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 54	90.86 1		96.85 70					99.61 4	96.03 21	99.06 9	99.07 5

No_MVS				96.52 1	97.78 54	90.86 1		96.85 70					99.61 4	96.03 21	99.06 9	99.07 5

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 59	92.59 2	98.94 83	92.25 80	98.99 14	98.84 14

HPM-MVS++		95.14 10	94.91 18	95.83 4	98.25 29	89.65 4	95.92 78	96.96 59	91.75 10	94.02 60	96.83 71	88.12 24	99.55 16	93.41 55	98.94 16	98.28 55

MM		95.10 11	94.91 18	95.68 5	96.09 107	88.34 9	96.68 33	94.37 251	95.08 1	94.68 47	97.72 32	82.94 93	99.64 1	97.85 2	98.76 29	99.06 7

SMA-MVS		95.20 8	95.07 12	95.59 6	98.14 35	88.48 8	96.26 46	97.28 33	85.90 172	97.67 3	98.10 10	88.41 20	99.56 12	94.66 39	99.19 1	98.71 20
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
3Dnovator+	87.14 4	92.42 91	91.37 101	95.55 7	95.63 131	88.73 6	97.07 18	96.77 81	90.84 18	84.02 285	96.62 84	75.95 178	99.34 37	87.77 147	97.68 85	98.59 24

CNVR-MVS		95.40 7	95.37 7	95.50 8	98.11 36	88.51 7	95.29 116	96.96 59	92.09 7	95.32 39	97.08 59	89.49 15	99.33 40	95.10 35	98.85 20	98.66 21

MVS_0304		94.18 41	93.80 55	95.34 9	94.91 169	87.62 14	95.97 73	93.01 292	92.58 4	94.22 52	97.20 53	80.56 123	99.59 8	97.04 15	98.68 37	98.81 17

ACMMP_NAP		94.74 20	94.56 24	95.28 10	98.02 41	87.70 11	95.68 94	97.34 24	88.28 106	95.30 40	97.67 34	85.90 50	99.54 20	93.91 47	98.95 15	98.60 23

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 25	87.28 18	95.56 106	97.51 5	89.13 77	97.14 11	97.91 25	91.64 7	99.62 2	94.61 40	99.17 2	98.86 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SF-MVS		94.97 12	94.90 20	95.20 12	97.84 50	87.76 10	96.65 34	97.48 10	87.76 128	95.71 34	97.70 33	88.28 23	99.35 36	93.89 48	98.78 26	98.48 30

MCST-MVS		94.45 26	94.20 42	95.19 13	98.46 19	87.50 16	95.00 137	97.12 47	87.13 141	92.51 99	96.30 93	89.24 17	99.34 37	93.46 52	98.62 46	98.73 18

NCCC		94.81 17	94.69 23	95.17 14	97.83 51	87.46 17	95.66 97	96.93 63	92.34 5	93.94 61	96.58 86	87.74 27	99.44 29	92.83 64	98.40 54	98.62 22

DPM-MVS		92.58 87	91.74 97	95.08 15	96.19 99	89.31 5	92.66 266	96.56 101	83.44 232	91.68 122	95.04 149	86.60 42	98.99 73	85.60 177	97.92 76	96.93 143

ZNCC-MVS		94.47 25	94.28 36	95.03 16	98.52 15	86.96 20	96.85 28	97.32 28	88.24 107	93.15 76	97.04 62	86.17 47	99.62 2	92.40 74	98.81 23	98.52 26

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 16	97.49 6					99.61 4	95.62 28	99.08 7	98.99 9

MTAPA		94.42 30	94.22 39	95.00 18	98.42 21	86.95 21	94.36 184	96.97 56	91.07 14	93.14 77	97.56 36	84.30 74	99.56 12	93.43 53	98.75 30	98.47 33

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 25	97.47 11	91.73 11	96.10 27	96.69 76	89.90 12	99.30 43	94.70 38	98.04 72	99.13 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
region2R		94.43 28	94.27 38	94.92 20	98.65 8	86.67 30	96.92 24	97.23 36	88.60 97	93.58 68	97.27 47	85.22 58	99.54 20	92.21 81	98.74 31	98.56 25

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 28	86.29 46	97.46 6	97.40 20	89.03 82	96.20 26	98.10 10	89.39 16	99.34 37	95.88 23	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		94.43 28	94.28 36	94.91 21	98.63 9	86.69 28	96.94 20	97.32 28	88.63 94	93.53 71	97.26 49	85.04 62	99.54 20	92.35 77	98.78 26	98.50 27

GST-MVS		94.21 36	93.97 51	94.90 23	98.41 22	86.82 24	96.54 36	97.19 37	88.24 107	93.26 73	96.83 71	85.48 55	99.59 8	91.43 105	98.40 54	98.30 50

HFP-MVS		94.52 23	94.40 29	94.86 24	98.61 10	86.81 25	96.94 20	97.34 24	88.63 94	93.65 66	97.21 51	86.10 48	99.49 26	92.35 77	98.77 28	98.30 50

sasdasda		93.27 72	92.75 81	94.85 25	95.70 126	87.66 12	96.33 39	96.41 111	90.00 42	94.09 56	94.60 169	82.33 102	98.62 118	92.40 74	92.86 191	98.27 57

MP-MVS-pluss		94.21 36	94.00 50	94.85 25	98.17 33	86.65 31	94.82 149	97.17 42	86.26 164	92.83 86	97.87 27	85.57 54	99.56 12	94.37 43	98.92 17	98.34 43
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
canonicalmvs		93.27 72	92.75 81	94.85 25	95.70 126	87.66 12	96.33 39	96.41 111	90.00 42	94.09 56	94.60 169	82.33 102	98.62 118	92.40 74	92.86 191	98.27 57

XVS		94.45 26	94.32 32	94.85 25	98.54 13	86.60 34	96.93 22	97.19 37	90.66 26	92.85 84	97.16 57	85.02 63	99.49 26	91.99 91	98.56 50	98.47 33

X-MVStestdata		88.31 189	86.13 237	94.85 25	98.54 13	86.60 34	96.93 22	97.19 37	90.66 26	92.85 84	23.41 431	85.02 63	99.49 26	91.99 91	98.56 50	98.47 33

SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 25	96.99 75	86.33 42	97.33 7	97.30 30	91.38 13	95.39 38	97.46 39	88.98 19	99.40 30	94.12 44	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 54	86.00 50	98.29 1	97.49 6	90.75 21	97.62 5	98.06 16	92.59 2	99.61 4	95.64 26	99.02 12	98.86 11

alignmvs		93.08 79	92.50 87	94.81 32	95.62 132	87.61 15	95.99 71	96.07 143	89.77 55	94.12 55	94.87 155	80.56 123	98.66 111	92.42 73	93.10 187	98.15 68

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 52	97.13 14	97.44 15	90.31 32	97.71 1	98.07 14	92.31 4	99.58 10	95.66 24	99.13 3	98.84 14

DeepC-MVS_fast	89.43 2	94.04 44	93.79 56	94.80 33	97.48 64	86.78 26	95.65 99	96.89 67	89.40 66	92.81 87	96.97 64	85.37 57	99.24 46	90.87 114	98.69 35	98.38 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		94.25 33	94.07 47	94.77 35	98.47 18	86.31 44	96.71 31	96.98 55	89.04 80	91.98 109	97.19 54	85.43 56	99.56 12	92.06 90	98.79 24	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APD-MVS		94.24 34	94.07 47	94.75 36	98.06 39	86.90 23	95.88 80	96.94 62	85.68 178	95.05 45	97.18 55	87.31 35	99.07 56	91.90 97	98.61 48	98.28 55
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		94.34 31	94.21 41	94.74 37	98.39 23	86.64 32	97.60 4	97.24 34	88.53 99	92.73 92	97.23 50	85.20 59	99.32 41	92.15 84	98.83 22	98.25 62

PGM-MVS		93.96 49	93.72 60	94.68 38	98.43 20	86.22 47	95.30 114	97.78 1	87.45 135	93.26 73	97.33 45	84.62 71	99.51 24	90.75 116	98.57 49	98.32 49

DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 55	97.09 16	96.73 87	90.27 36	97.04 15	98.05 18	91.47 8	99.55 16	95.62 28	99.08 7	98.45 36
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
mPP-MVS		93.99 47	93.78 57	94.63 40	98.50 16	85.90 60	96.87 26	96.91 65	88.70 92	91.83 118	97.17 56	83.96 78	99.55 16	91.44 104	98.64 45	98.43 38

PHI-MVS		93.89 51	93.65 64	94.62 41	96.84 78	86.43 39	96.69 32	97.49 6	85.15 191	93.56 70	96.28 94	85.60 53	99.31 42	92.45 71	98.79 24	98.12 72

TSAR-MVS + MP.		94.85 14	94.94 16	94.58 42	98.25 29	86.33 42	96.11 59	96.62 96	88.14 112	96.10 27	96.96 65	89.09 18	98.94 83	94.48 41	98.68 37	98.48 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CANet		93.54 60	93.20 73	94.55 43	95.65 129	85.73 65	94.94 140	96.69 92	91.89 9	90.69 134	95.88 114	81.99 114	99.54 20	93.14 59	97.95 75	98.39 40

train_agg		93.44 65	93.08 74	94.52 44	97.53 61	86.49 37	94.07 201	96.78 79	81.86 273	92.77 89	96.20 97	87.63 29	99.12 54	92.14 85	98.69 35	97.94 82

CDPH-MVS		92.83 83	92.30 89	94.44 45	97.79 52	86.11 49	94.06 203	96.66 93	80.09 304	92.77 89	96.63 83	86.62 40	99.04 60	87.40 152	98.66 41	98.17 67

3Dnovator	86.66 5	91.73 101	90.82 113	94.44 45	94.59 188	86.37 41	97.18 12	97.02 53	89.20 74	84.31 280	96.66 79	73.74 215	99.17 50	86.74 162	97.96 74	97.79 94

SR-MVS		94.23 35	94.17 45	94.43 47	98.21 32	85.78 63	96.40 38	96.90 66	88.20 110	94.33 51	97.40 42	84.75 70	99.03 61	93.35 56	97.99 73	98.48 30

HPM-MVS		94.02 45	93.88 52	94.43 47	98.39 23	85.78 63	97.25 10	97.07 51	86.90 149	92.62 96	96.80 75	84.85 69	99.17 50	92.43 72	98.65 44	98.33 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TSAR-MVS + GP.		93.66 58	93.41 68	94.41 49	96.59 85	86.78 26	94.40 176	93.93 268	89.77 55	94.21 53	95.59 127	87.35 34	98.61 120	92.72 67	96.15 122	97.83 92

reproduce-ours		94.82 15	94.97 14	94.38 50	97.91 47	85.46 68	95.86 81	97.15 44	89.82 48	95.23 42	98.10 10	87.09 37	99.37 33	95.30 32	98.25 60	98.30 50

our_new_method		94.82 15	94.97 14	94.38 50	97.91 47	85.46 68	95.86 81	97.15 44	89.82 48	95.23 42	98.10 10	87.09 37	99.37 33	95.30 32	98.25 60	98.30 50

test12				94.34 52	97.13 73	86.15 48		96.29 119		91.04 131		85.08 61	99.01 66		98.13 67	97.86 89

ACMMP		93.24 74	92.88 79	94.30 53	98.09 38	85.33 72	96.86 27	97.45 14	88.33 103	90.15 144	97.03 63	81.44 117	99.51 24	90.85 115	95.74 127	98.04 77
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
reproduce_model		94.76 19	94.92 17	94.29 54	97.92 43	85.18 74	95.95 76	97.19 37	89.67 58	95.27 41	98.16 3	86.53 43	99.36 35	95.42 31	98.15 65	98.33 45

DeepC-MVS	88.79 3	93.31 71	92.99 77	94.26 55	96.07 109	85.83 61	94.89 143	96.99 54	89.02 83	89.56 149	97.37 44	82.51 99	99.38 31	92.20 82	98.30 57	97.57 107
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCFI-Net		93.03 80	92.63 84	94.23 56	95.62 132	85.92 57	96.08 61	96.33 117	89.86 46	93.89 63	94.66 166	82.11 109	98.50 126	92.33 79	92.82 194	98.27 57

fmvsm_l_conf0.5_n_3		94.80 18	95.01 13	94.15 57	95.64 130	85.08 75	96.09 60	97.36 22	90.98 16	97.09 13	98.12 7	84.98 67	98.94 83	97.07 12	97.80 80	98.43 38

EPNet		91.79 98	91.02 109	94.10 58	90.10 357	85.25 73	96.03 68	92.05 318	92.83 3	87.39 192	95.78 119	79.39 139	99.01 66	88.13 143	97.48 88	98.05 76
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmconf_n		94.60 22	94.81 21	93.98 59	94.62 186	84.96 78	96.15 54	97.35 23	89.37 67	96.03 30	98.11 8	86.36 44	99.01 66	97.45 7	97.83 79	97.96 81

DELS-MVS		93.43 69	93.25 71	93.97 60	95.42 140	85.04 76	93.06 254	97.13 46	90.74 23	91.84 116	95.09 148	86.32 45	99.21 48	91.22 106	98.45 52	97.65 102
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DP-MVS Recon		91.95 96	91.28 103	93.96 61	98.33 27	85.92 57	94.66 160	96.66 93	82.69 252	90.03 146	95.82 117	82.30 104	99.03 61	84.57 189	96.48 116	96.91 145

HPM-MVS_fast		93.40 70	93.22 72	93.94 62	98.36 25	84.83 80	97.15 13	96.80 78	85.77 175	92.47 100	97.13 58	82.38 100	99.07 56	90.51 119	98.40 54	97.92 85

test_fmvsmconf0.1_n		94.20 38	94.31 34	93.88 63	92.46 276	84.80 81	96.18 51	96.82 75	89.29 71	95.68 35	98.11 8	85.10 60	98.99 73	97.38 8	97.75 84	97.86 89

SD-MVS		94.96 13	95.33 8	93.88 63	97.25 72	86.69 28	96.19 49	97.11 49	90.42 29	96.95 17	97.27 47	89.53 14	96.91 269	94.38 42	98.85 20	98.03 78
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
MVS_111021_HR		93.45 64	93.31 69	93.84 65	96.99 75	84.84 79	93.24 247	97.24 34	88.76 89	91.60 123	95.85 115	86.07 49	98.66 111	91.91 95	98.16 64	98.03 78

SR-MVS-dyc-post		93.82 53	93.82 54	93.82 66	97.92 43	84.57 87	96.28 43	96.76 82	87.46 133	93.75 64	97.43 40	84.24 75	99.01 66	92.73 65	97.80 80	97.88 87

test_prior				93.82 66	97.29 70	84.49 91		96.88 68					98.87 90			98.11 73

APD-MVS_3200maxsize		93.78 54	93.77 58	93.80 68	97.92 43	84.19 102	96.30 41	96.87 69	86.96 145	93.92 62	97.47 38	83.88 79	98.96 80	92.71 68	97.87 77	98.26 61

fmvsm_l_conf0.5_n		94.29 32	94.46 27	93.79 69	95.28 145	85.43 70	95.68 94	96.43 109	86.56 156	96.84 19	97.81 30	87.56 32	98.77 103	97.14 10	96.82 106	97.16 128

CSCG		93.23 75	93.05 75	93.76 70	98.04 40	84.07 104	96.22 48	97.37 21	84.15 214	90.05 145	95.66 124	87.77 26	99.15 53	89.91 124	98.27 58	98.07 74

GDP-MVS		92.04 94	91.46 100	93.75 71	94.55 193	84.69 84	95.60 105	96.56 101	87.83 125	93.07 80	95.89 113	73.44 219	98.65 113	90.22 122	96.03 124	97.91 86

BP-MVS1		92.48 89	92.07 92	93.72 72	94.50 196	84.39 99	95.90 79	94.30 254	90.39 30	92.67 94	95.94 110	74.46 199	98.65 113	93.14 59	97.35 92	98.13 69

test_fmvsmconf0.01_n		93.19 76	93.02 76	93.71 73	89.25 370	84.42 98	96.06 65	96.29 119	89.06 78	94.68 47	98.13 4	79.22 141	98.98 77	97.22 9	97.24 94	97.74 97

UA-Net		92.83 83	92.54 86	93.68 74	96.10 106	84.71 83	95.66 97	96.39 113	91.92 8	93.22 75	96.49 89	83.16 88	98.87 90	84.47 191	95.47 134	97.45 112

fmvsm_l_conf0.5_n_a		94.20 38	94.40 29	93.60 75	95.29 144	84.98 77	95.61 102	96.28 122	86.31 162	96.75 21	97.86 28	87.40 33	98.74 106	97.07 12	97.02 99	97.07 131

QAPM		89.51 152	88.15 176	93.59 76	94.92 167	84.58 86	96.82 29	96.70 91	78.43 331	83.41 301	96.19 100	73.18 223	99.30 43	77.11 300	96.54 113	96.89 146

test_fmvsm_n_1920		94.71 21	95.11 11	93.50 77	95.79 121	84.62 85	96.15 54	97.64 2	89.85 47	97.19 10	97.89 26	86.28 46	98.71 109	97.11 11	98.08 71	97.17 124

casdiffmvs_mvg		92.96 82	92.83 80	93.35 78	94.59 188	83.40 125	95.00 137	96.34 116	90.30 34	92.05 107	96.05 105	83.43 82	98.15 160	92.07 87	95.67 128	98.49 29
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_5		93.96 49	94.18 44	93.30 79	94.79 176	83.81 111	95.77 89	96.74 86	88.02 115	96.23 25	97.84 29	83.36 86	98.83 97	97.49 5	97.34 93	97.25 119

EI-MVSNet-Vis-set		93.01 81	92.92 78	93.29 80	95.01 159	83.51 122	94.48 168	95.77 168	90.87 17	92.52 98	96.67 78	84.50 72	99.00 71	91.99 91	94.44 161	97.36 114

Vis-MVSNet		91.75 100	91.23 104	93.29 80	95.32 143	83.78 112	96.14 56	95.98 150	89.89 44	90.45 136	96.58 86	75.09 190	98.31 151	84.75 187	96.90 102	97.78 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_conf03		93.98 48	94.22 39	93.26 82	96.13 101	83.29 128	96.27 45	96.52 104	89.82 48	95.56 37	95.51 129	84.50 72	98.79 101	94.83 37	98.86 19	97.72 98

SPE-MVS-test		94.02 45	94.29 35	93.24 83	96.69 81	83.24 129	97.49 5	96.92 64	92.14 6	92.90 82	95.77 120	85.02 63	98.33 148	93.03 61	98.62 46	98.13 69

VNet		92.24 93	91.91 94	93.24 83	96.59 85	83.43 123	94.84 148	96.44 108	89.19 75	94.08 59	95.90 112	77.85 160	98.17 158	88.90 134	93.38 180	98.13 69

VDD-MVS		90.74 119	89.92 131	93.20 85	96.27 97	83.02 142	95.73 91	93.86 272	88.42 102	92.53 97	96.84 70	62.09 334	98.64 115	90.95 112	92.62 196	97.93 84

CS-MVS		94.12 42	94.44 28	93.17 86	96.55 88	83.08 139	97.63 3	96.95 61	91.71 12	93.50 72	96.21 96	85.61 52	98.24 153	93.64 50	98.17 63	98.19 65

nrg030		91.08 113	90.39 117	93.17 86	93.07 258	86.91 22	96.41 37	96.26 124	88.30 105	88.37 170	94.85 158	82.19 108	97.64 201	91.09 107	82.95 316	94.96 226

MVSMamba_PlusPlus		93.44 65	93.54 66	93.14 88	96.58 87	83.05 140	96.06 65	96.50 106	84.42 211	94.09 56	95.56 128	85.01 66	98.69 110	94.96 36	98.66 41	97.67 101

EI-MVSNet-UG-set		92.74 85	92.62 85	93.12 89	94.86 172	83.20 131	94.40 176	95.74 171	90.71 25	92.05 107	96.60 85	84.00 77	98.99 73	91.55 102	93.63 171	97.17 124

test_fmvsmvis_n_1920		93.44 65	93.55 65	93.10 90	93.67 240	84.26 101	95.83 85	96.14 134	89.00 84	92.43 101	97.50 37	83.37 85	98.72 107	96.61 19	97.44 89	96.32 168

新几何1				93.10 90	97.30 69	84.35 100		95.56 185	71.09 397	91.26 129	96.24 95	82.87 95	98.86 92	79.19 279	98.10 68	96.07 183

OMC-MVS		91.23 109	90.62 116	93.08 92	96.27 97	84.07 104	93.52 229	95.93 154	86.95 146	89.51 150	96.13 103	78.50 151	98.35 145	85.84 175	92.90 190	96.83 150

OpenMVS	83.78 11	88.74 178	87.29 195	93.08 92	92.70 271	85.39 71	96.57 35	96.43 109	78.74 326	80.85 333	96.07 104	69.64 266	99.01 66	78.01 291	96.65 111	94.83 233

MAR-MVS		90.30 130	89.37 142	93.07 94	96.61 84	84.48 92	95.68 94	95.67 177	82.36 257	87.85 179	92.85 230	76.63 171	98.80 99	80.01 267	96.68 110	95.91 189
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		90.92 114	90.21 120	93.03 95	93.86 230	83.88 109	92.81 263	93.86 272	79.84 307	91.76 119	94.29 179	77.92 157	98.04 176	90.48 120	97.11 95	97.17 124

Effi-MVS+		91.59 104	91.11 106	93.01 96	94.35 208	83.39 126	94.60 162	95.10 215	87.10 142	90.57 135	93.10 225	81.43 118	98.07 174	89.29 130	94.48 159	97.59 106

fmvsm_s_conf0.5_n_a		93.57 59	93.76 59	93.00 97	95.02 158	83.67 115	96.19 49	96.10 140	87.27 138	95.98 31	98.05 18	83.07 92	98.45 136	96.68 18	95.51 131	96.88 147

MVS_111021_LR		92.47 90	92.29 90	92.98 98	95.99 115	84.43 96	93.08 252	96.09 141	88.20 110	91.12 130	95.72 123	81.33 119	97.76 191	91.74 99	97.37 91	96.75 152

fmvsm_s_conf0.1_n_a		93.19 76	93.26 70	92.97 99	92.49 274	83.62 118	96.02 69	95.72 174	86.78 151	96.04 29	98.19 1	82.30 104	98.43 140	96.38 20	95.42 137	96.86 148

ETV-MVS		92.74 85	92.66 83	92.97 99	95.20 151	84.04 106	95.07 133	96.51 105	90.73 24	92.96 81	91.19 290	84.06 76	98.34 146	91.72 100	96.54 113	96.54 163

LFMVS		90.08 135	89.13 148	92.95 101	96.71 80	82.32 165	96.08 61	89.91 372	86.79 150	92.15 106	96.81 73	62.60 332	98.34 146	87.18 156	93.90 167	98.19 65

UGNet		89.95 140	88.95 152	92.95 101	94.51 195	83.31 127	95.70 93	95.23 208	89.37 67	87.58 186	93.94 194	64.00 322	98.78 102	83.92 198	96.31 118	96.74 153
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		90.80 117	90.10 124	92.90 103	93.04 261	83.53 121	93.08 252	94.15 261	80.22 301	91.41 126	94.91 152	76.87 165	97.93 185	90.28 121	96.90 102	97.24 120
jason: jason.
DP-MVS		87.25 229	85.36 266	92.90 103	97.65 58	83.24 129	94.81 150	92.00 320	74.99 365	81.92 322	95.00 150	72.66 228	99.05 58	66.92 377	92.33 201	96.40 165

fmvsm_s_conf0.5_n		93.76 55	94.06 49	92.86 105	95.62 132	83.17 132	96.14 56	96.12 138	88.13 113	95.82 33	98.04 21	83.43 82	98.48 128	96.97 16	96.23 119	96.92 144

fmvsm_s_conf0.1_n		93.46 63	93.66 63	92.85 106	93.75 236	83.13 134	96.02 69	95.74 171	87.68 130	95.89 32	98.17 2	82.78 96	98.46 132	96.71 17	96.17 121	96.98 140

CANet_DTU		90.26 132	89.41 141	92.81 107	93.46 247	83.01 143	93.48 230	94.47 247	89.43 65	87.76 184	94.23 184	70.54 255	99.03 61	84.97 182	96.39 117	96.38 166

MVSFormer		91.68 103	91.30 102	92.80 108	93.86 230	83.88 109	95.96 74	95.90 158	84.66 207	91.76 119	94.91 152	77.92 157	97.30 236	89.64 126	97.11 95	97.24 120

PVSNet_Blended_VisFu		91.38 106	90.91 111	92.80 108	96.39 94	83.17 132	94.87 145	96.66 93	83.29 237	89.27 156	94.46 174	80.29 126	99.17 50	87.57 150	95.37 138	96.05 186

fmvsm_s_conf0.5_n_6		94.11 43	94.56 24	92.76 110	94.98 162	81.96 172	95.79 87	97.29 32	89.31 69	97.52 7	97.61 35	83.25 87	98.88 89	97.05 14	98.22 62	97.43 113

VDDNet		89.56 151	88.49 167	92.76 110	95.07 157	82.09 167	96.30 41	93.19 287	81.05 295	91.88 114	96.86 69	61.16 350	98.33 148	88.43 140	92.49 200	97.84 91

h-mvs33		90.80 117	90.15 123	92.75 112	96.01 111	82.66 156	95.43 108	95.53 189	89.80 51	93.08 78	95.64 125	75.77 179	99.00 71	92.07 87	78.05 373	96.60 158

casdiffmvs		92.51 88	92.43 88	92.74 113	94.41 203	81.98 170	94.54 166	96.23 128	89.57 61	91.96 111	96.17 101	82.58 98	98.01 178	90.95 112	95.45 136	98.23 63
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_yl		90.69 121	90.02 129	92.71 114	95.72 124	82.41 163	94.11 196	95.12 213	85.63 179	91.49 124	94.70 162	74.75 194	98.42 141	86.13 170	92.53 198	97.31 115

DCV-MVSNet		90.69 121	90.02 129	92.71 114	95.72 124	82.41 163	94.11 196	95.12 213	85.63 179	91.49 124	94.70 162	74.75 194	98.42 141	86.13 170	92.53 198	97.31 115

PCF-MVS	84.11 10	87.74 204	86.08 241	92.70 116	94.02 221	84.43 96	89.27 352	95.87 162	73.62 379	84.43 272	94.33 176	78.48 152	98.86 92	70.27 351	94.45 160	94.81 234
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
baseline		92.39 92	92.29 90	92.69 117	94.46 199	81.77 175	94.14 193	96.27 123	89.22 73	91.88 114	96.00 106	82.35 101	97.99 180	91.05 108	95.27 142	98.30 50

MSLP-MVS++		93.72 57	94.08 46	92.65 118	97.31 68	83.43 123	95.79 87	97.33 26	90.03 41	93.58 68	96.96 65	84.87 68	97.76 191	92.19 83	98.66 41	96.76 151

EC-MVSNet		93.44 65	93.71 61	92.63 119	95.21 150	82.43 160	97.27 9	96.71 90	90.57 28	92.88 83	95.80 118	83.16 88	98.16 159	93.68 49	98.14 66	97.31 115

ab-mvs		89.41 157	88.35 169	92.60 120	95.15 155	82.65 157	92.20 283	95.60 184	83.97 218	88.55 166	93.70 207	74.16 207	98.21 157	82.46 220	89.37 244	96.94 142

LS3D		87.89 199	86.32 230	92.59 121	96.07 109	82.92 146	95.23 121	94.92 227	75.66 357	82.89 308	95.98 108	72.48 231	99.21 48	68.43 365	95.23 143	95.64 202

Anonymous20240529		88.09 195	86.59 219	92.58 122	96.53 90	81.92 173	95.99 71	95.84 164	74.11 374	89.06 160	95.21 142	61.44 342	98.81 98	83.67 203	87.47 275	97.01 138

fmvsm_s_conf0.5_n_3		94.49 24	95.13 10	92.56 123	95.49 138	81.10 197	95.93 77	97.16 43	92.96 2	97.39 8	98.13 4	83.63 81	98.80 99	97.89 1	97.61 87	97.78 95

CPTT-MVS		91.99 95	91.80 95	92.55 124	98.24 31	81.98 170	96.76 30	96.49 107	81.89 272	90.24 139	96.44 91	78.59 149	98.61 120	89.68 125	97.85 78	97.06 132

114514_t		89.51 152	88.50 165	92.54 125	98.11 36	81.99 169	95.16 129	96.36 115	70.19 401	85.81 226	95.25 139	76.70 169	98.63 117	82.07 230	96.86 105	97.00 139

PAPM_NR		91.22 110	90.78 114	92.52 126	97.60 59	81.46 184	94.37 182	96.24 127	86.39 161	87.41 189	94.80 160	82.06 112	98.48 128	82.80 215	95.37 138	97.61 104

DeepPCF-MVS	89.96 1	94.20 38	94.77 22	92.49 127	96.52 91	80.00 232	94.00 209	97.08 50	90.05 40	95.65 36	97.29 46	89.66 13	98.97 78	93.95 46	98.71 32	98.50 27

IS-MVSNet		91.43 105	91.09 108	92.46 128	95.87 120	81.38 187	96.95 19	93.69 279	89.72 57	89.50 152	95.98 108	78.57 150	97.77 190	83.02 209	96.50 115	98.22 64

API-MVS		90.66 123	90.07 125	92.45 129	96.36 95	84.57 87	96.06 65	95.22 210	82.39 255	89.13 157	94.27 182	80.32 125	98.46 132	80.16 266	96.71 109	94.33 257

xiu_mvs_v1_base_debu		90.64 124	90.05 126	92.40 130	93.97 227	84.46 93	93.32 238	95.46 192	85.17 188	92.25 102	94.03 186	70.59 251	98.57 123	90.97 109	94.67 151	94.18 260

xiu_mvs_v1_base		90.64 124	90.05 126	92.40 130	93.97 227	84.46 93	93.32 238	95.46 192	85.17 188	92.25 102	94.03 186	70.59 251	98.57 123	90.97 109	94.67 151	94.18 260

xiu_mvs_v1_base_debi		90.64 124	90.05 126	92.40 130	93.97 227	84.46 93	93.32 238	95.46 192	85.17 188	92.25 102	94.03 186	70.59 251	98.57 123	90.97 109	94.67 151	94.18 260

fmvsm_s_conf0.5_n_2		93.47 62	93.83 53	92.39 133	95.36 141	81.19 193	95.20 126	96.56 101	90.37 31	97.13 12	98.03 22	77.47 161	98.96 80	97.79 3	96.58 112	97.03 135

fmvsm_s_conf0.1_n_2		93.16 78	93.42 67	92.37 134	94.62 186	81.13 195	95.23 121	95.89 160	90.30 34	96.74 22	98.02 23	76.14 173	98.95 82	97.64 4	96.21 120	97.03 135

AdaColmap		89.89 143	89.07 149	92.37 134	97.41 65	83.03 141	94.42 175	95.92 155	82.81 249	86.34 215	94.65 167	73.89 211	99.02 64	80.69 257	95.51 131	95.05 221

CNLPA		89.07 168	87.98 179	92.34 136	96.87 77	84.78 82	94.08 200	93.24 285	81.41 286	84.46 270	95.13 147	75.57 186	96.62 280	77.21 298	93.84 169	95.61 205

fmvsm_s_conf0.5_n_4		93.86 52	94.37 31	92.33 137	95.13 156	80.95 202	95.64 100	96.97 56	89.60 60	96.85 18	97.77 31	83.08 91	98.92 86	97.49 5	96.78 107	97.13 129

ET-MVSNet_ETH3D		87.51 217	85.91 249	92.32 138	93.70 239	83.93 107	92.33 278	90.94 352	84.16 213	72.09 397	92.52 243	69.90 261	95.85 327	89.20 131	88.36 262	97.17 124

Anonymous202405211		87.68 205	86.13 237	92.31 139	96.66 82	80.74 209	94.87 145	91.49 337	80.47 300	89.46 153	95.44 131	54.72 386	98.23 154	82.19 226	89.89 234	97.97 80

CHOSEN 1792x2688		88.84 174	87.69 185	92.30 140	96.14 100	81.42 186	90.01 339	95.86 163	74.52 370	87.41 189	93.94 194	75.46 187	98.36 143	80.36 262	95.53 130	97.12 130

HY-MVS	83.01 12	89.03 170	87.94 181	92.29 141	94.86 172	82.77 148	92.08 288	94.49 246	81.52 285	86.93 196	92.79 236	78.32 154	98.23 154	79.93 268	90.55 222	95.88 191

CDS-MVSNet		89.45 155	88.51 164	92.29 141	93.62 242	83.61 120	93.01 255	94.68 243	81.95 267	87.82 182	93.24 219	78.69 147	96.99 263	80.34 263	93.23 185	96.28 171
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		90.02 137	89.27 147	92.29 141	95.78 122	80.95 202	92.68 265	96.22 129	81.91 269	86.66 206	93.75 206	82.23 106	98.44 138	79.40 278	94.79 149	97.48 110

mvsmamba		90.33 129	89.69 134	92.25 144	95.17 152	81.64 177	95.27 119	93.36 284	84.88 198	89.51 150	94.27 182	69.29 275	97.42 222	89.34 129	96.12 123	97.68 100

PLC	84.53 7	89.06 169	88.03 178	92.15 145	97.27 71	82.69 155	94.29 185	95.44 197	79.71 309	84.01 286	94.18 185	76.68 170	98.75 104	77.28 297	93.41 179	95.02 222
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPP-MVSNet		91.70 102	91.56 99	92.13 146	95.88 118	80.50 215	97.33 7	95.25 207	86.15 167	89.76 148	95.60 126	83.42 84	98.32 150	87.37 154	93.25 184	97.56 108

patch_mono-2		93.74 56	94.32 32	92.01 147	97.54 60	78.37 269	93.40 234	97.19 37	88.02 115	94.99 46	97.21 51	88.35 21	98.44 138	94.07 45	98.09 69	99.23 1

原ACMM1				92.01 147	97.34 67	81.05 198		96.81 77	78.89 320	90.45 136	95.92 111	82.65 97	98.84 96	80.68 258	98.26 59	96.14 177

UniMVSNet (Re)		89.80 145	89.07 149	92.01 147	93.60 243	84.52 90	94.78 152	97.47 11	89.26 72	86.44 212	92.32 249	82.10 110	97.39 233	84.81 186	80.84 350	94.12 264

MG-MVS		91.77 99	91.70 98	92.00 150	97.08 74	80.03 230	93.60 227	95.18 211	87.85 124	90.89 132	96.47 90	82.06 112	98.36 143	85.07 181	97.04 98	97.62 103

EIA-MVS		91.95 96	91.94 93	91.98 151	95.16 153	80.01 231	95.36 109	96.73 87	88.44 100	89.34 154	92.16 254	83.82 80	98.45 136	89.35 128	97.06 97	97.48 110

PVSNet_Blended		90.73 120	90.32 119	91.98 151	96.12 102	81.25 189	92.55 270	96.83 73	82.04 265	89.10 158	92.56 242	81.04 121	98.85 94	86.72 164	95.91 125	95.84 193

PS-MVSNAJ		91.18 111	90.92 110	91.96 153	95.26 148	82.60 159	92.09 287	95.70 175	86.27 163	91.84 116	92.46 244	79.70 134	98.99 73	89.08 132	95.86 126	94.29 258

TAMVS		89.21 163	88.29 173	91.96 153	93.71 237	82.62 158	93.30 242	94.19 259	82.22 260	87.78 183	93.94 194	78.83 144	96.95 266	77.70 293	92.98 189	96.32 168

SDMVSNet		90.19 133	89.61 136	91.93 155	96.00 112	83.09 138	92.89 260	95.98 150	88.73 90	86.85 202	95.20 143	72.09 235	97.08 255	88.90 134	89.85 236	95.63 203

FA-MVS(test-final)		89.66 147	88.91 154	91.93 155	94.57 191	80.27 219	91.36 303	94.74 240	84.87 199	89.82 147	92.61 241	74.72 197	98.47 131	83.97 197	93.53 174	97.04 134

MVS_Test		91.31 108	91.11 106	91.93 155	94.37 204	80.14 223	93.46 232	95.80 166	86.46 159	91.35 128	93.77 204	82.21 107	98.09 171	87.57 150	94.95 146	97.55 109

NR-MVSNet		88.58 184	87.47 191	91.93 155	93.04 261	84.16 103	94.77 153	96.25 126	89.05 79	80.04 346	93.29 217	79.02 143	97.05 260	81.71 241	80.05 360	94.59 241

HyFIR lowres test		88.09 195	86.81 207	91.93 155	96.00 112	80.63 211	90.01 339	95.79 167	73.42 381	87.68 185	92.10 260	73.86 212	97.96 182	80.75 256	91.70 205	97.19 123

GeoE		90.05 136	89.43 140	91.90 160	95.16 153	80.37 218	95.80 86	94.65 244	83.90 219	87.55 188	94.75 161	78.18 155	97.62 203	81.28 246	93.63 171	97.71 99

thisisatest0530		88.67 179	87.61 187	91.86 161	94.87 171	80.07 226	94.63 161	89.90 373	84.00 217	88.46 168	93.78 203	66.88 299	98.46 132	83.30 205	92.65 195	97.06 132

xiu_mvs_v2_base		91.13 112	90.89 112	91.86 161	94.97 163	82.42 161	92.24 281	95.64 182	86.11 171	91.74 121	93.14 223	79.67 137	98.89 88	89.06 133	95.46 135	94.28 259

DU-MVS		89.34 162	88.50 165	91.85 163	93.04 261	83.72 113	94.47 171	96.59 98	89.50 62	86.46 209	93.29 217	77.25 163	97.23 245	84.92 183	81.02 346	94.59 241

OPM-MVS		90.12 134	89.56 137	91.82 164	93.14 254	83.90 108	94.16 192	95.74 171	88.96 85	87.86 178	95.43 133	72.48 231	97.91 186	88.10 145	90.18 229	93.65 295
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		90.60 127	90.19 121	91.82 164	94.70 182	82.73 152	95.85 83	96.22 129	90.81 19	86.91 198	94.86 156	74.23 203	98.12 161	88.15 141	89.99 230	94.63 238

UniMVSNet_NR-MVSNet		89.92 142	89.29 145	91.81 166	93.39 249	83.72 113	94.43 174	97.12 47	89.80 51	86.46 209	93.32 214	83.16 88	97.23 245	84.92 183	81.02 346	94.49 251

diffmvs		91.37 107	91.23 104	91.77 167	93.09 257	80.27 219	92.36 275	95.52 190	87.03 144	91.40 127	94.93 151	80.08 128	97.44 220	92.13 86	94.56 156	97.61 104
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
1112_ss		88.42 185	87.33 194	91.72 168	94.92 167	80.98 200	92.97 257	94.54 245	78.16 337	83.82 289	93.88 199	78.78 146	97.91 186	79.45 274	89.41 243	96.26 172

Fast-Effi-MVS+		89.41 157	88.64 160	91.71 169	94.74 177	80.81 207	93.54 228	95.10 215	83.11 241	86.82 204	90.67 313	79.74 133	97.75 194	80.51 261	93.55 173	96.57 161

WTY-MVS		89.60 149	88.92 153	91.67 170	95.47 139	81.15 194	92.38 274	94.78 238	83.11 241	89.06 160	94.32 177	78.67 148	96.61 283	81.57 242	90.89 218	97.24 120

TAPA-MVS	84.62 6	88.16 193	87.01 203	91.62 171	96.64 83	80.65 210	94.39 178	96.21 132	76.38 350	86.19 219	95.44 131	79.75 132	98.08 173	62.75 394	95.29 140	96.13 178
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VPA-MVSNet		89.62 148	88.96 151	91.60 172	93.86 230	82.89 147	95.46 107	97.33 26	87.91 119	88.43 169	93.31 215	74.17 206	97.40 230	87.32 155	82.86 321	94.52 246

FE-MVS		87.40 222	86.02 243	91.57 173	94.56 192	79.69 240	90.27 326	93.72 278	80.57 298	88.80 163	91.62 279	65.32 314	98.59 122	74.97 322	94.33 163	96.44 164

XVG-OURS		89.40 159	88.70 159	91.52 174	94.06 219	81.46 184	91.27 307	96.07 143	86.14 168	88.89 162	95.77 120	68.73 284	97.26 242	87.39 153	89.96 232	95.83 194

hse-mvs2		89.88 144	89.34 143	91.51 175	94.83 174	81.12 196	93.94 212	93.91 271	89.80 51	93.08 78	93.60 208	75.77 179	97.66 198	92.07 87	77.07 380	95.74 198

TranMVSNet+NR-MVSNet		88.84 174	87.95 180	91.49 176	92.68 272	83.01 143	94.92 142	96.31 118	89.88 45	85.53 235	93.85 201	76.63 171	96.96 265	81.91 234	79.87 363	94.50 249

AUN-MVS		87.78 203	86.54 222	91.48 177	94.82 175	81.05 198	93.91 216	93.93 268	83.00 244	86.93 196	93.53 209	69.50 269	97.67 196	86.14 168	77.12 379	95.73 200

XVG-OURS-SEG-HR		89.95 140	89.45 138	91.47 178	94.00 225	81.21 192	91.87 291	96.06 145	85.78 174	88.55 166	95.73 122	74.67 198	97.27 240	88.71 137	89.64 241	95.91 189

MVS		87.44 220	86.10 240	91.44 179	92.61 273	83.62 118	92.63 267	95.66 179	67.26 406	81.47 325	92.15 255	77.95 156	98.22 156	79.71 270	95.48 133	92.47 337

F-COLMAP		87.95 198	86.80 208	91.40 180	96.35 96	80.88 205	94.73 155	95.45 195	79.65 310	82.04 320	94.61 168	71.13 242	98.50 126	76.24 310	91.05 216	94.80 235

dcpmvs_2		93.49 61	94.19 43	91.38 181	97.69 57	76.78 302	94.25 187	96.29 119	88.33 103	94.46 49	96.88 68	88.07 25	98.64 115	93.62 51	98.09 69	98.73 18

thisisatest0515		87.33 225	85.99 244	91.37 182	93.49 245	79.55 241	90.63 321	89.56 381	80.17 302	87.56 187	90.86 303	67.07 296	98.28 152	81.50 243	93.02 188	96.29 170

HQP-MVS		89.80 145	89.28 146	91.34 183	94.17 214	81.56 178	94.39 178	96.04 146	88.81 86	85.43 244	93.97 193	73.83 213	97.96 182	87.11 159	89.77 239	94.50 249

RRT-MVS		90.85 116	90.70 115	91.30 184	94.25 210	76.83 301	94.85 147	96.13 137	89.04 80	90.23 140	94.88 154	70.15 260	98.72 107	91.86 98	94.88 147	98.34 43

FMVSNet3		87.40 222	86.11 239	91.30 184	93.79 235	83.64 117	94.20 191	94.81 236	83.89 220	84.37 273	91.87 270	68.45 287	96.56 288	78.23 288	85.36 292	93.70 294

FMVSNet2		87.19 235	85.82 252	91.30 184	94.01 222	83.67 115	94.79 151	94.94 222	83.57 227	83.88 288	92.05 264	66.59 304	96.51 292	77.56 295	85.01 295	93.73 292

RPMNet		83.95 311	81.53 322	91.21 187	90.58 348	79.34 248	85.24 397	96.76 82	71.44 395	85.55 233	82.97 404	70.87 247	98.91 87	61.01 398	89.36 245	95.40 209

IB-MVS	80.51 15	85.24 289	83.26 306	91.19 188	92.13 285	79.86 236	91.75 294	91.29 342	83.28 238	80.66 336	88.49 359	61.28 344	98.46 132	80.99 252	79.46 367	95.25 215
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		89.47 154	88.90 155	91.18 189	94.22 212	82.07 168	92.13 285	96.09 141	87.90 120	85.37 250	92.45 245	74.38 201	97.56 207	87.15 157	90.43 224	93.93 273
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		89.45 155	88.90 155	91.12 190	94.47 197	81.49 182	95.30 114	96.14 134	86.73 153	85.45 241	95.16 145	69.89 262	98.10 163	87.70 148	89.23 248	93.77 288

LGP-MVS_train				91.12 190	94.47 197	81.49 182		96.14 134	86.73 153	85.45 241	95.16 145	69.89 262	98.10 163	87.70 148	89.23 248	93.77 288

ACMM	84.12 9	89.14 164	88.48 168	91.12 190	94.65 185	81.22 191	95.31 112	96.12 138	85.31 187	85.92 224	94.34 175	70.19 259	98.06 175	85.65 176	88.86 253	94.08 268
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tttt0517		88.61 181	87.78 184	91.11 193	94.96 164	77.81 284	95.35 110	89.69 376	85.09 193	88.05 176	94.59 171	66.93 297	98.48 128	83.27 206	92.13 203	97.03 135

GBi-Net		87.26 227	85.98 245	91.08 194	94.01 222	83.10 135	95.14 130	94.94 222	83.57 227	84.37 273	91.64 275	66.59 304	96.34 305	78.23 288	85.36 292	93.79 283

test1		87.26 227	85.98 245	91.08 194	94.01 222	83.10 135	95.14 130	94.94 222	83.57 227	84.37 273	91.64 275	66.59 304	96.34 305	78.23 288	85.36 292	93.79 283

FMVSNet1		85.85 274	84.11 293	91.08 194	92.81 268	83.10 135	95.14 130	94.94 222	81.64 280	82.68 310	91.64 275	59.01 366	96.34 305	75.37 316	83.78 305	93.79 283

Test_1112_low_res		87.65 207	86.51 223	91.08 194	94.94 166	79.28 252	91.77 293	94.30 254	76.04 355	83.51 299	92.37 247	77.86 159	97.73 195	78.69 283	89.13 250	96.22 173

PS-MVSNAJss		89.97 139	89.62 135	91.02 198	91.90 294	80.85 206	95.26 120	95.98 150	86.26 164	86.21 218	94.29 179	79.70 134	97.65 199	88.87 136	88.10 264	94.57 243

BH-RMVSNet		88.37 187	87.48 190	91.02 198	95.28 145	79.45 244	92.89 260	93.07 290	85.45 184	86.91 198	94.84 159	70.35 256	97.76 191	73.97 330	94.59 155	95.85 192

UniMVSNet_ETH3D		87.53 216	86.37 227	91.00 200	92.44 277	78.96 257	94.74 154	95.61 183	84.07 216	85.36 251	94.52 173	59.78 358	97.34 235	82.93 210	87.88 269	96.71 154

FIs		90.51 128	90.35 118	90.99 201	93.99 226	80.98 200	95.73 91	97.54 4	89.15 76	86.72 205	94.68 164	81.83 116	97.24 244	85.18 180	88.31 263	94.76 236

ACMP	84.23 8	89.01 172	88.35 169	90.99 201	94.73 178	81.27 188	95.07 133	95.89 160	86.48 157	83.67 294	94.30 178	69.33 271	97.99 180	87.10 161	88.55 255	93.72 293
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20231211		86.59 257	85.13 272	90.98 203	96.52 91	81.50 180	96.14 56	96.16 133	73.78 377	83.65 295	92.15 255	63.26 328	97.37 234	82.82 214	81.74 335	94.06 269

sss		88.93 173	88.26 175	90.94 204	94.05 220	80.78 208	91.71 295	95.38 201	81.55 284	88.63 165	93.91 198	75.04 191	95.47 346	82.47 219	91.61 206	96.57 161

sd_testset		88.59 183	87.85 183	90.83 205	96.00 112	80.42 217	92.35 276	94.71 241	88.73 90	86.85 202	95.20 143	67.31 291	96.43 299	79.64 272	89.85 236	95.63 203

PVSNet_BlendedMVS		89.98 138	89.70 133	90.82 206	96.12 102	81.25 189	93.92 214	96.83 73	83.49 231	89.10 158	92.26 252	81.04 121	98.85 94	86.72 164	87.86 270	92.35 343

cascas		86.43 265	84.98 275	90.80 207	92.10 287	80.92 204	90.24 330	95.91 157	73.10 384	83.57 298	88.39 360	65.15 316	97.46 216	84.90 185	91.43 208	94.03 271

ECVR-MVS		89.09 167	88.53 163	90.77 208	95.62 132	75.89 315	96.16 52	84.22 406	87.89 122	90.20 141	96.65 80	63.19 329	98.10 163	85.90 173	96.94 100	98.33 45

GA-MVS		86.61 255	85.27 269	90.66 209	91.33 317	78.71 259	90.40 325	93.81 275	85.34 186	85.12 254	89.57 341	61.25 345	97.11 254	80.99 252	89.59 242	96.15 176

thres600view7		87.65 207	86.67 214	90.59 210	96.08 108	78.72 258	94.88 144	91.58 333	87.06 143	88.08 174	92.30 250	68.91 281	98.10 163	70.05 358	91.10 211	94.96 226

thres400		87.62 212	86.64 215	90.57 211	95.99 115	78.64 260	94.58 163	91.98 322	86.94 147	88.09 172	91.77 271	69.18 277	98.10 163	70.13 355	91.10 211	94.96 226

baseline1		88.10 194	87.28 196	90.57 211	94.96 164	80.07 226	94.27 186	91.29 342	86.74 152	87.41 189	94.00 191	76.77 168	96.20 310	80.77 255	79.31 369	95.44 207

FC-MVSNet-test		90.27 131	90.18 122	90.53 213	93.71 237	79.85 237	95.77 89	97.59 3	89.31 69	86.27 216	94.67 165	81.93 115	97.01 262	84.26 193	88.09 266	94.71 237

PAPM		86.68 254	85.39 264	90.53 213	93.05 260	79.33 251	89.79 342	94.77 239	78.82 323	81.95 321	93.24 219	76.81 166	97.30 236	66.94 375	93.16 186	94.95 229

WR-MVS		88.38 186	87.67 186	90.52 215	93.30 251	80.18 221	93.26 245	95.96 153	88.57 98	85.47 240	92.81 234	76.12 174	96.91 269	81.24 247	82.29 326	94.47 254

MVSTER		88.84 174	88.29 173	90.51 216	92.95 266	80.44 216	93.73 221	95.01 219	84.66 207	87.15 193	93.12 224	72.79 227	97.21 247	87.86 146	87.36 278	93.87 278

testdata				90.49 217	96.40 93	77.89 281		95.37 203	72.51 389	93.63 67	96.69 76	82.08 111	97.65 199	83.08 207	97.39 90	95.94 188

test1111		89.10 165	88.64 160	90.48 218	95.53 137	74.97 325	96.08 61	84.89 404	88.13 113	90.16 143	96.65 80	63.29 327	98.10 163	86.14 168	96.90 102	98.39 40

tt0805		86.92 243	85.74 258	90.48 218	92.22 281	79.98 233	95.63 101	94.88 230	83.83 222	84.74 263	92.80 235	57.61 372	97.67 196	85.48 179	84.42 299	93.79 283

jajsoiax		88.24 191	87.50 189	90.48 218	90.89 337	80.14 223	95.31 112	95.65 181	84.97 196	84.24 281	94.02 189	65.31 315	97.42 222	88.56 138	88.52 257	93.89 274

PatchMatch-RL		86.77 251	85.54 260	90.47 221	95.88 118	82.71 154	90.54 323	92.31 310	79.82 308	84.32 278	91.57 283	68.77 283	96.39 301	73.16 336	93.48 178	92.32 344

tfpn200view9		87.58 214	86.64 215	90.41 222	95.99 115	78.64 260	94.58 163	91.98 322	86.94 147	88.09 172	91.77 271	69.18 277	98.10 163	70.13 355	91.10 211	94.48 252

VPNet		88.20 192	87.47 191	90.39 223	93.56 244	79.46 243	94.04 204	95.54 188	88.67 93	86.96 195	94.58 172	69.33 271	97.15 249	84.05 196	80.53 355	94.56 244

ACMH	80.38 17	85.36 284	83.68 300	90.39 223	94.45 200	80.63 211	94.73 155	94.85 232	82.09 262	77.24 369	92.65 239	60.01 356	97.58 205	72.25 340	84.87 296	92.96 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres100view900		87.63 210	86.71 211	90.38 225	96.12 102	78.55 262	95.03 136	91.58 333	87.15 140	88.06 175	92.29 251	68.91 281	98.10 163	70.13 355	91.10 211	94.48 252

mvs_tets		88.06 197	87.28 196	90.38 225	90.94 333	79.88 235	95.22 123	95.66 179	85.10 192	84.21 282	93.94 194	63.53 325	97.40 230	88.50 139	88.40 261	93.87 278

1314		87.51 217	86.57 220	90.34 227	92.42 278	79.74 239	92.63 267	95.35 205	78.35 332	80.14 343	91.62 279	74.05 208	97.15 249	81.05 248	93.53 174	94.12 264

LTVRE_ROB	82.13 13	86.26 268	84.90 278	90.34 227	94.44 201	81.50 180	92.31 280	94.89 228	83.03 243	79.63 352	92.67 238	69.69 265	97.79 189	71.20 344	86.26 287	91.72 354
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
test_djsdf		89.03 170	88.64 160	90.21 229	90.74 343	79.28 252	95.96 74	95.90 158	84.66 207	85.33 252	92.94 229	74.02 209	97.30 236	89.64 126	88.53 256	94.05 270

v2v482		87.84 200	87.06 200	90.17 230	90.99 329	79.23 255	94.00 209	95.13 212	84.87 199	85.53 235	92.07 263	74.45 200	97.45 217	84.71 188	81.75 334	93.85 281

pmmvs4		85.43 282	83.86 298	90.16 231	90.02 360	82.97 145	90.27 326	92.67 302	75.93 356	80.73 334	91.74 273	71.05 243	95.73 335	78.85 282	83.46 312	91.78 353

V42		87.68 205	86.86 205	90.15 232	90.58 348	80.14 223	94.24 189	95.28 206	83.66 225	85.67 230	91.33 285	74.73 196	97.41 228	84.43 192	81.83 332	92.89 325

MSDG		84.86 297	83.09 309	90.14 233	93.80 233	80.05 228	89.18 355	93.09 289	78.89 320	78.19 361	91.91 268	65.86 313	97.27 240	68.47 364	88.45 259	93.11 317

anonymousdsp		87.84 200	87.09 199	90.12 234	89.13 371	80.54 214	94.67 159	95.55 186	82.05 263	83.82 289	92.12 257	71.47 240	97.15 249	87.15 157	87.80 273	92.67 331

thres200		87.21 233	86.24 234	90.12 234	95.36 141	78.53 263	93.26 245	92.10 316	86.42 160	88.00 177	91.11 296	69.24 276	98.00 179	69.58 359	91.04 217	93.83 282

CR-MVSNet		85.35 285	83.76 299	90.12 234	90.58 348	79.34 248	85.24 397	91.96 324	78.27 334	85.55 233	87.87 370	71.03 244	95.61 338	73.96 331	89.36 245	95.40 209

v1144		87.61 213	86.79 209	90.06 237	91.01 328	79.34 248	93.95 211	95.42 200	83.36 236	85.66 231	91.31 288	74.98 192	97.42 222	83.37 204	82.06 328	93.42 304

XXY-MVS		87.65 207	86.85 206	90.03 238	92.14 284	80.60 213	93.76 220	95.23 208	82.94 246	84.60 265	94.02 189	74.27 202	95.49 345	81.04 249	83.68 308	94.01 272

Vis-MVSNet (Re-imp)		89.59 150	89.44 139	90.03 238	95.74 123	75.85 316	95.61 102	90.80 356	87.66 132	87.83 181	95.40 134	76.79 167	96.46 297	78.37 284	96.73 108	97.80 93

test2506		87.21 233	86.28 232	90.02 240	95.62 132	73.64 341	96.25 47	71.38 429	87.89 122	90.45 136	96.65 80	55.29 383	98.09 171	86.03 172	96.94 100	98.33 45

BH-untuned		88.60 182	88.13 177	90.01 241	95.24 149	78.50 265	93.29 243	94.15 261	84.75 204	84.46 270	93.40 211	75.76 181	97.40 230	77.59 294	94.52 158	94.12 264

v1192		87.25 229	86.33 229	90.00 242	90.76 342	79.04 256	93.80 218	95.48 191	82.57 253	85.48 239	91.18 292	73.38 222	97.42 222	82.30 223	82.06 328	93.53 298

v7n		86.81 246	85.76 256	89.95 243	90.72 344	79.25 254	95.07 133	95.92 155	84.45 210	82.29 314	90.86 303	72.60 230	97.53 209	79.42 277	80.52 356	93.08 319

testing91		87.11 238	86.18 235	89.92 244	94.43 202	75.38 324	91.53 300	92.27 312	86.48 157	86.50 207	90.24 321	61.19 348	97.53 209	82.10 228	90.88 219	96.84 149

v8		87.50 219	86.71 211	89.89 245	91.37 314	79.40 245	94.50 167	95.38 201	84.81 202	83.60 297	91.33 285	76.05 175	97.42 222	82.84 213	80.51 357	92.84 327

v10		87.25 229	86.38 226	89.85 246	91.19 320	79.50 242	94.48 168	95.45 195	83.79 223	83.62 296	91.19 290	75.13 189	97.42 222	81.94 233	80.60 352	92.63 333

baseline2		86.50 261	85.39 264	89.84 247	91.12 325	76.70 304	91.88 290	88.58 384	82.35 258	79.95 347	90.95 301	73.42 220	97.63 202	80.27 265	89.95 233	95.19 216

pm-mvs1		86.61 255	85.54 260	89.82 248	91.44 309	80.18 221	95.28 118	94.85 232	83.84 221	81.66 323	92.62 240	72.45 233	96.48 294	79.67 271	78.06 372	92.82 328

TR-MVS		86.78 248	85.76 256	89.82 248	94.37 204	78.41 267	92.47 271	92.83 296	81.11 294	86.36 213	92.40 246	68.73 284	97.48 213	73.75 334	89.85 236	93.57 297

ACMH+	81.04 14	85.05 292	83.46 303	89.82 248	94.66 184	79.37 246	94.44 173	94.12 264	82.19 261	78.04 363	92.82 233	58.23 369	97.54 208	73.77 333	82.90 320	92.54 334

EI-MVSNet		89.10 165	88.86 157	89.80 251	91.84 296	78.30 271	93.70 224	95.01 219	85.73 176	87.15 193	95.28 137	79.87 131	97.21 247	83.81 200	87.36 278	93.88 277

v144192		87.19 235	86.35 228	89.74 252	90.64 346	78.24 273	93.92 214	95.43 198	81.93 268	85.51 237	91.05 299	74.21 205	97.45 217	82.86 212	81.56 336	93.53 298

COLMAP_ROB	80.39 16	83.96 310	82.04 319	89.74 252	95.28 145	79.75 238	94.25 187	92.28 311	75.17 363	78.02 364	93.77 204	58.60 368	97.84 188	65.06 386	85.92 288	91.63 356
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SCA		86.32 267	85.18 271	89.73 254	92.15 283	76.60 305	91.12 311	91.69 329	83.53 230	85.50 238	88.81 353	66.79 300	96.48 294	76.65 303	90.35 226	96.12 179

IterMVS-LS		88.36 188	87.91 182	89.70 255	93.80 233	78.29 272	93.73 221	95.08 217	85.73 176	84.75 262	91.90 269	79.88 130	96.92 268	83.83 199	82.51 322	93.89 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing11		86.44 264	85.35 267	89.69 256	94.29 209	75.40 323	91.30 305	90.53 359	84.76 203	85.06 256	90.13 327	58.95 367	97.45 217	82.08 229	91.09 215	96.21 175

testing99		86.72 252	85.73 259	89.69 256	94.23 211	74.91 327	91.35 304	90.97 350	86.14 168	86.36 213	90.22 322	59.41 361	97.48 213	82.24 225	90.66 221	96.69 156

v1921920		86.97 242	86.06 242	89.69 256	90.53 351	78.11 276	93.80 218	95.43 198	81.90 270	85.33 252	91.05 299	72.66 228	97.41 228	82.05 231	81.80 333	93.53 298

Fast-Effi-MVS+-dtu		87.44 220	86.72 210	89.63 259	92.04 288	77.68 290	94.03 205	93.94 267	85.81 173	82.42 313	91.32 287	70.33 257	97.06 258	80.33 264	90.23 228	94.14 263

v1240		86.78 248	85.85 251	89.56 260	90.45 352	77.79 286	93.61 226	95.37 203	81.65 279	85.43 244	91.15 294	71.50 239	97.43 221	81.47 244	82.05 330	93.47 302

Effi-MVS+-dtu		88.65 180	88.35 169	89.54 261	93.33 250	76.39 309	94.47 171	94.36 252	87.70 129	85.43 244	89.56 342	73.45 218	97.26 242	85.57 178	91.28 210	94.97 223

AllTest		83.42 317	81.39 323	89.52 262	95.01 159	77.79 286	93.12 249	90.89 354	77.41 341	76.12 377	93.34 212	54.08 389	97.51 211	68.31 366	84.27 301	93.26 307

TestCases				89.52 262	95.01 159	77.79 286		90.89 354	77.41 341	76.12 377	93.34 212	54.08 389	97.51 211	68.31 366	84.27 301	93.26 307

mvs_anonymous		89.37 161	89.32 144	89.51 264	93.47 246	74.22 334	91.65 298	94.83 234	82.91 247	85.45 241	93.79 202	81.23 120	96.36 304	86.47 166	94.09 164	97.94 82

XVG-ACMP-BASELINE		86.00 270	84.84 280	89.45 265	91.20 319	78.00 277	91.70 296	95.55 186	85.05 194	82.97 307	92.25 253	54.49 387	97.48 213	82.93 210	87.45 277	92.89 325

testing222		84.84 298	83.32 304	89.43 266	94.15 217	75.94 314	91.09 312	89.41 382	84.90 197	85.78 227	89.44 343	52.70 394	96.28 308	70.80 350	91.57 207	96.07 183

MVP-Stereo		85.97 271	84.86 279	89.32 267	90.92 335	82.19 166	92.11 286	94.19 259	78.76 325	78.77 360	91.63 278	68.38 288	96.56 288	75.01 321	93.95 166	89.20 392
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchmatchNet		85.85 274	84.70 282	89.29 268	91.76 300	75.54 320	88.49 364	91.30 341	81.63 281	85.05 257	88.70 357	71.71 236	96.24 309	74.61 326	89.05 251	96.08 182
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v148		87.04 240	86.32 230	89.21 269	90.94 333	77.26 295	93.71 223	94.43 248	84.84 201	84.36 276	90.80 307	76.04 176	97.05 260	82.12 227	79.60 366	93.31 306

tfpnnormal		84.72 300	83.23 307	89.20 270	92.79 269	80.05 228	94.48 168	95.81 165	82.38 256	81.08 331	91.21 289	69.01 280	96.95 266	61.69 396	80.59 353	90.58 379

cl22		86.78 248	85.98 245	89.18 271	92.34 279	77.62 291	90.84 317	94.13 263	81.33 288	83.97 287	90.15 326	73.96 210	96.60 285	84.19 194	82.94 317	93.33 305

BH-w/o		87.57 215	87.05 201	89.12 272	94.90 170	77.90 280	92.41 272	93.51 281	82.89 248	83.70 293	91.34 284	75.75 182	97.07 257	75.49 314	93.49 176	92.39 341

WR-MVS_H		87.80 202	87.37 193	89.10 273	93.23 252	78.12 275	95.61 102	97.30 30	87.90 120	83.72 292	92.01 265	79.65 138	96.01 319	76.36 307	80.54 354	93.16 315

miper_enhance_ethall		86.90 244	86.18 235	89.06 274	91.66 305	77.58 292	90.22 332	94.82 235	79.16 316	84.48 269	89.10 347	79.19 142	96.66 278	84.06 195	82.94 317	92.94 323

c3_l		87.14 237	86.50 224	89.04 275	92.20 282	77.26 295	91.22 310	94.70 242	82.01 266	84.34 277	90.43 318	78.81 145	96.61 283	83.70 202	81.09 343	93.25 309

miper_ehance_all_eth		87.22 232	86.62 218	89.02 276	92.13 285	77.40 294	90.91 316	94.81 236	81.28 289	84.32 278	90.08 329	79.26 140	96.62 280	83.81 200	82.94 317	93.04 320

gg-mvs-nofinetune		81.77 329	79.37 344	88.99 277	90.85 339	77.73 289	86.29 389	79.63 417	74.88 368	83.19 306	69.05 420	60.34 353	96.11 314	75.46 315	94.64 154	93.11 317

ETVMVS		84.43 304	82.92 313	88.97 278	94.37 204	74.67 328	91.23 309	88.35 386	83.37 235	86.06 222	89.04 348	55.38 381	95.67 337	67.12 373	91.34 209	96.58 160

pmmvs6		83.42 317	81.60 321	88.87 279	88.01 386	77.87 282	94.96 139	94.24 258	74.67 369	78.80 359	91.09 297	60.17 355	96.49 293	77.06 302	75.40 386	92.23 346

test_cas_vis1_n_1920		88.83 177	88.85 158	88.78 280	91.15 324	76.72 303	93.85 217	94.93 226	83.23 240	92.81 87	96.00 106	61.17 349	94.45 357	91.67 101	94.84 148	95.17 217

MIMVSNet		82.59 323	80.53 328	88.76 281	91.51 307	78.32 270	86.57 388	90.13 366	79.32 312	80.70 335	88.69 358	52.98 393	93.07 382	66.03 381	88.86 253	94.90 230

cl____		86.52 260	85.78 253	88.75 282	92.03 289	76.46 307	90.74 318	94.30 254	81.83 275	83.34 303	90.78 308	75.74 184	96.57 286	81.74 239	81.54 337	93.22 311

DIV-MVS_self_test		86.53 259	85.78 253	88.75 282	92.02 290	76.45 308	90.74 318	94.30 254	81.83 275	83.34 303	90.82 306	75.75 182	96.57 286	81.73 240	81.52 338	93.24 310

CP-MVSNet		87.63 210	87.26 198	88.74 284	93.12 255	76.59 306	95.29 116	96.58 99	88.43 101	83.49 300	92.98 228	75.28 188	95.83 328	78.97 280	81.15 342	93.79 283

eth_miper_zixun_eth		86.50 261	85.77 255	88.68 285	91.94 291	75.81 317	90.47 324	94.89 228	82.05 263	84.05 284	90.46 317	75.96 177	96.77 273	82.76 216	79.36 368	93.46 303

CHOSEN 280x420		85.15 290	83.99 296	88.65 286	92.47 275	78.40 268	79.68 419	92.76 299	74.90 367	81.41 327	89.59 340	69.85 264	95.51 342	79.92 269	95.29 140	92.03 349

PS-CasMVS		87.32 226	86.88 204	88.63 287	92.99 264	76.33 311	95.33 111	96.61 97	88.22 109	83.30 305	93.07 226	73.03 225	95.79 332	78.36 285	81.00 348	93.75 290

TransMVSNet (Re)		84.43 304	83.06 311	88.54 288	91.72 301	78.44 266	95.18 127	92.82 298	82.73 251	79.67 351	92.12 257	73.49 217	95.96 321	71.10 348	68.73 402	91.21 366

EG-PatchMatch MVS		82.37 325	80.34 331	88.46 289	90.27 354	79.35 247	92.80 264	94.33 253	77.14 345	73.26 394	90.18 325	47.47 405	96.72 274	70.25 352	87.32 280	89.30 389

PEN-MVS		86.80 247	86.27 233	88.40 290	92.32 280	75.71 319	95.18 127	96.38 114	87.97 117	82.82 309	93.15 222	73.39 221	95.92 323	76.15 311	79.03 371	93.59 296

Baseline_NR-MVSNet		87.07 239	86.63 217	88.40 290	91.44 309	77.87 282	94.23 190	92.57 304	84.12 215	85.74 229	92.08 261	77.25 163	96.04 315	82.29 224	79.94 361	91.30 364

UBG		85.51 280	84.57 286	88.35 292	94.21 213	71.78 365	90.07 337	89.66 378	82.28 259	85.91 225	89.01 349	61.30 343	97.06 258	76.58 306	92.06 204	96.22 173

D2MVS		85.90 272	85.09 273	88.35 292	90.79 340	77.42 293	91.83 292	95.70 175	80.77 297	80.08 345	90.02 331	66.74 302	96.37 302	81.88 235	87.97 268	91.26 365

pmmvs5		84.21 306	82.84 316	88.34 294	88.95 373	76.94 299	92.41 272	91.91 326	75.63 358	80.28 340	91.18 292	64.59 319	95.57 339	77.09 301	83.47 311	92.53 335

mamv4		90.92 114	91.78 96	88.33 295	95.67 128	70.75 378	92.92 259	96.02 149	81.90 270	88.11 171	95.34 135	85.88 51	96.97 264	95.22 34	95.01 145	97.26 118

LCM-MVSNet-Re		88.30 190	88.32 172	88.27 296	94.71 181	72.41 360	93.15 248	90.98 349	87.77 127	79.25 355	91.96 266	78.35 153	95.75 333	83.04 208	95.62 129	96.65 157

CostFormer		85.77 277	84.94 277	88.26 297	91.16 323	72.58 358	89.47 350	91.04 348	76.26 353	86.45 211	89.97 333	70.74 249	96.86 272	82.35 222	87.07 283	95.34 213

ITE_SJBPF				88.24 298	91.88 295	77.05 298		92.92 293	85.54 182	80.13 344	93.30 216	57.29 373	96.20 310	72.46 339	84.71 297	91.49 360

PVSNet	78.82 18	85.55 279	84.65 283	88.23 299	94.72 180	71.93 361	87.12 384	92.75 300	78.80 324	84.95 259	90.53 315	64.43 320	96.71 276	74.74 324	93.86 168	96.06 185

IterMVS-SCA-FT		85.45 281	84.53 287	88.18 300	91.71 302	76.87 300	90.19 334	92.65 303	85.40 185	81.44 326	90.54 314	66.79 300	95.00 354	81.04 249	81.05 344	92.66 332

EPNet_dtu		86.49 263	85.94 248	88.14 301	90.24 355	72.82 350	94.11 196	92.20 314	86.66 155	79.42 354	92.36 248	73.52 216	95.81 330	71.26 343	93.66 170	95.80 196
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmtry		82.71 321	80.93 327	88.06 302	90.05 359	76.37 310	84.74 402	91.96 324	72.28 392	81.32 329	87.87 370	71.03 244	95.50 344	68.97 361	80.15 359	92.32 344

test_vis1_n_1920		89.39 160	89.84 132	88.04 303	92.97 265	72.64 355	94.71 157	96.03 148	86.18 166	91.94 113	96.56 88	61.63 338	95.74 334	93.42 54	95.11 144	95.74 198

DTE-MVSNet		86.11 269	85.48 262	87.98 304	91.65 306	74.92 326	94.93 141	95.75 170	87.36 137	82.26 315	93.04 227	72.85 226	95.82 329	74.04 329	77.46 377	93.20 313

PMMVS		85.71 278	84.96 276	87.95 305	88.90 374	77.09 297	88.68 362	90.06 368	72.32 391	86.47 208	90.76 309	72.15 234	94.40 359	81.78 238	93.49 176	92.36 342

GG-mvs-BLEND				87.94 306	89.73 366	77.91 279	87.80 373	78.23 422		80.58 337	83.86 397	59.88 357	95.33 348	71.20 344	92.22 202	90.60 378

MonoMVSNet		86.89 245	86.55 221	87.92 307	89.46 369	73.75 338	94.12 194	93.10 288	87.82 126	85.10 255	90.76 309	69.59 267	94.94 355	86.47 166	82.50 323	95.07 220

reproduce_monomvs		86.37 266	85.87 250	87.87 308	93.66 241	73.71 339	93.44 233	95.02 218	88.61 96	82.64 312	91.94 267	57.88 371	96.68 277	89.96 123	79.71 365	93.22 311

pmmvs-eth3d		80.97 343	78.72 355	87.74 309	84.99 404	79.97 234	90.11 336	91.65 331	75.36 360	73.51 392	86.03 387	59.45 360	93.96 369	75.17 318	72.21 391	89.29 391

MS-PatchMatch		85.05 292	84.16 291	87.73 310	91.42 312	78.51 264	91.25 308	93.53 280	77.50 340	80.15 342	91.58 281	61.99 335	95.51 342	75.69 313	94.35 162	89.16 393

mmtdpeth		85.04 294	84.15 292	87.72 311	93.11 256	75.74 318	94.37 182	92.83 296	84.98 195	89.31 155	86.41 384	61.61 340	97.14 252	92.63 70	62.11 412	90.29 380

test_0402		81.30 339	79.17 349	87.67 312	93.19 253	78.17 274	92.98 256	91.71 327	75.25 362	76.02 379	90.31 320	59.23 362	96.37 302	50.22 415	83.63 309	88.47 400

IterMVS		84.88 296	83.98 297	87.60 313	91.44 309	76.03 313	90.18 335	92.41 306	83.24 239	81.06 332	90.42 319	66.60 303	94.28 363	79.46 273	80.98 349	92.48 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmatch-test		81.37 337	79.30 345	87.58 314	90.92 335	74.16 336	80.99 414	87.68 391	70.52 399	76.63 374	88.81 353	71.21 241	92.76 384	60.01 402	86.93 284	95.83 194

EPMVS		83.90 313	82.70 317	87.51 315	90.23 356	72.67 353	88.62 363	81.96 412	81.37 287	85.01 258	88.34 361	66.31 307	94.45 357	75.30 317	87.12 281	95.43 208

ADS-MVSNet2		81.66 332	79.71 341	87.50 316	91.35 315	74.19 335	83.33 407	88.48 385	72.90 386	82.24 316	85.77 390	64.98 317	93.20 380	64.57 388	83.74 306	95.12 218

OurMVSNet-221017-0		85.35 285	84.64 284	87.49 317	90.77 341	72.59 357	94.01 207	94.40 250	84.72 205	79.62 353	93.17 221	61.91 336	96.72 274	81.99 232	81.16 340	93.16 315

tpm2		84.08 308	82.94 312	87.48 318	91.39 313	71.27 370	89.23 354	90.37 361	71.95 393	84.64 264	89.33 344	67.30 292	96.55 290	75.17 318	87.09 282	94.63 238

RPSCF		85.07 291	84.27 288	87.48 318	92.91 267	70.62 380	91.69 297	92.46 305	76.20 354	82.67 311	95.22 140	63.94 323	97.29 239	77.51 296	85.80 289	94.53 245

myMVS_eth3d28		85.80 276	85.26 270	87.42 320	94.73 178	69.92 385	90.60 322	90.95 351	87.21 139	86.06 222	90.04 330	59.47 359	96.02 317	74.89 323	93.35 183	96.33 167

WBMVS		84.97 295	84.18 290	87.34 321	94.14 218	71.62 369	90.20 333	92.35 307	81.61 282	84.06 283	90.76 309	61.82 337	96.52 291	78.93 281	83.81 304	93.89 274

miper_lstm_enhance		85.27 288	84.59 285	87.31 322	91.28 318	74.63 329	87.69 378	94.09 265	81.20 293	81.36 328	89.85 336	74.97 193	94.30 362	81.03 251	79.84 364	93.01 321

FMVSNet5		81.52 335	79.60 342	87.27 323	91.17 321	77.95 278	91.49 301	92.26 313	76.87 346	76.16 376	87.91 369	51.67 395	92.34 387	67.74 370	81.16 340	91.52 359

USDC		82.76 320	81.26 325	87.26 324	91.17 321	74.55 330	89.27 352	93.39 283	78.26 335	75.30 383	92.08 261	54.43 388	96.63 279	71.64 341	85.79 290	90.61 376

test-LLR		85.87 273	85.41 263	87.25 325	90.95 331	71.67 367	89.55 346	89.88 374	83.41 233	84.54 267	87.95 367	67.25 293	95.11 351	81.82 236	93.37 181	94.97 223

test-mter		84.54 303	83.64 301	87.25 325	90.95 331	71.67 367	89.55 346	89.88 374	79.17 315	84.54 267	87.95 367	55.56 379	95.11 351	81.82 236	93.37 181	94.97 223

JIA-IIPM		81.04 340	78.98 353	87.25 325	88.64 375	73.48 343	81.75 413	89.61 380	73.19 383	82.05 319	73.71 416	66.07 312	95.87 326	71.18 346	84.60 298	92.41 340

TDRefinement		79.81 353	77.34 359	87.22 328	79.24 419	75.48 321	93.12 249	92.03 319	76.45 349	75.01 384	91.58 281	49.19 401	96.44 298	70.22 354	69.18 399	89.75 385

tpmvs		83.35 319	82.07 318	87.20 329	91.07 327	71.00 376	88.31 367	91.70 328	78.91 318	80.49 339	87.18 379	69.30 274	97.08 255	68.12 369	83.56 310	93.51 301

ppachtmachnet_test		81.84 328	80.07 336	87.15 330	88.46 379	74.43 333	89.04 358	92.16 315	75.33 361	77.75 366	88.99 350	66.20 309	95.37 347	65.12 385	77.60 375	91.65 355

dmvs_re		84.20 307	83.22 308	87.14 331	91.83 298	77.81 284	90.04 338	90.19 364	84.70 206	81.49 324	89.17 346	64.37 321	91.13 398	71.58 342	85.65 291	92.46 338

tpm cat1		81.96 326	80.27 332	87.01 332	91.09 326	71.02 375	87.38 382	91.53 336	66.25 407	80.17 341	86.35 386	68.22 289	96.15 313	69.16 360	82.29 326	93.86 280

test_fmvs1_n		87.03 241	87.04 202	86.97 333	89.74 365	71.86 362	94.55 165	94.43 248	78.47 329	91.95 112	95.50 130	51.16 397	93.81 370	93.02 62	94.56 156	95.26 214

OpenMVS_ROB	74.94 19	79.51 356	77.03 364	86.93 334	87.00 392	76.23 312	92.33 278	90.74 357	68.93 403	74.52 388	88.23 364	49.58 400	96.62 280	57.64 407	84.29 300	87.94 403

SixPastTwentyTwo		83.91 312	82.90 314	86.92 335	90.99 329	70.67 379	93.48 230	91.99 321	85.54 182	77.62 368	92.11 259	60.59 352	96.87 271	76.05 312	77.75 374	93.20 313

ADS-MVSNet		81.56 334	79.78 338	86.90 336	91.35 315	71.82 363	83.33 407	89.16 383	72.90 386	82.24 316	85.77 390	64.98 317	93.76 371	64.57 388	83.74 306	95.12 218

PatchT		82.68 322	81.27 324	86.89 337	90.09 358	70.94 377	84.06 404	90.15 365	74.91 366	85.63 232	83.57 399	69.37 270	94.87 356	65.19 383	88.50 258	94.84 232

tpm		84.73 299	84.02 295	86.87 338	90.33 353	68.90 388	89.06 357	89.94 371	80.85 296	85.75 228	89.86 335	68.54 286	95.97 320	77.76 292	84.05 303	95.75 197

Patchmatch-RL test		81.67 331	79.96 337	86.81 339	85.42 402	71.23 371	82.17 412	87.50 392	78.47 329	77.19 370	82.50 406	70.81 248	93.48 375	82.66 217	72.89 390	95.71 201

test_vis1_n		86.56 258	86.49 225	86.78 340	88.51 376	72.69 352	94.68 158	93.78 277	79.55 311	90.70 133	95.31 136	48.75 402	93.28 378	93.15 58	93.99 165	94.38 256

testing3-2		86.72 252	86.71 211	86.74 341	96.11 105	65.92 399	93.39 235	89.65 379	89.46 63	87.84 180	92.79 236	59.17 364	97.60 204	81.31 245	90.72 220	96.70 155

test_fmvs1		87.34 224	87.56 188	86.68 342	90.59 347	71.80 364	94.01 207	94.04 266	78.30 333	91.97 110	95.22 140	56.28 377	93.71 372	92.89 63	94.71 150	94.52 246

MDA-MVSNet-bldmvs		78.85 361	76.31 366	86.46 343	89.76 364	73.88 337	88.79 360	90.42 360	79.16 316	59.18 416	88.33 362	60.20 354	94.04 365	62.00 395	68.96 400	91.48 361

mvs5depth		80.98 342	79.15 350	86.45 344	84.57 405	73.29 345	87.79 374	91.67 330	80.52 299	82.20 318	89.72 338	55.14 384	95.93 322	73.93 332	66.83 404	90.12 382

tpmrst		85.35 285	84.99 274	86.43 345	90.88 338	67.88 393	88.71 361	91.43 339	80.13 303	86.08 221	88.80 355	73.05 224	96.02 317	82.48 218	83.40 314	95.40 209

TESTMET0.1,1		83.74 315	82.85 315	86.42 346	89.96 361	71.21 372	89.55 346	87.88 388	77.41 341	83.37 302	87.31 375	56.71 375	93.65 374	80.62 259	92.85 193	94.40 255

our_test_3		81.93 327	80.46 330	86.33 347	88.46 379	73.48 343	88.46 365	91.11 344	76.46 348	76.69 373	88.25 363	66.89 298	94.36 360	68.75 362	79.08 370	91.14 368

lessismore_v0				86.04 348	88.46 379	68.78 389		80.59 415		73.01 395	90.11 328	55.39 380	96.43 299	75.06 320	65.06 407	92.90 324

TinyColmap		79.76 354	77.69 358	85.97 349	91.71 302	73.12 346	89.55 346	90.36 362	75.03 364	72.03 398	90.19 324	46.22 409	96.19 312	63.11 392	81.03 345	88.59 399

KD-MVS_2432*1600		78.50 362	76.02 369	85.93 350	86.22 395	74.47 331	84.80 400	92.33 308	79.29 313	76.98 371	85.92 388	53.81 391	93.97 367	67.39 371	57.42 417	89.36 387

miper_refine_blended		78.50 362	76.02 369	85.93 350	86.22 395	74.47 331	84.80 400	92.33 308	79.29 313	76.98 371	85.92 388	53.81 391	93.97 367	67.39 371	57.42 417	89.36 387

K. test v3		81.59 333	80.15 335	85.91 352	89.89 363	69.42 387	92.57 269	87.71 390	85.56 181	73.44 393	89.71 339	55.58 378	95.52 341	77.17 299	69.76 396	92.78 329

SSC-MVS3.2		84.60 302	84.19 289	85.85 353	92.74 270	68.07 390	88.15 369	93.81 275	87.42 136	83.76 291	91.07 298	62.91 330	95.73 335	74.56 327	83.24 315	93.75 290

mvsany_test1		85.42 283	85.30 268	85.77 354	87.95 388	75.41 322	87.61 381	80.97 414	76.82 347	88.68 164	95.83 116	77.44 162	90.82 400	85.90 173	86.51 285	91.08 372

MIMVSNet1		79.38 357	77.28 360	85.69 355	86.35 394	73.67 340	91.61 299	92.75 300	78.11 338	72.64 396	88.12 365	48.16 403	91.97 392	60.32 399	77.49 376	91.43 362

UWE-MVS		83.69 316	83.09 309	85.48 356	93.06 259	65.27 404	90.92 315	86.14 396	79.90 306	86.26 217	90.72 312	57.17 374	95.81 330	71.03 349	92.62 196	95.35 212

UnsupCasMVSNet_eth		80.07 350	78.27 357	85.46 357	85.24 403	72.63 356	88.45 366	94.87 231	82.99 245	71.64 400	88.07 366	56.34 376	91.75 393	73.48 335	63.36 410	92.01 350

CL-MVSNet_self_test		81.74 330	80.53 328	85.36 358	85.96 397	72.45 359	90.25 328	93.07 290	81.24 291	79.85 350	87.29 376	70.93 246	92.52 385	66.95 374	69.23 398	91.11 370

MDA-MVSNet_test_wron		79.21 359	77.19 362	85.29 359	88.22 383	72.77 351	85.87 391	90.06 368	74.34 371	62.62 413	87.56 373	66.14 310	91.99 391	66.90 378	73.01 388	91.10 371

YYNet1		79.22 358	77.20 361	85.28 360	88.20 384	72.66 354	85.87 391	90.05 370	74.33 372	62.70 411	87.61 372	66.09 311	92.03 389	66.94 375	72.97 389	91.15 367

WB-MVSnew		83.77 314	83.28 305	85.26 361	91.48 308	71.03 374	91.89 289	87.98 387	78.91 318	84.78 261	90.22 322	69.11 279	94.02 366	64.70 387	90.44 223	90.71 374

dp		81.47 336	80.23 333	85.17 362	89.92 362	65.49 402	86.74 386	90.10 367	76.30 352	81.10 330	87.12 380	62.81 331	95.92 323	68.13 368	79.88 362	94.09 267

UnsupCasMVSNet_bld		76.23 371	73.27 375	85.09 363	83.79 407	72.92 348	85.65 394	93.47 282	71.52 394	68.84 406	79.08 411	49.77 399	93.21 379	66.81 379	60.52 414	89.13 395

Anonymous20231206		81.03 341	79.77 340	84.82 364	87.85 389	70.26 382	91.42 302	92.08 317	73.67 378	77.75 366	89.25 345	62.43 333	93.08 381	61.50 397	82.00 331	91.12 369

test0.0.03 1		82.41 324	81.69 320	84.59 365	88.23 382	72.89 349	90.24 330	87.83 389	83.41 233	79.86 349	89.78 337	67.25 293	88.99 410	65.18 384	83.42 313	91.90 352

CMPMVS	59.16 21	80.52 345	79.20 348	84.48 366	83.98 406	67.63 396	89.95 341	93.84 274	64.79 410	66.81 408	91.14 295	57.93 370	95.17 349	76.25 309	88.10 264	90.65 375
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		84.69 301	84.79 281	84.37 367	91.84 296	64.92 405	93.70 224	91.47 338	66.19 408	86.16 220	95.28 137	67.18 295	93.33 377	80.89 254	90.42 225	94.88 231

PVSNet_0	73.20 20	77.22 367	74.83 373	84.37 367	90.70 345	71.10 373	83.09 409	89.67 377	72.81 388	73.93 391	83.13 401	60.79 351	93.70 373	68.54 363	50.84 422	88.30 401

LF4IMVS		80.37 348	79.07 352	84.27 369	86.64 393	69.87 386	89.39 351	91.05 347	76.38 350	74.97 385	90.00 332	47.85 404	94.25 364	74.55 328	80.82 351	88.69 398

Anonymous20240521		80.44 347	79.21 347	84.11 370	85.75 400	67.89 392	92.86 262	93.23 286	75.61 359	75.59 382	87.47 374	50.03 398	94.33 361	71.14 347	81.21 339	90.12 382

PM-MVS		78.11 364	76.12 368	84.09 371	83.54 408	70.08 383	88.97 359	85.27 403	79.93 305	74.73 387	86.43 383	34.70 420	93.48 375	79.43 276	72.06 392	88.72 397

test_fmvs2		83.98 309	84.03 294	83.83 372	87.16 391	67.53 397	93.93 213	92.89 294	77.62 339	86.89 201	93.53 209	47.18 406	92.02 390	90.54 117	86.51 285	91.93 351

testgi		80.94 344	80.20 334	83.18 373	87.96 387	66.29 398	91.28 306	90.70 358	83.70 224	78.12 362	92.84 231	51.37 396	90.82 400	63.34 391	82.46 324	92.43 339

KD-MVS_self_test		80.20 349	79.24 346	83.07 374	85.64 401	65.29 403	91.01 314	93.93 268	78.71 327	76.32 375	86.40 385	59.20 363	92.93 383	72.59 338	69.35 397	91.00 373

testing3		80.46 346	79.59 343	83.06 375	93.44 248	64.64 406	93.33 237	85.47 401	84.34 212	79.93 348	90.84 305	44.35 412	92.39 386	57.06 409	87.56 274	92.16 348

ambc				83.06 375	79.99 417	63.51 410	77.47 420	92.86 295		74.34 390	84.45 396	28.74 421	95.06 353	73.06 337	68.89 401	90.61 376

test20.03		79.95 352	79.08 351	82.55 377	85.79 399	67.74 395	91.09 312	91.08 345	81.23 292	74.48 389	89.96 334	61.63 338	90.15 402	60.08 400	76.38 382	89.76 384

MVStest1		72.91 375	69.70 380	82.54 378	78.14 420	73.05 347	88.21 368	86.21 395	60.69 414	64.70 409	90.53 315	46.44 408	85.70 417	58.78 405	53.62 419	88.87 396

test_vis1_rt		77.96 365	76.46 365	82.48 379	85.89 398	71.74 366	90.25 328	78.89 418	71.03 398	71.30 401	81.35 408	42.49 414	91.05 399	84.55 190	82.37 325	84.65 406

EU-MVSNet		81.32 338	80.95 326	82.42 380	88.50 378	63.67 409	93.32 238	91.33 340	64.02 411	80.57 338	92.83 232	61.21 347	92.27 388	76.34 308	80.38 358	91.32 363

myMVS_eth3d		79.67 355	78.79 354	82.32 381	91.92 292	64.08 407	89.75 344	87.40 393	81.72 277	78.82 357	87.20 377	45.33 410	91.29 396	59.09 404	87.84 271	91.60 357

ttmdpeth		76.55 369	74.64 374	82.29 382	82.25 413	67.81 394	89.76 343	85.69 399	70.35 400	75.76 380	91.69 274	46.88 407	89.77 404	66.16 380	63.23 411	89.30 389

pmmvs3		71.81 378	68.71 381	81.11 383	75.86 422	70.42 381	86.74 386	83.66 407	58.95 417	68.64 407	80.89 409	36.93 418	89.52 406	63.10 393	63.59 409	83.39 407

Syy-MVS		80.07 350	79.78 338	80.94 384	91.92 292	59.93 416	89.75 344	87.40 393	81.72 277	78.82 357	87.20 377	66.29 308	91.29 396	47.06 417	87.84 271	91.60 357

UWE-MVS-28		78.98 360	78.38 356	80.80 385	88.18 385	60.66 415	90.65 320	78.51 419	78.84 322	77.93 365	90.93 302	59.08 365	89.02 409	50.96 414	90.33 227	92.72 330

new-patchmatchnet		76.41 370	75.17 372	80.13 386	82.65 412	59.61 417	87.66 379	91.08 345	78.23 336	69.85 404	83.22 400	54.76 385	91.63 395	64.14 390	64.89 408	89.16 393

mvsany_test3		74.95 372	73.26 376	80.02 387	74.61 423	63.16 411	85.53 395	78.42 420	74.16 373	74.89 386	86.46 382	36.02 419	89.09 408	82.39 221	66.91 403	87.82 404

test_fmvs3		77.67 366	77.16 363	79.22 388	79.52 418	61.14 413	92.34 277	91.64 332	73.98 375	78.86 356	86.59 381	27.38 424	87.03 412	88.12 144	75.97 384	89.50 386

DSMNet-mixed		76.94 368	76.29 367	78.89 389	83.10 410	56.11 425	87.78 375	79.77 416	60.65 415	75.64 381	88.71 356	61.56 341	88.34 411	60.07 401	89.29 247	92.21 347

EGC-MVSNET		61.97 386	56.37 391	78.77 390	89.63 367	73.50 342	89.12 356	82.79 409	0.21 436	1.24 437	84.80 394	39.48 415	90.04 403	44.13 419	75.94 385	72.79 418

new_pmnet		72.15 376	70.13 379	78.20 391	82.95 411	65.68 400	83.91 405	82.40 411	62.94 413	64.47 410	79.82 410	42.85 413	86.26 416	57.41 408	74.44 387	82.65 411

MVS-HIRNet		73.70 374	72.20 377	78.18 392	91.81 299	56.42 424	82.94 410	82.58 410	55.24 418	68.88 405	66.48 421	55.32 382	95.13 350	58.12 406	88.42 260	83.01 409

LCM-MVSNet		66.00 383	62.16 388	77.51 393	64.51 433	58.29 419	83.87 406	90.90 353	48.17 422	54.69 419	73.31 417	16.83 433	86.75 413	65.47 382	61.67 413	87.48 405

APD_test1		69.04 379	66.26 385	77.36 394	80.51 416	62.79 412	85.46 396	83.51 408	54.11 420	59.14 417	84.79 395	23.40 427	89.61 405	55.22 410	70.24 395	79.68 415

test_f		71.95 377	70.87 378	75.21 395	74.21 425	59.37 418	85.07 399	85.82 398	65.25 409	70.42 403	83.13 401	23.62 425	82.93 423	78.32 286	71.94 393	83.33 408

ANet_high		58.88 390	54.22 395	72.86 396	56.50 436	56.67 421	80.75 415	86.00 397	73.09 385	37.39 428	64.63 424	22.17 428	79.49 426	43.51 420	23.96 430	82.43 412

test_vis3_rt		65.12 384	62.60 386	72.69 397	71.44 426	60.71 414	87.17 383	65.55 430	63.80 412	53.22 420	65.65 423	14.54 434	89.44 407	76.65 303	65.38 406	67.91 421

FPMVS		64.63 385	62.55 387	70.88 398	70.80 427	56.71 420	84.42 403	84.42 405	51.78 421	49.57 421	81.61 407	23.49 426	81.48 424	40.61 424	76.25 383	74.46 417

dmvs_testset		74.57 373	75.81 371	70.86 399	87.72 390	40.47 434	87.05 385	77.90 424	82.75 250	71.15 402	85.47 392	67.98 290	84.12 421	45.26 418	76.98 381	88.00 402

N_pmnet		68.89 380	68.44 382	70.23 400	89.07 372	28.79 439	88.06 370	19.50 439	69.47 402	71.86 399	84.93 393	61.24 346	91.75 393	54.70 411	77.15 378	90.15 381

testf1		59.54 388	56.11 392	69.85 401	69.28 428	56.61 422	80.37 416	76.55 427	42.58 425	45.68 424	75.61 412	11.26 435	84.18 419	43.20 421	60.44 415	68.75 419

APD_test2		59.54 388	56.11 392	69.85 401	69.28 428	56.61 422	80.37 416	76.55 427	42.58 425	45.68 424	75.61 412	11.26 435	84.18 419	43.20 421	60.44 415	68.75 419

WB-MVS		67.92 381	67.49 383	69.21 403	81.09 414	41.17 433	88.03 371	78.00 423	73.50 380	62.63 412	83.11 403	63.94 323	86.52 414	25.66 429	51.45 421	79.94 414

PMMVS2		59.60 387	56.40 390	69.21 403	68.83 430	46.58 429	73.02 424	77.48 425	55.07 419	49.21 422	72.95 418	17.43 432	80.04 425	49.32 416	44.33 425	80.99 413

SSC-MVS		67.06 382	66.56 384	68.56 405	80.54 415	40.06 435	87.77 376	77.37 426	72.38 390	61.75 414	82.66 405	63.37 326	86.45 415	24.48 430	48.69 424	79.16 416

Gipuma		57.99 392	54.91 394	67.24 406	88.51 376	65.59 401	52.21 427	90.33 363	43.58 424	42.84 427	51.18 428	20.29 430	85.07 418	34.77 425	70.45 394	51.05 427
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	47.18 22	52.22 394	48.46 398	63.48 407	45.72 438	46.20 430	73.41 423	78.31 421	41.03 427	30.06 430	65.68 422	6.05 437	83.43 422	30.04 427	65.86 405	60.80 422
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		58.82 391	58.24 389	60.56 408	83.13 409	45.09 432	82.32 411	48.22 438	67.61 405	61.70 415	69.15 419	38.75 416	76.05 427	32.01 426	41.31 426	60.55 423

MVE	39.65 23	43.39 396	38.59 402	57.77 409	56.52 435	48.77 428	55.38 426	58.64 434	29.33 430	28.96 431	52.65 427	4.68 438	64.62 431	28.11 428	33.07 428	59.93 424
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.52 395	48.47 397	56.66 410	52.26 437	18.98 441	41.51 429	81.40 413	10.10 431	44.59 426	75.01 415	28.51 422	68.16 428	53.54 412	49.31 423	82.83 410

DeepMVS_CX				56.31 411	74.23 424	51.81 427		56.67 435	44.85 423	48.54 423	75.16 414	27.87 423	58.74 433	40.92 423	52.22 420	58.39 425

kuosan		53.51 393	53.30 396	54.13 412	76.06 421	45.36 431	80.11 418	48.36 437	59.63 416	54.84 418	63.43 425	37.41 417	62.07 432	20.73 432	39.10 427	54.96 426

E-PMN		43.23 397	42.29 399	46.03 413	65.58 432	37.41 436	73.51 422	64.62 431	33.99 428	28.47 432	47.87 429	19.90 431	67.91 429	22.23 431	24.45 429	32.77 428

EMVS		42.07 398	41.12 400	44.92 414	63.45 434	35.56 438	73.65 421	63.48 432	33.05 429	26.88 433	45.45 430	21.27 429	67.14 430	19.80 433	23.02 431	32.06 429

tmp_tt		35.64 399	39.24 401	24.84 415	14.87 439	23.90 440	62.71 425	51.51 436	6.58 433	36.66 429	62.08 426	44.37 411	30.34 435	52.40 413	22.00 432	20.27 430

wuyk23d		21.27 401	20.48 404	23.63 416	68.59 431	36.41 437	49.57 428	6.85 440	9.37 432	7.89 434	4.46 436	4.03 439	31.37 434	17.47 434	16.07 433	3.12 431

test123		8.76 403	11.22 406	1.39 417	0.85 441	0.97 442	85.76 393	0.35 442	0.54 435	2.45 436	8.14 435	0.60 440	0.48 436	2.16 436	0.17 435	2.71 432

testmvs		8.92 402	11.52 405	1.12 418	1.06 440	0.46 443	86.02 390	0.65 441	0.62 434	2.74 435	9.52 434	0.31 441	0.45 437	2.38 435	0.39 434	2.46 433

mmdepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

monomultidepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

test_blank		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet_test		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

DCPMVS		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

cdsmvs_eth3d_5k		22.14 400	29.52 403	0.00 419	0.00 442	0.00 444	0.00 430	95.76 169	0.00 437	0.00 438	94.29 179	75.66 185	0.00 438	0.00 437	0.00 436	0.00 434

pcd_1.5k_mvsjas		6.64 405	8.86 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	79.70 134	0.00 438	0.00 437	0.00 436	0.00 434

sosnet-low-res		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uncertanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

Regformer		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

ab-mvs-re		7.82 404	10.43 407	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	93.88 199	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

WAC-MVS						64.08 407								59.14 403

FOURS1					98.86 1	85.54 67	98.29 1	97.49 6	89.79 54	96.29 24

PC_three_1452									82.47 254	97.09 13	97.07 61	92.72 1	98.04 176	92.70 69	99.02 12	98.86 11

test_one_0601					98.58 11	85.83 61		97.44 15	91.05 15	96.78 20	98.06 16	91.45 11

eth-test2					0.00 442

eth-test					0.00 442

ZD-MVS					98.15 34	86.62 33		97.07 51	83.63 226	94.19 54	96.91 67	87.57 31	99.26 45	91.99 91	98.44 53

RE-MVS-def			93.68 62		97.92 43	84.57 87	96.28 43	96.76 82	87.46 133	93.75 64	97.43 40	82.94 93		92.73 65	97.80 80	97.88 87

IU-MVS					98.77 5	86.00 50		96.84 72	81.26 290	97.26 9				95.50 30	99.13 3	99.03 8

test_241102_TWO								97.44 15	90.31 32	97.62 5	98.07 14	91.46 10	99.58 10	95.66 24	99.12 6	98.98 10

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

9.14			94.47 26		97.79 52		96.08 61	97.44 15	86.13 170	95.10 44	97.40 42	88.34 22	99.22 47	93.25 57	98.70 34

save fliter					97.85 49	85.63 66	95.21 124	96.82 75	89.44 64

test_0728_THIRD									90.75 21	97.04 15	98.05 18	92.09 6	99.55 16	95.64 26	99.13 3	99.13 2

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

GSMVS																96.12 179

test_part2					98.55 12	87.22 19				96.40 23

sam_mvs1												71.70 237				96.12 179

sam_mvs												70.60 250

MTGPA								96.97 56

test_post1							88.00 372				9.81 433	69.31 273	95.53 340	76.65 303

test_post											10.29 432	70.57 254	95.91 325

patchmatchnet-post											83.76 398	71.53 238	96.48 294

MTMP							96.16 52	60.64 433

gm-plane-assit					89.60 368	68.00 391			77.28 344		88.99 350		97.57 206	79.44 275

test9_res														91.91 95	98.71 32	98.07 74

TEST9					97.53 61	86.49 37	94.07 201	96.78 79	81.61 282	92.77 89	96.20 97	87.71 28	99.12 54

test_8					97.49 63	86.30 45	94.02 206	96.76 82	81.86 273	92.70 93	96.20 97	87.63 29	99.02 64

agg_prior2														90.54 117	98.68 37	98.27 57

agg_prior					97.38 66	85.92 57		96.72 89		92.16 105			98.97 78

test_prior4						85.96 54	94.11 196

test_prior2							94.12 194		87.67 131	92.63 95	96.39 92	86.62 40		91.50 103	98.67 40

旧先验2							93.36 236		71.25 396	94.37 50			97.13 253	86.74 162

新几何2							93.11 251

旧先验1					96.79 79	81.81 174		95.67 177			96.81 73	86.69 39			97.66 86	96.97 141

无先验							93.28 244	96.26 124	73.95 376				99.05 58	80.56 260		96.59 159

原ACMM2							92.94 258

test222					96.55 88	81.70 176	92.22 282	95.01 219	68.36 404	90.20 141	96.14 102	80.26 127			97.80 80	96.05 186

testdata2													98.75 104	78.30 287

segment_acmp												87.16 36

testdata1							92.15 284		87.94 118

plane_prior7					94.70 182	82.74 151

plane_prior6					94.52 194	82.75 149						74.23 203

plane_prior5								96.22 129					98.12 161	88.15 141	89.99 230	94.63 238

plane_prior4											94.86 156

plane_prior3						82.75 149			90.26 38	86.91 198

plane_prior2							95.85 83		90.81 19

plane_prior1					94.59 188

plane_prior						82.73 152	95.21 124		89.66 59						89.88 235

n2								0.00 443

nn								0.00 443

door-mid								85.49 400

test11								96.57 100

door								85.33 402

HQP5-MVS						81.56 178

HQP-NCC					94.17 214		94.39 178		88.81 86	85.43 244

ACMP_Plane					94.17 214		94.39 178		88.81 86	85.43 244

BP-MVS														87.11 159

HQP4-MVS										85.43 244			97.96 182			94.51 248

HQP3-MVS								96.04 146							89.77 239

HQP2-MVS												73.83 213

NP-MVS					94.37 204	82.42 161					93.98 192

MDTV_nov1_ep13_2view						55.91 426	87.62 380		73.32 382	84.59 266		70.33 257		74.65 325		95.50 206

MDTV_nov1_ep13			83.56 302		91.69 304	69.93 384	87.75 377	91.54 335	78.60 328	84.86 260	88.90 352	69.54 268	96.03 316	70.25 352	88.93 252

ACMMP++_ref															87.47 275

ACMMP++															88.01 267

Test By Simon												80.02 129

High-resolution multi-view benchmark