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.

test_vis1_n_1920		96.71 114	96.84 96	96.31 245	99.11 97	89.74 312	99.05 64	98.58 137	98.08 3	99.87 1	99.37 25	78.48 320	99.93 18	99.29 1	99.69 50	99.27 120

SED-MVS		99.09 1	98.91 1	99.63 4	99.71 19	99.24 5	99.02 73	98.87 57	97.65 10	99.73 2	99.48 9	97.53 7	99.94 3	98.43 28	99.81 12	99.70 46

test_241102_ONE					99.71 19	99.24 5		98.87 57	97.62 12	99.73 2	99.39 19	97.53 7	99.74 97

SD-MVS		98.64 12	98.68 7	98.53 78	99.33 56	98.36 40	98.90 93	98.85 66	97.28 32	99.72 4	99.39 19	96.63 19	97.60 327	98.17 38	99.85 5	99.64 64
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
test_fmvs1_n		95.90 152	95.99 133	95.63 272	98.67 136	88.32 338	99.26 27	98.22 206	96.40 78	99.67 5	99.26 43	73.91 347	99.70 105	99.02 5	99.50 82	98.87 165

test_vis1_n		95.47 173	95.13 173	96.49 229	97.77 207	90.41 304	99.27 26	98.11 229	96.58 69	99.66 6	99.18 59	67.00 357	99.62 123	99.21 2	99.40 95	99.44 99

mvsany_test1		97.69 66	97.70 57	97.66 147	98.24 171	94.18 225	97.53 271	97.53 284	95.52 115	99.66 6	99.51 5	94.30 84	99.56 131	98.38 31	98.62 131	99.23 124

test_fmvs1		96.42 126	96.67 107	95.66 271	98.82 122	88.53 334	98.80 119	98.20 209	96.39 79	99.64 8	99.20 53	80.35 310	99.67 112	99.04 4	99.57 70	98.78 173

IU-MVS					99.71 19	99.23 7		98.64 125	95.28 129	99.63 9				98.35 33	99.81 12	99.83 7

PC_three_1452									95.08 142	99.60 10	99.16 63	97.86 2	98.47 259	97.52 83	99.72 46	99.74 30

test0726					99.72 12	99.25 2	99.06 62	98.88 50	97.62 12	99.56 11	99.50 6	97.42 9

TSAR-MVS + MP.		98.78 7	98.62 9	99.24 35	99.69 24	98.28 45	99.14 48	98.66 120	96.84 57	99.56 11	99.31 37	96.34 23	99.70 105	98.32 34	99.73 43	99.73 35
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPE-MVS		98.92 5	98.67 8	99.65 2	99.58 32	99.20 9	98.42 185	98.91 44	97.58 15	99.54 13	99.46 14	97.10 12	99.94 3	97.64 72	99.84 10	99.83 7
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		99.08 2	98.89 2	99.64 3	99.17 88	99.23 7	99.69 1	98.88 50	97.32 29	99.53 14	99.47 11	97.81 3	99.94 3	98.47 24	99.72 46	99.74 30

test_241102_TWO								98.87 57	97.65 10	99.53 14	99.48 9	97.34 11	99.94 3	98.43 28	99.80 19	99.83 7

DVP-MVS		99.03 3	98.83 5	99.63 4	99.72 12	99.25 2	98.97 82	98.58 137	97.62 12	99.45 16	99.46 14	97.42 9	99.94 3	98.47 24	99.81 12	99.69 49
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 29	99.45 16	99.46 14	97.88 1	99.94 3	98.47 24	99.86 1	99.85 4

MSP-MVS		98.74 9	98.55 13	99.29 28	99.75 3	98.23 46	99.26 27	98.88 50	97.52 17	99.41 18	98.78 116	96.00 33	99.79 84	97.79 61	99.59 66	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
APDe-MVS		99.02 4	98.84 4	99.55 9	99.57 33	98.96 16	99.39 12	98.93 38	97.38 26	99.41 18	99.54 1	96.66 17	99.84 53	98.86 8	99.85 5	99.87 1

FOURS1					99.82 1	98.66 24	99.69 1	98.95 34	97.46 21	99.39 20

SMA-MVS		98.58 19	98.25 36	99.56 8	99.51 39	99.04 15	98.95 86	98.80 82	93.67 206	99.37 21	99.52 3	96.52 21	99.89 36	98.06 43	99.81 12	99.76 27
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
SteuartSystems-ACMMP		98.90 6	98.75 6	99.36 21	99.22 83	98.43 33	99.10 57	98.87 57	97.38 26	99.35 22	99.40 18	97.78 5	99.87 45	97.77 62	99.85 5	99.78 15
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		98.59 17	98.32 32	99.41 17	99.54 35	98.71 22	99.04 67	98.81 74	95.12 137	99.32 23	99.39 19	96.22 24	99.84 53	97.72 65	99.73 43	99.67 58

dcpmvs_2		98.08 49	98.59 10	96.56 220	99.57 33	90.34 306	99.15 46	98.38 180	96.82 59	99.29 24	99.49 8	95.78 40	99.57 128	98.94 6	99.86 1	99.77 21

test_part2					99.63 29	99.18 10				99.27 25

DeepPCF-MVS	96.37 2	97.93 55	98.48 17	96.30 246	99.00 106	89.54 317	97.43 276	98.87 57	98.16 2	99.26 26	99.38 24	96.12 29	99.64 117	98.30 35	99.77 28	99.72 38

APD-MVS		98.35 42	98.00 50	99.42 16	99.51 39	98.72 21	98.80 119	98.82 69	94.52 164	99.23 27	99.25 47	95.54 47	99.80 74	96.52 126	99.77 28	99.74 30
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_one_0601					99.66 26	99.25 2		98.86 63	97.55 16	99.20 28	99.47 11	97.57 6

APD-MVS_3200maxsize		98.53 27	98.33 31	99.15 44	99.50 41	97.92 60	99.15 46	98.81 74	96.24 83	99.20 28	99.37 25	95.30 57	99.80 74	97.73 64	99.67 52	99.72 38

patch_mono-2		98.36 40	98.87 3	96.82 196	99.53 36	90.68 299	98.64 153	99.29 8	97.88 5	99.19 30	99.52 3	96.80 15	99.97 1	99.11 3	99.86 1	99.82 10

SR-MVS-dyc-post		98.54 26	98.35 24	99.13 45	99.49 45	97.86 61	99.11 54	98.80 82	96.49 72	99.17 31	99.35 31	95.34 55	99.82 62	97.72 65	99.65 55	99.71 42

RE-MVS-def			98.34 27		99.49 45	97.86 61	99.11 54	98.80 82	96.49 72	99.17 31	99.35 31	95.29 58		97.72 65	99.65 55	99.71 42

9.14			98.06 47		99.47 47		98.71 139	98.82 69	94.36 169	99.16 33	99.29 39	96.05 31	99.81 67	97.00 99	99.71 48

ACMMP_NAP		98.61 14	98.30 33	99.55 9	99.62 30	98.95 17	98.82 112	98.81 74	95.80 102	99.16 33	99.47 11	95.37 53	99.92 23	97.89 53	99.75 38	99.79 13

SR-MVS		98.57 22	98.35 24	99.24 35	99.53 36	98.18 49	99.09 58	98.82 69	96.58 69	99.10 35	99.32 35	95.39 51	99.82 62	97.70 69	99.63 60	99.72 38

PGM-MVS		98.49 29	98.23 39	99.27 33	99.72 12	98.08 55	98.99 79	99.49 5	95.43 119	99.03 36	99.32 35	95.56 45	99.94 3	96.80 118	99.77 28	99.78 15

VNet		97.79 60	97.40 74	98.96 55	98.88 116	97.55 71	98.63 155	98.93 38	96.74 63	99.02 37	98.84 109	90.33 155	99.83 55	98.53 16	96.66 189	99.50 84

xiu_mvs_v1_base_debu		97.60 71	97.56 63	97.72 138	98.35 159	95.98 136	97.86 246	98.51 151	97.13 45	99.01 38	98.40 156	91.56 127	99.80 74	98.53 16	98.68 126	97.37 224

xiu_mvs_v1_base		97.60 71	97.56 63	97.72 138	98.35 159	95.98 136	97.86 246	98.51 151	97.13 45	99.01 38	98.40 156	91.56 127	99.80 74	98.53 16	98.68 126	97.37 224

xiu_mvs_v1_base_debi		97.60 71	97.56 63	97.72 138	98.35 159	95.98 136	97.86 246	98.51 151	97.13 45	99.01 38	98.40 156	91.56 127	99.80 74	98.53 16	98.68 126	97.37 224

TSAR-MVS + GP.		98.38 38	98.24 38	98.81 61	99.22 83	97.25 84	98.11 222	98.29 198	97.19 40	98.99 41	99.02 84	96.22 24	99.67 112	98.52 22	98.56 135	99.51 82

CS-MVS		98.44 34	98.49 15	98.31 97	99.08 99	96.73 102	99.67 3	98.47 162	97.17 41	98.94 42	99.10 72	95.73 41	99.13 178	98.71 11	99.49 84	99.09 145

HFP-MVS		98.63 13	98.40 18	99.32 27	99.72 12	98.29 44	99.23 31	98.96 33	96.10 90	98.94 42	99.17 60	96.06 30	99.92 23	97.62 73	99.78 26	99.75 28

region2R		98.61 14	98.38 20	99.29 28	99.74 7	98.16 51	99.23 31	98.93 38	96.15 87	98.94 42	99.17 60	95.91 37	99.94 3	97.55 80	99.79 23	99.78 15

HPM-MVS_fast		98.38 38	98.13 43	99.12 47	99.75 3	97.86 61	99.44 11	98.82 69	94.46 167	98.94 42	99.20 53	95.16 65	99.74 97	97.58 76	99.85 5	99.77 21

ACMMPR		98.59 17	98.36 22	99.29 28	99.74 7	98.15 52	99.23 31	98.95 34	96.10 90	98.93 46	99.19 58	95.70 42	99.94 3	97.62 73	99.79 23	99.78 15

DeepC-MVS_fast	96.70 1	98.55 25	98.34 27	99.18 40	99.25 75	98.04 56	98.50 174	98.78 89	97.72 7	98.92 47	99.28 40	95.27 59	99.82 62	97.55 80	99.77 28	99.69 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CS-MVS-test		98.49 29	98.50 14	98.46 85	99.20 86	97.05 89	99.64 4	98.50 156	97.45 22	98.88 48	99.14 67	95.25 61	99.15 175	98.83 9	99.56 76	99.20 127

DROMVSNet		98.21 48	98.11 45	98.49 82	98.34 164	97.26 83	99.61 5	98.43 171	96.78 60	98.87 49	98.84 109	93.72 92	99.01 199	98.91 7	99.50 82	99.19 131

EI-MVSNet-Vis-set		98.47 32	98.39 19	98.69 65	99.46 49	96.49 116	98.30 197	98.69 109	97.21 38	98.84 50	99.36 29	95.41 50	99.78 87	98.62 13	99.65 55	99.80 12

MSLP-MVS++		98.56 24	98.57 11	98.55 74	99.26 74	96.80 98	98.71 139	99.05 25	97.28 32	98.84 50	99.28 40	96.47 22	99.40 153	98.52 22	99.70 49	99.47 92

PHI-MVS		98.34 43	98.06 47	99.18 40	99.15 94	98.12 54	99.04 67	99.09 21	93.32 220	98.83 52	99.10 72	96.54 20	99.83 55	97.70 69	99.76 34	99.59 72

MVSFormer		97.57 75	97.49 67	97.84 126	98.07 189	95.76 155	99.47 9	98.40 175	94.98 145	98.79 53	98.83 111	92.34 105	98.41 273	96.91 104	99.59 66	99.34 107

lupinMVS		97.44 83	97.22 81	98.12 112	98.07 189	95.76 155	97.68 260	97.76 265	94.50 165	98.79 53	98.61 132	92.34 105	99.30 159	97.58 76	99.59 66	99.31 113

CDPH-MVS		97.94 54	97.49 67	99.28 31	99.47 47	98.44 31	97.91 239	98.67 117	92.57 248	98.77 55	98.85 108	95.93 36	99.72 99	95.56 158	99.69 50	99.68 54

CNVR-MVS		98.78 7	98.56 12	99.45 15	99.32 59	98.87 19	98.47 177	98.81 74	97.72 7	98.76 56	99.16 63	97.05 13	99.78 87	98.06 43	99.66 54	99.69 49

EI-MVSNet-UG-set		98.41 36	98.34 27	98.61 70	99.45 52	96.32 125	98.28 200	98.68 112	97.17 41	98.74 57	99.37 25	95.25 61	99.79 84	98.57 14	99.54 79	99.73 35

diffmvs		97.58 74	97.40 74	98.13 110	98.32 168	95.81 154	98.06 225	98.37 181	96.20 85	98.74 57	98.89 104	91.31 136	99.25 162	98.16 39	98.52 136	99.34 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GST-MVS		98.43 35	98.12 44	99.34 23	99.72 12	98.38 35	99.09 58	98.82 69	95.71 107	98.73 59	99.06 82	95.27 59	99.93 18	97.07 98	99.63 60	99.72 38

UA-Net		97.96 52	97.62 59	98.98 53	98.86 118	97.47 74	98.89 97	99.08 22	96.67 66	98.72 60	99.54 1	93.15 97	99.81 67	94.87 174	98.83 122	99.65 62

h-mvs33		96.17 138	95.62 152	97.81 130	99.03 102	94.45 212	98.64 153	98.75 95	97.48 19	98.67 61	98.72 123	89.76 162	99.86 49	97.95 48	81.59 350	99.11 143

hse-mvs2		95.71 162	95.30 167	96.93 188	98.50 148	93.53 246	98.36 187	98.10 232	97.48 19	98.67 61	97.99 196	89.76 162	99.02 197	97.95 48	80.91 354	98.22 200

ZD-MVS					99.46 49	98.70 23		98.79 87	93.21 225	98.67 61	98.97 91	95.70 42	99.83 55	96.07 137	99.58 69

旧先验2							97.57 270		91.30 289	98.67 61			99.80 74	95.70 155

PS-MVSNAJ		97.73 62	97.77 54	97.62 149	98.68 135	95.58 160	97.34 285	98.51 151	97.29 31	98.66 65	97.88 206	94.51 77	99.90 34	97.87 55	99.17 106	97.39 222

xiu_mvs_v2_base		97.66 68	97.70 57	97.56 153	98.61 142	95.46 166	97.44 274	98.46 163	97.15 43	98.65 66	98.15 183	94.33 83	99.80 74	97.84 58	98.66 130	97.41 220

LFMVS		95.86 154	94.98 182	98.47 84	98.87 117	96.32 125	98.84 109	96.02 339	93.40 217	98.62 67	99.20 53	74.99 342	99.63 120	97.72 65	97.20 179	99.46 96

HPM-MVS		98.36 40	98.10 46	99.13 45	99.74 7	97.82 65	99.53 8	98.80 82	94.63 160	98.61 68	98.97 91	95.13 66	99.77 92	97.65 71	99.83 11	99.79 13
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testdata				98.26 101	99.20 86	95.36 169		98.68 112	91.89 270	98.60 69	99.10 72	94.44 82	99.82 62	94.27 197	99.44 91	99.58 76

CP-MVS		98.57 22	98.36 22	99.19 38	99.66 26	97.86 61	99.34 18	98.87 57	95.96 95	98.60 69	99.13 68	96.05 31	99.94 3	97.77 62	99.86 1	99.77 21

jason		97.32 90	97.08 86	98.06 116	97.45 235	95.59 159	97.87 245	97.91 259	94.79 153	98.55 71	98.83 111	91.12 139	99.23 165	97.58 76	99.60 64	99.34 107
jason: jason.
MCST-MVS		98.65 11	98.37 21	99.48 13	99.60 31	98.87 19	98.41 186	98.68 112	97.04 49	98.52 72	98.80 114	96.78 16	99.83 55	97.93 50	99.61 63	99.74 30

XVS		98.70 10	98.49 15	99.34 23	99.70 22	98.35 41	99.29 22	98.88 50	97.40 23	98.46 73	99.20 53	95.90 38	99.89 36	97.85 56	99.74 41	99.78 15

X-MVStestdata		94.06 265	92.30 286	99.34 23	99.70 22	98.35 41	99.29 22	98.88 50	97.40 23	98.46 73	43.50 374	95.90 38	99.89 36	97.85 56	99.74 41	99.78 15

MG-MVS		97.81 59	97.60 60	98.44 87	99.12 96	95.97 141	97.75 255	98.78 89	96.89 56	98.46 73	99.22 50	93.90 91	99.68 111	94.81 178	99.52 81	99.67 58

NCCC		98.61 14	98.35 24	99.38 18	99.28 71	98.61 26	98.45 178	98.76 93	97.82 6	98.45 76	98.93 100	96.65 18	99.83 55	97.38 89	99.41 93	99.71 42

MVS_Test		97.28 91	97.00 89	98.13 110	98.33 166	95.97 141	98.74 130	98.07 239	94.27 171	98.44 77	98.07 188	92.48 103	99.26 161	96.43 129	98.19 152	99.16 137

MVS_111021_LR		98.34 43	98.23 39	98.67 67	99.27 72	96.90 95	97.95 235	99.58 3	97.14 44	98.44 77	99.01 88	95.03 69	99.62 123	97.91 51	99.75 38	99.50 84

ETV-MVS		97.96 52	97.81 53	98.40 92	98.42 153	97.27 79	98.73 134	98.55 143	96.84 57	98.38 79	97.44 245	95.39 51	99.35 156	97.62 73	98.89 117	98.58 188

test2506		94.44 240	93.91 237	96.04 254	99.02 103	88.99 327	99.06 62	79.47 381	96.96 53	98.36 80	99.26 43	77.21 332	99.52 142	96.78 119	99.04 109	99.59 72

VDDNet		95.36 184	94.53 201	97.86 125	98.10 188	95.13 180	98.85 106	97.75 266	90.46 306	98.36 80	99.39 19	73.27 349	99.64 117	97.98 46	96.58 192	98.81 169

mPP-MVS		98.51 28	98.26 35	99.25 34	99.75 3	98.04 56	99.28 24	98.81 74	96.24 83	98.35 82	99.23 48	95.46 48	99.94 3	97.42 87	99.81 12	99.77 21

DELS-MVS		98.40 37	98.20 41	98.99 52	99.00 106	97.66 66	97.75 255	98.89 47	97.71 9	98.33 83	98.97 91	94.97 70	99.88 44	98.42 30	99.76 34	99.42 103
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_HR		98.47 32	98.34 27	98.88 60	99.22 83	97.32 77	97.91 239	99.58 3	97.20 39	98.33 83	99.00 89	95.99 34	99.64 117	98.05 45	99.76 34	99.69 49

ZNCC-MVS		98.49 29	98.20 41	99.35 22	99.73 11	98.39 34	99.19 41	98.86 63	95.77 103	98.31 85	99.10 72	95.46 48	99.93 18	97.57 79	99.81 12	99.74 30

HPM-MVS++		98.58 19	98.25 36	99.55 9	99.50 41	99.08 11	98.72 138	98.66 120	97.51 18	98.15 86	98.83 111	95.70 42	99.92 23	97.53 82	99.67 52	99.66 61

新几何1				99.16 43	99.34 54	98.01 58		98.69 109	90.06 314	98.13 87	98.95 98	94.60 75	99.89 36	91.97 265	99.47 87	99.59 72

API-MVS		97.41 86	97.25 79	97.91 123	98.70 132	96.80 98	98.82 112	98.69 109	94.53 162	98.11 88	98.28 171	94.50 80	99.57 128	94.12 202	99.49 84	97.37 224

ECVR-MVS		95.95 147	95.71 146	96.65 206	99.02 103	90.86 294	99.03 70	91.80 369	96.96 53	98.10 89	99.26 43	81.31 300	99.51 143	96.90 107	99.04 109	99.59 72

CPTT-MVS		97.72 63	97.32 77	98.92 57	99.64 28	97.10 88	99.12 52	98.81 74	92.34 256	98.09 90	99.08 80	93.01 98	99.92 23	96.06 140	99.77 28	99.75 28

test12				99.18 40	99.16 92	98.19 48		98.53 147		98.07 91		95.13 66	99.72 99		99.56 76	99.63 66

test222					99.23 82	97.17 87	97.40 277	98.66 120	88.68 331	98.05 92	98.96 96	94.14 87			99.53 80	99.61 68

DP-MVS Recon		97.86 57	97.46 70	99.06 50	99.53 36	98.35 41	98.33 190	98.89 47	92.62 245	98.05 92	98.94 99	95.34 55	99.65 115	96.04 141	99.42 92	99.19 131

Vis-MVSNet		97.42 85	97.11 84	98.34 95	98.66 137	96.23 128	99.22 35	99.00 28	96.63 68	98.04 94	99.21 51	88.05 208	99.35 156	96.01 143	99.21 103	99.45 98
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test1111		95.94 149	95.78 140	96.41 238	98.99 109	90.12 308	99.04 67	92.45 368	96.99 52	98.03 95	99.27 42	81.40 299	99.48 148	96.87 113	99.04 109	99.63 66

baseline		97.64 69	97.44 72	98.25 102	98.35 159	96.20 129	99.00 77	98.32 188	96.33 82	98.03 95	99.17 60	91.35 134	99.16 172	98.10 41	98.29 151	99.39 104

test_yl		97.22 93	96.78 100	98.54 76	98.73 127	96.60 108	98.45 178	98.31 190	94.70 154	98.02 97	98.42 154	90.80 146	99.70 105	96.81 116	96.79 186	99.34 107

DCV-MVSNet		97.22 93	96.78 100	98.54 76	98.73 127	96.60 108	98.45 178	98.31 190	94.70 154	98.02 97	98.42 154	90.80 146	99.70 105	96.81 116	96.79 186	99.34 107

MTAPA		98.58 19	98.29 34	99.46 14	99.76 2	98.64 25	98.90 93	98.74 97	97.27 36	98.02 97	99.39 19	94.81 73	99.96 2	97.91 51	99.79 23	99.77 21

sss		97.39 87	96.98 91	98.61 70	98.60 143	96.61 107	98.22 205	98.93 38	93.97 183	98.01 100	98.48 146	91.98 118	99.85 50	96.45 128	98.15 153	99.39 104

alignmvs		97.56 76	97.07 87	99.01 51	98.66 137	98.37 39	98.83 110	98.06 244	96.74 63	98.00 101	97.65 228	90.80 146	99.48 148	98.37 32	96.56 193	99.19 131

OMC-MVS		97.55 77	97.34 76	98.20 105	99.33 56	95.92 148	98.28 200	98.59 132	95.52 115	97.97 102	99.10 72	93.28 96	99.49 144	95.09 171	98.88 118	99.19 131

VDD-MVS		95.82 157	95.23 169	97.61 150	98.84 121	93.98 229	98.68 146	97.40 296	95.02 144	97.95 103	99.34 34	74.37 346	99.78 87	98.64 12	96.80 185	99.08 149

casdiffmvs		97.63 70	97.41 73	98.28 98	98.33 166	96.14 132	98.82 112	98.32 188	96.38 80	97.95 103	99.21 51	91.23 138	99.23 165	98.12 40	98.37 145	99.48 90
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		96.73 113	96.60 109	97.12 175	99.25 75	95.35 171	98.26 203	99.26 9	94.28 170	97.94 105	97.46 242	92.74 101	99.81 67	96.88 110	93.32 254	96.20 317

PVSNet_Blended		97.38 88	97.12 83	98.14 108	99.25 75	95.35 171	97.28 290	99.26 9	93.13 228	97.94 105	98.21 179	92.74 101	99.81 67	96.88 110	99.40 95	99.27 120

DPM-MVS		97.55 77	96.99 90	99.23 37	99.04 101	98.55 27	97.17 299	98.35 184	94.85 152	97.93 107	98.58 137	95.07 68	99.71 104	92.60 245	99.34 99	99.43 101

MP-MVS		98.33 45	98.01 49	99.28 31	99.75 3	98.18 49	99.22 35	98.79 87	96.13 88	97.92 108	99.23 48	94.54 76	99.94 3	96.74 121	99.78 26	99.73 35
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MDTV_nov1_ep13_2view						84.26 353	96.89 319		90.97 299	97.90 109		89.89 161		93.91 209		99.18 136

test_prior2							97.80 251		96.12 89	97.89 110	98.69 125	95.96 35		96.89 108	99.60 64

原ACMM1				98.65 68	99.32 59	96.62 105		98.67 117	93.27 224	97.81 111	98.97 91	95.18 64	99.83 55	93.84 211	99.46 90	99.50 84

114514_t		96.93 106	96.27 121	98.92 57	99.50 41	97.63 68	98.85 106	98.90 45	84.80 351	97.77 112	99.11 70	92.84 99	99.66 114	94.85 175	99.77 28	99.47 92

casdiffmvs_mvg		97.72 63	97.48 69	98.44 87	98.42 153	96.59 110	98.92 91	98.44 167	96.20 85	97.76 113	99.20 53	91.66 125	99.23 165	98.27 37	98.41 144	99.49 89
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PMMVS		96.60 117	96.33 118	97.41 158	97.90 201	93.93 230	97.35 284	98.41 173	92.84 239	97.76 113	97.45 244	91.10 141	99.20 169	96.26 133	97.91 160	99.11 143

PVSNet	91.96 18	96.35 131	96.15 125	96.96 186	99.17 88	92.05 274	96.08 337	98.68 112	93.69 202	97.75 115	97.80 216	88.86 189	99.69 110	94.26 198	99.01 112	99.15 138

TEST9					99.31 61	98.50 29	97.92 237	98.73 100	92.63 244	97.74 116	98.68 126	96.20 26	99.80 74

train_agg		97.97 51	97.52 66	99.33 26	99.31 61	98.50 29	97.92 237	98.73 100	92.98 233	97.74 116	98.68 126	96.20 26	99.80 74	96.59 122	99.57 70	99.68 54

FE-MVS		95.62 168	94.90 186	97.78 132	98.37 158	94.92 191	97.17 299	97.38 298	90.95 300	97.73 118	97.70 222	85.32 262	99.63 120	91.18 277	98.33 148	98.79 170

CANet		98.05 50	97.76 55	98.90 59	98.73 127	97.27 79	98.35 188	98.78 89	97.37 28	97.72 119	98.96 96	91.53 131	99.92 23	98.79 10	99.65 55	99.51 82

test_8					99.29 67	98.44 31	97.89 243	98.72 102	92.98 233	97.70 120	98.66 129	96.20 26	99.80 74

MP-MVS-pluss		98.31 46	97.92 52	99.49 12	99.72 12	98.88 18	98.43 183	98.78 89	94.10 175	97.69 121	99.42 17	95.25 61	99.92 23	98.09 42	99.80 19	99.67 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
canonicalmvs		97.67 67	97.23 80	98.98 53	98.70 132	98.38 35	99.34 18	98.39 177	96.76 62	97.67 122	97.40 248	92.26 108	99.49 144	98.28 36	96.28 205	99.08 149

PVSNet_Blended_VisFu		97.70 65	97.46 70	98.44 87	99.27 72	95.91 149	98.63 155	99.16 18	94.48 166	97.67 122	98.88 105	92.80 100	99.91 31	97.11 96	99.12 107	99.50 84

WTY-MVS		97.37 89	96.92 93	98.72 64	98.86 118	96.89 97	98.31 195	98.71 105	95.26 130	97.67 122	98.56 140	92.21 111	99.78 87	95.89 145	96.85 184	99.48 90

Effi-MVS+		97.12 100	96.69 105	98.39 93	98.19 179	96.72 103	97.37 281	98.43 171	93.71 199	97.65 125	98.02 192	92.20 112	99.25 162	96.87 113	97.79 165	99.19 131

thisisatest0530		96.01 143	95.36 160	97.97 120	98.38 156	95.52 164	98.88 100	94.19 360	94.04 177	97.64 126	98.31 169	83.82 290	99.46 151	95.29 166	97.70 170	98.93 162

tttt0517		96.07 141	95.51 154	97.78 132	98.41 155	94.84 194	99.28 24	94.33 358	94.26 172	97.64 126	98.64 130	84.05 283	99.47 150	95.34 162	97.60 173	99.03 152

HyFIR lowres test		96.90 108	96.49 114	98.14 108	99.33 56	95.56 161	97.38 279	99.65 2	92.34 256	97.61 128	98.20 180	89.29 173	99.10 186	96.97 101	97.60 173	99.77 21

ACMMP		98.23 47	97.95 51	99.09 48	99.74 7	97.62 69	99.03 70	99.41 6	95.98 93	97.60 129	99.36 29	94.45 81	99.93 18	97.14 95	98.85 121	99.70 46
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
agg_prior					99.30 65	98.38 35		98.72 102		97.57 130			99.81 67

tpmrst		95.63 167	95.69 149	95.44 279	97.54 225	88.54 333	96.97 309	97.56 277	93.50 213	97.52 131	96.93 289	89.49 166	99.16 172	95.25 168	96.42 198	98.64 184

MDTV_nov1_ep13			95.40 155		97.48 229	88.34 337	96.85 322	97.29 302	93.74 196	97.48 132	97.26 254	89.18 177	99.05 190	91.92 266	97.43 176

FA-MVS(test-final)		96.41 130	95.94 134	97.82 129	98.21 175	95.20 176	97.80 251	97.58 275	93.21 225	97.36 133	97.70 222	89.47 168	99.56 131	94.12 202	97.99 157	98.71 177

EPMVS		94.99 205	94.48 204	96.52 227	97.22 248	91.75 279	97.23 292	91.66 370	94.11 174	97.28 134	96.81 296	85.70 252	98.84 223	93.04 234	97.28 178	98.97 158

EIA-MVS		97.75 61	97.58 61	98.27 99	98.38 156	96.44 118	99.01 75	98.60 130	95.88 99	97.26 135	97.53 239	94.97 70	99.33 158	97.38 89	99.20 104	99.05 151

IS-MVSNet		97.22 93	96.88 94	98.25 102	98.85 120	96.36 123	99.19 41	97.97 252	95.39 121	97.23 136	98.99 90	91.11 140	98.93 211	94.60 185	98.59 133	99.47 92

EPP-MVSNet		97.46 79	97.28 78	97.99 119	98.64 139	95.38 168	99.33 21	98.31 190	93.61 210	97.19 137	99.07 81	94.05 88	99.23 165	96.89 108	98.43 143	99.37 106

thisisatest0515		95.61 171	94.89 187	97.76 135	98.15 185	95.15 179	96.77 325	94.41 356	92.95 235	97.18 138	97.43 246	84.78 269	99.45 152	94.63 182	97.73 169	98.68 179

CANet_DTU		96.96 105	96.55 111	98.21 104	98.17 183	96.07 134	97.98 233	98.21 207	97.24 37	97.13 139	98.93 100	86.88 232	99.91 31	95.00 173	99.37 98	98.66 182

CHOSEN 1792x2688		97.12 100	96.80 97	98.08 114	99.30 65	94.56 210	98.05 226	99.71 1	93.57 211	97.09 140	98.91 103	88.17 203	99.89 36	96.87 113	99.56 76	99.81 11

PatchT		93.06 285	91.97 290	96.35 242	96.69 282	92.67 267	94.48 358	97.08 310	86.62 339	97.08 141	92.23 358	87.94 210	97.90 316	78.89 360	96.69 188	98.49 190

PatchmatchNet		95.71 162	95.52 153	96.29 247	97.58 220	90.72 298	96.84 323	97.52 285	94.06 176	97.08 141	96.96 285	89.24 176	98.90 216	92.03 263	98.37 145	99.26 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MAR-MVS		96.91 107	96.40 116	98.45 86	98.69 134	96.90 95	98.66 151	98.68 112	92.40 255	97.07 143	97.96 199	91.54 130	99.75 95	93.68 215	98.92 115	98.69 178
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
PAPM_NR		97.46 79	97.11 84	98.50 80	99.50 41	96.41 121	98.63 155	98.60 130	95.18 134	97.06 144	98.06 189	94.26 86	99.57 128	93.80 213	98.87 120	99.52 79

TAMVS		97.02 103	96.79 99	97.70 141	98.06 191	95.31 173	98.52 169	98.31 190	93.95 184	97.05 145	98.61 132	93.49 94	98.52 253	95.33 163	97.81 164	99.29 118

CSCG		97.85 58	97.74 56	98.20 105	99.67 25	95.16 177	99.22 35	99.32 7	93.04 231	97.02 146	98.92 102	95.36 54	99.91 31	97.43 86	99.64 59	99.52 79

CDS-MVSNet		96.99 104	96.69 105	97.90 124	98.05 192	95.98 136	98.20 208	98.33 187	93.67 206	96.95 147	98.49 145	93.54 93	98.42 265	95.24 169	97.74 168	99.31 113
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
XVG-OURS-SEG-HR		96.51 123	96.34 117	97.02 181	98.77 125	93.76 235	97.79 253	98.50 156	95.45 118	96.94 148	99.09 78	87.87 213	99.55 138	96.76 120	95.83 215	97.74 213

CR-MVSNet		94.76 217	94.15 221	96.59 216	97.00 262	93.43 249	94.96 350	97.56 277	92.46 249	96.93 149	96.24 314	88.15 204	97.88 320	87.38 324	96.65 190	98.46 191

RPMNet		92.81 287	91.34 295	97.24 166	97.00 262	93.43 249	94.96 350	98.80 82	82.27 356	96.93 149	92.12 359	86.98 230	99.82 62	76.32 364	96.65 190	98.46 191

SCA		95.46 174	95.13 173	96.46 235	97.67 214	91.29 289	97.33 286	97.60 274	94.68 157	96.92 151	97.10 263	83.97 285	98.89 217	92.59 247	98.32 150	99.20 127

PatchMatch-RL		96.59 118	96.03 131	98.27 99	99.31 61	96.51 115	97.91 239	99.06 23	93.72 198	96.92 151	98.06 189	88.50 198	99.65 115	91.77 269	99.00 113	98.66 182

DeepC-MVS	95.98 3	97.88 56	97.58 61	98.77 62	99.25 75	96.93 93	98.83 110	98.75 95	96.96 53	96.89 153	99.50 6	90.46 152	99.87 45	97.84 58	99.76 34	99.52 79
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVG-OURS		96.55 122	96.41 115	96.99 182	98.75 126	93.76 235	97.50 273	98.52 149	95.67 109	96.83 154	99.30 38	88.95 188	99.53 139	95.88 146	96.26 206	97.69 216

AdaColmap		97.15 99	96.70 104	98.48 83	99.16 92	96.69 104	98.01 230	98.89 47	94.44 168	96.83 154	98.68 126	90.69 149	99.76 93	94.36 192	99.29 102	98.98 157

CostFormer		94.95 209	94.73 193	95.60 274	97.28 244	89.06 324	97.53 271	96.89 324	89.66 321	96.82 156	96.72 299	86.05 246	98.95 210	95.53 159	96.13 211	98.79 170

UGNet		96.78 112	96.30 120	98.19 107	98.24 171	95.89 151	98.88 100	98.93 38	97.39 25	96.81 157	97.84 210	82.60 294	99.90 34	96.53 125	99.49 84	98.79 170
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
CNLPA		97.45 82	97.03 88	98.73 63	99.05 100	97.44 76	98.07 224	98.53 147	95.32 127	96.80 158	98.53 141	93.32 95	99.72 99	94.31 196	99.31 101	99.02 153

CHOSEN 280x420		97.18 97	97.18 82	97.20 168	98.81 123	93.27 256	95.78 344	99.15 19	95.25 131	96.79 159	98.11 186	92.29 107	99.07 189	98.56 15	99.85 5	99.25 123

HY-MVS	93.96 8	96.82 111	96.23 124	98.57 72	98.46 151	97.00 90	98.14 217	98.21 207	93.95 184	96.72 160	97.99 196	91.58 126	99.76 93	94.51 189	96.54 194	98.95 161

PAPR		96.84 110	96.24 123	98.65 68	98.72 131	96.92 94	97.36 283	98.57 139	93.33 219	96.67 161	97.57 236	94.30 84	99.56 131	91.05 282	98.59 133	99.47 92

Anonymous20240529		95.10 199	94.22 216	97.75 136	99.01 105	94.26 221	98.87 103	98.83 68	85.79 347	96.64 162	98.97 91	78.73 318	99.85 50	96.27 132	94.89 219	99.12 142

thres600view7		95.49 172	94.77 190	97.67 144	98.98 110	95.02 183	98.85 106	96.90 322	95.38 122	96.63 163	96.90 290	84.29 276	99.59 126	88.65 317	96.33 200	98.40 193

thres100view900		95.38 181	94.70 194	97.41 158	98.98 110	94.92 191	98.87 103	96.90 322	95.38 122	96.61 164	96.88 291	84.29 276	99.56 131	88.11 318	96.29 202	97.76 211

Vis-MVSNet (Re-imp)		96.87 109	96.55 111	97.83 127	98.73 127	95.46 166	99.20 39	98.30 196	94.96 147	96.60 165	98.87 106	90.05 158	98.59 245	93.67 217	98.60 132	99.46 96

CVMVSNet		95.43 177	96.04 130	93.57 318	97.93 199	83.62 355	98.12 220	98.59 132	95.68 108	96.56 166	99.02 84	87.51 220	97.51 332	93.56 221	97.44 175	99.60 70

RPSCF		94.87 213	95.40 155	93.26 324	98.89 115	82.06 360	98.33 190	98.06 244	90.30 311	96.56 166	99.26 43	87.09 227	99.49 144	93.82 212	96.32 201	98.24 199

tfpn200view9		95.32 188	94.62 197	97.43 157	98.94 112	94.98 187	98.68 146	96.93 320	95.33 125	96.55 168	96.53 307	84.23 279	99.56 131	88.11 318	96.29 202	97.76 211

thres400		95.38 181	94.62 197	97.65 148	98.94 112	94.98 187	98.68 146	96.93 320	95.33 125	96.55 168	96.53 307	84.23 279	99.56 131	88.11 318	96.29 202	98.40 193

thres200		95.25 190	94.57 199	97.28 165	98.81 123	94.92 191	98.20 208	97.11 309	95.24 133	96.54 170	96.22 318	84.58 273	99.53 139	87.93 322	96.50 196	97.39 222

ab-mvs		96.42 126	95.71 146	98.55 74	98.63 140	96.75 101	97.88 244	98.74 97	93.84 189	96.54 170	98.18 182	85.34 260	99.75 95	95.93 144	96.35 199	99.15 138

Anonymous202405211		95.28 189	94.49 203	97.67 144	99.00 106	93.75 237	98.70 143	97.04 313	90.66 302	96.49 172	98.80 114	78.13 324	99.83 55	96.21 136	95.36 218	99.44 99

ADS-MVSNet2		94.58 229	94.40 212	95.11 288	98.00 193	88.74 330	96.04 338	97.30 301	90.15 312	96.47 173	96.64 304	87.89 211	97.56 330	90.08 294	97.06 180	99.02 153

ADS-MVSNet		95.00 204	94.45 208	96.63 210	98.00 193	91.91 276	96.04 338	97.74 267	90.15 312	96.47 173	96.64 304	87.89 211	98.96 205	90.08 294	97.06 180	99.02 153

Effi-MVS+-dtu		96.29 133	96.56 110	95.51 275	97.89 202	90.22 307	98.80 119	98.10 232	96.57 71	96.45 175	96.66 301	90.81 145	98.91 213	95.72 152	97.99 157	97.40 221

PLC	95.07 4	97.20 96	96.78 100	98.44 87	99.29 67	96.31 127	98.14 217	98.76 93	92.41 254	96.39 176	98.31 169	94.92 72	99.78 87	94.06 205	98.77 125	99.23 124
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		94.13 258	93.80 245	95.12 287	96.50 292	87.91 343	97.44 274	95.89 344	92.62 245	96.37 177	96.30 313	84.13 282	98.30 286	93.24 227	91.66 274	99.14 140

TAPA-MVS	93.98 7	95.35 185	94.56 200	97.74 137	99.13 95	94.83 196	98.33 190	98.64 125	86.62 339	96.29 178	98.61 132	94.00 90	99.29 160	80.00 356	99.41 93	99.09 145
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		95.84 155	95.12 175	98.01 118	98.49 150	95.98 136	98.73 134	97.03 314	95.37 124	96.22 179	98.19 181	89.96 160	99.16 172	94.60 185	87.48 324	98.90 164

tpm2		94.19 254	93.76 250	95.46 278	97.23 247	89.04 325	97.31 288	96.85 328	87.08 338	96.21 180	96.79 297	83.75 291	98.74 232	92.43 255	96.23 208	98.59 186

F-COLMAP		97.09 102	96.80 97	97.97 120	99.45 52	94.95 190	98.55 168	98.62 129	93.02 232	96.17 181	98.58 137	94.01 89	99.81 67	93.95 207	98.90 116	99.14 140

GeoE		96.58 120	96.07 128	98.10 113	98.35 159	95.89 151	99.34 18	98.12 226	93.12 229	96.09 182	98.87 106	89.71 164	98.97 201	92.95 237	98.08 156	99.43 101

JIA-IIPM		93.35 276	92.49 283	95.92 260	96.48 294	90.65 300	95.01 349	96.96 318	85.93 345	96.08 183	87.33 364	87.70 218	98.78 230	91.35 275	95.58 216	98.34 196

BH-RMVSNet		95.92 151	95.32 164	97.69 142	98.32 168	94.64 202	98.19 211	97.45 292	94.56 161	96.03 184	98.61 132	85.02 264	99.12 180	90.68 287	99.06 108	99.30 116

dp		94.15 257	93.90 238	94.90 294	97.31 243	86.82 349	96.97 309	97.19 308	91.22 294	96.02 185	96.61 306	85.51 256	99.02 197	90.00 298	94.30 221	98.85 166

EPNet		97.28 91	96.87 95	98.51 79	94.98 337	96.14 132	98.90 93	97.02 316	98.28 1	95.99 186	99.11 70	91.36 133	99.89 36	96.98 100	99.19 105	99.50 84
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LS3D		97.16 98	96.66 108	98.68 66	98.53 147	97.19 86	98.93 90	98.90 45	92.83 240	95.99 186	99.37 25	92.12 114	99.87 45	93.67 217	99.57 70	98.97 158

AUN-MVS		94.53 233	93.73 252	96.92 191	98.50 148	93.52 247	98.34 189	98.10 232	93.83 191	95.94 188	97.98 198	85.59 254	99.03 194	94.35 193	80.94 353	98.22 200

TR-MVS		94.94 211	94.20 217	97.17 171	97.75 208	94.14 226	97.59 268	97.02 316	92.28 260	95.75 189	97.64 230	83.88 287	98.96 205	89.77 300	96.15 210	98.40 193

iter_conf_final		96.42 126	96.12 126	97.34 163	98.46 151	96.55 114	99.08 60	98.06 244	96.03 92	95.63 190	98.46 150	87.72 215	98.59 245	97.84 58	93.80 239	96.87 251

iter_conf05		96.13 140	95.79 139	97.15 172	98.16 184	95.99 135	98.88 100	97.98 250	95.91 96	95.58 191	98.46 150	85.53 255	98.59 245	97.88 54	93.75 240	96.86 254

VPA-MVSNet		95.75 159	95.11 176	97.69 142	97.24 246	97.27 79	98.94 88	99.23 13	95.13 136	95.51 192	97.32 251	85.73 251	98.91 213	97.33 91	89.55 300	96.89 248

HQP_MVS		96.14 139	95.90 136	96.85 194	97.42 237	94.60 208	98.80 119	98.56 141	97.28 32	95.34 193	98.28 171	87.09 227	99.03 194	96.07 137	94.27 222	96.92 240

plane_prior3						94.61 206			97.02 50	95.34 193

Fast-Effi-MVS+		96.28 135	95.70 148	98.03 117	98.29 170	95.97 141	98.58 161	98.25 204	91.74 273	95.29 195	97.23 257	91.03 143	99.15 175	92.90 239	97.96 159	98.97 158

test_fmvs2		93.43 274	93.58 259	92.95 328	96.97 265	83.91 354	99.19 41	97.24 306	95.74 104	95.20 196	98.27 174	69.65 352	98.72 234	96.26 133	93.73 241	96.24 315

mvsmamba		96.57 121	96.32 119	97.32 164	96.60 286	96.43 119	99.54 7	97.98 250	96.49 72	95.20 196	98.64 130	90.82 144	98.55 249	97.97 47	93.65 244	96.98 235

EI-MVSNet		95.96 146	95.83 138	96.36 241	97.93 199	93.70 241	98.12 220	98.27 199	93.70 201	95.07 198	99.02 84	92.23 110	98.54 251	94.68 180	93.46 249	96.84 256

MVSTER		96.06 142	95.72 143	97.08 178	98.23 173	95.93 147	98.73 134	98.27 199	94.86 151	95.07 198	98.09 187	88.21 202	98.54 251	96.59 122	93.46 249	96.79 260

OPM-MVS		95.69 165	95.33 163	96.76 199	96.16 309	94.63 203	98.43 183	98.39 177	96.64 67	95.02 200	98.78 116	85.15 263	99.05 190	95.21 170	94.20 225	96.60 283
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+-dtu		95.87 153	95.85 137	95.91 261	97.74 211	91.74 280	98.69 145	98.15 222	95.56 113	94.92 201	97.68 227	88.98 186	98.79 229	93.19 229	97.78 166	97.20 228

TESTMET0.1,1		94.18 256	93.69 255	95.63 272	96.92 268	89.12 323	96.91 314	94.78 353	93.17 227	94.88 202	96.45 310	78.52 319	98.92 212	93.09 231	98.50 138	98.85 166

VPNet		94.99 205	94.19 218	97.40 160	97.16 255	96.57 111	98.71 139	98.97 31	95.67 109	94.84 203	98.24 178	80.36 309	98.67 239	96.46 127	87.32 327	96.96 237

1112_ss		96.63 116	96.00 132	98.50 80	98.56 144	96.37 122	98.18 214	98.10 232	92.92 236	94.84 203	98.43 152	92.14 113	99.58 127	94.35 193	96.51 195	99.56 78

test-LLR		95.10 199	94.87 188	95.80 266	96.77 276	89.70 313	96.91 314	95.21 348	95.11 138	94.83 205	95.72 329	87.71 216	98.97 201	93.06 232	98.50 138	98.72 175

test-mter		94.08 263	93.51 263	95.80 266	96.77 276	89.70 313	96.91 314	95.21 348	92.89 237	94.83 205	95.72 329	77.69 327	98.97 201	93.06 232	98.50 138	98.72 175

Test_1112_low_res		96.34 132	95.66 151	98.36 94	98.56 144	95.94 144	97.71 258	98.07 239	92.10 265	94.79 207	97.29 253	91.75 122	99.56 131	94.17 200	96.50 196	99.58 76

GA-MVS		94.81 214	94.03 226	97.14 173	97.15 256	93.86 232	96.76 326	97.58 275	94.00 181	94.76 208	97.04 276	80.91 304	98.48 256	91.79 268	96.25 207	99.09 145

bld_raw_dy_0_64		95.74 160	95.31 166	97.03 180	96.35 300	95.76 155	99.12 52	97.37 299	95.97 94	94.70 209	98.48 146	85.80 250	98.49 255	96.55 124	93.48 248	96.84 256

BH-untuned		95.95 147	95.72 143	96.65 206	98.55 146	92.26 270	98.23 204	97.79 264	93.73 197	94.62 210	98.01 194	88.97 187	99.00 200	93.04 234	98.51 137	98.68 179

test_djsdf		96.00 144	95.69 149	96.93 188	95.72 323	95.49 165	99.47 9	98.40 175	94.98 145	94.58 211	97.86 207	89.16 178	98.41 273	96.91 104	94.12 230	96.88 249

cascas		94.63 225	93.86 241	96.93 188	96.91 270	94.27 220	96.00 341	98.51 151	85.55 348	94.54 212	96.23 316	84.20 281	98.87 220	95.80 150	96.98 183	97.66 217

DP-MVS		96.59 118	95.93 135	98.57 72	99.34 54	96.19 131	98.70 143	98.39 177	89.45 324	94.52 213	99.35 31	91.85 120	99.85 50	92.89 241	98.88 118	99.68 54

gg-mvs-nofinetune		92.21 293	90.58 301	97.13 174	96.75 279	95.09 181	95.85 342	89.40 374	85.43 349	94.50 214	81.98 367	80.80 307	98.40 279	92.16 257	98.33 148	97.88 208

mvs_anonymous		96.70 115	96.53 113	97.18 170	98.19 179	93.78 234	98.31 195	98.19 211	94.01 180	94.47 215	98.27 174	92.08 116	98.46 260	97.39 88	97.91 160	99.31 113

HQP-NCC					97.20 250		98.05 226		96.43 75	94.45 216

ACMP_Plane					97.20 250		98.05 226		96.43 75	94.45 216

HQP4-MVS										94.45 216			98.96 205			96.87 251

HQP-MVS		95.72 161	95.40 155	96.69 204	97.20 250	94.25 222	98.05 226	98.46 163	96.43 75	94.45 216	97.73 219	86.75 233	98.96 205	95.30 164	94.18 226	96.86 254

MSDG		95.93 150	95.30 167	97.83 127	98.90 114	95.36 169	96.83 324	98.37 181	91.32 288	94.43 220	98.73 122	90.27 156	99.60 125	90.05 296	98.82 123	98.52 189

nrg030		96.28 135	95.72 143	97.96 122	96.90 271	98.15 52	99.39 12	98.31 190	95.47 117	94.42 221	98.35 162	92.09 115	98.69 235	97.50 84	89.05 308	97.04 231

CLD-MVS		95.62 168	95.34 161	96.46 235	97.52 228	93.75 237	97.27 291	98.46 163	95.53 114	94.42 221	98.00 195	86.21 243	98.97 201	96.25 135	94.37 220	96.66 278
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LPG-MVS_test		95.62 168	95.34 161	96.47 232	97.46 231	93.54 244	98.99 79	98.54 145	94.67 158	94.36 223	98.77 118	85.39 257	99.11 182	95.71 153	94.15 228	96.76 263

LGP-MVS_train				96.47 232	97.46 231	93.54 244		98.54 145	94.67 158	94.36 223	98.77 118	85.39 257	99.11 182	95.71 153	94.15 228	96.76 263

v144192		94.39 243	93.70 254	96.48 231	96.06 312	94.35 218	98.58 161	98.16 221	91.45 281	94.33 225	97.02 278	87.50 222	98.45 261	91.08 279	89.11 307	96.63 280

V42		94.78 216	94.14 222	96.70 203	96.33 302	95.22 175	98.97 82	98.09 236	92.32 258	94.31 226	97.06 273	88.39 199	98.55 249	92.90 239	88.87 312	96.34 310

ACMM	93.85 9	95.69 165	95.38 159	96.61 213	97.61 218	93.84 233	98.91 92	98.44 167	95.25 131	94.28 227	98.47 148	86.04 248	99.12 180	95.50 160	93.95 235	96.87 251
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS-LS		95.46 174	95.21 170	96.22 249	98.12 186	93.72 240	98.32 194	98.13 225	93.71 199	94.26 228	97.31 252	92.24 109	98.10 300	94.63 182	90.12 291	96.84 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		94.20 253	93.47 265	96.40 240	95.98 315	94.08 227	98.52 169	98.15 222	91.33 287	94.25 229	97.20 260	86.41 240	98.42 265	90.04 297	89.39 304	96.69 277

BH-w/o		95.38 181	95.08 177	96.26 248	98.34 164	91.79 277	97.70 259	97.43 294	92.87 238	94.24 230	97.22 258	88.66 192	98.84 223	91.55 273	97.70 170	98.16 203

XVG-ACMP-BASELINE		94.54 231	94.14 222	95.75 269	96.55 289	91.65 282	98.11 222	98.44 167	94.96 147	94.22 231	97.90 203	79.18 317	99.11 182	94.05 206	93.85 237	96.48 304

v1144		94.59 228	93.92 235	96.60 215	96.21 304	94.78 200	98.59 159	98.14 224	91.86 272	94.21 232	97.02 278	87.97 209	98.41 273	91.72 270	89.57 298	96.61 282

v1192		94.32 246	93.58 259	96.53 226	96.10 310	94.45 212	98.50 174	98.17 219	91.54 279	94.19 233	97.06 273	86.95 231	98.43 264	90.14 292	89.57 298	96.70 272

PAPM		94.95 209	94.00 230	97.78 132	97.04 261	95.65 158	96.03 340	98.25 204	91.23 293	94.19 233	97.80 216	91.27 137	98.86 222	82.61 350	97.61 172	98.84 168

Patchmatch-test		94.42 241	93.68 256	96.63 210	97.60 219	91.76 278	94.83 354	97.49 289	89.45 324	94.14 235	97.10 263	88.99 183	98.83 225	85.37 338	98.13 154	99.29 118

v1240		94.06 265	93.29 270	96.34 243	96.03 314	93.90 231	98.44 181	98.17 219	91.18 296	94.13 236	97.01 280	86.05 246	98.42 265	89.13 313	89.50 302	96.70 272

GBi-Net		94.49 236	93.80 245	96.56 220	98.21 175	95.00 184	98.82 112	98.18 214	92.46 249	94.09 237	97.07 270	81.16 301	97.95 312	92.08 259	92.14 266	96.72 268

test1		94.49 236	93.80 245	96.56 220	98.21 175	95.00 184	98.82 112	98.18 214	92.46 249	94.09 237	97.07 270	81.16 301	97.95 312	92.08 259	92.14 266	96.72 268

FMVSNet3		94.97 208	94.26 215	97.11 176	98.18 181	96.62 105	98.56 167	98.26 203	93.67 206	94.09 237	97.10 263	84.25 278	98.01 308	92.08 259	92.14 266	96.70 272

MIMVSNet		93.26 280	92.21 287	96.41 238	97.73 212	93.13 261	95.65 345	97.03 314	91.27 292	94.04 240	96.06 321	75.33 340	97.19 337	86.56 328	96.23 208	98.92 163

FIs		96.51 123	96.12 126	97.67 144	97.13 257	97.54 72	99.36 15	99.22 15	95.89 97	94.03 241	98.35 162	91.98 118	98.44 263	96.40 130	92.76 262	97.01 233

v2v482		94.69 218	94.03 226	96.65 206	96.17 307	94.79 199	98.67 149	98.08 237	92.72 242	94.00 242	97.16 261	87.69 219	98.45 261	92.91 238	88.87 312	96.72 268

RRT_MVS		95.98 145	95.78 140	96.56 220	96.48 294	94.22 224	99.57 6	97.92 257	95.89 97	93.95 243	98.70 124	89.27 174	98.42 265	97.23 93	93.02 258	97.04 231

FC-MVSNet-test		96.42 126	96.05 129	97.53 154	96.95 266	97.27 79	99.36 15	99.23 13	95.83 101	93.93 244	98.37 160	92.00 117	98.32 282	96.02 142	92.72 263	97.00 234

UniMVSNet (Re)		95.78 158	95.19 171	97.58 151	96.99 264	97.47 74	98.79 124	99.18 17	95.60 111	93.92 245	97.04 276	91.68 123	98.48 256	95.80 150	87.66 323	96.79 260

miper_enhance_ethall		95.10 199	94.75 192	96.12 253	97.53 227	93.73 239	96.61 331	98.08 237	92.20 264	93.89 246	96.65 303	92.44 104	98.30 286	94.21 199	91.16 280	96.34 310

UniMVSNet_NR-MVSNet		95.71 162	95.15 172	97.40 160	96.84 274	96.97 91	98.74 130	99.24 11	95.16 135	93.88 247	97.72 221	91.68 123	98.31 284	95.81 148	87.25 328	96.92 240

DU-MVS		95.42 178	94.76 191	97.40 160	96.53 290	96.97 91	98.66 151	98.99 30	95.43 119	93.88 247	97.69 224	88.57 194	98.31 284	95.81 148	87.25 328	96.92 240

Baseline_NR-MVSNet		94.35 244	93.81 244	95.96 259	96.20 305	94.05 228	98.61 158	96.67 333	91.44 282	93.85 249	97.60 233	88.57 194	98.14 297	94.39 191	86.93 331	95.68 329

PS-MVSNAJss		96.43 125	96.26 122	96.92 191	95.84 321	95.08 182	99.16 45	98.50 156	95.87 100	93.84 250	98.34 166	94.51 77	98.61 242	96.88 110	93.45 251	97.06 230

UniMVSNet_ETH3D		94.24 251	93.33 268	96.97 185	97.19 253	93.38 253	98.74 130	98.57 139	91.21 295	93.81 251	98.58 137	72.85 350	98.77 231	95.05 172	93.93 236	98.77 174

tt0805		94.54 231	93.85 242	96.63 210	97.98 197	93.06 264	98.77 126	97.84 262	93.67 206	93.80 252	98.04 191	76.88 335	98.96 205	94.79 179	92.86 261	97.86 210

MVS_0304		92.81 287	92.01 289	95.23 283	97.46 231	91.33 287	98.17 215	98.81 74	91.13 297	93.80 252	95.68 332	66.08 359	98.06 305	90.79 284	96.13 211	96.32 313

tpmvs		94.60 226	94.36 213	95.33 282	97.46 231	88.60 332	96.88 320	97.68 268	91.29 290	93.80 252	96.42 311	88.58 193	99.24 164	91.06 280	96.04 213	98.17 202

3Dnovator	94.51 5	97.46 79	96.93 92	99.07 49	97.78 206	97.64 67	99.35 17	99.06 23	97.02 50	93.75 255	99.16 63	89.25 175	99.92 23	97.22 94	99.75 38	99.64 64

eth_miper_zixun_eth		94.68 220	94.41 211	95.47 277	97.64 216	91.71 281	96.73 328	98.07 239	92.71 243	93.64 256	97.21 259	90.54 151	98.17 295	93.38 223	89.76 295	96.54 292

ITE_SJBPF				95.44 279	97.42 237	91.32 288		97.50 287	95.09 141	93.59 257	98.35 162	81.70 297	98.88 219	89.71 302	93.39 253	96.12 319

TranMVSNet+NR-MVSNet		95.14 197	94.48 204	97.11 176	96.45 296	96.36 123	99.03 70	99.03 26	95.04 143	93.58 258	97.93 201	88.27 201	98.03 307	94.13 201	86.90 333	96.95 239

COLMAP_ROB	93.27 12	95.33 187	94.87 188	96.71 201	99.29 67	93.24 258	98.58 161	98.11 229	89.92 316	93.57 259	99.10 72	86.37 241	99.79 84	90.78 285	98.10 155	97.09 229
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tpm cat1		93.36 275	92.80 277	95.07 290	97.58 220	87.97 342	96.76 326	97.86 261	82.17 357	93.53 260	96.04 322	86.13 244	99.13 178	89.24 311	95.87 214	98.10 204

AllTest		95.24 191	94.65 196	96.99 182	99.25 75	93.21 259	98.59 159	98.18 214	91.36 284	93.52 261	98.77 118	84.67 271	99.72 99	89.70 303	97.87 162	98.02 206

TestCases				96.99 182	99.25 75	93.21 259		98.18 214	91.36 284	93.52 261	98.77 118	84.67 271	99.72 99	89.70 303	97.87 162	98.02 206

miper_ehance_all_eth		95.01 203	94.69 195	95.97 258	97.70 213	93.31 255	97.02 307	98.07 239	92.23 261	93.51 263	96.96 285	91.85 120	98.15 296	93.68 215	91.16 280	96.44 307

FMVSNet2		94.47 238	93.61 258	97.04 179	98.21 175	96.43 119	98.79 124	98.27 199	92.46 249	93.50 264	97.09 267	81.16 301	98.00 310	91.09 278	91.93 269	96.70 272

v148		94.29 248	93.76 250	95.91 261	96.10 310	92.93 265	98.58 161	97.97 252	92.59 247	93.47 265	96.95 287	88.53 197	98.32 282	92.56 249	87.06 330	96.49 303

c3_l		94.79 215	94.43 210	95.89 263	97.75 208	93.12 262	97.16 301	98.03 247	92.23 261	93.46 266	97.05 275	91.39 132	98.01 308	93.58 220	89.21 306	96.53 294

pmmvs4		94.69 218	93.99 232	96.81 197	95.74 322	95.94 144	97.40 277	97.67 269	90.42 308	93.37 267	97.59 234	89.08 181	98.20 293	92.97 236	91.67 273	96.30 314

PCF-MVS	93.45 11	94.68 220	93.43 266	98.42 91	98.62 141	96.77 100	95.48 348	98.20 209	84.63 352	93.34 268	98.32 168	88.55 196	99.81 67	84.80 342	98.96 114	98.68 179
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
cl22		94.68 220	94.19 218	96.13 252	98.11 187	93.60 242	96.94 311	98.31 190	92.43 253	93.32 269	96.87 293	86.51 236	98.28 290	94.10 204	91.16 280	96.51 300

XXY-MVS		95.20 194	94.45 208	97.46 155	96.75 279	96.56 112	98.86 105	98.65 124	93.30 222	93.27 270	98.27 174	84.85 268	98.87 220	94.82 177	91.26 279	96.96 237

jajsoiax		95.45 176	95.03 179	96.73 200	95.42 334	94.63 203	99.14 48	98.52 149	95.74 104	93.22 271	98.36 161	83.87 288	98.65 240	96.95 103	94.04 231	96.91 245

mvs_tets		95.41 180	95.00 180	96.65 206	95.58 327	94.42 214	99.00 77	98.55 143	95.73 106	93.21 272	98.38 159	83.45 292	98.63 241	97.09 97	94.00 233	96.91 245

anonymousdsp		95.42 178	94.91 185	96.94 187	95.10 336	95.90 150	99.14 48	98.41 173	93.75 194	93.16 273	97.46 242	87.50 222	98.41 273	95.63 157	94.03 232	96.50 302

v8		94.47 238	93.77 248	96.57 219	96.36 299	94.83 196	99.05 64	98.19 211	91.92 269	93.16 273	96.97 283	88.82 191	98.48 256	91.69 271	87.79 321	96.39 308

WR-MVS		95.15 196	94.46 206	97.22 167	96.67 284	96.45 117	98.21 206	98.81 74	94.15 173	93.16 273	97.69 224	87.51 220	98.30 286	95.29 166	88.62 314	96.90 247

EPNet_dtu		95.21 193	94.95 184	95.99 256	96.17 307	90.45 303	98.16 216	97.27 304	96.77 61	93.14 276	98.33 167	90.34 154	98.42 265	85.57 335	98.81 124	99.09 145
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
QAPM		96.29 133	95.40 155	98.96 55	97.85 203	97.60 70	99.23 31	98.93 38	89.76 319	93.11 277	99.02 84	89.11 180	99.93 18	91.99 264	99.62 62	99.34 107

GG-mvs-BLEND				96.59 216	96.34 301	94.98 187	96.51 334	88.58 375		93.10 278	94.34 345	80.34 311	98.05 306	89.53 306	96.99 182	96.74 265

v10		94.29 248	93.55 261	96.51 228	96.39 298	94.80 198	98.99 79	98.19 211	91.35 286	93.02 279	96.99 281	88.09 206	98.41 273	90.50 289	88.41 316	96.33 312

3Dnovator+	94.38 6	97.43 84	96.78 100	99.38 18	97.83 204	98.52 28	99.37 14	98.71 105	97.09 48	92.99 280	99.13 68	89.36 171	99.89 36	96.97 101	99.57 70	99.71 42

D2MVS		95.18 195	95.08 177	95.48 276	97.10 259	92.07 273	98.30 197	99.13 20	94.02 179	92.90 281	96.73 298	89.48 167	98.73 233	94.48 190	93.60 247	95.65 330

Patchmtry		93.22 281	92.35 285	95.84 265	96.77 276	93.09 263	94.66 357	97.56 277	87.37 337	92.90 281	96.24 314	88.15 204	97.90 316	87.37 325	90.10 292	96.53 294

DIV-MVS_self_test		94.52 234	94.03 226	95.99 256	97.57 224	93.38 253	97.05 305	97.94 255	91.74 273	92.81 283	97.10 263	89.12 179	98.07 304	92.60 245	90.30 288	96.53 294

Anonymous20231211		94.10 261	93.26 271	96.61 213	99.11 97	94.28 219	99.01 75	98.88 50	86.43 341	92.81 283	97.57 236	81.66 298	98.68 238	94.83 176	89.02 310	96.88 249

cl____		94.51 235	94.01 229	96.02 255	97.58 220	93.40 252	97.05 305	97.96 254	91.73 275	92.76 285	97.08 269	89.06 182	98.13 298	92.61 244	90.29 289	96.52 297

miper_lstm_enhance		94.33 245	94.07 225	95.11 288	97.75 208	90.97 293	97.22 293	98.03 247	91.67 277	92.76 285	96.97 283	90.03 159	97.78 323	92.51 252	89.64 297	96.56 289

v7n		94.19 254	93.43 266	96.47 232	95.90 318	94.38 217	99.26 27	98.34 186	91.99 267	92.76 285	97.13 262	88.31 200	98.52 253	89.48 308	87.70 322	96.52 297

MVS		94.67 223	93.54 262	98.08 114	96.88 272	96.56 112	98.19 211	98.50 156	78.05 361	92.69 288	98.02 192	91.07 142	99.63 120	90.09 293	98.36 147	98.04 205

DSMNet-mixed		92.52 291	92.58 282	92.33 331	94.15 346	82.65 358	98.30 197	94.26 359	89.08 329	92.65 289	95.73 327	85.01 265	95.76 355	86.24 330	97.76 167	98.59 186

EU-MVSNet		93.66 270	94.14 222	92.25 333	95.96 317	83.38 356	98.52 169	98.12 226	94.69 156	92.61 290	98.13 185	87.36 225	96.39 352	91.82 267	90.00 293	96.98 235

IterMVS-SCA-FT		94.11 260	93.87 240	94.85 296	97.98 197	90.56 302	97.18 297	98.11 229	93.75 194	92.58 291	97.48 241	83.97 285	97.41 334	92.48 254	91.30 277	96.58 285

pmmvs5		93.65 272	92.97 275	95.68 270	95.49 330	92.37 269	98.20 208	97.28 303	89.66 321	92.58 291	97.26 254	82.14 295	98.09 302	93.18 230	90.95 283	96.58 285

WR-MVS_H		95.05 202	94.46 206	96.81 197	96.86 273	95.82 153	99.24 30	99.24 11	93.87 188	92.53 293	96.84 295	90.37 153	98.24 292	93.24 227	87.93 320	96.38 309

ACMP	93.49 10	95.34 186	94.98 182	96.43 237	97.67 214	93.48 248	98.73 134	98.44 167	94.94 150	92.53 293	98.53 141	84.50 275	99.14 177	95.48 161	94.00 233	96.66 278
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test0.0.03 1		94.08 263	93.51 263	95.80 266	95.53 329	92.89 266	97.38 279	95.97 341	95.11 138	92.51 295	96.66 301	87.71 216	96.94 341	87.03 326	93.67 242	97.57 218

IB-MVS	91.98 17	93.27 279	91.97 290	97.19 169	97.47 230	93.41 251	97.09 304	95.99 340	93.32 220	92.47 296	95.73 327	78.06 325	99.53 139	94.59 187	82.98 345	98.62 185
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
IterMVS		94.09 262	93.85 242	94.80 299	97.99 195	90.35 305	97.18 297	98.12 226	93.68 204	92.46 297	97.34 249	84.05 283	97.41 334	92.51 252	91.33 276	96.62 281
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CP-MVSNet		94.94 211	94.30 214	96.83 195	96.72 281	95.56 161	99.11 54	98.95 34	93.89 186	92.42 298	97.90 203	87.19 226	98.12 299	94.32 195	88.21 317	96.82 259

PS-CasMVS		94.67 223	93.99 232	96.71 201	96.68 283	95.26 174	99.13 51	99.03 26	93.68 204	92.33 299	97.95 200	85.35 259	98.10 300	93.59 219	88.16 319	96.79 260

FMVSNet1		93.19 283	92.07 288	96.56 220	97.54 225	95.00 184	98.82 112	98.18 214	90.38 309	92.27 300	97.07 270	73.68 348	97.95 312	89.36 310	91.30 277	96.72 268

PEN-MVS		94.42 241	93.73 252	96.49 229	96.28 303	94.84 194	99.17 44	99.00 28	93.51 212	92.23 301	97.83 213	86.10 245	97.90 316	92.55 250	86.92 332	96.74 265

OurMVSNet-221017-0		94.21 252	94.00 230	94.85 296	95.60 326	89.22 322	98.89 97	97.43 294	95.29 128	92.18 302	98.52 144	82.86 293	98.59 245	93.46 222	91.76 271	96.74 265

MS-PatchMatch		93.84 269	93.63 257	94.46 310	96.18 306	89.45 318	97.76 254	98.27 199	92.23 261	92.13 303	97.49 240	79.50 314	98.69 235	89.75 301	99.38 97	95.25 334

ppachtmachnet_test		93.22 281	92.63 281	94.97 292	95.45 332	90.84 295	96.88 320	97.88 260	90.60 303	92.08 304	97.26 254	88.08 207	97.86 321	85.12 339	90.33 287	96.22 316

1314		96.25 137	95.73 142	97.79 131	97.13 257	95.55 163	98.19 211	98.59 132	93.47 214	92.03 305	97.82 214	91.33 135	99.49 144	94.62 184	98.44 141	98.32 198

baseline2		95.11 198	94.52 202	96.87 193	96.65 285	93.56 243	98.27 202	94.10 362	93.45 215	92.02 306	97.43 246	87.45 224	99.19 170	93.88 210	97.41 177	97.87 209

DTE-MVSNet		93.98 267	93.26 271	96.14 251	96.06 312	94.39 216	99.20 39	98.86 63	93.06 230	91.78 307	97.81 215	85.87 249	97.58 329	90.53 288	86.17 337	96.46 306

LF4IMVS		93.14 284	92.79 278	94.20 313	95.88 319	88.67 331	97.66 262	97.07 311	93.81 192	91.71 308	97.65 228	77.96 326	98.81 227	91.47 274	91.92 270	95.12 337

our_test_3		93.65 272	93.30 269	94.69 301	95.45 332	89.68 315	96.91 314	97.65 270	91.97 268	91.66 309	96.88 291	89.67 165	97.93 315	88.02 321	91.49 275	96.48 304

testgi		93.06 285	92.45 284	94.88 295	96.43 297	89.90 309	98.75 127	97.54 283	95.60 111	91.63 310	97.91 202	74.46 345	97.02 339	86.10 331	93.67 242	97.72 215

tfpnnormal		93.66 270	92.70 280	96.55 225	96.94 267	95.94 144	98.97 82	99.19 16	91.04 298	91.38 311	97.34 249	84.94 266	98.61 242	85.45 337	89.02 310	95.11 338

LTVRE_ROB	92.95 15	94.60 226	93.90 238	96.68 205	97.41 240	94.42 214	98.52 169	98.59 132	91.69 276	91.21 312	98.35 162	84.87 267	99.04 193	91.06 280	93.44 252	96.60 283
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
OpenMVS	93.04 13	95.83 156	95.00 180	98.32 96	97.18 254	97.32 77	99.21 38	98.97 31	89.96 315	91.14 313	99.05 83	86.64 235	99.92 23	93.38 223	99.47 87	97.73 214

pm-mvs1		93.94 268	93.06 273	96.59 216	96.49 293	95.16 177	98.95 86	98.03 247	92.32 258	91.08 314	97.84 210	84.54 274	98.41 273	92.16 257	86.13 339	96.19 318

MVS-HIRNet		89.46 317	88.40 316	92.64 329	97.58 220	82.15 359	94.16 361	93.05 367	75.73 363	90.90 315	82.52 366	79.42 315	98.33 281	83.53 347	98.68 126	97.43 219

FMVSNet5		91.81 294	90.92 297	94.49 307	97.21 249	92.09 272	98.00 232	97.55 282	89.31 327	90.86 316	95.61 333	74.48 344	95.32 359	85.57 335	89.70 296	96.07 321

USDC		93.33 278	92.71 279	95.21 284	96.83 275	90.83 296	96.91 314	97.50 287	93.84 189	90.72 317	98.14 184	77.69 327	98.82 226	89.51 307	93.21 257	95.97 323

MVP-Stereo		94.28 250	93.92 235	95.35 281	94.95 338	92.60 268	97.97 234	97.65 270	91.61 278	90.68 318	97.09 267	86.32 242	98.42 265	89.70 303	99.34 99	95.02 341
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	92.99 14	94.30 247	93.77 248	95.88 264	97.81 205	92.04 275	98.71 139	98.37 181	93.99 182	90.60 319	98.47 148	80.86 306	99.05 190	92.75 243	92.40 265	96.55 291

CL-MVSNet_self_test		90.11 310	89.14 313	93.02 327	91.86 358	88.23 340	96.51 334	98.07 239	90.49 304	90.49 320	94.41 341	84.75 270	95.34 358	80.79 354	74.95 364	95.50 331

KD-MVS_self_test		90.38 308	89.38 311	93.40 321	92.85 355	88.94 328	97.95 235	97.94 255	90.35 310	90.25 321	93.96 346	79.82 312	95.94 354	84.62 344	76.69 362	95.33 333

Anonymous20231206		91.66 296	91.10 296	93.33 322	94.02 350	87.35 346	98.58 161	97.26 305	90.48 305	90.16 322	96.31 312	83.83 289	96.53 350	79.36 358	89.90 294	96.12 319

SixPastTwentyTwo		93.34 277	92.86 276	94.75 300	95.67 324	89.41 320	98.75 127	96.67 333	93.89 186	90.15 323	98.25 177	80.87 305	98.27 291	90.90 283	90.64 285	96.57 287

PVSNet_0	88.72 19	91.28 300	90.03 306	95.00 291	97.99 195	87.29 347	94.84 353	98.50 156	92.06 266	89.86 324	95.19 335	79.81 313	99.39 154	92.27 256	69.79 367	98.33 197

ACMH	92.88 16	94.55 230	93.95 234	96.34 243	97.63 217	93.26 257	98.81 118	98.49 161	93.43 216	89.74 325	98.53 141	81.91 296	99.08 188	93.69 214	93.30 255	96.70 272
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		91.77 295	90.63 300	95.17 286	94.69 344	91.24 290	98.67 149	97.92 257	86.14 343	89.62 326	97.56 238	75.79 339	98.34 280	90.75 286	84.56 341	95.94 324

TinyColmap		92.31 292	91.53 293	94.65 303	96.92 268	89.75 311	96.92 312	96.68 332	90.45 307	89.62 326	97.85 209	76.06 338	98.81 227	86.74 327	92.51 264	95.41 332

Anonymous20240521		91.18 301	90.44 302	93.42 319	93.70 351	88.47 335	98.94 88	97.56 277	88.46 332	89.56 328	95.08 338	77.15 334	96.97 340	83.92 345	89.55 300	94.82 343

TransMVSNet (Re)		92.67 289	91.51 294	96.15 250	96.58 288	94.65 201	98.90 93	96.73 329	90.86 301	89.46 329	97.86 207	85.62 253	98.09 302	86.45 329	81.12 351	95.71 328

NR-MVSNet		94.98 207	94.16 220	97.44 156	96.53 290	97.22 85	98.74 130	98.95 34	94.96 147	89.25 330	97.69 224	89.32 172	98.18 294	94.59 187	87.40 326	96.92 240

LCM-MVSNet-Re		95.22 192	95.32 164	94.91 293	98.18 181	87.85 344	98.75 127	95.66 345	95.11 138	88.96 331	96.85 294	90.26 157	97.65 325	95.65 156	98.44 141	99.22 126

KD-MVS_2432*1600		89.61 315	87.96 321	94.54 305	94.06 348	91.59 283	95.59 346	97.63 272	89.87 317	88.95 332	94.38 343	78.28 322	96.82 342	84.83 340	68.05 368	95.21 335

miper_refine_blended		89.61 315	87.96 321	94.54 305	94.06 348	91.59 283	95.59 346	97.63 272	89.87 317	88.95 332	94.38 343	78.28 322	96.82 342	84.83 340	68.05 368	95.21 335

test_fmvs3		87.17 323	87.06 326	87.50 342	91.21 360	75.66 365	99.05 64	96.61 335	92.79 241	88.85 334	92.78 354	43.72 369	93.49 365	93.95 207	84.56 341	93.34 358

TDRefinement		91.06 303	89.68 308	95.21 284	85.35 372	91.49 285	98.51 173	97.07 311	91.47 280	88.83 335	97.84 210	77.31 331	99.09 187	92.79 242	77.98 360	95.04 340

N_pmnet		87.12 325	87.77 323	85.17 346	95.46 331	61.92 376	97.37 281	70.66 382	85.83 346	88.73 336	96.04 322	85.33 261	97.76 324	80.02 355	90.48 286	95.84 325

test_0402		91.32 298	90.27 304	94.48 308	96.60 286	91.12 291	98.50 174	97.22 307	86.10 344	88.30 337	96.98 282	77.65 329	97.99 311	78.13 362	92.94 260	94.34 345

test20.03		90.89 305	90.38 303	92.43 330	93.48 352	88.14 341	98.33 190	97.56 277	93.40 217	87.96 338	96.71 300	80.69 308	94.13 364	79.15 359	86.17 337	95.01 342

MIMVSNet1		89.67 314	88.28 318	93.82 316	92.81 356	91.08 292	98.01 230	97.45 292	87.95 334	87.90 339	95.87 324	67.63 356	94.56 363	78.73 361	88.18 318	95.83 326

mvsany_test3		88.80 319	88.04 319	91.09 337	89.78 364	81.57 361	97.83 250	95.49 346	93.81 192	87.53 340	93.95 347	56.14 365	97.43 333	94.68 180	83.13 344	94.26 346

Patchmatch-RL test		91.49 297	90.85 298	93.41 320	91.37 359	84.40 352	92.81 362	95.93 343	91.87 271	87.25 341	94.87 339	88.99 183	96.53 350	92.54 251	82.00 347	99.30 116

pmmvs3		86.67 326	84.86 330	92.11 334	88.16 366	87.19 348	96.63 330	94.75 354	79.88 359	87.22 342	92.75 356	66.56 358	95.20 360	81.24 353	76.56 363	93.96 354

test_vis1_rt		91.29 299	90.65 299	93.19 326	97.45 235	86.25 350	98.57 166	90.90 372	93.30 222	86.94 343	93.59 349	62.07 362	99.11 182	97.48 85	95.58 216	94.22 348

K. test v3		92.55 290	91.91 292	94.48 308	95.64 325	89.24 321	99.07 61	94.88 352	94.04 177	86.78 344	97.59 234	77.64 330	97.64 326	92.08 259	89.43 303	96.57 287

lessismore_v0				94.45 311	94.93 339	88.44 336		91.03 371		86.77 345	97.64 230	76.23 337	98.42 265	90.31 291	85.64 340	96.51 300

APD_test1		88.22 321	88.01 320	88.86 340	95.98 315	74.66 369	97.21 294	96.44 337	83.96 354	86.66 346	97.90 203	60.95 363	97.84 322	82.73 348	90.23 290	94.09 351

ambc				89.49 339	86.66 369	75.78 364	92.66 363	96.72 330		86.55 347	92.50 357	46.01 367	97.90 316	90.32 290	82.09 346	94.80 344

PM-MVS		87.77 322	86.55 327	91.40 336	91.03 362	83.36 357	96.92 312	95.18 350	91.28 291	86.48 348	93.42 350	53.27 366	96.74 344	89.43 309	81.97 348	94.11 350

OpenMVS_ROB	86.42 20	89.00 318	87.43 325	93.69 317	93.08 354	89.42 319	97.91 239	96.89 324	78.58 360	85.86 349	94.69 340	69.48 353	98.29 289	77.13 363	93.29 256	93.36 357

UnsupCasMVSNet_eth		90.99 304	89.92 307	94.19 314	94.08 347	89.83 310	97.13 303	98.67 117	93.69 202	85.83 350	96.19 319	75.15 341	96.74 344	89.14 312	79.41 356	96.00 322

new_pmnet		90.06 311	89.00 315	93.22 325	94.18 345	88.32 338	96.42 336	96.89 324	86.19 342	85.67 351	93.62 348	77.18 333	97.10 338	81.61 352	89.29 305	94.23 347

test_f		86.07 327	85.39 328	88.10 341	89.28 365	75.57 366	97.73 257	96.33 338	89.41 326	85.35 352	91.56 360	43.31 371	95.53 356	91.32 276	84.23 343	93.21 359

EG-PatchMatch MVS		91.13 302	90.12 305	94.17 315	94.73 343	89.00 326	98.13 219	97.81 263	89.22 328	85.32 353	96.46 309	67.71 355	98.42 265	87.89 323	93.82 238	95.08 339

pmmvs-eth3d		90.36 309	89.05 314	94.32 312	91.10 361	92.12 271	97.63 267	96.95 319	88.86 330	84.91 354	93.13 353	78.32 321	96.74 344	88.70 316	81.81 349	94.09 351

DeepMVS_CX				86.78 343	97.09 260	72.30 370		95.17 351	75.92 362	84.34 355	95.19 335	70.58 351	95.35 357	79.98 357	89.04 309	92.68 360

new-patchmatchnet		88.50 320	87.45 324	91.67 335	90.31 363	85.89 351	97.16 301	97.33 300	89.47 323	83.63 356	92.77 355	76.38 336	95.06 361	82.70 349	77.29 361	94.06 353

UnsupCasMVSNet_bld		87.17 323	85.12 329	93.31 323	91.94 357	88.77 329	94.92 352	98.30 196	84.30 353	82.30 357	90.04 361	63.96 361	97.25 336	85.85 334	74.47 366	93.93 355

CMPMVS	66.06 21	89.70 313	89.67 309	89.78 338	93.19 353	76.56 363	97.00 308	98.35 184	80.97 358	81.57 358	97.75 218	74.75 343	98.61 242	89.85 299	93.63 245	94.17 349
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_method		79.03 329	78.17 331	81.63 351	86.06 371	54.40 381	82.75 370	96.89 324	39.54 374	80.98 359	95.57 334	58.37 364	94.73 362	84.74 343	78.61 357	95.75 327

ET-MVSNet_ETH3D		94.13 258	92.98 274	97.58 151	98.22 174	96.20 129	97.31 288	95.37 347	94.53 162	79.56 360	97.63 232	86.51 236	97.53 331	96.91 104	90.74 284	99.02 153

LCM-MVSNet		78.70 332	76.24 337	86.08 344	77.26 378	71.99 371	94.34 359	96.72 330	61.62 369	76.53 361	89.33 362	33.91 377	92.78 369	81.85 351	74.60 365	93.46 356

PMMVS2		77.95 334	75.44 338	85.46 345	82.54 373	74.95 367	94.23 360	93.08 366	72.80 364	74.68 362	87.38 363	36.36 374	91.56 370	73.95 365	63.94 370	89.87 362

testf1		79.02 330	77.70 332	82.99 349	88.10 367	66.90 373	94.67 355	93.11 364	71.08 365	74.02 363	93.41 351	34.15 375	93.25 366	72.25 367	78.50 358	88.82 363

APD_test2		79.02 330	77.70 332	82.99 349	88.10 367	66.90 373	94.67 355	93.11 364	71.08 365	74.02 363	93.41 351	34.15 375	93.25 366	72.25 367	78.50 358	88.82 363

Gipuma		78.40 333	76.75 336	83.38 348	95.54 328	80.43 362	79.42 371	97.40 296	64.67 368	73.46 365	80.82 369	45.65 368	93.14 368	66.32 370	87.43 325	76.56 371
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		90.70 307	89.39 310	94.62 304	94.79 342	90.65 300	97.20 295	97.46 290	87.54 336	72.54 366	95.74 325	86.51 236	96.66 348	86.00 332	86.76 335	96.54 292

MDA-MVSNet_test_wron		90.71 306	89.38 311	94.68 302	94.83 340	90.78 297	97.19 296	97.46 290	87.60 335	72.41 367	95.72 329	86.51 236	96.71 347	85.92 333	86.80 334	96.56 289

MDA-MVSNet-bldmvs		89.97 312	88.35 317	94.83 298	95.21 335	91.34 286	97.64 264	97.51 286	88.36 333	71.17 368	96.13 320	79.22 316	96.63 349	83.65 346	86.27 336	96.52 297

FPMVS		77.62 335	77.14 335	79.05 353	79.25 376	60.97 377	95.79 343	95.94 342	65.96 367	67.93 369	94.40 342	37.73 373	88.88 372	68.83 369	88.46 315	87.29 365

test_vis3_rt		79.22 328	77.40 334	84.67 347	86.44 370	74.85 368	97.66 262	81.43 379	84.98 350	67.12 370	81.91 368	28.09 379	97.60 327	88.96 314	80.04 355	81.55 368

tmp_tt		68.90 338	66.97 340	74.68 355	50.78 382	59.95 378	87.13 367	83.47 378	38.80 375	62.21 371	96.23 316	64.70 360	76.91 377	88.91 315	30.49 375	87.19 366

E-PMN		64.94 340	64.25 342	67.02 357	82.28 374	59.36 379	91.83 365	85.63 376	52.69 371	60.22 372	77.28 371	41.06 372	80.12 375	46.15 374	41.14 372	61.57 373

EMVS		64.07 341	63.26 344	66.53 358	81.73 375	58.81 380	91.85 364	84.75 377	51.93 373	59.09 373	75.13 372	43.32 370	79.09 376	42.03 375	39.47 373	61.69 372

MVE	62.14 22	63.28 342	59.38 345	74.99 354	74.33 379	65.47 375	85.55 368	80.50 380	52.02 372	51.10 374	75.00 373	10.91 383	80.50 374	51.60 373	53.40 371	78.99 369
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		69.08 337	65.37 341	80.22 352	65.99 380	71.96 372	90.91 366	90.09 373	82.62 355	49.93 375	78.39 370	29.36 378	81.75 373	62.49 371	38.52 374	86.95 367

PMVS	61.03 23	65.95 339	63.57 343	73.09 356	57.90 381	51.22 382	85.05 369	93.93 363	54.45 370	44.32 376	83.57 365	13.22 380	89.15 371	58.68 372	81.00 352	78.91 370
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		21.48 345	24.95 348	11.09 361	14.89 383	6.47 385	96.56 332	9.87 384	7.55 377	17.93 377	39.02 375	9.43 384	5.90 380	16.56 378	12.72 377	20.91 375

test123		20.95 346	23.72 349	12.64 360	13.54 384	8.19 384	96.55 333	6.13 385	7.48 378	16.74 378	37.98 376	12.97 381	6.05 379	16.69 377	5.43 378	23.68 374

wuyk23d		30.17 343	30.18 347	30.16 359	78.61 377	43.29 383	66.79 372	14.21 383	17.31 376	14.82 379	11.93 379	11.55 382	41.43 378	37.08 376	19.30 376	5.76 376

EGC-MVSNET		75.22 336	69.54 339	92.28 332	94.81 341	89.58 316	97.64 264	96.50 336	1.82 379	5.57 380	95.74 325	68.21 354	96.26 353	73.80 366	91.71 272	90.99 361

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

cdsmvs_eth3d_5k		23.98 344	31.98 346	0.00 362	0.00 385	0.00 386	0.00 373	98.59 132	0.00 380	0.00 381	98.61 132	90.60 150	0.00 381	0.00 379	0.00 379	0.00 377

pcd_1.5k_mvsjas		7.88 348	10.50 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	94.51 77	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		8.20 347	10.94 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	98.43 152	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

MSC_two_6792asdad				99.62 6	99.17 88	99.08 11		98.63 127					99.94 3	98.53 16	99.80 19	99.86 2

No_MVS				99.62 6	99.17 88	99.08 11		98.63 127					99.94 3	98.53 16	99.80 19	99.86 2

eth-test2					0.00 385

eth-test					0.00 385

OPU-MVS				99.37 20	99.24 81	99.05 14	99.02 73				99.16 63	97.81 3	99.37 155	97.24 92	99.73 43	99.70 46

save fliter					99.46 49	98.38 35	98.21 206	98.71 105	97.95 4

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 82	98.88 50					99.94 3	98.47 24	99.81 12	99.84 6

GSMVS																99.20 127

sam_mvs1												89.45 169				99.20 127

sam_mvs												88.99 183

MTGPA								98.74 97

test_post1							96.68 329				30.43 378	87.85 214	98.69 235	92.59 247

test_post											31.83 377	88.83 190	98.91 213

patchmatchnet-post											95.10 337	89.42 170	98.89 217

MTMP							98.89 97	94.14 361

gm-plane-assit					95.88 319	87.47 345			89.74 320		96.94 288		99.19 170	93.32 226

test9_res														96.39 131	99.57 70	99.69 49

agg_prior2														95.87 147	99.57 70	99.68 54

test_prior4						98.01 58	97.86 246

test_prior				99.19 38	99.31 61	98.22 47		98.84 67					99.70 105			99.65 62

新几何2							97.64 264

旧先验1					99.29 67	97.48 73		98.70 108			99.09 78	95.56 45			99.47 87	99.61 68

无先验							97.58 269	98.72 102	91.38 283				99.87 45	93.36 225		99.60 70

原ACMM2							97.67 261

testdata2													99.89 36	91.65 272

segment_acmp												96.85 14

testdata1							97.32 287		96.34 81

plane_prior7					97.42 237	94.63 203

plane_prior6					97.35 242	94.61 206						87.09 227

plane_prior5								98.56 141					99.03 194	96.07 137	94.27 222	96.92 240

plane_prior4											98.28 171

plane_prior2							98.80 119		97.28 32

plane_prior1					97.37 241

plane_prior						94.60 208	98.44 181		96.74 63						94.22 224

n2								0.00 386

nn								0.00 386

door-mid								94.37 357

test11								98.66 120

door								94.64 355

HQP5-MVS						94.25 222

BP-MVS														95.30 164

HQP3-MVS								98.46 163							94.18 226

HQP2-MVS												86.75 233

NP-MVS					97.28 244	94.51 211					97.73 219

ACMMP++_ref															92.97 259

ACMMP++															93.61 246

Test By Simon												94.64 74

High-resolution multi-view benchmark