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.

DeepPCF-MVS	93.56 1	96.55 39	97.84 10	92.68 220	98.71 85	78.11 341	99.70 26	97.71 82	98.18 1	97.36 62	99.76 1	90.37 47	99.94 34	99.27 16	99.54 52	99.99 1

CNVR-MVS		98.46 1	98.38 1	98.72 9	99.80 4	96.19 15	99.80 15	97.99 52	97.05 6	99.41 4	99.59 2	92.89 25	100.00 1	98.99 25	99.90 7	99.96 10

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 25	99.77 17	97.72 78	94.17 43	99.30 8	99.54 3	93.32 19	99.98 9	99.70 4	99.81 23	99.99 1

test_241102_TWO								97.72 78	94.17 43	99.23 10	99.54 3	93.14 24	99.98 9	99.70 4	99.82 19	99.99 1

test0726					99.66 12	95.20 30	99.77 17	97.70 83	93.95 48	99.35 7	99.54 3	93.18 22

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 21	99.29 81	97.72 78	94.50 37	98.64 28	99.54 3	93.32 19	99.97 21	99.58 10	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DPM-MVS		97.86 8	97.25 20	99.68 1	98.25 93	99.10 1	99.76 20	97.78 70	96.61 12	98.15 41	99.53 7	93.62 17	100.00 1	91.79 157	99.80 26	99.94 18

SMA-MVS		97.24 19	96.99 23	98.00 29	99.30 54	94.20 55	99.16 93	97.65 96	89.55 154	99.22 12	99.52 8	90.34 48	99.99 5	98.32 43	99.83 15	99.82 32
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
test_241102_ONE					99.63 18	95.24 25		97.72 78	94.16 45	99.30 8	99.49 9	93.32 19	99.98 9

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 30	99.72 23	97.47 135	93.95 48	99.07 15	99.46 10	93.18 22	99.97 21	99.64 7	99.82 19	99.69 55
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									93.01 70	99.07 15	99.46 10	94.66 14	99.97 21	99.25 18	99.82 19	99.95 15

MSLP-MVS++		97.50 16	97.45 17	97.63 38	99.65 16	93.21 72	99.70 26	98.13 42	94.61 35	97.78 55	99.46 10	89.85 51	99.81 79	97.97 50	99.91 6	99.88 26

NCCC		98.12 5	98.11 3	98.13 24	99.76 6	94.46 48	99.81 11	97.88 56	96.54 13	98.84 24	99.46 10	92.55 27	99.98 9	98.25 46	99.93 1	99.94 18

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 22	99.55 44	97.68 87	93.01 70	99.23 10	99.45 14	95.12 8	99.98 9	99.25 18	99.92 3	99.97 7

test_one_0601					99.59 28	94.89 34		97.64 97	93.14 69	98.93 21	99.45 14	93.45 18

9.14			96.87 26		99.34 50		99.50 51	97.49 132	89.41 157	98.59 30	99.43 16	89.78 52	99.69 91	98.69 30	99.62 44

SF-MVS		97.22 21	96.92 24	98.12 26	99.11 66	94.88 35	99.44 62	97.45 138	89.60 150	98.70 26	99.42 17	90.42 45	99.72 89	98.47 38	99.65 38	99.77 43

DeepC-MVS_fast	93.52 2	97.16 23	96.84 28	98.13 24	99.61 24	94.45 49	98.85 131	97.64 97	96.51 16	95.88 97	99.39 18	87.35 87	99.99 5	96.61 77	99.69 36	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 26	97.98 53	97.18 3	95.96 94	99.33 19	92.62 26	100.00 1	98.99 25	99.93 1	99.98 6

HPM-MVS++		97.72 10	97.59 13	98.14 23	99.53 40	94.76 42	99.19 87	97.75 73	95.66 24	98.21 40	99.29 20	91.10 33	99.99 5	97.68 55	99.87 9	99.68 56

fmvsm_l_conf0.5_n_a		97.70 11	97.80 11	97.42 45	97.59 116	92.91 82	99.86 4	98.04 48	96.70 10	99.58 2	99.26 21	90.90 37	99.94 34	99.57 11	98.66 98	99.40 85

SteuartSystems-ACMMP		97.25 18	97.34 19	97.01 60	97.38 122	91.46 102	99.75 21	97.66 91	94.14 47	98.13 42	99.26 21	92.16 29	99.66 94	97.91 52	99.64 40	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS-pluss		95.80 63	95.30 71	97.29 50	98.95 76	92.66 85	98.59 162	97.14 168	88.95 169	93.12 142	99.25 23	85.62 122	99.94 34	96.56 79	99.48 54	99.28 97
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CSCG		94.87 86	94.71 83	95.36 135	99.54 36	86.49 224	99.34 77	98.15 40	82.71 302	90.15 187	99.25 23	89.48 54	99.86 63	94.97 111	98.82 90	99.72 50

MTAPA		96.09 50	95.80 60	96.96 67	99.29 55	91.19 106	97.23 260	97.45 138	92.58 79	94.39 124	99.24 25	86.43 110	99.99 5	96.22 83	99.40 62	99.71 51

fmvsm_l_conf0.5_n		97.65 12	97.72 12	97.41 46	97.51 120	92.78 84	99.85 7	98.05 46	96.78 8	99.60 1	99.23 26	90.42 45	99.92 40	99.55 12	98.50 103	99.55 72

CDPH-MVS		96.56 38	96.18 44	97.70 36	99.59 28	93.92 60	99.13 104	97.44 141	89.02 166	97.90 53	99.22 27	88.90 60	99.49 112	94.63 119	99.79 27	99.68 56

API-MVS		94.78 89	94.18 94	96.59 87	99.21 61	90.06 143	98.80 136	97.78 70	83.59 286	93.85 133	99.21 28	83.79 148	99.97 21	92.37 153	99.00 79	99.74 47

PHI-MVS		96.65 36	96.46 37	97.21 54	99.34 50	91.77 95	99.70 26	98.05 46	86.48 240	98.05 47	99.20 29	89.33 55	99.96 28	98.38 39	99.62 44	99.90 22

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 17				99.19 30	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

MSP-MVS		97.77 9	98.18 2	96.53 92	99.54 36	90.14 136	99.41 68	97.70 83	95.46 28	98.60 29	99.19 30	95.71 4	99.49 112	98.15 48	99.85 13	99.95 15
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
test_8					99.55 35	93.07 76	99.37 74	97.64 97	90.18 134	98.36 37	99.19 30	90.94 35	99.64 100

TEST9					99.57 33	93.17 73	99.38 71	97.66 91	89.57 152	98.39 35	99.18 33	90.88 38	99.66 94

train_agg		97.20 22	97.08 22	97.57 42	99.57 33	93.17 73	99.38 71	97.66 91	90.18 134	98.39 35	99.18 33	90.94 35	99.66 94	98.58 36	99.85 13	99.88 26

MAR-MVS		94.43 101	94.09 96	95.45 132	99.10 68	87.47 204	98.39 189	97.79 69	88.37 188	94.02 130	99.17 35	78.64 216	99.91 45	92.48 152	98.85 89	98.96 123
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
fmvsm_s_conf0.5_n_a		95.97 55	96.19 42	95.31 138	96.51 157	89.01 166	99.81 11	98.39 27	95.46 28	99.19 13	99.16 36	81.44 194	99.91 45	98.83 28	96.97 136	97.01 208

ZD-MVS					99.67 10	93.28 71		97.61 104	87.78 208	97.41 60	99.16 36	90.15 49	99.56 105	98.35 41	99.70 35

CP-MVS		96.22 47	96.15 50	96.42 97	99.67 10	89.62 154	99.70 26	97.61 104	90.07 140	96.00 93	99.16 36	87.43 81	99.92 40	96.03 88	99.72 31	99.70 52

fmvsm_s_conf0.5_n		96.19 48	96.49 35	95.30 139	97.37 123	89.16 160	99.86 4	98.47 25	95.68 23	98.87 22	99.15 39	82.44 180	99.92 40	99.14 21	97.43 127	96.83 212

旧先验1					98.97 73	92.90 83		97.74 74			99.15 39	91.05 34			99.33 63	99.60 67

testdata				95.26 141	98.20 95	87.28 211		97.60 106	85.21 257	98.48 33	99.15 39	88.15 70	98.72 162	90.29 173	99.45 57	99.78 38

ACMMP_NAP		96.59 37	96.18 44	97.81 34	98.82 81	93.55 66	98.88 130	97.59 110	90.66 119	97.98 51	99.14 42	86.59 104	100.00 1	96.47 81	99.46 55	99.89 25

PS-MVSNAJ		96.87 30	96.40 38	98.29 19	97.35 124	97.29 5	99.03 115	97.11 172	95.83 20	98.97 19	99.14 42	82.48 176	99.60 103	98.60 33	99.08 73	98.00 180

test_fmvsm_n_1920		97.08 26	97.55 14	95.67 126	97.94 104	89.61 155	99.93 1	98.48 24	97.08 5	99.08 14	99.13 44	88.17 68	99.93 38	99.11 23	99.06 75	97.47 193

DP-MVS Recon		95.85 61	95.15 76	97.95 30	99.87 2	94.38 52	99.60 38	97.48 133	86.58 235	94.42 123	99.13 44	87.36 86	99.98 9	93.64 135	98.33 107	99.48 79

PC_three_1452									94.60 36	99.41 4	99.12 46	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

SR-MVS		96.13 49	96.16 49	96.07 110	99.42 47	89.04 164	98.59 162	97.33 152	90.44 128	96.84 76	99.12 46	86.75 99	99.41 126	97.47 58	99.44 58	99.76 45

APDe-MVS		97.53 13	97.47 15	97.70 36	99.58 30	93.63 64	99.56 43	97.52 125	93.59 63	98.01 50	99.12 46	90.80 40	99.55 106	99.26 17	99.79 27	99.93 20
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PAPR		96.35 42	95.82 57	97.94 31	99.63 18	94.19 56	99.42 67	97.55 117	92.43 82	93.82 135	99.12 46	87.30 88	99.91 45	94.02 126	99.06 75	99.74 47

xiu_mvs_v2_base		96.66 35	96.17 47	98.11 27	97.11 137	96.96 6	99.01 118	97.04 179	95.51 27	98.86 23	99.11 50	82.19 184	99.36 130	98.59 35	98.14 111	98.00 180

region2R		96.30 45	96.17 47	96.70 81	99.70 7	90.31 130	99.46 59	97.66 91	90.55 124	97.07 71	99.07 51	86.85 97	99.97 21	95.43 99	99.74 29	99.81 33

APD-MVS		96.95 28	96.72 31	97.63 38	99.51 41	93.58 65	99.16 93	97.44 141	90.08 139	98.59 30	99.07 51	89.06 57	99.42 123	97.92 51	99.66 37	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
新几何1				97.40 47	98.92 77	92.51 90		97.77 72	85.52 253	96.69 83	99.06 53	88.08 72	99.89 53	84.88 235	99.62 44	99.79 36

CS-MVS-test		95.98 54	96.34 40	94.90 153	98.06 101	87.66 198	99.69 33	96.10 235	93.66 60	98.35 38	99.05 54	86.28 112	97.66 215	96.96 69	98.90 87	99.37 88

HFP-MVS		96.42 41	96.26 41	96.90 69	99.69 8	90.96 117	99.47 55	97.81 65	90.54 125	96.88 73	99.05 54	87.57 78	99.96 28	95.65 92	99.72 31	99.78 38

fmvsm_s_conf0.1_n		95.56 71	95.68 64	95.20 142	94.35 242	89.10 162	99.50 51	97.67 90	94.76 34	98.68 27	99.03 56	81.13 197	99.86 63	98.63 32	97.36 129	96.63 215

ACMMPR		96.28 46	96.14 51	96.73 78	99.68 9	90.47 128	99.47 55	97.80 67	90.54 125	96.83 78	99.03 56	86.51 108	99.95 31	95.65 92	99.72 31	99.75 46

test222					98.32 92	91.21 105	98.08 216	97.58 112	83.74 282	95.87 98	99.02 58	86.74 100			99.64 40	99.81 33

SD-MVS		97.51 15	97.40 18	97.81 34	99.01 72	93.79 63	99.33 78	97.38 148	93.73 59	98.83 25	99.02 58	90.87 39	99.88 54	98.69 30	99.74 29	99.77 43
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
fmvsm_s_conf0.1_n_a		95.16 80	95.15 76	95.18 143	92.06 291	88.94 170	99.29 81	97.53 121	94.46 38	98.98 18	98.99 60	79.99 202	99.85 67	98.24 47	96.86 138	96.73 213

APD-MVS_3200maxsize		95.64 70	95.65 67	95.62 128	99.24 58	87.80 194	98.42 180	97.22 159	88.93 171	96.64 86	98.98 61	85.49 126	99.36 130	96.68 74	99.27 68	99.70 52

SR-MVS-dyc-post		95.75 67	95.86 56	95.41 134	99.22 59	87.26 214	98.40 185	97.21 160	89.63 148	96.67 84	98.97 62	86.73 101	99.36 130	96.62 75	99.31 65	99.60 67

RE-MVS-def			95.70 63		99.22 59	87.26 214	98.40 185	97.21 160	89.63 148	96.67 84	98.97 62	85.24 132		96.62 75	99.31 65	99.60 67

test_prior2							99.57 42		91.43 105	98.12 44	98.97 62	90.43 44		98.33 42	99.81 23

原ACMM1				96.18 105	99.03 71	90.08 139		97.63 101	88.98 167	97.00 72	98.97 62	88.14 71	99.71 90	88.23 197	99.62 44	98.76 147

MM				98.86 5		96.83 7	99.81 11	99.13 9	97.66 2	98.29 39	98.96 66	85.84 121	99.90 50	99.72 3	98.80 91	99.85 30

XVS		96.47 40	96.37 39	96.77 74	99.62 22	90.66 125	99.43 65	97.58 112	92.41 85	96.86 74	98.96 66	87.37 83	99.87 58	95.65 92	99.43 59	99.78 38

CPTT-MVS		94.60 97	94.43 87	95.09 146	99.66 12	86.85 219	99.44 62	97.47 135	83.22 291	94.34 125	98.96 66	82.50 174	99.55 106	94.81 113	99.50 53	98.88 133

MP-MVS		96.00 52	95.82 57	96.54 91	99.47 46	90.13 138	99.36 75	97.41 145	90.64 122	95.49 107	98.95 69	85.51 125	99.98 9	96.00 89	99.59 49	99.52 75
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		95.85 61	95.65 67	96.45 95	99.50 42	89.77 151	98.22 201	98.90 13	89.19 161	96.74 81	98.95 69	85.91 120	99.92 40	93.94 128	99.46 55	99.66 60

mPP-MVS		95.90 60	95.75 62	96.38 100	99.58 30	89.41 158	99.26 84	97.41 145	90.66 119	94.82 117	98.95 69	86.15 116	99.98 9	95.24 104	99.64 40	99.74 47

ZNCC-MVS		96.09 50	95.81 59	96.95 68	99.42 47	91.19 106	99.55 44	97.53 121	89.72 145	95.86 99	98.94 72	86.59 104	99.97 21	95.13 105	99.56 50	99.68 56

MVS_0304		97.53 13	97.15 21	98.67 11	97.30 126	96.52 12	99.60 38	98.88 14	97.14 4	97.21 66	98.94 72	86.89 96	99.91 45	99.43 15	98.91 86	99.59 71

test_fmvsmconf_n		96.78 33	96.84 28	96.61 85	95.99 182	90.25 131	99.90 2	98.13 42	96.68 11	98.42 34	98.92 74	85.34 131	99.88 54	99.12 22	99.08 73	99.70 52

patch_mono-2		97.10 25	97.97 8	94.49 168	99.21 61	83.73 284	99.62 37	98.25 32	95.28 30	99.38 6	98.91 75	92.28 28	99.94 34	99.61 9	99.22 70	99.78 38

CANet		97.00 27	96.49 35	98.55 12	98.86 80	96.10 16	99.83 9	97.52 125	95.90 19	97.21 66	98.90 76	82.66 173	99.93 38	98.71 29	98.80 91	99.63 64

PAPM_NR		95.43 73	95.05 80	96.57 90	99.42 47	90.14 136	98.58 164	97.51 127	90.65 121	92.44 150	98.90 76	87.77 77	99.90 50	90.88 165	99.32 64	99.68 56

test_fmvsmvis_n_1920		95.47 72	95.40 70	95.70 124	94.33 243	90.22 134	99.70 26	96.98 186	96.80 7	92.75 146	98.89 78	82.46 179	99.92 40	98.36 40	98.33 107	96.97 209

CS-MVS		95.75 67	96.19 42	94.40 172	97.88 106	86.22 235	99.66 34	96.12 234	92.69 78	98.07 46	98.89 78	87.09 90	97.59 221	96.71 72	98.62 99	99.39 87

EI-MVSNet-Vis-set		95.76 66	95.63 69	96.17 107	99.14 64	90.33 129	98.49 173	97.82 62	91.92 95	94.75 118	98.88 80	87.06 92	99.48 116	95.40 100	97.17 134	98.70 150

CNLPA		93.64 123	92.74 132	96.36 101	98.96 75	90.01 146	99.19 87	95.89 260	86.22 243	89.40 195	98.85 81	80.66 200	99.84 69	88.57 193	96.92 137	99.24 100

xiu_mvs_v1_base_debu		94.73 91	93.98 99	96.99 62	95.19 209	95.24 25	98.62 156	96.50 209	92.99 72	97.52 57	98.83 82	72.37 257	99.15 141	97.03 65	96.74 139	96.58 218

xiu_mvs_v1_base		94.73 91	93.98 99	96.99 62	95.19 209	95.24 25	98.62 156	96.50 209	92.99 72	97.52 57	98.83 82	72.37 257	99.15 141	97.03 65	96.74 139	96.58 218

xiu_mvs_v1_base_debi		94.73 91	93.98 99	96.99 62	95.19 209	95.24 25	98.62 156	96.50 209	92.99 72	97.52 57	98.83 82	72.37 257	99.15 141	97.03 65	96.74 139	96.58 218

cdsmvs_eth3d_5k		22.52 364	30.03 367	0.00 384	0.00 406	0.00 409	0.00 395	97.17 166	0.00 402	0.00 403	98.77 85	74.35 239	0.00 403	0.00 402	0.00 401	0.00 399

EI-MVSNet-UG-set		95.43 73	95.29 72	95.86 119	99.07 70	89.87 148	98.43 179	97.80 67	91.78 97	94.11 128	98.77 85	86.25 114	99.48 116	94.95 112	96.45 143	98.22 174

lupinMVS		96.32 44	95.94 53	97.44 44	95.05 223	94.87 36	99.86 4	96.50 209	93.82 57	98.04 48	98.77 85	85.52 123	98.09 185	96.98 68	98.97 81	99.37 88

LS3D		90.19 197	88.72 209	94.59 167	98.97 73	86.33 232	96.90 272	96.60 200	74.96 354	84.06 243	98.74 88	75.78 228	99.83 73	74.93 318	97.57 121	97.62 190

MVS_111021_HR		96.69 34	96.69 32	96.72 80	98.58 88	91.00 116	99.14 101	99.45 1	93.86 54	95.15 113	98.73 89	88.48 64	99.76 86	97.23 63	99.56 50	99.40 85

OMC-MVS		93.90 113	93.62 110	94.73 161	98.63 87	87.00 217	98.04 219	96.56 205	92.19 90	92.46 149	98.73 89	79.49 208	99.14 145	92.16 155	94.34 172	98.03 179

GST-MVS		95.97 55	95.66 65	96.90 69	99.49 45	91.22 104	99.45 61	97.48 133	89.69 146	95.89 96	98.72 91	86.37 111	99.95 31	94.62 120	99.22 70	99.52 75

PAPM		96.35 42	95.94 53	97.58 40	94.10 248	95.25 24	98.93 125	98.17 37	94.26 42	93.94 131	98.72 91	89.68 53	97.88 197	96.36 82	99.29 67	99.62 66

ACMMP		94.67 95	94.30 88	95.79 121	99.25 57	88.13 188	98.41 182	98.67 22	90.38 130	91.43 165	98.72 91	82.22 183	99.95 31	93.83 132	95.76 157	99.29 96
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
mvsany_test1		94.57 99	95.09 79	92.98 211	95.84 186	82.07 305	98.76 142	95.24 299	92.87 77	96.45 87	98.71 94	84.81 138	99.15 141	97.68 55	95.49 162	97.73 185

MG-MVS		97.24 19	96.83 30	98.47 15	99.79 5	95.71 18	99.07 109	99.06 10	94.45 40	96.42 88	98.70 95	88.81 61	99.74 88	95.35 101	99.86 12	99.97 7

MVS_111021_LR		95.78 64	95.94 53	95.28 140	98.19 97	87.69 195	98.80 136	99.26 7	93.39 65	95.04 115	98.69 96	84.09 145	99.76 86	96.96 69	99.06 75	98.38 165

test_fmvsmconf0.1_n		95.94 58	95.79 61	96.40 99	92.42 285	89.92 147	99.79 16	96.85 190	96.53 15	97.22 65	98.67 97	82.71 172	99.84 69	98.92 27	98.98 80	99.43 84

AdaColmap		93.82 116	93.06 123	96.10 109	99.88 1	89.07 163	98.33 193	97.55 117	86.81 231	90.39 184	98.65 98	75.09 231	99.98 9	93.32 141	97.53 124	99.26 99

EIA-MVS		95.11 81	95.27 73	94.64 165	96.34 165	86.51 223	99.59 40	96.62 198	92.51 80	94.08 129	98.64 99	86.05 117	98.24 179	95.07 107	98.50 103	99.18 105

TSAR-MVS + MP.		97.44 17	97.46 16	97.39 48	99.12 65	93.49 69	98.52 167	97.50 130	94.46 38	98.99 17	98.64 99	91.58 30	99.08 148	98.49 37	99.83 15	99.60 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
dcpmvs_2		95.67 69	96.18 44	94.12 185	98.82 81	84.22 277	97.37 252	95.45 286	90.70 118	95.77 101	98.63 101	90.47 43	98.68 164	99.20 20	99.22 70	99.45 81

TSAR-MVS + GP.		96.95 28	96.91 25	97.07 57	98.88 79	91.62 98	99.58 41	96.54 207	95.09 32	96.84 76	98.63 101	91.16 31	99.77 85	99.04 24	96.42 144	99.81 33

alignmvs		95.77 65	95.00 81	98.06 28	97.35 124	95.68 19	99.71 25	97.50 130	91.50 102	96.16 92	98.61 103	86.28 112	99.00 150	96.19 84	91.74 203	99.51 77

MVS		93.92 111	92.28 140	98.83 7	95.69 191	96.82 8	96.22 297	98.17 37	84.89 266	84.34 240	98.61 103	79.32 209	99.83 73	93.88 130	99.43 59	99.86 29

TAPA-MVS	87.50 9	90.35 192	89.05 202	94.25 180	98.48 91	85.17 264	98.42 180	96.58 204	82.44 309	87.24 212	98.53 105	82.77 168	98.84 155	59.09 375	97.88 114	98.72 148
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVSFormer		94.71 94	94.08 97	96.61 85	95.05 223	94.87 36	97.77 234	96.17 231	86.84 229	98.04 48	98.52 106	85.52 123	95.99 300	89.83 176	98.97 81	98.96 123

jason		95.40 76	94.86 82	97.03 59	92.91 280	94.23 54	99.70 26	96.30 220	93.56 64	96.73 82	98.52 106	81.46 193	97.91 194	96.08 87	98.47 105	98.96 123
jason: jason.
1112_ss		92.71 145	91.55 157	96.20 104	95.56 195	91.12 109	98.48 175	94.69 317	88.29 193	86.89 218	98.50 108	87.02 93	98.66 165	84.75 236	89.77 224	98.81 141

ab-mvs-re		8.21 368	10.94 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	98.50 108	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

test_fmvsmconf0.01_n		94.14 105	93.51 112	96.04 111	86.79 359	89.19 159	99.28 83	95.94 248	95.70 21	95.50 106	98.49 110	73.27 249	99.79 82	98.28 45	98.32 109	99.15 107

canonicalmvs		95.02 84	93.96 102	98.20 21	97.53 119	95.92 17	98.71 144	96.19 229	91.78 97	95.86 99	98.49 110	79.53 207	99.03 149	96.12 85	91.42 211	99.66 60

HPM-MVS		95.41 75	95.22 74	95.99 115	99.29 55	89.14 161	99.17 92	97.09 176	87.28 221	95.40 108	98.48 112	84.93 135	99.38 128	95.64 96	99.65 38	99.47 80
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CANet_DTU		94.31 103	93.35 115	97.20 55	97.03 141	94.71 44	98.62 156	95.54 281	95.61 25	97.21 66	98.47 113	71.88 262	99.84 69	88.38 195	97.46 126	97.04 206

HPM-MVS_fast		94.89 85	94.62 84	95.70 124	99.11 66	88.44 184	99.14 101	97.11 172	85.82 248	95.69 103	98.47 113	83.46 153	99.32 135	93.16 143	99.63 43	99.35 90

WTY-MVS		95.97 55	95.11 78	98.54 13	97.62 113	96.65 9	99.44 62	98.74 16	92.25 89	95.21 111	98.46 115	86.56 106	99.46 118	95.00 110	92.69 186	99.50 78

EC-MVSNet		95.09 82	95.17 75	94.84 156	95.42 200	88.17 186	99.48 53	95.92 252	91.47 103	97.34 63	98.36 116	82.77 168	97.41 232	97.24 62	98.58 100	98.94 128

DeepC-MVS	91.02 4	94.56 100	93.92 104	96.46 94	97.16 132	90.76 121	98.39 189	97.11 172	93.92 50	88.66 200	98.33 117	78.14 218	99.85 67	95.02 108	98.57 101	98.78 145
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LFMVS		92.23 159	90.84 172	96.42 97	98.24 94	91.08 113	98.24 200	96.22 226	83.39 289	94.74 119	98.31 118	61.12 330	98.85 154	94.45 122	92.82 183	99.32 93

ETV-MVS		96.00 52	96.00 52	96.00 114	96.56 154	91.05 114	99.63 36	96.61 199	93.26 68	97.39 61	98.30 119	86.62 103	98.13 182	98.07 49	97.57 121	98.82 140

ET-MVSNet_ETH3D		92.56 151	91.45 159	95.88 118	96.39 163	94.13 58	99.46 59	96.97 187	92.18 91	66.94 369	98.29 120	94.65 15	94.28 342	94.34 123	83.82 263	99.24 100

DELS-MVS		97.12 24	96.60 34	98.68 10	98.03 102	96.57 11	99.84 8	97.84 59	96.36 18	95.20 112	98.24 121	88.17 68	99.83 73	96.11 86	99.60 48	99.64 62
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
EPNet		96.82 31	96.68 33	97.25 53	98.65 86	93.10 75	99.48 53	98.76 15	96.54 13	97.84 54	98.22 122	87.49 80	99.66 94	95.35 101	97.78 118	99.00 119
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		94.06 106	93.05 124	97.06 58	99.08 69	92.26 91	98.97 123	97.01 184	82.58 304	92.57 148	98.22 122	80.68 199	99.30 136	89.34 186	99.02 78	99.63 64

PLC	91.07 3	94.23 104	94.01 98	94.87 154	99.17 63	87.49 203	99.25 85	96.55 206	88.43 186	91.26 169	98.21 124	85.92 118	99.86 63	89.77 180	97.57 121	97.24 199
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VDD-MVS		91.24 177	90.18 183	94.45 171	97.08 138	85.84 250	98.40 185	96.10 235	86.99 223	93.36 139	98.16 125	54.27 354	99.20 138	96.59 78	90.63 219	98.31 171

PMMVS		93.62 124	93.90 105	92.79 215	96.79 149	81.40 312	98.85 131	96.81 191	91.25 109	96.82 79	98.15 126	77.02 224	98.13 182	93.15 144	96.30 148	98.83 139

test_vis1_n_1920		93.08 141	93.42 114	92.04 232	96.31 166	79.36 329	99.83 9	96.06 239	96.72 9	98.53 32	98.10 127	58.57 337	99.91 45	97.86 53	98.79 94	96.85 211

XVG-OURS		90.83 184	90.49 180	91.86 234	95.23 206	81.25 316	95.79 312	95.92 252	88.96 168	90.02 189	98.03 128	71.60 266	99.35 133	91.06 162	87.78 230	94.98 237

XVG-OURS-SEG-HR		90.95 182	90.66 178	91.83 235	95.18 212	81.14 319	95.92 304	95.92 252	88.40 187	90.33 185	97.85 129	70.66 272	99.38 128	92.83 148	88.83 226	94.98 237

sss		94.85 87	93.94 103	97.58 40	96.43 160	94.09 59	98.93 125	99.16 8	89.50 155	95.27 110	97.85 129	81.50 191	99.65 98	92.79 150	94.02 174	98.99 120

diffmvs		94.59 98	94.19 92	95.81 120	95.54 196	90.69 123	98.70 146	95.68 273	91.61 99	95.96 94	97.81 131	80.11 201	98.06 187	96.52 80	95.76 157	98.67 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-RMVSNet		91.25 176	89.99 185	95.03 150	96.75 150	88.55 181	98.65 152	94.95 307	87.74 211	87.74 206	97.80 132	68.27 285	98.14 181	80.53 282	97.49 125	98.41 162

F-COLMAP		92.07 163	91.75 154	93.02 210	98.16 98	82.89 295	98.79 140	95.97 243	86.54 237	87.92 205	97.80 132	78.69 215	99.65 98	85.97 221	95.93 156	96.53 221

test_cas_vis1_n_1920		93.86 115	93.74 108	94.22 181	95.39 203	86.08 241	99.73 22	96.07 238	96.38 17	97.19 69	97.78 134	65.46 312	99.86 63	96.71 72	98.92 85	96.73 213

PVSNet_Blended		95.94 58	95.66 65	96.75 76	98.77 83	91.61 99	99.88 3	98.04 48	93.64 62	94.21 126	97.76 135	83.50 151	99.87 58	97.41 59	97.75 119	98.79 143

VDDNet		90.08 201	88.54 217	94.69 162	94.41 241	87.68 196	98.21 203	96.40 214	76.21 349	93.33 140	97.75 136	54.93 352	98.77 157	94.71 117	90.96 214	97.61 191

test_yl		95.27 78	94.60 85	97.28 51	98.53 89	92.98 79	99.05 112	98.70 19	86.76 232	94.65 121	97.74 137	87.78 75	99.44 119	95.57 97	92.61 187	99.44 82

DCV-MVSNet		95.27 78	94.60 85	97.28 51	98.53 89	92.98 79	99.05 112	98.70 19	86.76 232	94.65 121	97.74 137	87.78 75	99.44 119	95.57 97	92.61 187	99.44 82

1314		93.44 127	91.98 148	97.84 32	95.24 205	94.38 52	96.22 297	97.92 55	90.18 134	82.28 269	97.71 139	77.63 221	99.80 81	91.94 156	98.67 97	99.34 92

baseline		93.91 112	93.30 117	95.72 123	95.10 220	90.07 140	97.48 248	95.91 257	91.03 111	93.54 137	97.68 140	79.58 205	98.02 191	94.27 124	95.14 165	99.08 115

PVSNet	87.13 12	93.69 119	92.83 131	96.28 103	97.99 103	90.22 134	99.38 71	98.93 12	91.42 106	93.66 136	97.68 140	71.29 269	99.64 100	87.94 202	97.20 131	98.98 121

casdiffmvs		93.98 110	93.43 113	95.61 129	95.07 222	89.86 149	98.80 136	95.84 265	90.98 113	92.74 147	97.66 142	79.71 204	98.10 184	94.72 116	95.37 163	98.87 135
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet (Re-imp)		93.26 136	93.00 128	94.06 188	96.14 177	86.71 222	98.68 148	96.70 194	88.30 192	89.71 194	97.64 143	85.43 129	96.39 275	88.06 200	96.32 146	99.08 115

3Dnovator+	87.72 8	93.43 128	91.84 151	98.17 22	95.73 190	95.08 32	98.92 127	97.04 179	91.42 106	81.48 286	97.60 144	74.60 234	99.79 82	90.84 166	98.97 81	99.64 62

thisisatest0515		94.75 90	94.19 92	96.43 96	96.13 180	92.64 88	99.47 55	97.60 106	87.55 217	93.17 141	97.59 145	94.71 13	98.42 170	88.28 196	93.20 179	98.24 173

3Dnovator	87.35 11	93.17 139	91.77 153	97.37 49	95.41 201	93.07 76	98.82 134	97.85 58	91.53 101	82.56 261	97.58 146	71.97 261	99.82 76	91.01 163	99.23 69	99.22 103

test_fmvs1		92.35 154	92.94 129	90.57 266	97.19 130	75.43 350	99.55 44	94.97 306	95.20 31	96.82 79	97.57 147	59.59 335	99.84 69	97.30 61	98.29 110	96.46 223

CHOSEN 280x420		96.80 32	96.85 27	96.66 84	97.85 107	94.42 51	94.76 321	98.36 29	92.50 81	95.62 105	97.52 148	97.92 1	97.38 233	98.31 44	98.80 91	98.20 176

IS-MVSNet		93.00 142	92.51 137	94.49 168	96.14 177	87.36 208	98.31 196	95.70 271	88.58 179	90.17 186	97.50 149	83.02 164	97.22 236	87.06 207	96.07 154	98.90 132

OpenMVS	85.28 14	90.75 186	88.84 206	96.48 93	93.58 267	93.51 68	98.80 136	97.41 145	82.59 303	78.62 315	97.49 150	68.00 289	99.82 76	84.52 241	98.55 102	96.11 229

test_fmvs1_n		91.07 179	91.41 160	90.06 280	94.10 248	74.31 354	99.18 89	94.84 310	94.81 33	96.37 89	97.46 151	50.86 365	99.82 76	97.14 64	97.90 113	96.04 230

PCF-MVS	89.78 5	91.26 174	89.63 189	96.16 108	95.44 199	91.58 101	95.29 317	96.10 235	85.07 261	82.75 255	97.45 152	78.28 217	99.78 84	80.60 281	95.65 160	97.12 201
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VNet		95.08 83	94.26 89	97.55 43	98.07 100	93.88 61	98.68 148	98.73 18	90.33 131	97.16 70	97.43 153	79.19 210	99.53 109	96.91 71	91.85 201	99.24 100

QAPM		91.41 172	89.49 192	97.17 56	95.66 193	93.42 70	98.60 160	97.51 127	80.92 327	81.39 287	97.41 154	72.89 254	99.87 58	82.33 266	98.68 96	98.21 175

casdiffmvs_mvg		94.00 108	93.33 116	96.03 112	95.22 207	90.90 119	99.09 107	95.99 241	90.58 123	91.55 163	97.37 155	79.91 203	98.06 187	95.01 109	95.22 164	99.13 110
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
thisisatest0530		94.00 108	93.52 111	95.43 133	95.76 189	90.02 145	98.99 120	97.60 106	86.58 235	91.74 157	97.36 156	94.78 12	98.34 172	86.37 218	92.48 190	97.94 182

test2506		94.80 88	94.21 91	96.58 88	96.41 161	92.18 93	98.01 220	98.96 11	90.82 116	93.46 138	97.28 157	85.92 118	98.45 169	89.82 178	97.19 132	99.12 111

ECVR-MVS		92.29 156	91.33 161	95.15 144	96.41 161	87.84 193	98.10 213	94.84 310	90.82 116	91.42 167	97.28 157	65.61 309	98.49 168	90.33 172	97.19 132	99.12 111

test1111		92.12 161	91.19 164	94.94 152	96.15 175	87.36 208	98.12 210	94.84 310	90.85 115	90.97 172	97.26 159	65.60 310	98.37 171	89.74 181	97.14 135	99.07 117

DP-MVS		88.75 227	86.56 246	95.34 136	98.92 77	87.45 205	97.64 244	93.52 341	70.55 366	81.49 285	97.25 160	74.43 237	99.88 54	71.14 340	94.09 173	98.67 152

TR-MVS		90.77 185	89.44 193	94.76 158	96.31 166	88.02 191	97.92 224	95.96 245	85.52 253	88.22 204	97.23 161	66.80 299	98.09 185	84.58 239	92.38 191	98.17 177

Vis-MVSNet		92.64 147	91.85 150	95.03 150	95.12 216	88.23 185	98.48 175	96.81 191	91.61 99	92.16 154	97.22 162	71.58 267	98.00 193	85.85 226	97.81 115	98.88 133
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
gm-plane-assit					94.69 235	88.14 187			88.22 195		97.20 163		98.29 175	90.79 168

tttt0517		93.30 133	93.01 127	94.17 183	95.57 194	86.47 225	98.51 170	97.60 106	85.99 246	90.55 179	97.19 164	94.80 11	98.31 173	85.06 232	91.86 200	97.74 184

EPP-MVSNet		93.75 118	93.67 109	94.01 191	95.86 185	85.70 252	98.67 150	97.66 91	84.46 271	91.36 168	97.18 165	91.16 31	97.79 203	92.93 146	93.75 176	98.53 157

Effi-MVS+		93.87 114	93.15 122	96.02 113	95.79 187	90.76 121	96.70 282	95.78 266	86.98 226	95.71 102	97.17 166	79.58 205	98.01 192	94.57 121	96.09 152	99.31 94

CLD-MVS		91.06 180	90.71 176	92.10 230	94.05 252	86.10 240	99.55 44	96.29 223	94.16 45	84.70 235	97.17 166	69.62 277	97.82 201	94.74 115	86.08 242	92.39 254
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EI-MVSNet		89.87 205	89.38 196	91.36 247	94.32 244	85.87 248	97.61 245	96.59 201	85.10 259	85.51 229	97.10 168	81.30 196	96.56 263	83.85 253	83.03 270	91.64 279

CVMVSNet		90.30 194	90.91 170	88.46 313	94.32 244	73.58 358	97.61 245	97.59 110	90.16 137	88.43 203	97.10 168	76.83 225	92.86 352	82.64 263	93.54 178	98.93 129

UA-Net		93.30 133	92.62 135	95.34 136	96.27 168	88.53 183	95.88 307	96.97 187	90.90 114	95.37 109	97.07 170	82.38 181	99.10 147	83.91 251	94.86 168	98.38 165

RPSCF		85.33 283	85.55 261	84.67 340	94.63 238	62.28 379	93.73 331	93.76 335	74.38 357	85.23 232	97.06 171	64.09 316	98.31 173	80.98 275	86.08 242	93.41 245

EPNet_dtu		92.28 157	92.15 144	92.70 219	97.29 127	84.84 269	98.64 154	97.82 62	92.91 75	93.02 144	97.02 172	85.48 128	95.70 314	72.25 337	94.89 167	97.55 192
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-w/o		92.32 155	91.79 152	93.91 194	96.85 144	86.18 237	99.11 106	95.74 269	88.13 197	84.81 233	97.00 173	77.26 223	97.91 194	89.16 191	98.03 112	97.64 187

thres200		93.69 119	92.59 136	96.97 66	97.76 108	94.74 43	99.35 76	99.36 2	89.23 160	91.21 171	96.97 174	83.42 154	98.77 157	85.08 231	90.96 214	97.39 195

test_vis1_n		90.40 191	90.27 182	90.79 261	91.55 301	76.48 346	99.12 105	94.44 322	94.31 41	97.34 63	96.95 175	43.60 376	99.42 123	97.57 57	97.60 120	96.47 222

baseline2		94.04 107	93.80 107	94.74 160	93.07 279	90.25 131	98.12 210	98.16 39	89.86 142	86.53 222	96.95 175	95.56 6	98.05 189	91.44 159	94.53 169	95.93 231

MSDG		88.29 235	86.37 248	94.04 190	96.90 143	86.15 239	96.52 285	94.36 327	77.89 344	79.22 310	96.95 175	69.72 275	99.59 104	73.20 333	92.58 189	96.37 226

tfpn200view9		93.43 128	92.27 141	96.90 69	97.68 111	94.84 38	99.18 89	99.36 2	88.45 183	90.79 174	96.90 178	83.31 155	98.75 159	84.11 247	90.69 216	97.12 201

thres400		93.39 130	92.27 141	96.73 78	97.68 111	94.84 38	99.18 89	99.36 2	88.45 183	90.79 174	96.90 178	83.31 155	98.75 159	84.11 247	90.69 216	96.61 216

Anonymous202405211		88.84 221	87.03 239	94.27 178	98.14 99	84.18 278	98.44 178	95.58 279	76.79 348	89.34 196	96.88 180	53.42 357	99.54 108	87.53 206	87.12 233	99.09 114

baseline1		92.61 149	91.28 162	96.58 88	97.05 140	94.63 46	97.72 238	96.20 227	89.82 143	88.56 201	96.85 181	86.85 97	97.82 201	88.42 194	80.10 286	97.30 197

Syy-MVS		84.10 301	84.53 280	82.83 348	95.14 214	65.71 376	97.68 241	96.66 196	86.52 238	82.63 258	96.84 182	68.15 286	89.89 372	45.62 386	91.54 208	92.87 246

myMVS_eth3d		88.68 230	89.07 201	87.50 320	95.14 214	79.74 327	97.68 241	96.66 196	86.52 238	82.63 258	96.84 182	85.22 133	89.89 372	69.43 346	91.54 208	92.87 246

GeoE		90.60 190	89.56 190	93.72 201	95.10 220	85.43 257	99.41 68	94.94 308	83.96 279	87.21 213	96.83 184	74.37 238	97.05 243	80.50 283	93.73 177	98.67 152

thres100view900		93.34 132	92.15 144	96.90 69	97.62 113	94.84 38	99.06 111	99.36 2	87.96 203	90.47 182	96.78 185	83.29 157	98.75 159	84.11 247	90.69 216	97.12 201

thres600view7		93.18 138	92.00 147	96.75 76	97.62 113	94.92 33	99.07 109	99.36 2	87.96 203	90.47 182	96.78 185	83.29 157	98.71 163	82.93 261	90.47 220	96.61 216

h-mvs33		92.47 153	91.95 149	94.05 189	97.13 135	85.01 267	98.36 191	98.08 44	93.85 55	96.27 90	96.73 187	83.19 160	99.43 122	95.81 90	68.09 354	97.70 186

BH-untuned		91.46 171	90.84 172	93.33 205	96.51 157	84.83 270	98.84 133	95.50 283	86.44 242	83.50 245	96.70 188	75.49 230	97.77 205	86.78 215	97.81 115	97.40 194

testing3		87.75 243	88.22 221	86.36 328	94.66 237	77.41 344	99.52 50	97.95 54	86.05 245	81.12 288	96.69 189	86.18 115	89.31 376	61.65 370	90.12 222	92.35 259

NP-MVS					93.94 256	86.22 235					96.67 190

HQP-MVS		91.50 169	91.23 163	92.29 224	93.95 253	86.39 228	99.16 93	96.37 216	93.92 50	87.57 207	96.67 190	73.34 246	97.77 205	93.82 133	86.29 237	92.72 248

HQP_MVS		91.26 174	90.95 169	92.16 228	93.84 260	86.07 243	99.02 116	96.30 220	93.38 66	86.99 214	96.52 192	72.92 252	97.75 211	93.46 138	86.17 240	92.67 250

plane_prior4											96.52 192

CDS-MVSNet		93.47 126	93.04 125	94.76 158	94.75 234	89.45 157	98.82 134	97.03 181	87.91 205	90.97 172	96.48 194	89.06 57	96.36 277	89.50 182	92.81 185	98.49 159
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OPM-MVS		89.76 206	89.15 200	91.57 244	90.53 315	85.58 255	98.11 212	95.93 251	92.88 76	86.05 223	96.47 195	67.06 298	97.87 198	89.29 189	86.08 242	91.26 300
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
GG-mvs-BLEND				96.98 65	96.53 155	94.81 41	87.20 369	97.74 74		93.91 132	96.40 196	96.56 2	96.94 247	95.08 106	98.95 84	99.20 104

CHOSEN 1792x2688		94.35 102	93.82 106	95.95 117	97.40 121	88.74 178	98.41 182	98.27 31	92.18 91	91.43 165	96.40 196	78.88 211	99.81 79	93.59 136	97.81 115	99.30 95

tmp_tt		53.66 358	52.86 360	56.05 376	32.75 403	41.97 400	73.42 390	76.12 397	21.91 397	39.68 393	96.39 198	42.59 377	65.10 396	78.00 298	14.92 397	61.08 389

PVSNet_Blended_VisFu		94.67 95	94.11 95	96.34 102	97.14 134	91.10 111	99.32 79	97.43 143	92.10 94	91.53 164	96.38 199	83.29 157	99.68 92	93.42 140	96.37 145	98.25 172

dmvs_re		88.69 229	88.06 224	90.59 265	93.83 262	78.68 335	95.75 313	96.18 230	87.99 202	84.48 239	96.32 200	67.52 293	96.94 247	84.98 234	85.49 246	96.14 228

test0.0.03 1		88.96 216	88.61 212	90.03 284	91.09 308	84.43 274	98.97 123	97.02 183	90.21 132	80.29 296	96.31 201	84.89 136	91.93 366	72.98 334	85.70 245	93.73 241

hse-mvs2		91.67 168	91.51 158	92.15 229	96.22 170	82.61 301	97.74 237	97.53 121	93.85 55	96.27 90	96.15 202	83.19 160	97.44 230	95.81 90	66.86 361	96.40 225

AUN-MVS		90.17 198	89.50 191	92.19 227	96.21 171	82.67 299	97.76 236	97.53 121	88.05 199	91.67 158	96.15 202	83.10 162	97.47 227	88.11 199	66.91 360	96.43 224

LPG-MVS_test		88.86 220	88.47 218	90.06 280	93.35 274	80.95 321	98.22 201	95.94 248	87.73 212	83.17 251	96.11 204	66.28 304	97.77 205	90.19 174	85.19 247	91.46 290

LGP-MVS_train				90.06 280	93.35 274	80.95 321		95.94 248	87.73 212	83.17 251	96.11 204	66.28 304	97.77 205	90.19 174	85.19 247	91.46 290

TAMVS		92.62 148	92.09 146	94.20 182	94.10 248	87.68 196	98.41 182	96.97 187	87.53 218	89.74 192	96.04 206	84.77 140	96.49 270	88.97 192	92.31 193	98.42 161

Anonymous20240529		87.66 247	85.58 260	93.92 193	97.59 116	85.01 267	98.13 208	97.13 170	66.69 380	88.47 202	96.01 207	55.09 351	99.51 110	87.00 209	84.12 258	97.23 200

dmvs_testset		77.17 335	78.99 322	71.71 364	87.25 355	38.55 401	91.44 354	81.76 392	85.77 249	69.49 358	95.94 208	69.71 276	84.37 384	52.71 383	76.82 304	92.21 264

COLMAP_ROB	82.69 18	84.54 293	82.82 294	89.70 292	96.72 151	78.85 332	95.89 305	92.83 349	71.55 363	77.54 324	95.89 209	59.40 336	99.14 145	67.26 354	88.26 227	91.11 304
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tt0805		86.50 265	84.79 274	91.63 243	91.97 292	81.49 310	96.49 286	97.38 148	82.24 311	82.44 263	95.82 210	51.22 362	98.25 178	84.55 240	80.96 282	95.13 236

PatchMatch-RL		91.47 170	90.54 179	94.26 179	98.20 95	86.36 230	96.94 270	97.14 168	87.75 210	88.98 198	95.75 211	71.80 264	99.40 127	80.92 277	97.39 128	97.02 207

Fast-Effi-MVS+		91.72 167	90.79 175	94.49 168	95.89 184	87.40 207	99.54 49	95.70 271	85.01 264	89.28 197	95.68 212	77.75 220	97.57 225	83.22 256	95.06 166	98.51 158

ACMP	87.39 10	88.71 228	88.24 220	90.12 279	93.91 258	81.06 320	98.50 171	95.67 274	89.43 156	80.37 295	95.55 213	65.67 307	97.83 200	90.55 170	84.51 251	91.47 289
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
AllTest		84.97 287	83.12 292	90.52 269	96.82 145	78.84 333	95.89 305	92.17 357	77.96 342	75.94 329	95.50 214	55.48 347	99.18 139	71.15 338	87.14 231	93.55 243

TestCases				90.52 269	96.82 145	78.84 333		92.17 357	77.96 342	75.94 329	95.50 214	55.48 347	99.18 139	71.15 338	87.14 231	93.55 243

ITE_SJBPF				87.93 315	92.26 287	76.44 347		93.47 342	87.67 215	79.95 301	95.49 216	56.50 344	97.38 233	75.24 316	82.33 276	89.98 333

iter_conf_final		93.22 137	93.04 125	93.76 198	97.03 141	92.22 92	99.05 112	93.31 343	92.11 93	86.93 216	95.42 217	95.01 10	96.59 259	93.98 127	84.48 253	92.46 253

iter_conf05		93.48 125	93.18 121	94.39 175	97.15 133	94.17 57	99.30 80	92.97 346	92.38 88	86.70 221	95.42 217	95.67 5	96.59 259	94.67 118	84.32 256	92.39 254

testgi		82.29 309	81.00 312	86.17 330	87.24 356	74.84 353	97.39 249	91.62 365	88.63 176	75.85 332	95.42 217	46.07 373	91.55 367	66.87 357	79.94 287	92.12 269

Fast-Effi-MVS+-dtu		88.84 221	88.59 214	89.58 295	93.44 272	78.18 339	98.65 152	94.62 319	88.46 182	84.12 242	95.37 220	68.91 279	96.52 266	82.06 269	91.70 205	94.06 240

SDMVSNet		91.09 178	89.91 186	94.65 163	96.80 147	90.54 127	97.78 232	97.81 65	88.34 190	85.73 225	95.26 221	66.44 303	98.26 177	94.25 125	86.75 234	95.14 234

sd_testset		89.23 212	88.05 225	92.74 218	96.80 147	85.33 260	95.85 310	97.03 181	88.34 190	85.73 225	95.26 221	61.12 330	97.76 210	85.61 227	86.75 234	95.14 234

ACMM	86.95 13	88.77 226	88.22 221	90.43 271	93.61 266	81.34 314	98.50 171	95.92 252	87.88 206	83.85 244	95.20 223	67.20 296	97.89 196	86.90 213	84.90 249	92.06 272
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HyFIR lowres test		93.68 121	93.29 118	94.87 154	97.57 118	88.04 190	98.18 205	98.47 25	87.57 216	91.24 170	95.05 224	85.49 126	97.46 228	93.22 142	92.82 183	99.10 113

mvsmamba		89.99 203	89.42 194	91.69 242	90.64 314	86.34 231	98.40 185	92.27 355	91.01 112	84.80 234	94.93 225	76.12 226	96.51 267	92.81 149	83.84 260	92.21 264

VPNet		88.30 234	86.57 245	93.49 202	91.95 294	91.35 103	98.18 205	97.20 164	88.61 177	84.52 238	94.89 226	62.21 325	96.76 255	89.34 186	72.26 341	92.36 256

TESTMET0.1,1		93.82 116	93.26 119	95.49 131	95.21 208	90.25 131	99.15 98	97.54 120	89.18 162	91.79 156	94.87 227	89.13 56	97.63 218	86.21 219	96.29 149	98.60 155

RRT_MVS		88.91 218	88.56 215	89.93 285	90.31 318	81.61 309	98.08 216	96.38 215	89.30 158	82.41 266	94.84 228	73.15 250	96.04 299	90.38 171	82.23 277	92.15 267

FIs		90.70 187	89.87 187	93.18 207	92.29 286	91.12 109	98.17 207	98.25 32	89.11 164	83.44 246	94.82 229	82.26 182	96.17 293	87.76 203	82.76 272	92.25 260

HY-MVS	88.56 7	95.29 77	94.23 90	98.48 14	97.72 109	96.41 13	94.03 329	98.74 16	92.42 84	95.65 104	94.76 230	86.52 107	99.49 112	95.29 103	92.97 182	99.53 74

FC-MVSNet-test		90.22 196	89.40 195	92.67 221	91.78 298	89.86 149	97.89 225	98.22 35	88.81 174	82.96 254	94.66 231	81.90 188	95.96 302	85.89 225	82.52 275	92.20 266

nrg030		90.23 195	88.87 205	94.32 177	91.53 302	93.54 67	98.79 140	95.89 260	88.12 198	84.55 237	94.61 232	78.80 214	96.88 249	92.35 154	75.21 309	92.53 252

bld_raw_dy_0_64		87.82 239	86.71 244	91.15 250	89.54 330	85.61 253	97.37 252	89.16 379	89.26 159	83.42 247	94.50 233	65.79 306	96.18 291	88.00 201	83.37 267	91.67 278

cascas		90.93 183	89.33 197	95.76 122	95.69 191	93.03 78	98.99 120	96.59 201	80.49 329	86.79 220	94.45 234	65.23 313	98.60 167	93.52 137	92.18 196	95.66 233

UniMVSNet_ETH3D		85.65 281	83.79 289	91.21 248	90.41 317	80.75 323	95.36 316	95.78 266	78.76 338	81.83 283	94.33 235	49.86 367	96.66 256	84.30 242	83.52 266	96.22 227

XXY-MVS		87.75 243	86.02 253	92.95 213	90.46 316	89.70 152	97.71 240	95.90 258	84.02 276	80.95 289	94.05 236	67.51 294	97.10 241	85.16 230	78.41 292	92.04 273

test-LLR		93.11 140	92.68 133	94.40 172	94.94 228	87.27 212	99.15 98	97.25 154	90.21 132	91.57 160	94.04 237	84.89 136	97.58 222	85.94 223	96.13 150	98.36 168

test-mter		93.27 135	92.89 130	94.40 172	94.94 228	87.27 212	99.15 98	97.25 154	88.95 169	91.57 160	94.04 237	88.03 73	97.58 222	85.94 223	96.13 150	98.36 168

MVS_Test		93.67 122	92.67 134	96.69 82	96.72 151	92.66 85	97.22 261	96.03 240	87.69 214	95.12 114	94.03 239	81.55 190	98.28 176	89.17 190	96.46 142	99.14 108

ACMH+	83.78 15	84.21 297	82.56 302	89.15 304	93.73 265	79.16 330	96.43 287	94.28 328	81.09 324	74.00 340	94.03 239	54.58 353	97.67 214	76.10 311	78.81 291	90.63 319

MVSTER		92.71 145	92.32 139	93.86 195	97.29 127	92.95 81	99.01 118	96.59 201	90.09 138	85.51 229	94.00 241	94.61 16	96.56 263	90.77 169	83.03 270	92.08 271

UniMVSNet_NR-MVSNet		89.60 208	88.55 216	92.75 217	92.17 289	90.07 140	98.74 143	98.15 40	88.37 188	83.21 249	93.98 242	82.86 166	95.93 304	86.95 210	72.47 338	92.25 260

mvs_anonymous		92.50 152	91.65 155	95.06 147	96.60 153	89.64 153	97.06 266	96.44 213	86.64 234	84.14 241	93.93 243	82.49 175	96.17 293	91.47 158	96.08 153	99.35 90

TranMVSNet+NR-MVSNet		87.75 243	86.31 249	92.07 231	90.81 311	88.56 180	98.33 193	97.18 165	87.76 209	81.87 280	93.90 244	72.45 256	95.43 320	83.13 259	71.30 348	92.23 262

ab-mvs		91.05 181	89.17 199	96.69 82	95.96 183	91.72 97	92.62 343	97.23 158	85.61 252	89.74 192	93.89 245	68.55 282	99.42 123	91.09 161	87.84 229	98.92 131

WR-MVS		88.54 232	87.22 237	92.52 222	91.93 296	89.50 156	98.56 165	97.84 59	86.99 223	81.87 280	93.81 246	74.25 241	95.92 306	85.29 229	74.43 318	92.12 269

PS-MVSNAJss		89.54 210	89.05 202	91.00 254	88.77 339	84.36 275	97.39 249	95.97 243	88.47 180	81.88 279	93.80 247	82.48 176	96.50 268	89.34 186	83.34 269	92.15 267

jajsoiax		87.35 250	86.51 247	89.87 286	87.75 353	81.74 307	97.03 267	95.98 242	88.47 180	80.15 298	93.80 247	61.47 327	96.36 277	89.44 184	84.47 254	91.50 288

DU-MVS		88.83 223	87.51 230	92.79 215	91.46 303	90.07 140	98.71 144	97.62 103	88.87 173	83.21 249	93.68 249	74.63 232	95.93 304	86.95 210	72.47 338	92.36 256

NR-MVSNet		87.74 246	86.00 254	92.96 212	91.46 303	90.68 124	96.65 283	97.42 144	88.02 201	73.42 343	93.68 249	77.31 222	95.83 310	84.26 243	71.82 345	92.36 256

IB-MVS	89.43 6	92.12 161	90.83 174	95.98 116	95.40 202	90.78 120	99.81 11	98.06 45	91.23 110	85.63 228	93.66 251	90.63 41	98.78 156	91.22 160	71.85 344	98.36 168
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
mvs_tets		87.09 253	86.22 250	89.71 291	87.87 349	81.39 313	96.73 281	95.90 258	88.19 196	79.99 300	93.61 252	59.96 334	96.31 285	89.40 185	84.34 255	91.43 292

UGNet		91.91 165	90.85 171	95.10 145	97.06 139	88.69 179	98.01 220	98.24 34	92.41 85	92.39 151	93.61 252	60.52 332	99.68 92	88.14 198	97.25 130	96.92 210
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
ACMH	83.09 17	84.60 291	82.61 301	90.57 266	93.18 277	82.94 292	96.27 292	94.92 309	81.01 325	72.61 352	93.61 252	56.54 343	97.79 203	74.31 323	81.07 281	90.99 306
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		86.75 258	85.92 255	89.22 302	91.97 292	82.47 302	96.91 271	96.14 233	83.74 282	77.73 322	93.53 255	58.19 339	97.37 235	76.75 307	98.35 106	87.84 353

Test_1112_low_res		92.27 158	90.97 168	96.18 105	95.53 197	91.10 111	98.47 177	94.66 318	88.28 194	86.83 219	93.50 256	87.00 94	98.65 166	84.69 237	89.74 225	98.80 142

test_fmvs2		85.10 285	85.45 263	84.02 343	89.85 324	65.63 377	98.49 173	92.59 351	90.45 127	85.43 231	93.32 257	43.94 374	96.59 259	90.81 167	84.19 257	89.85 335

CMPMVS	58.40 21	80.48 318	80.11 317	81.59 354	85.10 365	59.56 382	94.14 328	95.95 247	68.54 374	60.71 378	93.31 258	55.35 350	97.87 198	83.06 260	84.85 250	87.33 358
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		84.74 288	82.93 293	90.16 278	91.73 299	83.54 286	95.00 319	93.30 344	88.77 175	73.19 345	93.30 259	53.62 356	97.65 217	75.88 313	81.54 280	89.30 342

OurMVSNet-221017-0		84.13 300	83.59 290	85.77 333	87.81 350	70.24 369	94.89 320	93.65 339	86.08 244	76.53 325	93.28 260	61.41 328	96.14 295	80.95 276	77.69 300	90.93 307

PVSNet_0	83.28 16	87.31 251	85.16 266	93.74 200	94.78 233	84.59 272	98.91 128	98.69 21	89.81 144	78.59 317	93.23 261	61.95 326	99.34 134	94.75 114	55.72 381	97.30 197

EU-MVSNet		84.19 298	84.42 283	83.52 346	88.64 342	67.37 375	96.04 302	95.76 268	85.29 256	78.44 318	93.18 262	70.67 271	91.48 368	75.79 314	75.98 305	91.70 277

pmmvs4		87.58 249	86.17 252	91.80 237	89.58 328	88.92 173	97.25 258	95.28 295	82.54 305	80.49 294	93.17 263	75.62 229	96.05 298	82.75 262	78.90 290	90.42 322

GA-MVS		90.10 200	88.69 210	94.33 176	92.44 284	87.97 192	99.08 108	96.26 224	89.65 147	86.92 217	93.11 264	68.09 287	96.96 245	82.54 265	90.15 221	98.05 178

CP-MVSNet		86.54 263	85.45 263	89.79 290	91.02 310	82.78 298	97.38 251	97.56 116	85.37 255	79.53 307	93.03 265	71.86 263	95.25 325	79.92 284	73.43 332	91.34 296

LF4IMVS		81.94 312	81.17 311	84.25 342	87.23 357	68.87 374	93.35 335	91.93 362	83.35 290	75.40 334	93.00 266	49.25 370	96.65 257	78.88 292	78.11 294	87.22 360

XVG-ACMP-BASELINE		85.86 274	84.95 270	88.57 311	89.90 322	77.12 345	94.30 325	95.60 278	87.40 220	82.12 272	92.99 267	53.42 357	97.66 215	85.02 233	83.83 261	90.92 308

PS-CasMVS		85.81 276	84.58 279	89.49 299	90.77 312	82.11 304	97.20 262	97.36 150	84.83 267	79.12 312	92.84 268	67.42 295	95.16 327	78.39 297	73.25 333	91.21 301

LTVRE_ROB	81.71 19	84.59 292	82.72 299	90.18 277	92.89 281	83.18 290	93.15 336	94.74 314	78.99 335	75.14 336	92.69 269	65.64 308	97.63 218	69.46 345	81.82 279	89.74 336
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
PEN-MVS		85.21 284	83.93 288	89.07 306	89.89 323	81.31 315	97.09 265	97.24 157	84.45 272	78.66 314	92.68 270	68.44 284	94.87 332	75.98 312	70.92 349	91.04 305

PVSNet_BlendedMVS		93.36 131	93.20 120	93.84 196	98.77 83	91.61 99	99.47 55	98.04 48	91.44 104	94.21 126	92.63 271	83.50 151	99.87 58	97.41 59	83.37 267	90.05 331

DTE-MVSNet		84.14 299	82.80 295	88.14 314	88.95 338	79.87 326	96.81 275	96.24 225	83.50 287	77.60 323	92.52 272	67.89 291	94.24 343	72.64 336	69.05 352	90.32 324

miper_enhance_ethall		90.33 193	89.70 188	92.22 225	97.12 136	88.93 172	98.35 192	95.96 245	88.60 178	83.14 253	92.33 273	87.38 82	96.18 291	86.49 217	77.89 295	91.55 287

FA-MVS(test-final)		92.22 160	91.08 166	95.64 127	96.05 181	88.98 167	91.60 352	97.25 154	86.99 223	91.84 155	92.12 274	83.03 163	99.00 150	86.91 212	93.91 175	98.93 129

SixPastTwentyTwo		82.63 308	81.58 306	85.79 332	88.12 347	71.01 367	95.17 318	92.54 352	84.33 273	72.93 350	92.08 275	60.41 333	95.61 317	74.47 322	74.15 323	90.75 315

UniMVSNet (Re)		89.50 211	88.32 219	93.03 209	92.21 288	90.96 117	98.90 129	98.39 27	89.13 163	83.22 248	92.03 276	81.69 189	96.34 283	86.79 214	72.53 337	91.81 276

pmmvs5		85.87 273	84.40 284	90.30 276	88.53 343	84.23 276	98.60 160	93.71 337	81.53 319	80.29 296	92.02 277	64.51 315	95.52 318	82.04 270	78.34 293	91.15 302

pm-mvs1		84.68 290	82.78 297	90.40 272	89.58 328	85.18 263	97.31 254	94.73 315	81.93 316	76.05 328	92.01 278	65.48 311	96.11 296	78.75 294	69.14 351	89.91 334

VPA-MVSNet		89.10 214	87.66 229	93.45 203	92.56 282	91.02 115	97.97 223	98.32 30	86.92 228	86.03 224	92.01 278	68.84 281	97.10 241	90.92 164	75.34 308	92.23 262

FE-MVS		91.38 173	90.16 184	95.05 149	96.46 159	87.53 202	89.69 366	97.84 59	82.97 296	92.18 153	92.00 280	84.07 146	98.93 153	80.71 279	95.52 161	98.68 151

MVP-Stereo		86.61 262	85.83 256	88.93 309	88.70 341	83.85 283	96.07 301	94.41 326	82.15 313	75.64 333	91.96 281	67.65 292	96.45 273	77.20 303	98.72 95	86.51 364
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_djsdf		88.26 236	87.73 227	89.84 288	88.05 348	82.21 303	97.77 234	96.17 231	86.84 229	82.41 266	91.95 282	72.07 260	95.99 300	89.83 176	84.50 252	91.32 297

cl22		89.57 209	88.79 208	91.91 233	97.94 104	87.62 199	97.98 222	96.51 208	85.03 262	82.37 268	91.79 283	83.65 149	96.50 268	85.96 222	77.89 295	91.61 284

v2v482		87.27 252	85.76 257	91.78 241	89.59 327	87.58 200	98.56 165	95.54 281	84.53 270	82.51 262	91.78 284	73.11 251	96.47 271	82.07 268	74.14 324	91.30 298

TinyColmap		80.42 319	77.94 324	87.85 316	92.09 290	78.58 336	93.74 330	89.94 374	74.99 353	69.77 357	91.78 284	46.09 372	97.58 222	65.17 362	77.89 295	87.38 356

TransMVSNet (Re)		81.97 311	79.61 320	89.08 305	89.70 326	84.01 280	97.26 257	91.85 363	78.84 336	73.07 349	91.62 286	67.17 297	95.21 326	67.50 353	59.46 375	88.02 352

FMVSNet3		88.81 225	87.08 238	93.99 192	96.52 156	94.59 47	98.08 216	96.20 227	85.85 247	82.12 272	91.60 287	74.05 242	95.40 322	79.04 289	80.24 283	91.99 274

eth_miper_zixun_eth		87.76 242	87.00 240	90.06 280	94.67 236	82.65 300	97.02 269	95.37 292	84.19 274	81.86 282	91.58 288	81.47 192	95.90 308	83.24 255	73.61 327	91.61 284

miper_ehance_all_eth		88.94 217	88.12 223	91.40 245	95.32 204	86.93 218	97.85 229	95.55 280	84.19 274	81.97 277	91.50 289	84.16 144	95.91 307	84.69 237	77.89 295	91.36 295

Effi-MVS+-dtu		89.97 204	90.68 177	87.81 317	95.15 213	71.98 364	97.87 228	95.40 290	91.92 95	87.57 207	91.44 290	74.27 240	96.84 250	89.45 183	93.10 181	94.60 239

c3_l		88.19 237	87.23 236	91.06 252	94.97 226	86.17 238	97.72 238	95.38 291	83.43 288	81.68 284	91.37 291	82.81 167	95.72 313	84.04 250	73.70 326	91.29 299

Baseline_NR-MVSNet		85.83 275	84.82 273	88.87 310	88.73 340	83.34 288	98.63 155	91.66 364	80.41 332	82.44 263	91.35 292	74.63 232	95.42 321	84.13 246	71.39 347	87.84 353

DIV-MVS_self_test		87.82 239	86.81 242	90.87 259	94.87 231	85.39 259	97.81 230	95.22 304	82.92 300	80.76 291	91.31 293	81.99 185	95.81 311	81.36 273	75.04 311	91.42 293

cl____		87.82 239	86.79 243	90.89 258	94.88 230	85.43 257	97.81 230	95.24 299	82.91 301	80.71 292	91.22 294	81.97 187	95.84 309	81.34 274	75.06 310	91.40 294

IterMVS-LS		88.34 233	87.44 231	91.04 253	94.10 248	85.85 249	98.10 213	95.48 284	85.12 258	82.03 276	91.21 295	81.35 195	95.63 316	83.86 252	75.73 307	91.63 280
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet2		86.90 255	84.79 274	93.24 206	95.11 217	92.54 89	97.67 243	95.86 264	82.94 297	80.55 293	91.17 296	62.89 322	95.29 324	77.23 301	79.71 289	91.90 275

TDRefinement		78.01 331	75.31 335	86.10 331	70.06 390	73.84 356	93.59 334	91.58 366	74.51 356	73.08 348	91.04 297	49.63 369	97.12 238	74.88 319	59.47 374	87.33 358

ppachtmachnet_test		83.63 304	81.57 307	89.80 289	89.01 336	85.09 266	97.13 264	94.50 321	78.84 336	76.14 327	91.00 298	69.78 274	94.61 339	63.40 364	74.36 319	89.71 338

tfpnnormal		83.65 303	81.35 309	90.56 268	91.37 305	88.06 189	97.29 255	97.87 57	78.51 339	76.20 326	90.91 299	64.78 314	96.47 271	61.71 369	73.50 329	87.13 361

WR-MVS_H		86.53 264	85.49 262	89.66 294	91.04 309	83.31 289	97.53 247	98.20 36	84.95 265	79.64 304	90.90 300	78.01 219	95.33 323	76.29 310	72.81 334	90.35 323

Anonymous20231211		84.72 289	82.65 300	90.91 256	97.71 110	84.55 273	97.28 256	96.67 195	66.88 379	79.18 311	90.87 301	58.47 338	96.60 258	82.61 264	74.20 322	91.59 286

v1144		86.83 257	85.31 265	91.40 245	89.75 325	87.21 216	98.31 196	95.45 286	83.22 291	82.70 257	90.78 302	73.36 245	96.36 277	79.49 286	74.69 315	90.63 319

CostFormer		92.89 143	92.48 138	94.12 185	94.99 225	85.89 247	92.89 339	97.00 185	86.98 226	95.00 116	90.78 302	90.05 50	97.51 226	92.92 147	91.73 204	98.96 123

v1921920		86.02 271	84.44 282	90.77 262	89.32 334	85.20 262	98.10 213	95.35 294	82.19 312	82.25 270	90.71 304	70.73 270	96.30 288	76.85 306	74.49 317	90.80 311

anonymousdsp		86.69 259	85.75 258	89.53 296	86.46 361	82.94 292	96.39 288	95.71 270	83.97 278	79.63 305	90.70 305	68.85 280	95.94 303	86.01 220	84.02 259	89.72 337

tpmrst		92.78 144	92.16 143	94.65 163	96.27 168	87.45 205	91.83 348	97.10 175	89.10 165	94.68 120	90.69 306	88.22 67	97.73 213	89.78 179	91.80 202	98.77 146

V42		87.00 254	85.68 259	90.98 255	89.91 321	86.08 241	98.32 195	95.61 277	83.67 285	82.72 256	90.67 307	74.00 243	96.53 265	81.94 271	74.28 321	90.32 324

tpm2		91.77 166	91.09 165	93.82 197	94.83 232	85.56 256	92.51 344	97.16 167	84.00 277	93.83 134	90.66 308	87.54 79	97.17 237	87.73 204	91.55 207	98.72 148

EPMVS		92.59 150	91.59 156	95.59 130	97.22 129	90.03 144	91.78 349	98.04 48	90.42 129	91.66 159	90.65 309	86.49 109	97.46 228	81.78 272	96.31 147	99.28 97

LCM-MVSNet-Re		88.59 231	88.61 212	88.51 312	95.53 197	72.68 362	96.85 274	88.43 381	88.45 183	73.14 346	90.63 310	75.82 227	94.38 341	92.95 145	95.71 159	98.48 160

SCA		90.64 189	89.25 198	94.83 157	94.95 227	88.83 174	96.26 294	97.21 160	90.06 141	90.03 188	90.62 311	66.61 300	96.81 252	83.16 257	94.36 171	98.84 136

Patchmatch-test		86.25 269	84.06 286	92.82 214	94.42 240	82.88 296	82.88 384	94.23 329	71.58 362	79.39 308	90.62 311	89.00 59	96.42 274	63.03 366	91.37 212	99.16 106

v1192		86.32 268	84.71 276	91.17 249	89.53 331	86.40 227	98.13 208	95.44 288	82.52 306	82.42 265	90.62 311	71.58 267	96.33 284	77.23 301	74.88 312	90.79 312

v144192		86.40 266	84.89 271	90.91 256	89.48 332	85.59 254	98.21 203	95.43 289	82.45 308	82.62 260	90.58 314	72.79 255	96.36 277	78.45 296	74.04 325	90.79 312

PatchmatchNet		92.05 164	91.04 167	95.06 147	96.17 174	89.04 164	91.26 357	97.26 153	89.56 153	90.64 178	90.56 315	88.35 66	97.11 239	79.53 285	96.07 154	99.03 118
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v1240		85.77 278	84.11 285	90.73 263	89.26 335	85.15 265	97.88 227	95.23 303	81.89 317	82.16 271	90.55 316	69.60 278	96.31 285	75.59 315	74.87 313	90.72 316

our_test_3		84.47 295	82.80 295	89.50 297	89.01 336	83.90 282	97.03 267	94.56 320	81.33 321	75.36 335	90.52 317	71.69 265	94.54 340	68.81 348	76.84 303	90.07 329

miper_lstm_enhance		86.90 255	86.20 251	89.00 307	94.53 239	81.19 317	96.74 280	95.24 299	82.33 310	80.15 298	90.51 318	81.99 185	94.68 338	80.71 279	73.58 328	91.12 303

MDTV_nov1_ep13			90.47 181		96.14 177	88.55 181	91.34 356	97.51 127	89.58 151	92.24 152	90.50 319	86.99 95	97.61 220	77.64 300	92.34 192

IterMVS-SCA-FT		85.73 279	84.64 278	89.00 307	93.46 271	82.90 294	96.27 292	94.70 316	85.02 263	78.62 315	90.35 320	66.61 300	93.33 348	79.38 288	77.36 302	90.76 314

D2MVS		87.96 238	87.39 232	89.70 292	91.84 297	83.40 287	98.31 196	98.49 23	88.04 200	78.23 321	90.26 321	73.57 244	96.79 254	84.21 244	83.53 265	88.90 347

GBi-Net		86.67 260	84.96 268	91.80 237	95.11 217	88.81 175	96.77 276	95.25 296	82.94 297	82.12 272	90.25 322	62.89 322	94.97 329	79.04 289	80.24 283	91.62 281

test1		86.67 260	84.96 268	91.80 237	95.11 217	88.81 175	96.77 276	95.25 296	82.94 297	82.12 272	90.25 322	62.89 322	94.97 329	79.04 289	80.24 283	91.62 281

FMVSNet1		83.94 302	81.32 310	91.80 237	91.94 295	88.81 175	96.77 276	95.25 296	77.98 340	78.25 320	90.25 322	50.37 366	94.97 329	73.27 332	77.81 299	91.62 281

v148		86.38 267	85.06 267	90.37 275	89.47 333	84.10 279	98.52 167	95.48 284	83.80 281	80.93 290	90.22 325	74.60 234	96.31 285	80.92 277	71.55 346	90.69 317

lessismore_v0				85.08 336	85.59 364	69.28 372		90.56 372		67.68 366	90.21 326	54.21 355	95.46 319	73.88 327	62.64 369	90.50 321

dp		90.16 199	88.83 207	94.14 184	96.38 164	86.42 226	91.57 353	97.06 178	84.76 268	88.81 199	90.19 327	84.29 143	97.43 231	75.05 317	91.35 213	98.56 156

IterMVS		85.81 276	84.67 277	89.22 302	93.51 268	83.67 285	96.32 291	94.80 313	85.09 260	78.69 313	90.17 328	66.57 302	93.17 351	79.48 287	77.42 301	90.81 310
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_0402		78.81 327	76.33 332	86.26 329	91.18 307	78.44 338	95.88 307	91.34 368	68.55 373	70.51 356	89.91 329	52.65 359	94.99 328	47.14 385	79.78 288	85.34 370

v8		86.11 270	84.45 281	91.10 251	89.99 320	86.85 219	97.24 259	95.36 293	81.99 314	79.89 302	89.86 330	74.53 236	96.39 275	78.83 293	72.32 340	90.05 331

v10		85.73 279	84.01 287	90.87 259	90.03 319	86.73 221	97.20 262	95.22 304	81.25 322	79.85 303	89.75 331	73.30 248	96.28 289	76.87 305	72.64 336	89.61 339

test20.03		78.51 330	77.48 326	81.62 353	83.07 371	71.03 366	96.11 300	92.83 349	81.66 318	69.31 359	89.68 332	57.53 340	87.29 382	58.65 376	68.47 353	86.53 363

pmmvs6		79.90 321	77.31 327	87.67 318	84.17 368	78.13 340	95.86 309	93.68 338	67.94 376	72.67 351	89.62 333	50.98 364	95.75 312	74.80 321	66.04 362	89.14 345

tpm		89.67 207	88.95 204	91.82 236	92.54 283	81.43 311	92.95 338	95.92 252	87.81 207	90.50 181	89.44 334	84.99 134	95.65 315	83.67 254	82.71 273	98.38 165

v7n		84.42 296	82.75 298	89.43 300	88.15 346	81.86 306	96.75 279	95.67 274	80.53 328	78.38 319	89.43 335	69.89 273	96.35 282	73.83 329	72.13 342	90.07 329

K. test v3		81.04 316	79.77 319	84.83 338	87.41 354	70.23 370	95.60 315	93.93 334	83.70 284	67.51 367	89.35 336	55.76 345	93.58 347	76.67 308	68.03 355	90.67 318

tpmvs		89.16 213	87.76 226	93.35 204	97.19 130	84.75 271	90.58 364	97.36 150	81.99 314	84.56 236	89.31 337	83.98 147	98.17 180	74.85 320	90.00 223	97.12 201

Anonymous20231206		80.76 317	79.42 321	84.79 339	84.78 366	72.98 359	96.53 284	92.97 346	79.56 333	74.33 337	88.83 338	61.27 329	92.15 363	60.59 372	75.92 306	89.24 344

EG-PatchMatch MVS		79.92 320	77.59 325	86.90 325	87.06 358	77.90 343	96.20 299	94.06 332	74.61 355	66.53 371	88.76 339	40.40 381	96.20 290	67.02 355	83.66 264	86.61 362

tpm cat1		88.89 219	87.27 235	93.76 198	95.79 187	85.32 261	90.76 362	97.09 176	76.14 350	85.72 227	88.59 340	82.92 165	98.04 190	76.96 304	91.43 210	97.90 183

DeepMVS_CX				76.08 359	90.74 313	51.65 392		90.84 370	86.47 241	57.89 380	87.98 341	35.88 384	92.60 356	65.77 360	65.06 365	83.97 375

MDA-MVSNet-bldmvs		77.82 333	74.75 339	87.03 324	88.33 344	78.52 337	96.34 290	92.85 348	75.57 351	48.87 386	87.89 342	57.32 342	92.49 360	60.79 371	64.80 366	90.08 328

UnsupCasMVSNet_eth		78.90 326	76.67 331	85.58 334	82.81 373	74.94 352	91.98 347	96.31 219	84.64 269	65.84 373	87.71 343	51.33 361	92.23 362	72.89 335	56.50 380	89.56 340

MIMVSNet		84.48 294	81.83 304	92.42 223	91.73 299	87.36 208	85.52 373	94.42 325	81.40 320	81.91 278	87.58 344	51.92 360	92.81 354	73.84 328	88.15 228	97.08 205

YYNet1		79.64 324	77.04 329	87.43 322	87.80 351	79.98 325	96.23 296	94.44 322	73.83 359	51.83 383	87.53 345	67.96 290	92.07 365	66.00 359	67.75 358	90.23 326

APD_test1		68.93 347	66.98 350	74.77 362	80.62 378	53.15 389	87.97 368	85.01 387	53.76 385	59.26 379	87.52 346	25.19 388	89.95 371	56.20 378	67.33 359	81.19 380

KD-MVS_2432*1600		82.98 306	80.52 314	90.38 273	94.32 244	88.98 167	92.87 340	95.87 262	80.46 330	73.79 341	87.49 347	82.76 170	93.29 349	70.56 342	46.53 390	88.87 348

miper_refine_blended		82.98 306	80.52 314	90.38 273	94.32 244	88.98 167	92.87 340	95.87 262	80.46 330	73.79 341	87.49 347	82.76 170	93.29 349	70.56 342	46.53 390	88.87 348

MDA-MVSNet_test_wron		79.65 323	77.05 328	87.45 321	87.79 352	80.13 324	96.25 295	94.44 322	73.87 358	51.80 384	87.47 349	68.04 288	92.12 364	66.02 358	67.79 357	90.09 327

ADS-MVSNet2		87.62 248	86.88 241	89.86 287	96.21 171	79.14 331	87.15 370	92.99 345	83.01 294	89.91 190	87.27 350	78.87 212	92.80 355	74.20 325	92.27 194	97.64 187

ADS-MVSNet		88.99 215	87.30 234	94.07 187	96.21 171	87.56 201	87.15 370	96.78 193	83.01 294	89.91 190	87.27 350	78.87 212	97.01 244	74.20 325	92.27 194	97.64 187

DSMNet-mixed		81.60 314	81.43 308	82.10 351	84.36 367	60.79 380	93.63 333	86.74 384	79.00 334	79.32 309	87.15 352	63.87 318	89.78 374	66.89 356	91.92 199	95.73 232

OpenMVS_ROB	73.86 20	77.99 332	75.06 338	86.77 326	83.81 370	77.94 342	96.38 289	91.53 367	67.54 377	68.38 362	87.13 353	43.94 374	96.08 297	55.03 380	81.83 278	86.29 365

CR-MVSNet		88.83 223	87.38 233	93.16 208	93.47 269	86.24 233	84.97 377	94.20 330	88.92 172	90.76 176	86.88 354	84.43 141	94.82 334	70.64 341	92.17 197	98.41 162

Patchmtry		83.61 305	81.64 305	89.50 297	93.36 273	82.84 297	84.10 380	94.20 330	69.47 372	79.57 306	86.88 354	84.43 141	94.78 335	68.48 350	74.30 320	90.88 309

N_pmnet		70.19 345	69.87 347	71.12 366	88.24 345	30.63 405	95.85 310	28.70 404	70.18 368	68.73 361	86.55 356	64.04 317	93.81 344	53.12 382	73.46 330	88.94 346

MIMVSNet1		75.92 337	73.30 342	83.81 345	81.29 376	75.57 349	92.26 345	92.05 360	73.09 361	67.48 368	86.18 357	40.87 380	87.64 381	55.78 379	70.68 350	88.21 351

FMVSNet5		82.29 309	80.54 313	87.52 319	93.79 264	84.01 280	93.73 331	92.47 353	76.92 347	74.27 338	86.15 358	63.69 320	89.24 377	69.07 347	74.79 314	89.29 343

CL-MVSNet_self_test		79.89 322	78.34 323	84.54 341	81.56 375	75.01 351	96.88 273	95.62 276	81.10 323	75.86 331	85.81 359	68.49 283	90.26 370	63.21 365	56.51 379	88.35 350

patchmatchnet-post											84.86 360	88.73 62	96.81 252

Anonymous20240521		78.63 329	76.90 330	83.82 344	82.82 372	72.86 360	95.72 314	93.57 340	73.55 360	72.17 353	84.79 361	49.69 368	92.51 359	65.29 361	74.50 316	86.09 366

test_method		70.10 346	68.66 349	74.41 363	86.30 363	55.84 385	94.47 322	89.82 375	35.18 392	66.15 372	84.75 362	30.54 386	77.96 393	70.40 344	60.33 373	89.44 341

EGC-MVSNET		60.70 352	55.37 356	76.72 358	86.35 362	71.08 365	89.96 365	84.44 389	0.38 401	1.50 402	84.09 363	37.30 382	88.10 380	40.85 390	73.44 331	70.97 386

KD-MVS_self_test		77.47 334	75.88 334	82.24 349	81.59 374	68.93 373	92.83 342	94.02 333	77.03 346	73.14 346	83.39 364	55.44 349	90.42 369	67.95 351	57.53 378	87.38 356

PM-MVS		74.88 340	72.85 343	80.98 355	78.98 381	64.75 378	90.81 361	85.77 385	80.95 326	68.23 364	82.81 365	29.08 387	92.84 353	76.54 309	62.46 370	85.36 369

mvsany_test3		75.85 338	74.52 340	79.83 356	73.53 387	60.64 381	91.73 350	87.87 383	83.91 280	70.55 355	82.52 366	31.12 385	93.66 345	86.66 216	62.83 367	85.19 372

test_vis1_rt		81.31 315	80.05 318	85.11 335	91.29 306	70.66 368	98.98 122	77.39 396	85.76 250	68.80 360	82.40 367	36.56 383	99.44 119	92.67 151	86.55 236	85.24 371

pmmvs-eth3d		78.71 328	76.16 333	86.38 327	80.25 379	81.19 317	94.17 327	92.13 359	77.97 341	66.90 370	82.31 368	55.76 345	92.56 358	73.63 331	62.31 371	85.38 368

Patchmatch-RL test		81.90 313	80.13 316	87.23 323	80.71 377	70.12 371	84.07 381	88.19 382	83.16 293	70.57 354	82.18 369	87.18 89	92.59 357	82.28 267	62.78 368	98.98 121

WB-MVS		66.44 348	66.29 351	66.89 369	74.84 384	44.93 396	93.00 337	84.09 390	71.15 364	55.82 381	81.63 370	63.79 319	80.31 391	21.85 395	50.47 388	75.43 382

new_pmnet		76.02 336	73.71 341	82.95 347	83.88 369	72.85 361	91.26 357	92.26 356	70.44 367	62.60 376	81.37 371	47.64 371	92.32 361	61.85 368	72.10 343	83.68 376

test_fmvs3		75.09 339	75.19 336	74.81 361	77.45 383	54.08 387	95.93 303	90.64 371	82.51 307	73.29 344	81.19 372	22.29 390	86.29 383	85.50 228	67.89 356	84.06 374

FPMVS		61.57 350	60.32 353	65.34 371	60.14 397	42.44 399	91.02 360	89.72 376	44.15 387	42.63 390	80.93 373	19.02 392	80.59 390	42.50 387	72.76 335	73.00 384

SSC-MVS		65.42 349	65.20 352	66.06 370	73.96 385	43.83 397	92.08 346	83.54 391	69.77 370	54.73 382	80.92 374	63.30 321	79.92 392	20.48 396	48.02 389	74.44 383

pmmvs3		72.86 343	69.76 348	82.17 350	73.86 386	74.19 355	94.20 326	89.01 380	64.23 383	67.72 365	80.91 375	41.48 378	88.65 379	62.40 367	54.02 383	83.68 376

ambc				79.60 357	72.76 389	56.61 384	76.20 388	92.01 361		68.25 363	80.23 376	23.34 389	94.73 336	73.78 330	60.81 372	87.48 355

new-patchmatchnet		74.80 341	72.40 344	81.99 352	78.36 382	72.20 363	94.44 323	92.36 354	77.06 345	63.47 375	79.98 377	51.04 363	88.85 378	60.53 373	54.35 382	84.92 373

PatchT		85.44 282	83.19 291	92.22 225	93.13 278	83.00 291	83.80 383	96.37 216	70.62 365	90.55 179	79.63 378	84.81 138	94.87 332	58.18 377	91.59 206	98.79 143

RPMNet		85.07 286	81.88 303	94.64 165	93.47 269	86.24 233	84.97 377	97.21 160	64.85 382	90.76 176	78.80 379	80.95 198	99.27 137	53.76 381	92.17 197	98.41 162

test_f		71.94 344	70.82 345	75.30 360	72.77 388	53.28 388	91.62 351	89.66 377	75.44 352	64.47 374	78.31 380	20.48 391	89.56 375	78.63 295	66.02 363	83.05 379

testf1		56.38 355	53.73 358	64.31 373	64.84 392	45.11 394	80.50 386	75.94 398	38.87 388	42.74 388	75.07 381	11.26 400	81.19 387	41.11 388	53.27 384	66.63 387

APD_test2		56.38 355	53.73 358	64.31 373	64.84 392	45.11 394	80.50 386	75.94 398	38.87 388	42.74 388	75.07 381	11.26 400	81.19 387	41.11 388	53.27 384	66.63 387

UnsupCasMVSNet_bld		73.85 342	70.14 346	84.99 337	79.44 380	75.73 348	88.53 367	95.24 299	70.12 369	61.94 377	74.81 383	41.41 379	93.62 346	68.65 349	51.13 387	85.62 367

LCM-MVSNet		60.07 353	56.37 355	71.18 365	54.81 399	48.67 393	82.17 385	89.48 378	37.95 390	49.13 385	69.12 384	13.75 398	81.76 385	59.28 374	51.63 386	83.10 378

PMMVS2		58.97 354	55.07 357	70.69 367	62.72 394	55.37 386	85.97 372	80.52 393	49.48 386	45.94 387	68.31 385	15.73 396	80.78 389	49.79 384	37.12 392	75.91 381

JIA-IIPM		85.97 272	84.85 272	89.33 301	93.23 276	73.68 357	85.05 376	97.13 170	69.62 371	91.56 162	68.03 386	88.03 73	96.96 245	77.89 299	93.12 180	97.34 196

testmvs		18.81 365	23.05 368	6.10 383	4.48 404	2.29 408	97.78 232	3.00 406	3.27 399	18.60 399	62.71 387	1.53 406	2.49 402	14.26 400	1.80 399	13.50 397

gg-mvs-nofinetune		90.00 202	87.71 228	96.89 73	96.15 175	94.69 45	85.15 375	97.74 74	68.32 375	92.97 145	60.16 388	96.10 3	96.84 250	93.89 129	98.87 88	99.14 108

PMVS	41.42 23	45.67 360	42.50 363	55.17 377	34.28 402	32.37 403	66.24 391	78.71 395	30.72 393	22.04 398	59.59 389	4.59 402	77.85 394	27.49 393	58.84 376	55.29 391
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVS-HIRNet		79.01 325	75.13 337	90.66 264	93.82 263	81.69 308	85.16 374	93.75 336	54.54 384	74.17 339	59.15 390	57.46 341	96.58 262	63.74 363	94.38 170	93.72 242

test_vis3_rt		61.29 351	58.75 354	68.92 368	67.41 391	52.84 390	91.18 359	59.23 403	66.96 378	41.96 391	58.44 391	11.37 399	94.72 337	74.25 324	57.97 377	59.20 390

ANet_high		50.71 359	46.17 362	64.33 372	44.27 401	52.30 391	76.13 389	78.73 394	64.95 381	27.37 395	55.23 392	14.61 397	67.74 395	36.01 391	18.23 395	72.95 385

Gipuma		54.77 357	52.22 361	62.40 375	86.50 360	59.37 383	50.20 393	90.35 373	36.52 391	41.20 392	49.49 393	18.33 394	81.29 386	32.10 392	65.34 364	46.54 393
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	44.00 22	41.70 361	37.64 366	53.90 378	49.46 400	43.37 398	65.09 392	66.66 400	26.19 396	25.77 397	48.53 394	3.58 404	63.35 397	26.15 394	27.28 393	54.97 392
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		41.02 362	40.93 364	41.29 379	61.97 395	33.83 402	84.00 382	65.17 401	27.17 394	27.56 394	46.72 395	17.63 395	60.41 398	19.32 397	18.82 394	29.61 394

test_post											46.00 396	87.37 83	97.11 239

test123		16.58 367	19.47 369	7.91 382	3.59 405	5.37 407	94.32 324	1.39 407	2.49 400	13.98 400	44.60 397	2.91 405	2.65 401	11.35 401	0.57 400	15.70 396

EMVS		39.96 363	39.88 365	40.18 380	59.57 398	32.12 404	84.79 379	64.57 402	26.27 395	26.14 396	44.18 398	18.73 393	59.29 399	17.03 398	17.67 396	29.12 395

test_post1							90.74 363				41.37 399	85.38 130	96.36 277	83.16 257

X-MVStestdata		90.69 188	88.66 211	96.77 74	99.62 22	90.66 125	99.43 65	97.58 112	92.41 85	96.86 74	29.59 400	87.37 83	99.87 58	95.65 92	99.43 59	99.78 38

wuyk23d		16.71 366	16.73 370	16.65 381	60.15 396	25.22 406	41.24 394	5.17 405	6.56 398	5.48 401	3.61 401	3.64 403	22.72 400	15.20 399	9.52 398	1.99 398

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

pcd_1.5k_mvsjas		6.87 369	9.16 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	82.48 176	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						79.74 327								67.75 352

FOURS1					99.50 42	88.94 170	99.55 44	97.47 135	91.32 108	98.12 44

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 85					99.98 9	99.55 12	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 85					99.98 9	99.55 12	99.83 15	99.96 10

eth-test2					0.00 406

eth-test					0.00 406

IU-MVS					99.63 18	95.38 22		97.73 77	95.54 26	99.54 3				99.69 6	99.81 23	99.99 1

save fliter					99.34 50	93.85 62	99.65 35	97.63 101	95.69 22

test_0728_SECOND				98.77 8	99.66 12	96.37 14	99.72 23	97.68 87					99.98 9	99.64 7	99.82 19	99.96 10

GSMVS																98.84 136

test_part2					99.54 36	95.42 20				98.13 42

sam_mvs1												88.39 65				98.84 136

sam_mvs												87.08 91

MTGPA								97.45 138

MTMP							99.21 86	91.09 369

test9_res														98.60 33	99.87 9	99.90 22

agg_prior2														97.84 54	99.87 9	99.91 21

agg_prior					99.54 36	92.66 85		97.64 97		97.98 51			99.61 102

test_prior4						92.00 94	99.41 68

test_prior				97.01 60	99.58 30	91.77 95		97.57 115					99.49 112			99.79 36

旧先验2							98.67 150		85.75 251	98.96 20			98.97 152	93.84 131

新几何2							98.26 199

无先验							98.52 167	97.82 62	87.20 222				99.90 50	87.64 205		99.85 30

原ACMM2							98.69 147

testdata2													99.88 54	84.16 245

segment_acmp												90.56 42

testdata1							97.89 225		92.43 82

test12				97.83 33	99.33 53	94.45 49		97.55 117		97.56 56		88.60 63	99.50 111		99.71 34	99.55 72

plane_prior7					93.84 260	85.73 251

plane_prior6					93.92 257	86.02 245						72.92 252

plane_prior5								96.30 220					97.75 211	93.46 138	86.17 240	92.67 250

plane_prior3						85.91 246			93.65 61	86.99 214

plane_prior2							99.02 116		93.38 66

plane_prior1					93.90 259

plane_prior						86.07 243	99.14 101		93.81 58						86.26 239

n2								0.00 408

nn								0.00 408

door-mid								84.90 388

test11								97.68 87

door								85.30 386

HQP5-MVS						86.39 228

HQP-NCC					93.95 253		99.16 93		93.92 50	87.57 207

ACMP_Plane					93.95 253		99.16 93		93.92 50	87.57 207

BP-MVS														93.82 133

HQP4-MVS										87.57 207			97.77 205			92.72 248

HQP3-MVS								96.37 216							86.29 237

HQP2-MVS												73.34 246

MDTV_nov1_ep13_2view						91.17 108	91.38 355		87.45 219	93.08 143		86.67 102		87.02 208		98.95 127

ACMMP++_ref															82.64 274

ACMMP++															83.83 261

Test By Simon												83.62 150

High-resolution multi-view benchmark