High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 45					97.53 1	89.67 1	96.44 9	94.41 30

No_MVS				89.16 1	94.34 27	75.53 2		92.99 45					97.53 1	89.67 1	96.44 9	94.41 30

MSP-MVS		89.51 4	89.91 5	88.30 9	94.28 30	73.46 16	92.90 16	94.11 6	80.27 8	91.35 14	94.16 34	78.35 13	96.77 22	89.59 3	94.22 56	94.67 22
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
DVP-MVS++		90.23 1	91.01 1	87.89 22	94.34 27	71.25 55	95.06 1	94.23 3	78.38 31	92.78 4	95.74 6	82.45 3	97.49 3	89.42 4	96.68 2	94.95 8

test_0728_THIRD									78.38 31	92.12 9	95.78 4	81.46 7	97.40 7	89.42 4	96.57 7	94.67 22

APDe-MVS		89.15 6	89.63 6	87.73 26	94.49 18	71.69 50	93.83 4	93.96 13	75.70 87	91.06 16	96.03 1	76.84 14	97.03 15	89.09 6	95.65 27	94.47 29

DVP-MVS		89.60 3	90.35 3	87.33 38	95.27 5	71.25 55	93.49 9	92.73 59	77.33 46	92.12 9	95.78 4	80.98 9	97.40 7	89.08 7	96.41 12	93.33 76
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				87.71 30	95.34 1	71.43 54	93.49 9	94.23 3					97.49 3	89.08 7	96.41 12	94.21 40

SED-MVS		90.08 2	90.85 2	87.77 24	95.30 2	70.98 61	93.57 7	94.06 10	77.24 48	93.10 1	95.72 8	82.99 1	97.44 5	89.07 9	96.63 4	94.88 12

test_241102_TWO								94.06 10	77.24 48	92.78 4	95.72 8	81.26 8	97.44 5	89.07 9	96.58 6	94.26 39

IU-MVS					95.30 2	71.25 55		92.95 51	66.81 233	92.39 6				88.94 11	96.63 4	94.85 17

MP-MVS-pluss		87.67 19	87.72 19	87.54 34	93.64 44	72.04 47	89.80 77	93.50 25	75.17 96	86.34 33	95.29 12	70.86 53	96.00 47	88.78 12	96.04 16	94.58 25
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SMA-MVS		89.08 7	89.23 7	88.61 5	94.25 31	73.73 9	92.40 23	93.63 21	74.77 103	92.29 7	95.97 2	74.28 29	97.24 11	88.58 13	96.91 1	94.87 14
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
CNVR-MVS		88.93 9	89.13 9	88.33 7	94.77 12	73.82 8	90.51 59	93.00 43	80.90 5	88.06 25	94.06 38	76.43 16	96.84 19	88.48 14	95.99 18	94.34 35

TSAR-MVS + MP.		88.02 16	88.11 15	87.72 28	93.68 43	72.13 45	91.41 45	92.35 74	74.62 107	88.90 20	93.85 44	75.75 20	96.00 47	87.80 15	94.63 45	95.04 6
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMMP_NAP		88.05 15	88.08 16	87.94 17	93.70 41	73.05 21	90.86 54	93.59 23	76.27 77	88.14 23	95.09 14	71.06 52	96.67 27	87.67 16	96.37 14	94.09 44

SD-MVS		88.06 13	88.50 13	86.71 49	92.60 66	72.71 28	91.81 40	93.19 35	77.87 34	90.32 17	94.00 40	74.83 23	93.78 134	87.63 17	94.27 55	93.65 63
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
SteuartSystems-ACMMP		88.72 10	88.86 10	88.32 8	92.14 69	72.96 24	93.73 5	93.67 20	80.19 10	88.10 24	94.80 15	73.76 33	97.11 13	87.51 18	95.82 21	94.90 11
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		89.02 8	89.15 8	88.63 4	95.01 9	76.03 1	92.38 26	92.85 54	80.26 9	87.78 27	94.27 30	75.89 19	96.81 21	87.45 19	96.44 9	93.05 86

DPE-MVS		89.48 5	89.98 4	88.01 14	94.80 11	72.69 30	91.59 41	94.10 8	75.90 83	92.29 7	95.66 10	81.67 6	97.38 9	87.44 20	96.34 15	93.95 49
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SF-MVS		88.46 11	88.74 11	87.64 33	92.78 61	71.95 48	92.40 23	94.74 2	75.71 85	89.16 19	95.10 13	75.65 21	96.19 41	87.07 21	96.01 17	94.79 19

9.14			88.26 14		92.84 60		91.52 44	94.75 1	73.93 121	88.57 22	94.67 17	75.57 22	95.79 51	86.77 22	95.76 23

MTAPA		87.23 26	87.00 27	87.90 20	94.18 35	74.25 5	86.58 174	92.02 85	79.45 17	85.88 35	94.80 15	68.07 77	96.21 40	86.69 23	95.34 31	93.23 79

DeepPCF-MVS	80.84 1	88.10 12	88.56 12	86.73 48	92.24 68	69.03 93	89.57 83	93.39 30	77.53 43	89.79 18	94.12 35	78.98 12	96.58 33	85.66 24	95.72 24	94.58 25

MP-MVS		87.71 18	87.64 20	87.93 19	94.36 26	73.88 6	92.71 22	92.65 64	77.57 39	83.84 69	94.40 28	72.24 42	96.28 38	85.65 25	95.30 33	93.62 66
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		87.94 17	87.85 18	88.20 11	94.39 24	73.33 18	93.03 14	93.81 17	76.81 61	85.24 42	94.32 29	71.76 46	96.93 17	85.53 26	95.79 22	94.32 36

HPM-MVS		87.11 28	86.98 28	87.50 36	93.88 39	72.16 44	92.19 32	93.33 31	76.07 80	83.81 70	93.95 43	69.77 65	96.01 46	85.15 27	94.66 44	94.32 36
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
train_agg		86.43 37	86.20 39	87.13 42	93.26 50	72.96 24	88.75 106	91.89 93	68.69 218	85.00 45	93.10 54	74.43 26	95.41 65	84.97 28	95.71 25	93.02 88

test9_res														84.90 29	95.70 26	92.87 92

NCCC		88.06 13	88.01 17	88.24 10	94.41 22	73.62 10	91.22 50	92.83 55	81.50 3	85.79 37	93.47 49	73.02 39	97.00 16	84.90 29	94.94 37	94.10 43

MCST-MVS		87.37 25	87.25 24	87.73 26	94.53 17	72.46 37	89.82 75	93.82 16	73.07 140	84.86 50	92.89 61	76.22 17	96.33 36	84.89 31	95.13 34	94.40 32

DeepC-MVS	79.81 2	87.08 30	86.88 32	87.69 31	91.16 80	72.32 42	90.31 66	93.94 14	77.12 53	82.82 83	94.23 32	72.13 44	97.09 14	84.83 32	95.37 30	93.65 63
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS		86.73 32	86.67 33	86.91 44	94.11 37	72.11 46	92.37 27	92.56 67	74.50 108	86.84 31	94.65 18	67.31 85	95.77 52	84.80 33	92.85 65	92.84 93

ZD-MVS					94.38 25	72.22 43		92.67 61	70.98 171	87.75 28	94.07 37	74.01 32	96.70 25	84.66 34	94.84 41

PC_three_1452									68.21 225	92.02 12	94.00 40	82.09 5	95.98 49	84.58 35	96.68 2	94.95 8

HFP-MVS		87.58 20	87.47 22	87.94 17	94.58 16	73.54 14	93.04 12	93.24 33	76.78 63	84.91 47	94.44 26	70.78 54	96.61 30	84.53 36	94.89 39	93.66 59

ACMMPR		87.44 21	87.23 25	88.08 13	94.64 13	73.59 11	93.04 12	93.20 34	76.78 63	84.66 54	94.52 19	68.81 75	96.65 28	84.53 36	94.90 38	94.00 48

region2R		87.42 23	87.20 26	88.09 12	94.63 14	73.55 12	93.03 14	93.12 37	76.73 66	84.45 58	94.52 19	69.09 71	96.70 25	84.37 38	94.83 42	94.03 47

CANet		86.45 36	86.10 43	87.51 35	90.09 101	70.94 65	89.70 81	92.59 66	81.78 2	81.32 98	91.43 93	70.34 58	97.23 12	84.26 39	93.36 62	94.37 33

APD-MVS		87.44 21	87.52 21	87.19 40	94.24 32	72.39 38	91.86 39	92.83 55	73.01 142	88.58 21	94.52 19	73.36 34	96.49 34	84.26 39	95.01 35	92.70 95
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CS-MVS		86.69 33	86.95 29	85.90 61	90.76 90	67.57 129	92.83 17	93.30 32	79.67 15	84.57 57	92.27 73	71.47 49	95.02 84	84.24 41	93.46 61	95.13 5

CP-MVS		87.11 28	86.92 30	87.68 32	94.20 34	73.86 7	93.98 3	92.82 58	76.62 68	83.68 71	94.46 23	67.93 78	95.95 50	84.20 42	94.39 51	93.23 79

GST-MVS		87.42 23	87.26 23	87.89 22	94.12 36	72.97 23	92.39 25	93.43 28	76.89 59	84.68 51	93.99 42	70.67 56	96.82 20	84.18 43	95.01 35	93.90 51

DROMVSNet		86.01 41	86.38 36	84.91 82	89.31 129	66.27 153	92.32 29	93.63 21	79.37 18	84.17 64	91.88 80	69.04 74	95.43 63	83.93 44	93.77 59	93.01 89

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 39	82.45 3	96.87 18	83.77 45	96.48 8	94.88 12

casdiffmvs_mvg		85.99 42	86.09 44	85.70 64	87.65 189	67.22 138	88.69 110	93.04 38	79.64 16	85.33 41	92.54 70	73.30 35	94.50 105	83.49 46	91.14 87	95.37 1
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
dcpmvs_2		85.63 49	86.15 42	84.06 113	91.71 75	64.94 184	86.47 177	91.87 95	73.63 127	86.60 32	93.02 59	76.57 15	91.87 211	83.36 47	92.15 73	95.35 2

test_prior2							88.85 102		75.41 91	84.91 47	93.54 46	74.28 29		83.31 48	95.86 20

PHI-MVS		86.43 37	86.17 41	87.24 39	90.88 87	70.96 63	92.27 31	94.07 9	72.45 145	85.22 43	91.90 79	69.47 67	96.42 35	83.28 49	95.94 19	94.35 34

XVS		87.18 27	86.91 31	88.00 15	94.42 20	73.33 18	92.78 18	92.99 45	79.14 19	83.67 72	94.17 33	67.45 83	96.60 31	83.06 50	94.50 48	94.07 45

X-MVStestdata		80.37 131	77.83 168	88.00 15	94.42 20	73.33 18	92.78 18	92.99 45	79.14 19	83.67 72	12.47 374	67.45 83	96.60 31	83.06 50	94.50 48	94.07 45

APD-MVS_3200maxsize		85.97 43	85.88 45	86.22 55	92.69 63	69.53 86	91.93 36	92.99 45	73.54 131	85.94 34	94.51 22	65.80 102	95.61 55	83.04 52	92.51 69	93.53 71

agg_prior2														82.91 53	95.45 28	92.70 95

mPP-MVS		86.67 35	86.32 37	87.72 28	94.41 22	73.55 12	92.74 20	92.22 80	76.87 60	82.81 84	94.25 31	66.44 92	96.24 39	82.88 54	94.28 54	93.38 73

SR-MVS-dyc-post		85.77 46	85.61 48	86.23 54	93.06 55	70.63 71	91.88 37	92.27 76	73.53 132	85.69 38	94.45 24	65.00 110	95.56 56	82.75 55	91.87 77	92.50 103

RE-MVS-def			85.48 49		93.06 55	70.63 71	91.88 37	92.27 76	73.53 132	85.69 38	94.45 24	63.87 116		82.75 55	91.87 77	92.50 103

h-mvs33		83.15 75	82.19 83	86.02 59	90.56 92	70.85 68	88.15 128	89.16 171	76.02 81	84.67 52	91.39 94	61.54 149	95.50 59	82.71 57	75.48 273	91.72 126

hse-mvs2		81.72 96	80.94 102	84.07 112	88.72 151	67.68 127	85.87 193	87.26 221	76.02 81	84.67 52	88.22 174	61.54 149	93.48 149	82.71 57	73.44 300	91.06 146

PGM-MVS		86.68 34	86.27 38	87.90 20	94.22 33	73.38 17	90.22 68	93.04 38	75.53 89	83.86 68	94.42 27	67.87 80	96.64 29	82.70 59	94.57 47	93.66 59

ACMMP		85.89 45	85.39 50	87.38 37	93.59 45	72.63 32	92.74 20	93.18 36	76.78 63	80.73 107	93.82 45	64.33 112	96.29 37	82.67 60	90.69 91	93.23 79
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
diffmvs		82.10 88	81.88 90	82.76 169	83.00 273	63.78 206	83.68 242	89.76 153	72.94 143	82.02 90	89.85 125	65.96 101	90.79 239	82.38 61	87.30 128	93.71 58
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
patch_mono-2		83.65 66	84.54 61	80.99 207	90.06 106	65.83 162	84.21 234	88.74 191	71.60 160	85.01 44	92.44 71	74.51 25	83.50 312	82.15 62	92.15 73	93.64 65

CS-MVS-test		86.29 40	86.48 35	85.71 63	91.02 83	67.21 139	92.36 28	93.78 18	78.97 26	83.51 75	91.20 98	70.65 57	95.15 75	81.96 63	94.89 39	94.77 20

TSAR-MVS + GP.		85.71 48	85.33 51	86.84 45	91.34 78	72.50 35	89.07 95	87.28 220	76.41 70	85.80 36	90.22 121	74.15 31	95.37 70	81.82 64	91.88 76	92.65 99

alignmvs		85.48 50	85.32 52	85.96 60	89.51 118	69.47 88	89.74 79	92.47 68	76.17 78	87.73 29	91.46 92	70.32 59	93.78 134	81.51 65	88.95 108	94.63 24

canonicalmvs		85.91 44	85.87 46	86.04 58	89.84 111	69.44 91	90.45 64	93.00 43	76.70 67	88.01 26	91.23 96	73.28 36	93.91 129	81.50 66	88.80 111	94.77 20

baseline		84.93 58	84.98 56	84.80 86	87.30 202	65.39 175	87.30 152	92.88 52	77.62 37	84.04 67	92.26 74	71.81 45	93.96 122	81.31 67	90.30 94	95.03 7

casdiffmvs		85.11 56	85.14 55	85.01 76	87.20 204	65.77 166	87.75 140	92.83 55	77.84 35	84.36 61	92.38 72	72.15 43	93.93 128	81.27 68	90.48 92	95.33 3
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_111021_HR		85.14 55	84.75 59	86.32 53	91.65 76	72.70 29	85.98 189	90.33 138	76.11 79	82.08 89	91.61 87	71.36 51	94.17 118	81.02 69	92.58 68	92.08 118

HPM-MVS_fast		85.35 54	84.95 58	86.57 51	93.69 42	70.58 73	92.15 34	91.62 103	73.89 122	82.67 86	94.09 36	62.60 131	95.54 58	80.93 70	92.93 64	93.57 68

CPTT-MVS		83.73 64	83.33 68	84.92 81	93.28 49	70.86 67	92.09 35	90.38 134	68.75 217	79.57 118	92.83 63	60.60 170	93.04 173	80.92 71	91.56 82	90.86 154

ETV-MVS		84.90 60	84.67 60	85.59 65	89.39 123	68.66 108	88.74 108	92.64 65	79.97 13	84.10 65	85.71 239	69.32 69	95.38 67	80.82 72	91.37 84	92.72 94

DeepC-MVS_fast	79.65 3	86.91 31	86.62 34	87.76 25	93.52 46	72.37 40	91.26 46	93.04 38	76.62 68	84.22 62	93.36 51	71.44 50	96.76 23	80.82 72	95.33 32	94.16 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		83.88 62	83.53 65	84.96 78	86.77 212	69.28 92	90.46 63	92.67 61	74.79 102	82.95 79	91.33 95	72.70 40	93.09 169	80.79 74	79.28 230	92.50 103

mvsmamba		81.69 98	80.74 104	84.56 91	87.45 196	66.72 146	91.26 46	85.89 241	74.66 105	78.23 145	90.56 114	54.33 212	94.91 86	80.73 75	83.54 177	92.04 121

EI-MVSNet-Vis-set		84.19 61	83.81 64	85.31 68	88.18 168	67.85 122	87.66 142	89.73 155	80.05 12	82.95 79	89.59 133	70.74 55	94.82 93	80.66 76	84.72 159	93.28 78

MSLP-MVS++		85.43 52	85.76 47	84.45 96	91.93 72	70.24 74	90.71 56	92.86 53	77.46 45	84.22 62	92.81 65	67.16 87	92.94 175	80.36 77	94.35 53	90.16 178

MVS_111021_LR		82.61 84	82.11 84	84.11 107	88.82 145	71.58 51	85.15 209	86.16 237	74.69 104	80.47 109	91.04 104	62.29 138	90.55 243	80.33 78	90.08 99	90.20 177

DELS-MVS		85.41 53	85.30 53	85.77 62	88.49 158	67.93 121	85.52 206	93.44 27	78.70 27	83.63 74	89.03 149	74.57 24	95.71 54	80.26 79	94.04 57	93.66 59
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
EI-MVSNet-UG-set		83.81 63	83.38 67	85.09 74	87.87 178	67.53 130	87.44 148	89.66 156	79.74 14	82.23 88	89.41 142	70.24 60	94.74 96	79.95 80	83.92 169	92.99 90

CSCG		86.41 39	86.19 40	87.07 43	92.91 58	72.48 36	90.81 55	93.56 24	73.95 119	83.16 78	91.07 103	75.94 18	95.19 73	79.94 81	94.38 52	93.55 69

OPM-MVS		83.50 69	82.95 73	85.14 72	88.79 148	70.95 64	89.13 94	91.52 106	77.55 42	80.96 105	91.75 82	60.71 166	94.50 105	79.67 82	86.51 140	89.97 194
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
iter_conf_final		80.63 123	79.35 132	84.46 95	89.36 125	67.70 126	89.85 73	84.49 256	73.19 138	78.30 143	88.94 150	45.98 291	94.56 100	79.59 83	84.48 163	91.11 143

iter_conf05		80.00 140	78.70 146	83.91 124	87.84 180	65.83 162	88.84 103	84.92 251	71.61 159	78.70 130	88.94 150	43.88 305	94.56 100	79.28 84	84.28 166	91.33 136

CDPH-MVS		85.76 47	85.29 54	87.17 41	93.49 47	71.08 59	88.58 113	92.42 72	68.32 224	84.61 55	93.48 47	72.32 41	96.15 43	79.00 85	95.43 29	94.28 38

MVSFormer		82.85 81	82.05 86	85.24 70	87.35 197	70.21 75	90.50 60	90.38 134	68.55 220	81.32 98	89.47 136	61.68 146	93.46 151	78.98 86	90.26 95	92.05 119

test_djsdf		80.30 133	79.32 133	83.27 140	83.98 251	65.37 176	90.50 60	90.38 134	68.55 220	76.19 192	88.70 157	56.44 199	93.46 151	78.98 86	80.14 219	90.97 151

test_vis1_n_1920		75.52 231	75.78 209	74.75 294	79.84 319	57.44 288	83.26 251	85.52 244	62.83 283	79.34 122	86.17 232	45.10 300	79.71 328	78.75 88	81.21 204	87.10 271

HQP_MVS		83.64 67	83.14 69	85.14 72	90.08 102	68.71 104	91.25 48	92.44 69	79.12 21	78.92 127	91.00 107	60.42 172	95.38 67	78.71 89	86.32 142	91.33 136

plane_prior5								92.44 69					95.38 67	78.71 89	86.32 142	91.33 136

LPG-MVS_test		82.08 89	81.27 95	84.50 93	89.23 133	68.76 100	90.22 68	91.94 91	75.37 92	76.64 182	91.51 89	54.29 213	94.91 86	78.44 91	83.78 170	89.83 199

LGP-MVS_train				84.50 93	89.23 133	68.76 100		91.94 91	75.37 92	76.64 182	91.51 89	54.29 213	94.91 86	78.44 91	83.78 170	89.83 199

lupinMVS		81.39 106	80.27 115	84.76 87	87.35 197	70.21 75	85.55 202	86.41 232	62.85 282	81.32 98	88.61 161	61.68 146	92.24 198	78.41 93	90.26 95	91.83 123

jason		81.39 106	80.29 114	84.70 88	86.63 214	69.90 82	85.95 190	86.77 228	63.24 275	81.07 104	89.47 136	61.08 162	92.15 200	78.33 94	90.07 100	92.05 119
jason: jason.
xiu_mvs_v1_base_debu		80.80 118	79.72 123	84.03 117	87.35 197	70.19 77	85.56 199	88.77 187	69.06 210	81.83 91	88.16 175	50.91 247	92.85 177	78.29 95	87.56 123	89.06 217

xiu_mvs_v1_base		80.80 118	79.72 123	84.03 117	87.35 197	70.19 77	85.56 199	88.77 187	69.06 210	81.83 91	88.16 175	50.91 247	92.85 177	78.29 95	87.56 123	89.06 217

xiu_mvs_v1_base_debi		80.80 118	79.72 123	84.03 117	87.35 197	70.19 77	85.56 199	88.77 187	69.06 210	81.83 91	88.16 175	50.91 247	92.85 177	78.29 95	87.56 123	89.06 217

Effi-MVS+		83.62 68	83.08 70	85.24 70	88.38 163	67.45 131	88.89 100	89.15 172	75.50 90	82.27 87	88.28 171	69.61 66	94.45 107	77.81 98	87.84 121	93.84 54

PS-MVSNAJss		82.07 90	81.31 94	84.34 101	86.51 215	67.27 136	89.27 87	91.51 107	71.75 154	79.37 120	90.22 121	63.15 125	94.27 111	77.69 99	82.36 192	91.49 133

ACMP	74.13 6	81.51 105	80.57 107	84.36 99	89.42 121	68.69 107	89.97 72	91.50 110	74.46 110	75.04 223	90.41 117	53.82 218	94.54 102	77.56 100	82.91 184	89.86 198
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
BP-MVS														77.47 101

HQP-MVS		82.61 84	82.02 87	84.37 98	89.33 126	66.98 142	89.17 89	92.19 82	76.41 70	77.23 168	90.23 120	60.17 175	95.11 78	77.47 101	85.99 149	91.03 148

MVS_Test		83.15 75	83.06 71	83.41 136	86.86 208	63.21 220	86.11 187	92.00 87	74.31 112	82.87 81	89.44 141	70.03 61	93.21 158	77.39 103	88.50 117	93.81 55

3Dnovator+	77.84 4	85.48 50	84.47 62	88.51 6	91.08 81	73.49 15	93.18 11	93.78 18	80.79 6	76.66 181	93.37 50	60.40 174	96.75 24	77.20 104	93.73 60	95.29 4

anonymousdsp		78.60 173	77.15 185	82.98 156	80.51 312	67.08 140	87.24 154	89.53 158	65.66 251	75.16 218	87.19 201	52.52 224	92.25 197	77.17 105	79.34 229	89.61 206

VDD-MVS		83.01 80	82.36 81	84.96 78	91.02 83	66.40 150	88.91 99	88.11 200	77.57 39	84.39 60	93.29 52	52.19 230	93.91 129	77.05 106	88.70 113	94.57 27

XVG-OURS-SEG-HR		80.81 116	79.76 122	83.96 122	85.60 225	68.78 99	83.54 248	90.50 131	70.66 177	76.71 180	91.66 83	60.69 167	91.26 226	76.94 107	81.58 200	91.83 123

RRT_MVS		80.35 132	79.22 137	83.74 127	87.63 190	65.46 172	91.08 52	88.92 184	73.82 123	76.44 187	90.03 123	49.05 272	94.25 115	76.84 108	79.20 232	91.51 130

jajsoiax		79.29 156	77.96 163	83.27 140	84.68 240	66.57 149	89.25 88	90.16 143	69.20 205	75.46 206	89.49 135	45.75 296	93.13 167	76.84 108	80.80 209	90.11 182

bld_raw_dy_0_64		77.29 206	75.98 208	81.22 200	85.04 236	65.47 171	88.14 129	77.56 324	69.20 205	73.77 236	89.40 144	42.24 316	88.85 271	76.78 110	81.64 199	89.33 212

mvs_tets		79.13 160	77.77 172	83.22 144	84.70 239	66.37 151	89.17 89	90.19 142	69.38 199	75.40 209	89.46 138	44.17 303	93.15 165	76.78 110	80.70 211	90.14 179

DPM-MVS		84.93 58	84.29 63	86.84 45	90.20 99	73.04 22	87.12 156	93.04 38	69.80 191	82.85 82	91.22 97	73.06 38	96.02 45	76.72 112	94.63 45	91.46 135

ET-MVSNet_ETH3D		78.63 172	76.63 200	84.64 89	86.73 213	69.47 88	85.01 212	84.61 254	69.54 196	66.51 311	86.59 219	50.16 256	91.75 213	76.26 113	84.24 167	92.69 97

v2v482		80.23 134	79.29 134	83.05 152	83.62 256	64.14 199	87.04 158	89.97 148	73.61 128	78.18 148	87.22 199	61.10 161	93.82 132	76.11 114	76.78 255	91.18 141

test_fmvs1_n		70.86 271	70.24 269	72.73 307	72.51 356	55.28 315	81.27 274	79.71 313	51.49 345	78.73 129	84.87 258	27.54 353	77.02 340	76.06 115	79.97 221	85.88 293

CLD-MVS		82.31 86	81.65 92	84.29 103	88.47 159	67.73 125	85.81 197	92.35 74	75.78 84	78.33 142	86.58 221	64.01 115	94.35 108	76.05 116	87.48 126	90.79 155
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPNet		83.72 65	82.92 74	86.14 57	84.22 246	69.48 87	91.05 53	85.27 246	81.30 4	76.83 176	91.65 84	66.09 97	95.56 56	76.00 117	93.85 58	93.38 73
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvs1		70.93 270	70.52 264	72.16 310	73.71 348	55.05 317	80.82 275	78.77 318	51.21 346	78.58 135	84.41 264	31.20 349	76.94 341	75.88 118	80.12 220	84.47 310

XVG-OURS		80.41 129	79.23 136	83.97 121	85.64 224	69.02 94	83.03 258	90.39 133	71.09 169	77.63 159	91.49 91	54.62 211	91.35 224	75.71 119	83.47 178	91.54 129

V42		79.38 155	78.24 159	82.83 161	81.10 306	65.50 170	85.55 202	89.82 151	71.57 161	78.21 146	86.12 233	60.66 168	93.18 164	75.64 120	75.46 275	89.81 201

PS-MVSNAJ		81.69 98	81.02 100	83.70 128	89.51 118	68.21 117	84.28 233	90.09 145	70.79 173	81.26 102	85.62 243	63.15 125	94.29 109	75.62 121	88.87 110	88.59 238

xiu_mvs_v2_base		81.69 98	81.05 99	83.60 129	89.15 136	68.03 120	84.46 227	90.02 146	70.67 176	81.30 101	86.53 224	63.17 124	94.19 117	75.60 122	88.54 115	88.57 239

EIA-MVS		83.31 74	82.80 76	84.82 84	89.59 114	65.59 168	88.21 124	92.68 60	74.66 105	78.96 125	86.42 226	69.06 72	95.26 71	75.54 123	90.09 98	93.62 66

AUN-MVS		79.21 158	77.60 178	84.05 115	88.71 152	67.61 128	85.84 195	87.26 221	69.08 209	77.23 168	88.14 179	53.20 223	93.47 150	75.50 124	73.45 299	91.06 146

OMC-MVS		82.69 82	81.97 89	84.85 83	88.75 150	67.42 132	87.98 131	90.87 124	74.92 99	79.72 116	91.65 84	62.19 141	93.96 122	75.26 125	86.42 141	93.16 83

v1144		80.03 138	79.03 141	83.01 154	83.78 254	64.51 190	87.11 157	90.57 130	71.96 153	78.08 151	86.20 231	61.41 153	93.94 125	74.93 126	77.23 246	90.60 164

MVSTER		79.01 163	77.88 167	82.38 175	83.07 270	64.80 186	84.08 239	88.95 182	69.01 213	78.69 131	87.17 202	54.70 209	92.43 188	74.69 127	80.57 213	89.89 197

test_vis1_n		69.85 283	69.21 274	71.77 312	72.66 355	55.27 316	81.48 271	76.21 334	52.03 342	75.30 215	83.20 283	28.97 351	76.22 346	74.60 128	78.41 239	83.81 318

test_fmvs2		68.35 294	67.48 294	70.98 320	69.50 359	51.95 338	80.05 287	76.38 333	49.33 348	74.65 229	84.38 265	23.30 359	75.40 351	74.51 129	75.17 283	85.60 295

PVSNet_Blended_VisFu		82.62 83	81.83 91	84.96 78	90.80 89	69.76 84	88.74 108	91.70 102	69.39 198	78.96 125	88.46 166	65.47 104	94.87 92	74.42 130	88.57 114	90.24 176

v8		79.97 141	79.02 142	82.80 164	84.09 248	64.50 192	87.96 132	90.29 141	74.13 118	75.24 217	86.81 208	62.88 130	93.89 131	74.39 131	75.40 277	90.00 190

v144192		79.47 149	78.37 155	82.78 167	83.35 261	63.96 202	86.96 160	90.36 137	69.99 187	77.50 160	85.67 241	60.66 168	93.77 136	74.27 132	76.58 256	90.62 162

ACMM	73.20 8	80.78 121	79.84 121	83.58 130	89.31 129	68.37 112	89.99 71	91.60 104	70.28 183	77.25 166	89.66 129	53.37 221	93.53 147	74.24 133	82.85 185	88.85 230
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
旧先验2							86.56 175		58.10 320	87.04 30			88.98 266	74.07 134

v1192		79.59 146	78.43 154	83.07 151	83.55 258	64.52 189	86.93 162	90.58 129	70.83 172	77.78 156	85.90 235	59.15 178	93.94 125	73.96 135	77.19 248	90.76 157

v10		79.74 143	78.67 147	82.97 157	84.06 249	64.95 183	87.88 138	90.62 128	73.11 139	75.11 220	86.56 222	61.46 152	94.05 121	73.68 136	75.55 271	89.90 196

v1921920		79.22 157	78.03 162	82.80 164	83.30 263	63.94 203	86.80 166	90.33 138	69.91 189	77.48 161	85.53 244	58.44 182	93.75 138	73.60 137	76.85 253	90.71 160

cl22		78.07 186	77.01 187	81.23 199	82.37 288	61.83 240	83.55 247	87.98 204	68.96 214	75.06 222	83.87 271	61.40 154	91.88 210	73.53 138	76.39 260	89.98 193

Effi-MVS+-dtu		80.03 138	78.57 150	84.42 97	85.13 234	68.74 102	88.77 105	88.10 201	74.99 98	74.97 224	83.49 279	57.27 194	93.36 154	73.53 138	80.88 207	91.18 141

c3_l		78.75 168	77.91 165	81.26 198	82.89 276	61.56 243	84.09 238	89.13 174	69.97 188	75.56 202	84.29 267	66.36 93	92.09 202	73.47 140	75.48 273	90.12 181

VDDNet		81.52 103	80.67 106	84.05 115	90.44 95	64.13 200	89.73 80	85.91 240	71.11 168	83.18 77	93.48 47	50.54 253	93.49 148	73.40 141	88.25 119	94.54 28

CANet_DTU		80.61 124	79.87 120	82.83 161	85.60 225	63.17 223	87.36 149	88.65 193	76.37 74	75.88 198	88.44 167	53.51 220	93.07 170	73.30 142	89.74 103	92.25 112

miper_ehance_all_eth		78.59 174	77.76 173	81.08 205	82.66 281	61.56 243	83.65 243	89.15 172	68.87 215	75.55 203	83.79 275	66.49 91	92.03 203	73.25 143	76.39 260	89.64 205

3Dnovator	76.31 5	83.38 73	82.31 82	86.59 50	87.94 177	72.94 27	90.64 57	92.14 84	77.21 50	75.47 204	92.83 63	58.56 181	94.72 97	73.24 144	92.71 67	92.13 117

v1240		78.99 164	77.78 171	82.64 170	83.21 265	63.54 211	86.62 173	90.30 140	69.74 195	77.33 164	85.68 240	57.04 196	93.76 137	73.13 145	76.92 250	90.62 162

miper_enhance_ethall		77.87 193	76.86 191	80.92 209	81.65 295	61.38 245	82.68 259	88.98 179	65.52 253	75.47 204	82.30 294	65.76 103	92.00 205	72.95 146	76.39 260	89.39 210

MG-MVS		83.41 71	83.45 66	83.28 139	92.74 62	62.28 234	88.17 126	89.50 159	75.22 94	81.49 97	92.74 69	66.75 88	95.11 78	72.85 147	91.58 81	92.45 106

EPP-MVSNet		83.40 72	83.02 72	84.57 90	90.13 100	64.47 193	92.32 29	90.73 126	74.45 111	79.35 121	91.10 101	69.05 73	95.12 76	72.78 148	87.22 129	94.13 42

test_fmvs3		63.36 315	61.82 317	67.98 331	62.51 366	46.96 357	77.37 313	74.03 343	45.24 351	67.50 296	78.79 326	12.16 370	72.98 358	72.77 149	66.02 333	83.99 316

IterMVS-LS		80.06 137	79.38 130	82.11 178	85.89 220	63.20 221	86.79 167	89.34 162	74.19 115	75.45 207	86.72 211	66.62 89	92.39 190	72.58 150	76.86 252	90.75 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tt0805		78.73 169	77.83 168	81.43 192	85.17 230	60.30 259	89.41 85	90.90 122	71.21 166	77.17 172	88.73 156	46.38 286	93.21 158	72.57 151	78.96 233	90.79 155

EI-MVSNet		80.52 128	79.98 117	82.12 177	84.28 244	63.19 222	86.41 178	88.95 182	74.18 116	78.69 131	87.54 191	66.62 89	92.43 188	72.57 151	80.57 213	90.74 159

Vis-MVSNet		83.46 70	82.80 76	85.43 67	90.25 98	68.74 102	90.30 67	90.13 144	76.33 76	80.87 106	92.89 61	61.00 163	94.20 116	72.45 153	90.97 88	93.35 75
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
LFMVS		81.82 95	81.23 96	83.57 131	91.89 73	63.43 216	89.84 74	81.85 292	77.04 56	83.21 76	93.10 54	52.26 229	93.43 153	71.98 154	89.95 101	93.85 52

v148		78.72 170	77.80 170	81.47 191	82.73 279	61.96 238	86.30 182	88.08 202	73.26 136	76.18 193	85.47 246	62.46 135	92.36 192	71.92 155	73.82 296	90.09 184

PVSNet_BlendedMVS		80.60 125	80.02 116	82.36 176	88.85 142	65.40 173	86.16 186	92.00 87	69.34 200	78.11 149	86.09 234	66.02 99	94.27 111	71.52 156	82.06 194	87.39 259

PVSNet_Blended		80.98 111	80.34 112	82.90 159	88.85 142	65.40 173	84.43 229	92.00 87	67.62 228	78.11 149	85.05 257	66.02 99	94.27 111	71.52 156	89.50 104	89.01 222

eth_miper_zixun_eth		77.92 191	76.69 198	81.61 189	83.00 273	61.98 237	83.15 253	89.20 170	69.52 197	74.86 226	84.35 266	61.76 145	92.56 184	71.50 158	72.89 304	90.28 175

UA-Net		85.08 57	84.96 57	85.45 66	92.07 70	68.07 119	89.78 78	90.86 125	82.48 1	84.60 56	93.20 53	69.35 68	95.22 72	71.39 159	90.88 90	93.07 85

FA-MVS(test-final)		80.96 112	79.91 119	84.10 108	88.30 166	65.01 182	84.55 224	90.01 147	73.25 137	79.61 117	87.57 188	58.35 183	94.72 97	71.29 160	86.25 144	92.56 100

cl____		77.72 196	76.76 195	80.58 215	82.49 285	60.48 256	83.09 255	87.87 207	69.22 203	74.38 232	85.22 252	62.10 142	91.53 219	71.09 161	75.41 276	89.73 204

DIV-MVS_self_test		77.72 196	76.76 195	80.58 215	82.48 286	60.48 256	83.09 255	87.86 208	69.22 203	74.38 232	85.24 250	62.10 142	91.53 219	71.09 161	75.40 277	89.74 203

test_yl		81.17 108	80.47 110	83.24 142	89.13 137	63.62 207	86.21 184	89.95 149	72.43 148	81.78 95	89.61 131	57.50 191	93.58 142	70.75 163	86.90 133	92.52 101

DCV-MVSNet		81.17 108	80.47 110	83.24 142	89.13 137	63.62 207	86.21 184	89.95 149	72.43 148	81.78 95	89.61 131	57.50 191	93.58 142	70.75 163	86.90 133	92.52 101

VNet		82.21 87	82.41 79	81.62 187	90.82 88	60.93 248	84.47 225	89.78 152	76.36 75	84.07 66	91.88 80	64.71 111	90.26 245	70.68 165	88.89 109	93.66 59

mvs_anonymous		79.42 152	79.11 140	80.34 220	84.45 243	57.97 278	82.59 260	87.62 213	67.40 231	76.17 195	88.56 164	68.47 76	89.59 255	70.65 166	86.05 147	93.47 72

VPA-MVSNet		80.60 125	80.55 108	80.76 212	88.07 173	60.80 251	86.86 164	91.58 105	75.67 88	80.24 111	89.45 140	63.34 119	90.25 246	70.51 167	79.22 231	91.23 140

PAPM_NR		83.02 79	82.41 79	84.82 84	92.47 67	66.37 151	87.93 135	91.80 98	73.82 123	77.32 165	90.66 112	67.90 79	94.90 89	70.37 168	89.48 105	93.19 82

thisisatest0530		79.40 153	77.76 173	84.31 102	87.69 188	65.10 181	87.36 149	84.26 262	70.04 186	77.42 162	88.26 173	49.94 259	94.79 95	70.20 169	84.70 160	93.03 87

tttt0517		79.40 153	77.91 165	83.90 125	88.10 171	63.84 204	88.37 120	84.05 264	71.45 163	76.78 178	89.12 146	49.93 261	94.89 90	70.18 170	83.18 182	92.96 91

UniMVSNet_NR-MVSNet		81.88 93	81.54 93	82.92 158	88.46 160	63.46 214	87.13 155	92.37 73	80.19 10	78.38 140	89.14 145	71.66 48	93.05 171	70.05 171	76.46 258	92.25 112

DU-MVS		81.12 110	80.52 109	82.90 159	87.80 182	63.46 214	87.02 159	91.87 95	79.01 24	78.38 140	89.07 147	65.02 108	93.05 171	70.05 171	76.46 258	92.20 114

XVG-ACMP-BASELINE		76.11 224	74.27 232	81.62 187	83.20 266	64.67 188	83.60 246	89.75 154	69.75 193	71.85 256	87.09 204	32.78 345	92.11 201	69.99 173	80.43 215	88.09 245

GeoE		81.71 97	81.01 101	83.80 126	89.51 118	64.45 194	88.97 97	88.73 192	71.27 165	78.63 134	89.76 127	66.32 94	93.20 161	69.89 174	86.02 148	93.74 57

FIs		82.07 90	82.42 78	81.04 206	88.80 147	58.34 272	88.26 123	93.49 26	76.93 58	78.47 139	91.04 104	69.92 63	92.34 194	69.87 175	84.97 156	92.44 107

114514_t		80.68 122	79.51 127	84.20 105	94.09 38	67.27 136	89.64 82	91.11 118	58.75 317	74.08 234	90.72 111	58.10 184	95.04 83	69.70 176	89.42 106	90.30 174

Anonymous20231211		78.97 165	77.69 176	82.81 163	90.54 93	64.29 197	90.11 70	91.51 107	65.01 258	76.16 196	88.13 180	50.56 252	93.03 174	69.68 177	77.56 245	91.11 143

Patchmatch-RL test		70.24 278	67.78 290	77.61 265	77.43 334	59.57 266	71.16 336	70.33 348	62.94 281	68.65 287	72.77 348	50.62 251	85.49 298	69.58 178	66.58 331	87.77 251

UniMVSNet (Re)		81.60 102	81.11 98	83.09 149	88.38 163	64.41 195	87.60 143	93.02 42	78.42 30	78.56 136	88.16 175	69.78 64	93.26 157	69.58 178	76.49 257	91.60 127

IterMVS-SCA-FT		75.43 233	73.87 236	80.11 225	82.69 280	64.85 185	81.57 270	83.47 274	69.16 207	70.49 266	84.15 269	51.95 236	88.15 278	69.23 180	72.14 309	87.34 261

v7n		78.97 165	77.58 179	83.14 147	83.45 260	65.51 169	88.32 121	91.21 114	73.69 126	72.41 250	86.32 229	57.93 185	93.81 133	69.18 181	75.65 269	90.11 182

Anonymous20240529		80.19 136	78.89 144	84.10 108	90.60 91	64.75 187	88.95 98	90.90 122	65.97 248	80.59 108	91.17 100	49.97 258	93.73 140	69.16 182	82.70 189	93.81 55

miper_lstm_enhance		74.11 243	73.11 243	77.13 273	80.11 315	59.62 264	72.23 333	86.92 227	66.76 235	70.40 267	82.92 285	56.93 197	82.92 316	69.06 183	72.63 305	88.87 229

testdata				79.97 227	90.90 86	64.21 198		84.71 252	59.27 312	85.40 40	92.91 60	62.02 144	89.08 264	68.95 184	91.37 84	86.63 280

test1111		79.43 151	79.18 139	80.15 224	89.99 107	53.31 333	87.33 151	77.05 330	75.04 97	80.23 112	92.77 68	48.97 273	92.33 195	68.87 185	92.40 72	94.81 18

GA-MVS		76.87 212	75.17 222	81.97 182	82.75 278	62.58 229	81.44 273	86.35 235	72.16 152	74.74 227	82.89 286	46.20 290	92.02 204	68.85 186	81.09 205	91.30 139

test2506		77.30 205	76.49 201	79.74 232	90.08 102	52.02 336	87.86 139	63.10 364	74.88 100	80.16 113	92.79 66	38.29 332	92.35 193	68.74 187	92.50 70	94.86 15

ECVR-MVS		79.61 144	79.26 135	80.67 214	90.08 102	54.69 320	87.89 137	77.44 327	74.88 100	80.27 110	92.79 66	48.96 274	92.45 187	68.55 188	92.50 70	94.86 15

UGNet		80.83 115	79.59 126	84.54 92	88.04 174	68.09 118	89.42 84	88.16 199	76.95 57	76.22 191	89.46 138	49.30 267	93.94 125	68.48 189	90.31 93	91.60 127
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
FC-MVSNet-test		81.52 103	82.02 87	80.03 226	88.42 162	55.97 309	87.95 133	93.42 29	77.10 54	77.38 163	90.98 109	69.96 62	91.79 212	68.46 190	84.50 161	92.33 108

DP-MVS Recon		83.11 78	82.09 85	86.15 56	94.44 19	70.92 66	88.79 104	92.20 81	70.53 179	79.17 123	91.03 106	64.12 114	96.03 44	68.39 191	90.14 97	91.50 132

UniMVSNet_ETH3D		79.10 161	78.24 159	81.70 186	86.85 209	60.24 260	87.28 153	88.79 186	74.25 114	76.84 175	90.53 116	49.48 264	91.56 218	67.98 192	82.15 193	93.29 77

D2MVS		74.82 237	73.21 241	79.64 236	79.81 320	62.56 230	80.34 284	87.35 219	64.37 265	68.86 285	82.66 290	46.37 287	90.10 248	67.91 193	81.24 203	86.25 283

IS-MVSNet		83.15 75	82.81 75	84.18 106	89.94 109	63.30 218	91.59 41	88.46 197	79.04 23	79.49 119	92.16 75	65.10 107	94.28 110	67.71 194	91.86 79	94.95 8

Fast-Effi-MVS+-dtu		78.02 188	76.49 201	82.62 171	83.16 269	66.96 144	86.94 161	87.45 218	72.45 145	71.49 260	84.17 268	54.79 208	91.58 217	67.61 195	80.31 216	89.30 213

PAPR		81.66 101	80.89 103	83.99 120	90.27 97	64.00 201	86.76 170	91.77 101	68.84 216	77.13 174	89.50 134	67.63 81	94.88 91	67.55 196	88.52 116	93.09 84

cascas		76.72 214	74.64 225	82.99 155	85.78 222	65.88 161	82.33 262	89.21 169	60.85 299	72.74 245	81.02 305	47.28 281	93.75 138	67.48 197	85.02 155	89.34 211

1314		76.53 215	75.30 221	80.21 223	83.93 252	62.32 233	84.66 219	88.81 185	60.23 303	70.16 272	84.07 270	55.30 203	90.73 241	67.37 198	83.21 181	87.59 256

无先验							87.48 146	88.98 179	60.00 305				94.12 119	67.28 199		88.97 225

thisisatest0515		77.33 204	75.38 218	83.18 145	85.27 229	63.80 205	82.11 264	83.27 277	65.06 256	75.91 197	83.84 273	49.54 263	94.27 111	67.24 200	86.19 145	91.48 134

原ACMM1				84.35 100	93.01 57	68.79 98		92.44 69	63.96 273	81.09 103	91.57 88	66.06 98	95.45 61	67.19 201	94.82 43	88.81 232

Baseline_NR-MVSNet		78.15 184	78.33 157	77.61 265	85.79 221	56.21 307	86.78 168	85.76 242	73.60 129	77.93 154	87.57 188	65.02 108	88.99 265	67.14 202	75.33 279	87.63 253

TranMVSNet+NR-MVSNet		80.84 114	80.31 113	82.42 174	87.85 179	62.33 232	87.74 141	91.33 112	80.55 7	77.99 153	89.86 124	65.23 106	92.62 181	67.05 203	75.24 282	92.30 110

Fast-Effi-MVS+		80.81 116	79.92 118	83.47 132	88.85 142	64.51 190	85.53 204	89.39 161	70.79 173	78.49 138	85.06 256	67.54 82	93.58 142	67.03 204	86.58 138	92.32 109

VPNet		78.69 171	78.66 148	78.76 247	88.31 165	55.72 311	84.45 228	86.63 230	76.79 62	78.26 144	90.55 115	59.30 177	89.70 254	66.63 205	77.05 249	90.88 153

PM-MVS		66.41 304	64.14 306	73.20 305	73.92 347	56.45 301	78.97 299	64.96 362	63.88 274	64.72 322	80.24 313	19.84 362	83.44 313	66.24 206	64.52 338	79.71 343

test-LLR		72.94 257	72.43 247	74.48 295	81.35 302	58.04 276	78.38 303	77.46 325	66.66 237	69.95 276	79.00 323	48.06 277	79.24 329	66.13 207	84.83 157	86.15 286

test-mter		71.41 266	70.39 268	74.48 295	81.35 302	58.04 276	78.38 303	77.46 325	60.32 302	69.95 276	79.00 323	36.08 339	79.24 329	66.13 207	84.83 157	86.15 286

MVS		78.19 183	76.99 189	81.78 184	85.66 223	66.99 141	84.66 219	90.47 132	55.08 335	72.02 255	85.27 249	63.83 117	94.11 120	66.10 209	89.80 102	84.24 312

NR-MVSNet		80.23 134	79.38 130	82.78 167	87.80 182	63.34 217	86.31 181	91.09 119	79.01 24	72.17 253	89.07 147	67.20 86	92.81 180	66.08 210	75.65 269	92.20 114

CVMVSNet		72.99 256	72.58 246	74.25 298	84.28 244	50.85 346	86.41 178	83.45 275	44.56 352	73.23 241	87.54 191	49.38 265	85.70 296	65.90 211	78.44 237	86.19 285

IterMVS		74.29 240	72.94 244	78.35 254	81.53 298	63.49 213	81.58 269	82.49 286	68.06 226	69.99 275	83.69 277	51.66 242	85.54 297	65.85 212	71.64 312	86.01 290
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
OurMVSNet-221017-0		74.26 241	72.42 248	79.80 231	83.76 255	59.59 265	85.92 192	86.64 229	66.39 242	66.96 302	87.58 187	39.46 326	91.60 216	65.76 213	69.27 322	88.22 243

tpmrst		72.39 260	72.13 250	73.18 306	80.54 311	49.91 350	79.91 290	79.08 317	63.11 277	71.69 258	79.95 316	55.32 202	82.77 317	65.66 214	73.89 294	86.87 273

MAR-MVS		81.84 94	80.70 105	85.27 69	91.32 79	71.53 52	89.82 75	90.92 121	69.77 192	78.50 137	86.21 230	62.36 137	94.52 104	65.36 215	92.05 75	89.77 202
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
Anonymous202405211		78.25 179	77.01 187	81.99 181	91.03 82	60.67 253	84.77 217	83.90 266	70.65 178	80.00 114	91.20 98	41.08 322	91.43 222	65.21 216	85.26 154	93.85 52

ab-mvs		79.51 147	78.97 143	81.14 203	88.46 160	60.91 249	83.84 240	89.24 168	70.36 181	79.03 124	88.87 154	63.23 123	90.21 247	65.12 217	82.57 190	92.28 111

IB-MVS	68.01 15	75.85 227	73.36 240	83.31 138	84.76 238	66.03 155	83.38 249	85.06 248	70.21 185	69.40 282	81.05 304	45.76 295	94.66 99	65.10 218	75.49 272	89.25 214
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
WR-MVS		79.49 148	79.22 137	80.27 222	88.79 148	58.35 271	85.06 211	88.61 195	78.56 28	77.65 158	88.34 169	63.81 118	90.66 242	64.98 219	77.22 247	91.80 125

CostFormer		75.24 236	73.90 235	79.27 241	82.65 282	58.27 273	80.80 276	82.73 285	61.57 294	75.33 214	83.13 284	55.52 201	91.07 235	64.98 219	78.34 240	88.45 240

API-MVS		81.99 92	81.23 96	84.26 104	90.94 85	70.18 80	91.10 51	89.32 163	71.51 162	78.66 133	88.28 171	65.26 105	95.10 81	64.74 221	91.23 86	87.51 257

新几何1				83.42 134	93.13 52	70.71 69		85.48 245	57.43 325	81.80 94	91.98 77	63.28 120	92.27 196	64.60 222	92.99 63	87.27 263

pm-mvs1		77.25 207	76.68 199	78.93 245	84.22 246	58.62 270	86.41 178	88.36 198	71.37 164	73.31 239	88.01 181	61.22 159	89.15 263	64.24 223	73.01 303	89.03 221

TESTMET0.1,1		69.89 282	69.00 276	72.55 308	79.27 329	56.85 294	78.38 303	74.71 341	57.64 323	68.09 291	77.19 336	37.75 334	76.70 342	63.92 224	84.09 168	84.10 315

QAPM		80.88 113	79.50 128	85.03 75	88.01 176	68.97 96	91.59 41	92.00 87	66.63 240	75.15 219	92.16 75	57.70 188	95.45 61	63.52 225	88.76 112	90.66 161

baseline2		75.70 228	73.83 237	81.30 197	83.26 264	61.79 241	82.57 261	80.65 301	66.81 233	66.88 303	83.42 280	57.86 187	92.19 199	63.47 226	79.57 224	89.91 195

LCM-MVSNet-Re		77.05 208	76.94 190	77.36 268	87.20 204	51.60 341	80.06 286	80.46 305	75.20 95	67.69 294	86.72 211	62.48 134	88.98 266	63.44 227	89.25 107	91.51 130

gm-plane-assit					81.40 300	53.83 328			62.72 286		80.94 307		92.39 190	63.40 228

baseline1		76.98 210	76.75 197	77.66 263	88.13 169	55.66 312	85.12 210	81.89 290	73.04 141	76.79 177	88.90 152	62.43 136	87.78 283	63.30 229	71.18 315	89.55 208

AdaColmap		80.58 127	79.42 129	84.06 113	93.09 54	68.91 97	89.36 86	88.97 181	69.27 201	75.70 201	89.69 128	57.20 195	95.77 52	63.06 230	88.41 118	87.50 258

test_vis1_rt		60.28 319	58.42 322	65.84 335	67.25 362	55.60 313	70.44 341	60.94 366	44.33 353	59.00 343	66.64 355	24.91 355	68.67 363	62.80 231	69.48 320	73.25 353

GBi-Net		78.40 176	77.40 181	81.40 194	87.60 191	63.01 224	88.39 117	89.28 164	71.63 156	75.34 211	87.28 195	54.80 205	91.11 229	62.72 232	79.57 224	90.09 184

test1		78.40 176	77.40 181	81.40 194	87.60 191	63.01 224	88.39 117	89.28 164	71.63 156	75.34 211	87.28 195	54.80 205	91.11 229	62.72 232	79.57 224	90.09 184

FMVSNet3		77.88 192	76.85 192	80.97 208	86.84 210	62.36 231	86.52 176	88.77 187	71.13 167	75.34 211	86.66 217	54.07 216	91.10 232	62.72 232	79.57 224	89.45 209

CMPMVS	51.72 21	70.19 279	68.16 282	76.28 278	73.15 353	57.55 286	79.47 293	83.92 265	48.02 349	56.48 352	84.81 259	43.13 308	86.42 292	62.67 235	81.81 198	84.89 304
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet2		78.20 182	77.21 184	81.20 201	87.60 191	62.89 228	87.47 147	89.02 177	71.63 156	75.29 216	87.28 195	54.80 205	91.10 232	62.38 236	79.38 228	89.61 206

testdata2													91.01 236	62.37 237

CP-MVSNet		78.22 180	78.34 156	77.84 260	87.83 181	54.54 322	87.94 134	91.17 116	77.65 36	73.48 238	88.49 165	62.24 140	88.43 275	62.19 238	74.07 291	90.55 166

XXY-MVS		75.41 234	75.56 213	74.96 290	83.59 257	57.82 282	80.59 281	83.87 267	66.54 241	74.93 225	88.31 170	63.24 122	80.09 327	62.16 239	76.85 253	86.97 272

pmmvs6		74.69 238	73.39 239	78.61 249	81.38 301	57.48 287	86.64 172	87.95 205	64.99 259	70.18 270	86.61 218	50.43 254	89.52 256	62.12 240	70.18 319	88.83 231

1112_ss		77.40 203	76.43 203	80.32 221	89.11 141	60.41 258	83.65 243	87.72 212	62.13 291	73.05 243	86.72 211	62.58 133	89.97 249	62.11 241	80.80 209	90.59 165

PS-CasMVS		78.01 189	78.09 161	77.77 262	87.71 186	54.39 324	88.02 130	91.22 113	77.50 44	73.26 240	88.64 160	60.73 165	88.41 276	61.88 242	73.88 295	90.53 167

CDS-MVSNet		79.07 162	77.70 175	83.17 146	87.60 191	68.23 116	84.40 231	86.20 236	67.49 230	76.36 188	86.54 223	61.54 149	90.79 239	61.86 243	87.33 127	90.49 168
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OpenMVS	72.83 10	79.77 142	78.33 157	84.09 110	85.17 230	69.91 81	90.57 58	90.97 120	66.70 236	72.17 253	91.91 78	54.70 209	93.96 122	61.81 244	90.95 89	88.41 242

K. test v3		71.19 267	68.51 278	79.21 243	83.04 272	57.78 283	84.35 232	76.91 331	72.90 144	62.99 332	82.86 287	39.27 327	91.09 234	61.65 245	52.66 358	88.75 234

CHOSEN 1792x2688		77.63 199	75.69 210	83.44 133	89.98 108	68.58 110	78.70 302	87.50 216	56.38 330	75.80 200	86.84 207	58.67 180	91.40 223	61.58 246	85.75 153	90.34 173

PCF-MVS	73.52 7	80.38 130	78.84 145	85.01 76	87.71 186	68.99 95	83.65 243	91.46 111	63.00 279	77.77 157	90.28 118	66.10 96	95.09 82	61.40 247	88.22 120	90.94 152
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HY-MVS	69.67 12	77.95 190	77.15 185	80.36 219	87.57 195	60.21 261	83.37 250	87.78 211	66.11 244	75.37 210	87.06 206	63.27 121	90.48 244	61.38 248	82.43 191	90.40 172

HyFIR lowres test		77.53 200	75.40 217	83.94 123	89.59 114	66.62 147	80.36 283	88.64 194	56.29 331	76.45 184	85.17 253	57.64 189	93.28 156	61.34 249	83.10 183	91.91 122

PMMVS		69.34 285	68.67 277	71.35 317	75.67 340	62.03 236	75.17 323	73.46 344	50.00 347	68.68 286	79.05 321	52.07 234	78.13 334	61.16 250	82.77 186	73.90 352

FMVSNet1		77.44 201	76.12 207	81.40 194	86.81 211	63.01 224	88.39 117	89.28 164	70.49 180	74.39 231	87.28 195	49.06 271	91.11 229	60.91 251	78.52 235	90.09 184

sss		73.60 247	73.64 238	73.51 302	82.80 277	55.01 318	76.12 317	81.69 293	62.47 288	74.68 228	85.85 238	57.32 193	78.11 335	60.86 252	80.93 206	87.39 259

Test_1112_low_res		76.40 220	75.44 215	79.27 241	89.28 131	58.09 274	81.69 268	87.07 224	59.53 310	72.48 249	86.67 216	61.30 156	89.33 259	60.81 253	80.15 218	90.41 171

BH-untuned		79.47 149	78.60 149	82.05 179	89.19 135	65.91 160	86.07 188	88.52 196	72.18 150	75.42 208	87.69 185	61.15 160	93.54 146	60.38 254	86.83 135	86.70 278

WTY-MVS		75.65 229	75.68 211	75.57 284	86.40 216	56.82 295	77.92 310	82.40 287	65.10 255	76.18 193	87.72 183	63.13 128	80.90 324	60.31 255	81.96 195	89.00 224

pmmvs4		74.03 245	71.91 251	80.39 218	81.96 292	68.32 113	81.45 272	82.14 288	59.32 311	69.87 278	85.13 254	52.40 227	88.13 279	60.21 256	74.74 287	84.73 307

PEN-MVS		77.73 195	77.69 176	77.84 260	87.07 207	53.91 327	87.91 136	91.18 115	77.56 41	73.14 242	88.82 155	61.23 158	89.17 262	59.95 257	72.37 306	90.43 170

CR-MVSNet		73.37 249	71.27 258	79.67 235	81.32 304	65.19 178	75.92 319	80.30 307	59.92 306	72.73 246	81.19 302	52.50 225	86.69 289	59.84 258	77.71 242	87.11 269

lessismore_v0				78.97 244	81.01 307	57.15 291		65.99 359		61.16 337	82.82 288	39.12 328	91.34 225	59.67 259	46.92 364	88.43 241

CNLPA		78.08 185	76.79 194	81.97 182	90.40 96	71.07 60	87.59 144	84.55 255	66.03 247	72.38 251	89.64 130	57.56 190	86.04 294	59.61 260	83.35 179	88.79 233

BH-RMVSNet		79.61 144	78.44 153	83.14 147	89.38 124	65.93 159	84.95 214	87.15 223	73.56 130	78.19 147	89.79 126	56.67 198	93.36 154	59.53 261	86.74 136	90.13 180

MS-PatchMatch		73.83 246	72.67 245	77.30 270	83.87 253	66.02 156	81.82 265	84.66 253	61.37 297	68.61 288	82.82 288	47.29 280	88.21 277	59.27 262	84.32 165	77.68 347

test_post1							78.90 301				5.43 376	48.81 276	85.44 299	59.25 263

SCA		74.22 242	72.33 249	79.91 228	84.05 250	62.17 235	79.96 289	79.29 316	66.30 243	72.38 251	80.13 314	51.95 236	88.60 273	59.25 263	77.67 244	88.96 226

FE-MVS		77.78 194	75.68 211	84.08 111	88.09 172	66.00 157	83.13 254	87.79 210	68.42 223	78.01 152	85.23 251	45.50 298	95.12 76	59.11 265	85.83 152	91.11 143

SixPastTwentyTwo		73.37 249	71.26 259	79.70 233	85.08 235	57.89 280	85.57 198	83.56 271	71.03 170	65.66 315	85.88 236	42.10 317	92.57 183	59.11 265	63.34 340	88.65 237

MVS_0304		72.48 259	70.89 262	77.24 271	82.20 289	59.68 263	84.11 237	83.49 273	67.10 232	66.87 304	80.59 310	35.00 342	87.40 285	59.07 267	79.58 223	84.63 308

WR-MVS_H		78.51 175	78.49 151	78.56 250	88.02 175	56.38 304	88.43 115	92.67 61	77.14 52	73.89 235	87.55 190	66.25 95	89.24 261	58.92 268	73.55 298	90.06 188

PLC	70.83 11	78.05 187	76.37 205	83.08 150	91.88 74	67.80 123	88.19 125	89.46 160	64.33 266	69.87 278	88.38 168	53.66 219	93.58 142	58.86 269	82.73 187	87.86 249
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
RPSCF		73.23 253	71.46 254	78.54 251	82.50 284	59.85 262	82.18 263	82.84 284	58.96 314	71.15 263	89.41 142	45.48 299	84.77 304	58.82 270	71.83 311	91.02 150

EU-MVSNet		68.53 292	67.61 292	71.31 318	78.51 331	47.01 356	84.47 225	84.27 261	42.27 355	66.44 312	84.79 260	40.44 324	83.76 309	58.76 271	68.54 327	83.17 323

pmmvs-eth3d		70.50 276	67.83 288	78.52 252	77.37 335	66.18 154	81.82 265	81.51 294	58.90 315	63.90 328	80.42 312	42.69 311	86.28 293	58.56 272	65.30 336	83.11 325

TAMVS		78.89 167	77.51 180	83.03 153	87.80 182	67.79 124	84.72 218	85.05 249	67.63 227	76.75 179	87.70 184	62.25 139	90.82 238	58.53 273	87.13 130	90.49 168

ACMH+	68.96 14	76.01 225	74.01 233	82.03 180	88.60 155	65.31 177	88.86 101	87.55 214	70.25 184	67.75 293	87.47 193	41.27 320	93.19 163	58.37 274	75.94 266	87.60 254

tpm		72.37 262	71.71 253	74.35 297	82.19 290	52.00 337	79.22 296	77.29 328	64.56 262	72.95 244	83.68 278	51.35 243	83.26 315	58.33 275	75.80 267	87.81 250

BH-w/o		78.21 181	77.33 183	80.84 210	88.81 146	65.13 180	84.87 215	87.85 209	69.75 193	74.52 230	84.74 261	61.34 155	93.11 168	58.24 276	85.84 151	84.27 311

Vis-MVSNet (Re-imp)		78.36 178	78.45 152	78.07 258	88.64 154	51.78 340	86.70 171	79.63 314	74.14 117	75.11 220	90.83 110	61.29 157	89.75 252	58.10 277	91.60 80	92.69 97

MVP-Stereo		76.12 223	74.46 230	81.13 204	85.37 228	69.79 83	84.42 230	87.95 205	65.03 257	67.46 297	85.33 248	53.28 222	91.73 215	58.01 278	83.27 180	81.85 333
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ambc				75.24 288	73.16 352	50.51 348	63.05 362	87.47 217		64.28 324	77.81 333	17.80 364	89.73 253	57.88 279	60.64 346	85.49 296

TR-MVS		77.44 201	76.18 206	81.20 201	88.24 167	63.24 219	84.61 222	86.40 233	67.55 229	77.81 155	86.48 225	54.10 215	93.15 165	57.75 280	82.72 188	87.20 264

F-COLMAP		76.38 221	74.33 231	82.50 173	89.28 131	66.95 145	88.41 116	89.03 176	64.05 270	66.83 305	88.61 161	46.78 284	92.89 176	57.48 281	78.55 234	87.67 252

EG-PatchMatch MVS		74.04 244	71.82 252	80.71 213	84.92 237	67.42 132	85.86 194	88.08 202	66.04 246	64.22 325	83.85 272	35.10 341	92.56 184	57.44 282	80.83 208	82.16 332

PatchmatchNet		73.12 254	71.33 257	78.49 253	83.18 267	60.85 250	79.63 291	78.57 319	64.13 267	71.73 257	79.81 319	51.20 245	85.97 295	57.40 283	76.36 263	88.66 236
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DTE-MVSNet		76.99 209	76.80 193	77.54 267	86.24 217	53.06 335	87.52 145	90.66 127	77.08 55	72.50 248	88.67 159	60.48 171	89.52 256	57.33 284	70.74 317	90.05 189

UnsupCasMVSNet_eth		67.33 298	65.99 301	71.37 315	73.48 350	51.47 343	75.16 324	85.19 247	65.20 254	60.78 338	80.93 309	42.35 312	77.20 339	57.12 285	53.69 357	85.44 297

pmmvs5		71.55 265	70.20 270	75.61 283	77.83 332	56.39 303	81.74 267	80.89 297	57.76 322	67.46 297	84.49 262	49.26 268	85.32 300	57.08 286	75.29 280	85.11 303

Anonymous20240521		68.80 289	67.22 296	73.55 301	74.33 345	54.11 325	83.18 252	85.61 243	58.15 319	61.68 335	80.94 307	30.71 350	81.27 323	57.00 287	73.34 302	85.28 299

mvsany_test1		62.30 316	61.26 320	65.41 336	69.52 358	54.86 319	66.86 352	49.78 373	46.65 350	68.50 290	83.21 282	49.15 269	66.28 365	56.93 288	60.77 345	75.11 351

TransMVSNet (Re)		75.39 235	74.56 227	77.86 259	85.50 227	57.10 292	86.78 168	86.09 239	72.17 151	71.53 259	87.34 194	63.01 129	89.31 260	56.84 289	61.83 342	87.17 265

test_vis3_rt		49.26 332	47.02 334	56.00 346	54.30 371	45.27 362	66.76 354	48.08 374	36.83 361	44.38 361	53.20 366	7.17 377	64.07 367	56.77 290	55.66 353	58.65 363

EPMVS		69.02 287	68.16 282	71.59 313	79.61 324	49.80 352	77.40 312	66.93 357	62.82 284	70.01 273	79.05 321	45.79 294	77.86 337	56.58 291	75.26 281	87.13 268

KD-MVS_self_test		68.81 288	67.59 293	72.46 309	74.29 346	45.45 358	77.93 309	87.00 225	63.12 276	63.99 327	78.99 325	42.32 313	84.77 304	56.55 292	64.09 339	87.16 267

tpm2		73.26 252	71.46 254	78.63 248	83.34 262	56.71 298	80.65 280	80.40 306	56.63 329	73.55 237	82.02 299	51.80 240	91.24 227	56.35 293	78.42 238	87.95 246

LTVRE_ROB	69.57 13	76.25 222	74.54 228	81.41 193	88.60 155	64.38 196	79.24 295	89.12 175	70.76 175	69.79 280	87.86 182	49.09 270	93.20 161	56.21 294	80.16 217	86.65 279
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
ACMH	67.68 16	75.89 226	73.93 234	81.77 185	88.71 152	66.61 148	88.62 112	89.01 178	69.81 190	66.78 306	86.70 215	41.95 319	91.51 221	55.64 295	78.14 241	87.17 265
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		66.51 303	64.71 304	71.90 311	81.45 299	63.52 212	57.98 364	68.95 355	53.57 337	62.59 334	76.70 337	46.22 289	75.29 352	55.25 296	79.68 222	76.88 349

EPNet_dtu		75.46 232	74.86 223	77.23 272	82.57 283	54.60 321	86.89 163	83.09 281	71.64 155	66.25 313	85.86 237	55.99 200	88.04 280	54.92 297	86.55 139	89.05 220
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsany_test3		53.99 324	51.45 328	61.61 341	55.51 370	44.74 364	63.52 360	45.41 377	43.69 354	58.11 347	76.45 339	17.99 363	63.76 368	54.77 298	47.59 363	76.34 350

PVSNet	64.34 18	72.08 264	70.87 263	75.69 282	86.21 218	56.44 302	74.37 329	80.73 300	62.06 292	70.17 271	82.23 296	42.86 310	83.31 314	54.77 298	84.45 164	87.32 262

ITE_SJBPF				78.22 255	81.77 294	60.57 254		83.30 276	69.25 202	67.54 295	87.20 200	36.33 338	87.28 287	54.34 300	74.62 288	86.80 275

MDTV_nov1_ep13_2view						37.79 371	75.16 324		55.10 334	66.53 308		49.34 266		53.98 301		87.94 247

gg-mvs-nofinetune		69.95 281	67.96 285	75.94 280	83.07 270	54.51 323	77.23 314	70.29 349	63.11 277	70.32 268	62.33 357	43.62 306	88.69 272	53.88 302	87.76 122	84.62 309

PatchMatch-RL		72.38 261	70.90 261	76.80 276	88.60 155	67.38 134	79.53 292	76.17 335	62.75 285	69.36 283	82.00 300	45.51 297	84.89 303	53.62 303	80.58 212	78.12 346

test_f		52.09 328	50.82 329	55.90 347	53.82 373	42.31 368	59.42 363	58.31 369	36.45 362	56.12 354	70.96 352	12.18 369	57.79 370	53.51 304	56.57 352	67.60 356

Patchmtry		70.74 272	69.16 275	75.49 286	80.72 308	54.07 326	74.94 328	80.30 307	58.34 318	70.01 273	81.19 302	52.50 225	86.54 290	53.37 305	71.09 316	85.87 294

USDC		70.33 277	68.37 279	76.21 279	80.60 310	56.23 306	79.19 297	86.49 231	60.89 298	61.29 336	85.47 246	31.78 348	89.47 258	53.37 305	76.21 264	82.94 329

LF4IMVS		64.02 313	62.19 316	69.50 325	70.90 357	53.29 334	76.13 316	77.18 329	52.65 340	58.59 344	80.98 306	23.55 358	76.52 343	53.06 307	66.66 330	78.68 345

PAPM		77.68 198	76.40 204	81.51 190	87.29 203	61.85 239	83.78 241	89.59 157	64.74 260	71.23 261	88.70 157	62.59 132	93.66 141	52.66 308	87.03 132	89.01 222

CL-MVSNet_self_test		72.37 262	71.46 254	75.09 289	79.49 326	53.53 329	80.76 278	85.01 250	69.12 208	70.51 265	82.05 298	57.92 186	84.13 307	52.27 309	66.00 334	87.60 254

tpm cat1		70.57 274	68.31 280	77.35 269	82.41 287	57.95 279	78.08 307	80.22 309	52.04 341	68.54 289	77.66 334	52.00 235	87.84 282	51.77 310	72.07 310	86.25 283

our_test_3		69.14 286	67.00 297	75.57 284	79.80 321	58.80 268	77.96 308	77.81 322	59.55 309	62.90 333	78.25 330	47.43 279	83.97 308	51.71 311	67.58 328	83.93 317

MDTV_nov1_ep13			69.97 271		83.18 267	53.48 330	77.10 315	80.18 310	60.45 300	69.33 284	80.44 311	48.89 275	86.90 288	51.60 312	78.51 236

JIA-IIPM		66.32 305	62.82 315	76.82 275	77.09 336	61.72 242	65.34 357	75.38 336	58.04 321	64.51 323	62.32 358	42.05 318	86.51 291	51.45 313	69.22 323	82.21 331

MSDG		73.36 251	70.99 260	80.49 217	84.51 242	65.80 164	80.71 279	86.13 238	65.70 250	65.46 316	83.74 276	44.60 301	90.91 237	51.13 314	76.89 251	84.74 306

PatchT		68.46 293	67.85 287	70.29 322	80.70 309	43.93 365	72.47 332	74.88 338	60.15 304	70.55 264	76.57 338	49.94 259	81.59 320	50.58 315	74.83 286	85.34 298

GG-mvs-BLEND				75.38 287	81.59 297	55.80 310	79.32 294	69.63 351		67.19 300	73.67 347	43.24 307	88.90 270	50.41 316	84.50 161	81.45 335

KD-MVS_2432*1600		66.22 306	63.89 307	73.21 303	75.47 343	53.42 331	70.76 339	84.35 258	64.10 268	66.52 309	78.52 327	34.55 343	84.98 301	50.40 317	50.33 361	81.23 336

miper_refine_blended		66.22 306	63.89 307	73.21 303	75.47 343	53.42 331	70.76 339	84.35 258	64.10 268	66.52 309	78.52 327	34.55 343	84.98 301	50.40 317	50.33 361	81.23 336

AllTest		70.96 269	68.09 284	79.58 237	85.15 232	63.62 207	84.58 223	79.83 311	62.31 289	60.32 339	86.73 209	32.02 346	88.96 268	50.28 319	71.57 313	86.15 286

TestCases				79.58 237	85.15 232	63.62 207		79.83 311	62.31 289	60.32 339	86.73 209	32.02 346	88.96 268	50.28 319	71.57 313	86.15 286

TAPA-MVS	73.13 9	79.15 159	77.94 164	82.79 166	89.59 114	62.99 227	88.16 127	91.51 107	65.77 249	77.14 173	91.09 102	60.91 164	93.21 158	50.26 321	87.05 131	92.17 116
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
YYNet1		65.03 309	62.91 313	71.38 314	75.85 339	56.60 300	69.12 347	74.66 342	57.28 326	54.12 355	77.87 332	45.85 293	74.48 354	49.95 322	61.52 344	83.05 326

MDA-MVSNet_test_wron		65.03 309	62.92 312	71.37 315	75.93 338	56.73 296	69.09 348	74.73 340	57.28 326	54.03 356	77.89 331	45.88 292	74.39 355	49.89 323	61.55 343	82.99 328

tpmvs		71.09 268	69.29 273	76.49 277	82.04 291	56.04 308	78.92 300	81.37 296	64.05 270	67.18 301	78.28 329	49.74 262	89.77 251	49.67 324	72.37 306	83.67 319

ppachtmachnet_test		70.04 280	67.34 295	78.14 256	79.80 321	61.13 246	79.19 297	80.59 302	59.16 313	65.27 318	79.29 320	46.75 285	87.29 286	49.33 325	66.72 329	86.00 292

UnsupCasMVSNet_bld		63.70 314	61.53 319	70.21 323	73.69 349	51.39 344	72.82 331	81.89 290	55.63 333	57.81 348	71.80 350	38.67 329	78.61 332	49.26 326	52.21 359	80.63 339

dp		66.80 300	65.43 302	70.90 321	79.74 323	48.82 353	75.12 326	74.77 339	59.61 308	64.08 326	77.23 335	42.89 309	80.72 325	48.86 327	66.58 331	83.16 324

FMVSNet5		69.50 284	67.96 285	74.15 299	82.97 275	55.35 314	80.01 288	82.12 289	62.56 287	63.02 330	81.53 301	36.92 336	81.92 319	48.42 328	74.06 292	85.17 302

thres100view900		76.50 216	75.55 214	79.33 240	89.52 117	56.99 293	85.83 196	83.23 278	73.94 120	76.32 189	87.12 203	51.89 238	91.95 206	48.33 329	83.75 172	89.07 215

tfpn200view9		76.42 219	75.37 219	79.55 239	89.13 137	57.65 284	85.17 207	83.60 269	73.41 134	76.45 184	86.39 227	52.12 231	91.95 206	48.33 329	83.75 172	89.07 215

thres400		76.50 216	75.37 219	79.86 229	89.13 137	57.65 284	85.17 207	83.60 269	73.41 134	76.45 184	86.39 227	52.12 231	91.95 206	48.33 329	83.75 172	90.00 190

LCM-MVSNet		54.25 323	49.68 332	67.97 332	53.73 374	45.28 361	66.85 353	80.78 299	35.96 363	39.45 364	62.23 359	8.70 374	78.06 336	48.24 332	51.20 360	80.57 340

RPMNet		73.51 248	70.49 265	82.58 172	81.32 304	65.19 178	75.92 319	92.27 76	57.60 324	72.73 246	76.45 339	52.30 228	95.43 63	48.14 333	77.71 242	87.11 269

thres600view7		76.50 216	75.44 215	79.68 234	89.40 122	57.16 290	85.53 204	83.23 278	73.79 125	76.26 190	87.09 204	51.89 238	91.89 209	48.05 334	83.72 175	90.00 190

TDRefinement		67.49 296	64.34 305	76.92 274	73.47 351	61.07 247	84.86 216	82.98 282	59.77 307	58.30 346	85.13 254	26.06 354	87.89 281	47.92 335	60.59 347	81.81 334

thres200		75.55 230	74.47 229	78.82 246	87.78 185	57.85 281	83.07 257	83.51 272	72.44 147	75.84 199	84.42 263	52.08 233	91.75 213	47.41 336	83.64 176	86.86 274

PVSNet_0	57.27 20	61.67 318	59.27 321	68.85 328	79.61 324	57.44 288	68.01 349	73.44 345	55.93 332	58.54 345	70.41 353	44.58 302	77.55 338	47.01 337	35.91 367	71.55 355

DP-MVS		76.78 213	74.57 226	83.42 134	93.29 48	69.46 90	88.55 114	83.70 268	63.98 272	70.20 269	88.89 153	54.01 217	94.80 94	46.66 338	81.88 197	86.01 290

COLMAP_ROB	66.92 17	73.01 255	70.41 267	80.81 211	87.13 206	65.63 167	88.30 122	84.19 263	62.96 280	63.80 329	87.69 185	38.04 333	92.56 184	46.66 338	74.91 285	84.24 312
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet		70.69 273	69.30 272	74.88 291	84.52 241	56.35 305	75.87 321	79.42 315	64.59 261	67.76 292	82.41 292	41.10 321	81.54 321	46.64 340	81.34 201	86.75 277

LS3D		76.95 211	74.82 224	83.37 137	90.45 94	67.36 135	89.15 93	86.94 226	61.87 293	69.52 281	90.61 113	51.71 241	94.53 103	46.38 341	86.71 137	88.21 244

MDA-MVSNet-bldmvs		66.68 301	63.66 309	75.75 281	79.28 328	60.56 255	73.92 330	78.35 320	64.43 263	50.13 359	79.87 318	44.02 304	83.67 310	46.10 342	56.86 350	83.03 327

new-patchmatchnet		61.73 317	61.73 318	61.70 340	72.74 354	24.50 379	69.16 346	78.03 321	61.40 295	56.72 351	75.53 344	38.42 330	76.48 344	45.95 343	57.67 349	84.13 314

TinyColmap		67.30 299	64.81 303	74.76 293	81.92 293	56.68 299	80.29 285	81.49 295	60.33 301	56.27 353	83.22 281	24.77 356	87.66 284	45.52 344	69.47 321	79.95 342

pmmvs3		57.79 321	54.26 325	68.37 330	64.02 365	56.72 297	75.12 326	65.17 360	40.20 357	52.93 357	69.86 354	20.36 361	75.48 350	45.45 345	55.25 356	72.90 354

OpenMVS_ROB	64.09 19	70.56 275	68.19 281	77.65 264	80.26 313	59.41 267	85.01 212	82.96 283	58.76 316	65.43 317	82.33 293	37.63 335	91.23 228	45.34 346	76.03 265	82.32 330

test0.0.03 1		68.00 295	67.69 291	68.90 327	77.55 333	47.43 354	75.70 322	72.95 346	66.66 237	66.56 307	82.29 295	48.06 277	75.87 348	44.97 347	74.51 289	83.41 321

testgi		66.67 302	66.53 300	67.08 334	75.62 341	41.69 369	75.93 318	76.50 332	66.11 244	65.20 321	86.59 219	35.72 340	74.71 353	43.71 348	73.38 301	84.84 305

Anonymous20231206		68.60 290	67.80 289	71.02 319	80.23 314	50.75 347	78.30 306	80.47 304	56.79 328	66.11 314	82.63 291	46.35 288	78.95 331	43.62 349	75.70 268	83.36 322

tfpnnormal		74.39 239	73.16 242	78.08 257	86.10 219	58.05 275	84.65 221	87.53 215	70.32 182	71.22 262	85.63 242	54.97 204	89.86 250	43.03 350	75.02 284	86.32 282

MIMVSNet1		68.58 291	66.78 299	73.98 300	80.07 316	51.82 339	80.77 277	84.37 257	64.40 264	59.75 342	82.16 297	36.47 337	83.63 311	42.73 351	70.33 318	86.48 281

test20.03		67.45 297	66.95 298	68.94 326	75.48 342	44.84 363	77.50 311	77.67 323	66.66 237	63.01 331	83.80 274	47.02 282	78.40 333	42.53 352	68.86 326	83.58 320

ADS-MVSNet2		66.20 308	63.33 310	74.82 292	79.92 317	58.75 269	67.55 350	75.19 337	53.37 338	65.25 319	75.86 341	42.32 313	80.53 326	41.57 353	68.91 324	85.18 300

ADS-MVSNet		64.36 312	62.88 314	68.78 329	79.92 317	47.17 355	67.55 350	71.18 347	53.37 338	65.25 319	75.86 341	42.32 313	73.99 356	41.57 353	68.91 324	85.18 300

Patchmatch-test		64.82 311	63.24 311	69.57 324	79.42 327	49.82 351	63.49 361	69.05 354	51.98 343	59.95 341	80.13 314	50.91 247	70.98 359	40.66 355	73.57 297	87.90 248

MVS-HIRNet		59.14 320	57.67 323	63.57 338	81.65 295	43.50 366	71.73 334	65.06 361	39.59 359	51.43 358	57.73 363	38.34 331	82.58 318	39.53 356	73.95 293	64.62 359

DSMNet-mixed		57.77 322	56.90 324	60.38 342	67.70 361	35.61 372	69.18 345	53.97 371	32.30 367	57.49 349	79.88 317	40.39 325	68.57 364	38.78 357	72.37 306	76.97 348

N_pmnet		52.79 327	53.26 326	51.40 351	78.99 330	7.68 382	69.52 343	3.89 382	51.63 344	57.01 350	74.98 345	40.83 323	65.96 366	37.78 358	64.67 337	80.56 341

test_0402		72.79 258	70.44 266	79.84 230	88.13 169	65.99 158	85.93 191	84.29 260	65.57 252	67.40 299	85.49 245	46.92 283	92.61 182	35.88 359	74.38 290	80.94 338

new_pmnet		50.91 330	50.29 330	52.78 350	68.58 360	34.94 374	63.71 359	56.63 370	39.73 358	44.95 360	65.47 356	21.93 360	58.48 369	34.98 360	56.62 351	64.92 358

APD_test1		53.31 326	49.93 331	63.42 339	65.68 363	50.13 349	71.59 335	66.90 358	34.43 364	40.58 363	71.56 351	8.65 375	76.27 345	34.64 361	55.36 355	63.86 360

ANet_high		50.57 331	46.10 335	63.99 337	48.67 377	39.13 370	70.99 338	80.85 298	61.39 296	31.18 366	57.70 364	17.02 365	73.65 357	31.22 362	15.89 374	79.18 344

EGC-MVSNET		52.07 329	47.05 333	67.14 333	83.51 259	60.71 252	80.50 282	67.75 356	0.07 377	0.43 378	75.85 343	24.26 357	81.54 321	28.82 363	62.25 341	59.16 362

PMMVS2		40.82 337	38.86 340	46.69 352	53.84 372	16.45 380	48.61 367	49.92 372	37.49 360	31.67 365	60.97 360	8.14 376	56.42 371	28.42 364	30.72 369	67.19 357

tmp_tt		18.61 343	21.40 346	10.23 359	4.82 382	10.11 381	34.70 369	30.74 380	1.48 376	23.91 372	26.07 373	28.42 352	13.41 378	27.12 365	15.35 375	7.17 373

test_method		31.52 339	29.28 343	38.23 354	27.03 381	6.50 383	20.94 372	62.21 365	4.05 375	22.35 373	52.50 367	13.33 367	47.58 374	27.04 366	34.04 368	60.62 361

testf1		45.72 333	41.96 336	57.00 344	56.90 368	45.32 359	66.14 355	59.26 367	26.19 368	30.89 367	60.96 361	4.14 378	70.64 360	26.39 367	46.73 365	55.04 365

APD_test2		45.72 333	41.96 336	57.00 344	56.90 368	45.32 359	66.14 355	59.26 367	26.19 368	30.89 367	60.96 361	4.14 378	70.64 360	26.39 367	46.73 365	55.04 365

FPMVS		53.68 325	51.64 327	59.81 343	65.08 364	51.03 345	69.48 344	69.58 352	41.46 356	40.67 362	72.32 349	16.46 366	70.00 362	24.24 369	65.42 335	58.40 364

Gipuma		45.18 335	41.86 338	55.16 349	77.03 337	51.52 342	32.50 370	80.52 303	32.46 366	27.12 369	35.02 370	9.52 373	75.50 349	22.31 370	60.21 348	38.45 369
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX				27.40 357	40.17 380	26.90 377		24.59 381	17.44 373	23.95 371	48.61 368	9.77 372	26.48 376	18.06 371	24.47 370	28.83 370

PMVS	37.38 22	44.16 336	40.28 339	55.82 348	40.82 379	42.54 367	65.12 358	63.99 363	34.43 364	24.48 370	57.12 365	3.92 380	76.17 347	17.10 372	55.52 354	48.75 367
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 341	25.89 345	43.81 353	44.55 378	35.46 373	28.87 371	39.07 378	18.20 372	18.58 374	40.18 369	2.68 381	47.37 375	17.07 373	23.78 371	48.60 368
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		31.77 338	30.64 341	35.15 355	52.87 375	27.67 376	57.09 365	47.86 375	24.64 370	16.40 375	33.05 371	11.23 371	54.90 372	14.46 374	18.15 372	22.87 371

EMVS		30.81 340	29.65 342	34.27 356	50.96 376	25.95 378	56.58 366	46.80 376	24.01 371	15.53 376	30.68 372	12.47 368	54.43 373	12.81 375	17.05 373	22.43 372

wuyk23d		16.82 344	15.94 347	19.46 358	58.74 367	31.45 375	39.22 368	3.74 383	6.84 374	6.04 377	2.70 377	1.27 382	24.29 377	10.54 376	14.40 376	2.63 374

testmvs		6.04 347	8.02 350	0.10 361	0.08 383	0.03 385	69.74 342	0.04 384	0.05 378	0.31 379	1.68 378	0.02 384	0.04 379	0.24 377	0.02 377	0.25 376

test123		6.12 346	8.11 349	0.14 360	0.06 384	0.09 384	71.05 337	0.03 385	0.04 379	0.25 380	1.30 379	0.05 383	0.03 380	0.21 378	0.01 378	0.29 375

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

cdsmvs_eth3d_5k		19.96 342	26.61 344	0.00 362	0.00 385	0.00 386	0.00 373	89.26 167	0.00 380	0.00 381	88.61 161	61.62 148	0.00 381	0.00 379	0.00 379	0.00 377

pcd_1.5k_mvsjas		5.26 348	7.02 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	63.15 125	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		7.23 345	9.64 348	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	86.72 211	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					95.00 10	72.39 38	95.06 1	93.84 15	74.49 109	91.30 15

test_one_0601					95.07 7	71.46 53		94.14 5	78.27 33	92.05 11	95.74 6	80.83 11

eth-test2					0.00 385

eth-test					0.00 385

test_241102_ONE					95.30 2	70.98 61		94.06 10	77.17 51	93.10 1	95.39 11	82.99 1	97.27 10

save fliter					93.80 40	72.35 41	90.47 62	91.17 116	74.31 112

test0726					95.27 5	71.25 55	93.60 6	94.11 6	77.33 46	92.81 3	95.79 3	80.98 9

GSMVS																88.96 226

test_part2					95.06 8	72.65 31				91.80 13

sam_mvs1												51.32 244				88.96 226

sam_mvs												50.01 257

MTGPA								92.02 85

test_post											5.46 375	50.36 255	84.24 306

patchmatchnet-post											74.00 346	51.12 246	88.60 273

MTMP							92.18 33	32.83 379

TEST9					93.26 50	72.96 24	88.75 106	91.89 93	68.44 222	85.00 45	93.10 54	74.36 28	95.41 65

test_8					93.13 52	72.57 34	88.68 111	91.84 97	68.69 218	84.87 49	93.10 54	74.43 26	95.16 74

agg_prior					92.85 59	71.94 49		91.78 100		84.41 59			94.93 85

test_prior4						72.60 33	89.01 96

test_prior				86.33 52	92.61 65	69.59 85		92.97 50					95.48 60			93.91 50

新几何2							86.29 183

旧先验1					91.96 71	65.79 165		86.37 234			93.08 58	69.31 70			92.74 66	88.74 235

原ACMM2							86.86 164

test222					91.50 77	68.26 115	84.16 235	83.20 280	54.63 336	79.74 115	91.63 86	58.97 179			91.42 83	86.77 276

segment_acmp												73.08 37

testdata1							84.14 236		75.71 85

test12				86.80 47	92.63 64	70.70 70		91.79 99		82.71 85		71.67 47	96.16 42		94.50 48	93.54 70

plane_prior7					90.08 102	68.51 111

plane_prior6					89.84 111	68.70 106						60.42 172

plane_prior4											91.00 107

plane_prior3						68.60 109			78.44 29	78.92 127

plane_prior2							91.25 48		79.12 21

plane_prior1					89.90 110

plane_prior						68.71 104	90.38 65		77.62 37						86.16 146

n2								0.00 386

nn								0.00 386

door-mid								69.98 350

test11								92.23 79

door								69.44 353

HQP5-MVS						66.98 142

HQP-NCC					89.33 126		89.17 89		76.41 70	77.23 168

ACMP_Plane					89.33 126		89.17 89		76.41 70	77.23 168

HQP4-MVS										77.24 167			95.11 78			91.03 148

HQP3-MVS								92.19 82							85.99 149

HQP2-MVS												60.17 175

NP-MVS					89.62 113	68.32 113					90.24 119

ACMMP++_ref															81.95 196

ACMMP++															81.25 202

Test By Simon												64.33 112

High-resolution multi-view benchmark