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 53	93.10 1	95.72 8	82.99 1	97.44 7	89.07 14	96.63 4	94.88 15

test_241102_ONE					95.30 2	70.98 66		94.06 10	77.17 56	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 33	92.78 4	95.74 6	82.45 3	97.49 4	89.42 9	96.68 2	94.95 11

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 47	82.45 3	96.87 20	83.77 64	96.48 8	94.88 15

PC_three_1452									68.21 254	92.02 12	94.00 49	82.09 5	95.98 56	84.58 53	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 90	92.29 7	95.66 10	81.67 6	97.38 11	87.44 33	96.34 15	93.95 59
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 33	92.12 9	95.78 4	81.46 7	97.40 9	89.42 9	96.57 7	94.67 28

test_241102_TWO								94.06 10	77.24 53	92.78 4	95.72 8	81.26 8	97.44 7	89.07 14	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 50	92.12 9	95.78 4	80.98 9	97.40 9	89.08 12	96.41 12	93.33 91
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 50	92.81 3	95.79 3	80.98 9

test_one_0601					95.07 7	71.46 57		94.14 5	78.27 35	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 46	89.79 18	94.12 42	78.98 12	96.58 35	85.66 40	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 40	78.35 13	96.77 24	89.59 8	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 94	91.06 16	96.03 1	76.84 14	97.03 17	89.09 11	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 58	86.15 48	84.06 133	91.71 78	64.94 202	86.47 196	91.87 103	73.63 139	86.60 50	93.02 75	76.57 15	91.87 223	83.36 66	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 29	94.06 45	76.43 16	96.84 21	88.48 24	95.99 18	94.34 44

MCST-MVS		87.37 29	87.25 29	87.73 28	94.53 17	72.46 38	89.82 79	93.82 16	73.07 156	84.86 68	92.89 77	76.22 17	96.33 41	84.89 48	95.13 36	94.40 41

CSCG		86.41 45	86.19 46	87.07 45	92.91 61	72.48 37	90.81 58	93.56 24	73.95 131	83.16 100	91.07 125	75.94 18	95.19 82	79.94 103	94.38 56	93.55 83

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 33	94.27 35	75.89 19	96.81 23	87.45 32	96.44 9	93.05 106

TSAR-MVS + MP.		88.02 17	88.11 16	87.72 30	93.68 43	72.13 46	91.41 50	92.35 82	74.62 119	88.90 22	93.85 55	75.75 20	96.00 54	87.80 28	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 92	89.16 19	95.10 16	75.65 21	96.19 46	87.07 34	96.01 17	94.79 22

9.14			88.26 15		92.84 63		91.52 48	94.75 1	73.93 133	88.57 25	94.67 21	75.57 22	95.79 58	86.77 35	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 36	90.32 17	94.00 49	74.83 23	93.78 141	87.63 30	94.27 59	93.65 76
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 63	85.30 65	85.77 72	88.49 169	67.93 137	85.52 226	93.44 27	78.70 29	83.63 96	89.03 172	74.57 24	95.71 61	80.26 100	94.04 61	93.66 72
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 84	84.54 73	80.99 226	90.06 112	65.83 182	84.21 255	88.74 207	71.60 178	85.01 62	92.44 87	74.51 25	83.50 345	82.15 82	92.15 80	93.64 78

train_agg		86.43 43	86.20 45	87.13 44	93.26 52	72.96 25	88.75 120	91.89 101	68.69 246	85.00 63	93.10 70	74.43 26	95.41 73	84.97 45	95.71 25	93.02 108

test_8					93.13 54	72.57 35	88.68 125	91.84 105	68.69 246	84.87 67	93.10 70	74.43 26	95.16 83

TEST9					93.26 52	72.96 25	88.75 120	91.89 101	68.44 251	85.00 63	93.10 70	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	74.77 115	92.29 7	95.97 2	74.28 29	97.24 13	88.58 21	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							88.85 117		75.41 98	84.91 65	93.54 59	74.28 29		83.31 67	95.86 20

TSAR-MVS + GP.		85.71 57	85.33 63	86.84 50	91.34 81	72.50 36	89.07 110	87.28 237	76.41 77	85.80 54	90.22 144	74.15 31	95.37 78	81.82 84	91.88 83	92.65 120

ZD-MVS					94.38 25	72.22 44		92.67 67	70.98 191	87.75 35	94.07 44	74.01 32	96.70 27	84.66 52	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 28	94.80 19	73.76 33	97.11 15	87.51 31	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	73.01 158	88.58 24	94.52 23	73.36 34	96.49 38	84.26 57	95.01 37	92.70 116
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
casdiffmvs_mvg		85.99 48	86.09 50	85.70 74	87.65 209	67.22 159	88.69 124	93.04 41	79.64 18	85.33 59	92.54 86	73.30 35	94.50 112	83.49 65	91.14 95	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 52	85.87 54	86.04 67	89.84 117	69.44 98	90.45 68	93.00 46	76.70 72	88.01 31	91.23 117	73.28 36	93.91 135	81.50 86	88.80 128	94.77 24

canonicalmvs		85.91 52	85.87 54	86.04 67	89.84 117	69.44 98	90.45 68	93.00 46	76.70 72	88.01 31	91.23 117	73.28 36	93.91 135	81.50 86	88.80 128	94.77 24

segment_acmp												73.08 38

DPM-MVS		84.93 70	84.29 77	86.84 50	90.20 105	73.04 23	87.12 175	93.04 41	69.80 218	82.85 104	91.22 119	73.06 39	96.02 52	76.72 133	94.63 48	91.46 159

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 55	93.47 63	73.02 40	97.00 18	84.90 46	94.94 40	94.10 52

test_fmvsmconf_n		85.92 51	86.04 51	85.57 76	85.03 262	69.51 93	89.62 89	90.58 140	73.42 147	87.75 35	94.02 47	72.85 41	93.24 166	90.37 3	90.75 99	93.96 58

MGCFI-Net		85.06 69	85.51 59	83.70 147	89.42 130	63.01 243	89.43 93	92.62 73	76.43 76	87.53 38	91.34 115	72.82 42	93.42 161	81.28 89	88.74 131	94.66 31

nrg030		83.88 79	83.53 83	84.96 92	86.77 231	69.28 102	90.46 67	92.67 67	74.79 114	82.95 101	91.33 116	72.70 43	93.09 180	80.79 96	79.28 259	92.50 125

CDPH-MVS		85.76 56	85.29 66	87.17 43	93.49 47	71.08 64	88.58 128	92.42 80	68.32 253	84.61 74	93.48 61	72.32 44	96.15 48	79.00 106	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 42	83.84 90	94.40 32	72.24 45	96.28 43	85.65 41	95.30 35	93.62 79
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffmvs		85.11 67	85.14 67	85.01 90	87.20 223	65.77 185	87.75 157	92.83 60	77.84 37	84.36 80	92.38 88	72.15 46	93.93 134	81.27 90	90.48 102	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 38	87.69 33	91.16 84	72.32 43	90.31 71	93.94 14	77.12 58	82.82 105	94.23 38	72.13 47	97.09 16	84.83 49	95.37 31	93.65 76
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 74	84.54 73	84.27 119	85.42 252	68.81 109	88.49 130	87.26 238	68.08 255	88.03 30	93.49 60	72.04 48	91.77 225	88.90 17	89.14 124	92.24 136

MVSMamba_PlusPlus		85.99 48	85.96 52	86.05 66	91.09 85	67.64 144	89.63 88	92.65 70	72.89 161	84.64 73	91.71 101	71.85 49	96.03 50	84.77 51	94.45 54	94.49 37

baseline		84.93 70	84.98 68	84.80 100	87.30 221	65.39 193	87.30 171	92.88 57	77.62 40	84.04 86	92.26 90	71.81 50	93.96 128	81.31 88	90.30 105	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 66	85.24 60	94.32 33	71.76 51	96.93 19	85.53 43	95.79 22	94.32 45

test_fmvsmconf0.1_n		85.61 59	85.65 57	85.50 77	82.99 309	69.39 100	89.65 86	90.29 153	73.31 150	87.77 34	94.15 41	71.72 52	93.23 167	90.31 4	90.67 101	93.89 63

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 41	94.97 18	71.70 53	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		82.71 107		71.67 54	96.16 47		94.50 51	93.54 84

UniMVSNet_NR-MVSNet		81.88 116	81.54 116	82.92 178	88.46 171	63.46 233	87.13 174	92.37 81	80.19 12	78.38 163	89.14 168	71.66 55	93.05 182	70.05 196	76.46 290	92.25 134

CS-MVS		86.69 39	86.95 35	85.90 71	90.76 96	67.57 147	92.83 17	93.30 32	79.67 17	84.57 76	92.27 89	71.47 56	95.02 93	84.24 59	93.46 67	95.13 8

DeepC-MVS_fast	79.65 3	86.91 36	86.62 40	87.76 27	93.52 46	72.37 41	91.26 51	93.04 41	76.62 74	84.22 81	93.36 66	71.44 57	96.76 25	80.82 94	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 65	85.34 62	85.13 87	86.12 241	69.93 86	88.65 126	90.78 136	69.97 214	88.27 26	93.98 52	71.39 58	91.54 235	88.49 23	90.45 103	93.91 60

MVS_111021_HR		85.14 66	84.75 71	86.32 58	91.65 79	72.70 30	85.98 209	90.33 150	76.11 86	82.08 111	91.61 107	71.36 59	94.17 124	81.02 91	92.58 75	92.08 142

balanced_conf03		86.78 37	86.99 33	86.15 63	91.24 83	67.61 145	90.51 62	92.90 56	77.26 52	87.44 40	91.63 105	71.27 60	96.06 49	85.62 42	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	74.98 108	88.96 20	95.54 12	71.20 61	96.54 36	86.28 37	93.49 65	93.06 104

our_new_method		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 108	88.96 20	95.54 12	71.20 61	96.54 36	86.28 37	93.49 65	93.06 104

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 84	88.14 27	95.09 17	71.06 63	96.67 29	87.67 29	96.37 14	94.09 53

fmvsm_l_conf0.5_n_a		84.13 77	84.16 78	84.06 133	85.38 253	68.40 125	88.34 137	86.85 248	67.48 262	87.48 39	93.40 64	70.89 64	91.61 229	88.38 25	89.22 122	92.16 140

MP-MVS-pluss		87.67 21	87.72 20	87.54 36	93.64 44	72.04 48	89.80 81	93.50 25	75.17 105	86.34 51	95.29 15	70.86 65	96.00 54	88.78 19	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 68	84.91 65	94.44 30	70.78 66	96.61 32	84.53 54	94.89 42	93.66 72

EI-MVSNet-Vis-set		84.19 76	83.81 80	85.31 81	88.18 180	67.85 138	87.66 159	89.73 168	80.05 14	82.95 101	89.59 157	70.74 67	94.82 101	80.66 97	84.72 181	93.28 93

GST-MVS		87.42 27	87.26 28	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 64	84.68 69	93.99 51	70.67 68	96.82 22	84.18 61	95.01 37	93.90 62

SPE-MVS-test		86.29 46	86.48 41	85.71 73	91.02 88	67.21 160	92.36 29	93.78 18	78.97 28	83.51 97	91.20 120	70.65 69	95.15 84	81.96 83	94.89 42	94.77 24

CANet		86.45 42	86.10 49	87.51 37	90.09 107	70.94 70	89.70 85	92.59 74	81.78 4	81.32 121	91.43 113	70.34 70	97.23 14	84.26 57	93.36 68	94.37 42

alignmvs		85.48 60	85.32 64	85.96 70	89.51 126	69.47 95	89.74 83	92.47 76	76.17 85	87.73 37	91.46 112	70.32 71	93.78 141	81.51 85	88.95 125	94.63 32

reproduce_model		87.28 30	87.39 27	86.95 48	93.10 56	71.24 63	91.60 42	93.19 35	74.69 116	88.80 23	95.61 11	70.29 72	96.44 39	86.20 39	93.08 69	93.16 99

EI-MVSNet-UG-set		83.81 80	83.38 86	85.09 88	87.87 197	67.53 148	87.44 167	89.66 169	79.74 16	82.23 110	89.41 166	70.24 73	94.74 104	79.95 102	83.92 195	92.99 111

MVS_Test		83.15 97	83.06 91	83.41 156	86.86 227	63.21 239	86.11 207	92.00 95	74.31 124	82.87 103	89.44 165	70.03 74	93.21 169	77.39 124	88.50 136	93.81 67

FC-MVSNet-test		81.52 125	82.02 110	80.03 246	88.42 174	55.97 336	87.95 150	93.42 29	77.10 59	77.38 184	90.98 132	69.96 75	91.79 224	68.46 215	84.50 184	92.33 130

FIs		82.07 113	82.42 100	81.04 225	88.80 158	58.34 297	88.26 140	93.49 26	76.93 63	78.47 162	91.04 126	69.92 76	92.34 206	69.87 200	84.97 178	92.44 129

UniMVSNet (Re)		81.60 124	81.11 121	83.09 169	88.38 175	64.41 214	87.60 160	93.02 45	78.42 32	78.56 159	88.16 197	69.78 77	93.26 165	69.58 203	76.49 289	91.60 150

HPM-MVS		87.11 33	86.98 34	87.50 38	93.88 39	72.16 45	92.19 33	93.33 31	76.07 87	83.81 91	93.95 54	69.77 78	96.01 53	85.15 44	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 87	83.08 90	85.24 83	88.38 175	67.45 149	88.89 115	89.15 189	75.50 97	82.27 109	88.28 193	69.61 79	94.45 114	77.81 119	87.84 141	93.84 66

PHI-MVS		86.43 43	86.17 47	87.24 41	90.88 92	70.96 68	92.27 32	94.07 9	72.45 163	85.22 61	91.90 96	69.47 80	96.42 40	83.28 68	95.94 19	94.35 43

UA-Net		85.08 68	84.96 69	85.45 78	92.07 73	68.07 134	89.78 82	90.86 135	82.48 2	84.60 75	93.20 69	69.35 81	95.22 81	71.39 183	90.88 98	93.07 103

ETV-MVS		84.90 72	84.67 72	85.59 75	89.39 133	68.66 120	88.74 122	92.64 72	79.97 15	84.10 84	85.71 261	69.32 82	95.38 75	80.82 94	91.37 92	92.72 115

旧先验1					91.96 74	65.79 184		86.37 255			93.08 74	69.31 83			92.74 73	88.74 263

fmvsm_s_conf0.5_n_a		83.63 86	83.41 85	84.28 117	86.14 240	68.12 132	89.43 93	82.87 308	70.27 207	87.27 43	93.80 57	69.09 84	91.58 231	88.21 26	83.65 203	93.14 101

region2R		87.42 27	87.20 31	88.09 14	94.63 14	73.55 13	93.03 14	93.12 40	76.73 71	84.45 77	94.52 23	69.09 84	96.70 27	84.37 56	94.83 45	94.03 56

EIA-MVS		83.31 96	82.80 97	84.82 98	89.59 122	65.59 188	88.21 141	92.68 66	74.66 118	78.96 149	86.42 248	69.06 86	95.26 80	75.54 145	90.09 109	93.62 79

EPP-MVSNet		83.40 93	83.02 92	84.57 104	90.13 106	64.47 212	92.32 30	90.73 137	74.45 123	79.35 145	91.10 123	69.05 87	95.12 85	72.78 172	87.22 149	94.13 51

EC-MVSNet		86.01 47	86.38 42	84.91 96	89.31 138	66.27 173	92.32 30	93.63 21	79.37 20	84.17 83	91.88 97	69.04 88	95.43 70	83.93 63	93.77 63	93.01 109

fmvsm_s_conf0.5_n		83.80 81	83.71 81	84.07 131	86.69 233	67.31 154	89.46 92	83.07 303	71.09 188	86.96 47	93.70 58	69.02 89	91.47 240	88.79 18	84.62 183	93.44 87

ACMMPR		87.44 25	87.23 30	88.08 15	94.64 13	73.59 12	93.04 12	93.20 34	76.78 68	84.66 72	94.52 23	68.81 90	96.65 30	84.53 54	94.90 41	94.00 57

test_fmvsmvis_n_1920		84.02 78	83.87 79	84.49 108	84.12 278	69.37 101	88.15 145	87.96 221	70.01 212	83.95 88	93.23 68	68.80 91	91.51 238	88.61 20	89.96 112	92.57 121

mvs_anonymous		79.42 173	79.11 162	80.34 240	84.45 273	57.97 303	82.59 282	87.62 230	67.40 263	76.17 218	88.56 186	68.47 92	89.59 278	70.65 191	86.05 168	93.47 86

fmvsm_s_conf0.1_n		83.56 88	83.38 86	84.10 125	84.86 264	67.28 155	89.40 97	83.01 304	70.67 196	87.08 44	93.96 53	68.38 93	91.45 241	88.56 22	84.50 184	93.56 82

fmvsm_s_conf0.1_n_a		83.32 95	82.99 93	84.28 117	83.79 286	68.07 134	89.34 100	82.85 309	69.80 218	87.36 42	94.06 45	68.34 94	91.56 233	87.95 27	83.46 208	93.21 97

MVS_0304		87.69 20	87.55 24	88.12 13	89.45 129	71.76 51	91.47 49	89.54 173	82.14 3	86.65 49	94.28 34	68.28 95	97.46 6	90.81 2	95.31 34	95.15 7

MTAPA		87.23 31	87.00 32	87.90 22	94.18 35	74.25 5	86.58 193	92.02 93	79.45 19	85.88 53	94.80 19	68.07 96	96.21 45	86.69 36	95.34 32	93.23 94

mamv4		76.81 234	78.23 182	72.54 344	86.12 241	65.75 186	78.76 335	82.07 317	64.12 304	72.97 276	91.02 129	67.97 97	68.08 408	83.04 71	78.02 271	83.80 354

CP-MVS		87.11 33	86.92 36	87.68 34	94.20 34	73.86 7	93.98 3	92.82 63	76.62 74	83.68 93	94.46 27	67.93 98	95.95 57	84.20 60	94.39 55	93.23 94

PAPM_NR		83.02 101	82.41 101	84.82 98	92.47 70	66.37 171	87.93 152	91.80 106	73.82 135	77.32 186	90.66 135	67.90 99	94.90 97	70.37 193	89.48 119	93.19 98

PGM-MVS		86.68 40	86.27 44	87.90 22	94.22 33	73.38 18	90.22 73	93.04 41	75.53 96	83.86 89	94.42 31	67.87 100	96.64 31	82.70 79	94.57 50	93.66 72

PAPR		81.66 123	80.89 126	83.99 141	90.27 103	64.00 220	86.76 189	91.77 109	68.84 244	77.13 196	89.50 158	67.63 101	94.88 99	67.55 221	88.52 135	93.09 102

Fast-Effi-MVS+		80.81 138	79.92 141	83.47 152	88.85 153	64.51 209	85.53 224	89.39 178	70.79 193	78.49 161	85.06 279	67.54 102	93.58 149	67.03 229	86.58 158	92.32 131

XVS		87.18 32	86.91 37	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 21	83.67 94	94.17 39	67.45 103	96.60 33	83.06 69	94.50 51	94.07 54

X-MVStestdata		80.37 154	77.83 190	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 21	83.67 94	12.47 420	67.45 103	96.60 33	83.06 69	94.50 51	94.07 54

SR-MVS		86.73 38	86.67 39	86.91 49	94.11 37	72.11 47	92.37 28	92.56 75	74.50 120	86.84 48	94.65 22	67.31 105	95.77 59	84.80 50	92.85 72	92.84 114

NR-MVSNet		80.23 156	79.38 153	82.78 187	87.80 201	63.34 236	86.31 201	91.09 129	79.01 26	72.17 288	89.07 170	67.20 106	92.81 191	66.08 235	75.65 303	92.20 137

MSLP-MVS++		85.43 62	85.76 56	84.45 109	91.93 75	70.24 79	90.71 59	92.86 58	77.46 48	84.22 81	92.81 81	67.16 107	92.94 186	80.36 98	94.35 57	90.16 203

MG-MVS		83.41 92	83.45 84	83.28 159	92.74 65	62.28 255	88.17 143	89.50 175	75.22 101	81.49 120	92.74 85	66.75 108	95.11 87	72.85 171	91.58 89	92.45 128

test_fmvsmconf0.01_n		84.73 73	84.52 75	85.34 80	80.25 350	69.03 103	89.47 91	89.65 170	73.24 154	86.98 46	94.27 35	66.62 109	93.23 167	90.26 5	89.95 113	93.78 69

EI-MVSNet		80.52 150	79.98 140	82.12 197	84.28 274	63.19 241	86.41 197	88.95 199	74.18 128	78.69 154	87.54 213	66.62 109	92.43 200	72.57 175	80.57 243	90.74 181

IterMVS-LS		80.06 159	79.38 153	82.11 198	85.89 244	63.20 240	86.79 186	89.34 179	74.19 127	75.45 231	86.72 233	66.62 109	92.39 202	72.58 174	76.86 284	90.75 180
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		78.59 195	77.76 195	81.08 224	82.66 316	61.56 264	83.65 264	89.15 189	68.87 243	75.55 227	83.79 305	66.49 112	92.03 215	73.25 167	76.39 292	89.64 230

mPP-MVS		86.67 41	86.32 43	87.72 30	94.41 22	73.55 13	92.74 20	92.22 88	76.87 65	82.81 106	94.25 37	66.44 113	96.24 44	82.88 74	94.28 58	93.38 88

c3_l		78.75 189	77.91 187	81.26 218	82.89 311	61.56 264	84.09 258	89.13 191	69.97 214	75.56 226	84.29 294	66.36 114	92.09 214	73.47 164	75.48 307	90.12 206

GeoE		81.71 120	81.01 124	83.80 146	89.51 126	64.45 213	88.97 112	88.73 208	71.27 184	78.63 157	89.76 151	66.32 115	93.20 172	69.89 199	86.02 169	93.74 70

WR-MVS_H		78.51 196	78.49 172	78.56 274	88.02 190	56.38 330	88.43 131	92.67 67	77.14 57	73.89 265	87.55 212	66.25 116	89.24 285	58.92 297	73.55 333	90.06 213

PCF-MVS	73.52 7	80.38 152	78.84 167	85.01 90	87.71 206	68.99 106	83.65 264	91.46 119	63.00 317	77.77 178	90.28 140	66.10 117	95.09 91	61.40 276	88.22 139	90.94 174
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EPNet		83.72 83	82.92 95	86.14 65	84.22 276	69.48 94	91.05 56	85.27 268	81.30 6	76.83 198	91.65 103	66.09 118	95.56 63	76.00 139	93.85 62	93.38 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM1				84.35 113	93.01 60	68.79 110		92.44 77	63.96 310	81.09 126	91.57 108	66.06 119	95.45 68	67.19 226	94.82 46	88.81 258

PVSNet_BlendedMVS		80.60 146	80.02 139	82.36 196	88.85 153	65.40 191	86.16 206	92.00 95	69.34 228	78.11 170	86.09 256	66.02 120	94.27 118	71.52 180	82.06 225	87.39 290

PVSNet_Blended		80.98 133	80.34 134	82.90 179	88.85 153	65.40 191	84.43 250	92.00 95	67.62 259	78.11 170	85.05 280	66.02 120	94.27 118	71.52 180	89.50 118	89.01 248

diffmvs		82.10 111	81.88 113	82.76 189	83.00 307	63.78 225	83.68 263	89.76 166	72.94 159	82.02 112	89.85 149	65.96 122	90.79 259	82.38 81	87.30 148	93.71 71
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 50	85.88 53	86.22 60	92.69 66	69.53 92	91.93 37	92.99 49	73.54 143	85.94 52	94.51 26	65.80 123	95.61 62	83.04 71	92.51 76	93.53 85

miper_enhance_ethall		77.87 214	76.86 214	80.92 229	81.65 330	61.38 266	82.68 281	88.98 196	65.52 287	75.47 228	82.30 332	65.76 124	92.00 217	72.95 170	76.39 292	89.39 236

PVSNet_Blended_VisFu		82.62 105	81.83 114	84.96 92	90.80 94	69.76 90	88.74 122	91.70 110	69.39 226	78.96 149	88.46 188	65.47 125	94.87 100	74.42 154	88.57 133	90.24 201

API-MVS		81.99 115	81.23 119	84.26 121	90.94 90	70.18 85	91.10 55	89.32 180	71.51 180	78.66 156	88.28 193	65.26 126	95.10 90	64.74 246	91.23 94	87.51 288

TranMVSNet+NR-MVSNet		80.84 136	80.31 135	82.42 194	87.85 198	62.33 253	87.74 158	91.33 120	80.55 9	77.99 174	89.86 148	65.23 127	92.62 192	67.05 228	75.24 317	92.30 132

IS-MVSNet		83.15 97	82.81 96	84.18 123	89.94 115	63.30 237	91.59 43	88.46 213	79.04 25	79.49 143	92.16 91	65.10 128	94.28 117	67.71 219	91.86 86	94.95 11

DU-MVS		81.12 132	80.52 131	82.90 179	87.80 201	63.46 233	87.02 178	91.87 103	79.01 26	78.38 163	89.07 170	65.02 129	93.05 182	70.05 196	76.46 290	92.20 137

Baseline_NR-MVSNet		78.15 205	78.33 178	77.61 292	85.79 245	56.21 334	86.78 187	85.76 264	73.60 141	77.93 175	87.57 210	65.02 129	88.99 289	67.14 227	75.33 314	87.63 284

SR-MVS-dyc-post		85.77 55	85.61 58	86.23 59	93.06 58	70.63 76	91.88 38	92.27 84	73.53 144	85.69 56	94.45 28	65.00 131	95.56 63	82.75 75	91.87 84	92.50 125

VNet		82.21 110	82.41 101	81.62 207	90.82 93	60.93 270	84.47 246	89.78 165	76.36 82	84.07 85	91.88 97	64.71 132	90.26 265	70.68 190	88.89 126	93.66 72

Test By Simon												64.33 133

ACMMP		85.89 54	85.39 61	87.38 39	93.59 45	72.63 33	92.74 20	93.18 39	76.78 68	80.73 130	93.82 56	64.33 133	96.29 42	82.67 80	90.69 100	93.23 94
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		83.11 100	82.09 108	86.15 63	94.44 19	70.92 71	88.79 118	92.20 89	70.53 201	79.17 147	91.03 128	64.12 135	96.03 50	68.39 216	90.14 108	91.50 155

CLD-MVS		82.31 109	81.65 115	84.29 116	88.47 170	67.73 142	85.81 217	92.35 82	75.78 91	78.33 165	86.58 243	64.01 136	94.35 115	76.05 138	87.48 146	90.79 177
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 60		93.06 58	70.63 76	91.88 38	92.27 84	73.53 144	85.69 56	94.45 28	63.87 137		82.75 75	91.87 84	92.50 125

MVS		78.19 204	76.99 212	81.78 204	85.66 247	66.99 162	84.66 240	90.47 144	55.08 377	72.02 290	85.27 272	63.83 138	94.11 126	66.10 234	89.80 115	84.24 347

WR-MVS		79.49 169	79.22 160	80.27 242	88.79 159	58.35 296	85.06 232	88.61 211	78.56 30	77.65 179	88.34 191	63.81 139	90.66 262	64.98 244	77.22 279	91.80 148

VPA-MVSNet		80.60 146	80.55 130	80.76 232	88.07 188	60.80 273	86.86 183	91.58 113	75.67 95	80.24 134	89.45 164	63.34 140	90.25 266	70.51 192	79.22 260	91.23 163

新几何1				83.42 154	93.13 54	70.71 74		85.48 267	57.43 367	81.80 116	91.98 94	63.28 141	92.27 208	64.60 247	92.99 70	87.27 294

HY-MVS	69.67 12	77.95 211	77.15 208	80.36 239	87.57 214	60.21 283	83.37 271	87.78 228	66.11 278	75.37 235	87.06 228	63.27 142	90.48 264	61.38 277	82.43 221	90.40 195

XXY-MVS		75.41 259	75.56 237	74.96 321	83.59 291	57.82 307	80.59 309	83.87 288	66.54 275	74.93 252	88.31 192	63.24 143	80.09 363	62.16 268	76.85 285	86.97 303

ab-mvs		79.51 168	78.97 165	81.14 222	88.46 171	60.91 271	83.84 260	89.24 185	70.36 203	79.03 148	88.87 176	63.23 144	90.21 267	65.12 242	82.57 220	92.28 133

xiu_mvs_v2_base		81.69 121	81.05 122	83.60 149	89.15 145	68.03 136	84.46 248	90.02 159	70.67 196	81.30 124	86.53 246	63.17 145	94.19 123	75.60 144	88.54 134	88.57 267

pcd_1.5k_mvsjas		5.26 394	7.02 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	63.15 146	0.00 427	0.00 426	0.00 425	0.00 423

PS-MVSNAJss		82.07 113	81.31 117	84.34 114	86.51 236	67.27 156	89.27 101	91.51 115	71.75 173	79.37 144	90.22 144	63.15 146	94.27 118	77.69 120	82.36 222	91.49 156

PS-MVSNAJ		81.69 121	81.02 123	83.70 147	89.51 126	68.21 131	84.28 254	90.09 158	70.79 193	81.26 125	85.62 266	63.15 146	94.29 116	75.62 143	88.87 127	88.59 266

WTY-MVS		75.65 254	75.68 234	75.57 312	86.40 237	56.82 321	77.92 348	82.40 313	65.10 291	76.18 216	87.72 205	63.13 149	80.90 360	60.31 284	81.96 226	89.00 250

TransMVSNet (Re)		75.39 261	74.56 252	77.86 286	85.50 251	57.10 318	86.78 187	86.09 261	72.17 169	71.53 295	87.34 216	63.01 150	89.31 283	56.84 319	61.83 380	87.17 296

v8		79.97 162	79.02 164	82.80 184	84.09 279	64.50 211	87.96 149	90.29 153	74.13 130	75.24 243	86.81 230	62.88 151	93.89 138	74.39 155	75.40 312	90.00 215

HPM-MVS_fast		85.35 64	84.95 70	86.57 56	93.69 42	70.58 78	92.15 35	91.62 111	73.89 134	82.67 108	94.09 43	62.60 152	95.54 65	80.93 92	92.93 71	93.57 81

PAPM		77.68 220	76.40 227	81.51 210	87.29 222	61.85 260	83.78 261	89.59 172	64.74 296	71.23 297	88.70 179	62.59 153	93.66 148	52.66 339	87.03 152	89.01 248

1112_ss		77.40 225	76.43 226	80.32 241	89.11 150	60.41 280	83.65 264	87.72 229	62.13 330	73.05 275	86.72 233	62.58 154	89.97 271	62.11 270	80.80 239	90.59 187

LCM-MVSNet-Re		77.05 229	76.94 213	77.36 296	87.20 223	51.60 375	80.06 316	80.46 335	75.20 102	67.69 332	86.72 233	62.48 155	88.98 290	63.44 254	89.25 121	91.51 154

v148		78.72 191	77.80 192	81.47 211	82.73 314	61.96 259	86.30 202	88.08 218	73.26 152	76.18 216	85.47 269	62.46 156	92.36 204	71.92 179	73.82 331	90.09 209

baseline1		76.98 231	76.75 220	77.66 290	88.13 184	55.66 341	85.12 230	81.89 318	73.04 157	76.79 199	88.90 174	62.43 157	87.78 308	63.30 256	71.18 351	89.55 233

MAR-MVS		81.84 117	80.70 127	85.27 82	91.32 82	71.53 56	89.82 79	90.92 131	69.77 220	78.50 160	86.21 252	62.36 158	94.52 111	65.36 240	92.05 82	89.77 227
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		82.61 106	82.11 106	84.11 124	88.82 156	71.58 55	85.15 229	86.16 259	74.69 116	80.47 132	91.04 126	62.29 159	90.55 263	80.33 99	90.08 110	90.20 202

TAMVS		78.89 188	77.51 202	83.03 173	87.80 201	67.79 141	84.72 239	85.05 272	67.63 258	76.75 201	87.70 206	62.25 160	90.82 258	58.53 302	87.13 150	90.49 191

CP-MVSNet		78.22 201	78.34 177	77.84 287	87.83 200	54.54 353	87.94 151	91.17 125	77.65 39	73.48 270	88.49 187	62.24 161	88.43 300	62.19 267	74.07 326	90.55 188

OMC-MVS		82.69 104	81.97 112	84.85 97	88.75 161	67.42 150	87.98 148	90.87 134	74.92 110	79.72 140	91.65 103	62.19 162	93.96 128	75.26 149	86.42 161	93.16 99

cl____		77.72 217	76.76 218	80.58 235	82.49 320	60.48 278	83.09 276	87.87 224	69.22 232	74.38 262	85.22 275	62.10 163	91.53 236	71.09 185	75.41 311	89.73 229

DIV-MVS_self_test		77.72 217	76.76 218	80.58 235	82.48 321	60.48 278	83.09 276	87.86 225	69.22 232	74.38 262	85.24 273	62.10 163	91.53 236	71.09 185	75.40 312	89.74 228

testdata				79.97 247	90.90 91	64.21 217		84.71 274	59.27 351	85.40 58	92.91 76	62.02 165	89.08 288	68.95 209	91.37 92	86.63 311

eth_miper_zixun_eth		77.92 212	76.69 221	81.61 209	83.00 307	61.98 258	83.15 274	89.20 187	69.52 225	74.86 253	84.35 293	61.76 166	92.56 195	71.50 182	72.89 339	90.28 200

MVSFormer		82.85 103	82.05 109	85.24 83	87.35 215	70.21 80	90.50 64	90.38 146	68.55 248	81.32 121	89.47 160	61.68 167	93.46 158	78.98 107	90.26 106	92.05 143

lupinMVS		81.39 128	80.27 137	84.76 101	87.35 215	70.21 80	85.55 222	86.41 253	62.85 320	81.32 121	88.61 183	61.68 167	92.24 210	78.41 114	90.26 106	91.83 146

cdsmvs_eth3d_5k		19.96 388	26.61 390	0.00 408	0.00 431	0.00 433	0.00 419	89.26 184	0.00 426	0.00 427	88.61 183	61.62 169	0.00 427	0.00 426	0.00 425	0.00 423

h-mvs33		83.15 97	82.19 105	86.02 69	90.56 98	70.85 73	88.15 145	89.16 188	76.02 88	84.67 70	91.39 114	61.54 170	95.50 66	82.71 77	75.48 307	91.72 149

hse-mvs2		81.72 119	80.94 125	84.07 131	88.72 162	67.68 143	85.87 213	87.26 238	76.02 88	84.67 70	88.22 196	61.54 170	93.48 156	82.71 77	73.44 335	91.06 168

CDS-MVSNet		79.07 183	77.70 197	83.17 166	87.60 210	68.23 130	84.40 252	86.20 258	67.49 261	76.36 211	86.54 245	61.54 170	90.79 259	61.86 272	87.33 147	90.49 191
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v10		79.74 164	78.67 168	82.97 177	84.06 280	64.95 201	87.88 155	90.62 139	73.11 155	75.11 247	86.56 244	61.46 173	94.05 127	73.68 160	75.55 305	89.90 221

v1144		80.03 160	79.03 163	83.01 174	83.78 287	64.51 209	87.11 176	90.57 142	71.96 172	78.08 172	86.20 253	61.41 174	93.94 131	74.93 150	77.23 278	90.60 186

cl22		78.07 207	77.01 210	81.23 219	82.37 323	61.83 261	83.55 268	87.98 220	68.96 242	75.06 249	83.87 301	61.40 175	91.88 222	73.53 162	76.39 292	89.98 218

BH-w/o		78.21 202	77.33 206	80.84 230	88.81 157	65.13 198	84.87 236	87.85 226	69.75 221	74.52 259	84.74 286	61.34 176	93.11 179	58.24 306	85.84 172	84.27 346

Test_1112_low_res		76.40 244	75.44 239	79.27 261	89.28 140	58.09 299	81.69 291	87.07 242	59.53 349	72.48 283	86.67 238	61.30 177	89.33 282	60.81 282	80.15 248	90.41 194

Vis-MVSNet (Re-imp)		78.36 199	78.45 173	78.07 285	88.64 165	51.78 374	86.70 190	79.63 345	74.14 129	75.11 247	90.83 133	61.29 178	89.75 275	58.10 307	91.60 88	92.69 118

PEN-MVS		77.73 216	77.69 198	77.84 287	87.07 226	53.91 358	87.91 153	91.18 124	77.56 44	73.14 274	88.82 177	61.23 179	89.17 286	59.95 286	72.37 341	90.43 193

pm-mvs1		77.25 228	76.68 222	78.93 267	84.22 276	58.62 294	86.41 197	88.36 214	71.37 182	73.31 271	88.01 203	61.22 180	89.15 287	64.24 250	73.01 338	89.03 247

BH-untuned		79.47 170	78.60 170	82.05 199	89.19 144	65.91 180	86.07 208	88.52 212	72.18 168	75.42 232	87.69 207	61.15 181	93.54 153	60.38 283	86.83 155	86.70 309

v2v482		80.23 156	79.29 157	83.05 172	83.62 290	64.14 218	87.04 177	89.97 161	73.61 140	78.18 169	87.22 221	61.10 182	93.82 139	76.11 136	76.78 287	91.18 164

jason		81.39 128	80.29 136	84.70 102	86.63 235	69.90 88	85.95 210	86.77 249	63.24 313	81.07 127	89.47 160	61.08 183	92.15 212	78.33 115	90.07 111	92.05 143
jason: jason.
Vis-MVSNet		83.46 91	82.80 97	85.43 79	90.25 104	68.74 114	90.30 72	90.13 157	76.33 83	80.87 129	92.89 77	61.00 184	94.20 122	72.45 177	90.97 96	93.35 90
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAPA-MVS	73.13 9	79.15 180	77.94 186	82.79 186	89.59 122	62.99 247	88.16 144	91.51 115	65.77 283	77.14 195	91.09 124	60.91 185	93.21 169	50.26 354	87.05 151	92.17 139
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PS-CasMVS		78.01 210	78.09 183	77.77 289	87.71 206	54.39 355	88.02 147	91.22 122	77.50 47	73.26 272	88.64 182	60.73 186	88.41 301	61.88 271	73.88 330	90.53 189

OPM-MVS		83.50 90	82.95 94	85.14 85	88.79 159	70.95 69	89.13 108	91.52 114	77.55 45	80.96 128	91.75 100	60.71 187	94.50 112	79.67 105	86.51 160	89.97 219
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XVG-OURS-SEG-HR		80.81 138	79.76 145	83.96 143	85.60 249	68.78 111	83.54 269	90.50 143	70.66 199	76.71 202	91.66 102	60.69 188	91.26 246	76.94 129	81.58 230	91.83 146

v144192		79.47 170	78.37 176	82.78 187	83.35 295	63.96 221	86.96 179	90.36 149	69.99 213	77.50 181	85.67 264	60.66 189	93.77 143	74.27 156	76.58 288	90.62 184

V42		79.38 176	78.24 180	82.83 181	81.10 342	65.50 190	85.55 222	89.82 164	71.57 179	78.21 167	86.12 255	60.66 189	93.18 175	75.64 142	75.46 309	89.81 226

SDMVSNet		80.38 152	80.18 138	80.99 226	89.03 151	64.94 202	80.45 312	89.40 177	75.19 103	76.61 206	89.98 146	60.61 191	87.69 309	76.83 131	83.55 205	90.33 197

CPTT-MVS		83.73 82	83.33 88	84.92 95	93.28 49	70.86 72	92.09 36	90.38 146	68.75 245	79.57 142	92.83 79	60.60 192	93.04 184	80.92 93	91.56 90	90.86 176

DTE-MVSNet		76.99 230	76.80 216	77.54 295	86.24 238	53.06 367	87.52 162	90.66 138	77.08 60	72.50 282	88.67 181	60.48 193	89.52 279	57.33 314	70.74 353	90.05 214

HQP_MVS		83.64 85	83.14 89	85.14 85	90.08 108	68.71 116	91.25 52	92.44 77	79.12 23	78.92 151	91.00 130	60.42 194	95.38 75	78.71 110	86.32 162	91.33 160

plane_prior6					89.84 117	68.70 118						60.42 194

3Dnovator+	77.84 4	85.48 60	84.47 76	88.51 7	91.08 86	73.49 16	93.18 11	93.78 18	80.79 8	76.66 203	93.37 65	60.40 196	96.75 26	77.20 125	93.73 64	95.29 5

HQP2-MVS												60.17 197

HQP-MVS		82.61 106	82.02 110	84.37 111	89.33 135	66.98 163	89.17 103	92.19 90	76.41 77	77.23 189	90.23 143	60.17 197	95.11 87	77.47 122	85.99 170	91.03 170

VPNet		78.69 192	78.66 169	78.76 269	88.31 177	55.72 340	84.45 249	86.63 251	76.79 67	78.26 166	90.55 137	59.30 199	89.70 277	66.63 230	77.05 281	90.88 175

v1192		79.59 167	78.43 175	83.07 171	83.55 292	64.52 208	86.93 181	90.58 140	70.83 192	77.78 177	85.90 257	59.15 200	93.94 131	73.96 159	77.19 280	90.76 179

test222					91.50 80	68.26 129	84.16 256	83.20 301	54.63 378	79.74 139	91.63 105	58.97 201			91.42 91	86.77 307

CHOSEN 1792x2688		77.63 221	75.69 233	83.44 153	89.98 114	68.58 122	78.70 336	87.50 233	56.38 372	75.80 223	86.84 229	58.67 202	91.40 243	61.58 275	85.75 174	90.34 196

3Dnovator	76.31 5	83.38 94	82.31 104	86.59 55	87.94 194	72.94 28	90.64 60	92.14 92	77.21 55	75.47 228	92.83 79	58.56 203	94.72 105	73.24 168	92.71 74	92.13 141

v1921920		79.22 178	78.03 184	82.80 184	83.30 297	63.94 222	86.80 185	90.33 150	69.91 216	77.48 182	85.53 267	58.44 204	93.75 145	73.60 161	76.85 285	90.71 182

FA-MVS(test-final)		80.96 134	79.91 142	84.10 125	88.30 178	65.01 200	84.55 245	90.01 160	73.25 153	79.61 141	87.57 210	58.35 205	94.72 105	71.29 184	86.25 164	92.56 122

114514_t		80.68 144	79.51 150	84.20 122	94.09 38	67.27 156	89.64 87	91.11 128	58.75 357	74.08 264	90.72 134	58.10 206	95.04 92	69.70 201	89.42 120	90.30 199

v7n		78.97 186	77.58 201	83.14 167	83.45 294	65.51 189	88.32 138	91.21 123	73.69 138	72.41 284	86.32 251	57.93 207	93.81 140	69.18 206	75.65 303	90.11 207

CL-MVSNet_self_test		72.37 293	71.46 288	75.09 320	79.49 363	53.53 360	80.76 305	85.01 273	69.12 236	70.51 301	82.05 336	57.92 208	84.13 340	52.27 341	66.00 372	87.60 285

baseline2		75.70 253	73.83 264	81.30 217	83.26 298	61.79 262	82.57 283	80.65 331	66.81 265	66.88 341	83.42 313	57.86 209	92.19 211	63.47 253	79.57 253	89.91 220

QAPM		80.88 135	79.50 151	85.03 89	88.01 192	68.97 107	91.59 43	92.00 95	66.63 274	75.15 246	92.16 91	57.70 210	95.45 68	63.52 252	88.76 130	90.66 183

HyFIR lowres test		77.53 222	75.40 241	83.94 144	89.59 122	66.62 167	80.36 313	88.64 210	56.29 373	76.45 208	85.17 276	57.64 211	93.28 164	61.34 278	83.10 213	91.91 145

CNLPA		78.08 206	76.79 217	81.97 202	90.40 102	71.07 65	87.59 161	84.55 277	66.03 281	72.38 285	89.64 154	57.56 212	86.04 322	59.61 290	83.35 209	88.79 259

test_yl		81.17 130	80.47 132	83.24 162	89.13 146	63.62 226	86.21 204	89.95 162	72.43 166	81.78 117	89.61 155	57.50 213	93.58 149	70.75 188	86.90 153	92.52 123

DCV-MVSNet		81.17 130	80.47 132	83.24 162	89.13 146	63.62 226	86.21 204	89.95 162	72.43 166	81.78 117	89.61 155	57.50 213	93.58 149	70.75 188	86.90 153	92.52 123

sss		73.60 277	73.64 266	73.51 335	82.80 312	55.01 349	76.12 355	81.69 321	62.47 326	74.68 256	85.85 260	57.32 215	78.11 371	60.86 281	80.93 236	87.39 290

Effi-MVS+-dtu		80.03 160	78.57 171	84.42 110	85.13 260	68.74 114	88.77 119	88.10 217	74.99 107	74.97 251	83.49 312	57.27 216	93.36 162	73.53 162	80.88 237	91.18 164

AdaColmap		80.58 149	79.42 152	84.06 133	93.09 57	68.91 108	89.36 99	88.97 198	69.27 229	75.70 224	89.69 152	57.20 217	95.77 59	63.06 257	88.41 137	87.50 289

v1240		78.99 185	77.78 193	82.64 190	83.21 299	63.54 230	86.62 192	90.30 152	69.74 223	77.33 185	85.68 263	57.04 218	93.76 144	73.13 169	76.92 282	90.62 184

miper_lstm_enhance		74.11 271	73.11 271	77.13 300	80.11 352	59.62 288	72.23 376	86.92 247	66.76 267	70.40 303	82.92 322	56.93 219	82.92 349	69.06 208	72.63 340	88.87 255

BP-MVS1		84.32 75	83.71 81	86.17 61	87.84 199	67.85 138	89.38 98	89.64 171	77.73 38	83.98 87	92.12 93	56.89 220	95.43 70	84.03 62	91.75 87	95.24 6

BH-RMVSNet		79.61 165	78.44 174	83.14 167	89.38 134	65.93 179	84.95 235	87.15 241	73.56 142	78.19 168	89.79 150	56.67 221	93.36 162	59.53 291	86.74 156	90.13 205

RRT-MVS		82.60 108	82.10 107	84.10 125	87.98 193	62.94 248	87.45 166	91.27 121	77.42 49	79.85 138	90.28 140	56.62 222	94.70 107	79.87 104	88.15 140	94.67 28

test_djsdf		80.30 155	79.32 156	83.27 160	83.98 282	65.37 194	90.50 64	90.38 146	68.55 248	76.19 215	88.70 179	56.44 223	93.46 158	78.98 107	80.14 249	90.97 173

EPNet_dtu		75.46 257	74.86 248	77.23 299	82.57 318	54.60 352	86.89 182	83.09 302	71.64 174	66.25 352	85.86 259	55.99 224	88.04 305	54.92 328	86.55 159	89.05 246
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GDP-MVS		83.52 89	82.64 99	86.16 62	88.14 183	68.45 124	89.13 108	92.69 65	72.82 162	83.71 92	91.86 99	55.69 225	95.35 79	80.03 101	89.74 116	94.69 27

CostFormer		75.24 262	73.90 262	79.27 261	82.65 317	58.27 298	80.80 302	82.73 311	61.57 333	75.33 240	83.13 318	55.52 226	91.07 255	64.98 244	78.34 269	88.45 269

tpmrst		72.39 291	72.13 282	73.18 339	80.54 347	49.91 386	79.91 320	79.08 350	63.11 315	71.69 293	79.95 355	55.32 227	82.77 350	65.66 239	73.89 329	86.87 304

1314		76.53 238	75.30 245	80.21 243	83.93 283	62.32 254	84.66 240	88.81 201	60.23 342	70.16 308	84.07 300	55.30 228	90.73 261	67.37 223	83.21 211	87.59 287

tfpnnormal		74.39 266	73.16 270	78.08 284	86.10 243	58.05 300	84.65 242	87.53 232	70.32 205	71.22 298	85.63 265	54.97 229	89.86 272	43.03 386	75.02 319	86.32 313

sd_testset		77.70 219	77.40 203	78.60 272	89.03 151	60.02 284	79.00 331	85.83 263	75.19 103	76.61 206	89.98 146	54.81 230	85.46 330	62.63 263	83.55 205	90.33 197

GBi-Net		78.40 197	77.40 203	81.40 214	87.60 210	63.01 243	88.39 133	89.28 181	71.63 175	75.34 236	87.28 217	54.80 231	91.11 249	62.72 259	79.57 253	90.09 209

test1		78.40 197	77.40 203	81.40 214	87.60 210	63.01 243	88.39 133	89.28 181	71.63 175	75.34 236	87.28 217	54.80 231	91.11 249	62.72 259	79.57 253	90.09 209

FMVSNet2		78.20 203	77.21 207	81.20 220	87.60 210	62.89 249	87.47 164	89.02 194	71.63 175	75.29 242	87.28 217	54.80 231	91.10 252	62.38 264	79.38 257	89.61 231

Fast-Effi-MVS+-dtu		78.02 209	76.49 224	82.62 191	83.16 303	66.96 165	86.94 180	87.45 235	72.45 163	71.49 296	84.17 298	54.79 234	91.58 231	67.61 220	80.31 246	89.30 239

MVSTER		79.01 184	77.88 189	82.38 195	83.07 304	64.80 205	84.08 259	88.95 199	69.01 241	78.69 154	87.17 224	54.70 235	92.43 200	74.69 151	80.57 243	89.89 222

OpenMVS	72.83 10	79.77 163	78.33 178	84.09 129	85.17 256	69.91 87	90.57 61	90.97 130	66.70 268	72.17 288	91.91 95	54.70 235	93.96 128	61.81 273	90.95 97	88.41 271

XVG-OURS		80.41 151	79.23 159	83.97 142	85.64 248	69.02 105	83.03 280	90.39 145	71.09 188	77.63 180	91.49 111	54.62 237	91.35 244	75.71 141	83.47 207	91.54 153

LPG-MVS_test		82.08 112	81.27 118	84.50 106	89.23 142	68.76 112	90.22 73	91.94 99	75.37 99	76.64 204	91.51 109	54.29 238	94.91 95	78.44 112	83.78 196	89.83 224

LGP-MVS_train				84.50 106	89.23 142	68.76 112		91.94 99	75.37 99	76.64 204	91.51 109	54.29 238	94.91 95	78.44 112	83.78 196	89.83 224

TR-MVS		77.44 223	76.18 229	81.20 220	88.24 179	63.24 238	84.61 243	86.40 254	67.55 260	77.81 176	86.48 247	54.10 240	93.15 176	57.75 310	82.72 218	87.20 295

FMVSNet3		77.88 213	76.85 215	80.97 228	86.84 229	62.36 252	86.52 195	88.77 203	71.13 186	75.34 236	86.66 239	54.07 241	91.10 252	62.72 259	79.57 253	89.45 235

DP-MVS		76.78 235	74.57 251	83.42 154	93.29 48	69.46 97	88.55 129	83.70 289	63.98 309	70.20 305	88.89 175	54.01 242	94.80 102	46.66 372	81.88 228	86.01 321

ACMP	74.13 6	81.51 127	80.57 129	84.36 112	89.42 130	68.69 119	89.97 77	91.50 118	74.46 122	75.04 250	90.41 139	53.82 243	94.54 109	77.56 121	82.91 214	89.86 223
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PLC	70.83 11	78.05 208	76.37 228	83.08 170	91.88 77	67.80 140	88.19 142	89.46 176	64.33 302	69.87 314	88.38 190	53.66 244	93.58 149	58.86 298	82.73 217	87.86 280
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dmvs_testset		62.63 355	64.11 346	58.19 385	78.55 368	24.76 423	75.28 362	65.94 401	67.91 257	60.34 379	76.01 382	53.56 245	73.94 398	31.79 404	67.65 365	75.88 392

CANet_DTU		80.61 145	79.87 143	82.83 181	85.60 249	63.17 242	87.36 168	88.65 209	76.37 81	75.88 221	88.44 189	53.51 246	93.07 181	73.30 166	89.74 116	92.25 134

WB-MVSnew		71.96 298	71.65 286	72.89 340	84.67 270	51.88 372	82.29 285	77.57 357	62.31 327	73.67 268	83.00 320	53.49 247	81.10 359	45.75 379	82.13 224	85.70 327

ACMM	73.20 8	80.78 143	79.84 144	83.58 150	89.31 138	68.37 126	89.99 76	91.60 112	70.28 206	77.25 187	89.66 153	53.37 248	93.53 154	74.24 157	82.85 215	88.85 256
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVP-Stereo		76.12 247	74.46 255	81.13 223	85.37 254	69.79 89	84.42 251	87.95 222	65.03 293	67.46 335	85.33 271	53.28 249	91.73 228	58.01 308	83.27 210	81.85 373
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
AUN-MVS		79.21 179	77.60 200	84.05 136	88.71 163	67.61 145	85.84 215	87.26 238	69.08 237	77.23 189	88.14 201	53.20 250	93.47 157	75.50 146	73.45 334	91.06 168

anonymousdsp		78.60 194	77.15 208	82.98 176	80.51 348	67.08 161	87.24 173	89.53 174	65.66 285	75.16 245	87.19 223	52.52 251	92.25 209	77.17 126	79.34 258	89.61 231

CR-MVSNet		73.37 280	71.27 292	79.67 255	81.32 340	65.19 196	75.92 357	80.30 338	59.92 345	72.73 279	81.19 340	52.50 252	86.69 314	59.84 287	77.71 274	87.11 300

Patchmtry		70.74 307	69.16 310	75.49 315	80.72 344	54.07 357	74.94 368	80.30 338	58.34 358	70.01 309	81.19 340	52.50 252	86.54 316	53.37 336	71.09 352	85.87 326

pmmvs4		74.03 274	71.91 283	80.39 238	81.96 326	68.32 127	81.45 295	82.14 315	59.32 350	69.87 314	85.13 277	52.40 254	88.13 304	60.21 285	74.74 322	84.73 343

RPMNet		73.51 278	70.49 300	82.58 192	81.32 340	65.19 196	75.92 357	92.27 84	57.60 365	72.73 279	76.45 380	52.30 255	95.43 70	48.14 367	77.71 274	87.11 300

LFMVS		81.82 118	81.23 119	83.57 151	91.89 76	63.43 235	89.84 78	81.85 320	77.04 61	83.21 98	93.10 70	52.26 256	93.43 160	71.98 178	89.95 113	93.85 64

VDD-MVS		83.01 102	82.36 103	84.96 92	91.02 88	66.40 170	88.91 114	88.11 216	77.57 42	84.39 79	93.29 67	52.19 257	93.91 135	77.05 128	88.70 132	94.57 35

tfpn200view9		76.42 243	75.37 243	79.55 259	89.13 146	57.65 310	85.17 227	83.60 290	73.41 148	76.45 208	86.39 249	52.12 258	91.95 218	48.33 363	83.75 199	89.07 241

thres400		76.50 239	75.37 243	79.86 249	89.13 146	57.65 310	85.17 227	83.60 290	73.41 148	76.45 208	86.39 249	52.12 258	91.95 218	48.33 363	83.75 199	90.00 215

Syy-MVS		68.05 332	67.85 322	68.67 368	84.68 267	40.97 411	78.62 337	73.08 382	66.65 272	66.74 344	79.46 359	52.11 260	82.30 352	32.89 403	76.38 295	82.75 366

thres200		75.55 255	74.47 254	78.82 268	87.78 204	57.85 306	83.07 278	83.51 293	72.44 165	75.84 222	84.42 289	52.08 261	91.75 226	47.41 370	83.64 204	86.86 305

PMMVS		69.34 321	68.67 312	71.35 353	75.67 379	62.03 257	75.17 363	73.46 380	50.00 390	68.68 324	79.05 362	52.07 262	78.13 370	61.16 279	82.77 216	73.90 394

tpm cat1		70.57 309	68.31 315	77.35 297	82.41 322	57.95 304	78.08 345	80.22 340	52.04 384	68.54 327	77.66 375	52.00 263	87.84 307	51.77 342	72.07 346	86.25 314

IterMVS-SCA-FT		75.43 258	73.87 263	80.11 245	82.69 315	64.85 204	81.57 293	83.47 294	69.16 235	70.49 302	84.15 299	51.95 264	88.15 303	69.23 205	72.14 345	87.34 292

SCA		74.22 269	72.33 280	79.91 248	84.05 281	62.17 256	79.96 319	79.29 348	66.30 277	72.38 285	80.13 353	51.95 264	88.60 298	59.25 293	77.67 276	88.96 252

thres100view900		76.50 239	75.55 238	79.33 260	89.52 125	56.99 319	85.83 216	83.23 298	73.94 132	76.32 212	87.12 225	51.89 266	91.95 218	48.33 363	83.75 199	89.07 241

thres600view7		76.50 239	75.44 239	79.68 254	89.40 132	57.16 316	85.53 224	83.23 298	73.79 136	76.26 213	87.09 226	51.89 266	91.89 221	48.05 368	83.72 202	90.00 215

tpm2		73.26 283	71.46 288	78.63 270	83.34 296	56.71 324	80.65 308	80.40 337	56.63 371	73.55 269	82.02 337	51.80 268	91.24 247	56.35 323	78.42 267	87.95 277

MonoMVSNet		76.49 242	75.80 231	78.58 273	81.55 333	58.45 295	86.36 200	86.22 257	74.87 113	74.73 255	83.73 307	51.79 269	88.73 295	70.78 187	72.15 344	88.55 268

LS3D		76.95 232	74.82 249	83.37 157	90.45 100	67.36 153	89.15 107	86.94 245	61.87 332	69.52 317	90.61 136	51.71 270	94.53 110	46.38 375	86.71 157	88.21 274

IterMVS		74.29 267	72.94 273	78.35 280	81.53 334	63.49 232	81.58 292	82.49 312	68.06 256	69.99 311	83.69 309	51.66 271	85.54 328	65.85 237	71.64 348	86.01 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 293	71.71 285	74.35 328	82.19 324	52.00 369	79.22 327	77.29 362	64.56 298	72.95 277	83.68 310	51.35 272	83.26 348	58.33 305	75.80 301	87.81 281

sam_mvs1												51.32 273				88.96 252

mvsmamba		80.60 146	79.38 153	84.27 119	89.74 120	67.24 158	87.47 164	86.95 244	70.02 211	75.38 234	88.93 173	51.24 274	92.56 195	75.47 147	89.22 122	93.00 110

PatchmatchNet		73.12 285	71.33 291	78.49 278	83.18 301	60.85 272	79.63 321	78.57 352	64.13 303	71.73 292	79.81 358	51.20 275	85.97 323	57.40 313	76.36 297	88.66 264
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
patchmatchnet-post											74.00 389	51.12 276	88.60 298

xiu_mvs_v1_base_debu		80.80 140	79.72 146	84.03 138	87.35 215	70.19 82	85.56 219	88.77 203	69.06 238	81.83 113	88.16 197	50.91 277	92.85 188	78.29 116	87.56 143	89.06 243

xiu_mvs_v1_base		80.80 140	79.72 146	84.03 138	87.35 215	70.19 82	85.56 219	88.77 203	69.06 238	81.83 113	88.16 197	50.91 277	92.85 188	78.29 116	87.56 143	89.06 243

xiu_mvs_v1_base_debi		80.80 140	79.72 146	84.03 138	87.35 215	70.19 82	85.56 219	88.77 203	69.06 238	81.83 113	88.16 197	50.91 277	92.85 188	78.29 116	87.56 143	89.06 243

Patchmatch-test		64.82 350	63.24 351	69.57 361	79.42 364	49.82 387	63.49 407	69.05 393	51.98 386	59.95 382	80.13 353	50.91 277	70.98 401	40.66 392	73.57 332	87.90 279

Patchmatch-RL test		70.24 313	67.78 326	77.61 292	77.43 372	59.57 290	71.16 380	70.33 387	62.94 319	68.65 325	72.77 392	50.62 281	85.49 329	69.58 203	66.58 369	87.77 282

Anonymous20231211		78.97 186	77.69 198	82.81 183	90.54 99	64.29 216	90.11 75	91.51 115	65.01 294	76.16 219	88.13 202	50.56 282	93.03 185	69.68 202	77.56 277	91.11 166

VDDNet		81.52 125	80.67 128	84.05 136	90.44 101	64.13 219	89.73 84	85.91 262	71.11 187	83.18 99	93.48 61	50.54 283	93.49 155	73.40 165	88.25 138	94.54 36

pmmvs6		74.69 265	73.39 267	78.61 271	81.38 337	57.48 313	86.64 191	87.95 222	64.99 295	70.18 306	86.61 240	50.43 284	89.52 279	62.12 269	70.18 356	88.83 257

test_post											5.46 421	50.36 285	84.24 339

ET-MVSNet_ETH3D		78.63 193	76.63 223	84.64 103	86.73 232	69.47 95	85.01 233	84.61 276	69.54 224	66.51 350	86.59 241	50.16 286	91.75 226	76.26 135	84.24 192	92.69 118

sam_mvs												50.01 287

Anonymous20240529		80.19 158	78.89 166	84.10 125	90.60 97	64.75 206	88.95 113	90.90 132	65.97 282	80.59 131	91.17 122	49.97 288	93.73 147	69.16 207	82.70 219	93.81 67

thisisatest0530		79.40 174	77.76 195	84.31 115	87.69 208	65.10 199	87.36 168	84.26 283	70.04 210	77.42 183	88.26 195	49.94 289	94.79 103	70.20 194	84.70 182	93.03 107

PatchT		68.46 330	67.85 322	70.29 359	80.70 345	43.93 403	72.47 375	74.88 374	60.15 343	70.55 300	76.57 379	49.94 289	81.59 355	50.58 348	74.83 321	85.34 332

tttt0517		79.40 174	77.91 187	83.90 145	88.10 186	63.84 223	88.37 136	84.05 285	71.45 181	76.78 200	89.12 169	49.93 291	94.89 98	70.18 195	83.18 212	92.96 112

tpmvs		71.09 303	69.29 308	76.49 304	82.04 325	56.04 335	78.92 333	81.37 325	64.05 307	67.18 339	78.28 370	49.74 292	89.77 274	49.67 357	72.37 341	83.67 355

thisisatest0515		77.33 226	75.38 242	83.18 165	85.27 255	63.80 224	82.11 287	83.27 297	65.06 292	75.91 220	83.84 303	49.54 293	94.27 118	67.24 225	86.19 165	91.48 157

UniMVSNet_ETH3D		79.10 182	78.24 180	81.70 206	86.85 228	60.24 282	87.28 172	88.79 202	74.25 126	76.84 197	90.53 138	49.48 294	91.56 233	67.98 217	82.15 223	93.29 92

dmvs_re		71.14 302	70.58 298	72.80 341	81.96 326	59.68 287	75.60 361	79.34 347	68.55 248	69.27 321	80.72 348	49.42 295	76.54 379	52.56 340	77.79 273	82.19 371

CVMVSNet		72.99 288	72.58 277	74.25 329	84.28 274	50.85 382	86.41 197	83.45 295	44.56 397	73.23 273	87.54 213	49.38 296	85.70 325	65.90 236	78.44 266	86.19 316

MDTV_nov1_ep13_2view						37.79 413	75.16 364		55.10 376	66.53 347		49.34 297		53.98 332		87.94 278

UGNet		80.83 137	79.59 149	84.54 105	88.04 189	68.09 133	89.42 95	88.16 215	76.95 62	76.22 214	89.46 162	49.30 298	93.94 131	68.48 214	90.31 104	91.60 150
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		71.55 299	70.20 305	75.61 311	77.83 370	56.39 329	81.74 290	80.89 327	57.76 363	67.46 335	84.49 287	49.26 299	85.32 332	57.08 316	75.29 315	85.11 338

mvsany_test1		62.30 356	61.26 360	65.41 377	69.52 401	54.86 350	66.86 397	49.78 417	46.65 394	68.50 328	83.21 316	49.15 300	66.28 409	56.93 318	60.77 383	75.11 393

LTVRE_ROB	69.57 13	76.25 246	74.54 253	81.41 213	88.60 166	64.38 215	79.24 326	89.12 192	70.76 195	69.79 316	87.86 204	49.09 301	93.20 172	56.21 324	80.16 247	86.65 310
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		77.44 223	76.12 230	81.40 214	86.81 230	63.01 243	88.39 133	89.28 181	70.49 202	74.39 261	87.28 217	49.06 302	91.11 249	60.91 280	78.52 264	90.09 209

test1111		79.43 172	79.18 161	80.15 244	89.99 113	53.31 364	87.33 170	77.05 364	75.04 106	80.23 135	92.77 84	48.97 303	92.33 207	68.87 210	92.40 79	94.81 21

ECVR-MVS		79.61 165	79.26 158	80.67 234	90.08 108	54.69 351	87.89 154	77.44 360	74.88 111	80.27 133	92.79 82	48.96 304	92.45 199	68.55 213	92.50 77	94.86 18

MDTV_nov1_ep13			69.97 306		83.18 301	53.48 361	77.10 353	80.18 341	60.45 339	69.33 320	80.44 349	48.89 305	86.90 313	51.60 344	78.51 265

test_post1							78.90 334				5.43 422	48.81 306	85.44 331	59.25 293

test-LLR		72.94 289	72.43 278	74.48 326	81.35 338	58.04 301	78.38 340	77.46 358	66.66 269	69.95 312	79.00 364	48.06 307	79.24 365	66.13 232	84.83 179	86.15 317

test0.0.03 1		68.00 333	67.69 327	68.90 365	77.55 371	47.43 391	75.70 360	72.95 384	66.66 269	66.56 346	82.29 333	48.06 307	75.87 387	44.97 383	74.51 324	83.41 357

our_test_3		69.14 322	67.00 335	75.57 312	79.80 358	58.80 292	77.96 346	77.81 355	59.55 348	62.90 372	78.25 371	47.43 309	83.97 341	51.71 343	67.58 366	83.93 352

MS-PatchMatch		73.83 275	72.67 275	77.30 298	83.87 285	66.02 176	81.82 288	84.66 275	61.37 336	68.61 326	82.82 325	47.29 310	88.21 302	59.27 292	84.32 191	77.68 388

cascas		76.72 236	74.64 250	82.99 175	85.78 246	65.88 181	82.33 284	89.21 186	60.85 338	72.74 278	81.02 343	47.28 311	93.75 145	67.48 222	85.02 177	89.34 238

WB-MVS		54.94 365	54.72 366	55.60 391	73.50 390	20.90 425	74.27 371	61.19 408	59.16 352	50.61 400	74.15 388	47.19 312	75.78 388	17.31 416	35.07 410	70.12 398

test20.03		67.45 335	66.95 336	68.94 364	75.48 381	44.84 401	77.50 349	77.67 356	66.66 269	63.01 370	83.80 304	47.02 313	78.40 369	42.53 389	68.86 363	83.58 356

test_0402		72.79 290	70.44 301	79.84 250	88.13 184	65.99 178	85.93 211	84.29 281	65.57 286	67.40 337	85.49 268	46.92 314	92.61 193	35.88 400	74.38 325	80.94 378

F-COLMAP		76.38 245	74.33 257	82.50 193	89.28 140	66.95 166	88.41 132	89.03 193	64.05 307	66.83 342	88.61 183	46.78 315	92.89 187	57.48 311	78.55 263	87.67 283

ppachtmachnet_test		70.04 315	67.34 333	78.14 283	79.80 358	61.13 267	79.19 328	80.59 332	59.16 352	65.27 357	79.29 361	46.75 316	87.29 311	49.33 358	66.72 367	86.00 323

WBMVS		73.43 279	72.81 274	75.28 318	87.91 195	50.99 381	78.59 339	81.31 326	65.51 289	74.47 260	84.83 283	46.39 317	86.68 315	58.41 303	77.86 272	88.17 275

tt0805		78.73 190	77.83 190	81.43 212	85.17 256	60.30 281	89.41 96	90.90 132	71.21 185	77.17 194	88.73 178	46.38 318	93.21 169	72.57 175	78.96 261	90.79 177

D2MVS		74.82 264	73.21 269	79.64 256	79.81 357	62.56 251	80.34 314	87.35 236	64.37 301	68.86 323	82.66 327	46.37 319	90.10 268	67.91 218	81.24 233	86.25 314

Anonymous20231206		68.60 326	67.80 325	71.02 356	80.23 351	50.75 383	78.30 344	80.47 334	56.79 370	66.11 353	82.63 328	46.35 320	78.95 367	43.62 385	75.70 302	83.36 358

SSC-MVS		53.88 368	53.59 368	54.75 393	72.87 396	19.59 426	73.84 373	60.53 410	57.58 366	49.18 404	73.45 391	46.34 321	75.47 391	16.20 419	32.28 412	69.20 399

CHOSEN 280x420		66.51 342	64.71 343	71.90 347	81.45 335	63.52 231	57.98 410	68.95 394	53.57 380	62.59 373	76.70 378	46.22 322	75.29 393	55.25 326	79.68 252	76.88 390

testing91		76.54 237	75.66 236	79.18 264	88.43 173	55.89 337	81.08 299	83.00 305	73.76 137	75.34 236	84.29 294	46.20 323	90.07 269	64.33 248	84.50 184	91.58 152

GA-MVS		76.87 233	75.17 246	81.97 202	82.75 313	62.58 250	81.44 296	86.35 256	72.16 170	74.74 254	82.89 323	46.20 323	92.02 216	68.85 211	81.09 235	91.30 162

MDA-MVSNet_test_wron		65.03 348	62.92 352	71.37 351	75.93 376	56.73 322	69.09 392	74.73 376	57.28 368	54.03 397	77.89 372	45.88 325	74.39 396	49.89 356	61.55 381	82.99 364

YYNet1		65.03 348	62.91 353	71.38 350	75.85 378	56.60 326	69.12 391	74.66 378	57.28 368	54.12 396	77.87 373	45.85 326	74.48 395	49.95 355	61.52 382	83.05 362

EPMVS		69.02 323	68.16 317	71.59 349	79.61 361	49.80 388	77.40 350	66.93 398	62.82 322	70.01 309	79.05 362	45.79 327	77.86 373	56.58 321	75.26 316	87.13 299

IB-MVS	68.01 15	75.85 252	73.36 268	83.31 158	84.76 265	66.03 175	83.38 270	85.06 271	70.21 209	69.40 318	81.05 342	45.76 328	94.66 108	65.10 243	75.49 306	89.25 240
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		79.29 177	77.96 185	83.27 160	84.68 267	66.57 169	89.25 102	90.16 156	69.20 234	75.46 230	89.49 159	45.75 329	93.13 178	76.84 130	80.80 239	90.11 207

UBG		73.08 286	72.27 281	75.51 314	88.02 190	51.29 379	78.35 343	77.38 361	65.52 287	73.87 266	82.36 330	45.55 330	86.48 318	55.02 327	84.39 190	88.75 261

PatchMatch-RL		72.38 292	70.90 296	76.80 303	88.60 166	67.38 152	79.53 322	76.17 370	62.75 323	69.36 319	82.00 338	45.51 331	84.89 336	53.62 334	80.58 242	78.12 387

FE-MVS		77.78 215	75.68 234	84.08 130	88.09 187	66.00 177	83.13 275	87.79 227	68.42 252	78.01 173	85.23 274	45.50 332	95.12 85	59.11 295	85.83 173	91.11 166

RPSCF		73.23 284	71.46 288	78.54 275	82.50 319	59.85 285	82.18 286	82.84 310	58.96 354	71.15 299	89.41 166	45.48 333	84.77 337	58.82 299	71.83 347	91.02 172

test_vis1_n_1920		75.52 256	75.78 232	74.75 325	79.84 356	57.44 314	83.26 272	85.52 266	62.83 321	79.34 146	86.17 254	45.10 334	79.71 364	78.75 109	81.21 234	87.10 302

MSDG		73.36 282	70.99 295	80.49 237	84.51 272	65.80 183	80.71 307	86.13 260	65.70 284	65.46 355	83.74 306	44.60 335	90.91 257	51.13 347	76.89 283	84.74 342

PVSNet_0	57.27 20	61.67 358	59.27 361	68.85 366	79.61 361	57.44 314	68.01 393	73.44 381	55.93 374	58.54 386	70.41 397	44.58 336	77.55 374	47.01 371	35.91 409	71.55 397

testing99		76.09 249	75.12 247	79.00 265	88.16 181	55.50 343	80.79 303	81.40 324	73.30 151	75.17 244	84.27 296	44.48 337	90.02 270	64.28 249	84.22 193	91.48 157

test_cas_vis1_n_1920		73.76 276	73.74 265	73.81 333	75.90 377	59.77 286	80.51 310	82.40 313	58.30 359	81.62 119	85.69 262	44.35 338	76.41 382	76.29 134	78.61 262	85.23 334

mvs_tets		79.13 181	77.77 194	83.22 164	84.70 266	66.37 171	89.17 103	90.19 155	69.38 227	75.40 233	89.46 162	44.17 339	93.15 176	76.78 132	80.70 241	90.14 204

MDA-MVSNet-bldmvs		66.68 340	63.66 349	75.75 309	79.28 365	60.56 277	73.92 372	78.35 353	64.43 299	50.13 402	79.87 357	44.02 340	83.67 343	46.10 377	56.86 388	83.03 363

mmtdpeth		74.16 270	73.01 272	77.60 294	83.72 289	61.13 267	85.10 231	85.10 270	72.06 171	77.21 193	80.33 351	43.84 341	85.75 324	77.14 127	52.61 398	85.91 324

gg-mvs-nofinetune		69.95 316	67.96 320	75.94 307	83.07 304	54.51 354	77.23 352	70.29 388	63.11 315	70.32 304	62.33 401	43.62 342	88.69 296	53.88 333	87.76 142	84.62 344

testing11		75.14 263	74.01 259	78.53 276	88.16 181	56.38 330	80.74 306	80.42 336	70.67 196	72.69 281	83.72 308	43.61 343	89.86 272	62.29 266	83.76 198	89.36 237

GG-mvs-BLEND				75.38 317	81.59 332	55.80 339	79.32 325	69.63 390		67.19 338	73.67 390	43.24 344	88.90 294	50.41 349	84.50 184	81.45 375

CMPMVS	51.72 21	70.19 314	68.16 317	76.28 305	73.15 395	57.55 312	79.47 323	83.92 286	48.02 393	56.48 393	84.81 284	43.13 345	86.42 319	62.67 262	81.81 229	84.89 340
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dp		66.80 339	65.43 341	70.90 358	79.74 360	48.82 389	75.12 366	74.77 375	59.61 347	64.08 365	77.23 376	42.89 346	80.72 361	48.86 361	66.58 369	83.16 360

PVSNet	64.34 18	72.08 297	70.87 297	75.69 310	86.21 239	56.44 328	74.37 370	80.73 330	62.06 331	70.17 307	82.23 334	42.86 347	83.31 347	54.77 329	84.45 188	87.32 293

pmmvs-eth3d		70.50 311	67.83 324	78.52 277	77.37 373	66.18 174	81.82 288	81.51 322	58.90 355	63.90 367	80.42 350	42.69 348	86.28 320	58.56 301	65.30 374	83.11 361

UnsupCasMVSNet_eth		67.33 336	65.99 340	71.37 351	73.48 391	51.47 377	75.16 364	85.19 269	65.20 290	60.78 378	80.93 347	42.35 349	77.20 375	57.12 315	53.69 396	85.44 331

KD-MVS_self_test		68.81 324	67.59 330	72.46 345	74.29 385	45.45 396	77.93 347	87.00 243	63.12 314	63.99 366	78.99 366	42.32 350	84.77 337	56.55 322	64.09 377	87.16 298

ADS-MVSNet2		66.20 347	63.33 350	74.82 323	79.92 354	58.75 293	67.55 395	75.19 372	53.37 381	65.25 358	75.86 383	42.32 350	80.53 362	41.57 390	68.91 361	85.18 335

ADS-MVSNet		64.36 351	62.88 354	68.78 367	79.92 354	47.17 392	67.55 395	71.18 386	53.37 381	65.25 358	75.86 383	42.32 350	73.99 397	41.57 390	68.91 361	85.18 335

SixPastTwentyTwo		73.37 280	71.26 293	79.70 253	85.08 261	57.89 305	85.57 218	83.56 292	71.03 190	65.66 354	85.88 258	42.10 353	92.57 194	59.11 295	63.34 378	88.65 265

JIA-IIPM		66.32 344	62.82 355	76.82 302	77.09 374	61.72 263	65.34 403	75.38 371	58.04 362	64.51 362	62.32 402	42.05 354	86.51 317	51.45 345	69.22 360	82.21 370

ACMH	67.68 16	75.89 251	73.93 261	81.77 205	88.71 163	66.61 168	88.62 127	89.01 195	69.81 217	66.78 343	86.70 237	41.95 355	91.51 238	55.64 325	78.14 270	87.17 296
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	68.96 14	76.01 250	74.01 259	82.03 200	88.60 166	65.31 195	88.86 116	87.55 231	70.25 208	67.75 331	87.47 215	41.27 356	93.19 174	58.37 304	75.94 300	87.60 285

MIMVSNet		70.69 308	69.30 307	74.88 322	84.52 271	56.35 332	75.87 359	79.42 346	64.59 297	67.76 330	82.41 329	41.10 357	81.54 356	46.64 374	81.34 231	86.75 308

Anonymous202405211		78.25 200	77.01 210	81.99 201	91.03 87	60.67 275	84.77 238	83.90 287	70.65 200	80.00 137	91.20 120	41.08 358	91.43 242	65.21 241	85.26 176	93.85 64

N_pmnet		52.79 371	53.26 369	51.40 395	78.99 367	7.68 429	69.52 387	3.89 428	51.63 387	57.01 391	74.98 387	40.83 359	65.96 410	37.78 397	64.67 375	80.56 382

ETVMVS		72.25 295	71.05 294	75.84 308	87.77 205	51.91 371	79.39 324	74.98 373	69.26 230	73.71 267	82.95 321	40.82 360	86.14 321	46.17 376	84.43 189	89.47 234

EU-MVSNet		68.53 329	67.61 329	71.31 354	78.51 369	47.01 393	84.47 246	84.27 282	42.27 400	66.44 351	84.79 285	40.44 361	83.76 342	58.76 300	68.54 364	83.17 359

DSMNet-mixed		57.77 363	56.90 365	60.38 383	67.70 404	35.61 414	69.18 389	53.97 415	32.30 413	57.49 390	79.88 356	40.39 362	68.57 407	38.78 396	72.37 341	76.97 389

UWE-MVS		72.13 296	71.49 287	74.03 331	86.66 234	47.70 390	81.40 297	76.89 366	63.60 312	75.59 225	84.22 297	39.94 363	85.62 327	48.98 360	86.13 167	88.77 260

OurMVSNet-221017-0		74.26 268	72.42 279	79.80 251	83.76 288	59.59 289	85.92 212	86.64 250	66.39 276	66.96 340	87.58 209	39.46 364	91.60 230	65.76 238	69.27 359	88.22 273

K. test v3		71.19 301	68.51 313	79.21 263	83.04 306	57.78 309	84.35 253	76.91 365	72.90 160	62.99 371	82.86 324	39.27 365	91.09 254	61.65 274	52.66 397	88.75 261

lessismore_v0				78.97 266	81.01 343	57.15 317		65.99 400		61.16 377	82.82 325	39.12 366	91.34 245	59.67 289	46.92 404	88.43 270

testing222		74.04 272	72.66 276	78.19 282	87.89 196	55.36 344	81.06 300	79.20 349	71.30 183	74.65 257	83.57 311	39.11 367	88.67 297	51.43 346	85.75 174	90.53 189

reproduce_monomvs		75.40 260	74.38 256	78.46 279	83.92 284	57.80 308	83.78 261	86.94 245	73.47 146	72.25 287	84.47 288	38.74 368	89.27 284	75.32 148	70.53 354	88.31 272

UnsupCasMVSNet_bld		63.70 353	61.53 359	70.21 360	73.69 389	51.39 378	72.82 374	81.89 318	55.63 375	57.81 389	71.80 394	38.67 369	78.61 368	49.26 359	52.21 399	80.63 380

new-patchmatchnet		61.73 357	61.73 358	61.70 381	72.74 397	24.50 424	69.16 390	78.03 354	61.40 334	56.72 392	75.53 386	38.42 370	76.48 381	45.95 378	57.67 387	84.13 349

MVS-HIRNet		59.14 361	57.67 363	63.57 379	81.65 330	43.50 404	71.73 377	65.06 403	39.59 404	51.43 399	57.73 407	38.34 371	82.58 351	39.53 393	73.95 328	64.62 403

test2506		77.30 227	76.49 224	79.74 252	90.08 108	52.02 368	87.86 156	63.10 406	74.88 111	80.16 136	92.79 82	38.29 372	92.35 205	68.74 212	92.50 77	94.86 18

COLMAP_ROB	66.92 17	73.01 287	70.41 302	80.81 231	87.13 225	65.63 187	88.30 139	84.19 284	62.96 318	63.80 368	87.69 207	38.04 373	92.56 195	46.66 372	74.91 320	84.24 347
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TESTMET0.1,1		69.89 317	69.00 311	72.55 343	79.27 366	56.85 320	78.38 340	74.71 377	57.64 364	68.09 329	77.19 377	37.75 374	76.70 378	63.92 251	84.09 194	84.10 350

OpenMVS_ROB	64.09 19	70.56 310	68.19 316	77.65 291	80.26 349	59.41 291	85.01 233	82.96 307	58.76 356	65.43 356	82.33 331	37.63 375	91.23 248	45.34 382	76.03 299	82.32 369

FMVSNet5		69.50 319	67.96 320	74.15 330	82.97 310	55.35 345	80.01 318	82.12 316	62.56 325	63.02 369	81.53 339	36.92 376	81.92 354	48.42 362	74.06 327	85.17 337

MIMVSNet1		68.58 327	66.78 337	73.98 332	80.07 353	51.82 373	80.77 304	84.37 278	64.40 300	59.75 383	82.16 335	36.47 377	83.63 344	42.73 387	70.33 355	86.48 312

ITE_SJBPF				78.22 281	81.77 329	60.57 276		83.30 296	69.25 231	67.54 333	87.20 222	36.33 378	87.28 312	54.34 331	74.62 323	86.80 306

test-mter		71.41 300	70.39 303	74.48 326	81.35 338	58.04 301	78.38 340	77.46 358	60.32 341	69.95 312	79.00 364	36.08 379	79.24 365	66.13 232	84.83 179	86.15 317

testgi		66.67 341	66.53 338	67.08 375	75.62 380	41.69 410	75.93 356	76.50 367	66.11 278	65.20 360	86.59 241	35.72 380	74.71 394	43.71 384	73.38 336	84.84 341

EG-PatchMatch MVS		74.04 272	71.82 284	80.71 233	84.92 263	67.42 150	85.86 214	88.08 218	66.04 280	64.22 364	83.85 302	35.10 381	92.56 195	57.44 312	80.83 238	82.16 372

KD-MVS_2432*1600		66.22 345	63.89 347	73.21 336	75.47 382	53.42 362	70.76 383	84.35 279	64.10 305	66.52 348	78.52 368	34.55 382	84.98 334	50.40 350	50.33 401	81.23 376

miper_refine_blended		66.22 345	63.89 347	73.21 336	75.47 382	53.42 362	70.76 383	84.35 279	64.10 305	66.52 348	78.52 368	34.55 382	84.98 334	50.40 350	50.33 401	81.23 376

mvs5depth		69.45 320	67.45 332	75.46 316	73.93 386	55.83 338	79.19 328	83.23 298	66.89 264	71.63 294	83.32 314	33.69 384	85.09 333	59.81 288	55.34 394	85.46 330

XVG-ACMP-BASELINE		76.11 248	74.27 258	81.62 207	83.20 300	64.67 207	83.60 267	89.75 167	69.75 221	71.85 291	87.09 226	32.78 385	92.11 213	69.99 198	80.43 245	88.09 276

AllTest		70.96 304	68.09 319	79.58 257	85.15 258	63.62 226	84.58 244	79.83 342	62.31 327	60.32 380	86.73 231	32.02 386	88.96 292	50.28 352	71.57 349	86.15 317

TestCases				79.58 257	85.15 258	63.62 226		79.83 342	62.31 327	60.32 380	86.73 231	32.02 386	88.96 292	50.28 352	71.57 349	86.15 317

USDC		70.33 312	68.37 314	76.21 306	80.60 346	56.23 333	79.19 328	86.49 252	60.89 337	61.29 376	85.47 269	31.78 388	89.47 281	53.37 336	76.21 298	82.94 365

myMVS_eth3d		67.02 338	66.29 339	69.21 363	84.68 267	42.58 406	78.62 337	73.08 382	66.65 272	66.74 344	79.46 359	31.53 389	82.30 352	39.43 395	76.38 295	82.75 366

test_fmvs1		70.93 305	70.52 299	72.16 346	73.71 388	55.05 348	80.82 301	78.77 351	51.21 389	78.58 158	84.41 290	31.20 390	76.94 377	75.88 140	80.12 250	84.47 345

Anonymous20240521		68.80 325	67.22 334	73.55 334	74.33 384	54.11 356	83.18 273	85.61 265	58.15 360	61.68 375	80.94 345	30.71 391	81.27 358	57.00 317	73.34 337	85.28 333

testing3		68.56 328	67.67 328	71.22 355	87.33 220	42.87 405	83.06 279	71.54 385	70.36 203	69.08 322	84.38 291	30.33 392	85.69 326	37.50 398	75.45 310	85.09 339

test_vis1_n		69.85 318	69.21 309	71.77 348	72.66 398	55.27 347	81.48 294	76.21 369	52.03 385	75.30 241	83.20 317	28.97 393	76.22 384	74.60 152	78.41 268	83.81 353

tmp_tt		18.61 389	21.40 392	10.23 405	4.82 428	10.11 428	34.70 415	30.74 426	1.48 422	23.91 418	26.07 419	28.42 394	13.41 424	27.12 408	15.35 421	7.17 419

test_fmvs1_n		70.86 306	70.24 304	72.73 342	72.51 399	55.28 346	81.27 298	79.71 344	51.49 388	78.73 153	84.87 282	27.54 395	77.02 376	76.06 137	79.97 251	85.88 325

TDRefinement		67.49 334	64.34 344	76.92 301	73.47 392	61.07 269	84.86 237	82.98 306	59.77 346	58.30 387	85.13 277	26.06 396	87.89 306	47.92 369	60.59 385	81.81 374

dongtai		45.42 379	45.38 380	45.55 397	73.36 393	26.85 421	67.72 394	34.19 423	54.15 379	49.65 403	56.41 410	25.43 397	62.94 413	19.45 414	28.09 414	46.86 413

MVStest1		56.63 364	52.76 370	68.25 371	61.67 412	53.25 366	71.67 378	68.90 395	38.59 405	50.59 401	83.05 319	25.08 398	70.66 402	36.76 399	38.56 408	80.83 379

test_vis1_rt		60.28 359	58.42 362	65.84 376	67.25 405	55.60 342	70.44 385	60.94 409	44.33 398	59.00 384	66.64 399	24.91 399	68.67 406	62.80 258	69.48 357	73.25 395

TinyColmap		67.30 337	64.81 342	74.76 324	81.92 328	56.68 325	80.29 315	81.49 323	60.33 340	56.27 394	83.22 315	24.77 400	87.66 310	45.52 380	69.47 358	79.95 383

EGC-MVSNET		52.07 373	47.05 377	67.14 374	83.51 293	60.71 274	80.50 311	67.75 396	0.07 423	0.43 424	75.85 385	24.26 401	81.54 356	28.82 406	62.25 379	59.16 406

kuosan		39.70 383	40.40 384	37.58 400	64.52 409	26.98 419	65.62 402	33.02 424	46.12 395	42.79 407	48.99 413	24.10 402	46.56 421	12.16 422	26.30 415	39.20 414

LF4IMVS		64.02 352	62.19 356	69.50 362	70.90 400	53.29 365	76.13 354	77.18 363	52.65 383	58.59 385	80.98 344	23.55 403	76.52 380	53.06 338	66.66 368	78.68 386

test_fmvs2		68.35 331	67.48 331	70.98 357	69.50 402	51.95 370	80.05 317	76.38 368	49.33 391	74.65 257	84.38 291	23.30 404	75.40 392	74.51 153	75.17 318	85.60 328

new_pmnet		50.91 374	50.29 374	52.78 394	68.58 403	34.94 416	63.71 405	56.63 414	39.73 403	44.95 405	65.47 400	21.93 405	58.48 414	34.98 401	56.62 389	64.92 402

ttmdpeth		59.91 360	57.10 364	68.34 370	67.13 406	46.65 395	74.64 369	67.41 397	48.30 392	62.52 374	85.04 281	20.40 406	75.93 386	42.55 388	45.90 407	82.44 368

pmmvs3		57.79 362	54.26 367	68.37 369	64.02 410	56.72 323	75.12 366	65.17 402	40.20 402	52.93 398	69.86 398	20.36 407	75.48 390	45.45 381	55.25 395	72.90 396

PM-MVS		66.41 343	64.14 345	73.20 338	73.92 387	56.45 327	78.97 332	64.96 404	63.88 311	64.72 361	80.24 352	19.84 408	83.44 346	66.24 231	64.52 376	79.71 384

mvsany_test3		53.99 367	51.45 372	61.61 382	55.51 416	44.74 402	63.52 406	45.41 421	43.69 399	58.11 388	76.45 380	17.99 409	63.76 412	54.77 329	47.59 403	76.34 391

ambc				75.24 319	73.16 394	50.51 384	63.05 408	87.47 234		64.28 363	77.81 374	17.80 410	89.73 276	57.88 309	60.64 384	85.49 329

ANet_high		50.57 375	46.10 379	63.99 378	48.67 423	39.13 412	70.99 382	80.85 328	61.39 335	31.18 412	57.70 408	17.02 411	73.65 399	31.22 405	15.89 420	79.18 385

FPMVS		53.68 369	51.64 371	59.81 384	65.08 408	51.03 380	69.48 388	69.58 391	41.46 401	40.67 408	72.32 393	16.46 412	70.00 405	24.24 412	65.42 373	58.40 408

test_method		31.52 385	29.28 389	38.23 399	27.03 427	6.50 430	20.94 418	62.21 407	4.05 421	22.35 419	52.50 412	13.33 413	47.58 419	27.04 409	34.04 411	60.62 405

EMVS		30.81 386	29.65 388	34.27 402	50.96 422	25.95 422	56.58 412	46.80 420	24.01 417	15.53 422	30.68 418	12.47 414	54.43 418	12.81 421	17.05 419	22.43 418

test_f		52.09 372	50.82 373	55.90 389	53.82 419	42.31 409	59.42 409	58.31 413	36.45 408	56.12 395	70.96 396	12.18 415	57.79 415	53.51 335	56.57 390	67.60 400

test_fmvs3		63.36 354	61.82 357	67.98 372	62.51 411	46.96 394	77.37 351	74.03 379	45.24 396	67.50 334	78.79 367	12.16 416	72.98 400	72.77 173	66.02 371	83.99 351

E-PMN		31.77 384	30.64 387	35.15 401	52.87 421	27.67 418	57.09 411	47.86 419	24.64 416	16.40 421	33.05 417	11.23 417	54.90 417	14.46 420	18.15 418	22.87 417

DeepMVS_CX				27.40 403	40.17 426	26.90 420		24.59 427	17.44 419	23.95 417	48.61 414	9.77 418	26.48 422	18.06 415	24.47 416	28.83 416

Gipuma		45.18 380	41.86 383	55.16 392	77.03 375	51.52 376	32.50 416	80.52 333	32.46 412	27.12 415	35.02 416	9.52 419	75.50 389	22.31 413	60.21 386	38.45 415
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		54.25 366	49.68 376	67.97 373	53.73 420	45.28 399	66.85 398	80.78 329	35.96 409	39.45 410	62.23 403	8.70 420	78.06 372	48.24 366	51.20 400	80.57 381

APD_test1		53.31 370	49.93 375	63.42 380	65.68 407	50.13 385	71.59 379	66.90 399	34.43 410	40.58 409	71.56 395	8.65 421	76.27 383	34.64 402	55.36 393	63.86 404

PMMVS2		40.82 382	38.86 386	46.69 396	53.84 418	16.45 427	48.61 413	49.92 416	37.49 406	31.67 411	60.97 404	8.14 422	56.42 416	28.42 407	30.72 413	67.19 401

test_vis3_rt		49.26 376	47.02 378	56.00 388	54.30 417	45.27 400	66.76 399	48.08 418	36.83 407	44.38 406	53.20 411	7.17 423	64.07 411	56.77 320	55.66 391	58.65 407

testf1		45.72 377	41.96 381	57.00 386	56.90 414	45.32 397	66.14 400	59.26 411	26.19 414	30.89 413	60.96 405	4.14 424	70.64 403	26.39 410	46.73 405	55.04 409

APD_test2		45.72 377	41.96 381	57.00 386	56.90 414	45.32 397	66.14 400	59.26 411	26.19 414	30.89 413	60.96 405	4.14 424	70.64 403	26.39 410	46.73 405	55.04 409

PMVS	37.38 22	44.16 381	40.28 385	55.82 390	40.82 425	42.54 408	65.12 404	63.99 405	34.43 410	24.48 416	57.12 409	3.92 426	76.17 385	17.10 417	55.52 392	48.75 411
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 387	25.89 391	43.81 398	44.55 424	35.46 415	28.87 417	39.07 422	18.20 418	18.58 420	40.18 415	2.68 427	47.37 420	17.07 418	23.78 417	48.60 412
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		16.82 390	15.94 393	19.46 404	58.74 413	31.45 417	39.22 414	3.74 429	6.84 420	6.04 423	2.70 423	1.27 428	24.29 423	10.54 423	14.40 422	2.63 420

test123		6.12 392	8.11 395	0.14 406	0.06 430	0.09 431	71.05 381	0.03 431	0.04 425	0.25 426	1.30 425	0.05 429	0.03 426	0.21 425	0.01 424	0.29 421

testmvs		6.04 393	8.02 396	0.10 407	0.08 429	0.03 432	69.74 386	0.04 430	0.05 424	0.31 425	1.68 424	0.02 430	0.04 425	0.24 424	0.02 423	0.25 422

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		7.23 391	9.64 394	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	86.72 233	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						42.58 406								39.46 394

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 121	91.30 15

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 6	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 6	96.44 9	94.41 39

eth-test2					0.00 431

eth-test					0.00 431

IU-MVS					95.30 2	71.25 59		92.95 55	66.81 265	92.39 6				88.94 16	96.63 4	94.85 20

save fliter					93.80 40	72.35 42	90.47 66	91.17 125	74.31 124

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

GSMVS																88.96 252

test_part2					95.06 8	72.65 32				91.80 13

MTGPA								92.02 93

MTMP							92.18 34	32.83 425

gm-plane-assit					81.40 336	53.83 359			62.72 324		80.94 345		92.39 202	63.40 255

test9_res														84.90 46	95.70 26	92.87 113

agg_prior2														82.91 73	95.45 29	92.70 116

agg_prior					92.85 62	71.94 50		91.78 108		84.41 78			94.93 94

test_prior4						72.60 34	89.01 111

test_prior				86.33 57	92.61 68	69.59 91		92.97 54					95.48 67			93.91 60

旧先验2							86.56 194		58.10 361	87.04 45			88.98 290	74.07 158

新几何2							86.29 203

无先验							87.48 163	88.98 196	60.00 344				94.12 125	67.28 224		88.97 251

原ACMM2							86.86 183

testdata2													91.01 256	62.37 265

testdata1							84.14 257		75.71 92

plane_prior7					90.08 108	68.51 123

plane_prior5								92.44 77					95.38 75	78.71 110	86.32 162	91.33 160

plane_prior4											91.00 130

plane_prior3						68.60 121			78.44 31	78.92 151

plane_prior2							91.25 52		79.12 23

plane_prior1					89.90 116

plane_prior						68.71 116	90.38 70		77.62 40						86.16 166

n2								0.00 432

nn								0.00 432

door-mid								69.98 389

test11								92.23 87

door								69.44 392

HQP5-MVS						66.98 163

HQP-NCC					89.33 135		89.17 103		76.41 77	77.23 189

ACMP_Plane					89.33 135		89.17 103		76.41 77	77.23 189

BP-MVS														77.47 122

HQP4-MVS										77.24 188			95.11 87			91.03 170

HQP3-MVS								92.19 90							85.99 170

NP-MVS					89.62 121	68.32 127					90.24 142

ACMMP++_ref															81.95 227

ACMMP++															81.25 232

High-resolution multi-view benchmark