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 71					99.61 4	96.03 22	99.06 9	99.07 5

No_MVS				96.52 1	97.78 54	90.86 1		96.85 71					99.61 4	96.03 22	99.06 9	99.07 5

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 60	92.59 2	98.94 83	92.25 81	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 60	91.75 10	94.02 61	96.83 72	88.12 24	99.55 16	93.41 56	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	94.37 252	95.08 1	94.68 47	97.72 33	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	85.90 173	97.67 3	98.10 10	88.41 20	99.56 12	94.66 40	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 92	91.37 102	95.55 7	95.63 131	88.73 6	97.07 18	96.77 82	90.84 18	84.02 286	96.62 85	75.95 179	99.34 37	87.77 148	97.68 86	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 60	92.09 7	95.32 39	97.08 60	89.49 15	99.33 40	95.10 36	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	93.01 293	92.58 4	94.22 52	97.20 54	80.56 124	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	88.28 107	95.30 40	97.67 35	85.90 50	99.54 20	93.91 48	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 78	97.14 11	97.91 26	91.64 7	99.62 2	94.61 41	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	87.76 129	95.71 34	97.70 34	88.28 23	99.35 36	93.89 49	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 48	87.13 142	92.51 100	96.30 94	89.24 17	99.34 37	93.46 53	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 64	92.34 5	93.94 62	96.58 87	87.74 27	99.44 29	92.83 65	98.40 54	98.62 22

DPM-MVS		92.58 88	91.74 98	95.08 15	96.19 99	89.31 5	92.66 267	96.56 102	83.44 233	91.68 123	95.04 150	86.60 42	98.99 73	85.60 178	97.92 77	96.93 144

ZNCC-MVS		94.47 25	94.28 36	95.03 16	98.52 15	86.96 20	96.85 28	97.32 28	88.24 108	93.15 77	97.04 63	86.17 47	99.62 2	92.40 75	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 29	99.08 7	98.99 9

MTAPA		94.42 30	94.22 39	95.00 18	98.42 21	86.95 21	94.36 185	96.97 57	91.07 14	93.14 78	97.56 37	84.30 74	99.56 12	93.43 54	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 77	89.90 12	99.30 43	94.70 39	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 98	93.58 69	97.27 48	85.22 58	99.54 20	92.21 82	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 83	96.20 26	98.10 10	89.39 16	99.34 37	95.88 24	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 95	93.53 72	97.26 50	85.04 62	99.54 20	92.35 78	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	88.24 108	93.26 74	96.83 72	85.48 55	99.59 8	91.43 106	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 95	93.65 67	97.21 52	86.10 48	99.49 26	92.35 78	98.77 28	98.30 50

sasdasda		93.27 72	92.75 82	94.85 25	95.70 126	87.66 12	96.33 39	96.41 112	90.00 42	94.09 57	94.60 170	82.33 102	98.62 118	92.40 75	92.86 192	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	86.26 165	92.83 87	97.87 28	85.57 54	99.56 12	94.37 44	98.92 17	98.34 43
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
canonicalmvs		93.27 72	92.75 82	94.85 25	95.70 126	87.66 12	96.33 39	96.41 112	90.00 42	94.09 57	94.60 170	82.33 102	98.62 118	92.40 75	92.86 192	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 85	97.16 58	85.02 63	99.49 26	91.99 92	98.56 50	98.47 33

X-MVStestdata		88.31 190	86.13 238	94.85 25	98.54 13	86.60 34	96.93 22	97.19 37	90.66 26	92.85 85	23.41 432	85.02 63	99.49 26	91.99 92	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 40	88.98 19	99.40 30	94.12 45	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 17	92.59 2	99.61 4	95.64 27	99.02 12	98.86 11

alignmvs		93.08 80	92.50 88	94.81 32	95.62 132	87.61 15	95.99 71	96.07 144	89.77 55	94.12 56	94.87 156	80.56 124	98.66 111	92.42 74	93.10 188	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 15	92.31 4	99.58 10	95.66 25	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 68	89.40 66	92.81 88	96.97 65	85.37 57	99.24 46	90.87 115	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 56	89.04 81	91.98 110	97.19 55	85.43 56	99.56 12	92.06 91	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 63	85.68 179	95.05 45	97.18 56	87.31 35	99.07 56	91.90 98	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	88.53 100	92.73 93	97.23 51	85.20 59	99.32 41	92.15 85	98.83 22	98.25 62

PGM-MVS		93.96 49	93.72 61	94.68 38	98.43 20	86.22 47	95.30 114	97.78 1	87.45 136	93.26 74	97.33 46	84.62 71	99.51 24	90.75 117	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 88	90.27 36	97.04 15	98.05 19	91.47 8	99.55 16	95.62 29	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 66	88.70 93	91.83 119	97.17 57	83.96 78	99.55 16	91.44 105	98.64 45	98.43 38

PHI-MVS		93.89 51	93.65 65	94.62 41	96.84 78	86.43 39	96.69 32	97.49 6	85.15 192	93.56 71	96.28 95	85.60 53	99.31 42	92.45 72	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 97	88.14 113	96.10 27	96.96 66	89.09 18	98.94 83	94.48 42	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 74	94.55 43	95.65 129	85.73 65	94.94 140	96.69 93	91.89 9	90.69 135	95.88 115	81.99 114	99.54 20	93.14 60	97.95 76	98.39 40

train_agg		93.44 65	93.08 75	94.52 44	97.53 61	86.49 37	94.07 202	96.78 80	81.86 274	92.77 90	96.20 98	87.63 29	99.12 54	92.14 86	98.69 35	97.94 82

CDPH-MVS		92.83 84	92.30 90	94.44 45	97.79 52	86.11 49	94.06 204	96.66 94	80.09 305	92.77 90	96.63 84	86.62 40	99.04 60	87.40 153	98.66 41	98.17 67

3Dnovator	86.66 5	91.73 102	90.82 114	94.44 45	94.59 188	86.37 41	97.18 12	97.02 54	89.20 75	84.31 281	96.66 80	73.74 216	99.17 50	86.74 163	97.96 75	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 67	88.20 111	94.33 51	97.40 43	84.75 70	99.03 61	93.35 57	97.99 74	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 52	86.90 150	92.62 97	96.80 76	84.85 69	99.17 50	92.43 73	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 69	94.41 49	96.59 85	86.78 26	94.40 177	93.93 269	89.77 55	94.21 53	95.59 128	87.35 34	98.61 120	92.72 68	96.15 123	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 33	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 33	98.25 60	98.30 50

test12				94.34 52	97.13 73	86.15 48		96.29 120		91.04 132		85.08 61	99.01 66		98.13 67	97.86 89

ACMMP		93.24 74	92.88 80	94.30 53	98.09 38	85.33 72	96.86 27	97.45 14	88.33 104	90.15 145	97.03 64	81.44 118	99.51 24	90.85 116	95.74 128	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 32	98.15 65	98.33 45

DeepC-MVS	88.79 3	93.31 71	92.99 78	94.26 55	96.07 109	85.83 61	94.89 143	96.99 55	89.02 84	89.56 150	97.37 45	82.51 99	99.38 31	92.20 83	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 81	92.63 85	94.23 56	95.62 132	85.92 57	96.08 61	96.33 118	89.86 46	93.89 64	94.66 167	82.11 109	98.50 126	92.33 80	92.82 195	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 81	98.43 38

EPNet		91.79 99	91.02 110	94.10 58	90.10 358	85.25 73	96.03 68	92.05 319	92.83 3	87.39 193	95.78 120	79.39 140	99.01 66	88.13 144	97.48 89	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 80	97.96 81

DELS-MVS		93.43 69	93.25 72	93.97 60	95.42 140	85.04 76	93.06 255	97.13 47	90.74 23	91.84 117	95.09 149	86.32 45	99.21 48	91.22 107	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 97	91.28 104	93.96 61	98.33 27	85.92 57	94.66 160	96.66 94	82.69 253	90.03 147	95.82 118	82.30 104	99.03 61	84.57 190	96.48 117	96.91 146

HPM-MVS_fast		93.40 70	93.22 73	93.94 62	98.36 25	84.83 80	97.15 13	96.80 79	85.77 176	92.47 101	97.13 59	82.38 100	99.07 56	90.51 120	98.40 54	97.92 85

test_fmvsmconf0.1_n		94.20 38	94.31 34	93.88 63	92.46 277	84.80 81	96.18 51	96.82 76	89.29 72	95.68 35	98.11 8	85.10 60	98.99 73	97.38 8	97.75 85	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 50	90.42 29	96.95 17	97.27 48	89.53 14	96.91 270	94.38 43	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 70	93.84 65	96.99 75	84.84 79	93.24 248	97.24 34	88.76 90	91.60 124	95.85 116	86.07 49	98.66 111	91.91 96	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 83	87.46 134	93.75 65	97.43 41	84.24 75	99.01 66	92.73 66	97.80 81	97.88 87

test_prior				93.82 66	97.29 70	84.49 91		96.88 69					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 70	86.96 146	93.92 63	97.47 39	83.88 79	98.96 80	92.71 69	97.87 78	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	96.43 110	86.56 157	96.84 19	97.81 31	87.56 32	98.77 103	97.14 10	96.82 107	97.16 128

CSCG		93.23 75	93.05 76	93.76 70	98.04 40	84.07 104	96.22 48	97.37 21	84.15 215	90.05 146	95.66 125	87.77 26	99.15 53	89.91 125	98.27 58	98.07 74

GDP-MVS		92.04 95	91.46 101	93.75 71	94.55 193	84.69 84	95.60 105	96.56 102	87.83 126	93.07 81	95.89 114	73.44 220	98.65 113	90.22 123	96.03 125	97.91 86

BP-MVS1		92.48 90	92.07 93	93.72 72	94.50 196	84.39 99	95.90 79	94.30 255	90.39 30	92.67 95	95.94 111	74.46 200	98.65 113	93.14 60	97.35 93	98.13 69

test_fmvsmconf0.01_n		93.19 76	93.02 77	93.71 73	89.25 371	84.42 98	96.06 65	96.29 120	89.06 79	94.68 47	98.13 4	79.22 142	98.98 77	97.22 9	97.24 95	97.74 97

UA-Net		92.83 84	92.54 87	93.68 74	96.10 106	84.71 83	95.66 97	96.39 114	91.92 8	93.22 76	96.49 90	83.16 88	98.87 90	84.47 192	95.47 135	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	96.28 123	86.31 163	96.75 21	97.86 29	87.40 33	98.74 106	97.07 12	97.02 100	97.07 131

QAPM		89.51 153	88.15 177	93.59 76	94.92 167	84.58 86	96.82 29	96.70 92	78.43 332	83.41 302	96.19 101	73.18 224	99.30 43	77.11 301	96.54 114	96.89 147

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 27	86.28 46	98.71 109	97.11 11	98.08 71	97.17 124

casdiffmvs_mvg		92.96 83	92.83 81	93.35 78	94.59 188	83.40 125	95.00 137	96.34 117	90.30 34	92.05 108	96.05 106	83.43 82	98.15 160	92.07 88	95.67 129	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 87	88.02 116	96.23 25	97.84 30	83.36 86	98.83 97	97.49 5	97.34 94	97.25 119

EI-MVSNet-Vis-set		93.01 82	92.92 79	93.29 80	95.01 159	83.51 122	94.48 169	95.77 169	90.87 17	92.52 99	96.67 79	84.50 72	99.00 71	91.99 92	94.44 162	97.36 114

Vis-MVSNet		91.75 101	91.23 105	93.29 80	95.32 143	83.78 112	96.14 56	95.98 151	89.89 44	90.45 137	96.58 87	75.09 191	98.31 151	84.75 188	96.90 103	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	96.52 105	89.82 48	95.56 37	95.51 130	84.50 72	98.79 101	94.83 38	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 65	92.14 6	92.90 83	95.77 121	85.02 63	98.33 148	93.03 62	98.62 46	98.13 69

VNet		92.24 94	91.91 95	93.24 83	96.59 85	83.43 123	94.84 148	96.44 109	89.19 76	94.08 60	95.90 113	77.85 161	98.17 158	88.90 135	93.38 181	98.13 69

VDD-MVS		90.74 120	89.92 132	93.20 85	96.27 97	83.02 142	95.73 91	93.86 273	88.42 103	92.53 98	96.84 71	62.09 335	98.64 115	90.95 113	92.62 197	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 62	91.71 12	93.50 73	96.21 97	85.61 52	98.24 153	93.64 51	98.17 63	98.19 65

nrg030		91.08 114	90.39 118	93.17 86	93.07 259	86.91 22	96.41 37	96.26 125	88.30 106	88.37 171	94.85 159	82.19 108	97.64 201	91.09 108	82.95 317	94.96 227

MVSMamba_PlusPlus		93.44 65	93.54 67	93.14 88	96.58 87	83.05 140	96.06 65	96.50 107	84.42 212	94.09 57	95.56 129	85.01 66	98.69 110	94.96 37	98.66 41	97.67 101

EI-MVSNet-UG-set		92.74 86	92.62 86	93.12 89	94.86 172	83.20 131	94.40 177	95.74 172	90.71 25	92.05 108	96.60 86	84.00 77	98.99 73	91.55 103	93.63 172	97.17 124

test_fmvsmvis_n_1920		93.44 65	93.55 66	93.10 90	93.67 241	84.26 101	95.83 85	96.14 135	89.00 85	92.43 102	97.50 38	83.37 85	98.72 107	96.61 19	97.44 90	96.32 169

新几何1				93.10 90	97.30 69	84.35 100		95.56 186	71.09 398	91.26 130	96.24 96	82.87 95	98.86 92	79.19 280	98.10 68	96.07 184

OMC-MVS		91.23 110	90.62 117	93.08 92	96.27 97	84.07 104	93.52 230	95.93 155	86.95 147	89.51 151	96.13 104	78.50 152	98.35 145	85.84 176	92.90 191	96.83 151

OpenMVS	83.78 11	88.74 179	87.29 196	93.08 92	92.70 272	85.39 71	96.57 35	96.43 110	78.74 327	80.85 334	96.07 105	69.64 267	99.01 66	78.01 292	96.65 112	94.83 234

MAR-MVS		90.30 131	89.37 143	93.07 94	96.61 84	84.48 92	95.68 94	95.67 178	82.36 258	87.85 180	92.85 231	76.63 172	98.80 99	80.01 268	96.68 111	95.91 190
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		90.92 115	90.21 121	93.03 95	93.86 231	83.88 109	92.81 264	93.86 273	79.84 308	91.76 120	94.29 180	77.92 158	98.04 176	90.48 121	97.11 96	97.17 124

Effi-MVS+		91.59 105	91.11 107	93.01 96	94.35 209	83.39 126	94.60 162	95.10 216	87.10 143	90.57 136	93.10 226	81.43 119	98.07 174	89.29 131	94.48 160	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	96.10 141	87.27 139	95.98 31	98.05 19	83.07 92	98.45 136	96.68 18	95.51 132	96.88 148

MVS_111021_LR		92.47 91	92.29 91	92.98 98	95.99 115	84.43 96	93.08 253	96.09 142	88.20 111	91.12 131	95.72 124	81.33 120	97.76 191	91.74 100	97.37 92	96.75 153

fmvsm_s_conf0.1_n_a		93.19 76	93.26 71	92.97 99	92.49 275	83.62 118	96.02 69	95.72 175	86.78 152	96.04 29	98.19 1	82.30 104	98.43 140	96.38 20	95.42 138	96.86 149

ETV-MVS		92.74 86	92.66 84	92.97 99	95.20 151	84.04 106	95.07 133	96.51 106	90.73 24	92.96 82	91.19 291	84.06 76	98.34 146	91.72 101	96.54 114	96.54 164

LFMVS		90.08 136	89.13 149	92.95 101	96.71 80	82.32 165	96.08 61	89.91 373	86.79 151	92.15 107	96.81 74	62.60 333	98.34 146	87.18 157	93.90 168	98.19 65

UGNet		89.95 141	88.95 153	92.95 101	94.51 195	83.31 127	95.70 93	95.23 209	89.37 67	87.58 187	93.94 195	64.00 323	98.78 102	83.92 199	96.31 119	96.74 154
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		90.80 118	90.10 125	92.90 103	93.04 262	83.53 121	93.08 253	94.15 262	80.22 302	91.41 127	94.91 153	76.87 166	97.93 185	90.28 122	96.90 103	97.24 120
jason: jason.
DP-MVS		87.25 230	85.36 267	92.90 103	97.65 58	83.24 129	94.81 150	92.00 321	74.99 366	81.92 323	95.00 151	72.66 229	99.05 58	66.92 378	92.33 202	96.40 166

fmvsm_s_conf0.5_n		93.76 55	94.06 49	92.86 105	95.62 132	83.17 132	96.14 56	96.12 139	88.13 114	95.82 33	98.04 22	83.43 82	98.48 128	96.97 16	96.23 120	96.92 145

fmvsm_s_conf0.1_n		93.46 63	93.66 64	92.85 106	93.75 237	83.13 134	96.02 69	95.74 172	87.68 131	95.89 32	98.17 2	82.78 96	98.46 132	96.71 17	96.17 122	96.98 140

CANet_DTU		90.26 133	89.41 142	92.81 107	93.46 248	83.01 143	93.48 231	94.47 248	89.43 65	87.76 185	94.23 185	70.54 256	99.03 61	84.97 183	96.39 118	96.38 167

MVSFormer		91.68 104	91.30 103	92.80 108	93.86 231	83.88 109	95.96 74	95.90 159	84.66 208	91.76 120	94.91 153	77.92 158	97.30 237	89.64 127	97.11 96	97.24 120

PVSNet_Blended_VisFu		91.38 107	90.91 112	92.80 108	96.39 94	83.17 132	94.87 145	96.66 94	83.29 238	89.27 157	94.46 175	80.29 127	99.17 50	87.57 151	95.37 139	96.05 187

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 70	97.52 7	97.61 36	83.25 87	98.88 89	97.05 14	98.22 62	97.43 113

VDDNet		89.56 152	88.49 168	92.76 110	95.07 157	82.09 167	96.30 41	93.19 288	81.05 296	91.88 115	96.86 70	61.16 351	98.33 148	88.43 141	92.49 201	97.84 91

h-mvs33		90.80 118	90.15 124	92.75 112	96.01 111	82.66 156	95.43 108	95.53 190	89.80 51	93.08 79	95.64 126	75.77 180	99.00 71	92.07 88	78.05 374	96.60 159

casdiffmvs		92.51 89	92.43 89	92.74 113	94.41 204	81.98 170	94.54 166	96.23 129	89.57 61	91.96 112	96.17 102	82.58 98	98.01 178	90.95 113	95.45 137	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		90.69 122	90.02 130	92.71 114	95.72 124	82.41 163	94.11 197	95.12 214	85.63 180	91.49 125	94.70 163	74.75 195	98.42 141	86.13 171	92.53 199	97.31 115

DCV-MVSNet		90.69 122	90.02 130	92.71 114	95.72 124	82.41 163	94.11 197	95.12 214	85.63 180	91.49 125	94.70 163	74.75 195	98.42 141	86.13 171	92.53 199	97.31 115

PCF-MVS	84.11 10	87.74 205	86.08 242	92.70 116	94.02 222	84.43 96	89.27 353	95.87 163	73.62 380	84.43 273	94.33 177	78.48 153	98.86 92	70.27 352	94.45 161	94.81 235
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
baseline		92.39 93	92.29 91	92.69 117	94.46 199	81.77 175	94.14 194	96.27 124	89.22 74	91.88 115	96.00 107	82.35 101	97.99 180	91.05 109	95.27 143	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 69	96.96 66	84.87 68	97.76 191	92.19 84	98.66 41	96.76 152

EC-MVSNet		93.44 65	93.71 62	92.63 119	95.21 150	82.43 160	97.27 9	96.71 91	90.57 28	92.88 84	95.80 119	83.16 88	98.16 159	93.68 50	98.14 66	97.31 115

ab-mvs		89.41 158	88.35 170	92.60 120	95.15 155	82.65 157	92.20 284	95.60 185	83.97 219	88.55 167	93.70 208	74.16 208	98.21 157	82.46 221	89.37 245	96.94 143

LS3D		87.89 200	86.32 231	92.59 121	96.07 109	82.92 146	95.23 121	94.92 228	75.66 358	82.89 309	95.98 109	72.48 232	99.21 48	68.43 366	95.23 144	95.64 203

Anonymous20240529		88.09 196	86.59 220	92.58 122	96.53 90	81.92 173	95.99 71	95.84 165	74.11 375	89.06 161	95.21 143	61.44 343	98.81 98	83.67 204	87.47 276	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 88	97.78 95

CPTT-MVS		91.99 96	91.80 96	92.55 124	98.24 31	81.98 170	96.76 30	96.49 108	81.89 273	90.24 140	96.44 92	78.59 150	98.61 120	89.68 126	97.85 79	97.06 132

114514_t		89.51 153	88.50 166	92.54 125	98.11 36	81.99 169	95.16 129	96.36 116	70.19 402	85.81 227	95.25 140	76.70 170	98.63 117	82.07 231	96.86 106	97.00 139

PAPM_NR		91.22 111	90.78 115	92.52 126	97.60 59	81.46 184	94.37 183	96.24 128	86.39 162	87.41 190	94.80 161	82.06 112	98.48 128	82.80 216	95.37 139	97.61 104

DeepPCF-MVS	89.96 1	94.20 38	94.77 22	92.49 127	96.52 91	80.00 232	94.00 210	97.08 51	90.05 40	95.65 36	97.29 47	89.66 13	98.97 78	93.95 47	98.71 32	98.50 27

IS-MVSNet		91.43 106	91.09 109	92.46 128	95.87 120	81.38 187	96.95 19	93.69 280	89.72 57	89.50 153	95.98 109	78.57 151	97.77 190	83.02 210	96.50 116	98.22 64

API-MVS		90.66 124	90.07 126	92.45 129	96.36 95	84.57 87	96.06 65	95.22 211	82.39 256	89.13 158	94.27 183	80.32 126	98.46 132	80.16 267	96.71 110	94.33 258

xiu_mvs_v1_base_debu		90.64 125	90.05 127	92.40 130	93.97 228	84.46 93	93.32 239	95.46 193	85.17 189	92.25 103	94.03 187	70.59 252	98.57 123	90.97 110	94.67 152	94.18 261

xiu_mvs_v1_base		90.64 125	90.05 127	92.40 130	93.97 228	84.46 93	93.32 239	95.46 193	85.17 189	92.25 103	94.03 187	70.59 252	98.57 123	90.97 110	94.67 152	94.18 261

xiu_mvs_v1_base_debi		90.64 125	90.05 127	92.40 130	93.97 228	84.46 93	93.32 239	95.46 193	85.17 189	92.25 103	94.03 187	70.59 252	98.57 123	90.97 110	94.67 152	94.18 261

fmvsm_s_conf0.5_n_2		93.47 62	93.83 53	92.39 133	95.36 141	81.19 193	95.20 126	96.56 102	90.37 31	97.13 12	98.03 23	77.47 162	98.96 80	97.79 3	96.58 113	97.03 135

fmvsm_s_conf0.1_n_2		93.16 78	93.42 68	92.37 134	94.62 186	81.13 195	95.23 121	95.89 161	90.30 34	96.74 22	98.02 24	76.14 174	98.95 82	97.64 4	96.21 121	97.03 135

AdaColmap		89.89 144	89.07 150	92.37 134	97.41 65	83.03 141	94.42 176	95.92 156	82.81 250	86.34 216	94.65 168	73.89 212	99.02 64	80.69 258	95.51 132	95.05 222

CNLPA		89.07 169	87.98 180	92.34 136	96.87 77	84.78 82	94.08 201	93.24 286	81.41 287	84.46 271	95.13 148	75.57 187	96.62 281	77.21 299	93.84 170	95.61 206

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 57	89.60 60	96.85 18	97.77 32	83.08 91	98.92 86	97.49 5	96.78 108	97.13 129

ET-MVSNet_ETH3D		87.51 218	85.91 250	92.32 138	93.70 240	83.93 107	92.33 279	90.94 353	84.16 214	72.09 398	92.52 244	69.90 262	95.85 328	89.20 132	88.36 263	97.17 124

Anonymous202405211		87.68 206	86.13 238	92.31 139	96.66 82	80.74 209	94.87 145	91.49 338	80.47 301	89.46 154	95.44 132	54.72 387	98.23 154	82.19 227	89.89 235	97.97 80

CHOSEN 1792x2688		88.84 175	87.69 186	92.30 140	96.14 100	81.42 186	90.01 340	95.86 164	74.52 371	87.41 190	93.94 195	75.46 188	98.36 143	80.36 263	95.53 131	97.12 130

HY-MVS	83.01 12	89.03 171	87.94 182	92.29 141	94.86 172	82.77 148	92.08 289	94.49 247	81.52 286	86.93 197	92.79 237	78.32 155	98.23 154	79.93 269	90.55 223	95.88 192

CDS-MVSNet		89.45 156	88.51 165	92.29 141	93.62 243	83.61 120	93.01 256	94.68 244	81.95 268	87.82 183	93.24 220	78.69 148	96.99 264	80.34 264	93.23 186	96.28 172
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		90.02 138	89.27 148	92.29 141	95.78 122	80.95 202	92.68 266	96.22 130	81.91 270	86.66 207	93.75 207	82.23 106	98.44 138	79.40 279	94.79 150	97.48 110

mvsmamba		90.33 130	89.69 135	92.25 144	95.17 152	81.64 177	95.27 119	93.36 285	84.88 199	89.51 151	94.27 183	69.29 276	97.42 223	89.34 130	96.12 124	97.68 100

PLC	84.53 7	89.06 170	88.03 179	92.15 145	97.27 71	82.69 155	94.29 186	95.44 198	79.71 310	84.01 287	94.18 186	76.68 171	98.75 104	77.28 298	93.41 180	95.02 223
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPP-MVSNet		91.70 103	91.56 100	92.13 146	95.88 118	80.50 215	97.33 7	95.25 208	86.15 168	89.76 149	95.60 127	83.42 84	98.32 150	87.37 155	93.25 185	97.56 108

patch_mono-2		93.74 56	94.32 32	92.01 147	97.54 60	78.37 270	93.40 235	97.19 37	88.02 116	94.99 46	97.21 52	88.35 21	98.44 138	94.07 46	98.09 69	99.23 1

原ACMM1				92.01 147	97.34 67	81.05 198		96.81 78	78.89 321	90.45 137	95.92 112	82.65 97	98.84 96	80.68 259	98.26 59	96.14 178

UniMVSNet (Re)		89.80 146	89.07 150	92.01 147	93.60 244	84.52 90	94.78 152	97.47 11	89.26 73	86.44 213	92.32 250	82.10 110	97.39 234	84.81 187	80.84 351	94.12 265

MG-MVS		91.77 100	91.70 99	92.00 150	97.08 74	80.03 230	93.60 228	95.18 212	87.85 125	90.89 133	96.47 91	82.06 112	98.36 143	85.07 182	97.04 99	97.62 103

EIA-MVS		91.95 97	91.94 94	91.98 151	95.16 153	80.01 231	95.36 109	96.73 88	88.44 101	89.34 155	92.16 255	83.82 80	98.45 136	89.35 129	97.06 98	97.48 110

PVSNet_Blended		90.73 121	90.32 120	91.98 151	96.12 102	81.25 189	92.55 271	96.83 74	82.04 266	89.10 159	92.56 243	81.04 122	98.85 94	86.72 165	95.91 126	95.84 194

PS-MVSNAJ		91.18 112	90.92 111	91.96 153	95.26 148	82.60 159	92.09 288	95.70 176	86.27 164	91.84 117	92.46 245	79.70 135	98.99 73	89.08 133	95.86 127	94.29 259

TAMVS		89.21 164	88.29 174	91.96 153	93.71 238	82.62 158	93.30 243	94.19 260	82.22 261	87.78 184	93.94 195	78.83 145	96.95 267	77.70 294	92.98 190	96.32 169

SDMVSNet		90.19 134	89.61 137	91.93 155	96.00 112	83.09 138	92.89 261	95.98 151	88.73 91	86.85 203	95.20 144	72.09 236	97.08 256	88.90 135	89.85 237	95.63 204

FA-MVS(test-final)		89.66 148	88.91 155	91.93 155	94.57 191	80.27 219	91.36 304	94.74 241	84.87 200	89.82 148	92.61 242	74.72 198	98.47 131	83.97 198	93.53 175	97.04 134

MVS_Test		91.31 109	91.11 107	91.93 155	94.37 205	80.14 223	93.46 233	95.80 167	86.46 160	91.35 129	93.77 205	82.21 107	98.09 171	87.57 151	94.95 147	97.55 109

NR-MVSNet		88.58 185	87.47 192	91.93 155	93.04 262	84.16 103	94.77 153	96.25 127	89.05 80	80.04 347	93.29 218	79.02 144	97.05 261	81.71 242	80.05 361	94.59 242

HyFIR lowres test		88.09 196	86.81 208	91.93 155	96.00 112	80.63 211	90.01 340	95.79 168	73.42 382	87.68 186	92.10 261	73.86 213	97.96 182	80.75 257	91.70 206	97.19 123

GeoE		90.05 137	89.43 141	91.90 160	95.16 153	80.37 218	95.80 86	94.65 245	83.90 220	87.55 189	94.75 162	78.18 156	97.62 203	81.28 247	93.63 172	97.71 99

thisisatest0530		88.67 180	87.61 188	91.86 161	94.87 171	80.07 226	94.63 161	89.90 374	84.00 218	88.46 169	93.78 204	66.88 300	98.46 132	83.30 206	92.65 196	97.06 132

xiu_mvs_v2_base		91.13 113	90.89 113	91.86 161	94.97 163	82.42 161	92.24 282	95.64 183	86.11 172	91.74 122	93.14 224	79.67 138	98.89 88	89.06 134	95.46 136	94.28 260

DU-MVS		89.34 163	88.50 166	91.85 163	93.04 262	83.72 113	94.47 172	96.59 99	89.50 62	86.46 210	93.29 218	77.25 164	97.23 246	84.92 184	81.02 347	94.59 242

OPM-MVS		90.12 135	89.56 138	91.82 164	93.14 255	83.90 108	94.16 193	95.74 172	88.96 86	87.86 179	95.43 134	72.48 232	97.91 186	88.10 146	90.18 230	93.65 296
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		90.60 128	90.19 122	91.82 164	94.70 182	82.73 152	95.85 83	96.22 130	90.81 19	86.91 199	94.86 157	74.23 204	98.12 161	88.15 142	89.99 231	94.63 239

UniMVSNet_NR-MVSNet		89.92 143	89.29 146	91.81 166	93.39 250	83.72 113	94.43 175	97.12 48	89.80 51	86.46 210	93.32 215	83.16 88	97.23 246	84.92 184	81.02 347	94.49 252

diffmvs		91.37 108	91.23 105	91.77 167	93.09 258	80.27 219	92.36 276	95.52 191	87.03 145	91.40 128	94.93 152	80.08 129	97.44 221	92.13 87	94.56 157	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		88.42 186	87.33 195	91.72 168	94.92 167	80.98 200	92.97 258	94.54 246	78.16 338	83.82 290	93.88 200	78.78 147	97.91 186	79.45 275	89.41 244	96.26 173

Fast-Effi-MVS+		89.41 158	88.64 161	91.71 169	94.74 177	80.81 207	93.54 229	95.10 216	83.11 242	86.82 205	90.67 314	79.74 134	97.75 194	80.51 262	93.55 174	96.57 162

WTY-MVS		89.60 150	88.92 154	91.67 170	95.47 139	81.15 194	92.38 275	94.78 239	83.11 242	89.06 161	94.32 178	78.67 149	96.61 284	81.57 243	90.89 219	97.24 120

TAPA-MVS	84.62 6	88.16 194	87.01 204	91.62 171	96.64 83	80.65 210	94.39 179	96.21 133	76.38 351	86.19 220	95.44 132	79.75 133	98.08 173	62.75 395	95.29 141	96.13 179
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VPA-MVSNet		89.62 149	88.96 152	91.60 172	93.86 231	82.89 147	95.46 107	97.33 26	87.91 120	88.43 170	93.31 216	74.17 207	97.40 231	87.32 156	82.86 322	94.52 247

FE-MVS		87.40 223	86.02 244	91.57 173	94.56 192	79.69 240	90.27 327	93.72 279	80.57 299	88.80 164	91.62 280	65.32 315	98.59 122	74.97 323	94.33 164	96.44 165

XVG-OURS		89.40 160	88.70 160	91.52 174	94.06 220	81.46 184	91.27 308	96.07 144	86.14 169	88.89 163	95.77 121	68.73 285	97.26 243	87.39 154	89.96 233	95.83 195

hse-mvs2		89.88 145	89.34 144	91.51 175	94.83 174	81.12 196	93.94 213	93.91 272	89.80 51	93.08 79	93.60 209	75.77 180	97.66 198	92.07 88	77.07 381	95.74 199

TranMVSNet+NR-MVSNet		88.84 175	87.95 181	91.49 176	92.68 273	83.01 143	94.92 142	96.31 119	89.88 45	85.53 236	93.85 202	76.63 172	96.96 266	81.91 235	79.87 364	94.50 250

AUN-MVS		87.78 204	86.54 223	91.48 177	94.82 175	81.05 198	93.91 217	93.93 269	83.00 245	86.93 197	93.53 210	69.50 270	97.67 196	86.14 169	77.12 380	95.73 201

XVG-OURS-SEG-HR		89.95 141	89.45 139	91.47 178	94.00 226	81.21 192	91.87 292	96.06 146	85.78 175	88.55 167	95.73 123	74.67 199	97.27 241	88.71 138	89.64 242	95.91 190

MVS		87.44 221	86.10 241	91.44 179	92.61 274	83.62 118	92.63 268	95.66 180	67.26 407	81.47 326	92.15 256	77.95 157	98.22 156	79.71 271	95.48 134	92.47 338

F-COLMAP		87.95 199	86.80 209	91.40 180	96.35 96	80.88 205	94.73 155	95.45 196	79.65 311	82.04 321	94.61 169	71.13 243	98.50 126	76.24 311	91.05 217	94.80 236

dcpmvs_2		93.49 61	94.19 43	91.38 181	97.69 57	76.78 303	94.25 188	96.29 120	88.33 104	94.46 49	96.88 69	88.07 25	98.64 115	93.62 52	98.09 69	98.73 18

thisisatest0515		87.33 226	85.99 245	91.37 182	93.49 246	79.55 241	90.63 322	89.56 382	80.17 303	87.56 188	90.86 304	67.07 297	98.28 152	81.50 244	93.02 189	96.29 171

HQP-MVS		89.80 146	89.28 147	91.34 183	94.17 215	81.56 178	94.39 179	96.04 147	88.81 87	85.43 245	93.97 194	73.83 214	97.96 182	87.11 160	89.77 240	94.50 250

fmvsm_s_conf0.5_n_7		93.15 79	93.76 59	91.31 184	94.42 203	79.48 243	94.52 167	97.14 46	89.33 69	94.17 55	98.09 14	81.83 116	97.49 213	96.33 21	98.02 73	96.95 142

RRT-MVS		90.85 117	90.70 116	91.30 185	94.25 211	76.83 302	94.85 147	96.13 138	89.04 81	90.23 141	94.88 155	70.15 261	98.72 107	91.86 99	94.88 148	98.34 43

FMVSNet3		87.40 223	86.11 240	91.30 185	93.79 236	83.64 117	94.20 192	94.81 237	83.89 221	84.37 274	91.87 271	68.45 288	96.56 289	78.23 289	85.36 293	93.70 295

FMVSNet2		87.19 236	85.82 253	91.30 185	94.01 223	83.67 115	94.79 151	94.94 223	83.57 228	83.88 289	92.05 265	66.59 305	96.51 293	77.56 296	85.01 296	93.73 293

RPMNet		83.95 312	81.53 323	91.21 188	90.58 349	79.34 249	85.24 398	96.76 83	71.44 396	85.55 234	82.97 405	70.87 248	98.91 87	61.01 399	89.36 246	95.40 210

IB-MVS	80.51 15	85.24 290	83.26 307	91.19 189	92.13 286	79.86 236	91.75 295	91.29 343	83.28 239	80.66 337	88.49 360	61.28 345	98.46 132	80.99 253	79.46 368	95.25 216
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		89.47 155	88.90 156	91.18 190	94.22 213	82.07 168	92.13 286	96.09 142	87.90 121	85.37 251	92.45 246	74.38 202	97.56 207	87.15 158	90.43 225	93.93 274
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		89.45 156	88.90 156	91.12 191	94.47 197	81.49 182	95.30 114	96.14 135	86.73 154	85.45 242	95.16 146	69.89 263	98.10 163	87.70 149	89.23 249	93.77 289

LGP-MVS_train				91.12 191	94.47 197	81.49 182		96.14 135	86.73 154	85.45 242	95.16 146	69.89 263	98.10 163	87.70 149	89.23 249	93.77 289

ACMM	84.12 9	89.14 165	88.48 169	91.12 191	94.65 185	81.22 191	95.31 112	96.12 139	85.31 188	85.92 225	94.34 176	70.19 260	98.06 175	85.65 177	88.86 254	94.08 269
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tttt0517		88.61 182	87.78 185	91.11 194	94.96 164	77.81 285	95.35 110	89.69 377	85.09 194	88.05 177	94.59 172	66.93 298	98.48 128	83.27 207	92.13 204	97.03 135

GBi-Net		87.26 228	85.98 246	91.08 195	94.01 223	83.10 135	95.14 130	94.94 223	83.57 228	84.37 274	91.64 276	66.59 305	96.34 306	78.23 289	85.36 293	93.79 284

test1		87.26 228	85.98 246	91.08 195	94.01 223	83.10 135	95.14 130	94.94 223	83.57 228	84.37 274	91.64 276	66.59 305	96.34 306	78.23 289	85.36 293	93.79 284

FMVSNet1		85.85 275	84.11 294	91.08 195	92.81 269	83.10 135	95.14 130	94.94 223	81.64 281	82.68 311	91.64 276	59.01 367	96.34 306	75.37 317	83.78 306	93.79 284

Test_1112_low_res		87.65 208	86.51 224	91.08 195	94.94 166	79.28 253	91.77 294	94.30 255	76.04 356	83.51 300	92.37 248	77.86 160	97.73 195	78.69 284	89.13 251	96.22 174

PS-MVSNAJss		89.97 140	89.62 136	91.02 199	91.90 295	80.85 206	95.26 120	95.98 151	86.26 165	86.21 219	94.29 180	79.70 135	97.65 199	88.87 137	88.10 265	94.57 244

BH-RMVSNet		88.37 188	87.48 191	91.02 199	95.28 145	79.45 245	92.89 261	93.07 291	85.45 185	86.91 199	94.84 160	70.35 257	97.76 191	73.97 331	94.59 156	95.85 193

UniMVSNet_ETH3D		87.53 217	86.37 228	91.00 201	92.44 278	78.96 258	94.74 154	95.61 184	84.07 217	85.36 252	94.52 174	59.78 359	97.34 236	82.93 211	87.88 270	96.71 155

FIs		90.51 129	90.35 119	90.99 202	93.99 227	80.98 200	95.73 91	97.54 4	89.15 77	86.72 206	94.68 165	81.83 116	97.24 245	85.18 181	88.31 264	94.76 237

ACMP	84.23 8	89.01 173	88.35 170	90.99 202	94.73 178	81.27 188	95.07 133	95.89 161	86.48 158	83.67 295	94.30 179	69.33 272	97.99 180	87.10 162	88.55 256	93.72 294
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20231211		86.59 258	85.13 273	90.98 204	96.52 91	81.50 180	96.14 56	96.16 134	73.78 378	83.65 296	92.15 256	63.26 329	97.37 235	82.82 215	81.74 336	94.06 270

sss		88.93 174	88.26 176	90.94 205	94.05 221	80.78 208	91.71 296	95.38 202	81.55 285	88.63 166	93.91 199	75.04 192	95.47 347	82.47 220	91.61 207	96.57 162

sd_testset		88.59 184	87.85 184	90.83 206	96.00 112	80.42 217	92.35 277	94.71 242	88.73 91	86.85 203	95.20 144	67.31 292	96.43 300	79.64 273	89.85 237	95.63 204

PVSNet_BlendedMVS		89.98 139	89.70 134	90.82 207	96.12 102	81.25 189	93.92 215	96.83 74	83.49 232	89.10 159	92.26 253	81.04 122	98.85 94	86.72 165	87.86 271	92.35 344

cascas		86.43 266	84.98 276	90.80 208	92.10 288	80.92 204	90.24 331	95.91 158	73.10 385	83.57 299	88.39 361	65.15 317	97.46 217	84.90 186	91.43 209	94.03 272

ECVR-MVS		89.09 168	88.53 164	90.77 209	95.62 132	75.89 316	96.16 52	84.22 407	87.89 123	90.20 142	96.65 81	63.19 330	98.10 163	85.90 174	96.94 101	98.33 45

GA-MVS		86.61 256	85.27 270	90.66 210	91.33 318	78.71 260	90.40 326	93.81 276	85.34 187	85.12 255	89.57 342	61.25 346	97.11 255	80.99 253	89.59 243	96.15 177

thres600view7		87.65 208	86.67 215	90.59 211	96.08 108	78.72 259	94.88 144	91.58 334	87.06 144	88.08 175	92.30 251	68.91 282	98.10 163	70.05 359	91.10 212	94.96 227

thres400		87.62 213	86.64 216	90.57 212	95.99 115	78.64 261	94.58 163	91.98 323	86.94 148	88.09 173	91.77 272	69.18 278	98.10 163	70.13 356	91.10 212	94.96 227

baseline1		88.10 195	87.28 197	90.57 212	94.96 164	80.07 226	94.27 187	91.29 343	86.74 153	87.41 190	94.00 192	76.77 169	96.20 311	80.77 256	79.31 370	95.44 208

FC-MVSNet-test		90.27 132	90.18 123	90.53 214	93.71 238	79.85 237	95.77 89	97.59 3	89.31 70	86.27 217	94.67 166	81.93 115	97.01 263	84.26 194	88.09 267	94.71 238

PAPM		86.68 255	85.39 265	90.53 214	93.05 261	79.33 252	89.79 343	94.77 240	78.82 324	81.95 322	93.24 220	76.81 167	97.30 237	66.94 376	93.16 187	94.95 230

WR-MVS		88.38 187	87.67 187	90.52 216	93.30 252	80.18 221	93.26 246	95.96 154	88.57 99	85.47 241	92.81 235	76.12 175	96.91 270	81.24 248	82.29 327	94.47 255

MVSTER		88.84 175	88.29 174	90.51 217	92.95 267	80.44 216	93.73 222	95.01 220	84.66 208	87.15 194	93.12 225	72.79 228	97.21 248	87.86 147	87.36 279	93.87 279

testdata				90.49 218	96.40 93	77.89 282		95.37 204	72.51 390	93.63 68	96.69 77	82.08 111	97.65 199	83.08 208	97.39 91	95.94 189

test1111		89.10 166	88.64 161	90.48 219	95.53 137	74.97 326	96.08 61	84.89 405	88.13 114	90.16 144	96.65 81	63.29 328	98.10 163	86.14 169	96.90 103	98.39 40

tt0805		86.92 244	85.74 259	90.48 219	92.22 282	79.98 233	95.63 101	94.88 231	83.83 223	84.74 264	92.80 236	57.61 373	97.67 196	85.48 180	84.42 300	93.79 284

jajsoiax		88.24 192	87.50 190	90.48 219	90.89 338	80.14 223	95.31 112	95.65 182	84.97 197	84.24 282	94.02 190	65.31 316	97.42 223	88.56 139	88.52 258	93.89 275

PatchMatch-RL		86.77 252	85.54 261	90.47 222	95.88 118	82.71 154	90.54 324	92.31 311	79.82 309	84.32 279	91.57 284	68.77 284	96.39 302	73.16 337	93.48 179	92.32 345

tfpn200view9		87.58 215	86.64 216	90.41 223	95.99 115	78.64 261	94.58 163	91.98 323	86.94 148	88.09 173	91.77 272	69.18 278	98.10 163	70.13 356	91.10 212	94.48 253

VPNet		88.20 193	87.47 192	90.39 224	93.56 245	79.46 244	94.04 205	95.54 189	88.67 94	86.96 196	94.58 173	69.33 272	97.15 250	84.05 197	80.53 356	94.56 245

ACMH	80.38 17	85.36 285	83.68 301	90.39 224	94.45 200	80.63 211	94.73 155	94.85 233	82.09 263	77.24 370	92.65 240	60.01 357	97.58 205	72.25 341	84.87 297	92.96 323
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres100view900		87.63 211	86.71 212	90.38 226	96.12 102	78.55 263	95.03 136	91.58 334	87.15 141	88.06 176	92.29 252	68.91 282	98.10 163	70.13 356	91.10 212	94.48 253

mvs_tets		88.06 198	87.28 197	90.38 226	90.94 334	79.88 235	95.22 123	95.66 180	85.10 193	84.21 283	93.94 195	63.53 326	97.40 231	88.50 140	88.40 262	93.87 279

1314		87.51 218	86.57 221	90.34 228	92.42 279	79.74 239	92.63 268	95.35 206	78.35 333	80.14 344	91.62 280	74.05 209	97.15 250	81.05 249	93.53 175	94.12 265

LTVRE_ROB	82.13 13	86.26 269	84.90 279	90.34 228	94.44 201	81.50 180	92.31 281	94.89 229	83.03 244	79.63 353	92.67 239	69.69 266	97.79 189	71.20 345	86.26 288	91.72 355
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		89.03 171	88.64 161	90.21 230	90.74 344	79.28 253	95.96 74	95.90 159	84.66 208	85.33 253	92.94 230	74.02 210	97.30 237	89.64 127	88.53 257	94.05 271

v2v482		87.84 201	87.06 201	90.17 231	90.99 330	79.23 256	94.00 210	95.13 213	84.87 200	85.53 236	92.07 264	74.45 201	97.45 218	84.71 189	81.75 335	93.85 282

pmmvs4		85.43 283	83.86 299	90.16 232	90.02 361	82.97 145	90.27 327	92.67 303	75.93 357	80.73 335	91.74 274	71.05 244	95.73 336	78.85 283	83.46 313	91.78 354

V42		87.68 206	86.86 206	90.15 233	90.58 349	80.14 223	94.24 190	95.28 207	83.66 226	85.67 231	91.33 286	74.73 197	97.41 229	84.43 193	81.83 333	92.89 326

MSDG		84.86 298	83.09 310	90.14 234	93.80 234	80.05 228	89.18 356	93.09 290	78.89 321	78.19 362	91.91 269	65.86 314	97.27 241	68.47 365	88.45 260	93.11 318

anonymousdsp		87.84 201	87.09 200	90.12 235	89.13 372	80.54 214	94.67 159	95.55 187	82.05 264	83.82 290	92.12 258	71.47 241	97.15 250	87.15 158	87.80 274	92.67 332

thres200		87.21 234	86.24 235	90.12 235	95.36 141	78.53 264	93.26 246	92.10 317	86.42 161	88.00 178	91.11 297	69.24 277	98.00 179	69.58 360	91.04 218	93.83 283

CR-MVSNet		85.35 286	83.76 300	90.12 235	90.58 349	79.34 249	85.24 398	91.96 325	78.27 335	85.55 234	87.87 371	71.03 245	95.61 339	73.96 332	89.36 246	95.40 210

v1144		87.61 214	86.79 210	90.06 238	91.01 329	79.34 249	93.95 212	95.42 201	83.36 237	85.66 232	91.31 289	74.98 193	97.42 223	83.37 205	82.06 329	93.42 305

XXY-MVS		87.65 208	86.85 207	90.03 239	92.14 285	80.60 213	93.76 221	95.23 209	82.94 247	84.60 266	94.02 190	74.27 203	95.49 346	81.04 250	83.68 309	94.01 273

Vis-MVSNet (Re-imp)		89.59 151	89.44 140	90.03 239	95.74 123	75.85 317	95.61 102	90.80 357	87.66 133	87.83 182	95.40 135	76.79 168	96.46 298	78.37 285	96.73 109	97.80 93

test2506		87.21 234	86.28 233	90.02 241	95.62 132	73.64 342	96.25 47	71.38 430	87.89 123	90.45 137	96.65 81	55.29 384	98.09 171	86.03 173	96.94 101	98.33 45

BH-untuned		88.60 183	88.13 178	90.01 242	95.24 149	78.50 266	93.29 244	94.15 262	84.75 205	84.46 271	93.40 212	75.76 182	97.40 231	77.59 295	94.52 159	94.12 265

v1192		87.25 230	86.33 230	90.00 243	90.76 343	79.04 257	93.80 219	95.48 192	82.57 254	85.48 240	91.18 293	73.38 223	97.42 223	82.30 224	82.06 329	93.53 299

v7n		86.81 247	85.76 257	89.95 244	90.72 345	79.25 255	95.07 133	95.92 156	84.45 211	82.29 315	90.86 304	72.60 231	97.53 209	79.42 278	80.52 357	93.08 320

testing91		87.11 239	86.18 236	89.92 245	94.43 202	75.38 325	91.53 301	92.27 313	86.48 158	86.50 208	90.24 322	61.19 349	97.53 209	82.10 229	90.88 220	96.84 150

v8		87.50 220	86.71 212	89.89 246	91.37 315	79.40 246	94.50 168	95.38 202	84.81 203	83.60 298	91.33 286	76.05 176	97.42 223	82.84 214	80.51 358	92.84 328

v10		87.25 230	86.38 227	89.85 247	91.19 321	79.50 242	94.48 169	95.45 196	83.79 224	83.62 297	91.19 291	75.13 190	97.42 223	81.94 234	80.60 353	92.63 334

baseline2		86.50 262	85.39 265	89.84 248	91.12 326	76.70 305	91.88 291	88.58 385	82.35 259	79.95 348	90.95 302	73.42 221	97.63 202	80.27 266	89.95 234	95.19 217

pm-mvs1		86.61 256	85.54 261	89.82 249	91.44 310	80.18 221	95.28 118	94.85 233	83.84 222	81.66 324	92.62 241	72.45 234	96.48 295	79.67 272	78.06 373	92.82 329

TR-MVS		86.78 249	85.76 257	89.82 249	94.37 205	78.41 268	92.47 272	92.83 297	81.11 295	86.36 214	92.40 247	68.73 285	97.48 214	73.75 335	89.85 237	93.57 298

ACMH+	81.04 14	85.05 293	83.46 304	89.82 249	94.66 184	79.37 247	94.44 174	94.12 265	82.19 262	78.04 364	92.82 234	58.23 370	97.54 208	73.77 334	82.90 321	92.54 335

EI-MVSNet		89.10 166	88.86 158	89.80 252	91.84 297	78.30 272	93.70 225	95.01 220	85.73 177	87.15 194	95.28 138	79.87 132	97.21 248	83.81 201	87.36 279	93.88 278

v144192		87.19 236	86.35 229	89.74 253	90.64 347	78.24 274	93.92 215	95.43 199	81.93 269	85.51 238	91.05 300	74.21 206	97.45 218	82.86 213	81.56 337	93.53 299

COLMAP_ROB	80.39 16	83.96 311	82.04 320	89.74 253	95.28 145	79.75 238	94.25 188	92.28 312	75.17 364	78.02 365	93.77 205	58.60 369	97.84 188	65.06 387	85.92 289	91.63 357
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SCA		86.32 268	85.18 272	89.73 255	92.15 284	76.60 306	91.12 312	91.69 330	83.53 231	85.50 239	88.81 354	66.79 301	96.48 295	76.65 304	90.35 227	96.12 180

IterMVS-LS		88.36 189	87.91 183	89.70 256	93.80 234	78.29 273	93.73 222	95.08 218	85.73 177	84.75 263	91.90 270	79.88 131	96.92 269	83.83 200	82.51 323	93.89 275
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing11		86.44 265	85.35 268	89.69 257	94.29 210	75.40 324	91.30 306	90.53 360	84.76 204	85.06 257	90.13 328	58.95 368	97.45 218	82.08 230	91.09 216	96.21 176

testing99		86.72 253	85.73 260	89.69 257	94.23 212	74.91 328	91.35 305	90.97 351	86.14 169	86.36 214	90.22 323	59.41 362	97.48 214	82.24 226	90.66 222	96.69 157

v1921920		86.97 243	86.06 243	89.69 257	90.53 352	78.11 277	93.80 219	95.43 199	81.90 271	85.33 253	91.05 300	72.66 229	97.41 229	82.05 232	81.80 334	93.53 299

Fast-Effi-MVS+-dtu		87.44 221	86.72 211	89.63 260	92.04 289	77.68 291	94.03 206	93.94 268	85.81 174	82.42 314	91.32 288	70.33 258	97.06 259	80.33 265	90.23 229	94.14 264

v1240		86.78 249	85.85 252	89.56 261	90.45 353	77.79 287	93.61 227	95.37 204	81.65 280	85.43 245	91.15 295	71.50 240	97.43 222	81.47 245	82.05 331	93.47 303

Effi-MVS+-dtu		88.65 181	88.35 170	89.54 262	93.33 251	76.39 310	94.47 172	94.36 253	87.70 130	85.43 245	89.56 343	73.45 219	97.26 243	85.57 179	91.28 211	94.97 224

AllTest		83.42 318	81.39 324	89.52 263	95.01 159	77.79 287	93.12 250	90.89 355	77.41 342	76.12 378	93.34 213	54.08 390	97.51 211	68.31 367	84.27 302	93.26 308

TestCases				89.52 263	95.01 159	77.79 287		90.89 355	77.41 342	76.12 378	93.34 213	54.08 390	97.51 211	68.31 367	84.27 302	93.26 308

mvs_anonymous		89.37 162	89.32 145	89.51 265	93.47 247	74.22 335	91.65 299	94.83 235	82.91 248	85.45 242	93.79 203	81.23 121	96.36 305	86.47 167	94.09 165	97.94 82

XVG-ACMP-BASELINE		86.00 271	84.84 281	89.45 266	91.20 320	78.00 278	91.70 297	95.55 187	85.05 195	82.97 308	92.25 254	54.49 388	97.48 214	82.93 211	87.45 278	92.89 326

testing222		84.84 299	83.32 305	89.43 267	94.15 218	75.94 315	91.09 313	89.41 383	84.90 198	85.78 228	89.44 344	52.70 395	96.28 309	70.80 351	91.57 208	96.07 184

MVP-Stereo		85.97 272	84.86 280	89.32 268	90.92 336	82.19 166	92.11 287	94.19 260	78.76 326	78.77 361	91.63 279	68.38 289	96.56 289	75.01 322	93.95 167	89.20 393
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchmatchNet		85.85 275	84.70 283	89.29 269	91.76 301	75.54 321	88.49 365	91.30 342	81.63 282	85.05 258	88.70 358	71.71 237	96.24 310	74.61 327	89.05 252	96.08 183
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v148		87.04 241	86.32 231	89.21 270	90.94 334	77.26 296	93.71 224	94.43 249	84.84 202	84.36 277	90.80 308	76.04 177	97.05 261	82.12 228	79.60 367	93.31 307

tfpnnormal		84.72 301	83.23 308	89.20 271	92.79 270	80.05 228	94.48 169	95.81 166	82.38 257	81.08 332	91.21 290	69.01 281	96.95 267	61.69 397	80.59 354	90.58 380

cl22		86.78 249	85.98 246	89.18 272	92.34 280	77.62 292	90.84 318	94.13 264	81.33 289	83.97 288	90.15 327	73.96 211	96.60 286	84.19 195	82.94 318	93.33 306

BH-w/o		87.57 216	87.05 202	89.12 273	94.90 170	77.90 281	92.41 273	93.51 282	82.89 249	83.70 294	91.34 285	75.75 183	97.07 258	75.49 315	93.49 177	92.39 342

WR-MVS_H		87.80 203	87.37 194	89.10 274	93.23 253	78.12 276	95.61 102	97.30 30	87.90 121	83.72 293	92.01 266	79.65 139	96.01 320	76.36 308	80.54 355	93.16 316

miper_enhance_ethall		86.90 245	86.18 236	89.06 275	91.66 306	77.58 293	90.22 333	94.82 236	79.16 317	84.48 270	89.10 348	79.19 143	96.66 279	84.06 196	82.94 318	92.94 324

c3_l		87.14 238	86.50 225	89.04 276	92.20 283	77.26 296	91.22 311	94.70 243	82.01 267	84.34 278	90.43 319	78.81 146	96.61 284	83.70 203	81.09 344	93.25 310

miper_ehance_all_eth		87.22 233	86.62 219	89.02 277	92.13 286	77.40 295	90.91 317	94.81 237	81.28 290	84.32 279	90.08 330	79.26 141	96.62 281	83.81 201	82.94 318	93.04 321

gg-mvs-nofinetune		81.77 330	79.37 345	88.99 278	90.85 340	77.73 290	86.29 390	79.63 418	74.88 369	83.19 307	69.05 421	60.34 354	96.11 315	75.46 316	94.64 155	93.11 318

ETVMVS		84.43 305	82.92 314	88.97 279	94.37 205	74.67 329	91.23 310	88.35 387	83.37 236	86.06 223	89.04 349	55.38 382	95.67 338	67.12 374	91.34 210	96.58 161

pmmvs6		83.42 318	81.60 322	88.87 280	88.01 387	77.87 283	94.96 139	94.24 259	74.67 370	78.80 360	91.09 298	60.17 356	96.49 294	77.06 303	75.40 387	92.23 347

test_cas_vis1_n_1920		88.83 178	88.85 159	88.78 281	91.15 325	76.72 304	93.85 218	94.93 227	83.23 241	92.81 88	96.00 107	61.17 350	94.45 358	91.67 102	94.84 149	95.17 218

MIMVSNet		82.59 324	80.53 329	88.76 282	91.51 308	78.32 271	86.57 389	90.13 367	79.32 313	80.70 336	88.69 359	52.98 394	93.07 383	66.03 382	88.86 254	94.90 231

cl____		86.52 261	85.78 254	88.75 283	92.03 290	76.46 308	90.74 319	94.30 255	81.83 276	83.34 304	90.78 309	75.74 185	96.57 287	81.74 240	81.54 338	93.22 312

DIV-MVS_self_test		86.53 260	85.78 254	88.75 283	92.02 291	76.45 309	90.74 319	94.30 255	81.83 276	83.34 304	90.82 307	75.75 183	96.57 287	81.73 241	81.52 339	93.24 311

CP-MVSNet		87.63 211	87.26 199	88.74 285	93.12 256	76.59 307	95.29 116	96.58 100	88.43 102	83.49 301	92.98 229	75.28 189	95.83 329	78.97 281	81.15 343	93.79 284

eth_miper_zixun_eth		86.50 262	85.77 256	88.68 286	91.94 292	75.81 318	90.47 325	94.89 229	82.05 264	84.05 285	90.46 318	75.96 178	96.77 274	82.76 217	79.36 369	93.46 304

CHOSEN 280x420		85.15 291	83.99 297	88.65 287	92.47 276	78.40 269	79.68 420	92.76 300	74.90 368	81.41 328	89.59 341	69.85 265	95.51 343	79.92 270	95.29 141	92.03 350

PS-CasMVS		87.32 227	86.88 205	88.63 288	92.99 265	76.33 312	95.33 111	96.61 98	88.22 110	83.30 306	93.07 227	73.03 226	95.79 333	78.36 286	81.00 349	93.75 291

TransMVSNet (Re)		84.43 305	83.06 312	88.54 289	91.72 302	78.44 267	95.18 127	92.82 299	82.73 252	79.67 352	92.12 258	73.49 218	95.96 322	71.10 349	68.73 403	91.21 367

EG-PatchMatch MVS		82.37 326	80.34 332	88.46 290	90.27 355	79.35 248	92.80 265	94.33 254	77.14 346	73.26 395	90.18 326	47.47 406	96.72 275	70.25 353	87.32 281	89.30 390

PEN-MVS		86.80 248	86.27 234	88.40 291	92.32 281	75.71 320	95.18 127	96.38 115	87.97 118	82.82 310	93.15 223	73.39 222	95.92 324	76.15 312	79.03 372	93.59 297

Baseline_NR-MVSNet		87.07 240	86.63 218	88.40 291	91.44 310	77.87 283	94.23 191	92.57 305	84.12 216	85.74 230	92.08 262	77.25 164	96.04 316	82.29 225	79.94 362	91.30 365

UBG		85.51 281	84.57 287	88.35 293	94.21 214	71.78 366	90.07 338	89.66 379	82.28 260	85.91 226	89.01 350	61.30 344	97.06 259	76.58 307	92.06 205	96.22 174

D2MVS		85.90 273	85.09 274	88.35 293	90.79 341	77.42 294	91.83 293	95.70 176	80.77 298	80.08 346	90.02 332	66.74 303	96.37 303	81.88 236	87.97 269	91.26 366

pmmvs5		84.21 307	82.84 317	88.34 295	88.95 374	76.94 300	92.41 273	91.91 327	75.63 359	80.28 341	91.18 293	64.59 320	95.57 340	77.09 302	83.47 312	92.53 336

mamv4		90.92 115	91.78 97	88.33 296	95.67 128	70.75 379	92.92 260	96.02 150	81.90 271	88.11 172	95.34 136	85.88 51	96.97 265	95.22 35	95.01 146	97.26 118

LCM-MVSNet-Re		88.30 191	88.32 173	88.27 297	94.71 181	72.41 361	93.15 249	90.98 350	87.77 128	79.25 356	91.96 267	78.35 154	95.75 334	83.04 209	95.62 130	96.65 158

CostFormer		85.77 278	84.94 278	88.26 298	91.16 324	72.58 359	89.47 351	91.04 349	76.26 354	86.45 212	89.97 334	70.74 250	96.86 273	82.35 223	87.07 284	95.34 214

ITE_SJBPF				88.24 299	91.88 296	77.05 299		92.92 294	85.54 183	80.13 345	93.30 217	57.29 374	96.20 311	72.46 340	84.71 298	91.49 361

PVSNet	78.82 18	85.55 280	84.65 284	88.23 300	94.72 180	71.93 362	87.12 385	92.75 301	78.80 325	84.95 260	90.53 316	64.43 321	96.71 277	74.74 325	93.86 169	96.06 186

IterMVS-SCA-FT		85.45 282	84.53 288	88.18 301	91.71 303	76.87 301	90.19 335	92.65 304	85.40 186	81.44 327	90.54 315	66.79 301	95.00 355	81.04 250	81.05 345	92.66 333

EPNet_dtu		86.49 264	85.94 249	88.14 302	90.24 356	72.82 351	94.11 197	92.20 315	86.66 156	79.42 355	92.36 249	73.52 217	95.81 331	71.26 344	93.66 171	95.80 197
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmtry		82.71 322	80.93 328	88.06 303	90.05 360	76.37 311	84.74 403	91.96 325	72.28 393	81.32 330	87.87 371	71.03 245	95.50 345	68.97 362	80.15 360	92.32 345

test_vis1_n_1920		89.39 161	89.84 133	88.04 304	92.97 266	72.64 356	94.71 157	96.03 149	86.18 167	91.94 114	96.56 89	61.63 339	95.74 335	93.42 55	95.11 145	95.74 199

DTE-MVSNet		86.11 270	85.48 263	87.98 305	91.65 307	74.92 327	94.93 141	95.75 171	87.36 138	82.26 316	93.04 228	72.85 227	95.82 330	74.04 330	77.46 378	93.20 314

PMMVS		85.71 279	84.96 277	87.95 306	88.90 375	77.09 298	88.68 363	90.06 369	72.32 392	86.47 209	90.76 310	72.15 235	94.40 360	81.78 239	93.49 177	92.36 343

GG-mvs-BLEND				87.94 307	89.73 367	77.91 280	87.80 374	78.23 423		80.58 338	83.86 398	59.88 358	95.33 349	71.20 345	92.22 203	90.60 379

MonoMVSNet		86.89 246	86.55 222	87.92 308	89.46 370	73.75 339	94.12 195	93.10 289	87.82 127	85.10 256	90.76 310	69.59 268	94.94 356	86.47 167	82.50 324	95.07 221

reproduce_monomvs		86.37 267	85.87 251	87.87 309	93.66 242	73.71 340	93.44 234	95.02 219	88.61 97	82.64 313	91.94 268	57.88 372	96.68 278	89.96 124	79.71 366	93.22 312

pmmvs-eth3d		80.97 344	78.72 356	87.74 310	84.99 405	79.97 234	90.11 337	91.65 332	75.36 361	73.51 393	86.03 388	59.45 361	93.96 370	75.17 319	72.21 392	89.29 392

MS-PatchMatch		85.05 293	84.16 292	87.73 311	91.42 313	78.51 265	91.25 309	93.53 281	77.50 341	80.15 343	91.58 282	61.99 336	95.51 343	75.69 314	94.35 163	89.16 394

mmtdpeth		85.04 295	84.15 293	87.72 312	93.11 257	75.74 319	94.37 183	92.83 297	84.98 196	89.31 156	86.41 385	61.61 341	97.14 253	92.63 71	62.11 413	90.29 381

test_0402		81.30 340	79.17 350	87.67 313	93.19 254	78.17 275	92.98 257	91.71 328	75.25 363	76.02 380	90.31 321	59.23 363	96.37 303	50.22 416	83.63 310	88.47 401

IterMVS		84.88 297	83.98 298	87.60 314	91.44 310	76.03 314	90.18 336	92.41 307	83.24 240	81.06 333	90.42 320	66.60 304	94.28 364	79.46 274	80.98 350	92.48 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmatch-test		81.37 338	79.30 346	87.58 315	90.92 336	74.16 337	80.99 415	87.68 392	70.52 400	76.63 375	88.81 354	71.21 242	92.76 385	60.01 403	86.93 285	95.83 195

EPMVS		83.90 314	82.70 318	87.51 316	90.23 357	72.67 354	88.62 364	81.96 413	81.37 288	85.01 259	88.34 362	66.31 308	94.45 358	75.30 318	87.12 282	95.43 209

ADS-MVSNet2		81.66 333	79.71 342	87.50 317	91.35 316	74.19 336	83.33 408	88.48 386	72.90 387	82.24 317	85.77 391	64.98 318	93.20 381	64.57 389	83.74 307	95.12 219

OurMVSNet-221017-0		85.35 286	84.64 285	87.49 318	90.77 342	72.59 358	94.01 208	94.40 251	84.72 206	79.62 354	93.17 222	61.91 337	96.72 275	81.99 233	81.16 341	93.16 316

tpm2		84.08 309	82.94 313	87.48 319	91.39 314	71.27 371	89.23 355	90.37 362	71.95 394	84.64 265	89.33 345	67.30 293	96.55 291	75.17 319	87.09 283	94.63 239

RPSCF		85.07 292	84.27 289	87.48 319	92.91 268	70.62 381	91.69 298	92.46 306	76.20 355	82.67 312	95.22 141	63.94 324	97.29 240	77.51 297	85.80 290	94.53 246

myMVS_eth3d28		85.80 277	85.26 271	87.42 321	94.73 178	69.92 386	90.60 323	90.95 352	87.21 140	86.06 223	90.04 331	59.47 360	96.02 318	74.89 324	93.35 184	96.33 168

WBMVS		84.97 296	84.18 291	87.34 322	94.14 219	71.62 370	90.20 334	92.35 308	81.61 283	84.06 284	90.76 310	61.82 338	96.52 292	78.93 282	83.81 305	93.89 275

miper_lstm_enhance		85.27 289	84.59 286	87.31 323	91.28 319	74.63 330	87.69 379	94.09 266	81.20 294	81.36 329	89.85 337	74.97 194	94.30 363	81.03 252	79.84 365	93.01 322

FMVSNet5		81.52 336	79.60 343	87.27 324	91.17 322	77.95 279	91.49 302	92.26 314	76.87 347	76.16 377	87.91 370	51.67 396	92.34 388	67.74 371	81.16 341	91.52 360

USDC		82.76 321	81.26 326	87.26 325	91.17 322	74.55 331	89.27 353	93.39 284	78.26 336	75.30 384	92.08 262	54.43 389	96.63 280	71.64 342	85.79 291	90.61 377

test-LLR		85.87 274	85.41 264	87.25 326	90.95 332	71.67 368	89.55 347	89.88 375	83.41 234	84.54 268	87.95 368	67.25 294	95.11 352	81.82 237	93.37 182	94.97 224

test-mter		84.54 304	83.64 302	87.25 326	90.95 332	71.67 368	89.55 347	89.88 375	79.17 316	84.54 268	87.95 368	55.56 380	95.11 352	81.82 237	93.37 182	94.97 224

JIA-IIPM		81.04 341	78.98 354	87.25 326	88.64 376	73.48 344	81.75 414	89.61 381	73.19 384	82.05 320	73.71 417	66.07 313	95.87 327	71.18 347	84.60 299	92.41 341

TDRefinement		79.81 354	77.34 360	87.22 329	79.24 420	75.48 322	93.12 250	92.03 320	76.45 350	75.01 385	91.58 282	49.19 402	96.44 299	70.22 355	69.18 400	89.75 386

tpmvs		83.35 320	82.07 319	87.20 330	91.07 328	71.00 377	88.31 368	91.70 329	78.91 319	80.49 340	87.18 380	69.30 275	97.08 256	68.12 370	83.56 311	93.51 302

ppachtmachnet_test		81.84 329	80.07 337	87.15 331	88.46 380	74.43 334	89.04 359	92.16 316	75.33 362	77.75 367	88.99 351	66.20 310	95.37 348	65.12 386	77.60 376	91.65 356

dmvs_re		84.20 308	83.22 309	87.14 332	91.83 299	77.81 285	90.04 339	90.19 365	84.70 207	81.49 325	89.17 347	64.37 322	91.13 399	71.58 343	85.65 292	92.46 339

tpm cat1		81.96 327	80.27 333	87.01 333	91.09 327	71.02 376	87.38 383	91.53 337	66.25 408	80.17 342	86.35 387	68.22 290	96.15 314	69.16 361	82.29 327	93.86 281

test_fmvs1_n		87.03 242	87.04 203	86.97 334	89.74 366	71.86 363	94.55 165	94.43 249	78.47 330	91.95 113	95.50 131	51.16 398	93.81 371	93.02 63	94.56 157	95.26 215

OpenMVS_ROB	74.94 19	79.51 357	77.03 365	86.93 335	87.00 393	76.23 313	92.33 279	90.74 358	68.93 404	74.52 389	88.23 365	49.58 401	96.62 281	57.64 408	84.29 301	87.94 404

SixPastTwentyTwo		83.91 313	82.90 315	86.92 336	90.99 330	70.67 380	93.48 231	91.99 322	85.54 183	77.62 369	92.11 260	60.59 353	96.87 272	76.05 313	77.75 375	93.20 314

ADS-MVSNet		81.56 335	79.78 339	86.90 337	91.35 316	71.82 364	83.33 408	89.16 384	72.90 387	82.24 317	85.77 391	64.98 318	93.76 372	64.57 389	83.74 307	95.12 219

PatchT		82.68 323	81.27 325	86.89 338	90.09 359	70.94 378	84.06 405	90.15 366	74.91 367	85.63 233	83.57 400	69.37 271	94.87 357	65.19 384	88.50 259	94.84 233

tpm		84.73 300	84.02 296	86.87 339	90.33 354	68.90 389	89.06 358	89.94 372	80.85 297	85.75 229	89.86 336	68.54 287	95.97 321	77.76 293	84.05 304	95.75 198

Patchmatch-RL test		81.67 332	79.96 338	86.81 340	85.42 403	71.23 372	82.17 413	87.50 393	78.47 330	77.19 371	82.50 407	70.81 249	93.48 376	82.66 218	72.89 391	95.71 202

test_vis1_n		86.56 259	86.49 226	86.78 341	88.51 377	72.69 353	94.68 158	93.78 278	79.55 312	90.70 134	95.31 137	48.75 403	93.28 379	93.15 59	93.99 166	94.38 257

testing3-2		86.72 253	86.71 212	86.74 342	96.11 105	65.92 400	93.39 236	89.65 380	89.46 63	87.84 181	92.79 237	59.17 365	97.60 204	81.31 246	90.72 221	96.70 156

test_fmvs1		87.34 225	87.56 189	86.68 343	90.59 348	71.80 365	94.01 208	94.04 267	78.30 334	91.97 111	95.22 141	56.28 378	93.71 373	92.89 64	94.71 151	94.52 247

MDA-MVSNet-bldmvs		78.85 362	76.31 367	86.46 344	89.76 365	73.88 338	88.79 361	90.42 361	79.16 317	59.18 417	88.33 363	60.20 355	94.04 366	62.00 396	68.96 401	91.48 362

mvs5depth		80.98 343	79.15 351	86.45 345	84.57 406	73.29 346	87.79 375	91.67 331	80.52 300	82.20 319	89.72 339	55.14 385	95.93 323	73.93 333	66.83 405	90.12 383

tpmrst		85.35 286	84.99 275	86.43 346	90.88 339	67.88 394	88.71 362	91.43 340	80.13 304	86.08 222	88.80 356	73.05 225	96.02 318	82.48 219	83.40 315	95.40 210

TESTMET0.1,1		83.74 316	82.85 316	86.42 347	89.96 362	71.21 373	89.55 347	87.88 389	77.41 342	83.37 303	87.31 376	56.71 376	93.65 375	80.62 260	92.85 194	94.40 256

our_test_3		81.93 328	80.46 331	86.33 348	88.46 380	73.48 344	88.46 366	91.11 345	76.46 349	76.69 374	88.25 364	66.89 299	94.36 361	68.75 363	79.08 371	91.14 369

lessismore_v0				86.04 349	88.46 380	68.78 390		80.59 416		73.01 396	90.11 329	55.39 381	96.43 300	75.06 321	65.06 408	92.90 325

TinyColmap		79.76 355	77.69 359	85.97 350	91.71 303	73.12 347	89.55 347	90.36 363	75.03 365	72.03 399	90.19 325	46.22 410	96.19 313	63.11 393	81.03 346	88.59 400

KD-MVS_2432*1600		78.50 363	76.02 370	85.93 351	86.22 396	74.47 332	84.80 401	92.33 309	79.29 314	76.98 372	85.92 389	53.81 392	93.97 368	67.39 372	57.42 418	89.36 388

miper_refine_blended		78.50 363	76.02 370	85.93 351	86.22 396	74.47 332	84.80 401	92.33 309	79.29 314	76.98 372	85.92 389	53.81 392	93.97 368	67.39 372	57.42 418	89.36 388

K. test v3		81.59 334	80.15 336	85.91 353	89.89 364	69.42 388	92.57 270	87.71 391	85.56 182	73.44 394	89.71 340	55.58 379	95.52 342	77.17 300	69.76 397	92.78 330

SSC-MVS3.2		84.60 303	84.19 290	85.85 354	92.74 271	68.07 391	88.15 370	93.81 276	87.42 137	83.76 292	91.07 299	62.91 331	95.73 336	74.56 328	83.24 316	93.75 291

mvsany_test1		85.42 284	85.30 269	85.77 355	87.95 389	75.41 323	87.61 382	80.97 415	76.82 348	88.68 165	95.83 117	77.44 163	90.82 401	85.90 174	86.51 286	91.08 373

MIMVSNet1		79.38 358	77.28 361	85.69 356	86.35 395	73.67 341	91.61 300	92.75 301	78.11 339	72.64 397	88.12 366	48.16 404	91.97 393	60.32 400	77.49 377	91.43 363

UWE-MVS		83.69 317	83.09 310	85.48 357	93.06 260	65.27 405	90.92 316	86.14 397	79.90 307	86.26 218	90.72 313	57.17 375	95.81 331	71.03 350	92.62 197	95.35 213

UnsupCasMVSNet_eth		80.07 351	78.27 358	85.46 358	85.24 404	72.63 357	88.45 367	94.87 232	82.99 246	71.64 401	88.07 367	56.34 377	91.75 394	73.48 336	63.36 411	92.01 351

CL-MVSNet_self_test		81.74 331	80.53 329	85.36 359	85.96 398	72.45 360	90.25 329	93.07 291	81.24 292	79.85 351	87.29 377	70.93 247	92.52 386	66.95 375	69.23 399	91.11 371

MDA-MVSNet_test_wron		79.21 360	77.19 363	85.29 360	88.22 384	72.77 352	85.87 392	90.06 369	74.34 372	62.62 414	87.56 374	66.14 311	91.99 392	66.90 379	73.01 389	91.10 372

YYNet1		79.22 359	77.20 362	85.28 361	88.20 385	72.66 355	85.87 392	90.05 371	74.33 373	62.70 412	87.61 373	66.09 312	92.03 390	66.94 376	72.97 390	91.15 368

WB-MVSnew		83.77 315	83.28 306	85.26 362	91.48 309	71.03 375	91.89 290	87.98 388	78.91 319	84.78 262	90.22 323	69.11 280	94.02 367	64.70 388	90.44 224	90.71 375

dp		81.47 337	80.23 334	85.17 363	89.92 363	65.49 403	86.74 387	90.10 368	76.30 353	81.10 331	87.12 381	62.81 332	95.92 324	68.13 369	79.88 363	94.09 268

UnsupCasMVSNet_bld		76.23 372	73.27 376	85.09 364	83.79 408	72.92 349	85.65 395	93.47 283	71.52 395	68.84 407	79.08 412	49.77 400	93.21 380	66.81 380	60.52 415	89.13 396

Anonymous20231206		81.03 342	79.77 341	84.82 365	87.85 390	70.26 383	91.42 303	92.08 318	73.67 379	77.75 367	89.25 346	62.43 334	93.08 382	61.50 398	82.00 332	91.12 370

test0.0.03 1		82.41 325	81.69 321	84.59 366	88.23 383	72.89 350	90.24 331	87.83 390	83.41 234	79.86 350	89.78 338	67.25 294	88.99 411	65.18 385	83.42 314	91.90 353

CMPMVS	59.16 21	80.52 346	79.20 349	84.48 367	83.98 407	67.63 397	89.95 342	93.84 275	64.79 411	66.81 409	91.14 296	57.93 371	95.17 350	76.25 310	88.10 265	90.65 376
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		84.69 302	84.79 282	84.37 368	91.84 297	64.92 406	93.70 225	91.47 339	66.19 409	86.16 221	95.28 138	67.18 296	93.33 378	80.89 255	90.42 226	94.88 232

PVSNet_0	73.20 20	77.22 368	74.83 374	84.37 368	90.70 346	71.10 374	83.09 410	89.67 378	72.81 389	73.93 392	83.13 402	60.79 352	93.70 374	68.54 364	50.84 423	88.30 402

LF4IMVS		80.37 349	79.07 353	84.27 370	86.64 394	69.87 387	89.39 352	91.05 348	76.38 351	74.97 386	90.00 333	47.85 405	94.25 365	74.55 329	80.82 352	88.69 399

Anonymous20240521		80.44 348	79.21 348	84.11 371	85.75 401	67.89 393	92.86 263	93.23 287	75.61 360	75.59 383	87.47 375	50.03 399	94.33 362	71.14 348	81.21 340	90.12 383

PM-MVS		78.11 365	76.12 369	84.09 372	83.54 409	70.08 384	88.97 360	85.27 404	79.93 306	74.73 388	86.43 384	34.70 421	93.48 376	79.43 277	72.06 393	88.72 398

test_fmvs2		83.98 310	84.03 295	83.83 373	87.16 392	67.53 398	93.93 214	92.89 295	77.62 340	86.89 202	93.53 210	47.18 407	92.02 391	90.54 118	86.51 286	91.93 352

testgi		80.94 345	80.20 335	83.18 374	87.96 388	66.29 399	91.28 307	90.70 359	83.70 225	78.12 363	92.84 232	51.37 397	90.82 401	63.34 392	82.46 325	92.43 340

KD-MVS_self_test		80.20 350	79.24 347	83.07 375	85.64 402	65.29 404	91.01 315	93.93 269	78.71 328	76.32 376	86.40 386	59.20 364	92.93 384	72.59 339	69.35 398	91.00 374

testing3		80.46 347	79.59 344	83.06 376	93.44 249	64.64 407	93.33 238	85.47 402	84.34 213	79.93 349	90.84 306	44.35 413	92.39 387	57.06 410	87.56 275	92.16 349

ambc				83.06 376	79.99 418	63.51 411	77.47 421	92.86 296		74.34 391	84.45 397	28.74 422	95.06 354	73.06 338	68.89 402	90.61 377

test20.03		79.95 353	79.08 352	82.55 378	85.79 400	67.74 396	91.09 313	91.08 346	81.23 293	74.48 390	89.96 335	61.63 339	90.15 403	60.08 401	76.38 383	89.76 385

MVStest1		72.91 376	69.70 381	82.54 379	78.14 421	73.05 348	88.21 369	86.21 396	60.69 415	64.70 410	90.53 316	46.44 409	85.70 418	58.78 406	53.62 420	88.87 397

test_vis1_rt		77.96 366	76.46 366	82.48 380	85.89 399	71.74 367	90.25 329	78.89 419	71.03 399	71.30 402	81.35 409	42.49 415	91.05 400	84.55 191	82.37 326	84.65 407

EU-MVSNet		81.32 339	80.95 327	82.42 381	88.50 379	63.67 410	93.32 239	91.33 341	64.02 412	80.57 339	92.83 233	61.21 348	92.27 389	76.34 309	80.38 359	91.32 364

myMVS_eth3d		79.67 356	78.79 355	82.32 382	91.92 293	64.08 408	89.75 345	87.40 394	81.72 278	78.82 358	87.20 378	45.33 411	91.29 397	59.09 405	87.84 272	91.60 358

ttmdpeth		76.55 370	74.64 375	82.29 383	82.25 414	67.81 395	89.76 344	85.69 400	70.35 401	75.76 381	91.69 275	46.88 408	89.77 405	66.16 381	63.23 412	89.30 390

pmmvs3		71.81 379	68.71 382	81.11 384	75.86 423	70.42 382	86.74 387	83.66 408	58.95 418	68.64 408	80.89 410	36.93 419	89.52 407	63.10 394	63.59 410	83.39 408

Syy-MVS		80.07 351	79.78 339	80.94 385	91.92 293	59.93 417	89.75 345	87.40 394	81.72 278	78.82 358	87.20 378	66.29 309	91.29 397	47.06 418	87.84 272	91.60 358

UWE-MVS-28		78.98 361	78.38 357	80.80 386	88.18 386	60.66 416	90.65 321	78.51 420	78.84 323	77.93 366	90.93 303	59.08 366	89.02 410	50.96 415	90.33 228	92.72 331

new-patchmatchnet		76.41 371	75.17 373	80.13 387	82.65 413	59.61 418	87.66 380	91.08 346	78.23 337	69.85 405	83.22 401	54.76 386	91.63 396	64.14 391	64.89 409	89.16 394

mvsany_test3		74.95 373	73.26 377	80.02 388	74.61 424	63.16 412	85.53 396	78.42 421	74.16 374	74.89 387	86.46 383	36.02 420	89.09 409	82.39 222	66.91 404	87.82 405

test_fmvs3		77.67 367	77.16 364	79.22 389	79.52 419	61.14 414	92.34 278	91.64 333	73.98 376	78.86 357	86.59 382	27.38 425	87.03 413	88.12 145	75.97 385	89.50 387

DSMNet-mixed		76.94 369	76.29 368	78.89 390	83.10 411	56.11 426	87.78 376	79.77 417	60.65 416	75.64 382	88.71 357	61.56 342	88.34 412	60.07 402	89.29 248	92.21 348

EGC-MVSNET		61.97 387	56.37 392	78.77 391	89.63 368	73.50 343	89.12 357	82.79 410	0.21 437	1.24 438	84.80 395	39.48 416	90.04 404	44.13 420	75.94 386	72.79 419

new_pmnet		72.15 377	70.13 380	78.20 392	82.95 412	65.68 401	83.91 406	82.40 412	62.94 414	64.47 411	79.82 411	42.85 414	86.26 417	57.41 409	74.44 388	82.65 412

MVS-HIRNet		73.70 375	72.20 378	78.18 393	91.81 300	56.42 425	82.94 411	82.58 411	55.24 419	68.88 406	66.48 422	55.32 383	95.13 351	58.12 407	88.42 261	83.01 410

LCM-MVSNet		66.00 384	62.16 389	77.51 394	64.51 434	58.29 420	83.87 407	90.90 354	48.17 423	54.69 420	73.31 418	16.83 434	86.75 414	65.47 383	61.67 414	87.48 406

APD_test1		69.04 380	66.26 386	77.36 395	80.51 417	62.79 413	85.46 397	83.51 409	54.11 421	59.14 418	84.79 396	23.40 428	89.61 406	55.22 411	70.24 396	79.68 416

test_f		71.95 378	70.87 379	75.21 396	74.21 426	59.37 419	85.07 400	85.82 399	65.25 410	70.42 404	83.13 402	23.62 426	82.93 424	78.32 287	71.94 394	83.33 409

ANet_high		58.88 391	54.22 396	72.86 397	56.50 437	56.67 422	80.75 416	86.00 398	73.09 386	37.39 429	64.63 425	22.17 429	79.49 427	43.51 421	23.96 431	82.43 413

test_vis3_rt		65.12 385	62.60 387	72.69 398	71.44 427	60.71 415	87.17 384	65.55 431	63.80 413	53.22 421	65.65 424	14.54 435	89.44 408	76.65 304	65.38 407	67.91 422

FPMVS		64.63 386	62.55 388	70.88 399	70.80 428	56.71 421	84.42 404	84.42 406	51.78 422	49.57 422	81.61 408	23.49 427	81.48 425	40.61 425	76.25 384	74.46 418

dmvs_testset		74.57 374	75.81 372	70.86 400	87.72 391	40.47 435	87.05 386	77.90 425	82.75 251	71.15 403	85.47 393	67.98 291	84.12 422	45.26 419	76.98 382	88.00 403

N_pmnet		68.89 381	68.44 383	70.23 401	89.07 373	28.79 440	88.06 371	19.50 440	69.47 403	71.86 400	84.93 394	61.24 347	91.75 394	54.70 412	77.15 379	90.15 382

testf1		59.54 389	56.11 393	69.85 402	69.28 429	56.61 423	80.37 417	76.55 428	42.58 426	45.68 425	75.61 413	11.26 436	84.18 420	43.20 422	60.44 416	68.75 420

APD_test2		59.54 389	56.11 393	69.85 402	69.28 429	56.61 423	80.37 417	76.55 428	42.58 426	45.68 425	75.61 413	11.26 436	84.18 420	43.20 422	60.44 416	68.75 420

WB-MVS		67.92 382	67.49 384	69.21 404	81.09 415	41.17 434	88.03 372	78.00 424	73.50 381	62.63 413	83.11 404	63.94 324	86.52 415	25.66 430	51.45 422	79.94 415

PMMVS2		59.60 388	56.40 391	69.21 404	68.83 431	46.58 430	73.02 425	77.48 426	55.07 420	49.21 423	72.95 419	17.43 433	80.04 426	49.32 417	44.33 426	80.99 414

SSC-MVS		67.06 383	66.56 385	68.56 406	80.54 416	40.06 436	87.77 377	77.37 427	72.38 391	61.75 415	82.66 406	63.37 327	86.45 416	24.48 431	48.69 425	79.16 417

Gipuma		57.99 393	54.91 395	67.24 407	88.51 377	65.59 402	52.21 428	90.33 364	43.58 425	42.84 428	51.18 429	20.29 431	85.07 419	34.77 426	70.45 395	51.05 428
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	47.18 22	52.22 395	48.46 399	63.48 408	45.72 439	46.20 431	73.41 424	78.31 422	41.03 428	30.06 431	65.68 423	6.05 438	83.43 423	30.04 428	65.86 406	60.80 423
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		58.82 392	58.24 390	60.56 409	83.13 410	45.09 433	82.32 412	48.22 439	67.61 406	61.70 416	69.15 420	38.75 417	76.05 428	32.01 427	41.31 427	60.55 424

MVE	39.65 23	43.39 397	38.59 403	57.77 410	56.52 436	48.77 429	55.38 427	58.64 435	29.33 431	28.96 432	52.65 428	4.68 439	64.62 432	28.11 429	33.07 429	59.93 425
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.52 396	48.47 398	56.66 411	52.26 438	18.98 442	41.51 430	81.40 414	10.10 432	44.59 427	75.01 416	28.51 423	68.16 429	53.54 413	49.31 424	82.83 411

DeepMVS_CX				56.31 412	74.23 425	51.81 428		56.67 436	44.85 424	48.54 424	75.16 415	27.87 424	58.74 434	40.92 424	52.22 421	58.39 426

kuosan		53.51 394	53.30 397	54.13 413	76.06 422	45.36 432	80.11 419	48.36 438	59.63 417	54.84 419	63.43 426	37.41 418	62.07 433	20.73 433	39.10 428	54.96 427

E-PMN		43.23 398	42.29 400	46.03 414	65.58 433	37.41 437	73.51 423	64.62 432	33.99 429	28.47 433	47.87 430	19.90 432	67.91 430	22.23 432	24.45 430	32.77 429

EMVS		42.07 399	41.12 401	44.92 415	63.45 435	35.56 439	73.65 422	63.48 433	33.05 430	26.88 434	45.45 431	21.27 430	67.14 431	19.80 434	23.02 432	32.06 430

tmp_tt		35.64 400	39.24 402	24.84 416	14.87 440	23.90 441	62.71 426	51.51 437	6.58 434	36.66 430	62.08 427	44.37 412	30.34 436	52.40 414	22.00 433	20.27 431

wuyk23d		21.27 402	20.48 405	23.63 417	68.59 432	36.41 438	49.57 429	6.85 441	9.37 433	7.89 435	4.46 437	4.03 440	31.37 435	17.47 435	16.07 434	3.12 432

test123		8.76 404	11.22 407	1.39 418	0.85 442	0.97 443	85.76 394	0.35 443	0.54 436	2.45 437	8.14 436	0.60 441	0.48 437	2.16 437	0.17 436	2.71 433

testmvs		8.92 403	11.52 406	1.12 419	1.06 441	0.46 444	86.02 391	0.65 442	0.62 435	2.74 436	9.52 435	0.31 442	0.45 438	2.38 436	0.39 435	2.46 434

mmdepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

monomultidepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

test_blank		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet_test		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

DCPMVS		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

cdsmvs_eth3d_5k		22.14 401	29.52 404	0.00 420	0.00 443	0.00 445	0.00 431	95.76 170	0.00 438	0.00 439	94.29 180	75.66 186	0.00 439	0.00 438	0.00 437	0.00 435

pcd_1.5k_mvsjas		6.64 406	8.86 409	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	79.70 135	0.00 439	0.00 438	0.00 437	0.00 435

sosnet-low-res		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

sosnet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uncertanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

Regformer		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

ab-mvs-re		7.82 405	10.43 408	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	93.88 200	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

WAC-MVS						64.08 408								59.14 404

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

PC_three_1452									82.47 255	97.09 13	97.07 62	92.72 1	98.04 176	92.70 70	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 17	91.45 11

eth-test2					0.00 443

eth-test					0.00 443

ZD-MVS					98.15 34	86.62 33		97.07 52	83.63 227	94.19 54	96.91 68	87.57 31	99.26 45	91.99 92	98.44 53

RE-MVS-def			93.68 63		97.92 43	84.57 87	96.28 43	96.76 83	87.46 134	93.75 65	97.43 41	82.94 93		92.73 66	97.80 81	97.88 87

IU-MVS					98.77 5	86.00 50		96.84 73	81.26 291	97.26 9				95.50 31	99.13 3	99.03 8

test_241102_TWO								97.44 15	90.31 32	97.62 5	98.07 15	91.46 10	99.58 10	95.66 25	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 25	92.31 4	99.38 31

9.14			94.47 26		97.79 52		96.08 61	97.44 15	86.13 171	95.10 44	97.40 43	88.34 22	99.22 47	93.25 58	98.70 34

save fliter					97.85 49	85.63 66	95.21 124	96.82 76	89.44 64

test_0728_THIRD									90.75 21	97.04 15	98.05 19	92.09 6	99.55 16	95.64 27	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																96.12 180

test_part2					98.55 12	87.22 19				96.40 23

sam_mvs1												71.70 238				96.12 180

sam_mvs												70.60 251

MTGPA								96.97 57

test_post1							88.00 373				9.81 434	69.31 274	95.53 341	76.65 304

test_post											10.29 433	70.57 255	95.91 326

patchmatchnet-post											83.76 399	71.53 239	96.48 295

MTMP							96.16 52	60.64 434

gm-plane-assit					89.60 369	68.00 392			77.28 345		88.99 351		97.57 206	79.44 276

test9_res														91.91 96	98.71 32	98.07 74

TEST9					97.53 61	86.49 37	94.07 202	96.78 80	81.61 283	92.77 90	96.20 98	87.71 28	99.12 54

test_8					97.49 63	86.30 45	94.02 207	96.76 83	81.86 274	92.70 94	96.20 98	87.63 29	99.02 64

agg_prior2														90.54 118	98.68 37	98.27 57

agg_prior					97.38 66	85.92 57		96.72 90		92.16 106			98.97 78

test_prior4						85.96 54	94.11 197

test_prior2							94.12 195		87.67 132	92.63 96	96.39 93	86.62 40		91.50 104	98.67 40

旧先验2							93.36 237		71.25 397	94.37 50			97.13 254	86.74 163

新几何2							93.11 252

旧先验1					96.79 79	81.81 174		95.67 178			96.81 74	86.69 39			97.66 87	96.97 141

无先验							93.28 245	96.26 125	73.95 377				99.05 58	80.56 261		96.59 160

原ACMM2							92.94 259

test222					96.55 88	81.70 176	92.22 283	95.01 220	68.36 405	90.20 142	96.14 103	80.26 128			97.80 81	96.05 187

testdata2													98.75 104	78.30 288

segment_acmp												87.16 36

testdata1							92.15 285		87.94 119

plane_prior7					94.70 182	82.74 151

plane_prior6					94.52 194	82.75 149						74.23 204

plane_prior5								96.22 130					98.12 161	88.15 142	89.99 231	94.63 239

plane_prior4											94.86 157

plane_prior3						82.75 149			90.26 38	86.91 199

plane_prior2							95.85 83		90.81 19

plane_prior1					94.59 188

plane_prior						82.73 152	95.21 124		89.66 59						89.88 236

n2								0.00 444

nn								0.00 444

door-mid								85.49 401

test11								96.57 101

door								85.33 403

HQP5-MVS						81.56 178

HQP-NCC					94.17 215		94.39 179		88.81 87	85.43 245

ACMP_Plane					94.17 215		94.39 179		88.81 87	85.43 245

BP-MVS														87.11 160

HQP4-MVS										85.43 245			97.96 182			94.51 249

HQP3-MVS								96.04 147							89.77 240

HQP2-MVS												73.83 214

NP-MVS					94.37 205	82.42 161					93.98 193

MDTV_nov1_ep13_2view						55.91 427	87.62 381		73.32 383	84.59 267		70.33 258		74.65 326		95.50 207

MDTV_nov1_ep13			83.56 303		91.69 305	69.93 385	87.75 378	91.54 336	78.60 329	84.86 261	88.90 353	69.54 269	96.03 317	70.25 353	88.93 253

ACMMP++_ref															87.47 276

ACMMP++															88.01 268

Test By Simon												80.02 130

High-resolution multi-view benchmark