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									82.47 211	97.09 9	97.07 38	92.72 1	98.04 146	92.70 42	99.02 12	98.86 10

DVP-MVS++		95.98 1	96.36 1	94.82 28	97.78 51	86.00 47	98.29 1	97.49 5	90.75 17	97.62 5	98.06 6	92.59 2	99.61 3	95.64 6	99.02 12	98.86 10

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 36	92.59 2	98.94 73	92.25 50	98.99 14	98.84 13

SED-MVS		95.91 2	96.28 2	94.80 30	98.77 5	85.99 49	97.13 14	97.44 14	90.31 26	97.71 1	98.07 4	92.31 4	99.58 8	95.66 4	99.13 3	98.84 13

test_241102_ONE					98.77 5	85.99 49		97.44 14	90.26 31	97.71 1	97.96 10	92.31 4	99.38 29

test_0728_THIRD									90.75 17	97.04 10	98.05 8	92.09 6	99.55 14	95.64 6	99.13 3	99.13 2

DPE-MVS		95.57 4	95.67 4	95.25 9	98.36 25	87.28 15	95.56 82	97.51 4	89.13 58	97.14 8	97.91 11	91.64 7	99.62 1	94.61 14	99.17 2	98.86 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.67 3	96.02 3	94.64 36	98.78 3	85.93 52	97.09 16	96.73 76	90.27 29	97.04 10	98.05 8	91.47 8	99.55 14	95.62 8	99.08 7	98.45 34
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					98.78 3	85.93 52	97.19 11	97.47 10	90.27 29	97.64 4	98.13 1	91.47 8

test_241102_TWO								97.44 14	90.31 26	97.62 5	98.07 4	91.46 10	99.58 8	95.66 4	99.12 6	98.98 9

test_one_0601					98.58 11	85.83 57		97.44 14	91.05 12	96.78 13	98.06 6	91.45 11

MSP-MVS		95.42 6	95.56 6	94.98 17	98.49 17	86.52 33	96.91 25	97.47 10	91.73 8	96.10 17	96.69 53	89.90 12	99.30 38	94.70 12	98.04 63	99.13 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DeepPCF-MVS	89.96 1	94.20 29	94.77 14	92.49 101	96.52 87	80.00 204	94.00 181	97.08 42	90.05 33	95.65 20	97.29 24	89.66 13	98.97 70	93.95 20	98.71 30	98.50 25

SD-MVS		94.96 12	95.33 8	93.88 54	97.25 69	86.69 25	96.19 48	97.11 41	90.42 25	96.95 12	97.27 25	89.53 14	96.91 234	94.38 16	98.85 19	98.03 68
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 7	98.11 36	88.51 7	95.29 92	96.96 50	92.09 4	95.32 22	97.08 36	89.49 15	99.33 35	95.10 11	98.85 19	98.66 19

APDe-MVS		95.46 5	95.64 5	94.91 19	98.26 28	86.29 43	97.46 6	97.40 19	89.03 61	96.20 16	98.10 2	89.39 16	99.34 32	95.88 3	99.03 11	99.10 4

MCST-MVS		94.45 18	94.20 28	95.19 11	98.46 19	87.50 13	95.00 112	97.12 39	87.13 111	92.51 70	96.30 70	89.24 17	99.34 32	93.46 26	98.62 42	98.73 16

TSAR-MVS + MP.		94.85 13	94.94 11	94.58 39	98.25 29	86.33 39	96.11 53	96.62 85	88.14 89	96.10 17	96.96 42	89.09 18	98.94 73	94.48 15	98.68 35	98.48 28
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 23	96.99 72	86.33 39	97.33 7	97.30 27	91.38 10	95.39 21	97.46 17	88.98 19	99.40 28	94.12 18	98.89 18	98.82 15
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		95.20 8	95.07 10	95.59 5	98.14 35	88.48 8	96.26 45	97.28 29	85.90 138	97.67 3	98.10 2	88.41 20	99.56 10	94.66 13	99.19 1	98.71 18
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 39	94.32 20	92.01 117	97.54 57	78.37 242	93.40 204	97.19 33	88.02 91	94.99 26	97.21 29	88.35 21	98.44 109	94.07 19	98.09 61	99.23 1

9.14			94.47 17		97.79 49		96.08 54	97.44 14	86.13 136	95.10 24	97.40 20	88.34 22	99.22 42	93.25 31	98.70 32

SF-MVS		94.97 11	94.90 13	95.20 10	97.84 47	87.76 9	96.65 34	97.48 9	87.76 101	95.71 19	97.70 13	88.28 23	99.35 31	93.89 22	98.78 25	98.48 28

HPM-MVS++		95.14 10	94.91 12	95.83 4	98.25 29	89.65 4	95.92 63	96.96 50	91.75 7	94.02 35	96.83 48	88.12 24	99.55 14	93.41 29	98.94 16	98.28 48

dcpmvs_2		93.49 43	94.19 29	91.38 151	97.69 54	76.78 274	94.25 160	96.29 101	88.33 79	94.46 27	96.88 45	88.07 25	98.64 91	93.62 25	98.09 61	98.73 16

CSCG		93.23 52	93.05 51	93.76 59	98.04 40	84.07 87	96.22 47	97.37 20	84.15 174	90.05 114	95.66 98	87.77 26	99.15 48	89.91 93	98.27 54	98.07 64

NCCC		94.81 14	94.69 15	95.17 12	97.83 48	87.46 14	95.66 76	96.93 54	92.34 2	93.94 36	96.58 63	87.74 27	99.44 27	92.83 37	98.40 50	98.62 20

TEST9					97.53 58	86.49 34	94.07 173	96.78 69	81.61 235	92.77 61	96.20 74	87.71 28	99.12 49

train_agg		93.44 45	93.08 50	94.52 41	97.53 58	86.49 34	94.07 173	96.78 69	81.86 228	92.77 61	96.20 74	87.63 29	99.12 49	92.14 55	98.69 33	97.94 71

test_8					97.49 60	86.30 42	94.02 178	96.76 72	81.86 228	92.70 65	96.20 74	87.63 29	99.02 59

ZD-MVS					98.15 34	86.62 30		97.07 43	83.63 186	94.19 31	96.91 44	87.57 31	99.26 40	91.99 61	98.44 49

TSAR-MVS + GP.		93.66 41	93.41 45	94.41 46	96.59 82	86.78 23	94.40 150	93.93 235	89.77 42	94.21 30	95.59 101	87.35 32	98.61 95	92.72 40	96.15 98	97.83 79

APD-MVS		94.24 25	94.07 32	94.75 33	98.06 39	86.90 20	95.88 64	96.94 53	85.68 144	95.05 25	97.18 32	87.31 33	99.07 51	91.90 67	98.61 44	98.28 48
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
segment_acmp												87.16 34

旧先验1					96.79 76	81.81 150		95.67 148			96.81 50	86.69 35			97.66 74	96.97 113

test_prior2							94.12 167		87.67 103	92.63 66	96.39 69	86.62 36		91.50 71	98.67 37

CDPH-MVS		92.83 56	92.30 62	94.44 42	97.79 49	86.11 46	94.06 175	96.66 82	80.09 255	92.77 61	96.63 60	86.62 36	99.04 55	87.40 121	98.66 38	98.17 58

DPM-MVS		92.58 60	91.74 68	95.08 13	96.19 95	89.31 5	92.66 233	96.56 90	83.44 192	91.68 92	95.04 118	86.60 38	98.99 67	85.60 145	97.92 67	96.93 115

DELS-MVS		93.43 47	93.25 47	93.97 51	95.42 124	85.04 67	93.06 223	97.13 38	90.74 19	91.84 86	95.09 117	86.32 39	99.21 43	91.22 74	98.45 48	97.65 84
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
ZNCC-MVS		94.47 17	94.28 23	95.03 14	98.52 15	86.96 17	96.85 28	97.32 25	88.24 83	93.15 50	97.04 39	86.17 40	99.62 1	92.40 46	98.81 22	98.52 24

HFP-MVS		94.52 16	94.40 19	94.86 22	98.61 10	86.81 22	96.94 20	97.34 21	88.63 71	93.65 40	97.21 29	86.10 41	99.49 24	92.35 48	98.77 27	98.30 45

MVS_111021_HR		93.45 44	93.31 46	93.84 55	96.99 72	84.84 68	93.24 216	97.24 30	88.76 68	91.60 93	95.85 89	86.07 42	98.66 89	91.91 65	98.16 57	98.03 68

ACMMP_NAP		94.74 15	94.56 16	95.28 8	98.02 41	87.70 10	95.68 74	97.34 21	88.28 82	95.30 23	97.67 14	85.90 43	99.54 18	93.91 21	98.95 15	98.60 21

CS-MVS		94.12 30	94.44 18	93.17 68	96.55 84	83.08 115	97.63 3	96.95 52	91.71 9	93.50 46	96.21 73	85.61 44	98.24 123	93.64 24	98.17 56	98.19 56

PHI-MVS		93.89 36	93.65 44	94.62 38	96.84 75	86.43 36	96.69 32	97.49 5	85.15 158	93.56 44	96.28 71	85.60 45	99.31 37	92.45 43	98.79 23	98.12 62

MP-MVS-pluss		94.21 27	94.00 34	94.85 23	98.17 33	86.65 28	94.82 123	97.17 37	86.26 130	92.83 59	97.87 12	85.57 46	99.56 10	94.37 17	98.92 17	98.34 40
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
GST-MVS		94.21 27	93.97 35	94.90 21	98.41 22	86.82 21	96.54 36	97.19 33	88.24 83	93.26 47	96.83 48	85.48 47	99.59 7	91.43 73	98.40 50	98.30 45

MP-MVS		94.25 24	94.07 32	94.77 32	98.47 18	86.31 41	96.71 31	96.98 47	89.04 60	91.98 79	97.19 31	85.43 48	99.56 10	92.06 60	98.79 23	98.44 35
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 31	93.79 38	94.80 30	97.48 61	86.78 23	95.65 78	96.89 58	89.40 50	92.81 60	96.97 41	85.37 49	99.24 41	90.87 83	98.69 33	98.38 39
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
region2R		94.43 20	94.27 25	94.92 18	98.65 8	86.67 27	96.92 24	97.23 32	88.60 73	93.58 42	97.27 25	85.22 50	99.54 18	92.21 51	98.74 29	98.56 23

CP-MVS		94.34 23	94.21 27	94.74 34	98.39 23	86.64 29	97.60 4	97.24 30	88.53 75	92.73 64	97.23 28	85.20 51	99.32 36	92.15 54	98.83 21	98.25 53

test12				94.34 47	97.13 70	86.15 45		96.29 101		91.04 101		85.08 52	99.01 61		98.13 59	97.86 77

ACMMPR		94.43 20	94.28 23	94.91 19	98.63 9	86.69 25	96.94 20	97.32 25	88.63 71	93.53 45	97.26 27	85.04 53	99.54 18	92.35 48	98.78 25	98.50 25

CS-MVS-test		94.02 32	94.29 22	93.24 65	96.69 78	83.24 108	97.49 5	96.92 55	92.14 3	92.90 55	95.77 94	85.02 54	98.33 118	93.03 34	98.62 42	98.13 60

XVS		94.45 18	94.32 20	94.85 23	98.54 13	86.60 31	96.93 22	97.19 33	90.66 22	92.85 57	97.16 34	85.02 54	99.49 24	91.99 61	98.56 46	98.47 31

X-MVStestdata		88.31 158	86.13 204	94.85 23	98.54 13	86.60 31	96.93 22	97.19 33	90.66 22	92.85 57	23.41 374	85.02 54	99.49 24	91.99 61	98.56 46	98.47 31

MSLP-MVS++		93.72 40	94.08 31	92.65 93	97.31 65	83.43 103	95.79 68	97.33 23	90.03 34	93.58 42	96.96 42	84.87 57	97.76 161	92.19 53	98.66 38	96.76 119

HPM-MVS		94.02 32	93.88 36	94.43 44	98.39 23	85.78 59	97.25 10	97.07 43	86.90 119	92.62 67	96.80 52	84.85 58	99.17 45	92.43 44	98.65 40	98.33 41
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SR-MVS		94.23 26	94.17 30	94.43 44	98.21 32	85.78 59	96.40 39	96.90 57	88.20 87	94.33 29	97.40 20	84.75 59	99.03 56	93.35 30	97.99 64	98.48 28

PGM-MVS		93.96 35	93.72 41	94.68 35	98.43 20	86.22 44	95.30 90	97.78 1	87.45 107	93.26 47	97.33 23	84.62 60	99.51 22	90.75 85	98.57 45	98.32 44

EI-MVSNet-Vis-set		93.01 54	92.92 53	93.29 63	95.01 138	83.51 102	94.48 142	95.77 141	90.87 13	92.52 69	96.67 55	84.50 61	99.00 65	91.99 61	94.44 130	97.36 95

MTAPA		94.42 22	94.22 26	95.00 16	98.42 21	86.95 18	94.36 157	96.97 48	91.07 11	93.14 51	97.56 15	84.30 62	99.56 10	93.43 27	98.75 28	98.47 31

SR-MVS-dyc-post		93.82 37	93.82 37	93.82 56	97.92 43	84.57 73	96.28 43	96.76 72	87.46 105	93.75 38	97.43 18	84.24 63	99.01 61	92.73 38	97.80 70	97.88 75

ETV-MVS		92.74 58	92.66 57	92.97 78	95.20 132	84.04 89	95.07 108	96.51 91	90.73 20	92.96 54	91.19 257	84.06 64	98.34 116	91.72 69	96.54 92	96.54 128

EI-MVSNet-UG-set		92.74 58	92.62 58	93.12 70	94.86 149	83.20 110	94.40 150	95.74 144	90.71 21	92.05 77	96.60 62	84.00 65	98.99 67	91.55 70	93.63 140	97.17 103

mPP-MVS		93.99 34	93.78 39	94.63 37	98.50 16	85.90 56	96.87 26	96.91 56	88.70 69	91.83 88	97.17 33	83.96 66	99.55 14	91.44 72	98.64 41	98.43 36

APD-MVS_3200maxsize		93.78 38	93.77 40	93.80 58	97.92 43	84.19 85	96.30 41	96.87 60	86.96 115	93.92 37	97.47 16	83.88 67	98.96 72	92.71 41	97.87 68	98.26 52

EIA-MVS		91.95 67	91.94 65	91.98 121	95.16 133	80.01 203	95.36 85	96.73 76	88.44 76	89.34 122	92.16 223	83.82 68	98.45 108	89.35 97	97.06 80	97.48 92

casdiffmvs_mvg		92.96 55	92.83 55	93.35 62	94.59 161	83.40 105	95.00 112	96.34 99	90.30 28	92.05 77	96.05 82	83.43 69	98.15 130	92.07 57	95.67 102	98.49 27
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 73	91.56 70	92.13 116	95.88 109	80.50 187	97.33 7	95.25 178	86.15 134	89.76 117	95.60 100	83.42 70	98.32 120	87.37 123	93.25 152	97.56 90

UA-Net		92.83 56	92.54 59	93.68 60	96.10 100	84.71 71	95.66 76	96.39 96	91.92 5	93.22 49	96.49 66	83.16 71	98.87 77	84.47 159	95.47 107	97.45 94

UniMVSNet_NR-MVSNet		89.92 110	89.29 113	91.81 135	93.39 209	83.72 95	94.43 148	97.12 39	89.80 38	86.46 174	93.32 184	83.16 71	97.23 214	84.92 151	81.02 299	94.49 208

DROMVSNet		93.44 45	93.71 42	92.63 94	95.21 131	82.43 136	97.27 9	96.71 79	90.57 24	92.88 56	95.80 92	83.16 71	98.16 129	93.68 23	98.14 58	97.31 96

RE-MVS-def			93.68 43		97.92 43	84.57 73	96.28 43	96.76 72	87.46 105	93.75 38	97.43 18	82.94 74		92.73 38	97.80 70	97.88 75

新几何1				93.10 71	97.30 66	84.35 84		95.56 156	71.09 344	91.26 99	96.24 72	82.87 75	98.86 79	79.19 242	98.10 60	96.07 144

原ACMM1				92.01 117	97.34 64	81.05 171		96.81 67	78.89 270	90.45 106	95.92 86	82.65 76	98.84 83	80.68 222	98.26 55	96.14 138

casdiffmvs		92.51 61	92.43 61	92.74 88	94.41 173	81.98 146	94.54 140	96.23 108	89.57 46	91.96 81	96.17 78	82.58 77	98.01 148	90.95 81	95.45 109	98.23 54
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 49	92.99 52	94.26 49	96.07 102	85.83 57	94.89 118	96.99 46	89.02 63	89.56 118	97.37 22	82.51 78	99.38 29	92.20 52	98.30 53	97.57 89
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 48	93.22 48	93.94 53	98.36 25	84.83 69	97.15 13	96.80 68	85.77 141	92.47 71	97.13 35	82.38 79	99.07 51	90.51 90	98.40 50	97.92 74

baseline		92.39 64	92.29 63	92.69 92	94.46 170	81.77 151	94.14 166	96.27 103	89.22 54	91.88 84	96.00 83	82.35 80	97.99 150	91.05 76	95.27 114	98.30 45

canonicalmvs		93.27 50	92.75 56	94.85 23	95.70 116	87.66 11	96.33 40	96.41 95	90.00 35	94.09 33	94.60 138	82.33 81	98.62 94	92.40 46	92.86 159	98.27 50

DP-MVS Recon		91.95 67	91.28 73	93.96 52	98.33 27	85.92 54	94.66 134	96.66 82	82.69 209	90.03 115	95.82 91	82.30 82	99.03 56	84.57 157	96.48 95	96.91 116

PAPR		90.02 104	89.27 115	92.29 112	95.78 112	80.95 175	92.68 232	96.22 109	81.91 225	86.66 172	93.75 176	82.23 83	98.44 109	79.40 241	94.79 118	97.48 92

MVS_Test		91.31 79	91.11 76	91.93 125	94.37 174	80.14 195	93.46 203	95.80 139	86.46 126	91.35 98	93.77 174	82.21 84	98.09 141	87.57 119	94.95 117	97.55 91

nrg030		91.08 84	90.39 86	93.17 68	93.07 217	86.91 19	96.41 37	96.26 104	88.30 81	88.37 137	94.85 126	82.19 85	97.64 172	91.09 75	82.95 270	94.96 181

UniMVSNet (Re)		89.80 113	89.07 117	92.01 117	93.60 204	84.52 76	94.78 126	97.47 10	89.26 53	86.44 177	92.32 218	82.10 86	97.39 201	84.81 154	80.84 303	94.12 223

testdata				90.49 187	96.40 89	77.89 254		95.37 174	72.51 337	93.63 41	96.69 53	82.08 87	97.65 169	83.08 175	97.39 76	95.94 148

PAPM_NR		91.22 81	90.78 84	92.52 100	97.60 56	81.46 160	94.37 156	96.24 107	86.39 128	87.41 154	94.80 129	82.06 88	98.48 102	82.80 183	95.37 110	97.61 86

MG-MVS		91.77 70	91.70 69	92.00 120	97.08 71	80.03 202	93.60 198	95.18 182	87.85 99	90.89 102	96.47 67	82.06 88	98.36 113	85.07 149	97.04 81	97.62 85

CANet		93.54 42	93.20 49	94.55 40	95.65 117	85.73 61	94.94 115	96.69 81	91.89 6	90.69 104	95.88 88	81.99 90	99.54 18	93.14 33	97.95 66	98.39 37

FC-MVSNet-test		90.27 99	90.18 91	90.53 183	93.71 200	79.85 209	95.77 69	97.59 2	89.31 52	86.27 180	94.67 135	81.93 91	97.01 228	84.26 161	88.09 224	94.71 192

FIs		90.51 97	90.35 87	90.99 172	93.99 190	80.98 173	95.73 71	97.54 3	89.15 57	86.72 171	94.68 134	81.83 92	97.24 213	85.18 148	88.31 220	94.76 191

ACMMP		93.24 51	92.88 54	94.30 48	98.09 38	85.33 65	96.86 27	97.45 13	88.33 79	90.15 113	97.03 40	81.44 93	99.51 22	90.85 84	95.74 101	98.04 67
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 75	91.11 76	93.01 76	94.35 177	83.39 106	94.60 136	95.10 186	87.10 112	90.57 105	93.10 195	81.43 94	98.07 144	89.29 99	94.48 128	97.59 88

MVS_111021_LR		92.47 62	92.29 63	92.98 77	95.99 106	84.43 82	93.08 221	96.09 117	88.20 87	91.12 100	95.72 97	81.33 95	97.76 161	91.74 68	97.37 77	96.75 120

mvs_anonymous		89.37 130	89.32 112	89.51 233	93.47 207	74.22 299	91.65 263	94.83 203	82.91 205	85.45 202	93.79 172	81.23 96	96.36 267	86.47 135	94.09 133	97.94 71

PVSNet_BlendedMVS		89.98 105	89.70 102	90.82 176	96.12 97	81.25 165	93.92 186	96.83 64	83.49 191	89.10 125	92.26 221	81.04 97	98.85 81	86.72 133	87.86 228	92.35 298

PVSNet_Blended		90.73 89	90.32 88	91.98 121	96.12 97	81.25 165	92.55 237	96.83 64	82.04 221	89.10 125	92.56 211	81.04 97	98.85 81	86.72 133	95.91 99	95.84 153

alignmvs		93.08 53	92.50 60	94.81 29	95.62 119	87.61 12	95.99 59	96.07 119	89.77 42	94.12 32	94.87 123	80.56 99	98.66 89	92.42 45	93.10 155	98.15 59

API-MVS		90.66 92	90.07 94	92.45 103	96.36 91	84.57 73	96.06 57	95.22 181	82.39 212	89.13 124	94.27 151	80.32 100	98.46 105	80.16 230	96.71 89	94.33 214

PVSNet_Blended_VisFu		91.38 77	90.91 81	92.80 84	96.39 90	83.17 111	94.87 120	96.66 82	83.29 196	89.27 123	94.46 142	80.29 101	99.17 45	87.57 119	95.37 110	96.05 146

test222					96.55 84	81.70 152	92.22 248	95.01 189	68.36 350	90.20 110	96.14 79	80.26 102			97.80 70	96.05 146

diffmvs		91.37 78	91.23 74	91.77 136	93.09 216	80.27 190	92.36 242	95.52 161	87.03 114	91.40 97	94.93 120	80.08 103	97.44 189	92.13 56	94.56 125	97.61 86
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												80.02 104

IterMVS-LS		88.36 157	87.91 152	89.70 226	93.80 197	78.29 245	93.73 192	95.08 188	85.73 142	84.75 220	91.90 237	79.88 105	96.92 233	83.83 167	82.51 276	93.89 233
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 134	88.86 125	89.80 222	91.84 251	78.30 244	93.70 195	95.01 189	85.73 142	87.15 159	95.28 108	79.87 106	97.21 216	83.81 168	87.36 234	93.88 235

TAPA-MVS	84.62 6	88.16 162	87.01 172	91.62 140	96.64 80	80.65 182	94.39 152	96.21 112	76.38 299	86.19 182	95.44 103	79.75 107	98.08 143	62.75 347	95.29 112	96.13 139
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 126	88.64 128	91.71 138	94.74 153	80.81 179	93.54 199	95.10 186	83.11 199	86.82 170	90.67 274	79.74 108	97.75 164	80.51 225	93.55 142	96.57 126

pcd_1.5k_mvsjas		6.64 348	8.86 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	79.70 109	0.00 381	0.00 379	0.00 379	0.00 377

PS-MVSNAJss		89.97 106	89.62 103	91.02 169	91.90 249	80.85 178	95.26 95	95.98 125	86.26 130	86.21 181	94.29 148	79.70 109	97.65 169	88.87 104	88.10 222	94.57 198

PS-MVSNAJ		91.18 82	90.92 80	91.96 123	95.26 129	82.60 135	92.09 253	95.70 146	86.27 129	91.84 86	92.46 213	79.70 109	98.99 67	89.08 101	95.86 100	94.29 217

xiu_mvs_v2_base		91.13 83	90.89 82	91.86 130	94.97 141	82.42 137	92.24 247	95.64 153	86.11 137	91.74 91	93.14 193	79.67 112	98.89 76	89.06 102	95.46 108	94.28 218

WR-MVS_H		87.80 171	87.37 162	89.10 241	93.23 212	78.12 248	95.61 80	97.30 27	87.90 95	83.72 248	92.01 234	79.65 113	96.01 280	76.36 268	80.54 307	93.16 272

EPNet		91.79 69	91.02 79	94.10 50	90.10 311	85.25 66	96.03 58	92.05 282	92.83 1	87.39 157	95.78 93	79.39 114	99.01 61	88.13 111	97.48 75	98.05 66
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 202	86.62 187	89.02 244	92.13 242	77.40 267	90.91 275	94.81 205	81.28 241	84.32 236	90.08 285	79.26 115	96.62 245	83.81 168	82.94 271	93.04 277

miper_enhance_ethall		86.90 213	86.18 203	89.06 242	91.66 260	77.58 264	90.22 289	94.82 204	79.16 267	84.48 227	89.10 299	79.19 116	96.66 242	84.06 163	82.94 271	92.94 280

NR-MVSNet		88.58 153	87.47 160	91.93 125	93.04 219	84.16 86	94.77 127	96.25 106	89.05 59	80.04 300	93.29 187	79.02 117	97.05 226	81.71 206	80.05 313	94.59 196

TAMVS		89.21 132	88.29 142	91.96 123	93.71 200	82.62 134	93.30 210	94.19 226	82.22 216	87.78 148	93.94 164	78.83 118	96.95 231	77.70 255	92.98 157	96.32 132

c3_l		87.14 207	86.50 192	89.04 243	92.20 239	77.26 268	91.22 271	94.70 210	82.01 222	84.34 235	90.43 278	78.81 119	96.61 248	83.70 170	81.09 296	93.25 267

1112_ss		88.42 154	87.33 163	91.72 137	94.92 145	80.98 173	92.97 226	94.54 213	78.16 286	83.82 246	93.88 169	78.78 120	97.91 156	79.45 237	89.41 197	96.26 135

CDS-MVSNet		89.45 123	88.51 133	92.29 112	93.62 203	83.61 100	93.01 224	94.68 211	81.95 223	87.82 147	93.24 189	78.69 121	96.99 229	80.34 227	93.23 153	96.28 134
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 117	88.92 121	91.67 139	95.47 123	81.15 169	92.38 241	94.78 207	83.11 199	89.06 127	94.32 146	78.67 122	96.61 248	81.57 207	90.89 179	97.24 99

CPTT-MVS		91.99 66	91.80 67	92.55 98	98.24 31	81.98 146	96.76 30	96.49 92	81.89 227	90.24 109	96.44 68	78.59 123	98.61 95	89.68 94	97.85 69	97.06 107

IS-MVSNet		91.43 76	91.09 78	92.46 102	95.87 111	81.38 163	96.95 19	93.69 246	89.72 44	89.50 120	95.98 84	78.57 124	97.77 160	83.02 177	96.50 94	98.22 55

OMC-MVS		91.23 80	90.62 85	93.08 72	96.27 93	84.07 87	93.52 200	95.93 128	86.95 116	89.51 119	96.13 80	78.50 125	98.35 115	85.84 143	92.90 158	96.83 118

PCF-MVS	84.11 10	87.74 173	86.08 208	92.70 91	94.02 185	84.43 82	89.27 303	95.87 135	73.62 328	84.43 230	94.33 145	78.48 126	98.86 79	70.27 307	94.45 129	94.81 189
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 159	88.32 141	88.27 260	94.71 156	72.41 321	93.15 217	90.98 312	87.77 100	79.25 308	91.96 235	78.35 127	95.75 292	83.04 176	95.62 103	96.65 123

HY-MVS	83.01 12	89.03 140	87.94 151	92.29 112	94.86 149	82.77 124	92.08 254	94.49 214	81.52 237	86.93 164	92.79 206	78.32 128	98.23 124	79.93 232	90.55 180	95.88 151

GeoE		90.05 103	89.43 108	91.90 129	95.16 133	80.37 189	95.80 67	94.65 212	83.90 179	87.55 153	94.75 131	78.18 129	97.62 174	81.28 210	93.63 140	97.71 83

MVS		87.44 190	86.10 207	91.44 149	92.61 232	83.62 99	92.63 234	95.66 150	67.26 351	81.47 278	92.15 224	77.95 130	98.22 126	79.71 234	95.48 106	92.47 293

MVSFormer		91.68 74	91.30 72	92.80 84	93.86 194	83.88 92	95.96 61	95.90 132	84.66 169	91.76 89	94.91 121	77.92 131	97.30 205	89.64 95	97.11 78	97.24 99

lupinMVS		90.92 85	90.21 89	93.03 75	93.86 194	83.88 92	92.81 230	93.86 239	79.84 258	91.76 89	94.29 148	77.92 131	98.04 146	90.48 91	97.11 78	97.17 103

Test_1112_low_res		87.65 176	86.51 191	91.08 165	94.94 144	79.28 225	91.77 258	94.30 222	76.04 304	83.51 255	92.37 216	77.86 133	97.73 165	78.69 245	89.13 204	96.22 136

VNet		92.24 65	91.91 66	93.24 65	96.59 82	83.43 103	94.84 122	96.44 93	89.19 56	94.08 34	95.90 87	77.85 134	98.17 128	88.90 103	93.38 149	98.13 60

mvsany_test1		85.42 245	85.30 232	85.77 310	87.95 339	75.41 291	87.61 327	80.97 363	76.82 296	88.68 131	95.83 90	77.44 135	90.82 351	85.90 141	86.51 242	91.08 325

DU-MVS		89.34 131	88.50 134	91.85 132	93.04 219	83.72 95	94.47 145	96.59 87	89.50 47	86.46 174	93.29 187	77.25 136	97.23 214	84.92 151	81.02 299	94.59 196

Baseline_NR-MVSNet		87.07 208	86.63 186	88.40 256	91.44 263	77.87 255	94.23 163	92.57 267	84.12 175	85.74 188	92.08 230	77.25 136	96.04 277	82.29 192	79.94 314	91.30 316

jason		90.80 86	90.10 93	92.90 81	93.04 219	83.53 101	93.08 221	94.15 228	80.22 252	91.41 96	94.91 121	76.87 138	97.93 155	90.28 92	96.90 84	97.24 99
jason: jason.
PAPM		86.68 220	85.39 229	90.53 183	93.05 218	79.33 224	89.79 296	94.77 208	78.82 272	81.95 275	93.24 189	76.81 139	97.30 205	66.94 330	93.16 154	94.95 184

Vis-MVSNet (Re-imp)		89.59 118	89.44 107	90.03 210	95.74 113	75.85 286	95.61 80	90.80 317	87.66 104	87.83 146	95.40 106	76.79 140	96.46 261	78.37 246	96.73 88	97.80 80

baseline1		88.10 163	87.28 165	90.57 181	94.96 142	80.07 198	94.27 159	91.29 305	86.74 121	87.41 154	94.00 161	76.77 141	96.20 272	80.77 219	79.31 321	95.44 165

114514_t		89.51 120	88.50 134	92.54 99	98.11 36	81.99 145	95.16 103	96.36 98	70.19 347	85.81 186	95.25 110	76.70 142	98.63 93	82.07 195	96.86 87	97.00 112

PLC	84.53 7	89.06 139	88.03 148	92.15 115	97.27 68	82.69 131	94.29 158	95.44 168	79.71 260	84.01 243	94.18 153	76.68 143	98.75 87	77.28 259	93.41 148	95.02 177
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 145	87.95 150	91.49 146	92.68 231	83.01 118	94.92 117	96.31 100	89.88 37	85.53 195	93.85 171	76.63 144	96.96 230	81.91 199	79.87 316	94.50 206

MAR-MVS		90.30 98	89.37 110	93.07 74	96.61 81	84.48 78	95.68 74	95.67 148	82.36 214	87.85 145	92.85 200	76.63 144	98.80 85	80.01 231	96.68 90	95.91 149
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
WR-MVS		88.38 155	87.67 155	90.52 185	93.30 211	80.18 193	93.26 213	95.96 127	88.57 74	85.47 201	92.81 204	76.12 146	96.91 234	81.24 211	82.29 279	94.47 211

v8		87.50 189	86.71 181	89.89 216	91.37 268	79.40 218	94.50 141	95.38 172	84.81 166	83.60 253	91.33 252	76.05 147	97.42 191	82.84 181	80.51 310	92.84 284

v148		87.04 209	86.32 198	89.21 237	90.94 286	77.26 268	93.71 194	94.43 216	84.84 165	84.36 234	90.80 271	76.04 148	97.05 226	82.12 194	79.60 318	93.31 264

eth_miper_zixun_eth		86.50 227	85.77 221	88.68 251	91.94 248	75.81 287	90.47 281	94.89 197	82.05 219	84.05 241	90.46 277	75.96 149	96.77 238	82.76 184	79.36 320	93.46 261

3Dnovator+	87.14 4	92.42 63	91.37 71	95.55 6	95.63 118	88.73 6	97.07 18	96.77 71	90.84 14	84.02 242	96.62 61	75.95 150	99.34 32	87.77 115	97.68 73	98.59 22

h-mvs33		90.80 86	90.15 92	92.75 87	96.01 104	82.66 132	95.43 84	95.53 160	89.80 38	93.08 52	95.64 99	75.77 151	99.00 65	92.07 57	78.05 325	96.60 124

hse-mvs2		89.88 112	89.34 111	91.51 145	94.83 151	81.12 170	93.94 184	93.91 238	89.80 38	93.08 52	93.60 178	75.77 151	97.66 168	92.07 57	77.07 332	95.74 158

BH-untuned		88.60 152	88.13 146	90.01 213	95.24 130	78.50 238	93.29 211	94.15 228	84.75 167	84.46 228	93.40 181	75.76 153	97.40 198	77.59 256	94.52 127	94.12 223

DIV-MVS_self_test		86.53 225	85.78 219	88.75 248	92.02 247	76.45 279	90.74 277	94.30 222	81.83 230	83.34 259	90.82 270	75.75 154	96.57 251	81.73 205	81.52 291	93.24 268

BH-w/o		87.57 185	87.05 170	89.12 240	94.90 147	77.90 253	92.41 239	93.51 248	82.89 206	83.70 249	91.34 251	75.75 154	97.07 224	75.49 276	93.49 145	92.39 296

cl____		86.52 226	85.78 219	88.75 248	92.03 246	76.46 278	90.74 277	94.30 222	81.83 230	83.34 259	90.78 272	75.74 156	96.57 251	81.74 204	81.54 290	93.22 269

cdsmvs_eth3d_5k		22.14 343	29.52 346	0.00 362	0.00 385	0.00 386	0.00 373	95.76 142	0.00 380	0.00 381	94.29 148	75.66 157	0.00 381	0.00 379	0.00 379	0.00 377

CNLPA		89.07 138	87.98 149	92.34 108	96.87 74	84.78 70	94.08 172	93.24 251	81.41 238	84.46 228	95.13 116	75.57 158	96.62 245	77.21 260	93.84 138	95.61 163

CHOSEN 1792x2688		88.84 145	87.69 154	92.30 111	96.14 96	81.42 162	90.01 293	95.86 136	74.52 319	87.41 154	93.94 164	75.46 159	98.36 113	80.36 226	95.53 104	97.12 106

CP-MVSNet		87.63 179	87.26 167	88.74 250	93.12 215	76.59 277	95.29 92	96.58 88	88.43 77	83.49 256	92.98 198	75.28 160	95.83 288	78.97 243	81.15 295	93.79 241

v10		87.25 199	86.38 194	89.85 217	91.19 274	79.50 215	94.48 142	95.45 166	83.79 183	83.62 252	91.19 257	75.13 161	97.42 191	81.94 198	80.60 305	92.63 289

Vis-MVSNet		91.75 71	91.23 74	93.29 63	95.32 126	83.78 94	96.14 51	95.98 125	89.89 36	90.45 106	96.58 63	75.09 162	98.31 121	84.75 155	96.90 84	97.78 82
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 143	88.26 144	90.94 175	94.05 184	80.78 180	91.71 260	95.38 172	81.55 236	88.63 132	93.91 168	75.04 163	95.47 304	82.47 187	91.61 170	96.57 126

v1144		87.61 182	86.79 178	90.06 209	91.01 281	79.34 221	93.95 183	95.42 171	83.36 195	85.66 190	91.31 255	74.98 164	97.42 191	83.37 172	82.06 281	93.42 262

miper_lstm_enhance		85.27 250	84.59 248	87.31 282	91.28 272	74.63 294	87.69 324	94.09 232	81.20 245	81.36 281	89.85 291	74.97 165	94.30 318	81.03 215	79.84 317	93.01 278

test_yl		90.69 90	90.02 98	92.71 89	95.72 114	82.41 139	94.11 168	95.12 184	85.63 146	91.49 94	94.70 132	74.75 166	98.42 111	86.13 138	92.53 163	97.31 96

DCV-MVSNet		90.69 90	90.02 98	92.71 89	95.72 114	82.41 139	94.11 168	95.12 184	85.63 146	91.49 94	94.70 132	74.75 166	98.42 111	86.13 138	92.53 163	97.31 96

V42		87.68 174	86.86 174	90.15 204	90.58 302	80.14 195	94.24 162	95.28 177	83.66 185	85.67 189	91.33 252	74.73 168	97.41 196	84.43 160	81.83 285	92.89 282

FA-MVS(test-final)		89.66 115	88.91 122	91.93 125	94.57 164	80.27 190	91.36 267	94.74 209	84.87 163	89.82 116	92.61 210	74.72 169	98.47 104	83.97 165	93.53 143	97.04 109

XVG-OURS-SEG-HR		89.95 108	89.45 106	91.47 148	94.00 189	81.21 168	91.87 256	96.06 121	85.78 140	88.55 133	95.73 96	74.67 170	97.27 209	88.71 105	89.64 195	95.91 149

v2v482		87.84 169	87.06 169	90.17 202	90.99 282	79.23 228	94.00 181	95.13 183	84.87 163	85.53 195	92.07 232	74.45 171	97.45 187	84.71 156	81.75 287	93.85 239

CLD-MVS		89.47 122	88.90 123	91.18 159	94.22 179	82.07 144	92.13 251	96.09 117	87.90 95	85.37 211	92.45 214	74.38 172	97.56 177	87.15 126	90.43 181	93.93 232
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 176	86.85 175	90.03 210	92.14 241	80.60 185	93.76 191	95.23 179	82.94 204	84.60 223	94.02 159	74.27 173	95.49 303	81.04 213	83.68 263	94.01 231

HQP_MVS		90.60 96	90.19 90	91.82 133	94.70 157	82.73 128	95.85 65	96.22 109	90.81 15	86.91 166	94.86 124	74.23 174	98.12 131	88.15 109	89.99 186	94.63 193

plane_prior6					94.52 166	82.75 125						74.23 174

v144192		87.19 205	86.35 196	89.74 223	90.64 299	78.24 246	93.92 186	95.43 169	81.93 224	85.51 197	91.05 265	74.21 176	97.45 187	82.86 180	81.56 289	93.53 256

VPA-MVSNet		89.62 116	88.96 119	91.60 141	93.86 194	82.89 123	95.46 83	97.33 23	87.91 94	88.43 136	93.31 185	74.17 177	97.40 198	87.32 124	82.86 275	94.52 201

ab-mvs		89.41 126	88.35 138	92.60 95	95.15 135	82.65 133	92.20 249	95.60 155	83.97 178	88.55 133	93.70 177	74.16 178	98.21 127	82.46 188	89.37 198	96.94 114

1314		87.51 187	86.57 189	90.34 198	92.42 235	79.74 211	92.63 234	95.35 176	78.35 281	80.14 297	91.62 246	74.05 179	97.15 218	81.05 212	93.53 143	94.12 223

test_djsdf		89.03 140	88.64 128	90.21 200	90.74 296	79.28 225	95.96 61	95.90 132	84.66 169	85.33 213	92.94 199	74.02 180	97.30 205	89.64 95	88.53 213	94.05 229

cl22		86.78 216	85.98 212	89.18 239	92.34 236	77.62 263	90.84 276	94.13 230	81.33 240	83.97 244	90.15 283	73.96 181	96.60 250	84.19 162	82.94 271	93.33 263

AdaColmap		89.89 111	89.07 117	92.37 107	97.41 62	83.03 116	94.42 149	95.92 129	82.81 207	86.34 179	94.65 136	73.89 182	99.02 59	80.69 221	95.51 105	95.05 176

HyFIR lowres test		88.09 164	86.81 176	91.93 125	96.00 105	80.63 183	90.01 293	95.79 140	73.42 329	87.68 150	92.10 229	73.86 183	97.96 152	80.75 220	91.70 169	97.19 102

HQP2-MVS												73.83 184

HQP-MVS		89.80 113	89.28 114	91.34 153	94.17 180	81.56 154	94.39 152	96.04 122	88.81 65	85.43 205	93.97 163	73.83 184	97.96 152	87.11 128	89.77 193	94.50 206

3Dnovator	86.66 5	91.73 72	90.82 83	94.44 42	94.59 161	86.37 38	97.18 12	97.02 45	89.20 55	84.31 238	96.66 56	73.74 186	99.17 45	86.74 131	97.96 65	97.79 81

EPNet_dtu		86.49 229	85.94 215	88.14 265	90.24 309	72.82 311	94.11 168	92.20 276	86.66 124	79.42 307	92.36 217	73.52 187	95.81 290	71.26 301	93.66 139	95.80 156
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 262	83.06 266	88.54 254	91.72 255	78.44 239	95.18 100	92.82 261	82.73 208	79.67 304	92.12 226	73.49 188	95.96 282	71.10 306	68.73 353	91.21 319

Effi-MVS+-dtu		88.65 150	88.35 138	89.54 230	93.33 210	76.39 280	94.47 145	94.36 220	87.70 102	85.43 205	89.56 296	73.45 189	97.26 211	85.57 146	91.28 172	94.97 178

baseline2		86.50 227	85.39 229	89.84 218	91.12 278	76.70 275	91.88 255	88.58 341	82.35 215	79.95 301	90.95 267	73.42 190	97.63 173	80.27 229	89.95 189	95.19 173

PEN-MVS		86.80 215	86.27 201	88.40 256	92.32 237	75.71 288	95.18 100	96.38 97	87.97 92	82.82 265	93.15 192	73.39 191	95.92 283	76.15 272	79.03 323	93.59 254

v1192		87.25 199	86.33 197	90.00 214	90.76 295	79.04 229	93.80 189	95.48 162	82.57 210	85.48 200	91.18 259	73.38 192	97.42 191	82.30 191	82.06 281	93.53 256

QAPM		89.51 120	88.15 145	93.59 61	94.92 145	84.58 72	96.82 29	96.70 80	78.43 280	83.41 257	96.19 77	73.18 193	99.30 38	77.11 262	96.54 92	96.89 117

mvsmamba		89.96 107	89.50 105	91.33 154	92.90 226	81.82 149	96.68 33	92.37 270	89.03 61	87.00 162	94.85 126	73.05 194	97.65 169	91.03 77	88.63 211	94.51 203

tpmrst		85.35 247	84.99 237	86.43 302	90.88 291	67.88 348	88.71 312	91.43 302	80.13 254	86.08 184	88.80 305	73.05 194	96.02 279	82.48 186	83.40 269	95.40 167

PS-CasMVS		87.32 196	86.88 173	88.63 253	92.99 222	76.33 282	95.33 87	96.61 86	88.22 85	83.30 261	93.07 196	73.03 196	95.79 291	78.36 247	81.00 301	93.75 248

DTE-MVSNet		86.11 233	85.48 227	87.98 269	91.65 261	74.92 293	94.93 116	95.75 143	87.36 108	82.26 270	93.04 197	72.85 197	95.82 289	74.04 289	77.46 329	93.20 270

MVSTER		88.84 145	88.29 142	90.51 186	92.95 224	80.44 188	93.73 192	95.01 189	84.66 169	87.15 159	93.12 194	72.79 198	97.21 216	87.86 114	87.36 234	93.87 236

v1921920		86.97 211	86.06 209	89.69 227	90.53 305	78.11 249	93.80 189	95.43 169	81.90 226	85.33 213	91.05 265	72.66 199	97.41 196	82.05 196	81.80 286	93.53 256

DP-MVS		87.25 199	85.36 231	92.90 81	97.65 55	83.24 108	94.81 124	92.00 284	74.99 314	81.92 276	95.00 119	72.66 199	99.05 53	66.92 332	92.33 166	96.40 130

v7n		86.81 214	85.76 222	89.95 215	90.72 297	79.25 227	95.07 108	95.92 129	84.45 172	82.29 269	90.86 268	72.60 201	97.53 181	79.42 240	80.52 309	93.08 276

OPM-MVS		90.12 101	89.56 104	91.82 133	93.14 214	83.90 91	94.16 165	95.74 144	88.96 64	87.86 144	95.43 105	72.48 202	97.91 156	88.10 113	90.18 185	93.65 253
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 168	86.32 198	92.59 96	96.07 102	82.92 122	95.23 96	94.92 196	75.66 306	82.89 264	95.98 84	72.48 202	99.21 43	68.43 321	95.23 115	95.64 162

pm-mvs1		86.61 221	85.54 225	89.82 219	91.44 263	80.18 193	95.28 94	94.85 201	83.84 181	81.66 277	92.62 209	72.45 204	96.48 258	79.67 235	78.06 324	92.82 285

PMMVS		85.71 241	84.96 239	87.95 270	88.90 326	77.09 270	88.68 313	90.06 327	72.32 338	86.47 173	90.76 273	72.15 205	94.40 315	81.78 203	93.49 145	92.36 297

PatchmatchNet		85.85 238	84.70 245	89.29 236	91.76 254	75.54 289	88.49 315	91.30 304	81.63 234	85.05 216	88.70 307	71.71 206	96.24 271	74.61 287	89.05 205	96.08 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 207				96.12 140

patchmatchnet-post											83.76 345	71.53 208	96.48 258

v1240		86.78 216	85.85 217	89.56 229	90.45 306	77.79 258	93.61 197	95.37 174	81.65 232	85.43 205	91.15 261	71.50 209	97.43 190	81.47 209	82.05 283	93.47 260

anonymousdsp		87.84 169	87.09 168	90.12 206	89.13 323	80.54 186	94.67 133	95.55 157	82.05 219	83.82 246	92.12 226	71.47 210	97.15 218	87.15 126	87.80 230	92.67 287

Patchmatch-test		81.37 292	79.30 298	87.58 276	90.92 288	74.16 301	80.99 358	87.68 346	70.52 346	76.63 324	88.81 303	71.21 211	92.76 339	60.01 355	86.93 240	95.83 154

F-COLMAP		87.95 167	86.80 177	91.40 150	96.35 92	80.88 177	94.73 129	95.45 166	79.65 261	82.04 274	94.61 137	71.13 212	98.50 101	76.24 271	91.05 177	94.80 190

pmmvs4		85.43 244	83.86 257	90.16 203	90.02 314	82.97 120	90.27 283	92.67 265	75.93 305	80.73 287	91.74 241	71.05 213	95.73 294	78.85 244	83.46 267	91.78 307

CR-MVSNet		85.35 247	83.76 258	90.12 206	90.58 302	79.34 221	85.24 342	91.96 288	78.27 283	85.55 192	87.87 320	71.03 214	95.61 295	73.96 291	89.36 199	95.40 167

Patchmtry		82.71 276	80.93 282	88.06 267	90.05 313	76.37 281	84.74 347	91.96 288	72.28 339	81.32 282	87.87 320	71.03 214	95.50 302	68.97 317	80.15 312	92.32 299

CL-MVSNet_self_test		81.74 285	80.53 283	85.36 313	85.96 347	72.45 320	90.25 285	93.07 255	81.24 243	79.85 303	87.29 326	70.93 216	92.52 340	66.95 329	69.23 349	91.11 323

RPMNet		83.95 267	81.53 277	91.21 157	90.58 302	79.34 221	85.24 342	96.76 72	71.44 342	85.55 192	82.97 350	70.87 217	98.91 75	61.01 351	89.36 199	95.40 167

Patchmatch-RL test		81.67 286	79.96 292	86.81 298	85.42 352	71.23 330	82.17 356	87.50 347	78.47 278	77.19 320	82.50 351	70.81 218	93.48 330	82.66 185	72.89 341	95.71 161

CostFormer		85.77 240	84.94 240	88.26 261	91.16 277	72.58 319	89.47 301	91.04 311	76.26 302	86.45 176	89.97 288	70.74 219	96.86 237	82.35 190	87.07 239	95.34 170

sam_mvs												70.60 220

xiu_mvs_v1_base_debu		90.64 93	90.05 95	92.40 104	93.97 191	84.46 79	93.32 206	95.46 163	85.17 155	92.25 72	94.03 156	70.59 221	98.57 98	90.97 78	94.67 120	94.18 219

xiu_mvs_v1_base		90.64 93	90.05 95	92.40 104	93.97 191	84.46 79	93.32 206	95.46 163	85.17 155	92.25 72	94.03 156	70.59 221	98.57 98	90.97 78	94.67 120	94.18 219

xiu_mvs_v1_base_debi		90.64 93	90.05 95	92.40 104	93.97 191	84.46 79	93.32 206	95.46 163	85.17 155	92.25 72	94.03 156	70.59 221	98.57 98	90.97 78	94.67 120	94.18 219

test_post											10.29 375	70.57 224	95.91 285

CANet_DTU		90.26 100	89.41 109	92.81 83	93.46 208	83.01 118	93.48 201	94.47 215	89.43 49	87.76 149	94.23 152	70.54 225	99.03 56	84.97 150	96.39 96	96.38 131

BH-RMVSNet		88.37 156	87.48 159	91.02 169	95.28 127	79.45 217	92.89 228	93.07 255	85.45 151	86.91 166	94.84 128	70.35 226	97.76 161	73.97 290	94.59 124	95.85 152

Fast-Effi-MVS+-dtu		87.44 190	86.72 180	89.63 228	92.04 245	77.68 262	94.03 177	93.94 234	85.81 139	82.42 268	91.32 254	70.33 227	97.06 225	80.33 228	90.23 184	94.14 222

MDTV_nov1_ep13_2view						55.91 373	87.62 326		73.32 330	84.59 224		70.33 227		74.65 286		95.50 164

ACMM	84.12 9	89.14 133	88.48 137	91.12 161	94.65 160	81.22 167	95.31 88	96.12 116	85.31 154	85.92 185	94.34 144	70.19 229	98.06 145	85.65 144	88.86 209	94.08 227
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ET-MVSNet_ETH3D		87.51 187	85.91 216	92.32 109	93.70 202	83.93 90	92.33 244	90.94 313	84.16 173	72.09 346	92.52 212	69.90 230	95.85 287	89.20 100	88.36 219	97.17 103

LPG-MVS_test		89.45 123	88.90 123	91.12 161	94.47 168	81.49 158	95.30 90	96.14 114	86.73 122	85.45 202	95.16 114	69.89 231	98.10 133	87.70 117	89.23 202	93.77 246

LGP-MVS_train				91.12 161	94.47 168	81.49 158		96.14 114	86.73 122	85.45 202	95.16 114	69.89 231	98.10 133	87.70 117	89.23 202	93.77 246

CHOSEN 280x420		85.15 252	83.99 255	88.65 252	92.47 233	78.40 241	79.68 362	92.76 262	74.90 316	81.41 280	89.59 294	69.85 233	95.51 300	79.92 233	95.29 112	92.03 303

LTVRE_ROB	82.13 13	86.26 232	84.90 241	90.34 198	94.44 172	81.50 156	92.31 246	94.89 197	83.03 201	79.63 305	92.67 207	69.69 234	97.79 159	71.20 302	86.26 244	91.72 308
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	88.74 148	87.29 164	93.08 72	92.70 230	85.39 64	96.57 35	96.43 94	78.74 275	80.85 286	96.07 81	69.64 235	99.01 61	78.01 253	96.65 91	94.83 188

MDTV_nov1_ep13			83.56 261		91.69 259	69.93 341	87.75 323	91.54 298	78.60 277	84.86 219	88.90 302	69.54 236	96.03 278	70.25 308	88.93 208

AUN-MVS		87.78 172	86.54 190	91.48 147	94.82 152	81.05 171	93.91 188	93.93 235	83.00 202	86.93 164	93.53 179	69.50 237	97.67 166	86.14 136	77.12 331	95.73 160

PatchT		82.68 277	81.27 279	86.89 296	90.09 312	70.94 335	84.06 349	90.15 324	74.91 315	85.63 191	83.57 346	69.37 238	94.87 313	65.19 337	88.50 215	94.84 187

RRT_MVS		89.09 136	88.62 131	90.49 187	92.85 227	79.65 213	96.41 37	94.41 218	88.22 85	85.50 198	94.77 130	69.36 239	97.31 204	89.33 98	86.73 241	94.51 203

VPNet		88.20 161	87.47 160	90.39 194	93.56 205	79.46 216	94.04 176	95.54 159	88.67 70	86.96 163	94.58 140	69.33 240	97.15 218	84.05 164	80.53 308	94.56 199

ACMP	84.23 8	89.01 142	88.35 138	90.99 172	94.73 154	81.27 164	95.07 108	95.89 134	86.48 125	83.67 250	94.30 147	69.33 240	97.99 150	87.10 130	88.55 212	93.72 250
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 320				9.81 376	69.31 242	95.53 298	76.65 265

tpmvs		83.35 274	82.07 272	87.20 289	91.07 280	71.00 334	88.31 318	91.70 292	78.91 269	80.49 292	87.18 328	69.30 243	97.08 223	68.12 325	83.56 265	93.51 259

thres200		87.21 203	86.24 202	90.12 206	95.36 125	78.53 236	93.26 213	92.10 280	86.42 127	88.00 143	91.11 263	69.24 244	98.00 149	69.58 315	91.04 178	93.83 240

tfpn200view9		87.58 184	86.64 184	90.41 193	95.99 106	78.64 233	94.58 137	91.98 286	86.94 117	88.09 138	91.77 239	69.18 245	98.10 133	70.13 311	91.10 173	94.48 209

thres400		87.62 181	86.64 184	90.57 181	95.99 106	78.64 233	94.58 137	91.98 286	86.94 117	88.09 138	91.77 239	69.18 245	98.10 133	70.13 311	91.10 173	94.96 181

tfpnnormal		84.72 259	83.23 264	89.20 238	92.79 229	80.05 200	94.48 142	95.81 138	82.38 213	81.08 284	91.21 256	69.01 247	96.95 231	61.69 349	80.59 306	90.58 331

thres100view900		87.63 179	86.71 181	90.38 196	96.12 97	78.55 235	95.03 111	91.58 296	87.15 110	88.06 141	92.29 220	68.91 248	98.10 133	70.13 311	91.10 173	94.48 209

thres600view7		87.65 176	86.67 183	90.59 180	96.08 101	78.72 231	94.88 119	91.58 296	87.06 113	88.08 140	92.30 219	68.91 248	98.10 133	70.05 314	91.10 173	94.96 181

PatchMatch-RL		86.77 219	85.54 225	90.47 192	95.88 109	82.71 130	90.54 280	92.31 273	79.82 259	84.32 236	91.57 250	68.77 250	96.39 264	73.16 295	93.48 147	92.32 299

XVG-OURS		89.40 128	88.70 126	91.52 144	94.06 183	81.46 160	91.27 269	96.07 119	86.14 135	88.89 129	95.77 94	68.73 251	97.26 211	87.39 122	89.96 188	95.83 154

TR-MVS		86.78 216	85.76 222	89.82 219	94.37 174	78.41 240	92.47 238	92.83 260	81.11 246	86.36 178	92.40 215	68.73 251	97.48 184	73.75 293	89.85 192	93.57 255

tpm		84.73 258	84.02 254	86.87 297	90.33 307	68.90 344	89.06 308	89.94 330	80.85 248	85.75 187	89.86 290	68.54 253	95.97 281	77.76 254	84.05 259	95.75 157

FMVSNet3		87.40 192	86.11 206	91.30 155	93.79 199	83.64 98	94.20 164	94.81 205	83.89 180	84.37 231	91.87 238	68.45 254	96.56 253	78.23 250	85.36 248	93.70 252

MVP-Stereo		85.97 235	84.86 242	89.32 235	90.92 288	82.19 142	92.11 252	94.19 226	78.76 274	78.77 311	91.63 245	68.38 255	96.56 253	75.01 283	93.95 135	89.20 341
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 281	80.27 287	87.01 291	91.09 279	71.02 333	87.38 328	91.53 299	66.25 352	80.17 295	86.35 334	68.22 256	96.15 275	69.16 316	82.29 279	93.86 238

tpm2		84.08 264	82.94 267	87.48 280	91.39 267	71.27 329	89.23 305	90.37 321	71.95 340	84.64 222	89.33 297	67.30 257	96.55 255	75.17 280	87.09 238	94.63 193

test-LLR		85.87 237	85.41 228	87.25 285	90.95 284	71.67 327	89.55 297	89.88 333	83.41 193	84.54 225	87.95 317	67.25 258	95.11 309	81.82 201	93.37 150	94.97 178

test0.0.03 1		82.41 279	81.69 275	84.59 319	88.23 334	72.89 310	90.24 287	87.83 344	83.41 193	79.86 302	89.78 292	67.25 258	88.99 359	65.18 338	83.42 268	91.90 306

CVMVSNet		84.69 260	84.79 244	84.37 321	91.84 251	64.92 357	93.70 195	91.47 301	66.19 353	86.16 183	95.28 108	67.18 260	93.33 332	80.89 218	90.42 182	94.88 186

iter_conf_final		89.42 125	88.69 127	91.60 141	95.12 136	82.93 121	95.75 70	92.14 279	87.32 109	87.12 161	94.07 154	67.09 261	97.55 178	90.61 87	89.01 206	94.32 215

thisisatest0515		87.33 195	85.99 211	91.37 152	93.49 206	79.55 214	90.63 279	89.56 338	80.17 253	87.56 152	90.86 268	67.07 262	98.28 122	81.50 208	93.02 156	96.29 133

tttt0517		88.61 151	87.78 153	91.11 164	94.96 142	77.81 257	95.35 86	89.69 335	85.09 160	88.05 142	94.59 139	66.93 263	98.48 102	83.27 174	92.13 168	97.03 110

our_test_3		81.93 282	80.46 285	86.33 304	88.46 331	73.48 306	88.46 316	91.11 307	76.46 297	76.69 323	88.25 313	66.89 264	94.36 316	68.75 318	79.08 322	91.14 321

thisisatest0530		88.67 149	87.61 156	91.86 130	94.87 148	80.07 198	94.63 135	89.90 332	84.00 177	88.46 135	93.78 173	66.88 265	98.46 105	83.30 173	92.65 161	97.06 107

IterMVS-SCA-FT		85.45 243	84.53 249	88.18 264	91.71 257	76.87 273	90.19 290	92.65 266	85.40 152	81.44 279	90.54 275	66.79 266	95.00 312	81.04 213	81.05 297	92.66 288

SCA		86.32 231	85.18 234	89.73 225	92.15 240	76.60 276	91.12 272	91.69 293	83.53 190	85.50 198	88.81 303	66.79 266	96.48 258	76.65 265	90.35 183	96.12 140

D2MVS		85.90 236	85.09 236	88.35 258	90.79 293	77.42 266	91.83 257	95.70 146	80.77 249	80.08 299	90.02 286	66.74 268	96.37 265	81.88 200	87.97 226	91.26 317

IterMVS		84.88 256	83.98 256	87.60 275	91.44 263	76.03 284	90.18 291	92.41 269	83.24 198	81.06 285	90.42 279	66.60 269	94.28 319	79.46 236	80.98 302	92.48 292
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 197	85.98 212	91.08 165	94.01 186	83.10 112	95.14 104	94.94 192	83.57 187	84.37 231	91.64 242	66.59 270	96.34 268	78.23 250	85.36 248	93.79 241

test1		87.26 197	85.98 212	91.08 165	94.01 186	83.10 112	95.14 104	94.94 192	83.57 187	84.37 231	91.64 242	66.59 270	96.34 268	78.23 250	85.36 248	93.79 241

FMVSNet2		87.19 205	85.82 218	91.30 155	94.01 186	83.67 97	94.79 125	94.94 192	83.57 187	83.88 245	92.05 233	66.59 270	96.51 256	77.56 257	85.01 251	93.73 249

EPMVS		83.90 269	82.70 271	87.51 277	90.23 310	72.67 314	88.62 314	81.96 361	81.37 239	85.01 217	88.34 311	66.31 273	94.45 314	75.30 279	87.12 237	95.43 166

ppachtmachnet_test		81.84 283	80.07 291	87.15 290	88.46 331	74.43 298	89.04 309	92.16 277	75.33 310	77.75 316	88.99 300	66.20 274	95.37 305	65.12 339	77.60 327	91.65 309

MDA-MVSNet_test_wron		79.21 310	77.19 312	85.29 314	88.22 335	72.77 312	85.87 336	90.06 327	74.34 320	62.62 359	87.56 323	66.14 275	91.99 345	66.90 333	73.01 339	91.10 324

YYNet1		79.22 309	77.20 311	85.28 315	88.20 336	72.66 315	85.87 336	90.05 329	74.33 321	62.70 358	87.61 322	66.09 276	92.03 343	66.94 330	72.97 340	91.15 320

JIA-IIPM		81.04 295	78.98 305	87.25 285	88.64 327	73.48 306	81.75 357	89.61 337	73.19 331	82.05 273	73.71 361	66.07 277	95.87 286	71.18 304	84.60 254	92.41 295

MSDG		84.86 257	83.09 265	90.14 205	93.80 197	80.05 200	89.18 306	93.09 254	78.89 270	78.19 312	91.91 236	65.86 278	97.27 209	68.47 320	88.45 216	93.11 274

FE-MVS		87.40 192	86.02 210	91.57 143	94.56 165	79.69 212	90.27 283	93.72 245	80.57 250	88.80 130	91.62 246	65.32 279	98.59 97	74.97 284	94.33 132	96.44 129

jajsoiax		88.24 160	87.50 158	90.48 189	90.89 290	80.14 195	95.31 88	95.65 152	84.97 162	84.24 239	94.02 159	65.31 280	97.42 191	88.56 106	88.52 214	93.89 233

cascas		86.43 230	84.98 238	90.80 177	92.10 244	80.92 176	90.24 287	95.91 131	73.10 332	83.57 254	88.39 310	65.15 281	97.46 186	84.90 153	91.43 171	94.03 230

ADS-MVSNet2		81.66 287	79.71 295	87.50 278	91.35 269	74.19 300	83.33 352	88.48 342	72.90 334	82.24 271	85.77 338	64.98 282	93.20 335	64.57 341	83.74 261	95.12 174

ADS-MVSNet		81.56 289	79.78 293	86.90 295	91.35 269	71.82 324	83.33 352	89.16 339	72.90 334	82.24 271	85.77 338	64.98 282	93.76 326	64.57 341	83.74 261	95.12 174

pmmvs5		84.21 263	82.84 270	88.34 259	88.95 325	76.94 272	92.41 239	91.91 290	75.63 307	80.28 294	91.18 259	64.59 284	95.57 296	77.09 263	83.47 266	92.53 291

PVSNet	78.82 18	85.55 242	84.65 246	88.23 263	94.72 155	71.93 322	87.12 330	92.75 263	78.80 273	84.95 218	90.53 276	64.43 285	96.71 241	74.74 285	93.86 137	96.06 145

UGNet		89.95 108	88.95 120	92.95 79	94.51 167	83.31 107	95.70 73	95.23 179	89.37 51	87.58 151	93.94 164	64.00 286	98.78 86	83.92 166	96.31 97	96.74 121
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
RPSCF		85.07 253	84.27 250	87.48 280	92.91 225	70.62 337	91.69 262	92.46 268	76.20 303	82.67 267	95.22 111	63.94 287	97.29 208	77.51 258	85.80 246	94.53 200

bld_raw_dy_0_64		87.60 183	86.73 179	90.21 200	91.72 255	80.26 192	95.09 107	88.61 340	85.68 144	85.55 192	94.38 143	63.93 288	96.66 242	87.73 116	87.84 229	93.72 250

iter_conf05		88.85 144	88.08 147	91.17 160	94.27 178	81.64 153	95.18 100	92.15 278	86.23 132	87.28 158	94.07 154	63.89 289	97.55 178	90.63 86	89.00 207	94.32 215

mvs_tets		88.06 166	87.28 165	90.38 196	90.94 286	79.88 207	95.22 97	95.66 150	85.10 159	84.21 240	93.94 164	63.53 290	97.40 198	88.50 107	88.40 218	93.87 236

test1111		89.10 134	88.64 128	90.48 189	95.53 122	74.97 292	96.08 54	84.89 353	88.13 90	90.16 112	96.65 57	63.29 291	98.10 133	86.14 136	96.90 84	98.39 37

Anonymous20231211		86.59 223	85.13 235	90.98 174	96.52 87	81.50 156	96.14 51	96.16 113	73.78 326	83.65 251	92.15 224	63.26 292	97.37 202	82.82 182	81.74 288	94.06 228

ECVR-MVS		89.09 136	88.53 132	90.77 178	95.62 119	75.89 285	96.16 49	84.22 355	87.89 97	90.20 110	96.65 57	63.19 293	98.10 133	85.90 141	96.94 82	98.33 41

dp		81.47 291	80.23 288	85.17 316	89.92 316	65.49 355	86.74 331	90.10 326	76.30 301	81.10 283	87.12 329	62.81 294	95.92 283	68.13 324	79.88 315	94.09 226

LFMVS		90.08 102	89.13 116	92.95 79	96.71 77	82.32 141	96.08 54	89.91 331	86.79 120	92.15 76	96.81 50	62.60 295	98.34 116	87.18 125	93.90 136	98.19 56

Anonymous20231206		81.03 296	79.77 294	84.82 318	87.85 340	70.26 339	91.42 266	92.08 281	73.67 327	77.75 316	89.25 298	62.43 296	93.08 336	61.50 350	82.00 284	91.12 322

VDD-MVS		90.74 88	89.92 100	93.20 67	96.27 93	83.02 117	95.73 71	93.86 239	88.42 78	92.53 68	96.84 47	62.09 297	98.64 91	90.95 81	92.62 162	97.93 73

MS-PatchMatch		85.05 254	84.16 251	87.73 273	91.42 266	78.51 237	91.25 270	93.53 247	77.50 289	80.15 296	91.58 248	61.99 298	95.51 300	75.69 275	94.35 131	89.16 342

OurMVSNet-221017-0		85.35 247	84.64 247	87.49 279	90.77 294	72.59 318	94.01 179	94.40 219	84.72 168	79.62 306	93.17 191	61.91 299	96.72 239	81.99 197	81.16 293	93.16 272

test_vis1_n_1920		89.39 129	89.84 101	88.04 268	92.97 223	72.64 316	94.71 131	96.03 124	86.18 133	91.94 83	96.56 65	61.63 300	95.74 293	93.42 28	95.11 116	95.74 158

test20.03		79.95 304	79.08 303	82.55 330	85.79 349	67.74 349	91.09 273	91.08 308	81.23 244	74.48 338	89.96 289	61.63 300	90.15 353	60.08 353	76.38 333	89.76 334

DSMNet-mixed		76.94 318	76.29 317	78.89 337	83.10 358	56.11 372	87.78 322	79.77 365	60.65 359	75.64 330	88.71 306	61.56 302	88.34 360	60.07 354	89.29 201	92.21 302

Anonymous20240529		88.09 164	86.59 188	92.58 97	96.53 86	81.92 148	95.99 59	95.84 137	74.11 323	89.06 127	95.21 113	61.44 303	98.81 84	83.67 171	87.47 231	97.01 111

IB-MVS	80.51 15	85.24 251	83.26 263	91.19 158	92.13 242	79.86 208	91.75 259	91.29 305	83.28 197	80.66 289	88.49 309	61.28 304	98.46 105	80.99 216	79.46 319	95.25 172
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		86.61 221	85.27 233	90.66 179	91.33 271	78.71 232	90.40 282	93.81 242	85.34 153	85.12 215	89.57 295	61.25 305	97.11 222	80.99 216	89.59 196	96.15 137

N_pmnet		68.89 327	68.44 329	70.23 347	89.07 324	28.79 381	88.06 319	19.50 382	69.47 348	71.86 348	84.93 340	61.24 306	91.75 347	54.70 360	77.15 330	90.15 332

EU-MVSNet		81.32 293	80.95 281	82.42 332	88.50 330	63.67 358	93.32 206	91.33 303	64.02 356	80.57 291	92.83 202	61.21 307	92.27 342	76.34 269	80.38 311	91.32 315

VDDNet		89.56 119	88.49 136	92.76 86	95.07 137	82.09 143	96.30 41	93.19 253	81.05 247	91.88 84	96.86 46	61.16 308	98.33 118	88.43 108	92.49 165	97.84 78

PVSNet_0	73.20 20	77.22 317	74.83 322	84.37 321	90.70 298	71.10 332	83.09 354	89.67 336	72.81 336	73.93 340	83.13 348	60.79 309	93.70 328	68.54 319	50.84 368	88.30 349

SixPastTwentyTwo		83.91 268	82.90 268	86.92 294	90.99 282	70.67 336	93.48 201	91.99 285	85.54 149	77.62 318	92.11 228	60.59 310	96.87 236	76.05 273	77.75 326	93.20 270

gg-mvs-nofinetune		81.77 284	79.37 297	88.99 245	90.85 292	77.73 261	86.29 334	79.63 366	74.88 317	83.19 262	69.05 364	60.34 311	96.11 276	75.46 277	94.64 123	93.11 274

MDA-MVSNet-bldmvs		78.85 311	76.31 316	86.46 301	89.76 318	73.88 302	88.79 311	90.42 320	79.16 267	59.18 360	88.33 312	60.20 312	94.04 321	62.00 348	68.96 351	91.48 313

pmmvs6		83.42 272	81.60 276	88.87 246	88.01 337	77.87 255	94.96 114	94.24 225	74.67 318	78.80 310	91.09 264	60.17 313	96.49 257	77.06 264	75.40 337	92.23 301

ACMH	80.38 17	85.36 246	83.68 259	90.39 194	94.45 171	80.63 183	94.73 129	94.85 201	82.09 218	77.24 319	92.65 208	60.01 314	97.58 175	72.25 299	84.87 252	92.96 279
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 271	89.73 320	77.91 252	87.80 321	78.23 370		80.58 290	83.86 344	59.88 315	95.33 306	71.20 302	92.22 167	90.60 330

UniMVSNet_ETH3D		87.53 186	86.37 195	91.00 171	92.44 234	78.96 230	94.74 128	95.61 154	84.07 176	85.36 212	94.52 141	59.78 316	97.34 203	82.93 178	87.88 227	96.71 122

pmmvs-eth3d		80.97 297	78.72 306	87.74 272	84.99 354	79.97 206	90.11 292	91.65 294	75.36 309	73.51 341	86.03 335	59.45 317	93.96 324	75.17 280	72.21 342	89.29 340

test_0402		81.30 294	79.17 302	87.67 274	93.19 213	78.17 247	92.98 225	91.71 291	75.25 311	76.02 329	90.31 280	59.23 318	96.37 265	50.22 363	83.63 264	88.47 348

KD-MVS_self_test		80.20 302	79.24 299	83.07 328	85.64 351	65.29 356	91.01 274	93.93 235	78.71 276	76.32 325	86.40 333	59.20 319	92.93 338	72.59 297	69.35 348	91.00 326

FMVSNet1		85.85 238	84.11 252	91.08 165	92.81 228	83.10 112	95.14 104	94.94 192	81.64 233	82.68 266	91.64 242	59.01 320	96.34 268	75.37 278	83.78 260	93.79 241

COLMAP_ROB	80.39 16	83.96 266	82.04 273	89.74 223	95.28 127	79.75 210	94.25 160	92.28 274	75.17 312	78.02 315	93.77 174	58.60 321	97.84 158	65.06 340	85.92 245	91.63 310
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	85.05 254	83.46 262	89.82 219	94.66 159	79.37 219	94.44 147	94.12 231	82.19 217	78.04 314	92.82 203	58.23 322	97.54 180	73.77 292	82.90 274	92.54 290

CMPMVS	59.16 21	80.52 299	79.20 301	84.48 320	83.98 355	67.63 350	89.95 295	93.84 241	64.79 355	66.81 356	91.14 262	57.93 323	95.17 307	76.25 270	88.10 222	90.65 327
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tt0805		86.92 212	85.74 224	90.48 189	92.22 238	79.98 205	95.63 79	94.88 199	83.83 182	84.74 221	92.80 205	57.61 324	97.67 166	85.48 147	84.42 255	93.79 241

ITE_SJBPF				88.24 262	91.88 250	77.05 271		92.92 257	85.54 149	80.13 298	93.30 186	57.29 325	96.20 272	72.46 298	84.71 253	91.49 312

TESTMET0.1,1		83.74 270	82.85 269	86.42 303	89.96 315	71.21 331	89.55 297	87.88 343	77.41 290	83.37 258	87.31 325	56.71 326	93.65 329	80.62 223	92.85 160	94.40 212

UnsupCasMVSNet_eth		80.07 303	78.27 307	85.46 312	85.24 353	72.63 317	88.45 317	94.87 200	82.99 203	71.64 349	88.07 316	56.34 327	91.75 347	73.48 294	63.36 360	92.01 304

test_fmvs1		87.34 194	87.56 157	86.68 300	90.59 301	71.80 325	94.01 179	94.04 233	78.30 282	91.97 80	95.22 111	56.28 328	93.71 327	92.89 36	94.71 119	94.52 201

K. test v3		81.59 288	80.15 290	85.91 309	89.89 317	69.42 343	92.57 236	87.71 345	85.56 148	73.44 342	89.71 293	55.58 329	95.52 299	77.17 261	69.76 347	92.78 286

test-mter		84.54 261	83.64 260	87.25 285	90.95 284	71.67 327	89.55 297	89.88 333	79.17 266	84.54 225	87.95 317	55.56 330	95.11 309	81.82 201	93.37 150	94.97 178

lessismore_v0				86.04 305	88.46 331	68.78 345		80.59 364		73.01 344	90.11 284	55.39 331	96.43 263	75.06 282	65.06 357	92.90 281

MVS-HIRNet		73.70 322	72.20 325	78.18 340	91.81 253	56.42 371	82.94 355	82.58 359	55.24 361	68.88 353	66.48 365	55.32 332	95.13 308	58.12 356	88.42 217	83.01 356

test2506		87.21 203	86.28 200	90.02 212	95.62 119	73.64 304	96.25 46	71.38 374	87.89 97	90.45 106	96.65 57	55.29 333	98.09 141	86.03 140	96.94 82	98.33 41

new-patchmatchnet		76.41 319	75.17 321	80.13 334	82.65 360	59.61 364	87.66 325	91.08 308	78.23 285	69.85 352	83.22 347	54.76 334	91.63 349	64.14 343	64.89 358	89.16 342

Anonymous202405211		87.68 174	86.13 204	92.31 110	96.66 79	80.74 181	94.87 120	91.49 300	80.47 251	89.46 121	95.44 103	54.72 335	98.23 124	82.19 193	89.89 190	97.97 70

XVG-ACMP-BASELINE		86.00 234	84.84 243	89.45 234	91.20 273	78.00 250	91.70 261	95.55 157	85.05 161	82.97 263	92.25 222	54.49 336	97.48 184	82.93 178	87.45 233	92.89 282

USDC		82.76 275	81.26 280	87.26 284	91.17 275	74.55 295	89.27 303	93.39 250	78.26 284	75.30 332	92.08 230	54.43 337	96.63 244	71.64 300	85.79 247	90.61 328

AllTest		83.42 272	81.39 278	89.52 231	95.01 138	77.79 258	93.12 218	90.89 315	77.41 290	76.12 327	93.34 182	54.08 338	97.51 182	68.31 322	84.27 257	93.26 265

TestCases				89.52 231	95.01 138	77.79 258		90.89 315	77.41 290	76.12 327	93.34 182	54.08 338	97.51 182	68.31 322	84.27 257	93.26 265

KD-MVS_2432*1600		78.50 312	76.02 319	85.93 307	86.22 345	74.47 296	84.80 345	92.33 271	79.29 264	76.98 321	85.92 336	53.81 340	93.97 322	67.39 327	57.42 365	89.36 337

miper_refine_blended		78.50 312	76.02 319	85.93 307	86.22 345	74.47 296	84.80 345	92.33 271	79.29 264	76.98 321	85.92 336	53.81 340	93.97 322	67.39 327	57.42 365	89.36 337

MIMVSNet		82.59 278	80.53 283	88.76 247	91.51 262	78.32 243	86.57 333	90.13 325	79.32 263	80.70 288	88.69 308	52.98 342	93.07 337	66.03 335	88.86 209	94.90 185

FMVSNet5		81.52 290	79.60 296	87.27 283	91.17 275	77.95 251	91.49 265	92.26 275	76.87 295	76.16 326	87.91 319	51.67 343	92.34 341	67.74 326	81.16 293	91.52 311

testgi		80.94 298	80.20 289	83.18 327	87.96 338	66.29 352	91.28 268	90.70 319	83.70 184	78.12 313	92.84 201	51.37 344	90.82 351	63.34 344	82.46 277	92.43 294

test_fmvs1_n		87.03 210	87.04 171	86.97 292	89.74 319	71.86 323	94.55 139	94.43 216	78.47 278	91.95 82	95.50 102	51.16 345	93.81 325	93.02 35	94.56 125	95.26 171

Anonymous20240521		80.44 300	79.21 300	84.11 324	85.75 350	67.89 347	92.86 229	93.23 252	75.61 308	75.59 331	87.47 324	50.03 346	94.33 317	71.14 305	81.21 292	90.12 333

UnsupCasMVSNet_bld		76.23 320	73.27 323	85.09 317	83.79 356	72.92 309	85.65 339	93.47 249	71.52 341	68.84 354	79.08 356	49.77 347	93.21 334	66.81 334	60.52 362	89.13 344

OpenMVS_ROB	74.94 19	79.51 307	77.03 314	86.93 293	87.00 342	76.23 283	92.33 244	90.74 318	68.93 349	74.52 337	88.23 314	49.58 348	96.62 245	57.64 357	84.29 256	87.94 350

TDRefinement		79.81 305	77.34 309	87.22 288	79.24 364	75.48 290	93.12 218	92.03 283	76.45 298	75.01 333	91.58 248	49.19 349	96.44 262	70.22 310	69.18 350	89.75 335

test_vis1_n		86.56 224	86.49 193	86.78 299	88.51 328	72.69 313	94.68 132	93.78 243	79.55 262	90.70 103	95.31 107	48.75 350	93.28 333	93.15 32	93.99 134	94.38 213

MIMVSNet1		79.38 308	77.28 310	85.69 311	86.35 344	73.67 303	91.61 264	92.75 263	78.11 287	72.64 345	88.12 315	48.16 351	91.97 346	60.32 352	77.49 328	91.43 314

MVS_0304		83.46 271	81.92 274	88.10 266	90.63 300	77.49 265	93.26 213	93.75 244	80.04 256	80.44 293	87.24 327	47.94 352	95.55 297	75.79 274	88.16 221	91.26 317

LF4IMVS		80.37 301	79.07 304	84.27 323	86.64 343	69.87 342	89.39 302	91.05 310	76.38 299	74.97 334	90.00 287	47.85 353	94.25 320	74.55 288	80.82 304	88.69 346

EG-PatchMatch MVS		82.37 280	80.34 286	88.46 255	90.27 308	79.35 220	92.80 231	94.33 221	77.14 294	73.26 343	90.18 282	47.47 354	96.72 239	70.25 308	87.32 236	89.30 339

test_fmvs2		83.98 265	84.03 253	83.83 326	87.16 341	67.53 351	93.93 185	92.89 258	77.62 288	86.89 169	93.53 179	47.18 355	92.02 344	90.54 88	86.51 242	91.93 305

TinyColmap		79.76 306	77.69 308	85.97 306	91.71 257	73.12 308	89.55 297	90.36 322	75.03 313	72.03 347	90.19 281	46.22 356	96.19 274	63.11 345	81.03 298	88.59 347

tmp_tt		35.64 342	39.24 344	24.84 358	14.87 382	23.90 382	62.71 368	51.51 381	6.58 376	36.66 372	62.08 369	44.37 357	30.34 378	52.40 362	22.00 375	20.27 373

new_pmnet		72.15 323	70.13 327	78.20 339	82.95 359	65.68 353	83.91 350	82.40 360	62.94 358	64.47 357	79.82 355	42.85 358	86.26 363	57.41 358	74.44 338	82.65 358

test_vis1_rt		77.96 315	76.46 315	82.48 331	85.89 348	71.74 326	90.25 285	78.89 367	71.03 345	71.30 350	81.35 353	42.49 359	91.05 350	84.55 158	82.37 278	84.65 353

EGC-MVSNET		61.97 331	56.37 335	78.77 338	89.63 321	73.50 305	89.12 307	82.79 358	0.21 379	1.24 380	84.80 341	39.48 360	90.04 354	44.13 365	75.94 336	72.79 363

pmmvs3		71.81 325	68.71 328	81.11 333	75.86 365	70.42 338	86.74 331	83.66 356	58.95 360	68.64 355	80.89 354	36.93 361	89.52 356	63.10 346	63.59 359	83.39 354

mvsany_test3		74.95 321	73.26 324	80.02 335	74.61 366	63.16 360	85.53 340	78.42 368	74.16 322	74.89 335	86.46 331	36.02 362	89.09 358	82.39 189	66.91 354	87.82 351

PM-MVS		78.11 314	76.12 318	84.09 325	83.54 357	70.08 340	88.97 310	85.27 352	79.93 257	74.73 336	86.43 332	34.70 363	93.48 330	79.43 239	72.06 343	88.72 345

ambc				83.06 329	79.99 362	63.51 359	77.47 363	92.86 259		74.34 339	84.45 343	28.74 364	95.06 311	73.06 296	68.89 352	90.61 328

test_method		50.52 338	48.47 340	56.66 354	52.26 380	18.98 383	41.51 372	81.40 362	10.10 374	44.59 369	75.01 360	28.51 365	68.16 372	53.54 361	49.31 369	82.83 357

DeepMVS_CX				56.31 355	74.23 367	51.81 374		56.67 380	44.85 366	48.54 366	75.16 359	27.87 366	58.74 376	40.92 369	52.22 367	58.39 369

test_fmvs3		77.67 316	77.16 313	79.22 336	79.52 363	61.14 362	92.34 243	91.64 295	73.98 324	78.86 309	86.59 330	27.38 367	87.03 361	88.12 112	75.97 335	89.50 336

test_f		71.95 324	70.87 326	75.21 343	74.21 368	59.37 365	85.07 344	85.82 349	65.25 354	70.42 351	83.13 348	23.62 368	82.93 368	78.32 248	71.94 344	83.33 355

FPMVS		64.63 330	62.55 332	70.88 346	70.80 370	56.71 367	84.42 348	84.42 354	51.78 364	49.57 364	81.61 352	23.49 369	81.48 369	40.61 370	76.25 334	74.46 362

APD_test1		69.04 326	66.26 330	77.36 342	80.51 361	62.79 361	85.46 341	83.51 357	54.11 363	59.14 361	84.79 342	23.40 370	89.61 355	55.22 359	70.24 346	79.68 361

ANet_high		58.88 335	54.22 339	72.86 344	56.50 379	56.67 368	80.75 359	86.00 348	73.09 333	37.39 371	64.63 368	22.17 371	79.49 371	43.51 366	23.96 373	82.43 359

EMVS		42.07 341	41.12 343	44.92 357	63.45 377	35.56 380	73.65 364	63.48 377	33.05 372	26.88 376	45.45 373	21.27 372	67.14 374	19.80 375	23.02 374	32.06 372

Gipuma		57.99 336	54.91 338	67.24 351	88.51 328	65.59 354	52.21 370	90.33 323	43.58 367	42.84 370	51.18 371	20.29 373	85.07 364	34.77 371	70.45 345	51.05 370
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 340	42.29 342	46.03 356	65.58 375	37.41 378	73.51 365	64.62 376	33.99 371	28.47 375	47.87 372	19.90 374	67.91 373	22.23 374	24.45 372	32.77 371

PMMVS2		59.60 332	56.40 334	69.21 350	68.83 373	46.58 376	73.02 367	77.48 371	55.07 362	49.21 365	72.95 363	17.43 375	80.04 370	49.32 364	44.33 370	80.99 360

LCM-MVSNet		66.00 328	62.16 333	77.51 341	64.51 376	58.29 366	83.87 351	90.90 314	48.17 365	54.69 362	73.31 362	16.83 376	86.75 362	65.47 336	61.67 361	87.48 352

test_vis3_rt		65.12 329	62.60 331	72.69 345	71.44 369	60.71 363	87.17 329	65.55 375	63.80 357	53.22 363	65.65 367	14.54 377	89.44 357	76.65 265	65.38 356	67.91 366

testf1		59.54 333	56.11 336	69.85 348	69.28 371	56.61 369	80.37 360	76.55 372	42.58 368	45.68 367	75.61 357	11.26 378	84.18 365	43.20 367	60.44 363	68.75 364

APD_test2		59.54 333	56.11 336	69.85 348	69.28 371	56.61 369	80.37 360	76.55 372	42.58 368	45.68 367	75.61 357	11.26 378	84.18 365	43.20 367	60.44 363	68.75 364

PMVS	47.18 22	52.22 337	48.46 341	63.48 352	45.72 381	46.20 377	73.41 366	78.31 369	41.03 370	30.06 373	65.68 366	6.05 380	83.43 367	30.04 372	65.86 355	60.80 367
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 339	38.59 345	57.77 353	56.52 378	48.77 375	55.38 369	58.64 379	29.33 373	28.96 374	52.65 370	4.68 381	64.62 375	28.11 373	33.07 371	59.93 368
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 344	20.48 347	23.63 359	68.59 374	36.41 379	49.57 371	6.85 383	9.37 375	7.89 377	4.46 379	4.03 382	31.37 377	17.47 376	16.07 376	3.12 374

test123		8.76 346	11.22 349	1.39 360	0.85 384	0.97 384	85.76 338	0.35 385	0.54 378	2.45 379	8.14 378	0.60 383	0.48 379	2.16 378	0.17 378	2.71 375

testmvs		8.92 345	11.52 348	1.12 361	1.06 383	0.46 385	86.02 335	0.65 384	0.62 377	2.74 378	9.52 377	0.31 384	0.45 380	2.38 377	0.39 377	2.46 376

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		7.82 347	10.43 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	93.88 169	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

FOURS1					98.86 1	85.54 63	98.29 1	97.49 5	89.79 41	96.29 15

MSC_two_6792asdad				96.52 1	97.78 51	90.86 1		96.85 61					99.61 3	96.03 1	99.06 9	99.07 5

No_MVS				96.52 1	97.78 51	90.86 1		96.85 61					99.61 3	96.03 1	99.06 9	99.07 5

eth-test2					0.00 385

eth-test					0.00 385

IU-MVS					98.77 5	86.00 47		96.84 63	81.26 242	97.26 7				95.50 10	99.13 3	99.03 7

save fliter					97.85 46	85.63 62	95.21 98	96.82 66	89.44 48

test_0728_SECOND				95.01 15	98.79 2	86.43 36	97.09 16	97.49 5					99.61 3	95.62 8	99.08 7	98.99 8

GSMVS																96.12 140

test_part2					98.55 12	87.22 16				96.40 14

MTGPA								96.97 48

MTMP							96.16 49	60.64 378

gm-plane-assit					89.60 322	68.00 346			77.28 293		88.99 300		97.57 176	79.44 238

test9_res														91.91 65	98.71 30	98.07 64

agg_prior2														90.54 88	98.68 35	98.27 50

agg_prior					97.38 63	85.92 54		96.72 78		92.16 75			98.97 70

test_prior4						85.96 51	94.11 168

test_prior				93.82 56	97.29 67	84.49 77		96.88 59					98.87 77			98.11 63

旧先验2							93.36 205		71.25 343	94.37 28			97.13 221	86.74 131

新几何2							93.11 220

无先验							93.28 212	96.26 104	73.95 325				99.05 53	80.56 224		96.59 125

原ACMM2							92.94 227

testdata2													98.75 87	78.30 249

testdata1							92.15 250		87.94 93

plane_prior7					94.70 157	82.74 127

plane_prior5								96.22 109					98.12 131	88.15 109	89.99 186	94.63 193

plane_prior4											94.86 124

plane_prior3						82.75 125			90.26 31	86.91 166

plane_prior2							95.85 65		90.81 15

plane_prior1					94.59 161

plane_prior						82.73 128	95.21 98		89.66 45						89.88 191

n2								0.00 386

nn								0.00 386

door-mid								85.49 350

test11								96.57 89

door								85.33 351

HQP5-MVS						81.56 154

HQP-NCC					94.17 180		94.39 152		88.81 65	85.43 205

ACMP_Plane					94.17 180		94.39 152		88.81 65	85.43 205

BP-MVS														87.11 128

HQP4-MVS										85.43 205			97.96 152			94.51 203

HQP3-MVS								96.04 122							89.77 193

NP-MVS					94.37 174	82.42 137					93.98 162

ACMMP++_ref															87.47 231

ACMMP++															88.01 225

High-resolution multi-view benchmark