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.

SMA-MVS		95.20 8	95.07 11	95.59 6	98.14 35	88.48 8	96.26 47	97.28 31	85.90 153	97.67 3	98.10 7	88.41 20	99.56 12	94.66 26	99.19 1	98.71 19
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
DPE-MVS		95.57 4	95.67 4	95.25 10	98.36 25	87.28 17	95.56 95	97.51 5	89.13 63	97.14 9	97.91 18	91.64 7	99.62 2	94.61 27	99.17 2	98.86 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SED-MVS		95.91 2	96.28 2	94.80 32	98.77 5	85.99 51	97.13 14	97.44 15	90.31 28	97.71 1	98.07 9	92.31 4	99.58 10	95.66 17	99.13 3	98.84 14

IU-MVS					98.77 5	86.00 49		96.84 65	81.26 263	97.26 7				95.50 23	99.13 3	99.03 8

test_0728_THIRD									90.75 19	97.04 11	98.05 13	92.09 6	99.55 16	95.64 19	99.13 3	99.13 2

test_241102_TWO								97.44 15	90.31 28	97.62 5	98.07 9	91.46 10	99.58 10	95.66 17	99.12 6	98.98 10

DVP-MVS		95.67 3	96.02 3	94.64 38	98.78 3	85.93 54	97.09 16	96.73 79	90.27 31	97.04 11	98.05 13	91.47 8	99.55 16	95.62 21	99.08 7	98.45 36
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				95.01 17	98.79 2	86.43 38	97.09 16	97.49 6					99.61 4	95.62 21	99.08 7	98.99 9

MSC_two_6792asdad				96.52 1	97.78 51	90.86 1		96.85 63					99.61 4	96.03 14	99.06 9	99.07 5

No_MVS				96.52 1	97.78 51	90.86 1		96.85 63					99.61 4	96.03 14	99.06 9	99.07 5

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 28	86.29 45	97.46 6	97.40 20	89.03 67	96.20 19	98.10 7	89.39 16	99.34 34	95.88 16	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS++		95.98 1	96.36 1	94.82 30	97.78 51	86.00 49	98.29 1	97.49 6	90.75 19	97.62 5	98.06 11	92.59 2	99.61 4	95.64 19	99.02 12	98.86 11

PC_three_1452									82.47 230	97.09 10	97.07 51	92.72 1	98.04 159	92.70 55	99.02 12	98.86 11

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 49	92.59 2	98.94 78	92.25 63	98.99 14	98.84 14

ACMMP_NAP		94.74 15	94.56 18	95.28 9	98.02 41	87.70 11	95.68 85	97.34 23	88.28 91	95.30 32	97.67 26	85.90 47	99.54 20	93.91 34	98.95 15	98.60 23

HPM-MVS++		95.14 10	94.91 13	95.83 4	98.25 29	89.65 4	95.92 73	96.96 52	91.75 9	94.02 46	96.83 61	88.12 24	99.55 16	93.41 42	98.94 16	98.28 50

MP-MVS-pluss		94.21 31	94.00 41	94.85 25	98.17 33	86.65 30	94.82 136	97.17 39	86.26 145	92.83 71	97.87 20	85.57 50	99.56 12	94.37 30	98.92 17	98.34 42
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 25	96.99 72	86.33 41	97.33 7	97.30 29	91.38 12	95.39 30	97.46 30	88.98 19	99.40 30	94.12 31	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
SD-MVS		94.96 12	95.33 8	93.88 57	97.25 69	86.69 27	96.19 50	97.11 43	90.42 27	96.95 13	97.27 38	89.53 14	96.91 248	94.38 29	98.85 19	98.03 70
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
CNVR-MVS		95.40 7	95.37 7	95.50 8	98.11 36	88.51 7	95.29 105	96.96 52	92.09 6	95.32 31	97.08 49	89.49 15	99.33 37	95.10 24	98.85 19	98.66 20

CP-MVS		94.34 26	94.21 33	94.74 36	98.39 23	86.64 31	97.60 4	97.24 32	88.53 84	92.73 77	97.23 41	85.20 55	99.32 38	92.15 67	98.83 21	98.25 55

ZNCC-MVS		94.47 20	94.28 29	95.03 16	98.52 15	86.96 19	96.85 28	97.32 27	88.24 92	93.15 61	97.04 52	86.17 44	99.62 2	92.40 59	98.81 22	98.52 26

MP-MVS		94.25 28	94.07 38	94.77 34	98.47 18	86.31 43	96.71 31	96.98 49	89.04 66	91.98 93	97.19 44	85.43 52	99.56 12	92.06 73	98.79 23	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		93.89 42	93.65 53	94.62 40	96.84 75	86.43 38	96.69 32	97.49 6	85.15 173	93.56 55	96.28 84	85.60 49	99.31 39	92.45 56	98.79 23	98.12 64

SF-MVS		94.97 11	94.90 14	95.20 12	97.84 47	87.76 10	96.65 35	97.48 10	87.76 111	95.71 27	97.70 25	88.28 23	99.35 33	93.89 35	98.78 25	98.48 30

ACMMPR		94.43 23	94.28 29	94.91 21	98.63 9	86.69 27	96.94 20	97.32 27	88.63 80	93.53 56	97.26 40	85.04 58	99.54 20	92.35 61	98.78 25	98.50 27

HFP-MVS		94.52 19	94.40 22	94.86 24	98.61 10	86.81 24	96.94 20	97.34 23	88.63 80	93.65 51	97.21 42	86.10 45	99.49 26	92.35 61	98.77 27	98.30 47

MM				95.68 5		88.34 9	96.68 33	94.37 234	95.08 1	94.68 36	97.72 24	82.94 83	99.64 1	97.85 1	98.76 28	99.06 7

MVS_0304		94.60 17	94.38 24	95.23 11	95.41 129	87.49 15	96.53 38	92.75 277	93.82 2	93.07 65	97.84 22	83.66 74	99.59 8	97.61 2	98.76 28	98.61 22

MTAPA		94.42 25	94.22 32	95.00 18	98.42 21	86.95 20	94.36 170	96.97 50	91.07 13	93.14 62	97.56 27	84.30 67	99.56 12	93.43 40	98.75 30	98.47 33

region2R		94.43 23	94.27 31	94.92 20	98.65 8	86.67 29	96.92 24	97.23 34	88.60 82	93.58 53	97.27 38	85.22 54	99.54 20	92.21 64	98.74 31	98.56 25

test9_res														91.91 78	98.71 32	98.07 66

DeepPCF-MVS	89.96 1	94.20 33	94.77 16	92.49 114	96.52 87	80.00 219	94.00 194	97.08 44	90.05 35	95.65 29	97.29 37	89.66 13	98.97 75	93.95 33	98.71 32	98.50 27

9.14			94.47 19		97.79 49		96.08 61	97.44 15	86.13 151	95.10 33	97.40 33	88.34 22	99.22 44	93.25 44	98.70 34

train_agg		93.44 54	93.08 61	94.52 43	97.53 58	86.49 36	94.07 186	96.78 72	81.86 247	92.77 74	96.20 87	87.63 29	99.12 51	92.14 68	98.69 35	97.94 74

DeepC-MVS_fast	89.43 2	94.04 37	93.79 45	94.80 32	97.48 61	86.78 25	95.65 90	96.89 60	89.40 53	92.81 72	96.97 54	85.37 53	99.24 43	90.87 97	98.69 35	98.38 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + MP.		94.85 13	94.94 12	94.58 41	98.25 29	86.33 41	96.11 60	96.62 88	88.14 98	96.10 20	96.96 55	89.09 18	98.94 78	94.48 28	98.68 37	98.48 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
agg_prior2														90.54 102	98.68 37	98.27 52

test_prior2							94.12 180		87.67 114	92.63 79	96.39 82	86.62 38		91.50 85	98.67 39

MSLP-MVS++		93.72 47	94.08 37	92.65 106	97.31 65	83.43 114	95.79 79	97.33 25	90.03 36	93.58 53	96.96 55	84.87 62	97.76 174	92.19 66	98.66 40	96.76 131

CDPH-MVS		92.83 68	92.30 74	94.44 44	97.79 49	86.11 48	94.06 188	96.66 85	80.09 276	92.77 74	96.63 73	86.62 38	99.04 57	87.40 136	98.66 40	98.17 60

HPM-MVS		94.02 38	93.88 43	94.43 46	98.39 23	85.78 61	97.25 10	97.07 45	86.90 131	92.62 80	96.80 65	84.85 63	99.17 47	92.43 57	98.65 42	98.33 43
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		93.99 40	93.78 46	94.63 39	98.50 16	85.90 58	96.87 26	96.91 58	88.70 78	91.83 102	97.17 46	83.96 71	99.55 16	91.44 86	98.64 43	98.43 38

CS-MVS-test		94.02 38	94.29 28	93.24 73	96.69 78	83.24 119	97.49 5	96.92 57	92.14 5	92.90 67	95.77 108	85.02 59	98.33 131	93.03 47	98.62 44	98.13 62

MCST-MVS		94.45 21	94.20 34	95.19 13	98.46 19	87.50 14	95.00 125	97.12 41	87.13 123	92.51 83	96.30 83	89.24 17	99.34 34	93.46 39	98.62 44	98.73 17

APD-MVS		94.24 29	94.07 38	94.75 35	98.06 39	86.90 22	95.88 74	96.94 55	85.68 159	95.05 34	97.18 45	87.31 35	99.07 53	91.90 80	98.61 46	98.28 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PGM-MVS		93.96 41	93.72 49	94.68 37	98.43 20	86.22 46	95.30 103	97.78 1	87.45 118	93.26 58	97.33 36	84.62 65	99.51 24	90.75 99	98.57 47	98.32 46

XVS		94.45 21	94.32 25	94.85 25	98.54 13	86.60 33	96.93 22	97.19 35	90.66 24	92.85 69	97.16 47	85.02 59	99.49 26	91.99 74	98.56 48	98.47 33

X-MVStestdata		88.31 173	86.13 219	94.85 25	98.54 13	86.60 33	96.93 22	97.19 35	90.66 24	92.85 69	23.41 396	85.02 59	99.49 26	91.99 74	98.56 48	98.47 33

DELS-MVS		93.43 57	93.25 58	93.97 54	95.42 128	85.04 70	93.06 237	97.13 40	90.74 21	91.84 100	95.09 133	86.32 42	99.21 45	91.22 88	98.45 50	97.65 89
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
ZD-MVS					98.15 34	86.62 32		97.07 45	83.63 203	94.19 42	96.91 57	87.57 31	99.26 42	91.99 74	98.44 51

GST-MVS		94.21 31	93.97 42	94.90 23	98.41 22	86.82 23	96.54 37	97.19 35	88.24 92	93.26 58	96.83 61	85.48 51	99.59 8	91.43 87	98.40 52	98.30 47

HPM-MVS_fast		93.40 58	93.22 59	93.94 56	98.36 25	84.83 74	97.15 13	96.80 71	85.77 156	92.47 84	97.13 48	82.38 90	99.07 53	90.51 104	98.40 52	97.92 77

NCCC		94.81 14	94.69 17	95.17 14	97.83 48	87.46 16	95.66 88	96.93 56	92.34 4	93.94 47	96.58 76	87.74 27	99.44 29	92.83 50	98.40 52	98.62 21

DeepC-MVS	88.79 3	93.31 59	92.99 64	94.26 51	96.07 102	85.83 59	94.89 131	96.99 48	89.02 69	89.56 132	97.37 35	82.51 89	99.38 31	92.20 65	98.30 55	97.57 94
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		93.23 62	93.05 62	93.76 64	98.04 40	84.07 96	96.22 49	97.37 21	84.15 191	90.05 128	95.66 112	87.77 26	99.15 50	89.91 107	98.27 56	98.07 66

原ACMM1				92.01 130	97.34 64	81.05 185		96.81 70	78.89 290	90.45 120	95.92 100	82.65 87	98.84 88	80.68 237	98.26 57	96.14 151

CS-MVS		94.12 36	94.44 21	93.17 76	96.55 84	83.08 129	97.63 3	96.95 54	91.71 11	93.50 57	96.21 86	85.61 48	98.24 136	93.64 37	98.17 58	98.19 58

MVS_111021_HR		93.45 53	93.31 56	93.84 59	96.99 72	84.84 73	93.24 230	97.24 32	88.76 75	91.60 107	95.85 103	86.07 46	98.66 98	91.91 78	98.16 59	98.03 70

EC-MVSNet		93.44 54	93.71 50	92.63 107	95.21 138	82.43 150	97.27 9	96.71 82	90.57 26	92.88 68	95.80 106	83.16 79	98.16 142	93.68 36	98.14 60	97.31 101

test12				94.34 49	97.13 70	86.15 47		96.29 105		91.04 115		85.08 57	99.01 63		98.13 61	97.86 80

新几何1				93.10 79	97.30 66	84.35 92		95.56 168	71.09 366	91.26 113	96.24 85	82.87 85	98.86 84	79.19 258	98.10 62	96.07 157

patch_mono-2		93.74 46	94.32 25	92.01 130	97.54 57	78.37 257	93.40 218	97.19 35	88.02 101	94.99 35	97.21 42	88.35 21	98.44 121	94.07 32	98.09 63	99.23 1

dcpmvs_2		93.49 51	94.19 35	91.38 165	97.69 54	76.78 289	94.25 173	96.29 105	88.33 88	94.46 38	96.88 58	88.07 25	98.64 100	93.62 38	98.09 63	98.73 17

test_fmvsm_n_1920		94.71 16	95.11 10	93.50 69	95.79 114	84.62 78	96.15 55	97.64 2	89.85 40	97.19 8	97.89 19	86.28 43	98.71 97	97.11 7	98.08 65	97.17 108

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 35	96.91 25	97.47 11	91.73 10	96.10 20	96.69 66	89.90 12	99.30 40	94.70 25	98.04 66	99.13 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
SR-MVS		94.23 30	94.17 36	94.43 46	98.21 32	85.78 61	96.40 41	96.90 59	88.20 96	94.33 40	97.40 33	84.75 64	99.03 58	93.35 43	97.99 67	98.48 30

3Dnovator	86.66 5	91.73 84	90.82 95	94.44 44	94.59 170	86.37 40	97.18 12	97.02 47	89.20 60	84.31 254	96.66 69	73.74 199	99.17 47	86.74 146	97.96 68	97.79 85

CANet		93.54 50	93.20 60	94.55 42	95.65 120	85.73 63	94.94 128	96.69 84	91.89 8	90.69 118	95.88 102	81.99 102	99.54 20	93.14 46	97.95 69	98.39 39

DPM-MVS		92.58 72	91.74 80	95.08 15	96.19 95	89.31 5	92.66 248	96.56 93	83.44 209	91.68 106	95.04 134	86.60 40	98.99 70	85.60 160	97.92 70	96.93 124

APD-MVS_3200maxsize		93.78 44	93.77 47	93.80 62	97.92 43	84.19 94	96.30 43	96.87 62	86.96 127	93.92 48	97.47 29	83.88 72	98.96 77	92.71 54	97.87 71	98.26 54

CPTT-MVS		91.99 78	91.80 79	92.55 111	98.24 31	81.98 160	96.76 30	96.49 95	81.89 246	90.24 123	96.44 81	78.59 136	98.61 104	89.68 108	97.85 72	97.06 115

test_fmvsmconf_n		94.60 17	94.81 15	93.98 53	94.62 169	84.96 72	96.15 55	97.35 22	89.37 54	96.03 23	98.11 5	86.36 41	99.01 63	97.45 3	97.83 73	97.96 73

SR-MVS-dyc-post		93.82 43	93.82 44	93.82 60	97.92 43	84.57 80	96.28 45	96.76 75	87.46 116	93.75 49	97.43 31	84.24 68	99.01 63	92.73 51	97.80 74	97.88 78

RE-MVS-def			93.68 51		97.92 43	84.57 80	96.28 45	96.76 75	87.46 116	93.75 49	97.43 31	82.94 83		92.73 51	97.80 74	97.88 78

test222					96.55 84	81.70 166	92.22 264	95.01 201	68.36 372	90.20 124	96.14 92	80.26 114			97.80 74	96.05 159

test_fmvsmconf0.1_n		94.20 33	94.31 27	93.88 57	92.46 247	84.80 75	96.18 52	96.82 68	89.29 57	95.68 28	98.11 5	85.10 56	98.99 70	97.38 4	97.75 77	97.86 80

3Dnovator+	87.14 4	92.42 75	91.37 83	95.55 7	95.63 121	88.73 6	97.07 18	96.77 74	90.84 16	84.02 258	96.62 74	75.95 163	99.34 34	87.77 130	97.68 78	98.59 24

旧先验1					96.79 76	81.81 164		95.67 160			96.81 63	86.69 37			97.66 79	96.97 122

EPNet		91.79 81	91.02 91	94.10 52	90.10 328	85.25 69	96.03 66	92.05 297	92.83 3	87.39 171	95.78 107	79.39 126	99.01 63	88.13 126	97.48 80	98.05 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmvis_n_1920		93.44 54	93.55 54	93.10 79	93.67 213	84.26 93	95.83 77	96.14 120	89.00 70	92.43 85	97.50 28	83.37 78	98.72 96	96.61 12	97.44 81	96.32 144

testdata				90.49 202	96.40 89	77.89 269		95.37 186	72.51 358	93.63 52	96.69 66	82.08 99	97.65 182	83.08 190	97.39 82	95.94 161

MVS_111021_LR		92.47 74	92.29 75	92.98 87	95.99 108	84.43 89	93.08 235	96.09 126	88.20 96	91.12 114	95.72 111	81.33 107	97.76 174	91.74 81	97.37 83	96.75 132

test_fmvsmconf0.01_n		93.19 63	93.02 63	93.71 65	89.25 340	84.42 91	96.06 64	96.29 105	89.06 64	94.68 36	98.13 3	79.22 128	98.98 74	97.22 5	97.24 84	97.74 87

MVSFormer		91.68 86	91.30 84	92.80 97	93.86 203	83.88 101	95.96 71	95.90 142	84.66 185	91.76 103	94.91 137	77.92 144	97.30 218	89.64 109	97.11 85	97.24 104

lupinMVS		90.92 97	90.21 101	93.03 84	93.86 203	83.88 101	92.81 245	93.86 254	79.84 278	91.76 103	94.29 164	77.92 144	98.04 159	90.48 105	97.11 85	97.17 108

EIA-MVS		91.95 79	91.94 77	91.98 134	95.16 140	80.01 218	95.36 98	96.73 79	88.44 85	89.34 136	92.16 239	83.82 73	98.45 119	89.35 111	97.06 87	97.48 97

MG-MVS		91.77 82	91.70 81	92.00 133	97.08 71	80.03 217	93.60 212	95.18 194	87.85 109	90.89 116	96.47 80	82.06 100	98.36 126	85.07 164	97.04 88	97.62 90

fmvsm_l_conf0.5_n_a		94.20 33	94.40 22	93.60 67	95.29 132	84.98 71	95.61 92	96.28 108	86.31 143	96.75 16	97.86 21	87.40 33	98.74 95	97.07 8	97.02 89	97.07 114

test2506		87.21 218	86.28 215	90.02 227	95.62 122	73.64 320	96.25 48	71.38 396	87.89 107	90.45 120	96.65 70	55.29 354	98.09 154	86.03 155	96.94 90	98.33 43

ECVR-MVS		89.09 149	88.53 146	90.77 193	95.62 122	75.89 301	96.16 53	84.22 374	87.89 107	90.20 124	96.65 70	63.19 313	98.10 146	85.90 156	96.94 90	98.33 43

test1111		89.10 147	88.64 142	90.48 204	95.53 126	74.97 308	96.08 61	84.89 372	88.13 99	90.16 126	96.65 70	63.29 311	98.10 146	86.14 151	96.90 92	98.39 39

jason		90.80 98	90.10 105	92.90 92	93.04 231	83.53 112	93.08 235	94.15 243	80.22 273	91.41 110	94.91 137	76.87 151	97.93 168	90.28 106	96.90 92	97.24 104
jason: jason.
Vis-MVSNet		91.75 83	91.23 86	93.29 71	95.32 131	83.78 103	96.14 57	95.98 134	89.89 38	90.45 120	96.58 76	75.09 175	98.31 134	84.75 170	96.90 92	97.78 86
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
114514_t		89.51 133	88.50 148	92.54 112	98.11 36	81.99 159	95.16 116	96.36 102	70.19 369	85.81 202	95.25 124	76.70 155	98.63 102	82.07 210	96.86 95	97.00 120

fmvsm_l_conf0.5_n		94.29 27	94.46 20	93.79 63	95.28 133	85.43 66	95.68 85	96.43 97	86.56 138	96.84 14	97.81 23	87.56 32	98.77 92	97.14 6	96.82 96	97.16 112

Vis-MVSNet (Re-imp)		89.59 131	89.44 120	90.03 225	95.74 116	75.85 302	95.61 92	90.80 332	87.66 115	87.83 160	95.40 120	76.79 153	96.46 275	78.37 262	96.73 97	97.80 84

API-MVS		90.66 104	90.07 106	92.45 116	96.36 91	84.57 80	96.06 64	95.22 193	82.39 231	89.13 138	94.27 167	80.32 112	98.46 115	80.16 245	96.71 98	94.33 230

MAR-MVS		90.30 110	89.37 123	93.07 83	96.61 81	84.48 85	95.68 85	95.67 160	82.36 233	87.85 159	92.85 216	76.63 157	98.80 90	80.01 246	96.68 99	95.91 162
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
OpenMVS	83.78 11	88.74 162	87.29 179	93.08 81	92.70 242	85.39 67	96.57 36	96.43 97	78.74 295	80.85 303	96.07 94	69.64 249	99.01 63	78.01 269	96.65 100	94.83 204

ETV-MVS		92.74 70	92.66 69	92.97 88	95.20 139	84.04 98	95.07 121	96.51 94	90.73 22	92.96 66	91.19 273	84.06 69	98.34 129	91.72 82	96.54 101	96.54 140

QAPM		89.51 133	88.15 159	93.59 68	94.92 153	84.58 79	96.82 29	96.70 83	78.43 300	83.41 273	96.19 90	73.18 206	99.30 40	77.11 278	96.54 101	96.89 127

IS-MVSNet		91.43 88	91.09 90	92.46 115	95.87 113	81.38 177	96.95 19	93.69 260	89.72 47	89.50 134	95.98 98	78.57 137	97.77 173	83.02 192	96.50 103	98.22 57

DP-MVS Recon		91.95 79	91.28 85	93.96 55	98.33 27	85.92 56	94.66 147	96.66 85	82.69 228	90.03 129	95.82 105	82.30 93	99.03 58	84.57 172	96.48 104	96.91 126

CANet_DTU		90.26 112	89.41 122	92.81 96	93.46 219	83.01 132	93.48 215	94.47 229	89.43 52	87.76 163	94.23 168	70.54 239	99.03 58	84.97 165	96.39 105	96.38 143

UGNet		89.95 121	88.95 133	92.95 90	94.51 176	83.31 118	95.70 84	95.23 191	89.37 54	87.58 165	93.94 180	64.00 304	98.78 91	83.92 181	96.31 106	96.74 133
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
fmvsm_s_conf0.5_n		93.76 45	94.06 40	92.86 94	95.62 122	83.17 122	96.14 57	96.12 123	88.13 99	95.82 26	98.04 16	83.43 75	98.48 111	96.97 9	96.23 107	96.92 125

fmvsm_s_conf0.1_n		93.46 52	93.66 52	92.85 95	93.75 209	83.13 124	96.02 67	95.74 154	87.68 113	95.89 25	98.17 2	82.78 86	98.46 115	96.71 10	96.17 108	96.98 121

TSAR-MVS + GP.		93.66 48	93.41 55	94.41 48	96.59 82	86.78 25	94.40 163	93.93 250	89.77 45	94.21 41	95.59 115	87.35 34	98.61 104	92.72 53	96.15 109	97.83 83

PVSNet_Blended		90.73 101	90.32 100	91.98 134	96.12 97	81.25 179	92.55 252	96.83 66	82.04 240	89.10 139	92.56 227	81.04 109	98.85 86	86.72 148	95.91 110	95.84 166

PS-MVSNAJ		91.18 94	90.92 92	91.96 136	95.26 136	82.60 149	92.09 269	95.70 158	86.27 144	91.84 100	92.46 229	79.70 121	98.99 70	89.08 115	95.86 111	94.29 233

ACMMP		93.24 61	92.88 66	94.30 50	98.09 38	85.33 68	96.86 27	97.45 14	88.33 88	90.15 127	97.03 53	81.44 105	99.51 24	90.85 98	95.74 112	98.04 69
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
casdiffmvs_mvg		92.96 67	92.83 67	93.35 70	94.59 170	83.40 116	95.00 125	96.34 103	90.30 30	92.05 91	96.05 95	83.43 75	98.15 143	92.07 70	95.67 113	98.49 29
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LCM-MVSNet-Re		88.30 174	88.32 155	88.27 276	94.71 164	72.41 337	93.15 231	90.98 327	87.77 110	79.25 325	91.96 251	78.35 140	95.75 307	83.04 191	95.62 114	96.65 135

CHOSEN 1792x2688		88.84 158	87.69 169	92.30 124	96.14 96	81.42 176	90.01 310	95.86 146	74.52 339	87.41 168	93.94 180	75.46 172	98.36 126	80.36 241	95.53 115	97.12 113

fmvsm_s_conf0.5_n_a		93.57 49	93.76 48	93.00 86	95.02 145	83.67 106	96.19 50	96.10 125	87.27 121	95.98 24	98.05 13	83.07 82	98.45 119	96.68 11	95.51 116	96.88 128

AdaColmap		89.89 124	89.07 130	92.37 120	97.41 62	83.03 130	94.42 162	95.92 139	82.81 225	86.34 195	94.65 152	73.89 195	99.02 61	80.69 236	95.51 116	95.05 192

MVS		87.44 205	86.10 222	91.44 163	92.61 244	83.62 109	92.63 249	95.66 162	67.26 373	81.47 295	92.15 240	77.95 143	98.22 139	79.71 249	95.48 118	92.47 309

UA-Net		92.83 68	92.54 71	93.68 66	96.10 100	84.71 77	95.66 88	96.39 100	91.92 7	93.22 60	96.49 79	83.16 79	98.87 82	84.47 174	95.47 119	97.45 99

xiu_mvs_v2_base		91.13 95	90.89 94	91.86 144	94.97 149	82.42 151	92.24 263	95.64 165	86.11 152	91.74 105	93.14 209	79.67 124	98.89 81	89.06 116	95.46 120	94.28 234

casdiffmvs		92.51 73	92.43 73	92.74 101	94.41 182	81.98 160	94.54 153	96.23 114	89.57 49	91.96 95	96.17 91	82.58 88	98.01 161	90.95 95	95.45 121	98.23 56
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.1_n_a		93.19 63	93.26 57	92.97 88	92.49 245	83.62 109	96.02 67	95.72 157	86.78 133	96.04 22	98.19 1	82.30 93	98.43 123	96.38 13	95.42 122	96.86 129

PVSNet_Blended_VisFu		91.38 89	90.91 93	92.80 97	96.39 90	83.17 122	94.87 133	96.66 85	83.29 213	89.27 137	94.46 158	80.29 113	99.17 47	87.57 134	95.37 123	96.05 159

PAPM_NR		91.22 93	90.78 96	92.52 113	97.60 56	81.46 174	94.37 169	96.24 113	86.39 142	87.41 168	94.80 145	82.06 100	98.48 111	82.80 198	95.37 123	97.61 91

CHOSEN 280x420		85.15 267	83.99 270	88.65 268	92.47 246	78.40 256	79.68 384	92.76 276	74.90 336	81.41 297	89.59 311	69.85 247	95.51 314	79.92 248	95.29 125	92.03 321

TAPA-MVS	84.62 6	88.16 177	87.01 187	91.62 154	96.64 80	80.65 196	94.39 165	96.21 118	76.38 319	86.19 198	95.44 117	79.75 119	98.08 156	62.75 363	95.29 125	96.13 152
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline		92.39 76	92.29 75	92.69 105	94.46 179	81.77 165	94.14 179	96.27 109	89.22 59	91.88 98	96.00 96	82.35 91	97.99 163	91.05 90	95.27 127	98.30 47

LS3D		87.89 183	86.32 213	92.59 109	96.07 102	82.92 136	95.23 109	94.92 209	75.66 326	82.89 280	95.98 98	72.48 215	99.21 45	68.43 337	95.23 128	95.64 175

test_vis1_n_1920		89.39 142	89.84 113	88.04 283	92.97 235	72.64 332	94.71 144	96.03 133	86.18 148	91.94 97	96.56 78	61.63 320	95.74 308	93.42 41	95.11 129	95.74 171

MVS_Test		91.31 91	91.11 88	91.93 138	94.37 183	80.14 210	93.46 217	95.80 149	86.46 140	91.35 112	93.77 190	82.21 96	98.09 154	87.57 134	94.95 130	97.55 96

test_cas_vis1_n_1920		88.83 161	88.85 139	88.78 262	91.15 295	76.72 290	93.85 202	94.93 208	83.23 216	92.81 72	96.00 96	61.17 328	94.45 328	91.67 83	94.84 131	95.17 189

PAPR		90.02 117	89.27 128	92.29 125	95.78 115	80.95 189	92.68 247	96.22 115	81.91 244	86.66 188	93.75 192	82.23 95	98.44 121	79.40 257	94.79 132	97.48 97

test_fmvs1		87.34 209	87.56 172	86.68 316	90.59 318	71.80 341	94.01 192	94.04 248	78.30 302	91.97 94	95.22 125	56.28 349	93.71 342	92.89 49	94.71 133	94.52 217

xiu_mvs_v1_base_debu		90.64 105	90.05 107	92.40 117	93.97 200	84.46 86	93.32 221	95.46 175	85.17 170	92.25 86	94.03 172	70.59 235	98.57 107	90.97 92	94.67 134	94.18 235

xiu_mvs_v1_base		90.64 105	90.05 107	92.40 117	93.97 200	84.46 86	93.32 221	95.46 175	85.17 170	92.25 86	94.03 172	70.59 235	98.57 107	90.97 92	94.67 134	94.18 235

xiu_mvs_v1_base_debi		90.64 105	90.05 107	92.40 117	93.97 200	84.46 86	93.32 221	95.46 175	85.17 170	92.25 86	94.03 172	70.59 235	98.57 107	90.97 92	94.67 134	94.18 235

gg-mvs-nofinetune		81.77 299	79.37 314	88.99 260	90.85 310	77.73 277	86.29 356	79.63 385	74.88 337	83.19 278	69.05 386	60.34 332	96.11 291	75.46 292	94.64 137	93.11 290

BH-RMVSNet		88.37 171	87.48 174	91.02 183	95.28 133	79.45 232	92.89 242	93.07 269	85.45 166	86.91 180	94.84 144	70.35 240	97.76 174	73.97 305	94.59 138	95.85 165

test_fmvs1_n		87.03 225	87.04 186	86.97 308	89.74 336	71.86 339	94.55 152	94.43 230	78.47 298	91.95 96	95.50 116	51.16 366	93.81 340	93.02 48	94.56 139	95.26 186

diffmvs		91.37 90	91.23 86	91.77 150	93.09 228	80.27 205	92.36 257	95.52 173	87.03 126	91.40 111	94.93 136	80.08 115	97.44 202	92.13 69	94.56 139	97.61 91
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-untuned		88.60 166	88.13 160	90.01 228	95.24 137	78.50 253	93.29 226	94.15 243	84.75 182	84.46 244	93.40 197	75.76 166	97.40 211	77.59 272	94.52 141	94.12 239

Effi-MVS+		91.59 87	91.11 88	93.01 85	94.35 186	83.39 117	94.60 149	95.10 198	87.10 124	90.57 119	93.10 211	81.43 106	98.07 157	89.29 113	94.48 142	97.59 93

PCF-MVS	84.11 10	87.74 188	86.08 223	92.70 104	94.02 194	84.43 89	89.27 322	95.87 145	73.62 348	84.43 246	94.33 161	78.48 139	98.86 84	70.27 323	94.45 143	94.81 205
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EI-MVSNet-Vis-set		93.01 66	92.92 65	93.29 71	95.01 146	83.51 113	94.48 155	95.77 151	90.87 15	92.52 82	96.67 68	84.50 66	99.00 68	91.99 74	94.44 144	97.36 100

MS-PatchMatch		85.05 269	84.16 266	87.73 288	91.42 283	78.51 252	91.25 286	93.53 261	77.50 309	80.15 312	91.58 264	61.99 318	95.51 314	75.69 290	94.35 145	89.16 361

FE-MVS		87.40 207	86.02 225	91.57 157	94.56 174	79.69 227	90.27 299	93.72 259	80.57 271	88.80 144	91.62 262	65.32 296	98.59 106	74.97 299	94.33 146	96.44 141

mvs_anonymous		89.37 143	89.32 125	89.51 248	93.47 218	74.22 315	91.65 279	94.83 216	82.91 223	85.45 218	93.79 188	81.23 108	96.36 282	86.47 150	94.09 147	97.94 74

test_vis1_n		86.56 239	86.49 208	86.78 315	88.51 346	72.69 329	94.68 145	93.78 258	79.55 282	90.70 117	95.31 121	48.75 371	93.28 348	93.15 45	93.99 148	94.38 229

MVP-Stereo		85.97 250	84.86 257	89.32 250	90.92 306	82.19 156	92.11 268	94.19 241	78.76 294	78.77 330	91.63 261	68.38 269	96.56 267	75.01 298	93.95 149	89.20 360
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LFMVS		90.08 115	89.13 129	92.95 90	96.71 77	82.32 155	96.08 61	89.91 347	86.79 132	92.15 90	96.81 63	62.60 315	98.34 129	87.18 140	93.90 150	98.19 58

PVSNet	78.82 18	85.55 257	84.65 261	88.23 279	94.72 163	71.93 338	87.12 351	92.75 277	78.80 293	84.95 234	90.53 293	64.43 302	96.71 255	74.74 300	93.86 151	96.06 158

CNLPA		89.07 151	87.98 163	92.34 121	96.87 74	84.78 76	94.08 185	93.24 265	81.41 259	84.46 244	95.13 132	75.57 171	96.62 259	77.21 276	93.84 152	95.61 178

EPNet_dtu		86.49 244	85.94 230	88.14 281	90.24 326	72.82 327	94.11 181	92.20 291	86.66 137	79.42 324	92.36 233	73.52 200	95.81 305	71.26 317	93.66 153	95.80 169
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GeoE		90.05 116	89.43 121	91.90 143	95.16 140	80.37 204	95.80 78	94.65 226	83.90 196	87.55 167	94.75 147	78.18 142	97.62 187	81.28 225	93.63 154	97.71 88

EI-MVSNet-UG-set		92.74 70	92.62 70	93.12 78	94.86 157	83.20 121	94.40 163	95.74 154	90.71 23	92.05 91	96.60 75	84.00 70	98.99 70	91.55 84	93.63 154	97.17 108

Fast-Effi-MVS+		89.41 139	88.64 142	91.71 152	94.74 161	80.81 193	93.54 213	95.10 198	83.11 217	86.82 186	90.67 291	79.74 120	97.75 177	80.51 240	93.55 156	96.57 138

FA-MVS(test-final)		89.66 128	88.91 135	91.93 138	94.57 173	80.27 205	91.36 283	94.74 222	84.87 178	89.82 130	92.61 226	74.72 182	98.47 114	83.97 180	93.53 157	97.04 117

1314		87.51 202	86.57 204	90.34 213	92.42 249	79.74 226	92.63 249	95.35 188	78.35 301	80.14 313	91.62 262	74.05 192	97.15 231	81.05 227	93.53 157	94.12 239

BH-w/o		87.57 200	87.05 185	89.12 255	94.90 155	77.90 268	92.41 254	93.51 262	82.89 224	83.70 265	91.34 267	75.75 167	97.07 238	75.49 291	93.49 159	92.39 313

PMMVS		85.71 256	84.96 254	87.95 285	88.90 344	77.09 285	88.68 332	90.06 343	72.32 360	86.47 189	90.76 290	72.15 218	94.40 330	81.78 218	93.49 159	92.36 314

PatchMatch-RL		86.77 234	85.54 240	90.47 207	95.88 111	82.71 144	90.54 296	92.31 288	79.82 279	84.32 252	91.57 266	68.77 264	96.39 279	73.16 310	93.48 161	92.32 316

PLC	84.53 7	89.06 152	88.03 162	92.15 128	97.27 68	82.69 145	94.29 171	95.44 180	79.71 280	84.01 259	94.18 169	76.68 156	98.75 93	77.28 275	93.41 162	95.02 193
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VNet		92.24 77	91.91 78	93.24 73	96.59 82	83.43 114	94.84 135	96.44 96	89.19 61	94.08 45	95.90 101	77.85 147	98.17 141	88.90 117	93.38 163	98.13 62

test-LLR		85.87 252	85.41 243	87.25 300	90.95 302	71.67 343	89.55 316	89.88 349	83.41 210	84.54 241	87.95 335	67.25 274	95.11 323	81.82 216	93.37 164	94.97 194

test-mter		84.54 276	83.64 275	87.25 300	90.95 302	71.67 343	89.55 316	89.88 349	79.17 286	84.54 241	87.95 335	55.56 351	95.11 323	81.82 216	93.37 164	94.97 194

EPP-MVSNet		91.70 85	91.56 82	92.13 129	95.88 111	80.50 201	97.33 7	95.25 190	86.15 149	89.76 131	95.60 114	83.42 77	98.32 133	87.37 138	93.25 166	97.56 95

CDS-MVSNet		89.45 136	88.51 147	92.29 125	93.62 214	83.61 111	93.01 238	94.68 225	81.95 242	87.82 161	93.24 205	78.69 134	96.99 243	80.34 242	93.23 167	96.28 147
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPM		86.68 235	85.39 244	90.53 198	93.05 230	79.33 239	89.79 313	94.77 221	78.82 292	81.95 291	93.24 205	76.81 152	97.30 218	66.94 346	93.16 168	94.95 200

alignmvs		93.08 65	92.50 72	94.81 31	95.62 122	87.61 13	95.99 69	96.07 128	89.77 45	94.12 43	94.87 139	80.56 111	98.66 98	92.42 58	93.10 169	98.15 61

thisisatest0515		87.33 210	85.99 226	91.37 166	93.49 217	79.55 229	90.63 295	89.56 354	80.17 274	87.56 166	90.86 284	67.07 278	98.28 135	81.50 223	93.02 170	96.29 146

TAMVS		89.21 145	88.29 156	91.96 136	93.71 210	82.62 148	93.30 225	94.19 241	82.22 235	87.78 162	93.94 180	78.83 131	96.95 245	77.70 271	92.98 171	96.32 144

OMC-MVS		91.23 92	90.62 97	93.08 81	96.27 93	84.07 96	93.52 214	95.93 138	86.95 128	89.51 133	96.13 93	78.50 138	98.35 128	85.84 158	92.90 172	96.83 130

canonicalmvs		93.27 60	92.75 68	94.85 25	95.70 119	87.66 12	96.33 42	96.41 99	90.00 37	94.09 44	94.60 154	82.33 92	98.62 103	92.40 59	92.86 173	98.27 52

TESTMET0.1,1		83.74 286	82.85 285	86.42 319	89.96 332	71.21 347	89.55 316	87.88 359	77.41 310	83.37 274	87.31 343	56.71 347	93.65 344	80.62 238	92.85 174	94.40 228

thisisatest0530		88.67 163	87.61 171	91.86 144	94.87 156	80.07 213	94.63 148	89.90 348	84.00 194	88.46 149	93.78 189	66.88 281	98.46 115	83.30 188	92.65 175	97.06 115

VDD-MVS		90.74 100	89.92 112	93.20 75	96.27 93	83.02 131	95.73 82	93.86 254	88.42 87	92.53 81	96.84 60	62.09 317	98.64 100	90.95 95	92.62 176	97.93 76

test_yl		90.69 102	90.02 110	92.71 102	95.72 117	82.41 153	94.11 181	95.12 196	85.63 161	91.49 108	94.70 148	74.75 179	98.42 124	86.13 153	92.53 177	97.31 101

DCV-MVSNet		90.69 102	90.02 110	92.71 102	95.72 117	82.41 153	94.11 181	95.12 196	85.63 161	91.49 108	94.70 148	74.75 179	98.42 124	86.13 153	92.53 177	97.31 101

VDDNet		89.56 132	88.49 150	92.76 99	95.07 144	82.09 157	96.30 43	93.19 267	81.05 268	91.88 98	96.86 59	61.16 329	98.33 131	88.43 123	92.49 179	97.84 82

DP-MVS		87.25 214	85.36 246	92.90 92	97.65 55	83.24 119	94.81 137	92.00 299	74.99 334	81.92 292	95.00 135	72.66 212	99.05 55	66.92 348	92.33 180	96.40 142

GG-mvs-BLEND				87.94 286	89.73 337	77.91 267	87.80 341	78.23 389		80.58 307	83.86 364	59.88 336	95.33 320	71.20 318	92.22 181	90.60 349

tttt0517		88.61 165	87.78 168	91.11 178	94.96 150	77.81 272	95.35 99	89.69 351	85.09 175	88.05 156	94.59 155	66.93 279	98.48 111	83.27 189	92.13 182	97.03 118

HyFIR lowres test		88.09 179	86.81 191	91.93 138	96.00 105	80.63 197	90.01 310	95.79 150	73.42 350	87.68 164	92.10 245	73.86 196	97.96 165	80.75 235	91.70 183	97.19 107

sss		88.93 156	88.26 158	90.94 189	94.05 193	80.78 194	91.71 276	95.38 184	81.55 257	88.63 146	93.91 184	75.04 176	95.47 318	82.47 202	91.61 184	96.57 138

cascas		86.43 245	84.98 253	90.80 192	92.10 258	80.92 190	90.24 303	95.91 141	73.10 353	83.57 270	88.39 328	65.15 298	97.46 199	84.90 168	91.43 185	94.03 246

Effi-MVS+-dtu		88.65 164	88.35 152	89.54 245	93.33 222	76.39 296	94.47 158	94.36 235	87.70 112	85.43 221	89.56 313	73.45 202	97.26 224	85.57 161	91.28 186	94.97 194

thres100view900		87.63 194	86.71 196	90.38 211	96.12 97	78.55 250	95.03 124	91.58 311	87.15 122	88.06 155	92.29 236	68.91 262	98.10 146	70.13 327	91.10 187	94.48 225

tfpn200view9		87.58 199	86.64 199	90.41 208	95.99 108	78.64 248	94.58 150	91.98 301	86.94 129	88.09 152	91.77 255	69.18 259	98.10 146	70.13 327	91.10 187	94.48 225

thres600view7		87.65 191	86.67 198	90.59 195	96.08 101	78.72 246	94.88 132	91.58 311	87.06 125	88.08 154	92.30 235	68.91 262	98.10 146	70.05 330	91.10 187	94.96 197

thres400		87.62 196	86.64 199	90.57 196	95.99 108	78.64 248	94.58 150	91.98 301	86.94 129	88.09 152	91.77 255	69.18 259	98.10 146	70.13 327	91.10 187	94.96 197

F-COLMAP		87.95 182	86.80 192	91.40 164	96.35 92	80.88 191	94.73 142	95.45 178	79.65 281	82.04 290	94.61 153	71.13 226	98.50 110	76.24 287	91.05 191	94.80 206

thres200		87.21 218	86.24 217	90.12 221	95.36 130	78.53 251	93.26 228	92.10 295	86.42 141	88.00 157	91.11 279	69.24 258	98.00 162	69.58 331	91.04 192	93.83 256

WTY-MVS		89.60 130	88.92 134	91.67 153	95.47 127	81.15 183	92.38 256	94.78 220	83.11 217	89.06 141	94.32 162	78.67 135	96.61 262	81.57 222	90.89 193	97.24 104

HY-MVS	83.01 12	89.03 153	87.94 165	92.29 125	94.86 157	82.77 138	92.08 270	94.49 228	81.52 258	86.93 178	92.79 222	78.32 141	98.23 137	79.93 247	90.55 194	95.88 164

CLD-MVS		89.47 135	88.90 136	91.18 173	94.22 188	82.07 158	92.13 267	96.09 126	87.90 105	85.37 227	92.45 230	74.38 185	97.56 190	87.15 141	90.43 195	93.93 248
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CVMVSNet		84.69 275	84.79 259	84.37 337	91.84 267	64.92 373	93.70 209	91.47 316	66.19 375	86.16 199	95.28 122	67.18 276	93.33 347	80.89 233	90.42 196	94.88 202

SCA		86.32 246	85.18 249	89.73 240	92.15 254	76.60 292	91.12 288	91.69 308	83.53 207	85.50 214	88.81 321	66.79 282	96.48 272	76.65 281	90.35 197	96.12 153

Fast-Effi-MVS+-dtu		87.44 205	86.72 195	89.63 243	92.04 259	77.68 278	94.03 190	93.94 249	85.81 154	82.42 284	91.32 270	70.33 241	97.06 239	80.33 243	90.23 198	94.14 238

OPM-MVS		90.12 114	89.56 117	91.82 147	93.14 226	83.90 100	94.16 178	95.74 154	88.96 71	87.86 158	95.43 119	72.48 215	97.91 169	88.10 128	90.18 199	93.65 269
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		90.60 108	90.19 102	91.82 147	94.70 165	82.73 142	95.85 75	96.22 115	90.81 17	86.91 180	94.86 140	74.23 187	98.12 144	88.15 124	89.99 200	94.63 209

plane_prior5								96.22 115					98.12 144	88.15 124	89.99 200	94.63 209

XVG-OURS		89.40 141	88.70 140	91.52 158	94.06 192	81.46 174	91.27 285	96.07 128	86.14 150	88.89 143	95.77 108	68.73 265	97.26 224	87.39 137	89.96 202	95.83 167

baseline2		86.50 242	85.39 244	89.84 233	91.12 296	76.70 291	91.88 271	88.58 357	82.35 234	79.95 317	90.95 283	73.42 203	97.63 186	80.27 244	89.95 203	95.19 188

Anonymous202405211		87.68 189	86.13 219	92.31 123	96.66 79	80.74 195	94.87 133	91.49 315	80.47 272	89.46 135	95.44 117	54.72 356	98.23 137	82.19 208	89.89 204	97.97 72

plane_prior						82.73 142	95.21 111		89.66 48						89.88 205

SDMVSNet		90.19 113	89.61 116	91.93 138	96.00 105	83.09 128	92.89 242	95.98 134	88.73 76	86.85 184	95.20 128	72.09 219	97.08 236	88.90 117	89.85 206	95.63 176

sd_testset		88.59 167	87.85 167	90.83 190	96.00 105	80.42 203	92.35 258	94.71 223	88.73 76	86.85 184	95.20 128	67.31 272	96.43 277	79.64 251	89.85 206	95.63 176

TR-MVS		86.78 231	85.76 237	89.82 234	94.37 183	78.41 255	92.47 253	92.83 274	81.11 267	86.36 194	92.40 231	68.73 265	97.48 197	73.75 308	89.85 206	93.57 271

HQP3-MVS								96.04 131							89.77 209

HQP-MVS		89.80 126	89.28 127	91.34 167	94.17 189	81.56 168	94.39 165	96.04 131	88.81 72	85.43 221	93.97 179	73.83 197	97.96 165	87.11 143	89.77 209	94.50 222

XVG-OURS-SEG-HR		89.95 121	89.45 119	91.47 162	94.00 198	81.21 182	91.87 272	96.06 130	85.78 155	88.55 147	95.73 110	74.67 183	97.27 222	88.71 120	89.64 211	95.91 162

GA-MVS		86.61 236	85.27 248	90.66 194	91.33 288	78.71 247	90.40 298	93.81 257	85.34 168	85.12 231	89.57 312	61.25 325	97.11 235	80.99 231	89.59 212	96.15 150

1112_ss		88.42 169	87.33 178	91.72 151	94.92 153	80.98 187	92.97 240	94.54 227	78.16 306	83.82 262	93.88 185	78.78 133	97.91 169	79.45 253	89.41 213	96.26 148

ab-mvs		89.41 139	88.35 152	92.60 108	95.15 142	82.65 147	92.20 265	95.60 167	83.97 195	88.55 147	93.70 193	74.16 191	98.21 140	82.46 203	89.37 214	96.94 123

CR-MVSNet		85.35 262	83.76 273	90.12 221	90.58 319	79.34 236	85.24 364	91.96 303	78.27 303	85.55 208	87.87 338	71.03 228	95.61 310	73.96 306	89.36 215	95.40 182

RPMNet		83.95 283	81.53 292	91.21 171	90.58 319	79.34 236	85.24 364	96.76 75	71.44 364	85.55 208	82.97 371	70.87 231	98.91 80	61.01 367	89.36 215	95.40 182

DSMNet-mixed		76.94 336	76.29 335	78.89 356	83.10 377	56.11 392	87.78 342	79.77 384	60.65 381	75.64 349	88.71 324	61.56 322	88.34 379	60.07 370	89.29 217	92.21 319

LPG-MVS_test		89.45 136	88.90 136	91.12 175	94.47 177	81.49 172	95.30 103	96.14 120	86.73 135	85.45 218	95.16 130	69.89 245	98.10 146	87.70 132	89.23 218	93.77 262

LGP-MVS_train				91.12 175	94.47 177	81.49 172		96.14 120	86.73 135	85.45 218	95.16 130	69.89 245	98.10 146	87.70 132	89.23 218	93.77 262

Test_1112_low_res		87.65 191	86.51 206	91.08 179	94.94 152	79.28 240	91.77 274	94.30 237	76.04 324	83.51 271	92.37 232	77.86 146	97.73 178	78.69 261	89.13 220	96.22 149

PatchmatchNet		85.85 253	84.70 260	89.29 251	91.76 271	75.54 305	88.49 334	91.30 319	81.63 255	85.05 232	88.70 325	71.71 220	96.24 286	74.61 302	89.05 221	96.08 156
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
iter_conf_final		89.42 138	88.69 141	91.60 155	95.12 143	82.93 135	95.75 81	92.14 294	87.32 120	87.12 175	94.07 170	67.09 277	97.55 191	90.61 101	89.01 222	94.32 231

iter_conf05		88.85 157	88.08 161	91.17 174	94.27 187	81.64 167	95.18 113	92.15 293	86.23 147	87.28 172	94.07 170	63.89 308	97.55 191	90.63 100	89.00 223	94.32 231

MDTV_nov1_ep13			83.56 276		91.69 276	69.93 357	87.75 344	91.54 313	78.60 297	84.86 235	88.90 320	69.54 250	96.03 293	70.25 324	88.93 224

MIMVSNet		82.59 293	80.53 298	88.76 263	91.51 279	78.32 258	86.57 355	90.13 341	79.32 283	80.70 305	88.69 326	52.98 363	93.07 352	66.03 351	88.86 225	94.90 201

ACMM	84.12 9	89.14 146	88.48 151	91.12 175	94.65 168	81.22 181	95.31 101	96.12 123	85.31 169	85.92 201	94.34 160	70.19 243	98.06 158	85.65 159	88.86 225	94.08 243
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvsmamba		89.96 120	89.50 118	91.33 168	92.90 238	81.82 163	96.68 33	92.37 285	89.03 67	87.00 176	94.85 142	73.05 207	97.65 182	91.03 91	88.63 227	94.51 219

ACMP	84.23 8	89.01 155	88.35 152	90.99 186	94.73 162	81.27 178	95.07 121	95.89 144	86.48 139	83.67 266	94.30 163	69.33 254	97.99 163	87.10 145	88.55 228	93.72 266
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		89.03 153	88.64 142	90.21 215	90.74 314	79.28 240	95.96 71	95.90 142	84.66 185	85.33 229	92.94 215	74.02 193	97.30 218	89.64 109	88.53 229	94.05 245

jajsoiax		88.24 175	87.50 173	90.48 204	90.89 308	80.14 210	95.31 101	95.65 164	84.97 177	84.24 255	94.02 175	65.31 297	97.42 204	88.56 121	88.52 230	93.89 249

PatchT		82.68 292	81.27 294	86.89 312	90.09 329	70.94 351	84.06 371	90.15 340	74.91 335	85.63 207	83.57 366	69.37 252	94.87 327	65.19 353	88.50 231	94.84 203

MSDG		84.86 272	83.09 281	90.14 220	93.80 206	80.05 215	89.18 325	93.09 268	78.89 290	78.19 331	91.91 252	65.86 295	97.27 222	68.47 336	88.45 232	93.11 290

MVS-HIRNet		73.70 341	72.20 344	78.18 359	91.81 270	56.42 391	82.94 377	82.58 378	55.24 383	68.88 373	66.48 387	55.32 353	95.13 322	58.12 374	88.42 233	83.01 376

mvs_tets		88.06 181	87.28 180	90.38 211	90.94 304	79.88 222	95.22 110	95.66 162	85.10 174	84.21 256	93.94 180	63.53 309	97.40 211	88.50 122	88.40 234	93.87 252

ET-MVSNet_ETH3D		87.51 202	85.91 231	92.32 122	93.70 212	83.93 99	92.33 260	90.94 328	84.16 190	72.09 365	92.52 228	69.90 244	95.85 302	89.20 114	88.36 235	97.17 108

FIs		90.51 109	90.35 99	90.99 186	93.99 199	80.98 187	95.73 82	97.54 4	89.15 62	86.72 187	94.68 150	81.83 104	97.24 226	85.18 163	88.31 236	94.76 207

PS-MVSNAJss		89.97 119	89.62 115	91.02 183	91.90 265	80.85 192	95.26 108	95.98 134	86.26 145	86.21 197	94.29 164	79.70 121	97.65 182	88.87 119	88.10 237	94.57 214

CMPMVS	59.16 21	80.52 314	79.20 318	84.48 336	83.98 374	67.63 366	89.95 312	93.84 256	64.79 377	66.81 376	91.14 278	57.93 344	95.17 321	76.25 286	88.10 237	90.65 346
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FC-MVSNet-test		90.27 111	90.18 103	90.53 198	93.71 210	79.85 224	95.77 80	97.59 3	89.31 56	86.27 196	94.67 151	81.93 103	97.01 242	84.26 176	88.09 239	94.71 208

ACMMP++															88.01 240

D2MVS		85.90 251	85.09 251	88.35 274	90.79 311	77.42 281	91.83 273	95.70 158	80.77 270	80.08 315	90.02 303	66.74 284	96.37 280	81.88 215	87.97 241	91.26 337

UniMVSNet_ETH3D		87.53 201	86.37 210	91.00 185	92.44 248	78.96 245	94.74 141	95.61 166	84.07 193	85.36 228	94.52 157	59.78 337	97.34 216	82.93 193	87.88 242	96.71 134

PVSNet_BlendedMVS		89.98 118	89.70 114	90.82 191	96.12 97	81.25 179	93.92 199	96.83 66	83.49 208	89.10 139	92.26 237	81.04 109	98.85 86	86.72 148	87.86 243	92.35 315

Syy-MVS		80.07 319	79.78 308	80.94 352	91.92 263	59.93 383	89.75 314	87.40 364	81.72 251	78.82 327	87.20 345	66.29 290	91.29 366	47.06 384	87.84 244	91.60 329

myMVS_eth3d		79.67 324	78.79 323	82.32 350	91.92 263	64.08 375	89.75 314	87.40 364	81.72 251	78.82 327	87.20 345	45.33 377	91.29 366	59.09 373	87.84 244	91.60 329

bld_raw_dy_0_64		87.60 198	86.73 194	90.21 215	91.72 272	80.26 207	95.09 120	88.61 356	85.68 159	85.55 208	94.38 159	63.93 307	96.66 256	87.73 131	87.84 244	93.72 266

anonymousdsp		87.84 184	87.09 183	90.12 221	89.13 341	80.54 200	94.67 146	95.55 169	82.05 238	83.82 262	92.12 242	71.47 224	97.15 231	87.15 141	87.80 247	92.67 303

testing3		80.46 315	79.59 313	83.06 345	93.44 220	64.64 374	93.33 220	85.47 369	84.34 189	79.93 318	90.84 286	44.35 379	92.39 356	57.06 377	87.56 248	92.16 320

Anonymous20240529		88.09 179	86.59 203	92.58 110	96.53 86	81.92 162	95.99 69	95.84 147	74.11 343	89.06 141	95.21 127	61.44 323	98.81 89	83.67 186	87.47 249	97.01 119

ACMMP++_ref															87.47 249

XVG-ACMP-BASELINE		86.00 249	84.84 258	89.45 249	91.20 290	78.00 265	91.70 277	95.55 169	85.05 176	82.97 279	92.25 238	54.49 357	97.48 197	82.93 193	87.45 251	92.89 298

EI-MVSNet		89.10 147	88.86 138	89.80 237	91.84 267	78.30 259	93.70 209	95.01 201	85.73 157	87.15 173	95.28 122	79.87 118	97.21 229	83.81 183	87.36 252	93.88 251

MVSTER		88.84 158	88.29 156	90.51 201	92.95 236	80.44 202	93.73 206	95.01 201	84.66 185	87.15 173	93.12 210	72.79 211	97.21 229	87.86 129	87.36 252	93.87 252

EG-PatchMatch MVS		82.37 295	80.34 301	88.46 271	90.27 325	79.35 235	92.80 246	94.33 236	77.14 314	73.26 362	90.18 299	47.47 374	96.72 253	70.25 324	87.32 254	89.30 358

EPMVS		83.90 285	82.70 287	87.51 292	90.23 327	72.67 330	88.62 333	81.96 380	81.37 260	85.01 233	88.34 329	66.31 289	94.45 328	75.30 294	87.12 255	95.43 181

tpm2		84.08 280	82.94 283	87.48 295	91.39 284	71.27 345	89.23 324	90.37 336	71.95 362	84.64 238	89.33 314	67.30 273	96.55 269	75.17 295	87.09 256	94.63 209

CostFormer		85.77 255	84.94 255	88.26 277	91.16 294	72.58 335	89.47 320	91.04 326	76.26 322	86.45 192	89.97 305	70.74 233	96.86 251	82.35 205	87.07 257	95.34 185

Patchmatch-test		81.37 307	79.30 315	87.58 291	90.92 306	74.16 317	80.99 380	87.68 362	70.52 368	76.63 343	88.81 321	71.21 225	92.76 354	60.01 371	86.93 258	95.83 167

RRT_MVS		89.09 149	88.62 145	90.49 202	92.85 239	79.65 228	96.41 39	94.41 232	88.22 94	85.50 214	94.77 146	69.36 253	97.31 217	89.33 112	86.73 259	94.51 219

mvsany_test1		85.42 260	85.30 247	85.77 326	87.95 357	75.41 307	87.61 348	80.97 382	76.82 316	88.68 145	95.83 104	77.44 148	90.82 370	85.90 156	86.51 260	91.08 344

test_fmvs2		83.98 281	84.03 268	83.83 342	87.16 360	67.53 367	93.93 198	92.89 272	77.62 308	86.89 183	93.53 195	47.18 375	92.02 360	90.54 102	86.51 260	91.93 323

LTVRE_ROB	82.13 13	86.26 247	84.90 256	90.34 213	94.44 181	81.50 170	92.31 262	94.89 210	83.03 219	79.63 322	92.67 223	69.69 248	97.79 172	71.20 318	86.26 262	91.72 326
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
COLMAP_ROB	80.39 16	83.96 282	82.04 289	89.74 238	95.28 133	79.75 225	94.25 173	92.28 289	75.17 332	78.02 334	93.77 190	58.60 342	97.84 171	65.06 356	85.92 263	91.63 328
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RPSCF		85.07 268	84.27 265	87.48 295	92.91 237	70.62 353	91.69 278	92.46 283	76.20 323	82.67 283	95.22 125	63.94 305	97.29 221	77.51 274	85.80 264	94.53 216

USDC		82.76 290	81.26 295	87.26 299	91.17 292	74.55 311	89.27 322	93.39 264	78.26 304	75.30 351	92.08 246	54.43 358	96.63 258	71.64 315	85.79 265	90.61 347

dmvs_re		84.20 279	83.22 280	87.14 306	91.83 269	77.81 272	90.04 309	90.19 339	84.70 184	81.49 294	89.17 316	64.37 303	91.13 368	71.58 316	85.65 266	92.46 310

GBi-Net		87.26 212	85.98 227	91.08 179	94.01 195	83.10 125	95.14 117	94.94 204	83.57 204	84.37 247	91.64 258	66.59 286	96.34 283	78.23 266	85.36 267	93.79 257

test1		87.26 212	85.98 227	91.08 179	94.01 195	83.10 125	95.14 117	94.94 204	83.57 204	84.37 247	91.64 258	66.59 286	96.34 283	78.23 266	85.36 267	93.79 257

FMVSNet3		87.40 207	86.11 221	91.30 169	93.79 208	83.64 108	94.20 177	94.81 218	83.89 197	84.37 247	91.87 254	68.45 268	96.56 267	78.23 266	85.36 267	93.70 268

FMVSNet2		87.19 220	85.82 233	91.30 169	94.01 195	83.67 106	94.79 138	94.94 204	83.57 204	83.88 261	92.05 249	66.59 286	96.51 270	77.56 273	85.01 270	93.73 265

ACMH	80.38 17	85.36 261	83.68 274	90.39 209	94.45 180	80.63 197	94.73 142	94.85 214	82.09 237	77.24 338	92.65 224	60.01 335	97.58 188	72.25 314	84.87 271	92.96 295
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ITE_SJBPF				88.24 278	91.88 266	77.05 286		92.92 271	85.54 164	80.13 314	93.30 202	57.29 346	96.20 287	72.46 313	84.71 272	91.49 332

JIA-IIPM		81.04 310	78.98 322	87.25 300	88.64 345	73.48 322	81.75 379	89.61 353	73.19 352	82.05 289	73.71 383	66.07 294	95.87 301	71.18 320	84.60 273	92.41 312

tt0805		86.92 227	85.74 239	90.48 204	92.22 252	79.98 220	95.63 91	94.88 212	83.83 199	84.74 237	92.80 221	57.61 345	97.67 179	85.48 162	84.42 274	93.79 257

OpenMVS_ROB	74.94 19	79.51 325	77.03 332	86.93 309	87.00 361	76.23 299	92.33 260	90.74 333	68.93 371	74.52 356	88.23 332	49.58 369	96.62 259	57.64 375	84.29 275	87.94 370

AllTest		83.42 287	81.39 293	89.52 246	95.01 146	77.79 274	93.12 232	90.89 330	77.41 310	76.12 346	93.34 198	54.08 359	97.51 195	68.31 338	84.27 276	93.26 281

TestCases				89.52 246	95.01 146	77.79 274		90.89 330	77.41 310	76.12 346	93.34 198	54.08 359	97.51 195	68.31 338	84.27 276	93.26 281

tpm		84.73 273	84.02 269	86.87 313	90.33 324	68.90 360	89.06 327	89.94 346	80.85 269	85.75 203	89.86 307	68.54 267	95.97 296	77.76 270	84.05 278	95.75 170

FMVSNet1		85.85 253	84.11 267	91.08 179	92.81 240	83.10 125	95.14 117	94.94 204	81.64 254	82.68 282	91.64 258	59.01 341	96.34 283	75.37 293	83.78 279	93.79 257

ADS-MVSNet2		81.66 302	79.71 311	87.50 293	91.35 286	74.19 316	83.33 374	88.48 358	72.90 355	82.24 287	85.77 357	64.98 299	93.20 350	64.57 357	83.74 280	95.12 190

ADS-MVSNet		81.56 304	79.78 308	86.90 311	91.35 286	71.82 340	83.33 374	89.16 355	72.90 355	82.24 287	85.77 357	64.98 299	93.76 341	64.57 357	83.74 280	95.12 190

XXY-MVS		87.65 191	86.85 190	90.03 225	92.14 255	80.60 199	93.76 205	95.23 191	82.94 222	84.60 239	94.02 175	74.27 186	95.49 317	81.04 228	83.68 282	94.01 247

test_0402		81.30 309	79.17 319	87.67 289	93.19 225	78.17 262	92.98 239	91.71 306	75.25 331	76.02 348	90.31 297	59.23 339	96.37 280	50.22 382	83.63 283	88.47 367

tpmvs		83.35 289	82.07 288	87.20 304	91.07 298	71.00 350	88.31 337	91.70 307	78.91 289	80.49 309	87.18 347	69.30 257	97.08 236	68.12 341	83.56 284	93.51 275

pmmvs5		84.21 278	82.84 286	88.34 275	88.95 343	76.94 287	92.41 254	91.91 305	75.63 327	80.28 310	91.18 275	64.59 301	95.57 311	77.09 279	83.47 285	92.53 307

pmmvs4		85.43 259	83.86 272	90.16 218	90.02 331	82.97 134	90.27 299	92.67 280	75.93 325	80.73 304	91.74 257	71.05 227	95.73 309	78.85 260	83.46 286	91.78 325

test0.0.03 1		82.41 294	81.69 290	84.59 335	88.23 352	72.89 326	90.24 303	87.83 360	83.41 210	79.86 319	89.78 309	67.25 274	88.99 378	65.18 354	83.42 287	91.90 324

tpmrst		85.35 262	84.99 252	86.43 318	90.88 309	67.88 364	88.71 331	91.43 317	80.13 275	86.08 200	88.80 323	73.05 207	96.02 294	82.48 201	83.40 288	95.40 182

nrg030		91.08 96	90.39 98	93.17 76	93.07 229	86.91 21	96.41 39	96.26 110	88.30 90	88.37 151	94.85 142	82.19 97	97.64 185	91.09 89	82.95 289	94.96 197

cl22		86.78 231	85.98 227	89.18 254	92.34 250	77.62 279	90.84 292	94.13 245	81.33 261	83.97 260	90.15 300	73.96 194	96.60 264	84.19 177	82.94 290	93.33 279

miper_ehance_all_eth		87.22 217	86.62 202	89.02 259	92.13 256	77.40 282	90.91 291	94.81 218	81.28 262	84.32 252	90.08 302	79.26 127	96.62 259	83.81 183	82.94 290	93.04 293

miper_enhance_ethall		86.90 228	86.18 218	89.06 257	91.66 277	77.58 280	90.22 305	94.82 217	79.16 287	84.48 243	89.10 317	79.19 129	96.66 256	84.06 178	82.94 290	92.94 296

ACMH+	81.04 14	85.05 269	83.46 277	89.82 234	94.66 167	79.37 234	94.44 160	94.12 246	82.19 236	78.04 333	92.82 219	58.23 343	97.54 193	73.77 307	82.90 293	92.54 306

VPA-MVSNet		89.62 129	88.96 132	91.60 155	93.86 203	82.89 137	95.46 96	97.33 25	87.91 104	88.43 150	93.31 201	74.17 190	97.40 211	87.32 139	82.86 294	94.52 217

IterMVS-LS		88.36 172	87.91 166	89.70 241	93.80 206	78.29 260	93.73 206	95.08 200	85.73 157	84.75 236	91.90 253	79.88 117	96.92 247	83.83 182	82.51 295	93.89 249
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testgi		80.94 313	80.20 304	83.18 343	87.96 356	66.29 368	91.28 284	90.70 334	83.70 201	78.12 332	92.84 217	51.37 365	90.82 370	63.34 360	82.46 296	92.43 311

test_vis1_rt		77.96 333	76.46 333	82.48 348	85.89 367	71.74 342	90.25 301	78.89 386	71.03 367	71.30 369	81.35 375	42.49 381	91.05 369	84.55 173	82.37 297	84.65 373

WR-MVS		88.38 170	87.67 170	90.52 200	93.30 223	80.18 208	93.26 228	95.96 137	88.57 83	85.47 217	92.81 220	76.12 159	96.91 248	81.24 226	82.29 298	94.47 227

tpm cat1		81.96 296	80.27 302	87.01 307	91.09 297	71.02 349	87.38 349	91.53 314	66.25 374	80.17 311	86.35 353	68.22 270	96.15 290	69.16 332	82.29 298	93.86 254

v1192		87.25 214	86.33 212	90.00 229	90.76 313	79.04 244	93.80 203	95.48 174	82.57 229	85.48 216	91.18 275	73.38 205	97.42 204	82.30 206	82.06 300	93.53 272

v1144		87.61 197	86.79 193	90.06 224	91.01 299	79.34 236	93.95 196	95.42 183	83.36 212	85.66 206	91.31 271	74.98 177	97.42 204	83.37 187	82.06 300	93.42 278

v1240		86.78 231	85.85 232	89.56 244	90.45 323	77.79 274	93.61 211	95.37 186	81.65 253	85.43 221	91.15 277	71.50 223	97.43 203	81.47 224	82.05 302	93.47 276

Anonymous20231206		81.03 311	79.77 310	84.82 334	87.85 358	70.26 355	91.42 282	92.08 296	73.67 347	77.75 335	89.25 315	62.43 316	93.08 351	61.50 366	82.00 303	91.12 341

V42		87.68 189	86.86 189	90.15 219	90.58 319	80.14 210	94.24 175	95.28 189	83.66 202	85.67 205	91.33 268	74.73 181	97.41 209	84.43 175	81.83 304	92.89 298

v1921920		86.97 226	86.06 224	89.69 242	90.53 322	78.11 264	93.80 203	95.43 181	81.90 245	85.33 229	91.05 281	72.66 212	97.41 209	82.05 211	81.80 305	93.53 272

v2v482		87.84 184	87.06 184	90.17 217	90.99 300	79.23 243	94.00 194	95.13 195	84.87 178	85.53 211	92.07 248	74.45 184	97.45 200	84.71 171	81.75 306	93.85 255

Anonymous20231211		86.59 238	85.13 250	90.98 188	96.52 87	81.50 170	96.14 57	96.16 119	73.78 346	83.65 267	92.15 240	63.26 312	97.37 215	82.82 197	81.74 307	94.06 244

v144192		87.19 220	86.35 211	89.74 238	90.64 317	78.24 261	93.92 199	95.43 181	81.93 243	85.51 213	91.05 281	74.21 189	97.45 200	82.86 195	81.56 308	93.53 272

cl____		86.52 241	85.78 234	88.75 264	92.03 260	76.46 294	90.74 293	94.30 237	81.83 249	83.34 275	90.78 289	75.74 169	96.57 265	81.74 219	81.54 309	93.22 285

DIV-MVS_self_test		86.53 240	85.78 234	88.75 264	92.02 261	76.45 295	90.74 293	94.30 237	81.83 249	83.34 275	90.82 287	75.75 167	96.57 265	81.73 220	81.52 310	93.24 284

Anonymous20240521		80.44 316	79.21 317	84.11 340	85.75 369	67.89 363	92.86 244	93.23 266	75.61 328	75.59 350	87.47 342	50.03 367	94.33 332	71.14 321	81.21 311	90.12 352

OurMVSNet-221017-0		85.35 262	84.64 262	87.49 294	90.77 312	72.59 334	94.01 192	94.40 233	84.72 183	79.62 323	93.17 207	61.91 319	96.72 253	81.99 212	81.16 312	93.16 288

FMVSNet5		81.52 305	79.60 312	87.27 298	91.17 292	77.95 266	91.49 281	92.26 290	76.87 315	76.16 345	87.91 337	51.67 364	92.34 357	67.74 342	81.16 312	91.52 331

CP-MVSNet		87.63 194	87.26 182	88.74 266	93.12 227	76.59 293	95.29 105	96.58 91	88.43 86	83.49 272	92.98 214	75.28 173	95.83 303	78.97 259	81.15 314	93.79 257

c3_l		87.14 222	86.50 207	89.04 258	92.20 253	77.26 283	91.22 287	94.70 224	82.01 241	84.34 251	90.43 295	78.81 132	96.61 262	83.70 185	81.09 315	93.25 283

IterMVS-SCA-FT		85.45 258	84.53 264	88.18 280	91.71 274	76.87 288	90.19 306	92.65 281	85.40 167	81.44 296	90.54 292	66.79 282	95.00 326	81.04 228	81.05 316	92.66 304

TinyColmap		79.76 323	77.69 326	85.97 322	91.71 274	73.12 324	89.55 316	90.36 337	75.03 333	72.03 366	90.19 298	46.22 376	96.19 289	63.11 361	81.03 317	88.59 366

UniMVSNet_NR-MVSNet		89.92 123	89.29 126	91.81 149	93.39 221	83.72 104	94.43 161	97.12 41	89.80 41	86.46 190	93.32 200	83.16 79	97.23 227	84.92 166	81.02 318	94.49 224

DU-MVS		89.34 144	88.50 148	91.85 146	93.04 231	83.72 104	94.47 158	96.59 90	89.50 50	86.46 190	93.29 203	77.25 149	97.23 227	84.92 166	81.02 318	94.59 212

PS-CasMVS		87.32 211	86.88 188	88.63 269	92.99 234	76.33 298	95.33 100	96.61 89	88.22 94	83.30 277	93.07 212	73.03 209	95.79 306	78.36 263	81.00 320	93.75 264

IterMVS		84.88 271	83.98 271	87.60 290	91.44 280	76.03 300	90.18 307	92.41 284	83.24 215	81.06 302	90.42 296	66.60 285	94.28 334	79.46 252	80.98 321	92.48 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet (Re)		89.80 126	89.07 130	92.01 130	93.60 215	84.52 83	94.78 139	97.47 11	89.26 58	86.44 193	92.32 234	82.10 98	97.39 214	84.81 169	80.84 322	94.12 239

LF4IMVS		80.37 317	79.07 321	84.27 339	86.64 362	69.87 358	89.39 321	91.05 325	76.38 319	74.97 353	90.00 304	47.85 373	94.25 335	74.55 303	80.82 323	88.69 365

v10		87.25 214	86.38 209	89.85 232	91.19 291	79.50 230	94.48 155	95.45 178	83.79 200	83.62 268	91.19 273	75.13 174	97.42 204	81.94 213	80.60 324	92.63 305

tfpnnormal		84.72 274	83.23 279	89.20 253	92.79 241	80.05 215	94.48 155	95.81 148	82.38 232	81.08 301	91.21 272	69.01 261	96.95 245	61.69 365	80.59 325	90.58 350

WR-MVS_H		87.80 186	87.37 177	89.10 256	93.23 224	78.12 263	95.61 92	97.30 29	87.90 105	83.72 264	92.01 250	79.65 125	96.01 295	76.36 284	80.54 326	93.16 288

VPNet		88.20 176	87.47 175	90.39 209	93.56 216	79.46 231	94.04 189	95.54 171	88.67 79	86.96 177	94.58 156	69.33 254	97.15 231	84.05 179	80.53 327	94.56 215

v7n		86.81 229	85.76 237	89.95 230	90.72 315	79.25 242	95.07 121	95.92 139	84.45 188	82.29 285	90.86 284	72.60 214	97.53 194	79.42 256	80.52 328	93.08 292

v8		87.50 204	86.71 196	89.89 231	91.37 285	79.40 233	94.50 154	95.38 184	84.81 181	83.60 269	91.33 268	76.05 160	97.42 204	82.84 196	80.51 329	92.84 300

EU-MVSNet		81.32 308	80.95 296	82.42 349	88.50 348	63.67 377	93.32 221	91.33 318	64.02 378	80.57 308	92.83 218	61.21 327	92.27 358	76.34 285	80.38 330	91.32 335

Patchmtry		82.71 291	80.93 297	88.06 282	90.05 330	76.37 297	84.74 369	91.96 303	72.28 361	81.32 299	87.87 338	71.03 228	95.50 316	68.97 333	80.15 331	92.32 316

NR-MVSNet		88.58 168	87.47 175	91.93 138	93.04 231	84.16 95	94.77 140	96.25 112	89.05 65	80.04 316	93.29 203	79.02 130	97.05 240	81.71 221	80.05 332	94.59 212

Baseline_NR-MVSNet		87.07 223	86.63 201	88.40 272	91.44 280	77.87 270	94.23 176	92.57 282	84.12 192	85.74 204	92.08 246	77.25 149	96.04 292	82.29 207	79.94 333	91.30 336

dp		81.47 306	80.23 303	85.17 332	89.92 333	65.49 371	86.74 353	90.10 342	76.30 321	81.10 300	87.12 348	62.81 314	95.92 298	68.13 340	79.88 334	94.09 242

TranMVSNet+NR-MVSNet		88.84 158	87.95 164	91.49 160	92.68 243	83.01 132	94.92 130	96.31 104	89.88 39	85.53 211	93.85 187	76.63 157	96.96 244	81.91 214	79.87 335	94.50 222

miper_lstm_enhance		85.27 265	84.59 263	87.31 297	91.28 289	74.63 310	87.69 345	94.09 247	81.20 266	81.36 298	89.85 308	74.97 178	94.30 333	81.03 230	79.84 336	93.01 294

v148		87.04 224	86.32 213	89.21 252	90.94 304	77.26 283	93.71 208	94.43 230	84.84 180	84.36 250	90.80 288	76.04 161	97.05 240	82.12 209	79.60 337	93.31 280

IB-MVS	80.51 15	85.24 266	83.26 278	91.19 172	92.13 256	79.86 223	91.75 275	91.29 320	83.28 214	80.66 306	88.49 327	61.28 324	98.46 115	80.99 231	79.46 338	95.25 187
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
eth_miper_zixun_eth		86.50 242	85.77 236	88.68 267	91.94 262	75.81 303	90.47 297	94.89 210	82.05 238	84.05 257	90.46 294	75.96 162	96.77 252	82.76 199	79.36 339	93.46 277

baseline1		88.10 178	87.28 180	90.57 196	94.96 150	80.07 213	94.27 172	91.29 320	86.74 134	87.41 168	94.00 177	76.77 154	96.20 287	80.77 234	79.31 340	95.44 180

our_test_3		81.93 297	80.46 300	86.33 320	88.46 349	73.48 322	88.46 335	91.11 322	76.46 317	76.69 342	88.25 331	66.89 280	94.36 331	68.75 334	79.08 341	91.14 340

PEN-MVS		86.80 230	86.27 216	88.40 272	92.32 251	75.71 304	95.18 113	96.38 101	87.97 102	82.82 281	93.15 208	73.39 204	95.92 298	76.15 288	79.03 342	93.59 270

pm-mvs1		86.61 236	85.54 240	89.82 234	91.44 280	80.18 208	95.28 107	94.85 214	83.84 198	81.66 293	92.62 225	72.45 217	96.48 272	79.67 250	78.06 343	92.82 301

h-mvs33		90.80 98	90.15 104	92.75 100	96.01 104	82.66 146	95.43 97	95.53 172	89.80 41	93.08 63	95.64 113	75.77 164	99.00 68	92.07 70	78.05 344	96.60 136

SixPastTwentyTwo		83.91 284	82.90 284	86.92 310	90.99 300	70.67 352	93.48 215	91.99 300	85.54 164	77.62 337	92.11 244	60.59 331	96.87 250	76.05 289	77.75 345	93.20 286

ppachtmachnet_test		81.84 298	80.07 306	87.15 305	88.46 349	74.43 314	89.04 328	92.16 292	75.33 330	77.75 335	88.99 318	66.20 291	95.37 319	65.12 355	77.60 346	91.65 327

MIMVSNet1		79.38 326	77.28 328	85.69 327	86.35 363	73.67 319	91.61 280	92.75 277	78.11 307	72.64 364	88.12 333	48.16 372	91.97 362	60.32 368	77.49 347	91.43 334

DTE-MVSNet		86.11 248	85.48 242	87.98 284	91.65 278	74.92 309	94.93 129	95.75 153	87.36 119	82.26 286	93.04 213	72.85 210	95.82 304	74.04 304	77.46 348	93.20 286

N_pmnet		68.89 346	68.44 348	70.23 367	89.07 342	28.79 404	88.06 338	19.50 404	69.47 370	71.86 367	84.93 360	61.24 326	91.75 363	54.70 379	77.15 349	90.15 351

AUN-MVS		87.78 187	86.54 205	91.48 161	94.82 160	81.05 185	93.91 201	93.93 250	83.00 220	86.93 178	93.53 195	69.50 251	97.67 179	86.14 151	77.12 350	95.73 173

hse-mvs2		89.88 125	89.34 124	91.51 159	94.83 159	81.12 184	93.94 197	93.91 253	89.80 41	93.08 63	93.60 194	75.77 164	97.66 181	92.07 70	77.07 351	95.74 171

dmvs_testset		74.57 340	75.81 339	70.86 366	87.72 359	40.47 399	87.05 352	77.90 391	82.75 226	71.15 370	85.47 359	67.98 271	84.12 388	45.26 385	76.98 352	88.00 369

test20.03		79.95 321	79.08 320	82.55 347	85.79 368	67.74 365	91.09 289	91.08 323	81.23 265	74.48 357	89.96 306	61.63 320	90.15 372	60.08 369	76.38 353	89.76 353

FPMVS		64.63 351	62.55 353	70.88 365	70.80 391	56.71 387	84.42 370	84.42 373	51.78 386	49.57 386	81.61 374	23.49 391	81.48 391	40.61 391	76.25 354	74.46 384

test_fmvs3		77.67 334	77.16 331	79.22 355	79.52 384	61.14 381	92.34 259	91.64 310	73.98 344	78.86 326	86.59 349	27.38 389	87.03 380	88.12 127	75.97 355	89.50 355

EGC-MVSNET		61.97 352	56.37 356	78.77 357	89.63 338	73.50 321	89.12 326	82.79 377	0.21 401	1.24 402	84.80 361	39.48 382	90.04 373	44.13 386	75.94 356	72.79 385

pmmvs6		83.42 287	81.60 291	88.87 261	88.01 355	77.87 270	94.96 127	94.24 240	74.67 338	78.80 329	91.09 280	60.17 334	96.49 271	77.06 280	75.40 357	92.23 318

new_pmnet		72.15 342	70.13 346	78.20 358	82.95 378	65.68 369	83.91 372	82.40 379	62.94 380	64.47 377	79.82 377	42.85 380	86.26 384	57.41 376	74.44 358	82.65 378

MDA-MVSNet_test_wron		79.21 328	77.19 330	85.29 330	88.22 353	72.77 328	85.87 358	90.06 343	74.34 340	62.62 380	87.56 341	66.14 292	91.99 361	66.90 349	73.01 359	91.10 343

YYNet1		79.22 327	77.20 329	85.28 331	88.20 354	72.66 331	85.87 358	90.05 345	74.33 341	62.70 378	87.61 340	66.09 293	92.03 359	66.94 346	72.97 360	91.15 339

Patchmatch-RL test		81.67 301	79.96 307	86.81 314	85.42 371	71.23 346	82.17 378	87.50 363	78.47 298	77.19 339	82.50 373	70.81 232	93.48 345	82.66 200	72.89 361	95.71 174

pmmvs-eth3d		80.97 312	78.72 324	87.74 287	84.99 373	79.97 221	90.11 308	91.65 309	75.36 329	73.51 360	86.03 354	59.45 338	93.96 339	75.17 295	72.21 362	89.29 359

PM-MVS		78.11 332	76.12 336	84.09 341	83.54 376	70.08 356	88.97 329	85.27 371	79.93 277	74.73 355	86.43 351	34.70 385	93.48 345	79.43 255	72.06 363	88.72 364

test_f		71.95 343	70.87 345	75.21 362	74.21 389	59.37 385	85.07 366	85.82 367	65.25 376	70.42 371	83.13 368	23.62 390	82.93 390	78.32 264	71.94 364	83.33 375

Gipuma		57.99 357	54.91 359	67.24 373	88.51 346	65.59 370	52.21 392	90.33 338	43.58 389	42.84 392	51.18 393	20.29 395	85.07 385	34.77 392	70.45 365	51.05 392
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD_test1		69.04 345	66.26 351	77.36 361	80.51 382	62.79 380	85.46 363	83.51 376	54.11 385	59.14 383	84.79 362	23.40 392	89.61 374	55.22 378	70.24 366	79.68 382

K. test v3		81.59 303	80.15 305	85.91 325	89.89 334	69.42 359	92.57 251	87.71 361	85.56 163	73.44 361	89.71 310	55.58 350	95.52 313	77.17 277	69.76 367	92.78 302

KD-MVS_self_test		80.20 318	79.24 316	83.07 344	85.64 370	65.29 372	91.01 290	93.93 250	78.71 296	76.32 344	86.40 352	59.20 340	92.93 353	72.59 312	69.35 368	91.00 345

CL-MVSNet_self_test		81.74 300	80.53 298	85.36 329	85.96 366	72.45 336	90.25 301	93.07 269	81.24 264	79.85 320	87.29 344	70.93 230	92.52 355	66.95 345	69.23 369	91.11 342

TDRefinement		79.81 322	77.34 327	87.22 303	79.24 385	75.48 306	93.12 232	92.03 298	76.45 318	75.01 352	91.58 264	49.19 370	96.44 276	70.22 326	69.18 370	89.75 354

MDA-MVSNet-bldmvs		78.85 329	76.31 334	86.46 317	89.76 335	73.88 318	88.79 330	90.42 335	79.16 287	59.18 382	88.33 330	60.20 333	94.04 336	62.00 364	68.96 371	91.48 333

ambc				83.06 345	79.99 383	63.51 378	77.47 385	92.86 273		74.34 358	84.45 363	28.74 386	95.06 325	73.06 311	68.89 372	90.61 347

TransMVSNet (Re)		84.43 277	83.06 282	88.54 270	91.72 272	78.44 254	95.18 113	92.82 275	82.73 227	79.67 321	92.12 242	73.49 201	95.96 297	71.10 322	68.73 373	91.21 338

mvsany_test3		74.95 339	73.26 343	80.02 354	74.61 387	63.16 379	85.53 362	78.42 387	74.16 342	74.89 354	86.46 350	36.02 384	89.09 377	82.39 204	66.91 374	87.82 371

PMVS	47.18 22	52.22 358	48.46 362	63.48 374	45.72 402	46.20 397	73.41 388	78.31 388	41.03 392	30.06 395	65.68 388	6.05 402	83.43 389	30.04 393	65.86 375	60.80 389
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		65.12 350	62.60 352	72.69 364	71.44 390	60.71 382	87.17 350	65.55 397	63.80 379	53.22 385	65.65 389	14.54 399	89.44 376	76.65 281	65.38 376	67.91 388

lessismore_v0				86.04 321	88.46 349	68.78 361		80.59 383		73.01 363	90.11 301	55.39 352	96.43 277	75.06 297	65.06 377	92.90 297

new-patchmatchnet		76.41 337	75.17 340	80.13 353	82.65 379	59.61 384	87.66 346	91.08 323	78.23 305	69.85 372	83.22 367	54.76 355	91.63 365	64.14 359	64.89 378	89.16 361

pmmvs3		71.81 344	68.71 347	81.11 351	75.86 386	70.42 354	86.74 353	83.66 375	58.95 382	68.64 375	80.89 376	36.93 383	89.52 375	63.10 362	63.59 379	83.39 374

UnsupCasMVSNet_eth		80.07 319	78.27 325	85.46 328	85.24 372	72.63 333	88.45 336	94.87 213	82.99 221	71.64 368	88.07 334	56.34 348	91.75 363	73.48 309	63.36 380	92.01 322

LCM-MVSNet		66.00 349	62.16 354	77.51 360	64.51 397	58.29 386	83.87 373	90.90 329	48.17 387	54.69 384	73.31 384	16.83 398	86.75 381	65.47 352	61.67 381	87.48 372

UnsupCasMVSNet_bld		76.23 338	73.27 342	85.09 333	83.79 375	72.92 325	85.65 361	93.47 263	71.52 363	68.84 374	79.08 378	49.77 368	93.21 349	66.81 350	60.52 382	89.13 363

testf1		59.54 354	56.11 357	69.85 368	69.28 392	56.61 389	80.37 382	76.55 394	42.58 390	45.68 389	75.61 379	11.26 400	84.18 386	43.20 388	60.44 383	68.75 386

APD_test2		59.54 354	56.11 357	69.85 368	69.28 392	56.61 389	80.37 382	76.55 394	42.58 390	45.68 389	75.61 379	11.26 400	84.18 386	43.20 388	60.44 383	68.75 386

KD-MVS_2432*1600		78.50 330	76.02 337	85.93 323	86.22 364	74.47 312	84.80 367	92.33 286	79.29 284	76.98 340	85.92 355	53.81 361	93.97 337	67.39 343	57.42 385	89.36 356

miper_refine_blended		78.50 330	76.02 337	85.93 323	86.22 364	74.47 312	84.80 367	92.33 286	79.29 284	76.98 340	85.92 355	53.81 361	93.97 337	67.39 343	57.42 385	89.36 356

DeepMVS_CX				56.31 377	74.23 388	51.81 394		56.67 402	44.85 388	48.54 388	75.16 381	27.87 388	58.74 398	40.92 390	52.22 387	58.39 391

WB-MVS		67.92 347	67.49 349	69.21 370	81.09 380	41.17 398	88.03 339	78.00 390	73.50 349	62.63 379	83.11 370	63.94 305	86.52 382	25.66 395	51.45 388	79.94 381

PVSNet_0	73.20 20	77.22 335	74.83 341	84.37 337	90.70 316	71.10 348	83.09 376	89.67 352	72.81 357	73.93 359	83.13 368	60.79 330	93.70 343	68.54 335	50.84 389	88.30 368

test_method		50.52 359	48.47 361	56.66 376	52.26 401	18.98 406	41.51 394	81.40 381	10.10 396	44.59 391	75.01 382	28.51 387	68.16 394	53.54 380	49.31 390	82.83 377

SSC-MVS		67.06 348	66.56 350	68.56 372	80.54 381	40.06 400	87.77 343	77.37 393	72.38 359	61.75 381	82.66 372	63.37 310	86.45 383	24.48 396	48.69 391	79.16 383

PMMVS2		59.60 353	56.40 355	69.21 370	68.83 394	46.58 396	73.02 389	77.48 392	55.07 384	49.21 387	72.95 385	17.43 397	80.04 392	49.32 383	44.33 392	80.99 380

MVE	39.65 23	43.39 360	38.59 366	57.77 375	56.52 399	48.77 395	55.38 391	58.64 401	29.33 395	28.96 396	52.65 392	4.68 403	64.62 397	28.11 394	33.07 393	59.93 390
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		43.23 361	42.29 363	46.03 378	65.58 396	37.41 401	73.51 387	64.62 398	33.99 393	28.47 397	47.87 394	19.90 396	67.91 395	22.23 397	24.45 394	32.77 393

ANet_high		58.88 356	54.22 360	72.86 363	56.50 400	56.67 388	80.75 381	86.00 366	73.09 354	37.39 393	64.63 390	22.17 393	79.49 393	43.51 387	23.96 395	82.43 379

EMVS		42.07 362	41.12 364	44.92 379	63.45 398	35.56 403	73.65 386	63.48 399	33.05 394	26.88 398	45.45 395	21.27 394	67.14 396	19.80 398	23.02 396	32.06 394

tmp_tt		35.64 363	39.24 365	24.84 380	14.87 403	23.90 405	62.71 390	51.51 403	6.58 398	36.66 394	62.08 391	44.37 378	30.34 400	52.40 381	22.00 397	20.27 395

wuyk23d		21.27 365	20.48 368	23.63 381	68.59 395	36.41 402	49.57 393	6.85 405	9.37 397	7.89 399	4.46 401	4.03 404	31.37 399	17.47 399	16.07 398	3.12 396

testmvs		8.92 366	11.52 369	1.12 383	1.06 404	0.46 408	86.02 357	0.65 406	0.62 399	2.74 400	9.52 399	0.31 406	0.45 402	2.38 400	0.39 399	2.46 398

test123		8.76 367	11.22 370	1.39 382	0.85 405	0.97 407	85.76 360	0.35 407	0.54 400	2.45 401	8.14 400	0.60 405	0.48 401	2.16 401	0.17 400	2.71 397

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

cdsmvs_eth3d_5k		22.14 364	29.52 367	0.00 384	0.00 406	0.00 409	0.00 395	95.76 152	0.00 402	0.00 403	94.29 164	75.66 170	0.00 403	0.00 402	0.00 401	0.00 399

pcd_1.5k_mvsjas		6.64 369	8.86 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	79.70 121	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

ab-mvs-re		7.82 368	10.43 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	93.88 185	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						64.08 375								59.14 372

FOURS1					98.86 1	85.54 65	98.29 1	97.49 6	89.79 44	96.29 18

test_one_0601					98.58 11	85.83 59		97.44 15	91.05 14	96.78 15	98.06 11	91.45 11

eth-test2					0.00 406

eth-test					0.00 406

test_241102_ONE					98.77 5	85.99 51		97.44 15	90.26 33	97.71 1	97.96 17	92.31 4	99.38 31

save fliter					97.85 46	85.63 64	95.21 111	96.82 68	89.44 51

test0726					98.78 3	85.93 54	97.19 11	97.47 11	90.27 31	97.64 4	98.13 3	91.47 8

GSMVS																96.12 153

test_part2					98.55 12	87.22 18				96.40 17

sam_mvs1												71.70 221				96.12 153

sam_mvs												70.60 234

MTGPA								96.97 50

test_post1							88.00 340				9.81 398	69.31 256	95.53 312	76.65 281

test_post											10.29 397	70.57 238	95.91 300

patchmatchnet-post											83.76 365	71.53 222	96.48 272

MTMP							96.16 53	60.64 400

gm-plane-assit					89.60 339	68.00 362			77.28 313		88.99 318		97.57 189	79.44 254

TEST9					97.53 58	86.49 36	94.07 186	96.78 72	81.61 256	92.77 74	96.20 87	87.71 28	99.12 51

test_8					97.49 60	86.30 44	94.02 191	96.76 75	81.86 247	92.70 78	96.20 87	87.63 29	99.02 61

agg_prior					97.38 63	85.92 56		96.72 81		92.16 89			98.97 75

test_prior4						85.96 53	94.11 181

test_prior				93.82 60	97.29 67	84.49 84		96.88 61					98.87 82			98.11 65

旧先验2							93.36 219		71.25 365	94.37 39			97.13 234	86.74 146

新几何2							93.11 234

无先验							93.28 227	96.26 110	73.95 345				99.05 55	80.56 239		96.59 137

原ACMM2							92.94 241

testdata2													98.75 93	78.30 265

segment_acmp												87.16 36

testdata1							92.15 266		87.94 103

plane_prior7					94.70 165	82.74 141

plane_prior6					94.52 175	82.75 139						74.23 187

plane_prior4											94.86 140

plane_prior3						82.75 139			90.26 33	86.91 180

plane_prior2							95.85 75		90.81 17

plane_prior1					94.59 170

n2								0.00 408

nn								0.00 408

door-mid								85.49 368

test11								96.57 92

door								85.33 370

HQP5-MVS						81.56 168

HQP-NCC					94.17 189		94.39 165		88.81 72	85.43 221

ACMP_Plane					94.17 189		94.39 165		88.81 72	85.43 221

BP-MVS														87.11 143

HQP4-MVS										85.43 221			97.96 165			94.51 219

HQP2-MVS												73.83 197

NP-MVS					94.37 183	82.42 151					93.98 178

MDTV_nov1_ep13_2view						55.91 393	87.62 347		73.32 351	84.59 240		70.33 241		74.65 301		95.50 179

Test By Simon												80.02 116

High-resolution multi-view benchmark