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									82.47 316	97.09 20	97.07 73	92.72 1	98.04 202	92.70 82	99.02 12	98.86 16

DVP-MVS++		95.98 1	96.36 1	94.82 35	97.78 61	86.00 55	98.29 1	97.49 11	90.75 32	97.62 9	98.06 25	92.59 2	99.61 7	95.64 34	99.02 12	98.86 16

OPU-MVS				96.21 3	98.00 49	90.85 3	97.13 19				97.08 71	92.59 2	98.94 93	92.25 94	98.99 14	98.84 19

MED-MVS		95.95 2	96.31 2	94.90 25	98.88 1	85.89 66	97.32 10	97.86 1	90.76 30	97.21 15	98.09 19	92.42 4	99.67 1	95.27 42	98.95 15	99.14 2

SED-MVS		95.91 3	96.28 3	94.80 38	98.77 8	85.99 57	97.13 19	97.44 20	90.31 45	97.71 3	98.07 23	92.31 5	99.58 14	95.66 32	99.13 3	98.84 19

test_241102_ONE					98.77 8	85.99 57		97.44 20	90.26 51	97.71 3	97.96 34	92.31 5	99.38 36

test_0728_THIRD									90.75 32	97.04 22	98.05 28	92.09 7	99.55 21	95.64 34	99.13 3	99.13 4

DPE-MVS		95.57 5	95.67 6	95.25 12	98.36 32	87.28 19	95.56 119	97.51 10	89.13 92	97.14 18	97.91 35	91.64 8	99.62 5	94.61 51	99.17 2	98.86 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.67 4	96.02 4	94.64 44	98.78 6	85.93 60	97.09 21	96.73 99	90.27 49	97.04 22	98.05 28	91.47 9	99.55 21	95.62 36	99.08 7	98.45 42
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 6	85.93 60	97.19 16	97.47 16	90.27 49	97.64 7	98.13 8	91.47 9

test_241102_TWO								97.44 20	90.31 45	97.62 9	98.07 23	91.46 11	99.58 14	95.66 32	99.12 6	98.98 12

test_one_0601					98.58 14	85.83 69		97.44 20	91.05 24	96.78 28	98.06 25	91.45 12

fmvsm_l_mol_unc0.5_1		95.04 16	95.73 5	92.96 115	95.59 150	82.16 189	94.15 224	96.64 109	91.92 11	98.69 1	98.92 1	90.35 13	98.76 117	96.75 22	98.57 53	97.98 97

MSP-MVS		95.42 7	95.56 8	94.98 21	98.49 20	86.52 38	96.91 30	97.47 16	91.73 15	96.10 37	96.69 88	89.90 14	99.30 49	94.70 49	98.04 81	99.13 4
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DeepPCF-MVS	89.96 1	94.20 48	94.77 32	92.49 153	96.52 99	80.00 283	94.00 243	97.08 60	90.05 53	95.65 49	97.29 58	89.66 15	98.97 88	93.95 57	98.71 36	98.50 32

test-260524					98.47 21	86.91 23		97.38 27		95.81 45		89.60 16	99.63 4	95.95 30	98.95 15

SD-MVS		94.96 19	95.33 13	93.88 71	97.25 80	86.69 30	96.19 57	97.11 59	90.42 41	96.95 24	97.27 59	89.53 17	96.91 328	94.38 53	98.85 22	98.03 92
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 8	95.37 12	95.50 8	98.11 43	88.51 8	95.29 132	96.96 69	92.09 10	95.32 52	97.08 71	89.49 18	99.33 46	95.10 45	98.85 22	98.66 26

APDe-MVS		95.46 6	95.64 7	94.91 23	98.26 35	86.29 48	97.46 7	97.40 26	89.03 98	96.20 36	98.10 15	89.39 19	99.34 43	95.88 31	99.03 11	99.10 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TestfortrainingZip				95.40 9	97.32 75	88.97 6	97.32 10	96.82 86	89.07 93	95.69 47	96.49 101	89.27 20	99.29 51		95.80 145	97.95 100

aaEdge-Enhanced		95.17 12	95.29 15	94.81 36	98.39 29	85.89 66	95.91 88	97.55 8	89.01 100	95.86 43	97.54 47	89.24 21	99.59 11	95.27 42	98.85 22	98.95 13

MCST-MVS		94.45 35	94.20 52	95.19 14	98.46 23	87.50 17	95.00 157	97.12 56	87.13 179	92.51 115	96.30 107	89.24 21	99.34 43	93.46 65	98.62 50	98.73 23

TSAR-MVS + MP.		94.85 20	94.94 25	94.58 47	98.25 36	86.33 44	96.11 67	96.62 110	88.14 132	96.10 37	96.96 77	89.09 23	98.94 93	94.48 52	98.68 41	98.48 35
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TestfortrainingZip a		95.33 9	95.44 11	94.99 20	98.88 1	86.26 49	97.32 10	97.43 25	90.76 30	96.80 27	98.09 19	89.00 24	99.58 14	93.66 62	96.99 113	99.14 2

SteuartSystems-ACMMP		95.20 10	95.32 14	94.85 28	96.99 83	86.33 44	97.33 8	97.30 38	91.38 20	95.39 51	97.46 51	88.98 25	99.40 35	94.12 55	98.89 20	98.82 21
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		95.20 10	95.07 21	95.59 6	98.14 42	88.48 9	96.26 54	97.28 41	85.90 215	97.67 5	98.10 15	88.41 26	99.56 17	94.66 50	99.19 1	98.71 25
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
patch_mono-2		93.74 66	94.32 42	92.01 186	97.54 67	78.37 336	93.40 279	97.19 45	88.02 141	94.99 59	97.21 63	88.35 27	98.44 155	94.07 56	98.09 78	99.23 1

9.14			94.47 36		97.79 59		96.08 69	97.44 20	86.13 213	95.10 57	97.40 54	88.34 28	99.22 54	93.25 70	98.70 38

SF-MVS		94.97 18	94.90 29	95.20 13	97.84 57	87.76 11	96.65 39	97.48 15	87.76 157	95.71 46	97.70 43	88.28 29	99.35 42	93.89 59	98.78 30	98.48 35

HPM-MVS++		95.14 13	94.91 27	95.83 4	98.25 36	89.65 4	95.92 87	96.96 69	91.75 14	94.02 74	96.83 83	88.12 30	99.55 21	93.41 68	98.94 18	98.28 62

dcpmvs_2		93.49 71	94.19 53	91.38 230	97.69 64	76.78 380	94.25 218	96.29 134	88.33 122	94.46 62	96.88 80	88.07 31	98.64 132	93.62 64	98.09 78	98.73 23

CSCG		93.23 86	93.05 87	93.76 78	98.04 47	84.07 114	96.22 56	97.37 28	84.15 272	90.05 193	95.66 158	87.77 32	99.15 62	89.91 154	98.27 63	98.07 84

NCCC		94.81 23	94.69 33	95.17 15	97.83 58	87.46 18	95.66 110	96.93 73	92.34 7	93.94 75	96.58 98	87.74 33	99.44 34	92.83 77	98.40 59	98.62 27

TEST9					97.53 68	86.49 39	94.07 234	96.78 91	81.61 346	92.77 103	96.20 111	87.71 34	99.12 64

train_agg		93.44 76	93.08 86	94.52 49	97.53 68	86.49 39	94.07 234	96.78 91	81.86 337	92.77 103	96.20 111	87.63 35	99.12 64	92.14 100	98.69 39	97.94 101

test_8					97.49 70	86.30 47	94.02 240	96.76 94	81.86 337	92.70 107	96.20 111	87.63 35	99.02 74

ZD-MVS					98.15 41	86.62 35		97.07 61	83.63 285	94.19 67	96.91 79	87.57 37	99.26 52	91.99 107	98.44 58

fmvsm_l_conf0.5_n		94.29 42	94.46 37	93.79 77	95.28 161	85.43 78	95.68 107	96.43 123	86.56 198	96.84 26	97.81 40	87.56 38	98.77 116	97.14 15	96.82 121	97.16 176

fmvsm_l_conf0.5_n_a		94.20 48	94.40 39	93.60 83	95.29 160	84.98 85	95.61 115	96.28 137	86.31 205	96.75 29	97.86 38	87.40 39	98.74 121	97.07 17	97.02 112	97.07 181

TSAR-MVS + GP.		93.66 68	93.41 79	94.41 54	96.59 93	86.78 28	94.40 205	93.93 327	89.77 68	94.21 66	95.59 162	87.35 40	98.61 137	92.72 80	96.15 138	97.83 121

APD-MVS		94.24 44	94.07 57	94.75 41	98.06 46	86.90 25	95.88 90	96.94 72	85.68 222	95.05 58	97.18 67	87.31 41	99.07 66	91.90 113	98.61 52	98.28 62
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
segment_acmp												87.16 42

reproduce-ours		94.82 21	94.97 23	94.38 55	97.91 54	85.46 76	95.86 91	97.15 52	89.82 61	95.23 55	98.10 15	87.09 43	99.37 38	95.30 40	98.25 68	98.30 56

our_new_method		94.82 21	94.97 23	94.38 55	97.91 54	85.46 76	95.86 91	97.15 52	89.82 61	95.23 55	98.10 15	87.09 43	99.37 38	95.30 40	98.25 68	98.30 56

旧先验1					96.79 87	81.81 201		95.67 213			96.81 85	86.69 45			97.66 99	96.97 191

lecture		95.10 14	95.46 10	94.01 66	98.40 27	84.36 108	97.70 3	97.78 3	91.19 21	96.22 35	98.08 22	86.64 46	99.37 38	94.91 47	98.26 64	98.29 61

test_prior2							94.12 226		87.67 161	92.63 111	96.39 106	86.62 47		91.50 121	98.67 44

CDPH-MVS		92.83 95	92.30 104	94.44 50	97.79 59	86.11 54	94.06 236	96.66 106	80.09 368	92.77 103	96.63 95	86.62 47	99.04 70	87.40 197	98.66 45	98.17 75

DPM-MVS		92.58 101	91.74 113	95.08 16	96.19 108	89.31 5	92.66 320	96.56 115	83.44 291	91.68 143	95.04 194	86.60 49	98.99 83	85.60 224	97.92 86	96.93 195

reproduce_model		94.76 25	94.92 26	94.29 61	97.92 50	85.18 82	95.95 85	97.19 45	89.67 71	95.27 54	98.16 7	86.53 50	99.36 41	95.42 39	98.15 74	98.33 51

test_fmvsmconf_n		94.60 29	94.81 31	93.98 67	94.62 210	84.96 86	96.15 62	97.35 30	89.37 81	96.03 40	98.11 12	86.36 51	99.01 76	97.45 10	97.83 91	97.96 99

DELS-MVS		93.43 80	93.25 82	93.97 68	95.42 155	85.04 84	93.06 301	97.13 55	90.74 34	91.84 135	95.09 193	86.32 52	99.21 56	91.22 125	98.45 57	97.65 134
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 27	95.11 20	93.50 85	95.79 134	84.62 93	96.15 62	97.64 5	89.85 60	97.19 17	97.89 36	86.28 53	98.71 124	97.11 16	98.08 80	97.17 169

ZNCC-MVS		94.47 34	94.28 46	95.03 17	98.52 18	86.96 21	96.85 33	97.32 35	88.24 127	93.15 90	97.04 74	86.17 54	99.62 5	92.40 88	98.81 27	98.52 31

HFP-MVS		94.52 32	94.40 39	94.86 27	98.61 13	86.81 27	96.94 25	97.34 31	88.63 113	93.65 80	97.21 63	86.10 55	99.49 31	92.35 91	98.77 32	98.30 56

MVS_111021_HR		93.45 75	93.31 80	93.84 73	96.99 83	84.84 87	93.24 292	97.24 42	88.76 108	91.60 144	95.85 144	86.07 56	98.66 127	91.91 111	98.16 72	98.03 92

ACMMP_NAP		94.74 26	94.56 34	95.28 11	98.02 48	87.70 12	95.68 107	97.34 31	88.28 126	95.30 53	97.67 44	85.90 57	99.54 25	93.91 58	98.95 15	98.60 28

fmvsm_l_conf0.5_n_9		94.65 28	95.28 16	92.77 127	95.95 130	81.83 200	95.53 120	97.12 56	91.68 17	97.89 2	98.06 25	85.71 58	98.65 129	97.32 12	98.26 64	97.83 121

CS-MVS		94.12 52	94.44 38	93.17 99	96.55 96	83.08 154	97.63 4	96.95 71	91.71 16	93.50 86	96.21 110	85.61 59	98.24 172	93.64 63	98.17 71	98.19 73

PHI-MVS		93.89 61	93.65 75	94.62 46	96.84 86	86.43 41	96.69 37	97.49 11	85.15 246	93.56 84	96.28 108	85.60 60	99.31 48	92.45 85	98.79 28	98.12 82

MP-MVS-pluss		94.21 46	94.00 60	94.85 28	98.17 40	86.65 33	94.82 170	97.17 50	86.26 207	92.83 100	97.87 37	85.57 61	99.56 17	94.37 54	98.92 19	98.34 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
GST-MVS		94.21 46	93.97 61	94.90 25	98.41 26	86.82 26	96.54 41	97.19 45	88.24 127	93.26 87	96.83 83	85.48 62	99.59 11	91.43 123	98.40 59	98.30 56

MP-MVS		94.25 43	94.07 57	94.77 40	98.47 21	86.31 46	96.71 36	96.98 65	89.04 96	91.98 127	97.19 66	85.43 63	99.56 17	92.06 105	98.79 28	98.44 43
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 54	93.79 66	94.80 38	97.48 71	86.78 28	95.65 112	96.89 78	89.40 80	92.81 101	96.97 76	85.37 64	99.24 53	90.87 134	98.69 39	98.38 48
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.5_n_11		94.60 29	95.23 17	92.69 139	96.05 121	82.00 193	96.31 46	96.71 102	92.27 8	96.68 31	98.39 3	85.32 65	98.92 96	97.20 14	98.16 72	97.17 169

region2R		94.43 37	94.27 48	94.92 22	98.65 11	86.67 32	96.92 29	97.23 44	88.60 116	93.58 82	97.27 59	85.22 66	99.54 25	92.21 96	98.74 35	98.56 30

CP-MVS		94.34 41	94.21 51	94.74 42	98.39 29	86.64 34	97.60 5	97.24 42	88.53 118	92.73 106	97.23 62	85.20 67	99.32 47	92.15 99	98.83 26	98.25 70

test_fmvsmconf0.1_n		94.20 48	94.31 44	93.88 71	92.46 338	84.80 89	96.18 59	96.82 86	89.29 86	95.68 48	98.11 12	85.10 68	98.99 83	97.38 11	97.75 97	97.86 116

test12				94.34 58	97.13 81	86.15 53		96.29 134		91.04 166		85.08 69	99.01 76		98.13 76	97.86 116

ACMMPR		94.43 37	94.28 46	94.91 23	98.63 12	86.69 30	96.94 25	97.32 35	88.63 113	93.53 85	97.26 61	85.04 70	99.54 25	92.35 91	98.78 30	98.50 32

SPE-MVS-test		94.02 55	94.29 45	93.24 93	96.69 89	83.24 142	97.49 6	96.92 74	92.14 9	92.90 96	95.77 153	85.02 71	98.33 167	93.03 74	98.62 50	98.13 79

XVS		94.45 35	94.32 42	94.85 28	98.54 16	86.60 36	96.93 27	97.19 45	90.66 37	92.85 98	97.16 69	85.02 71	99.49 31	91.99 107	98.56 55	98.47 38

X-MVStestdata		88.31 244	86.13 293	94.85 28	98.54 16	86.60 36	96.93 27	97.19 45	90.66 37	92.85 98	23.41 541	85.02 71	99.49 31	91.99 107	98.56 55	98.47 38

MVSMamba_PlusPlus		93.44 76	93.54 77	93.14 101	96.58 95	83.05 155	96.06 73	96.50 120	84.42 268	94.09 70	95.56 164	85.01 74	98.69 126	94.96 46	98.66 45	97.67 133

fmvsm_l_conf0.5_n_3		94.80 24	95.01 22	94.15 64	95.64 143	85.08 83	96.09 68	97.36 29	90.98 25	97.09 20	98.12 11	84.98 75	98.94 93	97.07 17	97.80 93	98.43 44

MSLP-MVS++		93.72 67	94.08 56	92.65 142	97.31 76	83.43 135	95.79 98	97.33 33	90.03 54	93.58 82	96.96 77	84.87 76	97.76 234	92.19 98	98.66 45	96.76 207

HPM-MVS		94.02 55	93.88 62	94.43 52	98.39 29	85.78 71	97.25 15	97.07 61	86.90 190	92.62 112	96.80 87	84.85 77	99.17 58	92.43 86	98.65 48	98.33 51
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 17	95.50 9	93.44 86	96.51 101	82.25 187	95.76 102	96.92 74	93.37 3	97.63 8	98.43 2	84.82 78	99.16 61	98.15 1	97.92 86	98.90 15

SR-MVS		94.23 45	94.17 55	94.43 52	98.21 39	85.78 71	96.40 43	96.90 77	88.20 130	94.33 64	97.40 54	84.75 79	99.03 71	93.35 69	97.99 83	98.48 35

PGM-MVS		93.96 59	93.72 71	94.68 43	98.43 24	86.22 50	95.30 130	97.78 3	87.45 168	93.26 87	97.33 57	84.62 80	99.51 29	90.75 138	98.57 53	98.32 55

BridgeMVS		93.98 58	94.22 49	93.26 92	96.13 111	83.29 141	96.27 53	96.52 118	89.82 61	95.56 50	95.51 167	84.50 81	98.79 114	94.83 48	98.86 21	97.72 130

EI-MVSNet-Vis-set		93.01 93	92.92 90	93.29 90	95.01 175	83.51 134	94.48 193	95.77 201	90.87 26	92.52 114	96.67 90	84.50 81	99.00 81	91.99 107	94.44 186	97.36 153

MTAPA		94.42 40	94.22 49	95.00 19	98.42 25	86.95 22	94.36 213	96.97 66	91.07 23	93.14 91	97.56 46	84.30 83	99.56 17	93.43 66	98.75 34	98.47 38

SR-MVS-dyc-post		93.82 63	93.82 64	93.82 74	97.92 50	84.57 95	96.28 51	96.76 94	87.46 166	93.75 78	97.43 52	84.24 84	99.01 76	92.73 78	97.80 93	97.88 114

ETV-MVS		92.74 99	92.66 96	92.97 113	95.20 167	84.04 118	95.07 152	96.51 119	90.73 35	92.96 95	91.19 350	84.06 85	98.34 165	91.72 116	96.54 128	96.54 220

EI-MVSNet-UG-set		92.74 99	92.62 98	93.12 102	94.86 189	83.20 144	94.40 205	95.74 204	90.71 36	92.05 125	96.60 97	84.00 86	98.99 83	91.55 119	93.63 215	97.17 169

mPP-MVS		93.99 57	93.78 67	94.63 45	98.50 19	85.90 65	96.87 31	96.91 76	88.70 111	91.83 137	97.17 68	83.96 87	99.55 21	91.44 122	98.64 49	98.43 44

APD-MVS_3200maxsize		93.78 64	93.77 68	93.80 76	97.92 50	84.19 112	96.30 47	96.87 80	86.96 186	93.92 76	97.47 50	83.88 88	98.96 90	92.71 81	97.87 89	98.26 69

EIA-MVS		91.95 113	91.94 110	91.98 190	95.16 169	80.01 282	95.36 125	96.73 99	88.44 119	89.34 206	92.16 313	83.82 89	98.45 153	89.35 164	97.06 110	97.48 148

fmvsm_s_conf0.5_n_3		94.49 33	95.13 18	92.56 147	95.49 153	81.10 229	95.93 86	97.16 51	92.96 4	97.39 13	98.13 8	83.63 90	98.80 112	97.89 3	97.61 100	97.78 126

fmvsm_s_conf0.5_n		93.76 65	94.06 59	92.86 121	95.62 145	83.17 146	96.14 64	96.12 168	88.13 133	95.82 44	98.04 31	83.43 91	98.48 145	96.97 21	96.23 135	96.92 196

casdiffmvs_mvg		92.96 94	92.83 92	93.35 88	94.59 214	83.40 137	95.00 157	96.34 131	90.30 47	92.05 125	96.05 126	83.43 91	98.15 180	92.07 102	95.67 149	98.49 34
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPP-MVSNet		91.70 130	91.56 120	92.13 185	95.88 131	80.50 262	97.33 8	95.25 251	86.15 210	89.76 199	95.60 161	83.42 93	98.32 169	87.37 199	93.25 230	97.56 142

test_fmvsmvis_n_1920		93.44 76	93.55 76	93.10 103	93.67 288	84.26 110	95.83 95	96.14 164	89.00 101	92.43 117	97.50 49	83.37 94	98.72 122	96.61 25	97.44 102	96.32 225

fmvsm_s_conf0.5_n_5		93.96 59	94.18 54	93.30 89	94.79 193	83.81 123	95.77 100	96.74 98	88.02 141	96.23 34	97.84 39	83.36 95	98.83 110	97.49 8	97.34 106	97.25 161

fmvsm_s_conf0.5_n_6		94.11 53	94.56 34	92.76 130	94.98 179	81.96 197	95.79 98	97.29 40	89.31 84	97.52 12	97.61 45	83.25 96	98.88 100	97.05 19	98.22 70	97.43 152

UA-Net		92.83 95	92.54 99	93.68 82	96.10 116	84.71 91	95.66 110	96.39 127	91.92 11	93.22 89	96.49 101	83.16 97	98.87 101	84.47 246	95.47 156	97.45 150

UniMVSNet_NR-MVSNet		89.92 189	89.29 192	91.81 207	93.39 297	83.72 125	94.43 199	97.12 56	89.80 64	86.46 267	93.32 273	83.16 97	97.23 302	84.92 234	81.02 411	94.49 312

EC-MVSNet		93.44 76	93.71 72	92.63 143	95.21 166	82.43 180	97.27 14	96.71 102	90.57 40	92.88 97	95.80 149	83.16 97	98.16 179	93.68 61	98.14 75	97.31 154

fmvsm_s_conf0.5_n_4		93.86 62	94.37 41	92.33 167	95.13 172	80.95 236	95.64 113	96.97 66	89.60 73	96.85 25	97.77 41	83.08 100	98.92 96	97.49 8	96.78 122	97.13 177

fmvsm_s_conf0.5_n_a		93.57 69	93.76 69	93.00 111	95.02 174	83.67 127	96.19 57	96.10 170	87.27 173	95.98 41	98.05 28	83.07 101	98.45 153	96.68 24	95.51 153	96.88 199

MM		95.10 14	94.91 27	95.68 5	96.09 117	88.34 10	96.68 38	94.37 309	95.08 1	94.68 60	97.72 42	82.94 102	99.64 3	97.85 5	98.76 33	99.06 9

RE-MVS-def			93.68 73		97.92 50	84.57 95	96.28 51	96.76 94	87.46 166	93.75 78	97.43 52	82.94 102		92.73 78	97.80 93	97.88 114

新几何1				93.10 103	97.30 77	84.35 109		95.56 222	71.09 474	91.26 154	96.24 109	82.87 104	98.86 103	79.19 349	98.10 77	96.07 241

fmvsm_s_conf0.1_n		93.46 73	93.66 74	92.85 122	93.75 280	83.13 148	96.02 77	95.74 204	87.68 160	95.89 42	98.17 6	82.78 105	98.46 149	96.71 23	96.17 137	96.98 190

Casviewmamba		92.82 97	92.75 93	93.03 108	94.79 193	82.44 179	95.39 124	96.24 145	90.58 39	91.79 139	96.43 105	82.73 106	98.19 177	91.31 124	95.54 151	98.46 41

原ACMM1				92.01 186	97.34 74	81.05 231		96.81 89	78.89 384	90.45 177	95.92 137	82.65 107	98.84 107	80.68 317	98.26 64	96.14 235

casdiffmvs		92.51 102	92.43 101	92.74 134	94.41 235	81.98 195	94.54 190	96.23 147	89.57 75	91.96 129	96.17 116	82.58 108	98.01 209	90.95 132	95.45 158	98.23 71
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 82	92.99 89	94.26 62	96.07 119	85.83 69	94.89 163	96.99 64	89.02 99	89.56 201	97.37 56	82.51 109	99.38 36	92.20 97	98.30 62	97.57 141
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 81	93.22 83	93.94 70	98.36 32	84.83 88	97.15 18	96.80 90	85.77 219	92.47 116	97.13 70	82.38 110	99.07 66	90.51 143	98.40 59	97.92 110

baseline		92.39 107	92.29 105	92.69 139	94.46 230	81.77 205	94.14 225	96.27 138	89.22 88	91.88 133	96.00 130	82.35 111	97.99 211	91.05 127	95.27 164	98.30 56

sasdasda		93.27 83	92.75 93	94.85 28	95.70 140	87.66 13	96.33 44	96.41 125	90.00 55	94.09 70	94.60 220	82.33 112	98.62 135	92.40 88	92.86 242	98.27 65

canonicalmvs		93.27 83	92.75 93	94.85 28	95.70 140	87.66 13	96.33 44	96.41 125	90.00 55	94.09 70	94.60 220	82.33 112	98.62 135	92.40 88	92.86 242	98.27 65

fmvsm_s_conf0.1_n_a		93.19 87	93.26 81	92.97 113	92.49 336	83.62 130	96.02 77	95.72 208	86.78 192	96.04 39	98.19 5	82.30 114	98.43 157	96.38 26	95.42 159	96.86 201

DP-MVS Recon		91.95 113	91.28 133	93.96 69	98.33 34	85.92 62	94.66 184	96.66 106	82.69 314	90.03 194	95.82 147	82.30 114	99.03 71	84.57 244	96.48 131	96.91 197

hybridcas		92.43 105	92.33 102	92.74 134	94.51 222	81.84 199	95.05 155	96.16 162	89.60 73	91.40 151	96.20 111	82.23 116	98.09 191	89.95 153	95.87 143	98.28 62

PAPR		90.02 183	89.27 194	92.29 174	95.78 135	80.95 236	92.68 319	96.22 148	81.91 333	86.66 264	93.75 263	82.23 116	98.44 155	79.40 348	94.79 172	97.48 148

MVS_Test		91.31 139	91.11 136	91.93 195	94.37 236	80.14 271	93.46 277	95.80 199	86.46 201	91.35 153	93.77 261	82.21 118	98.09 191	87.57 194	94.95 168	97.55 144

nrg030		91.08 150	90.39 155	93.17 99	93.07 309	86.91 23	96.41 42	96.26 142	88.30 124	88.37 226	94.85 206	82.19 119	97.64 245	91.09 126	82.95 381	94.96 286

MGCFI-Net		93.03 92	92.63 97	94.23 63	95.62 145	85.92 62	96.08 69	96.33 132	89.86 59	93.89 77	94.66 216	82.11 120	98.50 143	92.33 93	92.82 245	98.27 65

UniMVSNet (Re)		89.80 193	89.07 198	92.01 186	93.60 291	84.52 98	94.78 174	97.47 16	89.26 87	86.44 270	92.32 308	82.10 121	97.39 284	84.81 237	80.84 415	94.12 326

testdata				90.49 276	96.40 102	77.89 352		95.37 242	72.51 466	93.63 81	96.69 88	82.08 122	97.65 243	83.08 265	97.39 103	95.94 246

PAPM_NR		91.22 142	90.78 147	92.52 151	97.60 66	81.46 215	94.37 211	96.24 145	86.39 204	87.41 247	94.80 208	82.06 123	98.48 145	82.80 273	95.37 160	97.61 137

MG-MVS		91.77 121	91.70 114	92.00 189	97.08 82	80.03 281	93.60 272	95.18 257	87.85 153	90.89 170	96.47 103	82.06 123	98.36 162	85.07 232	97.04 111	97.62 135

CANet		93.54 70	93.20 84	94.55 48	95.65 142	85.73 73	94.94 160	96.69 105	91.89 13	90.69 172	95.88 140	81.99 125	99.54 25	93.14 72	97.95 85	98.39 46

FC-MVSNet-test		90.27 174	90.18 162	90.53 269	93.71 285	79.85 290	95.77 100	97.59 6	89.31 84	86.27 274	94.67 215	81.93 126	97.01 321	84.26 248	88.09 326	94.71 298

fmvsm_s_conf0.5_n_10		94.43 37	94.84 30	93.20 95	95.73 137	83.19 145	95.99 79	97.31 37	91.08 22	97.67 5	98.11 12	81.87 127	99.22 54	97.86 4	97.91 88	97.20 167

fmvsm_s_conf0.5_n_7		93.15 90	93.76 69	91.31 233	94.42 234	79.48 302	94.52 191	97.14 54	89.33 83	94.17 68	98.09 19	81.83 128	97.49 261	96.33 27	98.02 82	96.95 192

FIs		90.51 170	90.35 156	90.99 251	93.99 267	80.98 234	95.73 104	97.54 9	89.15 91	86.72 263	94.68 212	81.83 128	97.24 301	85.18 230	88.31 323	94.76 297

fmvsm_s_conf0.5_n_8		94.56 31	95.12 19	92.87 120	95.96 129	81.32 219	95.76 102	97.57 7	93.48 2	97.53 11	98.32 4	81.78 130	99.13 63	97.91 2	97.81 92	98.16 76

E3new		91.76 122	91.58 118	92.28 178	94.69 207	80.90 239	93.68 270	96.17 160	87.15 177	91.09 165	95.70 157	81.75 131	98.05 201	89.67 161	94.35 188	97.90 113

viewcassd2359sk11		91.79 116	91.62 115	92.29 174	94.62 210	80.88 240	93.70 267	96.18 159	87.38 170	91.13 158	95.85 144	81.62 132	98.06 197	89.71 158	94.40 187	97.94 101

ACMMP		93.24 85	92.88 91	94.30 60	98.09 45	85.33 80	96.86 32	97.45 19	88.33 122	90.15 192	97.03 75	81.44 133	99.51 29	90.85 135	95.74 148	98.04 91
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+		91.59 133	91.11 136	93.01 110	94.35 240	83.39 138	94.60 186	95.10 261	87.10 180	90.57 176	93.10 284	81.43 134	98.07 196	89.29 166	94.48 184	97.59 140

MVS_111021_LR		92.47 104	92.29 105	92.98 112	95.99 126	84.43 104	93.08 298	96.09 171	88.20 130	91.12 159	95.72 156	81.33 135	97.76 234	91.74 115	97.37 104	96.75 208

E2		91.79 116	91.61 116	92.31 169	94.49 226	80.86 243	93.74 262	96.19 152	87.63 163	91.16 155	95.94 135	81.31 136	98.06 197	89.76 156	94.29 191	97.99 95

E3		91.78 119	91.61 116	92.30 172	94.48 227	80.86 243	93.73 263	96.19 152	87.63 163	91.16 155	95.95 134	81.30 137	98.06 197	89.76 156	94.29 191	97.99 95

mvs_anonymous		89.37 212	89.32 191	89.51 338	93.47 294	74.22 412	91.65 360	94.83 286	82.91 309	85.45 299	93.79 259	81.23 138	96.36 374	86.47 211	94.09 196	97.94 101

PVSNet_BlendedMVS		89.98 184	89.70 177	90.82 260	96.12 112	81.25 221	93.92 249	96.83 84	83.49 290	89.10 210	92.26 311	81.04 139	98.85 105	86.72 209	87.86 330	92.35 418

PVSNet_Blended		90.73 157	90.32 157	91.98 190	96.12 112	81.25 221	92.55 324	96.83 84	82.04 329	89.10 210	92.56 301	81.04 139	98.85 105	86.72 209	95.91 142	95.84 252

viewmanbaseed2359cas		91.78 119	91.58 118	92.37 162	94.32 243	81.07 230	93.76 260	95.96 184	87.26 174	91.50 146	95.88 140	80.92 141	97.97 216	89.70 159	94.92 169	98.07 84

PRO-TEST		92.11 110	92.00 109	92.44 157	94.50 224	81.48 214	94.67 182	96.19 152	88.04 140	92.23 121	94.64 218	80.86 142	97.82 231	90.78 137	96.11 140	98.02 94

E4		91.74 124	91.55 121	92.31 169	94.27 248	80.80 247	93.81 257	96.17 160	87.97 143	91.11 160	96.05 126	80.75 143	98.08 194	89.78 155	94.02 198	98.06 89

viewmamba		91.38 136	91.32 130	91.58 217	93.02 316	79.63 299	92.83 312	95.38 239	88.29 125	90.66 173	95.81 148	80.63 144	97.50 260	91.52 120	93.71 213	97.62 135

MGCNet		94.18 51	93.80 65	95.34 10	94.91 186	87.62 15	95.97 82	93.01 360	92.58 6	94.22 65	97.20 65	80.56 145	99.59 11	97.04 20	98.68 41	98.81 22

alignmvs		93.08 91	92.50 100	94.81 36	95.62 145	87.61 16	95.99 79	96.07 173	89.77 68	94.12 69	94.87 203	80.56 145	98.66 127	92.42 87	93.10 237	98.15 77

API-MVS		90.66 163	90.07 166	92.45 156	96.36 104	84.57 95	96.06 73	95.22 254	82.39 317	89.13 209	94.27 238	80.32 147	98.46 149	80.16 327	96.71 124	94.33 318

PVSNet_Blended_VisFu		91.38 136	90.91 143	92.80 125	96.39 103	83.17 146	94.87 165	96.66 106	83.29 296	89.27 208	94.46 229	80.29 148	99.17 58	87.57 194	95.37 160	96.05 244

viewdifsd2359ckpt07		91.11 148	91.02 140	91.41 228	94.21 253	78.37 336	92.91 308	95.71 209	87.50 165	90.32 182	95.88 140	80.27 149	97.99 211	88.78 177	93.55 217	97.86 116

test222					96.55 96	81.70 206	92.22 342	95.01 265	68.36 483	90.20 185	96.14 121	80.26 150			97.80 93	96.05 244

diffmvs		91.37 138	91.23 134	91.77 208	93.09 307	80.27 266	92.36 330	95.52 227	87.03 183	91.40 151	94.93 199	80.08 151	97.44 270	92.13 101	94.56 181	97.61 137
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												80.02 152

onestephybrid01		91.23 140	91.10 138	91.61 215	93.07 309	79.86 288	92.83 312	95.34 245	87.07 181	91.04 166	95.53 165	80.01 153	97.43 271	90.96 131	94.08 197	97.56 142

diffmvs_AUTHOR		91.51 134	91.44 127	91.73 209	93.09 307	80.27 266	92.51 325	95.58 221	87.22 175	91.80 138	95.57 163	79.96 154	97.48 262	92.23 95	94.97 167	97.45 150

E5new		91.71 126	91.55 121	92.20 180	94.33 241	80.62 254	94.41 201	96.19 152	88.06 136	91.11 160	96.16 117	79.92 155	98.03 205	90.00 148	93.80 208	97.94 101

E6new		91.71 126	91.55 121	92.20 180	94.32 243	80.62 254	94.41 201	96.19 152	88.06 136	91.11 160	96.16 117	79.92 155	98.03 205	90.00 148	93.80 208	97.94 101

E6		91.71 126	91.55 121	92.20 180	94.32 243	80.62 254	94.41 201	96.19 152	88.06 136	91.11 160	96.16 117	79.92 155	98.03 205	90.00 148	93.80 208	97.94 101

E5		91.71 126	91.55 121	92.20 180	94.33 241	80.62 254	94.41 201	96.19 152	88.06 136	91.11 160	96.16 117	79.92 155	98.03 205	90.00 148	93.80 208	97.94 101

viewmacassd2359aftdt		91.67 132	91.43 128	92.37 162	93.95 271	81.00 233	93.90 254	95.97 183	87.75 158	91.45 149	96.04 128	79.92 155	97.97 216	89.26 167	94.67 175	98.14 78

IterMVS-LS		88.36 243	87.91 237	89.70 322	93.80 277	78.29 340	93.73 263	95.08 263	85.73 220	84.75 320	91.90 329	79.88 160	96.92 327	83.83 255	82.51 387	93.89 338
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 217	88.86 209	89.80 316	91.84 358	78.30 339	93.70 267	95.01 265	85.73 220	87.15 251	95.28 180	79.87 161	97.21 304	83.81 256	87.36 338	93.88 341

TAPA-MVS	84.62 6	88.16 248	87.01 258	91.62 214	96.64 91	80.65 251	94.39 207	96.21 151	76.38 425	86.19 277	95.44 170	79.75 162	98.08 194	62.75 475	95.29 162	96.13 236
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 208	88.64 212	91.71 211	94.74 198	80.81 246	93.54 273	95.10 261	83.11 300	86.82 262	90.67 373	79.74 163	97.75 238	80.51 320	93.55 217	96.57 218

pcd_1.5k_mvsjas		6.64 527	8.86 528	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	79.70 164	0.00 563	0.00 562	0.00 562	0.00 559

PS-MVSNAJss		89.97 185	89.62 180	91.02 248	91.90 356	80.85 245	95.26 136	95.98 180	86.26 207	86.21 276	94.29 235	79.70 164	97.65 243	88.87 176	88.10 324	94.57 304

PS-MVSNAJ		91.18 144	90.92 142	91.96 192	95.26 164	82.60 177	92.09 347	95.70 210	86.27 206	91.84 135	92.46 303	79.70 164	98.99 83	89.08 169	95.86 144	94.29 319

viewdifsd2359ckpt09		91.18 144	90.65 151	92.75 132	94.61 213	82.36 185	94.32 214	95.74 204	84.72 261	89.66 200	95.15 191	79.69 167	98.04 202	87.70 191	94.27 193	97.85 119

viewdifsd2359ckpt13		91.20 143	90.75 148	92.54 149	94.30 246	82.13 190	94.03 238	95.89 192	85.60 225	90.20 185	95.36 176	79.69 167	97.90 226	87.85 189	93.86 204	97.61 137

xiu_mvs_v2_base		91.13 146	90.89 144	91.86 201	94.97 180	82.42 181	92.24 340	95.64 218	86.11 214	91.74 142	93.14 282	79.67 169	98.89 99	89.06 170	95.46 157	94.28 320

WR-MVS_H		87.80 257	87.37 248	89.10 347	93.23 300	78.12 343	95.61 115	97.30 38	87.90 149	83.72 351	92.01 324	79.65 170	96.01 389	76.36 380	80.54 419	93.16 381

viewmambaseed2359dif		90.04 182	89.78 176	90.83 258	92.85 324	77.92 348	92.23 341	95.01 265	81.90 334	90.20 185	95.45 169	79.64 171	97.34 288	87.52 196	93.17 232	97.23 166

EPNet		91.79 116	91.02 140	94.10 65	90.10 424	85.25 81	96.03 76	92.05 389	92.83 5	87.39 250	95.78 152	79.39 172	99.01 76	88.13 184	97.48 101	98.05 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 288	86.62 274	89.02 350	92.13 347	77.40 369	90.91 384	94.81 288	81.28 353	84.32 337	90.08 391	79.26 173	96.62 345	83.81 256	82.94 382	93.04 388

test_fmvsmconf0.01_n		93.19 87	93.02 88	93.71 81	89.25 437	84.42 106	96.06 73	96.29 134	89.06 94	94.68 60	98.13 8	79.22 174	98.98 87	97.22 13	97.24 107	97.74 128

miper_enhance_ethall		86.90 301	86.18 291	89.06 348	91.66 367	77.58 367	90.22 403	94.82 287	79.16 380	84.48 328	89.10 410	79.19 175	96.66 338	84.06 251	82.94 382	92.94 391

hybridnocas07		90.93 151	90.72 149	91.54 219	92.75 329	79.72 296	92.35 332	95.21 255	86.41 203	90.44 180	95.40 173	79.17 176	97.39 284	90.83 136	93.94 201	97.50 147

NR-MVSNet		88.58 237	87.47 246	91.93 195	93.04 313	84.16 113	94.77 175	96.25 144	89.05 95	80.04 410	93.29 276	79.02 177	97.05 318	81.71 299	80.05 425	94.59 302

hybrid		90.69 159	90.45 154	91.43 227	92.67 334	79.42 307	92.28 339	95.21 255	85.15 246	90.39 181	95.37 175	78.93 178	97.32 290	90.27 146	93.74 212	97.55 144

TAMVS		89.21 214	88.29 225	91.96 192	93.71 285	82.62 176	93.30 287	94.19 317	82.22 323	87.78 240	93.94 251	78.83 179	96.95 325	77.70 366	92.98 239	96.32 225

c3_l		87.14 294	86.50 280	89.04 349	92.20 344	77.26 371	91.22 376	94.70 294	82.01 330	84.34 336	90.43 378	78.81 180	96.61 348	83.70 260	81.09 408	93.25 375

1112_ss		88.42 239	87.33 249	91.72 210	94.92 184	80.98 234	92.97 306	94.54 300	78.16 402	83.82 348	93.88 256	78.78 181	97.91 224	79.45 344	89.41 303	96.26 229

CDS-MVSNet		89.45 204	88.51 216	92.29 174	93.62 290	83.61 132	93.01 302	94.68 295	81.95 331	87.82 239	93.24 278	78.69 182	96.99 322	80.34 323	93.23 231	96.28 228
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 198	88.92 205	91.67 212	95.47 154	81.15 226	92.38 329	94.78 290	83.11 300	89.06 212	94.32 233	78.67 183	96.61 348	81.57 300	90.89 277	97.24 162

CPTT-MVS		91.99 112	91.80 112	92.55 148	98.24 38	81.98 195	96.76 35	96.49 121	81.89 336	90.24 183	96.44 104	78.59 184	98.61 137	89.68 160	97.85 90	97.06 182

IS-MVSNet		91.43 135	91.09 139	92.46 154	95.87 133	81.38 218	96.95 24	93.69 344	89.72 70	89.50 204	95.98 132	78.57 185	97.77 233	83.02 267	96.50 130	98.22 72

dtuplus		89.78 195	89.43 186	90.85 257	92.83 325	77.91 349	92.32 337	94.97 271	82.33 321	90.20 185	95.53 165	78.56 186	97.38 286	85.15 231	92.95 240	97.24 162

casdiffseed414692147		91.11 148	90.55 153	92.81 123	94.27 248	82.58 178	94.81 171	96.03 178	87.93 147	90.17 190	95.62 160	78.51 187	97.90 226	84.18 250	93.45 224	97.94 101

OMC-MVS		91.23 140	90.62 152	93.08 105	96.27 106	84.07 114	93.52 274	95.93 186	86.95 187	89.51 202	96.13 122	78.50 188	98.35 164	85.84 222	92.90 241	96.83 206

IMVS_0403		89.97 185	89.64 179	90.96 254	93.72 281	77.75 360	93.00 303	95.34 245	85.53 229	88.77 219	94.49 225	78.49 189	97.84 229	84.75 238	92.65 247	97.28 157

PCF-MVS	84.11 10	87.74 259	86.08 297	92.70 138	94.02 262	84.43 104	89.27 424	95.87 195	73.62 456	84.43 331	94.33 232	78.48 190	98.86 103	70.27 431	94.45 185	94.81 295
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 245	88.32 224	88.27 371	94.71 204	72.41 439	93.15 293	90.98 422	87.77 156	79.25 425	91.96 326	78.35 191	95.75 403	83.04 266	95.62 150	96.65 213

HY-MVS	83.01 12	89.03 223	87.94 234	92.29 174	94.86 189	82.77 163	92.08 348	94.49 303	81.52 349	86.93 254	92.79 295	78.32 192	98.23 173	79.93 330	90.55 281	95.88 250

GeoE		90.05 181	89.43 186	91.90 200	95.16 169	80.37 265	95.80 96	94.65 296	83.90 277	87.55 246	94.75 209	78.18 193	97.62 247	81.28 305	93.63 215	97.71 131

NormalMVS		93.46 73	93.16 85	94.37 57	98.40 27	86.20 51	96.30 47	96.27 138	91.65 18	92.68 108	96.13 122	77.97 194	98.84 107	90.75 138	98.26 64	98.07 84

SymmetryMVS		92.81 98	92.31 103	94.32 59	96.15 109	86.20 51	96.30 47	94.43 305	91.65 18	92.68 108	96.13 122	77.97 194	98.84 107	90.75 138	94.72 173	97.92 110

MVS		87.44 276	86.10 296	91.44 226	92.61 335	83.62 130	92.63 321	95.66 215	67.26 486	81.47 388	92.15 314	77.95 196	98.22 175	79.71 333	95.48 155	92.47 411

MVSFormer		91.68 131	91.30 131	92.80 125	93.86 273	83.88 121	95.96 83	95.90 190	84.66 264	91.76 140	94.91 200	77.92 197	97.30 291	89.64 162	97.11 108	97.24 162

lupinMVS		90.92 152	90.21 160	93.03 108	93.86 273	83.88 121	92.81 314	93.86 331	79.84 371	91.76 140	94.29 235	77.92 197	98.04 202	90.48 144	97.11 108	97.17 169

Test_1112_low_res		87.65 262	86.51 279	91.08 244	94.94 183	79.28 316	91.77 355	94.30 312	76.04 431	83.51 358	92.37 306	77.86 199	97.73 239	78.69 355	89.13 310	96.22 230

VNet		92.24 108	91.91 111	93.24 93	96.59 93	83.43 135	94.84 169	96.44 122	89.19 90	94.08 73	95.90 138	77.85 200	98.17 178	88.90 174	93.38 226	98.13 79

icg_test_0407_2		89.15 215	88.97 202	89.68 328	93.72 281	77.75 360	88.26 443	95.34 245	85.53 229	88.34 227	94.49 225	77.69 201	93.99 443	84.75 238	92.65 247	97.28 157

IMVS_0407		89.85 192	89.51 183	90.88 256	93.72 281	77.75 360	93.07 300	95.34 245	85.53 229	88.34 227	94.49 225	77.69 201	97.60 248	84.75 238	92.65 247	97.28 157

fmvsm_s_conf0.5_n_2		93.47 72	93.83 63	92.39 161	95.36 157	81.19 225	95.20 144	96.56 115	90.37 43	97.13 19	98.03 32	77.47 203	98.96 90	97.79 6	96.58 127	97.03 185

mvsany_test1		85.42 343	85.30 327	85.77 430	87.95 456	75.41 400	87.61 457	80.97 497	76.82 421	88.68 220	95.83 146	77.44 204	90.82 483	85.90 220	86.51 345	91.08 450

DU-MVS		89.34 213	88.50 217	91.85 203	93.04 313	83.72 125	94.47 196	96.59 112	89.50 76	86.46 267	93.29 276	77.25 205	97.23 302	84.92 234	81.02 411	94.59 302

Baseline_NR-MVSNet		87.07 296	86.63 273	88.40 365	91.44 371	77.87 353	94.23 221	92.57 372	84.12 273	85.74 287	92.08 320	77.25 205	96.04 385	82.29 282	79.94 426	91.30 442

testing915		90.59 168	90.24 159	91.63 213	95.58 151	80.71 250	95.14 148	92.25 383	87.37 171	90.97 169	94.37 230	77.06 207	97.29 294	85.51 226	93.93 202	96.88 199

jason		90.80 154	90.10 164	92.90 118	93.04 313	83.53 133	93.08 298	94.15 320	80.22 365	91.41 150	94.91 200	76.87 208	97.93 222	90.28 145	96.90 117	97.24 162
jason: jason.
PAPM		86.68 313	85.39 323	90.53 269	93.05 312	79.33 315	89.79 413	94.77 291	78.82 387	81.95 384	93.24 278	76.81 209	97.30 291	66.94 455	93.16 233	94.95 290

Vis-MVSNet (Re-imp)		89.59 199	89.44 185	90.03 302	95.74 136	75.85 394	95.61 115	90.80 429	87.66 162	87.83 238	95.40 173	76.79 210	96.46 366	78.37 356	96.73 123	97.80 124

baseline1		88.10 249	87.28 251	90.57 265	94.96 181	80.07 276	94.27 217	91.29 414	86.74 193	87.41 247	94.00 248	76.77 211	96.20 380	80.77 314	79.31 434	95.44 266

114514_t		89.51 201	88.50 217	92.54 149	98.11 43	81.99 194	95.16 147	96.36 130	70.19 478	85.81 284	95.25 182	76.70 212	98.63 134	82.07 288	96.86 120	97.00 189

PLC	84.53 7	89.06 221	88.03 230	92.15 184	97.27 79	82.69 170	94.29 216	95.44 235	79.71 373	84.01 345	94.18 241	76.68 213	98.75 118	77.28 370	93.41 225	95.02 282
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 227	87.95 233	91.49 223	92.68 333	83.01 158	94.92 162	96.31 133	89.88 58	85.53 293	93.85 258	76.63 214	96.96 324	81.91 292	79.87 428	94.50 310

MAR-MVS		90.30 173	89.37 189	93.07 107	96.61 92	84.48 100	95.68 107	95.67 213	82.36 319	87.85 236	92.85 289	76.63 214	98.80 112	80.01 329	96.68 125	95.91 247
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 89	93.42 78	92.37 162	94.62 210	81.13 227	95.23 137	95.89 192	90.30 47	96.74 30	98.02 33	76.14 216	98.95 92	97.64 7	96.21 136	97.03 185

SSM_0407		90.47 171	89.80 175	92.46 154	94.76 195	82.66 171	93.98 245	95.00 269	85.41 234	88.96 214	95.35 177	76.13 217	97.88 228	85.46 228	93.15 234	96.85 202

SSM_0404		90.73 157	90.08 165	92.69 139	95.00 178	83.13 148	94.32 214	95.00 269	85.41 234	89.84 195	95.35 177	76.13 217	97.98 214	85.46 228	94.18 195	96.95 192

WR-MVS		88.38 241	87.67 241	90.52 273	93.30 299	80.18 269	93.26 290	95.96 184	88.57 117	85.47 298	92.81 293	76.12 219	96.91 328	81.24 306	82.29 391	94.47 315

v8		87.50 275	86.71 267	89.89 309	91.37 376	79.40 308	94.50 192	95.38 239	84.81 258	83.60 356	91.33 345	76.05 220	97.42 273	82.84 271	80.51 422	92.84 395

v148		87.04 297	86.32 286	89.21 343	90.94 396	77.26 371	93.71 266	94.43 305	84.84 257	84.36 335	90.80 367	76.04 221	97.05 318	82.12 285	79.60 431	93.31 372

mamba_0408		89.06 221	87.92 235	92.50 152	94.76 195	82.66 171	79.84 501	94.64 297	85.18 239	88.96 214	95.00 196	76.00 222	97.98 214	83.74 258	93.15 234	96.85 202

SSM_04072		88.57 238	87.92 235	90.51 274	94.76 195	82.66 171	79.84 501	94.64 297	85.18 239	88.96 214	95.00 196	76.00 222	92.03 468	83.74 258	93.15 234	96.85 202

eth_miper_zixun_eth		86.50 320	85.77 311	88.68 359	91.94 353	75.81 395	90.47 395	94.89 280	82.05 327	84.05 343	90.46 377	75.96 224	96.77 332	82.76 274	79.36 433	93.46 368

3Dnovator+	87.14 4	92.42 106	91.37 129	95.55 7	95.63 144	88.73 7	97.07 23	96.77 93	90.84 27	84.02 344	96.62 96	75.95 225	99.34 43	87.77 190	97.68 98	98.59 29

balanced_ft_v1		92.23 109	92.05 108	92.77 127	95.40 156	81.78 204	95.80 96	95.69 212	87.94 145	91.92 132	95.04 194	75.91 226	98.71 124	93.83 60	96.94 114	97.82 123

h-mvs33		90.80 154	90.15 163	92.75 132	96.01 122	82.66 171	95.43 123	95.53 226	89.80 64	93.08 92	95.64 159	75.77 227	99.00 81	92.07 102	78.05 438	96.60 215

hse-mvs2		89.88 191	89.34 190	91.51 222	94.83 191	81.12 228	93.94 247	93.91 330	89.80 64	93.08 92	93.60 266	75.77 227	97.66 242	92.07 102	77.07 446	95.74 257

BH-untuned		88.60 235	88.13 229	90.01 305	95.24 165	78.50 332	93.29 288	94.15 320	84.75 260	84.46 329	93.40 270	75.76 229	97.40 281	77.59 367	94.52 183	94.12 326

DIV-MVS_self_test		86.53 318	85.78 309	88.75 356	92.02 352	76.45 386	90.74 386	94.30 312	81.83 339	83.34 365	90.82 366	75.75 230	96.57 355	81.73 298	81.52 403	93.24 376

BH-w/o		87.57 271	87.05 256	89.12 346	94.90 187	77.90 351	92.41 327	93.51 347	82.89 310	83.70 352	91.34 344	75.75 230	97.07 315	75.49 388	93.49 221	92.39 416

cl____		86.52 319	85.78 309	88.75 356	92.03 351	76.46 385	90.74 386	94.30 312	81.83 339	83.34 365	90.78 368	75.74 232	96.57 355	81.74 297	81.54 402	93.22 377

cdsmvs_eth3d_5k		22.14 499	29.52 495	0.00 543	0.00 567	0.00 570	0.00 555	95.76 202	0.00 562	0.00 563	94.29 235	75.66 233	0.00 563	0.00 562	0.00 562	0.00 559

CNLPA		89.07 220	87.98 232	92.34 166	96.87 85	84.78 90	94.08 233	93.24 352	81.41 350	84.46 329	95.13 192	75.57 234	96.62 345	77.21 371	93.84 206	95.61 264

CHOSEN 1792x2688		88.84 227	87.69 240	92.30 172	96.14 110	81.42 217	90.01 410	95.86 196	74.52 446	87.41 247	93.94 251	75.46 235	98.36 162	80.36 322	95.53 152	97.12 178

CP-MVSNet		87.63 265	87.26 253	88.74 358	93.12 305	76.59 384	95.29 132	96.58 113	88.43 120	83.49 361	92.98 287	75.28 236	95.83 398	78.97 351	81.15 407	93.79 348

v10		87.25 285	86.38 282	89.85 311	91.19 382	79.50 301	94.48 193	95.45 233	83.79 282	83.62 355	91.19 350	75.13 237	97.42 273	81.94 291	80.60 417	92.63 402

Vis-MVSNet		91.75 123	91.23 134	93.29 90	95.32 159	83.78 124	96.14 64	95.98 180	89.89 57	90.45 177	96.58 98	75.09 238	98.31 170	84.75 238	96.90 117	97.78 126
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 226	88.26 227	90.94 255	94.05 261	80.78 248	91.71 357	95.38 239	81.55 348	88.63 221	93.91 255	75.04 239	95.47 416	82.47 277	91.61 263	96.57 218

v1144		87.61 268	86.79 265	90.06 300	91.01 391	79.34 312	93.95 246	95.42 238	83.36 295	85.66 289	91.31 348	74.98 240	97.42 273	83.37 262	82.06 393	93.42 369

miper_lstm_enhance		85.27 348	84.59 346	87.31 398	91.28 380	74.63 407	87.69 454	94.09 324	81.20 357	81.36 391	89.85 399	74.97 241	94.30 437	81.03 310	79.84 429	93.01 389

test_yl		90.69 159	90.02 170	92.71 136	95.72 138	82.41 183	94.11 228	95.12 259	85.63 223	91.49 147	94.70 210	74.75 242	98.42 158	86.13 217	92.53 254	97.31 154

DCV-MVSNet		90.69 159	90.02 170	92.71 136	95.72 138	82.41 183	94.11 228	95.12 259	85.63 223	91.49 147	94.70 210	74.75 242	98.42 158	86.13 217	92.53 254	97.31 154

V42		87.68 260	86.86 260	90.15 293	90.58 412	80.14 271	94.24 220	95.28 250	83.66 284	85.67 288	91.33 345	74.73 244	97.41 279	84.43 247	81.83 397	92.89 393

FA-MVS(test-final)		89.66 196	88.91 206	91.93 195	94.57 218	80.27 266	91.36 368	94.74 292	84.87 255	89.82 196	92.61 300	74.72 245	98.47 148	83.97 253	93.53 219	97.04 184

viewdifsd2359ckpt11		89.43 206	89.05 200	90.56 267	92.89 322	77.00 375	92.81 314	94.52 301	87.03 183	89.77 197	95.79 150	74.67 246	97.51 256	88.97 172	84.98 358	97.17 169

viewmsd2359difaftdt		89.43 206	89.05 200	90.56 267	92.89 322	77.00 375	92.81 314	94.52 301	87.03 183	89.77 197	95.79 150	74.67 246	97.51 256	88.97 172	84.98 358	97.17 169

XVG-OURS-SEG-HR		89.95 187	89.45 184	91.47 225	94.00 266	81.21 224	91.87 352	96.06 175	85.78 218	88.55 222	95.73 155	74.67 246	97.27 297	88.71 178	89.64 301	95.91 247

BP-MVS1		92.48 103	92.07 107	93.72 80	94.50 224	84.39 107	95.90 89	94.30 312	90.39 42	92.67 110	95.94 135	74.46 249	98.65 129	93.14 72	97.35 105	98.13 79

v2v482		87.84 255	87.06 255	90.17 291	90.99 392	79.23 319	94.00 243	95.13 258	84.87 255	85.53 293	92.07 322	74.45 250	97.45 267	84.71 243	81.75 399	93.85 345

CLD-MVS		89.47 203	88.90 207	91.18 239	94.22 252	82.07 192	92.13 345	96.09 171	87.90 149	85.37 308	92.45 304	74.38 251	97.56 252	87.15 202	90.43 283	93.93 337
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 262	86.85 261	90.03 302	92.14 346	80.60 259	93.76 260	95.23 252	82.94 308	84.60 323	94.02 246	74.27 252	95.49 415	81.04 308	83.68 373	94.01 334

HQP_MVS		90.60 167	90.19 161	91.82 205	94.70 205	82.73 167	95.85 93	96.22 148	90.81 28	86.91 256	94.86 204	74.23 253	98.12 181	88.15 182	89.99 290	94.63 299

plane_prior6					94.52 221	82.75 164						74.23 253

v144192		87.19 291	86.35 284	89.74 319	90.64 410	78.24 341	93.92 249	95.43 236	81.93 332	85.51 295	91.05 359	74.21 255	97.45 267	82.86 270	81.56 401	93.53 363

VPA-MVSNet		89.62 197	88.96 203	91.60 216	93.86 273	82.89 162	95.46 121	97.33 33	87.91 148	88.43 225	93.31 274	74.17 256	97.40 281	87.32 200	82.86 386	94.52 307

ab-mvs		89.41 208	88.35 221	92.60 144	95.15 171	82.65 175	92.20 343	95.60 220	83.97 276	88.55 222	93.70 265	74.16 257	98.21 176	82.46 278	89.37 304	96.94 194

1314		87.51 273	86.57 276	90.34 287	92.42 340	79.74 295	92.63 321	95.35 244	78.35 397	80.14 407	91.62 339	74.05 258	97.15 306	81.05 307	93.53 219	94.12 326

test_djsdf		89.03 223	88.64 212	90.21 290	90.74 407	79.28 316	95.96 83	95.90 190	84.66 264	85.33 310	92.94 288	74.02 259	97.30 291	89.64 162	88.53 316	94.05 332

cl22		86.78 307	85.98 301	89.18 345	92.34 341	77.62 366	90.84 385	94.13 322	81.33 352	83.97 346	90.15 388	73.96 260	96.60 352	84.19 249	82.94 382	93.33 371

SD_0403		84.71 361	84.65 343	84.92 441	92.95 319	65.95 479	92.07 349	93.23 353	83.82 281	79.03 426	93.73 264	73.90 261	92.91 461	63.02 474	90.05 289	95.89 249

AdaColmap		89.89 190	89.07 198	92.37 162	97.41 72	83.03 156	94.42 200	95.92 187	82.81 311	86.34 273	94.65 217	73.89 262	99.02 74	80.69 316	95.51 153	95.05 281

HyFIR lowres test		88.09 250	86.81 263	91.93 195	96.00 123	80.63 252	90.01 410	95.79 200	73.42 458	87.68 242	92.10 319	73.86 263	97.96 218	80.75 315	91.70 262	97.19 168

HQP2-MVS												73.83 264

HQP-MVS		89.80 193	89.28 193	91.34 232	94.17 255	81.56 208	94.39 207	96.04 176	88.81 105	85.43 302	93.97 250	73.83 264	97.96 218	87.11 204	89.77 299	94.50 310

3Dnovator	86.66 5	91.73 125	90.82 146	94.44 50	94.59 214	86.37 43	97.18 17	97.02 63	89.20 89	84.31 339	96.66 91	73.74 266	99.17 58	86.74 207	97.96 84	97.79 125

EPNet_dtu		86.49 322	85.94 304	88.14 376	90.24 422	72.82 429	94.11 228	92.20 384	86.66 197	79.42 421	92.36 307	73.52 267	95.81 400	71.26 421	93.66 214	95.80 255
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 365	83.06 373	88.54 362	91.72 363	78.44 333	95.18 145	92.82 366	82.73 313	79.67 418	92.12 316	73.49 268	95.96 391	71.10 426	68.73 483	91.21 444

Effi-MVS+-dtu		88.65 233	88.35 221	89.54 333	93.33 298	76.39 387	94.47 196	94.36 310	87.70 159	85.43 302	89.56 405	73.45 269	97.26 299	85.57 225	91.28 267	94.97 283

GDP-MVS		92.04 111	91.46 126	93.75 79	94.55 220	84.69 92	95.60 118	96.56 115	87.83 154	93.07 94	95.89 139	73.44 270	98.65 129	90.22 147	96.03 141	97.91 112

baseline2		86.50 320	85.39 323	89.84 312	91.12 387	76.70 382	91.88 351	88.58 466	82.35 320	79.95 412	90.95 361	73.42 271	97.63 246	80.27 325	89.95 293	95.19 275

PEN-MVS		86.80 306	86.27 289	88.40 365	92.32 342	75.71 397	95.18 145	96.38 128	87.97 143	82.82 372	93.15 281	73.39 272	95.92 393	76.15 384	79.03 436	93.59 361

v1192		87.25 285	86.33 285	90.00 306	90.76 406	79.04 320	93.80 258	95.48 228	82.57 315	85.48 297	91.18 352	73.38 273	97.42 273	82.30 281	82.06 393	93.53 363

guyue		91.12 147	90.84 145	91.96 192	94.59 214	80.57 260	94.87 165	93.71 343	88.96 102	91.14 157	95.22 183	73.22 274	97.76 234	92.01 106	93.81 207	97.54 146

QAPM		89.51 201	88.15 228	93.59 84	94.92 184	84.58 94	96.82 34	96.70 104	78.43 396	83.41 363	96.19 115	73.18 275	99.30 49	77.11 373	96.54 128	96.89 198

tpmrst		85.35 345	84.99 333	86.43 421	90.88 401	67.88 473	88.71 434	91.43 411	80.13 367	86.08 279	88.80 419	73.05 276	96.02 387	82.48 276	83.40 379	95.40 268

PS-CasMVS		87.32 282	86.88 259	88.63 361	92.99 317	76.33 389	95.33 127	96.61 111	88.22 129	83.30 367	93.07 285	73.03 277	95.79 402	78.36 357	81.00 413	93.75 355

DTE-MVSNet		86.11 329	85.48 321	87.98 379	91.65 368	74.92 404	94.93 161	95.75 203	87.36 172	82.26 378	93.04 286	72.85 278	95.82 399	74.04 404	77.46 442	93.20 379

MVSTER		88.84 227	88.29 225	90.51 274	92.95 319	80.44 263	93.73 263	95.01 265	84.66 264	87.15 251	93.12 283	72.79 279	97.21 304	87.86 188	87.36 338	93.87 342

v1921920		86.97 299	86.06 298	89.69 324	90.53 415	78.11 344	93.80 258	95.43 236	81.90 334	85.33 310	91.05 359	72.66 280	97.41 279	82.05 289	81.80 398	93.53 363

DP-MVS		87.25 285	85.36 325	92.90 118	97.65 65	83.24 142	94.81 171	92.00 391	74.99 441	81.92 385	95.00 196	72.66 280	99.05 68	66.92 457	92.33 257	96.40 222

VortexMVS		88.42 239	88.01 231	89.63 330	93.89 272	78.82 322	93.82 256	95.47 229	86.67 196	84.53 327	91.99 325	72.62 282	96.65 339	89.02 171	84.09 367	93.41 370

v7n		86.81 305	85.76 312	89.95 307	90.72 408	79.25 318	95.07 152	95.92 187	84.45 267	82.29 377	90.86 363	72.60 283	97.53 254	79.42 347	80.52 421	93.08 387

OPM-MVS		90.12 177	89.56 182	91.82 205	93.14 304	83.90 120	94.16 223	95.74 204	88.96 102	87.86 235	95.43 172	72.48 284	97.91 224	88.10 186	90.18 288	93.65 360
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 254	86.32 286	92.59 145	96.07 119	82.92 161	95.23 137	94.92 279	75.66 433	82.89 371	95.98 132	72.48 284	99.21 56	68.43 445	95.23 165	95.64 261

pm-mvs1		86.61 314	85.54 319	89.82 313	91.44 371	80.18 269	95.28 134	94.85 284	83.84 279	81.66 386	92.62 299	72.45 286	96.48 363	79.67 335	78.06 437	92.82 396

KinetiMVS		91.82 115	91.30 131	93.39 87	94.72 202	83.36 139	95.45 122	96.37 129	90.33 44	92.17 122	96.03 129	72.32 287	98.75 118	87.94 187	96.34 133	98.07 84

usedtu_dtu_shiyan1		86.84 303	85.61 317	90.53 269	90.50 416	81.80 202	90.97 381	94.96 272	83.05 302	83.50 359	90.32 380	72.15 288	96.65 339	79.49 341	85.55 352	93.15 383

FE-MVSNET3		86.84 303	85.61 317	90.53 269	90.50 416	81.80 202	90.97 381	94.96 272	83.05 302	83.50 359	90.32 380	72.15 288	96.65 339	79.49 341	85.55 352	93.15 383

PMMVS		85.71 338	84.96 335	87.95 380	88.90 441	77.09 373	88.68 435	90.06 445	72.32 468	86.47 266	90.76 369	72.15 288	94.40 433	81.78 296	93.49 221	92.36 417

SDMVSNet		90.19 176	89.61 181	91.93 195	96.00 123	83.09 153	92.89 309	95.98 180	88.73 109	86.85 260	95.20 187	72.09 291	97.08 313	88.90 174	89.85 296	95.63 262

PatchmatchNet		85.85 334	84.70 342	89.29 342	91.76 362	75.54 398	88.49 439	91.30 413	81.63 345	85.05 315	88.70 422	71.71 292	96.24 379	74.61 401	89.05 311	96.08 240
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 293				96.12 237

patchmatchnet-post											83.76 470	71.53 294	96.48 363

v1240		86.78 307	85.85 307	89.56 332	90.45 419	77.79 357	93.61 271	95.37 242	81.65 343	85.43 302	91.15 354	71.50 295	97.43 271	81.47 302	82.05 395	93.47 367

anonymousdsp		87.84 255	87.09 254	90.12 295	89.13 438	80.54 261	94.67 182	95.55 223	82.05 327	83.82 348	92.12 316	71.47 296	97.15 306	87.15 202	87.80 333	92.67 400

Patchmatch-test		81.37 409	79.30 415	87.58 389	90.92 398	74.16 414	80.99 496	87.68 473	70.52 476	76.63 451	88.81 417	71.21 297	92.76 463	60.01 484	86.93 344	95.83 253

F-COLMAP		87.95 253	86.80 264	91.40 229	96.35 105	80.88 240	94.73 178	95.45 233	79.65 374	82.04 383	94.61 219	71.13 298	98.50 143	76.24 383	91.05 273	94.80 296

pmmvs4		85.43 342	83.86 360	90.16 292	90.02 427	82.97 160	90.27 397	92.67 370	75.93 432	80.73 398	91.74 333	71.05 299	95.73 405	78.85 354	83.46 377	91.78 428

CR-MVSNet		85.35 345	83.76 361	90.12 295	90.58 412	79.34 312	85.24 477	91.96 395	78.27 399	85.55 291	87.87 435	71.03 300	95.61 408	73.96 406	89.36 305	95.40 268

Patchmtry		82.71 385	80.93 389	88.06 377	90.05 426	76.37 388	84.74 483	91.96 395	72.28 469	81.32 392	87.87 435	71.03 300	95.50 414	68.97 441	80.15 424	92.32 419

CL-MVSNet_self_test		81.74 400	80.53 390	85.36 434	85.96 469	72.45 438	90.25 399	93.07 358	81.24 355	79.85 415	87.29 441	70.93 302	92.52 464	66.95 454	69.23 473	91.11 448

RPMNet		83.95 373	81.53 384	91.21 237	90.58 412	79.34 312	85.24 477	96.76 94	71.44 472	85.55 291	82.97 478	70.87 303	98.91 98	61.01 479	89.36 305	95.40 268

Patchmatch-RL test		81.67 401	79.96 405	86.81 415	85.42 477	71.23 450	82.17 494	87.50 475	78.47 394	77.19 446	82.50 485	70.81 304	93.48 452	82.66 275	72.89 457	95.71 260

CostFormer		85.77 337	84.94 336	88.26 372	91.16 385	72.58 437	89.47 422	91.04 420	76.26 428	86.45 269	89.97 395	70.74 305	96.86 331	82.35 280	87.07 343	95.34 272

AstraMVS		90.69 159	90.30 158	91.84 204	93.81 276	79.85 290	94.76 176	92.39 375	88.96 102	91.01 168	95.87 143	70.69 306	97.94 221	92.49 84	92.70 246	97.73 129

sam_mvs												70.60 307

xiu_mvs_v1_base_debu		90.64 164	90.05 167	92.40 158	93.97 268	84.46 101	93.32 283	95.46 230	85.17 241	92.25 118	94.03 243	70.59 308	98.57 140	90.97 128	94.67 175	94.18 322

xiu_mvs_v1_base		90.64 164	90.05 167	92.40 158	93.97 268	84.46 101	93.32 283	95.46 230	85.17 241	92.25 118	94.03 243	70.59 308	98.57 140	90.97 128	94.67 175	94.18 322

xiu_mvs_v1_base_debi		90.64 164	90.05 167	92.40 158	93.97 268	84.46 101	93.32 283	95.46 230	85.17 241	92.25 118	94.03 243	70.59 308	98.57 140	90.97 128	94.67 175	94.18 322

test_post											10.29 556	70.57 311	95.91 395

CANet_DTU		90.26 175	89.41 188	92.81 123	93.46 295	83.01 158	93.48 275	94.47 304	89.43 79	87.76 241	94.23 240	70.54 312	99.03 71	84.97 233	96.39 132	96.38 223

BH-RMVSNet		88.37 242	87.48 245	91.02 248	95.28 161	79.45 304	92.89 309	93.07 358	85.45 233	86.91 256	94.84 207	70.35 313	97.76 234	73.97 405	94.59 180	95.85 251

Fast-Effi-MVS+-dtu		87.44 276	86.72 266	89.63 330	92.04 350	77.68 365	94.03 238	93.94 326	85.81 217	82.42 376	91.32 347	70.33 314	97.06 316	80.33 324	90.23 287	94.14 325

MDTV_nov1_ep13_2view						55.91 511	87.62 456		73.32 459	84.59 324		70.33 314		74.65 399		95.50 265

ACMM	84.12 9	89.14 216	88.48 220	91.12 240	94.65 209	81.22 223	95.31 128	96.12 168	85.31 238	85.92 282	94.34 231	70.19 316	98.06 197	85.65 223	88.86 313	94.08 330
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RRT-MVS		90.85 153	90.70 150	91.30 234	94.25 250	76.83 379	94.85 168	96.13 167	89.04 96	90.23 184	94.88 202	70.15 317	98.72 122	91.86 114	94.88 170	98.34 49

LuminaMVS		90.55 169	89.81 174	92.77 127	92.78 328	84.21 111	94.09 232	94.17 319	85.82 216	91.54 145	94.14 242	69.93 318	97.92 223	91.62 118	94.21 194	96.18 233

ET-MVSNet_ETH3D		87.51 273	85.91 305	92.32 168	93.70 287	83.93 119	92.33 335	90.94 425	84.16 271	72.09 477	92.52 302	69.90 319	95.85 397	89.20 168	88.36 322	97.17 169

LPG-MVS_test		89.45 204	88.90 207	91.12 240	94.47 228	81.49 212	95.30 130	96.14 164	86.73 194	85.45 299	95.16 189	69.89 320	98.10 183	87.70 191	89.23 308	93.77 353

LGP-MVS_train				91.12 240	94.47 228	81.49 212		96.14 164	86.73 194	85.45 299	95.16 189	69.89 320	98.10 183	87.70 191	89.23 308	93.77 353

CHOSEN 280x420		85.15 350	83.99 358	88.65 360	92.47 337	78.40 335	79.68 503	92.76 367	74.90 443	81.41 390	89.59 403	69.85 322	95.51 412	79.92 331	95.29 162	92.03 424

LTVRE_ROB	82.13 13	86.26 327	84.90 337	90.34 287	94.44 232	81.50 210	92.31 338	94.89 280	83.03 304	79.63 419	92.67 297	69.69 323	97.79 232	71.20 422	86.26 347	91.72 429
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	88.74 231	87.29 250	93.08 105	92.70 332	85.39 79	96.57 40	96.43 123	78.74 390	80.85 396	96.07 125	69.64 324	99.01 76	78.01 363	96.65 126	94.83 294

MonoMVSNet		86.89 302	86.55 277	87.92 382	89.46 436	73.75 416	94.12 226	93.10 356	87.82 155	85.10 313	90.76 369	69.59 325	94.94 427	86.47 211	82.50 388	95.07 279

MDTV_nov1_ep13			83.56 364		91.69 366	69.93 463	87.75 453	91.54 406	78.60 392	84.86 318	88.90 415	69.54 326	96.03 386	70.25 432	88.93 312

dtuonly		84.33 367	84.48 349	83.87 451	86.63 463	63.54 491	86.79 463	91.48 409	78.02 404	83.20 368	93.56 267	69.53 327	94.11 440	79.08 350	92.02 261	93.97 336

AUN-MVS		87.78 258	86.54 278	91.48 224	94.82 192	81.05 231	93.91 251	93.93 327	83.00 305	86.93 254	93.53 268	69.50 328	97.67 240	86.14 215	77.12 445	95.73 259

PatchT		82.68 386	81.27 386	86.89 413	90.09 425	70.94 456	84.06 486	90.15 442	74.91 442	85.63 290	83.57 473	69.37 329	94.87 428	65.19 463	88.50 318	94.84 293

VPNet		88.20 247	87.47 246	90.39 283	93.56 292	79.46 303	94.04 237	95.54 225	88.67 112	86.96 253	94.58 223	69.33 330	97.15 306	84.05 252	80.53 420	94.56 305

ACMP	84.23 8	89.01 225	88.35 221	90.99 251	94.73 200	81.27 220	95.07 152	95.89 192	86.48 199	83.67 353	94.30 234	69.33 330	97.99 211	87.10 206	88.55 315	93.72 358
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 448				9.81 557	69.31 332	95.53 410	76.65 376

tpmvs		83.35 381	82.07 380	87.20 405	91.07 389	71.00 455	88.31 442	91.70 399	78.91 382	80.49 403	87.18 444	69.30 333	97.08 313	68.12 449	83.56 375	93.51 366

mvsmamba		90.33 172	89.69 178	92.25 179	95.17 168	81.64 207	95.27 135	93.36 350	84.88 254	89.51 202	94.27 238	69.29 334	97.42 273	89.34 165	96.12 139	97.68 132

thres200		87.21 289	86.24 290	90.12 295	95.36 157	78.53 330	93.26 290	92.10 387	86.42 202	88.00 234	91.11 356	69.24 335	98.00 210	69.58 439	91.04 275	93.83 347

tfpn200view9		87.58 270	86.64 271	90.41 282	95.99 126	78.64 326	94.58 187	91.98 393	86.94 188	88.09 229	91.77 331	69.18 336	98.10 183	70.13 435	91.10 268	94.48 313

thres400		87.62 267	86.64 271	90.57 265	95.99 126	78.64 326	94.58 187	91.98 393	86.94 188	88.09 229	91.77 331	69.18 336	98.10 183	70.13 435	91.10 268	94.96 286

WB-MVSnew		83.77 376	83.28 367	85.26 437	91.48 370	71.03 453	91.89 350	87.98 469	78.91 382	84.78 319	90.22 384	69.11 338	94.02 442	64.70 467	90.44 282	90.71 452

tfpnnormal		84.72 360	83.23 369	89.20 344	92.79 327	80.05 278	94.48 193	95.81 198	82.38 318	81.08 394	91.21 349	69.01 339	96.95 325	61.69 477	80.59 418	90.58 457

thres100view900		87.63 265	86.71 267	90.38 285	96.12 112	78.55 329	95.03 156	91.58 404	87.15 177	88.06 232	92.29 310	68.91 340	98.10 183	70.13 435	91.10 268	94.48 313

thres600view7		87.65 262	86.67 270	90.59 264	96.08 118	78.72 323	94.88 164	91.58 404	87.06 182	88.08 231	92.30 309	68.91 340	98.10 183	70.05 438	91.10 268	94.96 286

PatchMatch-RL		86.77 310	85.54 319	90.47 280	95.88 131	82.71 169	90.54 392	92.31 379	79.82 372	84.32 337	91.57 343	68.77 342	96.39 371	73.16 411	93.48 223	92.32 419

XVG-OURS		89.40 210	88.70 211	91.52 220	94.06 260	81.46 215	91.27 373	96.07 173	86.14 211	88.89 217	95.77 153	68.73 343	97.26 299	87.39 198	89.96 292	95.83 253

TR-MVS		86.78 307	85.76 312	89.82 313	94.37 236	78.41 334	92.47 326	92.83 364	81.11 358	86.36 271	92.40 305	68.73 343	97.48 262	73.75 409	89.85 296	93.57 362

tpm		84.73 359	84.02 357	86.87 414	90.33 420	68.90 467	89.06 429	89.94 449	80.85 360	85.75 286	89.86 398	68.54 345	95.97 390	77.76 365	84.05 368	95.75 256

FMVSNet3		87.40 278	86.11 295	91.30 234	93.79 279	83.64 129	94.20 222	94.81 288	83.89 278	84.37 332	91.87 330	68.45 346	96.56 357	78.23 360	85.36 354	93.70 359

MVP-Stereo		85.97 331	84.86 339	89.32 341	90.92 398	82.19 188	92.11 346	94.19 317	78.76 389	78.77 434	91.63 338	68.38 347	96.56 357	75.01 395	93.95 200	89.20 472
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 394	80.27 396	87.01 408	91.09 388	71.02 454	87.38 459	91.53 407	66.25 490	80.17 405	86.35 456	68.22 348	96.15 383	69.16 440	82.29 391	93.86 344

dmvs_testset		74.57 452	75.81 449	70.86 483	87.72 458	40.47 525	87.05 462	77.90 507	82.75 312	71.15 483	85.47 463	67.98 349	84.12 506	45.26 507	76.98 447	88.00 484

sd_testset		88.59 236	87.85 238	90.83 258	96.00 123	80.42 264	92.35 332	94.71 293	88.73 109	86.85 260	95.20 187	67.31 350	96.43 369	79.64 336	89.85 296	95.63 262

tpm2		84.08 370	82.94 374	87.48 393	91.39 375	71.27 449	89.23 426	90.37 437	71.95 470	84.64 322	89.33 407	67.30 351	96.55 359	75.17 392	87.09 342	94.63 299

test-LLR		85.87 333	85.41 322	87.25 401	90.95 394	71.67 446	89.55 418	89.88 452	83.41 292	84.54 325	87.95 432	67.25 352	95.11 423	81.82 294	93.37 227	94.97 283

test0.0.03 1		82.41 391	81.69 382	84.59 444	88.23 450	72.89 428	90.24 401	87.83 471	83.41 292	79.86 414	89.78 400	67.25 352	88.99 493	65.18 464	83.42 378	91.90 427

CVMVSNet		84.69 362	84.79 341	84.37 446	91.84 358	64.92 486	93.70 267	91.47 410	66.19 491	86.16 278	95.28 180	67.18 354	93.33 454	80.89 313	90.42 284	94.88 292

thisisatest0515		87.33 281	85.99 300	91.37 231	93.49 293	79.55 300	90.63 389	89.56 459	80.17 366	87.56 245	90.86 363	67.07 355	98.28 171	81.50 301	93.02 238	96.29 227

tttt0517		88.61 234	87.78 239	91.11 243	94.96 181	77.81 355	95.35 126	89.69 454	85.09 249	88.05 233	94.59 222	66.93 356	98.48 145	83.27 264	92.13 259	97.03 185

our_test_3		81.93 396	80.46 394	86.33 423	88.46 446	73.48 421	88.46 440	91.11 416	76.46 422	76.69 450	88.25 428	66.89 357	94.36 435	68.75 442	79.08 435	91.14 446

thisisatest0530		88.67 232	87.61 242	91.86 201	94.87 188	80.07 276	94.63 185	89.90 451	84.00 275	88.46 224	93.78 260	66.88 358	98.46 149	83.30 263	92.65 247	97.06 182

IterMVS-SCA-FT		85.45 341	84.53 348	88.18 375	91.71 364	76.87 378	90.19 405	92.65 371	85.40 236	81.44 389	90.54 374	66.79 359	95.00 426	81.04 308	81.05 409	92.66 401

SCA		86.32 326	85.18 330	89.73 321	92.15 345	76.60 383	91.12 377	91.69 400	83.53 289	85.50 296	88.81 417	66.79 359	96.48 363	76.65 376	90.35 285	96.12 237

D2MVS		85.90 332	85.09 332	88.35 367	90.79 403	77.42 368	91.83 354	95.70 210	80.77 361	80.08 409	90.02 393	66.74 361	96.37 372	81.88 293	87.97 328	91.26 443

IterMVS		84.88 356	83.98 359	87.60 388	91.44 371	76.03 391	90.18 406	92.41 374	83.24 298	81.06 395	90.42 379	66.60 362	94.28 438	79.46 343	80.98 414	92.48 410
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 283	85.98 301	91.08 244	94.01 263	83.10 150	95.14 148	94.94 274	83.57 286	84.37 332	91.64 335	66.59 363	96.34 375	78.23 360	85.36 354	93.79 348

test1		87.26 283	85.98 301	91.08 244	94.01 263	83.10 150	95.14 148	94.94 274	83.57 286	84.37 332	91.64 335	66.59 363	96.34 375	78.23 360	85.36 354	93.79 348

FMVSNet2		87.19 291	85.82 308	91.30 234	94.01 263	83.67 127	94.79 173	94.94 274	83.57 286	83.88 347	92.05 323	66.59 363	96.51 361	77.56 368	85.01 357	93.73 357

IMVS_0404		87.60 269	86.84 262	89.89 309	93.72 281	77.75 360	88.56 437	95.34 245	85.53 229	79.98 411	94.49 225	66.54 366	94.64 429	84.75 238	92.65 247	97.28 157

EPMVS		83.90 375	82.70 379	87.51 390	90.23 423	72.67 432	88.62 436	81.96 495	81.37 351	85.01 316	88.34 426	66.31 367	94.45 430	75.30 391	87.12 341	95.43 267

Syy-MVS		80.07 425	79.78 407	80.94 465	91.92 354	59.93 501	89.75 416	87.40 476	81.72 341	78.82 431	87.20 442	66.29 368	91.29 478	47.06 506	87.84 331	91.60 432

ppachtmachnet_test		81.84 397	80.07 401	87.15 406	88.46 446	74.43 411	89.04 430	92.16 386	75.33 437	77.75 442	88.99 413	66.20 369	95.37 418	65.12 465	77.60 440	91.65 430

MDA-MVSNet_test_wron		79.21 436	77.19 438	85.29 435	88.22 451	72.77 430	85.87 471	90.06 445	74.34 447	62.62 497	87.56 438	66.14 370	91.99 471	66.90 458	73.01 455	91.10 449

YYNet1		79.22 435	77.20 437	85.28 436	88.20 452	72.66 433	85.87 471	90.05 447	74.33 448	62.70 495	87.61 437	66.09 371	92.03 468	66.94 455	72.97 456	91.15 445

JIA-IIPM		81.04 412	78.98 424	87.25 401	88.64 442	73.48 421	81.75 495	89.61 458	73.19 460	82.05 382	73.71 505	66.07 372	95.87 396	71.18 424	84.60 362	92.41 414

MSDG		84.86 357	83.09 371	90.14 294	93.80 277	80.05 278	89.18 427	93.09 357	78.89 384	78.19 436	91.91 328	65.86 373	97.27 297	68.47 444	88.45 319	93.11 385

FE-MVS		87.40 278	86.02 299	91.57 218	94.56 219	79.69 298	90.27 397	93.72 342	80.57 362	88.80 218	91.62 339	65.32 374	98.59 139	74.97 396	94.33 190	96.44 221

jajsoiax		88.24 246	87.50 244	90.48 277	90.89 400	80.14 271	95.31 128	95.65 217	84.97 252	84.24 340	94.02 246	65.31 375	97.42 273	88.56 179	88.52 317	93.89 338

cascas		86.43 324	84.98 334	90.80 261	92.10 349	80.92 238	90.24 401	95.91 189	73.10 461	83.57 357	88.39 425	65.15 376	97.46 266	84.90 236	91.43 265	94.03 333

ADS-MVSNet2		81.66 402	79.71 410	87.50 391	91.35 377	74.19 413	83.33 489	88.48 467	72.90 463	82.24 379	85.77 461	64.98 377	93.20 457	64.57 468	83.74 371	95.12 277

ADS-MVSNet		81.56 404	79.78 407	86.90 412	91.35 377	71.82 442	83.33 489	89.16 465	72.90 463	82.24 379	85.77 461	64.98 377	93.76 448	64.57 468	83.74 371	95.12 277

blended_shiyan6		82.78 383	80.48 393	89.67 329	85.53 474	79.76 293	91.37 367	93.82 334	77.14 412	79.30 424	83.73 471	64.96 379	96.63 342	79.68 334	68.75 479	92.63 402

blended_shiyan8		82.79 382	80.49 392	89.69 324	85.50 476	79.83 292	91.38 366	93.82 334	77.14 412	79.39 422	83.73 471	64.95 380	96.63 342	79.75 332	68.77 478	92.62 404

Elysia		90.12 177	89.10 196	93.18 97	93.16 302	84.05 116	95.22 139	96.27 138	85.16 244	90.59 174	94.68 212	64.64 381	98.37 160	86.38 213	95.77 146	97.12 178

StellarMVS		90.12 177	89.10 196	93.18 97	93.16 302	84.05 116	95.22 139	96.27 138	85.16 244	90.59 174	94.68 212	64.64 381	98.37 160	86.38 213	95.77 146	97.12 178

pmmvs5		84.21 368	82.84 378	88.34 369	88.95 440	76.94 377	92.41 327	91.91 397	75.63 434	80.28 404	91.18 352	64.59 383	95.57 409	77.09 374	83.47 376	92.53 409

PVSNet	78.82 18	85.55 339	84.65 343	88.23 374	94.72 202	71.93 440	87.12 461	92.75 368	78.80 388	84.95 317	90.53 375	64.43 384	96.71 336	74.74 398	93.86 204	96.06 243

dmvs_re		84.20 369	83.22 370	87.14 407	91.83 360	77.81 355	90.04 409	90.19 441	84.70 263	81.49 387	89.17 409	64.37 385	91.13 480	71.58 419	85.65 351	92.46 412

wanda-best-256-512		82.44 389	80.07 401	89.53 334	85.12 480	79.44 305	90.49 393	93.75 340	76.97 418	79.00 427	82.72 481	64.29 386	96.61 348	79.56 339	68.75 479	92.55 405

FE-blended-shiyan7		82.44 389	80.07 401	89.53 334	85.12 480	79.44 305	90.49 393	93.75 340	76.97 418	79.00 427	82.72 481	64.29 386	96.61 348	79.56 339	68.75 479	92.55 405

usedtu_blend_shiyan5		82.39 392	79.93 406	89.75 318	85.12 480	80.08 274	92.36 330	93.26 351	74.29 449	79.00 427	82.72 481	64.29 386	96.60 352	79.60 337	68.75 479	92.55 405

UGNet		89.95 187	88.95 204	92.95 116	94.51 222	83.31 140	95.70 106	95.23 252	89.37 81	87.58 244	93.94 251	64.00 389	98.78 115	83.92 254	96.31 134	96.74 209
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		67.92 462	67.49 463	69.21 488	81.09 497	41.17 524	88.03 447	78.00 506	73.50 457	62.63 496	83.11 477	63.94 390	86.52 497	25.66 526	51.45 506	79.94 499

RPSCF		85.07 351	84.27 350	87.48 393	92.91 321	70.62 458	91.69 359	92.46 373	76.20 430	82.67 374	95.22 183	63.94 390	97.29 294	77.51 369	85.80 349	94.53 306

mvs_tets		88.06 252	87.28 251	90.38 285	90.94 396	79.88 287	95.22 139	95.66 215	85.10 248	84.21 341	93.94 251	63.53 392	97.40 281	88.50 180	88.40 321	93.87 342

SSC-MVS		67.06 463	66.56 465	68.56 490	80.54 498	40.06 526	87.77 452	77.37 509	72.38 467	61.75 498	82.66 484	63.37 393	86.45 498	24.48 528	48.69 509	79.16 502

test1111		89.10 217	88.64 212	90.48 277	95.53 152	74.97 403	96.08 69	84.89 487	88.13 133	90.16 191	96.65 92	63.29 394	98.10 183	86.14 215	96.90 117	98.39 46

gbinet_0.2-2-1-0.02		82.59 387	80.19 399	89.77 317	85.23 479	80.05 278	91.59 362	93.52 346	77.60 406	79.78 416	82.87 480	63.26 395	96.45 367	78.93 352	68.97 475	92.81 397

Anonymous20231211		86.59 316	85.13 331	90.98 253	96.52 99	81.50 210	96.14 64	96.16 162	73.78 454	83.65 354	92.15 314	63.26 395	97.37 287	82.82 272	81.74 400	94.06 331

ECVR-MVS		89.09 219	88.53 215	90.77 262	95.62 145	75.89 393	96.16 60	84.22 489	87.89 151	90.20 185	96.65 92	63.19 397	98.10 183	85.90 220	96.94 114	98.33 51

dtuonlycased		79.67 430	79.05 423	81.54 463	88.34 449	68.44 469	88.96 432	90.65 434	78.48 393	73.21 474	85.88 460	63.18 398	91.00 482	70.40 430	72.32 458	85.19 489

SSC-MVS3.2		84.60 363	84.19 351	85.85 429	92.74 330	68.07 470	88.15 445	93.81 337	87.42 169	83.76 350	91.07 358	62.91 399	95.73 405	74.56 402	83.24 380	93.75 355

nomal-1		86.20 328	84.90 337	90.11 299	92.72 331	80.88 240	89.79 413	91.03 421	82.96 307	83.49 361	88.82 416	62.88 400	94.38 434	81.35 303	91.05 273	95.07 279

dp		81.47 408	80.23 397	85.17 438	89.92 429	65.49 483	86.74 465	90.10 444	76.30 427	81.10 393	87.12 445	62.81 401	95.92 393	68.13 448	79.88 427	94.09 329

LFMVS		90.08 180	89.13 195	92.95 116	96.71 88	82.32 186	96.08 69	89.91 450	86.79 191	92.15 124	96.81 85	62.60 402	98.34 165	87.18 201	93.90 203	98.19 73

Anonymous20231206		81.03 413	79.77 409	84.82 442	87.85 457	70.26 461	91.42 365	92.08 388	73.67 455	77.75 442	89.25 408	62.43 403	93.08 458	61.50 478	82.00 396	91.12 447

VDD-MVS		90.74 156	89.92 172	93.20 95	96.27 106	83.02 157	95.73 104	93.86 331	88.42 121	92.53 113	96.84 82	62.09 404	98.64 132	90.95 132	92.62 252	97.93 109

MS-PatchMatch		85.05 352	84.16 353	87.73 385	91.42 374	78.51 331	91.25 374	93.53 345	77.50 407	80.15 406	91.58 341	61.99 405	95.51 412	75.69 387	94.35 188	89.16 473

OurMVSNet-221017-0		85.35 345	84.64 345	87.49 392	90.77 405	72.59 436	94.01 241	94.40 308	84.72 261	79.62 420	93.17 280	61.91 406	96.72 334	81.99 290	81.16 405	93.16 381

WBMVS		84.97 355	84.18 352	87.34 396	94.14 259	71.62 448	90.20 404	92.35 376	81.61 346	84.06 342	90.76 369	61.82 407	96.52 360	78.93 352	83.81 369	93.89 338

test_vis1_n_1920		89.39 211	89.84 173	88.04 378	92.97 318	72.64 434	94.71 180	96.03 178	86.18 209	91.94 131	96.56 100	61.63 408	95.74 404	93.42 67	95.11 166	95.74 257

test20.03		79.95 427	79.08 421	82.55 457	85.79 471	67.74 475	91.09 378	91.08 417	81.23 356	74.48 467	89.96 396	61.63 408	90.15 485	60.08 482	76.38 448	89.76 464

mmtdpeth		85.04 354	84.15 354	87.72 386	93.11 306	75.74 396	94.37 211	92.83 364	84.98 251	89.31 207	86.41 454	61.61 410	97.14 309	92.63 83	62.11 495	90.29 458

DSMNet-mixed		76.94 446	76.29 444	78.89 470	83.10 491	56.11 510	87.78 451	79.77 499	60.65 499	75.64 459	88.71 421	61.56 411	88.34 494	60.07 483	89.29 307	92.21 422

Anonymous20240529		88.09 250	86.59 275	92.58 146	96.53 98	81.92 198	95.99 79	95.84 197	74.11 451	89.06 212	95.21 186	61.44 412	98.81 111	83.67 261	87.47 335	97.01 188

UBG		85.51 340	84.57 347	88.35 367	94.21 253	71.78 444	90.07 408	89.66 456	82.28 322	85.91 283	89.01 412	61.30 413	97.06 316	76.58 379	92.06 260	96.22 230

IB-MVS	80.51 15	85.24 349	83.26 368	91.19 238	92.13 347	79.86 288	91.75 356	91.29 414	83.28 297	80.66 400	88.49 424	61.28 414	98.46 149	80.99 311	79.46 432	95.25 274
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		86.61 314	85.27 328	90.66 263	91.33 379	78.71 325	90.40 396	93.81 337	85.34 237	85.12 312	89.57 404	61.25 415	97.11 311	80.99 311	89.59 302	96.15 234

N_pmnet		68.89 461	68.44 461	70.23 485	89.07 439	28.79 536	88.06 446	19.50 537	69.47 479	71.86 480	84.93 465	61.24 416	91.75 474	54.70 494	77.15 444	90.15 461

EU-MVSNet		81.32 410	80.95 388	82.42 460	88.50 445	63.67 490	93.32 283	91.33 412	64.02 495	80.57 402	92.83 291	61.21 417	92.27 467	76.34 381	80.38 423	91.32 441

testing91		87.11 295	86.18 291	89.92 308	94.43 233	75.38 402	91.53 363	92.27 381	86.48 199	86.50 265	90.24 383	61.19 418	97.53 254	82.10 286	90.88 278	96.84 205

FBQ-MVS		87.19 291	85.74 314	91.52 220	94.74 198	80.62 254	93.91 251	92.20 384	84.27 270	87.61 243	88.77 420	61.17 419	97.29 294	78.01 363	91.03 276	96.64 214

test_cas_vis1_n_1920		88.83 230	88.85 210	88.78 354	91.15 386	76.72 381	93.85 255	94.93 278	83.23 299	92.81 101	96.00 130	61.17 419	94.45 430	91.67 117	94.84 171	95.17 276

VDDNet		89.56 200	88.49 219	92.76 130	95.07 173	82.09 191	96.30 47	93.19 355	81.05 359	91.88 133	96.86 81	61.16 421	98.33 167	88.43 181	92.49 256	97.84 120

PVSNet_0	73.20 20	77.22 445	74.83 451	84.37 446	90.70 409	71.10 452	83.09 491	89.67 455	72.81 465	73.93 469	83.13 475	60.79 422	93.70 450	68.54 443	50.84 507	88.30 483

SixPastTwentyTwo		83.91 374	82.90 376	86.92 411	90.99 392	70.67 457	93.48 275	91.99 392	85.54 227	77.62 444	92.11 318	60.59 423	96.87 330	76.05 385	77.75 439	93.20 379

gg-mvs-nofinetune		81.77 399	79.37 413	88.99 351	90.85 402	77.73 364	86.29 468	79.63 500	74.88 444	83.19 369	69.05 512	60.34 424	96.11 384	75.46 389	94.64 179	93.11 385

MDA-MVSNet-bldmvs		78.85 438	76.31 443	86.46 419	89.76 431	73.88 415	88.79 433	90.42 436	79.16 380	59.18 500	88.33 427	60.20 425	94.04 441	62.00 476	68.96 476	91.48 438

pmmvs6		83.42 379	81.60 383	88.87 353	88.01 454	77.87 353	94.96 159	94.24 316	74.67 445	78.80 433	91.09 357	60.17 426	96.49 362	77.06 375	75.40 452	92.23 421

ACMH	80.38 17	85.36 344	83.68 362	90.39 283	94.45 231	80.63 252	94.73 178	94.85 284	82.09 325	77.24 445	92.65 298	60.01 427	97.58 250	72.25 416	84.87 360	92.96 390
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 381	89.73 433	77.91 349	87.80 449	78.23 505		80.58 401	83.86 469	59.88 428	95.33 419	71.20 422	92.22 258	90.60 456

UniMVSNet_ETH3D		87.53 272	86.37 283	91.00 250	92.44 339	78.96 321	94.74 177	95.61 219	84.07 274	85.36 309	94.52 224	59.78 429	97.34 288	82.93 268	87.88 329	96.71 210

myMVS_eth3d28		85.80 336	85.26 329	87.42 395	94.73 200	69.92 464	90.60 390	90.95 424	87.21 176	86.06 280	90.04 392	59.47 430	96.02 387	74.89 397	93.35 229	96.33 224

pmmvs-eth3d		80.97 415	78.72 426	87.74 384	84.99 483	79.97 285	90.11 407	91.65 402	75.36 436	73.51 471	86.03 457	59.45 431	93.96 446	75.17 392	72.21 459	89.29 471

testing99		86.72 311	85.73 316	89.69 324	94.23 251	74.91 405	91.35 369	90.97 423	86.14 211	86.36 271	90.22 384	59.41 432	97.48 262	82.24 283	90.66 280	96.69 212

test_0402		81.30 411	79.17 419	87.67 387	93.19 301	78.17 342	92.98 305	91.71 398	75.25 438	76.02 457	90.31 382	59.23 433	96.37 372	50.22 501	83.63 374	88.47 482

KD-MVS_self_test		80.20 423	79.24 416	83.07 454	85.64 473	65.29 484	91.01 380	93.93 327	78.71 391	76.32 452	86.40 455	59.20 434	92.93 460	72.59 414	69.35 472	91.00 451

testing3-2		86.72 311	86.71 267	86.74 417	96.11 115	65.92 480	93.39 280	89.65 457	89.46 77	87.84 237	92.79 295	59.17 435	97.60 248	81.31 304	90.72 279	96.70 211

UWE-MVS-28		78.98 437	78.38 429	80.80 466	88.18 453	60.66 500	90.65 388	78.51 502	78.84 386	77.93 440	90.93 362	59.08 436	89.02 492	50.96 499	90.33 286	92.72 399

FMVSNet1		85.85 334	84.11 355	91.08 244	92.81 326	83.10 150	95.14 148	94.94 274	81.64 344	82.68 373	91.64 335	59.01 437	96.34 375	75.37 390	83.78 370	93.79 348

testing11		86.44 323	85.35 326	89.69 324	94.29 247	75.40 401	91.30 370	90.53 435	84.76 259	85.06 314	90.13 389	58.95 438	97.45 267	82.08 287	91.09 272	96.21 232

COLMAP_ROB	80.39 16	83.96 372	82.04 381	89.74 319	95.28 161	79.75 294	94.25 218	92.28 380	75.17 439	78.02 439	93.77 261	58.60 439	97.84 229	65.06 466	85.92 348	91.63 431
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	85.05 352	83.46 365	89.82 313	94.66 208	79.37 309	94.44 198	94.12 323	82.19 324	78.04 438	92.82 292	58.23 440	97.54 253	73.77 408	82.90 385	92.54 408

CMPMVS	59.16 21	80.52 419	79.20 418	84.48 445	83.98 486	67.63 476	89.95 412	93.84 333	64.79 494	66.81 491	91.14 355	57.93 441	95.17 421	76.25 382	88.10 324	90.65 453
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
reproduce_monomvs		86.37 325	85.87 306	87.87 383	93.66 289	73.71 417	93.44 278	95.02 264	88.61 115	82.64 375	91.94 327	57.88 442	96.68 337	89.96 152	79.71 430	93.22 377

FE-MVSNET2		81.82 398	79.99 404	87.34 396	84.74 484	77.36 370	92.72 318	94.55 299	82.09 325	73.79 470	86.46 451	57.80 443	94.45 430	74.65 399	73.10 454	90.20 459

tt0805		86.92 300	85.74 314	90.48 277	92.22 343	79.98 284	95.63 114	94.88 282	83.83 280	84.74 321	92.80 294	57.61 444	97.67 240	85.48 227	84.42 363	93.79 348

ITE_SJBPF				88.24 373	91.88 357	77.05 374		92.92 361	85.54 227	80.13 408	93.30 275	57.29 445	96.20 380	72.46 415	84.71 361	91.49 437

UWE-MVS		83.69 378	83.09 371	85.48 432	93.06 311	65.27 485	90.92 383	86.14 479	79.90 370	86.26 275	90.72 372	57.17 446	95.81 400	71.03 427	92.62 252	95.35 271

TESTMET0.1,1		83.74 377	82.85 377	86.42 422	89.96 428	71.21 451	89.55 418	87.88 470	77.41 408	83.37 364	87.31 440	56.71 447	93.65 451	80.62 318	92.85 244	94.40 316

UnsupCasMVSNet_eth		80.07 425	78.27 430	85.46 433	85.24 478	72.63 435	88.45 441	94.87 283	82.99 306	71.64 481	88.07 431	56.34 448	91.75 474	73.48 410	63.36 493	92.01 425

test_fmvs1		87.34 280	87.56 243	86.68 418	90.59 411	71.80 443	94.01 241	94.04 325	78.30 398	91.97 128	95.22 183	56.28 449	93.71 449	92.89 76	94.71 174	94.52 307

K. test v3		81.59 403	80.15 400	85.91 428	89.89 430	69.42 466	92.57 323	87.71 472	85.56 226	73.44 472	89.71 402	55.58 450	95.52 411	77.17 372	69.76 471	92.78 398

test-mter		84.54 364	83.64 363	87.25 401	90.95 394	71.67 446	89.55 418	89.88 452	79.17 379	84.54 325	87.95 432	55.56 451	95.11 423	81.82 294	93.37 227	94.97 283

FE-MVSNET		78.19 441	76.03 446	84.69 443	83.70 488	73.31 423	90.58 391	90.00 448	77.11 416	71.91 479	85.47 463	55.53 452	91.94 473	59.69 485	70.24 468	88.83 477

lessismore_v0				86.04 424	88.46 446	68.78 468		80.59 498		73.01 475	90.11 390	55.39 453	96.43 369	75.06 394	65.06 490	92.90 392

ETVMVS		84.43 365	82.92 375	88.97 352	94.37 236	74.67 406	91.23 375	88.35 468	83.37 294	86.06 280	89.04 411	55.38 454	95.67 407	67.12 453	91.34 266	96.58 217

MVS-HIRNet		73.70 453	72.20 455	78.18 474	91.81 361	56.42 509	82.94 492	82.58 493	55.24 502	68.88 486	66.48 514	55.32 455	95.13 422	58.12 489	88.42 320	83.01 493

test2506		87.21 289	86.28 288	90.02 304	95.62 145	73.64 419	96.25 55	71.38 514	87.89 151	90.45 177	96.65 92	55.29 456	98.09 191	86.03 219	96.94 114	98.33 51

mvs5depth		80.98 414	79.15 420	86.45 420	84.57 485	73.29 424	87.79 450	91.67 401	80.52 363	82.20 381	89.72 401	55.14 457	95.93 392	73.93 407	66.83 486	90.12 462

0.4-1-1-0.2		80.84 417	77.77 431	90.06 300	86.18 468	79.35 310	86.75 464	89.54 460	76.23 429	78.59 435	75.46 500	55.03 458	96.99 322	80.11 328	72.05 462	93.85 345

0.4-1-1-0.1		81.55 405	78.59 428	90.42 281	87.55 459	79.90 286	88.56 437	89.19 464	77.01 417	79.72 417	77.71 494	54.84 459	97.11 311	80.50 321	72.20 460	94.26 321

blend_shiyan4		81.94 395	79.35 414	89.70 322	85.52 475	80.08 274	91.29 371	93.82 334	77.12 415	79.31 423	82.94 479	54.81 460	96.60 352	79.60 337	69.78 470	92.41 414

new-patchmatchnet		76.41 448	75.17 450	80.13 467	82.65 493	59.61 502	87.66 455	91.08 417	78.23 401	69.85 485	83.22 474	54.76 461	91.63 477	64.14 470	64.89 491	89.16 473

Anonymous202405211		87.68 260	86.13 293	92.31 169	96.66 90	80.74 249	94.87 165	91.49 408	80.47 364	89.46 205	95.44 170	54.72 462	98.23 173	82.19 284	89.89 294	97.97 98

XVG-ACMP-BASELINE		86.00 330	84.84 340	89.45 339	91.20 381	78.00 346	91.70 358	95.55 223	85.05 250	82.97 370	92.25 312	54.49 463	97.48 262	82.93 268	87.45 337	92.89 393

USDC		82.76 384	81.26 387	87.26 400	91.17 383	74.55 408	89.27 424	93.39 349	78.26 400	75.30 461	92.08 320	54.43 464	96.63 342	71.64 418	85.79 350	90.61 454

AllTest		83.42 379	81.39 385	89.52 336	95.01 175	77.79 357	93.12 294	90.89 427	77.41 408	76.12 454	93.34 271	54.08 465	97.51 256	68.31 446	84.27 365	93.26 373

TestCases				89.52 336	95.01 175	77.79 357		90.89 427	77.41 408	76.12 454	93.34 271	54.08 465	97.51 256	68.31 446	84.27 365	93.26 373

KD-MVS_2432*1600		78.50 439	76.02 447	85.93 426	86.22 466	74.47 409	84.80 481	92.33 377	79.29 377	76.98 447	85.92 458	53.81 467	93.97 444	67.39 451	57.42 500	89.36 467

miper_refine_blended		78.50 439	76.02 447	85.93 426	86.22 466	74.47 409	84.80 481	92.33 377	79.29 377	76.98 447	85.92 458	53.81 467	93.97 444	67.39 451	57.42 500	89.36 467

MIMVSNet		82.59 387	80.53 390	88.76 355	91.51 369	78.32 338	86.57 467	90.13 443	79.32 376	80.70 399	88.69 423	52.98 469	93.07 459	66.03 461	88.86 313	94.90 291

testing222		84.84 358	83.32 366	89.43 340	94.15 258	75.94 392	91.09 378	89.41 463	84.90 253	85.78 285	89.44 406	52.70 470	96.28 378	70.80 429	91.57 264	96.07 241

0.3-1-1-0.015		80.75 418	77.58 433	90.25 289	86.55 464	79.72 296	87.46 458	89.48 462	76.43 424	77.93 440	75.94 497	52.31 471	97.05 318	80.25 326	71.85 464	93.99 335

FMVSNet5		81.52 407	79.60 411	87.27 399	91.17 383	77.95 347	91.49 364	92.26 382	76.87 420	76.16 453	87.91 434	51.67 472	92.34 466	67.74 450	81.16 405	91.52 435

testgi		80.94 416	80.20 398	83.18 453	87.96 455	66.29 478	91.28 372	90.70 433	83.70 283	78.12 437	92.84 290	51.37 473	90.82 483	63.34 471	82.46 389	92.43 413

test_fmvs1_n		87.03 298	87.04 257	86.97 409	89.74 432	71.86 441	94.55 189	94.43 305	78.47 394	91.95 130	95.50 168	51.16 474	93.81 447	93.02 75	94.56 181	95.26 273

Anonymous20240521		80.44 421	79.21 417	84.11 449	85.75 472	67.89 472	92.86 311	93.23 353	75.61 435	75.59 460	87.47 439	50.03 475	94.33 436	71.14 425	81.21 404	90.12 462

UnsupCasMVSNet_bld		76.23 449	73.27 453	85.09 439	83.79 487	72.92 427	85.65 474	93.47 348	71.52 471	68.84 487	79.08 492	49.77 476	93.21 456	66.81 459	60.52 497	89.13 475

OpenMVS_ROB	74.94 19	79.51 433	77.03 440	86.93 410	87.00 461	76.23 390	92.33 335	90.74 431	68.93 480	74.52 466	88.23 429	49.58 477	96.62 345	57.64 490	84.29 364	87.94 485

tt0320		80.13 424	77.41 434	88.29 370	90.50 416	78.02 345	93.10 297	90.71 432	66.06 492	76.75 449	86.97 447	49.56 478	95.40 417	71.65 417	71.41 466	91.46 439

TDRefinement		79.81 428	77.34 435	87.22 404	79.24 502	75.48 399	93.12 294	92.03 390	76.45 423	75.01 462	91.58 341	49.19 479	96.44 368	70.22 434	69.18 474	89.75 465

test_vis1_n		86.56 317	86.49 281	86.78 416	88.51 443	72.69 431	94.68 181	93.78 339	79.55 375	90.70 171	95.31 179	48.75 480	93.28 455	93.15 71	93.99 199	94.38 317

MIMVSNet1		79.38 434	77.28 436	85.69 431	86.35 465	73.67 418	91.61 361	92.75 368	78.11 403	72.64 476	88.12 430	48.16 481	91.97 472	60.32 481	77.49 441	91.43 440

LF4IMVS		80.37 422	79.07 422	84.27 448	86.64 462	69.87 465	89.39 423	91.05 419	76.38 425	74.97 463	90.00 394	47.85 482	94.25 439	74.55 403	80.82 416	88.69 479

EG-PatchMatch MVS		82.37 393	80.34 395	88.46 364	90.27 421	79.35 310	92.80 317	94.33 311	77.14 412	73.26 473	90.18 387	47.47 483	96.72 334	70.25 432	87.32 340	89.30 469

test_fmvs2		83.98 371	84.03 356	83.83 452	87.16 460	67.53 477	93.93 248	92.89 362	77.62 405	86.89 259	93.53 268	47.18 484	92.02 470	90.54 141	86.51 345	91.93 426

ttmdpeth		76.55 447	74.64 452	82.29 462	82.25 494	67.81 474	89.76 415	85.69 482	70.35 477	75.76 458	91.69 334	46.88 485	89.77 487	66.16 460	63.23 494	89.30 469

sc_t1		81.53 406	78.67 427	90.12 295	90.78 404	78.64 326	93.91 251	90.20 440	68.42 482	80.82 397	89.88 397	46.48 486	96.76 333	76.03 386	71.47 465	94.96 286

MVStest1		72.91 454	69.70 459	82.54 458	78.14 503	73.05 426	88.21 444	86.21 478	60.69 498	64.70 493	90.53 375	46.44 487	85.70 501	58.78 488	53.62 503	88.87 476

tt0320-xc		79.63 432	76.66 441	88.52 363	91.03 390	78.72 323	93.00 303	89.53 461	66.37 489	76.11 456	87.11 446	46.36 488	95.32 420	72.78 413	67.67 484	91.51 436

TinyColmap		79.76 429	77.69 432	85.97 425	91.71 364	73.12 425	89.55 418	90.36 438	75.03 440	72.03 478	90.19 386	46.22 489	96.19 382	63.11 472	81.03 410	88.59 481

myMVS_eth3d		79.67 430	78.79 425	82.32 461	91.92 354	64.08 488	89.75 416	87.40 476	81.72 341	78.82 431	87.20 442	45.33 490	91.29 478	59.09 487	87.84 331	91.60 432

tmp_tt		35.64 491	39.24 491	24.84 514	14.87 562	23.90 540	62.71 517	51.51 523	6.58 541	36.66 523	62.08 522	44.37 491	30.34 537	52.40 498	22.00 531	20.27 537

testing3		80.46 420	79.59 412	83.06 455	93.44 296	64.64 487	93.33 282	85.47 484	84.34 269	79.93 413	90.84 365	44.35 492	92.39 465	57.06 492	87.56 334	92.16 423

new_pmnet		72.15 455	70.13 458	78.20 473	82.95 492	65.68 481	83.91 487	82.40 494	62.94 497	64.47 494	79.82 491	42.85 493	86.26 499	57.41 491	74.44 453	82.65 495

test_vis1_rt		77.96 443	76.46 442	82.48 459	85.89 470	71.74 445	90.25 399	78.89 501	71.03 475	71.30 482	81.35 488	42.49 494	91.05 481	84.55 245	82.37 390	84.65 490

EGC-MVSNET		61.97 467	56.37 472	78.77 471	89.63 434	73.50 420	89.12 428	82.79 492	0.21 560	1.24 562	84.80 466	39.48 495	90.04 486	44.13 508	75.94 451	72.79 506

dongtai		58.82 472	58.24 470	60.56 496	83.13 490	45.09 521	82.32 493	48.22 526	67.61 485	61.70 499	69.15 511	38.75 496	76.05 516	32.01 521	41.31 512	60.55 519

kuosan		53.51 477	53.30 477	54.13 504	76.06 505	45.36 520	80.11 500	48.36 525	59.63 500	54.84 502	63.43 520	37.41 497	62.07 526	20.73 530	39.10 514	54.96 523

usedtu_dtu_shiyan2		74.72 451	71.30 456	84.98 440	77.78 504	70.58 459	91.85 353	90.76 430	67.24 487	68.06 489	82.17 486	37.13 498	92.78 462	60.69 480	66.03 487	91.59 434

pmmvs3		71.81 457	68.71 460	81.11 464	75.86 506	70.42 460	86.74 465	83.66 490	58.95 501	68.64 488	80.89 490	36.93 499	89.52 489	63.10 473	63.59 492	83.39 491

mvsany_test3		74.95 450	73.26 454	80.02 468	74.61 507	63.16 493	85.53 475	78.42 503	74.16 450	74.89 464	86.46 451	36.02 500	89.09 491	82.39 279	66.91 485	87.82 486

PM-MVS		78.11 442	76.12 445	84.09 450	83.54 489	70.08 462	88.97 431	85.27 486	79.93 369	74.73 465	86.43 453	34.70 501	93.48 452	79.43 346	72.06 461	88.72 478

ambc				83.06 455	79.99 500	63.51 492	77.47 504	92.86 363		74.34 468	84.45 468	28.74 502	95.06 425	73.06 412	68.89 477	90.61 454

test_method		50.52 481	48.47 481	56.66 501	52.26 532	18.98 542	41.51 528	81.40 496	10.10 531	44.59 513	75.01 503	28.51 503	68.16 519	53.54 496	49.31 508	82.83 494

DeepMVS_CX				56.31 502	74.23 509	51.81 513		56.67 522	44.85 511	48.54 507	75.16 502	27.87 504	58.74 527	40.92 515	52.22 505	58.39 522

test_fmvs3		77.67 444	77.16 439	79.22 469	79.52 501	61.14 497	92.34 334	91.64 403	73.98 452	78.86 430	86.59 450	27.38 505	87.03 495	88.12 185	75.97 450	89.50 466

test_f		71.95 456	70.87 457	75.21 478	74.21 510	59.37 503	85.07 479	85.82 481	65.25 493	70.42 484	83.13 475	23.62 506	82.93 508	78.32 358	71.94 463	83.33 492

FPMVS		64.63 466	62.55 468	70.88 482	70.80 513	56.71 505	84.42 485	84.42 488	51.78 505	49.57 505	81.61 487	23.49 507	81.48 510	40.61 516	76.25 449	74.46 505

APD_test1		69.04 460	66.26 466	77.36 477	80.51 499	62.79 494	85.46 476	83.51 491	54.11 504	59.14 501	84.79 467	23.40 508	89.61 488	55.22 493	70.24 468	79.68 500

ANet_high		58.88 471	54.22 476	72.86 479	56.50 529	56.67 506	80.75 497	86.00 480	73.09 462	37.39 521	64.63 518	22.17 509	79.49 512	43.51 510	23.96 526	82.43 496

EMVS		42.07 488	41.12 490	44.92 510	63.45 523	35.56 531	73.65 507	63.48 519	33.05 521	26.88 531	45.45 528	21.27 510	67.14 521	19.80 531	23.02 528	32.06 531

ArgMatch-SfM		70.39 458	67.69 462	78.49 472	81.44 496	60.73 498	84.71 484	75.65 512	68.09 484	66.71 492	86.79 448	20.42 511	86.05 500	71.50 420	53.87 502	88.67 480

Gipuma		57.99 473	54.91 475	67.24 491	88.51 443	65.59 482	52.21 521	90.33 439	43.58 513	42.84 514	51.18 525	20.29 512	85.07 502	34.77 518	70.45 467	51.05 524
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 487	42.29 487	46.03 508	65.58 521	37.41 529	73.51 508	64.62 517	33.99 519	28.47 529	47.87 527	19.90 513	67.91 520	22.23 529	24.45 524	32.77 530

ArgMatch-Sym		69.79 459	67.05 464	77.99 475	81.59 495	61.16 496	84.99 480	71.84 513	67.17 488	67.90 490	86.60 449	19.89 514	85.00 503	70.93 428	52.57 504	87.82 486

PMMVS2		59.60 468	56.40 471	69.21 488	68.83 516	46.58 517	73.02 511	77.48 508	55.07 503	49.21 506	72.95 507	17.43 515	80.04 511	49.32 503	44.33 511	80.99 498

LCM-MVSNet		66.00 464	62.16 469	77.51 476	64.51 522	58.29 504	83.87 488	90.90 426	48.17 507	54.69 503	73.31 506	16.83 516	86.75 496	65.47 462	61.67 496	87.48 488

test_vis3_rt		65.12 465	62.60 467	72.69 480	71.44 512	60.71 499	87.17 460	65.55 516	63.80 496	53.22 504	65.65 517	14.54 517	89.44 490	76.65 376	65.38 489	67.91 515

testf1		59.54 469	56.11 473	69.85 486	69.28 514	56.61 507	80.37 498	76.55 510	42.58 514	45.68 511	75.61 498	11.26 518	84.18 504	43.20 512	60.44 498	68.75 512

APD_test2		59.54 469	56.11 473	69.85 486	69.28 514	56.61 507	80.37 498	76.55 510	42.58 514	45.68 511	75.61 498	11.26 518	84.18 504	43.20 512	60.44 498	68.75 512

MVS_clip		24.79 498	27.71 498	16.02 524	35.36 544	15.85 544	27.38 536	5.39 560	6.70 540	40.04 518	63.09 521	10.55 520	8.72 558	27.86 525	33.03 520	23.49 535

PDCNetPlus		48.34 482	45.15 485	57.91 499	61.43 524	41.85 523	65.98 516	38.30 530	47.59 508	37.96 520	71.85 508	10.18 521	66.85 523	52.94 497	20.14 537	65.03 517

VLMVS		10.93 514	11.73 514	8.51 536	11.99 563	6.47 566	9.10 553	5.11 561	0.73 557	17.62 536	25.59 540	9.61 522	6.56 560	6.19 541	19.64 538	12.50 540

VLMVS_CLIP		27.58 495	28.97 496	23.41 516	23.47 558	13.17 550	30.64 534	40.90 528	9.21 533	36.34 524	50.75 526	8.75 523	38.05 532	25.18 527	35.53 516	19.03 539

LoFTR		57.22 474	52.62 478	71.00 481	72.03 511	48.57 516	72.00 512	70.08 515	44.40 512	40.92 517	76.42 496	8.12 524	82.76 509	42.28 514	47.33 510	81.66 497

DenseAffine		56.77 475	52.17 479	70.54 484	74.27 508	53.25 512	77.23 505	50.43 524	49.87 506	47.26 510	77.37 495	7.99 525	79.10 513	50.35 500	34.79 517	79.28 501

RoMa-SfM		53.80 476	49.39 480	67.06 492	67.87 518	48.86 514	75.04 506	38.06 531	47.23 509	47.40 509	78.96 493	7.40 526	76.66 515	48.89 504	33.62 518	75.64 504

MASt3R-SfM		45.78 485	43.96 486	51.24 506	45.04 534	29.83 535	57.88 518	38.83 529	31.88 522	47.48 508	81.30 489	7.16 527	51.15 530	49.56 502	36.51 515	72.74 507

ALIKED-LG		28.00 494	26.54 499	32.41 511	58.12 526	31.80 532	47.26 524	21.21 536	14.15 528	19.16 534	41.93 530	6.72 528	35.73 533	5.96 542	24.32 525	29.69 532

MatchFormer		51.11 479	46.66 483	64.46 494	67.11 519	43.39 522	70.54 513	63.67 518	33.19 520	37.22 522	70.30 510	6.67 529	78.17 514	30.29 522	40.94 513	71.81 509

PMVS	47.18 22	52.22 478	48.46 482	63.48 495	45.72 533	46.20 518	73.41 509	78.31 504	41.03 516	30.06 527	65.68 516	6.05 530	83.43 507	30.04 523	65.86 488	60.80 518
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SP-DiffGlue		20.02 503	19.96 506	20.21 519	19.64 559	13.14 551	30.51 535	15.49 542	8.39 534	19.98 533	43.75 529	5.48 531	13.72 544	13.75 534	22.65 529	33.78 528

RoMa-HiRes		46.47 483	42.20 488	59.28 498	57.74 527	39.86 528	66.76 515	24.64 534	39.96 517	41.50 516	75.37 501	5.40 532	69.26 518	43.35 511	25.09 522	68.71 514

ALIKED-NN		26.07 497	24.75 501	30.02 513	55.08 531	30.61 534	44.20 527	19.22 538	10.98 530	17.98 535	40.71 531	5.39 533	32.83 535	5.59 543	23.63 527	26.63 534

ALIKED-MNN		26.28 496	24.57 502	31.39 512	56.22 530	31.73 533	45.54 525	19.13 539	11.12 529	17.11 537	39.35 532	5.01 534	34.53 534	5.54 544	22.12 530	27.92 533

DKM		50.92 480	46.13 484	65.30 493	66.27 520	45.98 519	73.05 510	31.91 533	45.08 510	42.04 515	75.01 503	4.95 535	73.81 517	47.90 505	28.96 521	76.09 503

SP-LightGlue		20.24 501	20.15 505	20.49 517	43.51 536	12.27 552	38.68 530	14.56 544	7.54 537	12.90 542	30.07 537	4.75 536	14.38 541	7.60 537	21.75 532	34.82 525

SP-SuperGlue		20.22 502	20.18 504	20.36 518	43.26 537	12.27 552	38.71 529	14.77 543	7.64 536	13.04 541	30.21 536	4.73 537	14.21 543	7.59 538	21.65 533	34.59 526

MVE	39.65 23	43.39 486	38.59 492	57.77 500	56.52 528	48.77 515	55.38 519	58.64 521	29.33 524	28.96 528	52.65 524	4.68 538	64.62 525	28.11 524	33.07 519	59.93 520
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SP-NN		19.44 505	19.37 508	19.67 521	41.70 539	11.48 557	37.75 532	13.72 547	6.86 538	11.86 543	29.97 538	4.23 539	14.25 542	7.13 539	21.07 534	33.30 529

SP-MNN		19.61 504	19.42 507	20.19 520	42.15 538	11.42 558	38.15 531	14.24 545	6.55 542	11.64 544	29.88 539	4.16 540	14.56 540	7.09 540	20.92 535	34.58 527

XFeat-MNN		17.43 506	16.95 509	18.86 522	16.90 560	11.28 559	27.31 537	17.08 540	8.08 535	15.61 539	35.73 533	4.06 541	22.95 538	10.20 535	17.59 541	22.35 536

wuyk23d		21.27 500	20.48 503	23.63 515	68.59 517	36.41 530	49.57 522	6.85 554	9.37 532	7.89 545	4.46 560	4.03 542	31.37 536	17.47 533	16.07 542	3.12 556

GLUNet-SfM		31.36 493	26.25 500	46.70 507	35.51 543	24.89 539	33.71 533	36.36 532	19.08 527	23.78 532	52.69 523	3.82 543	56.26 529	19.75 532	11.56 551	58.95 521

DKM-HiRes		45.90 484	41.41 489	59.36 497	59.55 525	39.90 527	67.13 514	23.25 535	39.95 518	38.74 519	71.81 509	3.67 544	66.42 524	43.82 509	24.82 523	71.77 510

XFeat-NN		15.96 507	15.86 510	16.25 523	15.78 561	9.87 562	25.17 538	13.83 546	6.76 539	15.68 538	34.83 534	3.61 545	19.28 539	9.22 536	17.90 539	19.58 538

ELoFTR		40.15 489	35.08 493	55.36 503	41.27 540	28.17 538	47.70 523	43.76 527	29.15 525	30.35 526	65.97 515	2.17 546	66.90 522	34.51 519	20.83 536	71.00 511

SIFT-NN		12.98 508	13.18 511	12.37 525	36.49 542	16.03 543	22.41 539	7.69 550	4.89 543	7.41 546	20.48 542	1.69 547	11.46 546	1.88 548	15.70 543	9.61 542

SIFT-MNN		12.44 509	12.55 512	12.11 526	34.55 545	15.21 545	20.91 540	7.74 549	4.86 544	6.54 548	20.09 543	1.51 548	11.47 545	1.88 548	14.87 545	9.64 541

SIFT-NN-NCMNet		12.12 510	12.25 513	11.75 527	32.82 547	14.83 546	20.73 541	7.58 551	4.72 546	6.60 547	19.53 544	1.49 549	11.15 548	1.74 550	15.02 544	9.28 543

SIFT-NN-UMatch		11.06 513	11.19 519	10.66 531	28.66 553	12.16 554	19.79 542	6.86 553	4.73 545	5.21 551	19.47 546	1.46 550	10.70 551	1.71 551	12.79 549	9.13 545

SIFT-NN-CMatch		11.26 512	11.31 517	11.13 529	30.21 551	13.40 549	18.43 544	6.79 555	4.71 547	6.47 549	19.53 544	1.43 551	10.72 550	1.71 551	12.49 550	9.26 544

SIFT-NN-PointCN		10.26 517	10.46 522	9.65 534	27.18 554	9.89 561	17.89 546	6.17 557	4.40 553	5.65 550	18.29 550	1.43 551	10.09 554	1.61 555	11.55 552	8.99 547

SIFT-NCM-Cal		11.58 511	11.64 515	11.40 528	33.45 546	14.10 547	19.75 543	6.89 552	4.68 549	4.55 555	18.60 549	1.34 553	11.28 547	1.53 556	13.95 546	8.82 548

SIFT-ConvMatch		10.91 515	10.94 520	10.84 530	32.07 548	13.57 548	17.23 547	6.35 556	4.71 547	5.18 552	18.94 547	1.30 554	10.76 549	1.65 554	11.02 553	8.19 549

SIFT-CM-Cal		10.08 518	10.13 524	9.92 533	30.71 550	11.88 555	15.35 549	5.44 559	4.59 551	4.72 553	18.04 552	1.26 555	10.19 553	1.46 558	9.60 555	7.69 551

SIFT-UMatch		10.58 516	10.73 521	10.15 532	31.05 549	11.65 556	18.01 545	5.92 558	4.65 550	4.72 553	18.93 548	1.25 556	10.62 552	1.66 553	10.39 554	8.16 550

SIFT-UM-Cal		9.80 519	10.00 525	9.22 535	30.05 552	10.15 560	16.31 548	4.85 563	4.54 552	4.19 556	18.23 551	1.19 557	9.95 555	1.52 557	9.11 557	7.57 552

MVS_baseline		7.30 526	8.69 529	3.12 540	8.45 564	0.31 569	3.27 554	0.80 566	0.16 561	14.50 540	32.51 535	1.15 558	0.00 563	4.24 545	13.11 548	9.06 546

PMatch-SfM		38.18 490	33.34 494	52.72 505	43.67 535	28.18 537	52.96 520	16.29 541	29.70 523	31.24 525	68.56 513	1.08 559	57.70 528	38.73 517	17.80 540	72.30 508

SIFT-PCN-Cal		8.65 523	8.88 527	7.98 537	26.74 555	7.47 564	13.90 551	4.61 564	4.09 555	3.82 557	15.86 553	1.01 560	8.94 556	1.34 559	8.52 558	7.53 553

SIFT-PointCN		8.76 521	9.03 526	7.96 538	26.50 556	7.60 563	14.94 550	5.08 562	4.10 554	3.74 558	15.46 554	0.94 561	8.92 557	1.33 560	9.14 556	7.37 554

SIFT-NCMNet		7.46 525	7.71 530	6.72 539	25.03 557	6.86 565	11.42 552	2.98 565	4.05 556	3.38 559	13.68 555	0.84 562	7.65 559	1.13 561	6.87 559	5.66 555

PMatch-Up-SfM		32.59 492	28.46 497	44.98 509	37.19 541	22.27 541	44.73 526	10.63 548	23.85 526	27.52 530	64.10 519	0.78 563	47.14 531	34.15 520	13.22 547	65.53 516

test123		8.76 521	11.22 518	1.39 541	0.85 566	0.97 567	85.76 473	0.35 568	0.54 559	2.45 561	8.14 559	0.60 564	0.48 561	2.16 547	0.17 561	2.71 557

testmvs		8.92 520	11.52 516	1.12 542	1.06 565	0.46 568	86.02 469	0.65 567	0.62 558	2.74 560	9.52 558	0.31 565	0.45 562	2.38 546	0.39 560	2.46 558

mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

ab-mvs-re		7.82 524	10.43 523	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	93.88 256	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet2					0.00 567	62.07 495	85.98 470	87.63 474	68.79 481
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														54.59 495	77.20 443	90.17 460
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.68 476
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
aaatest				94.84 34	98.88 1	85.89 66	97.32 10	97.86 1	88.11 135	97.21 15	97.54 47		99.67 1	95.27 42	98.85 22	98.95 13

WAC-MVS						64.08 488								59.14 486

FOURS1					98.86 4	85.54 75	98.29 1	97.49 11	89.79 67	96.29 33

MSC_two_6792asdad				96.52 1	97.78 61	90.86 1		96.85 81					99.61 7	96.03 28	99.06 9	99.07 7

No_MVS				96.52 1	97.78 61	90.86 1		96.85 81					99.61 7	96.03 28	99.06 9	99.07 7

eth-test2					0.00 567

eth-test					0.00 567

IU-MVS					98.77 8	86.00 55		96.84 83	81.26 354	97.26 14				95.50 38	99.13 3	99.03 10

save fliter					97.85 56	85.63 74	95.21 142	96.82 86	89.44 78

test_0728_SECOND				95.01 18	98.79 5	86.43 41	97.09 21	97.49 11					99.61 7	95.62 36	99.08 7	98.99 11

GSMVS																96.12 237

test_part2					98.55 15	87.22 20				96.40 32

MTGPA								96.97 66

MTMP							96.16 60	60.64 520

gm-plane-assit					89.60 435	68.00 471			77.28 411		88.99 413		97.57 251	79.44 345

test9_res														91.91 111	98.71 36	98.07 84

agg_prior2														90.54 141	98.68 41	98.27 65

agg_prior					97.38 73	85.92 62		96.72 101		92.16 123			98.97 88

test_prior4						85.96 59	94.11 228

test_prior				93.82 74	97.29 78	84.49 99		96.88 79					98.87 101			98.11 83

旧先验2							93.36 281		71.25 473	94.37 63			97.13 310	86.74 207

新几何2							93.11 296

无先验							93.28 289	96.26 142	73.95 453				99.05 68	80.56 319		96.59 216

原ACMM2							92.94 307

testdata2													98.75 118	78.30 359

testdata1							92.15 344		87.94 145

plane_prior7					94.70 205	82.74 166

plane_prior5								96.22 148					98.12 181	88.15 182	89.99 290	94.63 299

plane_prior4											94.86 204

plane_prior3						82.75 164			90.26 51	86.91 256

plane_prior2							95.85 93		90.81 28

plane_prior1					94.59 214

plane_prior						82.73 167	95.21 142		89.66 72						89.88 295

n2								0.00 569

nn								0.00 569

door-mid								85.49 483

test11								96.57 114

door								85.33 485

HQP5-MVS						81.56 208

HQP-NCC					94.17 255		94.39 207		88.81 105	85.43 302

ACMP_Plane					94.17 255		94.39 207		88.81 105	85.43 302

BP-MVS														87.11 204

HQP4-MVS										85.43 302			97.96 218			94.51 309

HQP3-MVS								96.04 176							89.77 299

NP-MVS					94.37 236	82.42 181					93.98 249

ACMMP++_ref															87.47 335

ACMMP++															88.01 327

High-resolution multi-view benchmark