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.

PC_three_1452									82.47 265	97.09 14	97.07 64	92.72 1	98.04 182	92.70 72	99.02 12	98.86 11

DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 55	86.00 51	98.29 1	97.49 8	90.75 24	97.62 5	98.06 19	92.59 2	99.61 4	95.64 28	99.02 12	98.86 11

OPU-MVS				96.21 3	98.00 43	90.85 3	97.13 15				97.08 62	92.59 2	98.94 85	92.25 84	98.99 14	98.84 14

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 53	97.13 15	97.44 17	90.31 36	97.71 1	98.07 17	92.31 4	99.58 10	95.66 26	99.13 3	98.84 14

test_241102_ONE					98.77 5	85.99 53		97.44 17	90.26 42	97.71 1	97.96 27	92.31 4	99.38 31

test_0728_THIRD									90.75 24	97.04 16	98.05 21	92.09 6	99.55 16	95.64 28	99.13 3	99.13 2

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 26	87.28 18	95.56 109	97.51 7	89.13 82	97.14 12	97.91 28	91.64 7	99.62 2	94.61 43	99.17 2	98.86 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 56	97.09 17	96.73 90	90.27 40	97.04 16	98.05 21	91.47 8	99.55 16	95.62 30	99.08 7	98.45 36
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
test0726					98.78 3	85.93 56	97.19 12	97.47 13	90.27 40	97.64 4	98.13 5	91.47 8

test_241102_TWO								97.44 17	90.31 36	97.62 5	98.07 17	91.46 10	99.58 10	95.66 26	99.12 6	98.98 10

test_one_0601					98.58 11	85.83 62		97.44 17	91.05 18	96.78 21	98.06 19	91.45 11

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 26	97.47 13	91.73 12	96.10 29	96.69 79	89.90 12	99.30 44	94.70 41	98.04 73	99.13 2
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
DeepPCF-MVS	89.96 1	94.20 40	94.77 24	92.49 134	96.52 92	80.00 240	94.00 219	97.08 53	90.05 44	95.65 38	97.29 49	89.66 13	98.97 80	93.95 49	98.71 32	98.50 27

SD-MVS		94.96 14	95.33 9	93.88 65	97.25 73	86.69 28	96.19 51	97.11 52	90.42 32	96.95 18	97.27 50	89.53 14	96.91 279	94.38 45	98.85 20	98.03 81
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
CNVR-MVS		95.40 7	95.37 8	95.50 8	98.11 37	88.51 7	95.29 120	96.96 62	92.09 8	95.32 41	97.08 62	89.49 15	99.33 41	95.10 37	98.85 20	98.66 21

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 29	86.29 46	97.46 7	97.40 22	89.03 87	96.20 28	98.10 11	89.39 16	99.34 38	95.88 25	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MCST-MVS		94.45 28	94.20 44	95.19 13	98.46 19	87.50 16	95.00 143	97.12 50	87.13 148	92.51 103	96.30 96	89.24 17	99.34 38	93.46 55	98.62 46	98.73 18

TSAR-MVS + MP.		94.85 15	94.94 18	94.58 42	98.25 30	86.33 42	96.11 61	96.62 99	88.14 119	96.10 29	96.96 68	89.09 18	98.94 85	94.48 44	98.68 37	98.48 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		95.20 8	95.32 10	94.85 25	96.99 76	86.33 42	97.33 8	97.30 32	91.38 15	95.39 40	97.46 42	88.98 19	99.40 30	94.12 47	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		95.20 8	95.07 14	95.59 6	98.14 36	88.48 8	96.26 48	97.28 35	85.90 180	97.67 3	98.10 11	88.41 20	99.56 12	94.66 42	99.19 1	98.71 20
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
patch_mono-2		93.74 58	94.32 34	92.01 154	97.54 61	78.37 282	93.40 246	97.19 39	88.02 122	94.99 48	97.21 54	88.35 21	98.44 142	94.07 48	98.09 70	99.23 1

9.14			94.47 28		97.79 53		96.08 63	97.44 17	86.13 178	95.10 46	97.40 45	88.34 22	99.22 48	93.25 60	98.70 34

SF-MVS		94.97 13	94.90 22	95.20 12	97.84 51	87.76 10	96.65 35	97.48 12	87.76 135	95.71 36	97.70 36	88.28 23	99.35 37	93.89 51	98.78 26	98.48 30

HPM-MVS++		95.14 10	94.91 20	95.83 4	98.25 30	89.65 4	95.92 80	96.96 62	91.75 11	94.02 63	96.83 74	88.12 24	99.55 16	93.41 58	98.94 16	98.28 56

dcpmvs_2		93.49 63	94.19 45	91.38 190	97.69 58	76.78 316	94.25 196	96.29 123	88.33 110	94.46 51	96.88 71	88.07 25	98.64 119	93.62 54	98.09 70	98.73 18

CSCG		93.23 77	93.05 78	93.76 72	98.04 41	84.07 107	96.22 50	97.37 23	84.15 225	90.05 155	95.66 130	87.77 26	99.15 54	89.91 131	98.27 58	98.07 76

NCCC		94.81 18	94.69 25	95.17 14	97.83 52	87.46 17	95.66 100	96.93 66	92.34 6	93.94 64	96.58 89	87.74 27	99.44 29	92.83 67	98.40 54	98.62 22

TEST9					97.53 62	86.49 37	94.07 211	96.78 82	81.61 293	92.77 92	96.20 100	87.71 28	99.12 56

train_agg		93.44 67	93.08 77	94.52 44	97.53 62	86.49 37	94.07 211	96.78 82	81.86 284	92.77 92	96.20 100	87.63 29	99.12 56	92.14 89	98.69 35	97.94 85

test_8					97.49 64	86.30 45	94.02 216	96.76 85	81.86 284	92.70 96	96.20 100	87.63 29	99.02 66

ZD-MVS					98.15 35	86.62 33		97.07 54	83.63 237	94.19 56	96.91 70	87.57 31	99.26 46	91.99 96	98.44 53

fmvsm_l_conf0.5_n		94.29 34	94.46 29	93.79 71	95.28 148	85.43 71	95.68 97	96.43 112	86.56 164	96.84 20	97.81 33	87.56 32	98.77 106	97.14 11	96.82 109	97.16 134

fmvsm_l_conf0.5_n_a		94.20 40	94.40 31	93.60 77	95.29 147	84.98 78	95.61 105	96.28 126	86.31 170	96.75 22	97.86 31	87.40 33	98.74 110	97.07 13	97.02 102	97.07 139

TSAR-MVS + GP.		93.66 60	93.41 71	94.41 49	96.59 86	86.78 26	94.40 185	93.93 277	89.77 59	94.21 55	95.59 133	87.35 34	98.61 124	92.72 70	96.15 126	97.83 96

APD-MVS		94.24 36	94.07 49	94.75 36	98.06 40	86.90 23	95.88 82	96.94 65	85.68 187	95.05 47	97.18 58	87.31 35	99.07 58	91.90 102	98.61 48	98.28 56
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
segment_acmp												87.16 36

reproduce-ours		94.82 16	94.97 16	94.38 50	97.91 48	85.46 69	95.86 83	97.15 46	89.82 52	95.23 44	98.10 11	87.09 37	99.37 33	95.30 34	98.25 61	98.30 50

our_new_method		94.82 16	94.97 16	94.38 50	97.91 48	85.46 69	95.86 83	97.15 46	89.82 52	95.23 44	98.10 11	87.09 37	99.37 33	95.30 34	98.25 61	98.30 50

旧先验1					96.79 80	81.81 180		95.67 183			96.81 76	86.69 39			97.66 89	96.97 149

lecture		95.10 11	95.46 7	94.01 60	98.40 23	84.36 101	97.70 3	97.78 1	91.19 16	96.22 27	98.08 16	86.64 40	99.37 33	94.91 39	98.26 59	98.29 55

test_prior2							94.12 203		87.67 138	92.63 99	96.39 95	86.62 41		91.50 109	98.67 40

CDPH-MVS		92.83 86	92.30 93	94.44 45	97.79 53	86.11 50	94.06 213	96.66 96	80.09 315	92.77 92	96.63 86	86.62 41	99.04 62	87.40 161	98.66 41	98.17 68

DPM-MVS		92.58 91	91.74 101	95.08 15	96.19 100	89.31 5	92.66 280	96.56 104	83.44 243	91.68 127	95.04 156	86.60 43	98.99 75	85.60 188	97.92 78	96.93 152

reproduce_model		94.76 20	94.92 19	94.29 55	97.92 44	85.18 75	95.95 78	97.19 39	89.67 62	95.27 43	98.16 4	86.53 44	99.36 36	95.42 33	98.15 66	98.33 45

test_fmvsmconf_n		94.60 23	94.81 23	93.98 61	94.62 190	84.96 79	96.15 56	97.35 25	89.37 71	96.03 32	98.11 9	86.36 45	99.01 68	97.45 8	97.83 81	97.96 84

DELS-MVS		93.43 71	93.25 74	93.97 62	95.42 143	85.04 77	93.06 267	97.13 49	90.74 26	91.84 121	95.09 155	86.32 46	99.21 49	91.22 112	98.45 52	97.65 107
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
test_fmvsm_n_1920		94.71 22	95.11 13	93.50 79	95.79 124	84.62 86	96.15 56	97.64 3	89.85 51	97.19 11	97.89 29	86.28 47	98.71 113	97.11 12	98.08 72	97.17 130

ZNCC-MVS		94.47 27	94.28 38	95.03 16	98.52 15	86.96 20	96.85 29	97.32 30	88.24 114	93.15 79	97.04 65	86.17 48	99.62 2	92.40 78	98.81 23	98.52 26

HFP-MVS		94.52 25	94.40 31	94.86 24	98.61 10	86.81 25	96.94 21	97.34 26	88.63 101	93.65 69	97.21 54	86.10 49	99.49 26	92.35 81	98.77 28	98.30 50

MVS_111021_HR		93.45 66	93.31 72	93.84 67	96.99 76	84.84 80	93.24 259	97.24 36	88.76 96	91.60 128	95.85 121	86.07 50	98.66 115	91.91 100	98.16 65	98.03 81

ACMMP_NAP		94.74 21	94.56 26	95.28 10	98.02 42	87.70 11	95.68 97	97.34 26	88.28 113	95.30 42	97.67 37	85.90 51	99.54 20	93.91 50	98.95 15	98.60 23

mamv4		90.92 120	91.78 100	88.33 308	95.67 131	70.75 392	92.92 273	96.02 155	81.90 281	88.11 181	95.34 141	85.88 52	96.97 274	95.22 36	95.01 151	97.26 124

CS-MVS		94.12 44	94.44 30	93.17 91	96.55 89	83.08 145	97.63 4	96.95 64	91.71 13	93.50 75	96.21 99	85.61 53	98.24 159	93.64 53	98.17 64	98.19 66

PHI-MVS		93.89 53	93.65 67	94.62 41	96.84 79	86.43 39	96.69 33	97.49 8	85.15 202	93.56 73	96.28 97	85.60 54	99.31 43	92.45 75	98.79 24	98.12 74

MP-MVS-pluss		94.21 38	94.00 52	94.85 25	98.17 34	86.65 31	94.82 156	97.17 44	86.26 172	92.83 89	97.87 30	85.57 55	99.56 12	94.37 46	98.92 17	98.34 43
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
GST-MVS		94.21 38	93.97 53	94.90 23	98.41 22	86.82 24	96.54 37	97.19 39	88.24 114	93.26 76	96.83 74	85.48 56	99.59 8	91.43 111	98.40 54	98.30 50

MP-MVS		94.25 35	94.07 49	94.77 35	98.47 18	86.31 44	96.71 32	96.98 58	89.04 85	91.98 114	97.19 57	85.43 57	99.56 12	92.06 94	98.79 24	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	89.43 2	94.04 46	93.79 58	94.80 33	97.48 65	86.78 26	95.65 102	96.89 70	89.40 70	92.81 90	96.97 67	85.37 58	99.24 47	90.87 120	98.69 35	98.38 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
region2R		94.43 30	94.27 40	94.92 20	98.65 8	86.67 30	96.92 25	97.23 38	88.60 104	93.58 71	97.27 50	85.22 59	99.54 20	92.21 85	98.74 31	98.56 25

CP-MVS		94.34 33	94.21 43	94.74 37	98.39 24	86.64 32	97.60 5	97.24 36	88.53 106	92.73 95	97.23 53	85.20 60	99.32 42	92.15 88	98.83 22	98.25 63

test_fmvsmconf0.1_n		94.20 40	94.31 36	93.88 65	92.46 287	84.80 82	96.18 53	96.82 78	89.29 76	95.68 37	98.11 9	85.10 61	98.99 75	97.38 9	97.75 87	97.86 93

test12				94.34 52	97.13 74	86.15 49		96.29 123		91.04 138		85.08 62	99.01 68		98.13 68	97.86 93

ACMMPR		94.43 30	94.28 38	94.91 21	98.63 9	86.69 28	96.94 21	97.32 30	88.63 101	93.53 74	97.26 52	85.04 63	99.54 20	92.35 81	98.78 26	98.50 27

SPE-MVS-test		94.02 47	94.29 37	93.24 86	96.69 82	83.24 135	97.49 6	96.92 67	92.14 7	92.90 85	95.77 126	85.02 64	98.33 154	93.03 64	98.62 46	98.13 71

XVS		94.45 28	94.32 34	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 29	92.85 87	97.16 60	85.02 64	99.49 26	91.99 96	98.56 50	98.47 33

X-MVStestdata		88.31 200	86.13 248	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 29	92.85 87	23.41 445	85.02 64	99.49 26	91.99 96	98.56 50	98.47 33

MVSMamba_PlusPlus		93.44 67	93.54 69	93.14 93	96.58 88	83.05 146	96.06 67	96.50 109	84.42 222	94.09 59	95.56 134	85.01 67	98.69 114	94.96 38	98.66 41	97.67 106

fmvsm_l_conf0.5_n_3		94.80 19	95.01 15	94.15 58	95.64 133	85.08 76	96.09 62	97.36 24	90.98 19	97.09 14	98.12 8	84.98 68	98.94 85	97.07 13	97.80 83	98.43 38

MSLP-MVS++		93.72 59	94.08 48	92.65 125	97.31 69	83.43 128	95.79 89	97.33 28	90.03 45	93.58 71	96.96 68	84.87 69	97.76 199	92.19 87	98.66 41	96.76 160

HPM-MVS		94.02 47	93.88 54	94.43 47	98.39 24	85.78 64	97.25 11	97.07 54	86.90 156	92.62 100	96.80 78	84.85 70	99.17 51	92.43 76	98.65 44	98.33 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SR-MVS		94.23 37	94.17 47	94.43 47	98.21 33	85.78 64	96.40 39	96.90 69	88.20 117	94.33 53	97.40 45	84.75 71	99.03 63	93.35 59	97.99 75	98.48 30

PGM-MVS		93.96 51	93.72 63	94.68 38	98.43 20	86.22 47	95.30 118	97.78 1	87.45 142	93.26 76	97.33 48	84.62 72	99.51 24	90.75 122	98.57 49	98.32 49

balanced_conf03		93.98 50	94.22 41	93.26 85	96.13 103	83.29 134	96.27 47	96.52 107	89.82 52	95.56 39	95.51 135	84.50 73	98.79 104	94.83 40	98.86 19	97.72 103

EI-MVSNet-Vis-set		93.01 84	92.92 81	93.29 83	95.01 162	83.51 127	94.48 177	95.77 174	90.87 20	92.52 102	96.67 81	84.50 73	99.00 73	91.99 96	94.44 168	97.36 120

MTAPA		94.42 32	94.22 41	95.00 18	98.42 21	86.95 21	94.36 193	96.97 59	91.07 17	93.14 80	97.56 39	84.30 75	99.56 12	93.43 56	98.75 30	98.47 33

SR-MVS-dyc-post		93.82 55	93.82 56	93.82 68	97.92 44	84.57 88	96.28 45	96.76 85	87.46 140	93.75 67	97.43 43	84.24 76	99.01 68	92.73 68	97.80 83	97.88 91

ETV-MVS		92.74 89	92.66 86	92.97 104	95.20 154	84.04 111	95.07 139	96.51 108	90.73 27	92.96 84	91.19 301	84.06 77	98.34 152	91.72 105	96.54 116	96.54 172

EI-MVSNet-UG-set		92.74 89	92.62 88	93.12 94	94.86 175	83.20 137	94.40 185	95.74 177	90.71 28	92.05 112	96.60 88	84.00 78	98.99 75	91.55 108	93.63 180	97.17 130

mPP-MVS		93.99 49	93.78 59	94.63 40	98.50 16	85.90 61	96.87 27	96.91 68	88.70 99	91.83 123	97.17 59	83.96 79	99.55 16	91.44 110	98.64 45	98.43 38

APD-MVS_3200maxsize		93.78 56	93.77 60	93.80 70	97.92 44	84.19 105	96.30 42	96.87 72	86.96 152	93.92 65	97.47 41	83.88 80	98.96 82	92.71 71	97.87 79	98.26 62

EIA-MVS		91.95 100	91.94 97	91.98 158	95.16 156	80.01 239	95.36 113	96.73 90	88.44 107	89.34 164	92.16 264	83.82 81	98.45 140	89.35 135	97.06 100	97.48 116

fmvsm_s_conf0.5_n_3		94.49 26	95.13 11	92.56 130	95.49 141	81.10 204	95.93 79	97.16 45	92.96 3	97.39 9	98.13 5	83.63 82	98.80 102	97.89 2	97.61 90	97.78 99

fmvsm_s_conf0.5_n		93.76 57	94.06 51	92.86 111	95.62 135	83.17 138	96.14 58	96.12 144	88.13 120	95.82 35	98.04 24	83.43 83	98.48 132	96.97 17	96.23 123	96.92 153

casdiffmvs_mvg		92.96 85	92.83 83	93.35 81	94.59 192	83.40 130	95.00 143	96.34 120	90.30 38	92.05 112	96.05 109	83.43 83	98.15 166	92.07 91	95.67 134	98.49 29
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPP-MVSNet		91.70 107	91.56 103	92.13 153	95.88 121	80.50 223	97.33 8	95.25 214	86.15 175	89.76 158	95.60 132	83.42 85	98.32 156	87.37 163	93.25 193	97.56 113

test_fmvsmvis_n_1920		93.44 67	93.55 68	93.10 95	93.67 248	84.26 103	95.83 87	96.14 140	89.00 89	92.43 105	97.50 40	83.37 86	98.72 111	96.61 20	97.44 92	96.32 177

fmvsm_s_conf0.5_n_5		93.96 51	94.18 46	93.30 82	94.79 179	83.81 116	95.77 91	96.74 89	88.02 122	96.23 26	97.84 32	83.36 87	98.83 100	97.49 6	97.34 96	97.25 125

fmvsm_s_conf0.5_n_6		94.11 45	94.56 26	92.76 117	94.98 165	81.96 178	95.79 89	97.29 34	89.31 74	97.52 8	97.61 38	83.25 88	98.88 91	97.05 15	98.22 63	97.43 119

UA-Net		92.83 86	92.54 89	93.68 76	96.10 108	84.71 84	95.66 100	96.39 116	91.92 9	93.22 78	96.49 92	83.16 89	98.87 92	84.47 202	95.47 140	97.45 118

UniMVSNet_NR-MVSNet		89.92 152	89.29 153	91.81 175	93.39 257	83.72 118	94.43 183	97.12 50	89.80 55	86.46 219	93.32 224	83.16 89	97.23 255	84.92 194	81.02 357	94.49 262

EC-MVSNet		93.44 67	93.71 64	92.63 126	95.21 153	82.43 166	97.27 10	96.71 93	90.57 31	92.88 86	95.80 124	83.16 89	98.16 165	93.68 52	98.14 67	97.31 121

fmvsm_s_conf0.5_n_4		93.86 54	94.37 33	92.33 144	95.13 159	80.95 209	95.64 103	96.97 59	89.60 64	96.85 19	97.77 34	83.08 92	98.92 88	97.49 6	96.78 110	97.13 135

fmvsm_s_conf0.5_n_a		93.57 61	93.76 61	93.00 102	95.02 161	83.67 120	96.19 51	96.10 146	87.27 145	95.98 33	98.05 21	83.07 93	98.45 140	96.68 19	95.51 137	96.88 156

MM		95.10 11	94.91 20	95.68 5	96.09 109	88.34 9	96.68 34	94.37 259	95.08 1	94.68 49	97.72 35	82.94 94	99.64 1	97.85 3	98.76 29	99.06 7

RE-MVS-def			93.68 65		97.92 44	84.57 88	96.28 45	96.76 85	87.46 140	93.75 67	97.43 43	82.94 94		92.73 68	97.80 83	97.88 91

新几何1				93.10 95	97.30 70	84.35 102		95.56 191	71.09 408	91.26 135	96.24 98	82.87 96	98.86 94	79.19 290	98.10 69	96.07 193

fmvsm_s_conf0.1_n		93.46 65	93.66 66	92.85 112	93.75 244	83.13 140	96.02 71	95.74 177	87.68 137	95.89 34	98.17 3	82.78 97	98.46 136	96.71 18	96.17 125	96.98 148

原ACMM1				92.01 154	97.34 68	81.05 205		96.81 80	78.89 331	90.45 146	95.92 116	82.65 98	98.84 98	80.68 269	98.26 59	96.14 187

casdiffmvs		92.51 92	92.43 91	92.74 120	94.41 209	81.98 176	94.54 174	96.23 134	89.57 65	91.96 116	96.17 104	82.58 99	98.01 184	90.95 118	95.45 142	98.23 64
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepC-MVS	88.79 3	93.31 73	92.99 80	94.26 56	96.07 111	85.83 62	94.89 149	96.99 57	89.02 88	89.56 159	97.37 47	82.51 100	99.38 31	92.20 86	98.30 57	97.57 112
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS_fast		93.40 72	93.22 75	93.94 64	98.36 26	84.83 81	97.15 14	96.80 81	85.77 184	92.47 104	97.13 61	82.38 101	99.07 58	90.51 126	98.40 54	97.92 88

baseline		92.39 96	92.29 94	92.69 124	94.46 204	81.77 181	94.14 202	96.27 127	89.22 78	91.88 119	96.00 111	82.35 102	97.99 186	91.05 114	95.27 148	98.30 50

sasdasda		93.27 74	92.75 84	94.85 25	95.70 129	87.66 12	96.33 40	96.41 114	90.00 46	94.09 59	94.60 178	82.33 103	98.62 122	92.40 78	92.86 200	98.27 58

canonicalmvs		93.27 74	92.75 84	94.85 25	95.70 129	87.66 12	96.33 40	96.41 114	90.00 46	94.09 59	94.60 178	82.33 103	98.62 122	92.40 78	92.86 200	98.27 58

fmvsm_s_conf0.1_n_a		93.19 78	93.26 73	92.97 104	92.49 285	83.62 123	96.02 71	95.72 180	86.78 158	96.04 31	98.19 2	82.30 105	98.43 144	96.38 21	95.42 143	96.86 157

DP-MVS Recon		91.95 100	91.28 108	93.96 63	98.33 28	85.92 58	94.66 168	96.66 96	82.69 263	90.03 156	95.82 123	82.30 105	99.03 63	84.57 200	96.48 119	96.91 154

PAPR		90.02 147	89.27 155	92.29 148	95.78 125	80.95 209	92.68 279	96.22 135	81.91 280	86.66 216	93.75 216	82.23 107	98.44 142	79.40 289	94.79 155	97.48 116

MVS_Test		91.31 113	91.11 111	91.93 163	94.37 210	80.14 231	93.46 244	95.80 172	86.46 167	91.35 134	93.77 214	82.21 108	98.09 177	87.57 159	94.95 152	97.55 114

nrg030		91.08 119	90.39 123	93.17 91	93.07 268	86.91 22	96.41 38	96.26 130	88.30 112	88.37 180	94.85 165	82.19 109	97.64 210	91.09 113	82.95 327	94.96 236

MGCFI-Net		93.03 83	92.63 87	94.23 57	95.62 135	85.92 58	96.08 63	96.33 121	89.86 50	93.89 66	94.66 175	82.11 110	98.50 130	92.33 83	92.82 203	98.27 58

UniMVSNet (Re)		89.80 155	89.07 159	92.01 154	93.60 251	84.52 91	94.78 159	97.47 13	89.26 77	86.44 222	92.32 259	82.10 111	97.39 243	84.81 197	80.84 361	94.12 275

testdata				90.49 227	96.40 94	77.89 295		95.37 210	72.51 400	93.63 70	96.69 79	82.08 112	97.65 208	83.08 218	97.39 93	95.94 198

PAPM_NR		91.22 115	90.78 120	92.52 133	97.60 60	81.46 190	94.37 191	96.24 133	86.39 169	87.41 199	94.80 167	82.06 113	98.48 132	82.80 226	95.37 144	97.61 109

MG-MVS		91.77 104	91.70 102	92.00 157	97.08 75	80.03 238	93.60 239	95.18 218	87.85 131	90.89 140	96.47 93	82.06 113	98.36 149	85.07 192	97.04 101	97.62 108

CANet		93.54 62	93.20 76	94.55 43	95.65 132	85.73 66	94.94 146	96.69 95	91.89 10	90.69 142	95.88 119	81.99 115	99.54 20	93.14 62	97.95 77	98.39 40

FC-MVSNet-test		90.27 139	90.18 129	90.53 223	93.71 245	79.85 245	95.77 91	97.59 4	89.31 74	86.27 226	94.67 174	81.93 116	97.01 272	84.26 204	88.09 276	94.71 248

fmvsm_s_conf0.5_n_7		93.15 81	93.76 61	91.31 193	94.42 208	79.48 252	94.52 175	97.14 48	89.33 73	94.17 57	98.09 15	81.83 117	97.49 222	96.33 22	98.02 74	96.95 150

FIs		90.51 136	90.35 124	90.99 211	93.99 232	80.98 207	95.73 94	97.54 6	89.15 81	86.72 215	94.68 171	81.83 117	97.24 254	85.18 191	88.31 273	94.76 247

fmvsm_s_conf0.5_n_8		94.56 24	95.12 12	92.87 110	95.96 120	81.32 194	95.76 93	97.57 5	93.48 2	97.53 7	98.32 1	81.78 119	99.13 55	97.91 1	97.81 82	98.16 69

ACMMP		93.24 76	92.88 82	94.30 54	98.09 39	85.33 73	96.86 28	97.45 16	88.33 110	90.15 154	97.03 66	81.44 120	99.51 24	90.85 121	95.74 133	98.04 80
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
Effi-MVS+		91.59 109	91.11 111	93.01 101	94.35 214	83.39 131	94.60 170	95.10 222	87.10 149	90.57 145	93.10 235	81.43 121	98.07 180	89.29 137	94.48 166	97.59 111

MVS_111021_LR		92.47 94	92.29 94	92.98 103	95.99 117	84.43 97	93.08 265	96.09 147	88.20 117	91.12 137	95.72 129	81.33 122	97.76 199	91.74 104	97.37 94	96.75 161

mvs_anonymous		89.37 171	89.32 152	89.51 276	93.47 254	74.22 348	91.65 312	94.83 241	82.91 258	85.45 251	93.79 212	81.23 123	96.36 316	86.47 175	94.09 172	97.94 85

PVSNet_BlendedMVS		89.98 148	89.70 141	90.82 216	96.12 104	81.25 196	93.92 224	96.83 76	83.49 242	89.10 168	92.26 262	81.04 124	98.85 96	86.72 173	87.86 280	92.35 355

PVSNet_Blended		90.73 126	90.32 125	91.98 158	96.12 104	81.25 196	92.55 284	96.83 76	82.04 276	89.10 168	92.56 252	81.04 124	98.85 96	86.72 173	95.91 129	95.84 203

MVS_0304		94.18 43	93.80 57	95.34 9	94.91 172	87.62 14	95.97 75	93.01 302	92.58 5	94.22 54	97.20 56	80.56 126	99.59 8	97.04 16	98.68 37	98.81 17

alignmvs		93.08 82	92.50 90	94.81 32	95.62 135	87.61 15	95.99 73	96.07 149	89.77 59	94.12 58	94.87 162	80.56 126	98.66 115	92.42 77	93.10 196	98.15 70

API-MVS		90.66 130	90.07 132	92.45 136	96.36 96	84.57 88	96.06 67	95.22 217	82.39 266	89.13 167	94.27 191	80.32 128	98.46 136	80.16 277	96.71 112	94.33 268

PVSNet_Blended_VisFu		91.38 111	90.91 116	92.80 114	96.39 95	83.17 138	94.87 151	96.66 96	83.29 248	89.27 166	94.46 183	80.29 129	99.17 51	87.57 159	95.37 144	96.05 196

test222					96.55 89	81.70 182	92.22 296	95.01 226	68.36 416	90.20 151	96.14 105	80.26 130			97.80 83	96.05 196

diffmvs		91.37 112	91.23 109	91.77 176	93.09 267	80.27 227	92.36 289	95.52 196	87.03 151	91.40 133	94.93 158	80.08 131	97.44 230	92.13 90	94.56 163	97.61 109
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Test By Simon												80.02 132

IterMVS-LS		88.36 199	87.91 193	89.70 266	93.80 241	78.29 285	93.73 233	95.08 224	85.73 185	84.75 272	91.90 280	79.88 133	96.92 278	83.83 210	82.51 333	93.89 285
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 175	88.86 167	89.80 262	91.84 307	78.30 284	93.70 236	95.01 226	85.73 185	87.15 203	95.28 143	79.87 134	97.21 257	83.81 211	87.36 288	93.88 288

TAPA-MVS	84.62 6	88.16 204	87.01 214	91.62 180	96.64 84	80.65 217	94.39 187	96.21 138	76.38 361	86.19 229	95.44 137	79.75 135	98.08 179	62.75 408	95.29 146	96.13 188
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 167	88.64 170	91.71 178	94.74 180	80.81 214	93.54 240	95.10 222	83.11 252	86.82 214	90.67 324	79.74 136	97.75 203	80.51 272	93.55 182	96.57 170

pcd_1.5k_mvsjas		6.64 419	8.86 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	79.70 137	0.00 452	0.00 451	0.00 450	0.00 448

PS-MVSNAJss		89.97 149	89.62 143	91.02 208	91.90 305	80.85 213	95.26 124	95.98 156	86.26 172	86.21 228	94.29 188	79.70 137	97.65 208	88.87 144	88.10 274	94.57 254

PS-MVSNAJ		91.18 116	90.92 115	91.96 160	95.26 151	82.60 165	92.09 301	95.70 181	86.27 171	91.84 121	92.46 254	79.70 137	98.99 75	89.08 139	95.86 130	94.29 269

xiu_mvs_v2_base		91.13 117	90.89 117	91.86 169	94.97 166	82.42 167	92.24 295	95.64 188	86.11 179	91.74 126	93.14 233	79.67 140	98.89 90	89.06 140	95.46 141	94.28 270

WR-MVS_H		87.80 213	87.37 204	89.10 285	93.23 260	78.12 288	95.61 105	97.30 32	87.90 127	83.72 303	92.01 275	79.65 141	96.01 331	76.36 318	80.54 365	93.16 327

EPNet		91.79 103	91.02 114	94.10 59	90.10 371	85.25 74	96.03 70	92.05 329	92.83 4	87.39 202	95.78 125	79.39 142	99.01 68	88.13 151	97.48 91	98.05 79
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 243	86.62 229	89.02 288	92.13 296	77.40 308	90.91 330	94.81 243	81.28 300	84.32 289	90.08 340	79.26 143	96.62 292	83.81 211	82.94 328	93.04 332

test_fmvsmconf0.01_n		93.19 78	93.02 79	93.71 75	89.25 384	84.42 99	96.06 67	96.29 123	89.06 83	94.68 49	98.13 5	79.22 144	98.98 79	97.22 10	97.24 97	97.74 101

miper_enhance_ethall		86.90 255	86.18 246	89.06 286	91.66 316	77.58 306	90.22 346	94.82 242	79.16 327	84.48 280	89.10 359	79.19 145	96.66 289	84.06 206	82.94 328	92.94 335

NR-MVSNet		88.58 194	87.47 202	91.93 163	93.04 271	84.16 106	94.77 160	96.25 132	89.05 84	80.04 358	93.29 227	79.02 146	97.05 270	81.71 252	80.05 371	94.59 252

TAMVS		89.21 173	88.29 183	91.96 160	93.71 245	82.62 164	93.30 254	94.19 267	82.22 271	87.78 193	93.94 204	78.83 147	96.95 276	77.70 304	92.98 198	96.32 177

c3_l		87.14 248	86.50 235	89.04 287	92.20 293	77.26 309	91.22 324	94.70 249	82.01 277	84.34 288	90.43 329	78.81 148	96.61 295	83.70 213	81.09 354	93.25 321

1112_ss		88.42 195	87.33 205	91.72 177	94.92 170	80.98 207	92.97 271	94.54 252	78.16 348	83.82 300	93.88 209	78.78 149	97.91 194	79.45 285	89.41 253	96.26 181

CDS-MVSNet		89.45 165	88.51 174	92.29 148	93.62 250	83.61 125	93.01 268	94.68 250	81.95 278	87.82 192	93.24 229	78.69 150	96.99 273	80.34 274	93.23 194	96.28 180
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 159	88.92 163	91.67 179	95.47 142	81.15 201	92.38 288	94.78 245	83.11 252	89.06 170	94.32 186	78.67 151	96.61 295	81.57 253	90.89 228	97.24 126

CPTT-MVS		91.99 99	91.80 99	92.55 131	98.24 32	81.98 176	96.76 31	96.49 110	81.89 283	90.24 149	96.44 94	78.59 152	98.61 124	89.68 132	97.85 80	97.06 140

IS-MVSNet		91.43 110	91.09 113	92.46 135	95.87 123	81.38 193	96.95 20	93.69 289	89.72 61	89.50 162	95.98 113	78.57 153	97.77 198	83.02 220	96.50 118	98.22 65

OMC-MVS		91.23 114	90.62 122	93.08 97	96.27 98	84.07 107	93.52 241	95.93 160	86.95 153	89.51 160	96.13 106	78.50 154	98.35 151	85.84 186	92.90 199	96.83 159

PCF-MVS	84.11 10	87.74 215	86.08 252	92.70 123	94.02 227	84.43 97	89.27 366	95.87 168	73.62 390	84.43 283	94.33 185	78.48 155	98.86 94	70.27 365	94.45 167	94.81 245
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 201	88.32 182	88.27 310	94.71 185	72.41 374	93.15 260	90.98 360	87.77 134	79.25 367	91.96 277	78.35 156	95.75 345	83.04 219	95.62 135	96.65 166

HY-MVS	83.01 12	89.03 180	87.94 192	92.29 148	94.86 175	82.77 154	92.08 302	94.49 253	81.52 296	86.93 206	92.79 246	78.32 157	98.23 160	79.93 279	90.55 232	95.88 201

GeoE		90.05 146	89.43 148	91.90 168	95.16 156	80.37 226	95.80 88	94.65 251	83.90 230	87.55 198	94.75 168	78.18 158	97.62 212	81.28 257	93.63 180	97.71 104

SymmetryMVS		92.81 88	92.31 92	94.32 53	96.15 101	86.20 48	96.30 42	94.43 255	91.65 14	92.68 97	96.13 106	77.97 159	98.84 98	90.75 122	94.72 156	97.92 88

MVS		87.44 231	86.10 251	91.44 188	92.61 284	83.62 123	92.63 281	95.66 185	67.26 418	81.47 336	92.15 265	77.95 160	98.22 162	79.71 281	95.48 139	92.47 349

MVSFormer		91.68 108	91.30 106	92.80 114	93.86 237	83.88 114	95.96 76	95.90 164	84.66 218	91.76 124	94.91 159	77.92 161	97.30 246	89.64 133	97.11 98	97.24 126

lupinMVS		90.92 120	90.21 127	93.03 100	93.86 237	83.88 114	92.81 277	93.86 281	79.84 318	91.76 124	94.29 188	77.92 161	98.04 182	90.48 127	97.11 98	97.17 130

Test_1112_low_res		87.65 218	86.51 234	91.08 204	94.94 169	79.28 262	91.77 307	94.30 262	76.04 366	83.51 310	92.37 257	77.86 163	97.73 204	78.69 294	89.13 260	96.22 182

VNet		92.24 97	91.91 98	93.24 86	96.59 86	83.43 128	94.84 155	96.44 111	89.19 80	94.08 62	95.90 117	77.85 164	98.17 164	88.90 142	93.38 189	98.13 71

fmvsm_s_conf0.5_n_2		93.47 64	93.83 55	92.39 140	95.36 144	81.19 200	95.20 132	96.56 104	90.37 34	97.13 13	98.03 25	77.47 165	98.96 82	97.79 4	96.58 115	97.03 143

mvsany_test1		85.42 294	85.30 279	85.77 368	87.95 402	75.41 336	87.61 395	80.97 428	76.82 358	88.68 174	95.83 122	77.44 166	90.82 414	85.90 184	86.51 295	91.08 386

DU-MVS		89.34 172	88.50 175	91.85 171	93.04 271	83.72 118	94.47 180	96.59 101	89.50 66	86.46 219	93.29 227	77.25 167	97.23 255	84.92 194	81.02 357	94.59 252

Baseline_NR-MVSNet		87.07 250	86.63 228	88.40 303	91.44 320	77.87 296	94.23 199	92.57 314	84.12 226	85.74 239	92.08 271	77.25 167	96.04 327	82.29 235	79.94 372	91.30 378

jason		90.80 123	90.10 131	92.90 108	93.04 271	83.53 126	93.08 265	94.15 270	80.22 312	91.41 132	94.91 159	76.87 169	97.93 192	90.28 128	96.90 105	97.24 126
jason: jason.
PAPM		86.68 265	85.39 275	90.53 223	93.05 270	79.33 261	89.79 356	94.77 246	78.82 334	81.95 332	93.24 229	76.81 170	97.30 246	66.94 389	93.16 195	94.95 240

Vis-MVSNet (Re-imp)		89.59 160	89.44 147	90.03 249	95.74 126	75.85 330	95.61 105	90.80 367	87.66 139	87.83 191	95.40 140	76.79 171	96.46 309	78.37 295	96.73 111	97.80 97

baseline1		88.10 205	87.28 207	90.57 221	94.96 167	80.07 234	94.27 195	91.29 353	86.74 159	87.41 199	94.00 201	76.77 172	96.20 322	80.77 266	79.31 380	95.44 217

114514_t		89.51 162	88.50 175	92.54 132	98.11 37	81.99 175	95.16 135	96.36 119	70.19 412	85.81 236	95.25 145	76.70 173	98.63 121	82.07 241	96.86 108	97.00 147

PLC	84.53 7	89.06 179	88.03 188	92.15 152	97.27 72	82.69 161	94.29 194	95.44 204	79.71 320	84.01 297	94.18 194	76.68 174	98.75 107	77.28 308	93.41 188	95.02 232
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 184	87.95 191	91.49 185	92.68 283	83.01 149	94.92 148	96.31 122	89.88 49	85.53 245	93.85 211	76.63 175	96.96 275	81.91 245	79.87 374	94.50 260

MAR-MVS		90.30 138	89.37 150	93.07 99	96.61 85	84.48 93	95.68 97	95.67 183	82.36 268	87.85 189	92.85 240	76.63 175	98.80 102	80.01 278	96.68 113	95.91 199
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_conf0.1_n_2		93.16 80	93.42 70	92.37 141	94.62 190	81.13 202	95.23 125	95.89 166	90.30 38	96.74 23	98.02 26	76.14 177	98.95 84	97.64 5	96.21 124	97.03 143

WR-MVS		88.38 197	87.67 197	90.52 225	93.30 259	80.18 229	93.26 257	95.96 159	88.57 105	85.47 250	92.81 244	76.12 178	96.91 279	81.24 258	82.29 337	94.47 265

v8		87.50 230	86.71 222	89.89 256	91.37 325	79.40 255	94.50 176	95.38 208	84.81 213	83.60 308	91.33 296	76.05 179	97.42 232	82.84 224	80.51 368	92.84 339

v148		87.04 251	86.32 241	89.21 281	90.94 345	77.26 309	93.71 235	94.43 255	84.84 212	84.36 287	90.80 318	76.04 180	97.05 270	82.12 238	79.60 377	93.31 318

eth_miper_zixun_eth		86.50 272	85.77 266	88.68 297	91.94 302	75.81 331	90.47 338	94.89 235	82.05 274	84.05 295	90.46 328	75.96 181	96.77 283	82.76 227	79.36 379	93.46 314

3Dnovator+	87.14 4	92.42 95	91.37 105	95.55 7	95.63 134	88.73 6	97.07 19	96.77 84	90.84 21	84.02 296	96.62 87	75.95 182	99.34 38	87.77 156	97.68 88	98.59 24

h-mvs33		90.80 123	90.15 130	92.75 119	96.01 113	82.66 162	95.43 112	95.53 195	89.80 55	93.08 81	95.64 131	75.77 183	99.00 73	92.07 91	78.05 384	96.60 167

hse-mvs2		89.88 154	89.34 151	91.51 184	94.83 177	81.12 203	93.94 222	93.91 280	89.80 55	93.08 81	93.60 218	75.77 183	97.66 207	92.07 91	77.07 391	95.74 208

BH-untuned		88.60 192	88.13 187	90.01 252	95.24 152	78.50 278	93.29 255	94.15 270	84.75 215	84.46 281	93.40 221	75.76 185	97.40 240	77.59 305	94.52 165	94.12 275

DIV-MVS_self_test		86.53 270	85.78 264	88.75 294	92.02 301	76.45 322	90.74 332	94.30 262	81.83 286	83.34 314	90.82 317	75.75 186	96.57 298	81.73 251	81.52 349	93.24 322

BH-w/o		87.57 226	87.05 212	89.12 284	94.90 173	77.90 294	92.41 286	93.51 291	82.89 259	83.70 304	91.34 295	75.75 186	97.07 267	75.49 326	93.49 185	92.39 353

cl____		86.52 271	85.78 264	88.75 294	92.03 300	76.46 321	90.74 332	94.30 262	81.83 286	83.34 314	90.78 319	75.74 188	96.57 298	81.74 250	81.54 348	93.22 323

cdsmvs_eth3d_5k		22.14 414	29.52 417	0.00 433	0.00 456	0.00 458	0.00 444	95.76 175	0.00 451	0.00 452	94.29 188	75.66 189	0.00 452	0.00 451	0.00 450	0.00 448

CNLPA		89.07 178	87.98 190	92.34 143	96.87 78	84.78 83	94.08 210	93.24 295	81.41 297	84.46 281	95.13 154	75.57 190	96.62 292	77.21 309	93.84 177	95.61 215

CHOSEN 1792x2688		88.84 184	87.69 196	92.30 147	96.14 102	81.42 192	90.01 353	95.86 169	74.52 381	87.41 199	93.94 204	75.46 191	98.36 149	80.36 273	95.53 136	97.12 136

CP-MVSNet		87.63 221	87.26 209	88.74 296	93.12 265	76.59 320	95.29 120	96.58 102	88.43 108	83.49 311	92.98 238	75.28 192	95.83 340	78.97 291	81.15 353	93.79 294

v10		87.25 240	86.38 237	89.85 257	91.19 331	79.50 251	94.48 177	95.45 202	83.79 234	83.62 307	91.19 301	75.13 193	97.42 232	81.94 244	80.60 363	92.63 345

Vis-MVSNet		91.75 105	91.23 109	93.29 83	95.32 146	83.78 117	96.14 58	95.98 156	89.89 48	90.45 146	96.58 89	75.09 194	98.31 157	84.75 198	96.90 105	97.78 99
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 183	88.26 185	90.94 214	94.05 226	80.78 215	91.71 309	95.38 208	81.55 295	88.63 175	93.91 208	75.04 195	95.47 358	82.47 230	91.61 216	96.57 170

v1144		87.61 224	86.79 220	90.06 248	91.01 340	79.34 258	93.95 221	95.42 207	83.36 247	85.66 241	91.31 299	74.98 196	97.42 232	83.37 215	82.06 339	93.42 315

miper_lstm_enhance		85.27 299	84.59 296	87.31 336	91.28 329	74.63 343	87.69 392	94.09 274	81.20 304	81.36 339	89.85 348	74.97 197	94.30 376	81.03 262	79.84 375	93.01 333

test_yl		90.69 127	90.02 136	92.71 121	95.72 127	82.41 169	94.11 205	95.12 220	85.63 188	91.49 130	94.70 169	74.75 198	98.42 145	86.13 181	92.53 208	97.31 121

DCV-MVSNet		90.69 127	90.02 136	92.71 121	95.72 127	82.41 169	94.11 205	95.12 220	85.63 188	91.49 130	94.70 169	74.75 198	98.42 145	86.13 181	92.53 208	97.31 121

V42		87.68 216	86.86 216	90.15 242	90.58 361	80.14 231	94.24 198	95.28 213	83.66 236	85.67 240	91.33 296	74.73 200	97.41 238	84.43 203	81.83 343	92.89 337

FA-MVS(test-final)		89.66 157	88.91 164	91.93 163	94.57 196	80.27 227	91.36 317	94.74 247	84.87 210	89.82 157	92.61 251	74.72 201	98.47 135	83.97 208	93.53 183	97.04 142

XVG-OURS-SEG-HR		89.95 150	89.45 146	91.47 187	94.00 231	81.21 199	91.87 305	96.06 151	85.78 183	88.55 176	95.73 128	74.67 202	97.27 250	88.71 145	89.64 251	95.91 199

BP-MVS1		92.48 93	92.07 96	93.72 74	94.50 201	84.39 100	95.90 81	94.30 262	90.39 33	92.67 98	95.94 115	74.46 203	98.65 117	93.14 62	97.35 95	98.13 71

v2v482		87.84 211	87.06 211	90.17 240	90.99 341	79.23 265	94.00 219	95.13 219	84.87 210	85.53 245	92.07 273	74.45 204	97.45 227	84.71 199	81.75 345	93.85 292

CLD-MVS		89.47 164	88.90 165	91.18 199	94.22 218	82.07 174	92.13 299	96.09 147	87.90 127	85.37 260	92.45 255	74.38 205	97.56 216	87.15 166	90.43 234	93.93 284
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 218	86.85 217	90.03 249	92.14 295	80.60 220	93.76 232	95.23 215	82.94 257	84.60 275	94.02 199	74.27 206	95.49 357	81.04 260	83.68 319	94.01 283

HQP_MVS		90.60 134	90.19 128	91.82 173	94.70 186	82.73 158	95.85 85	96.22 135	90.81 22	86.91 208	94.86 163	74.23 207	98.12 167	88.15 149	89.99 240	94.63 249

plane_prior6					94.52 199	82.75 155						74.23 207

v144192		87.19 246	86.35 239	89.74 263	90.64 359	78.24 286	93.92 224	95.43 205	81.93 279	85.51 247	91.05 310	74.21 209	97.45 227	82.86 223	81.56 347	93.53 309

VPA-MVSNet		89.62 158	88.96 161	91.60 181	93.86 237	82.89 153	95.46 110	97.33 28	87.91 126	88.43 179	93.31 225	74.17 210	97.40 240	87.32 164	82.86 332	94.52 257

ab-mvs		89.41 167	88.35 179	92.60 127	95.15 158	82.65 163	92.20 297	95.60 190	83.97 229	88.55 176	93.70 217	74.16 211	98.21 163	82.46 231	89.37 254	96.94 151

1314		87.51 228	86.57 231	90.34 237	92.42 289	79.74 248	92.63 281	95.35 212	78.35 343	80.14 355	91.62 290	74.05 212	97.15 259	81.05 259	93.53 183	94.12 275

test_djsdf		89.03 180	88.64 170	90.21 239	90.74 356	79.28 262	95.96 76	95.90 164	84.66 218	85.33 262	92.94 239	74.02 213	97.30 246	89.64 133	88.53 266	94.05 281

cl22		86.78 259	85.98 256	89.18 283	92.34 290	77.62 305	90.84 331	94.13 272	81.33 299	83.97 298	90.15 337	73.96 214	96.60 297	84.19 205	82.94 328	93.33 317

AdaColmap		89.89 153	89.07 159	92.37 141	97.41 66	83.03 147	94.42 184	95.92 161	82.81 260	86.34 225	94.65 176	73.89 215	99.02 66	80.69 268	95.51 137	95.05 231

HyFIR lowres test		88.09 206	86.81 218	91.93 163	96.00 114	80.63 218	90.01 353	95.79 173	73.42 392	87.68 195	92.10 270	73.86 216	97.96 188	80.75 267	91.70 215	97.19 129

HQP2-MVS												73.83 217

HQP-MVS		89.80 155	89.28 154	91.34 192	94.17 220	81.56 184	94.39 187	96.04 152	88.81 93	85.43 254	93.97 203	73.83 217	97.96 188	87.11 168	89.77 249	94.50 260

3Dnovator	86.66 5	91.73 106	90.82 119	94.44 45	94.59 192	86.37 41	97.18 13	97.02 56	89.20 79	84.31 291	96.66 82	73.74 219	99.17 51	86.74 171	97.96 76	97.79 98

EPNet_dtu		86.49 274	85.94 259	88.14 315	90.24 369	72.82 364	94.11 205	92.20 325	86.66 163	79.42 366	92.36 258	73.52 220	95.81 342	71.26 357	93.66 179	95.80 206
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 315	83.06 322	88.54 300	91.72 312	78.44 279	95.18 133	92.82 308	82.73 262	79.67 363	92.12 267	73.49 221	95.96 333	71.10 362	68.73 415	91.21 380

Effi-MVS+-dtu		88.65 190	88.35 179	89.54 273	93.33 258	76.39 323	94.47 180	94.36 260	87.70 136	85.43 254	89.56 354	73.45 222	97.26 252	85.57 189	91.28 220	94.97 233

GDP-MVS		92.04 98	91.46 104	93.75 73	94.55 198	84.69 85	95.60 108	96.56 104	87.83 132	93.07 83	95.89 118	73.44 223	98.65 117	90.22 129	96.03 128	97.91 90

baseline2		86.50 272	85.39 275	89.84 258	91.12 336	76.70 318	91.88 304	88.58 398	82.35 269	79.95 359	90.95 312	73.42 224	97.63 211	80.27 276	89.95 243	95.19 226

PEN-MVS		86.80 258	86.27 244	88.40 303	92.32 291	75.71 333	95.18 133	96.38 117	87.97 124	82.82 320	93.15 232	73.39 225	95.92 335	76.15 322	79.03 382	93.59 307

v1192		87.25 240	86.33 240	90.00 253	90.76 355	79.04 266	93.80 230	95.48 197	82.57 264	85.48 249	91.18 303	73.38 226	97.42 232	82.30 234	82.06 339	93.53 309

guyue		91.12 118	90.84 118	91.96 160	94.59 192	80.57 221	94.87 151	93.71 288	88.96 90	91.14 136	95.22 146	73.22 227	97.76 199	92.01 95	93.81 178	97.54 115

QAPM		89.51 162	88.15 186	93.59 78	94.92 170	84.58 87	96.82 30	96.70 94	78.43 342	83.41 312	96.19 103	73.18 228	99.30 44	77.11 311	96.54 116	96.89 155

tpmrst		85.35 296	84.99 285	86.43 359	90.88 350	67.88 407	88.71 375	91.43 350	80.13 314	86.08 231	88.80 367	73.05 229	96.02 329	82.48 229	83.40 325	95.40 219

PS-CasMVS		87.32 237	86.88 215	88.63 299	92.99 274	76.33 325	95.33 115	96.61 100	88.22 116	83.30 316	93.07 236	73.03 230	95.79 344	78.36 296	81.00 359	93.75 301

DTE-MVSNet		86.11 280	85.48 273	87.98 318	91.65 317	74.92 340	94.93 147	95.75 176	87.36 144	82.26 326	93.04 237	72.85 231	95.82 341	74.04 341	77.46 388	93.20 325

MVSTER		88.84 184	88.29 183	90.51 226	92.95 276	80.44 224	93.73 233	95.01 226	84.66 218	87.15 203	93.12 234	72.79 232	97.21 257	87.86 155	87.36 288	93.87 289

v1921920		86.97 253	86.06 253	89.69 267	90.53 364	78.11 289	93.80 230	95.43 205	81.90 281	85.33 262	91.05 310	72.66 233	97.41 238	82.05 242	81.80 344	93.53 309

DP-MVS		87.25 240	85.36 277	92.90 108	97.65 59	83.24 135	94.81 157	92.00 331	74.99 376	81.92 333	95.00 157	72.66 233	99.05 60	66.92 391	92.33 211	96.40 174

VortexMVS		88.42 195	88.01 189	89.63 270	93.89 236	78.82 268	93.82 229	95.47 198	86.67 162	84.53 279	91.99 276	72.62 235	96.65 290	89.02 141	84.09 313	93.41 316

v7n		86.81 257	85.76 267	89.95 254	90.72 357	79.25 264	95.07 139	95.92 161	84.45 221	82.29 325	90.86 314	72.60 236	97.53 218	79.42 288	80.52 367	93.08 331

OPM-MVS		90.12 142	89.56 145	91.82 173	93.14 264	83.90 113	94.16 201	95.74 177	88.96 90	87.86 188	95.43 139	72.48 237	97.91 194	88.10 153	90.18 239	93.65 306
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 210	86.32 241	92.59 128	96.07 111	82.92 152	95.23 125	94.92 234	75.66 368	82.89 319	95.98 113	72.48 237	99.21 49	68.43 379	95.23 149	95.64 212

pm-mvs1		86.61 266	85.54 271	89.82 259	91.44 320	80.18 229	95.28 122	94.85 239	83.84 232	81.66 334	92.62 250	72.45 239	96.48 306	79.67 282	78.06 383	92.82 340

KinetiMVS		91.82 102	91.30 106	93.39 80	94.72 183	83.36 132	95.45 111	96.37 118	90.33 35	92.17 109	96.03 110	72.32 240	98.75 107	87.94 154	96.34 121	98.07 76

PMMVS		85.71 289	84.96 287	87.95 319	88.90 388	77.09 311	88.68 376	90.06 381	72.32 402	86.47 218	90.76 320	72.15 241	94.40 373	81.78 249	93.49 185	92.36 354

SDMVSNet		90.19 141	89.61 144	91.93 163	96.00 114	83.09 144	92.89 274	95.98 156	88.73 97	86.85 212	95.20 150	72.09 242	97.08 265	88.90 142	89.85 246	95.63 213

PatchmatchNet		85.85 285	84.70 293	89.29 280	91.76 311	75.54 334	88.49 378	91.30 352	81.63 292	85.05 267	88.70 369	71.71 243	96.24 321	74.61 338	89.05 261	96.08 192
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 244				96.12 189

patchmatchnet-post											83.76 412	71.53 245	96.48 306

v1240		86.78 259	85.85 262	89.56 272	90.45 366	77.79 300	93.61 238	95.37 210	81.65 290	85.43 254	91.15 305	71.50 246	97.43 231	81.47 255	82.05 341	93.47 313

anonymousdsp		87.84 211	87.09 210	90.12 244	89.13 385	80.54 222	94.67 167	95.55 192	82.05 274	83.82 300	92.12 267	71.47 247	97.15 259	87.15 166	87.80 283	92.67 343

Patchmatch-test		81.37 349	79.30 356	87.58 328	90.92 347	74.16 350	80.99 428	87.68 405	70.52 410	76.63 387	88.81 365	71.21 248	92.76 398	60.01 416	86.93 294	95.83 204

F-COLMAP		87.95 209	86.80 219	91.40 189	96.35 97	80.88 212	94.73 163	95.45 202	79.65 321	82.04 331	94.61 177	71.13 249	98.50 130	76.24 321	91.05 226	94.80 246

pmmvs4		85.43 293	83.86 309	90.16 241	90.02 374	82.97 151	90.27 340	92.67 312	75.93 367	80.73 346	91.74 284	71.05 250	95.73 347	78.85 293	83.46 323	91.78 365

CR-MVSNet		85.35 296	83.76 310	90.12 244	90.58 361	79.34 258	85.24 411	91.96 335	78.27 345	85.55 243	87.87 382	71.03 251	95.61 350	73.96 343	89.36 255	95.40 219

Patchmtry		82.71 332	80.93 338	88.06 316	90.05 373	76.37 324	84.74 416	91.96 335	72.28 403	81.32 340	87.87 382	71.03 251	95.50 356	68.97 375	80.15 370	92.32 356

CL-MVSNet_self_test		81.74 341	80.53 339	85.36 372	85.96 411	72.45 373	90.25 342	93.07 300	81.24 302	79.85 362	87.29 388	70.93 253	92.52 399	66.95 388	69.23 411	91.11 384

RPMNet		83.95 322	81.53 333	91.21 197	90.58 361	79.34 258	85.24 411	96.76 85	71.44 406	85.55 243	82.97 418	70.87 254	98.91 89	61.01 412	89.36 255	95.40 219

Patchmatch-RL test		81.67 342	79.96 348	86.81 353	85.42 416	71.23 385	82.17 426	87.50 406	78.47 340	77.19 382	82.50 420	70.81 255	93.48 389	82.66 228	72.89 401	95.71 211

CostFormer		85.77 288	84.94 288	88.26 311	91.16 334	72.58 372	89.47 364	91.04 359	76.26 364	86.45 221	89.97 344	70.74 256	96.86 282	82.35 233	87.07 293	95.34 223

AstraMVS		90.69 127	90.30 126	91.84 172	93.81 240	79.85 245	94.76 161	92.39 317	88.96 90	91.01 139	95.87 120	70.69 257	97.94 191	92.49 74	92.70 204	97.73 102

sam_mvs												70.60 258

xiu_mvs_v1_base_debu		90.64 131	90.05 133	92.40 137	93.97 233	84.46 94	93.32 250	95.46 199	85.17 197	92.25 106	94.03 196	70.59 259	98.57 127	90.97 115	94.67 158	94.18 271

xiu_mvs_v1_base		90.64 131	90.05 133	92.40 137	93.97 233	84.46 94	93.32 250	95.46 199	85.17 197	92.25 106	94.03 196	70.59 259	98.57 127	90.97 115	94.67 158	94.18 271

xiu_mvs_v1_base_debi		90.64 131	90.05 133	92.40 137	93.97 233	84.46 94	93.32 250	95.46 199	85.17 197	92.25 106	94.03 196	70.59 259	98.57 127	90.97 115	94.67 158	94.18 271

test_post											10.29 446	70.57 262	95.91 337

CANet_DTU		90.26 140	89.41 149	92.81 113	93.46 255	83.01 149	93.48 242	94.47 254	89.43 69	87.76 194	94.23 193	70.54 263	99.03 63	84.97 193	96.39 120	96.38 175

BH-RMVSNet		88.37 198	87.48 201	91.02 208	95.28 148	79.45 254	92.89 274	93.07 300	85.45 193	86.91 208	94.84 166	70.35 264	97.76 199	73.97 342	94.59 162	95.85 202

Fast-Effi-MVS+-dtu		87.44 231	86.72 221	89.63 270	92.04 299	77.68 304	94.03 215	93.94 276	85.81 182	82.42 324	91.32 298	70.33 265	97.06 268	80.33 275	90.23 238	94.14 274

MDTV_nov1_ep13_2view						55.91 440	87.62 394		73.32 393	84.59 276		70.33 265		74.65 337		95.50 216

ACMM	84.12 9	89.14 174	88.48 178	91.12 200	94.65 189	81.22 198	95.31 116	96.12 144	85.31 196	85.92 234	94.34 184	70.19 267	98.06 181	85.65 187	88.86 263	94.08 279
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RRT-MVS		90.85 122	90.70 121	91.30 194	94.25 216	76.83 315	94.85 154	96.13 143	89.04 85	90.23 150	94.88 161	70.15 268	98.72 111	91.86 103	94.88 153	98.34 43

LuminaMVS		90.55 135	89.81 140	92.77 116	92.78 280	84.21 104	94.09 209	94.17 269	85.82 181	91.54 129	94.14 195	69.93 269	97.92 193	91.62 107	94.21 171	96.18 185

ET-MVSNet_ETH3D		87.51 228	85.91 260	92.32 145	93.70 247	83.93 112	92.33 292	90.94 363	84.16 224	72.09 411	92.52 253	69.90 270	95.85 339	89.20 138	88.36 272	97.17 130

LPG-MVS_test		89.45 165	88.90 165	91.12 200	94.47 202	81.49 188	95.30 118	96.14 140	86.73 160	85.45 251	95.16 152	69.89 271	98.10 169	87.70 157	89.23 258	93.77 299

LGP-MVS_train				91.12 200	94.47 202	81.49 188		96.14 140	86.73 160	85.45 251	95.16 152	69.89 271	98.10 169	87.70 157	89.23 258	93.77 299

CHOSEN 280x420		85.15 301	83.99 307	88.65 298	92.47 286	78.40 281	79.68 433	92.76 309	74.90 378	81.41 338	89.59 352	69.85 273	95.51 354	79.92 280	95.29 146	92.03 361

LTVRE_ROB	82.13 13	86.26 279	84.90 289	90.34 237	94.44 206	81.50 186	92.31 294	94.89 235	83.03 254	79.63 364	92.67 248	69.69 274	97.79 197	71.20 358	86.26 297	91.72 366
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	83.78 11	88.74 188	87.29 206	93.08 97	92.70 282	85.39 72	96.57 36	96.43 112	78.74 337	80.85 344	96.07 108	69.64 275	99.01 68	78.01 302	96.65 114	94.83 244

MonoMVSNet		86.89 256	86.55 232	87.92 321	89.46 383	73.75 352	94.12 203	93.10 298	87.82 133	85.10 265	90.76 320	69.59 276	94.94 369	86.47 175	82.50 334	95.07 230

MDTV_nov1_ep13			83.56 313		91.69 315	69.93 398	87.75 391	91.54 346	78.60 339	84.86 270	88.90 364	69.54 277	96.03 328	70.25 366	88.93 262

AUN-MVS		87.78 214	86.54 233	91.48 186	94.82 178	81.05 205	93.91 226	93.93 277	83.00 255	86.93 206	93.53 219	69.50 278	97.67 205	86.14 179	77.12 390	95.73 210

PatchT		82.68 333	81.27 335	86.89 351	90.09 372	70.94 391	84.06 418	90.15 378	74.91 377	85.63 242	83.57 413	69.37 279	94.87 370	65.19 397	88.50 268	94.84 243

VPNet		88.20 203	87.47 202	90.39 233	93.56 252	79.46 253	94.04 214	95.54 194	88.67 100	86.96 205	94.58 181	69.33 280	97.15 259	84.05 207	80.53 366	94.56 255

ACMP	84.23 8	89.01 182	88.35 179	90.99 211	94.73 181	81.27 195	95.07 139	95.89 166	86.48 165	83.67 305	94.30 187	69.33 280	97.99 186	87.10 170	88.55 265	93.72 304
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 386				9.81 447	69.31 282	95.53 352	76.65 314

tpmvs		83.35 330	82.07 329	87.20 343	91.07 338	71.00 390	88.31 381	91.70 339	78.91 329	80.49 351	87.18 391	69.30 283	97.08 265	68.12 383	83.56 321	93.51 312

mvsmamba		90.33 137	89.69 142	92.25 151	95.17 155	81.64 183	95.27 123	93.36 294	84.88 209	89.51 160	94.27 191	69.29 284	97.42 232	89.34 136	96.12 127	97.68 105

thres200		87.21 244	86.24 245	90.12 244	95.36 144	78.53 276	93.26 257	92.10 327	86.42 168	88.00 187	91.11 307	69.24 285	98.00 185	69.58 373	91.04 227	93.83 293

tfpn200view9		87.58 225	86.64 226	90.41 232	95.99 117	78.64 272	94.58 171	91.98 333	86.94 154	88.09 182	91.77 282	69.18 286	98.10 169	70.13 369	91.10 221	94.48 263

thres400		87.62 223	86.64 226	90.57 221	95.99 117	78.64 272	94.58 171	91.98 333	86.94 154	88.09 182	91.77 282	69.18 286	98.10 169	70.13 369	91.10 221	94.96 236

WB-MVSnew		83.77 325	83.28 316	85.26 375	91.48 319	71.03 388	91.89 303	87.98 401	78.91 329	84.78 271	90.22 333	69.11 288	94.02 380	64.70 401	90.44 233	90.71 388

tfpnnormal		84.72 311	83.23 318	89.20 282	92.79 279	80.05 236	94.48 177	95.81 171	82.38 267	81.08 342	91.21 300	69.01 289	96.95 276	61.69 410	80.59 364	90.58 393

thres100view900		87.63 221	86.71 222	90.38 235	96.12 104	78.55 275	95.03 142	91.58 344	87.15 147	88.06 185	92.29 261	68.91 290	98.10 169	70.13 369	91.10 221	94.48 263

thres600view7		87.65 218	86.67 225	90.59 220	96.08 110	78.72 269	94.88 150	91.58 344	87.06 150	88.08 184	92.30 260	68.91 290	98.10 169	70.05 372	91.10 221	94.96 236

PatchMatch-RL		86.77 262	85.54 271	90.47 231	95.88 121	82.71 160	90.54 337	92.31 321	79.82 319	84.32 289	91.57 294	68.77 292	96.39 313	73.16 348	93.48 187	92.32 356

XVG-OURS		89.40 169	88.70 169	91.52 183	94.06 225	81.46 190	91.27 321	96.07 149	86.14 176	88.89 172	95.77 126	68.73 293	97.26 252	87.39 162	89.96 242	95.83 204

TR-MVS		86.78 259	85.76 267	89.82 259	94.37 210	78.41 280	92.47 285	92.83 306	81.11 305	86.36 223	92.40 256	68.73 293	97.48 223	73.75 346	89.85 246	93.57 308

tpm		84.73 310	84.02 306	86.87 352	90.33 367	68.90 402	89.06 371	89.94 384	80.85 307	85.75 238	89.86 347	68.54 295	95.97 332	77.76 303	84.05 314	95.75 207

FMVSNet3		87.40 233	86.11 250	91.30 194	93.79 243	83.64 122	94.20 200	94.81 243	83.89 231	84.37 284	91.87 281	68.45 296	96.56 300	78.23 299	85.36 302	93.70 305

MVP-Stereo		85.97 282	84.86 290	89.32 279	90.92 347	82.19 172	92.11 300	94.19 267	78.76 336	78.77 372	91.63 289	68.38 297	96.56 300	75.01 333	93.95 174	89.20 406
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 337	80.27 343	87.01 346	91.09 337	71.02 389	87.38 396	91.53 347	66.25 420	80.17 353	86.35 400	68.22 298	96.15 325	69.16 374	82.29 337	93.86 291

dmvs_testset		74.57 387	75.81 385	70.86 413	87.72 404	40.47 448	87.05 399	77.90 438	82.75 261	71.15 416	85.47 406	67.98 299	84.12 435	45.26 432	76.98 392	88.00 416

sd_testset		88.59 193	87.85 194	90.83 215	96.00 114	80.42 225	92.35 290	94.71 248	88.73 97	86.85 212	95.20 150	67.31 300	96.43 311	79.64 283	89.85 246	95.63 213

tpm2		84.08 319	82.94 323	87.48 332	91.39 324	71.27 384	89.23 368	90.37 373	71.95 404	84.64 274	89.33 356	67.30 301	96.55 302	75.17 330	87.09 292	94.63 249

test-LLR		85.87 284	85.41 274	87.25 339	90.95 343	71.67 381	89.55 360	89.88 387	83.41 244	84.54 277	87.95 379	67.25 302	95.11 365	81.82 247	93.37 190	94.97 233

test0.0.03 1		82.41 335	81.69 331	84.59 379	88.23 396	72.89 363	90.24 344	87.83 403	83.41 244	79.86 361	89.78 349	67.25 302	88.99 424	65.18 398	83.42 324	91.90 364

CVMVSNet		84.69 312	84.79 292	84.37 381	91.84 307	64.92 419	93.70 236	91.47 349	66.19 421	86.16 230	95.28 143	67.18 304	93.33 391	80.89 265	90.42 235	94.88 242

thisisatest0515		87.33 236	85.99 255	91.37 191	93.49 253	79.55 250	90.63 335	89.56 394	80.17 313	87.56 197	90.86 314	67.07 305	98.28 158	81.50 254	93.02 197	96.29 179

tttt0517		88.61 191	87.78 195	91.11 203	94.96 167	77.81 298	95.35 114	89.69 389	85.09 204	88.05 186	94.59 180	66.93 306	98.48 132	83.27 217	92.13 213	97.03 143

our_test_3		81.93 338	80.46 341	86.33 361	88.46 393	73.48 357	88.46 379	91.11 355	76.46 359	76.69 386	88.25 375	66.89 307	94.36 374	68.75 376	79.08 381	91.14 382

thisisatest0530		88.67 189	87.61 198	91.86 169	94.87 174	80.07 234	94.63 169	89.90 386	84.00 228	88.46 178	93.78 213	66.88 308	98.46 136	83.30 216	92.65 205	97.06 140

IterMVS-SCA-FT		85.45 292	84.53 298	88.18 314	91.71 313	76.87 314	90.19 348	92.65 313	85.40 194	81.44 337	90.54 325	66.79 309	95.00 368	81.04 260	81.05 355	92.66 344

SCA		86.32 278	85.18 282	89.73 265	92.15 294	76.60 319	91.12 325	91.69 340	83.53 241	85.50 248	88.81 365	66.79 309	96.48 306	76.65 314	90.35 236	96.12 189

D2MVS		85.90 283	85.09 284	88.35 305	90.79 352	77.42 307	91.83 306	95.70 181	80.77 308	80.08 357	90.02 342	66.74 311	96.37 314	81.88 246	87.97 278	91.26 379

IterMVS		84.88 307	83.98 308	87.60 327	91.44 320	76.03 327	90.18 349	92.41 316	83.24 250	81.06 343	90.42 330	66.60 312	94.28 377	79.46 284	80.98 360	92.48 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 238	85.98 256	91.08 204	94.01 228	83.10 141	95.14 136	94.94 229	83.57 238	84.37 284	91.64 286	66.59 313	96.34 317	78.23 299	85.36 302	93.79 294

test1		87.26 238	85.98 256	91.08 204	94.01 228	83.10 141	95.14 136	94.94 229	83.57 238	84.37 284	91.64 286	66.59 313	96.34 317	78.23 299	85.36 302	93.79 294

FMVSNet2		87.19 246	85.82 263	91.30 194	94.01 228	83.67 120	94.79 158	94.94 229	83.57 238	83.88 299	92.05 274	66.59 313	96.51 304	77.56 306	85.01 305	93.73 303

EPMVS		83.90 324	82.70 328	87.51 329	90.23 370	72.67 367	88.62 377	81.96 426	81.37 298	85.01 268	88.34 373	66.31 316	94.45 371	75.30 329	87.12 291	95.43 218

Syy-MVS		80.07 363	79.78 349	80.94 398	91.92 303	59.93 430	89.75 358	87.40 407	81.72 288	78.82 369	87.20 389	66.29 317	91.29 410	47.06 431	87.84 281	91.60 369

ppachtmachnet_test		81.84 339	80.07 347	87.15 344	88.46 393	74.43 347	89.04 372	92.16 326	75.33 372	77.75 378	88.99 362	66.20 318	95.37 360	65.12 399	77.60 386	91.65 367

MDA-MVSNet_test_wron		79.21 373	77.19 375	85.29 373	88.22 397	72.77 365	85.87 405	90.06 381	74.34 382	62.62 427	87.56 385	66.14 319	91.99 405	66.90 392	73.01 399	91.10 385

YYNet1		79.22 372	77.20 374	85.28 374	88.20 398	72.66 368	85.87 405	90.05 383	74.33 383	62.70 425	87.61 384	66.09 320	92.03 403	66.94 389	72.97 400	91.15 381

JIA-IIPM		81.04 352	78.98 364	87.25 339	88.64 389	73.48 357	81.75 427	89.61 393	73.19 394	82.05 330	73.71 430	66.07 321	95.87 338	71.18 360	84.60 308	92.41 352

MSDG		84.86 308	83.09 320	90.14 243	93.80 241	80.05 236	89.18 369	93.09 299	78.89 331	78.19 373	91.91 279	65.86 322	97.27 250	68.47 378	88.45 269	93.11 329

FE-MVS		87.40 233	86.02 254	91.57 182	94.56 197	79.69 249	90.27 340	93.72 287	80.57 309	88.80 173	91.62 290	65.32 323	98.59 126	74.97 334	94.33 170	96.44 173

jajsoiax		88.24 202	87.50 200	90.48 228	90.89 349	80.14 231	95.31 116	95.65 187	84.97 207	84.24 292	94.02 199	65.31 324	97.42 232	88.56 146	88.52 267	93.89 285

cascas		86.43 276	84.98 286	90.80 217	92.10 298	80.92 211	90.24 344	95.91 163	73.10 395	83.57 309	88.39 372	65.15 325	97.46 226	84.90 196	91.43 218	94.03 282

ADS-MVSNet2		81.66 343	79.71 352	87.50 330	91.35 326	74.19 349	83.33 421	88.48 399	72.90 397	82.24 327	85.77 404	64.98 326	93.20 394	64.57 402	83.74 317	95.12 228

ADS-MVSNet		81.56 345	79.78 349	86.90 350	91.35 326	71.82 377	83.33 421	89.16 397	72.90 397	82.24 327	85.77 404	64.98 326	93.76 385	64.57 402	83.74 317	95.12 228

Elysia		90.12 142	89.10 157	93.18 89	93.16 262	84.05 109	95.22 127	96.27 127	85.16 200	90.59 143	94.68 171	64.64 328	98.37 147	86.38 177	95.77 131	97.12 136

StellarMVS		90.12 142	89.10 157	93.18 89	93.16 262	84.05 109	95.22 127	96.27 127	85.16 200	90.59 143	94.68 171	64.64 328	98.37 147	86.38 177	95.77 131	97.12 136

pmmvs5		84.21 317	82.84 327	88.34 307	88.95 387	76.94 313	92.41 286	91.91 337	75.63 369	80.28 352	91.18 303	64.59 330	95.57 351	77.09 312	83.47 322	92.53 347

PVSNet	78.82 18	85.55 290	84.65 294	88.23 313	94.72 183	71.93 375	87.12 398	92.75 310	78.80 335	84.95 269	90.53 326	64.43 331	96.71 287	74.74 336	93.86 176	96.06 195

dmvs_re		84.20 318	83.22 319	87.14 345	91.83 309	77.81 298	90.04 352	90.19 377	84.70 217	81.49 335	89.17 358	64.37 332	91.13 412	71.58 356	85.65 301	92.46 350

UGNet		89.95 150	88.95 162	92.95 106	94.51 200	83.31 133	95.70 96	95.23 215	89.37 71	87.58 196	93.94 204	64.00 333	98.78 105	83.92 209	96.31 122	96.74 162
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
WB-MVS		67.92 395	67.49 397	69.21 417	81.09 428	41.17 447	88.03 385	78.00 437	73.50 391	62.63 426	83.11 417	63.94 334	86.52 428	25.66 443	51.45 435	79.94 428

RPSCF		85.07 302	84.27 299	87.48 332	92.91 277	70.62 394	91.69 311	92.46 315	76.20 365	82.67 322	95.22 146	63.94 334	97.29 249	77.51 307	85.80 299	94.53 256

mvs_tets		88.06 208	87.28 207	90.38 235	90.94 345	79.88 243	95.22 127	95.66 185	85.10 203	84.21 293	93.94 204	63.53 336	97.40 240	88.50 147	88.40 271	93.87 289

SSC-MVS		67.06 396	66.56 398	68.56 419	80.54 429	40.06 449	87.77 390	77.37 440	72.38 401	61.75 428	82.66 419	63.37 337	86.45 429	24.48 444	48.69 438	79.16 430

test1111		89.10 175	88.64 170	90.48 228	95.53 140	74.97 339	96.08 63	84.89 418	88.13 120	90.16 153	96.65 83	63.29 338	98.10 169	86.14 179	96.90 105	98.39 40

Anonymous20231211		86.59 268	85.13 283	90.98 213	96.52 92	81.50 186	96.14 58	96.16 139	73.78 388	83.65 306	92.15 265	63.26 339	97.37 244	82.82 225	81.74 346	94.06 280

ECVR-MVS		89.09 177	88.53 173	90.77 218	95.62 135	75.89 329	96.16 54	84.22 420	87.89 129	90.20 151	96.65 83	63.19 340	98.10 169	85.90 184	96.94 103	98.33 45

SSC-MVS3.2		84.60 313	84.19 300	85.85 367	92.74 281	68.07 404	88.15 383	93.81 284	87.42 143	83.76 302	91.07 309	62.91 341	95.73 347	74.56 339	83.24 326	93.75 301

dp		81.47 348	80.23 344	85.17 376	89.92 376	65.49 416	86.74 400	90.10 380	76.30 363	81.10 341	87.12 392	62.81 342	95.92 335	68.13 382	79.88 373	94.09 278

LFMVS		90.08 145	89.13 156	92.95 106	96.71 81	82.32 171	96.08 63	89.91 385	86.79 157	92.15 111	96.81 76	62.60 343	98.34 152	87.18 165	93.90 175	98.19 66

Anonymous20231206		81.03 353	79.77 351	84.82 378	87.85 403	70.26 396	91.42 316	92.08 328	73.67 389	77.75 378	89.25 357	62.43 344	93.08 395	61.50 411	82.00 342	91.12 383

VDD-MVS		90.74 125	89.92 138	93.20 88	96.27 98	83.02 148	95.73 94	93.86 281	88.42 109	92.53 101	96.84 73	62.09 345	98.64 119	90.95 118	92.62 206	97.93 87

MS-PatchMatch		85.05 303	84.16 302	87.73 324	91.42 323	78.51 277	91.25 322	93.53 290	77.50 351	80.15 354	91.58 292	61.99 346	95.51 354	75.69 325	94.35 169	89.16 407

OurMVSNet-221017-0		85.35 296	84.64 295	87.49 331	90.77 354	72.59 371	94.01 217	94.40 258	84.72 216	79.62 365	93.17 231	61.91 347	96.72 285	81.99 243	81.16 351	93.16 327

WBMVS		84.97 306	84.18 301	87.34 335	94.14 224	71.62 383	90.20 347	92.35 318	81.61 293	84.06 294	90.76 320	61.82 348	96.52 303	78.93 292	83.81 315	93.89 285

test_vis1_n_1920		89.39 170	89.84 139	88.04 317	92.97 275	72.64 369	94.71 165	96.03 154	86.18 174	91.94 118	96.56 91	61.63 349	95.74 346	93.42 57	95.11 150	95.74 208

test20.03		79.95 365	79.08 362	82.55 391	85.79 413	67.74 409	91.09 326	91.08 356	81.23 303	74.48 403	89.96 345	61.63 349	90.15 416	60.08 414	76.38 393	89.76 398

mmtdpeth		85.04 305	84.15 303	87.72 325	93.11 266	75.74 332	94.37 191	92.83 306	84.98 206	89.31 165	86.41 398	61.61 351	97.14 262	92.63 73	62.11 426	90.29 394

DSMNet-mixed		76.94 382	76.29 381	78.89 403	83.10 424	56.11 439	87.78 389	79.77 430	60.65 429	75.64 395	88.71 368	61.56 352	88.34 425	60.07 415	89.29 257	92.21 359

Anonymous20240529		88.09 206	86.59 230	92.58 129	96.53 91	81.92 179	95.99 73	95.84 170	74.11 385	89.06 170	95.21 149	61.44 353	98.81 101	83.67 214	87.47 285	97.01 146

UBG		85.51 291	84.57 297	88.35 305	94.21 219	71.78 379	90.07 351	89.66 391	82.28 270	85.91 235	89.01 361	61.30 354	97.06 268	76.58 317	92.06 214	96.22 182

IB-MVS	80.51 15	85.24 300	83.26 317	91.19 198	92.13 296	79.86 244	91.75 308	91.29 353	83.28 249	80.66 348	88.49 371	61.28 355	98.46 136	80.99 263	79.46 378	95.25 225
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
GA-MVS		86.61 266	85.27 280	90.66 219	91.33 328	78.71 271	90.40 339	93.81 284	85.34 195	85.12 264	89.57 353	61.25 356	97.11 264	80.99 263	89.59 252	96.15 186

N_pmnet		68.89 394	68.44 396	70.23 414	89.07 386	28.79 453	88.06 384	19.50 453	69.47 413	71.86 413	84.93 407	61.24 357	91.75 407	54.70 425	77.15 389	90.15 395

EU-MVSNet		81.32 350	80.95 337	82.42 394	88.50 392	63.67 423	93.32 250	91.33 351	64.02 425	80.57 350	92.83 242	61.21 358	92.27 402	76.34 319	80.38 369	91.32 377

testing91		87.11 249	86.18 246	89.92 255	94.43 207	75.38 338	91.53 314	92.27 323	86.48 165	86.50 217	90.24 332	61.19 359	97.53 218	82.10 239	90.88 229	96.84 158

test_cas_vis1_n_1920		88.83 187	88.85 168	88.78 292	91.15 335	76.72 317	93.85 228	94.93 233	83.23 251	92.81 90	96.00 111	61.17 360	94.45 371	91.67 106	94.84 154	95.17 227

VDDNet		89.56 161	88.49 177	92.76 117	95.07 160	82.09 173	96.30 42	93.19 297	81.05 306	91.88 119	96.86 72	61.16 361	98.33 154	88.43 148	92.49 210	97.84 95

PVSNet_0	73.20 20	77.22 381	74.83 387	84.37 381	90.70 358	71.10 387	83.09 423	89.67 390	72.81 399	73.93 405	83.13 415	60.79 362	93.70 387	68.54 377	50.84 436	88.30 415

SixPastTwentyTwo		83.91 323	82.90 325	86.92 349	90.99 341	70.67 393	93.48 242	91.99 332	85.54 191	77.62 380	92.11 269	60.59 363	96.87 281	76.05 323	77.75 385	93.20 325

gg-mvs-nofinetune		81.77 340	79.37 355	88.99 289	90.85 351	77.73 303	86.29 403	79.63 431	74.88 379	83.19 317	69.05 434	60.34 364	96.11 326	75.46 327	94.64 161	93.11 329

MDA-MVSNet-bldmvs		78.85 375	76.31 380	86.46 357	89.76 378	73.88 351	88.79 374	90.42 372	79.16 327	59.18 430	88.33 374	60.20 365	94.04 379	62.00 409	68.96 413	91.48 374

pmmvs6		83.42 328	81.60 332	88.87 291	88.01 400	77.87 296	94.96 145	94.24 266	74.67 380	78.80 371	91.09 308	60.17 366	96.49 305	77.06 313	75.40 397	92.23 358

ACMH	80.38 17	85.36 295	83.68 311	90.39 233	94.45 205	80.63 218	94.73 163	94.85 239	82.09 273	77.24 381	92.65 249	60.01 367	97.58 214	72.25 353	84.87 306	92.96 334
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 320	89.73 380	77.91 293	87.80 387	78.23 436		80.58 349	83.86 411	59.88 368	95.33 361	71.20 358	92.22 212	90.60 392

UniMVSNet_ETH3D		87.53 227	86.37 238	91.00 210	92.44 288	78.96 267	94.74 162	95.61 189	84.07 227	85.36 261	94.52 182	59.78 369	97.34 245	82.93 221	87.88 279	96.71 163

myMVS_eth3d28		85.80 287	85.26 281	87.42 334	94.73 181	69.92 399	90.60 336	90.95 362	87.21 146	86.06 232	90.04 341	59.47 370	96.02 329	74.89 335	93.35 192	96.33 176

pmmvs-eth3d		80.97 355	78.72 366	87.74 323	84.99 418	79.97 242	90.11 350	91.65 342	75.36 371	73.51 406	86.03 401	59.45 371	93.96 383	75.17 330	72.21 402	89.29 405

testing99		86.72 263	85.73 270	89.69 267	94.23 217	74.91 341	91.35 318	90.97 361	86.14 176	86.36 223	90.22 333	59.41 372	97.48 223	82.24 236	90.66 231	96.69 165

test_0402		81.30 351	79.17 360	87.67 326	93.19 261	78.17 287	92.98 270	91.71 338	75.25 373	76.02 393	90.31 331	59.23 373	96.37 314	50.22 429	83.63 320	88.47 414

KD-MVS_self_test		80.20 361	79.24 357	83.07 388	85.64 415	65.29 417	91.01 328	93.93 277	78.71 338	76.32 388	86.40 399	59.20 374	92.93 397	72.59 351	69.35 410	91.00 387

testing3-2		86.72 263	86.71 222	86.74 355	96.11 107	65.92 413	93.39 247	89.65 392	89.46 67	87.84 190	92.79 246	59.17 375	97.60 213	81.31 256	90.72 230	96.70 164

UWE-MVS-28		78.98 374	78.38 368	80.80 399	88.18 399	60.66 429	90.65 334	78.51 433	78.84 333	77.93 377	90.93 313	59.08 376	89.02 423	50.96 428	90.33 237	92.72 342

FMVSNet1		85.85 285	84.11 304	91.08 204	92.81 278	83.10 141	95.14 136	94.94 229	81.64 291	82.68 321	91.64 286	59.01 377	96.34 317	75.37 328	83.78 316	93.79 294

testing11		86.44 275	85.35 278	89.69 267	94.29 215	75.40 337	91.30 319	90.53 371	84.76 214	85.06 266	90.13 338	58.95 378	97.45 227	82.08 240	91.09 225	96.21 184

COLMAP_ROB	80.39 16	83.96 321	82.04 330	89.74 263	95.28 148	79.75 247	94.25 196	92.28 322	75.17 374	78.02 376	93.77 214	58.60 379	97.84 196	65.06 400	85.92 298	91.63 368
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	81.04 14	85.05 303	83.46 314	89.82 259	94.66 188	79.37 256	94.44 182	94.12 273	82.19 272	78.04 375	92.82 243	58.23 380	97.54 217	73.77 345	82.90 331	92.54 346

CMPMVS	59.16 21	80.52 357	79.20 359	84.48 380	83.98 420	67.63 410	89.95 355	93.84 283	64.79 424	66.81 422	91.14 306	57.93 381	95.17 363	76.25 320	88.10 274	90.65 389
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
reproduce_monomvs		86.37 277	85.87 261	87.87 322	93.66 249	73.71 353	93.44 245	95.02 225	88.61 103	82.64 323	91.94 278	57.88 382	96.68 288	89.96 130	79.71 376	93.22 323

tt0805		86.92 254	85.74 269	90.48 228	92.22 292	79.98 241	95.63 104	94.88 237	83.83 233	84.74 273	92.80 245	57.61 383	97.67 205	85.48 190	84.42 309	93.79 294

ITE_SJBPF				88.24 312	91.88 306	77.05 312		92.92 303	85.54 191	80.13 356	93.30 226	57.29 384	96.20 322	72.46 352	84.71 307	91.49 373

UWE-MVS		83.69 327	83.09 320	85.48 370	93.06 269	65.27 418	90.92 329	86.14 410	79.90 317	86.26 227	90.72 323	57.17 385	95.81 342	71.03 363	92.62 206	95.35 222

TESTMET0.1,1		83.74 326	82.85 326	86.42 360	89.96 375	71.21 386	89.55 360	87.88 402	77.41 352	83.37 313	87.31 387	56.71 386	93.65 388	80.62 270	92.85 202	94.40 266

UnsupCasMVSNet_eth		80.07 363	78.27 369	85.46 371	85.24 417	72.63 370	88.45 380	94.87 238	82.99 256	71.64 414	88.07 378	56.34 387	91.75 407	73.48 347	63.36 424	92.01 362

test_fmvs1		87.34 235	87.56 199	86.68 356	90.59 360	71.80 378	94.01 217	94.04 275	78.30 344	91.97 115	95.22 146	56.28 388	93.71 386	92.89 66	94.71 157	94.52 257

K. test v3		81.59 344	80.15 346	85.91 366	89.89 377	69.42 401	92.57 283	87.71 404	85.56 190	73.44 407	89.71 351	55.58 389	95.52 353	77.17 310	69.76 409	92.78 341

test-mter		84.54 314	83.64 312	87.25 339	90.95 343	71.67 381	89.55 360	89.88 387	79.17 326	84.54 277	87.95 379	55.56 390	95.11 365	81.82 247	93.37 190	94.97 233

lessismore_v0				86.04 362	88.46 393	68.78 403		80.59 429		73.01 409	90.11 339	55.39 391	96.43 311	75.06 332	65.06 421	92.90 336

ETVMVS		84.43 315	82.92 324	88.97 290	94.37 210	74.67 342	91.23 323	88.35 400	83.37 246	86.06 232	89.04 360	55.38 392	95.67 349	67.12 387	91.34 219	96.58 169

MVS-HIRNet		73.70 388	72.20 391	78.18 406	91.81 310	56.42 438	82.94 424	82.58 424	55.24 432	68.88 419	66.48 435	55.32 393	95.13 364	58.12 420	88.42 270	83.01 423

test2506		87.21 244	86.28 243	90.02 251	95.62 135	73.64 355	96.25 49	71.38 443	87.89 129	90.45 146	96.65 83	55.29 394	98.09 177	86.03 183	96.94 103	98.33 45

mvs5depth		80.98 354	79.15 361	86.45 358	84.57 419	73.29 359	87.79 388	91.67 341	80.52 310	82.20 329	89.72 350	55.14 395	95.93 334	73.93 344	66.83 418	90.12 396

new-patchmatchnet		76.41 384	75.17 386	80.13 400	82.65 426	59.61 431	87.66 393	91.08 356	78.23 347	69.85 418	83.22 414	54.76 396	91.63 409	64.14 404	64.89 422	89.16 407

Anonymous202405211		87.68 216	86.13 248	92.31 146	96.66 83	80.74 216	94.87 151	91.49 348	80.47 311	89.46 163	95.44 137	54.72 397	98.23 160	82.19 237	89.89 244	97.97 83

XVG-ACMP-BASELINE		86.00 281	84.84 291	89.45 277	91.20 330	78.00 291	91.70 310	95.55 192	85.05 205	82.97 318	92.25 263	54.49 398	97.48 223	82.93 221	87.45 287	92.89 337

USDC		82.76 331	81.26 336	87.26 338	91.17 332	74.55 344	89.27 366	93.39 293	78.26 346	75.30 397	92.08 271	54.43 399	96.63 291	71.64 355	85.79 300	90.61 390

AllTest		83.42 328	81.39 334	89.52 274	95.01 162	77.79 300	93.12 261	90.89 365	77.41 352	76.12 390	93.34 222	54.08 400	97.51 220	68.31 380	84.27 311	93.26 319

TestCases				89.52 274	95.01 162	77.79 300		90.89 365	77.41 352	76.12 390	93.34 222	54.08 400	97.51 220	68.31 380	84.27 311	93.26 319

KD-MVS_2432*1600		78.50 376	76.02 383	85.93 364	86.22 409	74.47 345	84.80 414	92.33 319	79.29 324	76.98 383	85.92 402	53.81 402	93.97 381	67.39 385	57.42 431	89.36 401

miper_refine_blended		78.50 376	76.02 383	85.93 364	86.22 409	74.47 345	84.80 414	92.33 319	79.29 324	76.98 383	85.92 402	53.81 402	93.97 381	67.39 385	57.42 431	89.36 401

MIMVSNet		82.59 334	80.53 339	88.76 293	91.51 318	78.32 283	86.57 402	90.13 379	79.32 323	80.70 347	88.69 370	52.98 404	93.07 396	66.03 395	88.86 263	94.90 241

testing222		84.84 309	83.32 315	89.43 278	94.15 223	75.94 328	91.09 326	89.41 396	84.90 208	85.78 237	89.44 355	52.70 405	96.28 320	70.80 364	91.57 217	96.07 193

FMVSNet5		81.52 347	79.60 353	87.27 337	91.17 332	77.95 292	91.49 315	92.26 324	76.87 357	76.16 389	87.91 381	51.67 406	92.34 401	67.74 384	81.16 351	91.52 371

testgi		80.94 356	80.20 345	83.18 387	87.96 401	66.29 412	91.28 320	90.70 370	83.70 235	78.12 374	92.84 241	51.37 407	90.82 414	63.34 405	82.46 335	92.43 351

test_fmvs1_n		87.03 252	87.04 213	86.97 347	89.74 379	71.86 376	94.55 173	94.43 255	78.47 340	91.95 117	95.50 136	51.16 408	93.81 384	93.02 65	94.56 163	95.26 224

Anonymous20240521		80.44 359	79.21 358	84.11 384	85.75 414	67.89 406	92.86 276	93.23 296	75.61 370	75.59 396	87.47 386	50.03 409	94.33 375	71.14 361	81.21 350	90.12 396

UnsupCasMVSNet_bld		76.23 385	73.27 389	85.09 377	83.79 421	72.92 362	85.65 408	93.47 292	71.52 405	68.84 420	79.08 425	49.77 410	93.21 393	66.81 393	60.52 428	89.13 409

OpenMVS_ROB	74.94 19	79.51 370	77.03 377	86.93 348	87.00 406	76.23 326	92.33 292	90.74 368	68.93 414	74.52 402	88.23 376	49.58 411	96.62 292	57.64 421	84.29 310	87.94 417

tt0320		80.13 362	77.41 371	88.29 309	90.50 365	78.02 290	93.10 264	90.71 369	66.06 422	76.75 385	86.97 394	49.56 412	95.40 359	71.65 354	71.41 406	91.46 375

TDRefinement		79.81 366	77.34 372	87.22 342	79.24 433	75.48 335	93.12 261	92.03 330	76.45 360	75.01 398	91.58 292	49.19 413	96.44 310	70.22 368	69.18 412	89.75 399

test_vis1_n		86.56 269	86.49 236	86.78 354	88.51 390	72.69 366	94.68 166	93.78 286	79.55 322	90.70 141	95.31 142	48.75 414	93.28 392	93.15 61	93.99 173	94.38 267

MIMVSNet1		79.38 371	77.28 373	85.69 369	86.35 408	73.67 354	91.61 313	92.75 310	78.11 349	72.64 410	88.12 377	48.16 415	91.97 406	60.32 413	77.49 387	91.43 376

LF4IMVS		80.37 360	79.07 363	84.27 383	86.64 407	69.87 400	89.39 365	91.05 358	76.38 361	74.97 399	90.00 343	47.85 416	94.25 378	74.55 340	80.82 362	88.69 412

EG-PatchMatch MVS		82.37 336	80.34 342	88.46 302	90.27 368	79.35 257	92.80 278	94.33 261	77.14 356	73.26 408	90.18 336	47.47 417	96.72 285	70.25 366	87.32 290	89.30 403

test_fmvs2		83.98 320	84.03 305	83.83 386	87.16 405	67.53 411	93.93 223	92.89 304	77.62 350	86.89 211	93.53 219	47.18 418	92.02 404	90.54 124	86.51 295	91.93 363

ttmdpeth		76.55 383	74.64 388	82.29 396	82.25 427	67.81 408	89.76 357	85.69 413	70.35 411	75.76 394	91.69 285	46.88 419	89.77 418	66.16 394	63.23 425	89.30 403

sc_t1		81.53 346	78.67 367	90.12 244	90.78 353	78.64 272	93.91 226	90.20 376	68.42 415	80.82 345	89.88 346	46.48 420	96.76 284	76.03 324	71.47 405	94.96 236

MVStest1		72.91 389	69.70 394	82.54 392	78.14 434	73.05 361	88.21 382	86.21 409	60.69 428	64.70 423	90.53 326	46.44 421	85.70 431	58.78 419	53.62 433	88.87 410

tt0320-xc		79.63 369	76.66 378	88.52 301	91.03 339	78.72 269	93.00 269	89.53 395	66.37 419	76.11 392	87.11 393	46.36 422	95.32 362	72.78 350	67.67 416	91.51 372

TinyColmap		79.76 367	77.69 370	85.97 363	91.71 313	73.12 360	89.55 360	90.36 374	75.03 375	72.03 412	90.19 335	46.22 423	96.19 324	63.11 406	81.03 356	88.59 413

myMVS_eth3d		79.67 368	78.79 365	82.32 395	91.92 303	64.08 421	89.75 358	87.40 407	81.72 288	78.82 369	87.20 389	45.33 424	91.29 410	59.09 418	87.84 281	91.60 369

tmp_tt		35.64 413	39.24 415	24.84 429	14.87 453	23.90 454	62.71 439	51.51 450	6.58 447	36.66 443	62.08 440	44.37 425	30.34 449	52.40 427	22.00 446	20.27 444

testing3		80.46 358	79.59 354	83.06 389	93.44 256	64.64 420	93.33 249	85.47 415	84.34 223	79.93 360	90.84 316	44.35 426	92.39 400	57.06 423	87.56 284	92.16 360

new_pmnet		72.15 390	70.13 393	78.20 405	82.95 425	65.68 414	83.91 419	82.40 425	62.94 427	64.47 424	79.82 424	42.85 427	86.26 430	57.41 422	74.44 398	82.65 425

test_vis1_rt		77.96 379	76.46 379	82.48 393	85.89 412	71.74 380	90.25 342	78.89 432	71.03 409	71.30 415	81.35 422	42.49 428	91.05 413	84.55 201	82.37 336	84.65 420

EGC-MVSNET		61.97 400	56.37 405	78.77 404	89.63 381	73.50 356	89.12 370	82.79 423	0.21 450	1.24 451	84.80 408	39.48 429	90.04 417	44.13 433	75.94 396	72.79 432

dongtai		58.82 405	58.24 403	60.56 422	83.13 423	45.09 446	82.32 425	48.22 452	67.61 417	61.70 429	69.15 433	38.75 430	76.05 441	32.01 440	41.31 440	60.55 437

kuosan		53.51 407	53.30 410	54.13 426	76.06 435	45.36 445	80.11 432	48.36 451	59.63 430	54.84 432	63.43 439	37.41 431	62.07 446	20.73 446	39.10 441	54.96 440

pmmvs3		71.81 392	68.71 395	81.11 397	75.86 436	70.42 395	86.74 400	83.66 421	58.95 431	68.64 421	80.89 423	36.93 432	89.52 420	63.10 407	63.59 423	83.39 421

mvsany_test3		74.95 386	73.26 390	80.02 401	74.61 437	63.16 425	85.53 409	78.42 434	74.16 384	74.89 400	86.46 396	36.02 433	89.09 422	82.39 232	66.91 417	87.82 418

PM-MVS		78.11 378	76.12 382	84.09 385	83.54 422	70.08 397	88.97 373	85.27 417	79.93 316	74.73 401	86.43 397	34.70 434	93.48 389	79.43 287	72.06 403	88.72 411

ambc				83.06 389	79.99 431	63.51 424	77.47 434	92.86 305		74.34 404	84.45 410	28.74 435	95.06 367	73.06 349	68.89 414	90.61 390

test_method		50.52 409	48.47 411	56.66 424	52.26 451	18.98 455	41.51 443	81.40 427	10.10 445	44.59 440	75.01 429	28.51 436	68.16 442	53.54 426	49.31 437	82.83 424

DeepMVS_CX				56.31 425	74.23 438	51.81 441		56.67 449	44.85 437	48.54 437	75.16 428	27.87 437	58.74 447	40.92 437	52.22 434	58.39 439

test_fmvs3		77.67 380	77.16 376	79.22 402	79.52 432	61.14 427	92.34 291	91.64 343	73.98 386	78.86 368	86.59 395	27.38 438	87.03 426	88.12 152	75.97 395	89.50 400

test_f		71.95 391	70.87 392	75.21 409	74.21 439	59.37 432	85.07 413	85.82 412	65.25 423	70.42 417	83.13 415	23.62 439	82.93 437	78.32 297	71.94 404	83.33 422

FPMVS		64.63 399	62.55 401	70.88 412	70.80 441	56.71 434	84.42 417	84.42 419	51.78 435	49.57 435	81.61 421	23.49 440	81.48 438	40.61 438	76.25 394	74.46 431

APD_test1		69.04 393	66.26 399	77.36 408	80.51 430	62.79 426	85.46 410	83.51 422	54.11 434	59.14 431	84.79 409	23.40 441	89.61 419	55.22 424	70.24 408	79.68 429

ANet_high		58.88 404	54.22 409	72.86 410	56.50 450	56.67 435	80.75 429	86.00 411	73.09 396	37.39 442	64.63 438	22.17 442	79.49 440	43.51 434	23.96 444	82.43 426

EMVS		42.07 412	41.12 414	44.92 428	63.45 448	35.56 452	73.65 435	63.48 446	33.05 443	26.88 447	45.45 444	21.27 443	67.14 444	19.80 447	23.02 445	32.06 443

Gipuma		57.99 406	54.91 408	67.24 420	88.51 390	65.59 415	52.21 441	90.33 375	43.58 438	42.84 441	51.18 442	20.29 444	85.07 432	34.77 439	70.45 407	51.05 441
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 411	42.29 413	46.03 427	65.58 446	37.41 450	73.51 436	64.62 445	33.99 442	28.47 446	47.87 443	19.90 445	67.91 443	22.23 445	24.45 443	32.77 442

PMMVS2		59.60 401	56.40 404	69.21 417	68.83 444	46.58 443	73.02 438	77.48 439	55.07 433	49.21 436	72.95 432	17.43 446	80.04 439	49.32 430	44.33 439	80.99 427

LCM-MVSNet		66.00 397	62.16 402	77.51 407	64.51 447	58.29 433	83.87 420	90.90 364	48.17 436	54.69 433	73.31 431	16.83 447	86.75 427	65.47 396	61.67 427	87.48 419

test_vis3_rt		65.12 398	62.60 400	72.69 411	71.44 440	60.71 428	87.17 397	65.55 444	63.80 426	53.22 434	65.65 437	14.54 448	89.44 421	76.65 314	65.38 420	67.91 435

testf1		59.54 402	56.11 406	69.85 415	69.28 442	56.61 436	80.37 430	76.55 441	42.58 439	45.68 438	75.61 426	11.26 449	84.18 433	43.20 435	60.44 429	68.75 433

APD_test2		59.54 402	56.11 406	69.85 415	69.28 442	56.61 436	80.37 430	76.55 441	42.58 439	45.68 438	75.61 426	11.26 449	84.18 433	43.20 435	60.44 429	68.75 433

PMVS	47.18 22	52.22 408	48.46 412	63.48 421	45.72 452	46.20 444	73.41 437	78.31 435	41.03 441	30.06 444	65.68 436	6.05 451	83.43 436	30.04 441	65.86 419	60.80 436
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 410	38.59 416	57.77 423	56.52 449	48.77 442	55.38 440	58.64 448	29.33 444	28.96 445	52.65 441	4.68 452	64.62 445	28.11 442	33.07 442	59.93 438
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 415	20.48 418	23.63 430	68.59 445	36.41 451	49.57 442	6.85 454	9.37 446	7.89 448	4.46 450	4.03 453	31.37 448	17.47 448	16.07 447	3.12 445

test123		8.76 417	11.22 420	1.39 431	0.85 455	0.97 456	85.76 407	0.35 456	0.54 449	2.45 450	8.14 449	0.60 454	0.48 450	2.16 450	0.17 449	2.71 446

testmvs		8.92 416	11.52 419	1.12 432	1.06 454	0.46 457	86.02 404	0.65 455	0.62 448	2.74 449	9.52 448	0.31 455	0.45 451	2.38 449	0.39 448	2.46 447

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		7.82 418	10.43 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	93.88 209	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						64.08 421								59.14 417

FOURS1					98.86 1	85.54 68	98.29 1	97.49 8	89.79 58	96.29 25

MSC_two_6792asdad				96.52 1	97.78 55	90.86 1		96.85 73					99.61 4	96.03 23	99.06 9	99.07 5

No_MVS				96.52 1	97.78 55	90.86 1		96.85 73					99.61 4	96.03 23	99.06 9	99.07 5

eth-test2					0.00 456

eth-test					0.00 456

IU-MVS					98.77 5	86.00 51		96.84 75	81.26 301	97.26 10				95.50 32	99.13 3	99.03 8

save fliter					97.85 50	85.63 67	95.21 130	96.82 78	89.44 68

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 17	97.49 8					99.61 4	95.62 30	99.08 7	98.99 9

GSMVS																96.12 189

test_part2					98.55 12	87.22 19				96.40 24

MTGPA								96.97 59

MTMP							96.16 54	60.64 447

gm-plane-assit					89.60 382	68.00 405			77.28 355		88.99 362		97.57 215	79.44 286

test9_res														91.91 100	98.71 32	98.07 76

agg_prior2														90.54 124	98.68 37	98.27 58

agg_prior					97.38 67	85.92 58		96.72 92		92.16 110			98.97 80

test_prior4						85.96 55	94.11 205

test_prior				93.82 68	97.29 71	84.49 92		96.88 71					98.87 92			98.11 75

旧先验2							93.36 248		71.25 407	94.37 52			97.13 263	86.74 171

新几何2							93.11 263

无先验							93.28 256	96.26 130	73.95 387				99.05 60	80.56 271		96.59 168

原ACMM2							92.94 272

testdata2													98.75 107	78.30 298

testdata1							92.15 298		87.94 125

plane_prior7					94.70 186	82.74 157

plane_prior5								96.22 135					98.12 167	88.15 149	89.99 240	94.63 249

plane_prior4											94.86 163

plane_prior3						82.75 155			90.26 42	86.91 208

plane_prior2							95.85 85		90.81 22

plane_prior1					94.59 192

plane_prior						82.73 158	95.21 130		89.66 63						89.88 245

n2								0.00 457

nn								0.00 457

door-mid								85.49 414

test11								96.57 103

door								85.33 416

HQP5-MVS						81.56 184

HQP-NCC					94.17 220		94.39 187		88.81 93	85.43 254

ACMP_Plane					94.17 220		94.39 187		88.81 93	85.43 254

BP-MVS														87.11 168

HQP4-MVS										85.43 254			97.96 188			94.51 259

HQP3-MVS								96.04 152							89.77 249

NP-MVS					94.37 210	82.42 167					93.98 202

ACMMP++_ref															87.47 285

ACMMP++															88.01 277

High-resolution multi-view benchmark