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.

MM		95.10 11	94.91 13	95.68 5	96.09 101	88.34 9	96.68 33	94.37 234	95.08 1	94.68 36	97.72 24	82.94 83	99.64 1	97.85 1	98.76 28	99.06 7

ZNCC-MVS		94.47 21	94.28 30	95.03 16	98.52 15	86.96 19	96.85 28	97.32 27	88.24 92	93.15 61	97.04 52	86.17 44	99.62 2	92.40 59	98.81 22	98.52 26

DPE-MVS		95.57 4	95.67 4	95.25 10	98.36 25	87.28 17	95.56 95	97.51 5	89.13 63	97.14 9	97.91 18	91.64 7	99.62 2	94.61 27	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++		95.98 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 19	99.02 12	98.86 11

MSC_two_6792asdad				96.52 1	97.78 51	90.86 1		96.85 63					99.61 4	96.03 14	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 14	99.06 9	99.07 5

test_0728_SECOND				95.01 17	98.79 2	86.43 38	97.09 16	97.49 6					99.61 4	95.62 21	99.08 7	98.99 9

GST-MVS		94.21 32	93.97 43	94.90 23	98.41 22	86.82 23	96.54 37	97.19 35	88.24 92	93.26 58	96.83 61	85.48 51	99.59 8	91.43 87	98.40 52	98.30 47

MVS_0304		94.60 18	94.38 25	95.23 11	95.41 130	87.49 15	96.53 38	92.75 277	93.82 2	93.07 65	97.84 22	83.66 74	99.59 8	97.61 2	98.76 28	98.61 22

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 17	99.13 3	98.84 14

test_241102_TWO								97.44 15	90.31 28	97.62 5	98.07 9	91.46 10	99.58 10	95.66 17	99.12 6	98.98 10

SMA-MVS		95.20 8	95.07 11	95.59 6	98.14 35	88.48 8	96.26 47	97.28 31	85.90 155	97.67 3	98.10 7	88.41 20	99.56 12	94.66 26	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
MP-MVS-pluss		94.21 32	94.00 42	94.85 25	98.17 33	86.65 30	94.82 136	97.17 39	86.26 146	92.83 71	97.87 20	85.57 50	99.56 12	94.37 30	98.92 17	98.34 42
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MTAPA		94.42 26	94.22 33	95.00 18	98.42 21	86.95 20	94.36 170	96.97 50	91.07 13	93.14 62	97.56 27	84.30 67	99.56 12	93.43 40	98.75 30	98.47 33

MP-MVS		94.25 29	94.07 39	94.77 34	98.47 18	86.31 43	96.71 31	96.98 49	89.04 66	91.98 93	97.19 44	85.43 52	99.56 12	92.06 73	98.79 23	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
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 21	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_THIRD									90.75 19	97.04 11	98.05 13	92.09 6	99.55 16	95.64 19	99.13 3	99.13 2

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 46	96.83 61	88.12 24	99.55 16	93.41 42	98.94 16	98.28 50

mPP-MVS		93.99 41	93.78 47	94.63 39	98.50 16	85.90 58	96.87 26	96.91 58	88.70 78	91.83 102	97.17 46	83.96 71	99.55 16	91.44 86	98.64 43	98.43 38

CANet		93.54 51	93.20 61	94.55 42	95.65 121	85.73 63	94.94 128	96.69 84	91.89 8	90.69 118	95.88 102	81.99 102	99.54 20	93.14 46	97.95 69	98.39 39

ACMMP_NAP		94.74 16	94.56 19	95.28 9	98.02 41	87.70 11	95.68 85	97.34 23	88.28 91	95.30 32	97.67 26	85.90 47	99.54 20	93.91 34	98.95 15	98.60 23

region2R		94.43 24	94.27 32	94.92 20	98.65 8	86.67 29	96.92 24	97.23 34	88.60 82	93.58 53	97.27 38	85.22 54	99.54 20	92.21 64	98.74 31	98.56 25

ACMMPR		94.43 24	94.28 30	94.91 21	98.63 9	86.69 27	96.94 20	97.32 27	88.63 80	93.53 56	97.26 40	85.04 58	99.54 20	92.35 61	98.78 25	98.50 27

PGM-MVS		93.96 42	93.72 50	94.68 37	98.43 20	86.22 46	95.30 103	97.78 1	87.45 118	93.26 58	97.33 36	84.62 65	99.51 24	90.75 99	98.57 47	98.32 46

ACMMP		93.24 62	92.88 67	94.30 50	98.09 38	85.33 68	96.86 27	97.45 14	88.33 88	90.15 127	97.03 53	81.44 105	99.51 24	90.85 98	95.74 112	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
HFP-MVS		94.52 20	94.40 23	94.86 24	98.61 10	86.81 24	96.94 20	97.34 23	88.63 80	93.65 51	97.21 42	86.10 45	99.49 26	92.35 61	98.77 27	98.30 47

XVS		94.45 22	94.32 26	94.85 25	98.54 13	86.60 33	96.93 22	97.19 35	90.66 24	92.85 69	97.16 47	85.02 59	99.49 26	91.99 74	98.56 48	98.47 33

X-MVStestdata		88.31 174	86.13 221	94.85 25	98.54 13	86.60 33	96.93 22	97.19 35	90.66 24	92.85 69	23.41 403	85.02 59	99.49 26	91.99 74	98.56 48	98.47 33

NCCC		94.81 15	94.69 18	95.17 14	97.83 48	87.46 16	95.66 88	96.93 56	92.34 4	93.94 47	96.58 76	87.74 27	99.44 29	92.83 50	98.40 52	98.62 21

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 30	97.46 30	88.98 19	99.40 30	94.12 31	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
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

DeepC-MVS	88.79 3	93.31 60	92.99 65	94.26 51	96.07 103	85.83 59	94.89 131	96.99 48	89.02 69	89.56 132	97.37 35	82.51 89	99.38 31	92.20 65	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
SF-MVS		94.97 12	94.90 15	95.20 12	97.84 47	87.76 10	96.65 35	97.48 10	87.76 111	95.71 27	97.70 25	88.28 23	99.35 33	93.89 35	98.78 25	98.48 30

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 19	98.10 7	89.39 16	99.34 34	95.88 16	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 22	94.20 35	95.19 13	98.46 19	87.50 14	95.00 125	97.12 41	87.13 123	92.51 83	96.30 83	89.24 17	99.34 34	93.46 39	98.62 44	98.73 17

3Dnovator+	87.14 4	92.42 76	91.37 84	95.55 7	95.63 122	88.73 6	97.07 18	96.77 74	90.84 16	84.02 265	96.62 74	75.95 163	99.34 34	87.77 130	97.68 78	98.59 24

CNVR-MVS		95.40 7	95.37 7	95.50 8	98.11 36	88.51 7	95.29 105	96.96 52	92.09 6	95.32 31	97.08 49	89.49 15	99.33 37	95.10 24	98.85 19	98.66 20

CP-MVS		94.34 27	94.21 34	94.74 36	98.39 23	86.64 31	97.60 4	97.24 32	88.53 84	92.73 77	97.23 41	85.20 55	99.32 38	92.15 67	98.83 21	98.25 55

PHI-MVS		93.89 43	93.65 54	94.62 40	96.84 75	86.43 38	96.69 32	97.49 6	85.15 175	93.56 55	96.28 84	85.60 49	99.31 39	92.45 56	98.79 23	98.12 64

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 20	96.69 66	89.90 12	99.30 40	94.70 25	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
QAPM		89.51 134	88.15 160	93.59 68	94.92 154	84.58 79	96.82 29	96.70 83	78.43 307	83.41 280	96.19 90	73.18 206	99.30 40	77.11 281	96.54 101	96.89 127

ZD-MVS					98.15 34	86.62 32		97.07 45	83.63 207	94.19 42	96.91 57	87.57 31	99.26 42	91.99 74	98.44 51

DeepC-MVS_fast	89.43 2	94.04 38	93.79 46	94.80 32	97.48 61	86.78 25	95.65 90	96.89 60	89.40 53	92.81 72	96.97 54	85.37 53	99.24 43	90.87 97	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
9.14			94.47 20		97.79 49		96.08 61	97.44 15	86.13 153	95.10 33	97.40 33	88.34 22	99.22 44	93.25 44	98.70 34

DELS-MVS		93.43 58	93.25 59	93.97 54	95.42 129	85.04 70	93.06 237	97.13 40	90.74 21	91.84 100	95.09 133	86.32 42	99.21 45	91.22 88	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
LS3D		87.89 184	86.32 214	92.59 109	96.07 103	82.92 136	95.23 109	94.92 209	75.66 333	82.89 287	95.98 98	72.48 215	99.21 45	68.43 342	95.23 128	95.64 180

HPM-MVS		94.02 39	93.88 44	94.43 46	98.39 23	85.78 61	97.25 10	97.07 45	86.90 131	92.62 80	96.80 65	84.85 63	99.17 47	92.43 57	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
PVSNet_Blended_VisFu		91.38 90	90.91 94	92.80 97	96.39 90	83.17 122	94.87 133	96.66 85	83.29 218	89.27 137	94.46 158	80.29 113	99.17 47	87.57 134	95.37 123	96.05 164

3Dnovator	86.66 5	91.73 85	90.82 96	94.44 44	94.59 171	86.37 40	97.18 12	97.02 47	89.20 60	84.31 261	96.66 69	73.74 199	99.17 47	86.74 146	97.96 68	97.79 85

CSCG		93.23 63	93.05 63	93.76 64	98.04 40	84.07 96	96.22 49	97.37 21	84.15 195	90.05 128	95.66 112	87.77 26	99.15 50	89.91 107	98.27 56	98.07 66

TEST9					97.53 58	86.49 36	94.07 186	96.78 72	81.61 261	92.77 74	96.20 87	87.71 28	99.12 51

train_agg		93.44 55	93.08 62	94.52 43	97.53 58	86.49 36	94.07 186	96.78 72	81.86 252	92.77 74	96.20 87	87.63 29	99.12 51	92.14 68	98.69 35	97.94 74

HPM-MVS_fast		93.40 59	93.22 60	93.94 56	98.36 25	84.83 74	97.15 13	96.80 71	85.77 158	92.47 84	97.13 48	82.38 90	99.07 53	90.51 104	98.40 52	97.92 77

APD-MVS		94.24 30	94.07 39	94.75 35	98.06 39	86.90 22	95.88 74	96.94 55	85.68 161	95.05 34	97.18 45	87.31 35	99.07 53	91.90 80	98.61 46	98.28 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
无先验							93.28 227	96.26 110	73.95 352				99.05 55	80.56 242		96.59 139

DP-MVS		87.25 215	85.36 249	92.90 92	97.65 55	83.24 119	94.81 137	92.00 300	74.99 341	81.92 299	95.00 135	72.66 212	99.05 55	66.92 354	92.33 181	96.40 145

CDPH-MVS		92.83 69	92.30 75	94.44 44	97.79 49	86.11 48	94.06 188	96.66 85	80.09 281	92.77 74	96.63 73	86.62 38	99.04 57	87.40 136	98.66 40	98.17 60

SR-MVS		94.23 31	94.17 37	94.43 46	98.21 32	85.78 61	96.40 41	96.90 59	88.20 96	94.33 40	97.40 33	84.75 64	99.03 58	93.35 43	97.99 67	98.48 30

CANet_DTU		90.26 113	89.41 123	92.81 96	93.46 225	83.01 132	93.48 215	94.47 229	89.43 52	87.76 163	94.23 168	70.54 239	99.03 58	84.97 165	96.39 105	96.38 146

DP-MVS Recon		91.95 80	91.28 86	93.96 55	98.33 27	85.92 56	94.66 147	96.66 85	82.69 233	90.03 129	95.82 105	82.30 93	99.03 58	84.57 172	96.48 104	96.91 126

test_8					97.49 60	86.30 44	94.02 191	96.76 75	81.86 252	92.70 78	96.20 87	87.63 29	99.02 61

AdaColmap		89.89 125	89.07 131	92.37 120	97.41 62	83.03 130	94.42 162	95.92 139	82.81 230	86.34 197	94.65 152	73.89 195	99.02 61	80.69 239	95.51 116	95.05 198

test_fmvsmconf_n		94.60 18	94.81 16	93.98 53	94.62 170	84.96 72	96.15 55	97.35 22	89.37 54	96.03 23	98.11 5	86.36 41	99.01 63	97.45 3	97.83 73	97.96 73

SR-MVS-dyc-post		93.82 44	93.82 45	93.82 60	97.92 43	84.57 80	96.28 45	96.76 75	87.46 116	93.75 49	97.43 31	84.24 68	99.01 63	92.73 51	97.80 74	97.88 78

test12				94.34 49	97.13 70	86.15 47		96.29 105		91.04 115		85.08 57	99.01 63		98.13 61	97.86 80

EPNet		91.79 82	91.02 92	94.10 52	90.10 336	85.25 69	96.03 66	92.05 298	92.83 3	87.39 171	95.78 107	79.39 126	99.01 63	88.13 126	97.48 80	98.05 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OpenMVS	83.78 11	88.74 163	87.29 180	93.08 81	92.70 249	85.39 67	96.57 36	96.43 97	78.74 302	80.85 310	96.07 94	69.64 249	99.01 63	78.01 272	96.65 100	94.83 210

h-mvs33		90.80 99	90.15 105	92.75 100	96.01 105	82.66 146	95.43 97	95.53 172	89.80 41	93.08 63	95.64 113	75.77 164	99.00 68	92.07 70	78.05 351	96.60 138

EI-MVSNet-Vis-set		93.01 67	92.92 66	93.29 71	95.01 147	83.51 113	94.48 155	95.77 151	90.87 15	92.52 82	96.67 68	84.50 66	99.00 68	91.99 74	94.44 144	97.36 100

test_fmvsmconf0.1_n		94.20 34	94.31 28	93.88 57	92.46 254	84.80 75	96.18 52	96.82 68	89.29 57	95.68 28	98.11 5	85.10 56	98.99 70	97.38 4	97.75 77	97.86 80

DPM-MVS		92.58 73	91.74 81	95.08 15	96.19 95	89.31 5	92.66 248	96.56 93	83.44 213	91.68 106	95.04 134	86.60 40	98.99 70	85.60 160	97.92 70	96.93 124

PS-MVSNAJ		91.18 95	90.92 93	91.96 136	95.26 137	82.60 149	92.09 269	95.70 158	86.27 145	91.84 100	92.46 229	79.70 121	98.99 70	89.08 115	95.86 111	94.29 239

EI-MVSNet-UG-set		92.74 71	92.62 71	93.12 78	94.86 158	83.20 121	94.40 163	95.74 154	90.71 23	92.05 91	96.60 75	84.00 70	98.99 70	91.55 84	93.63 154	97.17 108

test_fmvsmconf0.01_n		93.19 64	93.02 64	93.71 65	89.25 348	84.42 91	96.06 64	96.29 105	89.06 64	94.68 36	98.13 3	79.22 128	98.98 74	97.22 5	97.24 84	97.74 87

agg_prior					97.38 63	85.92 56		96.72 81		92.16 89			98.97 75

DeepPCF-MVS	89.96 1	94.20 34	94.77 17	92.49 114	96.52 87	80.00 219	94.00 194	97.08 44	90.05 35	95.65 29	97.29 37	89.66 13	98.97 75	93.95 33	98.71 32	98.50 27

APD-MVS_3200maxsize		93.78 45	93.77 48	93.80 62	97.92 43	84.19 94	96.30 43	96.87 62	86.96 127	93.92 48	97.47 29	83.88 72	98.96 77	92.71 54	97.87 71	98.26 54

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 49	92.59 2	98.94 78	92.25 63	98.99 14	98.84 14

TSAR-MVS + MP.		94.85 14	94.94 12	94.58 41	98.25 29	86.33 41	96.11 60	96.62 88	88.14 98	96.10 20	96.96 55	89.09 18	98.94 78	94.48 28	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
RPMNet		83.95 289	81.53 300	91.21 171	90.58 327	79.34 236	85.24 371	96.76 75	71.44 371	85.55 213	82.97 378	70.87 231	98.91 80	61.01 374	89.36 222	95.40 187

xiu_mvs_v2_base		91.13 96	90.89 95	91.86 144	94.97 150	82.42 151	92.24 263	95.64 165	86.11 154	91.74 105	93.14 209	79.67 124	98.89 81	89.06 116	95.46 120	94.28 240

UA-Net		92.83 69	92.54 72	93.68 66	96.10 100	84.71 77	95.66 88	96.39 100	91.92 7	93.22 60	96.49 79	83.16 79	98.87 82	84.47 174	95.47 119	97.45 99

test_prior				93.82 60	97.29 67	84.49 84		96.88 61					98.87 82			98.11 65

新几何1				93.10 79	97.30 66	84.35 92		95.56 168	71.09 373	91.26 113	96.24 85	82.87 85	98.86 84	79.19 261	98.10 62	96.07 161

PCF-MVS	84.11 10	87.74 189	86.08 225	92.70 104	94.02 200	84.43 89	89.27 329	95.87 145	73.62 355	84.43 253	94.33 161	78.48 139	98.86 84	70.27 328	94.45 143	94.81 211
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_BlendedMVS		89.98 119	89.70 115	90.82 191	96.12 97	81.25 179	93.92 199	96.83 66	83.49 212	89.10 139	92.26 237	81.04 109	98.85 86	86.72 148	87.86 250	92.35 321

PVSNet_Blended		90.73 102	90.32 101	91.98 134	96.12 97	81.25 179	92.55 252	96.83 66	82.04 245	89.10 139	92.56 227	81.04 109	98.85 86	86.72 148	95.91 110	95.84 171

原ACMM1				92.01 130	97.34 64	81.05 185		96.81 70	78.89 297	90.45 120	95.92 100	82.65 87	98.84 88	80.68 240	98.26 57	96.14 155

Anonymous20240529		88.09 180	86.59 204	92.58 110	96.53 86	81.92 162	95.99 69	95.84 147	74.11 350	89.06 141	95.21 127	61.44 324	98.81 89	83.67 186	87.47 256	97.01 119

MAR-MVS		90.30 111	89.37 124	93.07 83	96.61 81	84.48 85	95.68 85	95.67 160	82.36 238	87.85 159	92.85 216	76.63 157	98.80 90	80.01 249	96.68 99	95.91 167
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
UGNet		89.95 122	88.95 134	92.95 90	94.51 177	83.31 118	95.70 84	95.23 191	89.37 54	87.58 165	93.94 180	64.00 305	98.78 91	83.92 181	96.31 106	96.74 134
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_l_conf0.5_n		94.29 28	94.46 21	93.79 63	95.28 134	85.43 66	95.68 85	96.43 97	86.56 138	96.84 14	97.81 23	87.56 32	98.77 92	97.14 6	96.82 96	97.16 112

testdata2													98.75 93	78.30 268

PLC	84.53 7	89.06 153	88.03 163	92.15 128	97.27 68	82.69 145	94.29 171	95.44 180	79.71 286	84.01 266	94.18 169	76.68 156	98.75 93	77.28 278	93.41 162	95.02 199
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
fmvsm_l_conf0.5_n_a		94.20 34	94.40 23	93.60 67	95.29 133	84.98 71	95.61 92	96.28 108	86.31 144	96.75 16	97.86 21	87.40 33	98.74 95	97.07 8	97.02 89	97.07 114

test_fmvsmvis_n_1920		93.44 55	93.55 55	93.10 79	93.67 219	84.26 93	95.83 77	96.14 120	89.00 70	92.43 85	97.50 28	83.37 78	98.72 96	96.61 12	97.44 81	96.32 147

test_fmvsm_n_1920		94.71 17	95.11 10	93.50 69	95.79 115	84.62 78	96.15 55	97.64 2	89.85 40	97.19 8	97.89 19	86.28 43	98.71 97	97.11 7	98.08 65	97.17 108

alignmvs		93.08 66	92.50 73	94.81 31	95.62 123	87.61 13	95.99 69	96.07 128	89.77 45	94.12 43	94.87 139	80.56 111	98.66 98	92.42 58	93.10 169	98.15 61

MVS_111021_HR		93.45 54	93.31 57	93.84 59	96.99 72	84.84 73	93.24 230	97.24 32	88.76 75	91.60 107	95.85 103	86.07 46	98.66 98	91.91 78	98.16 59	98.03 70

dcpmvs_2		93.49 52	94.19 36	91.38 165	97.69 54	76.78 289	94.25 173	96.29 105	88.33 88	94.46 38	96.88 58	88.07 25	98.64 100	93.62 38	98.09 63	98.73 17

VDD-MVS		90.74 101	89.92 113	93.20 75	96.27 93	83.02 131	95.73 82	93.86 254	88.42 87	92.53 81	96.84 60	62.09 318	98.64 100	90.95 95	92.62 176	97.93 76

114514_t		89.51 134	88.50 149	92.54 112	98.11 36	81.99 159	95.16 116	96.36 102	70.19 376	85.81 206	95.25 124	76.70 155	98.63 102	82.07 213	96.86 95	97.00 120

canonicalmvs		93.27 61	92.75 69	94.85 25	95.70 120	87.66 12	96.33 42	96.41 99	90.00 37	94.09 44	94.60 154	82.33 92	98.62 103	92.40 59	92.86 173	98.27 52

TSAR-MVS + GP.		93.66 49	93.41 56	94.41 48	96.59 82	86.78 25	94.40 163	93.93 250	89.77 45	94.21 41	95.59 115	87.35 34	98.61 104	92.72 53	96.15 109	97.83 83

CPTT-MVS		91.99 79	91.80 80	92.55 111	98.24 31	81.98 160	96.76 30	96.49 95	81.89 251	90.24 123	96.44 81	78.59 136	98.61 104	89.68 108	97.85 72	97.06 115

FE-MVS		87.40 208	86.02 227	91.57 157	94.56 175	79.69 227	90.27 306	93.72 259	80.57 276	88.80 144	91.62 262	65.32 297	98.59 106	74.97 302	94.33 146	96.44 144

xiu_mvs_v1_base_debu		90.64 106	90.05 108	92.40 117	93.97 206	84.46 86	93.32 221	95.46 175	85.17 172	92.25 86	94.03 172	70.59 235	98.57 107	90.97 92	94.67 134	94.18 241

xiu_mvs_v1_base		90.64 106	90.05 108	92.40 117	93.97 206	84.46 86	93.32 221	95.46 175	85.17 172	92.25 86	94.03 172	70.59 235	98.57 107	90.97 92	94.67 134	94.18 241

xiu_mvs_v1_base_debi		90.64 106	90.05 108	92.40 117	93.97 206	84.46 86	93.32 221	95.46 175	85.17 172	92.25 86	94.03 172	70.59 235	98.57 107	90.97 92	94.67 134	94.18 241

F-COLMAP		87.95 183	86.80 193	91.40 164	96.35 92	80.88 191	94.73 142	95.45 178	79.65 287	82.04 297	94.61 153	71.13 226	98.50 110	76.24 290	91.05 195	94.80 212

fmvsm_s_conf0.5_n		93.76 46	94.06 41	92.86 94	95.62 123	83.17 122	96.14 57	96.12 123	88.13 99	95.82 26	98.04 16	83.43 75	98.48 111	96.97 9	96.23 107	96.92 125

tttt0517		88.61 166	87.78 169	91.11 178	94.96 151	77.81 272	95.35 99	89.69 354	85.09 177	88.05 156	94.59 155	66.93 280	98.48 111	83.27 189	92.13 183	97.03 118

PAPM_NR		91.22 94	90.78 97	92.52 113	97.60 56	81.46 174	94.37 169	96.24 113	86.39 143	87.41 168	94.80 145	82.06 100	98.48 111	82.80 198	95.37 123	97.61 91

FA-MVS(test-final)		89.66 129	88.91 136	91.93 138	94.57 174	80.27 205	91.36 285	94.74 222	84.87 181	89.82 130	92.61 226	74.72 182	98.47 114	83.97 180	93.53 157	97.04 117

fmvsm_s_conf0.1_n		93.46 53	93.66 53	92.85 95	93.75 215	83.13 124	96.02 67	95.74 154	87.68 113	95.89 25	98.17 2	82.78 86	98.46 115	96.71 10	96.17 108	96.98 121

thisisatest0530		88.67 164	87.61 172	91.86 144	94.87 157	80.07 213	94.63 148	89.90 351	84.00 198	88.46 149	93.78 189	66.88 282	98.46 115	83.30 188	92.65 175	97.06 115

IB-MVS	80.51 15	85.24 270	83.26 284	91.19 172	92.13 263	79.86 223	91.75 276	91.29 321	83.28 219	80.66 313	88.49 334	61.28 325	98.46 115	80.99 234	79.46 345	95.25 193
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
API-MVS		90.66 105	90.07 107	92.45 116	96.36 91	84.57 80	96.06 64	95.22 193	82.39 236	89.13 138	94.27 167	80.32 112	98.46 115	80.16 248	96.71 98	94.33 236

fmvsm_s_conf0.5_n_a		93.57 50	93.76 49	93.00 86	95.02 146	83.67 106	96.19 50	96.10 125	87.27 121	95.98 24	98.05 13	83.07 82	98.45 119	96.68 11	95.51 116	96.88 128

EIA-MVS		91.95 80	91.94 78	91.98 134	95.16 141	80.01 218	95.36 98	96.73 79	88.44 85	89.34 136	92.16 239	83.82 73	98.45 119	89.35 111	97.06 87	97.48 97

patch_mono-2		93.74 47	94.32 26	92.01 130	97.54 57	78.37 257	93.40 218	97.19 35	88.02 101	94.99 35	97.21 42	88.35 21	98.44 121	94.07 32	98.09 63	99.23 1

PAPR		90.02 118	89.27 129	92.29 125	95.78 116	80.95 189	92.68 247	96.22 115	81.91 249	86.66 188	93.75 192	82.23 95	98.44 121	79.40 260	94.79 132	97.48 97

fmvsm_s_conf0.1_n_a		93.19 64	93.26 58	92.97 88	92.49 252	83.62 109	96.02 67	95.72 157	86.78 133	96.04 22	98.19 1	82.30 93	98.43 123	96.38 13	95.42 122	96.86 129

test_yl		90.69 103	90.02 111	92.71 102	95.72 118	82.41 153	94.11 181	95.12 196	85.63 163	91.49 108	94.70 148	74.75 179	98.42 124	86.13 153	92.53 178	97.31 101

DCV-MVSNet		90.69 103	90.02 111	92.71 102	95.72 118	82.41 153	94.11 181	95.12 196	85.63 163	91.49 108	94.70 148	74.75 179	98.42 124	86.13 153	92.53 178	97.31 101

CHOSEN 1792x2688		88.84 159	87.69 170	92.30 124	96.14 96	81.42 176	90.01 317	95.86 146	74.52 346	87.41 168	93.94 180	75.46 172	98.36 126	80.36 244	95.53 115	97.12 113

MG-MVS		91.77 83	91.70 82	92.00 133	97.08 71	80.03 217	93.60 212	95.18 194	87.85 109	90.89 116	96.47 80	82.06 100	98.36 126	85.07 164	97.04 88	97.62 90

OMC-MVS		91.23 93	90.62 98	93.08 81	96.27 93	84.07 96	93.52 214	95.93 138	86.95 128	89.51 133	96.13 93	78.50 138	98.35 128	85.84 158	92.90 172	96.83 131

ETV-MVS		92.74 71	92.66 70	92.97 88	95.20 140	84.04 98	95.07 121	96.51 94	90.73 22	92.96 66	91.19 273	84.06 69	98.34 129	91.72 82	96.54 101	96.54 143

LFMVS		90.08 116	89.13 130	92.95 90	96.71 77	82.32 155	96.08 61	89.91 350	86.79 132	92.15 90	96.81 63	62.60 316	98.34 129	87.18 140	93.90 150	98.19 58

CS-MVS-test		94.02 39	94.29 29	93.24 73	96.69 78	83.24 119	97.49 5	96.92 57	92.14 5	92.90 67	95.77 108	85.02 59	98.33 131	93.03 47	98.62 44	98.13 62

VDDNet		89.56 133	88.49 151	92.76 99	95.07 145	82.09 157	96.30 43	93.19 267	81.05 273	91.88 98	96.86 59	61.16 331	98.33 131	88.43 123	92.49 180	97.84 82

EPP-MVSNet		91.70 86	91.56 83	92.13 129	95.88 112	80.50 201	97.33 7	95.25 190	86.15 150	89.76 131	95.60 114	83.42 77	98.32 133	87.37 138	93.25 166	97.56 95

Vis-MVSNet		91.75 84	91.23 87	93.29 71	95.32 132	83.78 103	96.14 57	95.98 134	89.89 38	90.45 120	96.58 76	75.09 175	98.31 134	84.75 170	96.90 92	97.78 86
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0515		87.33 211	85.99 228	91.37 166	93.49 223	79.55 229	90.63 302	89.56 357	80.17 279	87.56 166	90.86 284	67.07 279	98.28 135	81.50 226	93.02 170	96.29 149

CS-MVS		94.12 37	94.44 22	93.17 76	96.55 84	83.08 129	97.63 3	96.95 54	91.71 11	93.50 57	96.21 86	85.61 48	98.24 136	93.64 37	98.17 58	98.19 58

Anonymous202405211		87.68 190	86.13 221	92.31 123	96.66 79	80.74 195	94.87 133	91.49 316	80.47 277	89.46 135	95.44 117	54.72 362	98.23 137	82.19 209	89.89 211	97.97 72

HY-MVS	83.01 12	89.03 154	87.94 166	92.29 125	94.86 158	82.77 138	92.08 270	94.49 228	81.52 263	86.93 178	92.79 222	78.32 141	98.23 137	79.93 250	90.55 200	95.88 169

MVS		87.44 206	86.10 224	91.44 163	92.61 251	83.62 109	92.63 249	95.66 162	67.26 380	81.47 302	92.15 240	77.95 143	98.22 139	79.71 252	95.48 118	92.47 315

ab-mvs		89.41 140	88.35 153	92.60 108	95.15 143	82.65 147	92.20 265	95.60 167	83.97 199	88.55 147	93.70 193	74.16 191	98.21 140	82.46 203	89.37 221	96.94 123

VNet		92.24 78	91.91 79	93.24 73	96.59 82	83.43 114	94.84 135	96.44 96	89.19 61	94.08 45	95.90 101	77.85 147	98.17 141	88.90 117	93.38 163	98.13 62

EC-MVSNet		93.44 55	93.71 51	92.63 107	95.21 139	82.43 150	97.27 9	96.71 82	90.57 26	92.88 68	95.80 106	83.16 79	98.16 142	93.68 36	98.14 60	97.31 101

casdiffmvs_mvg		92.96 68	92.83 68	93.35 70	94.59 171	83.40 116	95.00 125	96.34 103	90.30 30	92.05 91	96.05 95	83.43 75	98.15 143	92.07 70	95.67 113	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
HQP_MVS		90.60 109	90.19 103	91.82 147	94.70 166	82.73 142	95.85 75	96.22 115	90.81 17	86.91 180	94.86 140	74.23 187	98.12 144	88.15 124	89.99 207	94.63 215

plane_prior5								96.22 115					98.12 144	88.15 124	89.99 207	94.63 215

test1111		89.10 148	88.64 143	90.48 204	95.53 127	74.97 311	96.08 61	84.89 379	88.13 99	90.16 126	96.65 70	63.29 312	98.10 146	86.14 151	96.90 92	98.39 39

ECVR-MVS		89.09 150	88.53 147	90.77 193	95.62 123	75.89 302	96.16 53	84.22 381	87.89 107	90.20 124	96.65 70	63.19 314	98.10 146	85.90 156	96.94 90	98.33 43

thres100view900		87.63 195	86.71 197	90.38 211	96.12 97	78.55 250	95.03 124	91.58 312	87.15 122	88.06 155	92.29 236	68.91 263	98.10 146	70.13 332	91.10 190	94.48 231

tfpn200view9		87.58 200	86.64 200	90.41 208	95.99 109	78.64 248	94.58 150	91.98 302	86.94 129	88.09 152	91.77 255	69.18 259	98.10 146	70.13 332	91.10 190	94.48 231

thres600view7		87.65 192	86.67 199	90.59 195	96.08 102	78.72 246	94.88 132	91.58 312	87.06 125	88.08 154	92.30 235	68.91 263	98.10 146	70.05 335	91.10 190	94.96 203

thres400		87.62 197	86.64 200	90.57 196	95.99 109	78.64 248	94.58 150	91.98 302	86.94 129	88.09 152	91.77 255	69.18 259	98.10 146	70.13 332	91.10 190	94.96 203

LPG-MVS_test		89.45 137	88.90 137	91.12 175	94.47 178	81.49 172	95.30 103	96.14 120	86.73 135	85.45 223	95.16 130	69.89 245	98.10 146	87.70 132	89.23 225	93.77 268

LGP-MVS_train				91.12 175	94.47 178	81.49 172		96.14 120	86.73 135	85.45 223	95.16 130	69.89 245	98.10 146	87.70 132	89.23 225	93.77 268

test2506		87.21 219	86.28 216	90.02 227	95.62 123	73.64 325	96.25 48	71.38 403	87.89 107	90.45 120	96.65 70	55.29 360	98.09 154	86.03 155	96.94 90	98.33 43

MVS_Test		91.31 92	91.11 89	91.93 138	94.37 185	80.14 210	93.46 217	95.80 149	86.46 141	91.35 112	93.77 190	82.21 96	98.09 154	87.57 134	94.95 130	97.55 96

TAPA-MVS	84.62 6	88.16 178	87.01 188	91.62 154	96.64 80	80.65 196	94.39 165	96.21 118	76.38 326	86.19 201	95.44 117	79.75 119	98.08 156	62.75 370	95.29 125	96.13 156
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Effi-MVS+		91.59 88	91.11 89	93.01 85	94.35 189	83.39 117	94.60 149	95.10 198	87.10 124	90.57 119	93.10 211	81.43 106	98.07 157	89.29 113	94.48 142	97.59 93

ACMM	84.12 9	89.14 147	88.48 152	91.12 175	94.65 169	81.22 181	95.31 101	96.12 123	85.31 171	85.92 205	94.34 160	70.19 243	98.06 158	85.65 159	88.86 232	94.08 249
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PC_three_1452									82.47 235	97.09 10	97.07 51	92.72 1	98.04 159	92.70 55	99.02 12	98.86 11

lupinMVS		90.92 98	90.21 102	93.03 84	93.86 209	83.88 101	92.81 245	93.86 254	79.84 284	91.76 103	94.29 164	77.92 144	98.04 159	90.48 105	97.11 85	97.17 108

casdiffmvs		92.51 74	92.43 74	92.74 101	94.41 184	81.98 160	94.54 153	96.23 114	89.57 49	91.96 95	96.17 91	82.58 88	98.01 161	90.95 95	95.45 121	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
thres200		87.21 219	86.24 218	90.12 221	95.36 131	78.53 251	93.26 228	92.10 296	86.42 142	88.00 157	91.11 279	69.24 258	98.00 162	69.58 336	91.04 196	93.83 262

baseline		92.39 77	92.29 76	92.69 105	94.46 180	81.77 165	94.14 179	96.27 109	89.22 59	91.88 98	96.00 96	82.35 91	97.99 163	91.05 90	95.27 127	98.30 47

ACMP	84.23 8	89.01 156	88.35 153	90.99 186	94.73 163	81.27 178	95.07 121	95.89 144	86.48 139	83.67 273	94.30 163	69.33 254	97.99 163	87.10 145	88.55 235	93.72 272
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HQP4-MVS										85.43 226			97.96 165			94.51 225

HQP-MVS		89.80 127	89.28 128	91.34 167	94.17 194	81.56 168	94.39 165	96.04 131	88.81 72	85.43 226	93.97 179	73.83 197	97.96 165	87.11 143	89.77 216	94.50 228

HyFIR lowres test		88.09 180	86.81 192	91.93 138	96.00 106	80.63 197	90.01 317	95.79 150	73.42 357	87.68 164	92.10 245	73.86 196	97.96 165	80.75 238	91.70 184	97.19 107

jason		90.80 99	90.10 106	92.90 92	93.04 238	83.53 112	93.08 235	94.15 243	80.22 278	91.41 110	94.91 137	76.87 151	97.93 168	90.28 106	96.90 92	97.24 104
jason: jason.
OPM-MVS		90.12 115	89.56 118	91.82 147	93.14 232	83.90 100	94.16 178	95.74 154	88.96 71	87.86 158	95.43 119	72.48 215	97.91 169	88.10 128	90.18 206	93.65 275
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
1112_ss		88.42 170	87.33 179	91.72 151	94.92 154	80.98 187	92.97 240	94.54 227	78.16 313	83.82 269	93.88 185	78.78 133	97.91 169	79.45 256	89.41 220	96.26 151

COLMAP_ROB	80.39 16	83.96 288	82.04 297	89.74 239	95.28 134	79.75 225	94.25 173	92.28 289	75.17 339	78.02 341	93.77 190	58.60 346	97.84 171	65.06 362	85.92 270	91.63 334
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
LTVRE_ROB	82.13 13	86.26 251	84.90 260	90.34 213	94.44 182	81.50 170	92.31 262	94.89 210	83.03 224	79.63 329	92.67 223	69.69 248	97.79 172	71.20 321	86.26 269	91.72 332
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
IS-MVSNet		91.43 89	91.09 91	92.46 115	95.87 114	81.38 177	96.95 19	93.69 260	89.72 47	89.50 134	95.98 98	78.57 137	97.77 173	83.02 192	96.50 103	98.22 57

MSLP-MVS++		93.72 48	94.08 38	92.65 106	97.31 65	83.43 114	95.79 79	97.33 25	90.03 36	93.58 53	96.96 55	84.87 62	97.76 174	92.19 66	98.66 40	96.76 132

BH-RMVSNet		88.37 172	87.48 175	91.02 183	95.28 134	79.45 232	92.89 242	93.07 269	85.45 168	86.91 180	94.84 144	70.35 240	97.76 174	73.97 308	94.59 138	95.85 170

MVS_111021_LR		92.47 75	92.29 76	92.98 87	95.99 109	84.43 89	93.08 235	96.09 126	88.20 96	91.12 114	95.72 111	81.33 107	97.76 174	91.74 81	97.37 83	96.75 133

Fast-Effi-MVS+		89.41 140	88.64 143	91.71 152	94.74 162	80.81 193	93.54 213	95.10 198	83.11 222	86.82 186	90.67 292	79.74 120	97.75 177	80.51 243	93.55 156	96.57 141

Test_1112_low_res		87.65 192	86.51 207	91.08 179	94.94 153	79.28 240	91.77 275	94.30 237	76.04 331	83.51 278	92.37 232	77.86 146	97.73 178	78.69 264	89.13 227	96.22 152

tt0805		86.92 229	85.74 241	90.48 204	92.22 259	79.98 220	95.63 91	94.88 212	83.83 203	84.74 244	92.80 221	57.61 349	97.67 179	85.48 162	84.42 281	93.79 263

AUN-MVS		87.78 188	86.54 206	91.48 161	94.82 161	81.05 185	93.91 201	93.93 250	83.00 225	86.93 178	93.53 195	69.50 251	97.67 179	86.14 151	77.12 357	95.73 178

hse-mvs2		89.88 126	89.34 125	91.51 159	94.83 160	81.12 184	93.94 197	93.91 253	89.80 41	93.08 63	93.60 194	75.77 164	97.66 181	92.07 70	77.07 358	95.74 176

PS-MVSNAJss		89.97 120	89.62 116	91.02 183	91.90 272	80.85 192	95.26 108	95.98 134	86.26 146	86.21 200	94.29 164	79.70 121	97.65 182	88.87 119	88.10 244	94.57 220

testdata				90.49 202	96.40 89	77.89 269		95.37 186	72.51 365	93.63 52	96.69 66	82.08 99	97.65 182	83.08 190	97.39 82	95.94 166

mvsmamba		89.96 121	89.50 119	91.33 168	92.90 245	81.82 163	96.68 33	92.37 285	89.03 67	87.00 176	94.85 142	73.05 207	97.65 182	91.03 91	88.63 234	94.51 225

nrg030		91.08 97	90.39 99	93.17 76	93.07 235	86.91 21	96.41 39	96.26 110	88.30 90	88.37 151	94.85 142	82.19 97	97.64 185	91.09 89	82.95 296	94.96 203

baseline2		86.50 245	85.39 247	89.84 234	91.12 304	76.70 291	91.88 272	88.58 361	82.35 239	79.95 324	90.95 283	73.42 203	97.63 186	80.27 247	89.95 210	95.19 194

GeoE		90.05 117	89.43 122	91.90 143	95.16 141	80.37 204	95.80 78	94.65 226	83.90 200	87.55 167	94.75 147	78.18 142	97.62 187	81.28 228	93.63 154	97.71 88

ACMH	80.38 17	85.36 265	83.68 278	90.39 209	94.45 181	80.63 197	94.73 142	94.85 214	82.09 242	77.24 345	92.65 224	60.01 337	97.58 188	72.25 317	84.87 278	92.96 301
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
gm-plane-assit					89.60 347	68.00 368			77.28 320		88.99 325		97.57 189	79.44 257

CLD-MVS		89.47 136	88.90 137	91.18 173	94.22 193	82.07 158	92.13 267	96.09 126	87.90 105	85.37 232	92.45 230	74.38 185	97.56 190	87.15 141	90.43 202	93.93 254
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
iter_conf_final		89.42 139	88.69 142	91.60 155	95.12 144	82.93 135	95.75 81	92.14 295	87.32 120	87.12 175	94.07 170	67.09 278	97.55 191	90.61 101	89.01 229	94.32 237

iter_conf05		88.85 158	88.08 162	91.17 174	94.27 191	81.64 167	95.18 113	92.15 294	86.23 148	87.28 172	94.07 170	63.89 309	97.55 191	90.63 100	89.00 230	94.32 237

ACMH+	81.04 14	85.05 273	83.46 281	89.82 235	94.66 168	79.37 234	94.44 160	94.12 246	82.19 241	78.04 340	92.82 219	58.23 347	97.54 193	73.77 310	82.90 300	92.54 312

testing91		87.11 224	86.18 219	89.92 231	94.43 183	75.38 310	91.53 282	92.27 290	86.48 139	86.50 189	90.24 299	61.19 329	97.53 194	82.10 211	90.88 198	96.84 130

v7n		86.81 231	85.76 239	89.95 230	90.72 323	79.25 242	95.07 121	95.92 139	84.45 192	82.29 292	90.86 284	72.60 214	97.53 194	79.42 259	80.52 335	93.08 298

AllTest		83.42 295	81.39 301	89.52 249	95.01 147	77.79 274	93.12 232	90.89 332	77.41 317	76.12 353	93.34 198	54.08 365	97.51 196	68.31 343	84.27 283	93.26 287

TestCases				89.52 249	95.01 147	77.79 274		90.89 332	77.41 317	76.12 353	93.34 198	54.08 365	97.51 196	68.31 343	84.27 283	93.26 287

testing99		86.72 237	85.73 242	89.69 243	94.23 192	74.91 313	91.35 286	90.97 329	86.14 151	86.36 195	90.22 300	59.41 341	97.48 198	82.24 208	90.66 199	96.69 136

XVG-ACMP-BASELINE		86.00 253	84.84 262	89.45 252	91.20 298	78.00 265	91.70 278	95.55 169	85.05 178	82.97 286	92.25 238	54.49 363	97.48 198	82.93 193	87.45 258	92.89 304

TR-MVS		86.78 233	85.76 239	89.82 235	94.37 185	78.41 255	92.47 253	92.83 274	81.11 272	86.36 195	92.40 231	68.73 266	97.48 198	73.75 311	89.85 213	93.57 277

cascas		86.43 249	84.98 257	90.80 192	92.10 265	80.92 190	90.24 310	95.91 141	73.10 360	83.57 277	88.39 335	65.15 299	97.46 201	84.90 168	91.43 187	94.03 252

testing11		86.44 248	85.35 250	89.69 243	94.29 190	75.40 309	91.30 287	90.53 337	84.76 185	85.06 237	90.13 305	58.95 345	97.45 202	82.08 212	91.09 194	96.21 153

v144192		87.19 221	86.35 212	89.74 239	90.64 325	78.24 261	93.92 199	95.43 181	81.93 248	85.51 218	91.05 281	74.21 189	97.45 202	82.86 195	81.56 315	93.53 278

v2v482		87.84 185	87.06 185	90.17 217	90.99 308	79.23 243	94.00 194	95.13 195	84.87 181	85.53 216	92.07 248	74.45 184	97.45 202	84.71 171	81.75 313	93.85 261

diffmvs		91.37 91	91.23 87	91.77 150	93.09 234	80.27 205	92.36 257	95.52 173	87.03 126	91.40 111	94.93 136	80.08 115	97.44 205	92.13 69	94.56 139	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
v1240		86.78 233	85.85 234	89.56 247	90.45 331	77.79 274	93.61 211	95.37 186	81.65 258	85.43 226	91.15 277	71.50 223	97.43 206	81.47 227	82.05 309	93.47 282

v1192		87.25 215	86.33 213	90.00 229	90.76 321	79.04 244	93.80 203	95.48 174	82.57 234	85.48 221	91.18 275	73.38 205	97.42 207	82.30 206	82.06 307	93.53 278

v1144		87.61 198	86.79 194	90.06 224	91.01 307	79.34 236	93.95 196	95.42 183	83.36 217	85.66 211	91.31 271	74.98 177	97.42 207	83.37 187	82.06 307	93.42 284

jajsoiax		88.24 176	87.50 174	90.48 204	90.89 316	80.14 210	95.31 101	95.65 164	84.97 179	84.24 262	94.02 175	65.31 298	97.42 207	88.56 121	88.52 237	93.89 255

v8		87.50 205	86.71 197	89.89 232	91.37 293	79.40 233	94.50 154	95.38 184	84.81 184	83.60 276	91.33 268	76.05 160	97.42 207	82.84 196	80.51 336	92.84 306

v10		87.25 215	86.38 210	89.85 233	91.19 299	79.50 230	94.48 155	95.45 178	83.79 204	83.62 275	91.19 273	75.13 174	97.42 207	81.94 216	80.60 331	92.63 311

v1921920		86.97 228	86.06 226	89.69 243	90.53 330	78.11 264	93.80 203	95.43 181	81.90 250	85.33 234	91.05 281	72.66 212	97.41 212	82.05 214	81.80 312	93.53 278

V42		87.68 190	86.86 190	90.15 219	90.58 327	80.14 210	94.24 175	95.28 189	83.66 206	85.67 210	91.33 268	74.73 181	97.41 212	84.43 175	81.83 311	92.89 304

mvs_tets		88.06 182	87.28 181	90.38 211	90.94 312	79.88 222	95.22 110	95.66 162	85.10 176	84.21 263	93.94 180	63.53 310	97.40 214	88.50 122	88.40 241	93.87 258

VPA-MVSNet		89.62 130	88.96 133	91.60 155	93.86 209	82.89 137	95.46 96	97.33 25	87.91 104	88.43 150	93.31 201	74.17 190	97.40 214	87.32 139	82.86 301	94.52 223

BH-untuned		88.60 167	88.13 161	90.01 228	95.24 138	78.50 253	93.29 226	94.15 243	84.75 186	84.46 251	93.40 197	75.76 166	97.40 214	77.59 275	94.52 141	94.12 245

UniMVSNet (Re)		89.80 127	89.07 131	92.01 130	93.60 221	84.52 83	94.78 139	97.47 11	89.26 58	86.44 194	92.32 234	82.10 98	97.39 217	84.81 169	80.84 329	94.12 245

Anonymous20231211		86.59 241	85.13 254	90.98 188	96.52 87	81.50 170	96.14 57	96.16 119	73.78 353	83.65 274	92.15 240	63.26 313	97.37 218	82.82 197	81.74 314	94.06 250

UniMVSNet_ETH3D		87.53 202	86.37 211	91.00 185	92.44 255	78.96 245	94.74 141	95.61 166	84.07 197	85.36 233	94.52 157	59.78 339	97.34 219	82.93 193	87.88 249	96.71 135

RRT_MVS		89.09 150	88.62 146	90.49 202	92.85 246	79.65 228	96.41 39	94.41 232	88.22 94	85.50 219	94.77 146	69.36 253	97.31 220	89.33 112	86.73 266	94.51 225

MVSFormer		91.68 87	91.30 85	92.80 97	93.86 209	83.88 101	95.96 71	95.90 142	84.66 189	91.76 103	94.91 137	77.92 144	97.30 221	89.64 109	97.11 85	97.24 104

test_djsdf		89.03 154	88.64 143	90.21 215	90.74 322	79.28 240	95.96 71	95.90 142	84.66 189	85.33 234	92.94 215	74.02 193	97.30 221	89.64 109	88.53 236	94.05 251

PAPM		86.68 238	85.39 247	90.53 198	93.05 237	79.33 239	89.79 320	94.77 221	78.82 299	81.95 298	93.24 205	76.81 152	97.30 221	66.94 352	93.16 168	94.95 206

RPSCF		85.07 272	84.27 269	87.48 300	92.91 244	70.62 359	91.69 279	92.46 283	76.20 330	82.67 290	95.22 125	63.94 306	97.29 224	77.51 277	85.80 271	94.53 222

XVG-OURS-SEG-HR		89.95 122	89.45 120	91.47 162	94.00 204	81.21 182	91.87 273	96.06 130	85.78 157	88.55 147	95.73 110	74.67 183	97.27 225	88.71 120	89.64 218	95.91 167

MSDG		84.86 276	83.09 287	90.14 220	93.80 212	80.05 215	89.18 332	93.09 268	78.89 297	78.19 338	91.91 252	65.86 296	97.27 225	68.47 341	88.45 239	93.11 296

Effi-MVS+-dtu		88.65 165	88.35 153	89.54 248	93.33 228	76.39 296	94.47 158	94.36 235	87.70 112	85.43 226	89.56 318	73.45 202	97.26 227	85.57 161	91.28 189	94.97 200

XVG-OURS		89.40 142	88.70 141	91.52 158	94.06 198	81.46 174	91.27 289	96.07 128	86.14 151	88.89 143	95.77 108	68.73 266	97.26 227	87.39 137	89.96 209	95.83 172

FIs		90.51 110	90.35 100	90.99 186	93.99 205	80.98 187	95.73 82	97.54 4	89.15 62	86.72 187	94.68 150	81.83 104	97.24 229	85.18 163	88.31 243	94.76 213

UniMVSNet_NR-MVSNet		89.92 124	89.29 127	91.81 149	93.39 227	83.72 104	94.43 161	97.12 41	89.80 41	86.46 191	93.32 200	83.16 79	97.23 230	84.92 166	81.02 325	94.49 230

DU-MVS		89.34 145	88.50 149	91.85 146	93.04 238	83.72 104	94.47 158	96.59 90	89.50 50	86.46 191	93.29 203	77.25 149	97.23 230	84.92 166	81.02 325	94.59 218

EI-MVSNet		89.10 148	88.86 139	89.80 238	91.84 274	78.30 259	93.70 209	95.01 201	85.73 159	87.15 173	95.28 122	79.87 118	97.21 232	83.81 183	87.36 259	93.88 257

MVSTER		88.84 159	88.29 157	90.51 201	92.95 243	80.44 202	93.73 206	95.01 201	84.66 189	87.15 173	93.12 210	72.79 211	97.21 232	87.86 129	87.36 259	93.87 258

anonymousdsp		87.84 185	87.09 184	90.12 221	89.13 349	80.54 200	94.67 146	95.55 169	82.05 243	83.82 269	92.12 242	71.47 224	97.15 234	87.15 141	87.80 254	92.67 309

1314		87.51 203	86.57 205	90.34 213	92.42 256	79.74 226	92.63 249	95.35 188	78.35 308	80.14 320	91.62 262	74.05 192	97.15 234	81.05 230	93.53 157	94.12 245

VPNet		88.20 177	87.47 176	90.39 209	93.56 222	79.46 231	94.04 189	95.54 171	88.67 79	86.96 177	94.58 156	69.33 254	97.15 234	84.05 179	80.53 334	94.56 221

旧先验2							93.36 219		71.25 372	94.37 39			97.13 237	86.74 146

GA-MVS		86.61 239	85.27 252	90.66 194	91.33 296	78.71 247	90.40 305	93.81 257	85.34 170	85.12 236	89.57 317	61.25 326	97.11 238	80.99 234	89.59 219	96.15 154

SDMVSNet		90.19 114	89.61 117	91.93 138	96.00 106	83.09 128	92.89 242	95.98 134	88.73 76	86.85 184	95.20 128	72.09 219	97.08 239	88.90 117	89.85 213	95.63 181

tpmvs		83.35 297	82.07 296	87.20 309	91.07 306	71.00 356	88.31 344	91.70 308	78.91 295	80.49 316	87.18 354	69.30 257	97.08 239	68.12 346	83.56 291	93.51 281

BH-w/o		87.57 201	87.05 186	89.12 259	94.90 156	77.90 268	92.41 254	93.51 262	82.89 229	83.70 272	91.34 267	75.75 167	97.07 241	75.49 294	93.49 159	92.39 319

Fast-Effi-MVS+-dtu		87.44 206	86.72 196	89.63 246	92.04 266	77.68 278	94.03 190	93.94 249	85.81 156	82.42 291	91.32 270	70.33 241	97.06 242	80.33 246	90.23 205	94.14 244

v148		87.04 226	86.32 214	89.21 256	90.94 312	77.26 283	93.71 208	94.43 230	84.84 183	84.36 257	90.80 288	76.04 161	97.05 243	82.12 210	79.60 344	93.31 286

NR-MVSNet		88.58 169	87.47 176	91.93 138	93.04 238	84.16 95	94.77 140	96.25 112	89.05 65	80.04 323	93.29 203	79.02 130	97.05 243	81.71 224	80.05 339	94.59 218

FC-MVSNet-test		90.27 112	90.18 104	90.53 198	93.71 216	79.85 224	95.77 80	97.59 3	89.31 56	86.27 198	94.67 151	81.93 103	97.01 245	84.26 176	88.09 246	94.71 214

CDS-MVSNet		89.45 137	88.51 148	92.29 125	93.62 220	83.61 111	93.01 238	94.68 225	81.95 247	87.82 161	93.24 205	78.69 134	96.99 246	80.34 245	93.23 167	96.28 150
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TranMVSNet+NR-MVSNet		88.84 159	87.95 165	91.49 160	92.68 250	83.01 132	94.92 130	96.31 104	89.88 39	85.53 216	93.85 187	76.63 157	96.96 247	81.91 217	79.87 342	94.50 228

tfpnnormal		84.72 279	83.23 285	89.20 257	92.79 248	80.05 215	94.48 155	95.81 148	82.38 237	81.08 308	91.21 272	69.01 262	96.95 248	61.69 372	80.59 332	90.58 357

TAMVS		89.21 146	88.29 157	91.96 136	93.71 216	82.62 148	93.30 225	94.19 241	82.22 240	87.78 162	93.94 180	78.83 131	96.95 248	77.70 274	92.98 171	96.32 147

IterMVS-LS		88.36 173	87.91 167	89.70 242	93.80 212	78.29 260	93.73 206	95.08 200	85.73 159	84.75 243	91.90 253	79.88 117	96.92 250	83.83 182	82.51 302	93.89 255
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SD-MVS		94.96 13	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 38	89.53 14	96.91 251	94.38 29	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
WR-MVS		88.38 171	87.67 171	90.52 200	93.30 229	80.18 208	93.26 228	95.96 137	88.57 83	85.47 222	92.81 220	76.12 159	96.91 251	81.24 229	82.29 305	94.47 233

SixPastTwentyTwo		83.91 290	82.90 292	86.92 315	90.99 308	70.67 358	93.48 215	91.99 301	85.54 166	77.62 344	92.11 244	60.59 333	96.87 253	76.05 292	77.75 352	93.20 292

CostFormer		85.77 259	84.94 259	88.26 282	91.16 302	72.58 340	89.47 327	91.04 327	76.26 329	86.45 193	89.97 310	70.74 233	96.86 254	82.35 205	87.07 264	95.34 191

eth_miper_zixun_eth		86.50 245	85.77 238	88.68 272	91.94 269	75.81 304	90.47 304	94.89 210	82.05 243	84.05 264	90.46 295	75.96 162	96.77 255	82.76 199	79.36 346	93.46 283

OurMVSNet-221017-0		85.35 266	84.64 266	87.49 299	90.77 320	72.59 339	94.01 192	94.40 233	84.72 187	79.62 330	93.17 207	61.91 320	96.72 256	81.99 215	81.16 319	93.16 294

EG-PatchMatch MVS		82.37 303	80.34 309	88.46 276	90.27 333	79.35 235	92.80 246	94.33 236	77.14 321	73.26 369	90.18 303	47.47 381	96.72 256	70.25 329	87.32 261	89.30 365

PVSNet	78.82 18	85.55 261	84.65 265	88.23 284	94.72 164	71.93 343	87.12 358	92.75 277	78.80 300	84.95 240	90.53 294	64.43 303	96.71 258	74.74 303	93.86 151	96.06 163

bld_raw_dy_0_64		87.60 199	86.73 195	90.21 215	91.72 279	80.26 207	95.09 120	88.61 360	85.68 161	85.55 213	94.38 159	63.93 308	96.66 259	87.73 131	87.84 251	93.72 272

miper_enhance_ethall		86.90 230	86.18 219	89.06 261	91.66 284	77.58 280	90.22 312	94.82 217	79.16 293	84.48 250	89.10 323	79.19 129	96.66 259	84.06 178	82.94 297	92.94 302

USDC		82.76 298	81.26 303	87.26 304	91.17 300	74.55 316	89.27 329	93.39 264	78.26 311	75.30 358	92.08 246	54.43 364	96.63 261	71.64 318	85.79 272	90.61 354

miper_ehance_all_eth		87.22 218	86.62 203	89.02 263	92.13 263	77.40 282	90.91 298	94.81 218	81.28 267	84.32 259	90.08 307	79.26 127	96.62 262	83.81 183	82.94 297	93.04 299

CNLPA		89.07 152	87.98 164	92.34 121	96.87 74	84.78 76	94.08 185	93.24 265	81.41 264	84.46 251	95.13 132	75.57 171	96.62 262	77.21 279	93.84 152	95.61 183

OpenMVS_ROB	74.94 19	79.51 333	77.03 340	86.93 314	87.00 369	76.23 299	92.33 260	90.74 335	68.93 378	74.52 363	88.23 339	49.58 376	96.62 262	57.64 382	84.29 282	87.94 377

c3_l		87.14 223	86.50 208	89.04 262	92.20 260	77.26 283	91.22 292	94.70 224	82.01 246	84.34 258	90.43 296	78.81 132	96.61 265	83.70 185	81.09 322	93.25 289

WTY-MVS		89.60 131	88.92 135	91.67 153	95.47 128	81.15 183	92.38 256	94.78 220	83.11 222	89.06 141	94.32 162	78.67 135	96.61 265	81.57 225	90.89 197	97.24 104

cl22		86.78 233	85.98 229	89.18 258	92.34 257	77.62 279	90.84 299	94.13 245	81.33 266	83.97 267	90.15 304	73.96 194	96.60 267	84.19 177	82.94 297	93.33 285

cl____		86.52 244	85.78 236	88.75 269	92.03 267	76.46 294	90.74 300	94.30 237	81.83 254	83.34 282	90.78 289	75.74 169	96.57 268	81.74 222	81.54 316	93.22 291

DIV-MVS_self_test		86.53 243	85.78 236	88.75 269	92.02 268	76.45 295	90.74 300	94.30 237	81.83 254	83.34 282	90.82 287	75.75 167	96.57 268	81.73 223	81.52 317	93.24 290

MVP-Stereo		85.97 254	84.86 261	89.32 254	90.92 314	82.19 156	92.11 268	94.19 241	78.76 301	78.77 337	91.63 261	68.38 270	96.56 270	75.01 301	93.95 149	89.20 367
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
FMVSNet3		87.40 208	86.11 223	91.30 169	93.79 214	83.64 108	94.20 177	94.81 218	83.89 201	84.37 254	91.87 254	68.45 269	96.56 270	78.23 269	85.36 274	93.70 274

tpm2		84.08 286	82.94 290	87.48 300	91.39 292	71.27 350	89.23 331	90.37 339	71.95 369	84.64 245	89.33 320	67.30 274	96.55 272	75.17 298	87.09 263	94.63 215

FMVSNet2		87.19 221	85.82 235	91.30 169	94.01 201	83.67 106	94.79 138	94.94 204	83.57 208	83.88 268	92.05 249	66.59 287	96.51 273	77.56 276	85.01 277	93.73 271

pmmvs6		83.42 295	81.60 299	88.87 266	88.01 363	77.87 270	94.96 127	94.24 240	74.67 345	78.80 336	91.09 280	60.17 336	96.49 274	77.06 283	75.40 364	92.23 324

patchmatchnet-post											83.76 372	71.53 222	96.48 275

SCA		86.32 250	85.18 253	89.73 241	92.15 261	76.60 292	91.12 293	91.69 309	83.53 211	85.50 219	88.81 328	66.79 283	96.48 275	76.65 284	90.35 204	96.12 157

pm-mvs1		86.61 239	85.54 243	89.82 235	91.44 288	80.18 208	95.28 107	94.85 214	83.84 202	81.66 300	92.62 225	72.45 217	96.48 275	79.67 253	78.06 350	92.82 307

Vis-MVSNet (Re-imp)		89.59 132	89.44 121	90.03 225	95.74 117	75.85 303	95.61 92	90.80 334	87.66 115	87.83 160	95.40 120	76.79 153	96.46 278	78.37 265	96.73 97	97.80 84

TDRefinement		79.81 330	77.34 335	87.22 308	79.24 393	75.48 307	93.12 232	92.03 299	76.45 325	75.01 359	91.58 264	49.19 377	96.44 279	70.22 331	69.18 377	89.75 361

sd_testset		88.59 168	87.85 168	90.83 190	96.00 106	80.42 203	92.35 258	94.71 223	88.73 76	86.85 184	95.20 128	67.31 273	96.43 280	79.64 254	89.85 213	95.63 181

lessismore_v0				86.04 326	88.46 357	68.78 367		80.59 390		73.01 370	90.11 306	55.39 357	96.43 280	75.06 300	65.06 384	92.90 303

PatchMatch-RL		86.77 236	85.54 243	90.47 207	95.88 112	82.71 144	90.54 303	92.31 288	79.82 285	84.32 259	91.57 266	68.77 265	96.39 282	73.16 313	93.48 161	92.32 322

D2MVS		85.90 255	85.09 255	88.35 279	90.79 319	77.42 281	91.83 274	95.70 158	80.77 275	80.08 322	90.02 308	66.74 285	96.37 283	81.88 218	87.97 248	91.26 343

test_0402		81.30 317	79.17 327	87.67 294	93.19 231	78.17 262	92.98 239	91.71 307	75.25 338	76.02 355	90.31 298	59.23 342	96.37 283	50.22 389	83.63 290	88.47 374

mvs_anonymous		89.37 144	89.32 126	89.51 251	93.47 224	74.22 320	91.65 280	94.83 216	82.91 228	85.45 223	93.79 188	81.23 108	96.36 285	86.47 150	94.09 147	97.94 74

GBi-Net		87.26 213	85.98 229	91.08 179	94.01 201	83.10 125	95.14 117	94.94 204	83.57 208	84.37 254	91.64 258	66.59 287	96.34 286	78.23 269	85.36 274	93.79 263

test1		87.26 213	85.98 229	91.08 179	94.01 201	83.10 125	95.14 117	94.94 204	83.57 208	84.37 254	91.64 258	66.59 287	96.34 286	78.23 269	85.36 274	93.79 263

FMVSNet1		85.85 257	84.11 271	91.08 179	92.81 247	83.10 125	95.14 117	94.94 204	81.64 259	82.68 289	91.64 258	59.01 344	96.34 286	75.37 296	83.78 286	93.79 263

testing222		84.84 277	83.32 282	89.43 253	94.15 197	75.94 301	91.09 294	89.41 358	84.90 180	85.78 207	89.44 319	52.70 370	96.28 289	70.80 327	91.57 186	96.07 161

PatchmatchNet		85.85 257	84.70 264	89.29 255	91.76 278	75.54 306	88.49 341	91.30 320	81.63 260	85.05 238	88.70 332	71.71 220	96.24 290	74.61 305	89.05 228	96.08 160
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
baseline1		88.10 179	87.28 181	90.57 196	94.96 151	80.07 213	94.27 172	91.29 321	86.74 134	87.41 168	94.00 177	76.77 154	96.20 291	80.77 237	79.31 347	95.44 185

ITE_SJBPF				88.24 283	91.88 273	77.05 286		92.92 271	85.54 166	80.13 321	93.30 202	57.29 350	96.20 291	72.46 316	84.71 279	91.49 338

TinyColmap		79.76 331	77.69 334	85.97 327	91.71 281	73.12 329	89.55 323	90.36 340	75.03 340	72.03 373	90.19 302	46.22 383	96.19 293	63.11 368	81.03 324	88.59 373

tpm cat1		81.96 304	80.27 310	87.01 312	91.09 305	71.02 355	87.38 356	91.53 315	66.25 381	80.17 318	86.35 360	68.22 271	96.15 294	69.16 337	82.29 305	93.86 260

gg-mvs-nofinetune		81.77 307	79.37 322	88.99 264	90.85 318	77.73 277	86.29 363	79.63 392	74.88 344	83.19 285	69.05 393	60.34 334	96.11 295	75.46 295	94.64 137	93.11 296

Baseline_NR-MVSNet		87.07 225	86.63 202	88.40 277	91.44 288	77.87 270	94.23 176	92.57 282	84.12 196	85.74 209	92.08 246	77.25 149	96.04 296	82.29 207	79.94 340	91.30 342

MDTV_nov1_ep13			83.56 280		91.69 283	69.93 363	87.75 351	91.54 314	78.60 304	84.86 241	88.90 327	69.54 250	96.03 297	70.25 329	88.93 231

tpmrst		85.35 266	84.99 256	86.43 323	90.88 317	67.88 370	88.71 338	91.43 318	80.13 280	86.08 203	88.80 330	73.05 207	96.02 298	82.48 201	83.40 295	95.40 187

WR-MVS_H		87.80 187	87.37 178	89.10 260	93.23 230	78.12 263	95.61 92	97.30 29	87.90 105	83.72 271	92.01 250	79.65 125	96.01 299	76.36 287	80.54 333	93.16 294

tpm		84.73 278	84.02 273	86.87 318	90.33 332	68.90 366	89.06 334	89.94 349	80.85 274	85.75 208	89.86 312	68.54 268	95.97 300	77.76 273	84.05 285	95.75 175

TransMVSNet (Re)		84.43 282	83.06 289	88.54 275	91.72 279	78.44 254	95.18 113	92.82 275	82.73 232	79.67 328	92.12 242	73.49 201	95.96 301	71.10 325	68.73 380	91.21 344

PEN-MVS		86.80 232	86.27 217	88.40 277	92.32 258	75.71 305	95.18 113	96.38 101	87.97 102	82.82 288	93.15 208	73.39 204	95.92 302	76.15 291	79.03 349	93.59 276

dp		81.47 314	80.23 311	85.17 339	89.92 341	65.49 377	86.74 360	90.10 345	76.30 328	81.10 307	87.12 355	62.81 315	95.92 302	68.13 345	79.88 341	94.09 248

test_post											10.29 404	70.57 238	95.91 304

JIA-IIPM		81.04 318	78.98 330	87.25 305	88.64 353	73.48 327	81.75 386	89.61 356	73.19 359	82.05 296	73.71 390	66.07 295	95.87 305	71.18 323	84.60 280	92.41 318

ET-MVSNet_ETH3D		87.51 203	85.91 233	92.32 122	93.70 218	83.93 99	92.33 260	90.94 330	84.16 194	72.09 372	92.52 228	69.90 244	95.85 306	89.20 114	88.36 242	97.17 108

CP-MVSNet		87.63 195	87.26 183	88.74 271	93.12 233	76.59 293	95.29 105	96.58 91	88.43 86	83.49 279	92.98 214	75.28 173	95.83 307	78.97 262	81.15 321	93.79 263

DTE-MVSNet		86.11 252	85.48 245	87.98 289	91.65 285	74.92 312	94.93 129	95.75 153	87.36 119	82.26 293	93.04 213	72.85 210	95.82 308	74.04 307	77.46 355	93.20 292

UWE-MVS		83.69 294	83.09 287	85.48 333	93.06 236	65.27 379	90.92 297	86.14 372	79.90 283	86.26 199	90.72 291	57.17 351	95.81 309	71.03 326	92.62 176	95.35 190

EPNet_dtu		86.49 247	85.94 232	88.14 286	90.24 334	72.82 332	94.11 181	92.20 292	86.66 137	79.42 331	92.36 233	73.52 200	95.81 309	71.26 320	93.66 153	95.80 174
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PS-CasMVS		87.32 212	86.88 189	88.63 274	92.99 241	76.33 298	95.33 100	96.61 89	88.22 94	83.30 284	93.07 212	73.03 209	95.79 311	78.36 266	81.00 327	93.75 270

LCM-MVSNet-Re		88.30 175	88.32 156	88.27 281	94.71 165	72.41 342	93.15 231	90.98 328	87.77 110	79.25 332	91.96 251	78.35 140	95.75 312	83.04 191	95.62 114	96.65 137

test_vis1_n_1920		89.39 143	89.84 114	88.04 288	92.97 242	72.64 337	94.71 144	96.03 133	86.18 149	91.94 97	96.56 78	61.63 321	95.74 313	93.42 41	95.11 129	95.74 176

pmmvs4		85.43 263	83.86 276	90.16 218	90.02 339	82.97 134	90.27 306	92.67 280	75.93 332	80.73 311	91.74 257	71.05 227	95.73 314	78.85 263	83.46 293	91.78 331

ETVMVS		84.43 282	82.92 291	88.97 265	94.37 185	74.67 314	91.23 291	88.35 363	83.37 216	86.06 204	89.04 324	55.38 358	95.67 315	67.12 350	91.34 188	96.58 140

CR-MVSNet		85.35 266	83.76 277	90.12 221	90.58 327	79.34 236	85.24 371	91.96 304	78.27 310	85.55 213	87.87 345	71.03 228	95.61 316	73.96 309	89.36 222	95.40 187

pmmvs5		84.21 284	82.84 294	88.34 280	88.95 351	76.94 287	92.41 254	91.91 306	75.63 334	80.28 317	91.18 275	64.59 302	95.57 317	77.09 282	83.47 292	92.53 313

test_post1							88.00 347				9.81 405	69.31 256	95.53 318	76.65 284

K. test v3		81.59 311	80.15 313	85.91 330	89.89 342	69.42 365	92.57 251	87.71 367	85.56 165	73.44 368	89.71 315	55.58 355	95.52 319	77.17 280	69.76 374	92.78 308

CHOSEN 280x420		85.15 271	83.99 274	88.65 273	92.47 253	78.40 256	79.68 391	92.76 276	74.90 343	81.41 304	89.59 316	69.85 247	95.51 320	79.92 251	95.29 125	92.03 327

MS-PatchMatch		85.05 273	84.16 270	87.73 293	91.42 291	78.51 252	91.25 290	93.53 261	77.50 316	80.15 319	91.58 264	61.99 319	95.51 320	75.69 293	94.35 145	89.16 368

Patchmtry		82.71 299	80.93 305	88.06 287	90.05 338	76.37 297	84.74 376	91.96 304	72.28 368	81.32 306	87.87 345	71.03 228	95.50 322	68.97 338	80.15 338	92.32 322

XXY-MVS		87.65 192	86.85 191	90.03 225	92.14 262	80.60 199	93.76 205	95.23 191	82.94 227	84.60 246	94.02 175	74.27 186	95.49 323	81.04 231	83.68 289	94.01 253

sss		88.93 157	88.26 159	90.94 189	94.05 199	80.78 194	91.71 277	95.38 184	81.55 262	88.63 146	93.91 184	75.04 176	95.47 324	82.47 202	91.61 185	96.57 141

ppachtmachnet_test		81.84 306	80.07 314	87.15 310	88.46 357	74.43 319	89.04 335	92.16 293	75.33 337	77.75 342	88.99 325	66.20 292	95.37 325	65.12 361	77.60 353	91.65 333

GG-mvs-BLEND				87.94 291	89.73 345	77.91 267	87.80 348	78.23 396		80.58 314	83.86 371	59.88 338	95.33 326	71.20 321	92.22 182	90.60 356

CMPMVS	59.16 21	80.52 322	79.20 326	84.48 343	83.98 382	67.63 372	89.95 319	93.84 256	64.79 384	66.81 383	91.14 278	57.93 348	95.17 327	76.25 289	88.10 244	90.65 353
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVS-HIRNet		73.70 349	72.20 352	78.18 366	91.81 277	56.42 398	82.94 384	82.58 385	55.24 390	68.88 380	66.48 394	55.32 359	95.13 328	58.12 381	88.42 240	83.01 383

test-LLR		85.87 256	85.41 246	87.25 305	90.95 310	71.67 348	89.55 323	89.88 352	83.41 214	84.54 248	87.95 342	67.25 275	95.11 329	81.82 219	93.37 164	94.97 200

test-mter		84.54 281	83.64 279	87.25 305	90.95 310	71.67 348	89.55 323	89.88 352	79.17 292	84.54 248	87.95 342	55.56 356	95.11 329	81.82 219	93.37 164	94.97 200

ambc				83.06 352	79.99 391	63.51 385	77.47 392	92.86 273		74.34 365	84.45 370	28.74 393	95.06 331	73.06 314	68.89 379	90.61 354

IterMVS-SCA-FT		85.45 262	84.53 268	88.18 285	91.71 281	76.87 288	90.19 313	92.65 281	85.40 169	81.44 303	90.54 293	66.79 283	95.00 332	81.04 231	81.05 323	92.66 310

PatchT		82.68 300	81.27 302	86.89 317	90.09 337	70.94 357	84.06 378	90.15 343	74.91 342	85.63 212	83.57 373	69.37 252	94.87 333	65.19 359	88.50 238	94.84 209

test_cas_vis1_n_1920		88.83 162	88.85 140	88.78 267	91.15 303	76.72 290	93.85 202	94.93 208	83.23 221	92.81 72	96.00 96	61.17 330	94.45 334	91.67 83	94.84 131	95.17 195

EPMVS		83.90 291	82.70 295	87.51 297	90.23 335	72.67 335	88.62 340	81.96 387	81.37 265	85.01 239	88.34 336	66.31 290	94.45 334	75.30 297	87.12 262	95.43 186

PMMVS		85.71 260	84.96 258	87.95 290	88.90 352	77.09 285	88.68 339	90.06 346	72.32 367	86.47 190	90.76 290	72.15 218	94.40 336	81.78 221	93.49 159	92.36 320

our_test_3		81.93 305	80.46 308	86.33 325	88.46 357	73.48 327	88.46 342	91.11 323	76.46 324	76.69 349	88.25 338	66.89 281	94.36 337	68.75 339	79.08 348	91.14 346

Anonymous20240521		80.44 324	79.21 325	84.11 347	85.75 377	67.89 369	92.86 244	93.23 266	75.61 335	75.59 357	87.47 349	50.03 374	94.33 338	71.14 324	81.21 318	90.12 359

miper_lstm_enhance		85.27 269	84.59 267	87.31 302	91.28 297	74.63 315	87.69 352	94.09 247	81.20 271	81.36 305	89.85 313	74.97 178	94.30 339	81.03 233	79.84 343	93.01 300

IterMVS		84.88 275	83.98 275	87.60 295	91.44 288	76.03 300	90.18 314	92.41 284	83.24 220	81.06 309	90.42 297	66.60 286	94.28 340	79.46 255	80.98 328	92.48 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LF4IMVS		80.37 325	79.07 329	84.27 346	86.64 370	69.87 364	89.39 328	91.05 326	76.38 326	74.97 360	90.00 309	47.85 380	94.25 341	74.55 306	80.82 330	88.69 372

MDA-MVSNet-bldmvs		78.85 337	76.31 342	86.46 322	89.76 343	73.88 323	88.79 337	90.42 338	79.16 293	59.18 389	88.33 337	60.20 335	94.04 342	62.00 371	68.96 378	91.48 339

WB-MVSnew		83.77 292	83.28 283	85.26 338	91.48 287	71.03 354	91.89 271	87.98 364	78.91 295	84.78 242	90.22 300	69.11 261	94.02 343	64.70 363	90.44 201	90.71 352

KD-MVS_2432*1600		78.50 338	76.02 345	85.93 328	86.22 372	74.47 317	84.80 374	92.33 286	79.29 290	76.98 347	85.92 362	53.81 367	93.97 344	67.39 348	57.42 392	89.36 363

miper_refine_blended		78.50 338	76.02 345	85.93 328	86.22 372	74.47 317	84.80 374	92.33 286	79.29 290	76.98 347	85.92 362	53.81 367	93.97 344	67.39 348	57.42 392	89.36 363

pmmvs-eth3d		80.97 320	78.72 332	87.74 292	84.99 381	79.97 221	90.11 315	91.65 310	75.36 336	73.51 367	86.03 361	59.45 340	93.96 346	75.17 298	72.21 369	89.29 366

test_fmvs1_n		87.03 227	87.04 187	86.97 313	89.74 344	71.86 344	94.55 152	94.43 230	78.47 305	91.95 96	95.50 116	51.16 373	93.81 347	93.02 48	94.56 139	95.26 192

ADS-MVSNet		81.56 312	79.78 316	86.90 316	91.35 294	71.82 345	83.33 381	89.16 359	72.90 362	82.24 294	85.77 364	64.98 300	93.76 348	64.57 364	83.74 287	95.12 196

test_fmvs1		87.34 210	87.56 173	86.68 321	90.59 326	71.80 346	94.01 192	94.04 248	78.30 309	91.97 94	95.22 125	56.28 354	93.71 349	92.89 49	94.71 133	94.52 223

PVSNet_0	73.20 20	77.22 343	74.83 349	84.37 344	90.70 324	71.10 353	83.09 383	89.67 355	72.81 364	73.93 366	83.13 375	60.79 332	93.70 350	68.54 340	50.84 396	88.30 375

TESTMET0.1,1		83.74 293	82.85 293	86.42 324	89.96 340	71.21 352	89.55 323	87.88 365	77.41 317	83.37 281	87.31 350	56.71 352	93.65 351	80.62 241	92.85 174	94.40 234

Patchmatch-RL test		81.67 309	79.96 315	86.81 319	85.42 379	71.23 351	82.17 385	87.50 369	78.47 305	77.19 346	82.50 380	70.81 232	93.48 352	82.66 200	72.89 368	95.71 179

PM-MVS		78.11 340	76.12 344	84.09 348	83.54 384	70.08 362	88.97 336	85.27 378	79.93 282	74.73 362	86.43 358	34.70 392	93.48 352	79.43 258	72.06 370	88.72 371

CVMVSNet		84.69 280	84.79 263	84.37 344	91.84 274	64.92 380	93.70 209	91.47 317	66.19 382	86.16 202	95.28 122	67.18 277	93.33 354	80.89 236	90.42 203	94.88 208

test_vis1_n		86.56 242	86.49 209	86.78 320	88.51 354	72.69 334	94.68 145	93.78 258	79.55 288	90.70 117	95.31 121	48.75 378	93.28 355	93.15 45	93.99 148	94.38 235

UnsupCasMVSNet_bld		76.23 346	73.27 350	85.09 340	83.79 383	72.92 330	85.65 368	93.47 263	71.52 370	68.84 381	79.08 385	49.77 375	93.21 356	66.81 356	60.52 389	89.13 370

ADS-MVSNet2		81.66 310	79.71 319	87.50 298	91.35 294	74.19 321	83.33 381	88.48 362	72.90 362	82.24 294	85.77 364	64.98 300	93.20 357	64.57 364	83.74 287	95.12 196

Anonymous20231206		81.03 319	79.77 318	84.82 341	87.85 366	70.26 361	91.42 284	92.08 297	73.67 354	77.75 342	89.25 321	62.43 317	93.08 358	61.50 373	82.00 310	91.12 347

MIMVSNet		82.59 301	80.53 306	88.76 268	91.51 286	78.32 258	86.57 362	90.13 344	79.32 289	80.70 312	88.69 333	52.98 369	93.07 359	66.03 357	88.86 232	94.90 207

KD-MVS_self_test		80.20 326	79.24 324	83.07 351	85.64 378	65.29 378	91.01 296	93.93 250	78.71 303	76.32 351	86.40 359	59.20 343	92.93 360	72.59 315	69.35 375	91.00 351

Patchmatch-test		81.37 315	79.30 323	87.58 296	90.92 314	74.16 322	80.99 387	87.68 368	70.52 375	76.63 350	88.81 328	71.21 225	92.76 361	60.01 378	86.93 265	95.83 172

CL-MVSNet_self_test		81.74 308	80.53 306	85.36 335	85.96 374	72.45 341	90.25 308	93.07 269	81.24 269	79.85 327	87.29 351	70.93 230	92.52 362	66.95 351	69.23 376	91.11 348

testing3		80.46 323	79.59 321	83.06 352	93.44 226	64.64 381	93.33 220	85.47 376	84.34 193	79.93 325	90.84 286	44.35 386	92.39 363	57.06 384	87.56 255	92.16 326

FMVSNet5		81.52 313	79.60 320	87.27 303	91.17 300	77.95 266	91.49 283	92.26 291	76.87 322	76.16 352	87.91 344	51.67 371	92.34 364	67.74 347	81.16 319	91.52 337

EU-MVSNet		81.32 316	80.95 304	82.42 356	88.50 356	63.67 384	93.32 221	91.33 319	64.02 385	80.57 315	92.83 218	61.21 328	92.27 365	76.34 288	80.38 337	91.32 341

YYNet1		79.22 335	77.20 337	85.28 337	88.20 362	72.66 336	85.87 365	90.05 348	74.33 348	62.70 385	87.61 347	66.09 294	92.03 366	66.94 352	72.97 367	91.15 345

test_fmvs2		83.98 287	84.03 272	83.83 349	87.16 368	67.53 373	93.93 198	92.89 272	77.62 315	86.89 183	93.53 195	47.18 382	92.02 367	90.54 102	86.51 267	91.93 329

MDA-MVSNet_test_wron		79.21 336	77.19 338	85.29 336	88.22 361	72.77 333	85.87 365	90.06 346	74.34 347	62.62 387	87.56 348	66.14 293	91.99 368	66.90 355	73.01 366	91.10 349

MIMVSNet1		79.38 334	77.28 336	85.69 332	86.35 371	73.67 324	91.61 281	92.75 277	78.11 314	72.64 371	88.12 340	48.16 379	91.97 369	60.32 375	77.49 354	91.43 340

UnsupCasMVSNet_eth		80.07 327	78.27 333	85.46 334	85.24 380	72.63 338	88.45 343	94.87 213	82.99 226	71.64 375	88.07 341	56.34 353	91.75 370	73.48 312	63.36 387	92.01 328

N_pmnet		68.89 354	68.44 356	70.23 374	89.07 350	28.79 411	88.06 345	19.50 411	69.47 377	71.86 374	84.93 367	61.24 327	91.75 370	54.70 386	77.15 356	90.15 358

new-patchmatchnet		76.41 345	75.17 348	80.13 360	82.65 387	59.61 391	87.66 353	91.08 324	78.23 312	69.85 379	83.22 374	54.76 361	91.63 372	64.14 366	64.89 385	89.16 368

Syy-MVS		80.07 327	79.78 316	80.94 359	91.92 270	59.93 390	89.75 321	87.40 370	81.72 256	78.82 334	87.20 352	66.29 291	91.29 373	47.06 391	87.84 251	91.60 335

myMVS_eth3d		79.67 332	78.79 331	82.32 357	91.92 270	64.08 382	89.75 321	87.40 370	81.72 256	78.82 334	87.20 352	45.33 384	91.29 373	59.09 380	87.84 251	91.60 335

dmvs_re		84.20 285	83.22 286	87.14 311	91.83 276	77.81 272	90.04 316	90.19 342	84.70 188	81.49 301	89.17 322	64.37 304	91.13 375	71.58 319	85.65 273	92.46 316

test_vis1_rt		77.96 341	76.46 341	82.48 355	85.89 375	71.74 347	90.25 308	78.89 393	71.03 374	71.30 376	81.35 382	42.49 388	91.05 376	84.55 173	82.37 304	84.65 380

mvsany_test1		85.42 264	85.30 251	85.77 331	87.95 365	75.41 308	87.61 355	80.97 389	76.82 323	88.68 145	95.83 104	77.44 148	90.82 377	85.90 156	86.51 267	91.08 350

testgi		80.94 321	80.20 312	83.18 350	87.96 364	66.29 374	91.28 288	90.70 336	83.70 205	78.12 339	92.84 217	51.37 372	90.82 377	63.34 367	82.46 303	92.43 317

test20.03		79.95 329	79.08 328	82.55 354	85.79 376	67.74 371	91.09 294	91.08 324	81.23 270	74.48 364	89.96 311	61.63 321	90.15 379	60.08 376	76.38 360	89.76 360

EGC-MVSNET		61.97 360	56.37 364	78.77 364	89.63 346	73.50 326	89.12 333	82.79 384	0.21 408	1.24 409	84.80 368	39.48 389	90.04 380	44.13 393	75.94 363	72.79 392

APD_test1		69.04 353	66.26 359	77.36 368	80.51 390	62.79 387	85.46 370	83.51 383	54.11 392	59.14 390	84.79 369	23.40 399	89.61 381	55.22 385	70.24 373	79.68 389

pmmvs3		71.81 352	68.71 355	81.11 358	75.86 394	70.42 360	86.74 360	83.66 382	58.95 389	68.64 382	80.89 383	36.93 390	89.52 382	63.10 369	63.59 386	83.39 381

test_vis3_rt		65.12 358	62.60 360	72.69 371	71.44 398	60.71 389	87.17 357	65.55 404	63.80 386	53.22 392	65.65 396	14.54 406	89.44 383	76.65 284	65.38 383	67.91 395

mvsany_test3		74.95 347	73.26 351	80.02 361	74.61 395	63.16 386	85.53 369	78.42 394	74.16 349	74.89 361	86.46 357	36.02 391	89.09 384	82.39 204	66.91 381	87.82 378

test0.0.03 1		82.41 302	81.69 298	84.59 342	88.23 360	72.89 331	90.24 310	87.83 366	83.41 214	79.86 326	89.78 314	67.25 275	88.99 385	65.18 360	83.42 294	91.90 330

DSMNet-mixed		76.94 344	76.29 343	78.89 363	83.10 385	56.11 399	87.78 349	79.77 391	60.65 388	75.64 356	88.71 331	61.56 323	88.34 386	60.07 377	89.29 224	92.21 325

test_fmvs3		77.67 342	77.16 339	79.22 362	79.52 392	61.14 388	92.34 259	91.64 311	73.98 351	78.86 333	86.59 356	27.38 396	87.03 387	88.12 127	75.97 362	89.50 362

LCM-MVSNet		66.00 357	62.16 362	77.51 367	64.51 405	58.29 393	83.87 380	90.90 331	48.17 394	54.69 391	73.31 391	16.83 405	86.75 388	65.47 358	61.67 388	87.48 379

WB-MVS		67.92 355	67.49 357	69.21 377	81.09 388	41.17 405	88.03 346	78.00 397	73.50 356	62.63 386	83.11 377	63.94 306	86.52 389	25.66 402	51.45 395	79.94 388

SSC-MVS		67.06 356	66.56 358	68.56 379	80.54 389	40.06 407	87.77 350	77.37 400	72.38 366	61.75 388	82.66 379	63.37 311	86.45 390	24.48 403	48.69 398	79.16 390

new_pmnet		72.15 350	70.13 354	78.20 365	82.95 386	65.68 375	83.91 379	82.40 386	62.94 387	64.47 384	79.82 384	42.85 387	86.26 391	57.41 383	74.44 365	82.65 385

Gipuma		57.99 365	54.91 367	67.24 380	88.51 354	65.59 376	52.21 399	90.33 341	43.58 396	42.84 399	51.18 400	20.29 402	85.07 392	34.77 399	70.45 372	51.05 399
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testf1		59.54 362	56.11 365	69.85 375	69.28 400	56.61 396	80.37 389	76.55 401	42.58 397	45.68 396	75.61 386	11.26 407	84.18 393	43.20 395	60.44 390	68.75 393

APD_test2		59.54 362	56.11 365	69.85 375	69.28 400	56.61 396	80.37 389	76.55 401	42.58 397	45.68 396	75.61 386	11.26 407	84.18 393	43.20 395	60.44 390	68.75 393

dmvs_testset		74.57 348	75.81 347	70.86 373	87.72 367	40.47 406	87.05 359	77.90 398	82.75 231	71.15 377	85.47 366	67.98 272	84.12 395	45.26 392	76.98 359	88.00 376

PMVS	47.18 22	52.22 366	48.46 370	63.48 381	45.72 410	46.20 404	73.41 395	78.31 395	41.03 399	30.06 402	65.68 395	6.05 409	83.43 396	30.04 400	65.86 382	60.80 396
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_f		71.95 351	70.87 353	75.21 369	74.21 397	59.37 392	85.07 373	85.82 374	65.25 383	70.42 378	83.13 375	23.62 397	82.93 397	78.32 267	71.94 371	83.33 382

FPMVS		64.63 359	62.55 361	70.88 372	70.80 399	56.71 394	84.42 377	84.42 380	51.78 393	49.57 393	81.61 381	23.49 398	81.48 398	40.61 398	76.25 361	74.46 391

PMMVS2		59.60 361	56.40 363	69.21 377	68.83 402	46.58 403	73.02 396	77.48 399	55.07 391	49.21 394	72.95 392	17.43 404	80.04 399	49.32 390	44.33 399	80.99 387

ANet_high		58.88 364	54.22 368	72.86 370	56.50 408	56.67 395	80.75 388	86.00 373	73.09 361	37.39 400	64.63 397	22.17 400	79.49 400	43.51 394	23.96 402	82.43 386

test_method		50.52 367	48.47 369	56.66 383	52.26 409	18.98 413	41.51 401	81.40 388	10.10 403	44.59 398	75.01 389	28.51 394	68.16 401	53.54 387	49.31 397	82.83 384

E-PMN		43.23 369	42.29 371	46.03 385	65.58 404	37.41 408	73.51 394	64.62 405	33.99 400	28.47 404	47.87 401	19.90 403	67.91 402	22.23 404	24.45 401	32.77 400

EMVS		42.07 370	41.12 372	44.92 386	63.45 406	35.56 410	73.65 393	63.48 406	33.05 401	26.88 405	45.45 402	21.27 401	67.14 403	19.80 405	23.02 403	32.06 401

MVE	39.65 23	43.39 368	38.59 374	57.77 382	56.52 407	48.77 402	55.38 398	58.64 408	29.33 402	28.96 403	52.65 399	4.68 410	64.62 404	28.11 401	33.07 400	59.93 397
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				56.31 384	74.23 396	51.81 401		56.67 409	44.85 395	48.54 395	75.16 388	27.87 395	58.74 405	40.92 397	52.22 394	58.39 398

wuyk23d		21.27 373	20.48 376	23.63 388	68.59 403	36.41 409	49.57 400	6.85 412	9.37 404	7.89 406	4.46 408	4.03 411	31.37 406	17.47 406	16.07 405	3.12 403

tmp_tt		35.64 371	39.24 373	24.84 387	14.87 411	23.90 412	62.71 397	51.51 410	6.58 405	36.66 401	62.08 398	44.37 385	30.34 407	52.40 388	22.00 404	20.27 402

test123		8.76 375	11.22 378	1.39 389	0.85 413	0.97 414	85.76 367	0.35 414	0.54 407	2.45 408	8.14 407	0.60 412	0.48 408	2.16 408	0.17 407	2.71 404

testmvs		8.92 374	11.52 377	1.12 390	1.06 412	0.46 415	86.02 364	0.65 413	0.62 406	2.74 407	9.52 406	0.31 413	0.45 409	2.38 407	0.39 406	2.46 405

test_blank		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

cdsmvs_eth3d_5k		22.14 372	29.52 375	0.00 391	0.00 414	0.00 416	0.00 402	95.76 152	0.00 409	0.00 410	94.29 164	75.66 170	0.00 410	0.00 409	0.00 408	0.00 406

pcd_1.5k_mvsjas		6.64 377	8.86 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	79.70 121	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

ab-mvs-re		7.82 376	10.43 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	93.88 185	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

WAC-MVS						64.08 382								59.14 379

FOURS1					98.86 1	85.54 65	98.29 1	97.49 6	89.79 44	96.29 18

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

eth-test2					0.00 414

eth-test					0.00 414

RE-MVS-def			93.68 52		97.92 43	84.57 80	96.28 45	96.76 75	87.46 116	93.75 49	97.43 31	82.94 83		92.73 51	97.80 74	97.88 78

IU-MVS					98.77 5	86.00 49		96.84 65	81.26 268	97.26 7				95.50 23	99.13 3	99.03 8

save fliter					97.85 46	85.63 64	95.21 111	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																96.12 157

test_part2					98.55 12	87.22 18				96.40 17

sam_mvs1												71.70 221				96.12 157

sam_mvs												70.60 234

MTGPA								96.97 50

MTMP							96.16 53	60.64 407

test9_res														91.91 78	98.71 32	98.07 66

agg_prior2														90.54 102	98.68 37	98.27 52

test_prior4						85.96 53	94.11 181

test_prior2							94.12 180		87.67 114	92.63 79	96.39 82	86.62 38		91.50 85	98.67 39

新几何2							93.11 234

旧先验1					96.79 76	81.81 164		95.67 160			96.81 63	86.69 37			97.66 79	96.97 122

原ACMM2							92.94 241

test222					96.55 84	81.70 166	92.22 264	95.01 201	68.36 379	90.20 124	96.14 92	80.26 114			97.80 74	96.05 164

segment_acmp												87.16 36

testdata1							92.15 266		87.94 103

plane_prior7					94.70 166	82.74 141

plane_prior6					94.52 176	82.75 139						74.23 187

plane_prior4											94.86 140

plane_prior3						82.75 139			90.26 33	86.91 180

plane_prior2							95.85 75		90.81 17

plane_prior1					94.59 171

plane_prior						82.73 142	95.21 111		89.66 48						89.88 212

n2								0.00 415

nn								0.00 415

door-mid								85.49 375

test11								96.57 92

door								85.33 377

HQP5-MVS						81.56 168

HQP-NCC					94.17 194		94.39 165		88.81 72	85.43 226

ACMP_Plane					94.17 194		94.39 165		88.81 72	85.43 226

BP-MVS														87.11 143

HQP3-MVS								96.04 131							89.77 216

HQP2-MVS												73.83 197

NP-MVS					94.37 185	82.42 151					93.98 178

MDTV_nov1_ep13_2view						55.91 400	87.62 354		73.32 358	84.59 247		70.33 241		74.65 304		95.50 184

ACMMP++_ref															87.47 256

ACMMP++															88.01 247

Test By Simon												80.02 116

High-resolution multi-view benchmark