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		93.82 147	93.06 155	96.10 132	99.88 1	89.07 193	98.33 222	97.55 137	86.81 266	90.39 222	98.65 111	75.09 268	99.98 9	93.32 173	97.53 140	99.26 111

DP-MVS Recon		95.85 76	95.15 95	97.95 32	99.87 2	94.38 57	99.60 50	97.48 153	86.58 271	94.42 145	99.13 52	87.36 102	99.98 9	93.64 165	98.33 121	99.48 89

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 35	97.98 57	97.18 8	95.96 112	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 56	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	99.07 128	99.06 10	94.45 51	96.42 104	98.70 108	88.81 75	99.74 101	95.35 128	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 63	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 57	96.17 61	96.70 92	99.70 7	90.31 157	99.46 70	97.66 108	90.55 151	97.07 83	99.07 61	86.85 113	99.97 21	95.43 126	99.74 29	99.81 35

HFP-MVS		96.42 53	96.26 53	96.90 80	99.69 8	90.96 141	99.47 66	97.81 76	90.54 152	96.88 87	99.05 66	87.57 94	99.96 28	95.65 118	99.72 32	99.78 41

ACMMPR		96.28 58	96.14 65	96.73 89	99.68 9	90.47 154	99.47 66	97.80 78	90.54 152	96.83 92	99.03 68	86.51 127	99.95 32	95.65 118	99.72 32	99.75 49

ZD-MVS					99.67 10	93.28 79		97.61 124	87.78 241	97.41 73	99.16 43	90.15 58	99.56 118	98.35 54	99.70 37

CP-MVS		96.22 59	96.15 64	96.42 110	99.67 10	89.62 183	99.70 35	97.61 124	90.07 168	96.00 111	99.16 43	87.43 97	99.92 43	96.03 112	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	97.47 155	93.95 59	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	97.68 102					99.98 9	99.64 8	99.82 19	99.96 10

test0726					99.66 12	95.20 32	99.77 25	97.70 96	93.95 59	99.35 10	99.54 3	93.18 23

CPTT-MVS		94.60 124	94.43 112	95.09 180	99.66 12	86.85 255	99.44 73	97.47 155	83.22 329	94.34 149	98.96 79	82.50 198	99.55 119	94.81 143	99.50 55	98.88 147

MSLP-MVS++		97.50 17	97.45 18	97.63 42	99.65 16	93.21 81	99.70 35	98.13 45	94.61 45	97.78 68	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 91	94.17 54	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 90	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 91	94.16 56	99.30 12	99.49 9	93.32 20	99.98 9

PAPR		96.35 54	95.82 72	97.94 33	99.63 18	94.19 62	99.42 79	97.55 137	92.43 100	93.82 162	99.12 55	87.30 104	99.91 49	94.02 157	99.06 81	99.74 50

XVS		96.47 51	96.37 50	96.77 85	99.62 22	90.66 150	99.43 77	97.58 132	92.41 103	96.86 88	98.96 79	87.37 99	99.87 66	95.65 118	99.43 61	99.78 41

X-MVStestdata		90.69 226	88.66 252	96.77 85	99.62 22	90.66 150	99.43 77	97.58 132	92.41 103	96.86 88	29.59 449	87.37 99	99.87 66	95.65 118	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 55	97.68 102	93.01 86	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		97.69 100					99.98 9	99.55 14	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 100					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	98.85 151	97.64 117	96.51 21	95.88 115	99.39 18	87.35 103	99.99 5	96.61 96	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		97.64 117	93.14 85	98.93 27	99.45 14	93.45 18

CDPH-MVS		96.56 49	96.18 58	97.70 40	99.59 28	93.92 65	99.13 122	97.44 162	89.02 197	97.90 65	99.22 31	88.90 74	99.49 125	94.63 148	99.79 27	99.68 60

test_prior				97.01 70	99.58 30	91.77 118		97.57 135					99.49 125			99.79 38

APDe-MVS		97.53 15	97.47 16	97.70 40	99.58 30	93.63 70	99.56 54	97.52 145	93.59 76	98.01 62	99.12 55	90.80 45	99.55 119	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 74	95.75 77	96.38 114	99.58 30	89.41 187	99.26 99	97.41 166	90.66 143	94.82 137	98.95 82	86.15 135	99.98 9	95.24 133	99.64 42	99.74 50

TEST9					99.57 33	93.17 83	99.38 83	97.66 108	89.57 182	98.39 47	99.18 40	90.88 43	99.66 107

train_agg		97.20 23	97.08 23	97.57 46	99.57 33	93.17 83	99.38 83	97.66 108	90.18 162	98.39 47	99.18 40	90.94 39	99.66 107	98.58 45	99.85 13	99.88 26

test_8					99.55 35	93.07 86	99.37 86	97.64 117	90.18 162	98.36 49	99.19 37	90.94 39	99.64 113

test_part2					99.54 36	95.42 22				98.13 54

MSP-MVS		97.77 10	98.18 2	96.53 105	99.54 36	90.14 164	99.41 80	97.70 96	95.46 35	98.60 40	99.19 37	95.71 5	99.49 125	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		97.64 117		97.98 63			99.61 115

CSCG		94.87 113	94.71 106	95.36 167	99.54 36	86.49 261	99.34 90	98.15 43	82.71 342	90.15 225	99.25 26	89.48 66	99.86 72	94.97 140	98.82 96	99.72 53

HPM-MVS++		97.72 12	97.59 13	98.14 24	99.53 40	94.76 45	99.19 104	97.75 86	95.66 31	98.21 52	99.29 23	91.10 36	99.99 5	97.68 70	99.87 9	99.68 60

APD-MVS		96.95 31	96.72 38	97.63 42	99.51 41	93.58 71	99.16 110	97.44 162	90.08 167	98.59 41	99.07 61	89.06 69	99.42 136	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	88.94 202	99.55 55	97.47 155	91.32 128	98.12 56

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 23	99.29 93	97.72 91	94.50 47	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 76	95.65 82	96.45 108	99.50 42	89.77 179	98.22 231	98.90 13	89.19 192	96.74 97	98.95 82	85.91 139	99.92 43	93.94 158	99.46 57	99.66 64

GST-MVS		95.97 69	95.66 80	96.90 80	99.49 45	91.22 128	99.45 72	97.48 153	89.69 176	95.89 114	98.72 104	86.37 130	99.95 32	94.62 149	99.22 74	99.52 83

MP-MVS		96.00 66	95.82 72	96.54 104	99.47 46	90.13 166	99.36 87	97.41 166	90.64 146	95.49 127	98.95 82	85.51 144	99.98 9	96.00 113	99.59 51	99.52 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.09 63	95.81 74	96.95 78	99.42 47	91.19 130	99.55 55	97.53 141	89.72 175	95.86 117	98.94 85	86.59 122	99.97 21	95.13 134	99.56 52	99.68 60

SR-MVS		96.13 62	96.16 63	96.07 133	99.42 47	89.04 194	98.59 189	97.33 177	90.44 155	96.84 90	99.12 55	86.75 115	99.41 139	97.47 73	99.44 60	99.76 48

PAPM_NR		95.43 93	95.05 100	96.57 103	99.42 47	90.14 164	98.58 191	97.51 147	90.65 145	92.44 184	98.90 89	87.77 93	99.90 53	90.88 199	99.32 66	99.68 60

9.14			96.87 29		99.34 50		99.50 62	97.49 152	89.41 189	98.59 41	99.43 16	89.78 62	99.69 104	98.69 39	99.62 46

save fliter					99.34 50	93.85 67	99.65 45	97.63 121	95.69 29

PHI-MVS		96.65 44	96.46 48	97.21 62	99.34 50	91.77 118	99.70 35	98.05 50	86.48 276	98.05 59	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		97.55 137		97.56 69		88.60 78	99.50 124		99.71 36	99.55 80

SMA-MVS		97.24 20	96.99 24	98.00 31	99.30 54	94.20 61	99.16 110	97.65 115	89.55 184	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 63	95.80 75	96.96 77	99.29 55	91.19 130	97.23 297	97.45 158	92.58 97	94.39 147	99.24 28	86.43 129	99.99 5	96.22 103	99.40 64	99.71 54

HPM-MVS		95.41 95	95.22 93	95.99 139	99.29 55	89.14 191	99.17 109	97.09 203	87.28 255	95.40 128	98.48 128	84.93 155	99.38 141	95.64 122	99.65 40	99.47 91
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
lecture		96.67 40	96.77 36	96.39 113	99.27 57	89.71 180	99.65 45	98.62 22	92.28 106	98.62 39	99.07 61	86.74 116	99.79 94	97.83 69	98.82 96	99.66 64

ACMMP		94.67 122	94.30 113	95.79 148	99.25 58	88.13 223	98.41 210	98.67 21	90.38 157	91.43 201	98.72 104	82.22 207	99.95 32	93.83 162	95.76 180	99.29 108
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 89	95.65 82	95.62 160	99.24 59	87.80 229	98.42 208	97.22 185	88.93 202	96.64 102	98.98 73	85.49 145	99.36 143	96.68 93	99.27 70	99.70 55

SR-MVS-dyc-post		95.75 83	95.86 70	95.41 166	99.22 60	87.26 250	98.40 213	97.21 186	89.63 178	96.67 100	98.97 74	86.73 118	99.36 143	96.62 94	99.31 67	99.60 75

RE-MVS-def			95.70 78		99.22 60	87.26 250	98.40 213	97.21 186	89.63 178	96.67 100	98.97 74	85.24 152		96.62 94	99.31 67	99.60 75

patch_mono-2		97.10 27	97.97 8	94.49 204	99.21 62	83.73 321	99.62 49	98.25 34	95.28 37	99.38 9	98.91 87	92.28 31	99.94 35	99.61 11	99.22 74	99.78 41

API-MVS		94.78 116	94.18 119	96.59 100	99.21 62	90.06 171	98.80 157	97.78 83	83.59 324	93.85 160	99.21 33	83.79 169	99.97 21	92.37 184	99.00 85	99.74 50

PLC	91.07 3	94.23 134	94.01 123	94.87 188	99.17 64	87.49 239	99.25 100	96.55 240	88.43 218	91.26 205	98.21 141	85.92 137	99.86 72	89.77 214	97.57 137	97.24 231
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EI-MVSNet-Vis-set		95.76 82	95.63 84	96.17 128	99.14 65	90.33 156	98.49 201	97.82 72	91.92 113	94.75 139	98.88 93	87.06 109	99.48 129	95.40 127	97.17 150	98.70 168

TSAR-MVS + MP.		97.44 18	97.46 17	97.39 54	99.12 66	93.49 76	98.52 195	97.50 150	94.46 49	98.99 23	98.64 112	91.58 33	99.08 162	98.49 49	99.83 15	99.60 75
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 67	94.88 38	99.44 73	97.45 158	89.60 180	98.70 35	99.42 17	90.42 52	99.72 102	98.47 50	99.65 40	99.77 46

HPM-MVS_fast		94.89 109	94.62 107	95.70 152	99.11 67	88.44 219	99.14 118	97.11 199	85.82 284	95.69 123	98.47 129	83.46 174	99.32 148	93.16 175	99.63 45	99.35 102

MAR-MVS		94.43 130	94.09 121	95.45 164	99.10 69	87.47 240	98.39 217	97.79 80	88.37 220	94.02 155	99.17 42	78.64 249	99.91 49	92.48 183	98.85 95	98.96 136
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		94.06 137	93.05 156	97.06 68	99.08 70	92.26 109	98.97 142	97.01 211	82.58 344	92.57 182	98.22 139	80.68 227	99.30 149	89.34 220	99.02 84	99.63 72

EI-MVSNet-UG-set		95.43 93	95.29 90	95.86 145	99.07 71	89.87 176	98.43 207	97.80 78	91.78 115	94.11 152	98.77 98	86.25 133	99.48 129	94.95 141	96.45 163	98.22 201

原ACMM1				96.18 126	99.03 72	90.08 167		97.63 121	88.98 198	97.00 85	98.97 74	88.14 87	99.71 103	88.23 232	99.62 46	98.76 163

SD-MVS		97.51 16	97.40 19	97.81 36	99.01 73	93.79 69	99.33 91	97.38 170	93.73 71	98.83 31	99.02 70	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 74	96.57 11	99.91 2	98.17 39	97.45 4	98.76 33	98.97 74	86.69 119	99.96 28	99.72 3	98.92 91	99.69 58

旧先验1					98.97 74	92.90 94		97.74 87			99.15 47	91.05 38			99.33 65	99.60 75

LS3D		90.19 238	88.72 250	94.59 202	98.97 74	86.33 268	96.90 310	96.60 234	74.96 398	84.06 282	98.74 101	75.78 264	99.83 82	74.93 358	97.57 137	97.62 220

CNLPA		93.64 154	92.74 164	96.36 116	98.96 77	90.01 174	99.19 104	95.89 303	86.22 279	89.40 234	98.85 94	80.66 228	99.84 78	88.57 228	96.92 155	99.24 112

reproduce-ours		96.66 41	96.80 34	96.22 122	98.95 78	89.03 196	98.62 181	97.38 170	93.42 78	96.80 95	99.36 19	88.92 72	99.80 90	98.51 47	99.26 71	99.82 32

our_new_method		96.66 41	96.80 34	96.22 122	98.95 78	89.03 196	98.62 181	97.38 170	93.42 78	96.80 95	99.36 19	88.92 72	99.80 90	98.51 47	99.26 71	99.82 32

MP-MVS-pluss		95.80 79	95.30 89	97.29 57	98.95 78	92.66 98	98.59 189	97.14 195	88.95 200	93.12 171	99.25 26	85.62 141	99.94 35	96.56 98	99.48 56	99.28 109
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
reproduce_model		96.57 48	96.75 37	96.02 136	98.93 81	88.46 218	98.56 192	97.34 176	93.18 84	96.96 86	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 82	92.51 105		97.77 85	85.52 289	96.69 99	99.06 64	88.08 88	99.89 60	84.88 271	99.62 46	99.79 38

DP-MVS		88.75 267	86.56 286	95.34 169	98.92 82	87.45 241	97.64 280	93.52 387	70.55 411	81.49 325	97.25 180	74.43 274	99.88 62	71.14 383	94.09 199	98.67 170

TSAR-MVS + GP.		96.95 31	96.91 27	97.07 67	98.88 84	91.62 122	99.58 52	96.54 241	95.09 40	96.84 90	98.63 114	91.16 34	99.77 98	99.04 31	96.42 164	99.81 35

CANet		97.00 30	96.49 45	98.55 12	98.86 85	96.10 16	99.83 12	97.52 145	95.90 25	97.21 79	98.90 89	82.66 196	99.93 40	98.71 38	98.80 98	99.63 72

dcpmvs_2		95.67 88	96.18 58	94.12 220	98.82 86	84.22 314	97.37 290	95.45 331	90.70 142	95.77 120	98.63 114	90.47 50	98.68 185	99.20 25	99.22 74	99.45 92

ACMMP_NAP		96.59 45	96.18 58	97.81 36	98.82 86	93.55 73	98.88 150	97.59 130	90.66 143	97.98 63	99.14 50	86.59 122	100.00 1	96.47 100	99.46 57	99.89 25

PVSNet_BlendedMVS		93.36 163	93.20 153	93.84 232	98.77 88	91.61 123	99.47 66	98.04 52	91.44 124	94.21 150	92.63 308	83.50 172	99.87 66	97.41 74	83.37 305	90.05 373

PVSNet_Blended		95.94 72	95.66 80	96.75 87	98.77 88	91.61 123	99.88 4	98.04 52	93.64 75	94.21 150	97.76 153	83.50 172	99.87 66	97.41 74	97.75 134	98.79 157

DeepPCF-MVS	93.56 1	96.55 50	97.84 10	92.68 258	98.71 90	78.11 382	99.70 35	97.71 95	98.18 1	97.36 75	99.76 1	90.37 54	99.94 35	99.27 18	99.54 54	99.99 1

EPNet		96.82 35	96.68 40	97.25 61	98.65 91	93.10 85	99.48 64	98.76 14	96.54 18	97.84 66	98.22 139	87.49 96	99.66 107	95.35 128	97.78 133	99.00 132
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		93.90 144	93.62 141	94.73 195	98.63 92	87.00 253	98.04 250	96.56 239	92.19 108	92.46 183	98.73 102	79.49 238	99.14 159	92.16 186	94.34 197	98.03 208

MVS_111021_HR		96.69 39	96.69 39	96.72 91	98.58 93	91.00 140	99.14 118	99.45 1	93.86 66	95.15 133	98.73 102	88.48 79	99.76 99	97.23 80	99.56 52	99.40 96

test_yl		95.27 99	94.60 108	97.28 59	98.53 94	92.98 89	99.05 132	98.70 18	86.76 268	94.65 142	97.74 155	87.78 91	99.44 132	95.57 124	92.61 216	99.44 93

DCV-MVSNet		95.27 99	94.60 108	97.28 59	98.53 94	92.98 89	99.05 132	98.70 18	86.76 268	94.65 142	97.74 155	87.78 91	99.44 132	95.57 124	92.61 216	99.44 93

TAPA-MVS	87.50 9	90.35 233	89.05 241	94.25 215	98.48 96	85.17 300	98.42 208	96.58 238	82.44 349	87.24 253	98.53 118	82.77 190	98.84 173	59.09 423	97.88 129	98.72 166
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.32 97	91.21 129	98.08 248	97.58 132	83.74 320	95.87 116	99.02 70	86.74 116			99.64 42	99.81 35

MM		97.76 11	97.39 20	98.86 5	98.30 98	96.83 7	99.81 17	99.13 9	97.66 2	98.29 51	98.96 79	85.84 140	99.90 53	99.72 3	98.80 98	99.85 30

reproduce_monomvs		92.11 197	91.82 188	92.98 247	98.25 99	90.55 152	98.38 219	97.93 60	94.81 42	80.46 335	92.37 310	96.46 3	97.17 275	94.06 156	73.61 367	91.23 341

DPM-MVS		97.86 8	97.25 22	99.68 1	98.25 99	99.10 1	99.76 28	97.78 83	96.61 17	98.15 53	99.53 7	93.62 17	100.00 1	91.79 190	99.80 26	99.94 18

LFMVS		92.23 193	90.84 209	96.42 110	98.24 101	91.08 137	98.24 230	96.22 263	83.39 327	94.74 140	98.31 135	61.12 372	98.85 172	94.45 151	92.82 212	99.32 105

testdata				95.26 174	98.20 102	87.28 247		97.60 126	85.21 293	98.48 44	99.15 47	88.15 86	98.72 183	90.29 207	99.45 59	99.78 41

PatchMatch-RL		91.47 205	90.54 216	94.26 214	98.20 102	86.36 267	96.94 308	97.14 195	87.75 243	88.98 237	95.75 247	71.80 302	99.40 140	80.92 316	97.39 144	97.02 239

MVS_111021_LR		95.78 80	95.94 67	95.28 173	98.19 104	87.69 231	98.80 157	99.26 7	93.39 80	95.04 135	98.69 109	84.09 166	99.76 99	96.96 86	99.06 81	98.38 187

F-COLMAP		92.07 198	91.75 191	93.02 246	98.16 105	82.89 333	98.79 161	95.97 284	86.54 273	87.92 245	97.80 150	78.69 248	99.65 111	85.97 257	95.93 179	96.53 256

Anonymous202405211		88.84 261	87.03 280	94.27 213	98.14 106	84.18 315	98.44 206	95.58 324	76.79 390	89.34 235	96.88 207	53.42 402	99.54 121	87.53 240	87.12 273	99.09 127

VNet		95.08 106	94.26 114	97.55 47	98.07 107	93.88 66	98.68 172	98.73 17	90.33 158	97.16 82	97.43 172	79.19 241	99.53 122	96.91 88	91.85 234	99.24 112

SPE-MVS-test		95.98 68	96.34 52	94.90 187	98.06 108	87.66 234	99.69 42	96.10 275	93.66 73	98.35 50	99.05 66	86.28 131	97.66 251	96.96 86	98.90 93	99.37 99

DELS-MVS		97.12 25	96.60 42	98.68 11	98.03 109	96.57 11	99.84 11	97.84 67	96.36 23	95.20 132	98.24 138	88.17 84	99.83 82	96.11 109	99.60 50	99.64 69
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	93.69 150	92.83 163	96.28 121	97.99 110	90.22 161	99.38 83	98.93 12	91.42 126	93.66 164	97.68 158	71.29 307	99.64 113	87.94 236	97.20 147	98.98 134

test_fmvsm_n_1920		97.08 28	97.55 14	95.67 154	97.94 111	89.61 184	99.93 1	98.48 25	97.08 9	99.08 20	99.13 52	88.17 84	99.93 40	99.11 29	99.06 81	97.47 223

cl22		89.57 250	88.79 249	91.91 272	97.94 111	87.62 235	97.98 253	96.51 242	85.03 298	82.37 306	91.79 321	83.65 170	96.50 305	85.96 258	77.89 332	91.61 324

CS-MVS		95.75 83	96.19 56	94.40 208	97.88 113	86.22 271	99.66 43	96.12 274	92.69 96	98.07 58	98.89 91	87.09 107	97.59 257	96.71 91	98.62 107	99.39 98

CHOSEN 280x420		96.80 36	96.85 30	96.66 96	97.85 114	94.42 56	94.76 365	98.36 31	92.50 99	95.62 125	97.52 166	97.92 1	97.38 269	98.31 57	98.80 98	98.20 203

fmvsm_s_conf0.5_n_8		97.06 29	96.94 25	97.44 48	97.78 115	92.77 97	99.83 12	97.83 71	97.58 3	99.25 14	99.20 34	82.71 194	99.92 43	99.64 8	98.61 108	99.64 69

thres200		93.69 150	92.59 169	96.97 76	97.76 116	94.74 46	99.35 89	99.36 2	89.23 190	91.21 207	96.97 200	83.42 175	98.77 176	85.08 267	90.96 253	97.39 226

HY-MVS	88.56 7	95.29 98	94.23 115	98.48 14	97.72 117	96.41 13	94.03 374	98.74 15	92.42 102	95.65 124	94.76 266	86.52 126	99.49 125	95.29 131	92.97 211	99.53 82

Anonymous20231211		84.72 330	82.65 342	90.91 293	97.71 118	84.55 310	97.28 293	96.67 228	66.88 424	79.18 352	90.87 344	58.47 380	96.60 298	82.61 303	74.20 362	91.59 326

tfpn200view9		93.43 158	92.27 175	96.90 80	97.68 119	94.84 41	99.18 106	99.36 2	88.45 215	90.79 210	96.90 204	83.31 176	98.75 179	84.11 284	90.69 255	97.12 233

thres400		93.39 160	92.27 175	96.73 89	97.68 119	94.84 41	99.18 106	99.36 2	88.45 215	90.79 210	96.90 204	83.31 176	98.75 179	84.11 284	90.69 255	96.61 251

thres100view900		93.34 164	92.15 178	96.90 80	97.62 121	94.84 41	99.06 131	99.36 2	87.96 236	90.47 220	96.78 212	83.29 178	98.75 179	84.11 284	90.69 255	97.12 233

thres600view7		93.18 169	92.00 181	96.75 87	97.62 121	94.92 36	99.07 128	99.36 2	87.96 236	90.47 220	96.78 212	83.29 178	98.71 184	82.93 300	90.47 259	96.61 251

WTY-MVS		95.97 69	95.11 98	98.54 13	97.62 121	96.65 9	99.44 73	98.74 15	92.25 107	95.21 131	98.46 131	86.56 124	99.46 131	95.00 139	92.69 215	99.50 87

balanced_conf03		96.83 34	96.51 44	97.81 36	97.60 124	95.15 34	98.40 213	96.77 224	93.00 88	98.69 36	96.19 233	89.75 63	98.76 178	98.45 51	99.72 32	99.51 85

fmvsm_l_conf0.5_n_a		97.70 13	97.80 11	97.42 51	97.59 125	92.91 93	99.86 6	98.04 52	96.70 15	99.58 3	99.26 24	90.90 41	99.94 35	99.57 13	98.66 106	99.40 96

Anonymous20240529		87.66 287	85.58 300	93.92 229	97.59 125	85.01 303	98.13 239	97.13 197	66.69 425	88.47 242	96.01 240	55.09 394	99.51 123	87.00 243	84.12 296	97.23 232

HyFIR lowres test		93.68 152	93.29 151	94.87 188	97.57 127	88.04 225	98.18 235	98.47 26	87.57 249	91.24 206	95.05 262	85.49 145	97.46 264	93.22 174	92.82 212	99.10 126

sasdasda		95.02 107	93.96 128	98.20 21	97.53 128	95.92 17	98.71 167	96.19 267	91.78 115	95.86 117	98.49 125	79.53 236	99.03 163	96.12 107	91.42 248	99.66 64

canonicalmvs		95.02 107	93.96 128	98.20 21	97.53 128	95.92 17	98.71 167	96.19 267	91.78 115	95.86 117	98.49 125	79.53 236	99.03 163	96.12 107	91.42 248	99.66 64

fmvsm_l_conf0.5_n		97.65 14	97.72 12	97.41 52	97.51 130	92.78 96	99.85 9	98.05 50	96.78 13	99.60 2	99.23 29	90.42 52	99.92 43	99.55 14	98.50 114	99.55 80

MGCFI-Net		94.89 109	93.84 135	98.06 29	97.49 131	95.55 21	98.64 178	96.10 275	91.60 120	95.75 121	98.46 131	79.31 240	98.98 167	95.95 114	91.24 252	99.65 68

ETVMVS		94.50 128	93.90 133	96.31 120	97.48 132	92.98 89	99.07 128	97.86 65	88.09 231	94.40 146	96.90 204	88.35 81	97.28 273	90.72 204	92.25 227	98.66 173

myMVS_eth3d28		95.74 85	95.34 88	96.92 79	97.41 133	93.58 71	99.28 96	97.70 96	90.97 136	93.91 158	97.25 180	90.59 48	98.75 179	96.85 90	94.14 198	98.44 182

CHOSEN 1792x2688		94.35 131	93.82 136	95.95 141	97.40 134	88.74 211	98.41 210	98.27 33	92.18 109	91.43 201	96.40 226	78.88 242	99.81 88	93.59 166	97.81 130	99.30 107

fmvsm_l_conf0.5_n_3		97.12 25	96.89 28	97.79 39	97.39 135	93.84 68	99.87 5	97.70 96	97.34 6	99.39 8	99.20 34	82.86 187	99.94 35	99.21 24	99.07 80	99.58 79

SteuartSystems-ACMMP		97.25 19	97.34 21	97.01 70	97.38 136	91.46 126	99.75 30	97.66 108	94.14 58	98.13 54	99.26 24	92.16 32	99.66 107	97.91 65	99.64 42	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n		96.19 60	96.49 45	95.30 172	97.37 137	89.16 190	99.86 6	98.47 26	95.68 30	98.87 28	99.15 47	82.44 204	99.92 43	99.14 27	97.43 143	96.83 244

testing3-2		95.17 102	94.78 105	96.33 119	97.35 138	92.35 106	99.85 9	98.43 28	90.60 147	92.84 178	97.00 198	90.89 42	98.89 170	95.95 114	90.12 261	97.76 213

alignmvs		95.77 81	95.00 102	98.06 29	97.35 138	95.68 20	99.71 34	97.50 150	91.50 122	96.16 110	98.61 116	86.28 131	99.00 165	96.19 104	91.74 236	99.51 85

PS-MVSNAJ		96.87 33	96.40 49	98.29 19	97.35 138	97.29 5	99.03 134	97.11 199	95.83 26	98.97 25	99.14 50	82.48 200	99.60 116	98.60 42	99.08 78	98.00 209

testing222		94.48 129	94.00 124	95.95 141	97.30 141	92.27 108	98.82 154	97.92 61	89.20 191	94.82 137	97.26 178	87.13 106	97.32 272	91.95 188	91.56 240	98.25 197

EPNet_dtu		92.28 191	92.15 178	92.70 257	97.29 142	84.84 306	98.64 178	97.82 72	92.91 92	93.02 174	97.02 197	85.48 147	95.70 355	72.25 380	94.89 190	97.55 222
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVSTER		92.71 179	92.32 172	93.86 231	97.29 142	92.95 92	99.01 137	96.59 235	90.09 166	85.51 269	94.00 276	94.61 15	96.56 301	90.77 203	83.03 307	92.08 310

MVSMamba_PlusPlus		95.73 86	95.15 95	97.44 48	97.28 144	94.35 59	98.26 228	96.75 225	83.09 332	97.84 66	95.97 241	89.59 65	98.48 196	97.86 66	99.73 31	99.49 88

fmvsm_s_conf0.5_n_3		96.58 47	96.55 43	96.66 96	97.23 145	92.59 103	99.81 17	97.82 72	97.35 5	99.42 5	99.16 43	80.27 229	99.93 40	99.26 19	98.60 109	97.45 224

EPMVS		92.59 184	91.59 193	95.59 162	97.22 146	90.03 172	91.78 397	98.04 52	90.42 156	91.66 195	90.65 352	86.49 128	97.46 264	81.78 311	96.31 167	99.28 109

testing11		95.33 97	94.98 103	96.37 115	97.20 147	92.31 107	99.29 93	97.68 102	90.59 148	94.43 144	97.20 184	90.79 46	98.60 188	95.25 132	92.38 221	98.18 204

testing99		94.88 111	94.45 110	96.17 128	97.20 147	91.91 114	99.20 103	97.66 108	89.95 170	93.68 163	97.06 194	90.28 56	98.50 191	93.52 167	91.54 242	98.12 206

fmvsm_s_conf0.5_n_2		95.85 76	95.83 71	95.91 143	97.19 149	91.79 116	99.78 24	97.65 115	97.23 7	99.22 17	99.06 64	75.93 262	99.90 53	99.30 17	97.09 152	96.02 268

testing91		94.88 111	94.44 111	96.21 124	97.19 149	91.90 115	99.23 101	97.66 108	89.91 171	93.66 164	97.05 196	90.21 57	98.50 191	93.52 167	91.53 245	98.25 197

test_fmvs1		92.35 188	92.94 161	90.57 303	97.19 149	75.43 397	99.55 55	94.97 351	95.20 38	96.82 93	97.57 165	59.59 377	99.84 78	97.30 77	98.29 124	96.46 260

tpmvs		89.16 254	87.76 267	93.35 240	97.19 149	84.75 308	90.58 412	97.36 174	81.99 355	84.56 275	89.31 382	83.98 168	98.17 213	74.85 360	90.00 263	97.12 233

DeepC-MVS	91.02 4	94.56 127	93.92 131	96.46 107	97.16 153	90.76 146	98.39 217	97.11 199	93.92 61	88.66 240	98.33 134	78.14 253	99.85 76	95.02 137	98.57 111	98.78 159
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		94.67 122	94.11 120	96.34 117	97.14 154	91.10 135	99.32 92	97.43 164	92.10 112	91.53 200	96.38 229	83.29 178	99.68 105	93.42 172	96.37 165	98.25 197

SymmetryMVS		95.49 91	95.27 91	96.17 128	97.13 155	90.37 155	99.14 118	98.59 23	94.92 41	96.30 107	97.98 146	85.33 151	99.23 151	94.35 152	93.67 205	98.92 144

h-mvs33		92.47 187	91.95 184	94.05 224	97.13 155	85.01 303	98.36 220	98.08 47	93.85 67	96.27 108	96.73 215	83.19 181	99.43 135	95.81 116	68.09 396	97.70 216

miper_enhance_ethall		90.33 234	89.70 227	92.22 264	97.12 157	88.93 204	98.35 221	95.96 286	88.60 210	83.14 291	92.33 311	87.38 98	96.18 330	86.49 252	77.89 332	91.55 327

xiu_mvs_v2_base		96.66 41	96.17 61	98.11 28	97.11 158	96.96 6	99.01 137	97.04 206	95.51 34	98.86 29	99.11 59	82.19 208	99.36 143	98.59 44	98.14 125	98.00 209

mamv4		91.41 207	93.57 142	84.91 385	97.11 158	58.11 432	95.68 355	95.93 293	82.09 354	89.78 230	95.71 248	90.09 59	98.24 207	97.26 78	98.50 114	98.38 187

VDD-MVS		91.24 214	90.18 221	94.45 207	97.08 160	85.84 287	98.40 213	96.10 275	86.99 258	93.36 168	98.16 142	54.27 398	99.20 152	96.59 97	90.63 258	98.31 195

fmvsm_s_conf0.5_n_4		96.17 61	96.49 45	95.21 175	97.06 161	89.26 188	99.76 28	98.07 48	95.99 24	99.35 10	99.22 31	82.19 208	99.89 60	99.06 30	97.68 135	96.49 258

UGNet		91.91 200	90.85 208	95.10 179	97.06 161	88.69 212	98.01 251	98.24 36	92.41 103	92.39 186	93.61 288	60.52 374	99.68 105	88.14 233	97.25 146	96.92 242
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		92.61 183	91.28 199	96.58 101	97.05 163	94.63 51	97.72 271	96.20 265	89.82 173	88.56 241	96.85 208	86.85 113	97.82 237	88.42 229	80.10 322	97.30 228

CANet_DTU		94.31 132	93.35 148	97.20 63	97.03 164	94.71 48	98.62 181	95.54 326	95.61 32	97.21 79	98.47 129	71.88 300	99.84 78	88.38 230	97.46 142	97.04 238

WBMVS		91.35 210	90.49 217	93.94 228	96.97 165	93.40 78	99.27 98	96.71 226	87.40 253	83.10 292	91.76 324	92.38 29	96.23 328	88.95 227	77.89 332	92.17 306

UBG		95.73 86	95.41 86	96.69 93	96.97 165	93.23 80	99.13 122	97.79 80	91.28 129	94.38 148	96.78 212	92.37 30	98.56 190	96.17 105	93.84 202	98.26 196

MSDG		88.29 276	86.37 288	94.04 225	96.90 167	86.15 275	96.52 323	94.36 373	77.89 385	79.22 351	96.95 201	69.72 315	99.59 117	73.20 374	92.58 218	96.37 263

BH-w/o		92.32 189	91.79 189	93.91 230	96.85 168	86.18 273	99.11 125	95.74 314	88.13 229	84.81 273	97.00 198	77.26 258	97.91 229	89.16 225	98.03 126	97.64 217

AllTest		84.97 328	83.12 334	90.52 306	96.82 169	78.84 373	95.89 345	92.17 400	77.96 383	75.94 372	95.50 252	55.48 390	99.18 153	71.15 381	87.14 271	93.55 284

TestCases				90.52 306	96.82 169	78.84 373		92.17 400	77.96 383	75.94 372	95.50 252	55.48 390	99.18 153	71.15 381	87.14 271	93.55 284

SDMVSNet		91.09 215	89.91 224	94.65 198	96.80 171	90.54 153	97.78 264	97.81 76	88.34 222	85.73 265	95.26 259	66.44 344	98.26 205	94.25 155	86.75 274	95.14 274

sd_testset		89.23 253	88.05 266	92.74 256	96.80 171	85.33 296	95.85 350	97.03 208	88.34 222	85.73 265	95.26 259	61.12 372	97.76 246	85.61 263	86.75 274	95.14 274

PMMVS		93.62 155	93.90 133	92.79 253	96.79 173	81.40 349	98.85 151	96.81 220	91.25 130	96.82 93	98.15 143	77.02 259	98.13 215	93.15 176	96.30 168	98.83 153

BH-RMVSNet		91.25 213	89.99 223	95.03 184	96.75 174	88.55 215	98.65 176	94.95 352	87.74 244	87.74 247	97.80 150	68.27 326	98.14 214	80.53 321	97.49 141	98.41 184

MVS_Test		93.67 153	92.67 166	96.69 93	96.72 175	92.66 98	97.22 298	96.03 281	87.69 247	95.12 134	94.03 274	81.55 215	98.28 204	89.17 224	96.46 162	99.14 120

COLMAP_ROB	82.69 18	84.54 334	82.82 336	89.70 329	96.72 175	78.85 372	95.89 345	92.83 393	71.55 408	77.54 366	95.89 245	59.40 378	99.14 159	67.26 400	88.26 267	91.11 345
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
mvs_anonymous		92.50 186	91.65 192	95.06 181	96.60 177	89.64 182	97.06 304	96.44 247	86.64 270	84.14 280	93.93 279	82.49 199	96.17 332	91.47 192	96.08 176	99.35 102

UWE-MVS		93.18 169	93.40 147	92.50 261	96.56 178	83.55 323	98.09 247	97.84 67	89.50 185	91.72 193	96.23 232	91.08 37	96.70 295	86.28 254	93.33 207	97.26 230

ETV-MVS		96.00 66	96.00 66	96.00 138	96.56 178	91.05 138	99.63 48	96.61 233	93.26 83	97.39 74	98.30 136	86.62 121	98.13 215	98.07 62	97.57 137	98.82 154

GG-mvs-BLEND				96.98 75	96.53 180	94.81 44	87.20 417	97.74 87		93.91 158	96.40 226	96.56 2	96.94 286	95.08 135	98.95 90	99.20 116

FMVSNet3		88.81 265	87.08 279	93.99 227	96.52 181	94.59 52	98.08 248	96.20 265	85.85 283	82.12 310	91.60 327	74.05 279	95.40 364	79.04 328	80.24 319	91.99 313

fmvsm_s_conf0.5_n_a		95.97 69	96.19 56	95.31 171	96.51 182	89.01 198	99.81 17	98.39 29	95.46 35	99.19 19	99.16 43	81.44 220	99.91 49	98.83 37	96.97 153	97.01 240

BH-untuned		91.46 206	90.84 209	93.33 241	96.51 182	84.83 307	98.84 153	95.50 328	86.44 278	83.50 284	96.70 217	75.49 267	97.77 241	86.78 249	97.81 130	97.40 225

FE-MVS		91.38 209	90.16 222	95.05 183	96.46 184	87.53 238	89.69 414	97.84 67	82.97 335	92.18 188	92.00 318	84.07 167	98.93 169	80.71 318	95.52 184	98.68 169

sss		94.85 114	93.94 130	97.58 44	96.43 185	94.09 64	98.93 144	99.16 8	89.50 185	95.27 130	97.85 147	81.50 217	99.65 111	92.79 181	94.02 200	98.99 133

fmvsm_s_conf0.5_n_5		96.46 52	96.23 55	97.15 66	96.42 186	92.80 95	99.83 12	97.39 169	94.50 47	98.71 34	99.13 52	82.52 197	99.90 53	99.24 23	98.38 119	98.74 164

mvsmamba		94.27 133	93.91 132	95.35 168	96.42 186	88.61 213	97.77 266	96.38 252	91.17 133	94.05 154	95.27 258	78.41 251	97.96 228	97.36 76	98.40 118	99.48 89

test2506		94.80 115	94.21 116	96.58 101	96.41 188	92.18 110	98.01 251	98.96 11	90.82 140	93.46 167	97.28 176	85.92 137	98.45 197	89.82 212	97.19 148	99.12 123

ECVR-MVS		92.29 190	91.33 198	95.15 178	96.41 188	87.84 228	98.10 244	94.84 355	90.82 140	91.42 203	97.28 176	65.61 349	98.49 195	90.33 206	97.19 148	99.12 123

ET-MVSNet_ETH3D		92.56 185	91.45 196	95.88 144	96.39 190	94.13 63	99.46 70	96.97 214	92.18 109	66.94 417	98.29 137	94.65 14	94.28 384	94.34 153	83.82 300	99.24 112

dp		90.16 241	88.83 248	94.14 219	96.38 191	86.42 263	91.57 401	97.06 205	84.76 304	88.81 238	90.19 370	84.29 164	97.43 267	75.05 357	91.35 251	98.56 176

EIA-MVS		95.11 104	95.27 91	94.64 200	96.34 192	86.51 260	99.59 51	96.62 232	92.51 98	94.08 153	98.64 112	86.05 136	98.24 207	95.07 136	98.50 114	99.18 117

test_vis1_n_1920		93.08 174	93.42 146	92.04 271	96.31 193	79.36 368	99.83 12	96.06 280	96.72 14	98.53 43	98.10 144	58.57 379	99.91 49	97.86 66	98.79 101	96.85 243

TR-MVS		90.77 223	89.44 232	94.76 192	96.31 193	88.02 226	97.92 255	95.96 286	85.52 289	88.22 244	97.23 182	66.80 340	98.09 218	84.58 276	92.38 221	98.17 205

UA-Net		93.30 165	92.62 168	95.34 169	96.27 195	88.53 217	95.88 347	96.97 214	90.90 137	95.37 129	97.07 193	82.38 205	99.10 161	83.91 288	94.86 191	98.38 187

tpmrst		92.78 178	92.16 177	94.65 198	96.27 195	87.45 241	91.83 396	97.10 202	89.10 196	94.68 141	90.69 349	88.22 83	97.73 249	89.78 213	91.80 235	98.77 161

hse-mvs2		91.67 203	91.51 195	92.15 268	96.22 197	82.61 339	97.74 270	97.53 141	93.85 67	96.27 108	96.15 234	83.19 181	97.44 266	95.81 116	66.86 403	96.40 262

AUN-MVS		90.17 240	89.50 230	92.19 266	96.21 198	82.67 337	97.76 269	97.53 141	88.05 232	91.67 194	96.15 234	83.10 183	97.47 263	88.11 234	66.91 402	96.43 261

ADS-MVSNet2		87.62 288	86.88 282	89.86 323	96.21 198	79.14 371	87.15 418	92.99 390	83.01 333	89.91 228	87.27 396	78.87 243	92.80 400	74.20 365	92.27 225	97.64 217

ADS-MVSNet		88.99 256	87.30 275	94.07 222	96.21 198	87.56 237	87.15 418	96.78 223	83.01 333	89.91 228	87.27 396	78.87 243	97.01 283	74.20 365	92.27 225	97.64 217

fmvsm_s_conf0.5_n_7		95.87 75	96.25 54	94.72 196	96.19 201	87.74 230	99.66 43	97.94 59	95.78 27	98.44 45	99.23 29	81.26 223	99.90 53	99.17 26	98.57 111	96.52 257

PatchmatchNet		92.05 199	91.04 204	95.06 181	96.17 202	89.04 194	91.26 405	97.26 179	89.56 183	90.64 214	90.56 358	88.35 81	97.11 278	79.53 324	96.07 177	99.03 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test1111		92.12 195	91.19 201	94.94 186	96.15 203	87.36 244	98.12 241	94.84 355	90.85 139	90.97 208	97.26 178	65.60 350	98.37 199	89.74 215	97.14 151	99.07 130

gg-mvs-nofinetune		90.00 244	87.71 269	96.89 84	96.15 203	94.69 49	85.15 424	97.74 87	68.32 420	92.97 176	60.16 437	96.10 4	96.84 289	93.89 159	98.87 94	99.14 120

MDTV_nov1_ep13			90.47 219		96.14 205	88.55 215	91.34 404	97.51 147	89.58 181	92.24 187	90.50 362	86.99 112	97.61 256	77.64 339	92.34 223

IS-MVSNet		93.00 176	92.51 170	94.49 204	96.14 205	87.36 244	98.31 225	95.70 316	88.58 211	90.17 224	97.50 167	83.02 185	97.22 274	87.06 241	96.07 177	98.90 146

Vis-MVSNet (Re-imp)		93.26 168	93.00 160	94.06 223	96.14 205	86.71 258	98.68 172	96.70 227	88.30 224	89.71 233	97.64 161	85.43 148	96.39 312	88.06 235	96.32 166	99.08 128

thisisatest0515		94.75 117	94.19 117	96.43 109	96.13 208	92.64 101	99.47 66	97.60 126	87.55 250	93.17 170	97.59 163	94.71 12	98.42 198	88.28 231	93.20 208	98.24 200

RRT-MVS		93.39 160	92.64 167	95.64 156	96.11 209	88.75 210	97.40 286	95.77 312	89.46 187	92.70 181	95.42 255	72.98 289	98.81 174	96.91 88	96.97 153	99.37 99

FA-MVS(test-final)		92.22 194	91.08 203	95.64 156	96.05 210	88.98 199	91.60 400	97.25 180	86.99 258	91.84 190	92.12 312	83.03 184	99.00 165	86.91 246	93.91 201	98.93 142

fmvsm_s_conf0.5_n_6		96.78 37	96.64 41	97.20 63	96.03 211	93.20 82	99.82 16	97.68 102	95.20 38	99.61 1	99.11 59	84.52 161	99.90 53	99.04 31	98.77 102	98.50 179

test_fmvsmconf_n		96.78 37	96.84 31	96.61 98	95.99 212	90.25 158	99.90 3	98.13 45	96.68 16	98.42 46	98.92 86	85.34 150	99.88 62	99.12 28	99.08 78	99.70 55

ab-mvs		91.05 218	89.17 238	96.69 93	95.96 213	91.72 120	92.62 390	97.23 184	85.61 288	89.74 231	93.89 281	68.55 323	99.42 136	91.09 195	87.84 269	98.92 144

Fast-Effi-MVS+		91.72 202	90.79 212	94.49 204	95.89 214	87.40 243	99.54 60	95.70 316	85.01 300	89.28 236	95.68 249	77.75 255	97.57 261	83.22 295	95.06 189	98.51 178

kuosan		84.40 338	83.34 332	87.60 359	95.87 215	79.21 369	92.39 392	96.87 217	76.12 394	73.79 385	93.98 277	81.51 216	90.63 416	64.13 409	75.42 347	92.95 287

EPP-MVSNet		93.75 149	93.67 140	94.01 226	95.86 216	85.70 289	98.67 174	97.66 108	84.46 309	91.36 204	97.18 187	91.16 34	97.79 239	92.93 178	93.75 203	98.53 177

mvsany_test1		94.57 126	95.09 99	92.98 247	95.84 217	82.07 343	98.76 163	95.24 344	92.87 94	96.45 103	98.71 107	84.81 158	99.15 155	97.68 70	95.49 185	97.73 215

Effi-MVS+		93.87 145	93.15 154	96.02 136	95.79 218	90.76 146	96.70 320	95.78 310	86.98 261	95.71 122	97.17 188	79.58 234	98.01 226	94.57 150	96.09 175	99.31 106

tpm cat1		88.89 259	87.27 276	93.76 234	95.79 218	85.32 297	90.76 410	97.09 203	76.14 393	85.72 267	88.59 385	82.92 186	98.04 224	76.96 343	91.43 247	97.90 212

thisisatest0530		94.00 139	93.52 143	95.43 165	95.76 220	90.02 173	98.99 139	97.60 126	86.58 271	91.74 192	97.36 175	94.78 11	98.34 200	86.37 253	92.48 219	97.94 211

3Dnovator+	87.72 8	93.43 158	91.84 187	98.17 23	95.73 221	95.08 35	98.92 146	97.04 206	91.42 126	81.48 326	97.60 162	74.60 271	99.79 94	90.84 200	98.97 87	99.64 69

MVS		93.92 142	92.28 174	98.83 7	95.69 222	96.82 8	96.22 336	98.17 39	84.89 302	84.34 279	98.61 116	79.32 239	99.83 82	93.88 160	99.43 61	99.86 29

cascas		90.93 221	89.33 235	95.76 149	95.69 222	93.03 88	98.99 139	96.59 235	80.49 370	86.79 260	94.45 269	65.23 353	98.60 188	93.52 167	92.18 228	95.66 273

QAPM		91.41 207	89.49 231	97.17 65	95.66 224	93.42 77	98.60 187	97.51 147	80.92 368	81.39 327	97.41 173	72.89 292	99.87 66	82.33 305	98.68 104	98.21 202

fmvsm_s_conf0.1_n_2		95.24 101	95.04 101	95.83 146	95.60 225	91.71 121	99.65 45	96.18 269	96.99 11	98.79 32	98.91 87	73.91 281	99.87 66	99.00 33	96.30 168	95.91 270

VortexMVS		90.18 239	89.28 236	92.89 251	95.58 226	90.94 143	97.82 261	95.94 289	90.90 137	82.11 314	91.48 330	78.75 247	96.08 336	91.99 187	78.97 326	91.65 318

tttt0517		93.30 165	93.01 158	94.17 218	95.57 227	86.47 262	98.51 198	97.60 126	85.99 282	90.55 217	97.19 186	94.80 10	98.31 201	85.06 268	91.86 233	97.74 214

1112_ss		92.71 179	91.55 194	96.20 125	95.56 228	91.12 133	98.48 203	94.69 362	88.29 225	86.89 258	98.50 122	87.02 110	98.66 186	84.75 272	89.77 264	98.81 155

diffmvs		94.59 125	94.19 117	95.81 147	95.54 229	90.69 148	98.70 170	95.68 318	91.61 118	95.96 112	97.81 149	80.11 230	98.06 220	96.52 99	95.76 180	98.67 170
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		88.59 272	88.61 253	88.51 351	95.53 230	72.68 410	96.85 312	88.43 430	88.45 215	73.14 391	90.63 353	75.82 263	94.38 383	92.95 177	95.71 182	98.48 181

Test_1112_low_res		92.27 192	90.97 205	96.18 126	95.53 230	91.10 135	98.47 205	94.66 363	88.28 226	86.83 259	93.50 292	87.00 111	98.65 187	84.69 273	89.74 265	98.80 156

PCF-MVS	89.78 5	91.26 211	89.63 228	96.16 131	95.44 232	91.58 125	95.29 359	96.10 275	85.07 297	82.75 294	97.45 171	78.28 252	99.78 97	80.60 320	95.65 183	97.12 233
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EC-MVSNet		95.09 105	95.17 94	94.84 190	95.42 233	88.17 221	99.48 64	95.92 295	91.47 123	97.34 76	98.36 133	82.77 190	97.41 268	97.24 79	98.58 110	98.94 141

3Dnovator	87.35 11	93.17 171	91.77 190	97.37 55	95.41 234	93.07 86	98.82 154	97.85 66	91.53 121	82.56 300	97.58 164	71.97 299	99.82 85	91.01 197	99.23 73	99.22 115

IB-MVS	89.43 6	92.12 195	90.83 211	95.98 140	95.40 235	90.78 145	99.81 17	98.06 49	91.23 132	85.63 268	93.66 287	90.63 47	98.78 175	91.22 194	71.85 385	98.36 192
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		93.86 146	93.74 138	94.22 216	95.39 236	86.08 277	99.73 31	96.07 279	96.38 22	97.19 81	97.78 152	65.46 352	99.86 72	96.71 91	98.92 91	96.73 248

GDP-MVS		96.05 65	95.63 84	97.31 56	95.37 237	94.65 50	99.36 87	96.42 248	92.14 111	97.07 83	98.53 118	93.33 19	98.50 191	91.76 191	96.66 161	98.78 159

miper_ehance_all_eth		88.94 258	88.12 264	91.40 283	95.32 238	86.93 254	97.85 260	95.55 325	84.19 312	81.97 317	91.50 329	84.16 165	95.91 347	84.69 273	77.89 332	91.36 335

1314		93.44 157	91.98 182	97.84 34	95.24 239	94.38 57	96.22 336	97.92 61	90.18 162	82.28 307	97.71 157	77.63 256	99.80 90	91.94 189	98.67 105	99.34 104

XVG-OURS		90.83 222	90.49 217	91.86 273	95.23 240	81.25 353	95.79 352	95.92 295	88.96 199	90.02 227	98.03 145	71.60 304	99.35 146	91.06 196	87.78 270	94.98 277

guyue		94.21 135	93.72 139	95.66 155	95.22 241	90.17 163	98.74 164	96.85 218	93.67 72	93.01 175	96.72 216	78.83 245	98.06 220	96.04 111	94.44 194	98.77 161

casdiffmvs_mvg		94.00 139	93.33 149	96.03 135	95.22 241	90.90 144	99.09 126	95.99 282	90.58 149	91.55 199	97.37 174	79.91 232	98.06 220	95.01 138	95.22 187	99.13 122
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		93.82 147	93.26 152	95.49 163	95.21 243	90.25 158	99.15 115	97.54 140	89.18 193	91.79 191	94.87 264	89.13 68	97.63 254	86.21 255	96.29 170	98.60 175

xiu_mvs_v1_base_debu		94.73 118	93.98 125	96.99 72	95.19 244	95.24 27	98.62 181	96.50 243	92.99 89	97.52 70	98.83 95	72.37 295	99.15 155	97.03 82	96.74 158	96.58 253

xiu_mvs_v1_base		94.73 118	93.98 125	96.99 72	95.19 244	95.24 27	98.62 181	96.50 243	92.99 89	97.52 70	98.83 95	72.37 295	99.15 155	97.03 82	96.74 158	96.58 253

xiu_mvs_v1_base_debi		94.73 118	93.98 125	96.99 72	95.19 244	95.24 27	98.62 181	96.50 243	92.99 89	97.52 70	98.83 95	72.37 295	99.15 155	97.03 82	96.74 158	96.58 253

XVG-OURS-SEG-HR		90.95 220	90.66 215	91.83 274	95.18 247	81.14 356	95.92 344	95.92 295	88.40 219	90.33 223	97.85 147	70.66 311	99.38 141	92.83 180	88.83 266	94.98 277

Effi-MVS+-dtu		89.97 245	90.68 214	87.81 357	95.15 248	71.98 412	97.87 259	95.40 335	91.92 113	87.57 248	91.44 331	74.27 277	96.84 289	89.45 217	93.10 210	94.60 280

Syy-MVS		84.10 343	84.53 320	82.83 397	95.14 249	65.71 424	97.68 274	96.66 229	86.52 274	82.63 297	96.84 209	68.15 327	89.89 420	45.62 435	91.54 242	92.87 288

myMVS_eth3d		88.68 271	89.07 240	87.50 361	95.14 249	79.74 366	97.68 274	96.66 229	86.52 274	82.63 297	96.84 209	85.22 153	89.89 420	69.43 390	91.54 242	92.87 288

UWE-MVS-28		90.99 219	91.93 185	88.15 353	95.12 251	77.87 385	97.18 301	97.79 80	88.72 207	88.69 239	96.52 221	86.54 125	90.75 415	84.64 275	92.16 231	95.83 271

Vis-MVSNet		92.64 181	91.85 186	95.03 184	95.12 251	88.23 220	98.48 203	96.81 220	91.61 118	92.16 189	97.22 183	71.58 305	98.00 227	85.85 262	97.81 130	98.88 147
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GBi-Net		86.67 300	84.96 308	91.80 276	95.11 253	88.81 207	96.77 314	95.25 341	82.94 336	82.12 310	90.25 365	62.89 362	94.97 371	79.04 328	80.24 319	91.62 321

test1		86.67 300	84.96 308	91.80 276	95.11 253	88.81 207	96.77 314	95.25 341	82.94 336	82.12 310	90.25 365	62.89 362	94.97 371	79.04 328	80.24 319	91.62 321

FMVSNet2		86.90 295	84.79 314	93.24 242	95.11 253	92.54 104	97.67 276	95.86 307	82.94 336	80.55 333	91.17 338	62.89 362	95.29 366	77.23 340	79.71 325	91.90 314

GeoE		90.60 231	89.56 229	93.72 236	95.10 256	85.43 293	99.41 80	94.94 353	83.96 317	87.21 254	96.83 211	74.37 275	97.05 282	80.50 322	93.73 204	98.67 170

baseline		93.91 143	93.30 150	95.72 151	95.10 256	90.07 168	97.48 285	95.91 300	91.03 134	93.54 166	97.68 158	79.58 234	98.02 225	94.27 154	95.14 188	99.08 128

casdiffmvs		93.98 141	93.43 145	95.61 161	95.07 258	89.86 177	98.80 157	95.84 309	90.98 135	92.74 180	97.66 160	79.71 233	98.10 217	94.72 146	95.37 186	98.87 149
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 45	96.36 51	97.29 57	95.05 259	94.72 47	99.44 73	97.45 158	92.71 95	96.41 105	98.50 122	94.11 16	98.50 191	95.61 123	97.97 127	98.66 173

MVSFormer		94.71 121	94.08 122	96.61 98	95.05 259	94.87 39	97.77 266	96.17 271	86.84 264	98.04 60	98.52 120	85.52 142	95.99 340	89.83 210	98.97 87	98.96 136

lupinMVS		96.32 56	95.94 67	97.44 48	95.05 259	94.87 39	99.86 6	96.50 243	93.82 69	98.04 60	98.77 98	85.52 142	98.09 218	96.98 85	98.97 87	99.37 99

CostFormer		92.89 177	92.48 171	94.12 220	94.99 262	85.89 284	92.89 386	97.00 212	86.98 261	95.00 136	90.78 345	90.05 60	97.51 262	92.92 179	91.73 237	98.96 136

c3_l		88.19 278	87.23 277	91.06 289	94.97 263	86.17 274	97.72 271	95.38 336	83.43 326	81.68 324	91.37 332	82.81 189	95.72 354	84.04 287	73.70 366	91.29 339

SCA		90.64 228	89.25 237	94.83 191	94.95 264	88.83 206	96.26 333	97.21 186	90.06 169	90.03 226	90.62 354	66.61 341	96.81 291	83.16 296	94.36 196	98.84 150

test-LLR		93.11 173	92.68 165	94.40 208	94.94 265	87.27 248	99.15 115	97.25 180	90.21 160	91.57 196	94.04 272	84.89 156	97.58 258	85.94 259	96.13 173	98.36 192

test-mter		93.27 167	92.89 162	94.40 208	94.94 265	87.27 248	99.15 115	97.25 180	88.95 200	91.57 196	94.04 272	88.03 89	97.58 258	85.94 259	96.13 173	98.36 192

cl____		87.82 280	86.79 284	90.89 295	94.88 267	85.43 293	97.81 262	95.24 344	82.91 340	80.71 332	91.22 336	81.97 212	95.84 349	81.34 313	75.06 350	91.40 334

DIV-MVS_self_test		87.82 280	86.81 283	90.87 296	94.87 268	85.39 295	97.81 262	95.22 349	82.92 339	80.76 331	91.31 335	81.99 210	95.81 351	81.36 312	75.04 351	91.42 333

KinetiMVS		93.07 175	91.98 182	96.34 117	94.84 269	91.78 117	98.73 166	97.18 191	91.25 130	94.01 156	97.09 192	71.02 308	98.86 171	86.77 250	96.89 156	98.37 191

tpm2		91.77 201	91.09 202	93.82 233	94.83 270	85.56 292	92.51 391	97.16 194	84.00 315	93.83 161	90.66 351	87.54 95	97.17 275	87.73 238	91.55 241	98.72 166

PVSNet_0	83.28 16	87.31 291	85.16 306	93.74 235	94.78 271	84.59 309	98.91 147	98.69 20	89.81 174	78.59 358	93.23 297	61.95 368	99.34 147	94.75 144	55.72 428	97.30 228

CDS-MVSNet		93.47 156	93.04 157	94.76 192	94.75 272	89.45 186	98.82 154	97.03 208	87.91 238	90.97 208	96.48 224	89.06 69	96.36 314	89.50 216	92.81 214	98.49 180
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gm-plane-assit					94.69 273	88.14 222			88.22 227		97.20 184		98.29 203	90.79 202

eth_miper_zixun_eth		87.76 282	87.00 281	90.06 317	94.67 274	82.65 338	97.02 307	95.37 337	84.19 312	81.86 322	91.58 328	81.47 218	95.90 348	83.24 294	73.61 367	91.61 324

testing3		87.75 283	88.22 262	86.36 372	94.66 275	77.41 387	99.52 61	97.95 58	86.05 281	81.12 328	96.69 218	86.18 134	89.31 424	61.65 417	90.12 261	92.35 299

RPSCF		85.33 323	85.55 301	84.67 388	94.63 276	62.28 427	93.73 376	93.76 381	74.38 401	85.23 272	97.06 194	64.09 356	98.31 201	80.98 314	86.08 282	93.41 286

miper_lstm_enhance		86.90 295	86.20 291	89.00 346	94.53 277	81.19 354	96.74 318	95.24 344	82.33 350	80.15 339	90.51 361	81.99 210	94.68 380	80.71 318	73.58 369	91.12 344

Patchmatch-test		86.25 309	84.06 326	92.82 252	94.42 278	82.88 334	82.88 433	94.23 375	71.58 407	79.39 349	90.62 354	89.00 71	96.42 311	63.03 413	91.37 250	99.16 118

VDDNet		90.08 243	88.54 257	94.69 197	94.41 279	87.68 232	98.21 233	96.40 249	76.21 392	93.33 169	97.75 154	54.93 396	98.77 176	94.71 147	90.96 253	97.61 221

fmvsm_s_conf0.1_n		95.56 90	95.68 79	95.20 176	94.35 280	89.10 192	99.50 62	97.67 107	94.76 44	98.68 37	99.03 68	81.13 224	99.86 72	98.63 41	97.36 145	96.63 250

test_fmvsmvis_n_1920		95.47 92	95.40 87	95.70 152	94.33 281	90.22 161	99.70 35	96.98 213	96.80 12	92.75 179	98.89 91	82.46 203	99.92 43	98.36 53	98.33 121	96.97 241

KD-MVS_2432*1600		82.98 349	80.52 358	90.38 310	94.32 282	88.98 199	92.87 387	95.87 305	80.46 371	73.79 385	87.49 393	82.76 192	93.29 394	70.56 385	46.53 439	88.87 392

miper_refine_blended		82.98 349	80.52 358	90.38 310	94.32 282	88.98 199	92.87 387	95.87 305	80.46 371	73.79 385	87.49 393	82.76 192	93.29 394	70.56 385	46.53 439	88.87 392

EI-MVSNet		89.87 246	89.38 234	91.36 285	94.32 282	85.87 285	97.61 281	96.59 235	85.10 295	85.51 269	97.10 190	81.30 222	96.56 301	83.85 290	83.03 307	91.64 319

CVMVSNet		90.30 235	90.91 207	88.46 352	94.32 282	73.58 405	97.61 281	97.59 130	90.16 165	88.43 243	97.10 190	76.83 260	92.86 397	82.64 302	93.54 206	98.93 142

WB-MVSnew		88.69 269	88.34 259	89.77 327	94.30 286	85.99 282	98.14 238	97.31 178	87.15 257	87.85 246	96.07 238	69.91 312	95.52 359	72.83 377	91.47 246	87.80 399

dongtai		81.36 358	80.61 356	83.62 394	94.25 287	73.32 406	95.15 361	96.81 220	73.56 404	69.79 403	92.81 305	81.00 225	86.80 431	52.08 432	70.06 392	90.75 356

test_fmvs1_n		91.07 216	91.41 197	90.06 317	94.10 288	74.31 401	99.18 106	94.84 355	94.81 42	96.37 106	97.46 170	50.86 411	99.82 85	97.14 81	97.90 128	96.04 267

IterMVS-LS		88.34 274	87.44 272	91.04 290	94.10 288	85.85 286	98.10 244	95.48 329	85.12 294	82.03 315	91.21 337	81.35 221	95.63 357	83.86 289	75.73 346	91.63 320
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAMVS		92.62 182	92.09 180	94.20 217	94.10 288	87.68 232	98.41 210	96.97 214	87.53 251	89.74 231	96.04 239	84.77 160	96.49 307	88.97 226	92.31 224	98.42 183

PAPM		96.35 54	95.94 67	97.58 44	94.10 288	95.25 26	98.93 144	98.17 39	94.26 53	93.94 157	98.72 104	89.68 64	97.88 233	96.36 101	99.29 69	99.62 74

CLD-MVS		91.06 217	90.71 213	92.10 269	94.05 292	86.10 276	99.55 55	96.29 260	94.16 56	84.70 274	97.17 188	69.62 317	97.82 237	94.74 145	86.08 282	92.39 295
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP-NCC					93.95 293		99.16 110		93.92 61	87.57 248

ACMP_Plane					93.95 293		99.16 110		93.92 61	87.57 248

HQP-MVS		91.50 204	91.23 200	92.29 263	93.95 293	86.39 265	99.16 110	96.37 253	93.92 61	87.57 248	96.67 219	73.34 284	97.77 241	93.82 163	86.29 277	92.72 290

AstraMVS		93.38 162	93.01 158	94.50 203	93.94 296	86.55 259	98.91 147	95.86 307	93.88 65	92.88 177	97.49 168	75.61 266	98.21 211	96.15 106	92.39 220	98.73 165

NP-MVS					93.94 296	86.22 271					96.67 219

plane_prior6					93.92 298	86.02 281						72.92 290

ACMP	87.39 10	88.71 268	88.24 261	90.12 316	93.91 299	81.06 357	98.50 199	95.67 319	89.43 188	80.37 336	95.55 251	65.67 347	97.83 236	90.55 205	84.51 291	91.47 329
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
plane_prior1					93.90 300

HQP_MVS		91.26 211	90.95 206	92.16 267	93.84 301	86.07 279	99.02 135	96.30 257	93.38 81	86.99 255	96.52 221	72.92 290	97.75 247	93.46 170	86.17 280	92.67 292

plane_prior7					93.84 301	85.73 288

dmvs_re		88.69 269	88.06 265	90.59 302	93.83 303	78.68 375	95.75 353	96.18 269	87.99 235	84.48 278	96.32 230	67.52 334	96.94 286	84.98 270	85.49 286	96.14 265

MVS-HIRNet		79.01 370	75.13 383	90.66 301	93.82 304	81.69 346	85.16 423	93.75 382	54.54 433	74.17 383	59.15 439	57.46 383	96.58 300	63.74 410	94.38 195	93.72 283

FMVSNet5		82.29 352	80.54 357	87.52 360	93.79 305	84.01 317	93.73 376	92.47 397	76.92 388	74.27 382	86.15 404	63.69 360	89.24 425	69.07 392	74.79 354	89.29 385

ACMH+	83.78 15	84.21 339	82.56 345	89.15 343	93.73 306	79.16 370	96.43 326	94.28 374	81.09 365	74.00 384	94.03 274	54.58 397	97.67 250	76.10 351	78.81 328	90.63 361

ACMM	86.95 13	88.77 266	88.22 262	90.43 308	93.61 307	81.34 351	98.50 199	95.92 295	87.88 239	83.85 283	95.20 261	67.20 337	97.89 231	86.90 247	84.90 289	92.06 311
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS	85.28 14	90.75 224	88.84 247	96.48 106	93.58 308	93.51 75	98.80 157	97.41 166	82.59 343	78.62 356	97.49 168	68.00 330	99.82 85	84.52 278	98.55 113	96.11 266

IterMVS		85.81 316	84.67 317	89.22 340	93.51 309	83.67 322	96.32 330	94.80 358	85.09 296	78.69 354	90.17 371	66.57 343	93.17 396	79.48 326	77.42 339	90.81 351
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		88.83 263	87.38 274	93.16 244	93.47 310	86.24 269	84.97 426	94.20 376	88.92 203	90.76 212	86.88 400	84.43 162	94.82 376	70.64 384	92.17 229	98.41 184

RPMNet		85.07 327	81.88 346	94.64 200	93.47 310	86.24 269	84.97 426	97.21 186	64.85 427	90.76 212	78.80 428	80.95 226	99.27 150	53.76 429	92.17 229	98.41 184

IterMVS-SCA-FT		85.73 319	84.64 318	89.00 346	93.46 312	82.90 332	96.27 331	94.70 361	85.02 299	78.62 356	90.35 363	66.61 341	93.33 393	79.38 327	77.36 340	90.76 355

Fast-Effi-MVS+-dtu		88.84 261	88.59 255	89.58 332	93.44 313	78.18 379	98.65 176	94.62 364	88.46 214	84.12 281	95.37 257	68.91 320	96.52 304	82.06 308	91.70 238	94.06 281

Patchmtry		83.61 348	81.64 348	89.50 334	93.36 314	82.84 335	84.10 429	94.20 376	69.47 417	79.57 347	86.88 400	84.43 162	94.78 377	68.48 396	74.30 360	90.88 350

LPG-MVS_test		88.86 260	88.47 258	90.06 317	93.35 315	80.95 358	98.22 231	95.94 289	87.73 245	83.17 289	96.11 236	66.28 345	97.77 241	90.19 208	85.19 287	91.46 330

LGP-MVS_train				90.06 317	93.35 315	80.95 358		95.94 289	87.73 245	83.17 289	96.11 236	66.28 345	97.77 241	90.19 208	85.19 287	91.46 330

JIA-IIPM		85.97 312	84.85 312	89.33 339	93.23 317	73.68 404	85.05 425	97.13 197	69.62 416	91.56 198	68.03 435	88.03 89	96.96 284	77.89 338	93.12 209	97.34 227

ACMH	83.09 17	84.60 332	82.61 343	90.57 303	93.18 318	82.94 330	96.27 331	94.92 354	81.01 366	72.61 397	93.61 288	56.54 385	97.79 239	74.31 363	81.07 317	90.99 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PatchT		85.44 322	83.19 333	92.22 264	93.13 319	83.00 329	83.80 432	96.37 253	70.62 410	90.55 217	79.63 427	84.81 158	94.87 374	58.18 425	91.59 239	98.79 157

Elysia		90.62 229	88.95 243	95.64 156	93.08 320	91.94 112	97.65 278	96.39 250	84.72 305	90.59 215	95.95 242	62.22 365	98.23 209	83.69 291	96.23 171	96.74 246

StellarMVS		90.62 229	88.95 243	95.64 156	93.08 320	91.94 112	97.65 278	96.39 250	84.72 305	90.59 215	95.95 242	62.22 365	98.23 209	83.69 291	96.23 171	96.74 246

baseline2		94.04 138	93.80 137	94.74 194	93.07 322	90.25 158	98.12 241	98.16 42	89.86 172	86.53 261	96.95 201	95.56 6	98.05 223	91.44 193	94.53 193	95.93 269

jason		95.40 96	94.86 104	97.03 69	92.91 323	94.23 60	99.70 35	96.30 257	93.56 77	96.73 98	98.52 120	81.46 219	97.91 229	96.08 110	98.47 117	98.96 136
jason: jason.
LTVRE_ROB	81.71 19	84.59 333	82.72 341	90.18 314	92.89 324	83.18 328	93.15 383	94.74 359	78.99 376	75.14 379	92.69 306	65.64 348	97.63 254	69.46 389	81.82 315	89.74 378
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		83.69 345	82.59 344	86.99 367	92.82 325	76.98 390	96.16 339	91.63 409	82.89 341	92.41 185	82.90 413	54.95 395	98.19 212	96.27 102	53.27 431	85.81 413

VPA-MVSNet		89.10 255	87.66 270	93.45 238	92.56 326	91.02 139	97.97 254	98.32 32	86.92 263	86.03 263	92.01 316	68.84 322	97.10 280	90.92 198	75.34 348	92.23 302

tpm		89.67 248	88.95 243	91.82 275	92.54 327	81.43 348	92.95 385	95.92 295	87.81 240	90.50 219	89.44 379	84.99 154	95.65 356	83.67 293	82.71 310	98.38 187

GA-MVS		90.10 242	88.69 251	94.33 211	92.44 328	87.97 227	99.08 127	96.26 261	89.65 177	86.92 257	93.11 300	68.09 328	96.96 284	82.54 304	90.15 260	98.05 207

test_fmvsmconf0.1_n		95.94 72	95.79 76	96.40 112	92.42 329	89.92 175	99.79 23	96.85 218	96.53 20	97.22 78	98.67 110	82.71 194	99.84 78	98.92 36	98.98 86	99.43 95

FIs		90.70 225	89.87 225	93.18 243	92.29 330	91.12 133	98.17 237	98.25 34	89.11 195	83.44 285	94.82 265	82.26 206	96.17 332	87.76 237	82.76 309	92.25 300

LuminaMVS		93.16 172	92.30 173	95.76 149	92.26 331	92.64 101	97.60 283	96.21 264	90.30 159	93.06 173	95.59 250	76.00 261	97.89 231	94.93 142	94.70 192	96.76 245

ITE_SJBPF				87.93 355	92.26 331	76.44 392		93.47 388	87.67 248	79.95 342	95.49 254	56.50 386	97.38 269	75.24 356	82.33 313	89.98 375

UniMVSNet (Re)		89.50 252	88.32 260	93.03 245	92.21 333	90.96 141	98.90 149	98.39 29	89.13 194	83.22 286	92.03 314	81.69 214	96.34 320	86.79 248	72.53 378	91.81 315

UniMVSNet_NR-MVSNet		89.60 249	88.55 256	92.75 255	92.17 334	90.07 168	98.74 164	98.15 43	88.37 220	83.21 287	93.98 277	82.86 187	95.93 344	86.95 244	72.47 379	92.25 300

TinyColmap		80.42 363	77.94 368	87.85 356	92.09 335	78.58 376	93.74 375	89.94 422	74.99 397	69.77 404	91.78 322	46.09 418	97.58 258	65.17 408	77.89 332	87.38 401

fmvsm_s_conf0.1_n_a		95.16 103	95.15 95	95.18 177	92.06 336	88.94 202	99.29 93	97.53 141	94.46 49	98.98 24	98.99 72	79.99 231	99.85 76	98.24 60	96.86 157	96.73 248

tt0805		86.50 305	84.79 314	91.63 281	91.97 337	81.49 347	96.49 325	97.38 170	82.24 351	82.44 302	95.82 246	51.22 408	98.25 206	84.55 277	80.96 318	95.13 276

MS-PatchMatch		86.75 298	85.92 295	89.22 340	91.97 337	82.47 340	96.91 309	96.14 273	83.74 320	77.73 364	93.53 291	58.19 381	97.37 271	76.75 346	98.35 120	87.84 397

VPNet		88.30 275	86.57 285	93.49 237	91.95 339	91.35 127	98.18 235	97.20 190	88.61 209	84.52 277	94.89 263	62.21 367	96.76 294	89.34 220	72.26 382	92.36 296

FMVSNet1		83.94 344	81.32 353	91.80 276	91.94 340	88.81 207	96.77 314	95.25 341	77.98 381	78.25 361	90.25 365	50.37 412	94.97 371	73.27 373	77.81 337	91.62 321

WR-MVS		88.54 273	87.22 278	92.52 260	91.93 341	89.50 185	98.56 192	97.84 67	86.99 258	81.87 320	93.81 282	74.25 278	95.92 346	85.29 265	74.43 358	92.12 308

SSC-MVS3.2		85.22 324	83.90 329	89.17 342	91.87 342	79.84 365	97.66 277	96.63 231	86.81 266	81.99 316	91.35 333	55.80 387	96.00 339	76.52 349	76.53 343	91.67 317

D2MVS		87.96 279	87.39 273	89.70 329	91.84 343	83.40 325	98.31 225	98.49 24	88.04 233	78.23 362	90.26 364	73.57 282	96.79 293	84.21 281	83.53 303	88.90 391

MonoMVSNet		90.69 226	89.78 226	93.45 238	91.78 344	84.97 305	96.51 324	94.44 367	90.56 150	85.96 264	90.97 341	78.61 250	96.27 327	95.35 128	83.79 301	99.11 125

FC-MVSNet-test		90.22 237	89.40 233	92.67 259	91.78 344	89.86 177	97.89 256	98.22 37	88.81 205	82.96 293	94.66 267	81.90 213	95.96 342	85.89 261	82.52 312	92.20 305

MIMVSNet		84.48 335	81.83 347	92.42 262	91.73 346	87.36 244	85.52 421	94.42 371	81.40 361	81.91 318	87.58 390	51.92 405	92.81 399	73.84 369	88.15 268	97.08 237

USDC		84.74 329	82.93 335	90.16 315	91.73 346	83.54 324	95.00 362	93.30 389	88.77 206	73.19 390	93.30 295	53.62 401	97.65 253	75.88 353	81.54 316	89.30 384

test_vis1_n		90.40 232	90.27 220	90.79 298	91.55 348	76.48 391	99.12 124	94.44 367	94.31 52	97.34 76	96.95 201	43.60 422	99.42 136	97.57 72	97.60 136	96.47 259

nrg030		90.23 236	88.87 246	94.32 212	91.53 349	93.54 74	98.79 161	95.89 303	88.12 230	84.55 276	94.61 268	78.80 246	96.88 288	92.35 185	75.21 349	92.53 294

DU-MVS		88.83 263	87.51 271	92.79 253	91.46 350	90.07 168	98.71 167	97.62 123	88.87 204	83.21 287	93.68 285	74.63 269	95.93 344	86.95 244	72.47 379	92.36 296

NR-MVSNet		87.74 286	86.00 294	92.96 249	91.46 350	90.68 149	96.65 321	97.42 165	88.02 234	73.42 388	93.68 285	77.31 257	95.83 350	84.26 280	71.82 386	92.36 296

tfpnnormal		83.65 346	81.35 352	90.56 305	91.37 352	88.06 224	97.29 292	97.87 64	78.51 380	76.20 369	90.91 342	64.78 354	96.47 308	61.71 416	73.50 370	87.13 406

test_vis1_rt		81.31 359	80.05 362	85.11 382	91.29 353	70.66 416	98.98 141	77.39 445	85.76 286	68.80 408	82.40 416	36.56 432	99.44 132	92.67 182	86.55 276	85.24 420

test_0402		78.81 372	76.33 377	86.26 373	91.18 354	78.44 378	95.88 347	91.34 414	68.55 418	70.51 402	89.91 373	52.65 404	94.99 370	47.14 434	79.78 324	85.34 419

test0.0.03 1		88.96 257	88.61 253	90.03 321	91.09 355	84.43 311	98.97 142	97.02 210	90.21 160	80.29 337	96.31 231	84.89 156	91.93 411	72.98 375	85.70 285	93.73 282

WR-MVS_H		86.53 304	85.49 302	89.66 331	91.04 356	83.31 327	97.53 284	98.20 38	84.95 301	79.64 345	90.90 343	78.01 254	95.33 365	76.29 350	72.81 375	90.35 365

CP-MVSNet		86.54 303	85.45 303	89.79 326	91.02 357	82.78 336	97.38 289	97.56 136	85.37 291	79.53 348	93.03 301	71.86 301	95.25 367	79.92 323	73.43 373	91.34 336

TranMVSNet+NR-MVSNet		87.75 283	86.31 289	92.07 270	90.81 358	88.56 214	98.33 222	97.18 191	87.76 242	81.87 320	93.90 280	72.45 294	95.43 362	83.13 298	71.30 389	92.23 302

PS-CasMVS		85.81 316	84.58 319	89.49 336	90.77 359	82.11 342	97.20 299	97.36 174	84.83 303	79.12 353	92.84 304	67.42 336	95.16 369	78.39 336	73.25 374	91.21 342

DeepMVS_CX				76.08 408	90.74 360	51.65 441		90.84 416	86.47 277	57.89 429	87.98 387	35.88 433	92.60 401	65.77 406	65.06 407	83.97 424

OPM-MVS		89.76 247	89.15 239	91.57 282	90.53 361	85.58 291	98.11 243	95.93 293	92.88 93	86.05 262	96.47 225	67.06 339	97.87 234	89.29 223	86.08 282	91.26 340
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XXY-MVS		87.75 283	86.02 293	92.95 250	90.46 362	89.70 181	97.71 273	95.90 301	84.02 314	80.95 329	94.05 271	67.51 335	97.10 280	85.16 266	78.41 329	92.04 312

UniMVSNet_ETH3D		85.65 321	83.79 330	91.21 286	90.41 363	80.75 361	95.36 357	95.78 310	78.76 379	81.83 323	94.33 270	49.86 413	96.66 296	84.30 279	83.52 304	96.22 264

v10		85.73 319	84.01 327	90.87 296	90.03 364	86.73 257	97.20 299	95.22 349	81.25 363	79.85 344	89.75 375	73.30 286	96.28 326	76.87 344	72.64 377	89.61 381

v8		86.11 310	84.45 321	91.10 288	89.99 365	86.85 255	97.24 296	95.36 338	81.99 355	79.89 343	89.86 374	74.53 273	96.39 312	78.83 332	72.32 381	90.05 373

V42		87.00 294	85.68 299	90.98 292	89.91 366	86.08 277	98.32 224	95.61 322	83.67 323	82.72 295	90.67 350	74.00 280	96.53 303	81.94 310	74.28 361	90.32 366

XVG-ACMP-BASELINE		85.86 314	84.95 310	88.57 350	89.90 367	77.12 389	94.30 369	95.60 323	87.40 253	82.12 310	92.99 303	53.42 402	97.66 251	85.02 269	83.83 298	90.92 349

PEN-MVS		85.21 325	83.93 328	89.07 345	89.89 368	81.31 352	97.09 303	97.24 183	84.45 310	78.66 355	92.68 307	68.44 325	94.87 374	75.98 352	70.92 390	91.04 346

test_fmvs2		85.10 326	85.45 303	84.02 391	89.85 369	65.63 425	98.49 201	92.59 395	90.45 154	85.43 271	93.32 293	43.94 420	96.59 299	90.81 201	84.19 295	89.85 377

v1144		86.83 297	85.31 305	91.40 283	89.75 370	87.21 252	98.31 225	95.45 331	83.22 329	82.70 296	90.78 345	73.36 283	96.36 314	79.49 325	74.69 355	90.63 361

TransMVSNet (Re)		81.97 354	79.61 364	89.08 344	89.70 371	84.01 317	97.26 294	91.85 406	78.84 377	73.07 394	91.62 326	67.17 338	95.21 368	67.50 399	59.46 422	88.02 396

v2v482		87.27 292	85.76 297	91.78 280	89.59 372	87.58 236	98.56 192	95.54 326	84.53 308	82.51 301	91.78 322	73.11 288	96.47 308	82.07 307	74.14 364	91.30 338

pm-mvs1		84.68 331	82.78 339	90.40 309	89.58 373	85.18 299	97.31 291	94.73 360	81.93 357	76.05 371	92.01 316	65.48 351	96.11 335	78.75 333	69.14 393	89.91 376

pmmvs4		87.58 289	86.17 292	91.80 276	89.58 373	88.92 205	97.25 295	95.28 340	82.54 345	80.49 334	93.17 299	75.62 265	96.05 338	82.75 301	78.90 327	90.42 364

v1192		86.32 308	84.71 316	91.17 287	89.53 375	86.40 264	98.13 239	95.44 333	82.52 346	82.42 304	90.62 354	71.58 305	96.33 321	77.23 340	74.88 352	90.79 353

v144192		86.40 306	84.89 311	90.91 293	89.48 376	85.59 290	98.21 233	95.43 334	82.45 348	82.62 299	90.58 357	72.79 293	96.36 314	78.45 335	74.04 365	90.79 353

v148		86.38 307	85.06 307	90.37 312	89.47 377	84.10 316	98.52 195	95.48 329	83.80 319	80.93 330	90.22 368	74.60 271	96.31 322	80.92 316	71.55 387	90.69 359

v1921920		86.02 311	84.44 322	90.77 299	89.32 378	85.20 298	98.10 244	95.35 339	82.19 352	82.25 308	90.71 347	70.73 309	96.30 325	76.85 345	74.49 357	90.80 352

v1240		85.77 318	84.11 325	90.73 300	89.26 379	85.15 301	97.88 258	95.23 348	81.89 358	82.16 309	90.55 359	69.60 318	96.31 322	75.59 355	74.87 353	90.72 358

our_test_3		84.47 336	82.80 337	89.50 334	89.01 380	83.90 319	97.03 305	94.56 365	81.33 362	75.36 378	90.52 360	71.69 303	94.54 382	68.81 394	76.84 341	90.07 371

ppachtmachnet_test		83.63 347	81.57 350	89.80 325	89.01 380	85.09 302	97.13 302	94.50 366	78.84 377	76.14 370	91.00 340	69.78 314	94.61 381	63.40 411	74.36 359	89.71 380

DTE-MVSNet		84.14 341	82.80 337	88.14 354	88.95 382	79.87 364	96.81 313	96.24 262	83.50 325	77.60 365	92.52 309	67.89 332	94.24 385	72.64 378	69.05 394	90.32 366

PS-MVSNAJss		89.54 251	89.05 241	91.00 291	88.77 383	84.36 312	97.39 287	95.97 284	88.47 212	81.88 319	93.80 283	82.48 200	96.50 305	89.34 220	83.34 306	92.15 307

Baseline_NR-MVSNet		85.83 315	84.82 313	88.87 349	88.73 384	83.34 326	98.63 180	91.66 408	80.41 373	82.44 302	91.35 333	74.63 269	95.42 363	84.13 283	71.39 388	87.84 397

MVP-Stereo		86.61 302	85.83 296	88.93 348	88.70 385	83.85 320	96.07 341	94.41 372	82.15 353	75.64 376	91.96 319	67.65 333	96.45 310	77.20 342	98.72 103	86.51 409
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EU-MVSNet		84.19 340	84.42 323	83.52 395	88.64 386	67.37 423	96.04 342	95.76 313	85.29 292	78.44 359	93.18 298	70.67 310	91.48 413	75.79 354	75.98 344	91.70 316

pmmvs5		85.87 313	84.40 324	90.30 313	88.53 387	84.23 313	98.60 187	93.71 383	81.53 360	80.29 337	92.02 315	64.51 355	95.52 359	82.04 309	78.34 330	91.15 343

tt0320-xc		75.92 386	72.23 394	87.01 366	88.40 388	78.15 380	93.57 380	89.15 428	55.46 431	69.66 405	85.79 406	38.20 430	93.85 388	69.72 388	60.08 420	89.03 388

MDA-MVSNet-bldmvs		77.82 380	74.75 386	87.03 365	88.33 389	78.52 377	96.34 329	92.85 392	75.57 395	48.87 435	87.89 388	57.32 384	92.49 405	60.79 418	64.80 408	90.08 370

N_pmnet		70.19 395	69.87 397	71.12 415	88.24 390	30.63 454	95.85 350	28.70 453	70.18 413	68.73 409	86.55 402	64.04 357	93.81 389	53.12 430	73.46 371	88.94 390

v7n		84.42 337	82.75 340	89.43 338	88.15 391	81.86 344	96.75 317	95.67 319	80.53 369	78.38 360	89.43 380	69.89 313	96.35 319	73.83 370	72.13 383	90.07 371

SixPastTwentyTwo		82.63 351	81.58 349	85.79 378	88.12 392	71.01 415	95.17 360	92.54 396	84.33 311	72.93 395	92.08 313	60.41 375	95.61 358	74.47 362	74.15 363	90.75 356

test_djsdf		88.26 277	87.73 268	89.84 324	88.05 393	82.21 341	97.77 266	96.17 271	86.84 264	82.41 305	91.95 320	72.07 298	95.99 340	89.83 210	84.50 292	91.32 337

tt0320		76.58 383	73.16 391	86.86 369	88.03 394	77.60 386	93.55 381	90.63 418	55.37 432	70.93 399	84.98 407	41.57 424	94.01 387	69.02 393	64.32 410	88.97 389

sc_t1		78.53 375	74.87 385	89.48 337	87.92 395	77.36 388	94.80 364	90.61 419	57.65 430	76.28 368	89.59 378	38.25 429	96.18 330	74.04 367	64.72 409	94.91 279

mvs_tets		87.09 293	86.22 290	89.71 328	87.87 396	81.39 350	96.73 319	95.90 301	88.19 228	79.99 341	93.61 288	59.96 376	96.31 322	89.40 219	84.34 294	91.43 332

OurMVSNet-221017-0		84.13 342	83.59 331	85.77 379	87.81 397	70.24 417	94.89 363	93.65 385	86.08 280	76.53 367	93.28 296	61.41 370	96.14 334	80.95 315	77.69 338	90.93 348

YYNet1		79.64 369	77.04 374	87.43 363	87.80 398	79.98 363	96.23 335	94.44 367	73.83 403	51.83 432	87.53 391	67.96 331	92.07 410	66.00 405	67.75 400	90.23 368

MDA-MVSNet_test_wron		79.65 368	77.05 373	87.45 362	87.79 399	80.13 362	96.25 334	94.44 367	73.87 402	51.80 433	87.47 395	68.04 329	92.12 409	66.02 404	67.79 399	90.09 369

jajsoiax		87.35 290	86.51 287	89.87 322	87.75 400	81.74 345	97.03 305	95.98 283	88.47 212	80.15 339	93.80 283	61.47 369	96.36 314	89.44 218	84.47 293	91.50 328

K. test v3		81.04 360	79.77 363	84.83 386	87.41 401	70.23 418	95.60 356	93.93 380	83.70 322	67.51 415	89.35 381	55.76 388	93.58 392	76.67 347	68.03 397	90.67 360

dmvs_testset		77.17 382	78.99 366	71.71 413	87.25 402	38.55 450	91.44 402	81.76 441	85.77 285	69.49 406	95.94 244	69.71 316	84.37 433	52.71 431	76.82 342	92.21 304

testgi		82.29 352	81.00 355	86.17 374	87.24 403	74.84 400	97.39 287	91.62 410	88.63 208	75.85 375	95.42 255	46.07 419	91.55 412	66.87 403	79.94 323	92.12 308

LF4IMVS		81.94 355	81.17 354	84.25 390	87.23 404	68.87 422	93.35 382	91.93 405	83.35 328	75.40 377	93.00 302	49.25 416	96.65 297	78.88 331	78.11 331	87.22 405

EG-PatchMatch MVS		79.92 364	77.59 370	86.90 368	87.06 405	77.90 384	96.20 338	94.06 378	74.61 399	66.53 419	88.76 384	40.40 428	96.20 329	67.02 401	83.66 302	86.61 407

test_fmvsmconf0.01_n		94.14 136	93.51 144	96.04 134	86.79 406	89.19 189	99.28 96	95.94 289	95.70 28	95.50 126	98.49 125	73.27 287	99.79 94	98.28 58	98.32 123	99.15 119

Gipuma		54.77 407	52.22 411	62.40 424	86.50 407	59.37 431	50.20 442	90.35 421	36.52 440	41.20 441	49.49 442	18.33 443	81.29 435	32.10 441	65.34 406	46.54 442
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
anonymousdsp		86.69 299	85.75 298	89.53 333	86.46 408	82.94 330	96.39 327	95.71 315	83.97 316	79.63 346	90.70 348	68.85 321	95.94 343	86.01 256	84.02 297	89.72 379

EGC-MVSNET		60.70 402	55.37 406	76.72 407	86.35 409	71.08 413	89.96 413	84.44 438	0.38 450	1.50 451	84.09 411	37.30 431	88.10 428	40.85 439	73.44 372	70.97 435

MVStest1		76.56 384	73.43 389	85.96 377	86.30 410	80.88 360	94.26 370	91.74 407	61.98 429	58.53 428	89.96 372	69.30 319	91.47 414	59.26 422	49.56 437	85.52 416

test_method		70.10 396	68.66 399	74.41 412	86.30 410	55.84 434	94.47 366	89.82 423	35.18 441	66.15 420	84.75 410	30.54 435	77.96 442	70.40 387	60.33 419	89.44 383

lessismore_v0				85.08 383	85.59 412	69.28 420		90.56 420		67.68 414	90.21 369	54.21 399	95.46 361	73.88 368	62.64 413	90.50 363

CMPMVS	58.40 21	80.48 362	80.11 361	81.59 403	85.10 413	59.56 430	94.14 373	95.95 288	68.54 419	60.71 426	93.31 294	55.35 393	97.87 234	83.06 299	84.85 290	87.33 403
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20231206		80.76 361	79.42 365	84.79 387	84.78 414	72.98 407	96.53 322	92.97 391	79.56 374	74.33 381	88.83 383	61.27 371	92.15 408	60.59 419	75.92 345	89.24 386

DSMNet-mixed		81.60 357	81.43 351	82.10 400	84.36 415	60.79 428	93.63 378	86.74 433	79.00 375	79.32 350	87.15 398	63.87 358	89.78 422	66.89 402	91.92 232	95.73 272

pmmvs6		79.90 365	77.31 372	87.67 358	84.17 416	78.13 381	95.86 349	93.68 384	67.94 421	72.67 396	89.62 377	50.98 410	95.75 352	74.80 361	66.04 404	89.14 387

new_pmnet		76.02 385	73.71 388	82.95 396	83.88 417	72.85 409	91.26 405	92.26 399	70.44 412	62.60 424	81.37 420	47.64 417	92.32 406	61.85 415	72.10 384	83.68 425

OpenMVS_ROB	73.86 20	77.99 379	75.06 384	86.77 370	83.81 418	77.94 383	96.38 328	91.53 412	67.54 422	68.38 410	87.13 399	43.94 420	96.08 336	55.03 428	81.83 314	86.29 411

ttmdpeth		79.80 367	77.91 369	85.47 381	83.34 419	75.75 394	95.32 358	91.45 413	76.84 389	74.81 380	91.71 325	53.98 400	94.13 386	72.42 379	61.29 416	86.51 409

test20.03		78.51 376	77.48 371	81.62 402	83.07 420	71.03 414	96.11 340	92.83 393	81.66 359	69.31 407	89.68 376	57.53 382	87.29 430	58.65 424	68.47 395	86.53 408

Anonymous20240521		78.63 374	76.90 375	83.82 392	82.82 421	72.86 408	95.72 354	93.57 386	73.55 405	72.17 398	84.79 409	49.69 414	92.51 404	65.29 407	74.50 356	86.09 412

UnsupCasMVSNet_eth		78.90 371	76.67 376	85.58 380	82.81 422	74.94 399	91.98 395	96.31 256	84.64 307	65.84 421	87.71 389	51.33 407	92.23 407	72.89 376	56.50 427	89.56 382

KD-MVS_self_test		77.47 381	75.88 379	82.24 398	81.59 423	68.93 421	92.83 389	94.02 379	77.03 387	73.14 391	83.39 412	55.44 392	90.42 417	67.95 397	57.53 425	87.38 401

CL-MVSNet_self_test		79.89 366	78.34 367	84.54 389	81.56 424	75.01 398	96.88 311	95.62 321	81.10 364	75.86 374	85.81 405	68.49 324	90.26 418	63.21 412	56.51 426	88.35 394

MIMVSNet1		75.92 386	73.30 390	83.81 393	81.29 425	75.57 396	92.26 393	92.05 403	73.09 406	67.48 416	86.18 403	40.87 427	87.64 429	55.78 427	70.68 391	88.21 395

Patchmatch-RL test		81.90 356	80.13 360	87.23 364	80.71 426	70.12 419	84.07 430	88.19 431	83.16 331	70.57 400	82.18 418	87.18 105	92.59 402	82.28 306	62.78 412	98.98 134

APD_test1		68.93 397	66.98 400	74.77 411	80.62 427	53.15 438	87.97 416	85.01 436	53.76 434	59.26 427	87.52 392	25.19 437	89.95 419	56.20 426	67.33 401	81.19 429

mvs5depth		78.17 377	75.56 380	85.97 376	80.43 428	76.44 392	85.46 422	89.24 427	76.39 391	78.17 363	88.26 386	51.73 406	95.73 353	69.31 391	61.09 417	85.73 414

pmmvs-eth3d		78.71 373	76.16 378	86.38 371	80.25 429	81.19 354	94.17 372	92.13 402	77.97 382	66.90 418	82.31 417	55.76 388	92.56 403	73.63 372	62.31 415	85.38 417

UnsupCasMVSNet_bld		73.85 392	70.14 396	84.99 384	79.44 430	75.73 395	88.53 415	95.24 344	70.12 414	61.94 425	74.81 432	41.41 426	93.62 391	68.65 395	51.13 435	85.62 415

PM-MVS		74.88 390	72.85 392	80.98 404	78.98 431	64.75 426	90.81 409	85.77 434	80.95 367	68.23 412	82.81 414	29.08 436	92.84 398	76.54 348	62.46 414	85.36 418

new-patchmatchnet		74.80 391	72.40 393	81.99 401	78.36 432	72.20 411	94.44 367	92.36 398	77.06 386	63.47 423	79.98 426	51.04 409	88.85 426	60.53 420	54.35 429	84.92 422

test_fmvs3		75.09 389	75.19 382	74.81 410	77.45 433	54.08 436	95.93 343	90.64 417	82.51 347	73.29 389	81.19 421	22.29 439	86.29 432	85.50 264	67.89 398	84.06 423

WB-MVS		66.44 398	66.29 401	66.89 418	74.84 434	44.93 445	93.00 384	84.09 439	71.15 409	55.82 430	81.63 419	63.79 359	80.31 440	21.85 444	50.47 436	75.43 431

SSC-MVS		65.42 399	65.20 402	66.06 419	73.96 435	43.83 446	92.08 394	83.54 440	69.77 415	54.73 431	80.92 423	63.30 361	79.92 441	20.48 445	48.02 438	74.44 432

pmmvs3		72.86 393	69.76 398	82.17 399	73.86 436	74.19 402	94.20 371	89.01 429	64.23 428	67.72 413	80.91 424	41.48 425	88.65 427	62.40 414	54.02 430	83.68 425

mvsany_test3		75.85 388	74.52 387	79.83 405	73.53 437	60.64 429	91.73 398	87.87 432	83.91 318	70.55 401	82.52 415	31.12 434	93.66 390	86.66 251	62.83 411	85.19 421

test_f		71.94 394	70.82 395	75.30 409	72.77 438	53.28 437	91.62 399	89.66 425	75.44 396	64.47 422	78.31 429	20.48 440	89.56 423	78.63 334	66.02 405	83.05 428

ambc				79.60 406	72.76 439	56.61 433	76.20 437	92.01 404		68.25 411	80.23 425	23.34 438	94.73 378	73.78 371	60.81 418	87.48 400

TDRefinement		78.01 378	75.31 381	86.10 375	70.06 440	73.84 403	93.59 379	91.58 411	74.51 400	73.08 393	91.04 339	49.63 415	97.12 277	74.88 359	59.47 421	87.33 403

test_vis3_rt		61.29 401	58.75 404	68.92 417	67.41 441	52.84 439	91.18 407	59.23 452	66.96 423	41.96 440	58.44 440	11.37 448	94.72 379	74.25 364	57.97 424	59.20 439

testf1		56.38 405	53.73 408	64.31 422	64.84 442	45.11 443	80.50 435	75.94 447	38.87 437	42.74 437	75.07 430	11.26 449	81.19 436	41.11 437	53.27 431	66.63 436

APD_test2		56.38 405	53.73 408	64.31 422	64.84 442	45.11 443	80.50 435	75.94 447	38.87 437	42.74 437	75.07 430	11.26 449	81.19 436	41.11 437	53.27 431	66.63 436

PMMVS2		58.97 404	55.07 407	70.69 416	62.72 444	55.37 435	85.97 420	80.52 442	49.48 435	45.94 436	68.31 434	15.73 445	80.78 438	49.79 433	37.12 441	75.91 430

E-PMN		41.02 412	40.93 414	41.29 428	61.97 445	33.83 451	84.00 431	65.17 450	27.17 443	27.56 443	46.72 444	17.63 444	60.41 447	19.32 446	18.82 443	29.61 443

wuyk23d		16.71 416	16.73 420	16.65 430	60.15 446	25.22 455	41.24 443	5.17 454	6.56 447	5.48 450	3.61 450	3.64 452	22.72 449	15.20 448	9.52 447	1.99 447

FPMVS		61.57 400	60.32 403	65.34 420	60.14 447	42.44 448	91.02 408	89.72 424	44.15 436	42.63 439	80.93 422	19.02 441	80.59 439	42.50 436	72.76 376	73.00 433

EMVS		39.96 413	39.88 415	40.18 429	59.57 448	32.12 453	84.79 428	64.57 451	26.27 444	26.14 445	44.18 447	18.73 442	59.29 448	17.03 447	17.67 445	29.12 444

LCM-MVSNet		60.07 403	56.37 405	71.18 414	54.81 449	48.67 442	82.17 434	89.48 426	37.95 439	49.13 434	69.12 433	13.75 447	81.76 434	59.28 421	51.63 434	83.10 427

MVE	44.00 22	41.70 411	37.64 416	53.90 427	49.46 450	43.37 447	65.09 441	66.66 449	26.19 445	25.77 446	48.53 443	3.58 453	63.35 446	26.15 443	27.28 442	54.97 441
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		50.71 409	46.17 412	64.33 421	44.27 451	52.30 440	76.13 438	78.73 443	64.95 426	27.37 444	55.23 441	14.61 446	67.74 444	36.01 440	18.23 444	72.95 434

PMVS	41.42 23	45.67 410	42.50 413	55.17 426	34.28 452	32.37 452	66.24 440	78.71 444	30.72 442	22.04 447	59.59 438	4.59 451	77.85 443	27.49 442	58.84 423	55.29 440
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		53.66 408	52.86 410	56.05 425	32.75 453	41.97 449	73.42 439	76.12 446	21.91 446	39.68 442	96.39 228	42.59 423	65.10 445	78.00 337	14.92 446	61.08 438

testmvs		18.81 415	23.05 418	6.10 432	4.48 454	2.29 457	97.78 264	3.00 455	3.27 448	18.60 448	62.71 436	1.53 455	2.49 451	14.26 449	1.80 448	13.50 446

test123		16.58 417	19.47 419	7.91 431	3.59 455	5.37 456	94.32 368	1.39 456	2.49 449	13.98 449	44.60 446	2.91 454	2.65 450	11.35 450	0.57 449	15.70 445

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

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

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

eth-test2					0.00 456

eth-test					0.00 456

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

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

cdsmvs_eth3d_5k		22.52 414	30.03 417	0.00 433	0.00 456	0.00 458	0.00 444	97.17 193	0.00 451	0.00 452	98.77 98	74.35 276	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		6.87 419	9.16 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	82.48 200	0.00 452	0.00 451	0.00 450	0.00 448

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

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

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

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

ab-mvs-re		8.21 418	10.94 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	98.50 122	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

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

WAC-MVS						79.74 366								67.75 398

PC_three_1452									94.60 46	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 91	94.17 54	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 86	99.07 21	99.46 10	94.66 13	99.97 21	99.25 21	99.82 19	99.95 15

GSMVS																98.84 150

sam_mvs1												88.39 80				98.84 150

sam_mvs												87.08 108

MTGPA								97.45 158

test_post1							90.74 411				41.37 448	85.38 149	96.36 314	83.16 296

test_post											46.00 445	87.37 99	97.11 278

patchmatchnet-post											84.86 408	88.73 76	96.81 291

MTMP							99.21 102	91.09 415

test9_res														98.60 42	99.87 9	99.90 22

agg_prior2														97.84 68	99.87 9	99.91 21

test_prior4						92.00 111	99.41 80

test_prior2							99.57 53		91.43 125	98.12 56	98.97 74	90.43 51		98.33 55	99.81 23

旧先验2							98.67 174		85.75 287	98.96 26			98.97 168	93.84 161

新几何2							98.26 228

无先验							98.52 195	97.82 72	87.20 256				99.90 53	87.64 239		99.85 30

原ACMM2							98.69 171

testdata2													99.88 62	84.16 282

segment_acmp												90.56 49

testdata1							97.89 256		92.43 100

plane_prior5								96.30 257					97.75 247	93.46 170	86.17 280	92.67 292

plane_prior4											96.52 221

plane_prior3						85.91 283			93.65 74	86.99 255

plane_prior2							99.02 135		93.38 81

plane_prior						86.07 279	99.14 118		93.81 70						86.26 279

n2								0.00 457

nn								0.00 457

door-mid								84.90 437

test11								97.68 102

door								85.30 435

HQP5-MVS						86.39 265

BP-MVS														93.82 163

HQP4-MVS										87.57 248			97.77 241			92.72 290

HQP3-MVS								96.37 253							86.29 277

HQP2-MVS												73.34 284

MDTV_nov1_ep13_2view						91.17 132	91.38 403		87.45 252	93.08 172		86.67 120		87.02 242		98.95 140

ACMMP++_ref															82.64 311

ACMMP++															83.83 298

Test By Simon												83.62 171

High-resolution multi-view benchmark