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.

DROMVSNet		98.21 57	98.11 49	98.49 98	98.34 171	97.26 100	99.61 3	98.43 183	96.78 61	98.87 50	98.84 113	93.72 104	99.01 206	98.91 1	99.50 92	99.19 140

APDe-MVS		99.02 4	98.84 3	99.55 9	99.57 35	98.96 16	99.39 8	98.93 38	97.38 28	99.41 13	99.54 1	96.66 16	99.84 56	98.86 2	99.85 3	99.87 1

CANet		98.05 58	97.76 65	98.90 74	98.73 138	97.27 96	98.35 186	98.78 98	97.37 30	97.72 125	98.96 99	91.53 143	99.92 24	98.79 3	99.65 62	99.51 96

Regformer-4		98.64 15	98.53 12	98.99 66	99.43 59	97.37 92	98.40 181	98.79 95	97.46 22	99.09 34	99.31 37	95.86 45	99.80 83	98.64 4	99.76 34	99.79 12

VDD-MVS		95.82 163	95.23 174	97.61 163	98.84 132	93.98 239	98.68 138	97.40 302	95.02 144	97.95 110	99.34 33	74.37 354	99.78 99	98.64 4	96.80 192	99.08 157

EI-MVSNet-Vis-set		98.47 39	98.39 20	98.69 81	99.46 53	96.49 131	98.30 197	98.69 121	97.21 41	98.84 51	99.36 28	95.41 57	99.78 99	98.62 6	99.65 62	99.80 11

Regformer-3		98.59 21	98.50 15	98.86 76	99.43 59	97.05 106	98.40 181	98.68 124	97.43 24	99.06 35	99.31 37	95.80 46	99.77 104	98.62 6	99.76 34	99.78 15

CS-MVS		97.94 64	97.90 60	98.06 130	98.04 198	96.85 115	99.04 58	98.39 191	96.17 86	98.50 75	98.29 174	94.60 85	99.02 203	98.61 8	99.43 101	98.30 205

EI-MVSNet-UG-set		98.41 42	98.34 29	98.61 86	99.45 57	96.32 140	98.28 200	98.68 124	97.17 44	98.74 58	99.37 24	95.25 69	99.79 95	98.57 9	99.54 88	99.73 40

CHOSEN 280x420		97.18 109	97.18 92	97.20 180	98.81 134	93.27 266	95.78 342	99.15 18	95.25 130	96.79 165	98.11 189	92.29 120	99.07 194	98.56 10	99.85 3	99.25 134

MSC_two_6792asdad				99.62 6	99.17 100	99.08 11		98.63 142					99.94 3	98.53 11	99.80 17	99.86 2

No_MVS				99.62 6	99.17 100	99.08 11		98.63 142					99.94 3	98.53 11	99.80 17	99.86 2

xiu_mvs_v1_base_debu		97.60 81	97.56 72	97.72 152	98.35 166	95.98 150	97.86 249	98.51 166	97.13 47	99.01 39	98.40 158	91.56 139	99.80 83	98.53 11	98.68 136	97.37 231

xiu_mvs_v1_base		97.60 81	97.56 72	97.72 152	98.35 166	95.98 150	97.86 249	98.51 166	97.13 47	99.01 39	98.40 158	91.56 139	99.80 83	98.53 11	98.68 136	97.37 231

xiu_mvs_v1_base_debi		97.60 81	97.56 72	97.72 152	98.35 166	95.98 150	97.86 249	98.51 166	97.13 47	99.01 39	98.40 158	91.56 139	99.80 83	98.53 11	98.68 136	97.37 231

VNet		97.79 72	97.40 84	98.96 70	98.88 127	97.55 86	98.63 147	98.93 38	96.74 64	99.02 38	98.84 113	90.33 167	99.83 59	98.53 11	96.66 196	99.50 98

MSLP-MVS++		98.56 29	98.57 9	98.55 90	99.26 87	96.80 116	98.71 131	99.05 24	97.28 34	98.84 51	99.28 42	96.47 21	99.40 161	98.52 17	99.70 55	99.47 105

TSAR-MVS + GP.		98.38 44	98.24 42	98.81 77	99.22 96	97.25 101	98.11 225	98.29 212	97.19 43	98.99 42	99.02 86	96.22 23	99.67 125	98.52 17	98.56 144	99.51 96

DVP-MVS++		99.08 2	98.89 2	99.64 3	99.17 100	99.23 7	99.69 1	98.88 50	97.32 31	99.53 9	99.47 8	97.81 3	99.94 3	98.47 19	99.72 52	99.74 35

DVP-MVS		99.03 3	98.83 4	99.63 4	99.72 13	99.25 2	98.97 76	98.58 152	97.62 11	99.45 11	99.46 11	97.42 9	99.94 3	98.47 19	99.81 10	99.69 55
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									97.32 31	99.45 11	99.46 11	97.88 1	99.94 3	98.47 19	99.86 1	99.85 4

test_0728_SECOND				99.71 1	99.72 13	99.35 1	98.97 76	98.88 50					99.94 3	98.47 19	99.81 10	99.84 6

SED-MVS		99.09 1	98.91 1	99.63 4	99.71 21	99.24 5	99.02 66	98.87 57	97.65 9	99.73 1	99.48 6	97.53 7	99.94 3	98.43 23	99.81 10	99.70 52

test_241102_TWO								98.87 57	97.65 9	99.53 9	99.48 6	97.34 11	99.94 3	98.43 23	99.80 17	99.83 7

Regformer-1		98.66 13	98.51 14	99.12 60	99.35 62	97.81 79	98.37 183	98.76 102	97.49 18	99.20 25	99.21 53	96.08 32	99.79 95	98.42 25	99.73 45	99.75 30

DELS-MVS		98.40 43	98.20 45	98.99 66	99.00 117	97.66 81	97.75 258	98.89 47	97.71 8	98.33 87	98.97 93	94.97 77	99.88 46	98.42 25	99.76 34	99.42 115
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		98.69 12	98.52 13	99.19 46	99.35 62	98.01 67	98.37 183	98.81 79	97.48 19	99.21 24	99.21 53	96.13 30	99.80 83	98.40 27	99.73 45	99.75 30

alignmvs		97.56 87	97.07 97	99.01 65	98.66 147	98.37 46	98.83 103	98.06 257	96.74 64	98.00 108	97.65 230	90.80 158	99.48 155	98.37 28	96.56 200	99.19 140

IU-MVS					99.71 21	99.23 7		98.64 140	95.28 128	99.63 4				98.35 29	99.81 10	99.83 7

TSAR-MVS + MP.		98.78 7	98.62 8	99.24 43	99.69 26	98.28 53	99.14 41	98.66 135	96.84 59	99.56 6	99.31 37	96.34 22	99.70 118	98.32 30	99.73 45	99.73 40
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DeepPCF-MVS	96.37 2	97.93 66	98.48 18	96.30 252	99.00 117	89.54 325	97.43 276	98.87 57	98.16 2	99.26 21	99.38 23	96.12 31	99.64 129	98.30 31	99.77 28	99.72 44

canonicalmvs		97.67 77	97.23 90	98.98 68	98.70 143	98.38 40	99.34 15	98.39 191	96.76 63	97.67 128	97.40 251	92.26 121	99.49 151	98.28 32	96.28 212	99.08 157

SD-MVS		98.64 15	98.68 6	98.53 94	99.33 67	98.36 47	98.90 87	98.85 67	97.28 34	99.72 3	99.39 16	96.63 18	97.60 330	98.17 33	99.85 3	99.64 74
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
diffmvs		97.58 85	97.40 84	98.13 123	98.32 175	95.81 168	98.06 228	98.37 195	96.20 85	98.74 58	98.89 107	91.31 148	99.25 170	98.16 34	98.52 145	99.34 119

casdiffmvs		97.63 80	97.41 83	98.28 111	98.33 173	96.14 147	98.82 106	98.32 202	96.38 79	97.95 110	99.21 53	91.23 150	99.23 173	98.12 35	98.37 153	99.48 103

baseline		97.64 79	97.44 82	98.25 115	98.35 166	96.20 144	99.00 70	98.32 202	96.33 81	98.03 100	99.17 61	91.35 146	99.16 179	98.10 36	98.29 158	99.39 116

MP-MVS-pluss		98.31 53	97.92 59	99.49 12	99.72 13	98.88 18	98.43 177	98.78 98	94.10 177	97.69 127	99.42 14	95.25 69	99.92 24	98.09 37	99.80 17	99.67 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CS-MVS-test		97.90 67	97.83 62	98.11 126	98.14 190	96.49 131	99.35 13	98.40 188	96.31 82	98.27 90	98.31 171	94.42 94	99.05 195	98.07 38	99.20 113	98.80 177

SMA-MVS		98.58 24	98.25 39	99.56 8	99.51 41	99.04 15	98.95 80	98.80 90	93.67 207	99.37 16	99.52 3	96.52 20	99.89 38	98.06 39	99.81 10	99.76 28
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
CNVR-MVS		98.78 7	98.56 10	99.45 17	99.32 70	98.87 19	98.47 171	98.81 79	97.72 6	98.76 57	99.16 66	97.05 13	99.78 99	98.06 39	99.66 61	99.69 55

MVS_111021_HR		98.47 39	98.34 29	98.88 75	99.22 96	97.32 93	97.91 242	99.58 3	97.20 42	98.33 87	99.00 91	95.99 38	99.64 129	98.05 41	99.76 34	99.69 55

VDDNet		95.36 187	94.53 204	97.86 140	98.10 193	95.13 193	98.85 99	97.75 274	90.46 307	98.36 84	99.39 16	73.27 356	99.64 129	97.98 42	96.58 199	98.81 176

h-mvs33		96.17 146	95.62 157	97.81 145	99.03 113	94.45 224	98.64 146	98.75 105	97.48 19	98.67 63	98.72 127	89.76 174	99.86 52	97.95 43	81.59 350	99.11 152

hse-mvs2		95.71 167	95.30 172	96.93 198	98.50 158	93.53 256	98.36 185	98.10 243	97.48 19	98.67 63	97.99 198	89.76 174	99.02 203	97.95 43	80.91 354	98.22 207

MCST-MVS		98.65 14	98.37 22	99.48 13	99.60 33	98.87 19	98.41 180	98.68 124	97.04 51	98.52 74	98.80 118	96.78 15	99.83 59	97.93 45	99.61 71	99.74 35

zzz-MVS		98.55 31	98.25 39	99.46 15	99.76 2	98.64 27	98.55 161	98.74 107	97.27 38	98.02 102	99.39 16	94.81 80	99.96 1	97.91 46	99.79 21	99.77 22

MTAPA		98.58 24	98.29 36	99.46 15	99.76 2	98.64 27	98.90 87	98.74 107	97.27 38	98.02 102	99.39 16	94.81 80	99.96 1	97.91 46	99.79 21	99.77 22

MVS_111021_LR		98.34 49	98.23 43	98.67 83	99.27 85	96.90 112	97.95 238	99.58 3	97.14 46	98.44 80	99.01 90	95.03 76	99.62 134	97.91 46	99.75 40	99.50 98

ACMMP_NAP		98.61 18	98.30 35	99.55 9	99.62 32	98.95 17	98.82 106	98.81 79	95.80 100	99.16 30	99.47 8	95.37 60	99.92 24	97.89 49	99.75 40	99.79 12

PS-MVSNAJ		97.73 74	97.77 64	97.62 162	98.68 146	95.58 173	97.34 285	98.51 166	97.29 33	98.66 67	97.88 209	94.51 88	99.90 36	97.87 50	99.17 116	97.39 229

test1172		98.56 29	98.35 25	99.16 53	99.53 38	97.94 71	99.09 51	98.83 71	96.52 73	99.05 36	99.34 33	95.34 62	99.82 67	97.86 51	99.64 66	99.73 40

XVS		98.70 10	98.49 17	99.34 26	99.70 24	98.35 48	99.29 19	98.88 50	97.40 25	98.46 76	99.20 57	95.90 43	99.89 38	97.85 52	99.74 43	99.78 15

X-MVStestdata		94.06 271	92.30 291	99.34 26	99.70 24	98.35 48	99.29 19	98.88 50	97.40 25	98.46 76	43.50 371	95.90 43	99.89 38	97.85 52	99.74 43	99.78 15

xiu_mvs_v2_base		97.66 78	97.70 67	97.56 166	98.61 152	95.46 179	97.44 274	98.46 176	97.15 45	98.65 68	98.15 186	94.33 95	99.80 83	97.84 54	98.66 140	97.41 227

DeepC-MVS	95.98 3	97.88 68	97.58 70	98.77 78	99.25 88	96.93 110	98.83 103	98.75 105	96.96 55	96.89 159	99.50 4	90.46 164	99.87 47	97.84 54	99.76 34	99.52 92
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSP-MVS		98.74 9	98.55 11	99.29 34	99.75 4	98.23 54	99.26 23	98.88 50	97.52 16	99.41 13	98.78 120	96.00 37	99.79 95	97.79 56	99.59 75	99.85 4
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
CP-MVS		98.57 27	98.36 23	99.19 46	99.66 28	97.86 73	99.34 15	98.87 57	95.96 95	98.60 71	99.13 70	96.05 35	99.94 3	97.77 57	99.86 1	99.77 22

SteuartSystems-ACMMP		98.90 6	98.75 5	99.36 24	99.22 96	98.43 38	99.10 50	98.87 57	97.38 28	99.35 17	99.40 15	97.78 5	99.87 47	97.77 57	99.85 3	99.78 15
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS_3200maxsize		98.53 35	98.33 33	99.15 56	99.50 43	97.92 72	99.15 40	98.81 79	96.24 83	99.20 25	99.37 24	95.30 65	99.80 83	97.73 59	99.67 58	99.72 44

SR-MVS-dyc-post		98.54 33	98.35 25	99.13 57	99.49 47	97.86 73	99.11 47	98.80 90	96.49 74	99.17 28	99.35 30	95.34 62	99.82 67	97.72 60	99.65 62	99.71 48

RE-MVS-def			98.34 29		99.49 47	97.86 73	99.11 47	98.80 90	96.49 74	99.17 28	99.35 30	95.29 66		97.72 60	99.65 62	99.71 48

xxxxxxxxxxxxxcwj		98.70 10	98.50 15	99.30 33	99.46 53	98.38 40	98.21 206	98.52 163	97.95 3	99.32 18	99.39 16	96.22 23	99.84 56	97.72 60	99.73 45	99.67 65

SF-MVS		98.59 21	98.32 34	99.41 19	99.54 37	98.71 22	99.04 58	98.81 79	95.12 137	99.32 18	99.39 16	96.22 23	99.84 56	97.72 60	99.73 45	99.67 65

LFMVS		95.86 160	94.98 186	98.47 100	98.87 128	96.32 140	98.84 102	96.02 340	93.40 217	98.62 69	99.20 57	74.99 350	99.63 132	97.72 60	97.20 186	99.46 109

SR-MVS		98.57 27	98.35 25	99.24 43	99.53 38	98.18 58	99.09 51	98.82 73	96.58 70	99.10 33	99.32 35	95.39 58	99.82 67	97.70 65	99.63 68	99.72 44

PHI-MVS		98.34 49	98.06 51	99.18 50	99.15 106	98.12 63	99.04 58	99.09 20	93.32 220	98.83 53	99.10 75	96.54 19	99.83 59	97.70 65	99.76 34	99.59 85

HPM-MVS		98.36 46	98.10 50	99.13 57	99.74 8	97.82 77	99.53 4	98.80 90	94.63 162	98.61 70	98.97 93	95.13 73	99.77 104	97.65 67	99.83 9	99.79 12
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DPE-MVS		98.92 5	98.67 7	99.65 2	99.58 34	99.20 9	98.42 179	98.91 44	97.58 14	99.54 8	99.46 11	97.10 12	99.94 3	97.64 68	99.84 8	99.83 7
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ETV-MVS		97.96 60	97.81 63	98.40 106	98.42 162	97.27 96	98.73 126	98.55 157	96.84 59	98.38 83	97.44 248	95.39 58	99.35 164	97.62 69	98.89 127	98.58 194

HFP-MVS		98.63 17	98.40 19	99.32 31	99.72 13	98.29 51	99.23 26	98.96 32	96.10 92	98.94 43	99.17 61	96.06 33	99.92 24	97.62 69	99.78 25	99.75 30

ACMMPR		98.59 21	98.36 23	99.29 34	99.74 8	98.15 61	99.23 26	98.95 34	96.10 92	98.93 47	99.19 60	95.70 47	99.94 3	97.62 69	99.79 21	99.78 15

jason		97.32 102	97.08 96	98.06 130	97.45 241	95.59 172	97.87 248	97.91 268	94.79 153	98.55 73	98.83 115	91.12 151	99.23 173	97.58 72	99.60 72	99.34 119
jason: jason.
lupinMVS		97.44 94	97.22 91	98.12 125	98.07 194	95.76 169	97.68 262	97.76 273	94.50 167	98.79 54	98.61 136	92.34 118	99.30 167	97.58 72	99.59 75	99.31 125

HPM-MVS_fast		98.38 44	98.13 47	99.12 60	99.75 4	97.86 73	99.44 7	98.82 73	94.46 169	98.94 43	99.20 57	95.16 72	99.74 110	97.58 72	99.85 3	99.77 22

ZNCC-MVS		98.49 37	98.20 45	99.35 25	99.73 12	98.39 39	99.19 36	98.86 63	95.77 101	98.31 89	99.10 75	95.46 54	99.93 18	97.57 75	99.81 10	99.74 35

region2R		98.61 18	98.38 21	99.29 34	99.74 8	98.16 60	99.23 26	98.93 38	96.15 87	98.94 43	99.17 61	95.91 42	99.94 3	97.55 76	99.79 21	99.78 15

DeepC-MVS_fast	96.70 1	98.55 31	98.34 29	99.18 50	99.25 88	98.04 65	98.50 168	98.78 98	97.72 6	98.92 48	99.28 42	95.27 67	99.82 67	97.55 76	99.77 28	99.69 55
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS++		98.58 24	98.25 39	99.55 9	99.50 43	99.08 11	98.72 130	98.66 135	97.51 17	98.15 91	98.83 115	95.70 47	99.92 24	97.53 78	99.67 58	99.66 69

PC_three_1452									95.08 142	99.60 5	99.16 66	97.86 2	98.47 263	97.52 79	99.72 52	99.74 35

nrg030		96.28 143	95.72 148	97.96 137	96.90 277	98.15 61	99.39 8	98.31 204	95.47 116	94.42 226	98.35 164	92.09 128	98.69 240	97.50 80	89.05 310	97.04 239

CSCG		97.85 70	97.74 66	98.20 118	99.67 27	95.16 189	99.22 30	99.32 7	93.04 231	97.02 152	98.92 105	95.36 61	99.91 33	97.43 81	99.64 66	99.52 92

mPP-MVS		98.51 36	98.26 38	99.25 42	99.75 4	98.04 65	99.28 21	98.81 79	96.24 83	98.35 86	99.23 50	95.46 54	99.94 3	97.42 82	99.81 10	99.77 22

mvs_anonymous		96.70 126	96.53 124	97.18 182	98.19 184	93.78 244	98.31 195	98.19 223	94.01 182	94.47 220	98.27 178	92.08 129	98.46 264	97.39 83	97.91 167	99.31 125

EIA-MVS		97.75 73	97.58 70	98.27 112	98.38 164	96.44 134	99.01 68	98.60 145	95.88 97	97.26 141	97.53 241	94.97 77	99.33 166	97.38 84	99.20 113	99.05 159

NCCC		98.61 18	98.35 25	99.38 20	99.28 84	98.61 29	98.45 172	98.76 102	97.82 5	98.45 79	98.93 103	96.65 17	99.83 59	97.38 84	99.41 103	99.71 48

VPA-MVSNet		95.75 165	95.11 180	97.69 156	97.24 252	97.27 96	98.94 82	99.23 12	95.13 136	95.51 197	97.32 254	85.73 261	98.91 219	97.33 86	89.55 302	96.89 255

OPU-MVS				99.37 23	99.24 94	99.05 14	99.02 66				99.16 66	97.81 3	99.37 163	97.24 87	99.73 45	99.70 52

3Dnovator	94.51 5	97.46 90	96.93 103	99.07 63	97.78 212	97.64 82	99.35 13	99.06 22	97.02 52	93.75 258	99.16 66	89.25 185	99.92 24	97.22 88	99.75 40	99.64 74

#test#		98.54 33	98.27 37	99.32 31	99.72 13	98.29 51	98.98 75	98.96 32	95.65 108	98.94 43	99.17 61	96.06 33	99.92 24	97.21 89	99.78 25	99.75 30

ACMMP		98.23 55	97.95 57	99.09 62	99.74 8	97.62 84	99.03 62	99.41 6	95.98 94	97.60 135	99.36 28	94.45 92	99.93 18	97.14 90	98.85 131	99.70 52
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
PVSNet_Blended_VisFu		97.70 76	97.46 80	98.44 102	99.27 85	95.91 163	98.63 147	99.16 17	94.48 168	97.67 128	98.88 108	92.80 113	99.91 33	97.11 91	99.12 117	99.50 98

mvs_tets		95.41 183	95.00 184	96.65 216	95.58 329	94.42 226	99.00 70	98.55 157	95.73 103	93.21 276	98.38 161	83.45 300	98.63 247	97.09 92	94.00 240	96.91 252

GST-MVS		98.43 41	98.12 48	99.34 26	99.72 13	98.38 40	99.09 51	98.82 73	95.71 104	98.73 60	99.06 84	95.27 67	99.93 18	97.07 93	99.63 68	99.72 44

9.14			98.06 51		99.47 50		98.71 131	98.82 73	94.36 171	99.16 30	99.29 41	96.05 35	99.81 74	97.00 94	99.71 54

EPNet		97.28 103	96.87 106	98.51 95	94.98 339	96.14 147	98.90 87	97.02 319	98.28 1	95.99 193	99.11 73	91.36 145	99.89 38	96.98 95	99.19 115	99.50 98
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		96.90 120	96.49 125	98.14 121	99.33 67	95.56 174	97.38 279	99.65 2	92.34 256	97.61 134	98.20 183	89.29 184	99.10 191	96.97 96	97.60 180	99.77 22

3Dnovator+	94.38 6	97.43 95	96.78 110	99.38 20	97.83 210	98.52 32	99.37 10	98.71 117	97.09 50	92.99 284	99.13 70	89.36 182	99.89 38	96.97 96	99.57 79	99.71 48

abl_6		98.30 54	98.03 53	99.13 57	99.56 36	97.76 80	99.13 44	98.82 73	96.14 88	99.26 21	99.37 24	93.33 107	99.93 18	96.96 98	99.67 58	99.69 55

jajsoiax		95.45 179	95.03 183	96.73 210	95.42 336	94.63 215	99.14 41	98.52 163	95.74 102	93.22 275	98.36 163	83.87 296	98.65 246	96.95 99	94.04 238	96.91 252

ET-MVSNet_ETH3D		94.13 264	92.98 279	97.58 164	98.22 180	96.20 144	97.31 288	95.37 348	94.53 164	79.56 360	97.63 234	86.51 247	97.53 333	96.91 100	90.74 287	99.02 161

MVSFormer		97.57 86	97.49 78	97.84 141	98.07 194	95.76 169	99.47 5	98.40 188	94.98 145	98.79 54	98.83 115	92.34 118	98.41 276	96.91 100	99.59 75	99.34 119

test_djsdf		96.00 152	95.69 154	96.93 198	95.72 325	95.49 178	99.47 5	98.40 188	94.98 145	94.58 216	97.86 211	89.16 188	98.41 276	96.91 100	94.12 237	96.88 256

ECVR-MVS		95.95 154	95.71 151	96.65 216	99.02 114	90.86 305	99.03 62	91.80 368	96.96 55	98.10 94	99.26 45	81.31 310	99.51 150	96.90 103	99.04 119	99.59 85

test_prior3		98.22 56	97.90 60	99.19 46	99.31 72	98.22 55	97.80 254	98.84 68	96.12 90	97.89 117	98.69 128	95.96 39	99.70 118	96.89 104	99.60 72	99.65 71

test_prior2							97.80 254		96.12 90	97.89 117	98.69 128	95.96 39		96.89 104	99.60 72

EPP-MVSNet		97.46 90	97.28 88	97.99 134	98.64 149	95.38 181	99.33 18	98.31 204	93.61 210	97.19 143	99.07 83	94.05 99	99.23 173	96.89 104	98.43 152	99.37 118

PS-MVSNAJss		96.43 136	96.26 132	96.92 201	95.84 323	95.08 195	99.16 39	98.50 171	95.87 98	93.84 254	98.34 168	94.51 88	98.61 248	96.88 107	93.45 253	97.06 238

PVSNet_BlendedMVS		96.73 125	96.60 120	97.12 186	99.25 88	95.35 184	98.26 203	99.26 8	94.28 172	97.94 112	97.46 245	92.74 114	99.81 74	96.88 107	93.32 256	96.20 322

PVSNet_Blended		97.38 99	97.12 93	98.14 121	99.25 88	95.35 184	97.28 290	99.26 8	93.13 228	97.94 112	98.21 182	92.74 114	99.81 74	96.88 107	99.40 105	99.27 132

test1111		95.94 156	95.78 146	96.41 244	98.99 120	90.12 317	99.04 58	92.45 367	96.99 54	98.03 100	99.27 44	81.40 309	99.48 155	96.87 110	99.04 119	99.63 77

Effi-MVS+		97.12 112	96.69 116	98.39 107	98.19 184	96.72 120	97.37 281	98.43 183	93.71 200	97.65 131	98.02 194	92.20 125	99.25 170	96.87 110	97.79 172	99.19 140

CHOSEN 1792x2688		97.12 112	96.80 107	98.08 128	99.30 77	94.56 222	98.05 229	99.71 1	93.57 211	97.09 146	98.91 106	88.17 214	99.89 38	96.87 110	99.56 84	99.81 10

test_yl		97.22 105	96.78 110	98.54 92	98.73 138	96.60 125	98.45 172	98.31 204	94.70 155	98.02 102	98.42 156	90.80 158	99.70 118	96.81 113	96.79 193	99.34 119

DCV-MVSNet		97.22 105	96.78 110	98.54 92	98.73 138	96.60 125	98.45 172	98.31 204	94.70 155	98.02 102	98.42 156	90.80 158	99.70 118	96.81 113	96.79 193	99.34 119

ETH3D-3000-0.1		98.35 47	98.00 55	99.38 20	99.47 50	98.68 25	98.67 141	98.84 68	94.66 161	99.11 32	99.25 48	95.46 54	99.81 74	96.80 115	99.73 45	99.63 77

PGM-MVS		98.49 37	98.23 43	99.27 41	99.72 13	98.08 64	98.99 72	99.49 5	95.43 118	99.03 37	99.32 35	95.56 50	99.94 3	96.80 115	99.77 28	99.78 15

test2506		94.44 246	93.91 243	96.04 261	99.02 114	88.99 335	99.06 55	79.47 378	96.96 55	98.36 84	99.26 45	77.21 341	99.52 149	96.78 117	99.04 119	99.59 85

RRT_test8_iter05		94.56 236	94.19 223	95.67 278	97.60 224	91.34 296	98.93 84	98.42 185	94.75 154	93.39 270	97.87 210	79.00 327	98.61 248	96.78 117	90.99 285	97.07 237

XVG-OURS-SEG-HR		96.51 134	96.34 128	97.02 191	98.77 136	93.76 245	97.79 256	98.50 171	95.45 117	96.94 154	99.09 80	87.87 224	99.55 145	96.76 119	95.83 222	97.74 220

MP-MVS		98.33 51	98.01 54	99.28 38	99.75 4	98.18 58	99.22 30	98.79 95	96.13 89	97.92 115	99.23 50	94.54 87	99.94 3	96.74 120	99.78 25	99.73 40
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
agg_prior1		97.95 63	97.51 77	99.28 38	99.30 77	98.38 40	97.81 253	98.72 113	93.16 227	97.57 136	98.66 133	96.14 29	99.81 74	96.63 121	99.56 84	99.66 69

train_agg		97.97 59	97.52 75	99.33 30	99.31 72	98.50 34	97.92 240	98.73 111	92.98 233	97.74 123	98.68 130	96.20 26	99.80 83	96.59 122	99.57 79	99.68 61

MVSTER		96.06 149	95.72 148	97.08 189	98.23 179	95.93 161	98.73 126	98.27 213	94.86 151	95.07 202	98.09 190	88.21 212	98.54 256	96.59 122	93.46 251	96.79 265

bset_n11_16_dypcd		94.89 216	94.27 219	96.76 208	94.41 347	95.15 191	95.67 343	95.64 347	95.53 112	94.65 214	97.52 242	87.10 237	98.29 292	96.58 124	91.35 277	96.83 263

UGNet		96.78 124	96.30 130	98.19 120	98.24 178	95.89 165	98.88 94	98.93 38	97.39 27	96.81 163	97.84 214	82.60 302	99.90 36	96.53 125	99.49 93	98.79 178
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
APD-MVS		98.35 47	98.00 55	99.42 18	99.51 41	98.72 21	98.80 113	98.82 73	94.52 166	99.23 23	99.25 48	95.54 52	99.80 83	96.52 126	99.77 28	99.74 35
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPNet		94.99 208	94.19 223	97.40 174	97.16 261	96.57 127	98.71 131	98.97 30	95.67 106	94.84 208	98.24 181	80.36 319	98.67 244	96.46 127	87.32 330	96.96 244

ETH3D cwj APD-0.16		97.96 60	97.52 75	99.29 34	99.05 110	98.52 32	98.33 189	98.68 124	93.18 225	98.68 62	99.13 70	94.62 84	99.83 59	96.45 128	99.55 87	99.52 92

sss		97.39 98	96.98 102	98.61 86	98.60 153	96.61 124	98.22 205	98.93 38	93.97 185	98.01 106	98.48 150	91.98 131	99.85 53	96.45 128	98.15 160	99.39 116

MVS_Test		97.28 103	97.00 100	98.13 123	98.33 173	95.97 155	98.74 122	98.07 252	94.27 173	98.44 80	98.07 191	92.48 116	99.26 169	96.43 130	98.19 159	99.16 146

FIs		96.51 134	96.12 136	97.67 158	97.13 263	97.54 87	99.36 11	99.22 14	95.89 96	94.03 246	98.35 164	91.98 131	98.44 267	96.40 131	92.76 263	97.01 240

test9_res														96.39 132	99.57 79	99.69 55

Anonymous20240529		95.10 202	94.22 221	97.75 150	99.01 116	94.26 233	98.87 96	98.83 71	85.79 348	96.64 168	98.97 93	78.73 328	99.85 53	96.27 133	94.89 226	99.12 151

PMMVS		96.60 128	96.33 129	97.41 172	97.90 206	93.93 240	97.35 284	98.41 186	92.84 240	97.76 121	97.45 247	91.10 153	99.20 176	96.26 134	97.91 167	99.11 152

CLD-MVS		95.62 173	95.34 167	96.46 241	97.52 234	93.75 247	97.27 291	98.46 176	95.53 112	94.42 226	98.00 197	86.21 254	98.97 208	96.25 135	94.37 227	96.66 284
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous202405211		95.28 192	94.49 206	97.67 158	99.00 117	93.75 247	98.70 135	97.04 316	90.66 303	96.49 179	98.80 118	78.13 333	99.83 59	96.21 136	95.36 225	99.44 112

RRT_MVS		96.04 150	95.53 158	97.56 166	97.07 267	97.32 93	98.57 158	98.09 248	95.15 135	95.02 204	98.44 153	88.20 213	98.58 254	96.17 137	93.09 260	96.79 265

ZD-MVS					99.46 53	98.70 23		98.79 95	93.21 224	98.67 63	98.97 93	95.70 47	99.83 59	96.07 138	99.58 78

HQP_MVS		96.14 147	95.90 143	96.85 204	97.42 242	94.60 220	98.80 113	98.56 155	97.28 34	95.34 198	98.28 175	87.09 238	99.03 200	96.07 138	94.27 229	96.92 247

plane_prior5								98.56 155					99.03 200	96.07 138	94.27 229	96.92 247

CPTT-MVS		97.72 75	97.32 87	98.92 72	99.64 30	97.10 105	99.12 46	98.81 79	92.34 256	98.09 95	99.08 82	93.01 111	99.92 24	96.06 141	99.77 28	99.75 30

DP-MVS Recon		97.86 69	97.46 80	99.06 64	99.53 38	98.35 48	98.33 189	98.89 47	92.62 245	98.05 97	98.94 102	95.34 62	99.65 127	96.04 142	99.42 102	99.19 140

FC-MVSNet-test		96.42 137	96.05 138	97.53 168	96.95 272	97.27 96	99.36 11	99.23 12	95.83 99	93.93 248	98.37 162	92.00 130	98.32 285	96.02 143	92.72 264	97.00 241

Vis-MVSNet		97.42 96	97.11 94	98.34 109	98.66 147	96.23 143	99.22 30	99.00 27	96.63 69	98.04 99	99.21 53	88.05 219	99.35 164	96.01 144	99.21 112	99.45 111
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ab-mvs		96.42 137	95.71 151	98.55 90	98.63 150	96.75 119	97.88 247	98.74 107	93.84 191	96.54 176	98.18 185	85.34 269	99.75 108	95.93 145	96.35 206	99.15 147

WTY-MVS		97.37 100	96.92 104	98.72 80	98.86 129	96.89 114	98.31 195	98.71 117	95.26 129	97.67 128	98.56 144	92.21 124	99.78 99	95.89 146	96.85 191	99.48 103

XVG-OURS		96.55 133	96.41 126	96.99 192	98.75 137	93.76 245	97.50 273	98.52 163	95.67 106	96.83 160	99.30 40	88.95 198	99.53 146	95.88 147	96.26 213	97.69 223

agg_prior2														95.87 148	99.57 79	99.68 61

UniMVSNet_NR-MVSNet		95.71 167	95.15 177	97.40 174	96.84 280	96.97 108	98.74 122	99.24 10	95.16 134	93.88 251	97.72 225	91.68 136	98.31 287	95.81 149	87.25 331	96.92 247

DU-MVS		95.42 181	94.76 194	97.40 174	96.53 295	96.97 108	98.66 144	98.99 29	95.43 118	93.88 251	97.69 226	88.57 204	98.31 287	95.81 149	87.25 331	96.92 247

testtj		98.33 51	97.95 57	99.47 14	99.49 47	98.70 23	98.83 103	98.86 63	95.48 115	98.91 49	99.17 61	95.48 53	99.93 18	95.80 151	99.53 89	99.76 28

UniMVSNet (Re)		95.78 164	95.19 176	97.58 164	96.99 271	97.47 89	98.79 117	99.18 16	95.60 109	93.92 249	97.04 279	91.68 136	98.48 260	95.80 151	87.66 326	96.79 265

cascas		94.63 231	93.86 247	96.93 198	96.91 276	94.27 232	96.00 339	98.51 166	85.55 349	94.54 217	96.23 320	84.20 289	98.87 226	95.80 151	96.98 190	97.66 224

Effi-MVS+-dtu		96.29 141	96.56 121	95.51 281	97.89 207	90.22 316	98.80 113	98.10 243	96.57 71	96.45 182	96.66 304	90.81 156	98.91 219	95.72 154	97.99 165	97.40 228

mvs-test1		96.60 128	96.68 118	96.37 247	97.89 207	91.81 286	98.56 159	98.10 243	96.57 71	96.52 178	97.94 203	90.81 156	99.45 159	95.72 154	98.01 164	97.86 217

LPG-MVS_test		95.62 173	95.34 167	96.47 238	97.46 237	93.54 254	98.99 72	98.54 159	94.67 159	94.36 228	98.77 122	85.39 266	99.11 188	95.71 156	94.15 235	96.76 269

LGP-MVS_train				96.47 238	97.46 237	93.54 254		98.54 159	94.67 159	94.36 228	98.77 122	85.39 266	99.11 188	95.71 156	94.15 235	96.76 269

旧先验2							97.57 271		91.30 291	98.67 63			99.80 83	95.70 158

LCM-MVSNet-Re		95.22 195	95.32 170	94.91 299	98.18 186	87.85 350	98.75 119	95.66 346	95.11 138	88.96 336	96.85 297	90.26 169	97.65 328	95.65 159	98.44 150	99.22 136

anonymousdsp		95.42 181	94.91 189	96.94 197	95.10 338	95.90 164	99.14 41	98.41 186	93.75 195	93.16 277	97.46 245	87.50 232	98.41 276	95.63 160	94.03 239	96.50 308

CDPH-MVS		97.94 64	97.49 78	99.28 38	99.47 50	98.44 36	97.91 242	98.67 132	92.57 248	98.77 56	98.85 111	95.93 41	99.72 112	95.56 161	99.69 56	99.68 61

CostFormer		94.95 212	94.73 196	95.60 280	97.28 250	89.06 332	97.53 272	96.89 327	89.66 323	96.82 162	96.72 302	86.05 257	98.95 216	95.53 162	96.13 218	98.79 178

ACMM	93.85 9	95.69 170	95.38 165	96.61 222	97.61 223	93.84 243	98.91 86	98.44 180	95.25 130	94.28 232	98.47 151	86.04 259	99.12 185	95.50 163	93.95 242	96.87 258
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	93.49 10	95.34 189	94.98 186	96.43 243	97.67 219	93.48 258	98.73 126	98.44 180	94.94 150	92.53 297	98.53 145	84.50 283	99.14 183	95.48 164	94.00 240	96.66 284
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
tttt0517		96.07 148	95.51 160	97.78 147	98.41 163	94.84 206	99.28 21	94.33 359	94.26 174	97.64 132	98.64 135	84.05 291	99.47 157	95.34 165	97.60 180	99.03 160

TAMVS		97.02 115	96.79 109	97.70 155	98.06 196	95.31 186	98.52 163	98.31 204	93.95 186	97.05 151	98.61 136	93.49 106	98.52 258	95.33 166	97.81 171	99.29 130

BP-MVS														95.30 167

HQP-MVS		95.72 166	95.40 161	96.69 214	97.20 256	94.25 234	98.05 229	98.46 176	96.43 76	94.45 221	97.73 223	86.75 244	98.96 212	95.30 167	94.18 233	96.86 260

thisisatest0530		96.01 151	95.36 166	97.97 135	98.38 164	95.52 177	98.88 94	94.19 361	94.04 179	97.64 132	98.31 171	83.82 298	99.46 158	95.29 169	97.70 177	98.93 170

WR-MVS		95.15 199	94.46 209	97.22 179	96.67 290	96.45 133	98.21 206	98.81 79	94.15 175	93.16 277	97.69 226	87.51 230	98.30 289	95.29 169	88.62 316	96.90 254

tpmrst		95.63 172	95.69 154	95.44 285	97.54 231	88.54 341	96.97 307	97.56 284	93.50 213	97.52 138	96.93 292	89.49 178	99.16 179	95.25 171	96.42 205	98.64 190

CDS-MVSNet		96.99 116	96.69 116	97.90 139	98.05 197	95.98 150	98.20 209	98.33 201	93.67 207	96.95 153	98.49 149	93.54 105	98.42 269	95.24 172	97.74 175	99.31 125
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OPM-MVS		95.69 170	95.33 169	96.76 208	96.16 312	94.63 215	98.43 177	98.39 191	96.64 68	95.02 204	98.78 120	85.15 271	99.05 195	95.21 173	94.20 232	96.60 289
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
OMC-MVS		97.55 88	97.34 86	98.20 118	99.33 67	95.92 162	98.28 200	98.59 147	95.52 114	97.97 109	99.10 75	93.28 109	99.49 151	95.09 174	98.88 128	99.19 140

UniMVSNet_ETH3D		94.24 257	93.33 273	96.97 195	97.19 259	93.38 263	98.74 122	98.57 153	91.21 297	93.81 255	98.58 141	72.85 357	98.77 237	95.05 175	93.93 243	98.77 180

CANet_DTU		96.96 117	96.55 122	98.21 117	98.17 188	96.07 149	97.98 236	98.21 220	97.24 40	97.13 145	98.93 103	86.88 243	99.91 33	95.00 176	99.37 107	98.66 188

UA-Net		97.96 60	97.62 68	98.98 68	98.86 129	97.47 89	98.89 91	99.08 21	96.67 67	98.72 61	99.54 1	93.15 110	99.81 74	94.87 177	98.83 132	99.65 71

114514_t		96.93 118	96.27 131	98.92 72	99.50 43	97.63 83	98.85 99	98.90 45	84.80 351	97.77 120	99.11 73	92.84 112	99.66 126	94.85 178	99.77 28	99.47 105

Anonymous20231211		94.10 267	93.26 276	96.61 222	99.11 109	94.28 231	99.01 68	98.88 50	86.43 342	92.81 287	97.57 238	81.66 308	98.68 243	94.83 179	89.02 312	96.88 256

XXY-MVS		95.20 197	94.45 211	97.46 169	96.75 285	96.56 128	98.86 98	98.65 139	93.30 222	93.27 274	98.27 178	84.85 276	98.87 226	94.82 180	91.26 281	96.96 244

MG-MVS		97.81 71	97.60 69	98.44 102	99.12 108	95.97 155	97.75 258	98.78 98	96.89 58	98.46 76	99.22 52	93.90 103	99.68 124	94.81 181	99.52 91	99.67 65

test_part1		94.82 218	93.82 249	97.82 144	98.84 132	97.82 77	99.03 62	98.81 79	92.31 260	92.51 299	97.89 208	81.96 305	98.67 244	94.80 182	88.24 319	96.98 242

EI-MVSNet		95.96 153	95.83 145	96.36 248	97.93 204	93.70 251	98.12 223	98.27 213	93.70 202	95.07 202	99.02 86	92.23 123	98.54 256	94.68 183	93.46 251	96.84 261

thisisatest0515		95.61 175	94.89 190	97.76 149	98.15 189	95.15 191	96.77 323	94.41 357	92.95 235	97.18 144	97.43 249	84.78 277	99.45 159	94.63 184	97.73 176	98.68 185

IterMVS-LS		95.46 177	95.21 175	96.22 255	98.12 191	93.72 250	98.32 194	98.13 237	93.71 200	94.26 233	97.31 255	92.24 122	98.10 304	94.63 184	90.12 293	96.84 261
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.25 145	95.73 147	97.79 146	97.13 263	95.55 176	98.19 213	98.59 147	93.47 214	92.03 310	97.82 218	91.33 147	99.49 151	94.62 186	98.44 150	98.32 204

baseline1		95.84 161	95.12 179	98.01 133	98.49 160	95.98 150	98.73 126	97.03 317	95.37 123	96.22 186	98.19 184	89.96 172	99.16 179	94.60 187	87.48 327	98.90 172

IS-MVSNet		97.22 105	96.88 105	98.25 115	98.85 131	96.36 138	99.19 36	97.97 262	95.39 120	97.23 142	98.99 92	91.11 152	98.93 217	94.60 187	98.59 142	99.47 105

NR-MVSNet		94.98 210	94.16 226	97.44 170	96.53 295	97.22 102	98.74 122	98.95 34	94.96 147	89.25 335	97.69 226	89.32 183	98.18 298	94.59 189	87.40 329	96.92 247

IB-MVS	91.98 17	93.27 284	91.97 295	97.19 181	97.47 236	93.41 261	97.09 302	95.99 341	93.32 220	92.47 301	95.73 331	78.06 334	99.53 146	94.59 189	82.98 345	98.62 191
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
DWT-MVSNet_test		94.82 218	94.36 216	96.20 256	97.35 247	90.79 308	98.34 187	96.57 338	92.91 237	95.33 200	96.44 314	82.00 304	99.12 185	94.52 191	95.78 223	98.70 183

HY-MVS	93.96 8	96.82 123	96.23 134	98.57 88	98.46 161	97.00 107	98.14 220	98.21 220	93.95 186	96.72 166	97.99 198	91.58 138	99.76 106	94.51 192	96.54 201	98.95 169

D2MVS		95.18 198	95.08 181	95.48 282	97.10 265	92.07 282	98.30 197	99.13 19	94.02 181	92.90 285	96.73 301	89.48 179	98.73 239	94.48 193	93.60 250	95.65 335

Baseline_NR-MVSNet		94.35 250	93.81 250	95.96 266	96.20 308	94.05 238	98.61 150	96.67 336	91.44 284	93.85 253	97.60 235	88.57 204	98.14 301	94.39 194	86.93 334	95.68 334

AdaColmap		97.15 111	96.70 115	98.48 99	99.16 104	96.69 121	98.01 233	98.89 47	94.44 170	96.83 160	98.68 130	90.69 161	99.76 106	94.36 195	99.29 111	98.98 165

AUN-MVS		94.53 239	93.73 258	96.92 201	98.50 158	93.52 257	98.34 187	98.10 243	93.83 193	95.94 195	97.98 200	85.59 264	99.03 200	94.35 196	80.94 353	98.22 207

1112_ss		96.63 127	96.00 141	98.50 96	98.56 154	96.37 137	98.18 217	98.10 243	92.92 236	94.84 208	98.43 154	92.14 126	99.58 137	94.35 196	96.51 202	99.56 91

CP-MVSNet		94.94 214	94.30 218	96.83 205	96.72 287	95.56 174	99.11 47	98.95 34	93.89 188	92.42 303	97.90 206	87.19 236	98.12 303	94.32 198	88.21 320	96.82 264

CNLPA		97.45 93	97.03 98	98.73 79	99.05 110	97.44 91	98.07 227	98.53 161	95.32 126	96.80 164	98.53 145	93.32 108	99.72 112	94.31 199	99.31 110	99.02 161

testdata				98.26 114	99.20 99	95.36 182		98.68 124	91.89 271	98.60 71	99.10 75	94.44 93	99.82 67	94.27 200	99.44 100	99.58 89

PVSNet	91.96 18	96.35 139	96.15 135	96.96 196	99.17 100	92.05 283	96.08 335	98.68 124	93.69 203	97.75 122	97.80 220	88.86 199	99.69 123	94.26 201	99.01 122	99.15 147

miper_enhance_ethall		95.10 202	94.75 195	96.12 260	97.53 233	93.73 249	96.61 329	98.08 250	92.20 265	93.89 250	96.65 306	92.44 117	98.30 289	94.21 202	91.16 282	96.34 316

Test_1112_low_res		96.34 140	95.66 156	98.36 108	98.56 154	95.94 158	97.71 260	98.07 252	92.10 266	94.79 212	97.29 256	91.75 135	99.56 140	94.17 203	96.50 203	99.58 89

TranMVSNet+NR-MVSNet		95.14 200	94.48 207	97.11 187	96.45 300	96.36 138	99.03 62	99.03 25	95.04 143	93.58 261	97.93 204	88.27 211	98.03 311	94.13 204	86.90 336	96.95 246

API-MVS		97.41 97	97.25 89	97.91 138	98.70 143	96.80 116	98.82 106	98.69 121	94.53 164	98.11 93	98.28 175	94.50 91	99.57 138	94.12 205	99.49 93	97.37 231

ETH3 D test6400		97.59 84	97.01 99	99.34 26	99.40 61	98.56 30	98.20 209	98.81 79	91.63 279	98.44 80	98.85 111	93.98 102	99.82 67	94.11 206	99.69 56	99.64 74

cl22		94.68 226	94.19 223	96.13 259	98.11 192	93.60 252	96.94 309	98.31 204	92.43 253	93.32 273	96.87 296	86.51 247	98.28 294	94.10 207	91.16 282	96.51 306

PLC	95.07 4	97.20 108	96.78 110	98.44 102	99.29 80	96.31 142	98.14 220	98.76 102	92.41 254	96.39 183	98.31 171	94.92 79	99.78 99	94.06 208	98.77 135	99.23 135
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
XVG-ACMP-BASELINE		94.54 238	94.14 228	95.75 276	96.55 294	91.65 292	98.11 225	98.44 180	94.96 147	94.22 236	97.90 206	79.18 326	99.11 188	94.05 209	93.85 244	96.48 310

F-COLMAP		97.09 114	96.80 107	97.97 135	99.45 57	94.95 203	98.55 161	98.62 144	93.02 232	96.17 188	98.58 141	94.01 100	99.81 74	93.95 210	98.90 126	99.14 149

MDTV_nov1_ep13_2view						84.26 358	96.89 317		90.97 301	97.90 116		89.89 173		93.91 211		99.18 145

baseline2		95.11 201	94.52 205	96.87 203	96.65 291	93.56 253	98.27 202	94.10 363	93.45 215	92.02 311	97.43 249	87.45 234	99.19 177	93.88 212	97.41 184	97.87 216

原ACMM1				98.65 84	99.32 70	96.62 122		98.67 132	93.27 223	97.81 119	98.97 93	95.18 71	99.83 59	93.84 213	99.46 98	99.50 98

RPSCF		94.87 217	95.40 161	93.26 330	98.89 126	82.06 364	98.33 189	98.06 257	90.30 312	96.56 172	99.26 45	87.09 238	99.49 151	93.82 214	96.32 208	98.24 206

PAPM_NR		97.46 90	97.11 94	98.50 96	99.50 43	96.41 136	98.63 147	98.60 145	95.18 133	97.06 150	98.06 192	94.26 97	99.57 138	93.80 215	98.87 130	99.52 92

ACMH	92.88 16	94.55 237	93.95 240	96.34 250	97.63 222	93.26 267	98.81 112	98.49 175	93.43 216	89.74 330	98.53 145	81.91 306	99.08 193	93.69 216	93.30 257	96.70 278
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
miper_ehance_all_eth		95.01 206	94.69 198	95.97 265	97.70 218	93.31 265	97.02 305	98.07 252	92.23 262	93.51 266	96.96 288	91.85 133	98.15 300	93.68 217	91.16 282	96.44 313

MAR-MVS		96.91 119	96.40 127	98.45 101	98.69 145	96.90 112	98.66 144	98.68 124	92.40 255	97.07 149	97.96 201	91.54 142	99.75 108	93.68 217	98.92 125	98.69 184
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
Vis-MVSNet (Re-imp)		96.87 121	96.55 122	97.83 142	98.73 138	95.46 179	99.20 34	98.30 210	94.96 147	96.60 171	98.87 109	90.05 170	98.59 252	93.67 219	98.60 141	99.46 109

LS3D		97.16 110	96.66 119	98.68 82	98.53 157	97.19 103	98.93 84	98.90 45	92.83 241	95.99 193	99.37 24	92.12 127	99.87 47	93.67 219	99.57 79	98.97 166

PS-CasMVS		94.67 229	93.99 238	96.71 211	96.68 289	95.26 187	99.13 44	99.03 25	93.68 205	92.33 304	97.95 202	85.35 268	98.10 304	93.59 221	88.16 322	96.79 265

c3_l		94.79 221	94.43 213	95.89 270	97.75 213	93.12 272	97.16 299	98.03 259	92.23 262	93.46 269	97.05 278	91.39 144	98.01 312	93.58 222	89.21 308	96.53 300

CVMVSNet		95.43 180	96.04 139	93.57 324	97.93 204	83.62 359	98.12 223	98.59 147	95.68 105	96.56 172	99.02 86	87.51 230	97.51 334	93.56 223	97.44 182	99.60 83

OurMVSNet-221017-0		94.21 258	94.00 236	94.85 302	95.60 328	89.22 330	98.89 91	97.43 300	95.29 127	92.18 307	98.52 148	82.86 301	98.59 252	93.46 224	91.76 272	96.74 271

eth_miper_zixun_eth		94.68 226	94.41 214	95.47 283	97.64 221	91.71 291	96.73 326	98.07 252	92.71 243	93.64 259	97.21 262	90.54 163	98.17 299	93.38 225	89.76 297	96.54 298

OpenMVS	93.04 13	95.83 162	95.00 184	98.32 110	97.18 260	97.32 93	99.21 33	98.97 30	89.96 317	91.14 318	99.05 85	86.64 246	99.92 24	93.38 225	99.47 95	97.73 221

无先验							97.58 270	98.72 113	91.38 285				99.87 47	93.36 227		99.60 83

1121		97.37 100	96.77 114	99.16 53	99.34 64	97.99 70	98.19 213	98.68 124	90.14 315	98.01 106	98.97 93	94.80 82	99.87 47	93.36 227	99.46 98	99.61 80

gm-plane-assit					95.88 321	87.47 351			89.74 322		96.94 291		99.19 177	93.32 229

WR-MVS_H		95.05 205	94.46 209	96.81 206	96.86 279	95.82 167	99.24 25	99.24 10	93.87 190	92.53 297	96.84 298	90.37 165	98.24 296	93.24 230	87.93 323	96.38 315

tpm		94.13 264	93.80 251	95.12 293	96.50 297	87.91 349	97.44 274	95.89 345	92.62 245	96.37 184	96.30 317	84.13 290	98.30 289	93.24 230	91.66 275	99.14 149

Fast-Effi-MVS+-dtu		95.87 159	95.85 144	95.91 268	97.74 216	91.74 290	98.69 137	98.15 234	95.56 111	94.92 206	97.68 229	88.98 196	98.79 235	93.19 232	97.78 173	97.20 235

pmmvs5		93.65 278	92.97 280	95.68 277	95.49 332	92.37 278	98.20 209	97.28 307	89.66 323	92.58 295	97.26 257	82.14 303	98.09 306	93.18 233	90.95 286	96.58 291

TESTMET0.1,1		94.18 262	93.69 261	95.63 279	96.92 274	89.12 331	96.91 312	94.78 354	93.17 226	94.88 207	96.45 313	78.52 329	98.92 218	93.09 234	98.50 147	98.85 173

test-LLR		95.10 202	94.87 191	95.80 273	96.77 282	89.70 321	96.91 312	95.21 349	95.11 138	94.83 210	95.72 333	87.71 226	98.97 208	93.06 235	98.50 147	98.72 181

test-mter		94.08 269	93.51 268	95.80 273	96.77 282	89.70 321	96.91 312	95.21 349	92.89 238	94.83 210	95.72 333	77.69 336	98.97 208	93.06 235	98.50 147	98.72 181

BH-untuned		95.95 154	95.72 148	96.65 216	98.55 156	92.26 279	98.23 204	97.79 272	93.73 198	94.62 215	98.01 196	88.97 197	99.00 207	93.04 237	98.51 146	98.68 185

EPMVS		94.99 208	94.48 207	96.52 234	97.22 254	91.75 289	97.23 292	91.66 369	94.11 176	97.28 140	96.81 299	85.70 262	98.84 229	93.04 237	97.28 185	98.97 166

pmmvs4		94.69 224	93.99 238	96.81 206	95.74 324	95.94 158	97.40 277	97.67 277	90.42 309	93.37 271	97.59 236	89.08 191	98.20 297	92.97 239	91.67 274	96.30 320

GeoE		96.58 132	96.07 137	98.10 127	98.35 166	95.89 165	99.34 15	98.12 238	93.12 229	96.09 189	98.87 109	89.71 176	98.97 208	92.95 240	98.08 163	99.43 113

v2v482		94.69 224	94.03 232	96.65 216	96.17 310	94.79 211	98.67 141	98.08 250	92.72 242	94.00 247	97.16 264	87.69 229	98.45 265	92.91 241	88.87 314	96.72 274

Fast-Effi-MVS+		96.28 143	95.70 153	98.03 132	98.29 177	95.97 155	98.58 153	98.25 218	91.74 274	95.29 201	97.23 260	91.03 155	99.15 182	92.90 242	97.96 166	98.97 166

V42		94.78 222	94.14 228	96.70 213	96.33 305	95.22 188	98.97 76	98.09 248	92.32 258	94.31 231	97.06 276	88.39 209	98.55 255	92.90 242	88.87 314	96.34 316

DP-MVS		96.59 130	95.93 142	98.57 88	99.34 64	96.19 146	98.70 135	98.39 191	89.45 326	94.52 218	99.35 30	91.85 133	99.85 53	92.89 244	98.88 128	99.68 61

TDRefinement		91.06 307	89.68 312	95.21 290	85.35 369	91.49 295	98.51 167	97.07 314	91.47 282	88.83 339	97.84 214	77.31 340	99.09 192	92.79 245	77.98 357	95.04 345

ACMH+	92.99 14	94.30 253	93.77 254	95.88 271	97.81 211	92.04 284	98.71 131	98.37 195	93.99 184	90.60 324	98.47 151	80.86 316	99.05 195	92.75 246	92.40 266	96.55 297

cl____		94.51 241	94.01 235	96.02 262	97.58 226	93.40 262	97.05 303	97.96 264	91.73 276	92.76 289	97.08 272	89.06 192	98.13 302	92.61 247	90.29 292	96.52 303

DIV-MVS_self_test		94.52 240	94.03 232	95.99 263	97.57 230	93.38 263	97.05 303	97.94 265	91.74 274	92.81 287	97.10 266	89.12 189	98.07 308	92.60 248	90.30 291	96.53 300

DPM-MVS		97.55 88	96.99 101	99.23 45	99.04 112	98.55 31	97.17 298	98.35 198	94.85 152	97.93 114	98.58 141	95.07 75	99.71 117	92.60 248	99.34 108	99.43 113

test_post1							96.68 327				30.43 375	87.85 225	98.69 240	92.59 250

SCA		95.46 177	95.13 178	96.46 241	97.67 219	91.29 300	97.33 286	97.60 282	94.68 158	96.92 157	97.10 266	83.97 293	98.89 223	92.59 250	98.32 157	99.20 137

v148		94.29 254	93.76 256	95.91 268	96.10 313	92.93 274	98.58 153	97.97 262	92.59 247	93.47 268	96.95 290	88.53 207	98.32 285	92.56 252	87.06 333	96.49 309

PEN-MVS		94.42 247	93.73 258	96.49 236	96.28 306	94.84 206	99.17 38	99.00 27	93.51 212	92.23 306	97.83 217	86.10 256	97.90 320	92.55 253	86.92 335	96.74 271

Patchmatch-RL test		91.49 302	90.85 303	93.41 326	91.37 362	84.40 357	92.81 359	95.93 344	91.87 272	87.25 344	94.87 343	88.99 193	96.53 351	92.54 254	82.00 347	99.30 128

miper_lstm_enhance		94.33 251	94.07 231	95.11 294	97.75 213	90.97 304	97.22 293	98.03 259	91.67 278	92.76 289	96.97 286	90.03 171	97.78 326	92.51 255	89.64 299	96.56 295

IterMVS		94.09 268	93.85 248	94.80 305	97.99 201	90.35 315	97.18 296	98.12 238	93.68 205	92.46 302	97.34 252	84.05 291	97.41 335	92.51 255	91.33 278	96.62 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		94.11 266	93.87 246	94.85 302	97.98 203	90.56 313	97.18 296	98.11 241	93.75 195	92.58 295	97.48 244	83.97 293	97.41 335	92.48 257	91.30 279	96.58 291

tpm2		94.19 260	93.76 256	95.46 284	97.23 253	89.04 333	97.31 288	96.85 331	87.08 339	96.21 187	96.79 300	83.75 299	98.74 238	92.43 258	96.23 215	98.59 192

PVSNet_0	88.72 19	91.28 304	90.03 310	95.00 297	97.99 201	87.29 353	94.84 352	98.50 171	92.06 267	89.86 329	95.19 339	79.81 322	99.39 162	92.27 259	69.79 364	98.33 203

gg-mvs-nofinetune		92.21 298	90.58 305	97.13 185	96.75 285	95.09 194	95.85 340	89.40 372	85.43 350	94.50 219	81.98 365	80.80 317	98.40 282	92.16 260	98.33 156	97.88 215

pm-mvs1		93.94 274	93.06 278	96.59 225	96.49 298	95.16 189	98.95 80	98.03 259	92.32 258	91.08 319	97.84 214	84.54 282	98.41 276	92.16 260	86.13 342	96.19 323

K. test v3		92.55 295	91.91 297	94.48 314	95.64 327	89.24 329	99.07 54	94.88 353	94.04 179	86.78 346	97.59 236	77.64 339	97.64 329	92.08 262	89.43 305	96.57 293

GBi-Net		94.49 242	93.80 251	96.56 229	98.21 181	95.00 197	98.82 106	98.18 226	92.46 249	94.09 242	97.07 273	81.16 311	97.95 316	92.08 262	92.14 267	96.72 274

test1		94.49 242	93.80 251	96.56 229	98.21 181	95.00 197	98.82 106	98.18 226	92.46 249	94.09 242	97.07 273	81.16 311	97.95 316	92.08 262	92.14 267	96.72 274

FMVSNet3		94.97 211	94.26 220	97.11 187	98.18 186	96.62 122	98.56 159	98.26 217	93.67 207	94.09 242	97.10 266	84.25 286	98.01 312	92.08 262	92.14 267	96.70 278

PatchmatchNet		95.71 167	95.52 159	96.29 253	97.58 226	90.72 310	96.84 321	97.52 291	94.06 178	97.08 147	96.96 288	89.24 186	98.90 222	92.03 266	98.37 153	99.26 133
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
QAPM		96.29 141	95.40 161	98.96 70	97.85 209	97.60 85	99.23 26	98.93 38	89.76 321	93.11 281	99.02 86	89.11 190	99.93 18	91.99 267	99.62 70	99.34 119

新几何1				99.16 53	99.34 64	98.01 67		98.69 121	90.06 316	98.13 92	98.95 101	94.60 85	99.89 38	91.97 268	99.47 95	99.59 85

MDTV_nov1_ep13			95.40 161		97.48 235	88.34 344	96.85 320	97.29 306	93.74 197	97.48 139	97.26 257	89.18 187	99.05 195	91.92 269	97.43 183

EU-MVSNet		93.66 276	94.14 228	92.25 337	95.96 319	83.38 360	98.52 163	98.12 238	94.69 157	92.61 294	98.13 188	87.36 235	96.39 353	91.82 270	90.00 295	96.98 242

GA-MVS		94.81 220	94.03 232	97.14 184	97.15 262	93.86 242	96.76 324	97.58 283	94.00 183	94.76 213	97.04 279	80.91 314	98.48 260	91.79 271	96.25 214	99.09 154

PatchMatch-RL		96.59 130	96.03 140	98.27 112	99.31 72	96.51 130	97.91 242	99.06 22	93.72 199	96.92 157	98.06 192	88.50 208	99.65 127	91.77 272	99.00 123	98.66 188

v1144		94.59 234	93.92 241	96.60 224	96.21 307	94.78 212	98.59 151	98.14 236	91.86 273	94.21 237	97.02 281	87.97 220	98.41 276	91.72 273	89.57 300	96.61 288

v8		94.47 244	93.77 254	96.57 228	96.36 303	94.83 208	99.05 57	98.19 223	91.92 270	93.16 277	96.97 286	88.82 201	98.48 260	91.69 274	87.79 324	96.39 314

testdata2													99.89 38	91.65 275

BH-w/o		95.38 184	95.08 181	96.26 254	98.34 171	91.79 287	97.70 261	97.43 300	92.87 239	94.24 235	97.22 261	88.66 202	98.84 229	91.55 276	97.70 177	98.16 210

LF4IMVS		93.14 289	92.79 283	94.20 319	95.88 321	88.67 339	97.66 264	97.07 314	93.81 194	91.71 313	97.65 230	77.96 335	98.81 233	91.47 277	91.92 271	95.12 342

JIA-IIPM		93.35 281	92.49 288	95.92 267	96.48 299	90.65 311	95.01 348	96.96 321	85.93 346	96.08 190	87.33 362	87.70 228	98.78 236	91.35 278	95.58 224	98.34 202

FMVSNet2		94.47 244	93.61 264	97.04 190	98.21 181	96.43 135	98.79 117	98.27 213	92.46 249	93.50 267	97.09 270	81.16 311	98.00 314	91.09 279	91.93 270	96.70 278

v144192		94.39 249	93.70 260	96.48 237	96.06 315	94.35 230	98.58 153	98.16 233	91.45 283	94.33 230	97.02 281	87.50 232	98.45 265	91.08 280	89.11 309	96.63 286

tpmvs		94.60 232	94.36 216	95.33 288	97.46 237	88.60 340	96.88 318	97.68 276	91.29 292	93.80 256	96.42 315	88.58 203	99.24 172	91.06 281	96.04 220	98.17 209

LTVRE_ROB	92.95 15	94.60 232	93.90 244	96.68 215	97.41 245	94.42 226	98.52 163	98.59 147	91.69 277	91.21 317	98.35 164	84.87 275	99.04 199	91.06 281	93.44 254	96.60 289
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
PAPR		96.84 122	96.24 133	98.65 84	98.72 142	96.92 111	97.36 283	98.57 153	93.33 219	96.67 167	97.57 238	94.30 96	99.56 140	91.05 283	98.59 142	99.47 105

SixPastTwentyTwo		93.34 282	92.86 281	94.75 306	95.67 326	89.41 328	98.75 119	96.67 336	93.89 188	90.15 328	98.25 180	80.87 315	98.27 295	90.90 284	90.64 288	96.57 293

MVS_0304		92.81 292	92.01 294	95.23 289	97.46 237	91.33 298	98.17 218	98.81 79	91.13 299	93.80 256	95.68 336	66.08 364	98.06 309	90.79 285	96.13 218	96.32 319

COLMAP_ROB	93.27 12	95.33 190	94.87 191	96.71 211	99.29 80	93.24 268	98.58 153	98.11 241	89.92 318	93.57 262	99.10 75	86.37 252	99.79 95	90.78 286	98.10 162	97.09 236
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pmmvs6		91.77 300	90.63 304	95.17 292	94.69 346	91.24 301	98.67 141	97.92 267	86.14 344	89.62 331	97.56 240	75.79 347	98.34 283	90.75 287	84.56 344	95.94 329

BH-RMVSNet		95.92 158	95.32 170	97.69 156	98.32 175	94.64 214	98.19 213	97.45 298	94.56 163	96.03 191	98.61 136	85.02 272	99.12 185	90.68 288	99.06 118	99.30 128

DTE-MVSNet		93.98 273	93.26 276	96.14 258	96.06 315	94.39 228	99.20 34	98.86 63	93.06 230	91.78 312	97.81 219	85.87 260	97.58 331	90.53 289	86.17 340	96.46 312

v10		94.29 254	93.55 266	96.51 235	96.39 302	94.80 210	98.99 72	98.19 223	91.35 288	93.02 283	96.99 284	88.09 217	98.41 276	90.50 290	88.41 318	96.33 318

ambc				89.49 342	86.66 367	75.78 367	92.66 360	96.72 333		86.55 348	92.50 356	46.01 369	97.90 320	90.32 291	82.09 346	94.80 349

lessismore_v0				94.45 317	94.93 341	88.44 343		91.03 370		86.77 347	97.64 232	76.23 345	98.42 269	90.31 292	85.64 343	96.51 306

v1192		94.32 252	93.58 265	96.53 233	96.10 313	94.45 224	98.50 168	98.17 231	91.54 281	94.19 238	97.06 276	86.95 242	98.43 268	90.14 293	89.57 300	96.70 278

MVS		94.67 229	93.54 267	98.08 128	96.88 278	96.56 128	98.19 213	98.50 171	78.05 360	92.69 292	98.02 194	91.07 154	99.63 132	90.09 294	98.36 155	98.04 212

ADS-MVSNet2		94.58 235	94.40 215	95.11 294	98.00 199	88.74 338	96.04 336	97.30 305	90.15 313	96.47 180	96.64 307	87.89 222	97.56 332	90.08 295	97.06 187	99.02 161

ADS-MVSNet		95.00 207	94.45 211	96.63 220	98.00 199	91.91 285	96.04 336	97.74 275	90.15 313	96.47 180	96.64 307	87.89 222	98.96 212	90.08 295	97.06 187	99.02 161

MSDG		95.93 157	95.30 172	97.83 142	98.90 125	95.36 182	96.83 322	98.37 195	91.32 290	94.43 225	98.73 126	90.27 168	99.60 135	90.05 297	98.82 133	98.52 195

v1921920		94.20 259	93.47 270	96.40 246	95.98 318	94.08 237	98.52 163	98.15 234	91.33 289	94.25 234	97.20 263	86.41 251	98.42 269	90.04 298	89.39 306	96.69 283

dp		94.15 263	93.90 244	94.90 300	97.31 249	86.82 355	96.97 307	97.19 311	91.22 296	96.02 192	96.61 309	85.51 265	99.02 203	90.00 299	94.30 228	98.85 173

CMPMVS	66.06 21	89.70 317	89.67 313	89.78 341	93.19 356	76.56 366	97.00 306	98.35 198	80.97 357	81.57 358	97.75 222	74.75 351	98.61 248	89.85 300	93.63 248	94.17 352
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TR-MVS		94.94 214	94.20 222	97.17 183	97.75 213	94.14 236	97.59 269	97.02 319	92.28 261	95.75 196	97.64 232	83.88 295	98.96 212	89.77 301	96.15 217	98.40 199

MS-PatchMatch		93.84 275	93.63 263	94.46 316	96.18 309	89.45 326	97.76 257	98.27 213	92.23 262	92.13 308	97.49 243	79.50 323	98.69 240	89.75 302	99.38 106	95.25 339

ITE_SJBPF				95.44 285	97.42 242	91.32 299		97.50 293	95.09 141	93.59 260	98.35 164	81.70 307	98.88 225	89.71 303	93.39 255	96.12 324

MVP-Stereo		94.28 256	93.92 241	95.35 287	94.95 340	92.60 277	97.97 237	97.65 278	91.61 280	90.68 323	97.09 270	86.32 253	98.42 269	89.70 304	99.34 108	95.02 346
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
AllTest		95.24 194	94.65 199	96.99 192	99.25 88	93.21 269	98.59 151	98.18 226	91.36 286	93.52 264	98.77 122	84.67 279	99.72 112	89.70 304	97.87 169	98.02 213

TestCases				96.99 192	99.25 88	93.21 269		98.18 226	91.36 286	93.52 264	98.77 122	84.67 279	99.72 112	89.70 304	97.87 169	98.02 213

GG-mvs-BLEND				96.59 225	96.34 304	94.98 200	96.51 332	88.58 373		93.10 282	94.34 349	80.34 320	98.05 310	89.53 307	96.99 189	96.74 271

USDC		93.33 283	92.71 284	95.21 290	96.83 281	90.83 307	96.91 312	97.50 293	93.84 191	90.72 322	98.14 187	77.69 336	98.82 232	89.51 308	93.21 259	95.97 328

v7n		94.19 260	93.43 271	96.47 238	95.90 320	94.38 229	99.26 23	98.34 200	91.99 268	92.76 289	97.13 265	88.31 210	98.52 258	89.48 309	87.70 325	96.52 303

PM-MVS		87.77 324	86.55 328	91.40 340	91.03 364	83.36 361	96.92 310	95.18 351	91.28 293	86.48 349	93.42 352	53.27 368	96.74 345	89.43 310	81.97 348	94.11 353

FMVSNet1		93.19 288	92.07 293	96.56 229	97.54 231	95.00 197	98.82 106	98.18 226	90.38 310	92.27 305	97.07 273	73.68 355	97.95 316	89.36 311	91.30 279	96.72 274

tpm cat1		93.36 280	92.80 282	95.07 296	97.58 226	87.97 348	96.76 324	97.86 270	82.17 356	93.53 263	96.04 326	86.13 255	99.13 184	89.24 312	95.87 221	98.10 211

UnsupCasMVSNet_eth		90.99 308	89.92 311	94.19 320	94.08 350	89.83 319	97.13 301	98.67 132	93.69 203	85.83 351	96.19 323	75.15 349	96.74 345	89.14 313	79.41 355	96.00 327

v1240		94.06 271	93.29 275	96.34 250	96.03 317	93.90 241	98.44 175	98.17 231	91.18 298	94.13 241	97.01 283	86.05 257	98.42 269	89.13 314	89.50 304	96.70 278

tmp_tt		68.90 335	66.97 337	74.68 352	50.78 379	59.95 375	87.13 364	83.47 376	38.80 372	62.21 368	96.23 320	64.70 365	76.91 374	88.91 315	30.49 372	87.19 364

pmmvs-eth3d		90.36 313	89.05 318	94.32 318	91.10 363	92.12 280	97.63 268	96.95 322	88.86 331	84.91 354	93.13 353	78.32 330	96.74 345	88.70 316	81.81 349	94.09 354

thres600view7		95.49 176	94.77 193	97.67 158	98.98 121	95.02 196	98.85 99	96.90 325	95.38 121	96.63 169	96.90 293	84.29 284	99.59 136	88.65 317	96.33 207	98.40 199

thres100view900		95.38 184	94.70 197	97.41 172	98.98 121	94.92 204	98.87 96	96.90 325	95.38 121	96.61 170	96.88 294	84.29 284	99.56 140	88.11 318	96.29 209	97.76 218

tfpn200view9		95.32 191	94.62 200	97.43 171	98.94 123	94.98 200	98.68 138	96.93 323	95.33 124	96.55 174	96.53 310	84.23 287	99.56 140	88.11 318	96.29 209	97.76 218

thres400		95.38 184	94.62 200	97.65 161	98.94 123	94.98 200	98.68 138	96.93 323	95.33 124	96.55 174	96.53 310	84.23 287	99.56 140	88.11 318	96.29 209	98.40 199

our_test_3		93.65 278	93.30 274	94.69 307	95.45 334	89.68 323	96.91 312	97.65 278	91.97 269	91.66 314	96.88 294	89.67 177	97.93 319	88.02 321	91.49 276	96.48 310

thres200		95.25 193	94.57 202	97.28 177	98.81 134	94.92 204	98.20 209	97.11 312	95.24 132	96.54 176	96.22 322	84.58 281	99.53 146	87.93 322	96.50 203	97.39 229

EG-PatchMatch MVS		91.13 306	90.12 309	94.17 321	94.73 345	89.00 334	98.13 222	97.81 271	89.22 329	85.32 353	96.46 312	67.71 361	98.42 269	87.89 323	93.82 245	95.08 344

CR-MVSNet		94.76 223	94.15 227	96.59 225	97.00 269	93.43 259	94.96 349	97.56 284	92.46 249	96.93 155	96.24 318	88.15 215	97.88 324	87.38 324	96.65 197	98.46 197

Patchmtry		93.22 286	92.35 290	95.84 272	96.77 282	93.09 273	94.66 354	97.56 284	87.37 338	92.90 285	96.24 318	88.15 215	97.90 320	87.37 325	90.10 294	96.53 300

test0.0.03 1		94.08 269	93.51 268	95.80 273	95.53 331	92.89 275	97.38 279	95.97 342	95.11 138	92.51 299	96.66 304	87.71 226	96.94 342	87.03 326	93.67 246	97.57 225

TinyColmap		92.31 297	91.53 298	94.65 309	96.92 274	89.75 320	96.92 310	96.68 335	90.45 308	89.62 331	97.85 213	76.06 346	98.81 233	86.74 327	92.51 265	95.41 337

MIMVSNet		93.26 285	92.21 292	96.41 244	97.73 217	93.13 271	95.65 344	97.03 317	91.27 294	94.04 245	96.06 325	75.33 348	97.19 338	86.56 328	96.23 215	98.92 171

TransMVSNet (Re)		92.67 294	91.51 299	96.15 257	96.58 293	94.65 213	98.90 87	96.73 332	90.86 302	89.46 334	97.86 211	85.62 263	98.09 306	86.45 329	81.12 351	95.71 333

DSMNet-mixed		92.52 296	92.58 287	92.33 335	94.15 349	82.65 362	98.30 197	94.26 360	89.08 330	92.65 293	95.73 331	85.01 273	95.76 356	86.24 330	97.76 174	98.59 192

testgi		93.06 290	92.45 289	94.88 301	96.43 301	89.90 318	98.75 119	97.54 290	95.60 109	91.63 315	97.91 205	74.46 353	97.02 340	86.10 331	93.67 246	97.72 222

YYNet1		90.70 311	89.39 314	94.62 310	94.79 344	90.65 311	97.20 294	97.46 296	87.54 337	72.54 364	95.74 329	86.51 247	96.66 349	86.00 332	86.76 338	96.54 298

MDA-MVSNet_test_wron		90.71 310	89.38 315	94.68 308	94.83 342	90.78 309	97.19 295	97.46 296	87.60 336	72.41 365	95.72 333	86.51 247	96.71 348	85.92 333	86.80 337	96.56 295

UnsupCasMVSNet_bld		87.17 325	85.12 329	93.31 329	91.94 360	88.77 337	94.92 351	98.30 210	84.30 353	82.30 357	90.04 359	63.96 366	97.25 337	85.85 334	74.47 363	93.93 357

EPNet_dtu		95.21 196	94.95 188	95.99 263	96.17 310	90.45 314	98.16 219	97.27 308	96.77 62	93.14 280	98.33 169	90.34 166	98.42 269	85.57 335	98.81 134	99.09 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		91.81 299	90.92 302	94.49 313	97.21 255	92.09 281	98.00 235	97.55 289	89.31 328	90.86 321	95.61 337	74.48 352	95.32 359	85.57 335	89.70 298	96.07 326

tfpnnormal		93.66 276	92.70 285	96.55 232	96.94 273	95.94 158	98.97 76	99.19 15	91.04 300	91.38 316	97.34 252	84.94 274	98.61 248	85.45 337	89.02 312	95.11 343

Patchmatch-test		94.42 247	93.68 262	96.63 220	97.60 224	91.76 288	94.83 353	97.49 295	89.45 326	94.14 240	97.10 266	88.99 193	98.83 231	85.37 338	98.13 161	99.29 130

ppachtmachnet_test		93.22 286	92.63 286	94.97 298	95.45 334	90.84 306	96.88 318	97.88 269	90.60 304	92.08 309	97.26 257	88.08 218	97.86 325	85.12 339	90.33 290	96.22 321

KD-MVS_2432*1600		89.61 319	87.96 323	94.54 311	94.06 351	91.59 293	95.59 345	97.63 280	89.87 319	88.95 337	94.38 347	78.28 331	96.82 343	84.83 340	68.05 365	95.21 340

miper_refine_blended		89.61 319	87.96 323	94.54 311	94.06 351	91.59 293	95.59 345	97.63 280	89.87 319	88.95 337	94.38 347	78.28 331	96.82 343	84.83 340	68.05 365	95.21 340

PCF-MVS	93.45 11	94.68 226	93.43 271	98.42 105	98.62 151	96.77 118	95.48 347	98.20 222	84.63 352	93.34 272	98.32 170	88.55 206	99.81 74	84.80 342	98.96 124	98.68 185
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_method		79.03 328	78.17 331	81.63 348	86.06 368	54.40 378	82.75 367	96.89 327	39.54 371	80.98 359	95.57 338	58.37 367	94.73 362	84.74 343	78.61 356	95.75 332

KD-MVS_self_test		90.38 312	89.38 315	93.40 327	92.85 358	88.94 336	97.95 238	97.94 265	90.35 311	90.25 326	93.96 350	79.82 321	95.94 355	84.62 344	76.69 359	95.33 338

Anonymous20240521		91.18 305	90.44 306	93.42 325	93.70 354	88.47 342	98.94 82	97.56 284	88.46 333	89.56 333	95.08 342	77.15 343	96.97 341	83.92 345	89.55 302	94.82 348

MDA-MVSNet-bldmvs		89.97 316	88.35 321	94.83 304	95.21 337	91.34 296	97.64 265	97.51 292	88.36 334	71.17 366	96.13 324	79.22 325	96.63 350	83.65 346	86.27 339	96.52 303

MVS-HIRNet		89.46 321	88.40 320	92.64 333	97.58 226	82.15 363	94.16 358	93.05 366	75.73 362	90.90 320	82.52 364	79.42 324	98.33 284	83.53 347	98.68 136	97.43 226

new-patchmatchnet		88.50 323	87.45 326	91.67 339	90.31 365	85.89 356	97.16 299	97.33 304	89.47 325	83.63 356	92.77 354	76.38 344	95.06 361	82.70 348	77.29 358	94.06 355

PAPM		94.95 212	94.00 236	97.78 147	97.04 268	95.65 171	96.03 338	98.25 218	91.23 295	94.19 238	97.80 220	91.27 149	98.86 228	82.61 349	97.61 179	98.84 175

LCM-MVSNet		78.70 329	76.24 334	86.08 344	77.26 375	71.99 370	94.34 356	96.72 333	61.62 366	76.53 361	89.33 360	33.91 375	92.78 366	81.85 350	74.60 362	93.46 358

new_pmnet		90.06 315	89.00 319	93.22 331	94.18 348	88.32 345	96.42 334	96.89 327	86.19 343	85.67 352	93.62 351	77.18 342	97.10 339	81.61 351	89.29 307	94.23 351

pmmvs3		86.67 327	84.86 330	92.11 338	88.16 366	87.19 354	96.63 328	94.75 355	79.88 358	87.22 345	92.75 355	66.56 363	95.20 360	81.24 352	76.56 360	93.96 356

CL-MVSNet_self_test		90.11 314	89.14 317	93.02 332	91.86 361	88.23 346	96.51 332	98.07 252	90.49 305	90.49 325	94.41 345	84.75 278	95.34 358	80.79 353	74.95 361	95.50 336

N_pmnet		87.12 326	87.77 325	85.17 346	95.46 333	61.92 373	97.37 281	70.66 379	85.83 347	88.73 340	96.04 326	85.33 270	97.76 327	80.02 354	90.48 289	95.84 330

TAPA-MVS	93.98 7	95.35 188	94.56 203	97.74 151	99.13 107	94.83 208	98.33 189	98.64 140	86.62 340	96.29 185	98.61 136	94.00 101	99.29 168	80.00 355	99.41 103	99.09 154
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DeepMVS_CX				86.78 343	97.09 266	72.30 369		95.17 352	75.92 361	84.34 355	95.19 339	70.58 358	95.35 357	79.98 356	89.04 311	92.68 360

Anonymous20231206		91.66 301	91.10 301	93.33 328	94.02 353	87.35 352	98.58 153	97.26 309	90.48 306	90.16 327	96.31 316	83.83 297	96.53 351	79.36 357	89.90 296	96.12 324

test20.03		90.89 309	90.38 307	92.43 334	93.48 355	88.14 347	98.33 189	97.56 284	93.40 217	87.96 342	96.71 303	80.69 318	94.13 364	79.15 358	86.17 340	95.01 347

PatchT		93.06 290	91.97 295	96.35 249	96.69 288	92.67 276	94.48 355	97.08 313	86.62 340	97.08 147	92.23 357	87.94 221	97.90 320	78.89 359	96.69 195	98.49 196

MIMVSNet1		89.67 318	88.28 322	93.82 322	92.81 359	91.08 303	98.01 233	97.45 298	87.95 335	87.90 343	95.87 328	67.63 362	94.56 363	78.73 360	88.18 321	95.83 331

test_0402		91.32 303	90.27 308	94.48 314	96.60 292	91.12 302	98.50 168	97.22 310	86.10 345	88.30 341	96.98 285	77.65 338	97.99 315	78.13 361	92.94 262	94.34 350

OpenMVS_ROB	86.42 20	89.00 322	87.43 327	93.69 323	93.08 357	89.42 327	97.91 242	96.89 327	78.58 359	85.86 350	94.69 344	69.48 359	98.29 292	77.13 362	93.29 258	93.36 359

RPMNet		92.81 292	91.34 300	97.24 178	97.00 269	93.43 259	94.96 349	98.80 90	82.27 355	96.93 155	92.12 358	86.98 241	99.82 67	76.32 363	96.65 197	98.46 197

PMMVS2		77.95 331	75.44 335	85.46 345	82.54 370	74.95 368	94.23 357	93.08 365	72.80 363	74.68 362	87.38 361	36.36 374	91.56 367	73.95 364	63.94 367	89.87 362

EGC-MVSNET		75.22 333	69.54 336	92.28 336	94.81 343	89.58 324	97.64 265	96.50 339	1.82 376	5.57 377	95.74 329	68.21 360	96.26 354	73.80 365	91.71 273	90.99 361

FPMVS		77.62 332	77.14 332	79.05 350	79.25 373	60.97 374	95.79 341	95.94 343	65.96 364	67.93 367	94.40 346	37.73 373	88.88 369	68.83 366	88.46 317	87.29 363

Gipuma		78.40 330	76.75 333	83.38 347	95.54 330	80.43 365	79.42 368	97.40 302	64.67 365	73.46 363	80.82 366	45.65 370	93.14 365	66.32 367	87.43 328	76.56 368
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ANet_high		69.08 334	65.37 338	80.22 349	65.99 377	71.96 371	90.91 363	90.09 371	82.62 354	49.93 372	78.39 367	29.36 376	81.75 370	62.49 368	38.52 371	86.95 365

PMVS	61.03 23	65.95 336	63.57 340	73.09 353	57.90 378	51.22 379	85.05 366	93.93 364	54.45 367	44.32 373	83.57 363	13.22 377	89.15 368	58.68 369	81.00 352	78.91 367
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	62.14 22	63.28 339	59.38 342	74.99 351	74.33 376	65.47 372	85.55 365	80.50 377	52.02 369	51.10 371	75.00 370	10.91 380	80.50 371	51.60 370	53.40 368	78.99 366
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		64.94 337	64.25 339	67.02 354	82.28 371	59.36 376	91.83 362	85.63 374	52.69 368	60.22 369	77.28 368	41.06 372	80.12 372	46.15 371	41.14 369	61.57 370

EMVS		64.07 338	63.26 341	66.53 355	81.73 372	58.81 377	91.85 361	84.75 375	51.93 370	59.09 370	75.13 369	43.32 371	79.09 373	42.03 372	39.47 370	61.69 369

wuyk23d		30.17 340	30.18 344	30.16 356	78.61 374	43.29 380	66.79 369	14.21 380	17.31 373	14.82 376	11.93 376	11.55 379	41.43 375	37.08 373	19.30 373	5.76 373

test123		20.95 343	23.72 346	12.64 357	13.54 381	8.19 381	96.55 331	6.13 382	7.48 375	16.74 375	37.98 373	12.97 378	6.05 376	16.69 374	5.43 375	23.68 371

testmvs		21.48 342	24.95 345	11.09 358	14.89 380	6.47 382	96.56 330	9.87 381	7.55 374	17.93 374	39.02 372	9.43 381	5.90 377	16.56 375	12.72 374	20.91 372

test_blank		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

uanet_test		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

cdsmvs_eth3d_5k		23.98 341	31.98 343	0.00 359	0.00 382	0.00 383	0.00 370	98.59 147	0.00 377	0.00 378	98.61 136	90.60 162	0.00 378	0.00 376	0.00 376	0.00 374

pcd_1.5k_mvsjas		7.88 345	10.50 348	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	94.51 88	0.00 378	0.00 376	0.00 376	0.00 374

sosnet-low-res		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

sosnet		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

uncertanet		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

Regformer		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

ab-mvs-re		8.20 344	10.94 347	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	98.43 154	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

uanet		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

FOURS1					99.82 1	98.66 26	99.69 1	98.95 34	97.46 22	99.39 15

test_one_0601					99.66 28	99.25 2		98.86 63	97.55 15	99.20 25	99.47 8	97.57 6

eth-test2					0.00 382

eth-test					0.00 382

test_241102_ONE					99.71 21	99.24 5		98.87 57	97.62 11	99.73 1	99.39 16	97.53 7	99.74 110

save fliter					99.46 53	98.38 40	98.21 206	98.71 117	97.95 3

test0726					99.72 13	99.25 2	99.06 55	98.88 50	97.62 11	99.56 6	99.50 4	97.42 9

GSMVS																99.20 137

test_part2					99.63 31	99.18 10				99.27 20

sam_mvs1												89.45 180				99.20 137

sam_mvs												88.99 193

MTGPA								98.74 107

test_post											31.83 374	88.83 200	98.91 219

patchmatchnet-post											95.10 341	89.42 181	98.89 223

MTMP							98.89 91	94.14 362

TEST9					99.31 72	98.50 34	97.92 240	98.73 111	92.63 244	97.74 123	98.68 130	96.20 26	99.80 83

test_8					99.29 80	98.44 36	97.89 246	98.72 113	92.98 233	97.70 126	98.66 133	96.20 26	99.80 83

agg_prior					99.30 77	98.38 40		98.72 113		97.57 136			99.81 74

test_prior4						98.01 67	97.86 249

test_prior				99.19 46	99.31 72	98.22 55		98.84 68					99.70 118			99.65 71

新几何2							97.64 265

旧先验1					99.29 80	97.48 88		98.70 120			99.09 80	95.56 50			99.47 95	99.61 80

原ACMM2							97.67 263

test222					99.23 95	97.17 104	97.40 277	98.66 135	88.68 332	98.05 97	98.96 99	94.14 98			99.53 89	99.61 80

segment_acmp												96.85 14

testdata1							97.32 287		96.34 80

test12				99.18 50	99.16 104	98.19 57		98.53 161		98.07 96		95.13 73	99.72 112		99.56 84	99.63 77

plane_prior7					97.42 242	94.63 215

plane_prior6					97.35 247	94.61 218						87.09 238

plane_prior4											98.28 175

plane_prior3						94.61 218			97.02 52	95.34 198

plane_prior2							98.80 113		97.28 34

plane_prior1					97.37 246

plane_prior						94.60 220	98.44 175		96.74 64						94.22 231

n2								0.00 383

nn								0.00 383

door-mid								94.37 358

test11								98.66 135

door								94.64 356

HQP5-MVS						94.25 234

HQP-NCC					97.20 256		98.05 229		96.43 76	94.45 221

ACMP_Plane					97.20 256		98.05 229		96.43 76	94.45 221

HQP4-MVS										94.45 221			98.96 212			96.87 258

HQP3-MVS								98.46 176							94.18 233

HQP2-MVS												86.75 244

NP-MVS					97.28 250	94.51 223					97.73 223

ACMMP++_ref															92.97 261

ACMMP++															93.61 249

Test By Simon												94.64 83

High-resolution multi-view benchmark