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.

SED-MVS		90.08 1	90.85 1	87.77 23	95.30 2	70.98 64	93.57 5	94.06 11	77.24 47	93.10 1	95.72 6	82.99 1	97.44 2	89.07 6	96.63 2	94.88 7

test_241102_ONE					95.30 2	70.98 64		94.06 11	77.17 50	93.10 1	95.39 9	82.99 1	97.27 7

OPU-MVS				89.06 1	94.62 13	75.42 2	93.57 5				94.02 41	82.45 3	96.87 16	83.77 46	96.48 6	94.88 7

DPE-MVS		89.48 4	89.98 3	88.01 12	94.80 9	72.69 30	91.59 36	94.10 8	75.90 81	92.29 6	95.66 8	81.67 4	97.38 6	87.44 17	96.34 11	93.95 44

test_0728_THIRD									78.38 32	92.12 8	95.78 4	81.46 5	97.40 4	89.42 2	96.57 5	94.67 16

test_241102_TWO								94.06 11	77.24 47	92.78 4	95.72 6	81.26 6	97.44 2	89.07 6	96.58 4	94.26 31

MSP-MVS		89.60 2	90.35 2	87.33 42	95.27 5	71.25 58	93.49 7	92.73 58	77.33 45	92.12 8	95.78 4	80.98 7	97.40 4	89.08 4	96.41 8	93.33 75

test0726					95.27 5	71.25 58	93.60 4	94.11 6	77.33 45	92.81 3	95.79 3	80.98 7

DeepPCF-MVS	80.84 1	88.10 11	88.56 11	86.73 53	92.24 69	69.03 100	89.57 82	93.39 31	77.53 42	89.79 14	94.12 38	78.98 9	96.58 32	85.66 24	95.72 25	94.58 19

DVP-MVS		89.51 3	89.91 4	88.30 7	94.28 26	73.46 16	92.90 14	94.11 6	80.27 12	91.35 11	94.16 36	78.35 10	96.77 20	89.59 1	94.22 59	94.67 16

ETH3 D test6400		87.50 24	87.44 25	87.70 32	93.71 39	71.75 53	90.62 53	94.05 14	70.80 165	87.59 28	93.51 49	77.57 11	96.63 27	83.31 48	95.77 22	94.72 15

APDe-MVS		89.15 5	89.63 5	87.73 27	94.49 18	71.69 54	93.83 2	93.96 15	75.70 85	91.06 12	96.03 1	76.84 12	97.03 12	89.09 3	95.65 28	94.47 23

CNVR-MVS		88.93 8	89.13 8	88.33 5	94.77 10	73.82 7	90.51 55	93.00 43	80.90 9	88.06 24	94.06 40	76.43 13	96.84 17	88.48 11	95.99 15	94.34 27

MCST-MVS		87.37 29	87.25 29	87.73 27	94.53 17	72.46 38	89.82 74	93.82 17	73.07 134	84.86 53	92.89 64	76.22 14	96.33 35	84.89 32	95.13 37	94.40 24

CSCG		86.41 46	86.19 46	87.07 47	92.91 56	72.48 36	90.81 49	93.56 23	73.95 118	83.16 77	91.07 98	75.94 15	95.19 76	79.94 79	94.38 55	93.55 67

HPM-MVS++		89.02 7	89.15 7	88.63 2	95.01 8	76.03 1	92.38 23	92.85 53	80.26 13	87.78 26	94.27 31	75.89 16	96.81 19	87.45 16	96.44 7	93.05 86

TSAR-MVS + MP.		88.02 16	88.11 15	87.72 29	93.68 42	72.13 46	91.41 41	92.35 72	74.62 105	88.90 17	93.85 45	75.75 17	96.00 49	87.80 12	94.63 48	95.04 3
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
xxxxxxxxxxxxxcwj		87.88 18	87.92 18	87.77 23	93.80 37	72.35 42	90.47 58	89.69 157	74.31 110	89.16 15	95.10 11	75.65 18	96.19 41	87.07 18	96.01 13	94.79 11

SF-MVS		88.46 10	88.74 10	87.64 35	92.78 60	71.95 49	92.40 20	94.74 2	75.71 83	89.16 15	95.10 11	75.65 18	96.19 41	87.07 18	96.01 13	94.79 11

9.14			88.26 14		92.84 59		91.52 39	94.75 1	73.93 120	88.57 20	94.67 17	75.57 20	95.79 55	86.77 20	95.76 24

ETH3D-3000-0.1		88.09 12	88.29 13	87.50 38	92.76 61	71.89 52	91.43 40	94.70 3	74.47 107	88.86 18	94.61 19	75.23 21	95.84 53	86.62 23	95.92 17	94.78 13

ETH3D cwj APD-0.16		87.31 31	87.27 27	87.44 40	91.60 78	72.45 39	90.02 70	94.37 4	71.76 150	87.28 29	94.27 31	75.18 22	96.08 45	85.16 27	95.77 22	93.80 55

agg_prior1		86.22 48	86.09 49	86.62 56	92.85 57	71.94 50	88.59 111	91.78 97	68.96 205	84.41 59	93.18 57	74.94 23	94.93 86	84.75 35	95.33 34	93.01 89

SD-MVS		88.06 13	88.50 12	86.71 54	92.60 67	72.71 28	91.81 35	93.19 36	77.87 33	90.32 13	94.00 42	74.83 24	93.78 133	87.63 14	94.27 58	93.65 62
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
DELS-MVS		85.41 58	85.30 57	85.77 69	88.49 153	67.93 129	85.52 202	93.44 28	78.70 28	83.63 74	89.03 145	74.57 25	95.71 58	80.26 77	94.04 60	93.66 57
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
Regformer-2		86.63 42	86.53 41	86.95 48	89.33 120	71.24 61	88.43 114	92.05 81	82.50 1	86.88 31	90.09 117	74.45 26	95.61 59	84.38 38	90.63 88	94.01 41

train_agg		86.43 44	86.20 45	87.13 46	93.26 49	72.96 24	88.75 104	91.89 91	68.69 210	85.00 46	93.10 58	74.43 27	95.41 67	84.97 29	95.71 26	93.02 88

test_8					93.13 51	72.57 34	88.68 109	91.84 94	68.69 210	84.87 52	93.10 58	74.43 27	95.16 77

Regformer-1		86.41 46	86.33 42	86.64 55	89.33 120	70.93 69	88.43 114	91.39 110	82.14 3	86.65 33	90.09 117	74.39 29	95.01 85	83.97 45	90.63 88	93.97 43

TEST9					93.26 49	72.96 24	88.75 104	91.89 91	68.44 214	85.00 46	93.10 58	74.36 30	95.41 67

SMA-MVS		89.08 6	89.23 6	88.61 3	94.25 27	73.73 8	92.40 20	93.63 21	74.77 101	92.29 6	95.97 2	74.28 31	97.24 8	88.58 10	96.91 1	94.87 9

test_prior3		86.73 38	86.86 38	86.33 60	92.61 65	69.59 91	88.85 100	92.97 48	75.41 89	84.91 48	93.54 47	74.28 31	95.48 63	83.31 48	95.86 18	93.91 45

test_prior2							88.85 100		75.41 89	84.91 48	93.54 47	74.28 31		83.31 48	95.86 18

TSAR-MVS + GP.		85.71 53	85.33 55	86.84 50	91.34 80	72.50 35	89.07 94	87.28 219	76.41 70	85.80 38	90.22 115	74.15 34	95.37 72	81.82 63	91.88 74	92.65 99

SteuartSystems-ACMMP		88.72 9	88.86 9	88.32 6	92.14 71	72.96 24	93.73 3	93.67 20	80.19 14	88.10 23	94.80 14	73.76 35	97.11 10	87.51 15	95.82 20	94.90 6
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		87.44 25	87.52 23	87.19 44	94.24 28	72.39 40	91.86 34	92.83 54	73.01 136	88.58 19	94.52 20	73.36 36	96.49 33	84.26 40	95.01 38	92.70 95
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
canonicalmvs		85.91 50	85.87 51	86.04 67	89.84 106	69.44 98	90.45 61	93.00 43	76.70 66	88.01 25	91.23 92	73.28 37	93.91 128	81.50 65	88.80 109	94.77 14

testtj		87.78 19	87.78 20	87.77 23	94.55 16	72.47 37	92.23 28	93.49 26	74.75 102	88.33 21	94.43 27	73.27 38	97.02 13	84.18 43	94.84 44	93.82 52

segment_acmp												73.08 39

DPM-MVS		84.93 65	84.29 69	86.84 50	90.20 98	73.04 22	87.12 154	93.04 39	69.80 184	82.85 81	91.22 93	73.06 40	96.02 47	76.72 108	94.63 48	91.46 131

NCCC		88.06 13	88.01 17	88.24 8	94.41 22	73.62 9	91.22 45	92.83 54	81.50 6	85.79 39	93.47 52	73.02 41	97.00 14	84.90 30	94.94 40	94.10 35

nrg030		83.88 70	83.53 71	84.96 86	86.77 201	69.28 99	90.46 60	92.67 60	74.79 100	82.95 78	91.33 91	72.70 42	93.09 165	80.79 73	79.28 223	92.50 102

Regformer-4		85.68 54	85.45 53	86.35 59	88.95 137	69.67 90	88.29 124	91.29 112	81.73 5	85.36 41	90.01 119	72.62 43	95.35 73	83.28 51	87.57 121	94.03 39

Regformer-3		85.23 60	85.07 60	85.70 70	88.95 137	69.01 102	88.29 124	89.91 151	80.95 8	85.01 45	90.01 119	72.45 44	94.19 114	82.50 60	87.57 121	93.90 47

CDPH-MVS		85.76 52	85.29 58	87.17 45	93.49 46	71.08 62	88.58 112	92.42 70	68.32 215	84.61 56	93.48 50	72.32 45	96.15 44	79.00 82	95.43 30	94.28 30

MP-MVS		87.71 20	87.64 22	87.93 18	94.36 25	73.88 5	92.71 19	92.65 62	77.57 38	83.84 69	94.40 29	72.24 46	96.28 37	85.65 25	95.30 36	93.62 64
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffmvs		85.11 63	85.14 59	85.01 84	87.20 193	65.77 164	87.75 139	92.83 54	77.84 34	84.36 62	92.38 70	72.15 47	93.93 127	81.27 67	90.48 90	95.33 1

DeepC-MVS	79.81 2	87.08 36	86.88 37	87.69 33	91.16 82	72.32 44	90.31 63	93.94 16	77.12 52	82.82 82	94.23 34	72.13 48	97.09 11	84.83 33	95.37 31	93.65 62
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline		84.93 65	84.98 61	84.80 93	87.30 191	65.39 171	87.30 150	92.88 51	77.62 36	84.04 67	92.26 71	71.81 49	93.96 121	81.31 66	90.30 92	95.03 4

ZNCC-MVS		87.94 17	87.85 19	88.20 9	94.39 24	73.33 18	93.03 12	93.81 18	76.81 60	85.24 43	94.32 30	71.76 50	96.93 15	85.53 26	95.79 21	94.32 28

test12				86.80 52	92.63 64	70.70 74		91.79 96		82.71 84		71.67 51	96.16 43		94.50 51	93.54 68

UniMVSNet_NR-MVSNet		81.88 99	81.54 98	82.92 157	88.46 155	63.46 208	87.13 153	92.37 71	80.19 14	78.38 133	89.14 140	71.66 52	93.05 167	70.05 161	76.46 249	92.25 109

DeepC-MVS_fast	79.65 3	86.91 37	86.62 40	87.76 26	93.52 45	72.37 41	91.26 42	93.04 39	76.62 67	84.22 63	93.36 54	71.44 53	96.76 21	80.82 71	95.33 34	94.16 33
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVS_111021_HR		85.14 62	84.75 65	86.32 62	91.65 77	72.70 29	85.98 187	90.33 139	76.11 79	82.08 89	91.61 84	71.36 54	94.17 116	81.02 68	92.58 71	92.08 115

ACMMP_NAP		88.05 15	88.08 16	87.94 15	93.70 40	73.05 21	90.86 48	93.59 22	76.27 77	88.14 22	95.09 13	71.06 55	96.67 24	87.67 13	96.37 10	94.09 36

MP-MVS-pluss		87.67 21	87.72 21	87.54 36	93.64 43	72.04 48	89.80 76	93.50 25	75.17 96	86.34 34	95.29 10	70.86 56	96.00 49	88.78 9	96.04 12	94.58 19
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		87.58 22	87.47 24	87.94 15	94.58 14	73.54 13	93.04 10	93.24 33	76.78 62	84.91 48	94.44 25	70.78 57	96.61 28	84.53 36	94.89 42	93.66 57

#test#		87.33 30	87.13 32	87.94 15	94.58 14	73.54 13	92.34 25	93.24 33	75.23 93	84.91 48	94.44 25	70.78 57	96.61 28	83.75 47	94.89 42	93.66 57

EI-MVSNet-Vis-set		84.19 69	83.81 70	85.31 74	88.18 162	67.85 130	87.66 141	89.73 156	80.05 16	82.95 78	89.59 129	70.74 59	94.82 94	80.66 74	84.72 156	93.28 77

GST-MVS		87.42 27	87.26 28	87.89 22	94.12 33	72.97 23	92.39 22	93.43 29	76.89 58	84.68 54	93.99 43	70.67 60	96.82 18	84.18 43	95.01 38	93.90 47

CS-MVS		84.76 68	84.61 67	85.22 79	89.66 108	66.43 151	90.23 65	93.56 23	76.52 69	82.59 86	85.93 226	70.41 61	95.80 54	79.93 80	92.68 70	93.42 71

CANet		86.45 43	86.10 48	87.51 37	90.09 100	70.94 68	89.70 80	92.59 64	81.78 4	81.32 99	91.43 90	70.34 62	97.23 9	84.26 40	93.36 63	94.37 25

alignmvs		85.48 55	85.32 56	85.96 68	89.51 114	69.47 95	89.74 78	92.47 66	76.17 78	87.73 27	91.46 89	70.32 63	93.78 133	81.51 64	88.95 106	94.63 18

EI-MVSNet-UG-set		83.81 71	83.38 73	85.09 82	87.87 171	67.53 134	87.44 147	89.66 158	79.74 18	82.23 88	89.41 138	70.24 64	94.74 97	79.95 78	83.92 164	92.99 90

MVS_Test		83.15 82	83.06 77	83.41 135	86.86 197	63.21 214	86.11 185	92.00 85	74.31 110	82.87 80	89.44 137	70.03 65	93.21 156	77.39 100	88.50 115	93.81 53

FC-MVSNet-test		81.52 106	82.02 92	80.03 221	88.42 157	55.97 302	87.95 134	93.42 30	77.10 53	77.38 153	90.98 104	69.96 66	91.79 206	68.46 176	84.50 158	92.33 105

FIs		82.07 96	82.42 84	81.04 204	88.80 144	58.34 266	88.26 126	93.49 26	76.93 57	78.47 132	91.04 99	69.92 67	92.34 189	69.87 164	84.97 153	92.44 104

UniMVSNet (Re)		81.60 105	81.11 103	83.09 148	88.38 158	64.41 189	87.60 142	93.02 42	78.42 31	78.56 129	88.16 167	69.78 68	93.26 155	69.58 167	76.49 248	91.60 124

HPM-MVS		87.11 34	86.98 34	87.50 38	93.88 36	72.16 45	92.19 29	93.33 32	76.07 80	83.81 70	93.95 44	69.77 69	96.01 48	85.15 28	94.66 47	94.32 28
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
Effi-MVS+		83.62 75	83.08 76	85.24 77	88.38 158	67.45 135	88.89 98	89.15 173	75.50 88	82.27 87	88.28 164	69.61 70	94.45 104	77.81 95	87.84 119	93.84 51

PHI-MVS		86.43 44	86.17 47	87.24 43	90.88 88	70.96 66	92.27 27	94.07 10	72.45 139	85.22 44	91.90 77	69.47 71	96.42 34	83.28 51	95.94 16	94.35 26

UA-Net		85.08 64	84.96 62	85.45 72	92.07 72	68.07 127	89.78 77	90.86 125	82.48 2	84.60 57	93.20 56	69.35 72	95.22 75	71.39 150	90.88 86	93.07 85

ETV-MVS		84.90 67	84.67 66	85.59 71	89.39 118	68.66 116	88.74 106	92.64 63	79.97 17	84.10 65	85.71 231	69.32 73	95.38 69	80.82 71	91.37 80	92.72 94

旧先验1					91.96 73	65.79 163		86.37 230			93.08 62	69.31 74			92.74 68	88.74 227

region2R		87.42 27	87.20 31	88.09 10	94.63 12	73.55 11	93.03 12	93.12 38	76.73 65	84.45 58	94.52 20	69.09 75	96.70 23	84.37 39	94.83 45	94.03 39

EIA-MVS		83.31 81	82.80 82	84.82 91	89.59 110	65.59 166	88.21 127	92.68 59	74.66 104	78.96 121	86.42 218	69.06 76	95.26 74	75.54 118	90.09 96	93.62 64

EPP-MVSNet		83.40 79	83.02 78	84.57 97	90.13 99	64.47 188	92.32 26	90.73 126	74.45 109	79.35 118	91.10 96	69.05 77	95.12 78	72.78 141	87.22 129	94.13 34

ACMMPR		87.44 25	87.23 30	88.08 11	94.64 11	73.59 10	93.04 10	93.20 35	76.78 62	84.66 55	94.52 20	68.81 78	96.65 25	84.53 36	94.90 41	94.00 42

mvs_anonymous		79.42 152	79.11 139	80.34 216	84.45 233	57.97 272	82.59 253	87.62 212	67.40 221	76.17 183	88.56 157	68.47 79	89.59 250	70.65 156	86.05 146	93.47 70

zzz-MVS		87.53 23	87.41 26	87.90 19	94.18 31	74.25 3	90.23 65	92.02 82	79.45 19	85.88 36	94.80 14	68.07 80	96.21 39	86.69 21	95.34 32	93.23 78

MTAPA		87.23 32	87.00 33	87.90 19	94.18 31	74.25 3	86.58 172	92.02 82	79.45 19	85.88 36	94.80 14	68.07 80	96.21 39	86.69 21	95.34 32	93.23 78

CP-MVS		87.11 34	86.92 35	87.68 34	94.20 30	73.86 6	93.98 1	92.82 57	76.62 67	83.68 71	94.46 24	67.93 82	95.95 51	84.20 42	94.39 54	93.23 78

PAPM_NR		83.02 85	82.41 85	84.82 91	92.47 68	66.37 153	87.93 136	91.80 95	73.82 122	77.32 155	90.66 107	67.90 83	94.90 90	70.37 158	89.48 103	93.19 82

PGM-MVS		86.68 40	86.27 44	87.90 19	94.22 29	73.38 17	90.22 67	93.04 39	75.53 87	83.86 68	94.42 28	67.87 84	96.64 26	82.70 58	94.57 50	93.66 57

PAPR		81.66 104	80.89 106	83.99 122	90.27 96	64.00 195	86.76 168	91.77 99	68.84 208	77.13 162	89.50 130	67.63 85	94.88 92	67.55 182	88.52 114	93.09 84

Fast-Effi-MVS+		80.81 120	79.92 120	83.47 131	88.85 139	64.51 185	85.53 200	89.39 163	70.79 166	78.49 131	85.06 247	67.54 86	93.58 142	67.03 191	86.58 138	92.32 106

XVS		87.18 33	86.91 36	88.00 13	94.42 20	73.33 18	92.78 15	92.99 45	79.14 21	83.67 72	94.17 35	67.45 87	96.60 30	83.06 53	94.50 51	94.07 37

X-MVStestdata		80.37 134	77.83 167	88.00 13	94.42 20	73.33 18	92.78 15	92.99 45	79.14 21	83.67 72	12.47 347	67.45 87	96.60 30	83.06 53	94.50 51	94.07 37

SR-MVS		86.73 38	86.67 39	86.91 49	94.11 34	72.11 47	92.37 24	92.56 65	74.50 106	86.84 32	94.65 18	67.31 89	95.77 56	84.80 34	92.85 67	92.84 93

NR-MVSNet		80.23 136	79.38 133	82.78 167	87.80 174	63.34 211	86.31 179	91.09 120	79.01 26	72.17 239	89.07 143	67.20 90	92.81 177	66.08 197	75.65 260	92.20 111

MSLP-MVS++		85.43 57	85.76 52	84.45 101	91.93 74	70.24 78	90.71 51	92.86 52	77.46 44	84.22 63	92.81 68	67.16 91	92.94 171	80.36 75	94.35 56	90.16 171

MG-MVS		83.41 78	83.45 72	83.28 138	92.74 62	62.28 228	88.17 129	89.50 161	75.22 94	81.49 98	92.74 69	66.75 92	95.11 79	72.85 140	91.58 77	92.45 103

EI-MVSNet		80.52 131	79.98 119	82.12 176	84.28 234	63.19 216	86.41 176	88.95 183	74.18 115	78.69 126	87.54 181	66.62 93	92.43 184	72.57 143	80.57 206	90.74 150

IterMVS-LS		80.06 139	79.38 133	82.11 177	85.89 210	63.20 215	86.79 165	89.34 164	74.19 114	75.45 196	86.72 202	66.62 93	92.39 186	72.58 142	76.86 243	90.75 149
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		78.59 172	77.76 171	81.08 203	82.66 271	61.56 237	83.65 239	89.15 173	68.87 207	75.55 192	83.79 263	66.49 95	92.03 198	73.25 136	76.39 251	89.64 198

mPP-MVS		86.67 41	86.32 43	87.72 29	94.41 22	73.55 11	92.74 17	92.22 75	76.87 59	82.81 83	94.25 33	66.44 96	96.24 38	82.88 57	94.28 57	93.38 72

cl_fuxian		78.75 167	77.91 164	81.26 197	82.89 266	61.56 237	84.09 234	89.13 175	69.97 181	75.56 191	84.29 255	66.36 97	92.09 197	73.47 133	75.48 264	90.12 174

WR-MVS_H		78.51 173	78.49 149	78.56 246	88.02 168	56.38 297	88.43 114	92.67 60	77.14 51	73.89 222	87.55 180	66.25 98	89.24 256	58.92 254	73.55 288	90.06 181

PCF-MVS	73.52 7	80.38 133	78.84 144	85.01 84	87.71 178	68.99 103	83.65 239	91.46 109	63.00 267	77.77 147	90.28 112	66.10 99	95.09 83	61.40 234	88.22 118	90.94 144
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EPNet		83.72 73	82.92 80	86.14 65	84.22 236	69.48 94	91.05 47	85.27 240	81.30 7	76.83 164	91.65 81	66.09 100	95.56 61	76.00 113	93.85 61	93.38 72
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM1				84.35 106	93.01 55	68.79 106		92.44 67	63.96 262	81.09 104	91.57 85	66.06 101	95.45 65	67.19 188	94.82 46	88.81 224

PVSNet_BlendedMVS		80.60 128	80.02 118	82.36 175	88.85 139	65.40 169	86.16 184	92.00 85	69.34 193	78.11 140	86.09 225	66.02 102	94.27 108	71.52 147	82.06 189	87.39 251

PVSNet_Blended		80.98 114	80.34 114	82.90 158	88.85 139	65.40 169	84.43 225	92.00 85	67.62 218	78.11 140	85.05 248	66.02 102	94.27 108	71.52 147	89.50 102	89.01 214

diffmvs		82.10 94	81.88 95	82.76 169	83.00 262	63.78 200	83.68 238	89.76 154	72.94 137	82.02 90	89.85 122	65.96 104	90.79 233	82.38 62	87.30 128	93.71 56

APD-MVS_3200maxsize		85.97 49	85.88 50	86.22 63	92.69 63	69.53 93	91.93 33	92.99 45	73.54 128	85.94 35	94.51 23	65.80 105	95.61 59	83.04 55	92.51 72	93.53 69

miper_enhance_ethall		77.87 192	76.86 189	80.92 206	81.65 285	61.38 239	82.68 252	88.98 180	65.52 243	75.47 193	82.30 280	65.76 106	92.00 200	72.95 139	76.39 251	89.39 203

PVSNet_Blended_VisFu		82.62 89	81.83 96	84.96 86	90.80 90	69.76 88	88.74 106	91.70 100	69.39 191	78.96 121	88.46 159	65.47 107	94.87 93	74.42 122	88.57 112	90.24 169

API-MVS		81.99 98	81.23 101	84.26 110	90.94 86	70.18 84	91.10 46	89.32 165	71.51 157	78.66 128	88.28 164	65.26 108	95.10 82	64.74 208	91.23 83	87.51 249

TranMVSNet+NR-MVSNet		80.84 117	80.31 115	82.42 173	87.85 172	62.33 226	87.74 140	91.33 111	80.55 11	77.99 143	89.86 121	65.23 109	92.62 178	67.05 190	75.24 273	92.30 107

IS-MVSNet		83.15 82	82.81 81	84.18 112	89.94 104	63.30 212	91.59 36	88.46 196	79.04 25	79.49 116	92.16 72	65.10 110	94.28 107	67.71 180	91.86 75	94.95 5

DU-MVS		81.12 113	80.52 111	82.90 158	87.80 174	63.46 208	87.02 157	91.87 93	79.01 26	78.38 133	89.07 143	65.02 111	93.05 167	70.05 161	76.46 249	92.20 111

Baseline_NR-MVSNet		78.15 183	78.33 156	77.61 261	85.79 211	56.21 300	86.78 166	85.76 237	73.60 126	77.93 144	87.57 179	65.02 111	88.99 260	67.14 189	75.33 269	87.63 246

VNet		82.21 93	82.41 85	81.62 186	90.82 89	60.93 242	84.47 221	89.78 153	76.36 75	84.07 66	91.88 78	64.71 113	90.26 239	70.68 155	88.89 107	93.66 57

Test By Simon												64.33 114

ACMMP		85.89 51	85.39 54	87.38 41	93.59 44	72.63 32	92.74 17	93.18 37	76.78 62	80.73 108	93.82 46	64.33 114	96.29 36	82.67 59	90.69 87	93.23 78
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
DP-MVS Recon		83.11 84	82.09 90	86.15 64	94.44 19	70.92 70	88.79 102	92.20 76	70.53 172	79.17 119	91.03 101	64.12 116	96.03 46	68.39 177	90.14 95	91.50 128

CLD-MVS		82.31 92	81.65 97	84.29 109	88.47 154	67.73 133	85.81 193	92.35 72	75.78 82	78.33 135	86.58 213	64.01 117	94.35 105	76.05 112	87.48 126	90.79 147
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS		78.19 182	76.99 187	81.78 183	85.66 213	66.99 143	84.66 215	90.47 133	55.08 322	72.02 241	85.27 241	63.83 118	94.11 119	66.10 196	89.80 100	84.24 299

WR-MVS		79.49 149	79.22 138	80.27 218	88.79 145	58.35 265	85.06 207	88.61 194	78.56 29	77.65 148	88.34 162	63.81 119	90.66 236	64.98 206	77.22 238	91.80 123

1121		80.84 117	79.77 123	84.05 117	93.11 53	70.78 72	84.66 215	85.42 239	57.37 312	81.76 97	92.02 74	63.41 120	94.12 117	67.28 185	92.93 65	87.26 256

VPA-MVSNet		80.60 128	80.55 110	80.76 209	88.07 166	60.80 245	86.86 162	91.58 103	75.67 86	80.24 111	89.45 136	63.34 121	90.25 240	70.51 157	79.22 224	91.23 136

新几何1				83.42 133	93.13 51	70.71 73		85.48 238	57.43 311	81.80 94	91.98 75	63.28 122	92.27 190	64.60 209	92.99 64	87.27 255

HY-MVS	69.67 12	77.95 189	77.15 183	80.36 215	87.57 185	60.21 253	83.37 246	87.78 210	66.11 234	75.37 199	87.06 197	63.27 123	90.48 238	61.38 235	82.43 186	90.40 164

XXY-MVS		75.41 230	75.56 207	74.96 285	83.59 247	57.82 276	80.59 271	83.87 256	66.54 231	74.93 213	88.31 163	63.24 124	80.09 315	62.16 226	76.85 244	86.97 263

ab-mvs		79.51 148	78.97 142	81.14 201	88.46 155	60.91 243	83.84 236	89.24 170	70.36 174	79.03 120	88.87 148	63.23 125	90.21 241	65.12 204	82.57 185	92.28 108

xiu_mvs_v2_base		81.69 102	81.05 104	83.60 128	89.15 131	68.03 128	84.46 223	90.02 147	70.67 169	81.30 102	86.53 216	63.17 126	94.19 114	75.60 117	88.54 113	88.57 231

pcd_1.5k_mvsjas		5.26 325	7.02 327	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	63.15 127	0.00 354	0.00 351	0.00 351	0.00 350

PS-MVSNAJss		82.07 96	81.31 99	84.34 107	86.51 204	67.27 140	89.27 86	91.51 105	71.75 151	79.37 117	90.22 115	63.15 127	94.27 108	77.69 96	82.36 187	91.49 129

PS-MVSNAJ		81.69 102	81.02 105	83.70 127	89.51 114	68.21 125	84.28 229	90.09 146	70.79 166	81.26 103	85.62 235	63.15 127	94.29 106	75.62 116	88.87 108	88.59 230

WTY-MVS		75.65 226	75.68 206	75.57 280	86.40 205	56.82 288	77.92 297	82.40 276	65.10 246	76.18 181	87.72 174	63.13 130	80.90 312	60.31 242	81.96 190	89.00 216

TransMVSNet (Re)		75.39 231	74.56 221	77.86 255	85.50 217	57.10 285	86.78 166	86.09 235	72.17 146	71.53 245	87.34 185	63.01 131	89.31 255	56.84 273	61.83 324	87.17 258

v8		79.97 142	79.02 141	82.80 164	84.09 238	64.50 187	87.96 133	90.29 142	74.13 117	75.24 205	86.81 199	62.88 132	93.89 130	74.39 123	75.40 267	90.00 183

abl_6		85.23 60	84.95 63	86.07 66	92.23 70	70.48 77	90.80 50	92.08 80	73.51 129	85.26 42	94.16 36	62.75 133	95.92 52	82.46 61	91.30 82	91.81 122

HPM-MVS_fast		85.35 59	84.95 63	86.57 58	93.69 41	70.58 76	92.15 31	91.62 101	73.89 121	82.67 85	94.09 39	62.60 134	95.54 62	80.93 69	92.93 65	93.57 66

PAPM		77.68 196	76.40 201	81.51 189	87.29 192	61.85 233	83.78 237	89.59 159	64.74 251	71.23 247	88.70 150	62.59 135	93.66 141	52.66 288	87.03 132	89.01 214

1112_ss		77.40 201	76.43 200	80.32 217	89.11 136	60.41 251	83.65 239	87.72 211	62.13 278	73.05 229	86.72 202	62.58 136	89.97 244	62.11 228	80.80 202	90.59 157

LCM-MVSNet-Re		77.05 204	76.94 188	77.36 264	87.20 193	51.60 321	80.06 275	80.46 295	75.20 95	67.69 279	86.72 202	62.48 137	88.98 261	63.44 214	89.25 105	91.51 127

v148		78.72 168	77.80 168	81.47 190	82.73 269	61.96 232	86.30 180	88.08 202	73.26 132	76.18 181	85.47 238	62.46 138	92.36 188	71.92 146	73.82 286	90.09 177

baseline1		76.98 206	76.75 195	77.66 259	88.13 163	55.66 305	85.12 206	81.89 280	73.04 135	76.79 165	88.90 146	62.43 139	87.78 277	63.30 216	71.18 302	89.55 201

MAR-MVS		81.84 100	80.70 107	85.27 76	91.32 81	71.53 56	89.82 74	90.92 122	69.77 185	78.50 130	86.21 222	62.36 140	94.52 102	65.36 202	92.05 73	89.77 195
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
MVS_111021_LR		82.61 90	82.11 89	84.11 113	88.82 142	71.58 55	85.15 205	86.16 233	74.69 103	80.47 110	91.04 99	62.29 141	90.55 237	80.33 76	90.08 97	90.20 170

TAMVS		78.89 166	77.51 177	83.03 152	87.80 174	67.79 132	84.72 214	85.05 243	67.63 217	76.75 167	87.70 175	62.25 142	90.82 232	58.53 259	87.13 130	90.49 160

CP-MVSNet		78.22 179	78.34 155	77.84 256	87.83 173	54.54 309	87.94 135	91.17 117	77.65 35	73.48 224	88.49 158	62.24 143	88.43 269	62.19 225	74.07 281	90.55 158

OMC-MVS		82.69 88	81.97 94	84.85 90	88.75 147	67.42 136	87.98 132	90.87 124	74.92 99	79.72 114	91.65 81	62.19 144	93.96 121	75.26 119	86.42 141	93.16 83

cl-mvsnet_		77.72 194	76.76 193	80.58 211	82.49 275	60.48 249	83.09 248	87.87 207	69.22 196	74.38 219	85.22 243	62.10 145	91.53 213	71.09 151	75.41 266	89.73 197

cl-mvsnet1		77.72 194	76.76 193	80.58 211	82.48 276	60.48 249	83.09 248	87.86 208	69.22 196	74.38 219	85.24 242	62.10 145	91.53 213	71.09 151	75.40 267	89.74 196

testdata				79.97 222	90.90 87	64.21 192		84.71 244	59.27 299	85.40 40	92.91 63	62.02 147	89.08 259	68.95 173	91.37 80	86.63 271

eth_miper_zixun_eth		77.92 190	76.69 196	81.61 188	83.00 262	61.98 231	83.15 247	89.20 172	69.52 190	74.86 214	84.35 254	61.76 148	92.56 181	71.50 149	72.89 291	90.28 168

MVSFormer		82.85 87	82.05 91	85.24 77	87.35 186	70.21 79	90.50 56	90.38 135	68.55 212	81.32 99	89.47 132	61.68 149	93.46 149	78.98 83	90.26 93	92.05 116

lupinMVS		81.39 109	80.27 117	84.76 94	87.35 186	70.21 79	85.55 198	86.41 228	62.85 270	81.32 99	88.61 154	61.68 149	92.24 192	78.41 90	90.26 93	91.83 120

cdsmvs_eth3d_5k		19.96 319	26.61 320	0.00 337	0.00 356	0.00 357	0.00 348	89.26 169	0.00 352	0.00 353	88.61 154	61.62 151	0.00 354	0.00 351	0.00 351	0.00 350

CDS-MVSNet		79.07 161	77.70 173	83.17 145	87.60 181	68.23 124	84.40 227	86.20 232	67.49 220	76.36 176	86.54 215	61.54 152	90.79 233	61.86 230	87.33 127	90.49 160
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v10		79.74 145	78.67 145	82.97 156	84.06 239	64.95 179	87.88 138	90.62 128	73.11 133	75.11 208	86.56 214	61.46 153	94.05 120	73.68 128	75.55 262	89.90 189

v1144		80.03 140	79.03 140	83.01 153	83.78 244	64.51 185	87.11 155	90.57 130	71.96 149	78.08 142	86.20 223	61.41 154	93.94 124	74.93 120	77.23 237	90.60 155

cl-mvsnet2		78.07 185	77.01 185	81.23 198	82.37 278	61.83 234	83.55 243	87.98 204	68.96 205	75.06 210	83.87 259	61.40 155	91.88 205	73.53 130	76.39 251	89.98 186

BH-w/o		78.21 180	77.33 181	80.84 207	88.81 143	65.13 177	84.87 211	87.85 209	69.75 186	74.52 217	84.74 251	61.34 156	93.11 164	58.24 262	85.84 149	84.27 298

Test_1112_low_res		76.40 216	75.44 209	79.27 236	89.28 126	58.09 268	81.69 262	87.07 221	59.53 297	72.48 235	86.67 208	61.30 157	89.33 254	60.81 240	80.15 212	90.41 163

Vis-MVSNet (Re-imp)		78.36 177	78.45 150	78.07 254	88.64 149	51.78 320	86.70 169	79.63 303	74.14 116	75.11 208	90.83 105	61.29 158	89.75 247	58.10 263	91.60 76	92.69 97

PEN-MVS		77.73 193	77.69 174	77.84 256	87.07 196	53.91 313	87.91 137	91.18 116	77.56 40	73.14 228	88.82 149	61.23 159	89.17 257	59.95 244	72.37 293	90.43 162

pm-mvs1		77.25 203	76.68 197	78.93 241	84.22 236	58.62 264	86.41 176	88.36 197	71.37 159	73.31 225	88.01 172	61.22 160	89.15 258	64.24 210	73.01 290	89.03 213

BH-untuned		79.47 150	78.60 147	82.05 178	89.19 130	65.91 160	86.07 186	88.52 195	72.18 145	75.42 197	87.69 176	61.15 161	93.54 146	60.38 241	86.83 135	86.70 269

v2v482		80.23 136	79.29 136	83.05 151	83.62 246	64.14 193	87.04 156	89.97 148	73.61 125	78.18 139	87.22 190	61.10 162	93.82 131	76.11 111	76.78 246	91.18 137

jason		81.39 109	80.29 116	84.70 95	86.63 203	69.90 86	85.95 188	86.77 224	63.24 264	81.07 105	89.47 132	61.08 163	92.15 195	78.33 91	90.07 98	92.05 116
jason: jason.
Vis-MVSNet		83.46 77	82.80 82	85.43 73	90.25 97	68.74 110	90.30 64	90.13 145	76.33 76	80.87 107	92.89 64	61.00 164	94.20 113	72.45 144	90.97 84	93.35 74
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAPA-MVS	73.13 9	79.15 158	77.94 163	82.79 166	89.59 110	62.99 221	88.16 130	91.51 105	65.77 239	77.14 161	91.09 97	60.91 165	93.21 156	50.26 298	87.05 131	92.17 113
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PS-CasMVS		78.01 188	78.09 160	77.77 258	87.71 178	54.39 311	88.02 131	91.22 114	77.50 43	73.26 226	88.64 153	60.73 166	88.41 270	61.88 229	73.88 285	90.53 159

OPM-MVS		83.50 76	82.95 79	85.14 80	88.79 145	70.95 67	89.13 93	91.52 104	77.55 41	80.96 106	91.75 79	60.71 167	94.50 103	79.67 81	86.51 140	89.97 187

XVG-OURS-SEG-HR		80.81 120	79.76 124	83.96 124	85.60 215	68.78 107	83.54 244	90.50 132	70.66 170	76.71 168	91.66 80	60.69 168	91.26 220	76.94 105	81.58 194	91.83 120

v144192		79.47 150	78.37 154	82.78 167	83.35 250	63.96 196	86.96 158	90.36 138	69.99 180	77.50 150	85.67 233	60.66 169	93.77 135	74.27 124	76.58 247	90.62 153

V42		79.38 155	78.24 158	82.83 161	81.10 296	65.50 168	85.55 198	89.82 152	71.57 156	78.21 137	86.12 224	60.66 169	93.18 160	75.64 115	75.46 265	89.81 194

CPTT-MVS		83.73 72	83.33 74	84.92 89	93.28 48	70.86 71	92.09 32	90.38 135	68.75 209	79.57 115	92.83 66	60.60 171	93.04 169	80.92 70	91.56 78	90.86 146

DTE-MVSNet		76.99 205	76.80 191	77.54 263	86.24 206	53.06 317	87.52 144	90.66 127	77.08 54	72.50 234	88.67 152	60.48 172	89.52 251	57.33 270	70.74 304	90.05 182

HQP_MVS		83.64 74	83.14 75	85.14 80	90.08 101	68.71 112	91.25 43	92.44 67	79.12 23	78.92 123	91.00 102	60.42 173	95.38 69	78.71 85	86.32 142	91.33 133

plane_prior6					89.84 106	68.70 114						60.42 173

3Dnovator+	77.84 4	85.48 55	84.47 68	88.51 4	91.08 83	73.49 15	93.18 9	93.78 19	80.79 10	76.66 169	93.37 53	60.40 175	96.75 22	77.20 101	93.73 62	95.29 2

HQP2-MVS												60.17 176

HQP-MVS		82.61 90	82.02 92	84.37 104	89.33 120	66.98 144	89.17 88	92.19 77	76.41 70	77.23 158	90.23 114	60.17 176	95.11 79	77.47 98	85.99 147	91.03 140

VPNet		78.69 169	78.66 146	78.76 243	88.31 160	55.72 304	84.45 224	86.63 226	76.79 61	78.26 136	90.55 109	59.30 178	89.70 249	66.63 192	77.05 240	90.88 145

v1192		79.59 147	78.43 152	83.07 150	83.55 248	64.52 184	86.93 160	90.58 129	70.83 164	77.78 146	85.90 227	59.15 179	93.94 124	73.96 127	77.19 239	90.76 148

test222					91.50 79	68.26 123	84.16 230	83.20 269	54.63 323	79.74 113	91.63 83	58.97 180			91.42 79	86.77 267

CHOSEN 1792x2688		77.63 197	75.69 205	83.44 132	89.98 103	68.58 118	78.70 290	87.50 215	56.38 317	75.80 189	86.84 198	58.67 181	91.40 217	61.58 233	85.75 150	90.34 166

3Dnovator	76.31 5	83.38 80	82.31 88	86.59 57	87.94 170	72.94 27	90.64 52	92.14 79	77.21 49	75.47 193	92.83 66	58.56 182	94.72 98	73.24 137	92.71 69	92.13 114

v1921920		79.22 157	78.03 161	82.80 164	83.30 252	63.94 197	86.80 164	90.33 139	69.91 182	77.48 151	85.53 236	58.44 183	93.75 137	73.60 129	76.85 244	90.71 151

114514_t		80.68 126	79.51 129	84.20 111	94.09 35	67.27 140	89.64 81	91.11 119	58.75 304	74.08 221	90.72 106	58.10 184	95.04 84	69.70 165	89.42 104	90.30 167

v7n		78.97 164	77.58 176	83.14 146	83.45 249	65.51 167	88.32 122	91.21 115	73.69 124	72.41 236	86.32 221	57.93 185	93.81 132	69.18 170	75.65 260	90.11 175

baseline2		75.70 225	73.83 231	81.30 196	83.26 253	61.79 235	82.57 254	80.65 291	66.81 223	66.88 287	83.42 268	57.86 186	92.19 193	63.47 213	79.57 216	89.91 188

QAPM		80.88 115	79.50 130	85.03 83	88.01 169	68.97 104	91.59 36	92.00 85	66.63 230	75.15 207	92.16 72	57.70 187	95.45 65	63.52 212	88.76 110	90.66 152

HyFIR lowres test		77.53 198	75.40 211	83.94 125	89.59 110	66.62 148	80.36 272	88.64 193	56.29 318	76.45 172	85.17 244	57.64 188	93.28 154	61.34 236	83.10 178	91.91 118

CNLPA		78.08 184	76.79 192	81.97 181	90.40 95	71.07 63	87.59 143	84.55 247	66.03 237	72.38 237	89.64 126	57.56 189	86.04 289	59.61 247	83.35 173	88.79 225

test_yl		81.17 111	80.47 112	83.24 141	89.13 132	63.62 201	86.21 182	89.95 149	72.43 142	81.78 95	89.61 127	57.50 190	93.58 142	70.75 153	86.90 133	92.52 100

DCV-MVSNet		81.17 111	80.47 112	83.24 141	89.13 132	63.62 201	86.21 182	89.95 149	72.43 142	81.78 95	89.61 127	57.50 190	93.58 142	70.75 153	86.90 133	92.52 100

sss		73.60 244	73.64 232	73.51 295	82.80 267	55.01 307	76.12 303	81.69 283	62.47 275	74.68 216	85.85 230	57.32 192	78.11 322	60.86 239	80.93 199	87.39 251

Effi-MVS+-dtu		80.03 140	78.57 148	84.42 102	85.13 224	68.74 110	88.77 103	88.10 200	74.99 97	74.97 212	83.49 267	57.27 193	93.36 152	73.53 130	80.88 200	91.18 137

mvs-test1		80.88 115	79.40 132	85.29 75	85.13 224	69.75 89	89.28 85	88.10 200	74.99 97	76.44 175	86.72 202	57.27 193	94.26 112	73.53 130	83.18 176	91.87 119

AdaColmap		80.58 130	79.42 131	84.06 116	93.09 54	68.91 105	89.36 84	88.97 182	69.27 194	75.70 190	89.69 124	57.20 195	95.77 56	63.06 218	88.41 116	87.50 250

v1240		78.99 163	77.78 169	82.64 170	83.21 254	63.54 205	86.62 171	90.30 141	69.74 188	77.33 154	85.68 232	57.04 196	93.76 136	73.13 138	76.92 241	90.62 153

miper_lstm_enhance		74.11 239	73.11 238	77.13 269	80.11 305	59.62 256	72.23 319	86.92 223	66.76 225	70.40 253	82.92 271	56.93 197	82.92 306	69.06 172	72.63 292	88.87 221

BH-RMVSNet		79.61 146	78.44 151	83.14 146	89.38 119	65.93 159	84.95 210	87.15 220	73.56 127	78.19 138	89.79 123	56.67 198	93.36 152	59.53 248	86.74 136	90.13 173

test_djsdf		80.30 135	79.32 135	83.27 139	83.98 241	65.37 172	90.50 56	90.38 135	68.55 212	76.19 180	88.70 150	56.44 199	93.46 149	78.98 83	80.14 213	90.97 143

EPNet_dtu		75.46 228	74.86 217	77.23 268	82.57 273	54.60 308	86.89 161	83.09 270	71.64 152	66.25 295	85.86 229	55.99 200	88.04 274	54.92 279	86.55 139	89.05 212
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CostFormer		75.24 232	73.90 229	79.27 236	82.65 272	58.27 267	80.80 267	82.73 274	61.57 281	75.33 203	83.13 270	55.52 201	91.07 229	64.98 206	78.34 230	88.45 233

tpmrst		72.39 256	72.13 245	73.18 297	80.54 301	49.91 329	79.91 278	79.08 306	63.11 265	71.69 244	79.95 301	55.32 202	82.77 307	65.66 201	73.89 284	86.87 264

1314		76.53 211	75.30 215	80.21 219	83.93 242	62.32 227	84.66 215	88.81 185	60.23 290	70.16 258	84.07 258	55.30 203	90.73 235	67.37 184	83.21 175	87.59 248

tfpnnormal		74.39 235	73.16 237	78.08 253	86.10 208	58.05 269	84.65 218	87.53 214	70.32 175	71.22 248	85.63 234	54.97 204	89.86 245	43.03 327	75.02 274	86.32 273

GBi-Net		78.40 174	77.40 178	81.40 192	87.60 181	63.01 218	88.39 118	89.28 166	71.63 153	75.34 200	87.28 186	54.80 205	91.11 223	62.72 219	79.57 216	90.09 177

test1		78.40 174	77.40 178	81.40 192	87.60 181	63.01 218	88.39 118	89.28 166	71.63 153	75.34 200	87.28 186	54.80 205	91.11 223	62.72 219	79.57 216	90.09 177

FMVSNet2		78.20 181	77.21 182	81.20 199	87.60 181	62.89 222	87.47 146	89.02 178	71.63 153	75.29 204	87.28 186	54.80 205	91.10 226	62.38 223	79.38 220	89.61 199

Fast-Effi-MVS+-dtu		78.02 187	76.49 199	82.62 171	83.16 258	66.96 146	86.94 159	87.45 217	72.45 139	71.49 246	84.17 256	54.79 208	91.58 211	67.61 181	80.31 210	89.30 205

MVSTER		79.01 162	77.88 166	82.38 174	83.07 259	64.80 181	84.08 235	88.95 183	69.01 204	78.69 126	87.17 193	54.70 209	92.43 184	74.69 121	80.57 206	89.89 190

OpenMVS	72.83 10	79.77 144	78.33 156	84.09 115	85.17 221	69.91 85	90.57 54	90.97 121	66.70 226	72.17 239	91.91 76	54.70 209	93.96 121	61.81 231	90.95 85	88.41 235

XVG-OURS		80.41 132	79.23 137	83.97 123	85.64 214	69.02 101	83.03 251	90.39 134	71.09 162	77.63 149	91.49 88	54.62 211	91.35 218	75.71 114	83.47 172	91.54 126

LPG-MVS_test		82.08 95	81.27 100	84.50 99	89.23 128	68.76 108	90.22 67	91.94 89	75.37 91	76.64 170	91.51 86	54.29 212	94.91 88	78.44 88	83.78 165	89.83 192

LGP-MVS_train				84.50 99	89.23 128	68.76 108		91.94 89	75.37 91	76.64 170	91.51 86	54.29 212	94.91 88	78.44 88	83.78 165	89.83 192

TR-MVS		77.44 199	76.18 203	81.20 199	88.24 161	63.24 213	84.61 219	86.40 229	67.55 219	77.81 145	86.48 217	54.10 214	93.15 161	57.75 266	82.72 183	87.20 257

FMVSNet3		77.88 191	76.85 190	80.97 205	86.84 199	62.36 225	86.52 175	88.77 187	71.13 160	75.34 200	86.66 209	54.07 215	91.10 226	62.72 219	79.57 216	89.45 202

DP-MVS		76.78 209	74.57 220	83.42 133	93.29 47	69.46 97	88.55 113	83.70 257	63.98 261	70.20 255	88.89 147	54.01 216	94.80 95	46.66 315	81.88 192	86.01 281

ACMP	74.13 6	81.51 108	80.57 109	84.36 105	89.42 116	68.69 115	89.97 72	91.50 108	74.46 108	75.04 211	90.41 111	53.82 217	94.54 100	77.56 97	82.91 179	89.86 191
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PLC	70.83 11	78.05 186	76.37 202	83.08 149	91.88 76	67.80 131	88.19 128	89.46 162	64.33 257	69.87 264	88.38 161	53.66 218	93.58 142	58.86 255	82.73 182	87.86 242
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CANet_DTU		80.61 127	79.87 121	82.83 161	85.60 215	63.17 217	87.36 148	88.65 192	76.37 74	75.88 187	88.44 160	53.51 219	93.07 166	73.30 135	89.74 101	92.25 109

ACMM	73.20 8	80.78 125	79.84 122	83.58 129	89.31 125	68.37 120	89.99 71	91.60 102	70.28 176	77.25 156	89.66 125	53.37 220	93.53 147	74.24 125	82.85 180	88.85 222
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVP-Stereo		76.12 219	74.46 224	81.13 202	85.37 219	69.79 87	84.42 226	87.95 205	65.03 248	67.46 281	85.33 240	53.28 221	91.73 209	58.01 264	83.27 174	81.85 318
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
anonymousdsp		78.60 171	77.15 183	82.98 155	80.51 302	67.08 142	87.24 152	89.53 160	65.66 241	75.16 206	87.19 192	52.52 222	92.25 191	77.17 102	79.34 221	89.61 199

CR-MVSNet		73.37 245	71.27 253	79.67 229	81.32 294	65.19 175	75.92 305	80.30 297	59.92 293	72.73 232	81.19 287	52.50 223	86.69 283	59.84 245	77.71 232	87.11 261

Patchmtry		70.74 266	69.16 266	75.49 282	80.72 298	54.07 312	74.94 314	80.30 297	58.34 305	70.01 259	81.19 287	52.50 223	86.54 285	53.37 285	71.09 303	85.87 284

pmmvs4		74.03 241	71.91 246	80.39 214	81.96 282	68.32 121	81.45 265	82.14 278	59.32 298	69.87 264	85.13 245	52.40 225	88.13 273	60.21 243	74.74 277	84.73 295

RPMNet		71.62 260	68.94 268	79.67 229	81.32 294	65.19 175	75.92 305	78.30 309	57.60 310	72.73 232	76.45 321	52.30 226	86.69 283	48.14 310	77.71 232	87.11 261

LFMVS		81.82 101	81.23 101	83.57 130	91.89 75	63.43 210	89.84 73	81.85 282	77.04 55	83.21 75	93.10 58	52.26 227	93.43 151	71.98 145	89.95 99	93.85 49

VDD-MVS		83.01 86	82.36 87	84.96 86	91.02 85	66.40 152	88.91 97	88.11 199	77.57 38	84.39 61	93.29 55	52.19 228	93.91 128	77.05 103	88.70 111	94.57 21

tfpn200view9		76.42 215	75.37 213	79.55 234	89.13 132	57.65 278	85.17 203	83.60 258	73.41 130	76.45 172	86.39 219	52.12 229	91.95 201	48.33 306	83.75 167	89.07 207

thres400		76.50 212	75.37 213	79.86 224	89.13 132	57.65 278	85.17 203	83.60 258	73.41 130	76.45 172	86.39 219	52.12 229	91.95 201	48.33 306	83.75 167	90.00 183

thres200		75.55 227	74.47 223	78.82 242	87.78 177	57.85 275	83.07 250	83.51 261	72.44 141	75.84 188	84.42 253	52.08 231	91.75 207	47.41 313	83.64 171	86.86 265

PMMVS		69.34 278	68.67 269	71.35 304	75.67 329	62.03 230	75.17 309	73.46 327	50.00 331	68.68 272	79.05 306	52.07 232	78.13 321	61.16 237	82.77 181	73.90 333

tpm cat1		70.57 268	68.31 272	77.35 265	82.41 277	57.95 273	78.08 295	80.22 299	52.04 328	68.54 275	77.66 316	52.00 233	87.84 276	51.77 289	72.07 297	86.25 274

IterMVS-SCA-FT		75.43 229	73.87 230	80.11 220	82.69 270	64.85 180	81.57 264	83.47 263	69.16 199	70.49 252	84.15 257	51.95 234	88.15 272	69.23 169	72.14 296	87.34 253

SCA		74.22 238	72.33 244	79.91 223	84.05 240	62.17 229	79.96 277	79.29 305	66.30 233	72.38 237	80.13 299	51.95 234	88.60 267	59.25 250	77.67 234	88.96 218

thres100view900		76.50 212	75.55 208	79.33 235	89.52 113	56.99 286	85.83 192	83.23 267	73.94 119	76.32 177	87.12 194	51.89 236	91.95 201	48.33 306	83.75 167	89.07 207

thres600view7		76.50 212	75.44 209	79.68 228	89.40 117	57.16 283	85.53 200	83.23 267	73.79 123	76.26 178	87.09 195	51.89 236	91.89 204	48.05 311	83.72 170	90.00 183

tpm2		73.26 248	71.46 250	78.63 244	83.34 251	56.71 291	80.65 270	80.40 296	56.63 316	73.55 223	82.02 284	51.80 238	91.24 221	56.35 275	78.42 229	87.95 239

LS3D		76.95 207	74.82 218	83.37 136	90.45 93	67.36 139	89.15 92	86.94 222	61.87 280	69.52 267	90.61 108	51.71 239	94.53 101	46.38 318	86.71 137	88.21 237

IterMVS		74.29 236	72.94 239	78.35 250	81.53 288	63.49 207	81.58 263	82.49 275	68.06 216	69.99 261	83.69 265	51.66 240	85.54 292	65.85 199	71.64 299	86.01 281
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 258	71.71 249	74.35 291	82.19 280	52.00 318	79.22 284	77.29 315	64.56 253	72.95 230	83.68 266	51.35 241	83.26 305	58.33 261	75.80 258	87.81 243

sam_mvs1												51.32 242				88.96 218

PatchmatchNet		73.12 250	71.33 252	78.49 249	83.18 256	60.85 244	79.63 279	78.57 307	64.13 258	71.73 243	79.81 304	51.20 243	85.97 290	57.40 269	76.36 254	88.66 228
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
patchmatchnet-post											74.00 326	51.12 244	88.60 267

xiu_mvs_v1_base_debu		80.80 122	79.72 125	84.03 119	87.35 186	70.19 81	85.56 195	88.77 187	69.06 201	81.83 91	88.16 167	50.91 245	92.85 173	78.29 92	87.56 123	89.06 209

xiu_mvs_v1_base		80.80 122	79.72 125	84.03 119	87.35 186	70.19 81	85.56 195	88.77 187	69.06 201	81.83 91	88.16 167	50.91 245	92.85 173	78.29 92	87.56 123	89.06 209

xiu_mvs_v1_base_debi		80.80 122	79.72 125	84.03 119	87.35 186	70.19 81	85.56 195	88.77 187	69.06 201	81.83 91	88.16 167	50.91 245	92.85 173	78.29 92	87.56 123	89.06 209

Patchmatch-test		64.82 299	63.24 298	69.57 310	79.42 315	49.82 330	63.49 338	69.05 337	51.98 329	59.95 322	80.13 299	50.91 245	70.98 340	40.66 332	73.57 287	87.90 241

Patchmatch-RL test		70.24 272	67.78 282	77.61 261	77.43 322	59.57 258	71.16 321	70.33 331	62.94 269	68.65 273	72.77 328	50.62 249	85.49 293	69.58 167	66.58 317	87.77 244

Anonymous20231211		78.97 164	77.69 174	82.81 163	90.54 92	64.29 191	90.11 69	91.51 105	65.01 249	76.16 184	88.13 171	50.56 250	93.03 170	69.68 166	77.56 235	91.11 139

VDDNet		81.52 106	80.67 108	84.05 117	90.44 94	64.13 194	89.73 79	85.91 236	71.11 161	83.18 76	93.48 50	50.54 251	93.49 148	73.40 134	88.25 117	94.54 22

pmmvs6		74.69 234	73.39 233	78.61 245	81.38 291	57.48 281	86.64 170	87.95 205	64.99 250	70.18 256	86.61 210	50.43 252	89.52 251	62.12 227	70.18 306	88.83 223

test_post											5.46 348	50.36 253	84.24 298

ET-MVSNet_ETH3D		78.63 170	76.63 198	84.64 96	86.73 202	69.47 95	85.01 208	84.61 246	69.54 189	66.51 293	86.59 211	50.16 254	91.75 207	76.26 110	84.24 162	92.69 97

sam_mvs												50.01 255

Anonymous20240529		80.19 138	78.89 143	84.10 114	90.60 91	64.75 182	88.95 96	90.90 123	65.97 238	80.59 109	91.17 95	49.97 256	93.73 139	69.16 171	82.70 184	93.81 53

thisisatest0530		79.40 153	77.76 171	84.31 108	87.69 180	65.10 178	87.36 148	84.26 251	70.04 179	77.42 152	88.26 166	49.94 257	94.79 96	70.20 159	84.70 157	93.03 87

PatchT		68.46 284	67.85 279	70.29 308	80.70 299	43.93 338	72.47 318	74.88 322	60.15 291	70.55 251	76.57 320	49.94 257	81.59 310	50.58 294	74.83 276	85.34 287

tttt0517		79.40 153	77.91 164	83.90 126	88.10 165	63.84 198	88.37 121	84.05 253	71.45 158	76.78 166	89.12 142	49.93 259	94.89 91	70.18 160	83.18 176	92.96 91

tpmvs		71.09 264	69.29 265	76.49 273	82.04 281	56.04 301	78.92 288	81.37 286	64.05 259	67.18 285	78.28 311	49.74 260	89.77 246	49.67 301	72.37 293	83.67 304

thisisatest0515		77.33 202	75.38 212	83.18 144	85.27 220	63.80 199	82.11 258	83.27 266	65.06 247	75.91 185	83.84 261	49.54 261	94.27 108	67.24 187	86.19 144	91.48 130

UniMVSNet_ETH3D		79.10 160	78.24 158	81.70 185	86.85 198	60.24 252	87.28 151	88.79 186	74.25 113	76.84 163	90.53 110	49.48 262	91.56 212	67.98 178	82.15 188	93.29 76

CVMVSNet		72.99 252	72.58 241	74.25 292	84.28 234	50.85 326	86.41 176	83.45 264	44.56 333	73.23 227	87.54 181	49.38 263	85.70 291	65.90 198	78.44 228	86.19 276

MDTV_nov1_ep13_2view						37.79 343	75.16 310		55.10 321	66.53 292		49.34 264		53.98 282		87.94 240

UGNet		80.83 119	79.59 128	84.54 98	88.04 167	68.09 126	89.42 83	88.16 198	76.95 56	76.22 179	89.46 134	49.30 265	93.94 124	68.48 175	90.31 91	91.60 124
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
pmmvs5		71.55 261	70.20 262	75.61 279	77.83 320	56.39 296	81.74 261	80.89 287	57.76 308	67.46 281	84.49 252	49.26 266	85.32 295	57.08 272	75.29 271	85.11 291

LTVRE_ROB	69.57 13	76.25 218	74.54 222	81.41 191	88.60 150	64.38 190	79.24 283	89.12 176	70.76 168	69.79 266	87.86 173	49.09 267	93.20 158	56.21 276	80.16 211	86.65 270
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
FMVSNet1		77.44 199	76.12 204	81.40 192	86.81 200	63.01 218	88.39 118	89.28 166	70.49 173	74.39 218	87.28 186	49.06 268	91.11 223	60.91 238	78.52 226	90.09 177

MDTV_nov1_ep13			69.97 263		83.18 256	53.48 315	77.10 301	80.18 300	60.45 287	69.33 270	80.44 296	48.89 269	86.90 282	51.60 291	78.51 227

test_post1							78.90 289				5.43 349	48.81 270	85.44 294	59.25 250

test-LLR		72.94 253	72.43 242	74.48 289	81.35 292	58.04 270	78.38 291	77.46 313	66.66 227	69.95 262	79.00 308	48.06 271	79.24 316	66.13 194	84.83 154	86.15 277

test0.0.03 1		68.00 285	67.69 283	68.90 313	77.55 321	47.43 333	75.70 308	72.95 329	66.66 227	66.56 291	82.29 281	48.06 271	75.87 331	44.97 324	74.51 279	83.41 306

our_test_3		69.14 279	67.00 286	75.57 280	79.80 310	58.80 262	77.96 296	77.81 311	59.55 296	62.90 314	78.25 312	47.43 273	83.97 299	51.71 290	67.58 314	83.93 303

MS-PatchMatch		73.83 242	72.67 240	77.30 266	83.87 243	66.02 157	81.82 259	84.66 245	61.37 284	68.61 274	82.82 274	47.29 274	88.21 271	59.27 249	84.32 161	77.68 330

cascas		76.72 210	74.64 219	82.99 154	85.78 212	65.88 161	82.33 256	89.21 171	60.85 286	72.74 231	81.02 291	47.28 275	93.75 137	67.48 183	85.02 152	89.34 204

test20.03		67.45 287	66.95 287	68.94 312	75.48 331	44.84 337	77.50 298	77.67 312	66.66 227	63.01 312	83.80 262	47.02 276	78.40 320	42.53 329	68.86 312	83.58 305

test_0402		72.79 254	70.44 259	79.84 225	88.13 163	65.99 158	85.93 189	84.29 249	65.57 242	67.40 283	85.49 237	46.92 277	92.61 179	35.88 336	74.38 280	80.94 321

F-COLMAP		76.38 217	74.33 225	82.50 172	89.28 126	66.95 147	88.41 117	89.03 177	64.05 259	66.83 289	88.61 154	46.78 278	92.89 172	57.48 267	78.55 225	87.67 245

ppachtmachnet_test		70.04 274	67.34 285	78.14 252	79.80 310	61.13 240	79.19 285	80.59 292	59.16 300	65.27 300	79.29 305	46.75 279	87.29 280	49.33 302	66.72 315	86.00 283

D2MVS		74.82 233	73.21 236	79.64 231	79.81 309	62.56 224	80.34 273	87.35 218	64.37 256	68.86 271	82.66 276	46.37 280	90.10 243	67.91 179	81.24 197	86.25 274

Anonymous20231206		68.60 281	67.80 281	71.02 306	80.23 304	50.75 327	78.30 294	80.47 294	56.79 315	66.11 296	82.63 277	46.35 281	78.95 318	43.62 326	75.70 259	83.36 307

CHOSEN 280x420		66.51 293	64.71 293	71.90 299	81.45 289	63.52 206	57.98 340	68.95 338	53.57 324	62.59 315	76.70 319	46.22 282	75.29 334	55.25 278	79.68 214	76.88 332

GA-MVS		76.87 208	75.17 216	81.97 181	82.75 268	62.58 223	81.44 266	86.35 231	72.16 147	74.74 215	82.89 272	46.20 283	92.02 199	68.85 174	81.09 198	91.30 135

MDA-MVSNet_test_wron		65.03 297	62.92 299	71.37 302	75.93 327	56.73 289	69.09 330	74.73 324	57.28 313	54.03 334	77.89 313	45.88 284	74.39 337	49.89 300	61.55 325	82.99 313

YYNet1		65.03 297	62.91 300	71.38 301	75.85 328	56.60 293	69.12 329	74.66 326	57.28 313	54.12 333	77.87 314	45.85 285	74.48 336	49.95 299	61.52 326	83.05 311

EPMVS		69.02 280	68.16 274	71.59 300	79.61 313	49.80 331	77.40 299	66.93 339	62.82 271	70.01 259	79.05 306	45.79 286	77.86 324	56.58 274	75.26 272	87.13 260

IB-MVS	68.01 15	75.85 223	73.36 234	83.31 137	84.76 228	66.03 156	83.38 245	85.06 242	70.21 178	69.40 268	81.05 290	45.76 287	94.66 99	65.10 205	75.49 263	89.25 206
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
jajsoiax		79.29 156	77.96 162	83.27 139	84.68 230	66.57 150	89.25 87	90.16 144	69.20 198	75.46 195	89.49 131	45.75 288	93.13 163	76.84 106	80.80 202	90.11 175

PatchMatch-RL		72.38 257	70.90 256	76.80 272	88.60 150	67.38 138	79.53 280	76.17 319	62.75 272	69.36 269	82.00 285	45.51 289	84.89 296	53.62 284	80.58 205	78.12 329

RPSCF		73.23 249	71.46 250	78.54 247	82.50 274	59.85 254	82.18 257	82.84 273	58.96 301	71.15 249	89.41 138	45.48 290	84.77 297	58.82 256	71.83 298	91.02 142

RRT_test8_iter05		78.38 176	77.40 178	81.34 195	86.00 209	58.86 261	86.55 174	91.26 113	72.13 148	75.91 185	87.42 184	44.97 291	93.73 139	77.02 104	75.30 270	91.45 132

MSDG		73.36 247	70.99 255	80.49 213	84.51 232	65.80 162	80.71 269	86.13 234	65.70 240	65.46 298	83.74 264	44.60 292	90.91 231	51.13 293	76.89 242	84.74 294

PVSNet_0	57.27 20	61.67 304	59.27 306	68.85 314	79.61 313	57.44 282	68.01 331	73.44 328	55.93 319	58.54 325	70.41 331	44.58 293	77.55 325	47.01 314	35.91 340	71.55 335

RRT_MVS		79.88 143	78.38 153	84.38 103	85.42 218	70.60 75	88.71 108	88.75 191	72.30 144	78.83 125	89.14 140	44.44 294	92.18 194	78.50 87	79.33 222	90.35 165

DWT-MVSNet_test		73.70 243	71.86 247	79.21 238	82.91 265	58.94 260	82.34 255	82.17 277	65.21 244	71.05 250	78.31 310	44.21 295	90.17 242	63.29 217	77.28 236	88.53 232

mvs_tets		79.13 159	77.77 170	83.22 143	84.70 229	66.37 153	89.17 88	90.19 143	69.38 192	75.40 198	89.46 134	44.17 296	93.15 161	76.78 107	80.70 204	90.14 172

MDA-MVSNet-bldmvs		66.68 291	63.66 296	75.75 277	79.28 316	60.56 248	73.92 316	78.35 308	64.43 254	50.13 337	79.87 303	44.02 297	83.67 301	46.10 319	56.86 331	83.03 312

gg-mvs-nofinetune		69.95 275	67.96 277	75.94 276	83.07 259	54.51 310	77.23 300	70.29 332	63.11 265	70.32 254	62.33 334	43.62 298	88.69 266	53.88 283	87.76 120	84.62 297

GG-mvs-BLEND				75.38 283	81.59 287	55.80 303	79.32 282	69.63 334		67.19 284	73.67 327	43.24 299	88.90 265	50.41 295	84.50 158	81.45 320

CMPMVS	51.72 21	70.19 273	68.16 274	76.28 274	73.15 337	57.55 280	79.47 281	83.92 254	48.02 332	56.48 331	84.81 249	43.13 300	86.42 287	62.67 222	81.81 193	84.89 292
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dp		66.80 290	65.43 291	70.90 307	79.74 312	48.82 332	75.12 312	74.77 323	59.61 295	64.08 308	77.23 317	42.89 301	80.72 313	48.86 304	66.58 317	83.16 309

PVSNet	64.34 18	72.08 259	70.87 258	75.69 278	86.21 207	56.44 295	74.37 315	80.73 290	62.06 279	70.17 257	82.23 282	42.86 302	83.31 304	54.77 280	84.45 160	87.32 254

pmmvs-eth3d		70.50 270	67.83 280	78.52 248	77.37 323	66.18 155	81.82 259	81.51 284	58.90 302	63.90 309	80.42 297	42.69 303	86.28 288	58.56 258	65.30 320	83.11 310

UnsupCasMVSNet_eth		67.33 288	65.99 290	71.37 302	73.48 334	51.47 323	75.16 310	85.19 241	65.20 245	60.78 318	80.93 294	42.35 304	77.20 326	57.12 271	53.69 335	85.44 286

ADS-MVSNet2		66.20 296	63.33 297	74.82 287	79.92 307	58.75 263	67.55 332	75.19 321	53.37 325	65.25 301	75.86 322	42.32 305	80.53 314	41.57 330	68.91 310	85.18 288

ADS-MVSNet		64.36 300	62.88 301	68.78 315	79.92 307	47.17 334	67.55 332	71.18 330	53.37 325	65.25 301	75.86 322	42.32 305	73.99 338	41.57 330	68.91 310	85.18 288

SixPastTwentyTwo		73.37 245	71.26 254	79.70 227	85.08 226	57.89 274	85.57 194	83.56 260	71.03 163	65.66 297	85.88 228	42.10 307	92.57 180	59.11 252	63.34 323	88.65 229

JIA-IIPM		66.32 295	62.82 302	76.82 271	77.09 325	61.72 236	65.34 335	75.38 320	58.04 307	64.51 305	62.32 335	42.05 308	86.51 286	51.45 292	69.22 309	82.21 316

ACMH	67.68 16	75.89 222	73.93 228	81.77 184	88.71 148	66.61 149	88.62 110	89.01 179	69.81 183	66.78 290	86.70 207	41.95 309	91.51 215	55.64 277	78.14 231	87.17 258
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	68.96 14	76.01 221	74.01 227	82.03 179	88.60 150	65.31 173	88.86 99	87.55 213	70.25 177	67.75 278	87.47 183	41.27 310	93.19 159	58.37 260	75.94 257	87.60 247

MIMVSNet		70.69 267	69.30 264	74.88 286	84.52 231	56.35 298	75.87 307	79.42 304	64.59 252	67.76 277	82.41 278	41.10 311	81.54 311	46.64 317	81.34 195	86.75 268

Anonymous202405211		78.25 178	77.01 185	81.99 180	91.03 84	60.67 246	84.77 213	83.90 255	70.65 171	80.00 112	91.20 94	41.08 312	91.43 216	65.21 203	85.26 151	93.85 49

N_pmnet		52.79 310	53.26 310	51.40 327	78.99 318	7.68 354	69.52 325	3.89 354	51.63 330	57.01 329	74.98 325	40.83 313	65.96 343	37.78 335	64.67 321	80.56 324

testing_2		75.73 224	73.34 235	82.89 160	77.37 323	65.22 174	84.10 233	90.54 131	69.09 200	60.46 319	81.15 289	40.48 314	92.84 176	76.36 109	80.54 208	90.60 155

EU-MVSNet		68.53 283	67.61 284	71.31 305	78.51 319	47.01 335	84.47 221	84.27 250	42.27 334	66.44 294	84.79 250	40.44 315	83.76 300	58.76 257	68.54 313	83.17 308

DSMNet-mixed		57.77 307	56.90 308	60.38 322	67.70 341	35.61 344	69.18 327	53.97 346	32.30 343	57.49 328	79.88 302	40.39 316	68.57 342	38.78 334	72.37 293	76.97 331

OurMVSNet-221017-0		74.26 237	72.42 243	79.80 226	83.76 245	59.59 257	85.92 190	86.64 225	66.39 232	66.96 286	87.58 178	39.46 317	91.60 210	65.76 200	69.27 308	88.22 236

K. test v3		71.19 263	68.51 270	79.21 238	83.04 261	57.78 277	84.35 228	76.91 317	72.90 138	62.99 313	82.86 273	39.27 318	91.09 228	61.65 232	52.66 336	88.75 226

lessismore_v0				78.97 240	81.01 297	57.15 284		65.99 340		61.16 317	82.82 274	39.12 319	91.34 219	59.67 246	46.92 339	88.43 234

UnsupCasMVSNet_bld		63.70 302	61.53 305	70.21 309	73.69 333	51.39 324	72.82 317	81.89 280	55.63 320	57.81 327	71.80 330	38.67 320	78.61 319	49.26 303	52.21 337	80.63 322

new-patchmatchnet		61.73 303	61.73 304	61.70 321	72.74 338	24.50 351	69.16 328	78.03 310	61.40 282	56.72 330	75.53 324	38.42 321	76.48 329	45.95 320	57.67 330	84.13 301

MVS-HIRNet		59.14 305	57.67 307	63.57 320	81.65 285	43.50 339	71.73 320	65.06 342	39.59 338	51.43 336	57.73 338	38.34 322	82.58 308	39.53 333	73.95 283	64.62 338

COLMAP_ROB	66.92 17	73.01 251	70.41 260	80.81 208	87.13 195	65.63 165	88.30 123	84.19 252	62.96 268	63.80 310	87.69 176	38.04 323	92.56 181	46.66 315	74.91 275	84.24 299
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TESTMET0.1,1		69.89 276	69.00 267	72.55 298	79.27 317	56.85 287	78.38 291	74.71 325	57.64 309	68.09 276	77.19 318	37.75 324	76.70 327	63.92 211	84.09 163	84.10 302

OpenMVS_ROB	64.09 19	70.56 269	68.19 273	77.65 260	80.26 303	59.41 259	85.01 208	82.96 272	58.76 303	65.43 299	82.33 279	37.63 325	91.23 222	45.34 323	76.03 256	82.32 315

FMVSNet5		69.50 277	67.96 277	74.15 293	82.97 264	55.35 306	80.01 276	82.12 279	62.56 274	63.02 311	81.53 286	36.92 326	81.92 309	48.42 305	74.06 282	85.17 290

MIMVSNet1		68.58 282	66.78 288	73.98 294	80.07 306	51.82 319	80.77 268	84.37 248	64.40 255	59.75 323	82.16 283	36.47 327	83.63 302	42.73 328	70.33 305	86.48 272

ITE_SJBPF				78.22 251	81.77 284	60.57 247		83.30 265	69.25 195	67.54 280	87.20 191	36.33 328	87.28 281	54.34 281	74.62 278	86.80 266

test-mter		71.41 262	70.39 261	74.48 289	81.35 292	58.04 270	78.38 291	77.46 313	60.32 289	69.95 262	79.00 308	36.08 329	79.24 316	66.13 194	84.83 154	86.15 277

testgi		66.67 292	66.53 289	67.08 318	75.62 330	41.69 341	75.93 304	76.50 318	66.11 234	65.20 303	86.59 211	35.72 330	74.71 335	43.71 325	73.38 289	84.84 293

EG-PatchMatch MVS		74.04 240	71.82 248	80.71 210	84.92 227	67.42 136	85.86 191	88.08 202	66.04 236	64.22 307	83.85 260	35.10 331	92.56 181	57.44 268	80.83 201	82.16 317

MVS_0304		72.48 255	70.89 257	77.24 267	82.20 279	59.68 255	84.11 232	83.49 262	67.10 222	66.87 288	80.59 295	35.00 332	87.40 279	59.07 253	79.58 215	84.63 296

XVG-ACMP-BASELINE		76.11 220	74.27 226	81.62 186	83.20 255	64.67 183	83.60 242	89.75 155	69.75 186	71.85 242	87.09 195	32.78 333	92.11 196	69.99 163	80.43 209	88.09 238

AllTest		70.96 265	68.09 276	79.58 232	85.15 222	63.62 201	84.58 220	79.83 301	62.31 276	60.32 320	86.73 200	32.02 334	88.96 263	50.28 296	71.57 300	86.15 277

TestCases				79.58 232	85.15 222	63.62 201		79.83 301	62.31 276	60.32 320	86.73 200	32.02 334	88.96 263	50.28 296	71.57 300	86.15 277

USDC		70.33 271	68.37 271	76.21 275	80.60 300	56.23 299	79.19 285	86.49 227	60.89 285	61.29 316	85.47 238	31.78 336	89.47 253	53.37 285	76.21 255	82.94 314

tmp_tt		18.61 320	21.40 322	10.23 334	4.82 353	10.11 353	34.70 345	30.74 352	1.48 349	23.91 346	26.07 346	28.42 337	13.41 351	27.12 340	15.35 347	7.17 346

TDRefinement		67.49 286	64.34 294	76.92 270	73.47 335	61.07 241	84.86 212	82.98 271	59.77 294	58.30 326	85.13 245	26.06 338	87.89 275	47.92 312	60.59 328	81.81 319

TinyColmap		67.30 289	64.81 292	74.76 288	81.92 283	56.68 292	80.29 274	81.49 285	60.33 288	56.27 332	83.22 269	24.77 339	87.66 278	45.52 321	69.47 307	79.95 325

LF4IMVS		64.02 301	62.19 303	69.50 311	70.90 339	53.29 316	76.13 302	77.18 316	52.65 327	58.59 324	80.98 292	23.55 340	76.52 328	53.06 287	66.66 316	78.68 328

new_pmnet		50.91 311	50.29 312	52.78 326	68.58 340	34.94 346	63.71 337	56.63 345	39.73 337	44.95 338	65.47 333	21.93 341	58.48 344	34.98 337	56.62 332	64.92 337

pmmvs3		57.79 306	54.26 309	68.37 316	64.02 343	56.72 290	75.12 312	65.17 341	40.20 336	52.93 335	69.86 332	20.36 342	75.48 333	45.45 322	55.25 334	72.90 334

PM-MVS		66.41 294	64.14 295	73.20 296	73.92 332	56.45 294	78.97 287	64.96 343	63.88 263	64.72 304	80.24 298	19.84 343	83.44 303	66.24 193	64.52 322	79.71 326

ambc				75.24 284	73.16 336	50.51 328	63.05 339	87.47 216		64.28 306	77.81 315	17.80 344	89.73 248	57.88 265	60.64 327	85.49 285

ANet_high		50.57 312	46.10 314	63.99 319	48.67 349	39.13 342	70.99 323	80.85 288	61.39 283	31.18 342	57.70 339	17.02 345	73.65 339	31.22 338	15.89 346	79.18 327

FPMVS		53.68 309	51.64 311	59.81 323	65.08 342	51.03 325	69.48 326	69.58 335	41.46 335	40.67 339	72.32 329	16.46 346	70.00 341	24.24 341	65.42 319	58.40 339

EMVS		30.81 317	29.65 319	34.27 331	50.96 348	25.95 350	56.58 342	46.80 349	24.01 345	15.53 349	30.68 345	12.47 347	54.43 347	12.81 347	17.05 345	22.43 345

E-PMN		31.77 316	30.64 318	35.15 330	52.87 347	27.67 348	57.09 341	47.86 348	24.64 344	16.40 348	33.05 344	11.23 348	54.90 346	14.46 346	18.15 344	22.87 344

DeepMVS_CX				27.40 332	40.17 352	26.90 349		24.59 353	17.44 347	23.95 345	48.61 341	9.77 349	26.48 349	18.06 343	24.47 342	28.83 343

Gipuma		45.18 313	41.86 315	55.16 325	77.03 326	51.52 322	32.50 346	80.52 293	32.46 342	27.12 343	35.02 343	9.52 350	75.50 332	22.31 342	60.21 329	38.45 342
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		54.25 308	49.68 313	67.97 317	53.73 346	45.28 336	66.85 334	80.78 289	35.96 340	39.45 340	62.23 336	8.70 351	78.06 323	48.24 309	51.20 338	80.57 323

PMMVS2		40.82 315	38.86 317	46.69 328	53.84 345	16.45 352	48.61 343	49.92 347	37.49 339	31.67 341	60.97 337	8.14 352	56.42 345	28.42 339	30.72 341	67.19 336

PMVS	37.38 22	44.16 314	40.28 316	55.82 324	40.82 351	42.54 340	65.12 336	63.99 344	34.43 341	24.48 344	57.12 340	3.92 353	76.17 330	17.10 344	55.52 333	48.75 340
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 318	25.89 321	43.81 329	44.55 350	35.46 345	28.87 347	39.07 350	18.20 346	18.58 347	40.18 342	2.68 354	47.37 348	17.07 345	23.78 343	48.60 341
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		16.82 321	15.94 323	19.46 333	58.74 344	31.45 347	39.22 344	3.74 355	6.84 348	6.04 350	2.70 350	1.27 355	24.29 350	10.54 348	14.40 348	2.63 347

test123		6.12 323	8.11 325	0.14 335	0.06 355	0.09 355	71.05 322	0.03 357	0.04 351	0.25 352	1.30 352	0.05 356	0.03 353	0.21 350	0.01 350	0.29 348

testmvs		6.04 324	8.02 326	0.10 336	0.08 354	0.03 356	69.74 324	0.04 356	0.05 350	0.31 351	1.68 351	0.02 357	0.04 352	0.24 349	0.02 349	0.25 349

uanet_test		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

test_part1				0.00 337		0.00 357	0.00 348	94.09 9				0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

sosnet-low-res		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

sosnet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

uncertanet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

Regformer		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

ab-mvs-re		7.23 322	9.64 324	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	86.72 202	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

uanet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

IU-MVS					95.30 2	71.25 58		92.95 50	66.81 223	92.39 5				88.94 8	96.63 2	94.85 10

save fliter					93.80 37	72.35 42	90.47 58	91.17 117	74.31 110

test_0728_SECOND				87.71 31	95.34 1	71.43 57	93.49 7	94.23 5					97.49 1	89.08 4	96.41 8	94.21 32

GSMVS																88.96 218

test_part2					95.06 7	72.65 31				91.80 10

MTGPA								92.02 82

MTMP							92.18 30	32.83 351

gm-plane-assit					81.40 290	53.83 314			62.72 273		80.94 293		92.39 186	63.40 215

test9_res														84.90 30	95.70 27	92.87 92

agg_prior2														82.91 56	95.45 29	92.70 95

agg_prior					92.85 57	71.94 50		91.78 97		84.41 59			94.93 86

test_prior4						72.60 33	89.01 95

test_prior				86.33 60	92.61 65	69.59 91		92.97 48					95.48 63			93.91 45

旧先验2							86.56 173		58.10 306	87.04 30			88.98 261	74.07 126

新几何2							86.29 181

无先验							87.48 145	88.98 180	60.00 292				94.12 117	67.28 185		88.97 217

原ACMM2							86.86 162

testdata2													91.01 230	62.37 224

testdata1							84.14 231		75.71 83

plane_prior7					90.08 101	68.51 119

plane_prior5								92.44 67					95.38 69	78.71 85	86.32 142	91.33 133

plane_prior4											91.00 102

plane_prior3						68.60 117			78.44 30	78.92 123

plane_prior2							91.25 43		79.12 23

plane_prior1					89.90 105

plane_prior						68.71 112	90.38 62		77.62 36						86.16 145

n2								0.00 358

nn								0.00 358

door-mid								69.98 333

test11								92.23 74

door								69.44 336

HQP5-MVS						66.98 144

HQP-NCC					89.33 120		89.17 88		76.41 70	77.23 158

ACMP_Plane					89.33 120		89.17 88		76.41 70	77.23 158

BP-MVS														77.47 98

HQP4-MVS										77.24 157			95.11 79			91.03 140

HQP3-MVS								92.19 77							85.99 147

NP-MVS					89.62 109	68.32 121					90.24 113

ACMMP++_ref															81.95 191

ACMMP++															81.25 196

High-resolution multi-view benchmark