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.

SMA-MVS		95.20 8	95.07 11	95.59 6	98.14 35	88.48 8	96.26 47	97.28 31	85.90 151	97.67 3	98.10 7	88.41 20	99.56 12	94.66 24	99.19 1	98.71 19
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DPE-MVS		95.57 4	95.67 4	95.25 10	98.36 25	87.28 17	95.56 93	97.51 5	89.13 63	97.14 9	97.91 18	91.64 7	99.62 2	94.61 25	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
SED-MVS		95.91 2	96.28 2	94.80 32	98.77 5	85.99 51	97.13 14	97.44 15	90.31 28	97.71 1	98.07 9	92.31 4	99.58 10	95.66 15	99.13 3	98.84 14

IU-MVS					98.77 5	86.00 49		96.84 65	81.26 261	97.26 7				95.50 21	99.13 3	99.03 8

test_0728_THIRD									90.75 19	97.04 11	98.05 13	92.09 6	99.55 16	95.64 17	99.13 3	99.13 2

test_241102_TWO								97.44 15	90.31 28	97.62 5	98.07 9	91.46 10	99.58 10	95.66 15	99.12 6	98.98 10

DVP-MVS		95.67 3	96.02 3	94.64 38	98.78 3	85.93 54	97.09 16	96.73 79	90.27 31	97.04 11	98.05 13	91.47 8	99.55 16	95.62 19	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
test_0728_SECOND				95.01 17	98.79 2	86.43 38	97.09 16	97.49 6					99.61 4	95.62 19	99.08 7	98.99 9

MSC_two_6792asdad				96.52 1	97.78 51	90.86 1		96.85 63					99.61 4	96.03 12	99.06 9	99.07 5

No_MVS				96.52 1	97.78 51	90.86 1		96.85 63					99.61 4	96.03 12	99.06 9	99.07 5

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 28	86.29 45	97.46 6	97.40 20	89.03 67	96.20 17	98.10 7	89.39 16	99.34 34	95.88 14	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS++		95.98 1	96.36 1	94.82 30	97.78 51	86.00 49	98.29 1	97.49 6	90.75 19	97.62 5	98.06 11	92.59 2	99.61 4	95.64 17	99.02 12	98.86 11

PC_three_1452									82.47 228	97.09 10	97.07 49	92.72 1	98.04 157	92.70 53	99.02 12	98.86 11

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 47	92.59 2	98.94 78	92.25 61	98.99 14	98.84 14

ACMMP_NAP		94.74 15	94.56 18	95.28 9	98.02 41	87.70 11	95.68 85	97.34 23	88.28 91	95.30 30	97.67 24	85.90 45	99.54 20	93.91 32	98.95 15	98.60 23

HPM-MVS++		95.14 10	94.91 13	95.83 4	98.25 29	89.65 4	95.92 73	96.96 52	91.75 9	94.02 44	96.83 59	88.12 24	99.55 16	93.41 40	98.94 16	98.28 50

MP-MVS-pluss		94.21 30	94.00 39	94.85 25	98.17 33	86.65 30	94.82 134	97.17 39	86.26 143	92.83 69	97.87 20	85.57 48	99.56 12	94.37 28	98.92 17	98.34 42
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 25	96.99 72	86.33 41	97.33 7	97.30 29	91.38 12	95.39 28	97.46 28	88.98 19	99.40 30	94.12 29	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
SD-MVS		94.96 12	95.33 8	93.88 57	97.25 69	86.69 27	96.19 50	97.11 43	90.42 27	96.95 13	97.27 36	89.53 14	96.91 246	94.38 27	98.85 19	98.03 70
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 7	95.50 8	98.11 36	88.51 7	95.29 103	96.96 52	92.09 6	95.32 29	97.08 47	89.49 15	99.33 37	95.10 22	98.85 19	98.66 20

CP-MVS		94.34 26	94.21 31	94.74 36	98.39 23	86.64 31	97.60 4	97.24 32	88.53 84	92.73 75	97.23 39	85.20 53	99.32 38	92.15 65	98.83 21	98.25 55

ZNCC-MVS		94.47 20	94.28 27	95.03 16	98.52 15	86.96 19	96.85 28	97.32 27	88.24 92	93.15 59	97.04 50	86.17 42	99.62 2	92.40 57	98.81 22	98.52 26

MP-MVS		94.25 27	94.07 36	94.77 34	98.47 18	86.31 43	96.71 31	96.98 49	89.04 66	91.98 91	97.19 42	85.43 50	99.56 12	92.06 71	98.79 23	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		93.89 40	93.65 51	94.62 40	96.84 75	86.43 38	96.69 32	97.49 6	85.15 171	93.56 53	96.28 82	85.60 47	99.31 39	92.45 54	98.79 23	98.12 64

SF-MVS		94.97 11	94.90 14	95.20 12	97.84 47	87.76 10	96.65 35	97.48 10	87.76 111	95.71 25	97.70 23	88.28 23	99.35 33	93.89 33	98.78 25	98.48 30

ACMMPR		94.43 23	94.28 27	94.91 21	98.63 9	86.69 27	96.94 20	97.32 27	88.63 80	93.53 54	97.26 38	85.04 56	99.54 20	92.35 59	98.78 25	98.50 27

HFP-MVS		94.52 19	94.40 21	94.86 24	98.61 10	86.81 24	96.94 20	97.34 23	88.63 80	93.65 49	97.21 40	86.10 43	99.49 26	92.35 59	98.77 27	98.30 47

MM				95.68 5		88.34 9	96.68 33	94.37 232	95.08 1	94.68 34	97.72 22	82.94 81	99.64 1	97.85 1	98.76 28	99.06 7

MVS_0304		94.60 17	94.38 22	95.23 11	95.41 129	87.49 15	96.53 38	92.75 275	93.82 2	93.07 63	97.84 21	83.66 72	99.59 8	97.61 2	98.76 28	98.61 22

MTAPA		94.42 25	94.22 30	95.00 18	98.42 21	86.95 20	94.36 168	96.97 50	91.07 13	93.14 60	97.56 25	84.30 65	99.56 12	93.43 38	98.75 30	98.47 33

region2R		94.43 23	94.27 29	94.92 20	98.65 8	86.67 29	96.92 24	97.23 34	88.60 82	93.58 51	97.27 36	85.22 52	99.54 20	92.21 62	98.74 31	98.56 25

test9_res														91.91 76	98.71 32	98.07 66

DeepPCF-MVS	89.96 1	94.20 32	94.77 16	92.49 112	96.52 87	80.00 217	94.00 192	97.08 44	90.05 35	95.65 27	97.29 35	89.66 13	98.97 75	93.95 31	98.71 32	98.50 27

9.14			94.47 19		97.79 49		96.08 61	97.44 15	86.13 149	95.10 31	97.40 31	88.34 22	99.22 44	93.25 42	98.70 34

train_agg		93.44 52	93.08 59	94.52 43	97.53 58	86.49 36	94.07 184	96.78 72	81.86 245	92.77 72	96.20 85	87.63 29	99.12 51	92.14 66	98.69 35	97.94 74

DeepC-MVS_fast	89.43 2	94.04 35	93.79 43	94.80 32	97.48 61	86.78 25	95.65 89	96.89 60	89.40 53	92.81 70	96.97 52	85.37 51	99.24 43	90.87 95	98.69 35	98.38 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + MP.		94.85 13	94.94 12	94.58 41	98.25 29	86.33 41	96.11 60	96.62 88	88.14 98	96.10 18	96.96 53	89.09 18	98.94 78	94.48 26	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
agg_prior2														90.54 100	98.68 37	98.27 52

test_prior2							94.12 178		87.67 114	92.63 77	96.39 80	86.62 36		91.50 83	98.67 39

MSLP-MVS++		93.72 45	94.08 35	92.65 104	97.31 65	83.43 112	95.79 79	97.33 25	90.03 36	93.58 51	96.96 53	84.87 60	97.76 172	92.19 64	98.66 40	96.76 129

CDPH-MVS		92.83 66	92.30 72	94.44 44	97.79 49	86.11 48	94.06 186	96.66 85	80.09 274	92.77 72	96.63 71	86.62 36	99.04 57	87.40 134	98.66 40	98.17 60

HPM-MVS		94.02 36	93.88 41	94.43 46	98.39 23	85.78 61	97.25 10	97.07 45	86.90 131	92.62 78	96.80 63	84.85 61	99.17 47	92.43 55	98.65 42	98.33 43
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		93.99 38	93.78 44	94.63 39	98.50 16	85.90 58	96.87 26	96.91 58	88.70 78	91.83 100	97.17 44	83.96 69	99.55 16	91.44 84	98.64 43	98.43 38

CS-MVS-test		94.02 36	94.29 26	93.24 71	96.69 78	83.24 117	97.49 5	96.92 57	92.14 5	92.90 65	95.77 106	85.02 57	98.33 129	93.03 45	98.62 44	98.13 62

MCST-MVS		94.45 21	94.20 32	95.19 13	98.46 19	87.50 14	95.00 123	97.12 41	87.13 123	92.51 81	96.30 81	89.24 17	99.34 34	93.46 37	98.62 44	98.73 17

APD-MVS		94.24 28	94.07 36	94.75 35	98.06 39	86.90 22	95.88 74	96.94 55	85.68 157	95.05 32	97.18 43	87.31 33	99.07 53	91.90 78	98.61 46	98.28 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PGM-MVS		93.96 39	93.72 47	94.68 37	98.43 20	86.22 46	95.30 101	97.78 1	87.45 118	93.26 56	97.33 34	84.62 63	99.51 24	90.75 97	98.57 47	98.32 46

XVS		94.45 21	94.32 23	94.85 25	98.54 13	86.60 33	96.93 22	97.19 35	90.66 24	92.85 67	97.16 45	85.02 57	99.49 26	91.99 72	98.56 48	98.47 33

X-MVStestdata		88.31 171	86.13 217	94.85 25	98.54 13	86.60 33	96.93 22	97.19 35	90.66 24	92.85 67	23.41 394	85.02 57	99.49 26	91.99 72	98.56 48	98.47 33

DELS-MVS		93.43 55	93.25 56	93.97 54	95.42 128	85.04 69	93.06 235	97.13 40	90.74 21	91.84 98	95.09 131	86.32 40	99.21 45	91.22 86	98.45 50	97.65 89
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
ZD-MVS					98.15 34	86.62 32		97.07 45	83.63 201	94.19 40	96.91 55	87.57 31	99.26 42	91.99 72	98.44 51

GST-MVS		94.21 30	93.97 40	94.90 23	98.41 22	86.82 23	96.54 37	97.19 35	88.24 92	93.26 56	96.83 59	85.48 49	99.59 8	91.43 85	98.40 52	98.30 47

HPM-MVS_fast		93.40 56	93.22 57	93.94 56	98.36 25	84.83 72	97.15 13	96.80 71	85.77 154	92.47 82	97.13 46	82.38 88	99.07 53	90.51 102	98.40 52	97.92 77

NCCC		94.81 14	94.69 17	95.17 14	97.83 48	87.46 16	95.66 87	96.93 56	92.34 4	93.94 45	96.58 74	87.74 27	99.44 29	92.83 48	98.40 52	98.62 21

DeepC-MVS	88.79 3	93.31 57	92.99 62	94.26 51	96.07 102	85.83 59	94.89 129	96.99 48	89.02 69	89.56 130	97.37 33	82.51 87	99.38 31	92.20 63	98.30 55	97.57 94
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		93.23 60	93.05 60	93.76 63	98.04 40	84.07 94	96.22 49	97.37 21	84.15 189	90.05 126	95.66 110	87.77 26	99.15 50	89.91 105	98.27 56	98.07 66

原ACMM1				92.01 128	97.34 64	81.05 183		96.81 70	78.89 288	90.45 118	95.92 98	82.65 85	98.84 88	80.68 235	98.26 57	96.14 149

CS-MVS		94.12 34	94.44 20	93.17 74	96.55 84	83.08 127	97.63 3	96.95 54	91.71 11	93.50 55	96.21 84	85.61 46	98.24 134	93.64 35	98.17 58	98.19 58

MVS_111021_HR		93.45 51	93.31 54	93.84 59	96.99 72	84.84 71	93.24 228	97.24 32	88.76 75	91.60 105	95.85 101	86.07 44	98.66 96	91.91 76	98.16 59	98.03 70

EC-MVSNet		93.44 52	93.71 48	92.63 105	95.21 136	82.43 148	97.27 9	96.71 82	90.57 26	92.88 66	95.80 104	83.16 77	98.16 140	93.68 34	98.14 60	97.31 101

test12				94.34 49	97.13 70	86.15 47		96.29 104		91.04 113		85.08 55	99.01 63		98.13 61	97.86 80

新几何1				93.10 77	97.30 66	84.35 90		95.56 166	71.09 364	91.26 111	96.24 83	82.87 83	98.86 84	79.19 256	98.10 62	96.07 155

patch_mono-2		93.74 44	94.32 23	92.01 128	97.54 57	78.37 255	93.40 216	97.19 35	88.02 101	94.99 33	97.21 40	88.35 21	98.44 119	94.07 30	98.09 63	99.23 1

dcpmvs_2		93.49 49	94.19 33	91.38 163	97.69 54	76.78 287	94.25 171	96.29 104	88.33 88	94.46 36	96.88 56	88.07 25	98.64 98	93.62 36	98.09 63	98.73 17

test_fmvsm_n_1920		94.71 16	95.11 10	93.50 67	95.79 114	84.62 76	96.15 55	97.64 2	89.85 40	97.19 8	97.89 19	86.28 41	98.71 95	97.11 6	98.08 65	97.17 108

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 35	96.91 25	97.47 11	91.73 10	96.10 18	96.69 64	89.90 12	99.30 40	94.70 23	98.04 66	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
SR-MVS		94.23 29	94.17 34	94.43 46	98.21 32	85.78 61	96.40 41	96.90 59	88.20 96	94.33 38	97.40 31	84.75 62	99.03 58	93.35 41	97.99 67	98.48 30

3Dnovator	86.66 5	91.73 82	90.82 93	94.44 44	94.59 168	86.37 40	97.18 12	97.02 47	89.20 60	84.31 252	96.66 67	73.74 197	99.17 47	86.74 144	97.96 68	97.79 85

CANet		93.54 48	93.20 58	94.55 42	95.65 120	85.73 63	94.94 126	96.69 84	91.89 8	90.69 116	95.88 100	81.99 100	99.54 20	93.14 44	97.95 69	98.39 39

DPM-MVS		92.58 70	91.74 78	95.08 15	96.19 95	89.31 5	92.66 246	96.56 93	83.44 207	91.68 104	95.04 132	86.60 38	98.99 70	85.60 158	97.92 70	96.93 122

APD-MVS_3200maxsize		93.78 42	93.77 45	93.80 62	97.92 43	84.19 92	96.30 43	96.87 62	86.96 127	93.92 46	97.47 27	83.88 70	98.96 77	92.71 52	97.87 71	98.26 54

CPTT-MVS		91.99 76	91.80 77	92.55 109	98.24 31	81.98 158	96.76 30	96.49 95	81.89 244	90.24 121	96.44 79	78.59 134	98.61 102	89.68 106	97.85 72	97.06 113

test_fmvsmconf_n		94.60 17	94.81 15	93.98 53	94.62 167	84.96 70	96.15 55	97.35 22	89.37 54	96.03 21	98.11 5	86.36 39	99.01 63	97.45 3	97.83 73	97.96 73

SR-MVS-dyc-post		93.82 41	93.82 42	93.82 60	97.92 43	84.57 78	96.28 45	96.76 75	87.46 116	93.75 47	97.43 29	84.24 66	99.01 63	92.73 49	97.80 74	97.88 78

RE-MVS-def			93.68 49		97.92 43	84.57 78	96.28 45	96.76 75	87.46 116	93.75 47	97.43 29	82.94 81		92.73 49	97.80 74	97.88 78

test222					96.55 84	81.70 164	92.22 262	95.01 199	68.36 370	90.20 122	96.14 90	80.26 112			97.80 74	96.05 157

test_fmvsmconf0.1_n		94.20 32	94.31 25	93.88 57	92.46 245	84.80 73	96.18 52	96.82 68	89.29 57	95.68 26	98.11 5	85.10 54	98.99 70	97.38 4	97.75 77	97.86 80

3Dnovator+	87.14 4	92.42 73	91.37 81	95.55 7	95.63 121	88.73 6	97.07 18	96.77 74	90.84 16	84.02 256	96.62 72	75.95 161	99.34 34	87.77 128	97.68 78	98.59 24

旧先验1					96.79 76	81.81 162		95.67 158			96.81 61	86.69 35			97.66 79	96.97 120

EPNet		91.79 79	91.02 89	94.10 52	90.10 326	85.25 68	96.03 66	92.05 295	92.83 3	87.39 169	95.78 105	79.39 124	99.01 63	88.13 124	97.48 80	98.05 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmvis_n_1920		93.44 52	93.55 52	93.10 77	93.67 211	84.26 91	95.83 77	96.14 118	89.00 70	92.43 83	97.50 26	83.37 76	98.72 94	96.61 10	97.44 81	96.32 142

testdata				90.49 200	96.40 89	77.89 267		95.37 184	72.51 356	93.63 50	96.69 64	82.08 97	97.65 180	83.08 188	97.39 82	95.94 159

MVS_111021_LR		92.47 72	92.29 73	92.98 85	95.99 108	84.43 87	93.08 233	96.09 124	88.20 96	91.12 112	95.72 109	81.33 105	97.76 172	91.74 79	97.37 83	96.75 130

test_fmvsmconf0.01_n		93.19 61	93.02 61	93.71 64	89.25 338	84.42 89	96.06 64	96.29 104	89.06 64	94.68 34	98.13 3	79.22 126	98.98 74	97.22 5	97.24 84	97.74 87

MVSFormer		91.68 84	91.30 82	92.80 95	93.86 201	83.88 99	95.96 71	95.90 140	84.66 183	91.76 101	94.91 135	77.92 142	97.30 216	89.64 107	97.11 85	97.24 104

lupinMVS		90.92 95	90.21 99	93.03 82	93.86 201	83.88 99	92.81 243	93.86 252	79.84 276	91.76 101	94.29 162	77.92 142	98.04 157	90.48 103	97.11 85	97.17 108

EIA-MVS		91.95 77	91.94 75	91.98 132	95.16 138	80.01 216	95.36 96	96.73 79	88.44 85	89.34 134	92.16 237	83.82 71	98.45 117	89.35 109	97.06 87	97.48 97

MG-MVS		91.77 80	91.70 79	92.00 131	97.08 71	80.03 215	93.60 210	95.18 192	87.85 109	90.89 114	96.47 78	82.06 98	98.36 124	85.07 162	97.04 88	97.62 90

test2506		87.21 216	86.28 213	90.02 225	95.62 122	73.64 318	96.25 48	71.38 394	87.89 107	90.45 118	96.65 68	55.29 352	98.09 152	86.03 153	96.94 89	98.33 43

ECVR-MVS		89.09 147	88.53 144	90.77 191	95.62 122	75.89 299	96.16 53	84.22 372	87.89 107	90.20 122	96.65 68	63.19 311	98.10 144	85.90 154	96.94 89	98.33 43

test1111		89.10 145	88.64 140	90.48 202	95.53 126	74.97 306	96.08 61	84.89 370	88.13 99	90.16 124	96.65 68	63.29 309	98.10 144	86.14 149	96.90 91	98.39 39

jason		90.80 96	90.10 103	92.90 90	93.04 229	83.53 110	93.08 233	94.15 241	80.22 271	91.41 108	94.91 135	76.87 149	97.93 166	90.28 104	96.90 91	97.24 104
jason: jason.
Vis-MVSNet		91.75 81	91.23 84	93.29 69	95.32 131	83.78 101	96.14 57	95.98 132	89.89 38	90.45 118	96.58 74	75.09 173	98.31 132	84.75 168	96.90 91	97.78 86
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
114514_t		89.51 131	88.50 146	92.54 110	98.11 36	81.99 157	95.16 114	96.36 101	70.19 367	85.81 200	95.25 122	76.70 153	98.63 100	82.07 208	96.86 94	97.00 118

Vis-MVSNet (Re-imp)		89.59 129	89.44 118	90.03 223	95.74 116	75.85 300	95.61 91	90.80 330	87.66 115	87.83 158	95.40 118	76.79 151	96.46 273	78.37 260	96.73 95	97.80 84

API-MVS		90.66 102	90.07 104	92.45 114	96.36 91	84.57 78	96.06 64	95.22 191	82.39 229	89.13 136	94.27 165	80.32 110	98.46 113	80.16 243	96.71 96	94.33 228

MAR-MVS		90.30 108	89.37 121	93.07 81	96.61 81	84.48 83	95.68 85	95.67 158	82.36 231	87.85 157	92.85 214	76.63 155	98.80 90	80.01 244	96.68 97	95.91 160
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
OpenMVS	83.78 11	88.74 160	87.29 177	93.08 79	92.70 240	85.39 66	96.57 36	96.43 97	78.74 293	80.85 301	96.07 92	69.64 247	99.01 63	78.01 267	96.65 98	94.83 202

ETV-MVS		92.74 68	92.66 67	92.97 86	95.20 137	84.04 96	95.07 119	96.51 94	90.73 22	92.96 64	91.19 271	84.06 67	98.34 127	91.72 80	96.54 99	96.54 138

QAPM		89.51 131	88.15 157	93.59 66	94.92 151	84.58 77	96.82 29	96.70 83	78.43 298	83.41 271	96.19 88	73.18 204	99.30 40	77.11 276	96.54 99	96.89 125

IS-MVSNet		91.43 86	91.09 88	92.46 113	95.87 113	81.38 175	96.95 19	93.69 258	89.72 47	89.50 132	95.98 96	78.57 135	97.77 171	83.02 190	96.50 101	98.22 57

DP-MVS Recon		91.95 77	91.28 83	93.96 55	98.33 27	85.92 56	94.66 145	96.66 85	82.69 226	90.03 127	95.82 103	82.30 91	99.03 58	84.57 170	96.48 102	96.91 124

CANet_DTU		90.26 110	89.41 120	92.81 94	93.46 217	83.01 130	93.48 213	94.47 227	89.43 52	87.76 161	94.23 166	70.54 237	99.03 58	84.97 163	96.39 103	96.38 141

UGNet		89.95 119	88.95 131	92.95 88	94.51 174	83.31 116	95.70 84	95.23 189	89.37 54	87.58 163	93.94 178	64.00 302	98.78 91	83.92 179	96.31 104	96.74 131
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
fmvsm_s_conf0.5_n		93.76 43	94.06 38	92.86 92	95.62 122	83.17 120	96.14 57	96.12 121	88.13 99	95.82 24	98.04 16	83.43 73	98.48 109	96.97 7	96.23 105	96.92 123

fmvsm_s_conf0.1_n		93.46 50	93.66 50	92.85 93	93.75 207	83.13 122	96.02 67	95.74 152	87.68 113	95.89 23	98.17 2	82.78 84	98.46 113	96.71 8	96.17 106	96.98 119

TSAR-MVS + GP.		93.66 46	93.41 53	94.41 48	96.59 82	86.78 25	94.40 161	93.93 248	89.77 45	94.21 39	95.59 113	87.35 32	98.61 102	92.72 51	96.15 107	97.83 83

PVSNet_Blended		90.73 99	90.32 98	91.98 132	96.12 97	81.25 177	92.55 250	96.83 66	82.04 238	89.10 137	92.56 225	81.04 107	98.85 86	86.72 146	95.91 108	95.84 164

PS-MVSNAJ		91.18 92	90.92 90	91.96 134	95.26 134	82.60 147	92.09 267	95.70 156	86.27 142	91.84 98	92.46 227	79.70 119	98.99 70	89.08 113	95.86 109	94.29 231

ACMMP		93.24 59	92.88 64	94.30 50	98.09 38	85.33 67	96.86 27	97.45 14	88.33 88	90.15 125	97.03 51	81.44 103	99.51 24	90.85 96	95.74 110	98.04 69
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
casdiffmvs_mvg		92.96 65	92.83 65	93.35 68	94.59 168	83.40 114	95.00 123	96.34 102	90.30 30	92.05 89	96.05 93	83.43 73	98.15 141	92.07 68	95.67 111	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
LCM-MVSNet-Re		88.30 172	88.32 153	88.27 274	94.71 162	72.41 335	93.15 229	90.98 325	87.77 110	79.25 323	91.96 249	78.35 138	95.75 305	83.04 189	95.62 112	96.65 133

CHOSEN 1792x2688		88.84 156	87.69 167	92.30 122	96.14 96	81.42 174	90.01 308	95.86 144	74.52 337	87.41 166	93.94 178	75.46 170	98.36 124	80.36 239	95.53 113	97.12 112

fmvsm_s_conf0.5_n_a		93.57 47	93.76 46	93.00 84	95.02 143	83.67 104	96.19 50	96.10 123	87.27 121	95.98 22	98.05 13	83.07 80	98.45 117	96.68 9	95.51 114	96.88 126

AdaColmap		89.89 122	89.07 128	92.37 118	97.41 62	83.03 128	94.42 160	95.92 137	82.81 223	86.34 193	94.65 150	73.89 193	99.02 61	80.69 234	95.51 114	95.05 190

MVS		87.44 203	86.10 220	91.44 161	92.61 242	83.62 107	92.63 247	95.66 160	67.26 371	81.47 293	92.15 238	77.95 141	98.22 137	79.71 247	95.48 116	92.47 307

UA-Net		92.83 66	92.54 69	93.68 65	96.10 100	84.71 75	95.66 87	96.39 99	91.92 7	93.22 58	96.49 77	83.16 77	98.87 82	84.47 172	95.47 117	97.45 99

xiu_mvs_v2_base		91.13 93	90.89 92	91.86 142	94.97 147	82.42 149	92.24 261	95.64 163	86.11 150	91.74 103	93.14 207	79.67 122	98.89 81	89.06 114	95.46 118	94.28 232

casdiffmvs		92.51 71	92.43 71	92.74 99	94.41 180	81.98 158	94.54 151	96.23 112	89.57 49	91.96 93	96.17 89	82.58 86	98.01 159	90.95 93	95.45 119	98.23 56
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.1_n_a		93.19 61	93.26 55	92.97 86	92.49 243	83.62 107	96.02 67	95.72 155	86.78 133	96.04 20	98.19 1	82.30 91	98.43 121	96.38 11	95.42 120	96.86 127

PVSNet_Blended_VisFu		91.38 87	90.91 91	92.80 95	96.39 90	83.17 120	94.87 131	96.66 85	83.29 211	89.27 135	94.46 156	80.29 111	99.17 47	87.57 132	95.37 121	96.05 157

PAPM_NR		91.22 91	90.78 94	92.52 111	97.60 56	81.46 172	94.37 167	96.24 111	86.39 141	87.41 166	94.80 143	82.06 98	98.48 109	82.80 196	95.37 121	97.61 91

CHOSEN 280x420		85.15 265	83.99 268	88.65 266	92.47 244	78.40 254	79.68 382	92.76 274	74.90 334	81.41 295	89.59 309	69.85 245	95.51 312	79.92 246	95.29 123	92.03 319

TAPA-MVS	84.62 6	88.16 175	87.01 185	91.62 152	96.64 80	80.65 194	94.39 163	96.21 116	76.38 317	86.19 196	95.44 115	79.75 117	98.08 154	62.75 361	95.29 123	96.13 150
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline		92.39 74	92.29 73	92.69 103	94.46 177	81.77 163	94.14 177	96.27 107	89.22 59	91.88 96	96.00 94	82.35 89	97.99 161	91.05 88	95.27 125	98.30 47

LS3D		87.89 181	86.32 211	92.59 107	96.07 102	82.92 134	95.23 107	94.92 207	75.66 324	82.89 278	95.98 96	72.48 213	99.21 45	68.43 335	95.23 126	95.64 173

test_vis1_n_1920		89.39 140	89.84 111	88.04 281	92.97 233	72.64 330	94.71 142	96.03 131	86.18 146	91.94 95	96.56 76	61.63 318	95.74 306	93.42 39	95.11 127	95.74 169

MVS_Test		91.31 89	91.11 86	91.93 136	94.37 181	80.14 208	93.46 215	95.80 147	86.46 139	91.35 110	93.77 188	82.21 94	98.09 152	87.57 132	94.95 128	97.55 96

test_cas_vis1_n_1920		88.83 159	88.85 137	88.78 260	91.15 293	76.72 288	93.85 200	94.93 206	83.23 214	92.81 70	96.00 94	61.17 326	94.45 326	91.67 81	94.84 129	95.17 187

PAPR		90.02 115	89.27 126	92.29 123	95.78 115	80.95 187	92.68 245	96.22 113	81.91 242	86.66 186	93.75 190	82.23 93	98.44 119	79.40 255	94.79 130	97.48 97

test_fmvs1		87.34 207	87.56 170	86.68 314	90.59 316	71.80 339	94.01 190	94.04 246	78.30 300	91.97 92	95.22 123	56.28 347	93.71 340	92.89 47	94.71 131	94.52 215

xiu_mvs_v1_base_debu		90.64 103	90.05 105	92.40 115	93.97 198	84.46 84	93.32 219	95.46 173	85.17 168	92.25 84	94.03 170	70.59 233	98.57 105	90.97 90	94.67 132	94.18 233

xiu_mvs_v1_base		90.64 103	90.05 105	92.40 115	93.97 198	84.46 84	93.32 219	95.46 173	85.17 168	92.25 84	94.03 170	70.59 233	98.57 105	90.97 90	94.67 132	94.18 233

xiu_mvs_v1_base_debi		90.64 103	90.05 105	92.40 115	93.97 198	84.46 84	93.32 219	95.46 173	85.17 168	92.25 84	94.03 170	70.59 233	98.57 105	90.97 90	94.67 132	94.18 233

gg-mvs-nofinetune		81.77 297	79.37 312	88.99 258	90.85 308	77.73 275	86.29 354	79.63 383	74.88 335	83.19 276	69.05 384	60.34 330	96.11 289	75.46 290	94.64 135	93.11 288

BH-RMVSNet		88.37 169	87.48 172	91.02 181	95.28 132	79.45 230	92.89 240	93.07 267	85.45 164	86.91 178	94.84 142	70.35 238	97.76 172	73.97 303	94.59 136	95.85 163

test_fmvs1_n		87.03 223	87.04 184	86.97 306	89.74 334	71.86 337	94.55 150	94.43 228	78.47 296	91.95 94	95.50 114	51.16 364	93.81 338	93.02 46	94.56 137	95.26 184

diffmvs		91.37 88	91.23 84	91.77 148	93.09 226	80.27 203	92.36 255	95.52 171	87.03 126	91.40 109	94.93 134	80.08 113	97.44 200	92.13 67	94.56 137	97.61 91
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-untuned		88.60 164	88.13 158	90.01 226	95.24 135	78.50 251	93.29 224	94.15 241	84.75 180	84.46 242	93.40 195	75.76 164	97.40 209	77.59 270	94.52 139	94.12 237

Effi-MVS+		91.59 85	91.11 86	93.01 83	94.35 184	83.39 115	94.60 147	95.10 196	87.10 124	90.57 117	93.10 209	81.43 104	98.07 155	89.29 111	94.48 140	97.59 93

PCF-MVS	84.11 10	87.74 186	86.08 221	92.70 102	94.02 192	84.43 87	89.27 320	95.87 143	73.62 346	84.43 244	94.33 159	78.48 137	98.86 84	70.27 321	94.45 141	94.81 203
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EI-MVSNet-Vis-set		93.01 64	92.92 63	93.29 69	95.01 144	83.51 111	94.48 153	95.77 149	90.87 15	92.52 80	96.67 66	84.50 64	99.00 68	91.99 72	94.44 142	97.36 100

MS-PatchMatch		85.05 267	84.16 264	87.73 286	91.42 281	78.51 250	91.25 284	93.53 259	77.50 307	80.15 310	91.58 262	61.99 316	95.51 312	75.69 288	94.35 143	89.16 359

FE-MVS		87.40 205	86.02 223	91.57 155	94.56 172	79.69 225	90.27 297	93.72 257	80.57 269	88.80 142	91.62 260	65.32 294	98.59 104	74.97 297	94.33 144	96.44 139

mvs_anonymous		89.37 141	89.32 123	89.51 246	93.47 216	74.22 313	91.65 277	94.83 214	82.91 221	85.45 216	93.79 186	81.23 106	96.36 280	86.47 148	94.09 145	97.94 74

test_vis1_n		86.56 237	86.49 206	86.78 313	88.51 344	72.69 327	94.68 143	93.78 256	79.55 280	90.70 115	95.31 119	48.75 369	93.28 346	93.15 43	93.99 146	94.38 227

MVP-Stereo		85.97 248	84.86 255	89.32 248	90.92 304	82.19 154	92.11 266	94.19 239	78.76 292	78.77 328	91.63 259	68.38 267	96.56 265	75.01 296	93.95 147	89.20 358
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LFMVS		90.08 113	89.13 127	92.95 88	96.71 77	82.32 153	96.08 61	89.91 345	86.79 132	92.15 88	96.81 61	62.60 313	98.34 127	87.18 138	93.90 148	98.19 58

PVSNet	78.82 18	85.55 255	84.65 259	88.23 277	94.72 161	71.93 336	87.12 349	92.75 275	78.80 291	84.95 232	90.53 291	64.43 300	96.71 253	74.74 298	93.86 149	96.06 156

CNLPA		89.07 149	87.98 161	92.34 119	96.87 74	84.78 74	94.08 183	93.24 263	81.41 257	84.46 242	95.13 130	75.57 169	96.62 257	77.21 274	93.84 150	95.61 176

EPNet_dtu		86.49 242	85.94 228	88.14 279	90.24 324	72.82 325	94.11 179	92.20 289	86.66 137	79.42 322	92.36 231	73.52 198	95.81 303	71.26 315	93.66 151	95.80 167
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GeoE		90.05 114	89.43 119	91.90 141	95.16 138	80.37 202	95.80 78	94.65 224	83.90 194	87.55 165	94.75 145	78.18 140	97.62 185	81.28 223	93.63 152	97.71 88

EI-MVSNet-UG-set		92.74 68	92.62 68	93.12 76	94.86 155	83.20 119	94.40 161	95.74 152	90.71 23	92.05 89	96.60 73	84.00 68	98.99 70	91.55 82	93.63 152	97.17 108

Fast-Effi-MVS+		89.41 137	88.64 140	91.71 150	94.74 159	80.81 191	93.54 211	95.10 196	83.11 215	86.82 184	90.67 289	79.74 118	97.75 175	80.51 238	93.55 154	96.57 136

FA-MVS(test-final)		89.66 126	88.91 133	91.93 136	94.57 171	80.27 203	91.36 281	94.74 220	84.87 176	89.82 128	92.61 224	74.72 180	98.47 112	83.97 178	93.53 155	97.04 115

1314		87.51 200	86.57 202	90.34 211	92.42 247	79.74 224	92.63 247	95.35 186	78.35 299	80.14 311	91.62 260	74.05 190	97.15 229	81.05 225	93.53 155	94.12 237

BH-w/o		87.57 198	87.05 183	89.12 253	94.90 153	77.90 266	92.41 252	93.51 260	82.89 222	83.70 263	91.34 265	75.75 165	97.07 236	75.49 289	93.49 157	92.39 311

PMMVS		85.71 254	84.96 252	87.95 283	88.90 342	77.09 283	88.68 330	90.06 341	72.32 358	86.47 187	90.76 288	72.15 216	94.40 328	81.78 216	93.49 157	92.36 312

PatchMatch-RL		86.77 232	85.54 238	90.47 205	95.88 111	82.71 142	90.54 294	92.31 286	79.82 277	84.32 250	91.57 264	68.77 262	96.39 277	73.16 308	93.48 159	92.32 314

PLC	84.53 7	89.06 150	88.03 160	92.15 126	97.27 68	82.69 143	94.29 169	95.44 178	79.71 278	84.01 257	94.18 167	76.68 154	98.75 92	77.28 273	93.41 160	95.02 191
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VNet		92.24 75	91.91 76	93.24 71	96.59 82	83.43 112	94.84 133	96.44 96	89.19 61	94.08 43	95.90 99	77.85 145	98.17 139	88.90 115	93.38 161	98.13 62

test-LLR		85.87 250	85.41 241	87.25 298	90.95 300	71.67 341	89.55 314	89.88 347	83.41 208	84.54 239	87.95 333	67.25 272	95.11 321	81.82 214	93.37 162	94.97 192

test-mter		84.54 274	83.64 273	87.25 298	90.95 300	71.67 341	89.55 314	89.88 347	79.17 284	84.54 239	87.95 333	55.56 349	95.11 321	81.82 214	93.37 162	94.97 192

EPP-MVSNet		91.70 83	91.56 80	92.13 127	95.88 111	80.50 199	97.33 7	95.25 188	86.15 147	89.76 129	95.60 112	83.42 75	98.32 131	87.37 136	93.25 164	97.56 95

CDS-MVSNet		89.45 134	88.51 145	92.29 123	93.62 212	83.61 109	93.01 236	94.68 223	81.95 240	87.82 159	93.24 203	78.69 132	96.99 241	80.34 240	93.23 165	96.28 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPM		86.68 233	85.39 242	90.53 196	93.05 228	79.33 237	89.79 311	94.77 219	78.82 290	81.95 289	93.24 203	76.81 150	97.30 216	66.94 344	93.16 166	94.95 198

alignmvs		93.08 63	92.50 70	94.81 31	95.62 122	87.61 13	95.99 69	96.07 126	89.77 45	94.12 41	94.87 137	80.56 109	98.66 96	92.42 56	93.10 167	98.15 61

thisisatest0515		87.33 208	85.99 224	91.37 164	93.49 215	79.55 227	90.63 293	89.56 352	80.17 272	87.56 164	90.86 282	67.07 276	98.28 133	81.50 221	93.02 168	96.29 144

TAMVS		89.21 143	88.29 154	91.96 134	93.71 208	82.62 146	93.30 223	94.19 239	82.22 233	87.78 160	93.94 178	78.83 129	96.95 243	77.70 269	92.98 169	96.32 142

OMC-MVS		91.23 90	90.62 95	93.08 79	96.27 93	84.07 94	93.52 212	95.93 136	86.95 128	89.51 131	96.13 91	78.50 136	98.35 126	85.84 156	92.90 170	96.83 128

canonicalmvs		93.27 58	92.75 66	94.85 25	95.70 119	87.66 12	96.33 42	96.41 98	90.00 37	94.09 42	94.60 152	82.33 90	98.62 101	92.40 57	92.86 171	98.27 52

TESTMET0.1,1		83.74 284	82.85 283	86.42 317	89.96 330	71.21 345	89.55 314	87.88 357	77.41 308	83.37 272	87.31 341	56.71 345	93.65 342	80.62 236	92.85 172	94.40 226

thisisatest0530		88.67 161	87.61 169	91.86 142	94.87 154	80.07 211	94.63 146	89.90 346	84.00 192	88.46 147	93.78 187	66.88 279	98.46 113	83.30 186	92.65 173	97.06 113

VDD-MVS		90.74 98	89.92 110	93.20 73	96.27 93	83.02 129	95.73 82	93.86 252	88.42 87	92.53 79	96.84 58	62.09 315	98.64 98	90.95 93	92.62 174	97.93 76

test_yl		90.69 100	90.02 108	92.71 100	95.72 117	82.41 151	94.11 179	95.12 194	85.63 159	91.49 106	94.70 146	74.75 177	98.42 122	86.13 151	92.53 175	97.31 101

DCV-MVSNet		90.69 100	90.02 108	92.71 100	95.72 117	82.41 151	94.11 179	95.12 194	85.63 159	91.49 106	94.70 146	74.75 177	98.42 122	86.13 151	92.53 175	97.31 101

VDDNet		89.56 130	88.49 148	92.76 97	95.07 142	82.09 155	96.30 43	93.19 265	81.05 266	91.88 96	96.86 57	61.16 327	98.33 129	88.43 121	92.49 177	97.84 82

DP-MVS		87.25 212	85.36 244	92.90 90	97.65 55	83.24 117	94.81 135	92.00 297	74.99 332	81.92 290	95.00 133	72.66 210	99.05 55	66.92 346	92.33 178	96.40 140

GG-mvs-BLEND				87.94 284	89.73 335	77.91 265	87.80 339	78.23 387		80.58 305	83.86 362	59.88 334	95.33 318	71.20 316	92.22 179	90.60 347

tttt0517		88.61 163	87.78 166	91.11 176	94.96 148	77.81 270	95.35 97	89.69 349	85.09 173	88.05 154	94.59 153	66.93 277	98.48 109	83.27 187	92.13 180	97.03 116

HyFIR lowres test		88.09 177	86.81 189	91.93 136	96.00 105	80.63 195	90.01 308	95.79 148	73.42 348	87.68 162	92.10 243	73.86 194	97.96 163	80.75 233	91.70 181	97.19 107

sss		88.93 154	88.26 156	90.94 187	94.05 191	80.78 192	91.71 274	95.38 182	81.55 255	88.63 144	93.91 182	75.04 174	95.47 316	82.47 200	91.61 182	96.57 136

cascas		86.43 243	84.98 251	90.80 190	92.10 256	80.92 188	90.24 301	95.91 139	73.10 351	83.57 268	88.39 326	65.15 296	97.46 197	84.90 166	91.43 183	94.03 244

Effi-MVS+-dtu		88.65 162	88.35 150	89.54 243	93.33 220	76.39 294	94.47 156	94.36 233	87.70 112	85.43 219	89.56 311	73.45 200	97.26 222	85.57 159	91.28 184	94.97 192

thres100view900		87.63 192	86.71 194	90.38 209	96.12 97	78.55 248	95.03 122	91.58 309	87.15 122	88.06 153	92.29 234	68.91 260	98.10 144	70.13 325	91.10 185	94.48 223

tfpn200view9		87.58 197	86.64 197	90.41 206	95.99 108	78.64 246	94.58 148	91.98 299	86.94 129	88.09 150	91.77 253	69.18 257	98.10 144	70.13 325	91.10 185	94.48 223

thres600view7		87.65 189	86.67 196	90.59 193	96.08 101	78.72 244	94.88 130	91.58 309	87.06 125	88.08 152	92.30 233	68.91 260	98.10 144	70.05 328	91.10 185	94.96 195

thres400		87.62 194	86.64 197	90.57 194	95.99 108	78.64 246	94.58 148	91.98 299	86.94 129	88.09 150	91.77 253	69.18 257	98.10 144	70.13 325	91.10 185	94.96 195

F-COLMAP		87.95 180	86.80 190	91.40 162	96.35 92	80.88 189	94.73 140	95.45 176	79.65 279	82.04 288	94.61 151	71.13 224	98.50 108	76.24 285	91.05 189	94.80 204

thres200		87.21 216	86.24 215	90.12 219	95.36 130	78.53 249	93.26 226	92.10 293	86.42 140	88.00 155	91.11 277	69.24 256	98.00 160	69.58 329	91.04 190	93.83 254

WTY-MVS		89.60 128	88.92 132	91.67 151	95.47 127	81.15 181	92.38 254	94.78 218	83.11 215	89.06 139	94.32 160	78.67 133	96.61 260	81.57 220	90.89 191	97.24 104

HY-MVS	83.01 12	89.03 151	87.94 163	92.29 123	94.86 155	82.77 136	92.08 268	94.49 226	81.52 256	86.93 176	92.79 220	78.32 139	98.23 135	79.93 245	90.55 192	95.88 162

CLD-MVS		89.47 133	88.90 134	91.18 171	94.22 186	82.07 156	92.13 265	96.09 124	87.90 105	85.37 225	92.45 228	74.38 183	97.56 188	87.15 139	90.43 193	93.93 246
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CVMVSNet		84.69 273	84.79 257	84.37 335	91.84 265	64.92 371	93.70 207	91.47 314	66.19 373	86.16 197	95.28 120	67.18 274	93.33 345	80.89 231	90.42 194	94.88 200

SCA		86.32 244	85.18 247	89.73 238	92.15 252	76.60 290	91.12 286	91.69 306	83.53 205	85.50 212	88.81 319	66.79 280	96.48 270	76.65 279	90.35 195	96.12 151

Fast-Effi-MVS+-dtu		87.44 203	86.72 193	89.63 241	92.04 257	77.68 276	94.03 188	93.94 247	85.81 152	82.42 282	91.32 268	70.33 239	97.06 237	80.33 241	90.23 196	94.14 236

OPM-MVS		90.12 112	89.56 115	91.82 145	93.14 224	83.90 98	94.16 176	95.74 152	88.96 71	87.86 156	95.43 117	72.48 213	97.91 167	88.10 126	90.18 197	93.65 267
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		90.60 106	90.19 100	91.82 145	94.70 163	82.73 140	95.85 75	96.22 113	90.81 17	86.91 178	94.86 138	74.23 185	98.12 142	88.15 122	89.99 198	94.63 207

plane_prior5								96.22 113					98.12 142	88.15 122	89.99 198	94.63 207

XVG-OURS		89.40 139	88.70 138	91.52 156	94.06 190	81.46 172	91.27 283	96.07 126	86.14 148	88.89 141	95.77 106	68.73 263	97.26 222	87.39 135	89.96 200	95.83 165

baseline2		86.50 240	85.39 242	89.84 231	91.12 294	76.70 289	91.88 269	88.58 355	82.35 232	79.95 315	90.95 281	73.42 201	97.63 184	80.27 242	89.95 201	95.19 186

Anonymous202405211		87.68 187	86.13 217	92.31 121	96.66 79	80.74 193	94.87 131	91.49 313	80.47 270	89.46 133	95.44 115	54.72 354	98.23 135	82.19 206	89.89 202	97.97 72

plane_prior						82.73 140	95.21 109		89.66 48						89.88 203

SDMVSNet		90.19 111	89.61 114	91.93 136	96.00 105	83.09 126	92.89 240	95.98 132	88.73 76	86.85 182	95.20 126	72.09 217	97.08 234	88.90 115	89.85 204	95.63 174

sd_testset		88.59 165	87.85 165	90.83 188	96.00 105	80.42 201	92.35 256	94.71 221	88.73 76	86.85 182	95.20 126	67.31 270	96.43 275	79.64 249	89.85 204	95.63 174

TR-MVS		86.78 229	85.76 235	89.82 232	94.37 181	78.41 253	92.47 251	92.83 272	81.11 265	86.36 192	92.40 229	68.73 263	97.48 195	73.75 306	89.85 204	93.57 269

HQP3-MVS								96.04 129							89.77 207

HQP-MVS		89.80 124	89.28 125	91.34 165	94.17 187	81.56 166	94.39 163	96.04 129	88.81 72	85.43 219	93.97 177	73.83 195	97.96 163	87.11 141	89.77 207	94.50 220

XVG-OURS-SEG-HR		89.95 119	89.45 117	91.47 160	94.00 196	81.21 180	91.87 270	96.06 128	85.78 153	88.55 145	95.73 108	74.67 181	97.27 220	88.71 118	89.64 209	95.91 160

GA-MVS		86.61 234	85.27 246	90.66 192	91.33 286	78.71 245	90.40 296	93.81 255	85.34 166	85.12 229	89.57 310	61.25 323	97.11 233	80.99 229	89.59 210	96.15 148

1112_ss		88.42 167	87.33 176	91.72 149	94.92 151	80.98 185	92.97 238	94.54 225	78.16 304	83.82 260	93.88 183	78.78 131	97.91 167	79.45 251	89.41 211	96.26 146

ab-mvs		89.41 137	88.35 150	92.60 106	95.15 140	82.65 145	92.20 263	95.60 165	83.97 193	88.55 145	93.70 191	74.16 189	98.21 138	82.46 201	89.37 212	96.94 121

CR-MVSNet		85.35 260	83.76 271	90.12 219	90.58 317	79.34 234	85.24 362	91.96 301	78.27 301	85.55 206	87.87 336	71.03 226	95.61 308	73.96 304	89.36 213	95.40 180

RPMNet		83.95 281	81.53 290	91.21 169	90.58 317	79.34 234	85.24 362	96.76 75	71.44 362	85.55 206	82.97 369	70.87 229	98.91 80	61.01 365	89.36 213	95.40 180

DSMNet-mixed		76.94 334	76.29 333	78.89 354	83.10 375	56.11 390	87.78 340	79.77 382	60.65 379	75.64 347	88.71 322	61.56 320	88.34 377	60.07 368	89.29 215	92.21 317

LPG-MVS_test		89.45 134	88.90 134	91.12 173	94.47 175	81.49 170	95.30 101	96.14 118	86.73 135	85.45 216	95.16 128	69.89 243	98.10 144	87.70 130	89.23 216	93.77 260

LGP-MVS_train				91.12 173	94.47 175	81.49 170		96.14 118	86.73 135	85.45 216	95.16 128	69.89 243	98.10 144	87.70 130	89.23 216	93.77 260

Test_1112_low_res		87.65 189	86.51 204	91.08 177	94.94 150	79.28 238	91.77 272	94.30 235	76.04 322	83.51 269	92.37 230	77.86 144	97.73 176	78.69 259	89.13 218	96.22 147

PatchmatchNet		85.85 251	84.70 258	89.29 249	91.76 269	75.54 303	88.49 332	91.30 317	81.63 253	85.05 230	88.70 323	71.71 218	96.24 284	74.61 300	89.05 219	96.08 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
iter_conf_final		89.42 136	88.69 139	91.60 153	95.12 141	82.93 133	95.75 81	92.14 292	87.32 120	87.12 173	94.07 168	67.09 275	97.55 189	90.61 99	89.01 220	94.32 229

iter_conf05		88.85 155	88.08 159	91.17 172	94.27 185	81.64 165	95.18 111	92.15 291	86.23 145	87.28 170	94.07 168	63.89 306	97.55 189	90.63 98	89.00 221	94.32 229

MDTV_nov1_ep13			83.56 274		91.69 274	69.93 355	87.75 342	91.54 311	78.60 295	84.86 233	88.90 318	69.54 248	96.03 291	70.25 322	88.93 222

MIMVSNet		82.59 291	80.53 296	88.76 261	91.51 277	78.32 256	86.57 353	90.13 339	79.32 281	80.70 303	88.69 324	52.98 361	93.07 350	66.03 349	88.86 223	94.90 199

ACMM	84.12 9	89.14 144	88.48 149	91.12 173	94.65 166	81.22 179	95.31 99	96.12 121	85.31 167	85.92 199	94.34 158	70.19 241	98.06 156	85.65 157	88.86 223	94.08 241
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvsmamba		89.96 118	89.50 116	91.33 166	92.90 236	81.82 161	96.68 33	92.37 283	89.03 67	87.00 174	94.85 140	73.05 205	97.65 180	91.03 89	88.63 225	94.51 217

ACMP	84.23 8	89.01 153	88.35 150	90.99 184	94.73 160	81.27 176	95.07 119	95.89 142	86.48 138	83.67 264	94.30 161	69.33 252	97.99 161	87.10 143	88.55 226	93.72 264
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		89.03 151	88.64 140	90.21 213	90.74 312	79.28 238	95.96 71	95.90 140	84.66 183	85.33 227	92.94 213	74.02 191	97.30 216	89.64 107	88.53 227	94.05 243

jajsoiax		88.24 173	87.50 171	90.48 202	90.89 306	80.14 208	95.31 99	95.65 162	84.97 175	84.24 253	94.02 173	65.31 295	97.42 202	88.56 119	88.52 228	93.89 247

PatchT		82.68 290	81.27 292	86.89 310	90.09 327	70.94 349	84.06 369	90.15 338	74.91 333	85.63 205	83.57 364	69.37 250	94.87 325	65.19 351	88.50 229	94.84 201

MSDG		84.86 270	83.09 279	90.14 218	93.80 204	80.05 213	89.18 323	93.09 266	78.89 288	78.19 329	91.91 250	65.86 293	97.27 220	68.47 334	88.45 230	93.11 288

MVS-HIRNet		73.70 339	72.20 342	78.18 357	91.81 268	56.42 389	82.94 375	82.58 376	55.24 381	68.88 371	66.48 385	55.32 351	95.13 320	58.12 372	88.42 231	83.01 374

mvs_tets		88.06 179	87.28 178	90.38 209	90.94 302	79.88 220	95.22 108	95.66 160	85.10 172	84.21 254	93.94 178	63.53 307	97.40 209	88.50 120	88.40 232	93.87 250

ET-MVSNet_ETH3D		87.51 200	85.91 229	92.32 120	93.70 210	83.93 97	92.33 258	90.94 326	84.16 188	72.09 363	92.52 226	69.90 242	95.85 300	89.20 112	88.36 233	97.17 108

FIs		90.51 107	90.35 97	90.99 184	93.99 197	80.98 185	95.73 82	97.54 4	89.15 62	86.72 185	94.68 148	81.83 102	97.24 224	85.18 161	88.31 234	94.76 205

PS-MVSNAJss		89.97 117	89.62 113	91.02 181	91.90 263	80.85 190	95.26 106	95.98 132	86.26 143	86.21 195	94.29 162	79.70 119	97.65 180	88.87 117	88.10 235	94.57 212

CMPMVS	59.16 21	80.52 312	79.20 316	84.48 334	83.98 372	67.63 364	89.95 310	93.84 254	64.79 375	66.81 374	91.14 276	57.93 342	95.17 319	76.25 284	88.10 235	90.65 344
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FC-MVSNet-test		90.27 109	90.18 101	90.53 196	93.71 208	79.85 222	95.77 80	97.59 3	89.31 56	86.27 194	94.67 149	81.93 101	97.01 240	84.26 174	88.09 237	94.71 206

ACMMP++															88.01 238

D2MVS		85.90 249	85.09 249	88.35 272	90.79 309	77.42 279	91.83 271	95.70 156	80.77 268	80.08 313	90.02 301	66.74 282	96.37 278	81.88 213	87.97 239	91.26 335

UniMVSNet_ETH3D		87.53 199	86.37 208	91.00 183	92.44 246	78.96 243	94.74 139	95.61 164	84.07 191	85.36 226	94.52 155	59.78 335	97.34 214	82.93 191	87.88 240	96.71 132

PVSNet_BlendedMVS		89.98 116	89.70 112	90.82 189	96.12 97	81.25 177	93.92 197	96.83 66	83.49 206	89.10 137	92.26 235	81.04 107	98.85 86	86.72 146	87.86 241	92.35 313

Syy-MVS		80.07 317	79.78 306	80.94 350	91.92 261	59.93 381	89.75 312	87.40 362	81.72 249	78.82 325	87.20 343	66.29 288	91.29 364	47.06 382	87.84 242	91.60 327

myMVS_eth3d		79.67 322	78.79 321	82.32 348	91.92 261	64.08 373	89.75 312	87.40 362	81.72 249	78.82 325	87.20 343	45.33 375	91.29 364	59.09 371	87.84 242	91.60 327

bld_raw_dy_0_64		87.60 196	86.73 192	90.21 213	91.72 270	80.26 205	95.09 118	88.61 354	85.68 157	85.55 206	94.38 157	63.93 305	96.66 254	87.73 129	87.84 242	93.72 264

anonymousdsp		87.84 182	87.09 181	90.12 219	89.13 339	80.54 198	94.67 144	95.55 167	82.05 236	83.82 260	92.12 240	71.47 222	97.15 229	87.15 139	87.80 245	92.67 301

testing3		80.46 313	79.59 311	83.06 343	93.44 218	64.64 372	93.33 218	85.47 367	84.34 187	79.93 316	90.84 284	44.35 377	92.39 354	57.06 375	87.56 246	92.16 318

Anonymous20240529		88.09 177	86.59 201	92.58 108	96.53 86	81.92 160	95.99 69	95.84 145	74.11 341	89.06 139	95.21 125	61.44 321	98.81 89	83.67 184	87.47 247	97.01 117

ACMMP++_ref															87.47 247

XVG-ACMP-BASELINE		86.00 247	84.84 256	89.45 247	91.20 288	78.00 263	91.70 275	95.55 167	85.05 174	82.97 277	92.25 236	54.49 355	97.48 195	82.93 191	87.45 249	92.89 296

EI-MVSNet		89.10 145	88.86 136	89.80 235	91.84 265	78.30 257	93.70 207	95.01 199	85.73 155	87.15 171	95.28 120	79.87 116	97.21 227	83.81 181	87.36 250	93.88 249

MVSTER		88.84 156	88.29 154	90.51 199	92.95 234	80.44 200	93.73 204	95.01 199	84.66 183	87.15 171	93.12 208	72.79 209	97.21 227	87.86 127	87.36 250	93.87 250

EG-PatchMatch MVS		82.37 293	80.34 299	88.46 269	90.27 323	79.35 233	92.80 244	94.33 234	77.14 312	73.26 360	90.18 297	47.47 372	96.72 251	70.25 322	87.32 252	89.30 356

EPMVS		83.90 283	82.70 285	87.51 290	90.23 325	72.67 328	88.62 331	81.96 378	81.37 258	85.01 231	88.34 327	66.31 287	94.45 326	75.30 292	87.12 253	95.43 179

tpm2		84.08 278	82.94 281	87.48 293	91.39 282	71.27 343	89.23 322	90.37 334	71.95 360	84.64 236	89.33 312	67.30 271	96.55 267	75.17 293	87.09 254	94.63 207

CostFormer		85.77 253	84.94 253	88.26 275	91.16 292	72.58 333	89.47 318	91.04 324	76.26 320	86.45 190	89.97 303	70.74 231	96.86 249	82.35 203	87.07 255	95.34 183

Patchmatch-test		81.37 305	79.30 313	87.58 289	90.92 304	74.16 315	80.99 378	87.68 360	70.52 366	76.63 341	88.81 319	71.21 223	92.76 352	60.01 369	86.93 256	95.83 165

RRT_MVS		89.09 147	88.62 143	90.49 200	92.85 237	79.65 226	96.41 39	94.41 230	88.22 94	85.50 212	94.77 144	69.36 251	97.31 215	89.33 110	86.73 257	94.51 217

mvsany_test1		85.42 258	85.30 245	85.77 324	87.95 355	75.41 305	87.61 346	80.97 380	76.82 314	88.68 143	95.83 102	77.44 146	90.82 368	85.90 154	86.51 258	91.08 342

test_fmvs2		83.98 279	84.03 266	83.83 340	87.16 358	67.53 365	93.93 196	92.89 270	77.62 306	86.89 181	93.53 193	47.18 373	92.02 358	90.54 100	86.51 258	91.93 321

LTVRE_ROB	82.13 13	86.26 245	84.90 254	90.34 211	94.44 179	81.50 168	92.31 260	94.89 208	83.03 217	79.63 320	92.67 221	69.69 246	97.79 170	71.20 316	86.26 260	91.72 324
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
COLMAP_ROB	80.39 16	83.96 280	82.04 287	89.74 236	95.28 132	79.75 223	94.25 171	92.28 287	75.17 330	78.02 332	93.77 188	58.60 340	97.84 169	65.06 354	85.92 261	91.63 326
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RPSCF		85.07 266	84.27 263	87.48 293	92.91 235	70.62 351	91.69 276	92.46 281	76.20 321	82.67 281	95.22 123	63.94 303	97.29 219	77.51 272	85.80 262	94.53 214

USDC		82.76 288	81.26 293	87.26 297	91.17 290	74.55 309	89.27 320	93.39 262	78.26 302	75.30 349	92.08 244	54.43 356	96.63 256	71.64 313	85.79 263	90.61 345

dmvs_re		84.20 277	83.22 278	87.14 304	91.83 267	77.81 270	90.04 307	90.19 337	84.70 182	81.49 292	89.17 314	64.37 301	91.13 366	71.58 314	85.65 264	92.46 308

GBi-Net		87.26 210	85.98 225	91.08 177	94.01 193	83.10 123	95.14 115	94.94 202	83.57 202	84.37 245	91.64 256	66.59 284	96.34 281	78.23 264	85.36 265	93.79 255

test1		87.26 210	85.98 225	91.08 177	94.01 193	83.10 123	95.14 115	94.94 202	83.57 202	84.37 245	91.64 256	66.59 284	96.34 281	78.23 264	85.36 265	93.79 255

FMVSNet3		87.40 205	86.11 219	91.30 167	93.79 206	83.64 106	94.20 175	94.81 216	83.89 195	84.37 245	91.87 252	68.45 266	96.56 265	78.23 264	85.36 265	93.70 266

FMVSNet2		87.19 218	85.82 231	91.30 167	94.01 193	83.67 104	94.79 136	94.94 202	83.57 202	83.88 259	92.05 247	66.59 284	96.51 268	77.56 271	85.01 268	93.73 263

ACMH	80.38 17	85.36 259	83.68 272	90.39 207	94.45 178	80.63 195	94.73 140	94.85 212	82.09 235	77.24 336	92.65 222	60.01 333	97.58 186	72.25 312	84.87 269	92.96 293
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ITE_SJBPF				88.24 276	91.88 264	77.05 284		92.92 269	85.54 162	80.13 312	93.30 200	57.29 344	96.20 285	72.46 311	84.71 270	91.49 330

JIA-IIPM		81.04 308	78.98 320	87.25 298	88.64 343	73.48 320	81.75 377	89.61 351	73.19 350	82.05 287	73.71 381	66.07 292	95.87 299	71.18 318	84.60 271	92.41 310

tt0805		86.92 225	85.74 237	90.48 202	92.22 250	79.98 218	95.63 90	94.88 210	83.83 197	84.74 235	92.80 219	57.61 343	97.67 177	85.48 160	84.42 272	93.79 255

OpenMVS_ROB	74.94 19	79.51 323	77.03 330	86.93 307	87.00 359	76.23 297	92.33 258	90.74 331	68.93 369	74.52 354	88.23 330	49.58 367	96.62 257	57.64 373	84.29 273	87.94 368

AllTest		83.42 285	81.39 291	89.52 244	95.01 144	77.79 272	93.12 230	90.89 328	77.41 308	76.12 344	93.34 196	54.08 357	97.51 193	68.31 336	84.27 274	93.26 279

TestCases				89.52 244	95.01 144	77.79 272		90.89 328	77.41 308	76.12 344	93.34 196	54.08 357	97.51 193	68.31 336	84.27 274	93.26 279

tpm		84.73 271	84.02 267	86.87 311	90.33 322	68.90 358	89.06 325	89.94 344	80.85 267	85.75 201	89.86 305	68.54 265	95.97 294	77.76 268	84.05 276	95.75 168

FMVSNet1		85.85 251	84.11 265	91.08 177	92.81 238	83.10 123	95.14 115	94.94 202	81.64 252	82.68 280	91.64 256	59.01 339	96.34 281	75.37 291	83.78 277	93.79 255

ADS-MVSNet2		81.66 300	79.71 309	87.50 291	91.35 284	74.19 314	83.33 372	88.48 356	72.90 353	82.24 285	85.77 355	64.98 297	93.20 348	64.57 355	83.74 278	95.12 188

ADS-MVSNet		81.56 302	79.78 306	86.90 309	91.35 284	71.82 338	83.33 372	89.16 353	72.90 353	82.24 285	85.77 355	64.98 297	93.76 339	64.57 355	83.74 278	95.12 188

XXY-MVS		87.65 189	86.85 188	90.03 223	92.14 253	80.60 197	93.76 203	95.23 189	82.94 220	84.60 237	94.02 173	74.27 184	95.49 315	81.04 226	83.68 280	94.01 245

test_0402		81.30 307	79.17 317	87.67 287	93.19 223	78.17 260	92.98 237	91.71 304	75.25 329	76.02 346	90.31 295	59.23 337	96.37 278	50.22 380	83.63 281	88.47 365

tpmvs		83.35 287	82.07 286	87.20 302	91.07 296	71.00 348	88.31 335	91.70 305	78.91 287	80.49 307	87.18 345	69.30 255	97.08 234	68.12 339	83.56 282	93.51 273

pmmvs5		84.21 276	82.84 284	88.34 273	88.95 341	76.94 285	92.41 252	91.91 303	75.63 325	80.28 308	91.18 273	64.59 299	95.57 309	77.09 277	83.47 283	92.53 305

pmmvs4		85.43 257	83.86 270	90.16 216	90.02 329	82.97 132	90.27 297	92.67 278	75.93 323	80.73 302	91.74 255	71.05 225	95.73 307	78.85 258	83.46 284	91.78 323

test0.0.03 1		82.41 292	81.69 288	84.59 333	88.23 350	72.89 324	90.24 301	87.83 358	83.41 208	79.86 317	89.78 307	67.25 272	88.99 376	65.18 352	83.42 285	91.90 322

tpmrst		85.35 260	84.99 250	86.43 316	90.88 307	67.88 362	88.71 329	91.43 315	80.13 273	86.08 198	88.80 321	73.05 205	96.02 292	82.48 199	83.40 286	95.40 180

nrg030		91.08 94	90.39 96	93.17 74	93.07 227	86.91 21	96.41 39	96.26 108	88.30 90	88.37 149	94.85 140	82.19 95	97.64 183	91.09 87	82.95 287	94.96 195

cl22		86.78 229	85.98 225	89.18 252	92.34 248	77.62 277	90.84 290	94.13 243	81.33 259	83.97 258	90.15 298	73.96 192	96.60 262	84.19 175	82.94 288	93.33 277

miper_ehance_all_eth		87.22 215	86.62 200	89.02 257	92.13 254	77.40 280	90.91 289	94.81 216	81.28 260	84.32 250	90.08 300	79.26 125	96.62 257	83.81 181	82.94 288	93.04 291

miper_enhance_ethall		86.90 226	86.18 216	89.06 255	91.66 275	77.58 278	90.22 303	94.82 215	79.16 285	84.48 241	89.10 315	79.19 127	96.66 254	84.06 176	82.94 288	92.94 294

ACMH+	81.04 14	85.05 267	83.46 275	89.82 232	94.66 165	79.37 232	94.44 158	94.12 244	82.19 234	78.04 331	92.82 217	58.23 341	97.54 191	73.77 305	82.90 291	92.54 304

VPA-MVSNet		89.62 127	88.96 130	91.60 153	93.86 201	82.89 135	95.46 94	97.33 25	87.91 104	88.43 148	93.31 199	74.17 188	97.40 209	87.32 137	82.86 292	94.52 215

IterMVS-LS		88.36 170	87.91 164	89.70 239	93.80 204	78.29 258	93.73 204	95.08 198	85.73 155	84.75 234	91.90 251	79.88 115	96.92 245	83.83 180	82.51 293	93.89 247
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testgi		80.94 311	80.20 302	83.18 341	87.96 354	66.29 366	91.28 282	90.70 332	83.70 199	78.12 330	92.84 215	51.37 363	90.82 368	63.34 358	82.46 294	92.43 309

test_vis1_rt		77.96 331	76.46 331	82.48 346	85.89 365	71.74 340	90.25 299	78.89 384	71.03 365	71.30 367	81.35 373	42.49 379	91.05 367	84.55 171	82.37 295	84.65 371

WR-MVS		88.38 168	87.67 168	90.52 198	93.30 221	80.18 206	93.26 226	95.96 135	88.57 83	85.47 215	92.81 218	76.12 157	96.91 246	81.24 224	82.29 296	94.47 225

tpm cat1		81.96 294	80.27 300	87.01 305	91.09 295	71.02 347	87.38 347	91.53 312	66.25 372	80.17 309	86.35 351	68.22 268	96.15 288	69.16 330	82.29 296	93.86 252

v1192		87.25 212	86.33 210	90.00 227	90.76 311	79.04 242	93.80 201	95.48 172	82.57 227	85.48 214	91.18 273	73.38 203	97.42 202	82.30 204	82.06 298	93.53 270

v1144		87.61 195	86.79 191	90.06 222	91.01 297	79.34 234	93.95 194	95.42 181	83.36 210	85.66 204	91.31 269	74.98 175	97.42 202	83.37 185	82.06 298	93.42 276

v1240		86.78 229	85.85 230	89.56 242	90.45 321	77.79 272	93.61 209	95.37 184	81.65 251	85.43 219	91.15 275	71.50 221	97.43 201	81.47 222	82.05 300	93.47 274

Anonymous20231206		81.03 309	79.77 308	84.82 332	87.85 356	70.26 353	91.42 280	92.08 294	73.67 345	77.75 333	89.25 313	62.43 314	93.08 349	61.50 364	82.00 301	91.12 339

V42		87.68 187	86.86 187	90.15 217	90.58 317	80.14 208	94.24 173	95.28 187	83.66 200	85.67 203	91.33 266	74.73 179	97.41 207	84.43 173	81.83 302	92.89 296

v1921920		86.97 224	86.06 222	89.69 240	90.53 320	78.11 262	93.80 201	95.43 179	81.90 243	85.33 227	91.05 279	72.66 210	97.41 207	82.05 209	81.80 303	93.53 270

v2v482		87.84 182	87.06 182	90.17 215	90.99 298	79.23 241	94.00 192	95.13 193	84.87 176	85.53 209	92.07 246	74.45 182	97.45 198	84.71 169	81.75 304	93.85 253

Anonymous20231211		86.59 236	85.13 248	90.98 186	96.52 87	81.50 168	96.14 57	96.16 117	73.78 344	83.65 265	92.15 238	63.26 310	97.37 213	82.82 195	81.74 305	94.06 242

v144192		87.19 218	86.35 209	89.74 236	90.64 315	78.24 259	93.92 197	95.43 179	81.93 241	85.51 211	91.05 279	74.21 187	97.45 198	82.86 193	81.56 306	93.53 270

cl____		86.52 239	85.78 232	88.75 262	92.03 258	76.46 292	90.74 291	94.30 235	81.83 247	83.34 273	90.78 287	75.74 167	96.57 263	81.74 217	81.54 307	93.22 283

DIV-MVS_self_test		86.53 238	85.78 232	88.75 262	92.02 259	76.45 293	90.74 291	94.30 235	81.83 247	83.34 273	90.82 285	75.75 165	96.57 263	81.73 218	81.52 308	93.24 282

Anonymous20240521		80.44 314	79.21 315	84.11 338	85.75 367	67.89 361	92.86 242	93.23 264	75.61 326	75.59 348	87.47 340	50.03 365	94.33 330	71.14 319	81.21 309	90.12 350

OurMVSNet-221017-0		85.35 260	84.64 260	87.49 292	90.77 310	72.59 332	94.01 190	94.40 231	84.72 181	79.62 321	93.17 205	61.91 317	96.72 251	81.99 210	81.16 310	93.16 286

FMVSNet5		81.52 303	79.60 310	87.27 296	91.17 290	77.95 264	91.49 279	92.26 288	76.87 313	76.16 343	87.91 335	51.67 362	92.34 355	67.74 340	81.16 310	91.52 329

CP-MVSNet		87.63 192	87.26 180	88.74 264	93.12 225	76.59 291	95.29 103	96.58 91	88.43 86	83.49 270	92.98 212	75.28 171	95.83 301	78.97 257	81.15 312	93.79 255

c3_l		87.14 220	86.50 205	89.04 256	92.20 251	77.26 281	91.22 285	94.70 222	82.01 239	84.34 249	90.43 293	78.81 130	96.61 260	83.70 183	81.09 313	93.25 281

IterMVS-SCA-FT		85.45 256	84.53 262	88.18 278	91.71 272	76.87 286	90.19 304	92.65 279	85.40 165	81.44 294	90.54 290	66.79 280	95.00 324	81.04 226	81.05 314	92.66 302

TinyColmap		79.76 321	77.69 324	85.97 320	91.71 272	73.12 322	89.55 314	90.36 335	75.03 331	72.03 364	90.19 296	46.22 374	96.19 287	63.11 359	81.03 315	88.59 364

UniMVSNet_NR-MVSNet		89.92 121	89.29 124	91.81 147	93.39 219	83.72 102	94.43 159	97.12 41	89.80 41	86.46 188	93.32 198	83.16 77	97.23 225	84.92 164	81.02 316	94.49 222

DU-MVS		89.34 142	88.50 146	91.85 144	93.04 229	83.72 102	94.47 156	96.59 90	89.50 50	86.46 188	93.29 201	77.25 147	97.23 225	84.92 164	81.02 316	94.59 210

PS-CasMVS		87.32 209	86.88 186	88.63 267	92.99 232	76.33 296	95.33 98	96.61 89	88.22 94	83.30 275	93.07 210	73.03 207	95.79 304	78.36 261	81.00 318	93.75 262

IterMVS		84.88 269	83.98 269	87.60 288	91.44 278	76.03 298	90.18 305	92.41 282	83.24 213	81.06 300	90.42 294	66.60 283	94.28 332	79.46 250	80.98 319	92.48 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet (Re)		89.80 124	89.07 128	92.01 128	93.60 213	84.52 81	94.78 137	97.47 11	89.26 58	86.44 191	92.32 232	82.10 96	97.39 212	84.81 167	80.84 320	94.12 237

LF4IMVS		80.37 315	79.07 319	84.27 337	86.64 360	69.87 356	89.39 319	91.05 323	76.38 317	74.97 351	90.00 302	47.85 371	94.25 333	74.55 301	80.82 321	88.69 363

v10		87.25 212	86.38 207	89.85 230	91.19 289	79.50 228	94.48 153	95.45 176	83.79 198	83.62 266	91.19 271	75.13 172	97.42 202	81.94 211	80.60 322	92.63 303

tfpnnormal		84.72 272	83.23 277	89.20 251	92.79 239	80.05 213	94.48 153	95.81 146	82.38 230	81.08 299	91.21 270	69.01 259	96.95 243	61.69 363	80.59 323	90.58 348

WR-MVS_H		87.80 184	87.37 175	89.10 254	93.23 222	78.12 261	95.61 91	97.30 29	87.90 105	83.72 262	92.01 248	79.65 123	96.01 293	76.36 282	80.54 324	93.16 286

VPNet		88.20 174	87.47 173	90.39 207	93.56 214	79.46 229	94.04 187	95.54 169	88.67 79	86.96 175	94.58 154	69.33 252	97.15 229	84.05 177	80.53 325	94.56 213

v7n		86.81 227	85.76 235	89.95 228	90.72 313	79.25 240	95.07 119	95.92 137	84.45 186	82.29 283	90.86 282	72.60 212	97.53 192	79.42 254	80.52 326	93.08 290

v8		87.50 202	86.71 194	89.89 229	91.37 283	79.40 231	94.50 152	95.38 182	84.81 179	83.60 267	91.33 266	76.05 158	97.42 202	82.84 194	80.51 327	92.84 298

EU-MVSNet		81.32 306	80.95 294	82.42 347	88.50 346	63.67 375	93.32 219	91.33 316	64.02 376	80.57 306	92.83 216	61.21 325	92.27 356	76.34 283	80.38 328	91.32 333

Patchmtry		82.71 289	80.93 295	88.06 280	90.05 328	76.37 295	84.74 367	91.96 301	72.28 359	81.32 297	87.87 336	71.03 226	95.50 314	68.97 331	80.15 329	92.32 314

NR-MVSNet		88.58 166	87.47 173	91.93 136	93.04 229	84.16 93	94.77 138	96.25 110	89.05 65	80.04 314	93.29 201	79.02 128	97.05 238	81.71 219	80.05 330	94.59 210

Baseline_NR-MVSNet		87.07 221	86.63 199	88.40 270	91.44 278	77.87 268	94.23 174	92.57 280	84.12 190	85.74 202	92.08 244	77.25 147	96.04 290	82.29 205	79.94 331	91.30 334

dp		81.47 304	80.23 301	85.17 330	89.92 331	65.49 369	86.74 351	90.10 340	76.30 319	81.10 298	87.12 346	62.81 312	95.92 296	68.13 338	79.88 332	94.09 240

TranMVSNet+NR-MVSNet		88.84 156	87.95 162	91.49 158	92.68 241	83.01 130	94.92 128	96.31 103	89.88 39	85.53 209	93.85 185	76.63 155	96.96 242	81.91 212	79.87 333	94.50 220

miper_lstm_enhance		85.27 263	84.59 261	87.31 295	91.28 287	74.63 308	87.69 343	94.09 245	81.20 264	81.36 296	89.85 306	74.97 176	94.30 331	81.03 228	79.84 334	93.01 292

v148		87.04 222	86.32 211	89.21 250	90.94 302	77.26 281	93.71 206	94.43 228	84.84 178	84.36 248	90.80 286	76.04 159	97.05 238	82.12 207	79.60 335	93.31 278

IB-MVS	80.51 15	85.24 264	83.26 276	91.19 170	92.13 254	79.86 221	91.75 273	91.29 318	83.28 212	80.66 304	88.49 325	61.28 322	98.46 113	80.99 229	79.46 336	95.25 185
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
eth_miper_zixun_eth		86.50 240	85.77 234	88.68 265	91.94 260	75.81 301	90.47 295	94.89 208	82.05 236	84.05 255	90.46 292	75.96 160	96.77 250	82.76 197	79.36 337	93.46 275

baseline1		88.10 176	87.28 178	90.57 194	94.96 148	80.07 211	94.27 170	91.29 318	86.74 134	87.41 166	94.00 175	76.77 152	96.20 285	80.77 232	79.31 338	95.44 178

our_test_3		81.93 295	80.46 298	86.33 318	88.46 347	73.48 320	88.46 333	91.11 320	76.46 315	76.69 340	88.25 329	66.89 278	94.36 329	68.75 332	79.08 339	91.14 338

PEN-MVS		86.80 228	86.27 214	88.40 270	92.32 249	75.71 302	95.18 111	96.38 100	87.97 102	82.82 279	93.15 206	73.39 202	95.92 296	76.15 286	79.03 340	93.59 268

pm-mvs1		86.61 234	85.54 238	89.82 232	91.44 278	80.18 206	95.28 105	94.85 212	83.84 196	81.66 291	92.62 223	72.45 215	96.48 270	79.67 248	78.06 341	92.82 299

h-mvs33		90.80 96	90.15 102	92.75 98	96.01 104	82.66 144	95.43 95	95.53 170	89.80 41	93.08 61	95.64 111	75.77 162	99.00 68	92.07 68	78.05 342	96.60 134

SixPastTwentyTwo		83.91 282	82.90 282	86.92 308	90.99 298	70.67 350	93.48 213	91.99 298	85.54 162	77.62 335	92.11 242	60.59 329	96.87 248	76.05 287	77.75 343	93.20 284

ppachtmachnet_test		81.84 296	80.07 304	87.15 303	88.46 347	74.43 312	89.04 326	92.16 290	75.33 328	77.75 333	88.99 316	66.20 289	95.37 317	65.12 353	77.60 344	91.65 325

MIMVSNet1		79.38 324	77.28 326	85.69 325	86.35 361	73.67 317	91.61 278	92.75 275	78.11 305	72.64 362	88.12 331	48.16 370	91.97 360	60.32 366	77.49 345	91.43 332

DTE-MVSNet		86.11 246	85.48 240	87.98 282	91.65 276	74.92 307	94.93 127	95.75 151	87.36 119	82.26 284	93.04 211	72.85 208	95.82 302	74.04 302	77.46 346	93.20 284

N_pmnet		68.89 344	68.44 346	70.23 365	89.07 340	28.79 402	88.06 336	19.50 402	69.47 368	71.86 365	84.93 358	61.24 324	91.75 361	54.70 377	77.15 347	90.15 349

AUN-MVS		87.78 185	86.54 203	91.48 159	94.82 158	81.05 183	93.91 199	93.93 248	83.00 218	86.93 176	93.53 193	69.50 249	97.67 177	86.14 149	77.12 348	95.73 171

hse-mvs2		89.88 123	89.34 122	91.51 157	94.83 157	81.12 182	93.94 195	93.91 251	89.80 41	93.08 61	93.60 192	75.77 162	97.66 179	92.07 68	77.07 349	95.74 169

dmvs_testset		74.57 338	75.81 337	70.86 364	87.72 357	40.47 397	87.05 350	77.90 389	82.75 224	71.15 368	85.47 357	67.98 269	84.12 386	45.26 383	76.98 350	88.00 367

test20.03		79.95 319	79.08 318	82.55 345	85.79 366	67.74 363	91.09 287	91.08 321	81.23 263	74.48 355	89.96 304	61.63 318	90.15 370	60.08 367	76.38 351	89.76 351

FPMVS		64.63 349	62.55 351	70.88 363	70.80 389	56.71 385	84.42 368	84.42 371	51.78 384	49.57 384	81.61 372	23.49 389	81.48 389	40.61 389	76.25 352	74.46 382

test_fmvs3		77.67 332	77.16 329	79.22 353	79.52 382	61.14 379	92.34 257	91.64 308	73.98 342	78.86 324	86.59 347	27.38 387	87.03 378	88.12 125	75.97 353	89.50 353

EGC-MVSNET		61.97 350	56.37 354	78.77 355	89.63 336	73.50 319	89.12 324	82.79 375	0.21 399	1.24 400	84.80 359	39.48 380	90.04 371	44.13 384	75.94 354	72.79 383

pmmvs6		83.42 285	81.60 289	88.87 259	88.01 353	77.87 268	94.96 125	94.24 238	74.67 336	78.80 327	91.09 278	60.17 332	96.49 269	77.06 278	75.40 355	92.23 316

new_pmnet		72.15 340	70.13 344	78.20 356	82.95 376	65.68 367	83.91 370	82.40 377	62.94 378	64.47 375	79.82 375	42.85 378	86.26 382	57.41 374	74.44 356	82.65 376

MDA-MVSNet_test_wron		79.21 326	77.19 328	85.29 328	88.22 351	72.77 326	85.87 356	90.06 341	74.34 338	62.62 378	87.56 339	66.14 290	91.99 359	66.90 347	73.01 357	91.10 341

YYNet1		79.22 325	77.20 327	85.28 329	88.20 352	72.66 329	85.87 356	90.05 343	74.33 339	62.70 376	87.61 338	66.09 291	92.03 357	66.94 344	72.97 358	91.15 337

Patchmatch-RL test		81.67 299	79.96 305	86.81 312	85.42 369	71.23 344	82.17 376	87.50 361	78.47 296	77.19 337	82.50 371	70.81 230	93.48 343	82.66 198	72.89 359	95.71 172

pmmvs-eth3d		80.97 310	78.72 322	87.74 285	84.99 371	79.97 219	90.11 306	91.65 307	75.36 327	73.51 358	86.03 352	59.45 336	93.96 337	75.17 293	72.21 360	89.29 357

PM-MVS		78.11 330	76.12 334	84.09 339	83.54 374	70.08 354	88.97 327	85.27 369	79.93 275	74.73 353	86.43 349	34.70 383	93.48 343	79.43 253	72.06 361	88.72 362

test_f		71.95 341	70.87 343	75.21 360	74.21 387	59.37 383	85.07 364	85.82 365	65.25 374	70.42 369	83.13 366	23.62 388	82.93 388	78.32 262	71.94 362	83.33 373

Gipuma		57.99 355	54.91 357	67.24 371	88.51 344	65.59 368	52.21 390	90.33 336	43.58 387	42.84 390	51.18 391	20.29 393	85.07 383	34.77 390	70.45 363	51.05 390
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD_test1		69.04 343	66.26 349	77.36 359	80.51 380	62.79 378	85.46 361	83.51 374	54.11 383	59.14 381	84.79 360	23.40 390	89.61 372	55.22 376	70.24 364	79.68 380

K. test v3		81.59 301	80.15 303	85.91 323	89.89 332	69.42 357	92.57 249	87.71 359	85.56 161	73.44 359	89.71 308	55.58 348	95.52 311	77.17 275	69.76 365	92.78 300

KD-MVS_self_test		80.20 316	79.24 314	83.07 342	85.64 368	65.29 370	91.01 288	93.93 248	78.71 294	76.32 342	86.40 350	59.20 338	92.93 351	72.59 310	69.35 366	91.00 343

CL-MVSNet_self_test		81.74 298	80.53 296	85.36 327	85.96 364	72.45 334	90.25 299	93.07 267	81.24 262	79.85 318	87.29 342	70.93 228	92.52 353	66.95 343	69.23 367	91.11 340

TDRefinement		79.81 320	77.34 325	87.22 301	79.24 383	75.48 304	93.12 230	92.03 296	76.45 316	75.01 350	91.58 262	49.19 368	96.44 274	70.22 324	69.18 368	89.75 352

MDA-MVSNet-bldmvs		78.85 327	76.31 332	86.46 315	89.76 333	73.88 316	88.79 328	90.42 333	79.16 285	59.18 380	88.33 328	60.20 331	94.04 334	62.00 362	68.96 369	91.48 331

ambc				83.06 343	79.99 381	63.51 376	77.47 383	92.86 271		74.34 356	84.45 361	28.74 384	95.06 323	73.06 309	68.89 370	90.61 345

TransMVSNet (Re)		84.43 275	83.06 280	88.54 268	91.72 270	78.44 252	95.18 111	92.82 273	82.73 225	79.67 319	92.12 240	73.49 199	95.96 295	71.10 320	68.73 371	91.21 336

mvsany_test3		74.95 337	73.26 341	80.02 352	74.61 385	63.16 377	85.53 360	78.42 385	74.16 340	74.89 352	86.46 348	36.02 382	89.09 375	82.39 202	66.91 372	87.82 369

PMVS	47.18 22	52.22 356	48.46 360	63.48 372	45.72 400	46.20 395	73.41 386	78.31 386	41.03 390	30.06 393	65.68 386	6.05 400	83.43 387	30.04 391	65.86 373	60.80 387
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		65.12 348	62.60 350	72.69 362	71.44 388	60.71 380	87.17 348	65.55 395	63.80 377	53.22 383	65.65 387	14.54 397	89.44 374	76.65 279	65.38 374	67.91 386

lessismore_v0				86.04 319	88.46 347	68.78 359		80.59 381		73.01 361	90.11 299	55.39 350	96.43 275	75.06 295	65.06 375	92.90 295

new-patchmatchnet		76.41 335	75.17 338	80.13 351	82.65 377	59.61 382	87.66 344	91.08 321	78.23 303	69.85 370	83.22 365	54.76 353	91.63 363	64.14 357	64.89 376	89.16 359

pmmvs3		71.81 342	68.71 345	81.11 349	75.86 384	70.42 352	86.74 351	83.66 373	58.95 380	68.64 373	80.89 374	36.93 381	89.52 373	63.10 360	63.59 377	83.39 372

UnsupCasMVSNet_eth		80.07 317	78.27 323	85.46 326	85.24 370	72.63 331	88.45 334	94.87 211	82.99 219	71.64 366	88.07 332	56.34 346	91.75 361	73.48 307	63.36 378	92.01 320

LCM-MVSNet		66.00 347	62.16 352	77.51 358	64.51 395	58.29 384	83.87 371	90.90 327	48.17 385	54.69 382	73.31 382	16.83 396	86.75 379	65.47 350	61.67 379	87.48 370

UnsupCasMVSNet_bld		76.23 336	73.27 340	85.09 331	83.79 373	72.92 323	85.65 359	93.47 261	71.52 361	68.84 372	79.08 376	49.77 366	93.21 347	66.81 348	60.52 380	89.13 361

testf1		59.54 352	56.11 355	69.85 366	69.28 390	56.61 387	80.37 380	76.55 392	42.58 388	45.68 387	75.61 377	11.26 398	84.18 384	43.20 386	60.44 381	68.75 384

APD_test2		59.54 352	56.11 355	69.85 366	69.28 390	56.61 387	80.37 380	76.55 392	42.58 388	45.68 387	75.61 377	11.26 398	84.18 384	43.20 386	60.44 381	68.75 384

KD-MVS_2432*1600		78.50 328	76.02 335	85.93 321	86.22 362	74.47 310	84.80 365	92.33 284	79.29 282	76.98 338	85.92 353	53.81 359	93.97 335	67.39 341	57.42 383	89.36 354

miper_refine_blended		78.50 328	76.02 335	85.93 321	86.22 362	74.47 310	84.80 365	92.33 284	79.29 282	76.98 338	85.92 353	53.81 359	93.97 335	67.39 341	57.42 383	89.36 354

DeepMVS_CX				56.31 375	74.23 386	51.81 392		56.67 400	44.85 386	48.54 386	75.16 379	27.87 386	58.74 396	40.92 388	52.22 385	58.39 389

WB-MVS		67.92 345	67.49 347	69.21 368	81.09 378	41.17 396	88.03 337	78.00 388	73.50 347	62.63 377	83.11 368	63.94 303	86.52 380	25.66 393	51.45 386	79.94 379

PVSNet_0	73.20 20	77.22 333	74.83 339	84.37 335	90.70 314	71.10 346	83.09 374	89.67 350	72.81 355	73.93 357	83.13 366	60.79 328	93.70 341	68.54 333	50.84 387	88.30 366

test_method		50.52 357	48.47 359	56.66 374	52.26 399	18.98 404	41.51 392	81.40 379	10.10 394	44.59 389	75.01 380	28.51 385	68.16 392	53.54 378	49.31 388	82.83 375

SSC-MVS		67.06 346	66.56 348	68.56 370	80.54 379	40.06 398	87.77 341	77.37 391	72.38 357	61.75 379	82.66 370	63.37 308	86.45 381	24.48 394	48.69 389	79.16 381

PMMVS2		59.60 351	56.40 353	69.21 368	68.83 392	46.58 394	73.02 387	77.48 390	55.07 382	49.21 385	72.95 383	17.43 395	80.04 390	49.32 381	44.33 390	80.99 378

MVE	39.65 23	43.39 358	38.59 364	57.77 373	56.52 397	48.77 393	55.38 389	58.64 399	29.33 393	28.96 394	52.65 390	4.68 401	64.62 395	28.11 392	33.07 391	59.93 388
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		43.23 359	42.29 361	46.03 376	65.58 394	37.41 399	73.51 385	64.62 396	33.99 391	28.47 395	47.87 392	19.90 394	67.91 393	22.23 395	24.45 392	32.77 391

ANet_high		58.88 354	54.22 358	72.86 361	56.50 398	56.67 386	80.75 379	86.00 364	73.09 352	37.39 391	64.63 388	22.17 391	79.49 391	43.51 385	23.96 393	82.43 377

EMVS		42.07 360	41.12 362	44.92 377	63.45 396	35.56 401	73.65 384	63.48 397	33.05 392	26.88 396	45.45 393	21.27 392	67.14 394	19.80 396	23.02 394	32.06 392

tmp_tt		35.64 361	39.24 363	24.84 378	14.87 401	23.90 403	62.71 388	51.51 401	6.58 396	36.66 392	62.08 389	44.37 376	30.34 398	52.40 379	22.00 395	20.27 393

wuyk23d		21.27 363	20.48 366	23.63 379	68.59 393	36.41 400	49.57 391	6.85 403	9.37 395	7.89 397	4.46 399	4.03 402	31.37 397	17.47 397	16.07 396	3.12 394

testmvs		8.92 364	11.52 367	1.12 381	1.06 402	0.46 406	86.02 355	0.65 404	0.62 397	2.74 398	9.52 397	0.31 404	0.45 400	2.38 398	0.39 397	2.46 396

test123		8.76 365	11.22 368	1.39 380	0.85 403	0.97 405	85.76 358	0.35 405	0.54 398	2.45 399	8.14 398	0.60 403	0.48 399	2.16 399	0.17 398	2.71 395

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

cdsmvs_eth3d_5k		22.14 362	29.52 365	0.00 382	0.00 404	0.00 407	0.00 393	95.76 150	0.00 400	0.00 401	94.29 162	75.66 168	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		6.64 367	8.86 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	79.70 119	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

ab-mvs-re		7.82 366	10.43 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	93.88 183	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

WAC-MVS						64.08 373								59.14 370

FOURS1					98.86 1	85.54 65	98.29 1	97.49 6	89.79 44	96.29 16

test_one_0601					98.58 11	85.83 59		97.44 15	91.05 14	96.78 14	98.06 11	91.45 11

eth-test2					0.00 404

eth-test					0.00 404

test_241102_ONE					98.77 5	85.99 51		97.44 15	90.26 33	97.71 1	97.96 17	92.31 4	99.38 31

save fliter					97.85 46	85.63 64	95.21 109	96.82 68	89.44 51

test0726					98.78 3	85.93 54	97.19 11	97.47 11	90.27 31	97.64 4	98.13 3	91.47 8

GSMVS																96.12 151

test_part2					98.55 12	87.22 18				96.40 15

sam_mvs1												71.70 219				96.12 151

sam_mvs												70.60 232

MTGPA								96.97 50

test_post1							88.00 338				9.81 396	69.31 254	95.53 310	76.65 279

test_post											10.29 395	70.57 236	95.91 298

patchmatchnet-post											83.76 363	71.53 220	96.48 270

MTMP							96.16 53	60.64 398

gm-plane-assit					89.60 337	68.00 360			77.28 311		88.99 316		97.57 187	79.44 252

TEST9					97.53 58	86.49 36	94.07 184	96.78 72	81.61 254	92.77 72	96.20 85	87.71 28	99.12 51

test_8					97.49 60	86.30 44	94.02 189	96.76 75	81.86 245	92.70 76	96.20 85	87.63 29	99.02 61

agg_prior					97.38 63	85.92 56		96.72 81		92.16 87			98.97 75

test_prior4						85.96 53	94.11 179

test_prior				93.82 60	97.29 67	84.49 82		96.88 61					98.87 82			98.11 65

旧先验2							93.36 217		71.25 363	94.37 37			97.13 232	86.74 144

新几何2							93.11 232

无先验							93.28 225	96.26 108	73.95 343				99.05 55	80.56 237		96.59 135

原ACMM2							92.94 239

testdata2													98.75 92	78.30 263

segment_acmp												87.16 34

testdata1							92.15 264		87.94 103

plane_prior7					94.70 163	82.74 139

plane_prior6					94.52 173	82.75 137						74.23 185

plane_prior4											94.86 138

plane_prior3						82.75 137			90.26 33	86.91 178

plane_prior2							95.85 75		90.81 17

plane_prior1					94.59 168

n2								0.00 406

nn								0.00 406

door-mid								85.49 366

test11								96.57 92

door								85.33 368

HQP5-MVS						81.56 166

HQP-NCC					94.17 187		94.39 163		88.81 72	85.43 219

ACMP_Plane					94.17 187		94.39 163		88.81 72	85.43 219

BP-MVS														87.11 141

HQP4-MVS										85.43 219			97.96 163			94.51 217

HQP2-MVS												73.83 195

NP-MVS					94.37 181	82.42 149					93.98 176

MDTV_nov1_ep13_2view						55.91 391	87.62 345		73.32 349	84.59 238		70.33 239		74.65 299		95.50 177

Test By Simon												80.02 114

High-resolution multi-view benchmark