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.

AdaColmap		93.82 144	93.06 152	96.10 129	99.88 1	89.07 185	98.33 217	97.55 135	86.81 259	90.39 214	98.65 110	75.09 262	99.98 9	93.32 168	97.53 139	99.26 110

DP-MVS Recon		95.85 75	95.15 93	97.95 32	99.87 2	94.38 57	99.60 49	97.48 151	86.58 264	94.42 143	99.13 52	87.36 102	99.98 9	93.64 160	98.33 120	99.48 88

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 35	97.98 55	97.18 8	95.96 110	99.33 22	92.62 27	100.00 1	98.99 34	99.93 1	99.98 6

CNVR-MVS		98.46 1	98.38 1	98.72 10	99.80 4	96.19 15	99.80 22	97.99 54	97.05 10	99.41 6	99.59 2	92.89 26	100.00 1	98.99 34	99.90 7	99.96 10

MG-MVS		97.24 20	96.83 33	98.47 15	99.79 5	95.71 19	99.07 126	99.06 10	94.45 50	96.42 103	98.70 107	88.81 75	99.74 100	95.35 125	99.86 12	99.97 7

NCCC		98.12 5	98.11 3	98.13 25	99.76 6	94.46 53	99.81 17	97.88 61	96.54 18	98.84 30	99.46 10	92.55 28	99.98 9	98.25 59	99.93 1	99.94 18

region2R		96.30 56	96.17 60	96.70 92	99.70 7	90.31 151	99.46 69	97.66 106	90.55 145	97.07 82	99.07 61	86.85 113	99.97 21	95.43 123	99.74 29	99.81 35

HFP-MVS		96.42 52	96.26 52	96.90 80	99.69 8	90.96 137	99.47 65	97.81 74	90.54 146	96.88 86	99.05 65	87.57 94	99.96 28	95.65 115	99.72 32	99.78 41

ACMMPR		96.28 57	96.14 64	96.73 89	99.68 9	90.47 149	99.47 65	97.80 76	90.54 146	96.83 91	99.03 67	86.51 126	99.95 32	95.65 115	99.72 32	99.75 49

ZD-MVS					99.67 10	93.28 79		97.61 122	87.78 234	97.41 72	99.16 43	90.15 58	99.56 117	98.35 54	99.70 37

CP-MVS		96.22 58	96.15 63	96.42 110	99.67 10	89.62 175	99.70 35	97.61 122	90.07 161	96.00 109	99.16 43	87.43 97	99.92 43	96.03 109	99.72 32	99.70 55

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 32	99.72 32	97.47 153	93.95 58	99.07 21	99.46 10	93.18 23	99.97 21	99.64 8	99.82 19	99.69 58
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				98.77 8	99.66 12	96.37 14	99.72 32	97.68 100					99.98 9	99.64 8	99.82 19	99.96 10

test0726					99.66 12	95.20 32	99.77 25	97.70 94	93.95 58	99.35 10	99.54 3	93.18 23

CPTT-MVS		94.60 122	94.43 110	95.09 173	99.66 12	86.85 247	99.44 72	97.47 153	83.22 320	94.34 147	98.96 78	82.50 196	99.55 118	94.81 139	99.50 55	98.88 145

MSLP-MVS++		97.50 17	97.45 18	97.63 42	99.65 16	93.21 81	99.70 35	98.13 43	94.61 44	97.78 67	99.46 10	89.85 61	99.81 88	97.97 63	99.91 6	99.88 26

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 25				99.19 37	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 27	99.77 25	97.72 89	94.17 53	99.30 12	99.54 3	93.32 20	99.98 9	99.70 5	99.81 23	99.99 1

IU-MVS					99.63 18	95.38 24		97.73 88	95.54 33	99.54 4				99.69 7	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 27		97.72 89	94.16 55	99.30 12	99.49 9	93.32 20	99.98 9

PAPR		96.35 53	95.82 71	97.94 33	99.63 18	94.19 62	99.42 78	97.55 135	92.43 97	93.82 159	99.12 55	87.30 104	99.91 49	94.02 152	99.06 81	99.74 50

XVS		96.47 50	96.37 49	96.77 85	99.62 22	90.66 145	99.43 76	97.58 130	92.41 100	96.86 87	98.96 78	87.37 99	99.87 66	95.65 115	99.43 61	99.78 41

X-MVStestdata		90.69 220	88.66 243	96.77 85	99.62 22	90.66 145	99.43 76	97.58 130	92.41 100	96.86 87	29.59 437	87.37 99	99.87 66	95.65 115	99.43 61	99.78 41

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 24	99.55 54	97.68 100	93.01 83	99.23 15	99.45 14	95.12 8	99.98 9	99.25 21	99.92 3	99.97 7

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 98					99.98 9	99.55 14	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 98					99.98 9	99.55 14	99.83 15	99.96 10

DeepC-MVS_fast	93.52 2	97.16 24	96.84 31	98.13 25	99.61 24	94.45 54	98.85 148	97.64 115	96.51 21	95.88 113	99.39 18	87.35 103	99.99 5	96.61 95	99.69 38	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_one_0601					99.59 28	94.89 37		97.64 115	93.14 82	98.93 27	99.45 14	93.45 18

CDPH-MVS		96.56 48	96.18 57	97.70 40	99.59 28	93.92 65	99.13 120	97.44 160	89.02 190	97.90 64	99.22 31	88.90 74	99.49 124	94.63 144	99.79 27	99.68 60

test_prior				97.01 70	99.58 30	91.77 114		97.57 133					99.49 124			99.79 38

APDe-MVS		97.53 15	97.47 16	97.70 40	99.58 30	93.63 70	99.56 53	97.52 143	93.59 73	98.01 61	99.12 55	90.80 45	99.55 118	99.26 19	99.79 27	99.93 20
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
mPP-MVS		95.90 73	95.75 76	96.38 113	99.58 30	89.41 179	99.26 98	97.41 164	90.66 137	94.82 135	98.95 81	86.15 134	99.98 9	95.24 130	99.64 42	99.74 50

TEST9					99.57 33	93.17 83	99.38 82	97.66 106	89.57 175	98.39 46	99.18 40	90.88 43	99.66 106

train_agg		97.20 23	97.08 23	97.57 46	99.57 33	93.17 83	99.38 82	97.66 106	90.18 155	98.39 46	99.18 40	90.94 39	99.66 106	98.58 45	99.85 13	99.88 26

test_8					99.55 35	93.07 86	99.37 85	97.64 115	90.18 155	98.36 48	99.19 37	90.94 39	99.64 112

test_part2					99.54 36	95.42 22				98.13 53

MSP-MVS		97.77 10	98.18 2	96.53 105	99.54 36	90.14 157	99.41 79	97.70 94	95.46 35	98.60 39	99.19 37	95.71 5	99.49 124	98.15 61	99.85 13	99.95 15
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
agg_prior					99.54 36	92.66 98		97.64 115		97.98 62			99.61 114

CSCG		94.87 111	94.71 104	95.36 160	99.54 36	86.49 252	99.34 89	98.15 41	82.71 333	90.15 217	99.25 26	89.48 66	99.86 72	94.97 137	98.82 96	99.72 53

HPM-MVS++		97.72 12	97.59 13	98.14 24	99.53 40	94.76 45	99.19 103	97.75 84	95.66 31	98.21 51	99.29 23	91.10 36	99.99 5	97.68 69	99.87 9	99.68 60

APD-MVS		96.95 31	96.72 37	97.63 42	99.51 41	93.58 71	99.16 109	97.44 160	90.08 160	98.59 40	99.07 61	89.06 69	99.42 135	97.92 64	99.66 39	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
FOURS1					99.50 42	88.94 194	99.55 54	97.47 153	91.32 124	98.12 55

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 23	99.29 92	97.72 89	94.50 46	98.64 38	99.54 3	93.32 20	99.97 21	99.58 12	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PGM-MVS		95.85 75	95.65 81	96.45 108	99.50 42	89.77 172	98.22 226	98.90 13	89.19 185	96.74 96	98.95 81	85.91 138	99.92 43	93.94 153	99.46 57	99.66 64

GST-MVS		95.97 68	95.66 79	96.90 80	99.49 45	91.22 124	99.45 71	97.48 151	89.69 169	95.89 112	98.72 103	86.37 129	99.95 32	94.62 145	99.22 74	99.52 82

MP-MVS		96.00 65	95.82 71	96.54 104	99.47 46	90.13 159	99.36 86	97.41 164	90.64 140	95.49 125	98.95 81	85.51 143	99.98 9	96.00 110	99.59 51	99.52 82
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.09 62	95.81 73	96.95 78	99.42 47	91.19 126	99.55 54	97.53 139	89.72 168	95.86 115	98.94 84	86.59 121	99.97 21	95.13 131	99.56 52	99.68 60

SR-MVS		96.13 61	96.16 62	96.07 130	99.42 47	89.04 186	98.59 184	97.33 175	90.44 149	96.84 89	99.12 55	86.75 115	99.41 138	97.47 72	99.44 60	99.76 48

PAPM_NR		95.43 91	95.05 98	96.57 103	99.42 47	90.14 157	98.58 186	97.51 145	90.65 139	92.44 178	98.90 88	87.77 93	99.90 53	90.88 193	99.32 66	99.68 60

9.14			96.87 29		99.34 50		99.50 61	97.49 150	89.41 182	98.59 40	99.43 16	89.78 62	99.69 103	98.69 39	99.62 46

save fliter					99.34 50	93.85 67	99.65 45	97.63 119	95.69 29

PHI-MVS		96.65 43	96.46 47	97.21 62	99.34 50	91.77 114	99.70 35	98.05 48	86.48 269	98.05 58	99.20 34	89.33 67	99.96 28	98.38 52	99.62 46	99.90 22

test12				97.83 35	99.33 53	94.45 54		97.55 135		97.56 68		88.60 78	99.50 123		99.71 36	99.55 79

SMA-MVS		97.24 20	96.99 24	98.00 31	99.30 54	94.20 61	99.16 109	97.65 113	89.55 177	99.22 17	99.52 8	90.34 55	99.99 5	98.32 56	99.83 15	99.82 32
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
MTAPA		96.09 62	95.80 74	96.96 77	99.29 55	91.19 126	97.23 288	97.45 156	92.58 94	94.39 145	99.24 28	86.43 128	99.99 5	96.22 102	99.40 64	99.71 54

HPM-MVS		95.41 93	95.22 91	95.99 136	99.29 55	89.14 183	99.17 108	97.09 200	87.28 248	95.40 126	98.48 127	84.93 153	99.38 140	95.64 119	99.65 40	99.47 90
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		94.67 120	94.30 111	95.79 145	99.25 57	88.13 215	98.41 205	98.67 21	90.38 151	91.43 195	98.72 103	82.22 205	99.95 32	93.83 157	95.76 176	99.29 107
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
APD-MVS_3200maxsize		95.64 88	95.65 81	95.62 153	99.24 58	87.80 221	98.42 203	97.22 183	88.93 195	96.64 101	98.98 72	85.49 144	99.36 142	96.68 92	99.27 70	99.70 55

SR-MVS-dyc-post		95.75 82	95.86 69	95.41 159	99.22 59	87.26 242	98.40 208	97.21 184	89.63 171	96.67 99	98.97 73	86.73 117	99.36 142	96.62 93	99.31 67	99.60 74

RE-MVS-def			95.70 77		99.22 59	87.26 242	98.40 208	97.21 184	89.63 171	96.67 99	98.97 73	85.24 150		96.62 93	99.31 67	99.60 74

patch_mono-2		97.10 27	97.97 8	94.49 196	99.21 61	83.73 312	99.62 48	98.25 32	95.28 37	99.38 9	98.91 86	92.28 31	99.94 35	99.61 11	99.22 74	99.78 41

API-MVS		94.78 114	94.18 117	96.59 100	99.21 61	90.06 164	98.80 154	97.78 81	83.59 315	93.85 157	99.21 33	83.79 167	99.97 21	92.37 179	99.00 85	99.74 50

PLC	91.07 3	94.23 132	94.01 121	94.87 181	99.17 63	87.49 231	99.25 99	96.55 236	88.43 211	91.26 199	98.21 140	85.92 136	99.86 72	89.77 208	97.57 136	97.24 226
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EI-MVSNet-Vis-set		95.76 81	95.63 83	96.17 126	99.14 64	90.33 150	98.49 196	97.82 70	91.92 109	94.75 137	98.88 92	87.06 109	99.48 128	95.40 124	97.17 149	98.70 164

TSAR-MVS + MP.		97.44 18	97.46 17	97.39 54	99.12 65	93.49 76	98.52 190	97.50 148	94.46 48	98.99 23	98.64 111	91.58 33	99.08 160	98.49 49	99.83 15	99.60 74
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		97.22 22	96.92 26	98.12 27	99.11 66	94.88 38	99.44 72	97.45 156	89.60 173	98.70 35	99.42 17	90.42 52	99.72 101	98.47 50	99.65 40	99.77 46

HPM-MVS_fast		94.89 107	94.62 105	95.70 148	99.11 66	88.44 211	99.14 117	97.11 196	85.82 277	95.69 121	98.47 128	83.46 172	99.32 147	93.16 170	99.63 45	99.35 101

MAR-MVS		94.43 128	94.09 119	95.45 157	99.10 68	87.47 232	98.39 212	97.79 78	88.37 213	94.02 153	99.17 42	78.64 245	99.91 49	92.48 178	98.85 95	98.96 135
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
114514_t		94.06 134	93.05 153	97.06 68	99.08 69	92.26 108	98.97 140	97.01 208	82.58 335	92.57 176	98.22 138	80.68 225	99.30 148	89.34 214	99.02 84	99.63 71

EI-MVSNet-UG-set		95.43 91	95.29 89	95.86 142	99.07 70	89.87 169	98.43 202	97.80 76	91.78 111	94.11 150	98.77 97	86.25 132	99.48 128	94.95 138	96.45 161	98.22 196

原ACMM1				96.18 124	99.03 71	90.08 160		97.63 119	88.98 191	97.00 84	98.97 73	88.14 87	99.71 102	88.23 226	99.62 46	98.76 160

SD-MVS		97.51 16	97.40 19	97.81 36	99.01 72	93.79 69	99.33 90	97.38 168	93.73 69	98.83 31	99.02 69	90.87 44	99.88 62	98.69 39	99.74 29	99.77 46
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
MVS_0304		97.81 9	97.51 15	98.74 9	98.97 73	96.57 11	99.91 2	98.17 37	97.45 4	98.76 33	98.97 73	86.69 118	99.96 28	99.72 3	98.92 91	99.69 58

旧先验1					98.97 73	92.90 94		97.74 85			99.15 47	91.05 38			99.33 65	99.60 74

LS3D		90.19 230	88.72 241	94.59 195	98.97 73	86.33 259	96.90 301	96.60 230	74.96 389	84.06 274	98.74 100	75.78 259	99.83 82	74.93 349	97.57 136	97.62 215

CNLPA		93.64 151	92.74 160	96.36 115	98.96 76	90.01 167	99.19 103	95.89 295	86.22 272	89.40 226	98.85 93	80.66 226	99.84 78	88.57 222	96.92 154	99.24 111

reproduce-ours		96.66 40	96.80 34	96.22 120	98.95 77	89.03 188	98.62 176	97.38 168	93.42 75	96.80 94	99.36 19	88.92 72	99.80 90	98.51 47	99.26 71	99.82 32

our_new_method		96.66 40	96.80 34	96.22 120	98.95 77	89.03 188	98.62 176	97.38 168	93.42 75	96.80 94	99.36 19	88.92 72	99.80 90	98.51 47	99.26 71	99.82 32

MP-MVS-pluss		95.80 78	95.30 88	97.29 57	98.95 77	92.66 98	98.59 184	97.14 192	88.95 193	93.12 168	99.25 26	85.62 140	99.94 35	96.56 97	99.48 56	99.28 108
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
reproduce_model		96.57 47	96.75 36	96.02 133	98.93 80	88.46 210	98.56 187	97.34 174	93.18 81	96.96 85	99.35 21	88.69 77	99.80 90	98.53 46	99.21 77	99.79 38

新几何1				97.40 53	98.92 81	92.51 104		97.77 83	85.52 282	96.69 98	99.06 63	88.08 88	99.89 60	84.88 264	99.62 46	99.79 38

DP-MVS		88.75 258	86.56 277	95.34 162	98.92 81	87.45 233	97.64 272	93.52 378	70.55 402	81.49 316	97.25 177	74.43 268	99.88 62	71.14 373	94.09 193	98.67 166

TSAR-MVS + GP.		96.95 31	96.91 27	97.07 67	98.88 83	91.62 118	99.58 51	96.54 237	95.09 40	96.84 89	98.63 113	91.16 34	99.77 97	99.04 31	96.42 162	99.81 35

CANet		97.00 30	96.49 44	98.55 12	98.86 84	96.10 16	99.83 12	97.52 143	95.90 25	97.21 78	98.90 88	82.66 194	99.93 40	98.71 38	98.80 97	99.63 71

dcpmvs_2		95.67 87	96.18 57	94.12 212	98.82 85	84.22 305	97.37 281	95.45 322	90.70 136	95.77 118	98.63 113	90.47 50	98.68 182	99.20 25	99.22 74	99.45 91

ACMMP_NAP		96.59 44	96.18 57	97.81 36	98.82 85	93.55 73	98.88 147	97.59 128	90.66 137	97.98 62	99.14 50	86.59 121	100.00 1	96.47 99	99.46 57	99.89 25

PVSNet_BlendedMVS		93.36 159	93.20 150	93.84 224	98.77 87	91.61 119	99.47 65	98.04 50	91.44 120	94.21 148	92.63 300	83.50 170	99.87 66	97.41 73	83.37 297	90.05 363

PVSNet_Blended		95.94 71	95.66 79	96.75 87	98.77 87	91.61 119	99.88 4	98.04 50	93.64 72	94.21 148	97.76 151	83.50 170	99.87 66	97.41 73	97.75 133	98.79 155

DeepPCF-MVS	93.56 1	96.55 49	97.84 10	92.68 249	98.71 89	78.11 372	99.70 35	97.71 93	98.18 1	97.36 74	99.76 1	90.37 54	99.94 35	99.27 18	99.54 54	99.99 1

EPNet		96.82 35	96.68 39	97.25 61	98.65 90	93.10 85	99.48 63	98.76 14	96.54 18	97.84 65	98.22 138	87.49 96	99.66 106	95.35 125	97.78 132	99.00 131
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		93.90 141	93.62 138	94.73 188	98.63 91	87.00 245	98.04 245	96.56 235	92.19 104	92.46 177	98.73 101	79.49 236	99.14 157	92.16 181	94.34 191	98.03 203

MVS_111021_HR		96.69 39	96.69 38	96.72 91	98.58 92	91.00 136	99.14 117	99.45 1	93.86 64	95.15 131	98.73 101	88.48 79	99.76 98	97.23 79	99.56 52	99.40 95

test_yl		95.27 97	94.60 106	97.28 59	98.53 93	92.98 89	99.05 130	98.70 18	86.76 261	94.65 140	97.74 153	87.78 91	99.44 131	95.57 121	92.61 209	99.44 92

DCV-MVSNet		95.27 97	94.60 106	97.28 59	98.53 93	92.98 89	99.05 130	98.70 18	86.76 261	94.65 140	97.74 153	87.78 91	99.44 131	95.57 121	92.61 209	99.44 92

TAPA-MVS	87.50 9	90.35 225	89.05 234	94.25 207	98.48 95	85.17 291	98.42 203	96.58 234	82.44 340	87.24 245	98.53 117	82.77 188	98.84 170	59.09 411	97.88 128	98.72 162
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.32 96	91.21 125	98.08 243	97.58 130	83.74 311	95.87 114	99.02 69	86.74 116			99.64 42	99.81 35

MM		97.76 11	97.39 20	98.86 5	98.30 97	96.83 7	99.81 17	99.13 9	97.66 2	98.29 50	98.96 78	85.84 139	99.90 53	99.72 3	98.80 97	99.85 30

reproduce_monomvs		92.11 191	91.82 182	92.98 239	98.25 98	90.55 147	98.38 214	97.93 58	94.81 41	80.46 326	92.37 302	96.46 3	97.17 267	94.06 151	73.61 358	91.23 331

DPM-MVS		97.86 8	97.25 22	99.68 1	98.25 98	99.10 1	99.76 28	97.78 81	96.61 17	98.15 52	99.53 7	93.62 17	100.00 1	91.79 184	99.80 26	99.94 18

LFMVS		92.23 187	90.84 203	96.42 110	98.24 100	91.08 133	98.24 225	96.22 257	83.39 318	94.74 138	98.31 134	61.12 363	98.85 169	94.45 147	92.82 205	99.32 104

testdata				95.26 167	98.20 101	87.28 239		97.60 124	85.21 286	98.48 43	99.15 47	88.15 86	98.72 180	90.29 201	99.45 59	99.78 41

PatchMatch-RL		91.47 199	90.54 210	94.26 206	98.20 101	86.36 258	96.94 299	97.14 192	87.75 236	88.98 229	95.75 240	71.80 296	99.40 139	80.92 307	97.39 143	97.02 234

MVS_111021_LR		95.78 79	95.94 66	95.28 166	98.19 103	87.69 223	98.80 154	99.26 7	93.39 77	95.04 133	98.69 108	84.09 164	99.76 98	96.96 85	99.06 81	98.38 183

F-COLMAP		92.07 192	91.75 185	93.02 238	98.16 104	82.89 324	98.79 158	95.97 277	86.54 266	87.92 237	97.80 148	78.69 244	99.65 110	85.97 250	95.93 175	96.53 248

Anonymous202405211		88.84 252	87.03 271	94.27 205	98.14 105	84.18 306	98.44 201	95.58 315	76.79 381	89.34 227	96.88 203	53.42 393	99.54 120	87.53 234	87.12 265	99.09 126

VNet		95.08 104	94.26 112	97.55 47	98.07 106	93.88 66	98.68 167	98.73 17	90.33 152	97.16 81	97.43 169	79.19 239	99.53 121	96.91 87	91.85 226	99.24 111

SPE-MVS-test		95.98 67	96.34 51	94.90 180	98.06 107	87.66 226	99.69 42	96.10 268	93.66 70	98.35 49	99.05 65	86.28 130	97.66 243	96.96 85	98.90 93	99.37 98

DELS-MVS		97.12 25	96.60 41	98.68 11	98.03 108	96.57 11	99.84 11	97.84 65	96.36 23	95.20 130	98.24 137	88.17 84	99.83 82	96.11 107	99.60 50	99.64 68
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
PVSNet	87.13 12	93.69 147	92.83 159	96.28 119	97.99 109	90.22 155	99.38 82	98.93 12	91.42 122	93.66 161	97.68 156	71.29 301	99.64 112	87.94 230	97.20 146	98.98 133

test_fmvsm_n_1920		97.08 28	97.55 14	95.67 150	97.94 110	89.61 176	99.93 1	98.48 23	97.08 9	99.08 20	99.13 52	88.17 84	99.93 40	99.11 29	99.06 81	97.47 218

cl22		89.57 241	88.79 240	91.91 263	97.94 110	87.62 227	97.98 248	96.51 238	85.03 291	82.37 298	91.79 313	83.65 168	96.50 297	85.96 251	77.89 323	91.61 314

CS-MVS		95.75 82	96.19 55	94.40 200	97.88 112	86.22 262	99.66 43	96.12 267	92.69 93	98.07 57	98.89 90	87.09 107	97.59 249	96.71 90	98.62 106	99.39 97

CHOSEN 280x420		96.80 36	96.85 30	96.66 96	97.85 113	94.42 56	94.76 355	98.36 29	92.50 96	95.62 123	97.52 164	97.92 1	97.38 261	98.31 57	98.80 97	98.20 198

fmvsm_s_conf0.5_n_8		97.06 29	96.94 25	97.44 48	97.78 114	92.77 97	99.83 12	97.83 69	97.58 3	99.25 14	99.20 34	82.71 192	99.92 43	99.64 8	98.61 107	99.64 68

thres200		93.69 147	92.59 165	96.97 76	97.76 115	94.74 46	99.35 88	99.36 2	89.23 183	91.21 201	96.97 196	83.42 173	98.77 173	85.08 260	90.96 245	97.39 221

HY-MVS	88.56 7	95.29 96	94.23 113	98.48 14	97.72 116	96.41 13	94.03 364	98.74 15	92.42 99	95.65 122	94.76 258	86.52 125	99.49 124	95.29 128	92.97 204	99.53 81

Anonymous20231211		84.72 321	82.65 333	90.91 284	97.71 117	84.55 301	97.28 284	96.67 224	66.88 415	79.18 343	90.87 335	58.47 371	96.60 290	82.61 294	74.20 353	91.59 316

tfpn200view9		93.43 155	92.27 170	96.90 80	97.68 118	94.84 41	99.18 105	99.36 2	88.45 208	90.79 204	96.90 200	83.31 174	98.75 176	84.11 277	90.69 247	97.12 228

thres400		93.39 157	92.27 170	96.73 89	97.68 118	94.84 41	99.18 105	99.36 2	88.45 208	90.79 204	96.90 200	83.31 174	98.75 176	84.11 277	90.69 247	96.61 243

thres100view900		93.34 160	92.15 173	96.90 80	97.62 120	94.84 41	99.06 129	99.36 2	87.96 229	90.47 212	96.78 208	83.29 176	98.75 176	84.11 277	90.69 247	97.12 228

thres600view7		93.18 165	92.00 176	96.75 87	97.62 120	94.92 36	99.07 126	99.36 2	87.96 229	90.47 212	96.78 208	83.29 176	98.71 181	82.93 291	90.47 251	96.61 243

WTY-MVS		95.97 68	95.11 96	98.54 13	97.62 120	96.65 9	99.44 72	98.74 15	92.25 103	95.21 129	98.46 130	86.56 123	99.46 130	95.00 136	92.69 208	99.50 86

balanced_conf03		96.83 34	96.51 43	97.81 36	97.60 123	95.15 34	98.40 208	96.77 220	93.00 85	98.69 36	96.19 228	89.75 63	98.76 175	98.45 51	99.72 32	99.51 84

fmvsm_l_conf0.5_n_a		97.70 13	97.80 11	97.42 51	97.59 124	92.91 93	99.86 6	98.04 50	96.70 15	99.58 3	99.26 24	90.90 41	99.94 35	99.57 13	98.66 105	99.40 95

Anonymous20240529		87.66 278	85.58 291	93.92 221	97.59 124	85.01 294	98.13 234	97.13 194	66.69 416	88.47 234	96.01 235	55.09 385	99.51 122	87.00 237	84.12 288	97.23 227

HyFIR lowres test		93.68 149	93.29 148	94.87 181	97.57 126	88.04 217	98.18 230	98.47 24	87.57 242	91.24 200	95.05 254	85.49 144	97.46 256	93.22 169	92.82 205	99.10 125

sasdasda		95.02 105	93.96 126	98.20 21	97.53 127	95.92 17	98.71 162	96.19 260	91.78 111	95.86 115	98.49 124	79.53 234	99.03 161	96.12 105	91.42 240	99.66 64

canonicalmvs		95.02 105	93.96 126	98.20 21	97.53 127	95.92 17	98.71 162	96.19 260	91.78 111	95.86 115	98.49 124	79.53 234	99.03 161	96.12 105	91.42 240	99.66 64

fmvsm_l_conf0.5_n		97.65 14	97.72 12	97.41 52	97.51 129	92.78 96	99.85 9	98.05 48	96.78 13	99.60 2	99.23 29	90.42 52	99.92 43	99.55 14	98.50 113	99.55 79

MGCFI-Net		94.89 107	93.84 133	98.06 29	97.49 130	95.55 21	98.64 173	96.10 268	91.60 116	95.75 119	98.46 130	79.31 238	98.98 165	95.95 111	91.24 244	99.65 67

ETVMVS		94.50 126	93.90 131	96.31 118	97.48 131	92.98 89	99.07 126	97.86 63	88.09 224	94.40 144	96.90 200	88.35 81	97.28 265	90.72 198	92.25 219	98.66 169

myMVS_eth3d28		95.74 84	95.34 87	96.92 79	97.41 132	93.58 71	99.28 95	97.70 94	90.97 131	93.91 155	97.25 177	90.59 48	98.75 176	96.85 89	94.14 192	98.44 178

CHOSEN 1792x2688		94.35 129	93.82 134	95.95 138	97.40 133	88.74 203	98.41 205	98.27 31	92.18 105	91.43 195	96.40 221	78.88 240	99.81 88	93.59 161	97.81 129	99.30 106

fmvsm_l_conf0.5_n_3		97.12 25	96.89 28	97.79 39	97.39 134	93.84 68	99.87 5	97.70 94	97.34 6	99.39 8	99.20 34	82.86 185	99.94 35	99.21 24	99.07 80	99.58 78

SteuartSystems-ACMMP		97.25 19	97.34 21	97.01 70	97.38 135	91.46 122	99.75 30	97.66 106	94.14 57	98.13 53	99.26 24	92.16 32	99.66 106	97.91 65	99.64 42	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n		96.19 59	96.49 44	95.30 165	97.37 136	89.16 182	99.86 6	98.47 24	95.68 30	98.87 28	99.15 47	82.44 202	99.92 43	99.14 27	97.43 142	96.83 239

testing3-2		95.17 100	94.78 103	96.33 117	97.35 137	92.35 105	99.85 9	98.43 26	90.60 141	92.84 172	97.00 194	90.89 42	98.89 168	95.95 111	90.12 253	97.76 208

alignmvs		95.77 80	95.00 100	98.06 29	97.35 137	95.68 20	99.71 34	97.50 148	91.50 118	96.16 108	98.61 115	86.28 130	99.00 163	96.19 103	91.74 228	99.51 84

PS-MVSNAJ		96.87 33	96.40 48	98.29 19	97.35 137	97.29 5	99.03 132	97.11 196	95.83 26	98.97 25	99.14 50	82.48 198	99.60 115	98.60 42	99.08 78	98.00 204

testing222		94.48 127	94.00 122	95.95 138	97.30 140	92.27 107	98.82 151	97.92 59	89.20 184	94.82 135	97.26 175	87.13 106	97.32 264	91.95 182	91.56 232	98.25 192

EPNet_dtu		92.28 185	92.15 173	92.70 248	97.29 141	84.84 297	98.64 173	97.82 70	92.91 89	93.02 170	97.02 193	85.48 146	95.70 345	72.25 370	94.89 186	97.55 217
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVSTER		92.71 173	92.32 168	93.86 223	97.29 141	92.95 92	99.01 135	96.59 231	90.09 159	85.51 261	94.00 268	94.61 15	96.56 293	90.77 197	83.03 299	92.08 301

MVSMamba_PlusPlus		95.73 85	95.15 93	97.44 48	97.28 143	94.35 59	98.26 223	96.75 221	83.09 323	97.84 65	95.97 236	89.59 65	98.48 193	97.86 66	99.73 31	99.49 87

fmvsm_s_conf0.5_n_3		96.58 46	96.55 42	96.66 96	97.23 144	92.59 102	99.81 17	97.82 70	97.35 5	99.42 5	99.16 43	80.27 227	99.93 40	99.26 19	98.60 108	97.45 219

EPMVS		92.59 178	91.59 187	95.59 155	97.22 145	90.03 165	91.78 385	98.04 50	90.42 150	91.66 189	90.65 343	86.49 127	97.46 256	81.78 302	96.31 165	99.28 108

testing11		95.33 95	94.98 101	96.37 114	97.20 146	92.31 106	99.29 92	97.68 100	90.59 142	94.43 142	97.20 181	90.79 46	98.60 185	95.25 129	92.38 213	98.18 199

testing99		94.88 109	94.45 108	96.17 126	97.20 146	91.91 111	99.20 102	97.66 106	89.95 163	93.68 160	97.06 190	90.28 56	98.50 188	93.52 162	91.54 234	98.12 201

fmvsm_s_conf0.5_n_2		95.85 75	95.83 70	95.91 140	97.19 148	91.79 113	99.78 24	97.65 113	97.23 7	99.22 17	99.06 63	75.93 257	99.90 53	99.30 17	97.09 151	96.02 260

testing91		94.88 109	94.44 109	96.21 122	97.19 148	91.90 112	99.23 100	97.66 106	89.91 164	93.66 161	97.05 192	90.21 57	98.50 188	93.52 162	91.53 237	98.25 192

test_fmvs1		92.35 182	92.94 157	90.57 294	97.19 148	75.43 385	99.55 54	94.97 342	95.20 38	96.82 92	97.57 163	59.59 368	99.84 78	97.30 76	98.29 123	96.46 252

tpmvs		89.16 245	87.76 258	93.35 232	97.19 148	84.75 299	90.58 400	97.36 172	81.99 346	84.56 267	89.31 372	83.98 166	98.17 207	74.85 351	90.00 255	97.12 228

DeepC-MVS	91.02 4	94.56 125	93.92 129	96.46 107	97.16 152	90.76 141	98.39 212	97.11 196	93.92 60	88.66 232	98.33 133	78.14 249	99.85 76	95.02 134	98.57 110	98.78 157
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PVSNet_Blended_VisFu		94.67 120	94.11 118	96.34 116	97.14 153	91.10 131	99.32 91	97.43 162	92.10 108	91.53 194	96.38 224	83.29 176	99.68 104	93.42 167	96.37 163	98.25 192

h-mvs33		92.47 181	91.95 178	94.05 216	97.13 154	85.01 294	98.36 215	98.08 45	93.85 65	96.27 106	96.73 211	83.19 179	99.43 134	95.81 113	68.09 387	97.70 211

miper_enhance_ethall		90.33 226	89.70 221	92.22 255	97.12 155	88.93 196	98.35 216	95.96 279	88.60 203	83.14 283	92.33 303	87.38 98	96.18 322	86.49 245	77.89 323	91.55 317

xiu_mvs_v2_base		96.66 40	96.17 60	98.11 28	97.11 156	96.96 6	99.01 135	97.04 203	95.51 34	98.86 29	99.11 59	82.19 206	99.36 142	98.59 44	98.14 124	98.00 204

mamv4		91.41 201	93.57 139	84.91 373	97.11 156	58.11 420	95.68 346	95.93 285	82.09 345	89.78 222	95.71 241	90.09 59	98.24 204	97.26 77	98.50 113	98.38 183

VDD-MVS		91.24 208	90.18 215	94.45 199	97.08 158	85.84 278	98.40 208	96.10 268	86.99 251	93.36 165	98.16 141	54.27 389	99.20 150	96.59 96	90.63 250	98.31 190

fmvsm_s_conf0.5_n_4		96.17 60	96.49 44	95.21 168	97.06 159	89.26 180	99.76 28	98.07 46	95.99 24	99.35 10	99.22 31	82.19 206	99.89 60	99.06 30	97.68 134	96.49 250

UGNet		91.91 194	90.85 202	95.10 172	97.06 159	88.69 204	98.01 246	98.24 34	92.41 100	92.39 180	93.61 280	60.52 365	99.68 104	88.14 227	97.25 145	96.92 237
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
baseline1		92.61 177	91.28 193	96.58 101	97.05 161	94.63 51	97.72 265	96.20 258	89.82 166	88.56 233	96.85 204	86.85 113	97.82 229	88.42 223	80.10 314	97.30 223

CANet_DTU		94.31 130	93.35 145	97.20 63	97.03 162	94.71 48	98.62 176	95.54 317	95.61 32	97.21 78	98.47 128	71.88 294	99.84 78	88.38 224	97.46 141	97.04 233

WBMVS		91.35 204	90.49 211	93.94 220	96.97 163	93.40 78	99.27 97	96.71 222	87.40 246	83.10 284	91.76 316	92.38 29	96.23 320	88.95 221	77.89 323	92.17 297

UBG		95.73 85	95.41 85	96.69 93	96.97 163	93.23 80	99.13 120	97.79 78	91.28 125	94.38 146	96.78 208	92.37 30	98.56 187	96.17 104	93.84 196	98.26 191

MSDG		88.29 267	86.37 279	94.04 217	96.90 165	86.15 266	96.52 314	94.36 364	77.89 376	79.22 342	96.95 197	69.72 308	99.59 116	73.20 364	92.58 211	96.37 255

BH-w/o		92.32 183	91.79 183	93.91 222	96.85 166	86.18 264	99.11 123	95.74 305	88.13 222	84.81 265	97.00 194	77.26 254	97.91 222	89.16 219	98.03 125	97.64 212

AllTest		84.97 319	83.12 325	90.52 297	96.82 167	78.84 364	95.89 336	92.17 391	77.96 374	75.94 362	95.50 244	55.48 381	99.18 151	71.15 371	87.14 263	93.55 275

TestCases				90.52 297	96.82 167	78.84 364		92.17 391	77.96 374	75.94 362	95.50 244	55.48 381	99.18 151	71.15 371	87.14 263	93.55 275

SDMVSNet		91.09 209	89.91 218	94.65 191	96.80 169	90.54 148	97.78 258	97.81 74	88.34 215	85.73 257	95.26 251	66.44 337	98.26 202	94.25 150	86.75 266	95.14 266

sd_testset		89.23 244	88.05 257	92.74 247	96.80 169	85.33 287	95.85 341	97.03 205	88.34 215	85.73 257	95.26 251	61.12 363	97.76 238	85.61 256	86.75 266	95.14 266

PMMVS		93.62 152	93.90 131	92.79 244	96.79 171	81.40 340	98.85 148	96.81 216	91.25 126	96.82 92	98.15 142	77.02 255	98.13 209	93.15 171	96.30 166	98.83 151

BH-RMVSNet		91.25 207	89.99 217	95.03 177	96.75 172	88.55 207	98.65 171	94.95 343	87.74 237	87.74 239	97.80 148	68.27 319	98.14 208	80.53 312	97.49 140	98.41 180

MVS_Test		93.67 150	92.67 162	96.69 93	96.72 173	92.66 98	97.22 289	96.03 274	87.69 240	95.12 132	94.03 266	81.55 213	98.28 201	89.17 218	96.46 160	99.14 119

COLMAP_ROB	82.69 18	84.54 325	82.82 327	89.70 320	96.72 173	78.85 363	95.89 336	92.83 384	71.55 399	77.54 357	95.89 238	59.40 369	99.14 157	67.26 388	88.26 259	91.11 335
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
mvs_anonymous		92.50 180	91.65 186	95.06 174	96.60 175	89.64 174	97.06 295	96.44 243	86.64 263	84.14 272	93.93 271	82.49 197	96.17 323	91.47 186	96.08 172	99.35 101

UWE-MVS		93.18 165	93.40 144	92.50 252	96.56 176	83.55 314	98.09 242	97.84 65	89.50 178	91.72 187	96.23 227	91.08 37	96.70 287	86.28 247	93.33 200	97.26 225

ETV-MVS		96.00 65	96.00 65	96.00 135	96.56 176	91.05 134	99.63 47	96.61 229	93.26 80	97.39 73	98.30 135	86.62 120	98.13 209	98.07 62	97.57 136	98.82 152

GG-mvs-BLEND				96.98 75	96.53 178	94.81 44	87.20 405	97.74 85		93.91 155	96.40 221	96.56 2	96.94 278	95.08 132	98.95 90	99.20 115

FMVSNet3		88.81 256	87.08 270	93.99 219	96.52 179	94.59 52	98.08 243	96.20 258	85.85 276	82.12 302	91.60 319	74.05 273	95.40 354	79.04 319	80.24 311	91.99 304

fmvsm_s_conf0.5_n_a		95.97 68	96.19 55	95.31 164	96.51 180	89.01 190	99.81 17	98.39 27	95.46 35	99.19 19	99.16 43	81.44 218	99.91 49	98.83 37	96.97 152	97.01 235

BH-untuned		91.46 200	90.84 203	93.33 233	96.51 180	84.83 298	98.84 150	95.50 319	86.44 271	83.50 276	96.70 212	75.49 261	97.77 233	86.78 243	97.81 129	97.40 220

FE-MVS		91.38 203	90.16 216	95.05 176	96.46 182	87.53 230	89.69 402	97.84 65	82.97 326	92.18 182	92.00 310	84.07 165	98.93 167	80.71 309	95.52 180	98.68 165

sss		94.85 112	93.94 128	97.58 44	96.43 183	94.09 64	98.93 142	99.16 8	89.50 178	95.27 128	97.85 145	81.50 215	99.65 110	92.79 176	94.02 194	98.99 132

fmvsm_s_conf0.5_n_5		96.46 51	96.23 54	97.15 66	96.42 184	92.80 95	99.83 12	97.39 167	94.50 46	98.71 34	99.13 52	82.52 195	99.90 53	99.24 23	98.38 118	98.74 161

mvsmamba		94.27 131	93.91 130	95.35 161	96.42 184	88.61 205	97.77 260	96.38 246	91.17 128	94.05 152	95.27 250	78.41 247	97.96 221	97.36 75	98.40 117	99.48 88

test2506		94.80 113	94.21 114	96.58 101	96.41 186	92.18 109	98.01 246	98.96 11	90.82 134	93.46 164	97.28 173	85.92 136	98.45 194	89.82 206	97.19 147	99.12 122

ECVR-MVS		92.29 184	91.33 192	95.15 171	96.41 186	87.84 220	98.10 239	94.84 346	90.82 134	91.42 197	97.28 173	65.61 342	98.49 192	90.33 200	97.19 147	99.12 122

ET-MVSNet_ETH3D		92.56 179	91.45 190	95.88 141	96.39 188	94.13 63	99.46 69	96.97 211	92.18 105	66.94 405	98.29 136	94.65 14	94.28 374	94.34 148	83.82 292	99.24 111

dp		90.16 232	88.83 239	94.14 211	96.38 189	86.42 254	91.57 389	97.06 202	84.76 297	88.81 230	90.19 361	84.29 162	97.43 259	75.05 348	91.35 243	98.56 172

EIA-MVS		95.11 102	95.27 90	94.64 193	96.34 190	86.51 251	99.59 50	96.62 228	92.51 95	94.08 151	98.64 111	86.05 135	98.24 204	95.07 133	98.50 113	99.18 116

test_vis1_n_1920		93.08 169	93.42 143	92.04 262	96.31 191	79.36 359	99.83 12	96.06 273	96.72 14	98.53 42	98.10 143	58.57 370	99.91 49	97.86 66	98.79 100	96.85 238

TR-MVS		90.77 217	89.44 226	94.76 185	96.31 191	88.02 218	97.92 250	95.96 279	85.52 282	88.22 236	97.23 179	66.80 333	98.09 212	84.58 269	92.38 213	98.17 200

UA-Net		93.30 161	92.62 164	95.34 162	96.27 193	88.53 209	95.88 338	96.97 211	90.90 132	95.37 127	97.07 189	82.38 203	99.10 159	83.91 281	94.86 187	98.38 183

tpmrst		92.78 172	92.16 172	94.65 191	96.27 193	87.45 233	91.83 384	97.10 199	89.10 189	94.68 139	90.69 340	88.22 83	97.73 241	89.78 207	91.80 227	98.77 159

hse-mvs2		91.67 197	91.51 189	92.15 259	96.22 195	82.61 330	97.74 264	97.53 139	93.85 65	96.27 106	96.15 229	83.19 179	97.44 258	95.81 113	66.86 394	96.40 254

AUN-MVS		90.17 231	89.50 224	92.19 257	96.21 196	82.67 328	97.76 263	97.53 139	88.05 225	91.67 188	96.15 229	83.10 181	97.47 255	88.11 228	66.91 393	96.43 253

ADS-MVSNet2		87.62 279	86.88 273	89.86 314	96.21 196	79.14 362	87.15 406	92.99 381	83.01 324	89.91 220	87.27 386	78.87 241	92.80 388	74.20 356	92.27 217	97.64 212

ADS-MVSNet		88.99 247	87.30 266	94.07 214	96.21 196	87.56 229	87.15 406	96.78 219	83.01 324	89.91 220	87.27 386	78.87 241	97.01 275	74.20 356	92.27 217	97.64 212

fmvsm_s_conf0.5_n_7		95.87 74	96.25 53	94.72 189	96.19 199	87.74 222	99.66 43	97.94 57	95.78 27	98.44 44	99.23 29	81.26 221	99.90 53	99.17 26	98.57 110	96.52 249

PatchmatchNet		92.05 193	91.04 198	95.06 174	96.17 200	89.04 186	91.26 393	97.26 177	89.56 176	90.64 208	90.56 349	88.35 81	97.11 270	79.53 315	96.07 173	99.03 130
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test1111		92.12 189	91.19 195	94.94 179	96.15 201	87.36 236	98.12 236	94.84 346	90.85 133	90.97 202	97.26 175	65.60 343	98.37 196	89.74 209	97.14 150	99.07 129

gg-mvs-nofinetune		90.00 235	87.71 260	96.89 84	96.15 201	94.69 49	85.15 412	97.74 85	68.32 411	92.97 171	60.16 425	96.10 4	96.84 281	93.89 154	98.87 94	99.14 119

MDTV_nov1_ep13			90.47 213		96.14 203	88.55 207	91.34 392	97.51 145	89.58 174	92.24 181	90.50 353	86.99 112	97.61 248	77.64 330	92.34 215

IS-MVSNet		93.00 170	92.51 166	94.49 196	96.14 203	87.36 236	98.31 220	95.70 307	88.58 204	90.17 216	97.50 165	83.02 183	97.22 266	87.06 235	96.07 173	98.90 144

Vis-MVSNet (Re-imp)		93.26 164	93.00 156	94.06 215	96.14 203	86.71 250	98.68 167	96.70 223	88.30 217	89.71 225	97.64 159	85.43 147	96.39 304	88.06 229	96.32 164	99.08 127

thisisatest0515		94.75 115	94.19 115	96.43 109	96.13 206	92.64 101	99.47 65	97.60 124	87.55 243	93.17 167	97.59 161	94.71 12	98.42 195	88.28 225	93.20 201	98.24 195

RRT-MVS		93.39 157	92.64 163	95.64 151	96.11 207	88.75 202	97.40 277	95.77 303	89.46 180	92.70 175	95.42 247	72.98 283	98.81 171	96.91 87	96.97 152	99.37 98

FA-MVS(test-final)		92.22 188	91.08 197	95.64 151	96.05 208	88.98 191	91.60 388	97.25 178	86.99 251	91.84 184	92.12 304	83.03 182	99.00 163	86.91 240	93.91 195	98.93 141

fmvsm_s_conf0.5_n_6		96.78 37	96.64 40	97.20 63	96.03 209	93.20 82	99.82 16	97.68 100	95.20 38	99.61 1	99.11 59	84.52 159	99.90 53	99.04 31	98.77 101	98.50 175

test_fmvsmconf_n		96.78 37	96.84 31	96.61 98	95.99 210	90.25 152	99.90 3	98.13 43	96.68 16	98.42 45	98.92 85	85.34 149	99.88 62	99.12 28	99.08 78	99.70 55

ab-mvs		91.05 212	89.17 231	96.69 93	95.96 211	91.72 116	92.62 378	97.23 182	85.61 281	89.74 223	93.89 273	68.55 316	99.42 135	91.09 189	87.84 261	98.92 143

Fast-Effi-MVS+		91.72 196	90.79 206	94.49 196	95.89 212	87.40 235	99.54 59	95.70 307	85.01 293	89.28 228	95.68 242	77.75 251	97.57 253	83.22 286	95.06 185	98.51 174

kuosan		84.40 329	83.34 323	87.60 349	95.87 213	79.21 360	92.39 380	96.87 214	76.12 385	73.79 375	93.98 269	81.51 214	90.63 404	64.13 397	75.42 338	92.95 278

EPP-MVSNet		93.75 146	93.67 137	94.01 218	95.86 214	85.70 280	98.67 169	97.66 106	84.46 300	91.36 198	97.18 184	91.16 34	97.79 231	92.93 173	93.75 197	98.53 173

mvsany_test1		94.57 124	95.09 97	92.98 239	95.84 215	82.07 334	98.76 160	95.24 335	92.87 91	96.45 102	98.71 106	84.81 156	99.15 153	97.68 69	95.49 181	97.73 210

Effi-MVS+		93.87 142	93.15 151	96.02 133	95.79 216	90.76 141	96.70 311	95.78 301	86.98 254	95.71 120	97.17 185	79.58 232	98.01 219	94.57 146	96.09 171	99.31 105

tpm cat1		88.89 250	87.27 267	93.76 226	95.79 216	85.32 288	90.76 398	97.09 200	76.14 384	85.72 259	88.59 375	82.92 184	98.04 217	76.96 334	91.43 239	97.90 207

thisisatest0530		94.00 136	93.52 140	95.43 158	95.76 218	90.02 166	98.99 137	97.60 124	86.58 264	91.74 186	97.36 172	94.78 11	98.34 197	86.37 246	92.48 212	97.94 206

3Dnovator+	87.72 8	93.43 155	91.84 181	98.17 23	95.73 219	95.08 35	98.92 144	97.04 203	91.42 122	81.48 317	97.60 160	74.60 265	99.79 94	90.84 194	98.97 87	99.64 68

MVS		93.92 139	92.28 169	98.83 7	95.69 220	96.82 8	96.22 327	98.17 37	84.89 295	84.34 271	98.61 115	79.32 237	99.83 82	93.88 155	99.43 61	99.86 29

cascas		90.93 215	89.33 229	95.76 146	95.69 220	93.03 88	98.99 137	96.59 231	80.49 361	86.79 252	94.45 261	65.23 346	98.60 185	93.52 162	92.18 220	95.66 265

QAPM		91.41 201	89.49 225	97.17 65	95.66 222	93.42 77	98.60 182	97.51 145	80.92 359	81.39 318	97.41 170	72.89 286	99.87 66	82.33 296	98.68 103	98.21 197

fmvsm_s_conf0.1_n_2		95.24 99	95.04 99	95.83 143	95.60 223	91.71 117	99.65 45	96.18 262	96.99 11	98.79 32	98.91 86	73.91 275	99.87 66	99.00 33	96.30 166	95.91 262

tttt0517		93.30 161	93.01 155	94.17 210	95.57 224	86.47 253	98.51 193	97.60 124	85.99 275	90.55 209	97.19 183	94.80 10	98.31 198	85.06 261	91.86 225	97.74 209

1112_ss		92.71 173	91.55 188	96.20 123	95.56 225	91.12 129	98.48 198	94.69 353	88.29 218	86.89 250	98.50 121	87.02 110	98.66 183	84.75 265	89.77 256	98.81 153

diffmvs		94.59 123	94.19 115	95.81 144	95.54 226	90.69 143	98.70 165	95.68 309	91.61 114	95.96 110	97.81 147	80.11 228	98.06 214	96.52 98	95.76 176	98.67 166
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		88.59 263	88.61 244	88.51 341	95.53 227	72.68 398	96.85 303	88.43 418	88.45 208	73.14 381	90.63 344	75.82 258	94.38 373	92.95 172	95.71 178	98.48 177

Test_1112_low_res		92.27 186	90.97 199	96.18 124	95.53 227	91.10 131	98.47 200	94.66 354	88.28 219	86.83 251	93.50 284	87.00 111	98.65 184	84.69 266	89.74 257	98.80 154

PCF-MVS	89.78 5	91.26 205	89.63 222	96.16 128	95.44 229	91.58 121	95.29 350	96.10 268	85.07 290	82.75 286	97.45 168	78.28 248	99.78 96	80.60 311	95.65 179	97.12 228
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EC-MVSNet		95.09 103	95.17 92	94.84 183	95.42 230	88.17 213	99.48 63	95.92 287	91.47 119	97.34 75	98.36 132	82.77 188	97.41 260	97.24 78	98.58 109	98.94 140

3Dnovator	87.35 11	93.17 167	91.77 184	97.37 55	95.41 231	93.07 86	98.82 151	97.85 64	91.53 117	82.56 292	97.58 162	71.97 293	99.82 85	91.01 191	99.23 73	99.22 114

IB-MVS	89.43 6	92.12 189	90.83 205	95.98 137	95.40 232	90.78 140	99.81 17	98.06 47	91.23 127	85.63 260	93.66 279	90.63 47	98.78 172	91.22 188	71.85 376	98.36 187
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
test_cas_vis1_n_1920		93.86 143	93.74 136	94.22 208	95.39 233	86.08 268	99.73 31	96.07 272	96.38 22	97.19 80	97.78 150	65.46 345	99.86 72	96.71 90	98.92 91	96.73 240

GDP-MVS		96.05 64	95.63 83	97.31 56	95.37 234	94.65 50	99.36 86	96.42 244	92.14 107	97.07 82	98.53 117	93.33 19	98.50 188	91.76 185	96.66 159	98.78 157

miper_ehance_all_eth		88.94 249	88.12 255	91.40 274	95.32 235	86.93 246	97.85 255	95.55 316	84.19 303	81.97 308	91.50 321	84.16 163	95.91 337	84.69 266	77.89 323	91.36 325

1314		93.44 154	91.98 177	97.84 34	95.24 236	94.38 57	96.22 327	97.92 59	90.18 155	82.28 299	97.71 155	77.63 252	99.80 90	91.94 183	98.67 104	99.34 103

XVG-OURS		90.83 216	90.49 211	91.86 264	95.23 237	81.25 344	95.79 343	95.92 287	88.96 192	90.02 219	98.03 144	71.60 298	99.35 145	91.06 190	87.78 262	94.98 269

casdiffmvs_mvg		94.00 136	93.33 146	96.03 132	95.22 238	90.90 139	99.09 124	95.99 275	90.58 143	91.55 193	97.37 171	79.91 230	98.06 214	95.01 135	95.22 183	99.13 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TESTMET0.1,1		93.82 144	93.26 149	95.49 156	95.21 239	90.25 152	99.15 114	97.54 138	89.18 186	91.79 185	94.87 256	89.13 68	97.63 246	86.21 248	96.29 168	98.60 171

xiu_mvs_v1_base_debu		94.73 116	93.98 123	96.99 72	95.19 240	95.24 27	98.62 176	96.50 239	92.99 86	97.52 69	98.83 94	72.37 289	99.15 153	97.03 81	96.74 156	96.58 245

xiu_mvs_v1_base		94.73 116	93.98 123	96.99 72	95.19 240	95.24 27	98.62 176	96.50 239	92.99 86	97.52 69	98.83 94	72.37 289	99.15 153	97.03 81	96.74 156	96.58 245

xiu_mvs_v1_base_debi		94.73 116	93.98 123	96.99 72	95.19 240	95.24 27	98.62 176	96.50 239	92.99 86	97.52 69	98.83 94	72.37 289	99.15 153	97.03 81	96.74 156	96.58 245

XVG-OURS-SEG-HR		90.95 214	90.66 209	91.83 265	95.18 243	81.14 347	95.92 335	95.92 287	88.40 212	90.33 215	97.85 145	70.66 304	99.38 140	92.83 175	88.83 258	94.98 269

Effi-MVS+-dtu		89.97 236	90.68 208	87.81 347	95.15 244	71.98 400	97.87 254	95.40 326	91.92 109	87.57 240	91.44 322	74.27 271	96.84 281	89.45 211	93.10 203	94.60 271

Syy-MVS		84.10 334	84.53 311	82.83 385	95.14 245	65.71 412	97.68 268	96.66 225	86.52 267	82.63 289	96.84 205	68.15 320	89.89 408	45.62 423	91.54 234	92.87 279

myMVS_eth3d		88.68 262	89.07 233	87.50 351	95.14 245	79.74 357	97.68 268	96.66 225	86.52 267	82.63 289	96.84 205	85.22 151	89.89 408	69.43 379	91.54 234	92.87 279

UWE-MVS-28		90.99 213	91.93 179	88.15 343	95.12 247	77.87 375	97.18 292	97.79 78	88.72 200	88.69 231	96.52 216	86.54 124	90.75 403	84.64 268	92.16 223	95.83 263

Vis-MVSNet		92.64 175	91.85 180	95.03 177	95.12 247	88.23 212	98.48 198	96.81 216	91.61 114	92.16 183	97.22 180	71.58 299	98.00 220	85.85 255	97.81 129	98.88 145
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GBi-Net		86.67 291	84.96 299	91.80 267	95.11 249	88.81 199	96.77 305	95.25 332	82.94 327	82.12 302	90.25 356	62.89 355	94.97 361	79.04 319	80.24 311	91.62 311

test1		86.67 291	84.96 299	91.80 267	95.11 249	88.81 199	96.77 305	95.25 332	82.94 327	82.12 302	90.25 356	62.89 355	94.97 361	79.04 319	80.24 311	91.62 311

FMVSNet2		86.90 286	84.79 305	93.24 234	95.11 249	92.54 103	97.67 270	95.86 299	82.94 327	80.55 324	91.17 329	62.89 355	95.29 356	77.23 331	79.71 317	91.90 305

GeoE		90.60 223	89.56 223	93.72 228	95.10 252	85.43 284	99.41 79	94.94 344	83.96 308	87.21 246	96.83 207	74.37 269	97.05 274	80.50 313	93.73 198	98.67 166

baseline		93.91 140	93.30 147	95.72 147	95.10 252	90.07 161	97.48 276	95.91 292	91.03 129	93.54 163	97.68 156	79.58 232	98.02 218	94.27 149	95.14 184	99.08 127

casdiffmvs		93.98 138	93.43 142	95.61 154	95.07 254	89.86 170	98.80 154	95.84 300	90.98 130	92.74 174	97.66 158	79.71 231	98.10 211	94.72 142	95.37 182	98.87 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BP-MVS1		96.59 44	96.36 50	97.29 57	95.05 255	94.72 47	99.44 72	97.45 156	92.71 92	96.41 104	98.50 121	94.11 16	98.50 188	95.61 120	97.97 126	98.66 169

MVSFormer		94.71 119	94.08 120	96.61 98	95.05 255	94.87 39	97.77 260	96.17 264	86.84 257	98.04 59	98.52 119	85.52 141	95.99 330	89.83 204	98.97 87	98.96 135

lupinMVS		96.32 55	95.94 66	97.44 48	95.05 255	94.87 39	99.86 6	96.50 239	93.82 67	98.04 59	98.77 97	85.52 141	98.09 212	96.98 84	98.97 87	99.37 98

CostFormer		92.89 171	92.48 167	94.12 212	94.99 258	85.89 275	92.89 374	97.00 209	86.98 254	95.00 134	90.78 336	90.05 60	97.51 254	92.92 174	91.73 229	98.96 135

c3_l		88.19 269	87.23 268	91.06 280	94.97 259	86.17 265	97.72 265	95.38 327	83.43 317	81.68 315	91.37 323	82.81 187	95.72 344	84.04 280	73.70 357	91.29 329

SCA		90.64 222	89.25 230	94.83 184	94.95 260	88.83 198	96.26 324	97.21 184	90.06 162	90.03 218	90.62 345	66.61 334	96.81 283	83.16 287	94.36 190	98.84 148

test-LLR		93.11 168	92.68 161	94.40 200	94.94 261	87.27 240	99.15 114	97.25 178	90.21 153	91.57 190	94.04 264	84.89 154	97.58 250	85.94 252	96.13 169	98.36 187

test-mter		93.27 163	92.89 158	94.40 200	94.94 261	87.27 240	99.15 114	97.25 178	88.95 193	91.57 190	94.04 264	88.03 89	97.58 250	85.94 252	96.13 169	98.36 187

cl____		87.82 271	86.79 275	90.89 286	94.88 263	85.43 284	97.81 256	95.24 335	82.91 331	80.71 323	91.22 327	81.97 210	95.84 339	81.34 304	75.06 341	91.40 324

DIV-MVS_self_test		87.82 271	86.81 274	90.87 287	94.87 264	85.39 286	97.81 256	95.22 340	82.92 330	80.76 322	91.31 326	81.99 208	95.81 341	81.36 303	75.04 342	91.42 323

tpm2		91.77 195	91.09 196	93.82 225	94.83 265	85.56 283	92.51 379	97.16 191	84.00 306	93.83 158	90.66 342	87.54 95	97.17 267	87.73 232	91.55 233	98.72 162

PVSNet_0	83.28 16	87.31 282	85.16 297	93.74 227	94.78 266	84.59 300	98.91 145	98.69 20	89.81 167	78.59 349	93.23 289	61.95 359	99.34 146	94.75 140	55.72 416	97.30 223

CDS-MVSNet		93.47 153	93.04 154	94.76 185	94.75 267	89.45 178	98.82 151	97.03 205	87.91 231	90.97 202	96.48 219	89.06 69	96.36 306	89.50 210	92.81 207	98.49 176
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gm-plane-assit					94.69 268	88.14 214			88.22 220		97.20 181		98.29 200	90.79 196

eth_miper_zixun_eth		87.76 273	87.00 272	90.06 308	94.67 269	82.65 329	97.02 298	95.37 328	84.19 303	81.86 313	91.58 320	81.47 216	95.90 338	83.24 285	73.61 358	91.61 314

testing3		87.75 274	88.22 253	86.36 360	94.66 270	77.41 376	99.52 60	97.95 56	86.05 274	81.12 319	96.69 213	86.18 133	89.31 412	61.65 405	90.12 253	92.35 290

RPSCF		85.33 314	85.55 292	84.67 376	94.63 271	62.28 415	93.73 366	93.76 372	74.38 392	85.23 264	97.06 190	64.09 349	98.31 198	80.98 305	86.08 274	93.41 277

miper_lstm_enhance		86.90 286	86.20 282	89.00 336	94.53 272	81.19 345	96.74 309	95.24 335	82.33 341	80.15 330	90.51 352	81.99 208	94.68 370	80.71 309	73.58 360	91.12 334

Patchmatch-test		86.25 300	84.06 317	92.82 243	94.42 273	82.88 325	82.88 421	94.23 366	71.58 398	79.39 340	90.62 345	89.00 71	96.42 303	63.03 401	91.37 242	99.16 117

VDDNet		90.08 234	88.54 248	94.69 190	94.41 274	87.68 224	98.21 228	96.40 245	76.21 383	93.33 166	97.75 152	54.93 387	98.77 173	94.71 143	90.96 245	97.61 216

fmvsm_s_conf0.1_n		95.56 89	95.68 78	95.20 169	94.35 275	89.10 184	99.50 61	97.67 105	94.76 43	98.68 37	99.03 67	81.13 222	99.86 72	98.63 41	97.36 144	96.63 242

test_fmvsmvis_n_1920		95.47 90	95.40 86	95.70 148	94.33 276	90.22 155	99.70 35	96.98 210	96.80 12	92.75 173	98.89 90	82.46 201	99.92 43	98.36 53	98.33 120	96.97 236

KD-MVS_2432*1600		82.98 340	80.52 349	90.38 301	94.32 277	88.98 191	92.87 375	95.87 297	80.46 362	73.79 375	87.49 383	82.76 190	93.29 382	70.56 375	46.53 427	88.87 380

miper_refine_blended		82.98 340	80.52 349	90.38 301	94.32 277	88.98 191	92.87 375	95.87 297	80.46 362	73.79 375	87.49 383	82.76 190	93.29 382	70.56 375	46.53 427	88.87 380

EI-MVSNet		89.87 237	89.38 228	91.36 276	94.32 277	85.87 276	97.61 273	96.59 231	85.10 288	85.51 261	97.10 187	81.30 220	96.56 293	83.85 283	83.03 299	91.64 309

CVMVSNet		90.30 227	90.91 201	88.46 342	94.32 277	73.58 393	97.61 273	97.59 128	90.16 158	88.43 235	97.10 187	76.83 256	92.86 385	82.64 293	93.54 199	98.93 141

WB-MVSnew		88.69 260	88.34 250	89.77 318	94.30 281	85.99 273	98.14 233	97.31 176	87.15 250	87.85 238	96.07 233	69.91 305	95.52 349	72.83 367	91.47 238	87.80 387

dongtai		81.36 349	80.61 347	83.62 382	94.25 282	73.32 394	95.15 352	96.81 216	73.56 395	69.79 392	92.81 297	81.00 223	86.80 419	52.08 420	70.06 383	90.75 346

test_fmvs1_n		91.07 210	91.41 191	90.06 308	94.10 283	74.31 389	99.18 105	94.84 346	94.81 41	96.37 105	97.46 167	50.86 402	99.82 85	97.14 80	97.90 127	96.04 259

IterMVS-LS		88.34 265	87.44 263	91.04 281	94.10 283	85.85 277	98.10 239	95.48 320	85.12 287	82.03 306	91.21 328	81.35 219	95.63 347	83.86 282	75.73 337	91.63 310
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAMVS		92.62 176	92.09 175	94.20 209	94.10 283	87.68 224	98.41 205	96.97 211	87.53 244	89.74 223	96.04 234	84.77 158	96.49 299	88.97 220	92.31 216	98.42 179

PAPM		96.35 53	95.94 66	97.58 44	94.10 283	95.25 26	98.93 142	98.17 37	94.26 52	93.94 154	98.72 103	89.68 64	97.88 225	96.36 100	99.29 69	99.62 73

CLD-MVS		91.06 211	90.71 207	92.10 260	94.05 287	86.10 267	99.55 54	96.29 254	94.16 55	84.70 266	97.17 185	69.62 310	97.82 229	94.74 141	86.08 274	92.39 286
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP-NCC					93.95 288		99.16 109		93.92 60	87.57 240

ACMP_Plane					93.95 288		99.16 109		93.92 60	87.57 240

HQP-MVS		91.50 198	91.23 194	92.29 254	93.95 288	86.39 256	99.16 109	96.37 247	93.92 60	87.57 240	96.67 214	73.34 278	97.77 233	93.82 158	86.29 269	92.72 281

NP-MVS					93.94 291	86.22 262					96.67 214

plane_prior6					93.92 292	86.02 272						72.92 284

ACMP	87.39 10	88.71 259	88.24 252	90.12 307	93.91 293	81.06 348	98.50 194	95.67 310	89.43 181	80.37 327	95.55 243	65.67 340	97.83 228	90.55 199	84.51 283	91.47 319
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
plane_prior1					93.90 294

HQP_MVS		91.26 205	90.95 200	92.16 258	93.84 295	86.07 270	99.02 133	96.30 251	93.38 78	86.99 247	96.52 216	72.92 284	97.75 239	93.46 165	86.17 272	92.67 283

plane_prior7					93.84 295	85.73 279

dmvs_re		88.69 260	88.06 256	90.59 293	93.83 297	78.68 366	95.75 344	96.18 262	87.99 228	84.48 270	96.32 225	67.52 327	96.94 278	84.98 263	85.49 278	96.14 257

MVS-HIRNet		79.01 361	75.13 374	90.66 292	93.82 298	81.69 337	85.16 411	93.75 373	54.54 421	74.17 373	59.15 427	57.46 374	96.58 292	63.74 398	94.38 189	93.72 274

FMVSNet5		82.29 343	80.54 348	87.52 350	93.79 299	84.01 308	93.73 366	92.47 388	76.92 379	74.27 372	86.15 394	63.69 353	89.24 413	69.07 381	74.79 345	89.29 375

ACMH+	83.78 15	84.21 330	82.56 336	89.15 333	93.73 300	79.16 361	96.43 317	94.28 365	81.09 356	74.00 374	94.03 266	54.58 388	97.67 242	76.10 342	78.81 319	90.63 351

ACMM	86.95 13	88.77 257	88.22 253	90.43 299	93.61 301	81.34 342	98.50 194	95.92 287	87.88 232	83.85 275	95.20 253	67.20 330	97.89 224	86.90 241	84.90 281	92.06 302
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS	85.28 14	90.75 218	88.84 238	96.48 106	93.58 302	93.51 75	98.80 154	97.41 164	82.59 334	78.62 347	97.49 166	68.00 323	99.82 85	84.52 271	98.55 112	96.11 258

IterMVS		85.81 307	84.67 308	89.22 330	93.51 303	83.67 313	96.32 321	94.80 349	85.09 289	78.69 345	90.17 362	66.57 336	93.17 384	79.48 317	77.42 330	90.81 341
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		88.83 254	87.38 265	93.16 236	93.47 304	86.24 260	84.97 414	94.20 367	88.92 196	90.76 206	86.88 390	84.43 160	94.82 366	70.64 374	92.17 221	98.41 180

RPMNet		85.07 318	81.88 337	94.64 193	93.47 304	86.24 260	84.97 414	97.21 184	64.85 418	90.76 206	78.80 416	80.95 224	99.27 149	53.76 417	92.17 221	98.41 180

IterMVS-SCA-FT		85.73 310	84.64 309	89.00 336	93.46 306	82.90 323	96.27 322	94.70 352	85.02 292	78.62 347	90.35 354	66.61 334	93.33 381	79.38 318	77.36 331	90.76 345

Fast-Effi-MVS+-dtu		88.84 252	88.59 246	89.58 323	93.44 307	78.18 370	98.65 171	94.62 355	88.46 207	84.12 273	95.37 249	68.91 313	96.52 296	82.06 299	91.70 230	94.06 272

Patchmtry		83.61 339	81.64 339	89.50 325	93.36 308	82.84 326	84.10 417	94.20 367	69.47 408	79.57 338	86.88 390	84.43 160	94.78 367	68.48 384	74.30 351	90.88 340

LPG-MVS_test		88.86 251	88.47 249	90.06 308	93.35 309	80.95 349	98.22 226	95.94 282	87.73 238	83.17 281	96.11 231	66.28 338	97.77 233	90.19 202	85.19 279	91.46 320

LGP-MVS_train				90.06 308	93.35 309	80.95 349		95.94 282	87.73 238	83.17 281	96.11 231	66.28 338	97.77 233	90.19 202	85.19 279	91.46 320

JIA-IIPM		85.97 303	84.85 303	89.33 329	93.23 311	73.68 392	85.05 413	97.13 194	69.62 407	91.56 192	68.03 423	88.03 89	96.96 276	77.89 329	93.12 202	97.34 222

ACMH	83.09 17	84.60 323	82.61 334	90.57 294	93.18 312	82.94 321	96.27 322	94.92 345	81.01 357	72.61 387	93.61 280	56.54 376	97.79 231	74.31 354	81.07 309	90.99 337
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PatchT		85.44 313	83.19 324	92.22 255	93.13 313	83.00 320	83.80 420	96.37 247	70.62 401	90.55 209	79.63 415	84.81 156	94.87 364	58.18 413	91.59 231	98.79 155

baseline2		94.04 135	93.80 135	94.74 187	93.07 314	90.25 152	98.12 236	98.16 40	89.86 165	86.53 253	96.95 197	95.56 6	98.05 216	91.44 187	94.53 188	95.93 261

jason		95.40 94	94.86 102	97.03 69	92.91 315	94.23 60	99.70 35	96.30 251	93.56 74	96.73 97	98.52 119	81.46 217	97.91 222	96.08 108	98.47 116	98.96 135
jason: jason.
LTVRE_ROB	81.71 19	84.59 324	82.72 332	90.18 305	92.89 316	83.18 319	93.15 371	94.74 350	78.99 367	75.14 369	92.69 298	65.64 341	97.63 246	69.46 378	81.82 307	89.74 368
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
mmtdpeth		83.69 336	82.59 335	86.99 356	92.82 317	76.98 378	96.16 330	91.63 400	82.89 332	92.41 179	82.90 401	54.95 386	98.19 206	96.27 101	53.27 419	85.81 401

VPA-MVSNet		89.10 246	87.66 261	93.45 230	92.56 318	91.02 135	97.97 249	98.32 30	86.92 256	86.03 255	92.01 308	68.84 315	97.10 272	90.92 192	75.34 339	92.23 293

tpm		89.67 239	88.95 236	91.82 266	92.54 319	81.43 339	92.95 373	95.92 287	87.81 233	90.50 211	89.44 369	84.99 152	95.65 346	83.67 284	82.71 302	98.38 183

GA-MVS		90.10 233	88.69 242	94.33 203	92.44 320	87.97 219	99.08 125	96.26 255	89.65 170	86.92 249	93.11 292	68.09 321	96.96 276	82.54 295	90.15 252	98.05 202

test_fmvsmconf0.1_n		95.94 71	95.79 75	96.40 112	92.42 321	89.92 168	99.79 23	96.85 215	96.53 20	97.22 77	98.67 109	82.71 192	99.84 78	98.92 36	98.98 86	99.43 94

FIs		90.70 219	89.87 219	93.18 235	92.29 322	91.12 129	98.17 232	98.25 32	89.11 188	83.44 277	94.82 257	82.26 204	96.17 323	87.76 231	82.76 301	92.25 291

ITE_SJBPF				87.93 345	92.26 323	76.44 380		93.47 379	87.67 241	79.95 333	95.49 246	56.50 377	97.38 261	75.24 347	82.33 305	89.98 365

UniMVSNet (Re)		89.50 243	88.32 251	93.03 237	92.21 324	90.96 137	98.90 146	98.39 27	89.13 187	83.22 278	92.03 306	81.69 212	96.34 312	86.79 242	72.53 369	91.81 306

UniMVSNet_NR-MVSNet		89.60 240	88.55 247	92.75 246	92.17 325	90.07 161	98.74 161	98.15 41	88.37 213	83.21 279	93.98 269	82.86 185	95.93 334	86.95 238	72.47 370	92.25 291

TinyColmap		80.42 354	77.94 359	87.85 346	92.09 326	78.58 367	93.74 365	89.94 411	74.99 388	69.77 393	91.78 314	46.09 409	97.58 250	65.17 396	77.89 323	87.38 389

fmvsm_s_conf0.1_n_a		95.16 101	95.15 93	95.18 170	92.06 327	88.94 194	99.29 92	97.53 139	94.46 48	98.98 24	98.99 71	79.99 229	99.85 76	98.24 60	96.86 155	96.73 240

tt0805		86.50 296	84.79 305	91.63 272	91.97 328	81.49 338	96.49 316	97.38 168	82.24 342	82.44 294	95.82 239	51.22 399	98.25 203	84.55 270	80.96 310	95.13 268

MS-PatchMatch		86.75 289	85.92 286	89.22 330	91.97 328	82.47 331	96.91 300	96.14 266	83.74 311	77.73 355	93.53 283	58.19 372	97.37 263	76.75 337	98.35 119	87.84 385

VPNet		88.30 266	86.57 276	93.49 229	91.95 330	91.35 123	98.18 230	97.20 188	88.61 202	84.52 269	94.89 255	62.21 358	96.76 286	89.34 214	72.26 373	92.36 287

FMVSNet1		83.94 335	81.32 344	91.80 267	91.94 331	88.81 199	96.77 305	95.25 332	77.98 372	78.25 352	90.25 356	50.37 403	94.97 361	73.27 363	77.81 328	91.62 311

WR-MVS		88.54 264	87.22 269	92.52 251	91.93 332	89.50 177	98.56 187	97.84 65	86.99 251	81.87 311	93.81 274	74.25 272	95.92 336	85.29 258	74.43 349	92.12 299

SSC-MVS3.2		85.22 315	83.90 320	89.17 332	91.87 333	79.84 356	97.66 271	96.63 227	86.81 259	81.99 307	91.35 324	55.80 378	96.00 329	76.52 340	76.53 334	91.67 308

D2MVS		87.96 270	87.39 264	89.70 320	91.84 334	83.40 316	98.31 220	98.49 22	88.04 226	78.23 353	90.26 355	73.57 276	96.79 285	84.21 274	83.53 295	88.90 379

MonoMVSNet		90.69 220	89.78 220	93.45 230	91.78 335	84.97 296	96.51 315	94.44 358	90.56 144	85.96 256	90.97 332	78.61 246	96.27 319	95.35 125	83.79 293	99.11 124

FC-MVSNet-test		90.22 229	89.40 227	92.67 250	91.78 335	89.86 170	97.89 251	98.22 35	88.81 198	82.96 285	94.66 259	81.90 211	95.96 332	85.89 254	82.52 304	92.20 296

MIMVSNet		84.48 326	81.83 338	92.42 253	91.73 337	87.36 236	85.52 409	94.42 362	81.40 352	81.91 309	87.58 380	51.92 396	92.81 387	73.84 359	88.15 260	97.08 232

USDC		84.74 320	82.93 326	90.16 306	91.73 337	83.54 315	95.00 353	93.30 380	88.77 199	73.19 380	93.30 287	53.62 392	97.65 245	75.88 344	81.54 308	89.30 374

test_vis1_n		90.40 224	90.27 214	90.79 289	91.55 339	76.48 379	99.12 122	94.44 358	94.31 51	97.34 75	96.95 197	43.60 413	99.42 135	97.57 71	97.60 135	96.47 251

nrg030		90.23 228	88.87 237	94.32 204	91.53 340	93.54 74	98.79 158	95.89 295	88.12 223	84.55 268	94.61 260	78.80 243	96.88 280	92.35 180	75.21 340	92.53 285

DU-MVS		88.83 254	87.51 262	92.79 244	91.46 341	90.07 161	98.71 162	97.62 121	88.87 197	83.21 279	93.68 277	74.63 263	95.93 334	86.95 238	72.47 370	92.36 287

NR-MVSNet		87.74 277	86.00 285	92.96 241	91.46 341	90.68 144	96.65 312	97.42 163	88.02 227	73.42 378	93.68 277	77.31 253	95.83 340	84.26 273	71.82 377	92.36 287

tfpnnormal		83.65 337	81.35 343	90.56 296	91.37 343	88.06 216	97.29 283	97.87 62	78.51 371	76.20 359	90.91 333	64.78 347	96.47 300	61.71 404	73.50 361	87.13 394

test_vis1_rt		81.31 350	80.05 353	85.11 370	91.29 344	70.66 404	98.98 139	77.39 433	85.76 279	68.80 396	82.40 404	36.56 420	99.44 131	92.67 177	86.55 268	85.24 408

test_0402		78.81 363	76.33 368	86.26 361	91.18 345	78.44 369	95.88 338	91.34 405	68.55 409	70.51 391	89.91 364	52.65 395	94.99 360	47.14 422	79.78 316	85.34 407

test0.0.03 1		88.96 248	88.61 244	90.03 312	91.09 346	84.43 302	98.97 140	97.02 207	90.21 153	80.29 328	96.31 226	84.89 154	91.93 399	72.98 365	85.70 277	93.73 273

WR-MVS_H		86.53 295	85.49 293	89.66 322	91.04 347	83.31 318	97.53 275	98.20 36	84.95 294	79.64 336	90.90 334	78.01 250	95.33 355	76.29 341	72.81 366	90.35 355

CP-MVSNet		86.54 294	85.45 294	89.79 317	91.02 348	82.78 327	97.38 280	97.56 134	85.37 284	79.53 339	93.03 293	71.86 295	95.25 357	79.92 314	73.43 364	91.34 326

TranMVSNet+NR-MVSNet		87.75 274	86.31 280	92.07 261	90.81 349	88.56 206	98.33 217	97.18 189	87.76 235	81.87 311	93.90 272	72.45 288	95.43 352	83.13 289	71.30 380	92.23 293

PS-CasMVS		85.81 307	84.58 310	89.49 327	90.77 350	82.11 333	97.20 290	97.36 172	84.83 296	79.12 344	92.84 296	67.42 329	95.16 359	78.39 327	73.25 365	91.21 332

DeepMVS_CX				76.08 396	90.74 351	51.65 429		90.84 407	86.47 270	57.89 417	87.98 377	35.88 421	92.60 389	65.77 394	65.06 398	83.97 412

OPM-MVS		89.76 238	89.15 232	91.57 273	90.53 352	85.58 282	98.11 238	95.93 285	92.88 90	86.05 254	96.47 220	67.06 332	97.87 226	89.29 217	86.08 274	91.26 330
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XXY-MVS		87.75 274	86.02 284	92.95 242	90.46 353	89.70 173	97.71 267	95.90 293	84.02 305	80.95 320	94.05 263	67.51 328	97.10 272	85.16 259	78.41 320	92.04 303

UniMVSNet_ETH3D		85.65 312	83.79 321	91.21 277	90.41 354	80.75 352	95.36 348	95.78 301	78.76 370	81.83 314	94.33 262	49.86 404	96.66 288	84.30 272	83.52 296	96.22 256

v10		85.73 310	84.01 318	90.87 287	90.03 355	86.73 249	97.20 290	95.22 340	81.25 354	79.85 335	89.75 366	73.30 280	96.28 318	76.87 335	72.64 368	89.61 371

v8		86.11 301	84.45 312	91.10 279	89.99 356	86.85 247	97.24 287	95.36 329	81.99 346	79.89 334	89.86 365	74.53 267	96.39 304	78.83 323	72.32 372	90.05 363

V42		87.00 285	85.68 290	90.98 283	89.91 357	86.08 268	98.32 219	95.61 313	83.67 314	82.72 287	90.67 341	74.00 274	96.53 295	81.94 301	74.28 352	90.32 356

XVG-ACMP-BASELINE		85.86 305	84.95 301	88.57 340	89.90 358	77.12 377	94.30 359	95.60 314	87.40 246	82.12 302	92.99 295	53.42 393	97.66 243	85.02 262	83.83 290	90.92 339

PEN-MVS		85.21 316	83.93 319	89.07 335	89.89 359	81.31 343	97.09 294	97.24 181	84.45 301	78.66 346	92.68 299	68.44 318	94.87 364	75.98 343	70.92 381	91.04 336

test_fmvs2		85.10 317	85.45 294	84.02 379	89.85 360	65.63 413	98.49 196	92.59 386	90.45 148	85.43 263	93.32 285	43.94 411	96.59 291	90.81 195	84.19 287	89.85 367

v1144		86.83 288	85.31 296	91.40 274	89.75 361	87.21 244	98.31 220	95.45 322	83.22 320	82.70 288	90.78 336	73.36 277	96.36 306	79.49 316	74.69 346	90.63 351

TransMVSNet (Re)		81.97 345	79.61 355	89.08 334	89.70 362	84.01 308	97.26 285	91.85 397	78.84 368	73.07 384	91.62 318	67.17 331	95.21 358	67.50 387	59.46 410	88.02 384

v2v482		87.27 283	85.76 288	91.78 271	89.59 363	87.58 228	98.56 187	95.54 317	84.53 299	82.51 293	91.78 314	73.11 282	96.47 300	82.07 298	74.14 355	91.30 328

pm-mvs1		84.68 322	82.78 330	90.40 300	89.58 364	85.18 290	97.31 282	94.73 351	81.93 348	76.05 361	92.01 308	65.48 344	96.11 326	78.75 324	69.14 384	89.91 366

pmmvs4		87.58 280	86.17 283	91.80 267	89.58 364	88.92 197	97.25 286	95.28 331	82.54 336	80.49 325	93.17 291	75.62 260	96.05 328	82.75 292	78.90 318	90.42 354

v1192		86.32 299	84.71 307	91.17 278	89.53 366	86.40 255	98.13 234	95.44 324	82.52 337	82.42 296	90.62 345	71.58 299	96.33 313	77.23 331	74.88 343	90.79 343

v144192		86.40 297	84.89 302	90.91 284	89.48 367	85.59 281	98.21 228	95.43 325	82.45 339	82.62 291	90.58 348	72.79 287	96.36 306	78.45 326	74.04 356	90.79 343

v148		86.38 298	85.06 298	90.37 303	89.47 368	84.10 307	98.52 190	95.48 320	83.80 310	80.93 321	90.22 359	74.60 265	96.31 314	80.92 307	71.55 378	90.69 349

v1921920		86.02 302	84.44 313	90.77 290	89.32 369	85.20 289	98.10 239	95.35 330	82.19 343	82.25 300	90.71 338	70.73 302	96.30 317	76.85 336	74.49 348	90.80 342

v1240		85.77 309	84.11 316	90.73 291	89.26 370	85.15 292	97.88 253	95.23 339	81.89 349	82.16 301	90.55 350	69.60 311	96.31 314	75.59 346	74.87 344	90.72 348

our_test_3		84.47 327	82.80 328	89.50 325	89.01 371	83.90 310	97.03 296	94.56 356	81.33 353	75.36 368	90.52 351	71.69 297	94.54 372	68.81 382	76.84 332	90.07 361

ppachtmachnet_test		83.63 338	81.57 341	89.80 316	89.01 371	85.09 293	97.13 293	94.50 357	78.84 368	76.14 360	91.00 331	69.78 307	94.61 371	63.40 399	74.36 350	89.71 370

DTE-MVSNet		84.14 332	82.80 328	88.14 344	88.95 373	79.87 355	96.81 304	96.24 256	83.50 316	77.60 356	92.52 301	67.89 325	94.24 375	72.64 368	69.05 385	90.32 356

PS-MVSNAJss		89.54 242	89.05 234	91.00 282	88.77 374	84.36 303	97.39 278	95.97 277	88.47 205	81.88 310	93.80 275	82.48 198	96.50 297	89.34 214	83.34 298	92.15 298

Baseline_NR-MVSNet		85.83 306	84.82 304	88.87 339	88.73 375	83.34 317	98.63 175	91.66 399	80.41 364	82.44 294	91.35 324	74.63 263	95.42 353	84.13 276	71.39 379	87.84 385

MVP-Stereo		86.61 293	85.83 287	88.93 338	88.70 376	83.85 311	96.07 332	94.41 363	82.15 344	75.64 366	91.96 311	67.65 326	96.45 302	77.20 333	98.72 102	86.51 397
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EU-MVSNet		84.19 331	84.42 314	83.52 383	88.64 377	67.37 411	96.04 333	95.76 304	85.29 285	78.44 350	93.18 290	70.67 303	91.48 401	75.79 345	75.98 335	91.70 307

pmmvs5		85.87 304	84.40 315	90.30 304	88.53 378	84.23 304	98.60 182	93.71 374	81.53 351	80.29 328	92.02 307	64.51 348	95.52 349	82.04 300	78.34 321	91.15 333

MDA-MVSNet-bldmvs		77.82 370	74.75 376	87.03 355	88.33 379	78.52 368	96.34 320	92.85 383	75.57 386	48.87 423	87.89 378	57.32 375	92.49 393	60.79 406	64.80 399	90.08 360

N_pmnet		70.19 383	69.87 385	71.12 403	88.24 380	30.63 442	95.85 341	28.70 441	70.18 404	68.73 397	86.55 392	64.04 350	93.81 377	53.12 418	73.46 362	88.94 378

v7n		84.42 328	82.75 331	89.43 328	88.15 381	81.86 335	96.75 308	95.67 310	80.53 360	78.38 351	89.43 370	69.89 306	96.35 311	73.83 360	72.13 374	90.07 361

SixPastTwentyTwo		82.63 342	81.58 340	85.79 366	88.12 382	71.01 403	95.17 351	92.54 387	84.33 302	72.93 385	92.08 305	60.41 366	95.61 348	74.47 353	74.15 354	90.75 346

test_djsdf		88.26 268	87.73 259	89.84 315	88.05 383	82.21 332	97.77 260	96.17 264	86.84 257	82.41 297	91.95 312	72.07 292	95.99 330	89.83 204	84.50 284	91.32 327

mvs_tets		87.09 284	86.22 281	89.71 319	87.87 384	81.39 341	96.73 310	95.90 293	88.19 221	79.99 332	93.61 280	59.96 367	96.31 314	89.40 213	84.34 286	91.43 322

OurMVSNet-221017-0		84.13 333	83.59 322	85.77 367	87.81 385	70.24 405	94.89 354	93.65 376	86.08 273	76.53 358	93.28 288	61.41 361	96.14 325	80.95 306	77.69 329	90.93 338

YYNet1		79.64 360	77.04 365	87.43 353	87.80 386	79.98 354	96.23 326	94.44 358	73.83 394	51.83 420	87.53 381	67.96 324	92.07 398	66.00 393	67.75 391	90.23 358

MDA-MVSNet_test_wron		79.65 359	77.05 364	87.45 352	87.79 387	80.13 353	96.25 325	94.44 358	73.87 393	51.80 421	87.47 385	68.04 322	92.12 397	66.02 392	67.79 390	90.09 359

jajsoiax		87.35 281	86.51 278	89.87 313	87.75 388	81.74 336	97.03 296	95.98 276	88.47 205	80.15 330	93.80 275	61.47 360	96.36 306	89.44 212	84.47 285	91.50 318

K. test v3		81.04 351	79.77 354	84.83 374	87.41 389	70.23 406	95.60 347	93.93 371	83.70 313	67.51 403	89.35 371	55.76 379	93.58 380	76.67 338	68.03 388	90.67 350

dmvs_testset		77.17 372	78.99 357	71.71 401	87.25 390	38.55 438	91.44 390	81.76 429	85.77 278	69.49 394	95.94 237	69.71 309	84.37 421	52.71 419	76.82 333	92.21 295

testgi		82.29 343	81.00 346	86.17 362	87.24 391	74.84 388	97.39 278	91.62 401	88.63 201	75.85 365	95.42 247	46.07 410	91.55 400	66.87 391	79.94 315	92.12 299

LF4IMVS		81.94 346	81.17 345	84.25 378	87.23 392	68.87 410	93.35 370	91.93 396	83.35 319	75.40 367	93.00 294	49.25 407	96.65 289	78.88 322	78.11 322	87.22 393

EG-PatchMatch MVS		79.92 355	77.59 361	86.90 357	87.06 393	77.90 374	96.20 329	94.06 369	74.61 390	66.53 407	88.76 374	40.40 418	96.20 321	67.02 389	83.66 294	86.61 395

test_fmvsmconf0.01_n		94.14 133	93.51 141	96.04 131	86.79 394	89.19 181	99.28 95	95.94 282	95.70 28	95.50 124	98.49 124	73.27 281	99.79 94	98.28 58	98.32 122	99.15 118

Gipuma		54.77 395	52.22 399	62.40 412	86.50 395	59.37 419	50.20 430	90.35 410	36.52 428	41.20 429	49.49 430	18.33 431	81.29 423	32.10 429	65.34 397	46.54 430
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
anonymousdsp		86.69 290	85.75 289	89.53 324	86.46 396	82.94 321	96.39 318	95.71 306	83.97 307	79.63 337	90.70 339	68.85 314	95.94 333	86.01 249	84.02 289	89.72 369

EGC-MVSNET		60.70 390	55.37 394	76.72 395	86.35 397	71.08 401	89.96 401	84.44 426	0.38 438	1.50 439	84.09 399	37.30 419	88.10 416	40.85 427	73.44 363	70.97 423

MVStest1		76.56 373	73.43 379	85.96 365	86.30 398	80.88 351	94.26 360	91.74 398	61.98 420	58.53 416	89.96 363	69.30 312	91.47 402	59.26 410	49.56 425	85.52 404

test_method		70.10 384	68.66 387	74.41 400	86.30 398	55.84 422	94.47 356	89.82 412	35.18 429	66.15 408	84.75 398	30.54 423	77.96 430	70.40 377	60.33 408	89.44 373

lessismore_v0				85.08 371	85.59 400	69.28 408		90.56 409		67.68 402	90.21 360	54.21 390	95.46 351	73.88 358	62.64 402	90.50 353

CMPMVS	58.40 21	80.48 353	80.11 352	81.59 391	85.10 401	59.56 418	94.14 363	95.95 281	68.54 410	60.71 414	93.31 286	55.35 384	97.87 226	83.06 290	84.85 282	87.33 391
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20231206		80.76 352	79.42 356	84.79 375	84.78 402	72.98 395	96.53 313	92.97 382	79.56 365	74.33 371	88.83 373	61.27 362	92.15 396	60.59 407	75.92 336	89.24 376

DSMNet-mixed		81.60 348	81.43 342	82.10 388	84.36 403	60.79 416	93.63 368	86.74 421	79.00 366	79.32 341	87.15 388	63.87 351	89.78 410	66.89 390	91.92 224	95.73 264

pmmvs6		79.90 356	77.31 363	87.67 348	84.17 404	78.13 371	95.86 340	93.68 375	67.94 412	72.67 386	89.62 368	50.98 401	95.75 342	74.80 352	66.04 395	89.14 377

new_pmnet		76.02 374	73.71 378	82.95 384	83.88 405	72.85 397	91.26 393	92.26 390	70.44 403	62.60 412	81.37 408	47.64 408	92.32 394	61.85 403	72.10 375	83.68 413

OpenMVS_ROB	73.86 20	77.99 369	75.06 375	86.77 358	83.81 406	77.94 373	96.38 319	91.53 403	67.54 413	68.38 398	87.13 389	43.94 411	96.08 327	55.03 416	81.83 306	86.29 399

ttmdpeth		79.80 358	77.91 360	85.47 369	83.34 407	75.75 382	95.32 349	91.45 404	76.84 380	74.81 370	91.71 317	53.98 391	94.13 376	72.42 369	61.29 405	86.51 397

test20.03		78.51 366	77.48 362	81.62 390	83.07 408	71.03 402	96.11 331	92.83 384	81.66 350	69.31 395	89.68 367	57.53 373	87.29 418	58.65 412	68.47 386	86.53 396

Anonymous20240521		78.63 365	76.90 366	83.82 380	82.82 409	72.86 396	95.72 345	93.57 377	73.55 396	72.17 388	84.79 397	49.69 405	92.51 392	65.29 395	74.50 347	86.09 400

UnsupCasMVSNet_eth		78.90 362	76.67 367	85.58 368	82.81 410	74.94 387	91.98 383	96.31 250	84.64 298	65.84 409	87.71 379	51.33 398	92.23 395	72.89 366	56.50 415	89.56 372

KD-MVS_self_test		77.47 371	75.88 370	82.24 386	81.59 411	68.93 409	92.83 377	94.02 370	77.03 378	73.14 381	83.39 400	55.44 383	90.42 405	67.95 385	57.53 413	87.38 389

CL-MVSNet_self_test		79.89 357	78.34 358	84.54 377	81.56 412	75.01 386	96.88 302	95.62 312	81.10 355	75.86 364	85.81 395	68.49 317	90.26 406	63.21 400	56.51 414	88.35 382

MIMVSNet1		75.92 375	73.30 380	83.81 381	81.29 413	75.57 384	92.26 381	92.05 394	73.09 397	67.48 404	86.18 393	40.87 417	87.64 417	55.78 415	70.68 382	88.21 383

Patchmatch-RL test		81.90 347	80.13 351	87.23 354	80.71 414	70.12 407	84.07 418	88.19 419	83.16 322	70.57 389	82.18 406	87.18 105	92.59 390	82.28 297	62.78 401	98.98 133

APD_test1		68.93 385	66.98 388	74.77 399	80.62 415	53.15 426	87.97 404	85.01 424	53.76 422	59.26 415	87.52 382	25.19 425	89.95 407	56.20 414	67.33 392	81.19 417

mvs5depth		78.17 367	75.56 371	85.97 364	80.43 416	76.44 380	85.46 410	89.24 416	76.39 382	78.17 354	88.26 376	51.73 397	95.73 343	69.31 380	61.09 406	85.73 402

pmmvs-eth3d		78.71 364	76.16 369	86.38 359	80.25 417	81.19 345	94.17 362	92.13 393	77.97 373	66.90 406	82.31 405	55.76 379	92.56 391	73.63 362	62.31 404	85.38 405

UnsupCasMVSNet_bld		73.85 380	70.14 384	84.99 372	79.44 418	75.73 383	88.53 403	95.24 335	70.12 405	61.94 413	74.81 420	41.41 416	93.62 379	68.65 383	51.13 423	85.62 403

PM-MVS		74.88 378	72.85 381	80.98 392	78.98 419	64.75 414	90.81 397	85.77 422	80.95 358	68.23 400	82.81 402	29.08 424	92.84 386	76.54 339	62.46 403	85.36 406

new-patchmatchnet		74.80 379	72.40 382	81.99 389	78.36 420	72.20 399	94.44 357	92.36 389	77.06 377	63.47 411	79.98 414	51.04 400	88.85 414	60.53 408	54.35 417	84.92 410

test_fmvs3		75.09 377	75.19 373	74.81 398	77.45 421	54.08 424	95.93 334	90.64 408	82.51 338	73.29 379	81.19 409	22.29 427	86.29 420	85.50 257	67.89 389	84.06 411

WB-MVS		66.44 386	66.29 389	66.89 406	74.84 422	44.93 433	93.00 372	84.09 427	71.15 400	55.82 418	81.63 407	63.79 352	80.31 428	21.85 432	50.47 424	75.43 419

SSC-MVS		65.42 387	65.20 390	66.06 407	73.96 423	43.83 434	92.08 382	83.54 428	69.77 406	54.73 419	80.92 411	63.30 354	79.92 429	20.48 433	48.02 426	74.44 420

pmmvs3		72.86 381	69.76 386	82.17 387	73.86 424	74.19 390	94.20 361	89.01 417	64.23 419	67.72 401	80.91 412	41.48 415	88.65 415	62.40 402	54.02 418	83.68 413

mvsany_test3		75.85 376	74.52 377	79.83 393	73.53 425	60.64 417	91.73 386	87.87 420	83.91 309	70.55 390	82.52 403	31.12 422	93.66 378	86.66 244	62.83 400	85.19 409

test_f		71.94 382	70.82 383	75.30 397	72.77 426	53.28 425	91.62 387	89.66 414	75.44 387	64.47 410	78.31 417	20.48 428	89.56 411	78.63 325	66.02 396	83.05 416

ambc				79.60 394	72.76 427	56.61 421	76.20 425	92.01 395		68.25 399	80.23 413	23.34 426	94.73 368	73.78 361	60.81 407	87.48 388

TDRefinement		78.01 368	75.31 372	86.10 363	70.06 428	73.84 391	93.59 369	91.58 402	74.51 391	73.08 383	91.04 330	49.63 406	97.12 269	74.88 350	59.47 409	87.33 391

test_vis3_rt		61.29 389	58.75 392	68.92 405	67.41 429	52.84 427	91.18 395	59.23 440	66.96 414	41.96 428	58.44 428	11.37 436	94.72 369	74.25 355	57.97 412	59.20 427

testf1		56.38 393	53.73 396	64.31 410	64.84 430	45.11 431	80.50 423	75.94 435	38.87 425	42.74 425	75.07 418	11.26 437	81.19 424	41.11 425	53.27 419	66.63 424

APD_test2		56.38 393	53.73 396	64.31 410	64.84 430	45.11 431	80.50 423	75.94 435	38.87 425	42.74 425	75.07 418	11.26 437	81.19 424	41.11 425	53.27 419	66.63 424

PMMVS2		58.97 392	55.07 395	70.69 404	62.72 432	55.37 423	85.97 408	80.52 430	49.48 423	45.94 424	68.31 422	15.73 433	80.78 426	49.79 421	37.12 429	75.91 418

E-PMN		41.02 400	40.93 402	41.29 416	61.97 433	33.83 439	84.00 419	65.17 438	27.17 431	27.56 431	46.72 432	17.63 432	60.41 435	19.32 434	18.82 431	29.61 431

wuyk23d		16.71 404	16.73 408	16.65 418	60.15 434	25.22 443	41.24 431	5.17 442	6.56 435	5.48 438	3.61 438	3.64 440	22.72 437	15.20 436	9.52 435	1.99 435

FPMVS		61.57 388	60.32 391	65.34 408	60.14 435	42.44 436	91.02 396	89.72 413	44.15 424	42.63 427	80.93 410	19.02 429	80.59 427	42.50 424	72.76 367	73.00 421

EMVS		39.96 401	39.88 403	40.18 417	59.57 436	32.12 441	84.79 416	64.57 439	26.27 432	26.14 433	44.18 435	18.73 430	59.29 436	17.03 435	17.67 433	29.12 432

LCM-MVSNet		60.07 391	56.37 393	71.18 402	54.81 437	48.67 430	82.17 422	89.48 415	37.95 427	49.13 422	69.12 421	13.75 435	81.76 422	59.28 409	51.63 422	83.10 415

MVE	44.00 22	41.70 399	37.64 404	53.90 415	49.46 438	43.37 435	65.09 429	66.66 437	26.19 433	25.77 434	48.53 431	3.58 441	63.35 434	26.15 431	27.28 430	54.97 429
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		50.71 397	46.17 400	64.33 409	44.27 439	52.30 428	76.13 426	78.73 431	64.95 417	27.37 432	55.23 429	14.61 434	67.74 432	36.01 428	18.23 432	72.95 422

PMVS	41.42 23	45.67 398	42.50 401	55.17 414	34.28 440	32.37 440	66.24 428	78.71 432	30.72 430	22.04 435	59.59 426	4.59 439	77.85 431	27.49 430	58.84 411	55.29 428
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		53.66 396	52.86 398	56.05 413	32.75 441	41.97 437	73.42 427	76.12 434	21.91 434	39.68 430	96.39 223	42.59 414	65.10 433	78.00 328	14.92 434	61.08 426

testmvs		18.81 403	23.05 406	6.10 420	4.48 442	2.29 445	97.78 258	3.00 443	3.27 436	18.60 436	62.71 424	1.53 443	2.49 439	14.26 437	1.80 436	13.50 434

test123		16.58 405	19.47 407	7.91 419	3.59 443	5.37 444	94.32 358	1.39 444	2.49 437	13.98 437	44.60 434	2.91 442	2.65 438	11.35 438	0.57 437	15.70 433

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

eth-test2					0.00 444

eth-test					0.00 444

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

cdsmvs_eth3d_5k		22.52 402	30.03 405	0.00 421	0.00 444	0.00 446	0.00 432	97.17 190	0.00 439	0.00 440	98.77 97	74.35 270	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		6.87 407	9.16 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	82.48 198	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

ab-mvs-re		8.21 406	10.94 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	98.50 121	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						79.74 357								67.75 386

PC_three_1452									94.60 45	99.41 6	99.12 55	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

test_241102_TWO								97.72 89	94.17 53	99.23 15	99.54 3	93.14 25	99.98 9	99.70 5	99.82 19	99.99 1

test_0728_THIRD									93.01 83	99.07 21	99.46 10	94.66 13	99.97 21	99.25 21	99.82 19	99.95 15

GSMVS																98.84 148

sam_mvs1												88.39 80				98.84 148

sam_mvs												87.08 108

MTGPA								97.45 156

test_post1							90.74 399				41.37 436	85.38 148	96.36 306	83.16 287

test_post											46.00 433	87.37 99	97.11 270

patchmatchnet-post											84.86 396	88.73 76	96.81 283

MTMP							99.21 101	91.09 406

test9_res														98.60 42	99.87 9	99.90 22

agg_prior2														97.84 68	99.87 9	99.91 21

test_prior4						92.00 110	99.41 79

test_prior2							99.57 52		91.43 121	98.12 55	98.97 73	90.43 51		98.33 55	99.81 23

旧先验2							98.67 169		85.75 280	98.96 26			98.97 166	93.84 156

新几何2							98.26 223

无先验							98.52 190	97.82 70	87.20 249				99.90 53	87.64 233		99.85 30

原ACMM2							98.69 166

testdata2													99.88 62	84.16 275

segment_acmp												90.56 49

testdata1							97.89 251		92.43 97

plane_prior5								96.30 251					97.75 239	93.46 165	86.17 272	92.67 283

plane_prior4											96.52 216

plane_prior3						85.91 274			93.65 71	86.99 247

plane_prior2							99.02 133		93.38 78

plane_prior						86.07 270	99.14 117		93.81 68						86.26 271

n2								0.00 445

nn								0.00 445

door-mid								84.90 425

test11								97.68 100

door								85.30 423

HQP5-MVS						86.39 256

BP-MVS														93.82 158

HQP4-MVS										87.57 240			97.77 233			92.72 281

HQP3-MVS								96.37 247							86.29 269

HQP2-MVS												73.34 278

MDTV_nov1_ep13_2view						91.17 128	91.38 391		87.45 245	93.08 169		86.67 119		87.02 236		98.95 139

ACMMP++_ref															82.64 303

ACMMP++															83.83 290

Test By Simon												83.62 169

High-resolution multi-view benchmark