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.

APDe-MVS		95.46 1	95.64 1	94.91 11	98.26 18	86.29 36	97.46 2	97.40 8	89.03 47	96.20 2	98.10 1	89.39 5	99.34 21	95.88 1	99.03 1	99.10 1

SteuartSystems-ACMMP		95.20 4	95.32 5	94.85 15	96.99 53	86.33 32	97.33 3	97.30 16	91.38 12	95.39 6	97.46 7	88.98 8	99.40 19	94.12 7	98.89 5	98.82 2
Skip Steuart: Steuart Systems R&D Blog.
MCST-MVS		94.45 12	94.20 19	95.19 5	98.46 10	87.50 8	95.00 82	97.12 25	87.13 86	92.51 48	96.30 52	89.24 6	99.34 21	93.46 12	98.62 30	98.73 3

CNVR-MVS		95.40 2	95.37 3	95.50 3	98.11 23	88.51 3	95.29 61	96.96 36	92.09 3	95.32 7	97.08 23	89.49 4	99.33 24	95.10 2	98.85 6	98.66 4

NCCC		94.81 8	94.69 9	95.17 6	97.83 30	87.46 9	95.66 49	96.93 39	92.34 2	93.94 18	96.58 43	87.74 12	99.44 18	92.83 20	98.40 37	98.62 5

ACMMP_Plus		94.74 9	94.56 10	95.28 4	98.02 28	87.70 4	95.68 47	97.34 10	88.28 65	95.30 8	97.67 3	85.90 31	99.54 8	93.91 9	98.95 2	98.60 6

3Dnovator+	87.14 4	92.42 55	91.37 59	95.55 2	95.63 95	88.73 2	97.07 8	96.77 51	90.84 17	84.02 200	96.62 41	75.95 133	99.34 21	87.77 83	97.68 53	98.59 7

region2R		94.43 14	94.27 15	94.92 10	98.65 1	86.67 21	96.92 14	97.23 20	88.60 58	93.58 25	97.27 11	85.22 37	99.54 8	92.21 29	98.74 16	98.56 8

ACMMPR		94.43 14	94.28 14	94.91 11	98.63 2	86.69 19	96.94 10	97.32 15	88.63 56	93.53 28	97.26 13	85.04 40	99.54 8	92.35 27	98.78 11	98.50 9

DeepPCF-MVS	89.96 1	94.20 24	94.77 8	92.49 87	96.52 64	80.00 170	94.00 155	97.08 28	90.05 26	95.65 5	97.29 10	89.66 2	98.97 59	93.95 8	98.71 17	98.50 9

TSAR-MVS + MP.		94.85 7	94.94 6	94.58 30	98.25 19	86.33 32	96.11 31	96.62 64	88.14 68	96.10 3	96.96 26	89.09 7	98.94 63	94.48 4	98.68 22	98.48 11

MPTG		94.47 11	94.30 13	95.00 8	98.42 12	86.95 10	95.06 80	96.97 33	91.07 14	93.14 32	97.56 4	84.30 47	99.56 1	93.43 13	98.75 14	98.47 12

MTAPA		94.42 16	94.22 16	95.00 8	98.42 12	86.95 10	94.36 131	96.97 33	91.07 14	93.14 32	97.56 4	84.30 47	99.56 1	93.43 13	98.75 14	98.47 12

XVS		94.45 12	94.32 12	94.85 15	98.54 5	86.60 24	96.93 12	97.19 21	90.66 22	92.85 34	97.16 21	85.02 41	99.49 14	91.99 36	98.56 33	98.47 12

X-MVStestdata		88.31 135	86.13 180	94.85 15	98.54 5	86.60 24	96.93 12	97.19 21	90.66 22	92.85 34	23.41 339	85.02 41	99.49 14	91.99 36	98.56 33	98.47 12

HSP-MVS		95.30 3	95.48 2	94.76 23	98.49 8	86.52 26	96.91 15	96.73 53	91.73 9	96.10 3	96.69 36	89.90 1	99.30 27	94.70 3	98.04 47	98.45 16

MP-MVS		94.25 20	94.07 23	94.77 22	98.47 9	86.31 34	96.71 20	96.98 32	89.04 46	91.98 58	97.19 18	85.43 35	99.56 1	92.06 35	98.79 9	98.44 17

mPP-MVS		93.99 27	93.78 29	94.63 28	98.50 7	85.90 45	96.87 16	96.91 40	88.70 54	91.83 62	97.17 20	83.96 50	99.55 5	91.44 49	98.64 29	98.43 18

CANet		93.54 36	93.20 39	94.55 31	95.65 94	85.73 48	94.94 85	96.69 59	91.89 5	90.69 75	95.88 70	81.99 69	99.54 8	93.14 18	97.95 49	98.39 19

DeepC-MVS_fast	89.43 2	94.04 25	93.79 28	94.80 21	97.48 39	86.78 16	95.65 51	96.89 41	89.40 38	92.81 37	96.97 25	85.37 36	99.24 29	90.87 56	98.69 19	98.38 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS-pluss		94.21 23	94.00 25	94.85 15	98.17 22	86.65 22	94.82 93	97.17 23	86.26 107	92.83 36	97.87 2	85.57 34	99.56 1	94.37 6	98.92 4	98.34 21
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HPM-MVS		94.02 26	93.88 26	94.43 36	98.39 14	85.78 47	97.25 5	97.07 29	86.90 97	92.62 45	96.80 33	84.85 44	99.17 33	92.43 24	98.65 28	98.33 22

PGM-MVS		93.96 28	93.72 31	94.68 26	98.43 11	86.22 37	95.30 59	97.78 1	87.45 83	93.26 29	97.33 9	84.62 45	99.51 12	90.75 58	98.57 32	98.32 23

HFP-MVS		94.52 10	94.40 11	94.86 13	98.61 3	86.81 14	96.94 10	97.34 10	88.63 56	93.65 21	97.21 16	86.10 27	99.49 14	92.35 27	98.77 12	98.30 24

#test#		94.32 19	94.14 20	94.86 13	98.61 3	86.81 14	96.43 23	97.34 10	87.51 82	93.65 21	97.21 16	86.10 27	99.49 14	91.68 45	98.77 12	98.30 24

MVS_0304		93.25 45	92.62 49	95.14 7	95.72 92	87.58 7	94.71 102	96.59 66	91.78 7	91.46 67	96.18 61	75.45 144	99.55 5	93.53 10	98.19 42	98.28 26

HPM-MVS++		95.14 5	94.91 7	95.83 1	98.25 19	89.65 1	95.92 38	96.96 36	91.75 8	94.02 17	96.83 30	88.12 9	99.55 5	93.41 15	98.94 3	98.28 26

APD-MVS		94.24 21	94.07 23	94.75 24	98.06 26	86.90 13	95.88 39	96.94 38	85.68 117	95.05 9	97.18 19	87.31 17	99.07 42	91.90 43	98.61 31	98.28 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
agg_prior2														90.54 59	98.68 22	98.27 29

canonicalmvs		93.27 43	92.75 48	94.85 15	95.70 93	87.66 5	96.33 25	96.41 74	90.00 28	94.09 15	94.60 104	82.33 60	98.62 82	92.40 26	92.86 132	98.27 29

APD-MVS_3200maxsize		93.78 31	93.77 30	93.80 53	97.92 29	84.19 73	96.30 26	96.87 44	86.96 93	93.92 19	97.47 6	83.88 51	98.96 62	92.71 22	97.87 50	98.26 31

CP-MVS		94.34 17	94.21 18	94.74 25	98.39 14	86.64 23	97.60 1	97.24 18	88.53 60	92.73 41	97.23 14	85.20 38	99.32 25	92.15 32	98.83 8	98.25 32

IS-MVSNet		91.43 66	91.09 65	92.46 88	95.87 89	81.38 135	96.95 9	93.69 221	89.72 34	89.50 87	95.98 66	78.57 100	97.77 134	83.02 137	96.50 74	98.22 33

LFMVS		90.08 89	89.13 98	92.95 72	96.71 58	82.32 119	96.08 32	89.91 301	86.79 98	92.15 56	96.81 31	62.60 270	98.34 96	87.18 92	93.90 110	98.19 34

CDPH-MVS		92.83 51	92.30 53	94.44 34	97.79 31	86.11 40	94.06 150	96.66 61	80.09 228	92.77 38	96.63 40	86.62 23	99.04 47	87.40 88	98.66 26	98.17 35

Regformer-2		94.33 18	94.22 16	94.68 26	95.54 97	86.75 18	94.57 110	96.70 57	91.84 6	94.41 10	96.56 45	87.19 18	99.13 38	93.50 11	97.65 55	98.16 36

alignmvs		93.08 49	92.50 52	94.81 20	95.62 96	87.61 6	95.99 35	96.07 95	89.77 32	94.12 14	94.87 94	80.56 78	98.66 78	92.42 25	93.10 127	98.15 37

Regformer-1		94.22 22	94.13 21	94.51 33	95.54 97	86.36 31	94.57 110	96.44 71	91.69 10	94.32 12	96.56 45	87.05 20	99.03 48	93.35 16	97.65 55	98.15 37

VNet		92.24 56	91.91 55	93.24 60	96.59 61	83.43 89	94.84 92	96.44 71	89.19 43	94.08 16	95.90 69	77.85 110	98.17 103	88.90 70	93.38 121	98.13 39

PHI-MVS		93.89 30	93.65 32	94.62 29	96.84 56	86.43 29	96.69 21	97.49 4	85.15 128	93.56 27	96.28 53	85.60 33	99.31 26	92.45 23	98.79 9	98.12 40

test_prior3		93.60 35	93.53 34	93.82 50	97.29 46	84.49 62	94.12 139	96.88 42	87.67 79	92.63 43	96.39 50	86.62 23	98.87 65	91.50 47	98.67 24	98.11 41

test_prior				93.82 50	97.29 46	84.49 62		96.88 42					98.87 65			98.11 41

test9_res														91.91 40	98.71 17	98.07 43

CSCG		93.23 47	93.05 41	93.76 54	98.04 27	84.07 75	96.22 28	97.37 9	84.15 148	90.05 82	95.66 77	87.77 11	99.15 36	89.91 63	98.27 40	98.07 43

EPNet		91.79 59	91.02 66	94.10 44	90.10 277	85.25 52	96.03 34	92.05 249	92.83 1	87.39 118	95.78 73	79.39 93	99.01 53	88.13 79	97.48 57	98.05 45
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		93.24 46	92.88 47	94.30 40	98.09 25	85.33 51	96.86 17	97.45 7	88.33 63	90.15 81	97.03 24	81.44 72	99.51 12	90.85 57	95.74 81	98.04 46
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
SD-MVS		94.96 6	95.33 4	93.88 48	97.25 50	86.69 19	96.19 29	97.11 27	90.42 24	96.95 1	97.27 11	89.53 3	96.91 212	94.38 5	98.85 6	98.03 47

MVS_111021_HR		93.45 37	93.31 36	93.84 49	96.99 53	84.84 54	93.24 195	97.24 18	88.76 53	91.60 66	95.85 71	86.07 29	98.66 78	91.91 40	98.16 43	98.03 47

Regformer-4		93.91 29	93.81 27	94.19 43	95.36 101	85.47 49	94.68 103	96.41 74	91.60 11	93.75 20	96.71 34	85.95 30	99.10 41	93.21 17	96.65 70	98.01 49

Regformer-3		93.68 33	93.64 33	93.81 52	95.36 101	84.61 58	94.68 103	95.83 112	91.27 13	93.60 24	96.71 34	85.75 32	98.86 68	92.87 19	96.65 70	97.96 50

train_agg		93.44 38	93.08 40	94.52 32	97.53 34	86.49 27	94.07 147	96.78 49	81.86 209	92.77 38	96.20 57	87.63 14	99.12 39	92.14 33	98.69 19	97.94 51

agg_prior3		93.27 43	92.89 46	94.40 38	97.49 37	86.12 39	94.07 147	96.73 53	81.46 217	92.46 50	96.05 65	86.90 21	99.15 36	92.14 33	98.69 19	97.94 51

mvs_anonymous		89.37 112	89.32 93	89.51 208	93.47 167	74.22 265	91.65 242	94.83 184	82.91 187	85.45 165	93.79 132	81.23 75	96.36 235	86.47 104	94.09 108	97.94 51

VDD-MVS		90.74 76	89.92 84	93.20 61	96.27 69	83.02 100	95.73 44	93.86 217	88.42 62	92.53 46	96.84 29	62.09 273	98.64 80	90.95 55	92.62 134	97.93 54

HPM-MVS_fast		93.40 40	93.22 38	93.94 47	98.36 16	84.83 55	97.15 7	96.80 48	85.77 114	92.47 49	97.13 22	82.38 59	99.07 42	90.51 60	98.40 37	97.92 55

agg_prior1		93.29 42	92.97 44	94.26 41	97.38 41	85.92 42	93.92 158	96.72 55	81.96 203	92.16 54	96.23 55	87.85 10	98.97 59	91.95 39	98.55 35	97.90 56

test12				94.34 39	97.13 51	86.15 38		96.29 80		91.04 73		85.08 39	99.01 53		98.13 44	97.86 57

VDDNet		89.56 102	88.49 113	92.76 79	95.07 110	82.09 121	96.30 26	93.19 227	81.05 222	91.88 59	96.86 28	61.16 282	98.33 97	88.43 75	92.49 135	97.84 58

TSAR-MVS + GP.		93.66 34	93.41 35	94.41 37	96.59 61	86.78 16	94.40 121	93.93 216	89.77 32	94.21 13	95.59 79	87.35 16	98.61 83	92.72 21	96.15 78	97.83 59

Vis-MVSNet (Re-imp)		89.59 101	89.44 90	90.03 188	95.74 91	75.85 259	95.61 52	90.80 285	87.66 81	87.83 110	95.40 82	76.79 115	96.46 230	78.37 208	96.73 67	97.80 60

3Dnovator	86.66 5	91.73 62	90.82 70	94.44 34	94.59 129	86.37 30	97.18 6	97.02 30	89.20 42	84.31 196	96.66 39	73.74 167	99.17 33	86.74 98	97.96 48	97.79 61

Vis-MVSNet		91.75 61	91.23 62	93.29 58	95.32 104	83.78 80	96.14 30	95.98 100	89.89 29	90.45 77	96.58 43	75.09 148	98.31 99	84.75 116	96.90 64	97.78 62
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DELS-MVS		93.43 39	93.25 37	93.97 45	95.42 100	85.04 53	93.06 202	97.13 24	90.74 20	91.84 60	95.09 90	86.32 26	99.21 30	91.22 50	98.45 36	97.65 63
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
MG-MVS		91.77 60	91.70 57	92.00 105	97.08 52	80.03 169	93.60 179	95.18 166	87.85 74	90.89 74	96.47 48	82.06 67	98.36 93	85.07 110	97.04 63	97.62 64

PAPM_NR		91.22 70	90.78 71	92.52 86	97.60 33	81.46 132	94.37 127	96.24 84	86.39 105	87.41 116	94.80 99	82.06 67	98.48 89	82.80 141	95.37 88	97.61 65

Effi-MVS+		91.59 65	91.11 63	93.01 70	94.35 140	83.39 91	94.60 107	95.10 168	87.10 87	90.57 76	93.10 151	81.43 73	98.07 120	89.29 67	94.48 102	97.59 66

DeepC-MVS	88.79 3	93.31 41	92.99 43	94.26 41	96.07 81	85.83 46	94.89 88	96.99 31	89.02 48	89.56 85	97.37 8	82.51 58	99.38 20	92.20 30	98.30 39	97.57 67
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EPP-MVSNet		91.70 63	91.56 58	92.13 102	95.88 87	80.50 160	97.33 3	95.25 159	86.15 109	89.76 84	95.60 78	83.42 52	98.32 98	87.37 90	93.25 124	97.56 68

MVS_Test		91.31 68	91.11 63	91.93 109	94.37 137	80.14 164	93.46 184	95.80 114	86.46 103	91.35 69	93.77 133	82.21 63	98.09 118	87.57 86	94.95 93	97.55 69

PAPR		90.02 90	89.27 96	92.29 96	95.78 90	80.95 148	92.68 213	96.22 85	81.91 206	86.66 130	93.75 135	82.23 62	98.44 92	79.40 202	94.79 94	97.48 70

UA-Net		92.83 51	92.54 51	93.68 55	96.10 79	84.71 57	95.66 49	96.39 76	91.92 4	93.22 30	96.49 47	83.16 53	98.87 65	84.47 119	95.47 86	97.45 71

EI-MVSNet-Vis-set		93.01 50	92.92 45	93.29 58	95.01 111	83.51 88	94.48 113	95.77 116	90.87 16	92.52 47	96.67 38	84.50 46	99.00 56	91.99 36	94.44 105	97.36 72

abl_6		93.18 48	93.05 41	93.57 57	97.52 36	84.27 72	95.53 54	96.67 60	87.85 74	93.20 31	97.22 15	80.35 79	99.18 32	91.91 40	97.21 60	97.26 73

MVSFormer		91.68 64	91.30 60	92.80 77	93.86 156	83.88 78	95.96 36	95.90 107	84.66 137	91.76 63	94.91 92	77.92 107	97.30 179	89.64 65	97.11 61	97.24 74

jason		90.80 75	90.10 79	92.90 74	93.04 180	83.53 87	93.08 200	94.15 203	80.22 226	91.41 68	94.91 92	76.87 113	97.93 129	90.28 62	96.90 64	97.24 74
jason: jason.
WTY-MVS		89.60 100	88.92 103	91.67 120	95.47 99	81.15 142	92.38 223	94.78 186	83.11 173	89.06 92	94.32 109	78.67 98	96.61 222	81.57 161	90.89 152	97.24 74

test_normal		88.13 141	86.78 159	92.18 99	90.55 269	81.19 141	92.74 211	94.64 189	83.84 152	77.49 272	90.51 238	68.49 240	98.16 104	88.22 76	94.55 100	97.21 77

HyFIR lowres test		88.09 142	86.81 156	91.93 109	96.00 83	80.63 155	90.01 260	95.79 115	73.42 285	87.68 114	92.10 186	73.86 164	97.96 126	80.75 171	91.70 138	97.19 78

EI-MVSNet-UG-set		92.74 53	92.62 49	93.12 64	94.86 119	83.20 94	94.40 121	95.74 119	90.71 21	92.05 57	96.60 42	84.00 49	98.99 57	91.55 46	93.63 114	97.17 79

DI_MVS_plusplus_test		88.15 140	86.82 155	92.14 101	90.67 264	81.07 143	93.01 203	94.59 190	83.83 154	77.78 269	90.63 233	68.51 239	98.16 104	88.02 81	94.37 106	97.17 79

lupinMVS		90.92 74	90.21 76	93.03 69	93.86 156	83.88 78	92.81 209	93.86 217	79.84 230	91.76 63	94.29 111	77.92 107	98.04 122	90.48 61	97.11 61	97.17 79

CHOSEN 1792x2688		88.84 124	87.69 130	92.30 95	96.14 75	81.42 134	90.01 260	95.86 111	74.52 279	87.41 116	93.94 124	75.46 143	98.36 93	80.36 179	95.53 83	97.12 82

Test4		85.75 211	83.72 225	91.83 114	88.08 300	81.03 145	92.48 219	95.54 133	83.38 168	73.40 300	88.57 264	50.99 312	97.37 176	86.61 103	94.47 103	97.09 83

CPTT-MVS		91.99 57	91.80 56	92.55 84	98.24 21	81.98 124	96.76 19	96.49 70	81.89 208	90.24 79	96.44 49	78.59 99	98.61 83	89.68 64	97.85 51	97.06 84

114514_t		89.51 103	88.50 111	92.54 85	98.11 23	81.99 123	95.16 74	96.36 78	70.19 307	85.81 144	95.25 85	76.70 116	98.63 81	82.07 152	96.86 66	97.00 85

旧先验1					96.79 57	81.81 125		95.67 122			96.81 31	86.69 22			97.66 54	96.97 86

ab-mvs		89.41 109	88.35 115	92.60 82	95.15 109	82.65 114	92.20 229	95.60 128	83.97 150	88.55 95	93.70 136	74.16 160	98.21 102	82.46 147	89.37 169	96.94 87

diffmvs		89.07 117	88.32 118	91.34 128	93.24 173	79.79 175	92.29 226	94.98 174	80.24 225	87.38 119	92.45 172	78.02 105	97.33 177	83.29 134	92.93 130	96.91 88

DP-MVS Recon		91.95 58	91.28 61	93.96 46	98.33 17	85.92 42	94.66 106	96.66 61	82.69 193	90.03 83	95.82 72	82.30 61	99.03 48	84.57 118	96.48 75	96.91 88

QAPM		89.51 103	88.15 123	93.59 56	94.92 116	84.58 59	96.82 18	96.70 57	78.43 246	83.41 214	96.19 60	73.18 174	99.30 27	77.11 223	96.54 73	96.89 90

OMC-MVS		91.23 69	90.62 72	93.08 66	96.27 69	84.07 75	93.52 181	95.93 103	86.95 94	89.51 86	96.13 63	78.50 101	98.35 95	85.84 105	92.90 131	96.83 91

MSLP-MVS++		93.72 32	94.08 22	92.65 81	97.31 44	83.43 89	95.79 42	97.33 13	90.03 27	93.58 25	96.96 26	84.87 43	97.76 135	92.19 31	98.66 26	96.76 92

MVS_111021_LR		92.47 54	92.29 54	92.98 71	95.99 84	84.43 69	93.08 200	96.09 93	88.20 67	91.12 72	95.72 76	81.33 74	97.76 135	91.74 44	97.37 59	96.75 93

UGNet		89.95 93	88.95 102	92.95 72	94.51 132	83.31 92	95.70 46	95.23 163	89.37 39	87.58 115	93.94 124	64.00 266	98.78 75	83.92 129	96.31 77	96.74 94
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
LCM-MVSNet-Re		88.30 136	88.32 118	88.27 243	94.71 124	72.41 285	93.15 196	90.98 280	87.77 76	79.25 262	91.96 192	78.35 103	95.75 258	83.04 136	95.62 82	96.65 95

无先验							93.28 192	96.26 81	73.95 282				99.05 44	80.56 175		96.59 96

Fast-Effi-MVS+		89.41 109	88.64 108	91.71 119	94.74 121	80.81 152	93.54 180	95.10 168	83.11 173	86.82 128	90.67 232	79.74 87	97.75 138	80.51 177	93.55 115	96.57 97

sss		88.93 123	88.26 122	90.94 145	94.05 146	80.78 153	91.71 239	95.38 150	81.55 215	88.63 94	93.91 128	75.04 149	95.47 269	82.47 146	91.61 139	96.57 97

DP-MVS		87.25 179	85.36 199	92.90 74	97.65 32	83.24 93	94.81 94	92.00 251	74.99 274	81.92 233	95.00 91	72.66 180	99.05 44	66.92 290	92.33 136	96.40 99

CANet_DTU		90.26 87	89.41 91	92.81 76	93.46 168	83.01 101	93.48 182	94.47 193	89.43 37	87.76 113	94.23 115	70.54 209	99.03 48	84.97 111	96.39 76	96.38 100

TAMVS		89.21 114	88.29 120	91.96 107	93.71 162	82.62 115	93.30 190	94.19 201	82.22 198	87.78 112	93.94 124	78.83 95	96.95 209	77.70 216	92.98 129	96.32 101

CDS-MVSNet		89.45 106	88.51 110	92.29 96	93.62 164	83.61 86	93.01 203	94.68 188	81.95 204	87.82 111	93.24 145	78.69 97	96.99 205	80.34 180	93.23 125	96.28 102
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		88.42 131	87.33 137	91.72 118	94.92 116	80.98 146	92.97 206	94.54 191	78.16 251	83.82 204	93.88 129	78.78 96	97.91 130	79.45 198	89.41 168	96.26 103

Test_1112_low_res		87.65 158	86.51 172	91.08 137	94.94 115	79.28 200	91.77 236	94.30 199	76.04 266	83.51 212	92.37 175	77.86 109	97.73 139	78.69 207	89.13 175	96.22 104

GA-MVS		86.61 194	85.27 201	90.66 148	91.33 229	78.71 212	90.40 254	93.81 220	85.34 123	85.12 177	89.57 252	61.25 279	97.11 197	80.99 168	89.59 167	96.15 105

原ACMM1				92.01 103	97.34 43	81.05 144		96.81 47	78.89 238	90.45 77	95.92 68	82.65 57	98.84 73	80.68 173	98.26 41	96.14 106

TAPA-MVS	84.62 6	88.16 139	87.01 150	91.62 121	96.64 59	80.65 154	94.39 123	96.21 88	76.38 261	86.19 140	95.44 80	79.75 86	98.08 119	62.75 304	95.29 90	96.13 107
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
1121		90.42 84	89.49 88	93.20 61	97.27 48	84.46 65	92.63 214	95.51 137	71.01 305	91.20 71	96.21 56	82.92 55	99.05 44	80.56 175	98.07 46	96.10 108

PatchmatchNet		85.85 207	84.70 212	89.29 213	91.76 205	75.54 261	88.49 281	91.30 270	81.63 213	85.05 178	88.70 262	71.71 188	96.24 239	74.61 244	89.05 176	96.08 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
新几何1				93.10 65	97.30 45	84.35 71		95.56 130	71.09 304	91.26 70	96.24 54	82.87 56	98.86 68	79.19 203	98.10 45	96.07 110

PVSNet	78.82 18	85.55 213	84.65 213	88.23 246	94.72 123	71.93 286	87.12 292	92.75 235	78.80 241	84.95 180	90.53 237	64.43 265	96.71 218	74.74 242	93.86 111	96.06 111

test222					96.55 63	81.70 126	92.22 228	95.01 171	68.36 311	90.20 80	96.14 62	80.26 82			97.80 52	96.05 112

PVSNet_Blended_VisFu		91.38 67	90.91 68	92.80 77	96.39 66	83.17 95	94.87 91	96.66 61	83.29 170	89.27 88	94.46 106	80.29 81	99.17 33	87.57 86	95.37 88	96.05 112

testdata				90.49 160	96.40 65	77.89 237		95.37 152	72.51 294	93.63 23	96.69 36	82.08 66	97.65 140	83.08 135	97.39 58	95.94 114

XVG-OURS-SEG-HR		89.95 93	89.45 89	91.47 125	94.00 151	81.21 140	91.87 235	96.06 97	85.78 113	88.55 95	95.73 75	74.67 152	97.27 183	88.71 72	89.64 166	95.91 115

MAR-MVS		90.30 85	89.37 92	93.07 68	96.61 60	84.48 64	95.68 47	95.67 122	82.36 197	87.85 105	92.85 160	76.63 118	98.80 74	80.01 185	96.68 69	95.91 115
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
HY-MVS	83.01 12	89.03 120	87.94 128	92.29 96	94.86 119	82.77 106	92.08 234	94.49 192	81.52 216	86.93 124	92.79 166	78.32 104	98.23 100	79.93 188	90.55 153	95.88 117

BH-RMVSNet		88.37 133	87.48 133	91.02 141	95.28 105	79.45 186	92.89 208	93.07 229	85.45 121	86.91 125	94.84 98	70.35 210	97.76 135	73.97 248	94.59 99	95.85 118

PVSNet_Blended		90.73 77	90.32 75	91.98 106	96.12 76	81.25 137	92.55 218	96.83 45	82.04 202	89.10 90	92.56 170	81.04 76	98.85 71	86.72 101	95.91 79	95.84 119

Patchmatch-test		81.37 267	79.30 271	87.58 257	90.92 254	74.16 267	80.99 321	87.68 318	70.52 306	76.63 275	88.81 259	71.21 195	92.76 306	60.01 312	86.93 203	95.83 120

XVG-OURS		89.40 111	88.70 107	91.52 123	94.06 145	81.46 132	91.27 248	96.07 95	86.14 110	88.89 93	95.77 74	68.73 236	97.26 185	87.39 89	89.96 161	95.83 120

EPNet_dtu		86.49 198	85.94 187	88.14 248	90.24 275	72.82 277	94.11 141	92.20 245	86.66 101	79.42 261	92.36 176	73.52 168	95.81 256	71.26 260	93.66 113	95.80 122
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmatch-test1		85.81 209	84.71 211	89.12 217	92.15 195	76.60 252	91.12 251	91.69 260	83.53 163	85.50 162	88.56 265	66.79 248	95.00 285	72.69 255	90.35 156	95.76 123

tpm		84.73 234	84.02 218	86.87 275	90.33 272	68.90 305	89.06 275	89.94 300	80.85 223	85.75 148	89.86 248	68.54 238	95.97 248	77.76 215	84.05 223	95.75 124

Patchmatch-RL test		81.67 261	79.96 265	86.81 276	85.42 309	71.23 291	82.17 319	87.50 320	78.47 245	77.19 274	82.50 310	70.81 202	93.48 298	82.66 142	72.89 299	95.71 125

tpmp4_e23		83.87 246	82.33 247	88.48 237	91.46 213	72.82 277	89.82 263	91.57 264	73.02 290	81.86 234	89.05 256	66.20 255	96.97 207	71.57 259	86.39 204	95.66 126

LS3D		87.89 148	86.32 176	92.59 83	96.07 81	82.92 104	95.23 69	94.92 179	75.66 268	82.89 219	95.98 66	72.48 184	99.21 30	68.43 282	95.23 92	95.64 127

CNLPA		89.07 117	87.98 126	92.34 94	96.87 55	84.78 56	94.08 145	93.24 226	81.41 218	84.46 188	95.13 89	75.57 141	96.62 220	77.21 221	93.84 112	95.61 128

MDTV_nov1_ep13_2view						55.91 330	87.62 290		73.32 286	84.59 185		70.33 211		74.65 243		95.50 129

mvs-test1		89.45 106	89.14 97	90.38 166	93.33 170	77.63 245	94.95 84	94.36 196	87.70 77	87.10 122	92.81 164	73.45 170	98.03 123	85.57 107	93.04 128	95.48 130

DWT-MVSNet_test		84.95 226	83.68 227	88.77 222	91.43 217	73.75 271	91.74 238	90.98 280	80.66 224	83.84 203	87.36 280	62.44 271	97.11 197	78.84 206	85.81 207	95.46 131

EPMVS		83.90 245	82.70 246	87.51 258	90.23 276	72.67 280	88.62 280	81.96 331	81.37 219	85.01 179	88.34 268	66.31 253	94.45 288	75.30 237	87.12 200	95.43 132

CR-MVSNet		85.35 216	83.76 222	90.12 179	90.58 266	79.34 196	85.24 304	91.96 255	78.27 248	85.55 157	87.87 276	71.03 198	95.61 260	73.96 249	89.36 170	95.40 133

tpmrst		85.35 216	84.99 203	86.43 278	90.88 257	67.88 308	88.71 278	91.43 268	80.13 227	86.08 142	88.80 260	73.05 175	96.02 246	82.48 145	83.40 233	95.40 133

RPMNet		83.18 252	80.87 258	90.12 179	90.58 266	79.34 196	85.24 304	90.78 286	71.44 300	85.55 157	82.97 309	70.87 200	95.61 260	61.01 308	89.36 170	95.40 133

CostFormer		85.77 210	84.94 206	88.26 244	91.16 244	72.58 284	89.47 269	91.04 279	76.26 264	86.45 134	89.97 246	70.74 203	96.86 215	82.35 148	87.07 202	95.34 136

IB-MVS	80.51 15	85.24 219	83.26 238	91.19 132	92.13 197	79.86 173	91.75 237	91.29 271	83.28 171	80.66 247	88.49 266	61.28 278	98.46 90	80.99 168	79.46 283	95.25 137
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
ADS-MVSNet2		81.66 262	79.71 268	87.50 259	91.35 227	74.19 266	83.33 315	88.48 312	72.90 291	82.24 226	85.77 297	64.98 262	93.20 302	64.57 298	83.74 225	95.12 138

ADS-MVSNet		81.56 264	79.78 266	86.90 273	91.35 227	71.82 287	83.33 315	89.16 308	72.90 291	82.24 226	85.77 297	64.98 262	93.76 294	64.57 298	83.74 225	95.12 138

AdaColmap		89.89 96	89.07 99	92.37 93	97.41 40	83.03 99	94.42 120	95.92 104	82.81 189	86.34 137	94.65 102	73.89 163	99.02 51	80.69 172	95.51 84	95.05 140

PLC	84.53 7	89.06 119	88.03 125	92.15 100	97.27 48	82.69 113	94.29 132	95.44 146	79.71 232	84.01 201	94.18 116	76.68 117	98.75 76	77.28 220	93.41 120	95.02 141
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PatchFormer-LS_test		86.02 203	85.13 202	88.70 225	91.52 211	74.12 268	91.19 250	92.09 247	82.71 192	84.30 197	87.24 282	70.87 200	96.98 206	81.04 165	85.17 214	95.00 142

Effi-MVS+-dtu		88.65 128	88.35 115	89.54 205	93.33 170	76.39 254	94.47 116	94.36 196	87.70 77	85.43 168	89.56 253	73.45 170	97.26 185	85.57 107	91.28 141	94.97 143

test-LLR		85.87 206	85.41 197	87.25 265	90.95 250	71.67 288	89.55 265	89.88 302	83.41 166	84.54 186	87.95 273	67.25 245	95.11 282	81.82 157	93.37 122	94.97 143

test-mter		84.54 239	83.64 229	87.25 265	90.95 250	71.67 288	89.55 265	89.88 302	79.17 235	84.54 186	87.95 273	55.56 301	95.11 282	81.82 157	93.37 122	94.97 143

view600		87.62 163	86.65 164	90.53 152	96.19 71	78.52 217	95.29 61	91.09 272	87.08 88	87.84 106	93.03 154	68.86 231	98.11 108	69.44 274	91.02 148	94.96 146

view800		87.62 163	86.65 164	90.53 152	96.19 71	78.52 217	95.29 61	91.09 272	87.08 88	87.84 106	93.03 154	68.86 231	98.11 108	69.44 274	91.02 148	94.96 146

conf0.05thres1000		87.62 163	86.65 164	90.53 152	96.19 71	78.52 217	95.29 61	91.09 272	87.08 88	87.84 106	93.03 154	68.86 231	98.11 108	69.44 274	91.02 148	94.96 146

tfpn		87.62 163	86.65 164	90.53 152	96.19 71	78.52 217	95.29 61	91.09 272	87.08 88	87.84 106	93.03 154	68.86 231	98.11 108	69.44 274	91.02 148	94.96 146

nrg030		91.08 73	90.39 73	93.17 63	93.07 178	86.91 12	96.41 24	96.26 81	88.30 64	88.37 98	94.85 97	82.19 64	97.64 142	91.09 51	82.95 234	94.96 146

thres600view7		87.65 158	86.67 163	90.59 149	96.08 80	78.72 211	94.88 90	91.58 262	87.06 92	88.08 101	92.30 178	68.91 229	98.10 112	70.05 272	91.10 142	94.96 146

thres400		87.62 163	86.64 168	90.57 150	95.99 84	78.64 213	94.58 108	91.98 253	86.94 95	88.09 99	91.77 196	69.18 226	98.10 112	70.13 269	91.10 142	94.96 146

PAPM		86.68 193	85.39 198	90.53 152	93.05 179	79.33 199	89.79 264	94.77 187	78.82 240	81.95 232	93.24 145	76.81 114	97.30 179	66.94 288	93.16 126	94.95 153

MIMVSNet		82.59 256	80.53 259	88.76 223	91.51 212	78.32 226	86.57 295	90.13 295	79.32 234	80.70 246	88.69 263	52.98 309	93.07 305	66.03 293	88.86 178	94.90 154

CVMVSNet		84.69 237	84.79 210	84.37 293	91.84 202	64.92 316	93.70 174	91.47 267	66.19 317	86.16 141	95.28 83	67.18 247	93.33 300	80.89 170	90.42 155	94.88 155

PatchT		82.68 255	81.27 253	86.89 274	90.09 278	70.94 296	84.06 311	90.15 294	74.91 275	85.63 156	83.57 305	69.37 220	94.87 287	65.19 295	88.50 183	94.84 156

OpenMVS	83.78 11	88.74 127	87.29 138	93.08 66	92.70 188	85.39 50	96.57 22	96.43 73	78.74 243	80.85 244	96.07 64	69.64 218	99.01 53	78.01 214	96.65 70	94.83 157

PCF-MVS	84.11 10	87.74 156	86.08 183	92.70 80	94.02 147	84.43 69	89.27 271	95.87 110	73.62 284	84.43 190	94.33 108	78.48 102	98.86 68	70.27 265	94.45 104	94.81 158
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
F-COLMAP		87.95 147	86.80 157	91.40 127	96.35 68	80.88 150	94.73 98	95.45 144	79.65 233	82.04 231	94.61 103	71.13 196	98.50 88	76.24 230	91.05 146	94.80 159

FIs		90.51 83	90.35 74	90.99 143	93.99 152	80.98 146	95.73 44	97.54 3	89.15 44	86.72 129	94.68 100	81.83 71	97.24 187	85.18 109	88.31 188	94.76 160

FC-MVSNet-test		90.27 86	90.18 78	90.53 152	93.71 162	79.85 174	95.77 43	97.59 2	89.31 40	86.27 138	94.67 101	81.93 70	97.01 204	84.26 124	88.09 191	94.71 161

HQP_MVS		90.60 82	90.19 77	91.82 115	94.70 125	82.73 110	95.85 40	96.22 85	90.81 18	86.91 125	94.86 95	74.23 156	98.12 106	88.15 77	89.99 159	94.63 162

plane_prior5								96.22 85					98.12 106	88.15 77	89.99 159	94.63 162

tpm2		84.08 242	82.94 242	87.48 261	91.39 220	71.27 290	89.23 273	90.37 290	71.95 298	84.64 183	89.33 254	67.30 244	96.55 225	75.17 238	87.09 201	94.63 162

pcd1.5k->3k		37.02 316	38.84 317	31.53 329	92.33 193	0.00 348	0.00 339	96.13 91	0.00 343	0.00 344	0.00 345	72.70 179	0.00 346	0.00 343	88.43 185	94.60 165

DU-MVS		89.34 113	88.50 111	91.85 113	93.04 180	83.72 81	94.47 116	96.59 66	89.50 36	86.46 132	93.29 143	77.25 111	97.23 189	84.92 112	81.02 262	94.59 166

NR-MVSNet		88.58 130	87.47 134	91.93 109	93.04 180	84.16 74	94.77 97	96.25 83	89.05 45	80.04 256	93.29 143	79.02 94	97.05 202	81.71 160	80.05 276	94.59 166

PS-MVSNAJss		89.97 92	89.62 86	91.02 141	91.90 200	80.85 151	95.26 68	95.98 100	86.26 107	86.21 139	94.29 111	79.70 88	97.65 140	88.87 71	88.10 189	94.57 168

VPNet		88.20 138	87.47 134	90.39 164	93.56 166	79.46 184	94.04 151	95.54 133	88.67 55	86.96 123	94.58 105	69.33 221	97.15 193	84.05 128	80.53 271	94.56 169

RPSCF		85.07 221	84.27 215	87.48 261	92.91 185	70.62 298	91.69 241	92.46 240	76.20 265	82.67 222	95.22 86	63.94 267	97.29 182	77.51 219	85.80 208	94.53 170

VPA-MVSNet		89.62 99	88.96 101	91.60 122	93.86 156	82.89 105	95.46 55	97.33 13	87.91 71	88.43 97	93.31 141	74.17 159	97.40 172	87.32 91	82.86 236	94.52 171

HQP4-MVS										85.43 168			97.96 126			94.51 172

TranMVSNet+NR-MVSNet		88.84 124	87.95 127	91.49 124	92.68 189	83.01 101	94.92 87	96.31 79	89.88 30	85.53 159	93.85 131	76.63 118	96.96 208	81.91 156	79.87 281	94.50 173

HQP-MVS		89.80 97	89.28 95	91.34 128	94.17 142	81.56 127	94.39 123	96.04 98	88.81 50	85.43 168	93.97 123	73.83 165	97.96 126	87.11 95	89.77 164	94.50 173

UniMVSNet_NR-MVSNet		89.92 95	89.29 94	91.81 117	93.39 169	83.72 81	94.43 119	97.12 25	89.80 31	86.46 132	93.32 140	83.16 53	97.23 189	84.92 112	81.02 262	94.49 175

thres100view900		87.63 161	86.71 161	90.38 166	96.12 76	78.55 215	95.03 81	91.58 262	87.15 85	88.06 102	92.29 179	68.91 229	98.10 112	70.13 269	91.10 142	94.48 176

tfpn200view9		87.58 169	86.64 168	90.41 163	95.99 84	78.64 213	94.58 108	91.98 253	86.94 95	88.09 99	91.77 196	69.18 226	98.10 112	70.13 269	91.10 142	94.48 176

WR-MVS		88.38 132	87.67 131	90.52 158	93.30 172	80.18 162	93.26 193	95.96 102	88.57 59	85.47 164	92.81 164	76.12 122	96.91 212	81.24 163	82.29 240	94.47 178

TESTMET0.1,1		83.74 247	82.85 244	86.42 279	89.96 281	71.21 292	89.55 265	87.88 315	77.41 254	83.37 215	87.31 281	56.71 298	93.65 296	80.62 174	92.85 133	94.40 179

API-MVS		90.66 78	90.07 80	92.45 89	96.36 67	84.57 60	96.06 33	95.22 165	82.39 195	89.13 89	94.27 114	80.32 80	98.46 90	80.16 184	96.71 68	94.33 180

PS-MVSNAJ		91.18 71	90.92 67	91.96 107	95.26 107	82.60 116	92.09 233	95.70 121	86.27 106	91.84 60	92.46 171	79.70 88	98.99 57	89.08 68	95.86 80	94.29 181

xiu_mvs_v2_base		91.13 72	90.89 69	91.86 112	94.97 114	82.42 117	92.24 227	95.64 127	86.11 111	91.74 65	93.14 149	79.67 91	98.89 64	89.06 69	95.46 87	94.28 182

xiu_mvs_v1_base_debu		90.64 79	90.05 81	92.40 90	93.97 153	84.46 65	93.32 186	95.46 140	85.17 125	92.25 51	94.03 117	70.59 205	98.57 85	90.97 52	94.67 95	94.18 183

xiu_mvs_v1_base		90.64 79	90.05 81	92.40 90	93.97 153	84.46 65	93.32 186	95.46 140	85.17 125	92.25 51	94.03 117	70.59 205	98.57 85	90.97 52	94.67 95	94.18 183

xiu_mvs_v1_base_debi		90.64 79	90.05 81	92.40 90	93.97 153	84.46 65	93.32 186	95.46 140	85.17 125	92.25 51	94.03 117	70.59 205	98.57 85	90.97 52	94.67 95	94.18 183

Fast-Effi-MVS+-dtu		87.44 173	86.72 160	89.63 203	92.04 199	77.68 244	94.03 152	93.94 215	85.81 112	82.42 223	91.32 214	70.33 211	97.06 201	80.33 181	90.23 157	94.14 186

1314		87.51 171	86.57 171	90.34 169	92.42 192	79.74 177	92.63 214	95.35 154	78.35 247	80.14 254	91.62 203	74.05 161	97.15 193	81.05 164	93.53 116	94.12 187

UniMVSNet (Re)		89.80 97	89.07 99	92.01 103	93.60 165	84.52 61	94.78 96	97.47 5	89.26 41	86.44 135	92.32 177	82.10 65	97.39 175	84.81 115	80.84 266	94.12 187

BH-untuned		88.60 129	88.13 124	90.01 190	95.24 108	78.50 222	93.29 191	94.15 203	84.75 135	84.46 188	93.40 137	75.76 138	97.40 172	77.59 217	94.52 101	94.12 187

dp		81.47 266	80.23 262	85.17 288	89.92 282	65.49 315	86.74 293	90.10 296	76.30 263	81.10 241	87.12 284	62.81 269	95.92 250	68.13 285	79.88 280	94.09 190

ACMM	84.12 9	89.14 115	88.48 114	91.12 134	94.65 128	81.22 139	95.31 57	96.12 92	85.31 124	85.92 143	94.34 107	70.19 213	98.06 121	85.65 106	88.86 178	94.08 191
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_djsdf		89.03 120	88.64 108	90.21 171	90.74 261	79.28 200	95.96 36	95.90 107	84.66 137	85.33 175	92.94 159	74.02 162	97.30 179	89.64 65	88.53 181	94.05 192

cascas		86.43 199	84.98 204	90.80 147	92.10 198	80.92 149	90.24 256	95.91 106	73.10 288	83.57 211	88.39 267	65.15 261	97.46 152	84.90 114	91.43 140	94.03 193

XXY-MVS		87.65 158	86.85 154	90.03 188	92.14 196	80.60 157	93.76 167	95.23 163	82.94 185	84.60 184	94.02 120	74.27 155	95.49 268	81.04 165	83.68 227	94.01 194

testing_2		83.40 250	81.02 255	90.56 151	85.06 311	80.51 159	91.37 246	95.57 129	82.92 186	67.06 316	85.54 299	49.47 315	97.24 187	86.74 98	85.44 210	93.93 195

CLD-MVS		89.47 105	88.90 104	91.18 133	94.22 141	82.07 122	92.13 231	96.09 93	87.90 72	85.37 174	92.45 172	74.38 154	97.56 145	87.15 93	90.43 154	93.93 195
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
jajsoiax		88.24 137	87.50 132	90.48 161	90.89 256	80.14 164	95.31 57	95.65 126	84.97 131	84.24 198	94.02 120	65.31 260	97.42 165	88.56 73	88.52 182	93.89 197

IterMVS-LS		88.36 134	87.91 129	89.70 201	93.80 159	78.29 228	93.73 170	95.08 170	85.73 115	84.75 182	91.90 194	79.88 84	96.92 211	83.83 130	82.51 238	93.89 197
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 116	88.86 106	89.80 198	91.84 202	78.30 227	93.70 174	95.01 171	85.73 115	87.15 120	95.28 83	79.87 85	97.21 191	83.81 131	87.36 197	93.88 199

mvs_tets		88.06 143	87.28 139	90.38 166	90.94 252	79.88 172	95.22 70	95.66 124	85.10 129	84.21 199	93.94 124	63.53 268	97.40 172	88.50 74	88.40 187	93.87 200

MVSTER		88.84 124	88.29 120	90.51 159	92.95 184	80.44 161	93.73 170	95.01 171	84.66 137	87.15 120	93.12 150	72.79 178	97.21 191	87.86 82	87.36 197	93.87 200

tpm cat1		81.96 259	80.27 261	87.01 270	91.09 245	71.02 294	87.38 291	91.53 266	66.25 316	80.17 252	86.35 294	68.22 243	96.15 242	69.16 278	82.29 240	93.86 202

v2v482		87.84 150	87.06 148	90.17 172	90.99 248	79.23 206	94.00 155	95.13 167	84.87 132	85.53 159	92.07 189	74.45 153	97.45 154	84.71 117	81.75 252	93.85 203

thres200		87.21 182	86.24 179	90.12 179	95.36 101	78.53 216	93.26 193	92.10 246	86.42 104	88.00 103	91.11 225	69.24 225	98.00 124	69.58 273	91.04 147	93.83 204

CP-MVSNet		87.63 161	87.26 140	88.74 224	93.12 177	76.59 253	95.29 61	96.58 68	88.43 61	83.49 213	92.98 158	75.28 145	95.83 254	78.97 204	81.15 259	93.79 205

GBi-Net		87.26 177	85.98 185	91.08 137	94.01 148	83.10 96	95.14 75	94.94 175	83.57 160	84.37 191	91.64 199	66.59 250	96.34 236	78.23 211	85.36 211	93.79 205

test1		87.26 177	85.98 185	91.08 137	94.01 148	83.10 96	95.14 75	94.94 175	83.57 160	84.37 191	91.64 199	66.59 250	96.34 236	78.23 211	85.36 211	93.79 205

FMVSNet1		85.85 207	84.11 217	91.08 137	92.81 186	83.10 96	95.14 75	94.94 175	81.64 212	82.68 221	91.64 199	59.01 292	96.34 236	75.37 236	83.78 224	93.79 205

LPG-MVS_test		89.45 106	88.90 104	91.12 134	94.47 133	81.49 130	95.30 59	96.14 89	86.73 99	85.45 165	95.16 87	69.89 214	98.10 112	87.70 84	89.23 173	93.77 209

LGP-MVS_train				91.12 134	94.47 133	81.49 130		96.14 89	86.73 99	85.45 165	95.16 87	69.89 214	98.10 112	87.70 84	89.23 173	93.77 209

PS-CasMVS		87.32 176	86.88 152	88.63 227	92.99 183	76.33 256	95.33 56	96.61 65	88.22 66	83.30 216	93.07 152	73.03 176	95.79 257	78.36 209	81.00 264	93.75 211

FMVSNet2		87.19 183	85.82 189	91.30 130	94.01 148	83.67 83	94.79 95	94.94 175	83.57 160	83.88 202	92.05 190	66.59 250	96.51 226	77.56 218	85.01 215	93.73 212

ACMP	84.23 8	89.01 122	88.35 115	90.99 143	94.73 122	81.27 136	95.07 78	95.89 109	86.48 102	83.67 208	94.30 110	69.33 221	97.99 125	87.10 97	88.55 180	93.72 213
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
FMVSNet3		87.40 175	86.11 181	91.30 130	93.79 161	83.64 84	94.20 137	94.81 185	83.89 151	84.37 191	91.87 195	68.45 241	96.56 223	78.23 211	85.36 211	93.70 214

OPM-MVS		90.12 88	89.56 87	91.82 115	93.14 176	83.90 77	94.16 138	95.74 119	88.96 49	87.86 104	95.43 81	72.48 184	97.91 130	88.10 80	90.18 158	93.65 215

divwei89l23v2f112		87.84 150	87.09 145	90.10 186	91.23 236	79.24 204	94.09 143	95.24 160	84.44 144	85.70 151	91.31 215	75.91 134	97.44 161	84.17 126	81.73 254	93.64 216

v1		87.85 149	87.10 144	90.11 184	91.21 238	79.24 204	94.09 143	95.24 160	84.44 144	85.70 151	91.31 215	75.96 132	97.45 154	84.18 125	81.73 254	93.64 216

v1141		87.84 150	87.09 145	90.11 184	91.23 236	79.25 202	94.08 145	95.24 160	84.44 144	85.69 153	91.31 215	75.91 134	97.44 161	84.17 126	81.74 253	93.63 218

v6		87.98 144	87.25 141	90.16 173	91.36 224	79.39 193	94.37 127	95.27 158	84.48 140	85.78 145	91.51 210	76.15 121	97.46 152	84.46 120	81.88 249	93.62 219

v1neww		87.98 144	87.25 141	90.16 173	91.38 221	79.41 188	94.37 127	95.28 155	84.48 140	85.77 146	91.53 208	76.12 122	97.45 154	84.45 121	81.89 247	93.61 220

v7new		87.98 144	87.25 141	90.16 173	91.38 221	79.41 188	94.37 127	95.28 155	84.48 140	85.77 146	91.53 208	76.12 122	97.45 154	84.45 121	81.89 247	93.61 220

PEN-MVS		86.80 189	86.27 178	88.40 240	92.32 194	75.71 260	95.18 72	96.38 77	87.97 69	82.82 220	93.15 148	73.39 172	95.92 250	76.15 231	79.03 284	93.59 222

TR-MVS		86.78 190	85.76 190	89.82 195	94.37 137	78.41 224	92.47 220	92.83 232	81.11 221	86.36 136	92.40 174	68.73 236	97.48 150	73.75 251	89.85 163	93.57 223

v144192		87.19 183	86.35 174	89.74 199	90.64 265	78.24 229	93.92 158	95.43 147	81.93 205	85.51 161	91.05 227	74.21 158	97.45 154	82.86 139	81.56 256	93.53 224

v1921920		86.97 187	86.06 184	89.69 202	90.53 270	78.11 232	93.80 164	95.43 147	81.90 207	85.33 175	91.05 227	72.66 180	97.41 170	82.05 153	81.80 251	93.53 224

v1192		87.25 179	86.33 175	90.00 191	90.76 260	79.04 208	93.80 164	95.48 139	82.57 194	85.48 163	91.18 221	73.38 173	97.42 165	82.30 149	82.06 243	93.53 224

tpmvs		83.35 251	82.07 248	87.20 269	91.07 246	71.00 295	88.31 283	91.70 259	78.91 237	80.49 250	87.18 283	69.30 224	97.08 199	68.12 286	83.56 229	93.51 227

v1240		86.78 190	85.85 188	89.56 204	90.45 271	77.79 240	93.61 178	95.37 152	81.65 211	85.43 168	91.15 223	71.50 193	97.43 163	81.47 162	82.05 245	93.47 228

v1144		87.61 168	86.79 158	90.06 187	91.01 247	79.34 196	93.95 157	95.42 149	83.36 169	85.66 155	91.31 215	74.98 150	97.42 165	83.37 133	82.06 243	93.42 229

v7		87.75 155	86.96 151	90.12 179	91.20 239	79.50 179	94.28 133	95.46 140	83.45 165	85.75 148	91.56 207	75.13 146	97.43 163	83.60 132	82.18 242	93.42 229

v148		87.04 186	86.32 176	89.21 215	90.94 252	77.26 247	93.71 173	94.43 194	84.84 133	84.36 194	90.80 230	76.04 128	97.05 202	82.12 151	79.60 282	93.31 231

AllTest		83.42 248	81.39 252	89.52 206	95.01 111	77.79 240	93.12 197	90.89 283	77.41 254	76.12 283	93.34 138	54.08 307	97.51 148	68.31 283	84.27 221	93.26 232

TestCases				89.52 206	95.01 111	77.79 240		90.89 283	77.41 254	76.12 283	93.34 138	54.08 307	97.51 148	68.31 283	84.27 221	93.26 232

DTE-MVSNet		86.11 202	85.48 196	87.98 250	91.65 210	74.92 263	94.93 86	95.75 118	87.36 84	82.26 225	93.04 153	72.85 177	95.82 255	74.04 247	77.46 289	93.20 234

SixPastTwentyTwo		83.91 244	82.90 243	86.92 272	90.99 248	70.67 297	93.48 182	91.99 252	85.54 119	77.62 271	92.11 185	60.59 284	96.87 214	76.05 232	77.75 287	93.20 234

WR-MVS_H		87.80 154	87.37 136	89.10 219	93.23 174	78.12 231	95.61 52	97.30 16	87.90 72	83.72 206	92.01 191	79.65 92	96.01 247	76.36 227	80.54 270	93.16 236

OurMVSNet-221017-0		85.35 216	84.64 214	87.49 260	90.77 259	72.59 283	94.01 154	94.40 195	84.72 136	79.62 260	93.17 147	61.91 275	96.72 216	81.99 154	81.16 257	93.16 236

gg-mvs-nofinetune		81.77 260	79.37 270	88.99 220	90.85 258	77.73 243	86.29 296	79.63 335	74.88 277	83.19 217	69.05 327	60.34 285	96.11 243	75.46 235	94.64 98	93.11 238

MSDG		84.86 229	83.09 240	90.14 178	93.80 159	80.05 167	89.18 274	93.09 228	78.89 238	78.19 265	91.91 193	65.86 259	97.27 183	68.47 281	88.45 184	93.11 238

v7n		86.81 188	85.76 190	89.95 192	90.72 262	79.25 202	95.07 78	95.92 104	84.45 143	82.29 224	90.86 229	72.60 182	97.53 147	79.42 201	80.52 272	93.08 240

ACMH	80.38 17	85.36 215	83.68 227	90.39 164	94.45 135	80.63 155	94.73 98	94.85 182	82.09 200	77.24 273	92.65 168	60.01 288	97.58 143	72.25 257	84.87 216	92.96 241
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lessismore_v0				86.04 280	88.46 296	68.78 306		80.59 333		73.01 302	90.11 244	55.39 302	96.43 232	75.06 240	65.06 320	92.90 242

V42		87.68 157	86.86 153	90.15 177	90.58 266	80.14 164	94.24 135	95.28 155	83.66 157	85.67 154	91.33 212	74.73 151	97.41 170	84.43 123	81.83 250	92.89 243

XVG-ACMP-BASELINE		86.00 204	84.84 209	89.45 209	91.20 239	78.00 233	91.70 240	95.55 131	85.05 130	82.97 218	92.25 181	54.49 305	97.48 150	82.93 138	87.45 196	92.89 243

v748		86.27 200	85.28 200	89.25 214	90.26 274	77.58 246	94.89 88	95.50 138	84.28 147	81.41 238	90.46 239	72.57 183	97.32 178	79.81 193	78.36 285	92.84 245

v8		87.50 172	86.71 161	89.89 193	91.37 223	79.40 192	94.50 112	95.38 150	84.81 134	83.60 210	91.33 212	76.05 126	97.42 165	82.84 140	80.51 273	92.84 245

pm-mvs1		86.61 194	85.54 192	89.82 195	91.44 214	80.18 162	95.28 67	94.85 182	83.84 152	81.66 235	92.62 169	72.45 186	96.48 228	79.67 195	78.06 286	92.82 247

K. test v3		81.59 263	80.15 264	85.91 282	89.89 283	69.42 304	92.57 217	87.71 317	85.56 118	73.44 299	89.71 250	55.58 300	95.52 264	77.17 222	69.76 314	92.78 248

anonymousdsp		87.84 150	87.09 145	90.12 179	89.13 288	80.54 158	94.67 105	95.55 131	82.05 201	83.82 204	92.12 183	71.47 194	97.15 193	87.15 93	87.80 194	92.67 249

semantic-postprocess				88.18 247	91.71 207	76.87 251		92.65 238	85.40 122	81.44 237	90.54 236	66.21 254	95.00 285	81.04 165	81.05 260	92.66 250

v10		87.25 179	86.38 173	89.85 194	91.19 241	79.50 179	94.48 113	95.45 144	83.79 155	83.62 209	91.19 220	75.13 146	97.42 165	81.94 155	80.60 268	92.63 251

ACMH+	81.04 14	85.05 222	83.46 234	89.82 195	94.66 127	79.37 194	94.44 118	94.12 205	82.19 199	78.04 267	92.82 163	58.23 294	97.54 146	73.77 250	82.90 235	92.54 252

pmmvs5		84.21 241	82.84 245	88.34 242	88.95 291	76.94 250	92.41 221	91.91 257	75.63 269	80.28 251	91.18 221	64.59 264	95.57 262	77.09 224	83.47 230	92.53 253

IterMVS		84.88 228	83.98 220	87.60 256	91.44 214	76.03 258	90.18 258	92.41 241	83.24 172	81.06 243	90.42 240	66.60 249	94.28 290	79.46 197	80.98 265	92.48 254
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS		87.44 173	86.10 182	91.44 126	92.61 190	83.62 85	92.63 214	95.66 124	67.26 315	81.47 236	92.15 182	77.95 106	98.22 101	79.71 194	95.48 85	92.47 255

testgi		80.94 273	80.20 263	83.18 297	87.96 302	66.29 312	91.28 247	90.70 288	83.70 156	78.12 266	92.84 161	51.37 311	90.82 315	63.34 301	82.46 239	92.43 256

JIA-IIPM		81.04 270	78.98 276	87.25 265	88.64 293	73.48 273	81.75 320	89.61 306	73.19 287	82.05 230	73.71 324	66.07 258	95.87 253	71.18 263	84.60 218	92.41 257

BH-w/o		87.57 170	87.05 149	89.12 217	94.90 118	77.90 236	92.41 221	93.51 223	82.89 188	83.70 207	91.34 211	75.75 139	97.07 200	75.49 234	93.49 117	92.39 258

PMMVS		85.71 212	84.96 205	87.95 251	88.90 292	77.09 248	88.68 279	90.06 297	72.32 295	86.47 131	90.76 231	72.15 187	94.40 289	81.78 159	93.49 117	92.36 259

PVSNet_BlendedMVS		89.98 91	89.70 85	90.82 146	96.12 76	81.25 137	93.92 158	96.83 45	83.49 164	89.10 90	92.26 180	81.04 76	98.85 71	86.72 101	87.86 193	92.35 260

Patchmtry		82.71 254	80.93 257	88.06 249	90.05 279	76.37 255	84.74 306	91.96 255	72.28 296	81.32 240	87.87 276	71.03 198	95.50 267	68.97 279	80.15 275	92.32 261

PatchMatch-RL		86.77 192	85.54 192	90.47 162	95.88 87	82.71 112	90.54 253	92.31 242	79.82 231	84.32 195	91.57 206	68.77 235	96.39 233	73.16 253	93.48 119	92.32 261

pmmvs6		83.42 248	81.60 251	88.87 221	88.01 301	77.87 238	94.96 83	94.24 200	74.67 278	78.80 263	91.09 226	60.17 287	96.49 227	77.06 225	75.40 294	92.23 263

DSMNet-mixed		76.94 287	76.29 286	78.89 304	83.10 317	56.11 329	87.78 287	79.77 334	60.65 325	75.64 289	88.71 261	61.56 277	88.34 320	60.07 311	89.29 172	92.21 264

CHOSEN 280x420		85.15 220	83.99 219	88.65 226	92.47 191	78.40 225	79.68 324	92.76 234	74.90 276	81.41 238	89.59 251	69.85 216	95.51 265	79.92 189	95.29 90	92.03 265

UnsupCasMVSNet_eth		80.07 276	78.27 278	85.46 285	85.24 310	72.63 282	88.45 282	94.87 181	82.99 184	71.64 308	88.07 272	56.34 299	91.75 312	73.48 252	63.36 325	92.01 266

test0.0.03 1		82.41 257	81.69 250	84.59 291	88.23 297	72.89 276	90.24 256	87.83 316	83.41 166	79.86 257	89.78 249	67.25 245	88.99 318	65.18 296	83.42 232	91.90 267

pmmvs4		85.43 214	83.86 221	90.16 173	90.02 280	82.97 103	90.27 255	92.67 237	75.93 267	80.73 245	91.74 198	71.05 197	95.73 259	78.85 205	83.46 231	91.78 268

V4		86.50 196	85.54 192	89.39 210	89.13 288	78.99 209	94.73 98	95.54 133	83.59 158	82.10 228	90.61 234	71.60 190	97.45 154	82.52 143	80.01 277	91.74 269

v52		86.50 196	85.53 195	89.39 210	89.17 287	78.99 209	94.72 101	95.54 133	83.59 158	82.10 228	90.60 235	71.59 191	97.45 154	82.52 143	79.99 278	91.73 270

LTVRE_ROB	82.13 13	86.26 201	84.90 207	90.34 169	94.44 136	81.50 129	92.31 225	94.89 180	83.03 180	79.63 259	92.67 167	69.69 217	97.79 133	71.20 261	86.26 205	91.72 271
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
COLMAP_ROB	80.39 16	83.96 243	82.04 249	89.74 199	95.28 105	79.75 176	94.25 134	92.28 243	75.17 272	78.02 268	93.77 133	58.60 293	97.84 132	65.06 297	85.92 206	91.63 272
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FMVSNet5		81.52 265	79.60 269	87.27 263	91.17 242	77.95 234	91.49 244	92.26 244	76.87 259	76.16 282	87.91 275	51.67 310	92.34 307	67.74 287	81.16 257	91.52 273

ITE_SJBPF				88.24 245	91.88 201	77.05 249		92.92 230	85.54 119	80.13 255	93.30 142	57.29 297	96.20 240	72.46 256	84.71 217	91.49 274

MDA-MVSNet-bldmvs		78.85 284	76.31 285	86.46 277	89.76 284	73.88 270	88.79 277	90.42 289	79.16 236	59.18 324	88.33 269	60.20 286	94.04 292	62.00 305	68.96 316	91.48 275

MIMVSNet1		79.38 281	77.28 281	85.69 283	86.35 307	73.67 272	91.61 243	92.75 235	78.11 252	72.64 304	88.12 271	48.16 317	91.97 311	60.32 309	77.49 288	91.43 276

EU-MVSNet		81.32 268	80.95 256	82.42 301	88.50 295	63.67 317	93.32 186	91.33 269	64.02 321	80.57 249	92.83 162	61.21 281	92.27 308	76.34 228	80.38 274	91.32 277

Baseline_NR-MVSNet		87.07 185	86.63 170	88.40 240	91.44 214	77.87 238	94.23 136	92.57 239	84.12 149	85.74 150	92.08 187	77.25 111	96.04 244	82.29 150	79.94 279	91.30 278

TransMVSNet (Re)		84.43 240	83.06 241	88.54 236	91.72 206	78.44 223	95.18 72	92.82 233	82.73 191	79.67 258	92.12 183	73.49 169	95.96 249	71.10 264	68.73 318	91.21 279

YYNet1		79.22 282	77.20 282	85.28 287	88.20 299	72.66 281	85.87 299	90.05 299	74.33 281	62.70 322	87.61 278	66.09 257	92.03 309	66.94 288	72.97 298	91.15 280

Anonymous20231206		81.03 271	79.77 267	84.82 290	87.85 304	70.26 300	91.42 245	92.08 248	73.67 283	77.75 270	89.25 255	62.43 272	93.08 304	61.50 307	82.00 246	91.12 281

MDA-MVSNet_test_wron		79.21 283	77.19 283	85.29 286	88.22 298	72.77 279	85.87 299	90.06 297	74.34 280	62.62 323	87.56 279	66.14 256	91.99 310	66.90 291	73.01 297	91.10 282

v18		84.97 224	83.76 222	88.60 230	91.36 224	79.41 188	93.82 163	94.04 206	83.00 183	76.61 276	86.60 285	76.19 120	95.43 270	80.39 178	71.79 303	90.96 283

v17		84.93 227	83.70 226	88.62 228	91.36 224	79.48 182	93.83 161	94.03 208	83.04 179	76.51 278	86.57 287	76.05 126	95.42 271	80.31 183	71.65 304	90.96 283

v16		84.96 225	83.74 224	88.62 228	91.40 219	79.48 182	93.83 161	94.04 206	83.03 180	76.54 277	86.59 286	76.11 125	95.42 271	80.33 181	71.80 302	90.95 285

v15		84.79 230	83.53 231	88.57 234	91.30 235	79.41 188	93.70 174	94.01 209	83.06 176	76.27 279	86.42 291	76.03 129	95.38 273	80.01 185	71.00 307	90.92 286

V14		84.79 230	83.52 232	88.57 234	91.32 231	79.43 187	93.72 172	94.01 209	83.06 176	76.22 280	86.43 288	76.01 130	95.37 274	79.96 187	70.99 308	90.91 287

V9		84.77 232	83.50 233	88.58 231	91.33 229	79.46 184	93.75 168	94.00 212	83.07 175	76.07 285	86.43 288	75.97 131	95.37 274	79.91 190	70.93 310	90.91 287

v12		84.74 233	83.46 234	88.58 231	91.32 231	79.50 179	93.75 168	94.01 209	83.06 176	75.98 287	86.41 292	75.82 137	95.36 276	79.87 191	70.89 311	90.89 289

v13		84.72 235	83.44 236	88.58 231	91.31 234	79.52 178	93.77 166	94.00 212	83.03 180	75.85 288	86.38 293	75.84 136	95.35 277	79.83 192	70.95 309	90.87 290

v11		84.67 238	83.41 237	88.44 239	91.32 231	79.13 207	93.69 177	93.99 214	82.81 189	76.20 281	86.24 295	75.48 142	95.35 277	79.53 196	71.48 306	90.85 291

CMPMVS	59.16 21	80.52 274	79.20 272	84.48 292	83.98 314	67.63 310	89.95 262	93.84 219	64.79 320	66.81 317	91.14 224	57.93 296	95.17 280	76.25 229	88.10 189	90.65 292
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ambc				83.06 298	79.99 323	63.51 318	77.47 327	92.86 231		74.34 296	84.45 301	28.74 332	95.06 284	73.06 254	68.89 317	90.61 293

USDC		82.76 253	81.26 254	87.26 264	91.17 242	74.55 264	89.27 271	93.39 225	78.26 249	75.30 290	92.08 187	54.43 306	96.63 219	71.64 258	85.79 209	90.61 293

GG-mvs-BLEND				87.94 252	89.73 285	77.91 235	87.80 286	78.23 337		80.58 248	83.86 303	59.88 289	95.33 279	71.20 261	92.22 137	90.60 295

tfpnnormal		84.72 235	83.23 239	89.20 216	92.79 187	80.05 167	94.48 113	95.81 113	82.38 196	81.08 242	91.21 219	69.01 228	96.95 209	61.69 306	80.59 269	90.58 296

N_pmnet		68.89 300	68.44 301	70.23 316	89.07 290	28.79 344	88.06 284	19.50 346	69.47 309	71.86 307	84.93 300	61.24 280	91.75 312	54.70 316	77.15 290	90.15 297

test20.03		79.95 277	79.08 274	82.55 300	85.79 308	67.74 309	91.09 252	91.08 276	81.23 220	74.48 295	89.96 247	61.63 276	90.15 316	60.08 310	76.38 291	89.76 298

TDRefinement		79.81 278	77.34 280	87.22 268	79.24 326	75.48 262	93.12 197	92.03 250	76.45 260	75.01 291	91.58 204	49.19 316	96.44 231	70.22 268	69.18 315	89.75 299

LP		75.51 290	72.15 294	85.61 284	87.86 303	73.93 269	80.20 323	88.43 313	67.39 312	70.05 309	80.56 317	58.18 295	93.18 303	46.28 328	70.36 313	89.71 300

EG-PatchMatch MVS		82.37 258	80.34 260	88.46 238	90.27 273	79.35 195	92.80 210	94.33 198	77.14 258	73.26 301	90.18 243	47.47 319	96.72 216	70.25 266	87.32 199	89.30 301

pmmvs-eth3d		80.97 272	78.72 277	87.74 253	84.99 312	79.97 171	90.11 259	91.65 261	75.36 270	73.51 298	86.03 296	59.45 290	93.96 293	75.17 238	72.21 300	89.29 302

MVP-Stereo		85.97 205	84.86 208	89.32 212	90.92 254	82.19 120	92.11 232	94.19 201	78.76 242	78.77 264	91.63 202	68.38 242	96.56 223	75.01 241	93.95 109	89.20 303
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
new-patchmatchnet		76.41 288	75.17 288	80.13 303	82.65 320	59.61 322	87.66 289	91.08 276	78.23 250	69.85 310	83.22 307	54.76 304	91.63 314	64.14 300	64.89 321	89.16 304

MS-PatchMatch		85.05 222	84.16 216	87.73 254	91.42 218	78.51 221	91.25 249	93.53 222	77.50 253	80.15 253	91.58 204	61.99 274	95.51 265	75.69 233	94.35 107	89.16 304

UnsupCasMVSNet_bld		76.23 289	73.27 291	85.09 289	83.79 315	72.92 275	85.65 303	93.47 224	71.52 299	68.84 312	79.08 320	49.77 313	93.21 301	66.81 292	60.52 327	89.13 306

testus		74.41 292	73.35 290	77.59 309	82.49 321	57.08 325	86.02 297	90.21 293	72.28 296	72.89 303	84.32 302	37.08 328	86.96 324	52.24 318	82.65 237	88.73 307

PM-MVS		78.11 285	76.12 287	84.09 296	83.54 316	70.08 301	88.97 276	85.27 325	79.93 229	74.73 293	86.43 288	34.70 330	93.48 298	79.43 200	72.06 301	88.72 308

LF4IMVS		80.37 275	79.07 275	84.27 295	86.64 306	69.87 303	89.39 270	91.05 278	76.38 261	74.97 292	90.00 245	47.85 318	94.25 291	74.55 245	80.82 267	88.69 309

TinyColmap		79.76 279	77.69 279	85.97 281	91.71 207	73.12 274	89.55 265	90.36 291	75.03 273	72.03 306	90.19 242	46.22 321	96.19 241	63.11 302	81.03 261	88.59 310

test2356		74.50 291	73.27 291	78.20 305	80.81 322	59.84 320	83.76 314	88.33 314	71.43 301	72.37 305	81.84 313	45.60 322	86.26 326	50.97 320	84.32 219	88.50 311

test1235678		72.22 295	70.31 296	77.93 308	78.04 327	58.04 324	85.76 301	89.80 304	70.15 308	63.43 321	80.20 318	42.24 325	87.24 323	48.68 324	74.50 295	88.50 311

Anonymous20231211		72.97 294	69.63 299	83.00 299	83.05 318	66.91 311	92.69 212	89.45 307	61.06 324	67.50 315	83.46 306	34.34 331	93.61 297	51.11 319	63.97 323	88.48 313

test_0402		81.30 269	79.17 273	87.67 255	93.19 175	78.17 230	92.98 205	91.71 258	75.25 271	76.02 286	90.31 241	59.23 291	96.37 234	50.22 322	83.63 228	88.47 314

PVSNet_0	73.20 20	77.22 286	74.83 289	84.37 293	90.70 263	71.10 293	83.09 317	89.67 305	72.81 293	73.93 297	83.13 308	60.79 283	93.70 295	68.54 280	50.84 330	88.30 315

OpenMVS_ROB	74.94 19	79.51 280	77.03 284	86.93 271	87.00 305	76.23 257	92.33 224	90.74 287	68.93 310	74.52 294	88.23 270	49.58 314	96.62 220	57.64 314	84.29 220	87.94 316

LCM-MVSNet		66.00 301	62.16 305	77.51 310	64.51 338	58.29 323	83.87 313	90.90 282	48.17 330	54.69 326	73.31 325	16.83 343	86.75 325	65.47 294	61.67 326	87.48 317

1111		70.54 299	69.71 298	73.04 313	79.30 324	44.83 337	84.23 309	88.96 309	67.33 313	65.42 318	82.28 311	41.11 326	88.11 321	47.12 326	71.60 305	86.19 318

testmv		65.49 302	62.66 303	73.96 312	68.78 333	53.14 332	84.70 307	88.56 311	65.94 318	52.35 327	74.65 323	25.02 336	85.14 329	43.54 330	60.40 328	83.60 319

pmmvs3		71.81 297	68.71 300	81.11 302	75.86 328	70.42 299	86.74 293	83.66 327	58.95 326	68.64 314	80.89 316	36.93 329	89.52 317	63.10 303	63.59 324	83.39 320

MVS-HIRNet		73.70 293	72.20 293	78.18 307	91.81 204	56.42 328	82.94 318	82.58 329	55.24 327	68.88 311	66.48 328	55.32 303	95.13 281	58.12 313	88.42 186	83.01 321

new_pmnet		72.15 296	70.13 297	78.20 305	82.95 319	65.68 313	83.91 312	82.40 330	62.94 323	64.47 320	79.82 319	42.85 324	86.26 326	57.41 315	74.44 296	82.65 322

ANet_high		58.88 307	54.22 310	72.86 314	56.50 342	56.67 327	80.75 322	86.00 322	73.09 289	37.39 333	64.63 331	22.17 338	79.49 336	43.51 331	23.96 337	82.43 323

test12356		64.99 303	63.78 302	68.61 320	72.69 330	39.14 340	78.46 325	87.61 319	64.91 319	55.77 325	77.48 321	28.10 333	85.59 328	44.69 329	64.35 322	81.12 324

PMMVS2		59.60 306	56.40 308	69.21 319	68.83 332	46.58 335	73.02 332	77.48 338	55.07 328	49.21 329	72.95 326	17.43 342	80.04 334	49.32 323	44.33 331	80.99 325

no-one		61.56 305	56.58 307	76.49 311	67.80 336	62.76 319	78.13 326	86.11 321	63.16 322	43.24 331	64.70 330	26.12 335	88.95 319	50.84 321	29.15 333	77.77 326

wuykxyi23d		50.55 311	44.13 313	69.81 317	56.77 340	54.58 331	73.22 331	80.78 332	39.79 335	22.08 340	46.69 337	4.03 347	79.71 335	47.65 325	26.13 335	75.14 327

FPMVS		64.63 304	62.55 304	70.88 315	70.80 331	56.71 326	84.42 308	84.42 326	51.78 329	49.57 328	81.61 314	23.49 337	81.48 333	40.61 333	76.25 292	74.46 328

testpf		71.41 298	72.11 295	69.30 318	84.53 313	59.79 321	62.74 334	83.14 328	71.11 303	68.83 313	81.57 315	46.70 320	84.83 331	74.51 246	75.86 293	63.30 329

PNet_i23d		50.48 312	47.18 312	60.36 323	68.59 334	44.56 339	72.75 333	72.61 339	43.92 332	33.91 335	60.19 333	6.16 344	73.52 337	38.50 334	28.04 334	63.01 330

PMVS	47.18 22	52.22 310	48.46 311	63.48 322	45.72 343	46.20 336	73.41 330	78.31 336	41.03 334	30.06 336	65.68 329	6.05 345	83.43 332	30.04 336	65.86 319	60.80 331
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 313	38.59 318	57.77 324	56.52 341	48.77 334	55.38 336	58.64 343	29.33 338	28.96 337	52.65 334	4.68 346	64.62 340	28.11 337	33.07 332	59.93 332
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				56.31 325	74.23 329	51.81 333		56.67 344	44.85 331	48.54 330	75.16 322	27.87 334	58.74 341	40.92 332	52.22 329	58.39 333

Gipuma		57.99 308	54.91 309	67.24 321	88.51 294	65.59 314	52.21 337	90.33 292	43.58 333	42.84 332	51.18 335	20.29 340	85.07 330	34.77 335	70.45 312	51.05 334
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 314	42.29 314	46.03 326	65.58 337	37.41 341	73.51 329	64.62 340	33.99 336	28.47 338	47.87 336	19.90 341	67.91 338	22.23 338	24.45 336	32.77 335

EMVS		42.07 315	41.12 315	44.92 328	63.45 339	35.56 343	73.65 328	63.48 341	33.05 337	26.88 339	45.45 338	21.27 339	67.14 339	19.80 339	23.02 338	32.06 336

tmp_tt		35.64 317	39.24 316	24.84 330	14.87 344	23.90 345	62.71 335	51.51 345	6.58 340	36.66 334	62.08 332	44.37 323	30.34 343	52.40 317	22.00 339	20.27 337

wuyk23d		21.27 319	20.48 320	23.63 331	68.59 334	36.41 342	49.57 338	6.85 347	9.37 339	7.89 341	4.46 344	4.03 347	31.37 342	17.47 340	16.07 340	3.12 338

test123		8.76 321	11.22 322	1.39 332	0.85 346	0.97 346	85.76 301	0.35 349	0.54 342	2.45 343	8.14 343	0.60 349	0.48 344	2.16 342	0.17 343	2.71 339

.test1245		57.63 309	61.79 306	45.14 327	79.30 324	44.83 337	84.23 309	88.96 309	67.33 313	65.42 318	82.28 311	41.11 326	88.11 321	47.12 326	0.39 341	2.46 340

testmvs		8.92 320	11.52 321	1.12 333	1.06 345	0.46 347	86.02 297	0.65 348	0.62 341	2.74 342	9.52 342	0.31 350	0.45 345	2.38 341	0.39 341	2.46 340

cdsmvs_eth3d_5k		22.14 318	29.52 319	0.00 334	0.00 347	0.00 348	0.00 339	95.76 117	0.00 343	0.00 344	94.29 111	75.66 140	0.00 346	0.00 343	0.00 344	0.00 342

pcd_1.5k_mvsjas		6.64 323	8.86 324	0.00 334	0.00 347	0.00 348	0.00 339	0.00 350	0.00 343	0.00 344	0.00 345	79.70 88	0.00 346	0.00 343	0.00 344	0.00 342

sosnet-low-res		0.00 324	0.00 325	0.00 334	0.00 347	0.00 348	0.00 339	0.00 350	0.00 343	0.00 344	0.00 345	0.00 351	0.00 346	0.00 343	0.00 344	0.00 342

sosnet		0.00 324	0.00 325	0.00 334	0.00 347	0.00 348	0.00 339	0.00 350	0.00 343	0.00 344	0.00 345	0.00 351	0.00 346	0.00 343	0.00 344	0.00 342

uncertanet		0.00 324	0.00 325	0.00 334	0.00 347	0.00 348	0.00 339	0.00 350	0.00 343	0.00 344	0.00 345	0.00 351	0.00 346	0.00 343	0.00 344	0.00 342

Regformer		0.00 324	0.00 325	0.00 334	0.00 347	0.00 348	0.00 339	0.00 350	0.00 343	0.00 344	0.00 345	0.00 351	0.00 346	0.00 343	0.00 344	0.00 342

ab-mvs-re		7.82 322	10.43 323	0.00 334	0.00 347	0.00 348	0.00 339	0.00 350	0.00 343	0.00 344	93.88 129	0.00 351	0.00 346	0.00 343	0.00 344	0.00 342

uanet		0.00 324	0.00 325	0.00 334	0.00 347	0.00 348	0.00 339	0.00 350	0.00 343	0.00 344	0.00 345	0.00 351	0.00 346	0.00 343	0.00 344	0.00 342

ESAPD								97.46 6

sam_mvs1												71.70 189

sam_mvs												70.60 204

MTGPA								96.97 33

test_post1							88.00 285				9.81 341	69.31 223	95.53 263	76.65 226

test_post											10.29 340	70.57 208	95.91 252

patchmatchnet-post											83.76 304	71.53 192	96.48 228

MTMP								60.64 342

gm-plane-assit					89.60 286	68.00 307			77.28 257		88.99 257		97.57 144	79.44 199

TEST9					97.53 34	86.49 27	94.07 147	96.78 49	81.61 214	92.77 38	96.20 57	87.71 13	99.12 39

test_8					97.49 37	86.30 35	94.02 153	96.76 52	81.86 209	92.70 42	96.20 57	87.63 14	99.02 51

agg_prior					97.38 41	85.92 42		96.72 55		92.16 54			98.97 59

test_prior4						85.96 41	94.11 141

test_prior2							94.12 139		87.67 79	92.63 43	96.39 50	86.62 23		91.50 47	98.67 24

旧先验2							93.36 185		71.25 302	94.37 11			97.13 196	86.74 98

新几何2							93.11 199

原ACMM2							92.94 207

testdata2													98.75 76	78.30 210

segment_acmp												87.16 19

testdata1							92.15 230		87.94 70

plane_prior7					94.70 125	82.74 109

plane_prior6					94.52 131	82.75 107						74.23 156

plane_prior4											94.86 95

plane_prior3						82.75 107			90.26 25	86.91 125

plane_prior2							95.85 40		90.81 18

plane_prior1					94.59 129

plane_prior						82.73 110	95.21 71		89.66 35						89.88 162

n2								0.00 350

nn								0.00 350

door-mid								85.49 323

test11								96.57 69

door								85.33 324

HQP5-MVS						81.56 127

HQP-NCC					94.17 142		94.39 123		88.81 50	85.43 168

ACMP_Plane					94.17 142		94.39 123		88.81 50	85.43 168

BP-MVS														87.11 95

HQP3-MVS								96.04 98							89.77 164

HQP2-MVS												73.83 165

NP-MVS					94.37 137	82.42 117					93.98 122

MDTV_nov1_ep13			83.56 230		91.69 209	69.93 302	87.75 288	91.54 265	78.60 244	84.86 181	88.90 258	69.54 219	96.03 245	70.25 266	88.93 177

ACMMP++_ref															87.47 195

ACMMP++															88.01 192

Test By Simon												80.02 83

High-resolution multi-view benchmark