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 72					99.61 4	96.03 23	99.06 9	99.07 5

No_MVS				96.52 1	97.78 54	90.86 1		96.85 72					99.61 4	96.03 23	99.06 9	99.07 5

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 61	92.59 2	98.94 84	92.25 82	98.99 14	98.84 14

HPM-MVS++		95.14 10	94.91 19	95.83 4	98.25 29	89.65 4	95.92 78	96.96 61	91.75 11	94.02 62	96.83 73	88.12 24	99.55 16	93.41 57	98.94 16	98.28 55

MM		95.10 11	94.91 19	95.68 5	96.09 107	88.34 9	96.68 33	94.37 253	95.08 1	94.68 48	97.72 34	82.94 93	99.64 1	97.85 3	98.76 29	99.06 7

SMA-MVS		95.20 8	95.07 13	95.59 6	98.14 35	88.48 8	96.26 46	97.28 34	85.90 174	97.67 3	98.10 11	88.41 20	99.56 12	94.66 41	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 93	91.37 103	95.55 7	95.63 132	88.73 6	97.07 18	96.77 83	90.84 19	84.02 287	96.62 86	75.95 180	99.34 37	87.77 149	97.68 87	98.59 24

CNVR-MVS		95.40 7	95.37 7	95.50 8	98.11 36	88.51 7	95.29 117	96.96 61	92.09 8	95.32 40	97.08 61	89.49 15	99.33 40	95.10 37	98.85 20	98.66 21

MVS_0304		94.18 42	93.80 56	95.34 9	94.91 170	87.62 14	95.97 73	93.01 294	92.58 5	94.22 53	97.20 55	80.56 125	99.59 8	97.04 16	98.68 37	98.81 17

ACMMP_NAP		94.74 20	94.56 25	95.28 10	98.02 41	87.70 11	95.68 95	97.34 25	88.28 108	95.30 41	97.67 36	85.90 50	99.54 20	93.91 49	98.95 15	98.60 23

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 25	87.28 18	95.56 107	97.51 6	89.13 79	97.14 12	97.91 27	91.64 7	99.62 2	94.61 42	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 21	95.20 12	97.84 50	87.76 10	96.65 34	97.48 11	87.76 130	95.71 35	97.70 35	88.28 23	99.35 36	93.89 50	98.78 26	98.48 30

MCST-MVS		94.45 27	94.20 43	95.19 13	98.46 19	87.50 16	95.00 138	97.12 49	87.13 143	92.51 101	96.30 95	89.24 17	99.34 37	93.46 54	98.62 46	98.73 18

NCCC		94.81 17	94.69 24	95.17 14	97.83 51	87.46 17	95.66 98	96.93 65	92.34 6	93.94 63	96.58 88	87.74 27	99.44 29	92.83 66	98.40 54	98.62 22

DPM-MVS		92.58 89	91.74 99	95.08 15	96.19 99	89.31 5	92.66 268	96.56 103	83.44 234	91.68 124	95.04 151	86.60 42	98.99 74	85.60 179	97.92 77	96.93 145

ZNCC-MVS		94.47 26	94.28 37	95.03 16	98.52 15	86.96 20	96.85 28	97.32 29	88.24 109	93.15 78	97.04 64	86.17 47	99.62 2	92.40 76	98.81 23	98.52 26

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 16	97.49 7					99.61 4	95.62 30	99.08 7	98.99 9

MTAPA		94.42 31	94.22 40	95.00 18	98.42 21	86.95 21	94.36 186	96.97 58	91.07 15	93.14 79	97.56 38	84.30 74	99.56 12	93.43 55	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 12	91.73 12	96.10 28	96.69 78	89.90 12	99.30 43	94.70 40	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 29	94.27 39	94.92 20	98.65 8	86.67 30	96.92 24	97.23 37	88.60 99	93.58 70	97.27 49	85.22 58	99.54 20	92.21 83	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 21	89.03 84	96.20 27	98.10 11	89.39 16	99.34 37	95.88 25	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 29	94.28 37	94.91 21	98.63 9	86.69 28	96.94 20	97.32 29	88.63 96	93.53 73	97.26 51	85.04 62	99.54 20	92.35 79	98.78 26	98.50 27

GST-MVS		94.21 37	93.97 52	94.90 23	98.41 22	86.82 24	96.54 36	97.19 38	88.24 109	93.26 75	96.83 73	85.48 55	99.59 8	91.43 107	98.40 54	98.30 50

HFP-MVS		94.52 24	94.40 30	94.86 24	98.61 10	86.81 25	96.94 20	97.34 25	88.63 96	93.65 68	97.21 53	86.10 48	99.49 26	92.35 79	98.77 28	98.30 50

sasdasda		93.27 73	92.75 83	94.85 25	95.70 127	87.66 12	96.33 39	96.41 113	90.00 43	94.09 58	94.60 171	82.33 102	98.62 119	92.40 76	92.86 193	98.27 57

MP-MVS-pluss		94.21 37	94.00 51	94.85 25	98.17 33	86.65 31	94.82 150	97.17 43	86.26 166	92.83 88	97.87 29	85.57 54	99.56 12	94.37 45	98.92 17	98.34 43
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
canonicalmvs		93.27 73	92.75 83	94.85 25	95.70 127	87.66 12	96.33 39	96.41 113	90.00 43	94.09 58	94.60 171	82.33 102	98.62 119	92.40 76	92.86 193	98.27 57

XVS		94.45 27	94.32 33	94.85 25	98.54 13	86.60 34	96.93 22	97.19 38	90.66 27	92.85 86	97.16 59	85.02 63	99.49 26	91.99 93	98.56 50	98.47 33

X-MVStestdata		88.31 191	86.13 239	94.85 25	98.54 13	86.60 34	96.93 22	97.19 38	90.66 27	92.85 86	23.41 433	85.02 63	99.49 26	91.99 93	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 31	91.38 14	95.39 39	97.46 41	88.98 19	99.40 30	94.12 46	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 7	90.75 22	97.62 5	98.06 18	92.59 2	99.61 4	95.64 28	99.02 12	98.86 11

alignmvs		93.08 81	92.50 89	94.81 32	95.62 133	87.61 15	95.99 71	96.07 145	89.77 56	94.12 57	94.87 157	80.56 125	98.66 112	92.42 75	93.10 189	98.15 69

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 52	97.13 14	97.44 16	90.31 33	97.71 1	98.07 16	92.31 4	99.58 10	95.66 26	99.13 3	98.84 14

DeepC-MVS_fast	89.43 2	94.04 45	93.79 57	94.80 33	97.48 64	86.78 26	95.65 100	96.89 69	89.40 67	92.81 89	96.97 66	85.37 57	99.24 46	90.87 116	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 34	94.07 48	94.77 35	98.47 18	86.31 44	96.71 31	96.98 57	89.04 82	91.98 111	97.19 56	85.43 56	99.56 12	92.06 92	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 35	94.07 48	94.75 36	98.06 39	86.90 23	95.88 80	96.94 64	85.68 180	95.05 46	97.18 57	87.31 35	99.07 57	91.90 99	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 32	94.21 42	94.74 37	98.39 23	86.64 32	97.60 4	97.24 35	88.53 101	92.73 94	97.23 52	85.20 59	99.32 41	92.15 86	98.83 22	98.25 62

PGM-MVS		93.96 50	93.72 62	94.68 38	98.43 20	86.22 47	95.30 115	97.78 1	87.45 137	93.26 75	97.33 47	84.62 71	99.51 24	90.75 118	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 89	90.27 37	97.04 16	98.05 20	91.47 8	99.55 16	95.62 30	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 48	93.78 58	94.63 40	98.50 16	85.90 60	96.87 26	96.91 67	88.70 94	91.83 120	97.17 58	83.96 78	99.55 16	91.44 106	98.64 45	98.43 38

PHI-MVS		93.89 52	93.65 66	94.62 41	96.84 78	86.43 39	96.69 32	97.49 7	85.15 193	93.56 72	96.28 96	85.60 53	99.31 42	92.45 73	98.79 24	98.12 73

TSAR-MVS + MP.		94.85 14	94.94 17	94.58 42	98.25 29	86.33 42	96.11 59	96.62 98	88.14 114	96.10 28	96.96 67	89.09 18	98.94 84	94.48 43	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 61	93.20 75	94.55 43	95.65 130	85.73 65	94.94 141	96.69 94	91.89 10	90.69 136	95.88 116	81.99 114	99.54 20	93.14 61	97.95 76	98.39 40

train_agg		93.44 66	93.08 76	94.52 44	97.53 61	86.49 37	94.07 203	96.78 81	81.86 275	92.77 91	96.20 99	87.63 29	99.12 55	92.14 87	98.69 35	97.94 83

CDPH-MVS		92.83 85	92.30 91	94.44 45	97.79 52	86.11 49	94.06 205	96.66 95	80.09 306	92.77 91	96.63 85	86.62 40	99.04 61	87.40 154	98.66 41	98.17 67

3Dnovator	86.66 5	91.73 103	90.82 115	94.44 45	94.59 189	86.37 41	97.18 12	97.02 55	89.20 76	84.31 282	96.66 81	73.74 217	99.17 50	86.74 164	97.96 75	97.79 95

SR-MVS		94.23 36	94.17 46	94.43 47	98.21 32	85.78 63	96.40 38	96.90 68	88.20 112	94.33 52	97.40 44	84.75 70	99.03 62	93.35 58	97.99 74	98.48 30

HPM-MVS		94.02 46	93.88 53	94.43 47	98.39 23	85.78 63	97.25 10	97.07 53	86.90 151	92.62 98	96.80 77	84.85 69	99.17 50	92.43 74	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 59	93.41 70	94.41 49	96.59 85	86.78 26	94.40 178	93.93 270	89.77 56	94.21 54	95.59 129	87.35 34	98.61 121	92.72 69	96.15 124	97.83 93

reproduce-ours		94.82 15	94.97 15	94.38 50	97.91 47	85.46 68	95.86 81	97.15 45	89.82 49	95.23 43	98.10 11	87.09 37	99.37 33	95.30 34	98.25 60	98.30 50

our_new_method		94.82 15	94.97 15	94.38 50	97.91 47	85.46 68	95.86 81	97.15 45	89.82 49	95.23 43	98.10 11	87.09 37	99.37 33	95.30 34	98.25 60	98.30 50

test12				94.34 52	97.13 73	86.15 48		96.29 121		91.04 133		85.08 61	99.01 67		98.13 67	97.86 90

ACMMP		93.24 75	92.88 81	94.30 53	98.09 38	85.33 72	96.86 27	97.45 15	88.33 105	90.15 146	97.03 65	81.44 119	99.51 24	90.85 117	95.74 129	98.04 78
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 18	94.29 54	97.92 43	85.18 74	95.95 76	97.19 38	89.67 59	95.27 42	98.16 4	86.53 43	99.36 35	95.42 33	98.15 65	98.33 45

DeepC-MVS	88.79 3	93.31 72	92.99 79	94.26 55	96.07 109	85.83 61	94.89 144	96.99 56	89.02 85	89.56 151	97.37 46	82.51 99	99.38 31	92.20 84	98.30 57	97.57 108
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 82	92.63 86	94.23 56	95.62 133	85.92 57	96.08 61	96.33 119	89.86 47	93.89 65	94.66 168	82.11 109	98.50 127	92.33 81	92.82 196	98.27 57

fmvsm_l_conf0.5_n_3		94.80 18	95.01 14	94.15 57	95.64 131	85.08 75	96.09 60	97.36 23	90.98 17	97.09 14	98.12 8	84.98 67	98.94 84	97.07 13	97.80 82	98.43 38

EPNet		91.79 100	91.02 111	94.10 58	90.10 359	85.25 73	96.03 68	92.05 320	92.83 4	87.39 194	95.78 121	79.39 141	99.01 67	88.13 145	97.48 90	98.05 77
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmconf_n		94.60 22	94.81 22	93.98 59	94.62 187	84.96 78	96.15 54	97.35 24	89.37 68	96.03 31	98.11 9	86.36 44	99.01 67	97.45 8	97.83 80	97.96 82

DELS-MVS		93.43 70	93.25 73	93.97 60	95.42 141	85.04 76	93.06 256	97.13 48	90.74 24	91.84 118	95.09 150	86.32 45	99.21 48	91.22 108	98.45 52	97.65 103
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 98	91.28 105	93.96 61	98.33 27	85.92 57	94.66 161	96.66 95	82.69 254	90.03 148	95.82 119	82.30 104	99.03 62	84.57 191	96.48 118	96.91 147

HPM-MVS_fast		93.40 71	93.22 74	93.94 62	98.36 25	84.83 80	97.15 13	96.80 80	85.77 177	92.47 102	97.13 60	82.38 100	99.07 57	90.51 121	98.40 54	97.92 86

test_fmvsmconf0.1_n		94.20 39	94.31 35	93.88 63	92.46 278	84.80 81	96.18 51	96.82 77	89.29 73	95.68 36	98.11 9	85.10 60	98.99 74	97.38 9	97.75 86	97.86 90

SD-MVS		94.96 13	95.33 8	93.88 63	97.25 72	86.69 28	96.19 49	97.11 51	90.42 30	96.95 18	97.27 49	89.53 14	96.91 271	94.38 44	98.85 20	98.03 79
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 65	93.31 71	93.84 65	96.99 75	84.84 79	93.24 249	97.24 35	88.76 91	91.60 125	95.85 117	86.07 49	98.66 112	91.91 97	98.16 64	98.03 79

SR-MVS-dyc-post		93.82 54	93.82 55	93.82 66	97.92 43	84.57 87	96.28 43	96.76 84	87.46 135	93.75 66	97.43 42	84.24 75	99.01 67	92.73 67	97.80 82	97.88 88

test_prior				93.82 66	97.29 70	84.49 91		96.88 70					98.87 91			98.11 74

APD-MVS_3200maxsize		93.78 55	93.77 59	93.80 68	97.92 43	84.19 102	96.30 41	96.87 71	86.96 147	93.92 64	97.47 40	83.88 79	98.96 81	92.71 70	97.87 78	98.26 61

fmvsm_l_conf0.5_n		94.29 33	94.46 28	93.79 69	95.28 146	85.43 70	95.68 95	96.43 111	86.56 158	96.84 20	97.81 32	87.56 32	98.77 104	97.14 11	96.82 108	97.16 129

CSCG		93.23 76	93.05 77	93.76 70	98.04 40	84.07 104	96.22 48	97.37 22	84.15 216	90.05 147	95.66 126	87.77 26	99.15 53	89.91 126	98.27 58	98.07 75

GDP-MVS		92.04 96	91.46 102	93.75 71	94.55 194	84.69 84	95.60 106	96.56 103	87.83 127	93.07 82	95.89 115	73.44 221	98.65 114	90.22 124	96.03 126	97.91 87

BP-MVS1		92.48 91	92.07 94	93.72 72	94.50 197	84.39 99	95.90 79	94.30 256	90.39 31	92.67 96	95.94 112	74.46 201	98.65 114	93.14 61	97.35 94	98.13 70

test_fmvsmconf0.01_n		93.19 77	93.02 78	93.71 73	89.25 372	84.42 98	96.06 65	96.29 121	89.06 80	94.68 48	98.13 5	79.22 143	98.98 78	97.22 10	97.24 96	97.74 98

UA-Net		92.83 85	92.54 88	93.68 74	96.10 106	84.71 83	95.66 98	96.39 115	91.92 9	93.22 77	96.49 91	83.16 88	98.87 91	84.47 193	95.47 136	97.45 113

fmvsm_l_conf0.5_n_a		94.20 39	94.40 30	93.60 75	95.29 145	84.98 77	95.61 103	96.28 124	86.31 164	96.75 22	97.86 30	87.40 33	98.74 107	97.07 13	97.02 101	97.07 132

QAPM		89.51 154	88.15 178	93.59 76	94.92 168	84.58 86	96.82 29	96.70 93	78.43 333	83.41 303	96.19 102	73.18 225	99.30 43	77.11 302	96.54 115	96.89 148

test_fmvsm_n_1920		94.71 21	95.11 12	93.50 77	95.79 122	84.62 85	96.15 54	97.64 2	89.85 48	97.19 11	97.89 28	86.28 46	98.71 110	97.11 12	98.08 71	97.17 125

casdiffmvs_mvg		92.96 84	92.83 82	93.35 78	94.59 189	83.40 125	95.00 138	96.34 118	90.30 35	92.05 109	96.05 107	83.43 82	98.15 161	92.07 89	95.67 130	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 50	94.18 45	93.30 79	94.79 177	83.81 111	95.77 89	96.74 88	88.02 117	96.23 26	97.84 31	83.36 86	98.83 98	97.49 6	97.34 95	97.25 120

EI-MVSNet-Vis-set		93.01 83	92.92 80	93.29 80	95.01 160	83.51 122	94.48 170	95.77 170	90.87 18	92.52 100	96.67 80	84.50 72	99.00 72	91.99 93	94.44 163	97.36 115

Vis-MVSNet		91.75 102	91.23 106	93.29 80	95.32 144	83.78 112	96.14 56	95.98 152	89.89 45	90.45 138	96.58 88	75.09 192	98.31 152	84.75 189	96.90 104	97.78 96
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_conf03		93.98 49	94.22 40	93.26 82	96.13 101	83.29 128	96.27 45	96.52 106	89.82 49	95.56 38	95.51 131	84.50 72	98.79 102	94.83 39	98.86 19	97.72 99

SPE-MVS-test		94.02 46	94.29 36	93.24 83	96.69 81	83.24 129	97.49 5	96.92 66	92.14 7	92.90 84	95.77 122	85.02 63	98.33 149	93.03 63	98.62 46	98.13 70

VNet		92.24 95	91.91 96	93.24 83	96.59 85	83.43 123	94.84 149	96.44 110	89.19 77	94.08 61	95.90 114	77.85 162	98.17 159	88.90 136	93.38 182	98.13 70

VDD-MVS		90.74 121	89.92 133	93.20 85	96.27 97	83.02 142	95.73 92	93.86 274	88.42 104	92.53 99	96.84 72	62.09 336	98.64 116	90.95 114	92.62 198	97.93 85

CS-MVS		94.12 43	94.44 29	93.17 86	96.55 88	83.08 139	97.63 3	96.95 63	91.71 13	93.50 74	96.21 98	85.61 52	98.24 154	93.64 52	98.17 63	98.19 65

nrg030		91.08 115	90.39 119	93.17 86	93.07 260	86.91 22	96.41 37	96.26 126	88.30 107	88.37 172	94.85 160	82.19 108	97.64 202	91.09 109	82.95 318	94.96 228

MVSMamba_PlusPlus		93.44 66	93.54 68	93.14 88	96.58 87	83.05 140	96.06 65	96.50 108	84.42 213	94.09 58	95.56 130	85.01 66	98.69 111	94.96 38	98.66 41	97.67 102

EI-MVSNet-UG-set		92.74 87	92.62 87	93.12 89	94.86 173	83.20 131	94.40 178	95.74 173	90.71 26	92.05 109	96.60 87	84.00 77	98.99 74	91.55 104	93.63 173	97.17 125

test_fmvsmvis_n_1920		93.44 66	93.55 67	93.10 90	93.67 242	84.26 101	95.83 85	96.14 136	89.00 86	92.43 103	97.50 39	83.37 85	98.72 108	96.61 20	97.44 91	96.32 170

新几何1				93.10 90	97.30 69	84.35 100		95.56 187	71.09 399	91.26 131	96.24 97	82.87 95	98.86 93	79.19 281	98.10 68	96.07 185

OMC-MVS		91.23 111	90.62 118	93.08 92	96.27 97	84.07 104	93.52 231	95.93 156	86.95 148	89.51 152	96.13 105	78.50 153	98.35 146	85.84 177	92.90 192	96.83 152

OpenMVS	83.78 11	88.74 180	87.29 197	93.08 92	92.70 273	85.39 71	96.57 35	96.43 111	78.74 328	80.85 335	96.07 106	69.64 268	99.01 67	78.01 293	96.65 113	94.83 235

MAR-MVS		90.30 132	89.37 144	93.07 94	96.61 84	84.48 92	95.68 95	95.67 179	82.36 259	87.85 181	92.85 232	76.63 173	98.80 100	80.01 269	96.68 112	95.91 191
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		90.92 116	90.21 122	93.03 95	93.86 232	83.88 109	92.81 265	93.86 274	79.84 309	91.76 121	94.29 181	77.92 159	98.04 177	90.48 122	97.11 97	97.17 125

Effi-MVS+		91.59 106	91.11 108	93.01 96	94.35 210	83.39 126	94.60 163	95.10 217	87.10 144	90.57 137	93.10 227	81.43 120	98.07 175	89.29 132	94.48 161	97.59 107

fmvsm_s_conf0.5_n_a		93.57 60	93.76 60	93.00 97	95.02 159	83.67 115	96.19 49	96.10 142	87.27 140	95.98 32	98.05 20	83.07 92	98.45 137	96.68 19	95.51 133	96.88 149

MVS_111021_LR		92.47 92	92.29 92	92.98 98	95.99 115	84.43 96	93.08 254	96.09 143	88.20 112	91.12 132	95.72 125	81.33 121	97.76 192	91.74 101	97.37 93	96.75 154

fmvsm_s_conf0.1_n_a		93.19 77	93.26 72	92.97 99	92.49 276	83.62 118	96.02 69	95.72 176	86.78 153	96.04 30	98.19 2	82.30 104	98.43 141	96.38 21	95.42 139	96.86 150

ETV-MVS		92.74 87	92.66 85	92.97 99	95.20 152	84.04 106	95.07 134	96.51 107	90.73 25	92.96 83	91.19 292	84.06 76	98.34 147	91.72 102	96.54 115	96.54 165

LFMVS		90.08 137	89.13 150	92.95 101	96.71 80	82.32 165	96.08 61	89.91 374	86.79 152	92.15 108	96.81 75	62.60 334	98.34 147	87.18 158	93.90 169	98.19 65

UGNet		89.95 142	88.95 154	92.95 101	94.51 196	83.31 127	95.70 94	95.23 210	89.37 68	87.58 188	93.94 196	64.00 324	98.78 103	83.92 200	96.31 120	96.74 155
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		90.80 119	90.10 126	92.90 103	93.04 263	83.53 121	93.08 254	94.15 263	80.22 303	91.41 128	94.91 154	76.87 167	97.93 186	90.28 123	96.90 104	97.24 121
jason: jason.
DP-MVS		87.25 231	85.36 268	92.90 103	97.65 58	83.24 129	94.81 151	92.00 322	74.99 367	81.92 324	95.00 152	72.66 230	99.05 59	66.92 379	92.33 203	96.40 167

fmvsm_s_conf0.5_n_8		94.56 23	95.12 11	92.87 105	95.96 118	81.32 188	95.76 91	97.57 4	93.48 2	97.53 7	98.32 1	81.78 118	99.13 54	97.91 1	97.81 81	98.16 68

fmvsm_s_conf0.5_n		93.76 56	94.06 50	92.86 106	95.62 133	83.17 132	96.14 56	96.12 140	88.13 115	95.82 34	98.04 23	83.43 82	98.48 129	96.97 17	96.23 121	96.92 146

fmvsm_s_conf0.1_n		93.46 64	93.66 65	92.85 107	93.75 238	83.13 134	96.02 69	95.74 173	87.68 132	95.89 33	98.17 3	82.78 96	98.46 133	96.71 18	96.17 123	96.98 141

CANet_DTU		90.26 134	89.41 143	92.81 108	93.46 249	83.01 143	93.48 232	94.47 249	89.43 66	87.76 186	94.23 186	70.54 257	99.03 62	84.97 184	96.39 119	96.38 168

MVSFormer		91.68 105	91.30 104	92.80 109	93.86 232	83.88 109	95.96 74	95.90 160	84.66 209	91.76 121	94.91 154	77.92 159	97.30 238	89.64 128	97.11 97	97.24 121

PVSNet_Blended_VisFu		91.38 108	90.91 113	92.80 109	96.39 94	83.17 132	94.87 146	96.66 95	83.29 239	89.27 158	94.46 176	80.29 128	99.17 50	87.57 152	95.37 140	96.05 188

fmvsm_s_conf0.5_n_6		94.11 44	94.56 25	92.76 111	94.98 163	81.96 172	95.79 87	97.29 33	89.31 71	97.52 8	97.61 37	83.25 87	98.88 90	97.05 15	98.22 62	97.43 114

VDDNet		89.56 153	88.49 169	92.76 111	95.07 158	82.09 167	96.30 41	93.19 289	81.05 297	91.88 116	96.86 71	61.16 352	98.33 149	88.43 142	92.49 202	97.84 92

h-mvs33		90.80 119	90.15 125	92.75 113	96.01 111	82.66 156	95.43 109	95.53 191	89.80 52	93.08 80	95.64 127	75.77 181	99.00 72	92.07 89	78.05 375	96.60 160

casdiffmvs		92.51 90	92.43 90	92.74 114	94.41 205	81.98 170	94.54 167	96.23 130	89.57 62	91.96 113	96.17 103	82.58 98	98.01 179	90.95 114	95.45 138	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		90.69 123	90.02 131	92.71 115	95.72 125	82.41 163	94.11 198	95.12 215	85.63 181	91.49 126	94.70 164	74.75 196	98.42 142	86.13 172	92.53 200	97.31 116

DCV-MVSNet		90.69 123	90.02 131	92.71 115	95.72 125	82.41 163	94.11 198	95.12 215	85.63 181	91.49 126	94.70 164	74.75 196	98.42 142	86.13 172	92.53 200	97.31 116

PCF-MVS	84.11 10	87.74 206	86.08 243	92.70 117	94.02 223	84.43 96	89.27 354	95.87 164	73.62 381	84.43 274	94.33 178	78.48 154	98.86 93	70.27 353	94.45 162	94.81 236
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
baseline		92.39 94	92.29 92	92.69 118	94.46 200	81.77 175	94.14 195	96.27 125	89.22 75	91.88 116	96.00 108	82.35 101	97.99 181	91.05 110	95.27 144	98.30 50

MSLP-MVS++		93.72 58	94.08 47	92.65 119	97.31 68	83.43 123	95.79 87	97.33 27	90.03 42	93.58 70	96.96 67	84.87 68	97.76 192	92.19 85	98.66 41	96.76 153

EC-MVSNet		93.44 66	93.71 63	92.63 120	95.21 151	82.43 160	97.27 9	96.71 92	90.57 29	92.88 85	95.80 120	83.16 88	98.16 160	93.68 51	98.14 66	97.31 116

ab-mvs		89.41 159	88.35 171	92.60 121	95.15 156	82.65 157	92.20 285	95.60 186	83.97 220	88.55 168	93.70 209	74.16 209	98.21 158	82.46 222	89.37 246	96.94 144

LS3D		87.89 201	86.32 232	92.59 122	96.07 109	82.92 146	95.23 122	94.92 229	75.66 359	82.89 310	95.98 110	72.48 233	99.21 48	68.43 367	95.23 145	95.64 204

Anonymous20240529		88.09 197	86.59 221	92.58 123	96.53 90	81.92 173	95.99 71	95.84 166	74.11 376	89.06 162	95.21 144	61.44 344	98.81 99	83.67 205	87.47 277	97.01 139

fmvsm_s_conf0.5_n_3		94.49 25	95.13 10	92.56 124	95.49 139	81.10 198	95.93 77	97.16 44	92.96 3	97.39 9	98.13 5	83.63 81	98.80 100	97.89 2	97.61 89	97.78 96

CPTT-MVS		91.99 97	91.80 97	92.55 125	98.24 31	81.98 170	96.76 30	96.49 109	81.89 274	90.24 141	96.44 93	78.59 151	98.61 121	89.68 127	97.85 79	97.06 133

114514_t		89.51 154	88.50 167	92.54 126	98.11 36	81.99 169	95.16 130	96.36 117	70.19 403	85.81 228	95.25 141	76.70 171	98.63 118	82.07 232	96.86 107	97.00 140

PAPM_NR		91.22 112	90.78 116	92.52 127	97.60 59	81.46 184	94.37 184	96.24 129	86.39 163	87.41 191	94.80 162	82.06 112	98.48 129	82.80 217	95.37 140	97.61 105

DeepPCF-MVS	89.96 1	94.20 39	94.77 23	92.49 128	96.52 91	80.00 233	94.00 211	97.08 52	90.05 41	95.65 37	97.29 48	89.66 13	98.97 79	93.95 48	98.71 32	98.50 27

IS-MVSNet		91.43 107	91.09 110	92.46 129	95.87 121	81.38 187	96.95 19	93.69 281	89.72 58	89.50 154	95.98 110	78.57 152	97.77 191	83.02 211	96.50 117	98.22 64

API-MVS		90.66 125	90.07 127	92.45 130	96.36 95	84.57 87	96.06 65	95.22 212	82.39 257	89.13 159	94.27 184	80.32 127	98.46 133	80.16 268	96.71 111	94.33 259

xiu_mvs_v1_base_debu		90.64 126	90.05 128	92.40 131	93.97 229	84.46 93	93.32 240	95.46 194	85.17 190	92.25 104	94.03 188	70.59 253	98.57 124	90.97 111	94.67 153	94.18 262

xiu_mvs_v1_base		90.64 126	90.05 128	92.40 131	93.97 229	84.46 93	93.32 240	95.46 194	85.17 190	92.25 104	94.03 188	70.59 253	98.57 124	90.97 111	94.67 153	94.18 262

xiu_mvs_v1_base_debi		90.64 126	90.05 128	92.40 131	93.97 229	84.46 93	93.32 240	95.46 194	85.17 190	92.25 104	94.03 188	70.59 253	98.57 124	90.97 111	94.67 153	94.18 262

fmvsm_s_conf0.5_n_2		93.47 63	93.83 54	92.39 134	95.36 142	81.19 194	95.20 127	96.56 103	90.37 32	97.13 13	98.03 24	77.47 163	98.96 81	97.79 4	96.58 114	97.03 136

fmvsm_s_conf0.1_n_2		93.16 79	93.42 69	92.37 135	94.62 187	81.13 196	95.23 122	95.89 162	90.30 35	96.74 23	98.02 25	76.14 175	98.95 83	97.64 5	96.21 122	97.03 136

AdaColmap		89.89 145	89.07 151	92.37 135	97.41 65	83.03 141	94.42 177	95.92 157	82.81 251	86.34 217	94.65 169	73.89 213	99.02 65	80.69 259	95.51 133	95.05 223

CNLPA		89.07 170	87.98 181	92.34 137	96.87 77	84.78 82	94.08 202	93.24 287	81.41 288	84.46 272	95.13 149	75.57 188	96.62 282	77.21 300	93.84 171	95.61 207

fmvsm_s_conf0.5_n_4		93.86 53	94.37 32	92.33 138	95.13 157	80.95 203	95.64 101	96.97 58	89.60 61	96.85 19	97.77 33	83.08 91	98.92 87	97.49 6	96.78 109	97.13 130

ET-MVSNet_ETH3D		87.51 219	85.91 251	92.32 139	93.70 241	83.93 107	92.33 280	90.94 354	84.16 215	72.09 399	92.52 245	69.90 263	95.85 329	89.20 133	88.36 264	97.17 125

Anonymous202405211		87.68 207	86.13 239	92.31 140	96.66 82	80.74 210	94.87 146	91.49 339	80.47 302	89.46 155	95.44 133	54.72 388	98.23 155	82.19 228	89.89 236	97.97 81

CHOSEN 1792x2688		88.84 176	87.69 187	92.30 141	96.14 100	81.42 186	90.01 341	95.86 165	74.52 372	87.41 191	93.94 196	75.46 189	98.36 144	80.36 264	95.53 132	97.12 131

HY-MVS	83.01 12	89.03 172	87.94 183	92.29 142	94.86 173	82.77 148	92.08 290	94.49 248	81.52 287	86.93 198	92.79 238	78.32 156	98.23 155	79.93 270	90.55 224	95.88 193

CDS-MVSNet		89.45 157	88.51 166	92.29 142	93.62 244	83.61 120	93.01 257	94.68 245	81.95 269	87.82 184	93.24 221	78.69 149	96.99 265	80.34 265	93.23 187	96.28 173
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		90.02 139	89.27 149	92.29 142	95.78 123	80.95 203	92.68 267	96.22 131	81.91 271	86.66 208	93.75 208	82.23 106	98.44 139	79.40 280	94.79 151	97.48 111

mvsmamba		90.33 131	89.69 136	92.25 145	95.17 153	81.64 177	95.27 120	93.36 286	84.88 200	89.51 152	94.27 184	69.29 277	97.42 224	89.34 131	96.12 125	97.68 101

PLC	84.53 7	89.06 171	88.03 180	92.15 146	97.27 71	82.69 155	94.29 187	95.44 199	79.71 311	84.01 288	94.18 187	76.68 172	98.75 105	77.28 299	93.41 181	95.02 224
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPP-MVSNet		91.70 104	91.56 101	92.13 147	95.88 119	80.50 216	97.33 7	95.25 209	86.15 169	89.76 150	95.60 128	83.42 84	98.32 151	87.37 156	93.25 186	97.56 109

patch_mono-2		93.74 57	94.32 33	92.01 148	97.54 60	78.37 271	93.40 236	97.19 38	88.02 117	94.99 47	97.21 53	88.35 21	98.44 139	94.07 47	98.09 69	99.23 1

原ACMM1				92.01 148	97.34 67	81.05 199		96.81 79	78.89 322	90.45 138	95.92 113	82.65 97	98.84 97	80.68 260	98.26 59	96.14 179

UniMVSNet (Re)		89.80 147	89.07 151	92.01 148	93.60 245	84.52 90	94.78 153	97.47 12	89.26 74	86.44 214	92.32 251	82.10 110	97.39 235	84.81 188	80.84 352	94.12 266

MG-MVS		91.77 101	91.70 100	92.00 151	97.08 74	80.03 231	93.60 229	95.18 213	87.85 126	90.89 134	96.47 92	82.06 112	98.36 144	85.07 183	97.04 100	97.62 104

EIA-MVS		91.95 98	91.94 95	91.98 152	95.16 154	80.01 232	95.36 110	96.73 89	88.44 102	89.34 156	92.16 256	83.82 80	98.45 137	89.35 130	97.06 99	97.48 111

PVSNet_Blended		90.73 122	90.32 121	91.98 152	96.12 102	81.25 190	92.55 272	96.83 75	82.04 267	89.10 160	92.56 244	81.04 123	98.85 95	86.72 166	95.91 127	95.84 195

PS-MVSNAJ		91.18 113	90.92 112	91.96 154	95.26 149	82.60 159	92.09 289	95.70 177	86.27 165	91.84 118	92.46 246	79.70 136	98.99 74	89.08 134	95.86 128	94.29 260

TAMVS		89.21 165	88.29 175	91.96 154	93.71 239	82.62 158	93.30 244	94.19 261	82.22 262	87.78 185	93.94 196	78.83 146	96.95 268	77.70 295	92.98 191	96.32 170

SDMVSNet		90.19 135	89.61 138	91.93 156	96.00 112	83.09 138	92.89 262	95.98 152	88.73 92	86.85 204	95.20 145	72.09 237	97.08 257	88.90 136	89.85 238	95.63 205

FA-MVS(test-final)		89.66 149	88.91 156	91.93 156	94.57 192	80.27 220	91.36 305	94.74 242	84.87 201	89.82 149	92.61 243	74.72 199	98.47 132	83.97 199	93.53 176	97.04 135

MVS_Test		91.31 110	91.11 108	91.93 156	94.37 206	80.14 224	93.46 234	95.80 168	86.46 161	91.35 130	93.77 206	82.21 107	98.09 172	87.57 152	94.95 148	97.55 110

NR-MVSNet		88.58 186	87.47 193	91.93 156	93.04 263	84.16 103	94.77 154	96.25 128	89.05 81	80.04 348	93.29 219	79.02 145	97.05 262	81.71 243	80.05 362	94.59 243

HyFIR lowres test		88.09 197	86.81 209	91.93 156	96.00 112	80.63 212	90.01 341	95.79 169	73.42 383	87.68 187	92.10 262	73.86 214	97.96 183	80.75 258	91.70 207	97.19 124

GeoE		90.05 138	89.43 142	91.90 161	95.16 154	80.37 219	95.80 86	94.65 246	83.90 221	87.55 190	94.75 163	78.18 157	97.62 204	81.28 248	93.63 173	97.71 100

thisisatest0530		88.67 181	87.61 189	91.86 162	94.87 172	80.07 227	94.63 162	89.90 375	84.00 219	88.46 170	93.78 205	66.88 301	98.46 133	83.30 207	92.65 197	97.06 133

xiu_mvs_v2_base		91.13 114	90.89 114	91.86 162	94.97 164	82.42 161	92.24 283	95.64 184	86.11 173	91.74 123	93.14 225	79.67 139	98.89 89	89.06 135	95.46 137	94.28 261

DU-MVS		89.34 164	88.50 167	91.85 164	93.04 263	83.72 113	94.47 173	96.59 100	89.50 63	86.46 211	93.29 219	77.25 165	97.23 247	84.92 185	81.02 348	94.59 243

OPM-MVS		90.12 136	89.56 139	91.82 165	93.14 256	83.90 108	94.16 194	95.74 173	88.96 87	87.86 180	95.43 135	72.48 233	97.91 187	88.10 147	90.18 231	93.65 297
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		90.60 129	90.19 123	91.82 165	94.70 183	82.73 152	95.85 83	96.22 131	90.81 20	86.91 200	94.86 158	74.23 205	98.12 162	88.15 143	89.99 232	94.63 240

UniMVSNet_NR-MVSNet		89.92 144	89.29 147	91.81 167	93.39 251	83.72 113	94.43 176	97.12 49	89.80 52	86.46 211	93.32 216	83.16 88	97.23 247	84.92 185	81.02 348	94.49 253

diffmvs		91.37 109	91.23 106	91.77 168	93.09 259	80.27 220	92.36 277	95.52 192	87.03 146	91.40 129	94.93 153	80.08 130	97.44 222	92.13 88	94.56 158	97.61 105
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		88.42 187	87.33 196	91.72 169	94.92 168	80.98 201	92.97 259	94.54 247	78.16 339	83.82 291	93.88 201	78.78 148	97.91 187	79.45 276	89.41 245	96.26 174

Fast-Effi-MVS+		89.41 159	88.64 162	91.71 170	94.74 178	80.81 208	93.54 230	95.10 217	83.11 243	86.82 206	90.67 315	79.74 135	97.75 195	80.51 263	93.55 175	96.57 163

WTY-MVS		89.60 151	88.92 155	91.67 171	95.47 140	81.15 195	92.38 276	94.78 240	83.11 243	89.06 162	94.32 179	78.67 150	96.61 285	81.57 244	90.89 220	97.24 121

TAPA-MVS	84.62 6	88.16 195	87.01 205	91.62 172	96.64 83	80.65 211	94.39 180	96.21 134	76.38 352	86.19 221	95.44 133	79.75 134	98.08 174	62.75 396	95.29 142	96.13 180
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VPA-MVSNet		89.62 150	88.96 153	91.60 173	93.86 232	82.89 147	95.46 108	97.33 27	87.91 121	88.43 171	93.31 217	74.17 208	97.40 232	87.32 157	82.86 323	94.52 248

FE-MVS		87.40 224	86.02 245	91.57 174	94.56 193	79.69 241	90.27 328	93.72 280	80.57 300	88.80 165	91.62 281	65.32 316	98.59 123	74.97 324	94.33 165	96.44 166

XVG-OURS		89.40 161	88.70 161	91.52 175	94.06 221	81.46 184	91.27 309	96.07 145	86.14 170	88.89 164	95.77 122	68.73 286	97.26 244	87.39 155	89.96 234	95.83 196

hse-mvs2		89.88 146	89.34 145	91.51 176	94.83 175	81.12 197	93.94 214	93.91 273	89.80 52	93.08 80	93.60 210	75.77 181	97.66 199	92.07 89	77.07 382	95.74 200

TranMVSNet+NR-MVSNet		88.84 176	87.95 182	91.49 177	92.68 274	83.01 143	94.92 143	96.31 120	89.88 46	85.53 237	93.85 203	76.63 173	96.96 267	81.91 236	79.87 365	94.50 251

AUN-MVS		87.78 205	86.54 224	91.48 178	94.82 176	81.05 199	93.91 218	93.93 270	83.00 246	86.93 198	93.53 211	69.50 271	97.67 197	86.14 170	77.12 381	95.73 202

XVG-OURS-SEG-HR		89.95 142	89.45 140	91.47 179	94.00 227	81.21 193	91.87 293	96.06 147	85.78 176	88.55 168	95.73 124	74.67 200	97.27 242	88.71 139	89.64 243	95.91 191

MVS		87.44 222	86.10 242	91.44 180	92.61 275	83.62 118	92.63 269	95.66 181	67.26 408	81.47 327	92.15 257	77.95 158	98.22 157	79.71 272	95.48 135	92.47 339

F-COLMAP		87.95 200	86.80 210	91.40 181	96.35 96	80.88 206	94.73 156	95.45 197	79.65 312	82.04 322	94.61 170	71.13 244	98.50 127	76.24 312	91.05 218	94.80 237

dcpmvs_2		93.49 62	94.19 44	91.38 182	97.69 57	76.78 304	94.25 189	96.29 121	88.33 105	94.46 50	96.88 70	88.07 25	98.64 116	93.62 53	98.09 69	98.73 18

thisisatest0515		87.33 227	85.99 246	91.37 183	93.49 247	79.55 242	90.63 323	89.56 383	80.17 304	87.56 189	90.86 305	67.07 298	98.28 153	81.50 245	93.02 190	96.29 172

HQP-MVS		89.80 147	89.28 148	91.34 184	94.17 216	81.56 178	94.39 180	96.04 148	88.81 88	85.43 246	93.97 195	73.83 215	97.96 183	87.11 161	89.77 241	94.50 251

fmvsm_s_conf0.5_n_7		93.15 80	93.76 60	91.31 185	94.42 204	79.48 244	94.52 168	97.14 47	89.33 70	94.17 56	98.09 15	81.83 116	97.49 214	96.33 22	98.02 73	96.95 143

RRT-MVS		90.85 118	90.70 117	91.30 186	94.25 212	76.83 303	94.85 148	96.13 139	89.04 82	90.23 142	94.88 156	70.15 262	98.72 108	91.86 100	94.88 149	98.34 43

FMVSNet3		87.40 224	86.11 241	91.30 186	93.79 237	83.64 117	94.20 193	94.81 238	83.89 222	84.37 275	91.87 272	68.45 289	96.56 290	78.23 290	85.36 294	93.70 296

FMVSNet2		87.19 237	85.82 254	91.30 186	94.01 224	83.67 115	94.79 152	94.94 224	83.57 229	83.88 290	92.05 266	66.59 306	96.51 294	77.56 297	85.01 297	93.73 294

RPMNet		83.95 313	81.53 324	91.21 189	90.58 350	79.34 250	85.24 399	96.76 84	71.44 397	85.55 235	82.97 406	70.87 249	98.91 88	61.01 400	89.36 247	95.40 211

IB-MVS	80.51 15	85.24 291	83.26 308	91.19 190	92.13 287	79.86 237	91.75 296	91.29 344	83.28 240	80.66 338	88.49 361	61.28 346	98.46 133	80.99 254	79.46 369	95.25 217
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		89.47 156	88.90 157	91.18 191	94.22 214	82.07 168	92.13 287	96.09 143	87.90 122	85.37 252	92.45 247	74.38 203	97.56 208	87.15 159	90.43 226	93.93 275
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		89.45 157	88.90 157	91.12 192	94.47 198	81.49 182	95.30 115	96.14 136	86.73 155	85.45 243	95.16 147	69.89 264	98.10 164	87.70 150	89.23 250	93.77 290

LGP-MVS_train				91.12 192	94.47 198	81.49 182		96.14 136	86.73 155	85.45 243	95.16 147	69.89 264	98.10 164	87.70 150	89.23 250	93.77 290

ACMM	84.12 9	89.14 166	88.48 170	91.12 192	94.65 186	81.22 192	95.31 113	96.12 140	85.31 189	85.92 226	94.34 177	70.19 261	98.06 176	85.65 178	88.86 255	94.08 270
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tttt0517		88.61 183	87.78 186	91.11 195	94.96 165	77.81 286	95.35 111	89.69 378	85.09 195	88.05 178	94.59 173	66.93 299	98.48 129	83.27 208	92.13 205	97.03 136

GBi-Net		87.26 229	85.98 247	91.08 196	94.01 224	83.10 135	95.14 131	94.94 224	83.57 229	84.37 275	91.64 277	66.59 306	96.34 307	78.23 290	85.36 294	93.79 285

test1		87.26 229	85.98 247	91.08 196	94.01 224	83.10 135	95.14 131	94.94 224	83.57 229	84.37 275	91.64 277	66.59 306	96.34 307	78.23 290	85.36 294	93.79 285

FMVSNet1		85.85 276	84.11 295	91.08 196	92.81 270	83.10 135	95.14 131	94.94 224	81.64 282	82.68 312	91.64 277	59.01 368	96.34 307	75.37 318	83.78 307	93.79 285

Test_1112_low_res		87.65 209	86.51 225	91.08 196	94.94 167	79.28 254	91.77 295	94.30 256	76.04 357	83.51 301	92.37 249	77.86 161	97.73 196	78.69 285	89.13 252	96.22 175

PS-MVSNAJss		89.97 141	89.62 137	91.02 200	91.90 296	80.85 207	95.26 121	95.98 152	86.26 166	86.21 220	94.29 181	79.70 136	97.65 200	88.87 138	88.10 266	94.57 245

BH-RMVSNet		88.37 189	87.48 192	91.02 200	95.28 146	79.45 246	92.89 262	93.07 292	85.45 186	86.91 200	94.84 161	70.35 258	97.76 192	73.97 332	94.59 157	95.85 194

UniMVSNet_ETH3D		87.53 218	86.37 229	91.00 202	92.44 279	78.96 259	94.74 155	95.61 185	84.07 218	85.36 253	94.52 175	59.78 360	97.34 237	82.93 212	87.88 271	96.71 156

FIs		90.51 130	90.35 120	90.99 203	93.99 228	80.98 201	95.73 92	97.54 5	89.15 78	86.72 207	94.68 166	81.83 116	97.24 246	85.18 182	88.31 265	94.76 238

ACMP	84.23 8	89.01 174	88.35 171	90.99 203	94.73 179	81.27 189	95.07 134	95.89 162	86.48 159	83.67 296	94.30 180	69.33 273	97.99 181	87.10 163	88.55 257	93.72 295
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20231211		86.59 259	85.13 274	90.98 205	96.52 91	81.50 180	96.14 56	96.16 135	73.78 379	83.65 297	92.15 257	63.26 330	97.37 236	82.82 216	81.74 337	94.06 271

sss		88.93 175	88.26 177	90.94 206	94.05 222	80.78 209	91.71 297	95.38 203	81.55 286	88.63 167	93.91 200	75.04 193	95.47 348	82.47 221	91.61 208	96.57 163

sd_testset		88.59 185	87.85 185	90.83 207	96.00 112	80.42 218	92.35 278	94.71 243	88.73 92	86.85 204	95.20 145	67.31 293	96.43 301	79.64 274	89.85 238	95.63 205

PVSNet_BlendedMVS		89.98 140	89.70 135	90.82 208	96.12 102	81.25 190	93.92 216	96.83 75	83.49 233	89.10 160	92.26 254	81.04 123	98.85 95	86.72 166	87.86 272	92.35 345

cascas		86.43 267	84.98 277	90.80 209	92.10 289	80.92 205	90.24 332	95.91 159	73.10 386	83.57 300	88.39 362	65.15 318	97.46 218	84.90 187	91.43 210	94.03 273

ECVR-MVS		89.09 169	88.53 165	90.77 210	95.62 133	75.89 317	96.16 52	84.22 408	87.89 124	90.20 143	96.65 82	63.19 331	98.10 164	85.90 175	96.94 102	98.33 45

GA-MVS		86.61 257	85.27 271	90.66 211	91.33 319	78.71 261	90.40 327	93.81 277	85.34 188	85.12 256	89.57 343	61.25 347	97.11 256	80.99 254	89.59 244	96.15 178

thres600view7		87.65 209	86.67 216	90.59 212	96.08 108	78.72 260	94.88 145	91.58 335	87.06 145	88.08 176	92.30 252	68.91 283	98.10 164	70.05 360	91.10 213	94.96 228

thres400		87.62 214	86.64 217	90.57 213	95.99 115	78.64 262	94.58 164	91.98 324	86.94 149	88.09 174	91.77 273	69.18 279	98.10 164	70.13 357	91.10 213	94.96 228

baseline1		88.10 196	87.28 198	90.57 213	94.96 165	80.07 227	94.27 188	91.29 344	86.74 154	87.41 191	94.00 193	76.77 170	96.20 312	80.77 257	79.31 371	95.44 209

FC-MVSNet-test		90.27 133	90.18 124	90.53 215	93.71 239	79.85 238	95.77 89	97.59 3	89.31 71	86.27 218	94.67 167	81.93 115	97.01 264	84.26 195	88.09 268	94.71 239

PAPM		86.68 256	85.39 266	90.53 215	93.05 262	79.33 253	89.79 344	94.77 241	78.82 325	81.95 323	93.24 221	76.81 168	97.30 238	66.94 377	93.16 188	94.95 231

WR-MVS		88.38 188	87.67 188	90.52 217	93.30 253	80.18 222	93.26 247	95.96 155	88.57 100	85.47 242	92.81 236	76.12 176	96.91 271	81.24 249	82.29 328	94.47 256

MVSTER		88.84 176	88.29 175	90.51 218	92.95 268	80.44 217	93.73 223	95.01 221	84.66 209	87.15 195	93.12 226	72.79 229	97.21 249	87.86 148	87.36 280	93.87 280

testdata				90.49 219	96.40 93	77.89 283		95.37 205	72.51 391	93.63 69	96.69 78	82.08 111	97.65 200	83.08 209	97.39 92	95.94 190

test1111		89.10 167	88.64 162	90.48 220	95.53 138	74.97 327	96.08 61	84.89 406	88.13 115	90.16 145	96.65 82	63.29 329	98.10 164	86.14 170	96.90 104	98.39 40

tt0805		86.92 245	85.74 260	90.48 220	92.22 283	79.98 234	95.63 102	94.88 232	83.83 224	84.74 265	92.80 237	57.61 374	97.67 197	85.48 181	84.42 301	93.79 285

jajsoiax		88.24 193	87.50 191	90.48 220	90.89 339	80.14 224	95.31 113	95.65 183	84.97 198	84.24 283	94.02 191	65.31 317	97.42 224	88.56 140	88.52 259	93.89 276

PatchMatch-RL		86.77 253	85.54 262	90.47 223	95.88 119	82.71 154	90.54 325	92.31 312	79.82 310	84.32 280	91.57 285	68.77 285	96.39 303	73.16 338	93.48 180	92.32 346

tfpn200view9		87.58 216	86.64 217	90.41 224	95.99 115	78.64 262	94.58 164	91.98 324	86.94 149	88.09 174	91.77 273	69.18 279	98.10 164	70.13 357	91.10 213	94.48 254

VPNet		88.20 194	87.47 193	90.39 225	93.56 246	79.46 245	94.04 206	95.54 190	88.67 95	86.96 197	94.58 174	69.33 273	97.15 251	84.05 198	80.53 357	94.56 246

ACMH	80.38 17	85.36 286	83.68 302	90.39 225	94.45 201	80.63 212	94.73 156	94.85 234	82.09 264	77.24 371	92.65 241	60.01 358	97.58 206	72.25 342	84.87 298	92.96 324
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres100view900		87.63 212	86.71 213	90.38 227	96.12 102	78.55 264	95.03 137	91.58 335	87.15 142	88.06 177	92.29 253	68.91 283	98.10 164	70.13 357	91.10 213	94.48 254

mvs_tets		88.06 199	87.28 198	90.38 227	90.94 335	79.88 236	95.22 124	95.66 181	85.10 194	84.21 284	93.94 196	63.53 327	97.40 232	88.50 141	88.40 263	93.87 280

1314		87.51 219	86.57 222	90.34 229	92.42 280	79.74 240	92.63 269	95.35 207	78.35 334	80.14 345	91.62 281	74.05 210	97.15 251	81.05 250	93.53 176	94.12 266

LTVRE_ROB	82.13 13	86.26 270	84.90 280	90.34 229	94.44 202	81.50 180	92.31 282	94.89 230	83.03 245	79.63 354	92.67 240	69.69 267	97.79 190	71.20 346	86.26 289	91.72 356
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		89.03 172	88.64 162	90.21 231	90.74 345	79.28 254	95.96 74	95.90 160	84.66 209	85.33 254	92.94 231	74.02 211	97.30 238	89.64 128	88.53 258	94.05 272

v2v482		87.84 202	87.06 202	90.17 232	90.99 331	79.23 257	94.00 211	95.13 214	84.87 201	85.53 237	92.07 265	74.45 202	97.45 219	84.71 190	81.75 336	93.85 283

pmmvs4		85.43 284	83.86 300	90.16 233	90.02 362	82.97 145	90.27 328	92.67 304	75.93 358	80.73 336	91.74 275	71.05 245	95.73 337	78.85 284	83.46 314	91.78 355

V42		87.68 207	86.86 207	90.15 234	90.58 350	80.14 224	94.24 191	95.28 208	83.66 227	85.67 232	91.33 287	74.73 198	97.41 230	84.43 194	81.83 334	92.89 327

MSDG		84.86 299	83.09 311	90.14 235	93.80 235	80.05 229	89.18 357	93.09 291	78.89 322	78.19 363	91.91 270	65.86 315	97.27 242	68.47 366	88.45 261	93.11 319

anonymousdsp		87.84 202	87.09 201	90.12 236	89.13 373	80.54 215	94.67 160	95.55 188	82.05 265	83.82 291	92.12 259	71.47 242	97.15 251	87.15 159	87.80 275	92.67 333

thres200		87.21 235	86.24 236	90.12 236	95.36 142	78.53 265	93.26 247	92.10 318	86.42 162	88.00 179	91.11 298	69.24 278	98.00 180	69.58 361	91.04 219	93.83 284

CR-MVSNet		85.35 287	83.76 301	90.12 236	90.58 350	79.34 250	85.24 399	91.96 326	78.27 336	85.55 235	87.87 372	71.03 246	95.61 340	73.96 333	89.36 247	95.40 211

v1144		87.61 215	86.79 211	90.06 239	91.01 330	79.34 250	93.95 213	95.42 202	83.36 238	85.66 233	91.31 290	74.98 194	97.42 224	83.37 206	82.06 330	93.42 306

XXY-MVS		87.65 209	86.85 208	90.03 240	92.14 286	80.60 214	93.76 222	95.23 210	82.94 248	84.60 267	94.02 191	74.27 204	95.49 347	81.04 251	83.68 310	94.01 274

Vis-MVSNet (Re-imp)		89.59 152	89.44 141	90.03 240	95.74 124	75.85 318	95.61 103	90.80 358	87.66 134	87.83 183	95.40 136	76.79 169	96.46 299	78.37 286	96.73 110	97.80 94

test2506		87.21 235	86.28 234	90.02 242	95.62 133	73.64 343	96.25 47	71.38 431	87.89 124	90.45 138	96.65 82	55.29 385	98.09 172	86.03 174	96.94 102	98.33 45

BH-untuned		88.60 184	88.13 179	90.01 243	95.24 150	78.50 267	93.29 245	94.15 263	84.75 206	84.46 272	93.40 213	75.76 183	97.40 232	77.59 296	94.52 160	94.12 266

v1192		87.25 231	86.33 231	90.00 244	90.76 344	79.04 258	93.80 220	95.48 193	82.57 255	85.48 241	91.18 294	73.38 224	97.42 224	82.30 225	82.06 330	93.53 300

v7n		86.81 248	85.76 258	89.95 245	90.72 346	79.25 256	95.07 134	95.92 157	84.45 212	82.29 316	90.86 305	72.60 232	97.53 210	79.42 279	80.52 358	93.08 321

testing91		87.11 240	86.18 237	89.92 246	94.43 203	75.38 326	91.53 302	92.27 314	86.48 159	86.50 209	90.24 323	61.19 350	97.53 210	82.10 230	90.88 221	96.84 151

v8		87.50 221	86.71 213	89.89 247	91.37 316	79.40 247	94.50 169	95.38 203	84.81 204	83.60 299	91.33 287	76.05 177	97.42 224	82.84 215	80.51 359	92.84 329

v10		87.25 231	86.38 228	89.85 248	91.19 322	79.50 243	94.48 170	95.45 197	83.79 225	83.62 298	91.19 292	75.13 191	97.42 224	81.94 235	80.60 354	92.63 335

baseline2		86.50 263	85.39 266	89.84 249	91.12 327	76.70 306	91.88 292	88.58 386	82.35 260	79.95 349	90.95 303	73.42 222	97.63 203	80.27 267	89.95 235	95.19 218

pm-mvs1		86.61 257	85.54 262	89.82 250	91.44 311	80.18 222	95.28 119	94.85 234	83.84 223	81.66 325	92.62 242	72.45 235	96.48 296	79.67 273	78.06 374	92.82 330

TR-MVS		86.78 250	85.76 258	89.82 250	94.37 206	78.41 269	92.47 273	92.83 298	81.11 296	86.36 215	92.40 248	68.73 286	97.48 215	73.75 336	89.85 238	93.57 299

ACMH+	81.04 14	85.05 294	83.46 305	89.82 250	94.66 185	79.37 248	94.44 175	94.12 266	82.19 263	78.04 365	92.82 235	58.23 371	97.54 209	73.77 335	82.90 322	92.54 336

EI-MVSNet		89.10 167	88.86 159	89.80 253	91.84 298	78.30 273	93.70 226	95.01 221	85.73 178	87.15 195	95.28 139	79.87 133	97.21 249	83.81 202	87.36 280	93.88 279

v144192		87.19 237	86.35 230	89.74 254	90.64 348	78.24 275	93.92 216	95.43 200	81.93 270	85.51 239	91.05 301	74.21 207	97.45 219	82.86 214	81.56 338	93.53 300

COLMAP_ROB	80.39 16	83.96 312	82.04 321	89.74 254	95.28 146	79.75 239	94.25 189	92.28 313	75.17 365	78.02 366	93.77 206	58.60 370	97.84 189	65.06 388	85.92 290	91.63 358
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SCA		86.32 269	85.18 273	89.73 256	92.15 285	76.60 307	91.12 313	91.69 331	83.53 232	85.50 240	88.81 355	66.79 302	96.48 296	76.65 305	90.35 228	96.12 181

IterMVS-LS		88.36 190	87.91 184	89.70 257	93.80 235	78.29 274	93.73 223	95.08 219	85.73 178	84.75 264	91.90 271	79.88 132	96.92 270	83.83 201	82.51 324	93.89 276
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing11		86.44 266	85.35 269	89.69 258	94.29 211	75.40 325	91.30 307	90.53 361	84.76 205	85.06 258	90.13 329	58.95 369	97.45 219	82.08 231	91.09 217	96.21 177

testing99		86.72 254	85.73 261	89.69 258	94.23 213	74.91 329	91.35 306	90.97 352	86.14 170	86.36 215	90.22 324	59.41 363	97.48 215	82.24 227	90.66 223	96.69 158

v1921920		86.97 244	86.06 244	89.69 258	90.53 353	78.11 278	93.80 220	95.43 200	81.90 272	85.33 254	91.05 301	72.66 230	97.41 230	82.05 233	81.80 335	93.53 300

Fast-Effi-MVS+-dtu		87.44 222	86.72 212	89.63 261	92.04 290	77.68 292	94.03 207	93.94 269	85.81 175	82.42 315	91.32 289	70.33 259	97.06 260	80.33 266	90.23 230	94.14 265

v1240		86.78 250	85.85 253	89.56 262	90.45 354	77.79 288	93.61 228	95.37 205	81.65 281	85.43 246	91.15 296	71.50 241	97.43 223	81.47 246	82.05 332	93.47 304

Effi-MVS+-dtu		88.65 182	88.35 171	89.54 263	93.33 252	76.39 311	94.47 173	94.36 254	87.70 131	85.43 246	89.56 344	73.45 220	97.26 244	85.57 180	91.28 212	94.97 225

AllTest		83.42 319	81.39 325	89.52 264	95.01 160	77.79 288	93.12 251	90.89 356	77.41 343	76.12 379	93.34 214	54.08 391	97.51 212	68.31 368	84.27 303	93.26 309

TestCases				89.52 264	95.01 160	77.79 288		90.89 356	77.41 343	76.12 379	93.34 214	54.08 391	97.51 212	68.31 368	84.27 303	93.26 309

mvs_anonymous		89.37 163	89.32 146	89.51 266	93.47 248	74.22 336	91.65 300	94.83 236	82.91 249	85.45 243	93.79 204	81.23 122	96.36 306	86.47 168	94.09 166	97.94 83

XVG-ACMP-BASELINE		86.00 272	84.84 282	89.45 267	91.20 321	78.00 279	91.70 298	95.55 188	85.05 196	82.97 309	92.25 255	54.49 389	97.48 215	82.93 212	87.45 279	92.89 327

testing222		84.84 300	83.32 306	89.43 268	94.15 219	75.94 316	91.09 314	89.41 384	84.90 199	85.78 229	89.44 345	52.70 396	96.28 310	70.80 352	91.57 209	96.07 185

MVP-Stereo		85.97 273	84.86 281	89.32 269	90.92 337	82.19 166	92.11 288	94.19 261	78.76 327	78.77 362	91.63 280	68.38 290	96.56 290	75.01 323	93.95 168	89.20 394
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchmatchNet		85.85 276	84.70 284	89.29 270	91.76 302	75.54 322	88.49 366	91.30 343	81.63 283	85.05 259	88.70 359	71.71 238	96.24 311	74.61 328	89.05 253	96.08 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v148		87.04 242	86.32 232	89.21 271	90.94 335	77.26 297	93.71 225	94.43 250	84.84 203	84.36 278	90.80 309	76.04 178	97.05 262	82.12 229	79.60 368	93.31 308

tfpnnormal		84.72 302	83.23 309	89.20 272	92.79 271	80.05 229	94.48 170	95.81 167	82.38 258	81.08 333	91.21 291	69.01 282	96.95 268	61.69 398	80.59 355	90.58 381

cl22		86.78 250	85.98 247	89.18 273	92.34 281	77.62 293	90.84 319	94.13 265	81.33 290	83.97 289	90.15 328	73.96 212	96.60 287	84.19 196	82.94 319	93.33 307

BH-w/o		87.57 217	87.05 203	89.12 274	94.90 171	77.90 282	92.41 274	93.51 283	82.89 250	83.70 295	91.34 286	75.75 184	97.07 259	75.49 316	93.49 178	92.39 343

WR-MVS_H		87.80 204	87.37 195	89.10 275	93.23 254	78.12 277	95.61 103	97.30 31	87.90 122	83.72 294	92.01 267	79.65 140	96.01 321	76.36 309	80.54 356	93.16 317

miper_enhance_ethall		86.90 246	86.18 237	89.06 276	91.66 307	77.58 294	90.22 334	94.82 237	79.16 318	84.48 271	89.10 349	79.19 144	96.66 280	84.06 197	82.94 319	92.94 325

c3_l		87.14 239	86.50 226	89.04 277	92.20 284	77.26 297	91.22 312	94.70 244	82.01 268	84.34 279	90.43 320	78.81 147	96.61 285	83.70 204	81.09 345	93.25 311

miper_ehance_all_eth		87.22 234	86.62 220	89.02 278	92.13 287	77.40 296	90.91 318	94.81 238	81.28 291	84.32 280	90.08 331	79.26 142	96.62 282	83.81 202	82.94 319	93.04 322

gg-mvs-nofinetune		81.77 331	79.37 346	88.99 279	90.85 341	77.73 291	86.29 391	79.63 419	74.88 370	83.19 308	69.05 422	60.34 355	96.11 316	75.46 317	94.64 156	93.11 319

ETVMVS		84.43 306	82.92 315	88.97 280	94.37 206	74.67 330	91.23 311	88.35 388	83.37 237	86.06 224	89.04 350	55.38 383	95.67 339	67.12 375	91.34 211	96.58 162

pmmvs6		83.42 319	81.60 323	88.87 281	88.01 388	77.87 284	94.96 140	94.24 260	74.67 371	78.80 361	91.09 299	60.17 357	96.49 295	77.06 304	75.40 388	92.23 348

test_cas_vis1_n_1920		88.83 179	88.85 160	88.78 282	91.15 326	76.72 305	93.85 219	94.93 228	83.23 242	92.81 89	96.00 108	61.17 351	94.45 359	91.67 103	94.84 150	95.17 219

MIMVSNet		82.59 325	80.53 330	88.76 283	91.51 309	78.32 272	86.57 390	90.13 368	79.32 314	80.70 337	88.69 360	52.98 395	93.07 384	66.03 383	88.86 255	94.90 232

cl____		86.52 262	85.78 255	88.75 284	92.03 291	76.46 309	90.74 320	94.30 256	81.83 277	83.34 305	90.78 310	75.74 186	96.57 288	81.74 241	81.54 339	93.22 313

DIV-MVS_self_test		86.53 261	85.78 255	88.75 284	92.02 292	76.45 310	90.74 320	94.30 256	81.83 277	83.34 305	90.82 308	75.75 184	96.57 288	81.73 242	81.52 340	93.24 312

CP-MVSNet		87.63 212	87.26 200	88.74 286	93.12 257	76.59 308	95.29 117	96.58 101	88.43 103	83.49 302	92.98 230	75.28 190	95.83 330	78.97 282	81.15 344	93.79 285

eth_miper_zixun_eth		86.50 263	85.77 257	88.68 287	91.94 293	75.81 319	90.47 326	94.89 230	82.05 265	84.05 286	90.46 319	75.96 179	96.77 275	82.76 218	79.36 370	93.46 305

CHOSEN 280x420		85.15 292	83.99 298	88.65 288	92.47 277	78.40 270	79.68 421	92.76 301	74.90 369	81.41 329	89.59 342	69.85 266	95.51 344	79.92 271	95.29 142	92.03 351

PS-CasMVS		87.32 228	86.88 206	88.63 289	92.99 266	76.33 313	95.33 112	96.61 99	88.22 111	83.30 307	93.07 228	73.03 227	95.79 334	78.36 287	81.00 350	93.75 292

TransMVSNet (Re)		84.43 306	83.06 313	88.54 290	91.72 303	78.44 268	95.18 128	92.82 300	82.73 253	79.67 353	92.12 259	73.49 219	95.96 323	71.10 350	68.73 404	91.21 368

EG-PatchMatch MVS		82.37 327	80.34 333	88.46 291	90.27 356	79.35 249	92.80 266	94.33 255	77.14 347	73.26 396	90.18 327	47.47 407	96.72 276	70.25 354	87.32 282	89.30 391

PEN-MVS		86.80 249	86.27 235	88.40 292	92.32 282	75.71 321	95.18 128	96.38 116	87.97 119	82.82 311	93.15 224	73.39 223	95.92 325	76.15 313	79.03 373	93.59 298

Baseline_NR-MVSNet		87.07 241	86.63 219	88.40 292	91.44 311	77.87 284	94.23 192	92.57 306	84.12 217	85.74 231	92.08 263	77.25 165	96.04 317	82.29 226	79.94 363	91.30 366

UBG		85.51 282	84.57 288	88.35 294	94.21 215	71.78 367	90.07 339	89.66 380	82.28 261	85.91 227	89.01 351	61.30 345	97.06 260	76.58 308	92.06 206	96.22 175

D2MVS		85.90 274	85.09 275	88.35 294	90.79 342	77.42 295	91.83 294	95.70 177	80.77 299	80.08 347	90.02 333	66.74 304	96.37 304	81.88 237	87.97 270	91.26 367

pmmvs5		84.21 308	82.84 318	88.34 296	88.95 375	76.94 301	92.41 274	91.91 328	75.63 360	80.28 342	91.18 294	64.59 321	95.57 341	77.09 303	83.47 313	92.53 337

mamv4		90.92 116	91.78 98	88.33 297	95.67 129	70.75 380	92.92 261	96.02 151	81.90 272	88.11 173	95.34 137	85.88 51	96.97 266	95.22 36	95.01 147	97.26 119

LCM-MVSNet-Re		88.30 192	88.32 174	88.27 298	94.71 182	72.41 362	93.15 250	90.98 351	87.77 129	79.25 357	91.96 268	78.35 155	95.75 335	83.04 210	95.62 131	96.65 159

CostFormer		85.77 279	84.94 279	88.26 299	91.16 325	72.58 360	89.47 352	91.04 350	76.26 355	86.45 213	89.97 335	70.74 251	96.86 274	82.35 224	87.07 285	95.34 215

ITE_SJBPF				88.24 300	91.88 297	77.05 300		92.92 295	85.54 184	80.13 346	93.30 218	57.29 375	96.20 312	72.46 341	84.71 299	91.49 362

PVSNet	78.82 18	85.55 281	84.65 285	88.23 301	94.72 181	71.93 363	87.12 386	92.75 302	78.80 326	84.95 261	90.53 317	64.43 322	96.71 278	74.74 326	93.86 170	96.06 187

IterMVS-SCA-FT		85.45 283	84.53 289	88.18 302	91.71 304	76.87 302	90.19 336	92.65 305	85.40 187	81.44 328	90.54 316	66.79 302	95.00 356	81.04 251	81.05 346	92.66 334

EPNet_dtu		86.49 265	85.94 250	88.14 303	90.24 357	72.82 352	94.11 198	92.20 316	86.66 157	79.42 356	92.36 250	73.52 218	95.81 332	71.26 345	93.66 172	95.80 198
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmtry		82.71 323	80.93 329	88.06 304	90.05 361	76.37 312	84.74 404	91.96 326	72.28 394	81.32 331	87.87 372	71.03 246	95.50 346	68.97 363	80.15 361	92.32 346

test_vis1_n_1920		89.39 162	89.84 134	88.04 305	92.97 267	72.64 357	94.71 158	96.03 150	86.18 168	91.94 115	96.56 90	61.63 340	95.74 336	93.42 56	95.11 146	95.74 200

DTE-MVSNet		86.11 271	85.48 264	87.98 306	91.65 308	74.92 328	94.93 142	95.75 172	87.36 139	82.26 317	93.04 229	72.85 228	95.82 331	74.04 331	77.46 379	93.20 315

PMMVS		85.71 280	84.96 278	87.95 307	88.90 376	77.09 299	88.68 364	90.06 370	72.32 393	86.47 210	90.76 311	72.15 236	94.40 361	81.78 240	93.49 178	92.36 344

GG-mvs-BLEND				87.94 308	89.73 368	77.91 281	87.80 375	78.23 424		80.58 339	83.86 399	59.88 359	95.33 350	71.20 346	92.22 204	90.60 380

MonoMVSNet		86.89 247	86.55 223	87.92 309	89.46 371	73.75 340	94.12 196	93.10 290	87.82 128	85.10 257	90.76 311	69.59 269	94.94 357	86.47 168	82.50 325	95.07 222

reproduce_monomvs		86.37 268	85.87 252	87.87 310	93.66 243	73.71 341	93.44 235	95.02 220	88.61 98	82.64 314	91.94 269	57.88 373	96.68 279	89.96 125	79.71 367	93.22 313

pmmvs-eth3d		80.97 345	78.72 357	87.74 311	84.99 406	79.97 235	90.11 338	91.65 333	75.36 362	73.51 394	86.03 389	59.45 362	93.96 371	75.17 320	72.21 393	89.29 393

MS-PatchMatch		85.05 294	84.16 293	87.73 312	91.42 314	78.51 266	91.25 310	93.53 282	77.50 342	80.15 344	91.58 283	61.99 337	95.51 344	75.69 315	94.35 164	89.16 395

mmtdpeth		85.04 296	84.15 294	87.72 313	93.11 258	75.74 320	94.37 184	92.83 298	84.98 197	89.31 157	86.41 386	61.61 342	97.14 254	92.63 72	62.11 414	90.29 382

test_0402		81.30 341	79.17 351	87.67 314	93.19 255	78.17 276	92.98 258	91.71 329	75.25 364	76.02 381	90.31 322	59.23 364	96.37 304	50.22 417	83.63 311	88.47 402

IterMVS		84.88 298	83.98 299	87.60 315	91.44 311	76.03 315	90.18 337	92.41 308	83.24 241	81.06 334	90.42 321	66.60 305	94.28 365	79.46 275	80.98 351	92.48 338
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmatch-test		81.37 339	79.30 347	87.58 316	90.92 337	74.16 338	80.99 416	87.68 393	70.52 401	76.63 376	88.81 355	71.21 243	92.76 386	60.01 404	86.93 286	95.83 196

EPMVS		83.90 315	82.70 319	87.51 317	90.23 358	72.67 355	88.62 365	81.96 414	81.37 289	85.01 260	88.34 363	66.31 309	94.45 359	75.30 319	87.12 283	95.43 210

ADS-MVSNet2		81.66 334	79.71 343	87.50 318	91.35 317	74.19 337	83.33 409	88.48 387	72.90 388	82.24 318	85.77 392	64.98 319	93.20 382	64.57 390	83.74 308	95.12 220

OurMVSNet-221017-0		85.35 287	84.64 286	87.49 319	90.77 343	72.59 359	94.01 209	94.40 252	84.72 207	79.62 355	93.17 223	61.91 338	96.72 276	81.99 234	81.16 342	93.16 317

tpm2		84.08 310	82.94 314	87.48 320	91.39 315	71.27 372	89.23 356	90.37 363	71.95 395	84.64 266	89.33 346	67.30 294	96.55 292	75.17 320	87.09 284	94.63 240

RPSCF		85.07 293	84.27 290	87.48 320	92.91 269	70.62 382	91.69 299	92.46 307	76.20 356	82.67 313	95.22 142	63.94 325	97.29 241	77.51 298	85.80 291	94.53 247

myMVS_eth3d28		85.80 278	85.26 272	87.42 322	94.73 179	69.92 387	90.60 324	90.95 353	87.21 141	86.06 224	90.04 332	59.47 361	96.02 319	74.89 325	93.35 185	96.33 169

WBMVS		84.97 297	84.18 292	87.34 323	94.14 220	71.62 371	90.20 335	92.35 309	81.61 284	84.06 285	90.76 311	61.82 339	96.52 293	78.93 283	83.81 306	93.89 276

miper_lstm_enhance		85.27 290	84.59 287	87.31 324	91.28 320	74.63 331	87.69 380	94.09 267	81.20 295	81.36 330	89.85 338	74.97 195	94.30 364	81.03 253	79.84 366	93.01 323

FMVSNet5		81.52 337	79.60 344	87.27 325	91.17 323	77.95 280	91.49 303	92.26 315	76.87 348	76.16 378	87.91 371	51.67 397	92.34 389	67.74 372	81.16 342	91.52 361

USDC		82.76 322	81.26 327	87.26 326	91.17 323	74.55 332	89.27 354	93.39 285	78.26 337	75.30 385	92.08 263	54.43 390	96.63 281	71.64 343	85.79 292	90.61 378

test-LLR		85.87 275	85.41 265	87.25 327	90.95 333	71.67 369	89.55 348	89.88 376	83.41 235	84.54 269	87.95 369	67.25 295	95.11 353	81.82 238	93.37 183	94.97 225

test-mter		84.54 305	83.64 303	87.25 327	90.95 333	71.67 369	89.55 348	89.88 376	79.17 317	84.54 269	87.95 369	55.56 381	95.11 353	81.82 238	93.37 183	94.97 225

JIA-IIPM		81.04 342	78.98 355	87.25 327	88.64 377	73.48 345	81.75 415	89.61 382	73.19 385	82.05 321	73.71 418	66.07 314	95.87 328	71.18 348	84.60 300	92.41 342

TDRefinement		79.81 355	77.34 361	87.22 330	79.24 421	75.48 323	93.12 251	92.03 321	76.45 351	75.01 386	91.58 283	49.19 403	96.44 300	70.22 356	69.18 401	89.75 387

tpmvs		83.35 321	82.07 320	87.20 331	91.07 329	71.00 378	88.31 369	91.70 330	78.91 320	80.49 341	87.18 381	69.30 276	97.08 257	68.12 371	83.56 312	93.51 303

ppachtmachnet_test		81.84 330	80.07 338	87.15 332	88.46 381	74.43 335	89.04 360	92.16 317	75.33 363	77.75 368	88.99 352	66.20 311	95.37 349	65.12 387	77.60 377	91.65 357

dmvs_re		84.20 309	83.22 310	87.14 333	91.83 300	77.81 286	90.04 340	90.19 366	84.70 208	81.49 326	89.17 348	64.37 323	91.13 400	71.58 344	85.65 293	92.46 340

tpm cat1		81.96 328	80.27 334	87.01 334	91.09 328	71.02 377	87.38 384	91.53 338	66.25 409	80.17 343	86.35 388	68.22 291	96.15 315	69.16 362	82.29 328	93.86 282

test_fmvs1_n		87.03 243	87.04 204	86.97 335	89.74 367	71.86 364	94.55 166	94.43 250	78.47 331	91.95 114	95.50 132	51.16 399	93.81 372	93.02 64	94.56 158	95.26 216

OpenMVS_ROB	74.94 19	79.51 358	77.03 366	86.93 336	87.00 394	76.23 314	92.33 280	90.74 359	68.93 405	74.52 390	88.23 366	49.58 402	96.62 282	57.64 409	84.29 302	87.94 405

SixPastTwentyTwo		83.91 314	82.90 316	86.92 337	90.99 331	70.67 381	93.48 232	91.99 323	85.54 184	77.62 370	92.11 261	60.59 354	96.87 273	76.05 314	77.75 376	93.20 315

ADS-MVSNet		81.56 336	79.78 340	86.90 338	91.35 317	71.82 365	83.33 409	89.16 385	72.90 388	82.24 318	85.77 392	64.98 319	93.76 373	64.57 390	83.74 308	95.12 220

PatchT		82.68 324	81.27 326	86.89 339	90.09 360	70.94 379	84.06 406	90.15 367	74.91 368	85.63 234	83.57 401	69.37 272	94.87 358	65.19 385	88.50 260	94.84 234

tpm		84.73 301	84.02 297	86.87 340	90.33 355	68.90 390	89.06 359	89.94 373	80.85 298	85.75 230	89.86 337	68.54 288	95.97 322	77.76 294	84.05 305	95.75 199

Patchmatch-RL test		81.67 333	79.96 339	86.81 341	85.42 404	71.23 373	82.17 414	87.50 394	78.47 331	77.19 372	82.50 408	70.81 250	93.48 377	82.66 219	72.89 392	95.71 203

test_vis1_n		86.56 260	86.49 227	86.78 342	88.51 378	72.69 354	94.68 159	93.78 279	79.55 313	90.70 135	95.31 138	48.75 404	93.28 380	93.15 60	93.99 167	94.38 258

testing3-2		86.72 254	86.71 213	86.74 343	96.11 105	65.92 401	93.39 237	89.65 381	89.46 64	87.84 182	92.79 238	59.17 366	97.60 205	81.31 247	90.72 222	96.70 157

test_fmvs1		87.34 226	87.56 190	86.68 344	90.59 349	71.80 366	94.01 209	94.04 268	78.30 335	91.97 112	95.22 142	56.28 379	93.71 374	92.89 65	94.71 152	94.52 248

MDA-MVSNet-bldmvs		78.85 363	76.31 368	86.46 345	89.76 366	73.88 339	88.79 362	90.42 362	79.16 318	59.18 418	88.33 364	60.20 356	94.04 367	62.00 397	68.96 402	91.48 363

mvs5depth		80.98 344	79.15 352	86.45 346	84.57 407	73.29 347	87.79 376	91.67 332	80.52 301	82.20 320	89.72 340	55.14 386	95.93 324	73.93 334	66.83 406	90.12 384

tpmrst		85.35 287	84.99 276	86.43 347	90.88 340	67.88 395	88.71 363	91.43 341	80.13 305	86.08 223	88.80 357	73.05 226	96.02 319	82.48 220	83.40 316	95.40 211

TESTMET0.1,1		83.74 317	82.85 317	86.42 348	89.96 363	71.21 374	89.55 348	87.88 390	77.41 343	83.37 304	87.31 377	56.71 377	93.65 376	80.62 261	92.85 195	94.40 257

our_test_3		81.93 329	80.46 332	86.33 349	88.46 381	73.48 345	88.46 367	91.11 346	76.46 350	76.69 375	88.25 365	66.89 300	94.36 362	68.75 364	79.08 372	91.14 370

lessismore_v0				86.04 350	88.46 381	68.78 391		80.59 417		73.01 397	90.11 330	55.39 382	96.43 301	75.06 322	65.06 409	92.90 326

TinyColmap		79.76 356	77.69 360	85.97 351	91.71 304	73.12 348	89.55 348	90.36 364	75.03 366	72.03 400	90.19 326	46.22 411	96.19 314	63.11 394	81.03 347	88.59 401

KD-MVS_2432*1600		78.50 364	76.02 371	85.93 352	86.22 397	74.47 333	84.80 402	92.33 310	79.29 315	76.98 373	85.92 390	53.81 393	93.97 369	67.39 373	57.42 419	89.36 389

miper_refine_blended		78.50 364	76.02 371	85.93 352	86.22 397	74.47 333	84.80 402	92.33 310	79.29 315	76.98 373	85.92 390	53.81 393	93.97 369	67.39 373	57.42 419	89.36 389

K. test v3		81.59 335	80.15 337	85.91 354	89.89 365	69.42 389	92.57 271	87.71 392	85.56 183	73.44 395	89.71 341	55.58 380	95.52 343	77.17 301	69.76 398	92.78 331

SSC-MVS3.2		84.60 304	84.19 291	85.85 355	92.74 272	68.07 392	88.15 371	93.81 277	87.42 138	83.76 293	91.07 300	62.91 332	95.73 337	74.56 329	83.24 317	93.75 292

mvsany_test1		85.42 285	85.30 270	85.77 356	87.95 390	75.41 324	87.61 383	80.97 416	76.82 349	88.68 166	95.83 118	77.44 164	90.82 402	85.90 175	86.51 287	91.08 374

MIMVSNet1		79.38 359	77.28 362	85.69 357	86.35 396	73.67 342	91.61 301	92.75 302	78.11 340	72.64 398	88.12 367	48.16 405	91.97 394	60.32 401	77.49 378	91.43 364

UWE-MVS		83.69 318	83.09 311	85.48 358	93.06 261	65.27 406	90.92 317	86.14 398	79.90 308	86.26 219	90.72 314	57.17 376	95.81 332	71.03 351	92.62 198	95.35 214

UnsupCasMVSNet_eth		80.07 352	78.27 359	85.46 359	85.24 405	72.63 358	88.45 368	94.87 233	82.99 247	71.64 402	88.07 368	56.34 378	91.75 395	73.48 337	63.36 412	92.01 352

CL-MVSNet_self_test		81.74 332	80.53 330	85.36 360	85.96 399	72.45 361	90.25 330	93.07 292	81.24 293	79.85 352	87.29 378	70.93 248	92.52 387	66.95 376	69.23 400	91.11 372

MDA-MVSNet_test_wron		79.21 361	77.19 364	85.29 361	88.22 385	72.77 353	85.87 393	90.06 370	74.34 373	62.62 415	87.56 375	66.14 312	91.99 393	66.90 380	73.01 390	91.10 373

YYNet1		79.22 360	77.20 363	85.28 362	88.20 386	72.66 356	85.87 393	90.05 372	74.33 374	62.70 413	87.61 374	66.09 313	92.03 391	66.94 377	72.97 391	91.15 369

WB-MVSnew		83.77 316	83.28 307	85.26 363	91.48 310	71.03 376	91.89 291	87.98 389	78.91 320	84.78 263	90.22 324	69.11 281	94.02 368	64.70 389	90.44 225	90.71 376

dp		81.47 338	80.23 335	85.17 364	89.92 364	65.49 404	86.74 388	90.10 369	76.30 354	81.10 332	87.12 382	62.81 333	95.92 325	68.13 370	79.88 364	94.09 269

UnsupCasMVSNet_bld		76.23 373	73.27 377	85.09 365	83.79 409	72.92 350	85.65 396	93.47 284	71.52 396	68.84 408	79.08 413	49.77 401	93.21 381	66.81 381	60.52 416	89.13 397

Anonymous20231206		81.03 343	79.77 342	84.82 366	87.85 391	70.26 384	91.42 304	92.08 319	73.67 380	77.75 368	89.25 347	62.43 335	93.08 383	61.50 399	82.00 333	91.12 371

test0.0.03 1		82.41 326	81.69 322	84.59 367	88.23 384	72.89 351	90.24 332	87.83 391	83.41 235	79.86 351	89.78 339	67.25 295	88.99 412	65.18 386	83.42 315	91.90 354

CMPMVS	59.16 21	80.52 347	79.20 350	84.48 368	83.98 408	67.63 398	89.95 343	93.84 276	64.79 412	66.81 410	91.14 297	57.93 372	95.17 351	76.25 311	88.10 266	90.65 377
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		84.69 303	84.79 283	84.37 369	91.84 298	64.92 407	93.70 226	91.47 340	66.19 410	86.16 222	95.28 139	67.18 297	93.33 379	80.89 256	90.42 227	94.88 233

PVSNet_0	73.20 20	77.22 369	74.83 375	84.37 369	90.70 347	71.10 375	83.09 411	89.67 379	72.81 390	73.93 393	83.13 403	60.79 353	93.70 375	68.54 365	50.84 424	88.30 403

LF4IMVS		80.37 350	79.07 354	84.27 371	86.64 395	69.87 388	89.39 353	91.05 349	76.38 352	74.97 387	90.00 334	47.85 406	94.25 366	74.55 330	80.82 353	88.69 400

Anonymous20240521		80.44 349	79.21 349	84.11 372	85.75 402	67.89 394	92.86 264	93.23 288	75.61 361	75.59 384	87.47 376	50.03 400	94.33 363	71.14 349	81.21 341	90.12 384

PM-MVS		78.11 366	76.12 370	84.09 373	83.54 410	70.08 385	88.97 361	85.27 405	79.93 307	74.73 389	86.43 385	34.70 422	93.48 377	79.43 278	72.06 394	88.72 399

test_fmvs2		83.98 311	84.03 296	83.83 374	87.16 393	67.53 399	93.93 215	92.89 296	77.62 341	86.89 203	93.53 211	47.18 408	92.02 392	90.54 119	86.51 287	91.93 353

testgi		80.94 346	80.20 336	83.18 375	87.96 389	66.29 400	91.28 308	90.70 360	83.70 226	78.12 364	92.84 233	51.37 398	90.82 402	63.34 393	82.46 326	92.43 341

KD-MVS_self_test		80.20 351	79.24 348	83.07 376	85.64 403	65.29 405	91.01 316	93.93 270	78.71 329	76.32 377	86.40 387	59.20 365	92.93 385	72.59 340	69.35 399	91.00 375

testing3		80.46 348	79.59 345	83.06 377	93.44 250	64.64 408	93.33 239	85.47 403	84.34 214	79.93 350	90.84 307	44.35 414	92.39 388	57.06 411	87.56 276	92.16 350

ambc				83.06 377	79.99 419	63.51 412	77.47 422	92.86 297		74.34 392	84.45 398	28.74 423	95.06 355	73.06 339	68.89 403	90.61 378

test20.03		79.95 354	79.08 353	82.55 379	85.79 401	67.74 397	91.09 314	91.08 347	81.23 294	74.48 391	89.96 336	61.63 340	90.15 404	60.08 402	76.38 384	89.76 386

MVStest1		72.91 377	69.70 382	82.54 380	78.14 422	73.05 349	88.21 370	86.21 397	60.69 416	64.70 411	90.53 317	46.44 410	85.70 419	58.78 407	53.62 421	88.87 398

test_vis1_rt		77.96 367	76.46 367	82.48 381	85.89 400	71.74 368	90.25 330	78.89 420	71.03 400	71.30 403	81.35 410	42.49 416	91.05 401	84.55 192	82.37 327	84.65 408

EU-MVSNet		81.32 340	80.95 328	82.42 382	88.50 380	63.67 411	93.32 240	91.33 342	64.02 413	80.57 340	92.83 234	61.21 349	92.27 390	76.34 310	80.38 360	91.32 365

myMVS_eth3d		79.67 357	78.79 356	82.32 383	91.92 294	64.08 409	89.75 346	87.40 395	81.72 279	78.82 359	87.20 379	45.33 412	91.29 398	59.09 406	87.84 273	91.60 359

ttmdpeth		76.55 371	74.64 376	82.29 384	82.25 415	67.81 396	89.76 345	85.69 401	70.35 402	75.76 382	91.69 276	46.88 409	89.77 406	66.16 382	63.23 413	89.30 391

pmmvs3		71.81 380	68.71 383	81.11 385	75.86 424	70.42 383	86.74 388	83.66 409	58.95 419	68.64 409	80.89 411	36.93 420	89.52 408	63.10 395	63.59 411	83.39 409

Syy-MVS		80.07 352	79.78 340	80.94 386	91.92 294	59.93 418	89.75 346	87.40 395	81.72 279	78.82 359	87.20 379	66.29 310	91.29 398	47.06 419	87.84 273	91.60 359

UWE-MVS-28		78.98 362	78.38 358	80.80 387	88.18 387	60.66 417	90.65 322	78.51 421	78.84 324	77.93 367	90.93 304	59.08 367	89.02 411	50.96 416	90.33 229	92.72 332

new-patchmatchnet		76.41 372	75.17 374	80.13 388	82.65 414	59.61 419	87.66 381	91.08 347	78.23 338	69.85 406	83.22 402	54.76 387	91.63 397	64.14 392	64.89 410	89.16 395

mvsany_test3		74.95 374	73.26 378	80.02 389	74.61 425	63.16 413	85.53 397	78.42 422	74.16 375	74.89 388	86.46 384	36.02 421	89.09 410	82.39 223	66.91 405	87.82 406

test_fmvs3		77.67 368	77.16 365	79.22 390	79.52 420	61.14 415	92.34 279	91.64 334	73.98 377	78.86 358	86.59 383	27.38 426	87.03 414	88.12 146	75.97 386	89.50 388

DSMNet-mixed		76.94 370	76.29 369	78.89 391	83.10 412	56.11 427	87.78 377	79.77 418	60.65 417	75.64 383	88.71 358	61.56 343	88.34 413	60.07 403	89.29 249	92.21 349

EGC-MVSNET		61.97 388	56.37 393	78.77 392	89.63 369	73.50 344	89.12 358	82.79 411	0.21 438	1.24 439	84.80 396	39.48 417	90.04 405	44.13 421	75.94 387	72.79 420

new_pmnet		72.15 378	70.13 381	78.20 393	82.95 413	65.68 402	83.91 407	82.40 413	62.94 415	64.47 412	79.82 412	42.85 415	86.26 418	57.41 410	74.44 389	82.65 413

MVS-HIRNet		73.70 376	72.20 379	78.18 394	91.81 301	56.42 426	82.94 412	82.58 412	55.24 420	68.88 407	66.48 423	55.32 384	95.13 352	58.12 408	88.42 262	83.01 411

LCM-MVSNet		66.00 385	62.16 390	77.51 395	64.51 435	58.29 421	83.87 408	90.90 355	48.17 424	54.69 421	73.31 419	16.83 435	86.75 415	65.47 384	61.67 415	87.48 407

APD_test1		69.04 381	66.26 387	77.36 396	80.51 418	62.79 414	85.46 398	83.51 410	54.11 422	59.14 419	84.79 397	23.40 429	89.61 407	55.22 412	70.24 397	79.68 417

test_f		71.95 379	70.87 380	75.21 397	74.21 427	59.37 420	85.07 401	85.82 400	65.25 411	70.42 405	83.13 403	23.62 427	82.93 425	78.32 288	71.94 395	83.33 410

ANet_high		58.88 392	54.22 397	72.86 398	56.50 438	56.67 423	80.75 417	86.00 399	73.09 387	37.39 430	64.63 426	22.17 430	79.49 428	43.51 422	23.96 432	82.43 414

test_vis3_rt		65.12 386	62.60 388	72.69 399	71.44 428	60.71 416	87.17 385	65.55 432	63.80 414	53.22 422	65.65 425	14.54 436	89.44 409	76.65 305	65.38 408	67.91 423

FPMVS		64.63 387	62.55 389	70.88 400	70.80 429	56.71 422	84.42 405	84.42 407	51.78 423	49.57 423	81.61 409	23.49 428	81.48 426	40.61 426	76.25 385	74.46 419

dmvs_testset		74.57 375	75.81 373	70.86 401	87.72 392	40.47 436	87.05 387	77.90 426	82.75 252	71.15 404	85.47 394	67.98 292	84.12 423	45.26 420	76.98 383	88.00 404

N_pmnet		68.89 382	68.44 384	70.23 402	89.07 374	28.79 441	88.06 372	19.50 441	69.47 404	71.86 401	84.93 395	61.24 348	91.75 395	54.70 413	77.15 380	90.15 383

testf1		59.54 390	56.11 394	69.85 403	69.28 430	56.61 424	80.37 418	76.55 429	42.58 427	45.68 426	75.61 414	11.26 437	84.18 421	43.20 423	60.44 417	68.75 421

APD_test2		59.54 390	56.11 394	69.85 403	69.28 430	56.61 424	80.37 418	76.55 429	42.58 427	45.68 426	75.61 414	11.26 437	84.18 421	43.20 423	60.44 417	68.75 421

WB-MVS		67.92 383	67.49 385	69.21 405	81.09 416	41.17 435	88.03 373	78.00 425	73.50 382	62.63 414	83.11 405	63.94 325	86.52 416	25.66 431	51.45 423	79.94 416

PMMVS2		59.60 389	56.40 392	69.21 405	68.83 432	46.58 431	73.02 426	77.48 427	55.07 421	49.21 424	72.95 420	17.43 434	80.04 427	49.32 418	44.33 427	80.99 415

SSC-MVS		67.06 384	66.56 386	68.56 407	80.54 417	40.06 437	87.77 378	77.37 428	72.38 392	61.75 416	82.66 407	63.37 328	86.45 417	24.48 432	48.69 426	79.16 418

Gipuma		57.99 394	54.91 396	67.24 408	88.51 378	65.59 403	52.21 429	90.33 365	43.58 426	42.84 429	51.18 430	20.29 432	85.07 420	34.77 427	70.45 396	51.05 429
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	47.18 22	52.22 396	48.46 400	63.48 409	45.72 440	46.20 432	73.41 425	78.31 423	41.03 429	30.06 432	65.68 424	6.05 439	83.43 424	30.04 429	65.86 407	60.80 424
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		58.82 393	58.24 391	60.56 410	83.13 411	45.09 434	82.32 413	48.22 440	67.61 407	61.70 417	69.15 421	38.75 418	76.05 429	32.01 428	41.31 428	60.55 425

MVE	39.65 23	43.39 398	38.59 404	57.77 411	56.52 437	48.77 430	55.38 428	58.64 436	29.33 432	28.96 433	52.65 429	4.68 440	64.62 433	28.11 430	33.07 430	59.93 426
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.52 397	48.47 399	56.66 412	52.26 439	18.98 443	41.51 431	81.40 415	10.10 433	44.59 428	75.01 417	28.51 424	68.16 430	53.54 414	49.31 425	82.83 412

DeepMVS_CX				56.31 413	74.23 426	51.81 429		56.67 437	44.85 425	48.54 425	75.16 416	27.87 425	58.74 435	40.92 425	52.22 422	58.39 427

kuosan		53.51 395	53.30 398	54.13 414	76.06 423	45.36 433	80.11 420	48.36 439	59.63 418	54.84 420	63.43 427	37.41 419	62.07 434	20.73 434	39.10 429	54.96 428

E-PMN		43.23 399	42.29 401	46.03 415	65.58 434	37.41 438	73.51 424	64.62 433	33.99 430	28.47 434	47.87 431	19.90 433	67.91 431	22.23 433	24.45 431	32.77 430

EMVS		42.07 400	41.12 402	44.92 416	63.45 436	35.56 440	73.65 423	63.48 434	33.05 431	26.88 435	45.45 432	21.27 431	67.14 432	19.80 435	23.02 433	32.06 431

tmp_tt		35.64 401	39.24 403	24.84 417	14.87 441	23.90 442	62.71 427	51.51 438	6.58 435	36.66 431	62.08 428	44.37 413	30.34 437	52.40 415	22.00 434	20.27 432

wuyk23d		21.27 403	20.48 406	23.63 418	68.59 433	36.41 439	49.57 430	6.85 442	9.37 434	7.89 436	4.46 438	4.03 441	31.37 436	17.47 436	16.07 435	3.12 433

test123		8.76 405	11.22 408	1.39 419	0.85 443	0.97 444	85.76 395	0.35 444	0.54 437	2.45 438	8.14 437	0.60 442	0.48 438	2.16 438	0.17 437	2.71 434

testmvs		8.92 404	11.52 407	1.12 420	1.06 442	0.46 445	86.02 392	0.65 443	0.62 436	2.74 437	9.52 436	0.31 443	0.45 439	2.38 437	0.39 436	2.46 435

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

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

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

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

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

cdsmvs_eth3d_5k		22.14 402	29.52 405	0.00 421	0.00 444	0.00 446	0.00 432	95.76 171	0.00 439	0.00 440	94.29 181	75.66 187	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		6.64 407	8.86 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	79.70 136	0.00 440	0.00 439	0.00 438	0.00 436

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

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

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

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

ab-mvs-re		7.82 406	10.43 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	93.88 201	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

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

WAC-MVS						64.08 409								59.14 405

FOURS1					98.86 1	85.54 67	98.29 1	97.49 7	89.79 55	96.29 25

PC_three_1452									82.47 256	97.09 14	97.07 63	92.72 1	98.04 177	92.70 71	99.02 12	98.86 11

test_one_0601					98.58 11	85.83 61		97.44 16	91.05 16	96.78 21	98.06 18	91.45 11

eth-test2					0.00 444

eth-test					0.00 444

ZD-MVS					98.15 34	86.62 33		97.07 53	83.63 228	94.19 55	96.91 69	87.57 31	99.26 45	91.99 93	98.44 53

RE-MVS-def			93.68 64		97.92 43	84.57 87	96.28 43	96.76 84	87.46 135	93.75 66	97.43 42	82.94 93		92.73 67	97.80 82	97.88 88

IU-MVS					98.77 5	86.00 50		96.84 74	81.26 292	97.26 10				95.50 32	99.13 3	99.03 8

test_241102_TWO								97.44 16	90.31 33	97.62 5	98.07 16	91.46 10	99.58 10	95.66 26	99.12 6	98.98 10

test_241102_ONE					98.77 5	85.99 52		97.44 16	90.26 39	97.71 1	97.96 26	92.31 4	99.38 31

9.14			94.47 27		97.79 52		96.08 61	97.44 16	86.13 172	95.10 45	97.40 44	88.34 22	99.22 47	93.25 59	98.70 34

save fliter					97.85 49	85.63 66	95.21 125	96.82 77	89.44 65

test_0728_THIRD									90.75 22	97.04 16	98.05 20	92.09 6	99.55 16	95.64 28	99.13 3	99.13 2

test0726					98.78 3	85.93 55	97.19 11	97.47 12	90.27 37	97.64 4	98.13 5	91.47 8

GSMVS																96.12 181

test_part2					98.55 12	87.22 19				96.40 24

sam_mvs1												71.70 239				96.12 181

sam_mvs												70.60 252

MTGPA								96.97 58

test_post1							88.00 374				9.81 435	69.31 275	95.53 342	76.65 305

test_post											10.29 434	70.57 256	95.91 327

patchmatchnet-post											83.76 400	71.53 240	96.48 296

MTMP							96.16 52	60.64 435

gm-plane-assit					89.60 370	68.00 393			77.28 346		88.99 352		97.57 207	79.44 277

test9_res														91.91 97	98.71 32	98.07 75

TEST9					97.53 61	86.49 37	94.07 203	96.78 81	81.61 284	92.77 91	96.20 99	87.71 28	99.12 55

test_8					97.49 63	86.30 45	94.02 208	96.76 84	81.86 275	92.70 95	96.20 99	87.63 29	99.02 65

agg_prior2														90.54 119	98.68 37	98.27 57

agg_prior					97.38 66	85.92 57		96.72 91		92.16 107			98.97 79

test_prior4						85.96 54	94.11 198

test_prior2							94.12 196		87.67 133	92.63 97	96.39 94	86.62 40		91.50 105	98.67 40

旧先验2							93.36 238		71.25 398	94.37 51			97.13 255	86.74 164

新几何2							93.11 253

旧先验1					96.79 79	81.81 174		95.67 179			96.81 75	86.69 39			97.66 88	96.97 142

无先验							93.28 246	96.26 126	73.95 378				99.05 59	80.56 262		96.59 161

原ACMM2							92.94 260

test222					96.55 88	81.70 176	92.22 284	95.01 221	68.36 406	90.20 143	96.14 104	80.26 129			97.80 82	96.05 188

testdata2													98.75 105	78.30 289

segment_acmp												87.16 36

testdata1							92.15 286		87.94 120

plane_prior7					94.70 183	82.74 151

plane_prior6					94.52 195	82.75 149						74.23 205

plane_prior5								96.22 131					98.12 162	88.15 143	89.99 232	94.63 240

plane_prior4											94.86 158

plane_prior3						82.75 149			90.26 39	86.91 200

plane_prior2							95.85 83		90.81 20

plane_prior1					94.59 189

plane_prior						82.73 152	95.21 125		89.66 60						89.88 237

n2								0.00 445

nn								0.00 445

door-mid								85.49 402

test11								96.57 102

door								85.33 404

HQP5-MVS						81.56 178

HQP-NCC					94.17 216		94.39 180		88.81 88	85.43 246

ACMP_Plane					94.17 216		94.39 180		88.81 88	85.43 246

BP-MVS														87.11 161

HQP4-MVS										85.43 246			97.96 183			94.51 250

HQP3-MVS								96.04 148							89.77 241

HQP2-MVS												73.83 215

NP-MVS					94.37 206	82.42 161					93.98 194

MDTV_nov1_ep13_2view						55.91 428	87.62 382		73.32 384	84.59 268		70.33 259		74.65 327		95.50 208

MDTV_nov1_ep13			83.56 304		91.69 306	69.93 386	87.75 379	91.54 337	78.60 330	84.86 262	88.90 354	69.54 270	96.03 318	70.25 354	88.93 254

ACMMP++_ref															87.47 277

ACMMP++															88.01 269

Test By Simon												80.02 131

High-resolution multi-view benchmark