 231

TR-MVS		77.44 228	76.18 234	81.20 225	88.24 180	63.24 243	84.61 248	86.40 259	67.55 268	77.81 181	86.48 253	54.10 245	93.15 176	57.75 315	82.72 225	87.20 303

FMVSNet3		77.88 218	76.85 220	80.97 233	86.84 233	62.36 257	86.52 200	88.77 206	71.13 194	75.34 242	86.66 245	54.07 246	91.10 257	62.72 264	79.57 261	89.45 242

DP-MVS		76.78 240	74.57 257	83.42 158	93.29 48	69.46 97	88.55 132	83.70 294	63.98 317	70.20 313	88.89 180	54.01 247	94.80 102	46.66 380	81.88 235	86.01 329

ACMP	74.13 6	81.51 132	80.57 134	84.36 113	89.42 131	68.69 119	89.97 77	91.50 118	74.46 127	75.04 256	90.41 144	53.82 248	94.54 109	77.56 126	82.91 221	89.86 230
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PLC	70.83 11	78.05 213	76.37 233	83.08 175	91.88 77	67.80 141	88.19 145	89.46 179	64.33 310	69.87 322	88.38 195	53.66 249	93.58 149	58.86 303	82.73 224	87.86 288
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dmvs_testset		62.63 364	64.11 355	58.19 394	78.55 377	24.76 432	75.28 370	65.94 409	67.91 265	60.34 388	76.01 391	53.56 250	73.94 407	31.79 412	67.65 374	75.88 401

CANet_DTU		80.61 150	79.87 148	82.83 186	85.60 256	63.17 247	87.36 171	88.65 212	76.37 83	75.88 227	88.44 194	53.51 251	93.07 181	73.30 171	89.74 118	92.25 140

WB-MVSnew		71.96 306	71.65 294	72.89 348	84.67 278	51.88 377	82.29 290	77.57 365	62.31 335	73.67 276	83.00 329	53.49 252	81.10 367	45.75 387	82.13 231	85.70 335

ACMM	73.20 8	80.78 148	79.84 149	83.58 154	89.31 139	68.37 127	89.99 76	91.60 112	70.28 214	77.25 192	89.66 158	53.37 253	93.53 154	74.24 162	82.85 222	88.85 263
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVP-Stereo		76.12 252	74.46 261	81.13 228	85.37 261	69.79 89	84.42 256	87.95 225	65.03 301	67.46 343	85.33 278	53.28 254	91.73 232	58.01 313	83.27 217	81.85 382
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
AUN-MVS		79.21 184	77.60 205	84.05 138	88.71 164	67.61 146	85.84 220	87.26 242	69.08 245	77.23 194	88.14 206	53.20 255	93.47 157	75.50 151	73.45 343	91.06 174

SSC-MVS3.2		73.35 290	73.39 274	73.23 343	85.30 262	49.01 394	74.58 378	81.57 327	75.21 106	73.68 275	85.58 273	52.53 256	82.05 361	54.33 338	77.69 284	88.63 273

anonymousdsp		78.60 199	77.15 213	82.98 181	80.51 356	67.08 162	87.24 176	89.53 177	65.66 293	75.16 251	87.19 229	52.52 257	92.25 213	77.17 131	79.34 266	89.61 238

CR-MVSNet		73.37 287	71.27 300	79.67 260	81.32 348	65.19 199	75.92 365	80.30 344	59.92 354	72.73 287	81.19 349	52.50 258	86.69 320	59.84 292	77.71 282	87.11 308

Patchmtry		70.74 315	69.16 318	75.49 320	80.72 352	54.07 362	74.94 376	80.30 344	58.34 367	70.01 317	81.19 349	52.50 258	86.54 322	53.37 343	71.09 361	85.87 334

pmmvs4		74.03 280	71.91 291	80.39 243	81.96 334	68.32 128	81.45 300	82.14 320	59.32 359	69.87 322	85.13 284	52.40 260	88.13 309	60.21 290	74.74 331	84.73 352

RPMNet		73.51 285	70.49 308	82.58 197	81.32 348	65.19 199	75.92 365	92.27 84	57.60 374	72.73 287	76.45 389	52.30 261	95.43 70	48.14 375	77.71 282	87.11 308

LFMVS		81.82 123	81.23 124	83.57 155	91.89 76	63.43 240	89.84 78	81.85 325	77.04 63	83.21 103	93.10 75	52.26 262	93.43 160	71.98 183	89.95 115	93.85 67

VDD-MVS		83.01 107	82.36 108	84.96 93	91.02 88	66.40 171	88.91 116	88.11 219	77.57 44	84.39 84	93.29 72	52.19 263	93.91 135	77.05 133	88.70 134	94.57 35

tfpn200view9		76.42 248	75.37 248	79.55 264	89.13 147	57.65 315	85.17 232	83.60 295	73.41 156	76.45 214	86.39 255	52.12 264	91.95 222	48.33 371	83.75 205	89.07 248

thres400		76.50 244	75.37 248	79.86 254	89.13 147	57.65 315	85.17 232	83.60 295	73.41 156	76.45 214	86.39 255	52.12 264	91.95 222	48.33 371	83.75 205	90.00 222

Syy-MVS		68.05 340	67.85 330	68.67 376	84.68 275	40.97 419	78.62 343	73.08 390	66.65 280	66.74 352	79.46 368	52.11 266	82.30 359	32.89 411	76.38 304	82.75 375

thres200		75.55 260	74.47 260	78.82 273	87.78 206	57.85 311	83.07 283	83.51 298	72.44 173	75.84 228	84.42 296	52.08 267	91.75 230	47.41 378	83.64 210	86.86 313

PMMVS		69.34 329	68.67 320	71.35 361	75.67 388	62.03 262	75.17 371	73.46 388	50.00 399	68.68 332	79.05 371	52.07 268	78.13 378	61.16 284	82.77 223	73.90 403

tpm cat1		70.57 317	68.31 323	77.35 302	82.41 330	57.95 309	78.08 351	80.22 346	52.04 393	68.54 335	77.66 384	52.00 269	87.84 312	51.77 349	72.07 355	86.25 322

IterMVS-SCA-FT		75.43 263	73.87 269	80.11 250	82.69 323	64.85 209	81.57 298	83.47 299	69.16 243	70.49 310	84.15 307	51.95 270	88.15 308	69.23 210	72.14 354	87.34 300

SCA		74.22 275	72.33 288	79.91 253	84.05 289	62.17 261	79.96 325	79.29 355	66.30 285	72.38 293	80.13 362	51.95 270	88.60 303	59.25 298	77.67 285	88.96 259

thres100view900		76.50 244	75.55 243	79.33 265	89.52 126	56.99 324	85.83 221	83.23 303	73.94 140	76.32 218	87.12 231	51.89 272	91.95 222	48.33 371	83.75 205	89.07 248

thres600view7		76.50 244	75.44 244	79.68 259	89.40 133	57.16 321	85.53 229	83.23 303	73.79 144	76.26 219	87.09 232	51.89 272	91.89 225	48.05 376	83.72 208	90.00 222

tpm2		73.26 291	71.46 296	78.63 275	83.34 304	56.71 329	80.65 313	80.40 343	56.63 380	73.55 277	82.02 346	51.80 274	91.24 252	56.35 329	78.42 275	87.95 285

MonoMVSNet		76.49 247	75.80 236	78.58 278	81.55 341	58.45 300	86.36 205	86.22 262	74.87 118	74.73 261	83.73 315	51.79 275	88.73 300	70.78 192	72.15 353	88.55 276

LS3D		76.95 237	74.82 255	83.37 161	90.45 100	67.36 154	89.15 108	86.94 249	61.87 341	69.52 325	90.61 141	51.71 276	94.53 110	46.38 383	86.71 163	88.21 282

IterMVS		74.29 273	72.94 281	78.35 285	81.53 342	63.49 237	81.58 297	82.49 317	68.06 264	69.99 319	83.69 317	51.66 277	85.54 334	65.85 242	71.64 357	86.01 329
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 301	71.71 293	74.35 334	82.19 332	52.00 374	79.22 333	77.29 370	64.56 306	72.95 285	83.68 318	51.35 278	83.26 355	58.33 310	75.80 310	87.81 289

sam_mvs1												51.32 279				88.96 259

mvsmamba		80.60 151	79.38 158	84.27 121	89.74 121	67.24 159	87.47 167	86.95 248	70.02 219	75.38 240	88.93 178	51.24 280	92.56 199	75.47 152	89.22 124	93.00 114

PatchmatchNet		73.12 293	71.33 299	78.49 283	83.18 309	60.85 277	79.63 327	78.57 359	64.13 311	71.73 300	79.81 367	51.20 281	85.97 329	57.40 318	76.36 306	88.66 271
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
patchmatchnet-post											74.00 398	51.12 282	88.60 303

xiu_mvs_v1_base_debu		80.80 145	79.72 151	84.03 140	87.35 217	70.19 82	85.56 224	88.77 206	69.06 246	81.83 118	88.16 202	50.91 283	92.85 189	78.29 121	87.56 148	89.06 250

xiu_mvs_v1_base		80.80 145	79.72 151	84.03 140	87.35 217	70.19 82	85.56 224	88.77 206	69.06 246	81.83 118	88.16 202	50.91 283	92.85 189	78.29 121	87.56 148	89.06 250

xiu_mvs_v1_base_debi		80.80 145	79.72 151	84.03 140	87.35 217	70.19 82	85.56 224	88.77 206	69.06 246	81.83 118	88.16 202	50.91 283	92.85 189	78.29 121	87.56 148	89.06 250

Patchmatch-test		64.82 359	63.24 360	69.57 369	79.42 372	49.82 392	63.49 416	69.05 401	51.98 395	59.95 391	80.13 362	50.91 283	70.98 410	40.66 400	73.57 341	87.90 287

Patchmatch-RL test		70.24 321	67.78 334	77.61 297	77.43 381	59.57 295	71.16 389	70.33 395	62.94 327	68.65 333	72.77 401	50.62 287	85.49 335	69.58 208	66.58 378	87.77 290

Anonymous20231211		78.97 191	77.69 203	82.81 188	90.54 99	64.29 221	90.11 75	91.51 115	65.01 302	76.16 225	88.13 207	50.56 288	93.03 186	69.68 207	77.56 286	91.11 172

VDDNet		81.52 130	80.67 133	84.05 138	90.44 101	64.13 224	89.73 84	85.91 267	71.11 195	83.18 104	93.48 66	50.54 289	93.49 155	73.40 170	88.25 141	94.54 36

pmmvs6		74.69 271	73.39 274	78.61 276	81.38 345	57.48 318	86.64 196	87.95 225	64.99 303	70.18 314	86.61 246	50.43 290	89.52 284	62.12 274	70.18 365	88.83 264

test_post											5.46 430	50.36 291	84.24 345

ET-MVSNet_ETH3D		78.63 198	76.63 228	84.64 104	86.73 236	69.47 95	85.01 238	84.61 281	69.54 232	66.51 358	86.59 247	50.16 292	91.75 230	76.26 140	84.24 198	92.69 122

sam_mvs												50.01 293

Anonymous20240529		80.19 163	78.89 171	84.10 127	90.60 97	64.75 211	88.95 115	90.90 132	65.97 290	80.59 136	91.17 127	49.97 294	93.73 147	69.16 212	82.70 226	93.81 71

thisisatest0530		79.40 179	77.76 200	84.31 116	87.69 210	65.10 202	87.36 171	84.26 288	70.04 218	77.42 188	88.26 200	49.94 295	94.79 103	70.20 199	84.70 188	93.03 111

PatchT		68.46 338	67.85 330	70.29 367	80.70 353	43.93 411	72.47 384	74.88 382	60.15 352	70.55 308	76.57 388	49.94 295	81.59 363	50.58 356	74.83 330	85.34 340

tttt0517		79.40 179	77.91 192	83.90 147	88.10 188	63.84 228	88.37 139	84.05 290	71.45 189	76.78 205	89.12 174	49.93 297	94.89 98	70.18 200	83.18 219	92.96 116

tpmvs		71.09 311	69.29 316	76.49 309	82.04 333	56.04 340	78.92 339	81.37 331	64.05 315	67.18 347	78.28 379	49.74 298	89.77 279	49.67 365	72.37 350	83.67 364

thisisatest0515		77.33 231	75.38 247	83.18 169	85.27 263	63.80 229	82.11 292	83.27 302	65.06 300	75.91 226	83.84 311	49.54 299	94.27 118	67.24 230	86.19 171	91.48 163

UniMVSNet_ETH3D		79.10 187	78.24 185	81.70 211	86.85 232	60.24 287	87.28 175	88.79 205	74.25 134	76.84 202	90.53 143	49.48 300	91.56 238	67.98 222	82.15 230	93.29 96

dmvs_re		71.14 310	70.58 306	72.80 349	81.96 334	59.68 292	75.60 369	79.34 354	68.55 256	69.27 329	80.72 357	49.42 301	76.54 387	52.56 347	77.79 281	82.19 380

CVMVSNet		72.99 296	72.58 285	74.25 335	84.28 282	50.85 387	86.41 202	83.45 300	44.56 406	73.23 281	87.54 219	49.38 302	85.70 331	65.90 241	78.44 274	86.19 324

MDTV_nov1_ep13_2view						37.79 422	75.16 372		55.10 385	66.53 355		49.34 303		53.98 339		87.94 286

UGNet		80.83 142	79.59 154	84.54 106	88.04 191	68.09 134	89.42 96	88.16 218	76.95 64	76.22 220	89.46 167	49.30 304	93.94 131	68.48 219	90.31 106	91.60 156
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
pmmvs5		71.55 307	70.20 313	75.61 316	77.83 379	56.39 334	81.74 295	80.89 333	57.76 372	67.46 343	84.49 294	49.26 305	85.32 338	57.08 321	75.29 324	85.11 346

mvsany_test1		62.30 365	61.26 369	65.41 386	69.52 410	54.86 355	66.86 406	49.78 426	46.65 403	68.50 336	83.21 325	49.15 306	66.28 418	56.93 324	60.77 392	75.11 402

LTVRE_ROB	69.57 13	76.25 251	74.54 259	81.41 218	88.60 167	64.38 220	79.24 332	89.12 195	70.76 203	69.79 324	87.86 209	49.09 307	93.20 172	56.21 330	80.16 255	86.65 318
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
FMVSNet1		77.44 228	76.12 235	81.40 219	86.81 234	63.01 248	88.39 136	89.28 184	70.49 210	74.39 267	87.28 223	49.06 308	91.11 254	60.91 285	78.52 272	90.09 216

test1111		79.43 177	79.18 166	80.15 249	89.99 114	53.31 369	87.33 173	77.05 372	75.04 111	80.23 140	92.77 89	48.97 309	92.33 211	68.87 215	92.40 79	94.81 21

ECVR-MVS		79.61 170	79.26 163	80.67 239	90.08 109	54.69 356	87.89 157	77.44 368	74.88 116	80.27 138	92.79 87	48.96 310	92.45 203	68.55 218	92.50 77	94.86 18

MDTV_nov1_ep13			69.97 314		83.18 309	53.48 366	77.10 361	80.18 347	60.45 348	69.33 328	80.44 358	48.89 311	86.90 319	51.60 351	78.51 273

test_post1							78.90 340				5.43 431	48.81 312	85.44 337	59.25 298

test-LLR		72.94 297	72.43 286	74.48 332	81.35 346	58.04 306	78.38 346	77.46 366	66.66 277	69.95 320	79.00 373	48.06 313	79.24 373	66.13 237	84.83 185	86.15 325

test0.0.03 1		68.00 341	67.69 335	68.90 373	77.55 380	47.43 397	75.70 368	72.95 392	66.66 277	66.56 354	82.29 342	48.06 313	75.87 396	44.97 391	74.51 333	83.41 366

our_test_3		69.14 330	67.00 343	75.57 317	79.80 366	58.80 297	77.96 353	77.81 363	59.55 357	62.90 381	78.25 380	47.43 315	83.97 347	51.71 350	67.58 375	83.93 361

MS-PatchMatch		73.83 281	72.67 283	77.30 303	83.87 293	66.02 177	81.82 293	84.66 280	61.37 345	68.61 334	82.82 334	47.29 316	88.21 307	59.27 297	84.32 197	77.68 397

cascas		76.72 241	74.64 256	82.99 180	85.78 252	65.88 182	82.33 289	89.21 189	60.85 347	72.74 286	81.02 352	47.28 317	93.75 145	67.48 227	85.02 183	89.34 245

WB-MVS		54.94 374	54.72 375	55.60 400	73.50 399	20.90 434	74.27 380	61.19 417	59.16 361	50.61 409	74.15 397	47.19 318	75.78 397	17.31 425	35.07 419	70.12 407

test20.03		67.45 343	66.95 344	68.94 372	75.48 390	44.84 409	77.50 357	77.67 364	66.66 277	63.01 379	83.80 312	47.02 319	78.40 377	42.53 397	68.86 372	83.58 365

test_0402		72.79 298	70.44 309	79.84 255	88.13 186	65.99 179	85.93 216	84.29 286	65.57 294	67.40 345	85.49 275	46.92 320	92.61 195	35.88 408	74.38 334	80.94 387

F-COLMAP		76.38 250	74.33 263	82.50 198	89.28 141	66.95 167	88.41 135	89.03 196	64.05 315	66.83 350	88.61 188	46.78 321	92.89 188	57.48 316	78.55 271	87.67 291

ppachtmachnet_test		70.04 323	67.34 341	78.14 288	79.80 366	61.13 272	79.19 334	80.59 338	59.16 361	65.27 365	79.29 370	46.75 322	87.29 316	49.33 366	66.72 376	86.00 331

WBMVS		73.43 286	72.81 282	75.28 323	87.91 197	50.99 386	78.59 345	81.31 332	65.51 297	74.47 266	84.83 290	46.39 323	86.68 321	58.41 308	77.86 280	88.17 283

tt0805		78.73 195	77.83 195	81.43 217	85.17 264	60.30 286	89.41 97	90.90 132	71.21 193	77.17 199	88.73 183	46.38 324	93.21 169	72.57 180	78.96 269	90.79 183

D2MVS		74.82 270	73.21 277	79.64 261	79.81 365	62.56 256	80.34 319	87.35 239	64.37 309	68.86 331	82.66 336	46.37 325	90.10 273	67.91 223	81.24 240	86.25 322

Anonymous20231206		68.60 334	67.80 333	71.02 364	80.23 359	50.75 388	78.30 350	80.47 340	56.79 379	66.11 361	82.63 337	46.35 326	78.95 375	43.62 393	75.70 311	83.36 367

SSC-MVS		53.88 377	53.59 377	54.75 402	72.87 405	19.59 435	73.84 382	60.53 419	57.58 375	49.18 413	73.45 400	46.34 327	75.47 400	16.20 428	32.28 421	69.20 408

CHOSEN 280x420		66.51 350	64.71 352	71.90 355	81.45 343	63.52 236	57.98 419	68.95 402	53.57 389	62.59 382	76.70 387	46.22 328	75.29 402	55.25 332	79.68 260	76.88 399

testing91		76.54 242	75.66 241	79.18 269	88.43 174	55.89 342	81.08 304	83.00 310	73.76 145	75.34 242	84.29 301	46.20 329	90.07 274	64.33 253	84.50 190	91.58 158

GA-MVS		76.87 238	75.17 252	81.97 207	82.75 321	62.58 255	81.44 301	86.35 261	72.16 178	74.74 260	82.89 332	46.20 329	92.02 220	68.85 216	81.09 242	91.30 168

MDA-MVSNet_test_wron		65.03 357	62.92 361	71.37 359	75.93 385	56.73 327	69.09 401	74.73 384	57.28 377	54.03 406	77.89 381	45.88 331	74.39 405	49.89 364	61.55 390	82.99 373

YYNet1		65.03 357	62.91 362	71.38 358	75.85 387	56.60 331	69.12 400	74.66 386	57.28 377	54.12 405	77.87 382	45.85 332	74.48 404	49.95 363	61.52 391	83.05 371

EPMVS		69.02 331	68.16 325	71.59 357	79.61 369	49.80 393	77.40 358	66.93 406	62.82 330	70.01 317	79.05 371	45.79 333	77.86 381	56.58 327	75.26 325	87.13 307

IB-MVS	68.01 15	75.85 257	73.36 276	83.31 162	84.76 273	66.03 176	83.38 275	85.06 276	70.21 217	69.40 326	81.05 351	45.76 334	94.66 108	65.10 248	75.49 315	89.25 247
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
jajsoiax		79.29 182	77.96 190	83.27 164	84.68 275	66.57 170	89.25 103	90.16 158	69.20 242	75.46 236	89.49 164	45.75 335	93.13 178	76.84 135	80.80 247	90.11 214

UBG		73.08 294	72.27 289	75.51 319	88.02 192	51.29 384	78.35 349	77.38 369	65.52 295	73.87 273	82.36 339	45.55 336	86.48 324	55.02 333	84.39 196	88.75 268

PatchMatch-RL		72.38 300	70.90 304	76.80 308	88.60 167	67.38 153	79.53 328	76.17 378	62.75 331	69.36 327	82.00 347	45.51 337	84.89 342	53.62 341	80.58 250	78.12 396

FE-MVS		77.78 220	75.68 239	84.08 132	88.09 189	66.00 178	83.13 280	87.79 230	68.42 260	78.01 178	85.23 281	45.50 338	95.12 85	59.11 300	85.83 179	91.11 172

RPSCF		73.23 292	71.46 296	78.54 280	82.50 327	59.85 290	82.18 291	82.84 315	58.96 363	71.15 307	89.41 171	45.48 339	84.77 343	58.82 304	71.83 356	91.02 178

test_vis1_n_1920		75.52 261	75.78 237	74.75 331	79.84 364	57.44 319	83.26 277	85.52 271	62.83 329	79.34 151	86.17 260	45.10 340	79.71 372	78.75 114	81.21 241	87.10 310

myMVS_eth3d28		73.62 283	73.53 273	73.90 339	88.20 181	47.41 398	78.06 352	79.37 353	74.29 133	73.98 271	84.29 301	44.67 341	83.54 351	51.47 352	87.39 152	90.74 187

MSDG		73.36 289	70.99 303	80.49 242	84.51 280	65.80 185	80.71 312	86.13 265	65.70 292	65.46 363	83.74 314	44.60 342	90.91 262	51.13 355	76.89 292	84.74 351

PVSNet_0	57.27 20	61.67 367	59.27 370	68.85 374	79.61 369	57.44 319	68.01 402	73.44 389	55.93 383	58.54 395	70.41 406	44.58 343	77.55 382	47.01 379	35.91 418	71.55 406

testing99		76.09 254	75.12 253	79.00 270	88.16 183	55.50 348	80.79 308	81.40 330	73.30 159	75.17 250	84.27 304	44.48 344	90.02 275	64.28 254	84.22 199	91.48 163

testing3-2		75.12 269	75.19 251	74.91 327	90.40 102	45.09 408	80.29 320	78.42 360	78.37 36	76.54 213	87.75 210	44.36 345	87.28 317	57.04 322	83.49 213	92.37 134

test_cas_vis1_n_1920		73.76 282	73.74 271	73.81 340	75.90 386	59.77 291	80.51 315	82.40 318	58.30 368	81.62 124	85.69 268	44.35 346	76.41 390	76.29 139	78.61 270	85.23 342

mvs_tets		79.13 186	77.77 199	83.22 168	84.70 274	66.37 172	89.17 104	90.19 157	69.38 235	75.40 239	89.46 167	44.17 347	93.15 176	76.78 137	80.70 249	90.14 211

MDA-MVSNet-bldmvs		66.68 348	63.66 358	75.75 314	79.28 373	60.56 282	73.92 381	78.35 361	64.43 307	50.13 411	79.87 366	44.02 348	83.67 349	46.10 385	56.86 397	83.03 372

mmtdpeth		74.16 276	73.01 280	77.60 299	83.72 297	61.13 272	85.10 236	85.10 275	72.06 179	77.21 198	80.33 360	43.84 349	85.75 330	77.14 132	52.61 407	85.91 332

gg-mvs-nofinetune		69.95 324	67.96 328	75.94 312	83.07 312	54.51 359	77.23 360	70.29 396	63.11 323	70.32 312	62.33 410	43.62 350	88.69 301	53.88 340	87.76 147	84.62 353

testing11		75.14 268	74.01 265	78.53 281	88.16 183	56.38 335	80.74 311	80.42 342	70.67 204	72.69 289	83.72 316	43.61 351	89.86 277	62.29 271	83.76 204	89.36 244

GG-mvs-BLEND				75.38 322	81.59 340	55.80 344	79.32 331	69.63 398		67.19 346	73.67 399	43.24 352	88.90 299	50.41 357	84.50 190	81.45 384

CMPMVS	51.72 21	70.19 322	68.16 325	76.28 310	73.15 404	57.55 317	79.47 329	83.92 291	48.02 402	56.48 402	84.81 291	43.13 353	86.42 325	62.67 267	81.81 236	84.89 349
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dp		66.80 347	65.43 349	70.90 366	79.74 368	48.82 395	75.12 374	74.77 383	59.61 356	64.08 374	77.23 385	42.89 354	80.72 369	48.86 369	66.58 378	83.16 369

PVSNet	64.34 18	72.08 305	70.87 305	75.69 315	86.21 244	56.44 333	74.37 379	80.73 336	62.06 339	70.17 315	82.23 343	42.86 355	83.31 354	54.77 335	84.45 194	87.32 301

pmmvs-eth3d		70.50 319	67.83 332	78.52 282	77.37 382	66.18 175	81.82 293	81.51 328	58.90 364	63.90 376	80.42 359	42.69 356	86.28 326	58.56 306	65.30 383	83.11 370

UnsupCasMVSNet_eth		67.33 344	65.99 348	71.37 359	73.48 400	51.47 382	75.16 372	85.19 274	65.20 298	60.78 387	80.93 356	42.35 357	77.20 383	57.12 320	53.69 405	85.44 339

KD-MVS_self_test		68.81 332	67.59 338	72.46 353	74.29 394	45.45 403	77.93 354	87.00 247	63.12 322	63.99 375	78.99 375	42.32 358	84.77 343	56.55 328	64.09 386	87.16 306

ADS-MVSNet2		66.20 355	63.33 359	74.82 329	79.92 362	58.75 298	67.55 404	75.19 380	53.37 390	65.25 366	75.86 392	42.32 358	80.53 370	41.57 398	68.91 370	85.18 343

ADS-MVSNet		64.36 360	62.88 363	68.78 375	79.92 362	47.17 399	67.55 404	71.18 394	53.37 390	65.25 366	75.86 392	42.32 358	73.99 406	41.57 398	68.91 370	85.18 343

SixPastTwentyTwo		73.37 287	71.26 301	79.70 258	85.08 269	57.89 310	85.57 223	83.56 297	71.03 198	65.66 362	85.88 264	42.10 361	92.57 198	59.11 300	63.34 387	88.65 272

JIA-IIPM		66.32 352	62.82 364	76.82 307	77.09 383	61.72 268	65.34 412	75.38 379	58.04 371	64.51 370	62.32 411	42.05 362	86.51 323	51.45 353	69.22 369	82.21 379

ACMH	67.68 16	75.89 256	73.93 267	81.77 210	88.71 164	66.61 169	88.62 130	89.01 198	69.81 225	66.78 351	86.70 243	41.95 363	91.51 243	55.64 331	78.14 278	87.17 304
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UWE-MVS-28		65.32 356	64.93 350	66.49 384	78.70 376	38.55 421	77.86 356	64.39 413	62.00 340	64.13 373	83.60 319	41.44 364	76.00 394	31.39 413	80.89 244	84.92 348

ACMH+	68.96 14	76.01 255	74.01 265	82.03 205	88.60 167	65.31 197	88.86 118	87.55 234	70.25 216	67.75 339	87.47 221	41.27 365	93.19 174	58.37 309	75.94 309	87.60 293

MIMVSNet		70.69 316	69.30 315	74.88 328	84.52 279	56.35 337	75.87 367	79.42 352	64.59 305	67.76 338	82.41 338	41.10 366	81.54 364	46.64 382	81.34 238	86.75 316

Anonymous202405211		78.25 205	77.01 215	81.99 206	91.03 87	60.67 280	84.77 243	83.90 292	70.65 208	80.00 142	91.20 125	41.08 367	91.43 247	65.21 246	85.26 182	93.85 67

N_pmnet		52.79 380	53.26 378	51.40 404	78.99 375	7.68 438	69.52 396	3.89 437	51.63 396	57.01 400	74.98 396	40.83 368	65.96 419	37.78 405	64.67 384	80.56 391

ETVMVS		72.25 303	71.05 302	75.84 313	87.77 207	51.91 376	79.39 330	74.98 381	69.26 238	73.71 274	82.95 330	40.82 369	86.14 327	46.17 384	84.43 195	89.47 241

EU-MVSNet		68.53 337	67.61 337	71.31 362	78.51 378	47.01 400	84.47 251	84.27 287	42.27 409	66.44 359	84.79 292	40.44 370	83.76 348	58.76 305	68.54 373	83.17 368

DSMNet-mixed		57.77 372	56.90 374	60.38 392	67.70 413	35.61 423	69.18 398	53.97 424	32.30 422	57.49 399	79.88 365	40.39 371	68.57 416	38.78 404	72.37 350	76.97 398

UWE-MVS		72.13 304	71.49 295	74.03 337	86.66 239	47.70 396	81.40 302	76.89 374	63.60 320	75.59 231	84.22 305	39.94 372	85.62 333	48.98 368	86.13 173	88.77 267

OurMVSNet-221017-0		74.26 274	72.42 287	79.80 256	83.76 296	59.59 294	85.92 217	86.64 254	66.39 284	66.96 348	87.58 215	39.46 373	91.60 235	65.76 243	69.27 368	88.22 281

K. test v3		71.19 309	68.51 321	79.21 268	83.04 314	57.78 314	84.35 258	76.91 373	72.90 168	62.99 380	82.86 333	39.27 374	91.09 259	61.65 279	52.66 406	88.75 268

lessismore_v0				78.97 271	81.01 351	57.15 322		65.99 408		61.16 386	82.82 334	39.12 375	91.34 250	59.67 294	46.92 413	88.43 278

testing222		74.04 278	72.66 284	78.19 287	87.89 198	55.36 349	81.06 305	79.20 356	71.30 191	74.65 263	83.57 320	39.11 376	88.67 302	51.43 354	85.75 180	90.53 196

reproduce_monomvs		75.40 265	74.38 262	78.46 284	83.92 292	57.80 313	83.78 266	86.94 249	73.47 154	72.25 295	84.47 295	38.74 377	89.27 289	75.32 153	70.53 363	88.31 280

UnsupCasMVSNet_bld		63.70 362	61.53 368	70.21 368	73.69 398	51.39 383	72.82 383	81.89 323	55.63 384	57.81 398	71.80 403	38.67 378	78.61 376	49.26 367	52.21 408	80.63 389

new-patchmatchnet		61.73 366	61.73 367	61.70 390	72.74 406	24.50 433	69.16 399	78.03 362	61.40 343	56.72 401	75.53 395	38.42 379	76.48 389	45.95 386	57.67 396	84.13 358

MVS-HIRNet		59.14 370	57.67 372	63.57 388	81.65 338	43.50 412	71.73 386	65.06 411	39.59 413	51.43 408	57.73 416	38.34 380	82.58 358	39.53 401	73.95 337	64.62 412

test2506		77.30 232	76.49 229	79.74 257	90.08 109	52.02 373	87.86 159	63.10 415	74.88 116	80.16 141	92.79 87	38.29 381	92.35 209	68.74 217	92.50 77	94.86 18

COLMAP_ROB	66.92 17	73.01 295	70.41 310	80.81 236	87.13 228	65.63 189	88.30 142	84.19 289	62.96 326	63.80 377	87.69 213	38.04 382	92.56 199	46.66 380	74.91 329	84.24 356
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TESTMET0.1,1		69.89 325	69.00 319	72.55 351	79.27 374	56.85 325	78.38 346	74.71 385	57.64 373	68.09 337	77.19 386	37.75 383	76.70 386	63.92 256	84.09 200	84.10 359

OpenMVS_ROB	64.09 19	70.56 318	68.19 324	77.65 296	80.26 357	59.41 296	85.01 238	82.96 312	58.76 365	65.43 364	82.33 340	37.63 384	91.23 253	45.34 390	76.03 308	82.32 378

FMVSNet5		69.50 327	67.96 328	74.15 336	82.97 318	55.35 350	80.01 324	82.12 321	62.56 333	63.02 378	81.53 348	36.92 385	81.92 362	48.42 370	74.06 336	85.17 345

MIMVSNet1		68.58 335	66.78 345	73.98 338	80.07 361	51.82 378	80.77 309	84.37 283	64.40 308	59.75 392	82.16 344	36.47 386	83.63 350	42.73 395	70.33 364	86.48 320

ITE_SJBPF				78.22 286	81.77 337	60.57 281		83.30 301	69.25 239	67.54 341	87.20 228	36.33 387	87.28 317	54.34 337	74.62 332	86.80 314

test-mter		71.41 308	70.39 311	74.48 332	81.35 346	58.04 306	78.38 346	77.46 366	60.32 350	69.95 320	79.00 373	36.08 388	79.24 373	66.13 237	84.83 185	86.15 325

testgi		66.67 349	66.53 346	67.08 383	75.62 389	41.69 418	75.93 364	76.50 375	66.11 286	65.20 368	86.59 247	35.72 389	74.71 403	43.71 392	73.38 345	84.84 350

EG-PatchMatch MVS		74.04 278	71.82 292	80.71 238	84.92 271	67.42 151	85.86 219	88.08 221	66.04 288	64.22 372	83.85 310	35.10 390	92.56 199	57.44 317	80.83 246	82.16 381

KD-MVS_2432*1600		66.22 353	63.89 356	73.21 344	75.47 391	53.42 367	70.76 392	84.35 284	64.10 313	66.52 356	78.52 377	34.55 391	84.98 340	50.40 358	50.33 410	81.23 385

miper_refine_blended		66.22 353	63.89 356	73.21 344	75.47 391	53.42 367	70.76 392	84.35 284	64.10 313	66.52 356	78.52 377	34.55 391	84.98 340	50.40 358	50.33 410	81.23 385

mvs5depth		69.45 328	67.45 340	75.46 321	73.93 395	55.83 343	79.19 334	83.23 303	66.89 272	71.63 302	83.32 323	33.69 393	85.09 339	59.81 293	55.34 403	85.46 338

XVG-ACMP-BASELINE		76.11 253	74.27 264	81.62 212	83.20 308	64.67 212	83.60 272	89.75 170	69.75 229	71.85 299	87.09 232	32.78 394	92.11 217	69.99 203	80.43 253	88.09 284

AllTest		70.96 312	68.09 327	79.58 262	85.15 266	63.62 231	84.58 249	79.83 348	62.31 335	60.32 389	86.73 237	32.02 395	88.96 297	50.28 360	71.57 358	86.15 325

TestCases				79.58 262	85.15 266	63.62 231		79.83 348	62.31 335	60.32 389	86.73 237	32.02 395	88.96 297	50.28 360	71.57 358	86.15 325

USDC		70.33 320	68.37 322	76.21 311	80.60 354	56.23 338	79.19 334	86.49 257	60.89 346	61.29 385	85.47 276	31.78 397	89.47 286	53.37 343	76.21 307	82.94 374

myMVS_eth3d		67.02 346	66.29 347	69.21 371	84.68 275	42.58 414	78.62 343	73.08 390	66.65 280	66.74 352	79.46 368	31.53 398	82.30 359	39.43 403	76.38 304	82.75 375

test_fmvs1		70.93 313	70.52 307	72.16 354	73.71 397	55.05 353	80.82 306	78.77 358	51.21 398	78.58 163	84.41 297	31.20 399	76.94 385	75.88 145	80.12 258	84.47 354

Anonymous20240521		68.80 333	67.22 342	73.55 341	74.33 393	54.11 361	83.18 278	85.61 270	58.15 369	61.68 384	80.94 354	30.71 400	81.27 366	57.00 323	73.34 346	85.28 341

testing3		68.56 336	67.67 336	71.22 363	87.33 222	42.87 413	83.06 284	71.54 393	70.36 211	69.08 330	84.38 298	30.33 401	85.69 332	37.50 406	75.45 319	85.09 347

test_vis1_n		69.85 326	69.21 317	71.77 356	72.66 407	55.27 352	81.48 299	76.21 377	52.03 394	75.30 247	83.20 326	28.97 402	76.22 392	74.60 157	78.41 276	83.81 362

tmp_tt		18.61 398	21.40 401	10.23 414	4.82 437	10.11 437	34.70 424	30.74 435	1.48 431	23.91 427	26.07 428	28.42 403	13.41 433	27.12 417	15.35 430	7.17 428

test_fmvs1_n		70.86 314	70.24 312	72.73 350	72.51 408	55.28 351	81.27 303	79.71 350	51.49 397	78.73 158	84.87 289	27.54 404	77.02 384	76.06 142	79.97 259	85.88 333

TDRefinement		67.49 342	64.34 353	76.92 306	73.47 401	61.07 274	84.86 242	82.98 311	59.77 355	58.30 396	85.13 284	26.06 405	87.89 311	47.92 377	60.59 394	81.81 383

dongtai		45.42 388	45.38 389	45.55 406	73.36 402	26.85 430	67.72 403	34.19 432	54.15 388	49.65 412	56.41 419	25.43 406	62.94 422	19.45 423	28.09 423	46.86 422

MVStest1		56.63 373	52.76 379	68.25 379	61.67 421	53.25 371	71.67 387	68.90 403	38.59 414	50.59 410	83.05 328	25.08 407	70.66 411	36.76 407	38.56 417	80.83 388

test_vis1_rt		60.28 368	58.42 371	65.84 385	67.25 414	55.60 347	70.44 394	60.94 418	44.33 407	59.00 393	66.64 408	24.91 408	68.67 415	62.80 263	69.48 366	73.25 404

TinyColmap		67.30 345	64.81 351	74.76 330	81.92 336	56.68 330	80.29 320	81.49 329	60.33 349	56.27 403	83.22 324	24.77 409	87.66 315	45.52 388	69.47 367	79.95 392

EGC-MVSNET		52.07 382	47.05 386	67.14 382	83.51 301	60.71 279	80.50 316	67.75 404	0.07 432	0.43 433	75.85 394	24.26 410	81.54 364	28.82 415	62.25 388	59.16 415

kuosan		39.70 392	40.40 393	37.58 409	64.52 418	26.98 428	65.62 411	33.02 433	46.12 404	42.79 416	48.99 422	24.10 411	46.56 430	12.16 431	26.30 424	39.20 423

LF4IMVS		64.02 361	62.19 365	69.50 370	70.90 409	53.29 370	76.13 362	77.18 371	52.65 392	58.59 394	80.98 353	23.55 412	76.52 388	53.06 345	66.66 377	78.68 395

test_fmvs2		68.35 339	67.48 339	70.98 365	69.50 411	51.95 375	80.05 323	76.38 376	49.33 400	74.65 263	84.38 298	23.30 413	75.40 401	74.51 158	75.17 327	85.60 336

new_pmnet		50.91 383	50.29 383	52.78 403	68.58 412	34.94 425	63.71 414	56.63 423	39.73 412	44.95 414	65.47 409	21.93 414	58.48 423	34.98 409	56.62 398	64.92 411

ttmdpeth		59.91 369	57.10 373	68.34 378	67.13 415	46.65 402	74.64 377	67.41 405	48.30 401	62.52 383	85.04 288	20.40 415	75.93 395	42.55 396	45.90 416	82.44 377

pmmvs3		57.79 371	54.26 376	68.37 377	64.02 419	56.72 328	75.12 374	65.17 410	40.20 411	52.93 407	69.86 407	20.36 416	75.48 399	45.45 389	55.25 404	72.90 405

PM-MVS		66.41 351	64.14 354	73.20 346	73.92 396	56.45 332	78.97 338	64.96 412	63.88 319	64.72 369	80.24 361	19.84 417	83.44 353	66.24 236	64.52 385	79.71 393

mvsany_test3		53.99 376	51.45 381	61.61 391	55.51 425	44.74 410	63.52 415	45.41 430	43.69 408	58.11 397	76.45 389	17.99 418	63.76 421	54.77 335	47.59 412	76.34 400

ambc				75.24 324	73.16 403	50.51 389	63.05 417	87.47 237		64.28 371	77.81 383	17.80 419	89.73 281	57.88 314	60.64 393	85.49 337

ANet_high		50.57 384	46.10 388	63.99 387	48.67 432	39.13 420	70.99 391	80.85 334	61.39 344	31.18 421	57.70 417	17.02 420	73.65 408	31.22 414	15.89 429	79.18 394

FPMVS		53.68 378	51.64 380	59.81 393	65.08 417	51.03 385	69.48 397	69.58 399	41.46 410	40.67 417	72.32 402	16.46 421	70.00 414	24.24 421	65.42 382	58.40 417

test_method		31.52 394	29.28 398	38.23 408	27.03 436	6.50 439	20.94 427	62.21 416	4.05 430	22.35 428	52.50 421	13.33 422	47.58 428	27.04 418	34.04 420	60.62 414

EMVS		30.81 395	29.65 397	34.27 411	50.96 431	25.95 431	56.58 421	46.80 429	24.01 426	15.53 431	30.68 427	12.47 423	54.43 427	12.81 430	17.05 428	22.43 427

test_f		52.09 381	50.82 382	55.90 398	53.82 428	42.31 417	59.42 418	58.31 422	36.45 417	56.12 404	70.96 405	12.18 424	57.79 424	53.51 342	56.57 399	67.60 409

test_fmvs3		63.36 363	61.82 366	67.98 380	62.51 420	46.96 401	77.37 359	74.03 387	45.24 405	67.50 342	78.79 376	12.16 425	72.98 409	72.77 178	66.02 380	83.99 360

E-PMN		31.77 393	30.64 396	35.15 410	52.87 430	27.67 427	57.09 420	47.86 428	24.64 425	16.40 430	33.05 426	11.23 426	54.90 426	14.46 429	18.15 427	22.87 426

DeepMVS_CX				27.40 412	40.17 435	26.90 429		24.59 436	17.44 428	23.95 426	48.61 423	9.77 427	26.48 431	18.06 424	24.47 425	28.83 425

Gipuma		45.18 389	41.86 392	55.16 401	77.03 384	51.52 381	32.50 425	80.52 339	32.46 421	27.12 424	35.02 425	9.52 428	75.50 398	22.31 422	60.21 395	38.45 424
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		54.25 375	49.68 385	67.97 381	53.73 429	45.28 406	66.85 407	80.78 335	35.96 418	39.45 419	62.23 412	8.70 429	78.06 380	48.24 374	51.20 409	80.57 390

APD_test1		53.31 379	49.93 384	63.42 389	65.68 416	50.13 390	71.59 388	66.90 407	34.43 419	40.58 418	71.56 404	8.65 430	76.27 391	34.64 410	55.36 402	63.86 413

PMMVS2		40.82 391	38.86 395	46.69 405	53.84 427	16.45 436	48.61 422	49.92 425	37.49 415	31.67 420	60.97 413	8.14 431	56.42 425	28.42 416	30.72 422	67.19 410

test_vis3_rt		49.26 385	47.02 387	56.00 397	54.30 426	45.27 407	66.76 408	48.08 427	36.83 416	44.38 415	53.20 420	7.17 432	64.07 420	56.77 326	55.66 400	58.65 416

testf1		45.72 386	41.96 390	57.00 395	56.90 423	45.32 404	66.14 409	59.26 420	26.19 423	30.89 422	60.96 414	4.14 433	70.64 412	26.39 419	46.73 414	55.04 418

APD_test2		45.72 386	41.96 390	57.00 395	56.90 423	45.32 404	66.14 409	59.26 420	26.19 423	30.89 422	60.96 414	4.14 433	70.64 412	26.39 419	46.73 414	55.04 418

PMVS	37.38 22	44.16 390	40.28 394	55.82 399	40.82 434	42.54 416	65.12 413	63.99 414	34.43 419	24.48 425	57.12 418	3.92 435	76.17 393	17.10 426	55.52 401	48.75 420
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 396	25.89 400	43.81 407	44.55 433	35.46 424	28.87 426	39.07 431	18.20 427	18.58 429	40.18 424	2.68 436	47.37 429	17.07 427	23.78 426	48.60 421
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		16.82 399	15.94 402	19.46 413	58.74 422	31.45 426	39.22 423	3.74 438	6.84 429	6.04 432	2.70 432	1.27 437	24.29 432	10.54 432	14.40 431	2.63 429

test123		6.12 401	8.11 404	0.14 415	0.06 439	0.09 440	71.05 390	0.03 440	0.04 434	0.25 435	1.30 434	0.05 438	0.03 435	0.21 434	0.01 433	0.29 430

testmvs		6.04 402	8.02 405	0.10 416	0.08 438	0.03 441	69.74 395	0.04 439	0.05 433	0.31 434	1.68 433	0.02 439	0.04 434	0.24 433	0.02 432	0.25 431

mmdepth		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

monomultidepth		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

test_blank		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uanet_test		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

DCPMVS		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

sosnet-low-res		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

sosnet		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uncertanet		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

Regformer		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

ab-mvs-re		7.23 400	9.64 403	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	86.72 239	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uanet		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

WAC-MVS						42.58 414								39.46 402

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 126	91.30 15

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 10	96.44 9	94.41 39

No_MVS				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 10	96.44 9	94.41 39

eth-test2					0.00 440

eth-test					0.00 440

IU-MVS					95.30 2	71.25 59		92.95 55	66.81 273	92.39 6				88.94 21	96.63 4	94.85 20

save fliter					93.80 40	72.35 42	90.47 66	91.17 125	74.31 131

test_0728_SECOND				87.71 32	95.34 1	71.43 58	93.49 9	94.23 3					97.49 4	89.08 16	96.41 12	94.21 49

GSMVS																88.96 259

test_part2					95.06 8	72.65 32				91.80 13

MTGPA								92.02 93

MTMP							92.18 34	32.83 434

gm-plane-assit					81.40 344	53.83 364			62.72 332		80.94 354		92.39 206	63.40 260

test9_res														84.90 51	95.70 26	92.87 117

agg_prior2														82.91 78	95.45 29	92.70 120

agg_prior					92.85 62	71.94 50		91.78 108		84.41 83			94.93 94

test_prior4						72.60 34	89.01 113

test_prior				86.33 57	92.61 68	69.59 91		92.97 54					95.48 67			93.91 63

旧先验2							86.56 199		58.10 370	87.04 50			88.98 295	74.07 163

新几何2							86.29 208

无先验							87.48 166	88.98 199	60.00 353				94.12 125	67.28 229		88.97 258

原ACMM2							86.86 188

testdata2													91.01 261	62.37 270

testdata1							84.14 262		75.71 94

plane_prior7					90.08 109	68.51 124

plane_prior5								92.44 77					95.38 75	78.71 115	86.32 168	91.33 166

plane_prior4											91.00 135

plane_prior3						68.60 121			78.44 32	78.92 156

plane_prior2							91.25 52		79.12 24

plane_prior1					89.90 117

plane_prior						68.71 116	90.38 70		77.62 42						86.16 172

n2								0.00 441

nn								0.00 441

door-mid								69.98 397

test11								92.23 87

door								69.44 400

HQP5-MVS						66.98 164

HQP-NCC					89.33 136		89.17 104		76.41 79	77.23 194

ACMP_Plane					89.33 136		89.17 104		76.41 79	77.23 194

BP-MVS														77.47 127

HQP4-MVS										77.24 193			95.11 87			91.03 176

HQP3-MVS								92.19 90							85.99 176

NP-MVS					89.62 122	68.32 128					90.24 147

ACMMP++_ref															81.95 234

ACMMP++															81.25 239

High-resolution multi-view benchmark