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		97.82 5	97.73 4	98.08 18	99.15 35	94.82 29	98.81 7	98.30 25	94.76 39	98.30 17	98.90 3	93.77 17	99.68 51	97.93 1	99.69 3	99.75 5

MSC_two_6792asdad				98.86 1	98.67 66	96.94 1		97.93 107					99.86 9	97.68 2	99.67 6	99.77 1

No_MVS				98.86 1	98.67 66	96.94 1		97.93 107					99.86 9	97.68 2	99.67 6	99.77 1

patch_mono-2		96.83 43	97.44 9	95.01 173	99.05 43	85.39 296	96.98 164	98.77 5	94.70 41	97.99 23	98.66 14	93.61 19	99.91 1	97.67 4	99.50 36	99.72 10

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 18	98.25 36	98.27 31	95.13 19	99.19 1	98.89 4	95.54 5	99.85 18	97.52 5	99.66 10	99.56 27

test_241102_TWO								98.27 31	95.13 19	98.93 6	98.89 4	94.99 11	99.85 18	97.52 5	99.65 12	99.74 7

DVP-MVS		97.91 3	97.81 3	98.22 12	99.45 3	95.36 13	98.21 43	97.85 118	94.92 28	98.73 10	98.87 6	95.08 8	99.84 23	97.52 5	99.67 6	99.48 47
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 28					99.86 9	97.52 5	99.67 6	99.75 5

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 66	95.39 11	99.29 1	98.28 28	94.78 37	98.93 6	98.87 6	96.04 2	99.86 9	97.45 9	99.58 22	99.59 20

test_0728_THIRD									94.78 37	98.73 10	98.87 6	95.87 4	99.84 23	97.45 9	99.72 2	99.77 1

DROMVSNet		96.42 58	96.47 52	96.26 112	97.01 168	91.52 127	98.89 5	97.75 124	94.42 48	96.64 65	97.68 101	89.32 92	98.60 191	97.45 9	99.11 88	98.67 129

IU-MVS					99.42 7	95.39 11		97.94 106	90.40 185	98.94 5				97.41 12	99.66 10	99.74 7

dcpmvs_2		96.37 61	97.05 17	94.31 212	98.96 50	84.11 314	97.56 107	97.51 153	93.92 60	97.43 36	98.52 25	92.75 28	99.32 120	97.32 13	99.50 36	99.51 39

CS-MVS		96.86 39	97.06 15	96.26 112	98.16 111	91.16 146	99.09 3	97.87 113	95.30 12	97.06 53	98.03 74	91.72 53	98.71 182	97.10 14	99.17 79	98.90 109

TSAR-MVS + MP.		97.42 9	97.33 11	97.69 45	99.25 29	94.24 43	98.07 53	97.85 118	93.72 68	98.57 13	98.35 42	93.69 18	99.40 113	97.06 15	99.46 44	99.44 53
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		97.68 6	97.44 9	98.37 7	98.90 55	95.86 6	97.27 135	98.08 68	95.81 4	97.87 28	98.31 51	94.26 13	99.68 51	97.02 16	99.49 40	99.57 24

SD-MVS		97.41 10	97.53 7	97.06 74	98.57 79	94.46 34	97.92 66	98.14 57	94.82 34	99.01 3	98.55 22	94.18 14	97.41 314	96.94 17	99.64 13	99.32 66
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
CS-MVS-test		96.89 37	97.04 18	96.45 97	98.29 96	91.66 121	99.03 4	97.85 118	95.84 3	96.90 56	97.97 80	91.24 67	98.75 176	96.92 18	99.33 59	98.94 104

Regformer-4		96.97 30	96.87 26	97.25 64	98.34 90	92.66 89	96.96 166	98.01 95	95.12 22	97.14 47	98.42 35	91.82 51	99.61 66	96.90 19	99.13 83	99.50 43

CANet		96.39 60	96.02 65	97.50 53	97.62 140	93.38 70	97.02 157	97.96 104	95.42 8	94.86 121	97.81 92	87.38 121	99.82 29	96.88 20	99.20 77	99.29 68

TSAR-MVS + GP.		96.69 49	96.49 51	97.27 63	98.31 95	93.39 69	96.79 181	96.72 233	94.17 55	97.44 34	97.66 104	92.76 27	99.33 118	96.86 21	97.76 129	99.08 89

Regformer-3		96.85 41	96.80 34	97.01 75	98.34 90	92.02 112	96.96 166	97.76 123	95.01 26	97.08 52	98.42 35	91.71 55	99.54 90	96.80 22	99.13 83	99.48 47

Regformer-2		97.16 19	96.99 21	97.67 46	98.32 93	93.84 56	96.83 177	98.10 65	95.24 13	97.49 31	98.25 59	92.57 35	99.61 66	96.80 22	99.29 64	99.56 27

Regformer-1		97.10 21	96.96 23	97.54 52	98.32 93	93.48 67	96.83 177	97.99 101	95.20 15	97.46 32	98.25 59	92.48 39	99.58 75	96.79 24	99.29 64	99.55 31

DeepPCF-MVS	93.97 1	96.61 52	97.09 14	95.15 165	98.09 114	86.63 276	96.00 246	98.15 55	95.43 7	97.95 24	98.56 20	93.40 20	99.36 117	96.77 25	99.48 41	99.45 51

SMA-MVS		97.35 13	97.03 19	98.30 8	99.06 42	95.42 10	97.94 64	98.18 50	90.57 181	98.85 9	98.94 1	93.33 21	99.83 26	96.72 26	99.68 4	99.63 14
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DPE-MVS		97.86 4	97.65 5	98.47 5	99.17 34	95.78 7	97.21 144	98.35 20	95.16 18	98.71 12	98.80 11	95.05 10	99.89 4	96.70 27	99.73 1	99.73 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.59 8	97.54 6	97.73 41	99.40 12	93.77 61	98.53 15	98.29 26	95.55 6	98.56 14	97.81 92	93.90 15	99.65 57	96.62 28	99.21 76	99.77 1
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
MSLP-MVS++		96.94 33	97.06 15	96.59 86	98.72 63	91.86 116	97.67 93	98.49 13	94.66 43	97.24 42	98.41 38	92.31 42	98.94 160	96.61 29	99.46 44	98.96 101

MP-MVS-pluss		96.70 48	96.27 59	97.98 24	99.23 32	94.71 30	96.96 166	98.06 77	90.67 172	95.55 110	98.78 12	91.07 72	99.86 9	96.58 30	99.55 25	99.38 62
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SteuartSystems-ACMMP		97.62 7	97.53 7	97.87 27	98.39 87	94.25 42	98.43 24	98.27 31	95.34 11	98.11 20	98.56 20	94.53 12	99.71 42	96.57 31	99.62 15	99.65 12
Skip Steuart: Steuart Systems R&D Blog.
MCST-MVS		97.18 17	96.84 30	98.20 13	99.30 26	95.35 15	97.12 152	98.07 74	93.54 76	96.08 88	97.69 100	93.86 16	99.71 42	96.50 32	99.39 53	99.55 31

xxxxxxxxxxxxxcwj		97.36 12	97.20 12	97.83 29	98.91 53	94.28 39	97.02 157	97.22 191	95.35 9	98.27 18	98.65 16	93.33 21	99.72 39	96.49 33	99.52 29	99.51 39

SF-MVS		97.39 11	97.13 13	98.17 14	99.02 46	95.28 20	98.23 40	98.27 31	92.37 123	98.27 18	98.65 16	93.33 21	99.72 39	96.49 33	99.52 29	99.51 39

EI-MVSNet-Vis-set		96.51 55	96.47 52	96.63 83	98.24 101	91.20 141	96.89 172	97.73 127	94.74 40	96.49 73	98.49 28	90.88 77	99.58 75	96.44 35	98.32 113	99.13 83

VDD-MVS		93.82 131	93.08 138	96.02 124	97.88 125	89.96 182	97.72 87	95.85 276	92.43 121	95.86 97	98.44 32	68.42 338	99.39 114	96.31 36	94.85 188	98.71 126

test1172		96.93 34	96.86 27	97.15 70	99.10 36	92.34 98	97.96 63	98.04 85	93.79 66	97.35 39	98.53 24	91.40 63	99.56 85	96.30 37	99.30 63	99.55 31

ACMMP_NAP		97.20 16	96.86 27	98.23 11	99.09 38	95.16 24	97.60 103	98.19 48	92.82 109	97.93 25	98.74 13	91.60 59	99.86 9	96.26 38	99.52 29	99.67 11

diffmvs		95.25 88	95.13 86	95.63 142	96.43 201	89.34 204	95.99 247	97.35 182	92.83 108	96.31 80	97.37 124	86.44 132	98.67 185	96.26 38	97.19 146	98.87 114

EI-MVSNet-UG-set		96.34 62	96.30 58	96.47 94	98.20 106	90.93 153	96.86 173	97.72 130	94.67 42	96.16 85	98.46 30	90.43 83	99.58 75	96.23 40	97.96 123	98.90 109

SR-MVS		97.01 29	96.86 27	97.47 54	99.09 38	93.27 75	97.98 58	98.07 74	93.75 67	97.45 33	98.48 29	91.43 62	99.59 72	96.22 41	99.27 68	99.54 34

xiu_mvs_v1_base_debu		95.01 94	94.76 92	95.75 134	96.58 189	91.71 117	96.25 231	97.35 182	92.99 98	96.70 60	96.63 168	82.67 193	99.44 108	96.22 41	97.46 133	96.11 230

xiu_mvs_v1_base		95.01 94	94.76 92	95.75 134	96.58 189	91.71 117	96.25 231	97.35 182	92.99 98	96.70 60	96.63 168	82.67 193	99.44 108	96.22 41	97.46 133	96.11 230

xiu_mvs_v1_base_debi		95.01 94	94.76 92	95.75 134	96.58 189	91.71 117	96.25 231	97.35 182	92.99 98	96.70 60	96.63 168	82.67 193	99.44 108	96.22 41	97.46 133	96.11 230

alignmvs		95.87 75	95.23 83	97.78 36	97.56 146	95.19 22	97.86 70	97.17 194	94.39 50	96.47 75	96.40 181	85.89 140	99.20 129	96.21 45	95.11 186	98.95 103

canonicalmvs		96.02 70	95.45 76	97.75 40	97.59 143	95.15 25	98.28 32	97.60 143	94.52 46	96.27 82	96.12 193	87.65 114	99.18 132	96.20 46	94.82 190	98.91 108

zzz-MVS		97.07 23	96.77 37	97.97 25	99.37 17	94.42 36	97.15 150	98.08 68	95.07 24	96.11 86	98.59 18	90.88 77	99.90 2	96.18 47	99.50 36	99.58 22

MTAPA		97.08 22	96.78 36	97.97 25	99.37 17	94.42 36	97.24 137	98.08 68	95.07 24	96.11 86	98.59 18	90.88 77	99.90 2	96.18 47	99.50 36	99.58 22

APD-MVS_3200maxsize		96.81 44	96.71 41	97.12 72	99.01 49	92.31 101	97.98 58	98.06 77	93.11 95	97.44 34	98.55 22	90.93 75	99.55 88	96.06 49	99.25 72	99.51 39

SR-MVS-dyc-post		96.88 38	96.80 34	97.11 73	99.02 46	92.34 98	97.98 58	98.03 88	93.52 78	97.43 36	98.51 26	91.40 63	99.56 85	96.05 50	99.26 70	99.43 55

RE-MVS-def			96.72 40		99.02 46	92.34 98	97.98 58	98.03 88	93.52 78	97.43 36	98.51 26	90.71 80		96.05 50	99.26 70	99.43 55

MVS_111021_HR		96.68 51	96.58 47	96.99 76	98.46 81	92.31 101	96.20 236	98.90 2	94.30 53	95.86 97	97.74 97	92.33 40	99.38 116	96.04 52	99.42 49	99.28 71

PHI-MVS		96.77 46	96.46 54	97.71 44	98.40 85	94.07 51	98.21 43	98.45 16	89.86 193	97.11 50	98.01 77	92.52 37	99.69 48	96.03 53	99.53 28	99.36 64

HPM-MVS++		97.34 14	96.97 22	98.47 5	99.08 40	96.16 4	97.55 109	97.97 103	95.59 5	96.61 67	97.89 82	92.57 35	99.84 23	95.95 54	99.51 33	99.40 59

DELS-MVS		96.61 52	96.38 57	97.30 60	97.79 130	93.19 76	95.96 248	98.18 50	95.23 14	95.87 96	97.65 105	91.45 61	99.70 47	95.87 55	99.44 48	99.00 99
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
MVS_111021_LR		96.24 65	96.19 63	96.39 102	98.23 105	91.35 133	96.24 234	98.79 4	93.99 59	95.80 99	97.65 105	89.92 90	99.24 126	95.87 55	99.20 77	98.58 131

h-mvs33		94.15 115	93.52 123	96.04 123	97.81 128	90.22 173	97.62 102	97.58 146	95.19 16	96.74 58	97.45 120	83.67 169	99.61 66	95.85 57	79.73 345	98.29 158

hse-mvs2		93.45 145	92.99 140	94.81 187	97.02 167	88.59 225	96.69 191	96.47 252	95.19 16	96.74 58	96.16 192	83.67 169	98.48 202	95.85 57	79.13 349	97.35 198

NCCC		97.30 15	97.03 19	98.11 17	98.77 61	95.06 26	97.34 128	98.04 85	95.96 2	97.09 51	97.88 84	93.18 24	99.71 42	95.84 59	99.17 79	99.56 27

VNet		95.89 74	95.45 76	97.21 68	98.07 116	92.94 83	97.50 112	98.15 55	93.87 62	97.52 30	97.61 111	85.29 147	99.53 93	95.81 60	95.27 182	99.16 79

PC_three_1452									90.77 168	98.89 8	98.28 57	96.24 1	98.35 210	95.76 61	99.58 22	99.59 20

9.14			96.75 38		98.93 51		97.73 84	98.23 42	91.28 156	97.88 27	98.44 32	93.00 25	99.65 57	95.76 61	99.47 42

XVS		97.18 17	96.96 23	97.81 33	99.38 15	94.03 53	98.59 12	98.20 46	94.85 30	96.59 69	98.29 54	91.70 56	99.80 31	95.66 63	99.40 51	99.62 16

X-MVStestdata		91.71 210	89.67 267	97.81 33	99.38 15	94.03 53	98.59 12	98.20 46	94.85 30	96.59 69	32.69 376	91.70 56	99.80 31	95.66 63	99.40 51	99.62 16

baseline		95.58 80	95.42 78	96.08 119	96.78 179	90.41 171	97.16 148	97.45 166	93.69 71	95.65 108	97.85 88	87.29 122	98.68 184	95.66 63	97.25 144	99.13 83

ETV-MVS		96.02 70	95.89 68	96.40 100	97.16 154	92.44 96	97.47 117	97.77 122	94.55 45	96.48 74	94.51 267	91.23 69	98.92 161	95.65 66	98.19 116	97.82 180

casdiffmvs		95.64 78	95.49 74	96.08 119	96.76 183	90.45 169	97.29 134	97.44 170	94.00 58	95.46 114	97.98 79	87.52 118	98.73 178	95.64 67	97.33 141	99.08 89

HFP-MVS		97.14 20	96.92 25	97.83 29	99.42 7	94.12 48	98.52 16	98.32 22	93.21 89	97.18 44	98.29 54	92.08 44	99.83 26	95.63 68	99.59 17	99.54 34

ACMMPR		97.07 23	96.84 30	97.79 35	99.44 6	93.88 55	98.52 16	98.31 24	93.21 89	97.15 46	98.33 48	91.35 65	99.86 9	95.63 68	99.59 17	99.62 16

HPM-MVS		96.69 49	96.45 55	97.40 56	99.36 20	93.11 78	98.87 6	98.06 77	91.17 160	96.40 78	97.99 78	90.99 74	99.58 75	95.61 70	99.61 16	99.49 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		97.02 27	96.81 33	97.64 49	99.33 23	93.54 65	98.80 8	98.28 28	92.99 98	96.45 77	98.30 53	91.90 50	99.85 18	95.61 70	99.68 4	99.54 34

DeepC-MVS	93.07 3	96.06 68	95.66 71	97.29 61	97.96 118	93.17 77	97.30 133	98.06 77	93.92 60	93.38 154	98.66 14	86.83 127	99.73 36	95.60 72	99.22 75	98.96 101
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		96.96 31	96.67 43	97.85 28	99.37 17	94.12 48	98.49 20	98.18 50	92.64 117	96.39 79	98.18 66	91.61 58	99.88 5	95.59 73	99.55 25	99.57 24

ETH3D-3000-0.1		97.07 23	96.71 41	98.14 16	98.90 55	95.33 17	97.68 92	98.24 38	91.57 144	97.90 26	98.37 40	92.61 34	99.66 56	95.59 73	99.51 33	99.43 55

mvsmamba		93.83 130	93.46 126	94.93 182	94.88 277	90.85 156	98.55 14	95.49 294	94.24 54	91.29 203	96.97 143	83.04 184	98.14 227	95.56 75	91.17 244	95.78 243

region2R		97.07 23	96.84 30	97.77 38	99.46 2	93.79 58	98.52 16	98.24 38	93.19 92	97.14 47	98.34 45	91.59 60	99.87 8	95.46 76	99.59 17	99.64 13

iter_conf05		93.18 156	92.63 156	94.83 184	96.64 185	90.69 162	97.60 103	95.53 293	92.52 119	91.58 191	96.64 162	76.35 293	98.13 228	95.43 77	91.42 239	95.68 254

OPU-MVS				98.55 3	98.82 60	96.86 3	98.25 36				98.26 58	96.04 2	99.24 126	95.36 78	99.59 17	99.56 27

iter_conf_final		93.60 138	93.11 137	95.04 170	97.13 157	91.30 134	97.92 66	95.65 287	92.98 103	91.60 190	96.64 162	79.28 254	98.13 228	95.34 79	91.49 236	95.70 251

lupinMVS		94.99 98	94.56 98	96.29 110	96.34 205	91.21 139	95.83 253	96.27 260	88.93 222	96.22 83	96.88 149	86.20 137	98.85 167	95.27 80	99.05 90	98.82 118

mPP-MVS		96.86 39	96.60 45	97.64 49	99.40 12	93.44 68	98.50 19	98.09 67	93.27 88	95.95 95	98.33 48	91.04 73	99.88 5	95.20 81	99.57 24	99.60 19

DeepC-MVS_fast	93.89 2	96.93 34	96.64 44	97.78 36	98.64 74	94.30 38	97.41 120	98.04 85	94.81 35	96.59 69	98.37 40	91.24 67	99.64 65	95.16 82	99.52 29	99.42 58
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
jason		94.84 103	94.39 106	96.18 117	95.52 237	90.93 153	96.09 240	96.52 250	89.28 210	96.01 93	97.32 125	84.70 154	98.77 174	95.15 83	98.91 97	98.85 115
jason: jason.
#test#		97.02 27	96.75 38	97.83 29	99.42 7	94.12 48	98.15 48	98.32 22	92.57 118	97.18 44	98.29 54	92.08 44	99.83 26	95.12 84	99.59 17	99.54 34

abl_6		96.40 59	96.21 61	96.98 77	98.89 58	92.20 106	97.89 68	98.03 88	93.34 87	97.22 43	98.42 35	87.93 110	99.72 39	95.10 85	99.07 89	99.02 92

train_agg		96.30 63	95.83 69	97.72 42	98.70 64	94.19 44	96.41 213	98.02 92	88.58 234	96.03 89	97.56 116	92.73 30	99.59 72	95.04 86	99.37 58	99.39 60

agg_prior1		96.22 66	95.77 70	97.56 51	98.67 66	93.79 58	96.28 229	98.00 97	88.76 231	95.68 104	97.55 118	92.70 32	99.57 83	95.01 87	99.32 60	99.32 66

test_prior3		96.46 57	96.20 62	97.23 65	98.67 66	92.99 80	96.35 221	98.00 97	92.80 110	96.03 89	97.59 112	92.01 46	99.41 111	95.01 87	99.38 54	99.29 68

test_prior2							96.35 221		92.80 110	96.03 89	97.59 112	92.01 46		95.01 87	99.38 54

nrg030		94.05 122	93.31 133	96.27 111	95.22 259	94.59 32	98.34 27	97.46 161	92.93 106	91.21 206	96.64 162	87.23 124	98.22 218	94.99 90	85.80 296	95.98 234

VDDNet		93.05 161	92.07 173	96.02 124	96.84 174	90.39 172	98.08 52	95.85 276	86.22 290	95.79 100	98.46 30	67.59 341	99.19 130	94.92 91	94.85 188	98.47 143

APD-MVS		96.95 32	96.60 45	98.01 22	99.03 45	94.93 28	97.72 87	98.10 65	91.50 146	98.01 22	98.32 50	92.33 40	99.58 75	94.85 92	99.51 33	99.53 38
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ETH3D cwj APD-0.16		96.56 54	96.06 64	98.05 20	98.26 100	95.19 22	96.99 162	98.05 84	89.85 195	97.26 41	98.22 61	91.80 52	99.69 48	94.84 93	99.28 66	99.27 73

GST-MVS		96.85 41	96.52 50	97.82 32	99.36 20	94.14 47	98.29 31	98.13 58	92.72 114	96.70 60	98.06 72	91.35 65	99.86 9	94.83 94	99.28 66	99.47 50

MP-MVS		96.77 46	96.45 55	97.72 42	99.39 14	93.80 57	98.41 25	98.06 77	93.37 84	95.54 112	98.34 45	90.59 82	99.88 5	94.83 94	99.54 27	99.49 45
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test9_res														94.81 96	99.38 54	99.45 51

PS-MVSNAJ		95.37 84	95.33 81	95.49 153	97.35 148	90.66 164	95.31 274	97.48 156	93.85 63	96.51 72	95.70 219	88.65 101	99.65 57	94.80 97	98.27 114	96.17 225

HPM-MVS_fast		96.51 55	96.27 59	97.22 67	99.32 24	92.74 86	98.74 9	98.06 77	90.57 181	96.77 57	98.35 42	90.21 86	99.53 93	94.80 97	99.63 14	99.38 62

xiu_mvs_v2_base		95.32 86	95.29 82	95.40 158	97.22 150	90.50 167	95.44 268	97.44 170	93.70 70	96.46 76	96.18 189	88.59 104	99.53 93	94.79 99	97.81 126	96.17 225

CSCG		96.05 69	95.91 67	96.46 96	99.24 30	90.47 168	98.30 30	98.57 12	89.01 217	93.97 141	97.57 114	92.62 33	99.76 34	94.66 100	99.27 68	99.15 81

EIA-MVS		95.53 82	95.47 75	95.71 139	97.06 163	89.63 188	97.82 75	97.87 113	93.57 72	93.92 142	95.04 244	90.61 81	98.95 159	94.62 101	98.68 102	98.54 133

ZD-MVS					99.05 43	94.59 32		98.08 68	89.22 212	97.03 54	98.10 68	92.52 37	99.65 57	94.58 102	99.31 62

ACMMP		96.27 64	95.93 66	97.28 62	99.24 30	92.62 91	98.25 36	98.81 3	92.99 98	94.56 127	98.39 39	88.96 96	99.85 18	94.57 103	97.63 130	99.36 64
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
PGM-MVS		96.81 44	96.53 49	97.65 47	99.35 22	93.53 66	97.65 96	98.98 1	92.22 125	97.14 47	98.44 32	91.17 71	99.85 18	94.35 104	99.46 44	99.57 24

RRT_MVS		93.10 158	92.83 146	93.93 233	94.76 282	88.04 243	98.47 22	96.55 249	93.44 81	90.01 232	97.04 140	80.64 229	97.93 267	94.33 105	90.21 259	95.83 239

ET-MVSNet_ETH3D		91.49 222	90.11 250	95.63 142	96.40 202	91.57 126	95.34 271	93.48 346	90.60 180	75.58 361	95.49 229	80.08 240	96.79 334	94.25 106	89.76 263	98.52 135

testtj		96.93 34	96.56 48	98.05 20	99.10 36	94.66 31	97.78 79	98.22 43	92.74 113	97.59 29	98.20 65	91.96 49	99.86 9	94.21 107	99.25 72	99.63 14

LFMVS		93.60 138	92.63 156	96.52 88	98.13 113	91.27 136	97.94 64	93.39 347	90.57 181	96.29 81	98.31 51	69.00 334	99.16 134	94.18 108	95.87 171	99.12 86

MVSFormer		95.37 84	95.16 85	95.99 126	96.34 205	91.21 139	98.22 41	97.57 147	91.42 150	96.22 83	97.32 125	86.20 137	97.92 268	94.07 109	99.05 90	98.85 115

test_djsdf		93.07 160	92.76 149	94.00 224	93.49 325	88.70 223	98.22 41	97.57 147	91.42 150	90.08 230	95.55 226	82.85 190	97.92 268	94.07 109	91.58 234	95.40 267

mvs_anonymous		93.82 131	93.74 114	94.06 220	96.44 200	85.41 294	95.81 254	97.05 207	89.85 195	90.09 229	96.36 183	87.44 120	97.75 284	93.97 111	96.69 157	99.02 92

VPA-MVSNet		93.24 151	92.48 166	95.51 150	95.70 231	92.39 97	97.86 70	98.66 10	92.30 124	92.09 184	95.37 232	80.49 232	98.40 205	93.95 112	85.86 295	95.75 248

agg_prior2														93.94 113	99.38 54	99.50 43

mvs_tets		92.31 189	91.76 183	93.94 231	93.41 327	88.29 233	97.63 101	97.53 151	92.04 134	88.76 268	96.45 178	74.62 304	98.09 238	93.91 114	91.48 237	95.45 263

Effi-MVS+		94.93 99	94.45 104	96.36 105	96.61 186	91.47 129	96.41 213	97.41 175	91.02 165	94.50 128	95.92 202	87.53 117	98.78 172	93.89 115	96.81 152	98.84 117

jajsoiax		92.42 183	91.89 181	94.03 223	93.33 330	88.50 230	97.73 84	97.53 151	92.00 136	88.85 264	96.50 176	75.62 300	98.11 234	93.88 116	91.56 235	95.48 258

XVG-OURS-SEG-HR		93.86 129	93.55 120	94.81 187	97.06 163	88.53 229	95.28 275	97.45 166	91.68 142	94.08 138	97.68 101	82.41 201	98.90 164	93.84 117	92.47 219	96.98 203

PS-MVSNAJss		93.74 134	93.51 124	94.44 204	93.91 312	89.28 209	97.75 81	97.56 150	92.50 120	89.94 233	96.54 174	88.65 101	98.18 223	93.83 118	90.90 250	95.86 235

EPNet		95.20 91	94.56 98	97.14 71	92.80 338	92.68 88	97.85 73	94.87 325	96.64 1	92.46 170	97.80 94	86.23 134	99.65 57	93.72 119	98.62 104	99.10 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		95.27 87	94.91 90	96.38 103	98.20 106	90.86 155	97.27 135	98.25 36	90.21 186	94.18 135	97.27 127	87.48 119	99.73 36	93.53 120	97.77 128	98.55 132

CPTT-MVS		95.57 81	95.19 84	96.70 80	99.27 28	91.48 128	98.33 28	98.11 63	87.79 258	95.17 118	98.03 74	87.09 125	99.61 66	93.51 121	99.42 49	99.02 92

MVSTER		93.20 152	92.81 148	94.37 208	96.56 192	89.59 191	97.06 153	97.12 198	91.24 157	91.30 200	95.96 200	82.02 208	98.05 245	93.48 122	90.55 254	95.47 261

PVSNet_BlendedMVS		94.06 121	93.92 110	94.47 203	98.27 97	89.46 199	96.73 185	98.36 17	90.17 187	94.36 130	95.24 238	88.02 107	99.58 75	93.44 123	90.72 253	94.36 320

PVSNet_Blended		94.87 102	94.56 98	95.81 131	98.27 97	89.46 199	95.47 267	98.36 17	88.84 225	94.36 130	96.09 197	88.02 107	99.58 75	93.44 123	98.18 117	98.40 151

3Dnovator	91.36 5	95.19 92	94.44 105	97.44 55	96.56 192	93.36 72	98.65 11	98.36 17	94.12 56	89.25 258	98.06 72	82.20 205	99.77 33	93.41 125	99.32 60	99.18 78

EPP-MVSNet		95.22 90	95.04 88	95.76 132	97.49 147	89.56 192	98.67 10	97.00 213	90.69 171	94.24 133	97.62 110	89.79 91	98.81 170	93.39 126	96.49 162	98.92 107

CHOSEN 280x420		93.12 157	92.72 154	94.34 210	96.71 184	87.27 258	90.29 354	97.72 130	86.61 284	91.34 197	95.29 234	84.29 162	98.41 204	93.25 127	98.94 95	97.35 198

3Dnovator+	91.43 4	95.40 83	94.48 103	98.16 15	96.90 172	95.34 16	98.48 21	97.87 113	94.65 44	88.53 273	98.02 76	83.69 168	99.71 42	93.18 128	98.96 94	99.44 53

test_yl		94.78 105	94.23 107	96.43 98	97.74 132	91.22 137	96.85 174	97.10 200	91.23 158	95.71 102	96.93 144	84.30 160	99.31 121	93.10 129	95.12 184	98.75 120

DCV-MVSNet		94.78 105	94.23 107	96.43 98	97.74 132	91.22 137	96.85 174	97.10 200	91.23 158	95.71 102	96.93 144	84.30 160	99.31 121	93.10 129	95.12 184	98.75 120

test1111		93.19 153	92.82 147	94.30 213	97.58 145	84.56 309	98.21 43	89.02 368	93.53 77	94.58 126	98.21 62	72.69 314	99.05 152	93.06 131	98.48 109	99.28 71

ECVR-MVS		93.19 153	92.73 153	94.57 201	97.66 137	85.41 294	98.21 43	88.23 369	93.43 82	94.70 124	98.21 62	72.57 315	99.07 149	93.05 132	98.49 107	99.25 74

HQP_MVS		93.78 133	93.43 129	94.82 185	96.21 209	89.99 178	97.74 82	97.51 153	94.85 30	91.34 197	96.64 162	81.32 219	98.60 191	93.02 133	92.23 222	95.86 235

plane_prior5								97.51 153					98.60 191	93.02 133	92.23 222	95.86 235

test2506		91.60 214	90.78 222	94.04 222	97.66 137	83.81 317	98.27 33	75.53 380	93.43 82	95.23 116	98.21 62	67.21 344	99.07 149	93.01 135	98.49 107	99.25 74

MVS_Test		94.89 101	94.62 96	95.68 140	96.83 176	89.55 193	96.70 189	97.17 194	91.17 160	95.60 109	96.11 196	87.87 111	98.76 175	93.01 135	97.17 147	98.72 124

bld_raw_dy_0_64		92.37 186	91.69 187	94.39 207	94.28 304	89.73 187	97.71 89	93.65 344	92.78 112	90.46 214	96.67 160	75.88 295	97.97 256	92.92 137	90.89 251	95.48 258

CLD-MVS		92.98 164	92.53 163	94.32 211	96.12 218	89.20 211	95.28 275	97.47 159	92.66 115	89.90 234	95.62 222	80.58 230	98.40 205	92.73 138	92.40 220	95.38 269
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XVG-OURS		93.72 135	93.35 132	94.80 190	97.07 160	88.61 224	94.79 286	97.46 161	91.97 137	93.99 139	97.86 87	81.74 214	98.88 166	92.64 139	92.67 217	96.92 207

ETH3 D test6400		96.16 67	95.52 73	98.07 19	98.90 55	95.06 26	97.03 154	98.21 44	88.16 247	96.64 65	97.70 99	91.18 70	99.67 53	92.44 140	99.47 42	99.48 47

旧先验2							95.94 249		81.66 339	97.34 40			98.82 169	92.26 141

CDPH-MVS		95.97 72	95.38 79	97.77 38	98.93 51	94.44 35	96.35 221	97.88 111	86.98 277	96.65 64	97.89 82	91.99 48	99.47 104	92.26 141	99.46 44	99.39 60

FIs		94.09 120	93.70 115	95.27 161	95.70 231	92.03 111	98.10 50	98.68 8	93.36 86	90.39 216	96.70 156	87.63 115	97.94 264	92.25 143	90.50 256	95.84 238

LPG-MVS_test		92.94 167	92.56 160	94.10 218	96.16 214	88.26 235	97.65 96	97.46 161	91.29 153	90.12 226	97.16 133	79.05 257	98.73 178	92.25 143	91.89 230	95.31 273

LGP-MVS_train				94.10 218	96.16 214	88.26 235		97.46 161	91.29 153	90.12 226	97.16 133	79.05 257	98.73 178	92.25 143	91.89 230	95.31 273

cascas		91.20 238	90.08 251	94.58 200	94.97 269	89.16 214	93.65 323	97.59 145	79.90 350	89.40 250	92.92 320	75.36 301	98.36 209	92.14 146	94.75 192	96.23 222

OPM-MVS		93.28 150	92.76 149	94.82 185	94.63 290	90.77 160	96.65 195	97.18 192	93.72 68	91.68 189	97.26 128	79.33 253	98.63 188	92.13 147	92.28 221	95.07 284
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BP-MVS														92.13 147

HQP-MVS		93.19 153	92.74 152	94.54 202	95.86 224	89.33 205	96.65 195	97.39 176	93.55 73	90.14 220	95.87 204	80.95 222	98.50 199	92.13 147	92.10 227	95.78 243

DP-MVS Recon		95.68 77	95.12 87	97.37 57	99.19 33	94.19 44	97.03 154	98.08 68	88.35 241	95.09 119	97.65 105	89.97 89	99.48 103	92.08 150	98.59 105	98.44 148

VPNet		92.23 195	91.31 201	94.99 174	95.56 235	90.96 151	97.22 143	97.86 117	92.96 105	90.96 208	96.62 171	75.06 302	98.20 220	91.90 151	83.65 330	95.80 242

sss		94.51 109	93.80 113	96.64 81	97.07 160	91.97 114	96.32 225	98.06 77	88.94 221	94.50 128	96.78 151	84.60 155	99.27 124	91.90 151	96.02 167	98.68 128

anonymousdsp		92.16 198	91.55 192	93.97 227	92.58 342	89.55 193	97.51 111	97.42 174	89.42 207	88.40 274	94.84 253	80.66 228	97.88 273	91.87 153	91.28 242	94.48 316

ACMP	89.59 10	92.62 178	92.14 172	94.05 221	96.40 202	88.20 238	97.36 127	97.25 190	91.52 145	88.30 277	96.64 162	78.46 269	98.72 181	91.86 154	91.48 237	95.23 280
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HyFIR lowres test		93.66 136	92.92 143	95.87 129	98.24 101	89.88 183	94.58 290	98.49 13	85.06 307	93.78 144	95.78 213	82.86 189	98.67 185	91.77 155	95.71 176	99.07 91

UGNet		94.04 123	93.28 134	96.31 107	96.85 173	91.19 142	97.88 69	97.68 135	94.40 49	93.00 162	96.18 189	73.39 313	99.61 66	91.72 156	98.46 110	98.13 163
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
UniMVSNet_NR-MVSNet		93.37 147	92.67 155	95.47 156	95.34 248	92.83 84	97.17 147	98.58 11	92.98 103	90.13 224	95.80 209	88.37 106	97.85 274	91.71 157	83.93 325	95.73 250

DU-MVS		92.90 169	92.04 174	95.49 153	94.95 271	92.83 84	97.16 148	98.24 38	93.02 97	90.13 224	95.71 217	83.47 172	97.85 274	91.71 157	83.93 325	95.78 243

Effi-MVS+-dtu		93.08 159	93.21 136	92.68 282	96.02 221	83.25 324	97.14 151	96.72 233	93.85 63	91.20 207	93.44 314	83.08 181	98.30 214	91.69 159	95.73 175	96.50 218

mvs-test1		93.63 137	93.69 116	93.46 255	96.02 221	84.61 308	97.24 137	96.72 233	93.85 63	92.30 177	95.76 214	83.08 181	98.89 165	91.69 159	96.54 160	96.87 209

UniMVSNet (Re)		93.31 149	92.55 161	95.61 144	95.39 242	93.34 73	97.39 124	98.71 6	93.14 94	90.10 228	94.83 254	87.71 112	98.03 249	91.67 161	83.99 324	95.46 262

LCM-MVSNet-Re		92.50 179	92.52 164	92.44 285	96.82 178	81.89 333	96.92 170	93.71 343	92.41 122	84.30 329	94.60 265	85.08 150	97.03 325	91.51 162	97.36 139	98.40 151

FC-MVSNet-test		93.94 126	93.57 119	95.04 170	95.48 239	91.45 131	98.12 49	98.71 6	93.37 84	90.23 219	96.70 156	87.66 113	97.85 274	91.49 163	90.39 257	95.83 239

PMMVS		92.86 171	92.34 168	94.42 206	94.92 273	86.73 272	94.53 292	96.38 256	84.78 312	94.27 132	95.12 243	83.13 180	98.40 205	91.47 164	96.49 162	98.12 164

Vis-MVSNet		95.23 89	94.81 91	96.51 91	97.18 153	91.58 125	98.26 35	98.12 60	94.38 51	94.90 120	98.15 67	82.28 203	98.92 161	91.45 165	98.58 106	99.01 96
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		94.15 115	93.51 124	96.06 121	98.27 97	89.38 202	95.18 281	98.48 15	85.60 298	93.76 145	97.11 136	83.15 179	99.61 66	91.33 166	98.72 101	99.19 77

OMC-MVS		95.09 93	94.70 95	96.25 115	98.46 81	91.28 135	96.43 211	97.57 147	92.04 134	94.77 123	97.96 81	87.01 126	99.09 144	91.31 167	96.77 153	98.36 155

MG-MVS		95.61 79	95.38 79	96.31 107	98.42 84	90.53 166	96.04 242	97.48 156	93.47 80	95.67 107	98.10 68	89.17 94	99.25 125	91.27 168	98.77 99	99.13 83

ACMM	89.79 8	92.96 165	92.50 165	94.35 209	96.30 207	88.71 222	97.58 105	97.36 181	91.40 152	90.53 212	96.65 161	79.77 246	98.75 176	91.24 169	91.64 232	95.59 256
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WTY-MVS		94.71 107	94.02 109	96.79 79	97.71 134	92.05 110	96.59 204	97.35 182	90.61 178	94.64 125	96.93 144	86.41 133	99.39 114	91.20 170	94.71 194	98.94 104

Anonymous20240529		91.98 204	90.73 225	95.73 137	98.14 112	89.40 201	97.99 57	97.72 130	79.63 351	93.54 149	97.41 123	69.94 332	99.56 85	91.04 171	91.11 245	98.22 160

test_part1		92.21 197	91.10 211	95.51 150	97.80 129	92.66 89	98.02 56	97.68 135	89.79 198	88.80 267	96.02 198	76.85 286	98.18 223	90.86 172	84.11 323	95.69 252

AUN-MVS		91.76 209	90.75 224	94.81 187	97.00 169	88.57 226	96.65 195	96.49 251	89.63 200	92.15 180	96.12 193	78.66 266	98.50 199	90.83 173	79.18 348	97.36 197

CANet_DTU		94.37 110	93.65 118	96.55 87	96.46 199	92.13 108	96.21 235	96.67 241	94.38 51	93.53 150	97.03 141	79.34 252	99.71 42	90.76 174	98.45 111	97.82 180

ab-mvs		93.57 141	92.55 161	96.64 81	97.28 149	91.96 115	95.40 269	97.45 166	89.81 197	93.22 160	96.28 186	79.62 249	99.46 105	90.74 175	93.11 211	98.50 138

CostFormer		91.18 241	90.70 226	92.62 283	94.84 279	81.76 334	94.09 309	94.43 332	84.15 318	92.72 169	93.77 303	79.43 251	98.20 220	90.70 176	92.18 225	97.90 173

Anonymous202405211		92.07 201	90.83 221	95.76 132	98.19 108	88.75 221	97.58 105	95.00 316	86.00 293	93.64 146	97.45 120	66.24 351	99.53 93	90.68 177	92.71 215	99.01 96

tpmrst		91.44 224	91.32 200	91.79 301	95.15 262	79.20 356	93.42 327	95.37 298	88.55 237	93.49 151	93.67 308	82.49 199	98.27 215	90.41 178	89.34 266	97.90 173

thisisatest0530		93.03 162	92.21 171	95.49 153	97.07 160	89.11 215	97.49 116	92.19 355	90.16 188	94.09 137	96.41 180	76.43 292	99.05 152	90.38 179	95.68 177	98.31 157

UA-Net		95.95 73	95.53 72	97.20 69	97.67 135	92.98 82	97.65 96	98.13 58	94.81 35	96.61 67	98.35 42	88.87 97	99.51 98	90.36 180	97.35 140	99.11 87

UniMVSNet_ETH3D		91.34 232	90.22 247	94.68 195	94.86 278	87.86 250	97.23 142	97.46 161	87.99 250	89.90 234	96.92 147	66.35 349	98.23 217	90.30 181	90.99 248	97.96 170

tttt0517		92.96 165	92.33 169	94.87 183	97.11 158	87.16 264	97.97 62	92.09 356	90.63 176	93.88 143	97.01 142	76.50 289	99.06 151	90.29 182	95.45 179	98.38 153

FA-MVS(test-final)		93.52 143	92.92 143	95.31 160	96.77 180	88.54 228	94.82 285	96.21 265	89.61 201	94.20 134	95.25 237	83.24 176	99.14 137	90.01 183	96.16 166	98.25 159

IS-MVSNet		94.90 100	94.52 101	96.05 122	97.67 135	90.56 165	98.44 23	96.22 263	93.21 89	93.99 139	97.74 97	85.55 145	98.45 203	89.98 184	97.86 124	99.14 82

miper_enhance_ethall		91.54 220	91.01 213	93.15 266	95.35 247	87.07 266	93.97 311	96.90 222	86.79 281	89.17 259	93.43 316	86.55 130	97.64 292	89.97 185	86.93 286	94.74 310

EI-MVSNet		93.03 162	92.88 145	93.48 253	95.77 229	86.98 267	96.44 209	97.12 198	90.66 174	91.30 200	97.64 108	86.56 129	98.05 245	89.91 186	90.55 254	95.41 264

IterMVS-LS		92.29 191	91.94 179	93.34 259	96.25 208	86.97 268	96.57 207	97.05 207	90.67 172	89.50 249	94.80 256	86.59 128	97.64 292	89.91 186	86.11 294	95.40 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		91.21 237	90.56 232	93.14 267	96.09 220	86.80 270	94.41 297	96.58 248	87.80 257	88.58 272	93.99 296	80.85 227	97.62 295	89.87 188	86.93 286	94.99 287

CDS-MVSNet		94.14 118	93.54 121	95.93 127	96.18 212	91.46 130	96.33 224	97.04 209	88.97 220	93.56 147	96.51 175	87.55 116	97.89 272	89.80 189	95.95 169	98.44 148
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WR-MVS		92.34 187	91.53 193	94.77 192	95.13 264	90.83 157	96.40 216	97.98 102	91.88 138	89.29 255	95.54 227	82.50 198	97.80 279	89.79 190	85.27 304	95.69 252

NR-MVSNet		92.34 187	91.27 204	95.53 149	94.95 271	93.05 79	97.39 124	98.07 74	92.65 116	84.46 327	95.71 217	85.00 151	97.77 283	89.71 191	83.52 331	95.78 243

Anonymous20231211		90.63 260	89.42 271	94.27 214	98.24 101	89.19 213	98.05 54	97.89 109	79.95 349	88.25 280	94.96 246	72.56 316	98.13 228	89.70 192	85.14 306	95.49 257

testdata				95.46 157	98.18 110	88.90 219		97.66 137	82.73 333	97.03 54	98.07 71	90.06 87	98.85 167	89.67 193	98.98 93	98.64 130

Baseline_NR-MVSNet		91.20 238	90.62 228	92.95 273	93.83 315	88.03 244	97.01 161	95.12 312	88.42 239	89.70 240	95.13 242	83.47 172	97.44 311	89.66 194	83.24 333	93.37 338

DPM-MVS		95.69 76	94.92 89	98.01 22	98.08 115	95.71 9	95.27 277	97.62 142	90.43 184	95.55 110	97.07 138	91.72 53	99.50 101	89.62 195	98.94 95	98.82 118

XXY-MVS		92.16 198	91.23 206	94.95 179	94.75 284	90.94 152	97.47 117	97.43 173	89.14 214	88.90 261	96.43 179	79.71 247	98.24 216	89.56 196	87.68 279	95.67 255

miper_ehance_all_eth		91.59 215	91.13 210	92.97 272	95.55 236	86.57 277	94.47 293	96.88 225	87.77 259	88.88 263	94.01 294	86.22 135	97.54 301	89.49 197	86.93 286	94.79 306

XVG-ACMP-BASELINE		90.93 250	90.21 248	93.09 268	94.31 302	85.89 287	95.33 272	97.26 188	91.06 164	89.38 251	95.44 231	68.61 336	98.60 191	89.46 198	91.05 246	94.79 306

thisisatest0515		92.29 191	91.30 202	95.25 162	96.60 187	88.90 219	94.36 299	92.32 354	87.92 252	93.43 153	94.57 266	77.28 284	99.00 156	89.42 199	95.86 172	97.86 176

c3_l		91.38 227	90.89 215	92.88 275	95.58 234	86.30 280	94.68 288	96.84 229	88.17 245	88.83 266	94.23 286	85.65 144	97.47 308	89.36 200	84.63 314	94.89 296

AdaColmap		94.34 111	93.68 117	96.31 107	98.59 76	91.68 120	96.59 204	97.81 121	89.87 192	92.15 180	97.06 139	83.62 171	99.54 90	89.34 201	98.07 120	97.70 184

TranMVSNet+NR-MVSNet		92.50 179	91.63 189	95.14 166	94.76 282	92.07 109	97.53 110	98.11 63	92.90 107	89.56 246	96.12 193	83.16 178	97.60 297	89.30 202	83.20 334	95.75 248

D2MVS		91.30 234	90.95 214	92.35 287	94.71 286	85.52 292	96.18 237	98.21 44	88.89 223	86.60 310	93.82 301	79.92 244	97.95 263	89.29 203	90.95 249	93.56 334

1314		92.81 175	92.03 175	95.14 166	95.33 251	89.52 196	96.04 242	97.44 170	87.72 262	86.25 313	95.33 233	83.84 166	98.79 171	89.26 204	97.05 149	97.11 201

v2v482		91.59 215	90.85 219	93.80 238	93.87 314	88.17 240	96.94 169	96.88 225	89.54 202	89.53 247	94.90 250	81.70 215	98.02 250	89.25 205	85.04 310	95.20 281

114514_t		93.95 125	93.06 139	96.63 83	99.07 41	91.61 122	97.46 119	97.96 104	77.99 357	93.00 162	97.57 114	86.14 139	99.33 118	89.22 206	99.15 81	98.94 104

PAPM_NR		95.01 94	94.59 97	96.26 112	98.89 58	90.68 163	97.24 137	97.73 127	91.80 139	92.93 167	96.62 171	89.13 95	99.14 137	89.21 207	97.78 127	98.97 100

baseline1		92.82 174	91.90 180	95.55 148	97.20 152	90.77 160	97.19 145	94.58 330	92.20 127	92.36 174	96.34 184	84.16 163	98.21 219	89.20 208	83.90 328	97.68 185

IB-MVS	87.33 17	89.91 275	88.28 287	94.79 191	95.26 258	87.70 253	95.12 283	93.95 342	89.35 209	87.03 304	92.49 325	70.74 326	99.19 130	89.18 209	81.37 341	97.49 195
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
HY-MVS	89.66 9	93.87 128	92.95 142	96.63 83	97.10 159	92.49 95	95.64 261	96.64 242	89.05 216	93.00 162	95.79 212	85.77 143	99.45 107	89.16 210	94.35 196	97.96 170

V42		91.58 217	90.87 216	93.73 240	94.05 309	88.50 230	97.32 131	96.97 214	88.80 230	89.71 239	94.33 278	82.54 197	98.05 245	89.01 211	85.07 308	94.64 314

OurMVSNet-221017-0		90.51 263	90.19 249	91.44 310	93.41 327	81.25 337	96.98 164	96.28 259	91.68 142	86.55 311	96.30 185	74.20 307	97.98 253	88.96 212	87.40 284	95.09 283

API-MVS		94.84 103	94.49 102	95.90 128	97.90 124	92.00 113	97.80 77	97.48 156	89.19 213	94.81 122	96.71 154	88.84 98	99.17 133	88.91 213	98.76 100	96.53 216

test-LLR		91.42 225	91.19 208	92.12 291	94.59 291	80.66 340	94.29 303	92.98 349	91.11 162	90.76 210	92.37 327	79.02 259	98.07 242	88.81 214	96.74 154	97.63 186

test-mter		90.19 271	89.54 270	92.12 291	94.59 291	80.66 340	94.29 303	92.98 349	87.68 263	90.76 210	92.37 327	67.67 340	98.07 242	88.81 214	96.74 154	97.63 186

eth_miper_zixun_eth		91.02 245	90.59 230	92.34 288	95.33 251	84.35 310	94.10 308	96.90 222	88.56 236	88.84 265	94.33 278	84.08 164	97.60 297	88.77 216	84.37 320	95.06 285

TAMVS		94.01 124	93.46 126	95.64 141	96.16 214	90.45 169	96.71 188	96.89 224	89.27 211	93.46 152	96.92 147	87.29 122	97.94 264	88.70 217	95.74 174	98.53 134

Patchmatch-RL test		87.38 303	86.24 304	90.81 320	88.74 366	78.40 360	88.12 363	93.17 348	87.11 276	82.17 344	89.29 353	81.95 210	95.60 350	88.64 218	77.02 352	98.41 150

baseline2		91.63 213	90.86 217	93.94 231	94.33 300	86.32 279	95.92 250	91.64 360	89.37 208	86.94 306	94.69 260	81.62 216	98.69 183	88.64 218	94.57 195	96.81 211

TESTMET0.1,1		90.06 273	89.42 271	91.97 294	94.41 298	80.62 342	94.29 303	91.97 358	87.28 273	90.44 215	92.47 326	68.79 335	97.67 289	88.50 220	96.60 159	97.61 190

Vis-MVSNet (Re-imp)		94.15 115	93.88 111	94.95 179	97.61 141	87.92 247	98.10 50	95.80 278	92.22 125	93.02 161	97.45 120	84.53 157	97.91 271	88.24 221	97.97 122	99.02 92

1112_ss		93.37 147	92.42 167	96.21 116	97.05 165	90.99 149	96.31 226	96.72 233	86.87 280	89.83 237	96.69 158	86.51 131	99.14 137	88.12 222	93.67 205	98.50 138

CVMVSNet		91.23 236	91.75 184	89.67 334	95.77 229	74.69 365	96.44 209	94.88 322	85.81 295	92.18 179	97.64 108	79.07 256	95.58 351	88.06 223	95.86 172	98.74 122

MAR-MVS		94.22 113	93.46 126	96.51 91	98.00 117	92.19 107	97.67 93	97.47 159	88.13 249	93.00 162	95.84 206	84.86 153	99.51 98	87.99 224	98.17 118	97.83 179
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
原ACMM1				96.38 103	98.59 76	91.09 148		97.89 109	87.41 269	95.22 117	97.68 101	90.25 84	99.54 90	87.95 225	99.12 86	98.49 140

CP-MVSNet		91.89 206	91.24 205	93.82 237	95.05 267	88.57 226	97.82 75	98.19 48	91.70 141	88.21 281	95.76 214	81.96 209	97.52 305	87.86 226	84.65 313	95.37 270

v148		90.99 246	90.38 236	92.81 278	93.83 315	85.80 288	96.78 183	96.68 239	89.45 206	88.75 269	93.93 298	82.96 188	97.82 278	87.83 227	83.25 332	94.80 304

v1144		91.37 229	90.60 229	93.68 245	93.89 313	88.23 237	96.84 176	97.03 211	88.37 240	89.69 241	94.39 274	82.04 207	97.98 253	87.80 228	85.37 301	94.84 298

DIV-MVS_self_test		90.97 248	90.33 237	92.88 275	95.36 246	86.19 284	94.46 295	96.63 245	87.82 255	88.18 282	94.23 286	82.99 185	97.53 303	87.72 229	85.57 298	94.93 292

gm-plane-assit					93.22 331	78.89 359			84.82 311		93.52 311		98.64 187	87.72 229

GeoE		93.89 127	93.28 134	95.72 138	96.96 171	89.75 186	98.24 39	96.92 221	89.47 205	92.12 182	97.21 131	84.42 158	98.39 208	87.71 231	96.50 161	99.01 96

cl____		90.96 249	90.32 238	92.89 274	95.37 245	86.21 283	94.46 295	96.64 242	87.82 255	88.15 283	94.18 289	82.98 186	97.54 301	87.70 232	85.59 297	94.92 294

pmmvs4		90.93 250	89.85 259	94.17 216	93.34 329	90.79 159	94.60 289	96.02 270	84.62 313	87.45 294	95.15 240	81.88 212	97.45 310	87.70 232	87.87 278	94.27 325

Test_1112_low_res		92.84 173	91.84 182	95.85 130	97.04 166	89.97 181	95.53 265	96.64 242	85.38 301	89.65 243	95.18 239	85.86 141	99.10 141	87.70 232	93.58 210	98.49 140

无先验							95.79 255	97.87 113	83.87 323				99.65 57	87.68 235		98.89 112

1121		94.71 107	93.83 112	97.34 58	98.57 79	93.64 63	96.04 242	97.73 127	81.56 341	95.68 104	97.85 88	90.23 85	99.65 57	87.68 235	99.12 86	98.73 123

Fast-Effi-MVS+		93.46 144	92.75 151	95.59 145	96.77 180	90.03 175	96.81 180	97.13 197	88.19 244	91.30 200	94.27 283	86.21 136	98.63 188	87.66 237	96.46 164	98.12 164

CNLPA		94.28 112	93.53 122	96.52 88	98.38 88	92.55 93	96.59 204	96.88 225	90.13 189	91.91 186	97.24 129	85.21 148	99.09 144	87.64 238	97.83 125	97.92 172

v8		91.29 235	90.53 233	93.57 250	94.15 305	88.12 242	97.34 128	97.06 206	88.99 218	88.32 276	94.26 285	83.08 181	98.01 251	87.62 239	83.92 327	94.57 315

pmmvs5		89.86 278	88.87 280	92.82 277	92.86 336	86.23 282	96.26 230	95.39 296	84.24 317	87.12 301	94.51 267	74.27 306	97.36 317	87.61 240	87.57 280	94.86 297

Fast-Effi-MVS+-dtu		92.29 191	91.99 177	93.21 265	95.27 255	85.52 292	97.03 154	96.63 245	92.09 132	89.11 260	95.14 241	80.33 236	98.08 239	87.54 241	94.74 193	96.03 233

OpenMVS	89.19 12	92.86 171	91.68 188	96.40 100	95.34 248	92.73 87	98.27 33	98.12 60	84.86 310	85.78 316	97.75 96	78.89 264	99.74 35	87.50 242	98.65 103	96.73 213

miper_lstm_enhance		90.50 264	90.06 254	91.83 298	95.33 251	83.74 318	93.86 316	96.70 238	87.56 266	87.79 289	93.81 302	83.45 174	96.92 331	87.39 243	84.62 315	94.82 301

IterMVS-SCA-FT		90.31 266	89.81 261	91.82 299	95.52 237	84.20 313	94.30 302	96.15 267	90.61 178	87.39 297	94.27 283	75.80 297	96.44 337	87.34 244	86.88 290	94.82 301

PLC	91.00 6	94.11 119	93.43 129	96.13 118	98.58 78	91.15 147	96.69 191	97.39 176	87.29 272	91.37 196	96.71 154	88.39 105	99.52 97	87.33 245	97.13 148	97.73 182
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		90.25 268	89.74 266	91.76 304	93.92 311	79.73 352	93.98 310	93.54 345	88.28 242	91.99 185	93.25 317	77.51 283	97.44 311	87.30 246	87.94 277	98.12 164

GA-MVS		91.38 227	90.31 239	94.59 196	94.65 288	87.62 254	94.34 300	96.19 266	90.73 170	90.35 217	93.83 299	71.84 318	97.96 261	87.22 247	93.61 208	98.21 161

BH-untuned		92.94 167	92.62 158	93.92 234	97.22 150	86.16 285	96.40 216	96.25 262	90.06 190	89.79 238	96.17 191	83.19 177	98.35 210	87.19 248	97.27 143	97.24 200

v144192		91.06 243	90.28 241	93.39 257	93.66 320	87.23 261	96.83 177	97.07 204	87.43 268	89.69 241	94.28 282	81.48 217	98.00 252	87.18 249	84.92 312	94.93 292

RPSCF		90.75 255	90.86 217	90.42 327	96.84 174	76.29 363	95.61 262	96.34 257	83.89 321	91.38 195	97.87 85	76.45 290	98.78 172	87.16 250	92.23 222	96.20 223

PS-CasMVS		91.55 219	90.84 220	93.69 244	94.96 270	88.28 234	97.84 74	98.24 38	91.46 148	88.04 285	95.80 209	79.67 248	97.48 307	87.02 251	84.54 318	95.31 273

pm-mvs1		90.72 257	89.65 269	93.96 228	94.29 303	89.63 188	97.79 78	96.82 230	89.07 215	86.12 315	95.48 230	78.61 267	97.78 281	86.97 252	81.67 339	94.46 317

IterMVS		90.15 272	89.67 267	91.61 306	95.48 239	83.72 319	94.33 301	96.12 268	89.99 191	87.31 300	94.15 291	75.78 299	96.27 340	86.97 252	86.89 289	94.83 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		93.58 140	92.98 141	95.37 159	98.40 85	88.98 217	97.18 146	97.29 187	87.75 261	90.49 213	97.10 137	85.21 148	99.50 101	86.70 254	96.72 156	97.63 186

PVSNet	86.66 18	92.24 194	91.74 186	93.73 240	97.77 131	83.69 321	92.88 336	96.72 233	87.91 253	93.00 162	94.86 252	78.51 268	99.05 152	86.53 255	97.45 137	98.47 143

v1192		91.07 242	90.23 245	93.58 249	93.70 318	87.82 251	96.73 185	97.07 204	87.77 259	89.58 244	94.32 280	80.90 226	97.97 256	86.52 256	85.48 299	94.95 288

新几何1				97.32 59	98.60 75	93.59 64		97.75 124	81.58 340	95.75 101	97.85 88	90.04 88	99.67 53	86.50 257	99.13 83	98.69 127

v10		91.04 244	90.23 245	93.49 252	94.12 306	88.16 241	97.32 131	97.08 203	88.26 243	88.29 278	94.22 288	82.17 206	97.97 256	86.45 258	84.12 322	94.33 321

v1921920		90.85 252	90.03 255	93.29 261	93.55 321	86.96 269	96.74 184	97.04 209	87.36 270	89.52 248	94.34 277	80.23 238	97.97 256	86.27 259	85.21 305	94.94 290

MDTV_nov1_ep13_2view						70.35 370	93.10 334		83.88 322	93.55 148		82.47 200		86.25 260		98.38 153

test_post1							92.81 338				16.58 380	80.53 231	97.68 288	86.20 261

SCA		91.84 207	91.18 209	93.83 236	95.59 233	84.95 304	94.72 287	95.58 290	90.82 166	92.25 178	93.69 305	75.80 297	98.10 235	86.20 261	95.98 168	98.45 145

PAPR		94.18 114	93.42 131	96.48 93	97.64 139	91.42 132	95.55 263	97.71 134	88.99 218	92.34 176	95.82 208	89.19 93	99.11 140	86.14 263	97.38 138	98.90 109

GBi-Net		91.35 230	90.27 242	94.59 196	96.51 195	91.18 143	97.50 112	96.93 217	88.82 227	89.35 252	94.51 267	73.87 308	97.29 320	86.12 264	88.82 269	95.31 273

test1		91.35 230	90.27 242	94.59 196	96.51 195	91.18 143	97.50 112	96.93 217	88.82 227	89.35 252	94.51 267	73.87 308	97.29 320	86.12 264	88.82 269	95.31 273

FMVSNet3		91.78 208	90.69 227	95.03 172	96.53 194	92.27 103	97.02 157	96.93 217	89.79 198	89.35 252	94.65 263	77.01 285	97.47 308	86.12 264	88.82 269	95.35 271

EPMVS		90.70 258	89.81 261	93.37 258	94.73 285	84.21 312	93.67 322	88.02 370	89.50 204	92.38 173	93.49 312	77.82 281	97.78 281	86.03 267	92.68 216	98.11 167

MVS		91.71 210	90.44 234	95.51 150	95.20 261	91.59 124	96.04 242	97.45 166	73.44 364	87.36 298	95.60 223	85.42 146	99.10 141	85.97 268	97.46 133	95.83 239

testdata2													99.67 53	85.96 269

K. test v3		87.64 302	86.75 303	90.32 328	93.02 335	79.48 354	96.61 201	92.08 357	90.66 174	80.25 353	94.09 292	67.21 344	96.65 336	85.96 269	80.83 343	94.83 299

WR-MVS_H		92.00 203	91.35 198	93.95 229	95.09 266	89.47 197	98.04 55	98.68 8	91.46 148	88.34 275	94.68 261	85.86 141	97.56 299	85.77 271	84.24 321	94.82 301

gg-mvs-nofinetune		87.82 300	85.61 309	94.44 204	94.46 295	89.27 210	91.21 349	84.61 375	80.88 344	89.89 236	74.98 368	71.50 320	97.53 303	85.75 272	97.21 145	96.51 217

tpm2		89.96 274	89.21 275	92.23 290	94.91 275	81.25 337	93.78 318	94.42 333	80.62 347	91.56 192	93.44 314	76.44 291	97.94 264	85.60 273	92.08 229	97.49 195

v1240		90.70 258	89.85 259	93.23 263	93.51 324	86.80 270	96.61 201	97.02 212	87.16 275	89.58 244	94.31 281	79.55 250	97.98 253	85.52 274	85.44 300	94.90 295

PEN-MVS		91.20 238	90.44 234	93.48 253	94.49 294	87.91 249	97.76 80	98.18 50	91.29 153	87.78 290	95.74 216	80.35 235	97.33 318	85.46 275	82.96 335	95.19 282

QAPM		93.45 145	92.27 170	96.98 77	96.77 180	92.62 91	98.39 26	98.12 60	84.50 315	88.27 279	97.77 95	82.39 202	99.81 30	85.40 276	98.81 98	98.51 137

EU-MVSNet		88.72 292	88.90 279	88.20 339	93.15 333	74.21 366	96.63 200	94.22 338	85.18 304	87.32 299	95.97 199	76.16 294	94.98 355	85.27 277	86.17 292	95.41 264

BH-w/o		92.14 200	91.75 184	93.31 260	96.99 170	85.73 289	95.67 258	95.69 283	88.73 232	89.26 257	94.82 255	82.97 187	98.07 242	85.26 278	96.32 165	96.13 229

FMVSNet2		91.31 233	90.08 251	94.99 174	96.51 195	92.21 104	97.41 120	96.95 215	88.82 227	88.62 270	94.75 258	73.87 308	97.42 313	85.20 279	88.55 274	95.35 271

PM-MVS		83.48 326	81.86 330	88.31 338	87.83 369	77.59 361	93.43 326	91.75 359	86.91 278	80.63 349	89.91 350	44.42 372	95.84 346	85.17 280	76.73 354	91.50 358

LF4IMVS		87.94 299	87.25 296	89.98 331	92.38 347	80.05 350	94.38 298	95.25 306	87.59 265	84.34 328	94.74 259	64.31 356	97.66 291	84.83 281	87.45 281	92.23 351

PatchmatchNet		91.91 205	91.35 198	93.59 248	95.38 243	84.11 314	93.15 332	95.39 296	89.54 202	92.10 183	93.68 307	82.82 191	98.13 228	84.81 282	95.32 181	98.52 135
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs6		87.81 301	86.19 305	92.69 281	91.32 351	86.30 280	97.34 128	96.41 255	80.59 348	84.05 335	94.37 276	67.37 343	97.67 289	84.75 283	79.51 347	94.09 329

v7n		90.76 254	89.86 258	93.45 256	93.54 322	87.60 255	97.70 91	97.37 179	88.85 224	87.65 292	94.08 293	81.08 221	98.10 235	84.68 284	83.79 329	94.66 313

SixPastTwentyTwo		89.15 284	88.54 284	90.98 317	93.49 325	80.28 347	96.70 189	94.70 326	90.78 167	84.15 332	95.57 224	71.78 319	97.71 287	84.63 285	85.07 308	94.94 290

TDRefinement		86.53 308	84.76 318	91.85 297	82.23 373	84.25 311	96.38 219	95.35 299	84.97 309	84.09 333	94.94 247	65.76 354	98.34 213	84.60 286	74.52 357	92.97 340

MVS_0304		88.79 290	87.57 292	92.46 284	94.65 288	86.15 286	96.40 216	97.17 194	86.44 285	88.02 286	91.71 339	56.68 366	97.03 325	84.47 287	92.58 218	94.19 326

ACMH	87.59 16	90.53 262	89.42 271	93.87 235	96.21 209	87.92 247	97.24 137	96.94 216	88.45 238	83.91 336	96.27 187	71.92 317	98.62 190	84.43 288	89.43 265	95.05 286
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	87.92 14	90.20 270	89.18 276	93.25 262	96.48 198	86.45 278	96.99 162	96.68 239	88.83 226	84.79 326	96.22 188	70.16 330	98.53 197	84.42 289	88.04 276	94.77 309

FE-MVS		92.05 202	91.05 212	95.08 169	96.83 176	87.93 246	93.91 315	95.70 281	86.30 287	94.15 136	94.97 245	76.59 288	99.21 128	84.10 290	96.86 150	98.09 168

MS-PatchMatch		90.27 267	89.77 263	91.78 302	94.33 300	84.72 307	95.55 263	96.73 232	86.17 291	86.36 312	95.28 236	71.28 322	97.80 279	84.09 291	98.14 119	92.81 343

PatchMatch-RL		92.90 169	92.02 176	95.56 146	98.19 108	90.80 158	95.27 277	97.18 192	87.96 251	91.86 188	95.68 220	80.44 233	98.99 157	84.01 292	97.54 132	96.89 208

lessismore_v0				90.45 326	91.96 350	79.09 358		87.19 373		80.32 352	94.39 274	66.31 350	97.55 300	84.00 293	76.84 353	94.70 311

CMPMVS	62.92 21	85.62 319	84.92 316	87.74 341	89.14 364	73.12 368	94.17 306	96.80 231	73.98 362	73.65 363	94.93 248	66.36 348	97.61 296	83.95 294	91.28 242	92.48 349
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVP-Stereo		90.74 256	90.08 251	92.71 280	93.19 332	88.20 238	95.86 252	96.27 260	86.07 292	84.86 325	94.76 257	77.84 280	97.75 284	83.88 295	98.01 121	92.17 354
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LS3D		93.57 141	92.61 159	96.47 94	97.59 143	91.61 122	97.67 93	97.72 130	85.17 305	90.29 218	98.34 45	84.60 155	99.73 36	83.85 296	98.27 114	98.06 169

DTE-MVSNet		90.56 261	89.75 265	93.01 270	93.95 310	87.25 259	97.64 100	97.65 139	90.74 169	87.12 301	95.68 220	79.97 243	97.00 329	83.33 297	81.66 340	94.78 308

BH-RMVSNet		92.72 177	91.97 178	94.97 177	97.16 154	87.99 245	96.15 238	95.60 288	90.62 177	91.87 187	97.15 135	78.41 270	98.57 195	83.16 298	97.60 131	98.36 155

pmmvs-eth3d		86.22 313	84.45 319	91.53 307	88.34 367	87.25 259	94.47 293	95.01 315	83.47 328	79.51 356	89.61 352	69.75 333	95.71 348	83.13 299	76.73 354	91.64 355

FMVSNet1		89.88 277	88.31 286	94.59 196	95.41 241	91.18 143	97.50 112	96.93 217	86.62 283	87.41 296	94.51 267	65.94 353	97.29 320	83.04 300	87.43 282	95.31 273

MDTV_nov1_ep13			90.76 223		95.22 259	80.33 345	93.03 335	95.28 303	88.14 248	92.84 168	93.83 299	81.34 218	98.08 239	82.86 301	94.34 197

TR-MVS		91.48 223	90.59 230	94.16 217	96.40 202	87.33 256	95.67 258	95.34 302	87.68 263	91.46 194	95.52 228	76.77 287	98.35 210	82.85 302	93.61 208	96.79 212

JIA-IIPM		88.26 297	87.04 301	91.91 295	93.52 323	81.42 336	89.38 360	94.38 334	80.84 345	90.93 209	80.74 366	79.22 255	97.92 268	82.76 303	91.62 233	96.38 221

PVSNet_0	82.17 19	85.46 320	83.64 323	90.92 318	95.27 255	79.49 353	90.55 353	95.60 288	83.76 324	83.00 342	89.95 349	71.09 323	97.97 256	82.75 304	60.79 371	95.31 273

ambc				86.56 345	83.60 371	70.00 371	85.69 365	94.97 318		80.60 350	88.45 354	37.42 374	96.84 333	82.69 305	75.44 356	92.86 342

USDC		88.94 286	87.83 291	92.27 289	94.66 287	84.96 303	93.86 316	95.90 274	87.34 271	83.40 338	95.56 225	67.43 342	98.19 222	82.64 306	89.67 264	93.66 333

ITE_SJBPF				92.43 286	95.34 248	85.37 297		95.92 272	91.47 147	87.75 291	96.39 182	71.00 324	97.96 261	82.36 307	89.86 262	93.97 330

UnsupCasMVSNet_eth		85.99 315	84.45 319	90.62 324	89.97 359	82.40 330	93.62 324	97.37 179	89.86 193	78.59 358	92.37 327	65.25 355	95.35 354	82.27 308	70.75 363	94.10 327

GG-mvs-BLEND				93.62 246	93.69 319	89.20 211	92.39 343	83.33 376		87.98 288	89.84 351	71.00 324	96.87 332	82.08 309	95.40 180	94.80 304

thres600view7		92.49 181	91.60 190	95.18 164	97.91 123	89.47 197	97.65 96	94.66 327	92.18 131	93.33 155	94.91 249	78.06 277	99.10 141	81.61 310	94.06 202	96.98 203

LTVRE_ROB	88.41 13	90.99 246	89.92 257	94.19 215	96.18 212	89.55 193	96.31 226	97.09 202	87.88 254	85.67 317	95.91 203	78.79 265	98.57 195	81.50 311	89.98 260	94.44 318
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
tpmvs		89.83 279	89.15 277	91.89 296	94.92 273	80.30 346	93.11 333	95.46 295	86.28 288	88.08 284	92.65 322	80.44 233	98.52 198	81.47 312	89.92 261	96.84 210

thres100view900		92.43 182	91.58 191	94.98 176	97.92 122	89.37 203	97.71 89	94.66 327	92.20 127	93.31 156	94.90 250	78.06 277	99.08 146	81.40 313	94.08 199	96.48 219

tfpn200view9		92.38 185	91.52 194	94.95 179	97.85 126	89.29 207	97.41 120	94.88 322	92.19 129	93.27 158	94.46 272	78.17 273	99.08 146	81.40 313	94.08 199	96.48 219

thres400		92.42 183	91.52 194	95.12 168	97.85 126	89.29 207	97.41 120	94.88 322	92.19 129	93.27 158	94.46 272	78.17 273	99.08 146	81.40 313	94.08 199	96.98 203

DP-MVS		92.76 176	91.51 196	96.52 88	98.77 61	90.99 149	97.38 126	96.08 269	82.38 334	89.29 255	97.87 85	83.77 167	99.69 48	81.37 316	96.69 157	98.89 112

thres200		92.23 195	91.39 197	94.75 194	97.61 141	89.03 216	96.60 203	95.09 313	92.08 133	93.28 157	94.00 295	78.39 271	99.04 155	81.26 317	94.18 198	96.19 224

CR-MVSNet		90.82 253	89.77 263	93.95 229	94.45 296	87.19 262	90.23 355	95.68 285	86.89 279	92.40 171	92.36 330	80.91 224	97.05 324	81.09 318	93.95 203	97.60 191

MSDG		91.42 225	90.24 244	94.96 178	97.15 156	88.91 218	93.69 321	96.32 258	85.72 297	86.93 307	96.47 177	80.24 237	98.98 158	80.57 319	95.05 187	96.98 203

dp		88.90 288	88.26 288	90.81 320	94.58 293	76.62 362	92.85 337	94.93 320	85.12 306	90.07 231	93.07 318	75.81 296	98.12 233	80.53 320	87.42 283	97.71 183

tpm cat1		88.36 295	87.21 298	91.81 300	95.13 264	80.55 343	92.58 340	95.70 281	74.97 361	87.45 294	91.96 335	78.01 279	98.17 225	80.39 321	88.74 272	96.72 214

KD-MVS_self_test		85.95 316	84.95 315	88.96 336	89.55 363	79.11 357	95.13 282	96.42 254	85.91 294	84.07 334	90.48 345	70.03 331	94.82 356	80.04 322	72.94 361	92.94 341

AllTest		90.23 269	88.98 278	93.98 225	97.94 120	86.64 273	96.51 208	95.54 291	85.38 301	85.49 319	96.77 152	70.28 328	99.15 135	80.02 323	92.87 212	96.15 227

TestCases				93.98 225	97.94 120	86.64 273		95.54 291	85.38 301	85.49 319	96.77 152	70.28 328	99.15 135	80.02 323	92.87 212	96.15 227

ADS-MVSNet2		89.45 281	88.59 283	92.03 293	95.86 224	82.26 331	90.93 350	94.32 337	83.23 330	91.28 204	91.81 337	79.01 261	95.99 342	79.52 325	91.39 240	97.84 177

ADS-MVSNet		89.89 276	88.68 282	93.53 251	95.86 224	84.89 305	90.93 350	95.07 314	83.23 330	91.28 204	91.81 337	79.01 261	97.85 274	79.52 325	91.39 240	97.84 177

our_test_3		88.78 291	87.98 290	91.20 315	92.45 345	82.53 327	93.61 325	95.69 283	85.77 296	84.88 324	93.71 304	79.99 242	96.78 335	79.47 327	86.24 291	94.28 324

EPNet_dtu		91.71 210	91.28 203	92.99 271	93.76 317	83.71 320	96.69 191	95.28 303	93.15 93	87.02 305	95.95 201	83.37 175	97.38 316	79.46 328	96.84 151	97.88 175
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		88.94 286	87.56 293	93.08 269	94.35 299	88.45 232	97.73 84	95.23 307	87.47 267	84.26 330	95.29 234	79.86 245	97.33 318	79.44 329	74.44 358	93.45 337

EG-PatchMatch MVS		87.02 306	85.44 310	91.76 304	92.67 340	85.00 302	96.08 241	96.45 253	83.41 329	79.52 355	93.49 312	57.10 365	97.72 286	79.34 330	90.87 252	92.56 347

Patchmtry		88.64 293	87.25 296	92.78 279	94.09 307	86.64 273	89.82 358	95.68 285	80.81 346	87.63 293	92.36 330	80.91 224	97.03 325	78.86 331	85.12 307	94.67 312

FMVSNet5		87.29 304	85.79 308	91.78 302	94.80 281	87.28 257	95.49 266	95.28 303	84.09 319	83.85 337	91.82 336	62.95 359	94.17 360	78.48 332	85.34 303	93.91 331

COLMAP_ROB	87.81 15	90.40 265	89.28 274	93.79 239	97.95 119	87.13 265	96.92 170	95.89 275	82.83 332	86.88 309	97.18 132	73.77 311	99.29 123	78.44 333	93.62 207	94.95 288
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240521		86.42 310	85.44 310	89.34 335	90.33 356	79.79 351	96.73 185	95.92 272	83.71 325	83.25 339	91.36 342	63.92 357	96.01 341	78.39 334	85.36 302	92.22 352

test0.0.03 1		89.37 283	88.70 281	91.41 311	92.47 344	85.63 290	95.22 280	92.70 352	91.11 162	86.91 308	93.65 309	79.02 259	93.19 366	78.00 335	89.18 267	95.41 264

MIMVSNet		88.50 294	86.76 302	93.72 242	94.84 279	87.77 252	91.39 345	94.05 339	86.41 286	87.99 287	92.59 324	63.27 358	95.82 347	77.44 336	92.84 214	97.57 193

MDA-MVSNet_test_wron		85.87 317	84.23 321	90.80 322	92.38 347	82.57 326	93.17 330	95.15 310	82.15 335	67.65 365	92.33 333	78.20 272	95.51 352	77.33 337	79.74 344	94.31 323

YYNet1		85.87 317	84.23 321	90.78 323	92.38 347	82.46 329	93.17 330	95.14 311	82.12 336	67.69 364	92.36 330	78.16 275	95.50 353	77.31 338	79.73 345	94.39 319

UnsupCasMVSNet_bld		82.13 330	79.46 333	90.14 330	88.00 368	82.47 328	90.89 352	96.62 247	78.94 354	75.61 360	84.40 364	56.63 367	96.31 339	77.30 339	66.77 367	91.63 356

KD-MVS_2432*1600		84.81 323	82.64 326	91.31 312	91.07 353	85.34 298	91.22 347	95.75 279	85.56 299	83.09 340	90.21 347	67.21 344	95.89 343	77.18 340	62.48 369	92.69 344

miper_refine_blended		84.81 323	82.64 326	91.31 312	91.07 353	85.34 298	91.22 347	95.75 279	85.56 299	83.09 340	90.21 347	67.21 344	95.89 343	77.18 340	62.48 369	92.69 344

PCF-MVS	89.48 11	91.56 218	89.95 256	96.36 105	96.60 187	92.52 94	92.51 341	97.26 188	79.41 352	88.90 261	96.56 173	84.04 165	99.55 88	77.01 342	97.30 142	97.01 202
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
testgi		87.97 298	87.21 298	90.24 329	92.86 336	80.76 339	96.67 194	94.97 318	91.74 140	85.52 318	95.83 207	62.66 360	94.47 359	76.25 343	88.36 275	95.48 258

TinyColmap		86.82 307	85.35 313	91.21 314	94.91 275	82.99 325	93.94 313	94.02 341	83.58 326	81.56 345	94.68 261	62.34 361	98.13 228	75.78 344	87.35 285	92.52 348

ppachtmachnet_test		88.35 296	87.29 295	91.53 307	92.45 345	83.57 322	93.75 319	95.97 271	84.28 316	85.32 322	94.18 289	79.00 263	96.93 330	75.71 345	84.99 311	94.10 327

PAPM		91.52 221	90.30 240	95.20 163	95.30 254	89.83 184	93.38 328	96.85 228	86.26 289	88.59 271	95.80 209	84.88 152	98.15 226	75.67 346	95.93 170	97.63 186

CL-MVSNet_self_test		86.31 312	85.15 314	89.80 333	88.83 365	81.74 335	93.93 314	96.22 263	86.67 282	85.03 323	90.80 344	78.09 276	94.50 357	74.92 347	71.86 362	93.15 339

tfpnnormal		89.70 280	88.40 285	93.60 247	95.15 262	90.10 174	97.56 107	98.16 54	87.28 273	86.16 314	94.63 264	77.57 282	98.05 245	74.48 348	84.59 316	92.65 346

DSMNet-mixed		86.34 311	86.12 307	87.00 344	89.88 360	70.43 369	94.93 284	90.08 366	77.97 358	85.42 321	92.78 321	74.44 305	93.96 361	74.43 349	95.14 183	96.62 215

Patchmatch-test		89.42 282	87.99 289	93.70 243	95.27 255	85.11 300	88.98 361	94.37 335	81.11 342	87.10 303	93.69 305	82.28 203	97.50 306	74.37 350	94.76 191	98.48 142

LCM-MVSNet		72.55 333	69.39 337	82.03 348	70.81 380	65.42 375	90.12 357	94.36 336	55.02 370	65.88 367	81.72 365	24.16 381	89.96 368	74.32 351	68.10 366	90.71 362

new-patchmatchnet		83.18 327	81.87 329	87.11 343	86.88 370	75.99 364	93.70 320	95.18 309	85.02 308	77.30 359	88.40 355	65.99 352	93.88 362	74.19 352	70.18 364	91.47 359

MDA-MVSNet-bldmvs		85.00 321	82.95 325	91.17 316	93.13 334	83.33 323	94.56 291	95.00 316	84.57 314	65.13 369	92.65 322	70.45 327	95.85 345	73.57 353	77.49 351	94.33 321

pmmvs3		79.97 331	77.50 335	87.39 342	82.80 372	79.38 355	92.70 339	90.75 365	70.69 365	78.66 357	87.47 362	51.34 370	93.40 364	73.39 354	69.65 365	89.38 364

test_method		66.11 338	64.89 340	69.79 355	72.62 378	35.23 385	65.19 373	92.83 351	20.35 376	65.20 368	88.08 359	43.14 373	82.70 373	73.12 355	63.46 368	91.45 360

PatchT		88.87 289	87.42 294	93.22 264	94.08 308	85.10 301	89.51 359	94.64 329	81.92 337	92.36 174	88.15 358	80.05 241	97.01 328	72.43 356	93.65 206	97.54 194

Anonymous20231206		87.09 305	86.14 306	89.93 332	91.22 352	80.35 344	96.11 239	95.35 299	83.57 327	84.16 331	93.02 319	73.54 312	95.61 349	72.16 357	86.14 293	93.84 332

MVS-HIRNet		82.47 329	81.21 331	86.26 346	95.38 243	69.21 372	88.96 362	89.49 367	66.28 366	80.79 348	74.08 370	68.48 337	97.39 315	71.93 358	95.47 178	92.18 353

new_pmnet		82.89 328	81.12 332	88.18 340	89.63 361	80.18 348	91.77 344	92.57 353	76.79 360	75.56 362	88.23 357	61.22 362	94.48 358	71.43 359	82.92 336	89.87 363

TAPA-MVS	90.10 7	92.30 190	91.22 207	95.56 146	98.33 92	89.60 190	96.79 181	97.65 139	81.83 338	91.52 193	97.23 130	87.94 109	98.91 163	71.31 360	98.37 112	98.17 162
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test20.03		86.14 314	85.40 312	88.35 337	90.12 357	80.06 349	95.90 251	95.20 308	88.59 233	81.29 346	93.62 310	71.43 321	92.65 367	71.26 361	81.17 342	92.34 350

tmp_tt		51.94 344	53.82 344	46.29 360	33.73 384	45.30 383	78.32 370	67.24 383	18.02 377	50.93 373	87.05 363	52.99 369	53.11 379	70.76 362	25.29 377	40.46 375

MIMVSNet1		84.93 322	83.05 324	90.56 325	89.56 362	84.84 306	95.40 269	95.35 299	83.91 320	80.38 351	92.21 334	57.23 364	93.34 365	70.69 363	82.75 338	93.50 335

RPMNet		88.98 285	87.05 300	94.77 192	94.45 296	87.19 262	90.23 355	98.03 88	77.87 359	92.40 171	87.55 361	80.17 239	99.51 98	68.84 364	93.95 203	97.60 191

N_pmnet		78.73 332	78.71 334	78.79 350	92.80 338	46.50 381	94.14 307	43.71 384	78.61 355	80.83 347	91.66 340	74.94 303	96.36 338	67.24 365	84.45 319	93.50 335

OpenMVS_ROB	81.14 20	84.42 325	82.28 328	90.83 319	90.06 358	84.05 316	95.73 257	94.04 340	73.89 363	80.17 354	91.53 341	59.15 363	97.64 292	66.92 366	89.05 268	90.80 361

PMMVS2		70.19 335	66.92 338	80.01 349	76.35 374	65.67 374	86.22 364	87.58 372	64.83 368	62.38 370	80.29 367	26.78 379	88.49 370	63.79 367	54.07 372	85.88 365

test_0402		86.46 309	84.79 317	91.45 309	95.02 268	85.55 291	96.29 228	94.89 321	80.90 343	82.21 343	93.97 297	68.21 339	97.29 320	62.98 368	88.68 273	91.51 357

DeepMVS_CX				74.68 354	90.84 355	64.34 376		81.61 378	65.34 367	67.47 366	88.01 360	48.60 371	80.13 375	62.33 369	73.68 360	79.58 369

EGC-MVSNET		68.77 336	63.01 341	86.07 347	92.49 343	82.24 332	93.96 312	90.96 364	0.71 381	2.62 382	90.89 343	53.66 368	93.46 363	57.25 370	84.55 317	82.51 367

FPMVS		71.27 334	69.85 336	75.50 352	74.64 375	59.03 377	91.30 346	91.50 361	58.80 369	57.92 371	88.28 356	29.98 377	85.53 372	53.43 371	82.84 337	81.95 368

ANet_high		63.94 339	59.58 342	77.02 351	61.24 382	66.06 373	85.66 366	87.93 371	78.53 356	42.94 374	71.04 371	25.42 380	80.71 374	52.60 372	30.83 375	84.28 366

Gipuma		67.86 337	65.41 339	75.18 353	92.66 341	73.45 367	66.50 372	94.52 331	53.33 371	57.80 372	66.07 372	30.81 375	89.20 369	48.15 373	78.88 350	62.90 372
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	53.92 22	58.58 340	55.40 343	68.12 356	51.00 383	48.64 379	78.86 369	87.10 374	46.77 372	35.84 378	74.28 369	8.76 382	86.34 371	42.07 374	73.91 359	69.38 370
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	50.73 23	53.25 342	48.81 347	66.58 357	65.34 381	57.50 378	72.49 371	70.94 382	40.15 375	39.28 377	63.51 373	6.89 384	73.48 378	38.29 375	42.38 373	68.76 371
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		53.28 341	52.56 345	55.43 358	74.43 376	47.13 380	83.63 368	76.30 379	42.23 373	42.59 375	62.22 374	28.57 378	74.40 376	31.53 376	31.51 374	44.78 373

EMVS		52.08 343	51.31 346	54.39 359	72.62 378	45.39 382	83.84 367	75.51 381	41.13 374	40.77 376	59.65 375	30.08 376	73.60 377	28.31 377	29.90 376	44.18 374

wuyk23d		25.11 345	24.57 349	26.74 361	73.98 377	39.89 384	57.88 374	9.80 385	12.27 378	10.39 379	6.97 381	7.03 383	36.44 380	25.43 378	17.39 378	3.89 378

testmvs		13.36 347	16.33 350	4.48 363	5.04 385	2.26 387	93.18 329	3.28 386	2.70 379	8.24 380	21.66 377	2.29 386	2.19 381	7.58 379	2.96 379	9.00 377

test123		13.04 348	15.66 351	5.18 362	4.51 386	3.45 386	92.50 342	1.81 387	2.50 380	7.58 381	20.15 378	3.67 385	2.18 382	7.13 380	1.07 380	9.90 376

test_blank		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet_test		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

DCPMVS		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

cdsmvs_eth3d_5k		23.24 346	30.99 348	0.00 364	0.00 387	0.00 388	0.00 375	97.63 141	0.00 382	0.00 383	96.88 149	84.38 159	0.00 383	0.00 381	0.00 381	0.00 379

pcd_1.5k_mvsjas		7.39 350	9.85 353	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	88.65 101	0.00 383	0.00 381	0.00 381	0.00 379

sosnet-low-res		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

sosnet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uncertanet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

Regformer		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

ab-mvs-re		8.06 349	10.74 352	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	96.69 158	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

FOURS1					99.55 1	93.34 73	99.29 1	98.35 20	94.98 27	98.49 15

test_one_0601					99.32 24	95.20 21		98.25 36	95.13 19	98.48 16	98.87 6	95.16 7

eth-test2					0.00 387

eth-test					0.00 387

test_241102_ONE					99.42 7	95.30 18		98.27 31	95.09 23	99.19 1	98.81 10	95.54 5	99.65 57

save fliter					98.91 53	94.28 39	97.02 157	98.02 92	95.35 9

test0726					99.45 3	95.36 13	98.31 29	98.29 26	94.92 28	98.99 4	98.92 2	95.08 8

GSMVS																98.45 145

test_part2					99.28 27	95.74 8				98.10 21

sam_mvs1												82.76 192				98.45 145

sam_mvs												81.94 211

MTGPA								98.08 68

test_post											17.58 379	81.76 213	98.08 239

patchmatchnet-post											90.45 346	82.65 196	98.10 235

MTMP							97.86 70	82.03 377

TEST9					98.70 64	94.19 44	96.41 213	98.02 92	88.17 245	96.03 89	97.56 116	92.74 29	99.59 72

test_8					98.67 66	94.06 52	96.37 220	98.01 95	88.58 234	95.98 94	97.55 118	92.73 30	99.58 75

agg_prior					98.67 66	93.79 58		98.00 97		95.68 104			99.57 83

test_prior4						93.66 62	96.42 212

test_prior				97.23 65	98.67 66	92.99 80		98.00 97					99.41 111			99.29 68

新几何2							95.79 255

旧先验1					98.38 88	93.38 70		97.75 124			98.09 70	92.30 43			99.01 92	99.16 79

原ACMM2							95.67 258

test222					98.24 101	92.21 104	95.33 272	97.60 143	79.22 353	95.25 115	97.84 91	88.80 99			99.15 81	98.72 124

segment_acmp												92.89 26

testdata1							95.26 279		93.10 96

test12				97.65 47	98.46 81	94.26 41		97.66 137		95.52 113		90.89 76	99.46 105		99.25 72	99.22 76

plane_prior7					96.21 209	89.98 180

plane_prior6					96.10 219	90.00 176						81.32 219

plane_prior4											96.64 162

plane_prior3						90.00 176			94.46 47	91.34 197

plane_prior2							97.74 82		94.85 30

plane_prior1					96.14 217

plane_prior						89.99 178	97.24 137		94.06 57						92.16 226

n2								0.00 388

nn								0.00 388

door-mid								91.06 363

test11								97.88 111

door								91.13 362

HQP5-MVS						89.33 205

HQP-NCC					95.86 224		96.65 195		93.55 73	90.14 220

ACMP_Plane					95.86 224		96.65 195		93.55 73	90.14 220

HQP4-MVS										90.14 220			98.50 199			95.78 243

HQP3-MVS								97.39 176							92.10 227

HQP2-MVS												80.95 222

NP-MVS					95.99 223	89.81 185					95.87 204

ACMMP++_ref															90.30 258

ACMMP++															91.02 247

Test By Simon												88.73 100

High-resolution multi-view benchmark