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.

MSC_two_6792asdad				96.52 1	97.78 60	90.86 1		96.85 80					99.61 6	96.03 27	99.06 9	99.07 7

No_MVS				96.52 1	97.78 60	90.86 1		96.85 80					99.61 6	96.03 27	99.06 9	99.07 7

OPU-MVS				96.21 3	98.00 48	90.85 3	97.13 19				97.08 70	92.59 2	98.94 92	92.25 92	98.99 14	98.84 19

HPM-MVS++		95.14 13	94.91 26	95.83 4	98.25 35	89.65 4	95.92 87	96.96 68	91.75 13	94.02 72	96.83 82	88.12 28	99.55 20	93.41 66	98.94 16	98.28 61

MM		95.10 14	94.91 26	95.68 5	96.09 116	88.34 10	96.68 38	94.37 301	95.08 1	94.68 58	97.72 41	82.94 100	99.64 3	97.85 5	98.76 32	99.06 9

SMA-MVS		95.20 10	95.07 20	95.59 6	98.14 41	88.48 9	96.26 54	97.28 40	85.90 208	97.67 4	98.10 14	88.41 24	99.56 16	94.66 48	99.19 1	98.71 25
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
3Dnovator+	87.14 4	92.42 104	91.37 126	95.55 7	95.63 143	88.73 7	97.07 23	96.77 92	90.84 26	84.02 334	96.62 95	75.95 216	99.34 42	87.77 183	97.68 96	98.59 29

CNVR-MVS		95.40 8	95.37 11	95.50 8	98.11 42	88.51 8	95.29 131	96.96 68	92.09 10	95.32 50	97.08 70	89.49 16	99.33 45	95.10 43	98.85 20	98.66 26

TestfortrainingZip				95.40 9	97.32 74	88.97 6	97.32 10	96.82 85	89.07 91	95.69 45	96.49 100	89.27 18	99.29 50		95.80 142	97.95 97

MGCNet		94.18 50	93.80 64	95.34 10	94.91 183	87.62 15	95.97 82	93.01 352	92.58 6	94.22 63	97.20 64	80.56 140	99.59 10	97.04 20	98.68 40	98.81 22

ACMMP_NAP		94.74 25	94.56 33	95.28 11	98.02 47	87.70 12	95.68 107	97.34 30	88.28 123	95.30 51	97.67 43	85.90 55	99.54 24	93.91 56	98.95 15	98.60 28

DPE-MVS		95.57 5	95.67 5	95.25 12	98.36 31	87.28 19	95.56 119	97.51 10	89.13 90	97.14 17	97.91 34	91.64 8	99.62 4	94.61 49	99.17 2	98.86 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SF-MVS		94.97 17	94.90 28	95.20 13	97.84 56	87.76 11	96.65 39	97.48 15	87.76 153	95.71 44	97.70 42	88.28 27	99.35 41	93.89 57	98.78 29	98.48 35

MCST-MVS		94.45 34	94.20 51	95.19 14	98.46 22	87.50 17	95.00 155	97.12 55	87.13 174	92.51 113	96.30 105	89.24 19	99.34 42	93.46 63	98.62 49	98.73 23

NCCC		94.81 22	94.69 32	95.17 15	97.83 57	87.46 18	95.66 110	96.93 72	92.34 7	93.94 73	96.58 97	87.74 31	99.44 33	92.83 75	98.40 57	98.62 27

DPM-MVS		92.58 99	91.74 110	95.08 16	96.19 107	89.31 5	92.66 313	96.56 113	83.44 283	91.68 139	95.04 188	86.60 47	98.99 82	85.60 217	97.92 84	96.93 188

ZNCC-MVS		94.47 33	94.28 45	95.03 17	98.52 18	86.96 21	96.85 33	97.32 34	88.24 124	93.15 88	97.04 73	86.17 52	99.62 4	92.40 86	98.81 26	98.52 31

test_0728_SECOND				95.01 18	98.79 5	86.43 40	97.09 21	97.49 11					99.61 6	95.62 34	99.08 7	98.99 11

MTAPA		94.42 39	94.22 48	95.00 19	98.42 24	86.95 22	94.36 210	96.97 65	91.07 22	93.14 89	97.56 45	84.30 81	99.56 16	93.43 64	98.75 33	98.47 38

TestfortrainingZip a		95.33 9	95.44 10	94.99 20	98.88 1	86.26 48	97.32 10	97.43 25	90.76 29	96.80 26	98.09 18	89.00 22	99.58 13	93.66 60	96.99 111	99.14 2

MSP-MVS		95.42 7	95.56 7	94.98 21	98.49 20	86.52 37	96.91 30	97.47 16	91.73 14	96.10 36	96.69 87	89.90 13	99.30 48	94.70 47	98.04 79	99.13 4
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
region2R		94.43 36	94.27 47	94.92 22	98.65 11	86.67 31	96.92 29	97.23 43	88.60 114	93.58 80	97.27 58	85.22 64	99.54 24	92.21 94	98.74 34	98.56 30

APDe-MVS		95.46 6	95.64 6	94.91 23	98.26 34	86.29 47	97.46 7	97.40 26	89.03 96	96.20 35	98.10 14	89.39 17	99.34 42	95.88 29	99.03 11	99.10 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		94.43 36	94.28 45	94.91 23	98.63 12	86.69 29	96.94 25	97.32 34	88.63 111	93.53 83	97.26 60	85.04 68	99.54 24	92.35 89	98.78 29	98.50 32

MED-MVS		95.95 2	96.29 2	94.90 25	98.88 1	85.89 65	97.32 10	97.86 1	90.76 29	97.21 14	98.09 18	92.42 4	99.67 1	95.27 40	98.85 20	99.14 2

GST-MVS		94.21 45	93.97 60	94.90 25	98.41 25	86.82 25	96.54 41	97.19 44	88.24 124	93.26 85	96.83 82	85.48 60	99.59 10	91.43 120	98.40 57	98.30 55

HFP-MVS		94.52 31	94.40 38	94.86 27	98.61 13	86.81 26	96.94 25	97.34 30	88.63 111	93.65 78	97.21 62	86.10 53	99.49 30	92.35 89	98.77 31	98.30 55

sasdasda		93.27 82	92.75 92	94.85 28	95.70 139	87.66 13	96.33 44	96.41 123	90.00 53	94.09 68	94.60 213	82.33 109	98.62 133	92.40 86	92.86 233	98.27 64

MP-MVS-pluss		94.21 45	94.00 59	94.85 28	98.17 39	86.65 32	94.82 168	97.17 49	86.26 200	92.83 98	97.87 36	85.57 59	99.56 16	94.37 52	98.92 17	98.34 48
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
canonicalmvs		93.27 82	92.75 92	94.85 28	95.70 139	87.66 13	96.33 44	96.41 123	90.00 53	94.09 68	94.60 213	82.33 109	98.62 133	92.40 86	92.86 233	98.27 64

XVS		94.45 34	94.32 41	94.85 28	98.54 16	86.60 35	96.93 27	97.19 44	90.66 36	92.85 96	97.16 68	85.02 69	99.49 30	91.99 105	98.56 53	98.47 38

X-MVStestdata		88.31 236	86.13 285	94.85 28	98.54 16	86.60 35	96.93 27	97.19 44	90.66 36	92.85 96	23.41 517	85.02 69	99.49 30	91.99 105	98.56 53	98.47 38

SteuartSystems-ACMMP		95.20 10	95.32 13	94.85 28	96.99 82	86.33 43	97.33 8	97.30 37	91.38 19	95.39 49	97.46 50	88.98 23	99.40 34	94.12 53	98.89 18	98.82 21
Skip Steuart: Steuart Systems R&D Blog.
MED-MVS test				94.84 34	98.88 1	85.89 65	97.32 10	97.86 1	88.11 132	97.21 14	97.54 46		99.67 1	95.27 40	98.85 20	98.95 13

DVP-MVS++		95.98 1	96.36 1	94.82 35	97.78 60	86.00 54	98.29 1	97.49 11	90.75 31	97.62 8	98.06 24	92.59 2	99.61 6	95.64 32	99.02 12	98.86 16

ME-MVS		95.17 12	95.29 14	94.81 36	98.39 28	85.89 65	95.91 88	97.55 8	89.01 98	95.86 42	97.54 46	89.24 19	99.59 10	95.27 40	98.85 20	98.95 13

alignmvs		93.08 90	92.50 98	94.81 36	95.62 144	87.61 16	95.99 79	96.07 169	89.77 66	94.12 67	94.87 197	80.56 140	98.66 125	92.42 85	93.10 229	98.15 76

SED-MVS		95.91 3	96.28 3	94.80 38	98.77 8	85.99 56	97.13 19	97.44 20	90.31 43	97.71 2	98.07 22	92.31 5	99.58 13	95.66 30	99.13 3	98.84 19

DeepC-MVS_fast	89.43 2	94.04 53	93.79 65	94.80 38	97.48 70	86.78 27	95.65 112	96.89 77	89.40 78	92.81 99	96.97 75	85.37 62	99.24 52	90.87 129	98.69 38	98.38 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		94.25 42	94.07 56	94.77 40	98.47 21	86.31 45	96.71 36	96.98 64	89.04 94	91.98 124	97.19 65	85.43 61	99.56 16	92.06 103	98.79 27	98.44 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APD-MVS		94.24 43	94.07 56	94.75 41	98.06 45	86.90 24	95.88 90	96.94 71	85.68 215	95.05 56	97.18 66	87.31 39	99.07 65	91.90 111	98.61 51	98.28 61
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		94.34 40	94.21 50	94.74 42	98.39 28	86.64 33	97.60 5	97.24 41	88.53 116	92.73 104	97.23 61	85.20 65	99.32 46	92.15 97	98.83 25	98.25 69

PGM-MVS		93.96 58	93.72 70	94.68 43	98.43 23	86.22 49	95.30 129	97.78 3	87.45 164	93.26 85	97.33 56	84.62 78	99.51 28	90.75 131	98.57 52	98.32 54

DVP-MVS		95.67 4	96.02 4	94.64 44	98.78 6	85.93 59	97.09 21	96.73 98	90.27 47	97.04 21	98.05 27	91.47 9	99.55 20	95.62 34	99.08 7	98.45 41
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
mPP-MVS		93.99 56	93.78 66	94.63 45	98.50 19	85.90 64	96.87 31	96.91 75	88.70 109	91.83 134	97.17 67	83.96 85	99.55 20	91.44 119	98.64 48	98.43 43

PHI-MVS		93.89 60	93.65 74	94.62 46	96.84 85	86.43 40	96.69 37	97.49 11	85.15 239	93.56 82	96.28 106	85.60 58	99.31 47	92.45 83	98.79 27	98.12 81

TSAR-MVS + MP.		94.85 19	94.94 24	94.58 47	98.25 35	86.33 43	96.11 67	96.62 108	88.14 129	96.10 36	96.96 76	89.09 21	98.94 92	94.48 50	98.68 40	98.48 35
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CANet		93.54 69	93.20 83	94.55 48	95.65 141	85.73 72	94.94 158	96.69 104	91.89 12	90.69 166	95.88 138	81.99 122	99.54 24	93.14 70	97.95 83	98.39 45

train_agg		93.44 75	93.08 85	94.52 49	97.53 67	86.49 38	94.07 230	96.78 90	81.86 327	92.77 101	96.20 109	87.63 33	99.12 63	92.14 98	98.69 38	97.94 98

CDPH-MVS		92.83 94	92.30 102	94.44 50	97.79 58	86.11 53	94.06 232	96.66 105	80.09 358	92.77 101	96.63 94	86.62 45	99.04 69	87.40 190	98.66 44	98.17 74

3Dnovator	86.66 5	91.73 122	90.82 141	94.44 50	94.59 209	86.37 42	97.18 17	97.02 62	89.20 87	84.31 329	96.66 90	73.74 257	99.17 57	86.74 200	97.96 82	97.79 122

SR-MVS		94.23 44	94.17 54	94.43 52	98.21 38	85.78 70	96.40 43	96.90 76	88.20 127	94.33 62	97.40 53	84.75 77	99.03 70	93.35 67	97.99 81	98.48 35

HPM-MVS		94.02 54	93.88 61	94.43 52	98.39 28	85.78 70	97.25 15	97.07 60	86.90 184	92.62 110	96.80 86	84.85 75	99.17 57	92.43 84	98.65 47	98.33 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TSAR-MVS + GP.		93.66 67	93.41 78	94.41 54	96.59 92	86.78 27	94.40 202	93.93 319	89.77 66	94.21 64	95.59 159	87.35 38	98.61 135	92.72 78	96.15 136	97.83 118

reproduce-ours		94.82 20	94.97 22	94.38 55	97.91 53	85.46 75	95.86 91	97.15 51	89.82 59	95.23 53	98.10 14	87.09 41	99.37 37	95.30 38	98.25 66	98.30 55

our_new_method		94.82 20	94.97 22	94.38 55	97.91 53	85.46 75	95.86 91	97.15 51	89.82 59	95.23 53	98.10 14	87.09 41	99.37 37	95.30 38	98.25 66	98.30 55

NormalMVS		93.46 72	93.16 84	94.37 57	98.40 26	86.20 50	96.30 47	96.27 136	91.65 17	92.68 106	96.13 120	77.97 186	98.84 106	90.75 131	98.26 62	98.07 83

test12				94.34 58	97.13 80	86.15 52		96.29 132		91.04 162		85.08 67	99.01 75		98.13 74	97.86 113

SymmetryMVS		92.81 96	92.31 101	94.32 59	96.15 108	86.20 50	96.30 47	94.43 297	91.65 17	92.68 106	96.13 120	77.97 186	98.84 106	90.75 131	94.72 169	97.92 107

ACMMP		93.24 84	92.88 90	94.30 60	98.09 44	85.33 79	96.86 32	97.45 19	88.33 120	90.15 183	97.03 74	81.44 130	99.51 28	90.85 130	95.74 145	98.04 90
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
reproduce_model		94.76 24	94.92 25	94.29 61	97.92 49	85.18 81	95.95 85	97.19 44	89.67 69	95.27 52	98.16 6	86.53 48	99.36 40	95.42 37	98.15 72	98.33 50

DeepC-MVS	88.79 3	93.31 81	92.99 88	94.26 62	96.07 118	85.83 68	94.89 161	96.99 63	89.02 97	89.56 192	97.37 55	82.51 106	99.38 35	92.20 95	98.30 60	97.57 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCFI-Net		93.03 91	92.63 95	94.23 63	95.62 144	85.92 61	96.08 69	96.33 130	89.86 57	93.89 75	94.66 210	82.11 117	98.50 141	92.33 91	92.82 236	98.27 64

fmvsm_l_conf0.5_n_3		94.80 23	95.01 21	94.15 64	95.64 142	85.08 82	96.09 68	97.36 28	90.98 24	97.09 19	98.12 10	84.98 73	98.94 92	97.07 17	97.80 91	98.43 43

EPNet		91.79 113	91.02 135	94.10 65	90.10 413	85.25 80	96.03 76	92.05 379	92.83 5	87.39 240	95.78 149	79.39 166	99.01 75	88.13 177	97.48 99	98.05 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
lecture		95.10 14	95.46 9	94.01 66	98.40 26	84.36 107	97.70 3	97.78 3	91.19 20	96.22 34	98.08 21	86.64 44	99.37 37	94.91 45	98.26 62	98.29 60

test_fmvsmconf_n		94.60 28	94.81 30	93.98 67	94.62 205	84.96 85	96.15 62	97.35 29	89.37 79	96.03 39	98.11 11	86.36 49	99.01 75	97.45 10	97.83 89	97.96 96

DELS-MVS		93.43 79	93.25 81	93.97 68	95.42 152	85.04 83	93.06 296	97.13 54	90.74 33	91.84 132	95.09 187	86.32 50	99.21 55	91.22 121	98.45 55	97.65 131
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
DP-MVS Recon		91.95 110	91.28 129	93.96 69	98.33 33	85.92 61	94.66 181	96.66 105	82.69 305	90.03 185	95.82 145	82.30 111	99.03 70	84.57 235	96.48 129	96.91 190

HPM-MVS_fast		93.40 80	93.22 82	93.94 70	98.36 31	84.83 87	97.15 18	96.80 89	85.77 212	92.47 114	97.13 69	82.38 107	99.07 65	90.51 136	98.40 57	97.92 107

test_fmvsmconf0.1_n		94.20 47	94.31 43	93.88 71	92.46 327	84.80 88	96.18 59	96.82 85	89.29 84	95.68 46	98.11 11	85.10 66	98.99 82	97.38 11	97.75 95	97.86 113

SD-MVS		94.96 18	95.33 12	93.88 71	97.25 79	86.69 29	96.19 57	97.11 58	90.42 39	96.95 23	97.27 58	89.53 15	96.91 318	94.38 51	98.85 20	98.03 91
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
MVS_111021_HR		93.45 74	93.31 79	93.84 73	96.99 82	84.84 86	93.24 287	97.24 41	88.76 106	91.60 140	95.85 142	86.07 54	98.66 125	91.91 109	98.16 70	98.03 91

SR-MVS-dyc-post		93.82 62	93.82 63	93.82 74	97.92 49	84.57 94	96.28 51	96.76 93	87.46 162	93.75 76	97.43 51	84.24 82	99.01 75	92.73 76	97.80 91	97.88 111

test_prior				93.82 74	97.29 77	84.49 98		96.88 78					98.87 100			98.11 82

APD-MVS_3200maxsize		93.78 63	93.77 67	93.80 76	97.92 49	84.19 111	96.30 47	96.87 79	86.96 180	93.92 74	97.47 49	83.88 86	98.96 89	92.71 79	97.87 87	98.26 68

fmvsm_l_conf0.5_n		94.29 41	94.46 36	93.79 77	95.28 158	85.43 77	95.68 107	96.43 121	86.56 192	96.84 25	97.81 39	87.56 36	98.77 115	97.14 15	96.82 119	97.16 169

CSCG		93.23 85	93.05 86	93.76 78	98.04 46	84.07 113	96.22 56	97.37 27	84.15 264	90.05 184	95.66 155	87.77 30	99.15 61	89.91 147	98.27 61	98.07 83

GDP-MVS		92.04 108	91.46 123	93.75 79	94.55 215	84.69 91	95.60 118	96.56 113	87.83 150	93.07 92	95.89 137	73.44 261	98.65 127	90.22 140	96.03 138	97.91 109

BP-MVS1		92.48 101	92.07 105	93.72 80	94.50 219	84.39 106	95.90 89	94.30 304	90.39 40	92.67 108	95.94 133	74.46 240	98.65 127	93.14 70	97.35 103	98.13 78

test_fmvsmconf0.01_n		93.19 86	93.02 87	93.71 81	89.25 426	84.42 105	96.06 73	96.29 132	89.06 92	94.68 58	98.13 7	79.22 168	98.98 86	97.22 13	97.24 105	97.74 125

UA-Net		92.83 94	92.54 97	93.68 82	96.10 115	84.71 90	95.66 110	96.39 125	91.92 11	93.22 87	96.49 100	83.16 95	98.87 100	84.47 237	95.47 152	97.45 144

fmvsm_l_conf0.5_n_a		94.20 47	94.40 38	93.60 83	95.29 157	84.98 84	95.61 115	96.28 135	86.31 198	96.75 28	97.86 37	87.40 37	98.74 119	97.07 17	97.02 110	97.07 174

QAPM		89.51 193	88.15 220	93.59 84	94.92 181	84.58 93	96.82 34	96.70 103	78.43 385	83.41 352	96.19 113	73.18 266	99.30 48	77.11 361	96.54 126	96.89 191

test_fmvsm_n_1920		94.71 26	95.11 19	93.50 85	95.79 133	84.62 92	96.15 62	97.64 5	89.85 58	97.19 16	97.89 35	86.28 51	98.71 122	97.11 16	98.08 78	97.17 162

fmvsm_s_conf0.5_n_9		94.99 16	95.50 8	93.44 86	96.51 100	82.25 185	95.76 102	96.92 73	93.37 3	97.63 7	98.43 1	84.82 76	99.16 60	98.15 1	97.92 84	98.90 15

KinetiMVS		91.82 112	91.30 127	93.39 87	94.72 197	83.36 138	95.45 122	96.37 127	90.33 42	92.17 119	96.03 127	72.32 278	98.75 116	87.94 180	96.34 131	98.07 83

casdiffmvs_mvg		92.96 93	92.83 91	93.35 88	94.59 209	83.40 136	95.00 155	96.34 129	90.30 45	92.05 122	96.05 124	83.43 89	98.15 177	92.07 100	95.67 146	98.49 34
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_5		93.96 58	94.18 53	93.30 89	94.79 190	83.81 122	95.77 100	96.74 97	88.02 137	96.23 33	97.84 38	83.36 93	98.83 109	97.49 8	97.34 104	97.25 155

EI-MVSNet-Vis-set		93.01 92	92.92 89	93.29 90	95.01 172	83.51 133	94.48 190	95.77 197	90.87 25	92.52 112	96.67 89	84.50 79	99.00 80	91.99 105	94.44 182	97.36 147

Vis-MVSNet		91.75 120	91.23 130	93.29 90	95.32 156	83.78 123	96.14 64	95.98 176	89.89 55	90.45 170	96.58 97	75.09 229	98.31 168	84.75 229	96.90 115	97.78 123
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
BridgeMVS		93.98 57	94.22 48	93.26 92	96.13 110	83.29 140	96.27 53	96.52 116	89.82 59	95.56 48	95.51 162	84.50 79	98.79 113	94.83 46	98.86 19	97.72 127

SPE-MVS-test		94.02 54	94.29 44	93.24 93	96.69 88	83.24 141	97.49 6	96.92 73	92.14 9	92.90 94	95.77 150	85.02 69	98.33 165	93.03 72	98.62 49	98.13 78

VNet		92.24 106	91.91 108	93.24 93	96.59 92	83.43 134	94.84 167	96.44 120	89.19 88	94.08 71	95.90 136	77.85 192	98.17 175	88.90 167	93.38 218	98.13 78

fmvsm_s_conf0.5_n_10		94.43 36	94.84 29	93.20 95	95.73 136	83.19 144	95.99 79	97.31 36	91.08 21	97.67 4	98.11 11	81.87 124	99.22 53	97.86 4	97.91 86	97.20 160

VDD-MVS		90.74 150	89.92 165	93.20 95	96.27 105	83.02 156	95.73 104	93.86 323	88.42 119	92.53 111	96.84 81	62.09 392	98.64 130	90.95 127	92.62 243	97.93 106

Elysia		90.12 170	89.10 188	93.18 97	93.16 296	84.05 115	95.22 138	96.27 136	85.16 237	90.59 167	94.68 206	64.64 371	98.37 158	86.38 206	95.77 143	97.12 171

StellarMVS		90.12 170	89.10 188	93.18 97	93.16 296	84.05 115	95.22 138	96.27 136	85.16 237	90.59 167	94.68 206	64.64 371	98.37 158	86.38 206	95.77 143	97.12 171

CS-MVS		94.12 51	94.44 37	93.17 99	96.55 95	83.08 153	97.63 4	96.95 70	91.71 15	93.50 84	96.21 108	85.61 57	98.24 170	93.64 61	98.17 69	98.19 72

nrg030		91.08 145	90.39 149	93.17 99	93.07 303	86.91 23	96.41 42	96.26 140	88.30 122	88.37 217	94.85 200	82.19 116	97.64 241	91.09 122	82.95 369	94.96 276

MVSMamba_PlusPlus		93.44 75	93.54 76	93.14 101	96.58 94	83.05 154	96.06 73	96.50 118	84.42 261	94.09 68	95.56 161	85.01 72	98.69 124	94.96 44	98.66 44	97.67 130

EI-MVSNet-UG-set		92.74 97	92.62 96	93.12 102	94.86 186	83.20 143	94.40 202	95.74 200	90.71 35	92.05 122	96.60 96	84.00 84	98.99 82	91.55 117	93.63 207	97.17 162

test_fmvsmvis_n_1920		93.44 75	93.55 75	93.10 103	93.67 282	84.26 109	95.83 95	96.14 160	89.00 99	92.43 115	97.50 48	83.37 92	98.72 120	96.61 24	97.44 100	96.32 216

新几何1				93.10 103	97.30 76	84.35 108		95.56 218	71.09 462	91.26 150	96.24 107	82.87 102	98.86 102	79.19 339	98.10 75	96.07 232

OMC-MVS		91.23 136	90.62 146	93.08 105	96.27 105	84.07 113	93.52 269	95.93 182	86.95 181	89.51 193	96.13 120	78.50 180	98.35 162	85.84 215	92.90 232	96.83 198

OpenMVS	83.78 11	88.74 223	87.29 242	93.08 105	92.70 321	85.39 78	96.57 40	96.43 121	78.74 380	80.85 384	96.07 123	69.64 315	99.01 75	78.01 352	96.65 124	94.83 284

MAR-MVS		90.30 166	89.37 181	93.07 107	96.61 91	84.48 99	95.68 107	95.67 209	82.36 310	87.85 227	92.85 280	76.63 205	98.80 111	80.01 319	96.68 123	95.91 238
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
lupinMVS		90.92 146	90.21 153	93.03 108	93.86 267	83.88 120	92.81 307	93.86 323	79.84 361	91.76 136	94.29 227	77.92 189	98.04 199	90.48 137	97.11 106	97.17 162

Effi-MVS+		91.59 130	91.11 132	93.01 109	94.35 234	83.39 137	94.60 183	95.10 254	87.10 175	90.57 169	93.10 275	81.43 131	98.07 193	89.29 159	94.48 180	97.59 136

fmvsm_s_conf0.5_n_a		93.57 68	93.76 68	93.00 110	95.02 171	83.67 126	96.19 57	96.10 166	87.27 168	95.98 40	98.05 27	83.07 99	98.45 151	96.68 23	95.51 149	96.88 192

MVS_111021_LR		92.47 102	92.29 103	92.98 111	95.99 125	84.43 103	93.08 293	96.09 167	88.20 127	91.12 155	95.72 153	81.33 132	97.76 230	91.74 113	97.37 102	96.75 200

fmvsm_s_conf0.1_n_a		93.19 86	93.26 80	92.97 112	92.49 325	83.62 129	96.02 77	95.72 204	86.78 186	96.04 38	98.19 4	82.30 111	98.43 155	96.38 25	95.42 155	96.86 193

ETV-MVS		92.74 97	92.66 94	92.97 112	95.20 164	84.04 117	95.07 150	96.51 117	90.73 34	92.96 93	91.19 341	84.06 83	98.34 163	91.72 114	96.54 126	96.54 211

LFMVS		90.08 173	89.13 187	92.95 114	96.71 87	82.32 184	96.08 69	89.91 437	86.79 185	92.15 121	96.81 84	62.60 390	98.34 163	87.18 194	93.90 196	98.19 72

UGNet		89.95 180	88.95 196	92.95 114	94.51 217	83.31 139	95.70 106	95.23 246	89.37 79	87.58 234	93.94 243	64.00 379	98.78 114	83.92 245	96.31 132	96.74 201
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
jason		90.80 148	90.10 157	92.90 116	93.04 306	83.53 132	93.08 293	94.15 312	80.22 355	91.41 146	94.91 194	76.87 199	97.93 219	90.28 138	96.90 115	97.24 156
jason: jason.
DP-MVS		87.25 277	85.36 316	92.90 116	97.65 64	83.24 141	94.81 169	92.00 381	74.99 429	81.92 373	95.00 190	72.66 271	99.05 67	66.92 442	92.33 248	96.40 213

fmvsm_s_conf0.5_n_8		94.56 30	95.12 18	92.87 118	95.96 128	81.32 215	95.76 102	97.57 7	93.48 2	97.53 10	98.32 3	81.78 127	99.13 62	97.91 2	97.81 90	98.16 75

fmvsm_s_conf0.5_n		93.76 64	94.06 58	92.86 119	95.62 144	83.17 145	96.14 64	96.12 164	88.13 130	95.82 43	98.04 30	83.43 89	98.48 143	96.97 21	96.23 133	96.92 189

fmvsm_s_conf0.1_n		93.46 72	93.66 73	92.85 120	93.75 274	83.13 147	96.02 77	95.74 200	87.68 156	95.89 41	98.17 5	82.78 103	98.46 147	96.71 22	96.17 135	96.98 183

casdiffseed414692147		91.11 143	90.55 147	92.81 121	94.27 242	82.58 177	94.81 169	96.03 174	87.93 143	90.17 181	95.62 157	78.51 179	97.90 223	84.18 241	93.45 216	97.94 98

CANet_DTU		90.26 168	89.41 180	92.81 121	93.46 289	83.01 157	93.48 270	94.47 296	89.43 77	87.76 232	94.23 232	70.54 303	99.03 70	84.97 224	96.39 130	96.38 214

MVSFormer		91.68 128	91.30 127	92.80 123	93.86 267	83.88 120	95.96 83	95.90 186	84.66 257	91.76 136	94.91 194	77.92 189	97.30 283	89.64 155	97.11 106	97.24 156

PVSNet_Blended_VisFu		91.38 133	90.91 138	92.80 123	96.39 102	83.17 145	94.87 163	96.66 105	83.29 288	89.27 199	94.46 222	80.29 143	99.17 57	87.57 187	95.37 156	96.05 235

fmvsm_l_conf0.5_n_9		94.65 27	95.28 15	92.77 125	95.95 129	81.83 197	95.53 120	97.12 55	91.68 16	97.89 1	98.06 24	85.71 56	98.65 127	97.32 12	98.26 62	97.83 118

LuminaMVS		90.55 162	89.81 167	92.77 125	92.78 319	84.21 110	94.09 228	94.17 311	85.82 209	91.54 141	94.14 234	69.93 309	97.92 220	91.62 116	94.21 190	96.18 224

balanced_ft_v1		92.23 107	92.05 106	92.77 125	95.40 153	81.78 201	95.80 96	95.69 208	87.94 141	91.92 129	95.04 188	75.91 217	98.71 122	93.83 58	96.94 112	97.82 120

fmvsm_s_conf0.5_n_6		94.11 52	94.56 33	92.76 128	94.98 176	81.96 194	95.79 98	97.29 39	89.31 82	97.52 11	97.61 44	83.25 94	98.88 99	97.05 19	98.22 68	97.43 146

VDDNet		89.56 192	88.49 211	92.76 128	95.07 170	82.09 188	96.30 47	93.19 347	81.05 349	91.88 130	96.86 80	61.16 408	98.33 165	88.43 174	92.49 247	97.84 117

viewdifsd2359ckpt09		91.18 139	90.65 145	92.75 130	94.61 208	82.36 183	94.32 211	95.74 200	84.72 254	89.66 191	95.15 185	79.69 161	98.04 199	87.70 184	94.27 189	97.85 116

h-mvs33		90.80 148	90.15 156	92.75 130	96.01 121	82.66 170	95.43 123	95.53 222	89.80 62	93.08 90	95.64 156	75.77 218	99.00 80	92.07 100	78.05 426	96.60 206

hybridcas		92.43 103	92.33 100	92.74 132	94.51 217	81.84 196	95.05 153	96.16 158	89.60 71	91.40 147	96.20 109	82.23 113	98.09 188	89.95 146	95.87 140	98.28 61

casdiffmvs		92.51 100	92.43 99	92.74 132	94.41 229	81.98 192	94.54 187	96.23 144	89.57 73	91.96 126	96.17 114	82.58 105	98.01 206	90.95 127	95.45 154	98.23 70
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_yl		90.69 153	90.02 163	92.71 134	95.72 137	82.41 181	94.11 224	95.12 252	85.63 216	91.49 143	94.70 204	74.75 233	98.42 156	86.13 210	92.53 245	97.31 148

DCV-MVSNet		90.69 153	90.02 163	92.71 134	95.72 137	82.41 181	94.11 224	95.12 252	85.63 216	91.49 143	94.70 204	74.75 233	98.42 156	86.13 210	92.53 245	97.31 148

PCF-MVS	84.11 10	87.74 251	86.08 289	92.70 136	94.02 256	84.43 103	89.27 414	95.87 191	73.62 444	84.43 321	94.33 224	78.48 182	98.86 102	70.27 416	94.45 181	94.81 285
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n_11		94.60 28	95.23 16	92.69 137	96.05 120	82.00 190	96.31 46	96.71 101	92.27 8	96.68 30	98.39 2	85.32 63	98.92 95	97.20 14	98.16 70	97.17 162

SSM_0404		90.73 151	90.08 158	92.69 137	95.00 175	83.13 147	94.32 211	95.00 262	85.41 227	89.84 186	95.35 171	76.13 208	97.98 211	85.46 220	94.18 191	96.95 185

baseline		92.39 105	92.29 103	92.69 137	94.46 224	81.77 202	94.14 221	96.27 136	89.22 86	91.88 130	96.00 128	82.35 108	97.99 208	91.05 123	95.27 160	98.30 55

MSLP-MVS++		93.72 66	94.08 55	92.65 140	97.31 75	83.43 134	95.79 98	97.33 32	90.03 52	93.58 80	96.96 76	84.87 74	97.76 230	92.19 96	98.66 44	96.76 199

EC-MVSNet		93.44 75	93.71 71	92.63 141	95.21 163	82.43 178	97.27 14	96.71 101	90.57 38	92.88 95	95.80 146	83.16 95	98.16 176	93.68 59	98.14 73	97.31 148

ab-mvs		89.41 200	88.35 213	92.60 142	95.15 168	82.65 174	92.20 334	95.60 216	83.97 268	88.55 213	93.70 257	74.16 248	98.21 174	82.46 269	89.37 292	96.94 187

LS3D		87.89 246	86.32 278	92.59 143	96.07 118	82.92 160	95.23 136	94.92 271	75.66 421	82.89 359	95.98 130	72.48 275	99.21 55	68.43 430	95.23 161	95.64 252

Anonymous20240529		88.09 242	86.59 267	92.58 144	96.53 97	81.92 195	95.99 79	95.84 193	74.11 439	89.06 203	95.21 180	61.44 400	98.81 110	83.67 252	87.47 323	97.01 181

fmvsm_s_conf0.5_n_3		94.49 32	95.13 17	92.56 145	95.49 150	81.10 225	95.93 86	97.16 50	92.96 4	97.39 12	98.13 7	83.63 88	98.80 111	97.89 3	97.61 98	97.78 123

CPTT-MVS		91.99 109	91.80 109	92.55 146	98.24 37	81.98 192	96.76 35	96.49 119	81.89 326	90.24 175	96.44 103	78.59 177	98.61 135	89.68 153	97.85 88	97.06 175

viewdifsd2359ckpt13		91.20 138	90.75 143	92.54 147	94.30 240	82.13 187	94.03 234	95.89 188	85.60 218	90.20 177	95.36 170	79.69 161	97.90 223	87.85 182	93.86 197	97.61 133

114514_t		89.51 193	88.50 209	92.54 147	98.11 42	81.99 191	95.16 146	96.36 128	70.19 466	85.81 274	95.25 176	76.70 203	98.63 132	82.07 279	96.86 118	97.00 182

PAPM_NR		91.22 137	90.78 142	92.52 149	97.60 65	81.46 211	94.37 208	96.24 143	86.39 197	87.41 237	94.80 202	82.06 120	98.48 143	82.80 264	95.37 156	97.61 133

mamba_0408		89.06 213	87.92 227	92.50 150	94.76 191	82.66 170	79.84 486	94.64 289	85.18 232	88.96 205	95.00 190	76.00 213	97.98 211	83.74 249	93.15 226	96.85 194

DeepPCF-MVS	89.96 1	94.20 47	94.77 31	92.49 151	96.52 98	80.00 276	94.00 239	97.08 59	90.05 51	95.65 47	97.29 57	89.66 14	98.97 87	93.95 55	98.71 35	98.50 32

SSM_0407		90.47 164	89.80 168	92.46 152	94.76 191	82.66 170	93.98 241	95.00 262	85.41 227	88.96 205	95.35 171	76.13 208	97.88 225	85.46 220	93.15 226	96.85 194

IS-MVSNet		91.43 132	91.09 134	92.46 152	95.87 132	81.38 214	96.95 24	93.69 336	89.72 68	89.50 195	95.98 130	78.57 178	97.77 229	83.02 258	96.50 128	98.22 71

API-MVS		90.66 157	90.07 159	92.45 154	96.36 103	84.57 94	96.06 73	95.22 248	82.39 308	89.13 200	94.27 230	80.32 142	98.46 147	80.16 317	96.71 122	94.33 308

xiu_mvs_v1_base_debu		90.64 158	90.05 160	92.40 155	93.97 262	84.46 100	93.32 278	95.46 226	85.17 234	92.25 116	94.03 235	70.59 299	98.57 138	90.97 124	94.67 171	94.18 312

xiu_mvs_v1_base		90.64 158	90.05 160	92.40 155	93.97 262	84.46 100	93.32 278	95.46 226	85.17 234	92.25 116	94.03 235	70.59 299	98.57 138	90.97 124	94.67 171	94.18 312

xiu_mvs_v1_base_debi		90.64 158	90.05 160	92.40 155	93.97 262	84.46 100	93.32 278	95.46 226	85.17 234	92.25 116	94.03 235	70.59 299	98.57 138	90.97 124	94.67 171	94.18 312

fmvsm_s_conf0.5_n_2		93.47 71	93.83 62	92.39 158	95.36 154	81.19 221	95.20 143	96.56 113	90.37 41	97.13 18	98.03 31	77.47 195	98.96 89	97.79 6	96.58 125	97.03 178

viewmacassd2359aftdt		91.67 129	91.43 125	92.37 159	93.95 265	81.00 229	93.90 249	95.97 179	87.75 154	91.45 145	96.04 126	79.92 149	97.97 213	89.26 160	94.67 171	98.14 77

viewmanbaseed2359cas		91.78 116	91.58 115	92.37 159	94.32 237	81.07 226	93.76 255	95.96 180	87.26 169	91.50 142	95.88 138	80.92 138	97.97 213	89.70 152	94.92 165	98.07 83

fmvsm_s_conf0.1_n_2		93.16 88	93.42 77	92.37 159	94.62 205	81.13 223	95.23 136	95.89 188	90.30 45	96.74 29	98.02 32	76.14 207	98.95 91	97.64 7	96.21 134	97.03 178

AdaColmap		89.89 183	89.07 190	92.37 159	97.41 71	83.03 155	94.42 197	95.92 183	82.81 302	86.34 263	94.65 211	73.89 253	99.02 73	80.69 306	95.51 149	95.05 271

CNLPA		89.07 212	87.98 224	92.34 163	96.87 84	84.78 89	94.08 229	93.24 344	81.41 340	84.46 319	95.13 186	75.57 225	96.62 335	77.21 359	93.84 199	95.61 255

fmvsm_s_conf0.5_n_4		93.86 61	94.37 40	92.33 164	95.13 169	80.95 232	95.64 113	96.97 65	89.60 71	96.85 24	97.77 40	83.08 98	98.92 95	97.49 8	96.78 120	97.13 170

ET-MVSNet_ETH3D		87.51 265	85.91 297	92.32 165	93.70 281	83.93 118	92.33 327	90.94 413	84.16 263	72.09 464	92.52 293	69.90 310	95.85 387	89.20 161	88.36 310	97.17 162

E4		91.74 121	91.55 118	92.31 166	94.27 242	80.80 242	93.81 252	96.17 156	87.97 139	91.11 156	96.05 124	80.75 139	98.08 191	89.78 148	94.02 193	98.06 88

E2		91.79 113	91.61 113	92.31 166	94.49 220	80.86 238	93.74 257	96.19 149	87.63 159	91.16 151	95.94 133	81.31 133	98.06 194	89.76 149	94.29 187	97.99 93

Anonymous202405211		87.68 252	86.13 285	92.31 166	96.66 89	80.74 244	94.87 163	91.49 398	80.47 354	89.46 196	95.44 165	54.72 449	98.23 171	82.19 275	89.89 282	97.97 95

E3		91.78 116	91.61 113	92.30 169	94.48 221	80.86 238	93.73 258	96.19 149	87.63 159	91.16 151	95.95 132	81.30 134	98.06 194	89.76 149	94.29 187	97.99 93

CHOSEN 1792x2688		88.84 219	87.69 232	92.30 169	96.14 109	81.42 213	90.01 401	95.86 192	74.52 434	87.41 237	93.94 243	75.46 226	98.36 160	80.36 312	95.53 148	97.12 171

viewcassd2359sk11		91.79 113	91.62 112	92.29 171	94.62 205	80.88 236	93.70 262	96.18 155	87.38 166	91.13 154	95.85 142	81.62 129	98.06 194	89.71 151	94.40 183	97.94 98

HY-MVS	83.01 12	89.03 215	87.94 226	92.29 171	94.86 186	82.77 162	92.08 339	94.49 295	81.52 339	86.93 244	92.79 286	78.32 184	98.23 171	79.93 320	90.55 269	95.88 241

CDS-MVSNet		89.45 196	88.51 208	92.29 171	93.62 284	83.61 131	93.01 297	94.68 287	81.95 321	87.82 230	93.24 269	78.69 175	96.99 312	80.34 313	93.23 223	96.28 219
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		90.02 176	89.27 186	92.29 171	95.78 134	80.95 232	92.68 312	96.22 145	81.91 323	86.66 254	93.75 255	82.23 113	98.44 153	79.40 338	94.79 168	97.48 142

E3new		91.76 119	91.58 115	92.28 175	94.69 202	80.90 235	93.68 265	96.17 156	87.15 172	91.09 161	95.70 154	81.75 128	98.05 198	89.67 154	94.35 184	97.90 110

mvsmamba		90.33 165	89.69 171	92.25 176	95.17 165	81.64 204	95.27 134	93.36 342	84.88 247	89.51 193	94.27 230	69.29 324	97.42 267	89.34 158	96.12 137	97.68 129

E5new		91.71 123	91.55 118	92.20 177	94.33 235	80.62 248	94.41 198	96.19 149	88.06 133	91.11 156	96.16 115	79.92 149	98.03 202	90.00 141	93.80 201	97.94 98

E6new		91.71 123	91.55 118	92.20 177	94.32 237	80.62 248	94.41 198	96.19 149	88.06 133	91.11 156	96.16 115	79.92 149	98.03 202	90.00 141	93.80 201	97.94 98

E6		91.71 123	91.55 118	92.20 177	94.32 237	80.62 248	94.41 198	96.19 149	88.06 133	91.11 156	96.16 115	79.92 149	98.03 202	90.00 141	93.80 201	97.94 98

E5		91.71 123	91.55 118	92.20 177	94.33 235	80.62 248	94.41 198	96.19 149	88.06 133	91.11 156	96.16 115	79.92 149	98.03 202	90.00 141	93.80 201	97.94 98

PLC	84.53 7	89.06 213	88.03 222	92.15 181	97.27 78	82.69 169	94.29 213	95.44 231	79.71 363	84.01 335	94.18 233	76.68 204	98.75 116	77.28 358	93.41 217	95.02 272
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPP-MVSNet		91.70 127	91.56 117	92.13 182	95.88 130	80.50 255	97.33 8	95.25 245	86.15 203	89.76 190	95.60 158	83.42 91	98.32 167	87.37 192	93.25 222	97.56 138

patch_mono-2		93.74 65	94.32 41	92.01 183	97.54 66	78.37 326	93.40 274	97.19 44	88.02 137	94.99 57	97.21 62	88.35 25	98.44 153	94.07 54	98.09 76	99.23 1

原ACMM1				92.01 183	97.34 73	81.05 227		96.81 88	78.89 374	90.45 170	95.92 135	82.65 104	98.84 106	80.68 307	98.26 62	96.14 226

UniMVSNet (Re)		89.80 186	89.07 190	92.01 183	93.60 285	84.52 97	94.78 172	97.47 16	89.26 85	86.44 260	92.32 299	82.10 118	97.39 278	84.81 228	80.84 403	94.12 316

MG-MVS		91.77 118	91.70 111	92.00 186	97.08 81	80.03 274	93.60 267	95.18 250	87.85 149	90.89 164	96.47 102	82.06 120	98.36 160	85.07 223	97.04 109	97.62 132

EIA-MVS		91.95 110	91.94 107	91.98 187	95.16 166	80.01 275	95.36 124	96.73 98	88.44 117	89.34 197	92.16 304	83.82 87	98.45 151	89.35 157	97.06 108	97.48 142

PVSNet_Blended		90.73 151	90.32 151	91.98 187	96.12 111	81.25 217	92.55 317	96.83 83	82.04 319	89.10 201	92.56 292	81.04 136	98.85 104	86.72 202	95.91 139	95.84 243

guyue		91.12 142	90.84 140	91.96 189	94.59 209	80.57 253	94.87 163	93.71 335	88.96 100	91.14 153	95.22 177	73.22 265	97.76 230	92.01 104	93.81 200	97.54 141

PS-MVSNAJ		91.18 139	90.92 137	91.96 189	95.26 161	82.60 176	92.09 338	95.70 206	86.27 199	91.84 132	92.46 294	79.70 158	98.99 82	89.08 162	95.86 141	94.29 309

TAMVS		89.21 206	88.29 217	91.96 189	93.71 279	82.62 175	93.30 282	94.19 309	82.22 313	87.78 231	93.94 243	78.83 172	96.95 315	77.70 354	92.98 231	96.32 216

SDMVSNet		90.19 169	89.61 174	91.93 192	96.00 122	83.09 152	92.89 304	95.98 176	88.73 107	86.85 250	95.20 181	72.09 282	97.08 303	88.90 167	89.85 284	95.63 253

FA-MVS(test-final)		89.66 188	88.91 198	91.93 192	94.57 213	80.27 259	91.36 359	94.74 284	84.87 248	89.82 187	92.61 291	74.72 236	98.47 146	83.97 244	93.53 211	97.04 177

MVS_Test		91.31 135	91.11 132	91.93 192	94.37 230	80.14 264	93.46 272	95.80 195	86.46 195	91.35 149	93.77 253	82.21 115	98.09 188	87.57 187	94.95 164	97.55 139

NR-MVSNet		88.58 229	87.47 238	91.93 192	93.04 306	84.16 112	94.77 173	96.25 142	89.05 93	80.04 398	93.29 267	79.02 170	97.05 308	81.71 290	80.05 413	94.59 292

HyFIR lowres test		88.09 242	86.81 255	91.93 192	96.00 122	80.63 246	90.01 401	95.79 196	73.42 446	87.68 233	92.10 310	73.86 254	97.96 215	80.75 305	91.70 252	97.19 161

GeoE		90.05 174	89.43 179	91.90 197	95.16 166	80.37 258	95.80 96	94.65 288	83.90 269	87.55 236	94.75 203	78.18 185	97.62 243	81.28 295	93.63 207	97.71 128

thisisatest0530		88.67 224	87.61 234	91.86 198	94.87 185	80.07 269	94.63 182	89.90 438	84.00 267	88.46 215	93.78 252	66.88 348	98.46 147	83.30 254	92.65 238	97.06 175

xiu_mvs_v2_base		91.13 141	90.89 139	91.86 198	94.97 177	82.42 179	92.24 331	95.64 214	86.11 207	91.74 138	93.14 273	79.67 163	98.89 98	89.06 163	95.46 153	94.28 310

DU-MVS		89.34 205	88.50 209	91.85 200	93.04 306	83.72 124	94.47 193	96.59 110	89.50 74	86.46 257	93.29 267	77.25 197	97.23 292	84.92 225	81.02 399	94.59 292

AstraMVS		90.69 153	90.30 152	91.84 201	93.81 270	79.85 282	94.76 174	92.39 367	88.96 100	91.01 163	95.87 141	70.69 297	97.94 218	92.49 82	92.70 237	97.73 126

OPM-MVS		90.12 170	89.56 175	91.82 202	93.14 298	83.90 119	94.16 220	95.74 200	88.96 100	87.86 226	95.43 167	72.48 275	97.91 221	88.10 179	90.18 276	93.65 349
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		90.60 161	90.19 154	91.82 202	94.70 200	82.73 166	95.85 93	96.22 145	90.81 27	86.91 246	94.86 198	74.23 244	98.12 178	88.15 175	89.99 278	94.63 289

UniMVSNet_NR-MVSNet		89.92 182	89.29 184	91.81 204	93.39 291	83.72 124	94.43 196	97.12 55	89.80 62	86.46 257	93.32 264	83.16 95	97.23 292	84.92 225	81.02 399	94.49 302

diffmvs		91.37 134	91.23 130	91.77 205	93.09 301	80.27 259	92.36 323	95.52 223	87.03 177	91.40 147	94.93 193	80.08 146	97.44 265	92.13 99	94.56 177	97.61 133
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs_AUTHOR		91.51 131	91.44 124	91.73 206	93.09 301	80.27 259	92.51 318	95.58 217	87.22 170	91.80 135	95.57 160	79.96 148	97.48 257	92.23 93	94.97 163	97.45 144

1112_ss		88.42 231	87.33 241	91.72 207	94.92 181	80.98 230	92.97 301	94.54 292	78.16 391	83.82 338	93.88 248	78.78 174	97.91 221	79.45 334	89.41 291	96.26 220

Fast-Effi-MVS+		89.41 200	88.64 204	91.71 208	94.74 194	80.81 241	93.54 268	95.10 254	83.11 292	86.82 252	90.67 364	79.74 157	97.75 234	80.51 310	93.55 209	96.57 209

WTY-MVS		89.60 190	88.92 197	91.67 209	95.47 151	81.15 222	92.38 322	94.78 282	83.11 292	89.06 203	94.32 225	78.67 176	96.61 338	81.57 291	90.89 265	97.24 156

TAPA-MVS	84.62 6	88.16 240	87.01 250	91.62 210	96.64 90	80.65 245	94.39 204	96.21 148	76.38 413	86.19 267	95.44 165	79.75 156	98.08 191	62.75 460	95.29 158	96.13 227
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VPA-MVSNet		89.62 189	88.96 195	91.60 211	93.86 267	82.89 161	95.46 121	97.33 32	87.91 144	88.43 216	93.31 265	74.17 247	97.40 275	87.32 193	82.86 374	94.52 297

FE-MVS		87.40 270	86.02 291	91.57 212	94.56 214	79.69 289	90.27 388	93.72 334	80.57 352	88.80 209	91.62 330	65.32 364	98.59 137	74.97 384	94.33 186	96.44 212

XVG-OURS		89.40 202	88.70 203	91.52 213	94.06 254	81.46 211	91.27 364	96.07 169	86.14 204	88.89 208	95.77 150	68.73 333	97.26 289	87.39 191	89.96 280	95.83 244

hse-mvs2		89.88 184	89.34 182	91.51 214	94.83 188	81.12 224	93.94 243	93.91 322	89.80 62	93.08 90	93.60 258	75.77 218	97.66 238	92.07 100	77.07 433	95.74 248

TranMVSNet+NR-MVSNet		88.84 219	87.95 225	91.49 215	92.68 322	83.01 157	94.92 160	96.31 131	89.88 56	85.53 283	93.85 250	76.63 205	96.96 314	81.91 283	79.87 416	94.50 300

AUN-MVS		87.78 250	86.54 270	91.48 216	94.82 189	81.05 227	93.91 247	93.93 319	83.00 297	86.93 244	93.53 259	69.50 318	97.67 236	86.14 208	77.12 432	95.73 250

XVG-OURS-SEG-HR		89.95 180	89.45 177	91.47 217	94.00 260	81.21 220	91.87 343	96.06 171	85.78 211	88.55 213	95.73 152	74.67 237	97.27 287	88.71 171	89.64 289	95.91 238

MVS		87.44 268	86.10 288	91.44 218	92.61 324	83.62 129	92.63 314	95.66 211	67.26 472	81.47 376	92.15 305	77.95 188	98.22 173	79.71 323	95.48 151	92.47 400

hybrid		90.69 153	90.45 148	91.43 219	92.67 323	79.42 297	92.28 330	95.21 249	85.15 239	90.39 173	95.37 169	78.93 171	97.32 282	90.27 139	93.74 205	97.55 139

viewdifsd2359ckpt07		91.11 143	91.02 135	91.41 220	94.21 247	78.37 326	92.91 303	95.71 205	87.50 161	90.32 174	95.88 138	80.27 144	97.99 208	88.78 170	93.55 209	97.86 113

F-COLMAP		87.95 245	86.80 256	91.40 221	96.35 104	80.88 236	94.73 176	95.45 229	79.65 364	82.04 371	94.61 212	71.13 289	98.50 141	76.24 371	91.05 263	94.80 286

dcpmvs_2		93.49 70	94.19 52	91.38 222	97.69 63	76.78 369	94.25 215	96.29 132	88.33 120	94.46 60	96.88 79	88.07 29	98.64 130	93.62 62	98.09 76	98.73 23

thisisatest0515		87.33 273	85.99 292	91.37 223	93.49 287	79.55 290	90.63 380	89.56 446	80.17 356	87.56 235	90.86 354	67.07 345	98.28 169	81.50 292	93.02 230	96.29 218

HQP-MVS		89.80 186	89.28 185	91.34 224	94.17 249	81.56 205	94.39 204	96.04 172	88.81 103	85.43 292	93.97 242	73.83 255	97.96 215	87.11 197	89.77 287	94.50 300

fmvsm_s_conf0.5_n_7		93.15 89	93.76 68	91.31 225	94.42 228	79.48 292	94.52 188	97.14 53	89.33 81	94.17 66	98.09 18	81.83 125	97.49 256	96.33 26	98.02 80	96.95 185

RRT-MVS		90.85 147	90.70 144	91.30 226	94.25 244	76.83 368	94.85 166	96.13 163	89.04 94	90.23 176	94.88 196	70.15 308	98.72 120	91.86 112	94.88 166	98.34 48

FMVSNet3		87.40 270	86.11 287	91.30 226	93.79 273	83.64 128	94.20 219	94.81 280	83.89 270	84.37 322	91.87 321	68.45 336	96.56 347	78.23 349	85.36 342	93.70 348

FMVSNet2		87.19 283	85.82 300	91.30 226	94.01 257	83.67 126	94.79 171	94.94 266	83.57 278	83.88 337	92.05 314	66.59 353	96.51 351	77.56 356	85.01 345	93.73 346

RPMNet		83.95 362	81.53 373	91.21 229	90.58 401	79.34 302	85.24 464	96.76 93	71.44 460	85.55 281	82.97 464	70.87 294	98.91 97	61.01 464	89.36 293	95.40 259

IB-MVS	80.51 15	85.24 339	83.26 357	91.19 230	92.13 336	79.86 281	91.75 347	91.29 403	83.28 289	80.66 388	88.49 413	61.28 402	98.46 147	80.99 301	79.46 420	95.25 265
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
CLD-MVS		89.47 195	88.90 199	91.18 231	94.22 246	82.07 189	92.13 336	96.09 167	87.90 145	85.37 298	92.45 295	74.38 242	97.56 248	87.15 195	90.43 271	93.93 326
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LPG-MVS_test		89.45 196	88.90 199	91.12 232	94.47 222	81.49 209	95.30 129	96.14 160	86.73 188	85.45 289	95.16 183	69.89 311	98.10 180	87.70 184	89.23 296	93.77 342

LGP-MVS_train				91.12 232	94.47 222	81.49 209		96.14 160	86.73 188	85.45 289	95.16 183	69.89 311	98.10 180	87.70 184	89.23 296	93.77 342

ACMM	84.12 9	89.14 208	88.48 212	91.12 232	94.65 204	81.22 219	95.31 127	96.12 164	85.31 231	85.92 272	94.34 223	70.19 307	98.06 194	85.65 216	88.86 301	94.08 320
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tttt0517		88.61 226	87.78 231	91.11 235	94.96 178	77.81 344	95.35 125	89.69 441	85.09 242	88.05 224	94.59 215	66.93 346	98.48 143	83.27 255	92.13 250	97.03 178

GBi-Net		87.26 275	85.98 293	91.08 236	94.01 257	83.10 149	95.14 147	94.94 266	83.57 278	84.37 322	91.64 326	66.59 353	96.34 365	78.23 349	85.36 342	93.79 337

test1		87.26 275	85.98 293	91.08 236	94.01 257	83.10 149	95.14 147	94.94 266	83.57 278	84.37 322	91.64 326	66.59 353	96.34 365	78.23 349	85.36 342	93.79 337

FMVSNet1		85.85 324	84.11 344	91.08 236	92.81 317	83.10 149	95.14 147	94.94 266	81.64 334	82.68 361	91.64 326	59.01 424	96.34 365	75.37 378	83.78 358	93.79 337

Test_1112_low_res		87.65 254	86.51 271	91.08 236	94.94 180	79.28 306	91.77 346	94.30 304	76.04 419	83.51 348	92.37 297	77.86 191	97.73 235	78.69 344	89.13 298	96.22 221

PS-MVSNAJss		89.97 178	89.62 173	91.02 240	91.90 345	80.85 240	95.26 135	95.98 176	86.26 200	86.21 266	94.29 227	79.70 158	97.65 239	88.87 169	88.10 312	94.57 294

BH-RMVSNet		88.37 234	87.48 237	91.02 240	95.28 158	79.45 294	92.89 304	93.07 350	85.45 226	86.91 246	94.84 201	70.35 304	97.76 230	73.97 393	94.59 176	95.85 242

UniMVSNet_ETH3D		87.53 264	86.37 275	91.00 242	92.44 328	78.96 311	94.74 175	95.61 215	84.07 266	85.36 299	94.52 217	59.78 416	97.34 280	82.93 259	87.88 317	96.71 202

FIs		90.51 163	90.35 150	90.99 243	93.99 261	80.98 230	95.73 104	97.54 9	89.15 89	86.72 253	94.68 206	81.83 125	97.24 291	85.18 222	88.31 311	94.76 287

ACMP	84.23 8	89.01 217	88.35 213	90.99 243	94.73 195	81.27 216	95.07 150	95.89 188	86.48 193	83.67 343	94.30 226	69.33 320	97.99 208	87.10 199	88.55 303	93.72 347
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20231211		86.59 307	85.13 322	90.98 245	96.52 98	81.50 207	96.14 64	96.16 158	73.78 442	83.65 344	92.15 305	63.26 385	97.37 279	82.82 263	81.74 388	94.06 321

IMVS_0403		89.97 178	89.64 172	90.96 246	93.72 275	77.75 349	93.00 298	95.34 240	85.53 222	88.77 210	94.49 218	78.49 181	97.84 226	84.75 229	92.65 238	97.28 151

sss		88.93 218	88.26 219	90.94 247	94.05 255	80.78 243	91.71 348	95.38 235	81.55 338	88.63 212	93.91 247	75.04 230	95.47 406	82.47 268	91.61 253	96.57 209

IMVS_0407		89.85 185	89.51 176	90.88 248	93.72 275	77.75 349	93.07 295	95.34 240	85.53 222	88.34 218	94.49 218	77.69 193	97.60 244	84.75 229	92.65 238	97.28 151

viewmambaseed2359dif		90.04 175	89.78 169	90.83 249	92.85 316	77.92 338	92.23 332	95.01 258	81.90 324	90.20 177	95.45 164	79.64 165	97.34 280	87.52 189	93.17 224	97.23 159

sd_testset		88.59 228	87.85 230	90.83 249	96.00 122	80.42 257	92.35 325	94.71 285	88.73 107	86.85 250	95.20 181	67.31 340	96.43 359	79.64 326	89.85 284	95.63 253

PVSNet_BlendedMVS		89.98 177	89.70 170	90.82 251	96.12 111	81.25 217	93.92 245	96.83 83	83.49 282	89.10 201	92.26 302	81.04 136	98.85 104	86.72 202	87.86 318	92.35 407

cascas		86.43 315	84.98 325	90.80 252	92.10 338	80.92 234	90.24 392	95.91 185	73.10 449	83.57 347	88.39 414	65.15 366	97.46 261	84.90 227	91.43 255	94.03 323

ECVR-MVS		89.09 211	88.53 207	90.77 253	95.62 144	75.89 382	96.16 60	84.22 475	87.89 147	90.20 177	96.65 91	63.19 387	98.10 180	85.90 213	96.94 112	98.33 50

GA-MVS		86.61 305	85.27 319	90.66 254	91.33 368	78.71 315	90.40 387	93.81 329	85.34 230	85.12 302	89.57 395	61.25 403	97.11 301	80.99 301	89.59 290	96.15 225

thres600view7		87.65 254	86.67 262	90.59 255	96.08 117	78.72 313	94.88 162	91.58 394	87.06 176	88.08 222	92.30 300	68.91 330	98.10 180	70.05 423	91.10 258	94.96 276

thres400		87.62 259	86.64 263	90.57 256	95.99 125	78.64 316	94.58 184	91.98 383	86.94 182	88.09 220	91.77 322	69.18 326	98.10 180	70.13 420	91.10 258	94.96 276

baseline1		88.10 241	87.28 243	90.57 256	94.96 178	80.07 269	94.27 214	91.29 403	86.74 187	87.41 237	94.00 240	76.77 202	96.20 370	80.77 304	79.31 422	95.44 257

viewdifsd2359ckpt11		89.43 198	89.05 192	90.56 258	92.89 314	77.00 364	92.81 307	94.52 293	87.03 177	89.77 188	95.79 147	74.67 237	97.51 252	88.97 165	84.98 346	97.17 162

viewmsd2359difaftdt		89.43 198	89.05 192	90.56 258	92.89 314	77.00 364	92.81 307	94.52 293	87.03 177	89.77 188	95.79 147	74.67 237	97.51 252	88.97 165	84.98 346	97.17 162

usedtu_dtu_shiyan1		86.84 294	85.61 308	90.53 260	90.50 405	81.80 199	90.97 372	94.96 264	83.05 294	83.50 349	90.32 371	72.15 279	96.65 329	79.49 331	85.55 340	93.15 372

FE-MVSNET3		86.84 294	85.61 308	90.53 260	90.50 405	81.80 199	90.97 372	94.96 264	83.05 294	83.50 349	90.32 371	72.15 279	96.65 329	79.49 331	85.55 340	93.15 372

FC-MVSNet-test		90.27 167	90.18 155	90.53 260	93.71 279	79.85 282	95.77 100	97.59 6	89.31 82	86.27 264	94.67 209	81.93 123	97.01 311	84.26 239	88.09 314	94.71 288

PAPM		86.68 304	85.39 314	90.53 260	93.05 305	79.33 305	89.79 404	94.77 283	78.82 377	81.95 372	93.24 269	76.81 200	97.30 283	66.94 440	93.16 225	94.95 280

WR-MVS		88.38 233	87.67 233	90.52 264	93.30 293	80.18 262	93.26 285	95.96 180	88.57 115	85.47 288	92.81 284	76.12 210	96.91 318	81.24 296	82.29 379	94.47 305

SSM_04072		88.57 230	87.92 227	90.51 265	94.76 191	82.66 170	79.84 486	94.64 289	85.18 232	88.96 205	95.00 190	76.00 213	92.03 456	83.74 249	93.15 226	96.85 194

MVSTER		88.84 219	88.29 217	90.51 265	92.95 311	80.44 256	93.73 258	95.01 258	84.66 257	87.15 241	93.12 274	72.79 270	97.21 294	87.86 181	87.36 326	93.87 331

testdata				90.49 267	96.40 101	77.89 341		95.37 237	72.51 454	93.63 79	96.69 87	82.08 119	97.65 239	83.08 256	97.39 101	95.94 237

test1111		89.10 209	88.64 204	90.48 268	95.53 149	74.97 392	96.08 69	84.89 473	88.13 130	90.16 182	96.65 91	63.29 384	98.10 180	86.14 208	96.90 115	98.39 45

tt0805		86.92 291	85.74 306	90.48 268	92.22 332	79.98 277	95.63 114	94.88 274	83.83 272	84.74 311	92.80 285	57.61 431	97.67 236	85.48 219	84.42 351	93.79 337

jajsoiax		88.24 238	87.50 236	90.48 268	90.89 389	80.14 264	95.31 127	95.65 213	84.97 245	84.24 330	94.02 238	65.31 365	97.42 267	88.56 172	88.52 305	93.89 327

PatchMatch-RL		86.77 301	85.54 310	90.47 271	95.88 130	82.71 168	90.54 383	92.31 371	79.82 362	84.32 327	91.57 334	68.77 332	96.39 361	73.16 399	93.48 215	92.32 408

0.4-1-1-0.1		81.55 394	78.59 416	90.42 272	87.55 447	79.90 279	88.56 426	89.19 451	77.01 405	79.72 405	77.71 479	54.84 446	97.11 301	80.50 311	72.20 446	94.26 311

tfpn200view9		87.58 262	86.64 263	90.41 273	95.99 125	78.64 316	94.58 184	91.98 383	86.94 182	88.09 220	91.77 322	69.18 326	98.10 180	70.13 420	91.10 258	94.48 303

VPNet		88.20 239	87.47 238	90.39 274	93.56 286	79.46 293	94.04 233	95.54 221	88.67 110	86.96 243	94.58 216	69.33 320	97.15 296	84.05 243	80.53 408	94.56 295

ACMH	80.38 17	85.36 334	83.68 351	90.39 274	94.45 225	80.63 246	94.73 176	94.85 276	82.09 315	77.24 433	92.65 289	60.01 414	97.58 246	72.25 404	84.87 348	92.96 379
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres100view900		87.63 257	86.71 259	90.38 276	96.12 111	78.55 319	95.03 154	91.58 394	87.15 172	88.06 223	92.29 301	68.91 330	98.10 180	70.13 420	91.10 258	94.48 303

mvs_tets		88.06 244	87.28 243	90.38 276	90.94 385	79.88 280	95.22 138	95.66 211	85.10 241	84.21 331	93.94 243	63.53 382	97.40 275	88.50 173	88.40 309	93.87 331

1314		87.51 265	86.57 268	90.34 278	92.42 329	79.74 287	92.63 314	95.35 239	78.35 386	80.14 395	91.62 330	74.05 249	97.15 296	81.05 297	93.53 211	94.12 316

LTVRE_ROB	82.13 13	86.26 318	84.90 328	90.34 278	94.44 226	81.50 207	92.31 329	94.89 272	83.03 296	79.63 407	92.67 288	69.69 314	97.79 228	71.20 409	86.26 335	91.72 418
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
0.3-1-1-0.015		80.75 407	77.58 421	90.25 280	86.55 451	79.72 288	87.46 447	89.48 449	76.43 412	77.93 428	75.94 481	52.31 458	97.05 308	80.25 316	71.85 450	93.99 325

test_djsdf		89.03 215	88.64 204	90.21 281	90.74 396	79.28 306	95.96 83	95.90 186	84.66 257	85.33 300	92.94 279	74.02 250	97.30 283	89.64 155	88.53 304	94.05 322

v2v482		87.84 247	87.06 247	90.17 282	90.99 381	79.23 309	94.00 239	95.13 251	84.87 248	85.53 283	92.07 313	74.45 241	97.45 262	84.71 234	81.75 387	93.85 334

pmmvs4		85.43 332	83.86 349	90.16 283	90.02 416	82.97 159	90.27 388	92.67 362	75.93 420	80.73 386	91.74 324	71.05 290	95.73 395	78.85 343	83.46 365	91.78 417

V42		87.68 252	86.86 252	90.15 284	90.58 401	80.14 264	94.24 217	95.28 244	83.66 276	85.67 278	91.33 336	74.73 235	97.41 273	84.43 238	81.83 385	92.89 382

MSDG		84.86 347	83.09 360	90.14 285	93.80 271	80.05 271	89.18 417	93.09 349	78.89 374	78.19 424	91.91 319	65.86 363	97.27 287	68.47 429	88.45 307	93.11 374

sc_t1		81.53 395	78.67 415	90.12 286	90.78 393	78.64 316	93.91 247	90.20 427	68.42 469	80.82 385	89.88 388	46.48 473	96.76 323	76.03 374	71.47 451	94.96 276

anonymousdsp		87.84 247	87.09 246	90.12 286	89.13 427	80.54 254	94.67 180	95.55 219	82.05 317	83.82 338	92.12 307	71.47 287	97.15 296	87.15 195	87.80 321	92.67 389

thres200		87.21 281	86.24 282	90.12 286	95.36 154	78.53 320	93.26 285	92.10 377	86.42 196	88.00 225	91.11 347	69.24 325	98.00 207	69.58 424	91.04 264	93.83 336

CR-MVSNet		85.35 335	83.76 350	90.12 286	90.58 401	79.34 302	85.24 464	91.96 385	78.27 388	85.55 281	87.87 424	71.03 291	95.61 398	73.96 394	89.36 293	95.40 259

0.4-1-1-0.2		80.84 406	77.77 419	90.06 290	86.18 455	79.35 300	86.75 452	89.54 447	76.23 417	78.59 423	75.46 484	55.03 445	96.99 312	80.11 318	72.05 448	93.85 334

v1144		87.61 260	86.79 257	90.06 290	91.01 380	79.34 302	93.95 242	95.42 234	83.36 287	85.66 279	91.31 339	74.98 231	97.42 267	83.37 253	82.06 381	93.42 358

XXY-MVS		87.65 254	86.85 253	90.03 292	92.14 335	80.60 252	93.76 255	95.23 246	82.94 299	84.60 313	94.02 238	74.27 243	95.49 405	81.04 298	83.68 361	94.01 324

Vis-MVSNet (Re-imp)		89.59 191	89.44 178	90.03 292	95.74 135	75.85 383	95.61 115	90.80 417	87.66 158	87.83 229	95.40 168	76.79 201	96.46 356	78.37 345	96.73 121	97.80 121

test2506		87.21 281	86.28 280	90.02 294	95.62 144	73.64 408	96.25 55	71.38 498	87.89 147	90.45 170	96.65 91	55.29 443	98.09 188	86.03 212	96.94 112	98.33 50

BH-untuned		88.60 227	88.13 221	90.01 295	95.24 162	78.50 322	93.29 283	94.15 312	84.75 253	84.46 319	93.40 261	75.76 220	97.40 275	77.59 355	94.52 179	94.12 316

v1192		87.25 277	86.33 277	90.00 296	90.76 395	79.04 310	93.80 253	95.48 224	82.57 306	85.48 287	91.18 343	73.38 264	97.42 267	82.30 272	82.06 381	93.53 352

v7n		86.81 296	85.76 304	89.95 297	90.72 397	79.25 308	95.07 150	95.92 183	84.45 260	82.29 365	90.86 354	72.60 274	97.53 250	79.42 337	80.52 409	93.08 376

testing91		87.11 286	86.18 283	89.92 298	94.43 227	75.38 391	91.53 354	92.27 373	86.48 193	86.50 255	90.24 374	61.19 406	97.53 250	82.10 277	90.88 266	96.84 197

IMVS_0404		87.60 261	86.84 254	89.89 299	93.72 275	77.75 349	88.56 426	95.34 240	85.53 222	79.98 399	94.49 218	66.54 356	94.64 419	84.75 229	92.65 238	97.28 151

v8		87.50 267	86.71 259	89.89 299	91.37 365	79.40 298	94.50 189	95.38 235	84.81 251	83.60 346	91.33 336	76.05 211	97.42 267	82.84 262	80.51 410	92.84 384

v10		87.25 277	86.38 274	89.85 301	91.19 371	79.50 291	94.48 190	95.45 229	83.79 274	83.62 345	91.19 341	75.13 228	97.42 267	81.94 282	80.60 405	92.63 391

baseline2		86.50 311	85.39 314	89.84 302	91.12 376	76.70 371	91.88 342	88.58 453	82.35 311	79.95 400	90.95 352	73.42 262	97.63 242	80.27 315	89.95 281	95.19 266

pm-mvs1		86.61 305	85.54 310	89.82 303	91.44 360	80.18 262	95.28 133	94.85 276	83.84 271	81.66 374	92.62 290	72.45 277	96.48 353	79.67 325	78.06 425	92.82 385

TR-MVS		86.78 298	85.76 304	89.82 303	94.37 230	78.41 324	92.47 319	92.83 356	81.11 348	86.36 261	92.40 296	68.73 333	97.48 257	73.75 397	89.85 284	93.57 351

ACMH+	81.04 14	85.05 342	83.46 354	89.82 303	94.66 203	79.37 299	94.44 195	94.12 315	82.19 314	78.04 426	92.82 283	58.23 427	97.54 249	73.77 396	82.90 373	92.54 397

EI-MVSNet		89.10 209	88.86 201	89.80 306	91.84 347	78.30 329	93.70 262	95.01 258	85.73 213	87.15 241	95.28 174	79.87 155	97.21 294	83.81 247	87.36 326	93.88 330

gbinet_0.2-2-1-0.02		82.59 376	80.19 388	89.77 307	85.23 466	80.05 271	91.59 353	93.52 338	77.60 394	79.78 404	82.87 466	63.26 385	96.45 357	78.93 341	68.97 461	92.81 386

usedtu_blend_shiyan5		82.39 381	79.93 395	89.75 308	85.12 467	80.08 267	92.36 323	93.26 343	74.29 437	79.00 415	82.72 467	64.29 376	96.60 342	79.60 327	68.75 465	92.55 394

v144192		87.19 283	86.35 276	89.74 309	90.64 399	78.24 331	93.92 245	95.43 232	81.93 322	85.51 285	91.05 350	74.21 246	97.45 262	82.86 261	81.56 389	93.53 352

COLMAP_ROB	80.39 16	83.96 361	82.04 370	89.74 309	95.28 158	79.75 286	94.25 215	92.28 372	75.17 427	78.02 427	93.77 253	58.60 426	97.84 226	65.06 451	85.92 336	91.63 420
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SCA		86.32 317	85.18 321	89.73 311	92.15 334	76.60 372	91.12 368	91.69 390	83.53 281	85.50 286	88.81 407	66.79 349	96.48 353	76.65 364	90.35 273	96.12 228

blend_shiyan4		81.94 384	79.35 403	89.70 312	85.52 462	80.08 267	91.29 362	93.82 326	77.12 403	79.31 411	82.94 465	54.81 447	96.60 342	79.60 327	69.78 456	92.41 403

IterMVS-LS		88.36 235	87.91 229	89.70 312	93.80 271	78.29 330	93.73 258	95.08 256	85.73 213	84.75 310	91.90 320	79.88 154	96.92 317	83.83 246	82.51 375	93.89 327
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
blended_shiyan8		82.79 371	80.49 381	89.69 314	85.50 463	79.83 284	91.38 357	93.82 326	77.14 400	79.39 410	83.73 457	64.95 370	96.63 332	79.75 322	68.77 464	92.62 393

testing11		86.44 314	85.35 317	89.69 314	94.29 241	75.40 390	91.30 361	90.53 422	84.76 252	85.06 304	90.13 380	58.95 425	97.45 262	82.08 278	91.09 262	96.21 223

testing99		86.72 302	85.73 307	89.69 314	94.23 245	74.91 394	91.35 360	90.97 411	86.14 204	86.36 261	90.22 375	59.41 419	97.48 257	82.24 274	90.66 268	96.69 204

v1921920		86.97 290	86.06 290	89.69 314	90.53 404	78.11 334	93.80 253	95.43 232	81.90 324	85.33 300	91.05 350	72.66 271	97.41 273	82.05 280	81.80 386	93.53 352

icg_test_0407_2		89.15 207	88.97 194	89.68 318	93.72 275	77.75 349	88.26 432	95.34 240	85.53 222	88.34 218	94.49 218	77.69 193	93.99 431	84.75 229	92.65 238	97.28 151

blended_shiyan6		82.78 372	80.48 382	89.67 319	85.53 461	79.76 285	91.37 358	93.82 326	77.14 400	79.30 412	83.73 457	64.96 369	96.63 332	79.68 324	68.75 465	92.63 391

VortexMVS		88.42 231	88.01 223	89.63 320	93.89 266	78.82 312	93.82 251	95.47 225	86.67 190	84.53 317	91.99 316	72.62 273	96.65 329	89.02 164	84.09 355	93.41 359

Fast-Effi-MVS+-dtu		87.44 268	86.72 258	89.63 320	92.04 339	77.68 354	94.03 234	93.94 318	85.81 210	82.42 364	91.32 338	70.33 305	97.06 306	80.33 314	90.23 275	94.14 315

v1240		86.78 298	85.85 299	89.56 322	90.45 408	77.79 346	93.61 266	95.37 237	81.65 333	85.43 292	91.15 345	71.50 286	97.43 266	81.47 293	82.05 383	93.47 356

Effi-MVS+-dtu		88.65 225	88.35 213	89.54 323	93.33 292	76.39 376	94.47 193	94.36 302	87.70 155	85.43 292	89.56 396	73.45 260	97.26 289	85.57 218	91.28 257	94.97 273

wanda-best-256-512		82.44 378	80.07 390	89.53 324	85.12 467	79.44 295	90.49 384	93.75 332	76.97 406	79.00 415	82.72 467	64.29 376	96.61 338	79.56 329	68.75 465	92.55 394

FE-blended-shiyan7		82.44 378	80.07 390	89.53 324	85.12 467	79.44 295	90.49 384	93.75 332	76.97 406	79.00 415	82.72 467	64.29 376	96.61 338	79.56 329	68.75 465	92.55 394

AllTest		83.42 368	81.39 374	89.52 326	95.01 172	77.79 346	93.12 289	90.89 415	77.41 396	76.12 442	93.34 262	54.08 452	97.51 252	68.31 431	84.27 353	93.26 362

TestCases				89.52 326	95.01 172	77.79 346		90.89 415	77.41 396	76.12 442	93.34 262	54.08 452	97.51 252	68.31 431	84.27 353	93.26 362

mvs_anonymous		89.37 204	89.32 183	89.51 328	93.47 288	74.22 401	91.65 351	94.83 278	82.91 300	85.45 289	93.79 251	81.23 135	96.36 364	86.47 204	94.09 192	97.94 98

XVG-ACMP-BASELINE		86.00 320	84.84 330	89.45 329	91.20 370	78.00 336	91.70 349	95.55 219	85.05 243	82.97 358	92.25 303	54.49 450	97.48 257	82.93 259	87.45 325	92.89 382

testing222		84.84 348	83.32 355	89.43 330	94.15 252	75.94 381	91.09 369	89.41 450	84.90 246	85.78 275	89.44 397	52.70 457	96.28 368	70.80 415	91.57 254	96.07 232

MVP-Stereo		85.97 321	84.86 329	89.32 331	90.92 387	82.19 186	92.11 337	94.19 309	78.76 379	78.77 422	91.63 329	68.38 337	96.56 347	75.01 383	93.95 195	89.20 460
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchmatchNet		85.85 324	84.70 332	89.29 332	91.76 351	75.54 387	88.49 428	91.30 402	81.63 335	85.05 305	88.70 411	71.71 283	96.24 369	74.61 389	89.05 299	96.08 231
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v148		87.04 288	86.32 278	89.21 333	90.94 385	77.26 360	93.71 261	94.43 297	84.84 250	84.36 325	90.80 358	76.04 212	97.05 308	82.12 276	79.60 419	93.31 361

tfpnnormal		84.72 350	83.23 358	89.20 334	92.79 318	80.05 271	94.48 190	95.81 194	82.38 309	81.08 382	91.21 340	69.01 329	96.95 315	61.69 462	80.59 406	90.58 446

cl22		86.78 298	85.98 293	89.18 335	92.34 330	77.62 355	90.84 376	94.13 314	81.33 342	83.97 336	90.15 379	73.96 251	96.60 342	84.19 240	82.94 370	93.33 360

BH-w/o		87.57 263	87.05 248	89.12 336	94.90 184	77.90 340	92.41 320	93.51 339	82.89 301	83.70 342	91.34 335	75.75 221	97.07 305	75.49 376	93.49 213	92.39 405

WR-MVS_H		87.80 249	87.37 240	89.10 337	93.23 294	78.12 333	95.61 115	97.30 37	87.90 145	83.72 341	92.01 315	79.65 164	96.01 379	76.36 368	80.54 407	93.16 370

miper_enhance_ethall		86.90 292	86.18 283	89.06 338	91.66 356	77.58 356	90.22 394	94.82 279	79.16 370	84.48 318	89.10 401	79.19 169	96.66 328	84.06 242	82.94 370	92.94 380

c3_l		87.14 285	86.50 272	89.04 339	92.20 333	77.26 360	91.22 367	94.70 286	82.01 320	84.34 326	90.43 369	78.81 173	96.61 338	83.70 251	81.09 396	93.25 364

miper_ehance_all_eth		87.22 280	86.62 266	89.02 340	92.13 336	77.40 358	90.91 375	94.81 280	81.28 343	84.32 327	90.08 382	79.26 167	96.62 335	83.81 247	82.94 370	93.04 377

gg-mvs-nofinetune		81.77 388	79.37 402	88.99 341	90.85 391	77.73 353	86.29 456	79.63 486	74.88 432	83.19 357	69.05 494	60.34 411	96.11 374	75.46 377	94.64 175	93.11 374

ETVMVS		84.43 355	82.92 364	88.97 342	94.37 230	74.67 395	91.23 366	88.35 455	83.37 286	86.06 270	89.04 402	55.38 441	95.67 397	67.12 438	91.34 256	96.58 208

pmmvs6		83.42 368	81.60 372	88.87 343	88.01 442	77.87 342	94.96 157	94.24 308	74.67 433	78.80 421	91.09 348	60.17 413	96.49 352	77.06 363	75.40 439	92.23 410

test_cas_vis1_n_1920		88.83 222	88.85 202	88.78 344	91.15 375	76.72 370	93.85 250	94.93 270	83.23 291	92.81 99	96.00 128	61.17 407	94.45 420	91.67 115	94.84 167	95.17 267

MIMVSNet		82.59 376	80.53 379	88.76 345	91.51 358	78.32 328	86.57 455	90.13 430	79.32 366	80.70 387	88.69 412	52.98 456	93.07 447	66.03 446	88.86 301	94.90 281

cl____		86.52 310	85.78 301	88.75 346	92.03 340	76.46 374	90.74 377	94.30 304	81.83 329	83.34 354	90.78 359	75.74 223	96.57 345	81.74 288	81.54 390	93.22 366

DIV-MVS_self_test		86.53 309	85.78 301	88.75 346	92.02 341	76.45 375	90.74 377	94.30 304	81.83 329	83.34 354	90.82 357	75.75 221	96.57 345	81.73 289	81.52 391	93.24 365

CP-MVSNet		87.63 257	87.26 245	88.74 348	93.12 299	76.59 373	95.29 131	96.58 111	88.43 118	83.49 351	92.98 278	75.28 227	95.83 388	78.97 340	81.15 395	93.79 337

eth_miper_zixun_eth		86.50 311	85.77 303	88.68 349	91.94 342	75.81 384	90.47 386	94.89 272	82.05 317	84.05 333	90.46 368	75.96 215	96.77 322	82.76 265	79.36 421	93.46 357

CHOSEN 280x420		85.15 340	83.99 347	88.65 350	92.47 326	78.40 325	79.68 488	92.76 359	74.90 431	81.41 378	89.59 394	69.85 313	95.51 402	79.92 321	95.29 158	92.03 413

PS-CasMVS		87.32 274	86.88 251	88.63 351	92.99 309	76.33 378	95.33 126	96.61 109	88.22 126	83.30 356	93.07 276	73.03 268	95.79 392	78.36 346	81.00 401	93.75 344

TransMVSNet (Re)		84.43 355	83.06 362	88.54 352	91.72 352	78.44 323	95.18 144	92.82 358	82.73 304	79.67 406	92.12 307	73.49 259	95.96 381	71.10 413	68.73 469	91.21 433

tt0320-xc		79.63 420	76.66 429	88.52 353	91.03 379	78.72 313	93.00 298	89.53 448	66.37 474	76.11 444	87.11 435	46.36 475	95.32 410	72.78 401	67.67 470	91.51 425

EG-PatchMatch MVS		82.37 382	80.34 384	88.46 354	90.27 410	79.35 300	92.80 310	94.33 303	77.14 400	73.26 461	90.18 378	47.47 470	96.72 324	70.25 417	87.32 328	89.30 457

PEN-MVS		86.80 297	86.27 281	88.40 355	92.32 331	75.71 386	95.18 144	96.38 126	87.97 139	82.82 360	93.15 272	73.39 263	95.92 383	76.15 372	79.03 424	93.59 350

Baseline_NR-MVSNet		87.07 287	86.63 265	88.40 355	91.44 360	77.87 342	94.23 218	92.57 364	84.12 265	85.74 277	92.08 311	77.25 197	96.04 375	82.29 273	79.94 414	91.30 431

UBG		85.51 330	84.57 337	88.35 357	94.21 247	71.78 433	90.07 399	89.66 443	82.28 312	85.91 273	89.01 403	61.30 401	97.06 306	76.58 367	92.06 251	96.22 221

D2MVS		85.90 322	85.09 323	88.35 357	90.79 392	77.42 357	91.83 345	95.70 206	80.77 351	80.08 397	90.02 384	66.74 351	96.37 362	81.88 284	87.97 316	91.26 432

pmmvs5		84.21 357	82.84 367	88.34 359	88.95 429	76.94 366	92.41 320	91.91 387	75.63 422	80.28 392	91.18 343	64.59 373	95.57 399	77.09 362	83.47 364	92.53 398

tt0320		80.13 413	77.41 422	88.29 360	90.50 405	78.02 335	93.10 292	90.71 420	66.06 477	76.75 437	86.97 436	49.56 465	95.40 407	71.65 405	71.41 452	91.46 428

LCM-MVSNet-Re		88.30 237	88.32 216	88.27 361	94.71 199	72.41 428	93.15 288	90.98 410	87.77 152	79.25 413	91.96 317	78.35 183	95.75 393	83.04 257	95.62 147	96.65 205

CostFormer		85.77 327	84.94 327	88.26 362	91.16 374	72.58 426	89.47 412	91.04 409	76.26 416	86.45 259	89.97 386	70.74 296	96.86 321	82.35 271	87.07 331	95.34 263

ITE_SJBPF				88.24 363	91.88 346	77.05 363		92.92 353	85.54 220	80.13 396	93.30 266	57.29 432	96.20 370	72.46 403	84.71 349	91.49 426

PVSNet	78.82 18	85.55 329	84.65 333	88.23 364	94.72 197	71.93 429	87.12 450	92.75 360	78.80 378	84.95 307	90.53 366	64.43 374	96.71 326	74.74 386	93.86 197	96.06 234

IterMVS-SCA-FT		85.45 331	84.53 338	88.18 365	91.71 353	76.87 367	90.19 396	92.65 363	85.40 229	81.44 377	90.54 365	66.79 349	95.00 416	81.04 298	81.05 397	92.66 390

EPNet_dtu		86.49 313	85.94 296	88.14 366	90.24 411	72.82 418	94.11 224	92.20 375	86.66 191	79.42 409	92.36 298	73.52 258	95.81 390	71.26 408	93.66 206	95.80 246
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmtry		82.71 374	80.93 378	88.06 367	90.05 415	76.37 377	84.74 469	91.96 385	72.28 457	81.32 380	87.87 424	71.03 291	95.50 404	68.97 426	80.15 412	92.32 408

test_vis1_n_1920		89.39 203	89.84 166	88.04 368	92.97 310	72.64 423	94.71 178	96.03 174	86.18 202	91.94 128	96.56 99	61.63 396	95.74 394	93.42 65	95.11 162	95.74 248

DTE-MVSNet		86.11 319	85.48 312	87.98 369	91.65 357	74.92 393	94.93 159	95.75 199	87.36 167	82.26 366	93.04 277	72.85 269	95.82 389	74.04 392	77.46 430	93.20 368

PMMVS		85.71 328	84.96 326	87.95 370	88.90 430	77.09 362	88.68 424	90.06 432	72.32 456	86.47 256	90.76 360	72.15 279	94.40 423	81.78 287	93.49 213	92.36 406

GG-mvs-BLEND				87.94 371	89.73 422	77.91 339	87.80 438	78.23 491		80.58 389	83.86 455	59.88 415	95.33 409	71.20 409	92.22 249	90.60 445

MonoMVSNet		86.89 293	86.55 269	87.92 372	89.46 425	73.75 405	94.12 222	93.10 348	87.82 151	85.10 303	90.76 360	69.59 316	94.94 417	86.47 204	82.50 376	95.07 270

reproduce_monomvs		86.37 316	85.87 298	87.87 373	93.66 283	73.71 406	93.44 273	95.02 257	88.61 113	82.64 363	91.94 318	57.88 429	96.68 327	89.96 145	79.71 418	93.22 366

pmmvs-eth3d		80.97 404	78.72 414	87.74 374	84.99 470	79.97 278	90.11 398	91.65 392	75.36 424	73.51 459	86.03 444	59.45 418	93.96 434	75.17 380	72.21 445	89.29 459

MS-PatchMatch		85.05 342	84.16 342	87.73 375	91.42 363	78.51 321	91.25 365	93.53 337	77.50 395	80.15 394	91.58 332	61.99 393	95.51 402	75.69 375	94.35 184	89.16 461

mmtdpeth		85.04 344	84.15 343	87.72 376	93.11 300	75.74 385	94.37 208	92.83 356	84.98 244	89.31 198	86.41 441	61.61 398	97.14 299	92.63 81	62.11 481	90.29 447

test_0402		81.30 400	79.17 408	87.67 377	93.19 295	78.17 332	92.98 300	91.71 388	75.25 426	76.02 445	90.31 373	59.23 420	96.37 362	50.22 484	83.63 362	88.47 469

IterMVS		84.88 346	83.98 348	87.60 378	91.44 360	76.03 380	90.18 397	92.41 366	83.24 290	81.06 383	90.42 370	66.60 352	94.28 427	79.46 333	80.98 402	92.48 399
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmatch-test		81.37 398	79.30 404	87.58 379	90.92 387	74.16 403	80.99 481	87.68 460	70.52 464	76.63 439	88.81 407	71.21 288	92.76 451	60.01 469	86.93 332	95.83 244

EPMVS		83.90 364	82.70 368	87.51 380	90.23 412	72.67 421	88.62 425	81.96 481	81.37 341	85.01 306	88.34 415	66.31 357	94.45 420	75.30 379	87.12 329	95.43 258

ADS-MVSNet2		81.66 391	79.71 399	87.50 381	91.35 366	74.19 402	83.33 474	88.48 454	72.90 451	82.24 367	85.77 447	64.98 367	93.20 445	64.57 453	83.74 359	95.12 268

OurMVSNet-221017-0		85.35 335	84.64 335	87.49 382	90.77 394	72.59 425	94.01 237	94.40 300	84.72 254	79.62 408	93.17 271	61.91 394	96.72 324	81.99 281	81.16 393	93.16 370

tpm2		84.08 359	82.94 363	87.48 383	91.39 364	71.27 438	89.23 416	90.37 424	71.95 458	84.64 312	89.33 398	67.30 341	96.55 349	75.17 380	87.09 330	94.63 289

RPSCF		85.07 341	84.27 339	87.48 383	92.91 313	70.62 447	91.69 350	92.46 365	76.20 418	82.67 362	95.22 177	63.94 380	97.29 286	77.51 357	85.80 337	94.53 296

myMVS_eth3d28		85.80 326	85.26 320	87.42 385	94.73 195	69.92 453	90.60 381	90.95 412	87.21 171	86.06 270	90.04 383	59.47 417	96.02 377	74.89 385	93.35 221	96.33 215

FE-MVSNET2		81.82 387	79.99 393	87.34 386	84.74 471	77.36 359	92.72 311	94.55 291	82.09 315	73.79 458	86.46 438	57.80 430	94.45 420	74.65 387	73.10 441	90.20 448

WBMVS		84.97 345	84.18 341	87.34 386	94.14 253	71.62 437	90.20 395	92.35 368	81.61 336	84.06 332	90.76 360	61.82 395	96.52 350	78.93 341	83.81 357	93.89 327

miper_lstm_enhance		85.27 338	84.59 336	87.31 388	91.28 369	74.63 396	87.69 443	94.09 316	81.20 347	81.36 379	89.85 390	74.97 232	94.30 426	81.03 300	79.84 417	93.01 378

FMVSNet5		81.52 396	79.60 400	87.27 389	91.17 372	77.95 337	91.49 355	92.26 374	76.87 408	76.16 441	87.91 423	51.67 459	92.34 454	67.74 435	81.16 393	91.52 424

USDC		82.76 373	81.26 376	87.26 390	91.17 372	74.55 397	89.27 414	93.39 341	78.26 389	75.30 449	92.08 311	54.43 451	96.63 332	71.64 406	85.79 338	90.61 443

test-LLR		85.87 323	85.41 313	87.25 391	90.95 383	71.67 435	89.55 408	89.88 439	83.41 284	84.54 315	87.95 421	67.25 342	95.11 413	81.82 285	93.37 219	94.97 273

test-mter		84.54 354	83.64 352	87.25 391	90.95 383	71.67 435	89.55 408	89.88 439	79.17 369	84.54 315	87.95 421	55.56 438	95.11 413	81.82 285	93.37 219	94.97 273

JIA-IIPM		81.04 401	78.98 412	87.25 391	88.64 431	73.48 410	81.75 480	89.61 445	73.19 448	82.05 370	73.71 488	66.07 362	95.87 386	71.18 411	84.60 350	92.41 403

TDRefinement		79.81 417	77.34 423	87.22 394	79.24 487	75.48 388	93.12 289	92.03 380	76.45 411	75.01 450	91.58 332	49.19 466	96.44 358	70.22 419	69.18 460	89.75 453

tpmvs		83.35 370	82.07 369	87.20 395	91.07 378	71.00 444	88.31 431	91.70 389	78.91 372	80.49 391	87.18 433	69.30 323	97.08 303	68.12 434	83.56 363	93.51 355

ppachtmachnet_test		81.84 386	80.07 390	87.15 396	88.46 435	74.43 400	89.04 420	92.16 376	75.33 425	77.75 430	88.99 404	66.20 359	95.37 408	65.12 450	77.60 428	91.65 419

dmvs_re		84.20 358	83.22 359	87.14 397	91.83 349	77.81 344	90.04 400	90.19 428	84.70 256	81.49 375	89.17 400	64.37 375	91.13 467	71.58 407	85.65 339	92.46 401

tpm cat1		81.96 383	80.27 385	87.01 398	91.09 377	71.02 443	87.38 448	91.53 397	66.25 475	80.17 393	86.35 443	68.22 338	96.15 373	69.16 425	82.29 379	93.86 333

test_fmvs1_n		87.03 289	87.04 249	86.97 399	89.74 421	71.86 430	94.55 186	94.43 297	78.47 383	91.95 127	95.50 163	51.16 461	93.81 435	93.02 73	94.56 177	95.26 264

OpenMVS_ROB	74.94 19	79.51 421	77.03 428	86.93 400	87.00 449	76.23 379	92.33 327	90.74 419	68.93 468	74.52 454	88.23 418	49.58 464	96.62 335	57.64 475	84.29 352	87.94 472

SixPastTwentyTwo		83.91 363	82.90 365	86.92 401	90.99 381	70.67 446	93.48 270	91.99 382	85.54 220	77.62 432	92.11 309	60.59 410	96.87 320	76.05 373	77.75 427	93.20 368

ADS-MVSNet		81.56 393	79.78 396	86.90 402	91.35 366	71.82 431	83.33 474	89.16 452	72.90 451	82.24 367	85.77 447	64.98 367	93.76 436	64.57 453	83.74 359	95.12 268

PatchT		82.68 375	81.27 375	86.89 403	90.09 414	70.94 445	84.06 471	90.15 429	74.91 430	85.63 280	83.57 459	69.37 319	94.87 418	65.19 448	88.50 306	94.84 283

tpm		84.73 349	84.02 346	86.87 404	90.33 409	68.90 456	89.06 419	89.94 436	80.85 350	85.75 276	89.86 389	68.54 335	95.97 380	77.76 353	84.05 356	95.75 247

Patchmatch-RL test		81.67 390	79.96 394	86.81 405	85.42 464	71.23 439	82.17 479	87.50 461	78.47 383	77.19 434	82.50 471	70.81 295	93.48 440	82.66 266	72.89 444	95.71 251

test_vis1_n		86.56 308	86.49 273	86.78 406	88.51 432	72.69 420	94.68 179	93.78 331	79.55 365	90.70 165	95.31 173	48.75 467	93.28 443	93.15 69	93.99 194	94.38 307

testing3-2		86.72 302	86.71 259	86.74 407	96.11 114	65.92 468	93.39 275	89.65 444	89.46 75	87.84 228	92.79 286	59.17 422	97.60 244	81.31 294	90.72 267	96.70 203

test_fmvs1		87.34 272	87.56 235	86.68 408	90.59 400	71.80 432	94.01 237	94.04 317	78.30 387	91.97 125	95.22 177	56.28 436	93.71 437	92.89 74	94.71 170	94.52 297

MDA-MVSNet-bldmvs		78.85 426	76.31 431	86.46 409	89.76 420	73.88 404	88.79 422	90.42 423	79.16 370	59.18 485	88.33 416	60.20 412	94.04 429	62.00 461	68.96 462	91.48 427

mvs5depth		80.98 403	79.15 409	86.45 410	84.57 472	73.29 413	87.79 439	91.67 391	80.52 353	82.20 369	89.72 392	55.14 444	95.93 382	73.93 395	66.83 472	90.12 450

tpmrst		85.35 335	84.99 324	86.43 411	90.88 390	67.88 461	88.71 423	91.43 400	80.13 357	86.08 269	88.80 409	73.05 267	96.02 377	82.48 267	83.40 367	95.40 259

TESTMET0.1,1		83.74 366	82.85 366	86.42 412	89.96 417	71.21 440	89.55 408	87.88 457	77.41 396	83.37 353	87.31 429	56.71 434	93.65 439	80.62 308	92.85 235	94.40 306

our_test_3		81.93 385	80.46 383	86.33 413	88.46 435	73.48 410	88.46 429	91.11 405	76.46 410	76.69 438	88.25 417	66.89 347	94.36 424	68.75 427	79.08 423	91.14 435

lessismore_v0				86.04 414	88.46 435	68.78 457		80.59 484		73.01 462	90.11 381	55.39 440	96.43 359	75.06 382	65.06 476	92.90 381

TinyColmap		79.76 418	77.69 420	85.97 415	91.71 353	73.12 414	89.55 408	90.36 425	75.03 428	72.03 465	90.19 377	46.22 476	96.19 372	63.11 457	81.03 398	88.59 468

KD-MVS_2432*1600		78.50 427	76.02 435	85.93 416	86.22 453	74.47 398	84.80 467	92.33 369	79.29 367	76.98 435	85.92 445	53.81 454	93.97 432	67.39 436	57.42 486	89.36 455

miper_refine_blended		78.50 427	76.02 435	85.93 416	86.22 453	74.47 398	84.80 467	92.33 369	79.29 367	76.98 435	85.92 445	53.81 454	93.97 432	67.39 436	57.42 486	89.36 455

K. test v3		81.59 392	80.15 389	85.91 418	89.89 419	69.42 455	92.57 316	87.71 459	85.56 219	73.44 460	89.71 393	55.58 437	95.52 401	77.17 360	69.76 457	92.78 387

SSC-MVS3.2		84.60 353	84.19 340	85.85 419	92.74 320	68.07 458	88.15 434	93.81 329	87.42 165	83.76 340	91.07 349	62.91 388	95.73 395	74.56 390	83.24 368	93.75 344

mvsany_test1		85.42 333	85.30 318	85.77 420	87.95 444	75.41 389	87.61 446	80.97 483	76.82 409	88.68 211	95.83 144	77.44 196	90.82 469	85.90 213	86.51 333	91.08 439

MIMVSNet1		79.38 422	77.28 424	85.69 421	86.35 452	73.67 407	91.61 352	92.75 360	78.11 392	72.64 463	88.12 419	48.16 468	91.97 460	60.32 466	77.49 429	91.43 429

UWE-MVS		83.69 367	83.09 360	85.48 422	93.06 304	65.27 473	90.92 374	86.14 465	79.90 360	86.26 265	90.72 363	57.17 433	95.81 390	71.03 414	92.62 243	95.35 262

UnsupCasMVSNet_eth		80.07 414	78.27 418	85.46 423	85.24 465	72.63 424	88.45 430	94.87 275	82.99 298	71.64 468	88.07 420	56.34 435	91.75 462	73.48 398	63.36 479	92.01 414

CL-MVSNet_self_test		81.74 389	80.53 379	85.36 424	85.96 456	72.45 427	90.25 390	93.07 350	81.24 345	79.85 403	87.29 430	70.93 293	92.52 452	66.95 439	69.23 459	91.11 437

MDA-MVSNet_test_wron		79.21 424	77.19 426	85.29 425	88.22 439	72.77 419	85.87 458	90.06 432	74.34 435	62.62 482	87.56 427	66.14 360	91.99 459	66.90 443	73.01 442	91.10 438

YYNet1		79.22 423	77.20 425	85.28 426	88.20 440	72.66 422	85.87 458	90.05 434	74.33 436	62.70 480	87.61 426	66.09 361	92.03 456	66.94 440	72.97 443	91.15 434

WB-MVSnew		83.77 365	83.28 356	85.26 427	91.48 359	71.03 442	91.89 341	87.98 456	78.91 372	84.78 309	90.22 375	69.11 328	94.02 430	64.70 452	90.44 270	90.71 441

dp		81.47 397	80.23 386	85.17 428	89.92 418	65.49 471	86.74 453	90.10 431	76.30 415	81.10 381	87.12 434	62.81 389	95.92 383	68.13 433	79.88 415	94.09 319

UnsupCasMVSNet_bld		76.23 437	73.27 441	85.09 429	83.79 474	72.92 416	85.65 461	93.47 340	71.52 459	68.84 474	79.08 477	49.77 463	93.21 444	66.81 444	60.52 483	89.13 463

usedtu_dtu_shiyan2		74.72 439	71.30 444	84.98 430	77.78 489	70.58 448	91.85 344	90.76 418	67.24 473	68.06 476	82.17 472	37.13 485	92.78 450	60.69 465	66.03 473	91.59 423

SD_0403		84.71 351	84.65 333	84.92 431	92.95 311	65.95 467	92.07 340	93.23 345	83.82 273	79.03 414	93.73 256	73.90 252	92.91 449	63.02 459	90.05 277	95.89 240

Anonymous20231206		81.03 402	79.77 398	84.82 432	87.85 445	70.26 450	91.42 356	92.08 378	73.67 443	77.75 430	89.25 399	62.43 391	93.08 446	61.50 463	82.00 384	91.12 436

FE-MVSNET		78.19 429	76.03 434	84.69 433	83.70 475	73.31 412	90.58 382	90.00 435	77.11 404	71.91 466	85.47 449	55.53 439	91.94 461	59.69 470	70.24 454	88.83 465

test0.0.03 1		82.41 380	81.69 371	84.59 434	88.23 438	72.89 417	90.24 392	87.83 458	83.41 284	79.86 402	89.78 391	67.25 342	88.99 479	65.18 449	83.42 366	91.90 416

CMPMVS	59.16 21	80.52 408	79.20 407	84.48 435	83.98 473	67.63 464	89.95 403	93.84 325	64.79 479	66.81 477	91.14 346	57.93 428	95.17 411	76.25 370	88.10 312	90.65 442
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		84.69 352	84.79 331	84.37 436	91.84 347	64.92 474	93.70 262	91.47 399	66.19 476	86.16 268	95.28 174	67.18 344	93.33 442	80.89 303	90.42 272	94.88 282

PVSNet_0	73.20 20	77.22 433	74.83 439	84.37 436	90.70 398	71.10 441	83.09 476	89.67 442	72.81 453	73.93 457	83.13 461	60.79 409	93.70 438	68.54 428	50.84 491	88.30 470

LF4IMVS		80.37 411	79.07 411	84.27 438	86.64 450	69.87 454	89.39 413	91.05 408	76.38 413	74.97 451	90.00 385	47.85 469	94.25 428	74.55 391	80.82 404	88.69 467

Anonymous20240521		80.44 410	79.21 406	84.11 439	85.75 459	67.89 460	92.86 306	93.23 345	75.61 423	75.59 448	87.47 428	50.03 462	94.33 425	71.14 412	81.21 392	90.12 450

PM-MVS		78.11 430	76.12 433	84.09 440	83.54 476	70.08 451	88.97 421	85.27 472	79.93 359	74.73 453	86.43 440	34.70 488	93.48 440	79.43 336	72.06 447	88.72 466

test_fmvs2		83.98 360	84.03 345	83.83 441	87.16 448	67.53 465	93.93 244	92.89 354	77.62 393	86.89 249	93.53 259	47.18 471	92.02 458	90.54 134	86.51 333	91.93 415

testgi		80.94 405	80.20 387	83.18 442	87.96 443	66.29 466	91.28 363	90.70 421	83.70 275	78.12 425	92.84 281	51.37 460	90.82 469	63.34 456	82.46 377	92.43 402

KD-MVS_self_test		80.20 412	79.24 405	83.07 443	85.64 460	65.29 472	91.01 371	93.93 319	78.71 381	76.32 440	86.40 442	59.20 421	92.93 448	72.59 402	69.35 458	91.00 440

testing3		80.46 409	79.59 401	83.06 444	93.44 290	64.64 475	93.33 277	85.47 470	84.34 262	79.93 401	90.84 356	44.35 479	92.39 453	57.06 477	87.56 322	92.16 412

ambc				83.06 444	79.99 485	63.51 479	77.47 489	92.86 355		74.34 456	84.45 454	28.74 489	95.06 415	73.06 400	68.89 463	90.61 443

test20.03		79.95 416	79.08 410	82.55 446	85.79 458	67.74 463	91.09 369	91.08 406	81.23 346	74.48 455	89.96 387	61.63 396	90.15 471	60.08 467	76.38 435	89.76 452

MVStest1		72.91 442	69.70 447	82.54 447	78.14 488	73.05 415	88.21 433	86.21 464	60.69 483	64.70 478	90.53 366	46.44 474	85.70 486	58.78 473	53.62 488	88.87 464

test_vis1_rt		77.96 431	76.46 430	82.48 448	85.89 457	71.74 434	90.25 390	78.89 487	71.03 463	71.30 469	81.35 474	42.49 481	91.05 468	84.55 236	82.37 378	84.65 475

EU-MVSNet		81.32 399	80.95 377	82.42 449	88.50 434	63.67 478	93.32 278	91.33 401	64.02 480	80.57 390	92.83 282	61.21 405	92.27 455	76.34 369	80.38 411	91.32 430

myMVS_eth3d		79.67 419	78.79 413	82.32 450	91.92 343	64.08 476	89.75 406	87.40 462	81.72 331	78.82 419	87.20 431	45.33 477	91.29 465	59.09 472	87.84 319	91.60 421

ttmdpeth		76.55 435	74.64 440	82.29 451	82.25 481	67.81 462	89.76 405	85.69 468	70.35 465	75.76 446	91.69 325	46.88 472	89.77 473	66.16 445	63.23 480	89.30 457

pmmvs3		71.81 445	68.71 448	81.11 452	75.86 491	70.42 449	86.74 453	83.66 476	58.95 486	68.64 475	80.89 475	36.93 486	89.52 475	63.10 458	63.59 478	83.39 476

Syy-MVS		80.07 414	79.78 396	80.94 453	91.92 343	59.93 485	89.75 406	87.40 462	81.72 331	78.82 419	87.20 431	66.29 358	91.29 465	47.06 488	87.84 319	91.60 421

UWE-MVS-28		78.98 425	78.38 417	80.80 454	88.18 441	60.66 484	90.65 379	78.51 488	78.84 376	77.93 428	90.93 353	59.08 423	89.02 478	50.96 483	90.33 274	92.72 388

new-patchmatchnet		76.41 436	75.17 438	80.13 455	82.65 480	59.61 486	87.66 444	91.08 406	78.23 390	69.85 472	83.22 460	54.76 448	91.63 464	64.14 455	64.89 477	89.16 461

mvsany_test3		74.95 438	73.26 442	80.02 456	74.61 492	63.16 480	85.53 462	78.42 489	74.16 438	74.89 452	86.46 438	36.02 487	89.09 477	82.39 270	66.91 471	87.82 473

test_fmvs3		77.67 432	77.16 427	79.22 457	79.52 486	61.14 482	92.34 326	91.64 393	73.98 440	78.86 418	86.59 437	27.38 492	87.03 481	88.12 178	75.97 437	89.50 454

DSMNet-mixed		76.94 434	76.29 432	78.89 458	83.10 478	56.11 494	87.78 440	79.77 485	60.65 484	75.64 447	88.71 410	61.56 399	88.34 480	60.07 468	89.29 295	92.21 411

EGC-MVSNET		61.97 453	56.37 458	78.77 459	89.63 423	73.50 409	89.12 418	82.79 478	0.21 536	1.24 537	84.80 452	39.48 482	90.04 472	44.13 490	75.94 438	72.79 490

new_pmnet		72.15 443	70.13 446	78.20 460	82.95 479	65.68 469	83.91 472	82.40 480	62.94 482	64.47 479	79.82 476	42.85 480	86.26 485	57.41 476	74.44 440	82.65 480

MVS-HIRNet		73.70 441	72.20 443	78.18 461	91.81 350	56.42 493	82.94 477	82.58 479	55.24 487	68.88 473	66.48 495	55.32 442	95.13 412	58.12 474	88.42 308	83.01 478

LCM-MVSNet		66.00 450	62.16 455	77.51 462	64.51 506	58.29 488	83.87 473	90.90 414	48.17 491	54.69 488	73.31 489	16.83 501	86.75 482	65.47 447	61.67 482	87.48 474

APD_test1		69.04 446	66.26 452	77.36 463	80.51 484	62.79 481	85.46 463	83.51 477	54.11 489	59.14 486	84.79 453	23.40 495	89.61 474	55.22 478	70.24 454	79.68 485

test_f		71.95 444	70.87 445	75.21 464	74.21 494	59.37 487	85.07 466	85.82 467	65.25 478	70.42 471	83.13 461	23.62 493	82.93 492	78.32 347	71.94 449	83.33 477

ANet_high		58.88 457	54.22 462	72.86 465	56.50 511	56.67 490	80.75 482	86.00 466	73.09 450	37.39 501	64.63 499	22.17 496	79.49 496	43.51 491	23.96 504	82.43 481

test_vis3_rt		65.12 451	62.60 453	72.69 466	71.44 496	60.71 483	87.17 449	65.55 500	63.80 481	53.22 489	65.65 498	14.54 502	89.44 476	76.65 364	65.38 475	67.91 495

LoFTR		57.22 460	52.62 464	71.00 467	72.03 495	48.57 499	72.00 496	70.08 499	44.40 496	40.92 499	76.42 480	8.12 506	82.76 493	42.28 494	47.33 494	81.66 482

FPMVS		64.63 452	62.55 454	70.88 468	70.80 497	56.71 489	84.42 470	84.42 474	51.78 490	49.57 490	81.61 473	23.49 494	81.48 494	40.61 496	76.25 436	74.46 489

dmvs_testset		74.57 440	75.81 437	70.86 469	87.72 446	40.47 508	87.05 451	77.90 493	82.75 303	71.15 470	85.47 449	67.98 339	84.12 490	45.26 489	76.98 434	88.00 471

N_pmnet		68.89 447	68.44 449	70.23 470	89.07 428	28.79 516	88.06 435	19.50 516	69.47 467	71.86 467	84.93 451	61.24 404	91.75 462	54.70 479	77.15 431	90.15 449

testf1		59.54 455	56.11 459	69.85 471	69.28 498	56.61 491	80.37 483	76.55 496	42.58 498	45.68 494	75.61 482	11.26 503	84.18 488	43.20 492	60.44 484	68.75 493

APD_test2		59.54 455	56.11 459	69.85 471	69.28 498	56.61 491	80.37 483	76.55 496	42.58 498	45.68 494	75.61 482	11.26 503	84.18 488	43.20 492	60.44 484	68.75 493

WB-MVS		67.92 448	67.49 450	69.21 473	81.09 482	41.17 507	88.03 436	78.00 492	73.50 445	62.63 481	83.11 463	63.94 380	86.52 483	25.66 503	51.45 490	79.94 484

PMMVS2		59.60 454	56.40 457	69.21 473	68.83 500	46.58 500	73.02 495	77.48 494	55.07 488	49.21 491	72.95 490	17.43 500	80.04 495	49.32 485	44.33 495	80.99 483

SSC-MVS		67.06 449	66.56 451	68.56 475	80.54 483	40.06 509	87.77 441	77.37 495	72.38 455	61.75 483	82.66 470	63.37 383	86.45 484	24.48 504	48.69 493	79.16 486

Gipuma		57.99 459	54.91 461	67.24 476	88.51 432	65.59 470	52.21 501	90.33 426	43.58 497	42.84 497	51.18 504	20.29 498	85.07 487	34.77 497	70.45 453	51.05 503
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
RoMa-SfM		53.80 461	49.39 465	67.06 477	67.87 502	48.86 497	75.04 490	38.06 512	47.23 493	47.40 493	78.96 478	7.40 507	76.66 498	48.89 486	33.62 499	75.64 488

DKM		50.92 465	46.13 469	65.30 478	66.27 504	45.98 502	73.05 494	31.91 514	45.08 494	42.04 498	75.01 486	4.95 514	73.81 500	47.90 487	28.96 501	76.09 487

MatchFormer		51.11 464	46.66 468	64.46 479	67.11 503	43.39 505	70.54 497	63.67 502	33.19 502	37.22 502	70.30 492	6.67 509	78.17 497	30.29 500	40.94 497	71.81 491

PMVS	47.18 22	52.22 463	48.46 467	63.48 480	45.72 515	46.20 501	73.41 493	78.31 490	41.03 500	30.06 505	65.68 497	6.05 510	83.43 491	30.04 501	65.86 474	60.80 497
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		58.82 458	58.24 456	60.56 481	83.13 477	45.09 504	82.32 478	48.22 509	67.61 471	61.70 484	69.15 493	38.75 483	76.05 499	32.01 499	41.31 496	60.55 498

PDCNetPlus		48.34 467	45.15 470	57.91 482	61.43 508	41.85 506	65.98 498	38.30 511	47.59 492	37.96 500	71.85 491	10.18 505	66.85 505	52.94 481	20.14 515	65.03 496

MVE	39.65 23	43.39 468	38.59 474	57.77 483	56.52 510	48.77 498	55.38 500	58.64 505	29.33 504	28.96 506	52.65 503	4.68 517	64.62 506	28.11 502	33.07 500	59.93 499
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.52 466	48.47 466	56.66 484	52.26 514	18.98 520	41.51 507	81.40 482	10.10 510	44.59 496	75.01 486	28.51 490	68.16 501	53.54 480	49.31 492	82.83 479

DeepMVS_CX				56.31 485	74.23 493	51.81 496		56.67 506	44.85 495	48.54 492	75.16 485	27.87 491	58.74 508	40.92 495	52.22 489	58.39 501

ELoFTR		40.15 471	35.08 475	55.36 486	41.27 520	28.17 517	47.70 503	43.76 510	29.15 505	30.35 504	65.97 496	2.17 524	66.90 504	34.51 498	20.83 514	71.00 492

kuosan		53.51 462	53.30 463	54.13 487	76.06 490	45.36 503	80.11 485	48.36 508	59.63 485	54.84 487	63.43 500	37.41 484	62.07 507	20.73 506	39.10 498	54.96 502

GLUNet-SfM		31.36 473	26.25 478	46.70 488	35.51 522	24.89 518	33.71 512	36.36 513	19.08 506	23.78 509	52.69 502	3.82 522	56.26 509	19.75 508	11.56 525	58.95 500

E-PMN		43.23 469	42.29 471	46.03 489	65.58 505	37.41 510	73.51 492	64.62 501	33.99 501	28.47 507	47.87 505	19.90 499	67.91 502	22.23 505	24.45 502	32.77 509

EMVS		42.07 470	41.12 472	44.92 490	63.45 507	35.56 512	73.65 491	63.48 503	33.05 503	26.88 508	45.45 506	21.27 497	67.14 503	19.80 507	23.02 506	32.06 510

ALIKED-LG		28.00 474	26.54 477	32.41 491	58.12 509	31.80 513	47.26 504	21.21 515	14.15 507	19.16 511	41.93 508	6.72 508	35.73 510	5.96 517	24.32 503	29.69 511

ALIKED-MNN		26.28 475	24.57 480	31.39 492	56.22 512	31.73 514	45.54 505	19.13 518	11.12 508	17.11 513	39.35 510	5.01 513	34.53 511	5.54 519	22.12 508	27.92 512

ALIKED-NN		26.07 476	24.75 479	30.02 493	55.08 513	30.61 515	44.20 506	19.22 517	10.98 509	17.98 512	40.71 509	5.39 512	32.83 512	5.59 518	23.63 505	26.63 513

tmp_tt		35.64 472	39.24 473	24.84 494	14.87 539	23.90 519	62.71 499	51.51 507	6.58 518	36.66 503	62.08 501	44.37 478	30.34 514	52.40 482	22.00 509	20.27 515

wuyk23d		21.27 478	20.48 481	23.63 495	68.59 501	36.41 511	49.57 502	6.85 531	9.37 511	7.89 520	4.46 536	4.03 521	31.37 513	17.47 509	16.07 518	3.12 531

SP-LightGlue		20.24 479	20.15 483	20.49 496	43.51 516	12.27 528	38.68 509	14.56 522	7.54 515	12.90 517	30.07 514	4.75 515	14.38 518	7.60 513	21.75 510	34.82 504

SP-SuperGlue		20.22 480	20.18 482	20.36 497	43.26 517	12.27 528	38.71 508	14.77 521	7.64 514	13.04 516	30.21 513	4.73 516	14.21 520	7.59 514	21.65 511	34.59 505

SP-DiffGlue		20.02 481	19.96 484	20.21 498	19.64 536	13.14 527	30.51 513	15.49 520	8.39 512	19.98 510	43.75 507	5.48 511	13.72 521	13.75 510	22.65 507	33.78 507

SP-MNN		19.61 482	19.42 485	20.19 499	42.15 518	11.42 534	38.15 510	14.24 523	6.55 519	11.64 519	29.88 516	4.16 519	14.56 517	7.09 516	20.92 513	34.58 506

SP-NN		19.44 483	19.37 486	19.67 500	41.70 519	11.48 533	37.75 511	13.72 525	6.86 516	11.86 518	29.97 515	4.23 518	14.25 519	7.13 515	21.07 512	33.30 508

XFeat-MNN		17.43 484	16.95 487	18.86 501	16.90 537	11.28 535	27.31 514	17.08 519	8.08 513	15.61 515	35.73 511	4.06 520	22.95 515	10.20 511	17.59 517	22.35 514

XFeat-NN		15.96 485	15.86 488	16.25 502	15.78 538	9.87 538	25.17 515	13.83 524	6.76 517	15.68 514	34.83 512	3.61 523	19.28 516	9.22 512	17.90 516	19.58 516

SIFT-NN		12.98 486	13.18 489	12.37 503	36.49 521	16.03 521	22.41 516	7.69 527	4.89 520	7.41 521	20.48 518	1.69 525	11.46 523	1.88 522	15.70 519	9.61 518

SIFT-MNN		12.44 487	12.55 490	12.11 504	34.55 523	15.21 522	20.91 517	7.74 526	4.86 521	6.54 523	20.09 519	1.51 526	11.47 522	1.88 522	14.87 521	9.64 517

SIFT-NN-NCMNet		12.12 488	12.25 491	11.75 505	32.82 525	14.83 523	20.73 518	7.58 528	4.72 523	6.60 522	19.53 520	1.49 527	11.15 525	1.74 524	15.02 520	9.28 519

SIFT-NCM-Cal		11.58 489	11.64 492	11.40 506	33.45 524	14.10 524	19.75 520	6.89 529	4.68 526	4.55 530	18.60 525	1.34 531	11.28 524	1.53 530	13.95 522	8.82 523

SIFT-NN-CMatch		11.26 490	11.31 494	11.13 507	30.21 529	13.40 526	18.43 521	6.79 532	4.71 524	6.47 524	19.53 520	1.43 529	10.72 527	1.71 525	12.49 524	9.26 520

SIFT-ConvMatch		10.91 492	10.94 497	10.84 508	32.07 526	13.57 525	17.23 524	6.35 533	4.71 524	5.18 527	18.94 523	1.30 532	10.76 526	1.65 528	11.02 527	8.19 524

SIFT-NN-UMatch		11.06 491	11.19 496	10.66 509	28.66 531	12.16 530	19.79 519	6.86 530	4.73 522	5.21 526	19.47 522	1.46 528	10.70 528	1.71 525	12.79 523	9.13 521

SIFT-UMatch		10.58 493	10.73 498	10.15 510	31.05 527	11.65 532	18.01 522	5.92 535	4.65 527	4.72 528	18.93 524	1.25 534	10.62 529	1.66 527	10.39 528	8.16 525

SIFT-CM-Cal		10.08 495	10.13 501	9.92 511	30.71 528	11.88 531	15.35 526	5.44 536	4.59 528	4.72 528	18.04 528	1.26 533	10.19 530	1.46 532	9.60 529	7.69 526

SIFT-NN-PointCN		10.26 494	10.46 499	9.65 512	27.18 532	9.89 537	17.89 523	6.17 534	4.40 530	5.65 525	18.29 526	1.43 529	10.09 531	1.61 529	11.55 526	8.99 522

SIFT-UM-Cal		9.80 496	10.00 502	9.22 513	30.05 530	10.15 536	16.31 525	4.85 538	4.54 529	4.19 531	18.23 527	1.19 535	9.95 532	1.52 531	9.11 531	7.57 527

SIFT-PCN-Cal		8.65 500	8.88 504	7.98 514	26.74 533	7.47 540	13.90 528	4.61 539	4.09 532	3.82 532	15.86 529	1.01 536	8.94 533	1.34 533	8.52 532	7.53 528

SIFT-PointCN		8.76 498	9.03 503	7.96 515	26.50 534	7.60 539	14.94 527	5.08 537	4.10 531	3.74 533	15.46 530	0.94 537	8.92 534	1.33 534	9.14 530	7.37 529

SIFT-NCMNet		7.46 502	7.71 506	6.72 516	25.03 535	6.86 541	11.42 529	2.98 540	4.05 533	3.38 534	13.68 531	0.84 538	7.65 535	1.13 535	6.87 533	5.66 530

test123		8.76 498	11.22 495	1.39 517	0.85 541	0.97 542	85.76 460	0.35 542	0.54 535	2.45 536	8.14 535	0.60 539	0.48 536	2.16 521	0.17 535	2.71 532

testmvs		8.92 497	11.52 493	1.12 518	1.06 540	0.46 543	86.02 457	0.65 541	0.62 534	2.74 535	9.52 534	0.31 540	0.45 537	2.38 520	0.39 534	2.46 533

mmdepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

monomultidepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

test_blank		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet_test		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

DCPMVS		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

cdsmvs_eth3d_5k		22.14 477	29.52 476	0.00 519	0.00 542	0.00 544	0.00 530	95.76 198	0.00 537	0.00 538	94.29 227	75.66 224	0.00 538	0.00 536	0.00 536	0.00 534

pcd_1.5k_mvsjas		6.64 503	8.86 505	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	79.70 158	0.00 538	0.00 536	0.00 536	0.00 534

sosnet-low-res		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

sosnet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uncertanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

Regformer		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

ab-mvs-re		7.82 501	10.43 500	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	93.88 248	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

WAC-MVS						64.08 476								59.14 471

FOURS1					98.86 4	85.54 74	98.29 1	97.49 11	89.79 65	96.29 32

PC_three_1452									82.47 307	97.09 19	97.07 72	92.72 1	98.04 199	92.70 80	99.02 12	98.86 16

test_one_0601					98.58 14	85.83 68		97.44 20	91.05 23	96.78 27	98.06 24	91.45 12

eth-test2					0.00 542

eth-test					0.00 542

ZD-MVS					98.15 40	86.62 34		97.07 60	83.63 277	94.19 65	96.91 78	87.57 35	99.26 51	91.99 105	98.44 56

RE-MVS-def			93.68 72		97.92 49	84.57 94	96.28 51	96.76 93	87.46 162	93.75 76	97.43 51	82.94 100		92.73 76	97.80 91	97.88 111

IU-MVS					98.77 8	86.00 54		96.84 82	81.26 344	97.26 13				95.50 36	99.13 3	99.03 10

test_241102_TWO								97.44 20	90.31 43	97.62 8	98.07 22	91.46 11	99.58 13	95.66 30	99.12 6	98.98 12

test_241102_ONE					98.77 8	85.99 56		97.44 20	90.26 49	97.71 2	97.96 33	92.31 5	99.38 35

9.14			94.47 35		97.79 58		96.08 69	97.44 20	86.13 206	95.10 55	97.40 53	88.34 26	99.22 53	93.25 68	98.70 37

save fliter					97.85 55	85.63 73	95.21 141	96.82 85	89.44 76

test_0728_THIRD									90.75 31	97.04 21	98.05 27	92.09 7	99.55 20	95.64 32	99.13 3	99.13 4

test0726					98.78 6	85.93 59	97.19 16	97.47 16	90.27 47	97.64 6	98.13 7	91.47 9

GSMVS																96.12 228

test_part2					98.55 15	87.22 20				96.40 31

sam_mvs1												71.70 284				96.12 228

sam_mvs												70.60 298

MTGPA								96.97 65

test_post1							88.00 437				9.81 533	69.31 322	95.53 400	76.65 364

test_post											10.29 532	70.57 302	95.91 385

patchmatchnet-post											83.76 456	71.53 285	96.48 353

MTMP							96.16 60	60.64 504

gm-plane-assit					89.60 424	68.00 459			77.28 399		88.99 404		97.57 247	79.44 335

test9_res														91.91 109	98.71 35	98.07 83

TEST9					97.53 67	86.49 38	94.07 230	96.78 90	81.61 336	92.77 101	96.20 109	87.71 32	99.12 63

test_8					97.49 69	86.30 46	94.02 236	96.76 93	81.86 327	92.70 105	96.20 109	87.63 33	99.02 73

agg_prior2														90.54 134	98.68 40	98.27 64

agg_prior					97.38 72	85.92 61		96.72 100		92.16 120			98.97 87

test_prior4						85.96 58	94.11 224

test_prior2							94.12 222		87.67 157	92.63 109	96.39 104	86.62 45		91.50 118	98.67 43

旧先验2							93.36 276		71.25 461	94.37 61			97.13 300	86.74 200

新几何2							93.11 291

旧先验1					96.79 86	81.81 198		95.67 209			96.81 84	86.69 43			97.66 97	96.97 184

无先验							93.28 284	96.26 140	73.95 441				99.05 67	80.56 309		96.59 207

原ACMM2							92.94 302

test222					96.55 95	81.70 203	92.22 333	95.01 258	68.36 470	90.20 177	96.14 119	80.26 145			97.80 91	96.05 235

testdata2													98.75 116	78.30 348

segment_acmp												87.16 40

testdata1							92.15 335		87.94 141

plane_prior7					94.70 200	82.74 165

plane_prior6					94.52 216	82.75 163						74.23 244

plane_prior5								96.22 145					98.12 178	88.15 175	89.99 278	94.63 289

plane_prior4											94.86 198

plane_prior3						82.75 163			90.26 49	86.91 246

plane_prior2							95.85 93		90.81 27

plane_prior1					94.59 209

plane_prior						82.73 166	95.21 141		89.66 70						89.88 283

n2								0.00 543

nn								0.00 543

door-mid								85.49 469

test11								96.57 112

door								85.33 471

HQP5-MVS						81.56 205

HQP-NCC					94.17 249		94.39 204		88.81 103	85.43 292

ACMP_Plane					94.17 249		94.39 204		88.81 103	85.43 292

BP-MVS														87.11 197

HQP4-MVS										85.43 292			97.96 215			94.51 299

HQP3-MVS								96.04 172							89.77 287

HQP2-MVS												73.83 255

NP-MVS					94.37 230	82.42 179					93.98 241

MDTV_nov1_ep13_2view						55.91 495	87.62 445		73.32 447	84.59 314		70.33 305		74.65 387		95.50 256

MDTV_nov1_ep13			83.56 353		91.69 355	69.93 452	87.75 442	91.54 396	78.60 382	84.86 308	88.90 406	69.54 317	96.03 376	70.25 417	88.93 300

ACMMP++_ref															87.47 323

ACMMP++															88.01 315

Test By Simon												80.02 147

High-resolution multi-view benchmark