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.

PC_three_1452									82.47 280	97.09 16	97.07 66	92.72 1	98.04 185	92.70 74	99.02 12	98.86 12

DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 56	86.00 52	98.29 1	97.49 8	90.75 27	97.62 7	98.06 20	92.59 2	99.61 4	95.64 30	99.02 12	98.86 12

OPU-MVS				96.21 3	98.00 44	90.85 3	97.13 15				97.08 64	92.59 2	98.94 86	92.25 86	98.99 14	98.84 15

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 54	97.13 15	97.44 17	90.31 39	97.71 2	98.07 18	92.31 4	99.58 10	95.66 28	99.13 3	98.84 15

test_241102_ONE					98.77 5	85.99 54		97.44 17	90.26 45	97.71 2	97.96 29	92.31 4	99.38 31

test_0728_THIRD									90.75 27	97.04 18	98.05 23	92.09 6	99.55 16	95.64 30	99.13 3	99.13 2

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 27	87.28 18	95.56 111	97.51 7	89.13 85	97.14 14	97.91 30	91.64 7	99.62 2	94.61 45	99.17 2	98.86 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 57	97.09 17	96.73 92	90.27 43	97.04 18	98.05 23	91.47 8	99.55 16	95.62 32	99.08 7	98.45 37
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					98.78 3	85.93 57	97.19 12	97.47 13	90.27 43	97.64 5	98.13 6	91.47 8

test_241102_TWO								97.44 17	90.31 39	97.62 7	98.07 18	91.46 10	99.58 10	95.66 28	99.12 6	98.98 10

test_one_0601					98.58 11	85.83 63		97.44 17	91.05 21	96.78 23	98.06 20	91.45 11

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 26	97.47 13	91.73 13	96.10 31	96.69 81	89.90 12	99.30 44	94.70 43	98.04 75	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
DeepPCF-MVS	89.96 1	94.20 42	94.77 26	92.49 139	96.52 93	80.00 249	94.00 223	97.08 54	90.05 47	95.65 40	97.29 51	89.66 13	98.97 81	93.95 51	98.71 32	98.50 28

SD-MVS		94.96 15	95.33 10	93.88 66	97.25 74	86.69 28	96.19 52	97.11 53	90.42 35	96.95 20	97.27 52	89.53 14	96.91 291	94.38 47	98.85 20	98.03 84
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
CNVR-MVS		95.40 7	95.37 9	95.50 8	98.11 38	88.51 7	95.29 123	96.96 63	92.09 9	95.32 43	97.08 64	89.49 15	99.33 41	95.10 39	98.85 20	98.66 22

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 30	86.29 46	97.46 7	97.40 22	89.03 90	96.20 30	98.10 12	89.39 16	99.34 38	95.88 27	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MCST-MVS		94.45 30	94.20 46	95.19 13	98.46 19	87.50 16	95.00 146	97.12 50	87.13 153	92.51 106	96.30 98	89.24 17	99.34 38	93.46 57	98.62 46	98.73 19

TSAR-MVS + MP.		94.85 16	94.94 20	94.58 42	98.25 31	86.33 42	96.11 62	96.62 101	88.14 122	96.10 31	96.96 70	89.09 18	98.94 86	94.48 46	98.68 37	98.48 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		95.20 8	95.32 11	94.85 25	96.99 77	86.33 42	97.33 8	97.30 32	91.38 18	95.39 42	97.46 44	88.98 19	99.40 30	94.12 49	98.89 18	98.82 17
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		95.20 8	95.07 16	95.59 6	98.14 37	88.48 8	96.26 49	97.28 35	85.90 186	97.67 4	98.10 12	88.41 20	99.56 12	94.66 44	99.19 1	98.71 21
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
patch_mono-2		93.74 60	94.32 36	92.01 161	97.54 62	78.37 291	93.40 252	97.19 39	88.02 125	94.99 50	97.21 56	88.35 21	98.44 145	94.07 50	98.09 72	99.23 1

9.14			94.47 30		97.79 54		96.08 64	97.44 17	86.13 184	95.10 48	97.40 47	88.34 22	99.22 48	93.25 62	98.70 34

SF-MVS		94.97 14	94.90 24	95.20 12	97.84 52	87.76 10	96.65 35	97.48 12	87.76 138	95.71 38	97.70 38	88.28 23	99.35 37	93.89 53	98.78 26	98.48 31

HPM-MVS++		95.14 10	94.91 22	95.83 4	98.25 31	89.65 4	95.92 81	96.96 63	91.75 12	94.02 65	96.83 76	88.12 24	99.55 16	93.41 60	98.94 16	98.28 57

dcpmvs_2		93.49 65	94.19 47	91.38 198	97.69 59	76.78 331	94.25 200	96.29 125	88.33 113	94.46 53	96.88 73	88.07 25	98.64 122	93.62 56	98.09 72	98.73 19

CSCG		93.23 80	93.05 81	93.76 73	98.04 42	84.07 108	96.22 51	97.37 23	84.15 239	90.05 161	95.66 135	87.77 26	99.15 55	89.91 135	98.27 58	98.07 77

NCCC		94.81 19	94.69 27	95.17 14	97.83 53	87.46 17	95.66 102	96.93 67	92.34 7	93.94 66	96.58 91	87.74 27	99.44 29	92.83 69	98.40 54	98.62 23

TEST9					97.53 63	86.49 37	94.07 215	96.78 84	81.61 309	92.77 94	96.20 102	87.71 28	99.12 57

train_agg		93.44 70	93.08 80	94.52 44	97.53 63	86.49 37	94.07 215	96.78 84	81.86 300	92.77 94	96.20 102	87.63 29	99.12 57	92.14 92	98.69 35	97.94 88

test_8					97.49 65	86.30 45	94.02 220	96.76 87	81.86 300	92.70 98	96.20 102	87.63 29	99.02 67

ZD-MVS					98.15 36	86.62 33		97.07 55	83.63 252	94.19 58	96.91 72	87.57 31	99.26 46	91.99 99	98.44 53

fmvsm_l_conf0.5_n		94.29 36	94.46 31	93.79 72	95.28 151	85.43 72	95.68 99	96.43 114	86.56 170	96.84 22	97.81 35	87.56 32	98.77 108	97.14 13	96.82 112	97.16 145

fmvsm_l_conf0.5_n_a		94.20 42	94.40 33	93.60 78	95.29 150	84.98 79	95.61 107	96.28 128	86.31 176	96.75 24	97.86 33	87.40 33	98.74 112	97.07 15	97.02 105	97.07 150

TSAR-MVS + GP.		93.66 62	93.41 73	94.41 49	96.59 87	86.78 26	94.40 188	93.93 292	89.77 62	94.21 57	95.59 138	87.35 34	98.61 127	92.72 72	96.15 129	97.83 99

APD-MVS		94.24 38	94.07 51	94.75 36	98.06 41	86.90 23	95.88 83	96.94 66	85.68 193	95.05 49	97.18 60	87.31 35	99.07 59	91.90 105	98.61 48	98.28 57
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
segment_acmp												87.16 36

reproduce-ours		94.82 17	94.97 18	94.38 50	97.91 49	85.46 70	95.86 84	97.15 46	89.82 55	95.23 46	98.10 12	87.09 37	99.37 33	95.30 36	98.25 63	98.30 51

our_new_method		94.82 17	94.97 18	94.38 50	97.91 49	85.46 70	95.86 84	97.15 46	89.82 55	95.23 46	98.10 12	87.09 37	99.37 33	95.30 36	98.25 63	98.30 51

旧先验1					96.79 81	81.81 187		95.67 187			96.81 78	86.69 39			97.66 92	96.97 160

lecture		95.10 11	95.46 8	94.01 61	98.40 23	84.36 102	97.70 3	97.78 1	91.19 19	96.22 29	98.08 17	86.64 40	99.37 33	94.91 41	98.26 59	98.29 56

test_prior2							94.12 207		87.67 141	92.63 102	96.39 97	86.62 41		91.50 112	98.67 40

CDPH-MVS		92.83 89	92.30 96	94.44 45	97.79 54	86.11 51	94.06 217	96.66 98	80.09 331	92.77 94	96.63 88	86.62 41	99.04 63	87.40 168	98.66 41	98.17 69

DPM-MVS		92.58 94	91.74 104	95.08 15	96.19 102	89.31 5	92.66 289	96.56 106	83.44 258	91.68 131	95.04 165	86.60 43	98.99 76	85.60 195	97.92 80	96.93 164

reproduce_model		94.76 21	94.92 21	94.29 56	97.92 45	85.18 76	95.95 79	97.19 39	89.67 65	95.27 45	98.16 5	86.53 44	99.36 36	95.42 35	98.15 68	98.33 46

test_fmvsmconf_n		94.60 25	94.81 25	93.98 62	94.62 197	84.96 80	96.15 57	97.35 25	89.37 74	96.03 34	98.11 10	86.36 45	99.01 69	97.45 9	97.83 84	97.96 87

DELS-MVS		93.43 74	93.25 76	93.97 63	95.42 146	85.04 78	93.06 274	97.13 49	90.74 29	91.84 124	95.09 164	86.32 46	99.21 49	91.22 115	98.45 52	97.65 111
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
test_fmvsm_n_1920		94.71 23	95.11 15	93.50 80	95.79 127	84.62 87	96.15 57	97.64 3	89.85 54	97.19 13	97.89 31	86.28 47	98.71 115	97.11 14	98.08 74	97.17 140

ZNCC-MVS		94.47 29	94.28 40	95.03 16	98.52 15	86.96 20	96.85 29	97.32 30	88.24 117	93.15 81	97.04 67	86.17 48	99.62 2	92.40 80	98.81 23	98.52 27

HFP-MVS		94.52 27	94.40 33	94.86 24	98.61 10	86.81 25	96.94 21	97.34 26	88.63 104	93.65 71	97.21 56	86.10 49	99.49 26	92.35 83	98.77 28	98.30 51

MVS_111021_HR		93.45 69	93.31 74	93.84 68	96.99 77	84.84 81	93.24 265	97.24 36	88.76 99	91.60 132	95.85 125	86.07 50	98.66 117	91.91 103	98.16 67	98.03 84

ACMMP_NAP		94.74 22	94.56 28	95.28 10	98.02 43	87.70 11	95.68 99	97.34 26	88.28 116	95.30 44	97.67 39	85.90 51	99.54 20	93.91 52	98.95 15	98.60 24

mamv4		90.92 125	91.78 103	88.33 323	95.67 134	70.75 407	92.92 281	96.02 158	81.90 296	88.11 195	95.34 150	85.88 52	96.97 286	95.22 38	95.01 154	97.26 133

fmvsm_l_conf0.5_n_9		94.65 24	95.28 12	92.77 118	95.95 123	81.83 186	95.53 112	97.12 50	91.68 15	97.89 1	98.06 20	85.71 53	98.65 119	97.32 11	98.26 59	97.83 99

CS-MVS		94.12 46	94.44 32	93.17 93	96.55 90	83.08 147	97.63 4	96.95 65	91.71 14	93.50 77	96.21 101	85.61 54	98.24 162	93.64 55	98.17 66	98.19 67

PHI-MVS		93.89 55	93.65 69	94.62 41	96.84 80	86.43 39	96.69 33	97.49 8	85.15 216	93.56 75	96.28 99	85.60 55	99.31 43	92.45 77	98.79 24	98.12 75

MP-MVS-pluss		94.21 40	94.00 54	94.85 25	98.17 35	86.65 31	94.82 159	97.17 44	86.26 178	92.83 91	97.87 32	85.57 56	99.56 12	94.37 48	98.92 17	98.34 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
GST-MVS		94.21 40	93.97 55	94.90 23	98.41 22	86.82 24	96.54 37	97.19 39	88.24 117	93.26 78	96.83 76	85.48 57	99.59 8	91.43 114	98.40 54	98.30 51

MP-MVS		94.25 37	94.07 51	94.77 35	98.47 18	86.31 44	96.71 32	96.98 59	89.04 88	91.98 117	97.19 59	85.43 58	99.56 12	92.06 97	98.79 24	98.44 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	89.43 2	94.04 48	93.79 60	94.80 33	97.48 66	86.78 26	95.65 104	96.89 72	89.40 73	92.81 92	96.97 69	85.37 59	99.24 47	90.87 123	98.69 35	98.38 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
region2R		94.43 32	94.27 42	94.92 20	98.65 8	86.67 30	96.92 25	97.23 38	88.60 107	93.58 73	97.27 52	85.22 60	99.54 20	92.21 88	98.74 31	98.56 26

CP-MVS		94.34 35	94.21 45	94.74 37	98.39 25	86.64 32	97.60 5	97.24 36	88.53 109	92.73 97	97.23 55	85.20 61	99.32 42	92.15 91	98.83 22	98.25 64

test_fmvsmconf0.1_n		94.20 42	94.31 38	93.88 66	92.46 303	84.80 83	96.18 54	96.82 80	89.29 79	95.68 39	98.11 10	85.10 62	98.99 76	97.38 10	97.75 90	97.86 96

test12				94.34 53	97.13 75	86.15 50		96.29 125		91.04 143		85.08 63	99.01 69		98.13 70	97.86 96

ACMMPR		94.43 32	94.28 40	94.91 21	98.63 9	86.69 28	96.94 21	97.32 30	88.63 104	93.53 76	97.26 54	85.04 64	99.54 20	92.35 83	98.78 26	98.50 28

SPE-MVS-test		94.02 49	94.29 39	93.24 88	96.69 83	83.24 136	97.49 6	96.92 68	92.14 8	92.90 87	95.77 131	85.02 65	98.33 157	93.03 66	98.62 46	98.13 72

XVS		94.45 30	94.32 36	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 32	92.85 89	97.16 62	85.02 65	99.49 26	91.99 99	98.56 50	98.47 34

X-MVStestdata		88.31 214	86.13 263	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 32	92.85 89	23.41 461	85.02 65	99.49 26	91.99 99	98.56 50	98.47 34

MVSMamba_PlusPlus		93.44 70	93.54 71	93.14 95	96.58 89	83.05 148	96.06 68	96.50 111	84.42 236	94.09 61	95.56 140	85.01 68	98.69 116	94.96 40	98.66 41	97.67 110

fmvsm_l_conf0.5_n_3		94.80 20	95.01 17	94.15 59	95.64 136	85.08 77	96.09 63	97.36 24	90.98 22	97.09 16	98.12 9	84.98 69	98.94 86	97.07 15	97.80 86	98.43 39

MSLP-MVS++		93.72 61	94.08 50	92.65 129	97.31 70	83.43 129	95.79 90	97.33 28	90.03 48	93.58 73	96.96 70	84.87 70	97.76 207	92.19 90	98.66 41	96.76 175

HPM-MVS		94.02 49	93.88 56	94.43 47	98.39 25	85.78 65	97.25 11	97.07 55	86.90 162	92.62 103	96.80 80	84.85 71	99.17 51	92.43 78	98.65 44	98.33 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_9		94.99 13	95.50 7	93.44 81	96.51 95	82.25 177	95.76 94	96.92 68	93.37 3	97.63 6	98.43 1	84.82 72	99.16 54	98.15 1	97.92 80	98.90 11

SR-MVS		94.23 39	94.17 49	94.43 47	98.21 34	85.78 65	96.40 39	96.90 71	88.20 120	94.33 55	97.40 47	84.75 73	99.03 64	93.35 61	97.99 77	98.48 31

PGM-MVS		93.96 53	93.72 65	94.68 38	98.43 20	86.22 47	95.30 121	97.78 1	87.45 145	93.26 78	97.33 50	84.62 74	99.51 24	90.75 125	98.57 49	98.32 50

balanced_conf03		93.98 52	94.22 43	93.26 87	96.13 105	83.29 135	96.27 48	96.52 109	89.82 55	95.56 41	95.51 141	84.50 75	98.79 106	94.83 42	98.86 19	97.72 107

EI-MVSNet-Vis-set		93.01 87	92.92 84	93.29 85	95.01 165	83.51 128	94.48 180	95.77 178	90.87 23	92.52 105	96.67 83	84.50 75	99.00 74	91.99 99	94.44 173	97.36 125

MTAPA		94.42 34	94.22 43	95.00 18	98.42 21	86.95 21	94.36 196	96.97 60	91.07 20	93.14 82	97.56 41	84.30 77	99.56 12	93.43 58	98.75 30	98.47 34

SR-MVS-dyc-post		93.82 57	93.82 58	93.82 69	97.92 45	84.57 89	96.28 46	96.76 87	87.46 143	93.75 69	97.43 45	84.24 78	99.01 69	92.73 70	97.80 86	97.88 94

ETV-MVS		92.74 92	92.66 89	92.97 106	95.20 157	84.04 112	95.07 142	96.51 110	90.73 30	92.96 86	91.19 317	84.06 79	98.34 155	91.72 108	96.54 119	96.54 187

EI-MVSNet-UG-set		92.74 92	92.62 91	93.12 96	94.86 179	83.20 138	94.40 188	95.74 181	90.71 31	92.05 115	96.60 90	84.00 80	98.99 76	91.55 111	93.63 186	97.17 140

mPP-MVS		93.99 51	93.78 61	94.63 40	98.50 16	85.90 62	96.87 27	96.91 70	88.70 102	91.83 126	97.17 61	83.96 81	99.55 16	91.44 113	98.64 45	98.43 39

APD-MVS_3200maxsize		93.78 58	93.77 62	93.80 71	97.92 45	84.19 106	96.30 42	96.87 74	86.96 158	93.92 67	97.47 43	83.88 82	98.96 83	92.71 73	97.87 82	98.26 63

EIA-MVS		91.95 103	91.94 100	91.98 165	95.16 159	80.01 248	95.36 116	96.73 92	88.44 110	89.34 172	92.16 280	83.82 83	98.45 143	89.35 140	97.06 103	97.48 120

fmvsm_s_conf0.5_n_3		94.49 28	95.13 13	92.56 134	95.49 144	81.10 211	95.93 80	97.16 45	92.96 4	97.39 11	98.13 6	83.63 84	98.80 104	97.89 3	97.61 93	97.78 103

fmvsm_s_conf0.5_n		93.76 59	94.06 53	92.86 113	95.62 138	83.17 139	96.14 59	96.12 147	88.13 123	95.82 37	98.04 26	83.43 85	98.48 135	96.97 19	96.23 126	96.92 165

casdiffmvs_mvg		92.96 88	92.83 86	93.35 83	94.59 199	83.40 131	95.00 146	96.34 122	90.30 41	92.05 115	96.05 112	83.43 85	98.15 169	92.07 94	95.67 137	98.49 30
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPP-MVSNet		91.70 111	91.56 107	92.13 160	95.88 124	80.50 231	97.33 8	95.25 223	86.15 181	89.76 166	95.60 137	83.42 87	98.32 159	87.37 170	93.25 199	97.56 117

test_fmvsmvis_n_1920		93.44 70	93.55 70	93.10 97	93.67 260	84.26 104	95.83 88	96.14 143	89.00 92	92.43 108	97.50 42	83.37 88	98.72 113	96.61 22	97.44 95	96.32 192

fmvsm_s_conf0.5_n_5		93.96 53	94.18 48	93.30 84	94.79 183	83.81 117	95.77 92	96.74 91	88.02 125	96.23 28	97.84 34	83.36 89	98.83 102	97.49 7	97.34 99	97.25 134

fmvsm_s_conf0.5_n_6		94.11 47	94.56 28	92.76 120	94.98 169	81.96 184	95.79 90	97.29 34	89.31 77	97.52 10	97.61 40	83.25 90	98.88 92	97.05 17	98.22 65	97.43 124

UA-Net		92.83 89	92.54 92	93.68 77	96.10 110	84.71 85	95.66 102	96.39 118	91.92 10	93.22 80	96.49 94	83.16 91	98.87 93	84.47 215	95.47 143	97.45 122

UniMVSNet_NR-MVSNet		89.92 161	89.29 163	91.81 182	93.39 269	83.72 119	94.43 186	97.12 50	89.80 58	86.46 233	93.32 240	83.16 91	97.23 267	84.92 203	81.02 373	94.49 278

EC-MVSNet		93.44 70	93.71 66	92.63 130	95.21 156	82.43 171	97.27 10	96.71 95	90.57 34	92.88 88	95.80 128	83.16 91	98.16 168	93.68 54	98.14 69	97.31 126

fmvsm_s_conf0.5_n_4		93.86 56	94.37 35	92.33 151	95.13 162	80.95 217	95.64 105	96.97 60	89.60 67	96.85 21	97.77 36	83.08 94	98.92 89	97.49 7	96.78 113	97.13 146

fmvsm_s_conf0.5_n_a		93.57 63	93.76 63	93.00 104	95.02 164	83.67 121	96.19 52	96.10 149	87.27 148	95.98 35	98.05 23	83.07 95	98.45 143	96.68 21	95.51 140	96.88 168

MM		95.10 11	94.91 22	95.68 5	96.09 111	88.34 9	96.68 34	94.37 274	95.08 1	94.68 51	97.72 37	82.94 96	99.64 1	97.85 4	98.76 29	99.06 7

RE-MVS-def			93.68 67		97.92 45	84.57 89	96.28 46	96.76 87	87.46 143	93.75 69	97.43 45	82.94 96		92.73 70	97.80 86	97.88 94

新几何1				93.10 97	97.30 71	84.35 103		95.56 196	71.09 424	91.26 140	96.24 100	82.87 98	98.86 95	79.19 305	98.10 71	96.07 208

fmvsm_s_conf0.1_n		93.46 67	93.66 68	92.85 114	93.75 252	83.13 141	96.02 72	95.74 181	87.68 140	95.89 36	98.17 4	82.78 99	98.46 139	96.71 20	96.17 128	96.98 159

原ACMM1				92.01 161	97.34 69	81.05 213		96.81 82	78.89 347	90.45 151	95.92 119	82.65 100	98.84 99	80.68 284	98.26 59	96.14 202

casdiffmvs		92.51 95	92.43 94	92.74 123	94.41 216	81.98 182	94.54 177	96.23 137	89.57 68	91.96 119	96.17 106	82.58 101	98.01 187	90.95 121	95.45 145	98.23 65
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepC-MVS	88.79 3	93.31 76	92.99 83	94.26 57	96.07 113	85.83 63	94.89 152	96.99 58	89.02 91	89.56 167	97.37 49	82.51 102	99.38 31	92.20 89	98.30 57	97.57 116
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS_fast		93.40 75	93.22 77	93.94 65	98.36 27	84.83 82	97.15 14	96.80 83	85.77 190	92.47 107	97.13 63	82.38 103	99.07 59	90.51 130	98.40 54	97.92 91

baseline		92.39 99	92.29 97	92.69 127	94.46 211	81.77 188	94.14 206	96.27 129	89.22 81	91.88 122	96.00 114	82.35 104	97.99 189	91.05 117	95.27 151	98.30 51

sasdasda		93.27 77	92.75 87	94.85 25	95.70 132	87.66 12	96.33 40	96.41 116	90.00 49	94.09 61	94.60 189	82.33 105	98.62 125	92.40 80	92.86 210	98.27 59

canonicalmvs		93.27 77	92.75 87	94.85 25	95.70 132	87.66 12	96.33 40	96.41 116	90.00 49	94.09 61	94.60 189	82.33 105	98.62 125	92.40 80	92.86 210	98.27 59

fmvsm_s_conf0.1_n_a		93.19 81	93.26 75	92.97 106	92.49 301	83.62 124	96.02 72	95.72 184	86.78 164	96.04 33	98.19 3	82.30 107	98.43 147	96.38 23	95.42 146	96.86 169

DP-MVS Recon		91.95 103	91.28 113	93.96 64	98.33 29	85.92 59	94.66 171	96.66 98	82.69 278	90.03 162	95.82 127	82.30 107	99.03 64	84.57 213	96.48 122	96.91 166

PAPR		90.02 155	89.27 165	92.29 155	95.78 128	80.95 217	92.68 288	96.22 138	81.91 295	86.66 230	93.75 231	82.23 109	98.44 145	79.40 304	94.79 160	97.48 120

MVS_Test		91.31 118	91.11 116	91.93 170	94.37 217	80.14 240	93.46 250	95.80 176	86.46 173	91.35 139	93.77 229	82.21 110	98.09 180	87.57 165	94.95 156	97.55 118

nrg030		91.08 124	90.39 128	93.17 93	93.07 281	86.91 22	96.41 38	96.26 133	88.30 115	88.37 192	94.85 176	82.19 111	97.64 218	91.09 116	82.95 343	94.96 252

MGCFI-Net		93.03 86	92.63 90	94.23 58	95.62 138	85.92 59	96.08 64	96.33 123	89.86 53	93.89 68	94.66 186	82.11 112	98.50 133	92.33 85	92.82 213	98.27 59

UniMVSNet (Re)		89.80 165	89.07 169	92.01 161	93.60 263	84.52 92	94.78 162	97.47 13	89.26 80	86.44 236	92.32 275	82.10 113	97.39 254	84.81 206	80.84 377	94.12 291

testdata				90.49 240	96.40 96	77.89 305		95.37 215	72.51 416	93.63 72	96.69 81	82.08 114	97.65 216	83.08 233	97.39 96	95.94 213

PAPM_NR		91.22 120	90.78 125	92.52 137	97.60 61	81.46 197	94.37 194	96.24 136	86.39 175	87.41 213	94.80 178	82.06 115	98.48 135	82.80 241	95.37 147	97.61 113

MG-MVS		91.77 108	91.70 105	92.00 164	97.08 76	80.03 247	93.60 245	95.18 227	87.85 134	90.89 145	96.47 95	82.06 115	98.36 152	85.07 201	97.04 104	97.62 112

CANet		93.54 64	93.20 78	94.55 43	95.65 135	85.73 67	94.94 149	96.69 97	91.89 11	90.69 147	95.88 122	81.99 117	99.54 20	93.14 64	97.95 79	98.39 41

FC-MVSNet-test		90.27 146	90.18 134	90.53 235	93.71 257	79.85 254	95.77 92	97.59 4	89.31 77	86.27 240	94.67 185	81.93 118	97.01 284	84.26 217	88.09 291	94.71 264

fmvsm_s_conf0.5_n_7		93.15 84	93.76 63	91.31 201	94.42 215	79.48 261	94.52 178	97.14 48	89.33 76	94.17 59	98.09 16	81.83 119	97.49 232	96.33 24	98.02 76	96.95 161

FIs		90.51 142	90.35 129	90.99 219	93.99 240	80.98 215	95.73 96	97.54 6	89.15 84	86.72 229	94.68 182	81.83 119	97.24 266	85.18 200	88.31 288	94.76 263

fmvsm_s_conf0.5_n_8		94.56 26	95.12 14	92.87 112	95.96 122	81.32 201	95.76 94	97.57 5	93.48 2	97.53 9	98.32 2	81.78 121	99.13 56	97.91 2	97.81 85	98.16 70

ACMMP		93.24 79	92.88 85	94.30 55	98.09 40	85.33 74	96.86 28	97.45 16	88.33 113	90.15 160	97.03 68	81.44 122	99.51 24	90.85 124	95.74 136	98.04 83
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
Effi-MVS+		91.59 113	91.11 116	93.01 103	94.35 221	83.39 132	94.60 173	95.10 231	87.10 154	90.57 150	93.10 251	81.43 123	98.07 183	89.29 142	94.48 171	97.59 115

MVS_111021_LR		92.47 97	92.29 97	92.98 105	95.99 119	84.43 98	93.08 271	96.09 150	88.20 120	91.12 142	95.72 134	81.33 124	97.76 207	91.74 107	97.37 97	96.75 176

mvs_anonymous		89.37 182	89.32 162	89.51 291	93.47 266	74.22 363	91.65 324	94.83 253	82.91 273	85.45 265	93.79 227	81.23 125	96.36 328	86.47 182	94.09 178	97.94 88

PVSNet_BlendedMVS		89.98 156	89.70 149	90.82 227	96.12 106	81.25 203	93.92 229	96.83 78	83.49 257	89.10 176	92.26 278	81.04 126	98.85 97	86.72 180	87.86 295	92.35 371

PVSNet_Blended		90.73 131	90.32 130	91.98 165	96.12 106	81.25 203	92.55 293	96.83 78	82.04 291	89.10 176	92.56 268	81.04 126	98.85 97	86.72 180	95.91 132	95.84 219

viewmanbaseed2359cas		91.78 107	91.58 106	92.37 147	94.32 222	81.07 212	93.76 237	95.96 162	87.26 149	91.50 134	95.88 122	80.92 128	97.97 193	89.70 136	94.92 157	98.07 77

MVS_0304		94.18 45	93.80 59	95.34 9	94.91 176	87.62 14	95.97 76	93.01 318	92.58 6	94.22 56	97.20 58	80.56 129	99.59 8	97.04 18	98.68 37	98.81 18

alignmvs		93.08 85	92.50 93	94.81 32	95.62 138	87.61 15	95.99 74	96.07 152	89.77 62	94.12 60	94.87 173	80.56 129	98.66 117	92.42 79	93.10 206	98.15 71

API-MVS		90.66 136	90.07 138	92.45 142	96.36 98	84.57 89	96.06 68	95.22 226	82.39 281	89.13 175	94.27 206	80.32 131	98.46 139	80.16 292	96.71 115	94.33 284

PVSNet_Blended_VisFu		91.38 116	90.91 121	92.80 116	96.39 97	83.17 139	94.87 154	96.66 98	83.29 263	89.27 174	94.46 198	80.29 132	99.17 51	87.57 165	95.37 147	96.05 211

test222					96.55 90	81.70 189	92.22 307	95.01 235	68.36 432	90.20 156	96.14 107	80.26 133			97.80 86	96.05 211

diffmvs		91.37 117	91.23 114	91.77 183	93.09 279	80.27 235	92.36 299	95.52 201	87.03 156	91.40 138	94.93 169	80.08 134	97.44 241	92.13 93	94.56 168	97.61 113
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 By Simon												80.02 135

diffmvs_AUTHOR		91.51 114	91.44 109	91.73 184	93.09 279	80.27 235	92.51 294	95.58 195	87.22 150	91.80 127	95.57 139	79.96 136	97.48 233	92.23 87	94.97 155	97.45 122

IterMVS-LS		88.36 213	87.91 207	89.70 280	93.80 249	78.29 294	93.73 239	95.08 233	85.73 191	84.75 286	91.90 296	79.88 137	96.92 290	83.83 223	82.51 349	93.89 301
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 187	88.86 179	89.80 276	91.84 323	78.30 293	93.70 242	95.01 235	85.73 191	87.15 217	95.28 152	79.87 138	97.21 269	83.81 224	87.36 303	93.88 304

TAPA-MVS	84.62 6	88.16 218	87.01 228	91.62 188	96.64 85	80.65 225	94.39 190	96.21 141	76.38 377	86.19 243	95.44 144	79.75 139	98.08 182	62.75 424	95.29 149	96.13 203
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 178	88.64 182	91.71 186	94.74 187	80.81 222	93.54 246	95.10 231	83.11 267	86.82 228	90.67 340	79.74 140	97.75 211	80.51 287	93.55 188	96.57 185

pcd_1.5k_mvsjas		6.64 435	8.86 438	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	79.70 141	0.00 468	0.00 467	0.00 466	0.00 464

PS-MVSNAJss		89.97 157	89.62 152	91.02 216	91.90 321	80.85 221	95.26 127	95.98 159	86.26 178	86.21 242	94.29 203	79.70 141	97.65 216	88.87 150	88.10 289	94.57 270

PS-MVSNAJ		91.18 121	90.92 120	91.96 167	95.26 154	82.60 170	92.09 312	95.70 185	86.27 177	91.84 124	92.46 270	79.70 141	98.99 76	89.08 144	95.86 133	94.29 285

xiu_mvs_v2_base		91.13 122	90.89 122	91.86 176	94.97 170	82.42 172	92.24 305	95.64 192	86.11 185	91.74 130	93.14 249	79.67 144	98.89 91	89.06 145	95.46 144	94.28 286

WR-MVS_H		87.80 227	87.37 218	89.10 300	93.23 272	78.12 297	95.61 107	97.30 32	87.90 130	83.72 317	92.01 291	79.65 145	96.01 343	76.36 333	80.54 381	93.16 343

viewmambaseed2359dif		90.04 154	89.78 148	90.83 225	92.85 293	77.92 302	92.23 306	95.01 235	81.90 296	90.20 156	95.45 143	79.64 146	97.34 256	87.52 167	93.17 201	97.23 138

EPNet		91.79 106	91.02 119	94.10 60	90.10 387	85.25 75	96.03 71	92.05 345	92.83 5	87.39 216	95.78 130	79.39 147	99.01 69	88.13 157	97.48 94	98.05 82
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 258	86.62 244	89.02 303	92.13 312	77.40 322	90.91 342	94.81 255	81.28 316	84.32 303	90.08 356	79.26 148	96.62 304	83.81 224	82.94 344	93.04 348

test_fmvsmconf0.01_n		93.19 81	93.02 82	93.71 76	89.25 400	84.42 100	96.06 68	96.29 125	89.06 86	94.68 51	98.13 6	79.22 149	98.98 80	97.22 12	97.24 100	97.74 105

miper_enhance_ethall		86.90 270	86.18 261	89.06 301	91.66 332	77.58 320	90.22 358	94.82 254	79.16 343	84.48 294	89.10 375	79.19 150	96.66 301	84.06 219	82.94 344	92.94 351

NR-MVSNet		88.58 207	87.47 216	91.93 170	93.04 284	84.16 107	94.77 163	96.25 135	89.05 87	80.04 372	93.29 243	79.02 151	97.05 282	81.71 267	80.05 387	94.59 268

TAMVS		89.21 184	88.29 195	91.96 167	93.71 257	82.62 169	93.30 260	94.19 282	82.22 286	87.78 207	93.94 219	78.83 152	96.95 288	77.70 319	92.98 208	96.32 192

c3_l		87.14 263	86.50 250	89.04 302	92.20 309	77.26 323	91.22 336	94.70 261	82.01 292	84.34 302	90.43 345	78.81 153	96.61 307	83.70 228	81.09 370	93.25 337

1112_ss		88.42 209	87.33 219	91.72 185	94.92 174	80.98 215	92.97 279	94.54 266	78.16 364	83.82 314	93.88 224	78.78 154	97.91 200	79.45 300	89.41 268	96.26 196

CDS-MVSNet		89.45 175	88.51 186	92.29 155	93.62 262	83.61 126	93.01 275	94.68 262	81.95 293	87.82 206	93.24 245	78.69 155	96.99 285	80.34 289	93.23 200	96.28 195
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 169	88.92 175	91.67 187	95.47 145	81.15 208	92.38 298	94.78 257	83.11 267	89.06 178	94.32 201	78.67 156	96.61 307	81.57 268	90.89 242	97.24 135

CPTT-MVS		91.99 102	91.80 102	92.55 135	98.24 33	81.98 182	96.76 31	96.49 112	81.89 299	90.24 154	96.44 96	78.59 157	98.61 127	89.68 137	97.85 83	97.06 151

IS-MVSNet		91.43 115	91.09 118	92.46 140	95.87 126	81.38 200	96.95 20	93.69 304	89.72 64	89.50 170	95.98 116	78.57 158	97.77 206	83.02 235	96.50 121	98.22 66

OMC-MVS		91.23 119	90.62 127	93.08 99	96.27 100	84.07 108	93.52 247	95.93 164	86.95 159	89.51 168	96.13 108	78.50 159	98.35 154	85.84 193	92.90 209	96.83 174

IMVS_0403		89.97 157	89.64 151	90.96 222	93.72 253	77.75 313	93.00 276	95.34 218	85.53 199	88.77 185	94.49 194	78.49 160	97.84 203	84.75 207	92.65 215	97.28 129

PCF-MVS	84.11 10	87.74 229	86.08 267	92.70 126	94.02 235	84.43 98	89.27 378	95.87 172	73.62 406	84.43 297	94.33 200	78.48 161	98.86 95	70.27 380	94.45 172	94.81 261
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 215	88.32 194	88.27 325	94.71 192	72.41 389	93.15 266	90.98 376	87.77 137	79.25 382	91.96 293	78.35 162	95.75 357	83.04 234	95.62 138	96.65 181

HY-MVS	83.01 12	89.03 193	87.94 204	92.29 155	94.86 179	82.77 156	92.08 313	94.49 268	81.52 312	86.93 220	92.79 262	78.32 163	98.23 163	79.93 294	90.55 246	95.88 217

GeoE		90.05 153	89.43 158	91.90 175	95.16 159	80.37 234	95.80 89	94.65 263	83.90 244	87.55 212	94.75 179	78.18 164	97.62 220	81.28 272	93.63 186	97.71 108

NormalMVS		93.46 67	93.16 79	94.37 52	98.40 23	86.20 48	96.30 42	96.27 129	91.65 16	92.68 99	96.13 108	77.97 165	98.84 99	90.75 125	98.26 59	98.07 77

SymmetryMVS		92.81 91	92.31 95	94.32 54	96.15 103	86.20 48	96.30 42	94.43 270	91.65 16	92.68 99	96.13 108	77.97 165	98.84 99	90.75 125	94.72 161	97.92 91

MVS		87.44 246	86.10 266	91.44 196	92.61 300	83.62 124	92.63 290	95.66 189	67.26 434	81.47 350	92.15 281	77.95 167	98.22 165	79.71 296	95.48 142	92.47 365

MVSFormer		91.68 112	91.30 111	92.80 116	93.86 245	83.88 115	95.96 77	95.90 168	84.66 232	91.76 128	94.91 170	77.92 168	97.30 258	89.64 138	97.11 101	97.24 135

lupinMVS		90.92 125	90.21 132	93.03 102	93.86 245	83.88 115	92.81 285	93.86 296	79.84 334	91.76 128	94.29 203	77.92 168	98.04 185	90.48 131	97.11 101	97.17 140

Test_1112_low_res		87.65 232	86.51 249	91.08 212	94.94 173	79.28 271	91.77 319	94.30 277	76.04 382	83.51 324	92.37 273	77.86 170	97.73 212	78.69 309	89.13 275	96.22 197

VNet		92.24 100	91.91 101	93.24 88	96.59 87	83.43 129	94.84 158	96.44 113	89.19 83	94.08 64	95.90 120	77.85 171	98.17 167	88.90 148	93.38 195	98.13 72

icg_test_0407_2		89.15 185	88.97 172	89.68 284	93.72 253	77.75 313	88.26 395	95.34 218	85.53 199	88.34 193	94.49 194	77.69 172	93.99 394	84.75 207	92.65 215	97.28 129

IMVS_0407		89.85 164	89.51 155	90.88 224	93.72 253	77.75 313	93.07 273	95.34 218	85.53 199	88.34 193	94.49 194	77.69 172	97.60 221	84.75 207	92.65 215	97.28 129

fmvsm_s_conf0.5_n_2		93.47 66	93.83 57	92.39 146	95.36 147	81.19 207	95.20 135	96.56 106	90.37 37	97.13 15	98.03 27	77.47 174	98.96 83	97.79 5	96.58 118	97.03 154

mvsany_test1		85.42 309	85.30 294	85.77 383	87.95 418	75.41 351	87.61 409	80.97 444	76.82 374	88.68 186	95.83 126	77.44 175	90.82 430	85.90 191	86.51 310	91.08 402

DU-MVS		89.34 183	88.50 187	91.85 178	93.04 284	83.72 119	94.47 183	96.59 103	89.50 69	86.46 233	93.29 243	77.25 176	97.23 267	84.92 203	81.02 373	94.59 268

Baseline_NR-MVSNet		87.07 265	86.63 243	88.40 318	91.44 336	77.87 306	94.23 203	92.57 330	84.12 240	85.74 253	92.08 287	77.25 176	96.04 339	82.29 250	79.94 388	91.30 394

jason		90.80 128	90.10 136	92.90 110	93.04 284	83.53 127	93.08 271	94.15 285	80.22 328	91.41 137	94.91 170	76.87 178	97.93 198	90.28 132	96.90 108	97.24 135
jason: jason.
PAPM		86.68 280	85.39 290	90.53 235	93.05 283	79.33 270	89.79 368	94.77 258	78.82 350	81.95 346	93.24 245	76.81 179	97.30 258	66.94 404	93.16 202	94.95 256

Vis-MVSNet (Re-imp)		89.59 170	89.44 157	90.03 262	95.74 129	75.85 345	95.61 107	90.80 383	87.66 142	87.83 205	95.40 147	76.79 180	96.46 321	78.37 310	96.73 114	97.80 101

baseline1		88.10 219	87.28 221	90.57 232	94.96 171	80.07 243	94.27 199	91.29 369	86.74 165	87.41 213	94.00 216	76.77 181	96.20 334	80.77 281	79.31 396	95.44 233

114514_t		89.51 172	88.50 187	92.54 136	98.11 38	81.99 181	95.16 138	96.36 121	70.19 428	85.81 250	95.25 154	76.70 182	98.63 124	82.07 256	96.86 111	97.00 158

PLC	84.53 7	89.06 191	88.03 200	92.15 159	97.27 73	82.69 163	94.29 198	95.44 209	79.71 336	84.01 311	94.18 209	76.68 183	98.75 109	77.28 323	93.41 194	95.02 248
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 197	87.95 203	91.49 193	92.68 299	83.01 151	94.92 151	96.31 124	89.88 52	85.53 259	93.85 226	76.63 184	96.96 287	81.91 260	79.87 390	94.50 276

MAR-MVS		90.30 145	89.37 160	93.07 101	96.61 86	84.48 94	95.68 99	95.67 187	82.36 283	87.85 203	92.85 256	76.63 184	98.80 104	80.01 293	96.68 116	95.91 214
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
fmvsm_s_conf0.1_n_2		93.16 83	93.42 72	92.37 147	94.62 197	81.13 209	95.23 128	95.89 170	90.30 41	96.74 25	98.02 28	76.14 186	98.95 85	97.64 6	96.21 127	97.03 154

SSM_0407		90.47 143	89.80 147	92.46 140	94.76 184	82.66 164	93.98 225	95.00 239	85.41 204	88.96 180	95.35 148	76.13 187	97.88 202	85.46 198	93.15 203	96.85 170

SSM_0404		90.73 131	90.08 137	92.69 127	95.00 168	83.13 141	94.32 197	95.00 239	85.41 204	89.84 163	95.35 148	76.13 187	97.98 191	85.46 198	94.18 177	96.95 161

WR-MVS		88.38 211	87.67 211	90.52 237	93.30 271	80.18 238	93.26 263	95.96 162	88.57 108	85.47 264	92.81 260	76.12 189	96.91 291	81.24 273	82.29 353	94.47 281

v8		87.50 245	86.71 237	89.89 269	91.37 341	79.40 264	94.50 179	95.38 213	84.81 227	83.60 322	91.33 312	76.05 190	97.42 243	82.84 239	80.51 384	92.84 355

v148		87.04 266	86.32 256	89.21 296	90.94 361	77.26 323	93.71 241	94.43 270	84.84 226	84.36 301	90.80 334	76.04 191	97.05 282	82.12 253	79.60 393	93.31 334

mamba_0408		89.06 191	87.92 205	92.50 138	94.76 184	82.66 164	79.84 447	94.64 264	85.18 209	88.96 180	95.00 166	76.00 192	97.98 191	83.74 226	93.15 203	96.85 170

SSM_04072		88.57 208	87.92 205	90.51 238	94.76 184	82.66 164	79.84 447	94.64 264	85.18 209	88.96 180	95.00 166	76.00 192	92.03 418	83.74 226	93.15 203	96.85 170

eth_miper_zixun_eth		86.50 287	85.77 281	88.68 312	91.94 318	75.81 346	90.47 350	94.89 247	82.05 289	84.05 309	90.46 344	75.96 194	96.77 295	82.76 242	79.36 395	93.46 330

3Dnovator+	87.14 4	92.42 98	91.37 110	95.55 7	95.63 137	88.73 6	97.07 19	96.77 86	90.84 24	84.02 310	96.62 89	75.95 195	99.34 38	87.77 162	97.68 91	98.59 25

h-mvs33		90.80 128	90.15 135	92.75 122	96.01 115	82.66 164	95.43 115	95.53 200	89.80 58	93.08 83	95.64 136	75.77 196	99.00 74	92.07 94	78.05 400	96.60 182

hse-mvs2		89.88 163	89.34 161	91.51 192	94.83 181	81.12 210	93.94 227	93.91 295	89.80 58	93.08 83	93.60 234	75.77 196	97.66 215	92.07 94	77.07 407	95.74 224

BH-untuned		88.60 205	88.13 199	90.01 265	95.24 155	78.50 287	93.29 261	94.15 285	84.75 229	84.46 295	93.40 237	75.76 198	97.40 251	77.59 320	94.52 170	94.12 291

DIV-MVS_self_test		86.53 285	85.78 279	88.75 309	92.02 317	76.45 337	90.74 344	94.30 277	81.83 302	83.34 328	90.82 333	75.75 199	96.57 310	81.73 266	81.52 365	93.24 338

BH-w/o		87.57 241	87.05 226	89.12 299	94.90 177	77.90 304	92.41 296	93.51 306	82.89 274	83.70 318	91.34 311	75.75 199	97.07 279	75.49 341	93.49 191	92.39 369

cl____		86.52 286	85.78 279	88.75 309	92.03 316	76.46 336	90.74 344	94.30 277	81.83 302	83.34 328	90.78 335	75.74 201	96.57 310	81.74 265	81.54 364	93.22 339

cdsmvs_eth3d_5k		22.14 430	29.52 433	0.00 449	0.00 472	0.00 474	0.00 460	95.76 179	0.00 467	0.00 468	94.29 203	75.66 202	0.00 468	0.00 467	0.00 466	0.00 464

CNLPA		89.07 190	87.98 202	92.34 150	96.87 79	84.78 84	94.08 214	93.24 310	81.41 313	84.46 295	95.13 163	75.57 203	96.62 304	77.21 324	93.84 183	95.61 231

CHOSEN 1792x2688		88.84 197	87.69 210	92.30 154	96.14 104	81.42 199	90.01 365	95.86 173	74.52 397	87.41 213	93.94 219	75.46 204	98.36 152	80.36 288	95.53 139	97.12 147

CP-MVSNet		87.63 235	87.26 223	88.74 311	93.12 277	76.59 335	95.29 123	96.58 104	88.43 111	83.49 325	92.98 254	75.28 205	95.83 352	78.97 306	81.15 369	93.79 310

v10		87.25 255	86.38 252	89.85 271	91.19 347	79.50 260	94.48 180	95.45 207	83.79 249	83.62 321	91.19 317	75.13 206	97.42 243	81.94 259	80.60 379	92.63 361

Vis-MVSNet		91.75 109	91.23 114	93.29 85	95.32 149	83.78 118	96.14 59	95.98 159	89.89 51	90.45 151	96.58 91	75.09 207	98.31 160	84.75 207	96.90 108	97.78 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 196	88.26 197	90.94 223	94.05 234	80.78 223	91.71 321	95.38 213	81.55 311	88.63 187	93.91 223	75.04 208	95.47 370	82.47 245	91.61 230	96.57 185

v1144		87.61 238	86.79 235	90.06 261	91.01 356	79.34 267	93.95 226	95.42 212	83.36 262	85.66 255	91.31 315	74.98 209	97.42 243	83.37 230	82.06 355	93.42 331

miper_lstm_enhance		85.27 314	84.59 312	87.31 351	91.28 345	74.63 358	87.69 406	94.09 289	81.20 320	81.36 353	89.85 364	74.97 210	94.30 389	81.03 277	79.84 391	93.01 349

test_yl		90.69 133	90.02 142	92.71 124	95.72 130	82.41 174	94.11 209	95.12 229	85.63 194	91.49 135	94.70 180	74.75 211	98.42 148	86.13 188	92.53 222	97.31 126

DCV-MVSNet		90.69 133	90.02 142	92.71 124	95.72 130	82.41 174	94.11 209	95.12 229	85.63 194	91.49 135	94.70 180	74.75 211	98.42 148	86.13 188	92.53 222	97.31 126

V42		87.68 230	86.86 230	90.15 255	90.58 377	80.14 240	94.24 202	95.28 222	83.66 251	85.67 254	91.33 312	74.73 213	97.41 249	84.43 216	81.83 359	92.89 353

FA-MVS(test-final)		89.66 167	88.91 176	91.93 170	94.57 203	80.27 235	91.36 329	94.74 259	84.87 224	89.82 164	92.61 267	74.72 214	98.47 138	83.97 221	93.53 189	97.04 153

viewmsd2359difaftdt		89.43 177	89.05 171	90.56 234	92.89 292	77.00 327	92.81 285	94.52 267	87.03 156	89.77 165	95.79 129	74.67 215	97.51 229	88.97 147	84.98 321	97.17 140

XVG-OURS-SEG-HR		89.95 159	89.45 156	91.47 195	94.00 239	81.21 206	91.87 317	96.06 154	85.78 189	88.55 188	95.73 133	74.67 215	97.27 262	88.71 151	89.64 266	95.91 214

BP-MVS1		92.48 96	92.07 99	93.72 75	94.50 208	84.39 101	95.90 82	94.30 277	90.39 36	92.67 101	95.94 118	74.46 217	98.65 119	93.14 64	97.35 98	98.13 72

v2v482		87.84 225	87.06 225	90.17 253	90.99 357	79.23 274	94.00 223	95.13 228	84.87 224	85.53 259	92.07 289	74.45 218	97.45 238	84.71 212	81.75 361	93.85 308

CLD-MVS		89.47 174	88.90 177	91.18 207	94.22 226	82.07 180	92.13 310	96.09 150	87.90 130	85.37 274	92.45 271	74.38 219	97.56 225	87.15 173	90.43 248	93.93 300
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 232	86.85 231	90.03 262	92.14 311	80.60 228	93.76 237	95.23 224	82.94 272	84.60 289	94.02 214	74.27 220	95.49 369	81.04 275	83.68 335	94.01 299

HQP_MVS		90.60 140	90.19 133	91.82 180	94.70 193	82.73 160	95.85 86	96.22 138	90.81 25	86.91 222	94.86 174	74.23 221	98.12 170	88.15 155	89.99 255	94.63 265

plane_prior6					94.52 206	82.75 157						74.23 221

v144192		87.19 261	86.35 254	89.74 277	90.64 375	78.24 295	93.92 229	95.43 210	81.93 294	85.51 261	91.05 326	74.21 223	97.45 238	82.86 238	81.56 363	93.53 325

VPA-MVSNet		89.62 168	88.96 173	91.60 189	93.86 245	82.89 155	95.46 113	97.33 28	87.91 129	88.43 191	93.31 241	74.17 224	97.40 251	87.32 171	82.86 348	94.52 273

ab-mvs		89.41 178	88.35 191	92.60 131	95.15 161	82.65 168	92.20 308	95.60 194	83.97 243	88.55 188	93.70 233	74.16 225	98.21 166	82.46 246	89.37 269	96.94 163

1314		87.51 243	86.57 246	90.34 250	92.42 305	79.74 257	92.63 290	95.35 217	78.35 359	80.14 369	91.62 306	74.05 226	97.15 271	81.05 274	93.53 189	94.12 291

test_djsdf		89.03 193	88.64 182	90.21 252	90.74 372	79.28 271	95.96 77	95.90 168	84.66 232	85.33 276	92.94 255	74.02 227	97.30 258	89.64 138	88.53 281	94.05 297

cl22		86.78 274	85.98 271	89.18 298	92.34 306	77.62 319	90.84 343	94.13 287	81.33 315	83.97 312	90.15 353	73.96 228	96.60 309	84.19 218	82.94 344	93.33 333

SD_0403		84.71 327	84.65 309	84.92 393	92.95 289	65.95 428	92.07 314	93.23 311	83.82 248	79.03 383	93.73 232	73.90 229	92.91 412	63.02 423	90.05 254	95.89 216

AdaColmap		89.89 162	89.07 169	92.37 147	97.41 67	83.03 149	94.42 187	95.92 165	82.81 275	86.34 239	94.65 187	73.89 230	99.02 67	80.69 283	95.51 140	95.05 247

HyFIR lowres test		88.09 220	86.81 233	91.93 170	96.00 116	80.63 226	90.01 365	95.79 177	73.42 408	87.68 209	92.10 286	73.86 231	97.96 194	80.75 282	91.70 229	97.19 139

HQP2-MVS												73.83 232

HQP-MVS		89.80 165	89.28 164	91.34 200	94.17 228	81.56 191	94.39 190	96.04 155	88.81 96	85.43 268	93.97 218	73.83 232	97.96 194	87.11 175	89.77 264	94.50 276

3Dnovator	86.66 5	91.73 110	90.82 124	94.44 45	94.59 199	86.37 41	97.18 13	97.02 57	89.20 82	84.31 305	96.66 84	73.74 234	99.17 51	86.74 178	97.96 78	97.79 102

EPNet_dtu		86.49 289	85.94 274	88.14 330	90.24 385	72.82 379	94.11 209	92.20 341	86.66 169	79.42 381	92.36 274	73.52 235	95.81 354	71.26 372	93.66 185	95.80 222
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 331	83.06 338	88.54 315	91.72 328	78.44 288	95.18 136	92.82 324	82.73 277	79.67 378	92.12 283	73.49 236	95.96 345	71.10 377	68.73 431	91.21 396

Effi-MVS+-dtu		88.65 203	88.35 191	89.54 288	93.33 270	76.39 338	94.47 183	94.36 275	87.70 139	85.43 268	89.56 370	73.45 237	97.26 264	85.57 196	91.28 234	94.97 249

GDP-MVS		92.04 101	91.46 108	93.75 74	94.55 205	84.69 86	95.60 110	96.56 106	87.83 135	93.07 85	95.89 121	73.44 238	98.65 119	90.22 133	96.03 131	97.91 93

baseline2		86.50 287	85.39 290	89.84 272	91.12 352	76.70 333	91.88 316	88.58 414	82.35 284	79.95 374	90.95 328	73.42 239	97.63 219	80.27 291	89.95 258	95.19 242

PEN-MVS		86.80 273	86.27 259	88.40 318	92.32 307	75.71 348	95.18 136	96.38 119	87.97 127	82.82 334	93.15 248	73.39 240	95.92 347	76.15 337	79.03 398	93.59 323

v1192		87.25 255	86.33 255	90.00 266	90.76 371	79.04 275	93.80 235	95.48 202	82.57 279	85.48 263	91.18 319	73.38 241	97.42 243	82.30 249	82.06 355	93.53 325

guyue		91.12 123	90.84 123	91.96 167	94.59 199	80.57 229	94.87 154	93.71 303	88.96 93	91.14 141	95.22 155	73.22 242	97.76 207	92.01 98	93.81 184	97.54 119

QAPM		89.51 172	88.15 198	93.59 79	94.92 174	84.58 88	96.82 30	96.70 96	78.43 358	83.41 326	96.19 105	73.18 243	99.30 44	77.11 326	96.54 119	96.89 167

tpmrst		85.35 311	84.99 300	86.43 374	90.88 366	67.88 422	88.71 387	91.43 366	80.13 330	86.08 245	88.80 383	73.05 244	96.02 341	82.48 244	83.40 341	95.40 235

PS-CasMVS		87.32 252	86.88 229	88.63 314	92.99 287	76.33 340	95.33 118	96.61 102	88.22 119	83.30 330	93.07 252	73.03 245	95.79 356	78.36 311	81.00 375	93.75 317

DTE-MVSNet		86.11 295	85.48 288	87.98 333	91.65 333	74.92 355	94.93 150	95.75 180	87.36 147	82.26 340	93.04 253	72.85 246	95.82 353	74.04 356	77.46 404	93.20 341

MVSTER		88.84 197	88.29 195	90.51 238	92.95 289	80.44 232	93.73 239	95.01 235	84.66 232	87.15 217	93.12 250	72.79 247	97.21 269	87.86 161	87.36 303	93.87 305

v1921920		86.97 268	86.06 268	89.69 281	90.53 380	78.11 298	93.80 235	95.43 210	81.90 296	85.33 276	91.05 326	72.66 248	97.41 249	82.05 257	81.80 360	93.53 325

DP-MVS		87.25 255	85.36 292	92.90 110	97.65 60	83.24 136	94.81 160	92.00 347	74.99 392	81.92 347	95.00 166	72.66 248	99.05 61	66.92 406	92.33 225	96.40 189

VortexMVS		88.42 209	88.01 201	89.63 285	93.89 244	78.82 277	93.82 234	95.47 203	86.67 168	84.53 293	91.99 292	72.62 250	96.65 302	89.02 146	84.09 329	93.41 332

v7n		86.81 272	85.76 282	89.95 267	90.72 373	79.25 273	95.07 142	95.92 165	84.45 235	82.29 339	90.86 330	72.60 251	97.53 227	79.42 303	80.52 383	93.08 347

OPM-MVS		90.12 149	89.56 154	91.82 180	93.14 276	83.90 114	94.16 205	95.74 181	88.96 93	87.86 202	95.43 146	72.48 252	97.91 200	88.10 159	90.18 253	93.65 322
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 224	86.32 256	92.59 132	96.07 113	82.92 154	95.23 128	94.92 246	75.66 384	82.89 333	95.98 116	72.48 252	99.21 49	68.43 394	95.23 152	95.64 228

pm-mvs1		86.61 281	85.54 286	89.82 273	91.44 336	80.18 238	95.28 125	94.85 251	83.84 246	81.66 348	92.62 266	72.45 254	96.48 318	79.67 297	78.06 399	92.82 356

KinetiMVS		91.82 105	91.30 111	93.39 82	94.72 190	83.36 133	95.45 114	96.37 120	90.33 38	92.17 112	96.03 113	72.32 255	98.75 109	87.94 160	96.34 124	98.07 77

PMMVS		85.71 304	84.96 302	87.95 334	88.90 404	77.09 325	88.68 388	90.06 397	72.32 418	86.47 232	90.76 336	72.15 256	94.40 386	81.78 264	93.49 191	92.36 370

SDMVSNet		90.19 148	89.61 153	91.93 170	96.00 116	83.09 146	92.89 282	95.98 159	88.73 100	86.85 226	95.20 159	72.09 257	97.08 277	88.90 148	89.85 261	95.63 229

PatchmatchNet		85.85 300	84.70 308	89.29 295	91.76 327	75.54 349	88.49 391	91.30 368	81.63 308	85.05 281	88.70 385	71.71 258	96.24 333	74.61 353	89.05 276	96.08 207
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 259				96.12 204

patchmatchnet-post											83.76 428	71.53 260	96.48 318

v1240		86.78 274	85.85 277	89.56 287	90.45 382	77.79 310	93.61 244	95.37 215	81.65 306	85.43 268	91.15 321	71.50 261	97.43 242	81.47 270	82.05 357	93.47 329

anonymousdsp		87.84 225	87.09 224	90.12 257	89.13 401	80.54 230	94.67 170	95.55 197	82.05 289	83.82 314	92.12 283	71.47 262	97.15 271	87.15 173	87.80 298	92.67 359

Patchmatch-test		81.37 365	79.30 372	87.58 343	90.92 363	74.16 365	80.99 442	87.68 421	70.52 426	76.63 403	88.81 381	71.21 263	92.76 413	60.01 432	86.93 309	95.83 220

F-COLMAP		87.95 223	86.80 234	91.40 197	96.35 99	80.88 220	94.73 166	95.45 207	79.65 337	82.04 345	94.61 188	71.13 264	98.50 133	76.24 336	91.05 240	94.80 262

pmmvs4		85.43 308	83.86 325	90.16 254	90.02 390	82.97 153	90.27 352	92.67 328	75.93 383	80.73 360	91.74 300	71.05 265	95.73 359	78.85 308	83.46 339	91.78 381

CR-MVSNet		85.35 311	83.76 326	90.12 257	90.58 377	79.34 267	85.24 425	91.96 351	78.27 361	85.55 257	87.87 398	71.03 266	95.61 362	73.96 358	89.36 270	95.40 235

Patchmtry		82.71 348	80.93 354	88.06 331	90.05 389	76.37 339	84.74 430	91.96 351	72.28 419	81.32 354	87.87 398	71.03 266	95.50 368	68.97 390	80.15 386	92.32 372

CL-MVSNet_self_test		81.74 357	80.53 355	85.36 387	85.96 427	72.45 388	90.25 354	93.07 316	81.24 318	79.85 377	87.29 404	70.93 268	92.52 414	66.95 403	69.23 427	91.11 400

RPMNet		83.95 338	81.53 349	91.21 205	90.58 377	79.34 267	85.24 425	96.76 87	71.44 422	85.55 257	82.97 434	70.87 269	98.91 90	61.01 428	89.36 270	95.40 235

Patchmatch-RL test		81.67 358	79.96 364	86.81 368	85.42 432	71.23 400	82.17 440	87.50 422	78.47 356	77.19 398	82.50 436	70.81 270	93.48 403	82.66 243	72.89 417	95.71 227

CostFormer		85.77 303	84.94 303	88.26 326	91.16 350	72.58 387	89.47 376	91.04 375	76.26 380	86.45 235	89.97 360	70.74 271	96.86 294	82.35 248	87.07 308	95.34 239

AstraMVS		90.69 133	90.30 131	91.84 179	93.81 248	79.85 254	94.76 164	92.39 333	88.96 93	91.01 144	95.87 124	70.69 272	97.94 197	92.49 76	92.70 214	97.73 106

sam_mvs												70.60 273

xiu_mvs_v1_base_debu		90.64 137	90.05 139	92.40 143	93.97 241	84.46 95	93.32 256	95.46 204	85.17 211	92.25 109	94.03 211	70.59 274	98.57 130	90.97 118	94.67 163	94.18 287

xiu_mvs_v1_base		90.64 137	90.05 139	92.40 143	93.97 241	84.46 95	93.32 256	95.46 204	85.17 211	92.25 109	94.03 211	70.59 274	98.57 130	90.97 118	94.67 163	94.18 287

xiu_mvs_v1_base_debi		90.64 137	90.05 139	92.40 143	93.97 241	84.46 95	93.32 256	95.46 204	85.17 211	92.25 109	94.03 211	70.59 274	98.57 130	90.97 118	94.67 163	94.18 287

test_post											10.29 462	70.57 277	95.91 349

CANet_DTU		90.26 147	89.41 159	92.81 115	93.46 267	83.01 151	93.48 248	94.47 269	89.43 72	87.76 208	94.23 208	70.54 278	99.03 64	84.97 202	96.39 123	96.38 190

BH-RMVSNet		88.37 212	87.48 215	91.02 216	95.28 151	79.45 263	92.89 282	93.07 316	85.45 203	86.91 222	94.84 177	70.35 279	97.76 207	73.97 357	94.59 167	95.85 218

Fast-Effi-MVS+-dtu		87.44 246	86.72 236	89.63 285	92.04 315	77.68 318	94.03 219	93.94 291	85.81 188	82.42 338	91.32 314	70.33 280	97.06 280	80.33 290	90.23 252	94.14 290

MDTV_nov1_ep13_2view						55.91 456	87.62 408		73.32 409	84.59 290		70.33 280		74.65 352		95.50 232

ACMM	84.12 9	89.14 186	88.48 190	91.12 208	94.65 196	81.22 205	95.31 119	96.12 147	85.31 208	85.92 248	94.34 199	70.19 282	98.06 184	85.65 194	88.86 278	94.08 295
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RRT-MVS		90.85 127	90.70 126	91.30 202	94.25 224	76.83 330	94.85 157	96.13 146	89.04 88	90.23 155	94.88 172	70.15 283	98.72 113	91.86 106	94.88 158	98.34 44

LuminaMVS		90.55 141	89.81 146	92.77 118	92.78 296	84.21 105	94.09 213	94.17 284	85.82 187	91.54 133	94.14 210	69.93 284	97.92 199	91.62 110	94.21 176	96.18 200

ET-MVSNet_ETH3D		87.51 243	85.91 275	92.32 152	93.70 259	83.93 113	92.33 302	90.94 379	84.16 238	72.09 427	92.52 269	69.90 285	95.85 351	89.20 143	88.36 287	97.17 140

LPG-MVS_test		89.45 175	88.90 177	91.12 208	94.47 209	81.49 195	95.30 121	96.14 143	86.73 166	85.45 265	95.16 161	69.89 286	98.10 172	87.70 163	89.23 273	93.77 315

LGP-MVS_train				91.12 208	94.47 209	81.49 195		96.14 143	86.73 166	85.45 265	95.16 161	69.89 286	98.10 172	87.70 163	89.23 273	93.77 315

CHOSEN 280x420		85.15 316	83.99 323	88.65 313	92.47 302	78.40 290	79.68 449	92.76 325	74.90 394	81.41 352	89.59 368	69.85 288	95.51 366	79.92 295	95.29 149	92.03 377

LTVRE_ROB	82.13 13	86.26 294	84.90 304	90.34 250	94.44 213	81.50 193	92.31 304	94.89 247	83.03 269	79.63 379	92.67 264	69.69 289	97.79 205	71.20 373	86.26 312	91.72 382
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
OpenMVS	83.78 11	88.74 201	87.29 220	93.08 99	92.70 298	85.39 73	96.57 36	96.43 114	78.74 353	80.85 358	96.07 111	69.64 290	99.01 69	78.01 317	96.65 117	94.83 260

MonoMVSNet		86.89 271	86.55 247	87.92 336	89.46 399	73.75 367	94.12 207	93.10 314	87.82 136	85.10 279	90.76 336	69.59 291	94.94 381	86.47 182	82.50 350	95.07 246

MDTV_nov1_ep13			83.56 329		91.69 331	69.93 413	87.75 405	91.54 362	78.60 355	84.86 284	88.90 380	69.54 292	96.03 340	70.25 381	88.93 277

AUN-MVS		87.78 228	86.54 248	91.48 194	94.82 182	81.05 213	93.91 231	93.93 292	83.00 270	86.93 220	93.53 235	69.50 293	97.67 213	86.14 186	77.12 406	95.73 226

PatchT		82.68 349	81.27 351	86.89 366	90.09 388	70.94 406	84.06 432	90.15 394	74.91 393	85.63 256	83.57 429	69.37 294	94.87 382	65.19 412	88.50 283	94.84 259

VPNet		88.20 217	87.47 216	90.39 246	93.56 264	79.46 262	94.04 218	95.54 199	88.67 103	86.96 219	94.58 192	69.33 295	97.15 271	84.05 220	80.53 382	94.56 271

ACMP	84.23 8	89.01 195	88.35 191	90.99 219	94.73 188	81.27 202	95.07 142	95.89 170	86.48 171	83.67 319	94.30 202	69.33 295	97.99 189	87.10 177	88.55 280	93.72 320
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 400				9.81 463	69.31 297	95.53 364	76.65 329

tpmvs		83.35 346	82.07 345	87.20 358	91.07 354	71.00 405	88.31 394	91.70 355	78.91 345	80.49 365	87.18 407	69.30 298	97.08 277	68.12 398	83.56 337	93.51 328

mvsmamba		90.33 144	89.69 150	92.25 158	95.17 158	81.64 190	95.27 126	93.36 309	84.88 223	89.51 168	94.27 206	69.29 299	97.42 243	89.34 141	96.12 130	97.68 109

thres200		87.21 259	86.24 260	90.12 257	95.36 147	78.53 285	93.26 263	92.10 343	86.42 174	88.00 201	91.11 323	69.24 300	98.00 188	69.58 388	91.04 241	93.83 309

tfpn200view9		87.58 240	86.64 241	90.41 245	95.99 119	78.64 281	94.58 174	91.98 349	86.94 160	88.09 196	91.77 298	69.18 301	98.10 172	70.13 384	91.10 235	94.48 279

thres400		87.62 237	86.64 241	90.57 232	95.99 119	78.64 281	94.58 174	91.98 349	86.94 160	88.09 196	91.77 298	69.18 301	98.10 172	70.13 384	91.10 235	94.96 252

WB-MVSnew		83.77 341	83.28 332	85.26 390	91.48 335	71.03 403	91.89 315	87.98 417	78.91 345	84.78 285	90.22 349	69.11 303	94.02 393	64.70 416	90.44 247	90.71 404

tfpnnormal		84.72 326	83.23 334	89.20 297	92.79 295	80.05 245	94.48 180	95.81 175	82.38 282	81.08 356	91.21 316	69.01 304	96.95 288	61.69 426	80.59 380	90.58 409

thres100view900		87.63 235	86.71 237	90.38 248	96.12 106	78.55 284	95.03 145	91.58 360	87.15 152	88.06 199	92.29 277	68.91 305	98.10 172	70.13 384	91.10 235	94.48 279

thres600view7		87.65 232	86.67 240	90.59 231	96.08 112	78.72 278	94.88 153	91.58 360	87.06 155	88.08 198	92.30 276	68.91 305	98.10 172	70.05 387	91.10 235	94.96 252

PatchMatch-RL		86.77 277	85.54 286	90.47 244	95.88 124	82.71 162	90.54 349	92.31 337	79.82 335	84.32 303	91.57 310	68.77 307	96.39 325	73.16 363	93.48 193	92.32 372

XVG-OURS		89.40 180	88.70 181	91.52 191	94.06 233	81.46 197	91.27 333	96.07 152	86.14 182	88.89 183	95.77 131	68.73 308	97.26 264	87.39 169	89.96 257	95.83 220

TR-MVS		86.78 274	85.76 282	89.82 273	94.37 217	78.41 289	92.47 295	92.83 322	81.11 321	86.36 237	92.40 272	68.73 308	97.48 233	73.75 361	89.85 261	93.57 324

tpm		84.73 325	84.02 322	86.87 367	90.33 383	68.90 417	89.06 383	89.94 400	80.85 323	85.75 252	89.86 363	68.54 310	95.97 344	77.76 318	84.05 330	95.75 223

FMVSNet3		87.40 248	86.11 265	91.30 202	93.79 251	83.64 123	94.20 204	94.81 255	83.89 245	84.37 298	91.87 297	68.45 311	96.56 312	78.23 314	85.36 317	93.70 321

MVP-Stereo		85.97 297	84.86 305	89.32 294	90.92 363	82.19 178	92.11 311	94.19 282	78.76 352	78.77 388	91.63 305	68.38 312	96.56 312	75.01 348	93.95 180	89.20 422
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 353	80.27 359	87.01 361	91.09 353	71.02 404	87.38 410	91.53 363	66.25 436	80.17 367	86.35 416	68.22 313	96.15 337	69.16 389	82.29 353	93.86 307

dmvs_testset		74.57 403	75.81 401	70.86 429	87.72 420	40.47 464	87.05 413	77.90 454	82.75 276	71.15 432	85.47 422	67.98 314	84.12 451	45.26 448	76.98 408	88.00 432

sd_testset		88.59 206	87.85 208	90.83 225	96.00 116	80.42 233	92.35 300	94.71 260	88.73 100	86.85 226	95.20 159	67.31 315	96.43 323	79.64 298	89.85 261	95.63 229

tpm2		84.08 335	82.94 339	87.48 347	91.39 340	71.27 399	89.23 380	90.37 389	71.95 420	84.64 288	89.33 372	67.30 316	96.55 314	75.17 345	87.09 307	94.63 265

test-LLR		85.87 299	85.41 289	87.25 354	90.95 359	71.67 396	89.55 372	89.88 403	83.41 259	84.54 291	87.95 395	67.25 317	95.11 377	81.82 262	93.37 196	94.97 249

test0.0.03 1		82.41 351	81.69 347	84.59 395	88.23 412	72.89 378	90.24 356	87.83 419	83.41 259	79.86 376	89.78 365	67.25 317	88.99 440	65.18 413	83.42 340	91.90 380

CVMVSNet		84.69 328	84.79 307	84.37 397	91.84 323	64.92 435	93.70 242	91.47 365	66.19 437	86.16 244	95.28 152	67.18 319	93.33 405	80.89 280	90.42 249	94.88 258

thisisatest0515		87.33 251	85.99 270	91.37 199	93.49 265	79.55 259	90.63 347	89.56 410	80.17 329	87.56 211	90.86 330	67.07 320	98.28 161	81.50 269	93.02 207	96.29 194

tttt0517		88.61 204	87.78 209	91.11 211	94.96 171	77.81 308	95.35 117	89.69 405	85.09 218	88.05 200	94.59 191	66.93 321	98.48 135	83.27 232	92.13 227	97.03 154

our_test_3		81.93 354	80.46 357	86.33 376	88.46 409	73.48 372	88.46 392	91.11 371	76.46 375	76.69 402	88.25 391	66.89 322	94.36 387	68.75 391	79.08 397	91.14 398

thisisatest0530		88.67 202	87.61 212	91.86 176	94.87 178	80.07 243	94.63 172	89.90 402	84.00 242	88.46 190	93.78 228	66.88 323	98.46 139	83.30 231	92.65 215	97.06 151

IterMVS-SCA-FT		85.45 307	84.53 314	88.18 329	91.71 329	76.87 329	90.19 360	92.65 329	85.40 206	81.44 351	90.54 341	66.79 324	95.00 380	81.04 275	81.05 371	92.66 360

SCA		86.32 293	85.18 297	89.73 279	92.15 310	76.60 334	91.12 337	91.69 356	83.53 256	85.50 262	88.81 381	66.79 324	96.48 318	76.65 329	90.35 250	96.12 204

D2MVS		85.90 298	85.09 299	88.35 320	90.79 368	77.42 321	91.83 318	95.70 185	80.77 324	80.08 371	90.02 358	66.74 326	96.37 326	81.88 261	87.97 293	91.26 395

IterMVS		84.88 322	83.98 324	87.60 342	91.44 336	76.03 342	90.18 361	92.41 332	83.24 265	81.06 357	90.42 346	66.60 327	94.28 390	79.46 299	80.98 376	92.48 364
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 253	85.98 271	91.08 212	94.01 236	83.10 143	95.14 139	94.94 241	83.57 253	84.37 298	91.64 302	66.59 328	96.34 329	78.23 314	85.36 317	93.79 310

test1		87.26 253	85.98 271	91.08 212	94.01 236	83.10 143	95.14 139	94.94 241	83.57 253	84.37 298	91.64 302	66.59 328	96.34 329	78.23 314	85.36 317	93.79 310

FMVSNet2		87.19 261	85.82 278	91.30 202	94.01 236	83.67 121	94.79 161	94.94 241	83.57 253	83.88 313	92.05 290	66.59 328	96.51 316	77.56 321	85.01 320	93.73 319

IMVS_0404		87.60 239	86.84 232	89.89 269	93.72 253	77.75 313	88.56 390	95.34 218	85.53 199	79.98 373	94.49 194	66.54 331	94.64 383	84.75 207	92.65 215	97.28 129

EPMVS		83.90 340	82.70 344	87.51 344	90.23 386	72.67 382	88.62 389	81.96 442	81.37 314	85.01 282	88.34 389	66.31 332	94.45 384	75.30 344	87.12 306	95.43 234

Syy-MVS		80.07 379	79.78 365	80.94 414	91.92 319	59.93 446	89.75 370	87.40 423	81.72 304	78.82 385	87.20 405	66.29 333	91.29 426	47.06 447	87.84 296	91.60 385

ppachtmachnet_test		81.84 355	80.07 363	87.15 359	88.46 409	74.43 362	89.04 384	92.16 342	75.33 388	77.75 394	88.99 378	66.20 334	95.37 372	65.12 414	77.60 402	91.65 383

MDA-MVSNet_test_wron		79.21 389	77.19 391	85.29 388	88.22 413	72.77 380	85.87 419	90.06 397	74.34 398	62.62 443	87.56 401	66.14 335	91.99 421	66.90 407	73.01 415	91.10 401

YYNet1		79.22 388	77.20 390	85.28 389	88.20 414	72.66 383	85.87 419	90.05 399	74.33 399	62.70 441	87.61 400	66.09 336	92.03 418	66.94 404	72.97 416	91.15 397

JIA-IIPM		81.04 368	78.98 380	87.25 354	88.64 405	73.48 372	81.75 441	89.61 409	73.19 410	82.05 344	73.71 446	66.07 337	95.87 350	71.18 375	84.60 324	92.41 368

MSDG		84.86 323	83.09 336	90.14 256	93.80 249	80.05 245	89.18 381	93.09 315	78.89 347	78.19 389	91.91 295	65.86 338	97.27 262	68.47 393	88.45 284	93.11 345

FE-MVS		87.40 248	86.02 269	91.57 190	94.56 204	79.69 258	90.27 352	93.72 302	80.57 325	88.80 184	91.62 306	65.32 339	98.59 129	74.97 349	94.33 175	96.44 188

jajsoiax		88.24 216	87.50 214	90.48 241	90.89 365	80.14 240	95.31 119	95.65 191	84.97 221	84.24 306	94.02 214	65.31 340	97.42 243	88.56 152	88.52 282	93.89 301

cascas		86.43 291	84.98 301	90.80 228	92.10 314	80.92 219	90.24 356	95.91 167	73.10 411	83.57 323	88.39 388	65.15 341	97.46 237	84.90 205	91.43 232	94.03 298

ADS-MVSNet2		81.66 359	79.71 368	87.50 345	91.35 342	74.19 364	83.33 435	88.48 415	72.90 413	82.24 341	85.77 420	64.98 342	93.20 408	64.57 417	83.74 333	95.12 244

ADS-MVSNet		81.56 361	79.78 365	86.90 365	91.35 342	71.82 392	83.33 435	89.16 413	72.90 413	82.24 341	85.77 420	64.98 342	93.76 399	64.57 417	83.74 333	95.12 244

Elysia		90.12 149	89.10 167	93.18 91	93.16 274	84.05 110	95.22 130	96.27 129	85.16 214	90.59 148	94.68 182	64.64 344	98.37 150	86.38 184	95.77 134	97.12 147

StellarMVS		90.12 149	89.10 167	93.18 91	93.16 274	84.05 110	95.22 130	96.27 129	85.16 214	90.59 148	94.68 182	64.64 344	98.37 150	86.38 184	95.77 134	97.12 147

pmmvs5		84.21 333	82.84 343	88.34 322	88.95 403	76.94 328	92.41 296	91.91 353	75.63 385	80.28 366	91.18 319	64.59 346	95.57 363	77.09 327	83.47 338	92.53 363

PVSNet	78.82 18	85.55 305	84.65 309	88.23 328	94.72 190	71.93 390	87.12 412	92.75 326	78.80 351	84.95 283	90.53 342	64.43 347	96.71 299	74.74 351	93.86 182	96.06 210

dmvs_re		84.20 334	83.22 335	87.14 360	91.83 325	77.81 308	90.04 364	90.19 393	84.70 231	81.49 349	89.17 374	64.37 348	91.13 428	71.58 371	85.65 316	92.46 366

UGNet		89.95 159	88.95 174	92.95 108	94.51 207	83.31 134	95.70 98	95.23 224	89.37 74	87.58 210	93.94 219	64.00 349	98.78 107	83.92 222	96.31 125	96.74 177
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
WB-MVS		67.92 411	67.49 413	69.21 433	81.09 444	41.17 463	88.03 399	78.00 453	73.50 407	62.63 442	83.11 433	63.94 350	86.52 444	25.66 459	51.45 451	79.94 444

RPSCF		85.07 317	84.27 315	87.48 347	92.91 291	70.62 409	91.69 323	92.46 331	76.20 381	82.67 336	95.22 155	63.94 350	97.29 261	77.51 322	85.80 314	94.53 272

mvs_tets		88.06 222	87.28 221	90.38 248	90.94 361	79.88 252	95.22 130	95.66 189	85.10 217	84.21 307	93.94 219	63.53 352	97.40 251	88.50 153	88.40 286	93.87 305

SSC-MVS		67.06 412	66.56 414	68.56 435	80.54 445	40.06 465	87.77 404	77.37 456	72.38 417	61.75 444	82.66 435	63.37 353	86.45 445	24.48 460	48.69 454	79.16 446

test1111		89.10 187	88.64 182	90.48 241	95.53 143	74.97 354	96.08 64	84.89 434	88.13 123	90.16 159	96.65 85	63.29 354	98.10 172	86.14 186	96.90 108	98.39 41

Anonymous20231211		86.59 283	85.13 298	90.98 221	96.52 93	81.50 193	96.14 59	96.16 142	73.78 404	83.65 320	92.15 281	63.26 355	97.37 255	82.82 240	81.74 362	94.06 296

ECVR-MVS		89.09 189	88.53 185	90.77 229	95.62 138	75.89 344	96.16 55	84.22 436	87.89 132	90.20 156	96.65 85	63.19 356	98.10 172	85.90 191	96.94 106	98.33 46

SSC-MVS3.2		84.60 329	84.19 316	85.85 382	92.74 297	68.07 419	88.15 397	93.81 299	87.42 146	83.76 316	91.07 325	62.91 357	95.73 359	74.56 354	83.24 342	93.75 317

dp		81.47 364	80.23 360	85.17 391	89.92 392	65.49 432	86.74 414	90.10 396	76.30 379	81.10 355	87.12 408	62.81 358	95.92 347	68.13 397	79.88 389	94.09 294

LFMVS		90.08 152	89.13 166	92.95 108	96.71 82	82.32 176	96.08 64	89.91 401	86.79 163	92.15 114	96.81 78	62.60 359	98.34 155	87.18 172	93.90 181	98.19 67

Anonymous20231206		81.03 369	79.77 367	84.82 394	87.85 419	70.26 411	91.42 328	92.08 344	73.67 405	77.75 394	89.25 373	62.43 360	93.08 409	61.50 427	82.00 358	91.12 399

VDD-MVS		90.74 130	89.92 144	93.20 90	96.27 100	83.02 150	95.73 96	93.86 296	88.42 112	92.53 104	96.84 75	62.09 361	98.64 122	90.95 121	92.62 220	97.93 90

MS-PatchMatch		85.05 318	84.16 318	87.73 339	91.42 339	78.51 286	91.25 334	93.53 305	77.50 367	80.15 368	91.58 308	61.99 362	95.51 366	75.69 340	94.35 174	89.16 423

OurMVSNet-221017-0		85.35 311	84.64 311	87.49 346	90.77 370	72.59 386	94.01 221	94.40 273	84.72 230	79.62 380	93.17 247	61.91 363	96.72 297	81.99 258	81.16 367	93.16 343

WBMVS		84.97 321	84.18 317	87.34 350	94.14 232	71.62 398	90.20 359	92.35 334	81.61 309	84.06 308	90.76 336	61.82 364	96.52 315	78.93 307	83.81 331	93.89 301

test_vis1_n_1920		89.39 181	89.84 145	88.04 332	92.97 288	72.64 384	94.71 168	96.03 157	86.18 180	91.94 121	96.56 93	61.63 365	95.74 358	93.42 59	95.11 153	95.74 224

test20.03		79.95 381	79.08 378	82.55 407	85.79 429	67.74 424	91.09 338	91.08 372	81.23 319	74.48 419	89.96 361	61.63 365	90.15 432	60.08 430	76.38 409	89.76 414

mmtdpeth		85.04 320	84.15 319	87.72 340	93.11 278	75.74 347	94.37 194	92.83 322	84.98 220	89.31 173	86.41 414	61.61 367	97.14 274	92.63 75	62.11 442	90.29 410

DSMNet-mixed		76.94 398	76.29 397	78.89 419	83.10 440	56.11 455	87.78 403	79.77 446	60.65 445	75.64 411	88.71 384	61.56 368	88.34 441	60.07 431	89.29 272	92.21 375

Anonymous20240529		88.09 220	86.59 245	92.58 133	96.53 92	81.92 185	95.99 74	95.84 174	74.11 401	89.06 178	95.21 158	61.44 369	98.81 103	83.67 229	87.47 300	97.01 157

UBG		85.51 306	84.57 313	88.35 320	94.21 227	71.78 394	90.07 363	89.66 407	82.28 285	85.91 249	89.01 377	61.30 370	97.06 280	76.58 332	92.06 228	96.22 197

IB-MVS	80.51 15	85.24 315	83.26 333	91.19 206	92.13 312	79.86 253	91.75 320	91.29 369	83.28 264	80.66 362	88.49 387	61.28 371	98.46 139	80.99 278	79.46 394	95.25 241
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
GA-MVS		86.61 281	85.27 295	90.66 230	91.33 344	78.71 280	90.40 351	93.81 299	85.34 207	85.12 278	89.57 369	61.25 372	97.11 276	80.99 278	89.59 267	96.15 201

N_pmnet		68.89 410	68.44 412	70.23 430	89.07 402	28.79 469	88.06 398	19.50 469	69.47 429	71.86 429	84.93 423	61.24 373	91.75 423	54.70 441	77.15 405	90.15 411

EU-MVSNet		81.32 366	80.95 353	82.42 410	88.50 408	63.67 439	93.32 256	91.33 367	64.02 441	80.57 364	92.83 258	61.21 374	92.27 417	76.34 334	80.38 385	91.32 393

testing91		87.11 264	86.18 261	89.92 268	94.43 214	75.38 353	91.53 326	92.27 339	86.48 171	86.50 231	90.24 348	61.19 375	97.53 227	82.10 254	90.88 243	96.84 173

test_cas_vis1_n_1920		88.83 200	88.85 180	88.78 307	91.15 351	76.72 332	93.85 233	94.93 245	83.23 266	92.81 92	96.00 114	61.17 376	94.45 384	91.67 109	94.84 159	95.17 243

VDDNet		89.56 171	88.49 189	92.76 120	95.07 163	82.09 179	96.30 42	93.19 313	81.05 322	91.88 122	96.86 74	61.16 377	98.33 157	88.43 154	92.49 224	97.84 98

PVSNet_0	73.20 20	77.22 397	74.83 403	84.37 397	90.70 374	71.10 402	83.09 437	89.67 406	72.81 415	73.93 421	83.13 431	60.79 378	93.70 401	68.54 392	50.84 452	88.30 431

SixPastTwentyTwo		83.91 339	82.90 341	86.92 364	90.99 357	70.67 408	93.48 248	91.99 348	85.54 197	77.62 396	92.11 285	60.59 379	96.87 293	76.05 338	77.75 401	93.20 341

gg-mvs-nofinetune		81.77 356	79.37 371	88.99 304	90.85 367	77.73 317	86.29 417	79.63 447	74.88 395	83.19 331	69.05 450	60.34 380	96.11 338	75.46 342	94.64 166	93.11 345

MDA-MVSNet-bldmvs		78.85 391	76.31 396	86.46 372	89.76 394	73.88 366	88.79 386	90.42 388	79.16 343	59.18 446	88.33 390	60.20 381	94.04 392	62.00 425	68.96 429	91.48 390

pmmvs6		83.42 344	81.60 348	88.87 306	88.01 416	77.87 306	94.96 148	94.24 281	74.67 396	78.80 387	91.09 324	60.17 382	96.49 317	77.06 328	75.40 413	92.23 374

ACMH	80.38 17	85.36 310	83.68 327	90.39 246	94.45 212	80.63 226	94.73 166	94.85 251	82.09 288	77.24 397	92.65 265	60.01 383	97.58 223	72.25 368	84.87 322	92.96 350
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 335	89.73 396	77.91 303	87.80 401	78.23 452		80.58 363	83.86 427	59.88 384	95.33 373	71.20 373	92.22 226	90.60 408

UniMVSNet_ETH3D		87.53 242	86.37 253	91.00 218	92.44 304	78.96 276	94.74 165	95.61 193	84.07 241	85.36 275	94.52 193	59.78 385	97.34 256	82.93 236	87.88 294	96.71 178

myMVS_eth3d28		85.80 302	85.26 296	87.42 349	94.73 188	69.92 414	90.60 348	90.95 378	87.21 151	86.06 246	90.04 357	59.47 386	96.02 341	74.89 350	93.35 198	96.33 191

pmmvs-eth3d		80.97 371	78.72 382	87.74 338	84.99 434	79.97 251	90.11 362	91.65 358	75.36 387	73.51 422	86.03 417	59.45 387	93.96 397	75.17 345	72.21 418	89.29 421

testing99		86.72 278	85.73 285	89.69 281	94.23 225	74.91 356	91.35 330	90.97 377	86.14 182	86.36 237	90.22 349	59.41 388	97.48 233	82.24 251	90.66 245	96.69 180

test_0402		81.30 367	79.17 376	87.67 341	93.19 273	78.17 296	92.98 278	91.71 354	75.25 389	76.02 409	90.31 347	59.23 389	96.37 326	50.22 445	83.63 336	88.47 430

KD-MVS_self_test		80.20 377	79.24 373	83.07 404	85.64 431	65.29 433	91.01 340	93.93 292	78.71 354	76.32 404	86.40 415	59.20 390	92.93 411	72.59 366	69.35 426	91.00 403

testing3-2		86.72 278	86.71 237	86.74 370	96.11 109	65.92 429	93.39 253	89.65 408	89.46 70	87.84 204	92.79 262	59.17 391	97.60 221	81.31 271	90.72 244	96.70 179

UWE-MVS-28		78.98 390	78.38 384	80.80 415	88.18 415	60.66 445	90.65 346	78.51 449	78.84 349	77.93 393	90.93 329	59.08 392	89.02 439	50.96 444	90.33 251	92.72 358

FMVSNet1		85.85 300	84.11 320	91.08 212	92.81 294	83.10 143	95.14 139	94.94 241	81.64 307	82.68 335	91.64 302	59.01 393	96.34 329	75.37 343	83.78 332	93.79 310

testing11		86.44 290	85.35 293	89.69 281	94.29 223	75.40 352	91.30 331	90.53 387	84.76 228	85.06 280	90.13 354	58.95 394	97.45 238	82.08 255	91.09 239	96.21 199

COLMAP_ROB	80.39 16	83.96 337	82.04 346	89.74 277	95.28 151	79.75 256	94.25 200	92.28 338	75.17 390	78.02 392	93.77 229	58.60 395	97.84 203	65.06 415	85.92 313	91.63 384
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	81.04 14	85.05 318	83.46 330	89.82 273	94.66 195	79.37 265	94.44 185	94.12 288	82.19 287	78.04 391	92.82 259	58.23 396	97.54 226	73.77 360	82.90 347	92.54 362

CMPMVS	59.16 21	80.52 373	79.20 375	84.48 396	83.98 436	67.63 425	89.95 367	93.84 298	64.79 440	66.81 438	91.14 322	57.93 397	95.17 375	76.25 335	88.10 289	90.65 405
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
reproduce_monomvs		86.37 292	85.87 276	87.87 337	93.66 261	73.71 368	93.44 251	95.02 234	88.61 106	82.64 337	91.94 294	57.88 398	96.68 300	89.96 134	79.71 392	93.22 339

tt0805		86.92 269	85.74 284	90.48 241	92.22 308	79.98 250	95.63 106	94.88 249	83.83 247	84.74 287	92.80 261	57.61 399	97.67 213	85.48 197	84.42 325	93.79 310

ITE_SJBPF				88.24 327	91.88 322	77.05 326		92.92 319	85.54 197	80.13 370	93.30 242	57.29 400	96.20 334	72.46 367	84.71 323	91.49 389

UWE-MVS		83.69 343	83.09 336	85.48 385	93.06 282	65.27 434	90.92 341	86.14 426	79.90 333	86.26 241	90.72 339	57.17 401	95.81 354	71.03 378	92.62 220	95.35 238

TESTMET0.1,1		83.74 342	82.85 342	86.42 375	89.96 391	71.21 401	89.55 372	87.88 418	77.41 368	83.37 327	87.31 403	56.71 402	93.65 402	80.62 285	92.85 212	94.40 282

UnsupCasMVSNet_eth		80.07 379	78.27 385	85.46 386	85.24 433	72.63 385	88.45 393	94.87 250	82.99 271	71.64 430	88.07 394	56.34 403	91.75 423	73.48 362	63.36 440	92.01 378

test_fmvs1		87.34 250	87.56 213	86.68 371	90.59 376	71.80 393	94.01 221	94.04 290	78.30 360	91.97 118	95.22 155	56.28 404	93.71 400	92.89 68	94.71 162	94.52 273

K. test v3		81.59 360	80.15 362	85.91 381	89.89 393	69.42 416	92.57 292	87.71 420	85.56 196	73.44 423	89.71 367	55.58 405	95.52 365	77.17 325	69.76 425	92.78 357

test-mter		84.54 330	83.64 328	87.25 354	90.95 359	71.67 396	89.55 372	89.88 403	79.17 342	84.54 291	87.95 395	55.56 406	95.11 377	81.82 262	93.37 196	94.97 249

lessismore_v0				86.04 377	88.46 409	68.78 418		80.59 445		73.01 425	90.11 355	55.39 407	96.43 323	75.06 347	65.06 437	92.90 352

ETVMVS		84.43 331	82.92 340	88.97 305	94.37 217	74.67 357	91.23 335	88.35 416	83.37 261	86.06 246	89.04 376	55.38 408	95.67 361	67.12 402	91.34 233	96.58 184

MVS-HIRNet		73.70 404	72.20 407	78.18 422	91.81 326	56.42 454	82.94 438	82.58 440	55.24 448	68.88 435	66.48 451	55.32 409	95.13 376	58.12 436	88.42 285	83.01 439

test2506		87.21 259	86.28 258	90.02 264	95.62 138	73.64 370	96.25 50	71.38 459	87.89 132	90.45 151	96.65 85	55.29 410	98.09 180	86.03 190	96.94 106	98.33 46

mvs5depth		80.98 370	79.15 377	86.45 373	84.57 435	73.29 374	87.79 402	91.67 357	80.52 326	82.20 343	89.72 366	55.14 411	95.93 346	73.93 359	66.83 434	90.12 412

new-patchmatchnet		76.41 400	75.17 402	80.13 416	82.65 442	59.61 447	87.66 407	91.08 372	78.23 363	69.85 434	83.22 430	54.76 412	91.63 425	64.14 419	64.89 438	89.16 423

Anonymous202405211		87.68 230	86.13 263	92.31 153	96.66 84	80.74 224	94.87 154	91.49 364	80.47 327	89.46 171	95.44 144	54.72 413	98.23 163	82.19 252	89.89 259	97.97 86

XVG-ACMP-BASELINE		86.00 296	84.84 306	89.45 292	91.20 346	78.00 300	91.70 322	95.55 197	85.05 219	82.97 332	92.25 279	54.49 414	97.48 233	82.93 236	87.45 302	92.89 353

USDC		82.76 347	81.26 352	87.26 353	91.17 348	74.55 359	89.27 378	93.39 308	78.26 362	75.30 413	92.08 287	54.43 415	96.63 303	71.64 370	85.79 315	90.61 406

AllTest		83.42 344	81.39 350	89.52 289	95.01 165	77.79 310	93.12 267	90.89 381	77.41 368	76.12 406	93.34 238	54.08 416	97.51 229	68.31 395	84.27 327	93.26 335

TestCases				89.52 289	95.01 165	77.79 310		90.89 381	77.41 368	76.12 406	93.34 238	54.08 416	97.51 229	68.31 395	84.27 327	93.26 335

KD-MVS_2432*1600		78.50 392	76.02 399	85.93 379	86.22 425	74.47 360	84.80 428	92.33 335	79.29 340	76.98 399	85.92 418	53.81 418	93.97 395	67.39 400	57.42 447	89.36 417

miper_refine_blended		78.50 392	76.02 399	85.93 379	86.22 425	74.47 360	84.80 428	92.33 335	79.29 340	76.98 399	85.92 418	53.81 418	93.97 395	67.39 400	57.42 447	89.36 417

MIMVSNet		82.59 350	80.53 355	88.76 308	91.51 334	78.32 292	86.57 416	90.13 395	79.32 339	80.70 361	88.69 386	52.98 420	93.07 410	66.03 410	88.86 278	94.90 257

testing222		84.84 324	83.32 331	89.43 293	94.15 231	75.94 343	91.09 338	89.41 412	84.90 222	85.78 251	89.44 371	52.70 421	96.28 332	70.80 379	91.57 231	96.07 208

FMVSNet5		81.52 363	79.60 369	87.27 352	91.17 348	77.95 301	91.49 327	92.26 340	76.87 373	76.16 405	87.91 397	51.67 422	92.34 416	67.74 399	81.16 367	91.52 387

testgi		80.94 372	80.20 361	83.18 403	87.96 417	66.29 427	91.28 332	90.70 386	83.70 250	78.12 390	92.84 257	51.37 423	90.82 430	63.34 420	82.46 351	92.43 367

test_fmvs1_n		87.03 267	87.04 227	86.97 362	89.74 395	71.86 391	94.55 176	94.43 270	78.47 356	91.95 120	95.50 142	51.16 424	93.81 398	93.02 67	94.56 168	95.26 240

Anonymous20240521		80.44 375	79.21 374	84.11 400	85.75 430	67.89 421	92.86 284	93.23 311	75.61 386	75.59 412	87.47 402	50.03 425	94.33 388	71.14 376	81.21 366	90.12 412

UnsupCasMVSNet_bld		76.23 401	73.27 405	85.09 392	83.79 437	72.92 377	85.65 422	93.47 307	71.52 421	68.84 436	79.08 441	49.77 426	93.21 407	66.81 408	60.52 444	89.13 425

OpenMVS_ROB	74.94 19	79.51 386	77.03 393	86.93 363	87.00 422	76.23 341	92.33 302	90.74 384	68.93 430	74.52 418	88.23 392	49.58 427	96.62 304	57.64 437	84.29 326	87.94 433

tt0320		80.13 378	77.41 387	88.29 324	90.50 381	78.02 299	93.10 270	90.71 385	66.06 438	76.75 401	86.97 410	49.56 428	95.40 371	71.65 369	71.41 422	91.46 391

TDRefinement		79.81 382	77.34 388	87.22 357	79.24 449	75.48 350	93.12 267	92.03 346	76.45 376	75.01 414	91.58 308	49.19 429	96.44 322	70.22 383	69.18 428	89.75 415

test_vis1_n		86.56 284	86.49 251	86.78 369	88.51 406	72.69 381	94.68 169	93.78 301	79.55 338	90.70 146	95.31 151	48.75 430	93.28 406	93.15 63	93.99 179	94.38 283

MIMVSNet1		79.38 387	77.28 389	85.69 384	86.35 424	73.67 369	91.61 325	92.75 326	78.11 365	72.64 426	88.12 393	48.16 431	91.97 422	60.32 429	77.49 403	91.43 392

LF4IMVS		80.37 376	79.07 379	84.27 399	86.64 423	69.87 415	89.39 377	91.05 374	76.38 377	74.97 415	90.00 359	47.85 432	94.25 391	74.55 355	80.82 378	88.69 428

EG-PatchMatch MVS		82.37 352	80.34 358	88.46 317	90.27 384	79.35 266	92.80 287	94.33 276	77.14 372	73.26 424	90.18 352	47.47 433	96.72 297	70.25 381	87.32 305	89.30 419

test_fmvs2		83.98 336	84.03 321	83.83 402	87.16 421	67.53 426	93.93 228	92.89 320	77.62 366	86.89 225	93.53 235	47.18 434	92.02 420	90.54 128	86.51 310	91.93 379

ttmdpeth		76.55 399	74.64 404	82.29 412	82.25 443	67.81 423	89.76 369	85.69 429	70.35 427	75.76 410	91.69 301	46.88 435	89.77 434	66.16 409	63.23 441	89.30 419

sc_t1		81.53 362	78.67 383	90.12 257	90.78 369	78.64 281	93.91 231	90.20 392	68.42 431	80.82 359	89.88 362	46.48 436	96.76 296	76.03 339	71.47 421	94.96 252

MVStest1		72.91 405	69.70 410	82.54 408	78.14 450	73.05 376	88.21 396	86.21 425	60.69 444	64.70 439	90.53 342	46.44 437	85.70 447	58.78 435	53.62 449	88.87 426

tt0320-xc		79.63 385	76.66 394	88.52 316	91.03 355	78.72 278	93.00 276	89.53 411	66.37 435	76.11 408	87.11 409	46.36 438	95.32 374	72.78 365	67.67 432	91.51 388

TinyColmap		79.76 383	77.69 386	85.97 378	91.71 329	73.12 375	89.55 372	90.36 390	75.03 391	72.03 428	90.19 351	46.22 439	96.19 336	63.11 421	81.03 372	88.59 429

myMVS_eth3d		79.67 384	78.79 381	82.32 411	91.92 319	64.08 437	89.75 370	87.40 423	81.72 304	78.82 385	87.20 405	45.33 440	91.29 426	59.09 434	87.84 296	91.60 385

tmp_tt		35.64 429	39.24 431	24.84 445	14.87 469	23.90 470	62.71 455	51.51 466	6.58 463	36.66 459	62.08 456	44.37 441	30.34 465	52.40 443	22.00 462	20.27 460

testing3		80.46 374	79.59 370	83.06 405	93.44 268	64.64 436	93.33 255	85.47 431	84.34 237	79.93 375	90.84 332	44.35 442	92.39 415	57.06 439	87.56 299	92.16 376

new_pmnet		72.15 406	70.13 409	78.20 421	82.95 441	65.68 430	83.91 433	82.40 441	62.94 443	64.47 440	79.82 440	42.85 443	86.26 446	57.41 438	74.44 414	82.65 441

test_vis1_rt		77.96 395	76.46 395	82.48 409	85.89 428	71.74 395	90.25 354	78.89 448	71.03 425	71.30 431	81.35 438	42.49 444	91.05 429	84.55 214	82.37 352	84.65 436

EGC-MVSNET		61.97 416	56.37 421	78.77 420	89.63 397	73.50 371	89.12 382	82.79 439	0.21 466	1.24 467	84.80 424	39.48 445	90.04 433	44.13 449	75.94 412	72.79 448

dongtai		58.82 421	58.24 419	60.56 438	83.13 439	45.09 462	82.32 439	48.22 468	67.61 433	61.70 445	69.15 449	38.75 446	76.05 457	32.01 456	41.31 456	60.55 453

kuosan		53.51 423	53.30 426	54.13 442	76.06 451	45.36 461	80.11 446	48.36 467	59.63 446	54.84 448	63.43 455	37.41 447	62.07 462	20.73 462	39.10 457	54.96 456

pmmvs3		71.81 408	68.71 411	81.11 413	75.86 452	70.42 410	86.74 414	83.66 437	58.95 447	68.64 437	80.89 439	36.93 448	89.52 436	63.10 422	63.59 439	83.39 437

mvsany_test3		74.95 402	73.26 406	80.02 417	74.61 453	63.16 441	85.53 423	78.42 450	74.16 400	74.89 416	86.46 412	36.02 449	89.09 438	82.39 247	66.91 433	87.82 434

PM-MVS		78.11 394	76.12 398	84.09 401	83.54 438	70.08 412	88.97 385	85.27 433	79.93 332	74.73 417	86.43 413	34.70 450	93.48 403	79.43 302	72.06 419	88.72 427

ambc				83.06 405	79.99 447	63.51 440	77.47 450	92.86 321		74.34 420	84.45 426	28.74 451	95.06 379	73.06 364	68.89 430	90.61 406

test_method		50.52 425	48.47 427	56.66 440	52.26 467	18.98 471	41.51 459	81.40 443	10.10 461	44.59 456	75.01 445	28.51 452	68.16 458	53.54 442	49.31 453	82.83 440

DeepMVS_CX				56.31 441	74.23 454	51.81 457		56.67 465	44.85 453	48.54 453	75.16 444	27.87 453	58.74 463	40.92 453	52.22 450	58.39 455

test_fmvs3		77.67 396	77.16 392	79.22 418	79.52 448	61.14 443	92.34 301	91.64 359	73.98 402	78.86 384	86.59 411	27.38 454	87.03 442	88.12 158	75.97 411	89.50 416

test_f		71.95 407	70.87 408	75.21 425	74.21 455	59.37 448	85.07 427	85.82 428	65.25 439	70.42 433	83.13 431	23.62 455	82.93 453	78.32 312	71.94 420	83.33 438

FPMVS		64.63 415	62.55 417	70.88 428	70.80 457	56.71 450	84.42 431	84.42 435	51.78 451	49.57 451	81.61 437	23.49 456	81.48 454	40.61 454	76.25 410	74.46 447

APD_test1		69.04 409	66.26 415	77.36 424	80.51 446	62.79 442	85.46 424	83.51 438	54.11 450	59.14 447	84.79 425	23.40 457	89.61 435	55.22 440	70.24 424	79.68 445

ANet_high		58.88 420	54.22 425	72.86 426	56.50 466	56.67 451	80.75 443	86.00 427	73.09 412	37.39 458	64.63 454	22.17 458	79.49 456	43.51 450	23.96 460	82.43 442

EMVS		42.07 428	41.12 430	44.92 444	63.45 464	35.56 468	73.65 451	63.48 462	33.05 459	26.88 463	45.45 460	21.27 459	67.14 460	19.80 463	23.02 461	32.06 459

Gipuma		57.99 422	54.91 424	67.24 436	88.51 406	65.59 431	52.21 457	90.33 391	43.58 454	42.84 457	51.18 458	20.29 460	85.07 448	34.77 455	70.45 423	51.05 457
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 427	42.29 429	46.03 443	65.58 462	37.41 466	73.51 452	64.62 461	33.99 458	28.47 462	47.87 459	19.90 461	67.91 459	22.23 461	24.45 459	32.77 458

PMMVS2		59.60 417	56.40 420	69.21 433	68.83 460	46.58 459	73.02 454	77.48 455	55.07 449	49.21 452	72.95 448	17.43 462	80.04 455	49.32 446	44.33 455	80.99 443

LCM-MVSNet		66.00 413	62.16 418	77.51 423	64.51 463	58.29 449	83.87 434	90.90 380	48.17 452	54.69 449	73.31 447	16.83 463	86.75 443	65.47 411	61.67 443	87.48 435

test_vis3_rt		65.12 414	62.60 416	72.69 427	71.44 456	60.71 444	87.17 411	65.55 460	63.80 442	53.22 450	65.65 453	14.54 464	89.44 437	76.65 329	65.38 436	67.91 451

testf1		59.54 418	56.11 422	69.85 431	69.28 458	56.61 452	80.37 444	76.55 457	42.58 455	45.68 454	75.61 442	11.26 465	84.18 449	43.20 451	60.44 445	68.75 449

APD_test2		59.54 418	56.11 422	69.85 431	69.28 458	56.61 452	80.37 444	76.55 457	42.58 455	45.68 454	75.61 442	11.26 465	84.18 449	43.20 451	60.44 445	68.75 449

PMVS	47.18 22	52.22 424	48.46 428	63.48 437	45.72 468	46.20 460	73.41 453	78.31 451	41.03 457	30.06 460	65.68 452	6.05 467	83.43 452	30.04 457	65.86 435	60.80 452
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 426	38.59 432	57.77 439	56.52 465	48.77 458	55.38 456	58.64 464	29.33 460	28.96 461	52.65 457	4.68 468	64.62 461	28.11 458	33.07 458	59.93 454
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 431	20.48 434	23.63 446	68.59 461	36.41 467	49.57 458	6.85 470	9.37 462	7.89 464	4.46 466	4.03 469	31.37 464	17.47 464	16.07 463	3.12 461

test123		8.76 433	11.22 436	1.39 447	0.85 471	0.97 472	85.76 421	0.35 472	0.54 465	2.45 466	8.14 465	0.60 470	0.48 466	2.16 466	0.17 465	2.71 462

testmvs		8.92 432	11.52 435	1.12 448	1.06 470	0.46 473	86.02 418	0.65 471	0.62 464	2.74 465	9.52 464	0.31 471	0.45 467	2.38 465	0.39 464	2.46 463

mmdepth		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

monomultidepth		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

test_blank		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

uanet_test		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

DCPMVS		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

sosnet-low-res		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

sosnet		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

uncertanet		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

Regformer		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

ab-mvs-re		7.82 434	10.43 437	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	93.88 224	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

uanet		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

WAC-MVS						64.08 437								59.14 433

FOURS1					98.86 1	85.54 69	98.29 1	97.49 8	89.79 61	96.29 27

MSC_two_6792asdad				96.52 1	97.78 56	90.86 1		96.85 75					99.61 4	96.03 25	99.06 9	99.07 5

No_MVS				96.52 1	97.78 56	90.86 1		96.85 75					99.61 4	96.03 25	99.06 9	99.07 5

eth-test2					0.00 472

eth-test					0.00 472

IU-MVS					98.77 5	86.00 52		96.84 77	81.26 317	97.26 12				95.50 34	99.13 3	99.03 8

save fliter					97.85 51	85.63 68	95.21 133	96.82 80	89.44 71

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 17	97.49 8					99.61 4	95.62 32	99.08 7	98.99 9

GSMVS																96.12 204

test_part2					98.55 12	87.22 19				96.40 26

MTGPA								96.97 60

MTMP							96.16 55	60.64 463

gm-plane-assit					89.60 398	68.00 420			77.28 371		88.99 378		97.57 224	79.44 301

test9_res														91.91 103	98.71 32	98.07 77

agg_prior2														90.54 128	98.68 37	98.27 59

agg_prior					97.38 68	85.92 59		96.72 94		92.16 113			98.97 81

test_prior4						85.96 56	94.11 209

test_prior				93.82 69	97.29 72	84.49 93		96.88 73					98.87 93			98.11 76

旧先验2							93.36 254		71.25 423	94.37 54			97.13 275	86.74 178

新几何2							93.11 269

无先验							93.28 262	96.26 133	73.95 403				99.05 61	80.56 286		96.59 183

原ACMM2							92.94 280

testdata2													98.75 109	78.30 313

testdata1							92.15 309		87.94 128

plane_prior7					94.70 193	82.74 159

plane_prior5								96.22 138					98.12 170	88.15 155	89.99 255	94.63 265

plane_prior4											94.86 174

plane_prior3						82.75 157			90.26 45	86.91 222

plane_prior2							95.85 86		90.81 25

plane_prior1					94.59 199

plane_prior						82.73 160	95.21 133		89.66 66						89.88 260

n2								0.00 473

nn								0.00 473

door-mid								85.49 430

test11								96.57 105

door								85.33 432

HQP5-MVS						81.56 191

HQP-NCC					94.17 228		94.39 190		88.81 96	85.43 268

ACMP_Plane					94.17 228		94.39 190		88.81 96	85.43 268

BP-MVS														87.11 175

HQP4-MVS										85.43 268			97.96 194			94.51 275

HQP3-MVS								96.04 155							89.77 264

NP-MVS					94.37 217	82.42 172					93.98 217

ACMMP++_ref															87.47 300

ACMMP++															88.01 292

High-resolution multi-view benchmark