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.

patch_mono-2		99.26 58	99.62 1	98.16 271	99.81 40	94.59 332	99.52 133	99.64 32	99.33 2	99.73 47	99.90 15	99.00 22	99.99 1	99.69 5	99.98 2	99.89 5

h-mvs33		97.70 250	97.28 269	98.97 173	99.70 91	97.27 250	99.36 208	99.45 179	98.94 41	99.66 68	99.64 175	94.93 193	99.99 1	99.48 24	84.36 360	99.65 112

xiu_mvs_v1_base_debu		99.29 53	99.27 48	99.34 121	99.63 118	98.97 139	99.12 265	99.51 102	98.86 47	99.84 17	99.47 238	98.18 91	99.99 1	99.50 19	99.31 142	99.08 199

xiu_mvs_v1_base		99.29 53	99.27 48	99.34 121	99.63 118	98.97 139	99.12 265	99.51 102	98.86 47	99.84 17	99.47 238	98.18 91	99.99 1	99.50 19	99.31 142	99.08 199

xiu_mvs_v1_base_debi		99.29 53	99.27 48	99.34 121	99.63 118	98.97 139	99.12 265	99.51 102	98.86 47	99.84 17	99.47 238	98.18 91	99.99 1	99.50 19	99.31 142	99.08 199

EPNet		98.86 113	98.71 117	99.30 132	97.20 355	98.18 212	99.62 82	98.91 312	99.28 5	98.63 275	99.81 75	95.96 157	99.99 1	99.24 51	99.72 103	99.73 82
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_vis1_n		97.92 213	97.44 247	99.34 121	99.53 149	98.08 218	99.74 42	99.49 129	99.15 9	100.00 1	99.94 4	79.51 361	99.98 7	99.88 1	99.76 95	99.97 1

xiu_mvs_v2_base		99.26 58	99.25 52	99.29 135	99.53 149	98.91 155	99.02 289	99.45 179	98.80 56	99.71 53	99.26 291	98.94 29	99.98 7	99.34 38	99.23 147	98.98 213

PS-MVSNAJ		99.32 49	99.32 32	99.30 132	99.57 139	98.94 151	98.97 302	99.46 168	98.92 44	99.71 53	99.24 293	99.01 18	99.98 7	99.35 34	99.66 113	98.97 214

QAPM		98.67 140	98.30 157	99.80 38	99.20 239	99.67 51	99.77 33	99.72 11	94.74 327	98.73 256	99.90 15	95.78 167	99.98 7	96.96 268	99.88 36	99.76 72

3Dnovator	97.25 9	99.24 62	99.05 71	99.81 36	99.12 257	99.66 53	99.84 13	99.74 10	99.09 19	98.92 231	99.90 15	95.94 160	99.98 7	98.95 76	99.92 13	99.79 59

OpenMVS	96.50 16	98.47 149	98.12 168	99.52 96	99.04 274	99.53 73	99.82 17	99.72 11	94.56 330	98.08 305	99.88 25	94.73 209	99.98 7	97.47 237	99.76 95	99.06 205

test_fmvs1_n		98.41 155	98.14 165	99.21 145	99.82 36	97.71 240	99.74 42	99.49 129	99.32 3	99.99 2	99.95 2	85.32 348	99.97 13	99.82 2	99.84 62	99.96 2

CANet_DTU		98.97 103	98.87 100	99.25 140	99.33 207	98.42 205	99.08 274	99.30 258	99.16 8	99.43 123	99.75 121	95.27 184	99.97 13	98.56 141	99.95 8	99.36 178

MTAPA		99.52 10	99.39 19	99.89 4	99.90 4	99.86 13	99.66 64	99.47 159	98.79 57	99.68 59	99.81 75	98.43 78	99.97 13	98.88 85	99.90 24	99.83 34

PGM-MVS		99.45 25	99.31 38	99.86 20	99.87 15	99.78 36	99.58 103	99.65 31	97.84 153	99.71 53	99.80 88	99.12 13	99.97 13	98.33 162	99.87 39	99.83 34

mPP-MVS		99.44 29	99.30 40	99.86 20	99.88 11	99.79 30	99.69 51	99.48 141	98.12 120	99.50 109	99.75 121	98.78 47	99.97 13	98.57 138	99.89 33	99.83 34

CP-MVS		99.45 25	99.32 32	99.85 25	99.83 34	99.75 39	99.69 51	99.52 88	98.07 130	99.53 104	99.63 181	98.93 33	99.97 13	98.74 110	99.91 17	99.83 34

SteuartSystems-ACMMP		99.54 8	99.42 15	99.87 11	99.82 36	99.81 25	99.59 95	99.51 102	98.62 66	99.79 29	99.83 55	99.28 4	99.97 13	98.48 148	99.90 24	99.84 25
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 66	98.97 87	99.82 33	99.17 250	99.68 48	99.81 20	99.51 102	99.20 7	98.72 257	99.89 19	95.68 172	99.97 13	98.86 93	99.86 47	99.81 46

mvsany_test1		99.50 12	99.46 14	99.62 69	99.61 128	99.09 122	98.94 308	99.48 141	99.10 15	99.96 5	99.91 11	98.85 39	99.96 21	99.72 4	99.58 122	99.82 39

test_fmvs1		98.88 109	98.79 111	99.16 150	99.69 94	97.61 242	99.55 122	99.49 129	99.32 3	99.98 3	99.91 11	91.41 298	99.96 21	99.82 2	99.92 13	99.90 3

DVP-MVS++		99.59 3	99.50 8	99.88 5	99.51 155	99.88 8	99.87 9	99.51 102	98.99 32	99.88 10	99.81 75	99.27 5	99.96 21	98.85 95	99.80 82	99.81 46

MSC_two_6792asdad				99.87 11	99.51 155	99.76 37		99.33 240					99.96 21	98.87 88	99.84 62	99.89 5

No_MVS				99.87 11	99.51 155	99.76 37		99.33 240					99.96 21	98.87 88	99.84 62	99.89 5

ZD-MVS					99.71 86	99.79 30		99.61 35	96.84 247	99.56 97	99.54 214	98.58 67	99.96 21	96.93 271	99.75 97

SED-MVS		99.61 2	99.52 6	99.88 5	99.84 30	99.90 2	99.60 89	99.48 141	99.08 20	99.91 6	99.81 75	99.20 7	99.96 21	98.91 82	99.85 54	99.79 59

test_241102_TWO								99.48 141	99.08 20	99.88 10	99.81 75	98.94 29	99.96 21	98.91 82	99.84 62	99.88 11

ZNCC-MVS		99.47 21	99.33 30	99.87 11	99.87 15	99.81 25	99.64 72	99.67 22	98.08 129	99.55 101	99.64 175	98.91 34	99.96 21	98.72 113	99.90 24	99.82 39

DVP-MVS		99.57 7	99.47 12	99.88 5	99.85 24	99.89 4	99.57 107	99.37 223	99.10 15	99.81 24	99.80 88	98.94 29	99.96 21	98.93 79	99.86 47	99.81 46
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									98.99 32	99.81 24	99.80 88	99.09 14	99.96 21	98.85 95	99.90 24	99.88 11

test_0728_SECOND				99.91 2	99.84 30	99.89 4	99.57 107	99.51 102					99.96 21	98.93 79	99.86 47	99.88 11

SR-MVS		99.43 32	99.29 44	99.86 20	99.75 63	99.83 16	99.59 95	99.62 33	98.21 107	99.73 47	99.79 99	98.68 61	99.96 21	98.44 153	99.77 92	99.79 59

DPE-MVS		99.46 23	99.32 32	99.91 2	99.78 46	99.88 8	99.36 208	99.51 102	98.73 60	99.88 10	99.84 51	98.72 58	99.96 21	98.16 175	99.87 39	99.88 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 34	99.29 44	99.80 38	99.62 124	99.55 68	99.50 144	99.70 15	98.79 57	99.77 37	99.96 1	97.45 109	99.96 21	98.92 81	99.90 24	99.89 5

HFP-MVS		99.49 14	99.37 22	99.86 20	99.87 15	99.80 27	99.66 64	99.67 22	98.15 116	99.68 59	99.69 151	99.06 16	99.96 21	98.69 118	99.87 39	99.84 25

region2R		99.48 18	99.35 26	99.87 11	99.88 11	99.80 27	99.65 70	99.66 26	98.13 119	99.66 68	99.68 157	98.96 24	99.96 21	98.62 126	99.87 39	99.84 25

HPM-MVS++		99.39 42	99.23 55	99.87 11	99.75 63	99.84 15	99.43 176	99.51 102	98.68 64	99.27 167	99.53 218	98.64 66	99.96 21	98.44 153	99.80 82	99.79 59

APDe-MVS		99.66 1	99.57 3	99.92 1	99.77 52	99.89 4	99.75 39	99.56 56	99.02 25	99.88 10	99.85 41	99.18 10	99.96 21	99.22 52	99.92 13	99.90 3

ACMMPR		99.49 14	99.36 24	99.86 20	99.87 15	99.79 30	99.66 64	99.67 22	98.15 116	99.67 63	99.69 151	98.95 27	99.96 21	98.69 118	99.87 39	99.84 25

MP-MVS		99.33 48	99.15 61	99.87 11	99.88 11	99.82 22	99.66 64	99.46 168	98.09 125	99.48 113	99.74 126	98.29 86	99.96 21	97.93 191	99.87 39	99.82 39
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 85	98.90 96	99.74 49	99.80 43	99.46 82	99.59 95	99.49 129	97.03 234	99.63 79	99.69 151	97.27 116	99.96 21	97.82 201	99.84 62	99.81 46

PVSNet_Blended_VisFu		99.36 45	99.28 46	99.61 70	99.86 20	99.07 127	99.47 163	99.93 2	97.66 174	99.71 53	99.86 36	97.73 104	99.96 21	99.47 26	99.82 75	99.79 59

UGNet		98.87 110	98.69 119	99.40 115	99.22 235	98.72 173	99.44 172	99.68 19	99.24 6	99.18 190	99.42 248	92.74 262	99.96 21	99.34 38	99.94 11	99.53 146
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
CSCG		99.32 49	99.32 32	99.32 127	99.85 24	98.29 208	99.71 48	99.66 26	98.11 122	99.41 130	99.80 88	98.37 83	99.96 21	98.99 72	99.96 7	99.72 88

ACMMP		99.45 25	99.32 32	99.82 33	99.89 8	99.67 51	99.62 82	99.69 18	98.12 120	99.63 79	99.84 51	98.73 57	99.96 21	98.55 144	99.83 71	99.81 46
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
SR-MVS-dyc-post		99.45 25	99.31 38	99.85 25	99.76 55	99.82 22	99.63 76	99.52 88	98.38 85	99.76 42	99.82 62	98.53 71	99.95 47	98.61 129	99.81 78	99.77 67

GST-MVS		99.40 41	99.24 53	99.85 25	99.86 20	99.79 30	99.60 89	99.67 22	97.97 141	99.63 79	99.68 157	98.52 72	99.95 47	98.38 156	99.86 47	99.81 46

CANet		99.25 61	99.14 62	99.59 72	99.41 187	99.16 111	99.35 213	99.57 51	98.82 52	99.51 108	99.61 190	96.46 142	99.95 47	99.59 10	99.98 2	99.65 112

MP-MVS-pluss		99.37 44	99.20 57	99.88 5	99.90 4	99.87 12	99.30 223	99.52 88	97.18 218	99.60 89	99.79 99	98.79 46	99.95 47	98.83 101	99.91 17	99.83 34
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 34	99.27 48	99.88 5	99.89 8	99.80 27	99.67 60	99.50 121	98.70 62	99.77 37	99.49 230	98.21 89	99.95 47	98.46 152	99.77 92	99.88 11
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
testdata2													99.95 47	96.67 283

APD-MVS_3200maxsize		99.48 18	99.35 26	99.85 25	99.76 55	99.83 16	99.63 76	99.54 72	98.36 89	99.79 29	99.82 62	98.86 38	99.95 47	98.62 126	99.81 78	99.78 65

RPMNet		96.72 288	95.90 299	99.19 147	99.18 244	98.49 197	99.22 251	99.52 88	88.72 360	99.56 97	97.38 354	94.08 234	99.95 47	86.87 365	98.58 191	99.14 191

sss		99.17 68	99.05 71	99.53 90	99.62 124	98.97 139	99.36 208	99.62 33	97.83 154	99.67 63	99.65 169	97.37 113	99.95 47	99.19 54	99.19 150	99.68 102

TSAR-MVS + MP.		99.58 4	99.50 8	99.81 36	99.91 1	99.66 53	99.63 76	99.39 209	98.91 45	99.78 34	99.85 41	99.36 2	99.94 56	98.84 98	99.88 36	99.82 39
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVS		99.53 9	99.42 15	99.87 11	99.85 24	99.83 16	99.69 51	99.68 19	98.98 35	99.37 143	99.74 126	98.81 44	99.94 56	98.79 106	99.86 47	99.84 25

X-MVStestdata		96.55 290	95.45 307	99.87 11	99.85 24	99.83 16	99.69 51	99.68 19	98.98 35	99.37 143	64.01 377	98.81 44	99.94 56	98.79 106	99.86 47	99.84 25

旧先验2							98.96 303		96.70 254	99.47 114			99.94 56	98.19 171

新几何1				99.75 47	99.75 63	99.59 62		99.54 72	96.76 250	99.29 162	99.64 175	98.43 78	99.94 56	96.92 273	99.66 113	99.72 88

testdata				99.54 82	99.75 63	98.95 148		99.51 102	97.07 230	99.43 123	99.70 141	98.87 37	99.94 56	97.76 207	99.64 116	99.72 88

HPM-MVS		99.42 34	99.28 46	99.83 32	99.90 4	99.72 42	99.81 20	99.54 72	97.59 178	99.68 59	99.63 181	98.91 34	99.94 56	98.58 135	99.91 17	99.84 25
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 64	99.10 66	99.45 108	99.89 8	98.52 193	99.39 197	99.94 1	98.73 60	99.11 199	99.89 19	95.50 176	99.94 56	99.50 19	99.97 5	99.89 5

APD-MVS		99.27 56	99.08 69	99.84 31	99.75 63	99.79 30	99.50 144	99.50 121	97.16 220	99.77 37	99.82 62	98.78 47	99.94 56	97.56 228	99.86 47	99.80 55
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 18	99.42 15	99.65 59	99.72 81	99.40 88	99.05 280	99.66 26	99.14 10	99.57 96	99.80 88	98.46 76	99.94 56	99.57 12	99.84 62	99.60 128
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
WTY-MVS		99.06 92	98.88 99	99.61 70	99.62 124	99.16 111	99.37 204	99.56 56	98.04 136	99.53 104	99.62 186	96.84 130	99.94 56	98.85 95	98.49 198	99.72 88

DeepC-MVS	98.35 2	99.30 51	99.19 58	99.64 64	99.82 36	99.23 104	99.62 82	99.55 64	98.94 41	99.63 79	99.95 2	95.82 166	99.94 56	99.37 33	99.97 5	99.73 82
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		99.27 56	99.12 64	99.74 49	99.18 244	99.75 39	99.56 113	99.57 51	98.45 79	99.49 112	99.85 41	97.77 103	99.94 56	98.33 162	99.84 62	99.52 147

FE-MVS		98.48 148	98.17 162	99.40 115	99.54 148	98.96 143	99.68 57	98.81 323	95.54 313	99.62 83	99.70 141	93.82 241	99.93 69	97.35 244	99.46 129	99.32 183

SF-MVS		99.38 43	99.24 53	99.79 41	99.79 44	99.68 48	99.57 107	99.54 72	97.82 158	99.71 53	99.80 88	98.95 27	99.93 69	98.19 171	99.84 62	99.74 77

dcpmvs_2		99.23 63	99.58 2	98.16 271	99.83 34	94.68 331	99.76 36	99.52 88	99.07 22	99.98 3	99.88 25	98.56 69	99.93 69	99.67 7	99.98 2	99.87 16

Anonymous20240529		98.09 184	97.68 219	99.34 121	99.66 107	98.44 202	99.40 193	99.43 193	93.67 337	99.22 178	99.89 19	90.23 314	99.93 69	99.26 50	98.33 201	99.66 108

ACMMP_NAP		99.47 21	99.34 28	99.88 5	99.87 15	99.86 13	99.47 163	99.48 141	98.05 135	99.76 42	99.86 36	98.82 43	99.93 69	98.82 105	99.91 17	99.84 25

EI-MVSNet-UG-set		99.58 4	99.57 3	99.64 64	99.78 46	99.14 117	99.60 89	99.45 179	99.01 27	99.90 8	99.83 55	98.98 23	99.93 69	99.59 10	99.95 8	99.86 18

无先验							98.99 296	99.51 102	96.89 244				99.93 69	97.53 231		99.72 88

VDDNet		97.55 262	97.02 279	99.16 150	99.49 166	98.12 217	99.38 202	99.30 258	95.35 315	99.68 59	99.90 15	82.62 356	99.93 69	99.31 41	98.13 216	99.42 171

ab-mvs		98.86 113	98.63 127	99.54 82	99.64 115	99.19 106	99.44 172	99.54 72	97.77 161	99.30 159	99.81 75	94.20 228	99.93 69	99.17 57	98.82 182	99.49 157

F-COLMAP		99.19 64	99.04 73	99.64 64	99.78 46	99.27 100	99.42 183	99.54 72	97.29 209	99.41 130	99.59 195	98.42 80	99.93 69	98.19 171	99.69 108	99.73 82

Anonymous202405211		98.30 165	97.98 185	99.26 139	99.57 139	98.16 213	99.41 185	98.55 342	96.03 307	99.19 187	99.74 126	91.87 285	99.92 79	99.16 58	98.29 206	99.70 96

EI-MVSNet-Vis-set		99.58 4	99.56 5	99.64 64	99.78 46	99.15 116	99.61 88	99.45 179	99.01 27	99.89 9	99.82 62	99.01 18	99.92 79	99.56 13	99.95 8	99.85 21

VDD-MVS		97.73 244	97.35 259	98.88 192	99.47 175	97.12 256	99.34 216	98.85 319	98.19 110	99.67 63	99.85 41	82.98 354	99.92 79	99.49 23	98.32 205	99.60 128

VNet		99.11 85	98.90 96	99.73 51	99.52 153	99.56 66	99.41 185	99.39 209	99.01 27	99.74 46	99.78 105	95.56 174	99.92 79	99.52 17	98.18 212	99.72 88

XVG-OURS-SEG-HR		98.69 137	98.62 132	98.89 190	99.71 86	97.74 235	99.12 265	99.54 72	98.44 82	99.42 126	99.71 137	94.20 228	99.92 79	98.54 145	98.90 176	99.00 210

HPM-MVS_fast		99.51 11	99.40 18	99.85 25	99.91 1	99.79 30	99.76 36	99.56 56	97.72 167	99.76 42	99.75 121	99.13 12	99.92 79	99.07 66	99.92 13	99.85 21

HY-MVS	97.30 7	98.85 120	98.64 126	99.47 105	99.42 184	99.08 125	99.62 82	99.36 224	97.39 202	99.28 163	99.68 157	96.44 144	99.92 79	98.37 158	98.22 207	99.40 175

DP-MVS		99.16 70	98.95 91	99.78 43	99.77 52	99.53 73	99.41 185	99.50 121	97.03 234	99.04 213	99.88 25	97.39 110	99.92 79	98.66 122	99.90 24	99.87 16

IB-MVS	95.67 18	96.22 296	95.44 308	98.57 228	99.21 237	96.70 282	98.65 336	97.74 357	96.71 253	97.27 326	98.54 339	86.03 344	99.92 79	98.47 151	86.30 358	99.10 194
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
DeepC-MVS_fast	98.69 1	99.49 14	99.39 19	99.77 45	99.63 118	99.59 62	99.36 208	99.46 168	99.07 22	99.79 29	99.82 62	98.85 39	99.92 79	98.68 120	99.87 39	99.82 39
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
9.14			99.10 66		99.72 81		99.40 193	99.51 102	97.53 187	99.64 78	99.78 105	98.84 41	99.91 89	97.63 219	99.82 75

SMA-MVS		99.44 29	99.30 40	99.85 25	99.73 77	99.83 16	99.56 113	99.47 159	97.45 194	99.78 34	99.82 62	99.18 10	99.91 89	98.79 106	99.89 33	99.81 46
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
TEST9					99.67 99	99.65 56	99.05 280	99.41 198	96.22 292	98.95 226	99.49 230	98.77 50	99.91 89

train_agg		99.02 97	98.77 112	99.77 45	99.67 99	99.65 56	99.05 280	99.41 198	96.28 286	98.95 226	99.49 230	98.76 51	99.91 89	97.63 219	99.72 103	99.75 73

test_8					99.67 99	99.61 60	99.03 286	99.41 198	96.28 286	98.93 230	99.48 235	98.76 51	99.91 89

agg_prior					99.67 99	99.62 59		99.40 206		98.87 240			99.91 89

原ACMM1				99.65 59	99.73 77	99.33 91		99.47 159	97.46 191	99.12 197	99.66 168	98.67 63	99.91 89	97.70 216	99.69 108	99.71 95

LFMVS		97.90 216	97.35 259	99.54 82	99.52 153	99.01 134	99.39 197	98.24 348	97.10 228	99.65 74	99.79 99	84.79 350	99.91 89	99.28 46	98.38 200	99.69 98

XVG-OURS		98.73 133	98.68 120	98.88 192	99.70 91	97.73 236	98.92 310	99.55 64	98.52 74	99.45 117	99.84 51	95.27 184	99.91 89	98.08 182	98.84 180	99.00 210

PLC	97.94 4	99.02 97	98.85 104	99.53 90	99.66 107	99.01 134	99.24 246	99.52 88	96.85 246	99.27 167	99.48 235	98.25 88	99.91 89	97.76 207	99.62 119	99.65 112
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 257	97.06 278	99.47 105	99.61 128	99.09 122	98.04 361	99.25 269	91.24 352	98.51 284	99.70 141	94.55 218	99.91 89	92.76 344	99.85 54	99.42 171
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_vis1_rt		95.81 305	95.65 304	96.32 331	99.67 99	91.35 357	99.49 154	96.74 365	98.25 100	95.24 346	98.10 348	74.96 362	99.90 100	99.53 15	98.85 179	97.70 350

FA-MVS(test-final)		98.75 131	98.53 144	99.41 114	99.55 147	99.05 130	99.80 24	99.01 299	96.59 267	99.58 93	99.59 195	95.39 179	99.90 100	97.78 204	99.49 128	99.28 186

MCST-MVS		99.43 32	99.30 40	99.82 33	99.79 44	99.74 41	99.29 227	99.40 206	98.79 57	99.52 106	99.62 186	98.91 34	99.90 100	98.64 124	99.75 97	99.82 39

CDPH-MVS		99.13 75	98.91 95	99.80 38	99.75 63	99.71 44	99.15 260	99.41 198	96.60 265	99.60 89	99.55 209	98.83 42	99.90 100	97.48 235	99.83 71	99.78 65

NCCC		99.34 47	99.19 58	99.79 41	99.61 128	99.65 56	99.30 223	99.48 141	98.86 47	99.21 181	99.63 181	98.72 58	99.90 100	98.25 167	99.63 118	99.80 55

114514_t		98.93 105	98.67 121	99.72 52	99.85 24	99.53 73	99.62 82	99.59 43	92.65 347	99.71 53	99.78 105	98.06 96	99.90 100	98.84 98	99.91 17	99.74 77

1112_ss		98.98 101	98.77 112	99.59 72	99.68 98	99.02 132	99.25 244	99.48 141	97.23 215	99.13 195	99.58 199	96.93 129	99.90 100	98.87 88	98.78 185	99.84 25

PHI-MVS		99.30 51	99.17 60	99.70 53	99.56 143	99.52 76	99.58 103	99.80 8	97.12 224	99.62 83	99.73 132	98.58 67	99.90 100	98.61 129	99.91 17	99.68 102

AdaColmap		99.01 100	98.80 108	99.66 55	99.56 143	99.54 70	99.18 255	99.70 15	98.18 114	99.35 150	99.63 181	96.32 147	99.90 100	97.48 235	99.77 92	99.55 139

COLMAP_ROB	97.56 6	98.86 113	98.75 114	99.17 149	99.88 11	98.53 189	99.34 216	99.59 43	97.55 183	98.70 264	99.89 19	95.83 165	99.90 100	98.10 177	99.90 24	99.08 199
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 161	98.03 180	99.31 128	99.63 118	98.56 186	99.54 126	96.75 364	97.53 187	99.73 47	99.65 169	91.25 302	99.89 110	98.62 126	99.56 123	99.48 158

tttt0517		98.42 153	98.14 165	99.28 137	99.66 107	98.38 206	99.74 42	96.85 362	97.68 171	99.79 29	99.74 126	91.39 299	99.89 110	98.83 101	99.56 123	99.57 137

test12				99.75 47	99.64 115	99.61 60		99.29 262		99.21 181		98.38 82	99.89 110		99.74 100	99.74 77

Test_1112_low_res		98.89 108	98.66 124	99.57 77	99.69 94	98.95 148	99.03 286	99.47 159	96.98 236	99.15 193	99.23 294	96.77 133	99.89 110	98.83 101	98.78 185	99.86 18

CNLPA		99.14 73	98.99 83	99.59 72	99.58 137	99.41 87	99.16 257	99.44 187	98.45 79	99.19 187	99.49 230	98.08 95	99.89 110	97.73 211	99.75 97	99.48 158

APD_test1		95.87 303	96.49 288	94.00 337	99.53 149	84.01 364	99.54 126	99.32 250	95.91 309	97.99 310	99.85 41	85.49 347	99.88 115	91.96 347	98.84 180	98.12 332

diffmvs		99.14 73	99.02 78	99.51 98	99.61 128	98.96 143	99.28 229	99.49 129	98.46 78	99.72 52	99.71 137	96.50 141	99.88 115	99.31 41	99.11 157	99.67 105
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		98.86 113	98.80 108	99.03 163	99.76 55	98.79 169	99.28 229	99.91 3	97.42 199	99.67 63	99.37 263	97.53 107	99.88 115	98.98 73	97.29 257	98.42 315

PVSNet_Blended		99.08 90	98.97 87	99.42 113	99.76 55	98.79 169	98.78 324	99.91 3	96.74 251	99.67 63	99.49 230	97.53 107	99.88 115	98.98 73	99.85 54	99.60 128

MVS		97.28 276	96.55 286	99.48 102	98.78 307	98.95 148	99.27 234	99.39 209	83.53 364	98.08 305	99.54 214	96.97 127	99.87 119	94.23 327	99.16 151	99.63 122

MG-MVS		99.13 75	99.02 78	99.45 108	99.57 139	98.63 180	99.07 275	99.34 233	98.99 32	99.61 86	99.82 62	97.98 98	99.87 119	97.00 264	99.80 82	99.85 21

MSDG		98.98 101	98.80 108	99.53 90	99.76 55	99.19 106	98.75 327	99.55 64	97.25 212	99.47 114	99.77 112	97.82 101	99.87 119	96.93 271	99.90 24	99.54 141

ETV-MVS		99.26 58	99.21 56	99.40 115	99.46 176	99.30 96	99.56 113	99.52 88	98.52 74	99.44 122	99.27 289	98.41 81	99.86 122	99.10 62	99.59 121	99.04 206

thisisatest0515		98.14 179	97.79 203	99.19 147	99.50 164	98.50 196	98.61 338	96.82 363	96.95 240	99.54 102	99.43 246	91.66 294	99.86 122	98.08 182	99.51 127	99.22 189

thres600view7		97.86 221	97.51 235	98.92 181	99.72 81	97.95 227	99.59 95	98.74 330	97.94 143	99.27 167	98.62 336	91.75 288	99.86 122	93.73 332	98.19 211	98.96 216

lupinMVS		99.13 75	99.01 82	99.46 107	99.51 155	98.94 151	99.05 280	99.16 282	97.86 149	99.80 27	99.56 206	97.39 110	99.86 122	98.94 77	99.85 54	99.58 136

PVSNet	96.02 17	98.85 120	98.84 105	98.89 190	99.73 77	97.28 249	98.32 354	99.60 40	97.86 149	99.50 109	99.57 203	96.75 134	99.86 122	98.56 141	99.70 107	99.54 141

MAR-MVS		98.86 113	98.63 127	99.54 82	99.37 198	99.66 53	99.45 167	99.54 72	96.61 263	99.01 216	99.40 255	97.09 121	99.86 122	97.68 218	99.53 126	99.10 194
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
test2506		96.81 286	96.65 284	97.29 313	99.74 70	92.21 354	99.60 89	85.06 381	99.13 11	99.77 37	99.93 6	87.82 340	99.85 128	99.38 31	99.38 134	99.80 55

AllTest		98.87 110	98.72 115	99.31 128	99.86 20	98.48 199	99.56 113	99.61 35	97.85 151	99.36 147	99.85 41	95.95 158	99.85 128	96.66 284	99.83 71	99.59 132

TestCases				99.31 128	99.86 20	98.48 199		99.61 35	97.85 151	99.36 147	99.85 41	95.95 158	99.85 128	96.66 284	99.83 71	99.59 132

jason		99.13 75	99.03 75	99.45 108	99.46 176	98.87 158	99.12 265	99.26 267	98.03 138	99.79 29	99.65 169	97.02 124	99.85 128	99.02 70	99.90 24	99.65 112
jason: jason.
CNVR-MVS		99.42 34	99.30 40	99.78 43	99.62 124	99.71 44	99.26 242	99.52 88	98.82 52	99.39 138	99.71 137	98.96 24	99.85 128	98.59 134	99.80 82	99.77 67

PAPM_NR		99.04 94	98.84 105	99.66 55	99.74 70	99.44 84	99.39 197	99.38 215	97.70 169	99.28 163	99.28 286	98.34 84	99.85 128	96.96 268	99.45 130	99.69 98

test1111		98.04 193	98.11 169	97.83 293	99.74 70	93.82 340	99.58 103	95.40 370	99.12 13	99.65 74	99.93 6	90.73 307	99.84 134	99.43 29	99.38 134	99.82 39

ECVR-MVS		98.04 193	98.05 178	98.00 283	99.74 70	94.37 335	99.59 95	94.98 371	99.13 11	99.66 68	99.93 6	90.67 308	99.84 134	99.40 30	99.38 134	99.80 55

test_yl		98.86 113	98.63 127	99.54 82	99.49 166	99.18 108	99.50 144	99.07 294	98.22 105	99.61 86	99.51 224	95.37 180	99.84 134	98.60 132	98.33 201	99.59 132

DCV-MVSNet		98.86 113	98.63 127	99.54 82	99.49 166	99.18 108	99.50 144	99.07 294	98.22 105	99.61 86	99.51 224	95.37 180	99.84 134	98.60 132	98.33 201	99.59 132

Fast-Effi-MVS+		98.70 135	98.43 148	99.51 98	99.51 155	99.28 98	99.52 133	99.47 159	96.11 302	99.01 216	99.34 272	96.20 151	99.84 134	97.88 194	98.82 182	99.39 176

TSAR-MVS + GP.		99.36 45	99.36 24	99.36 120	99.67 99	98.61 183	99.07 275	99.33 240	99.00 30	99.82 23	99.81 75	99.06 16	99.84 134	99.09 63	99.42 132	99.65 112

tpmrst		98.33 162	98.48 146	97.90 289	99.16 252	94.78 329	99.31 221	99.11 287	97.27 210	99.45 117	99.59 195	95.33 182	99.84 134	98.48 148	98.61 188	99.09 198

Vis-MVSNet		99.12 81	98.97 87	99.56 79	99.78 46	99.10 121	99.68 57	99.66 26	98.49 76	99.86 15	99.87 31	94.77 206	99.84 134	99.19 54	99.41 133	99.74 77
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 144	98.34 153	99.51 98	99.40 192	99.03 131	98.80 322	99.36 224	96.33 283	99.00 220	99.12 308	98.46 76	99.84 134	95.23 314	99.37 141	99.66 108

PatchMatch-RL		98.84 123	98.62 132	99.52 96	99.71 86	99.28 98	99.06 278	99.77 9	97.74 166	99.50 109	99.53 218	95.41 178	99.84 134	97.17 257	99.64 116	99.44 169

EPP-MVSNet		99.13 75	98.99 83	99.53 90	99.65 113	99.06 128	99.81 20	99.33 240	97.43 197	99.60 89	99.88 25	97.14 118	99.84 134	99.13 59	98.94 171	99.69 98

thres100view900		97.76 237	97.45 242	98.69 219	99.72 81	97.86 232	99.59 95	98.74 330	97.93 144	99.26 171	98.62 336	91.75 288	99.83 145	93.22 337	98.18 212	98.37 321

tfpn200view9		97.72 246	97.38 255	98.72 217	99.69 94	97.96 225	99.50 144	98.73 335	97.83 154	99.17 191	98.45 341	91.67 292	99.83 145	93.22 337	98.18 212	98.37 321

test_prior				99.68 54	99.67 99	99.48 80		99.56 56					99.83 145			99.74 77

1314		98.68 139	98.54 143	99.11 155	98.89 291	98.65 178	99.27 234	99.49 129	96.89 244	97.99 310	99.56 206	97.72 105	99.83 145	97.74 210	99.27 145	98.84 222

thres400		97.77 236	97.38 255	98.92 181	99.69 94	97.96 225	99.50 144	98.73 335	97.83 154	99.17 191	98.45 341	91.67 292	99.83 145	93.22 337	98.18 212	98.96 216

casdiffmvs		99.13 75	98.98 86	99.56 79	99.65 113	99.16 111	99.56 113	99.50 121	98.33 93	99.41 130	99.86 36	95.92 161	99.83 145	99.45 28	99.16 151	99.70 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS-test		99.49 14	99.48 10	99.54 82	99.78 46	99.30 96	99.89 2	99.58 48	98.56 70	99.73 47	99.69 151	98.55 70	99.82 151	99.69 5	99.85 54	99.48 158

MVS_Test		99.10 88	98.97 87	99.48 102	99.49 166	99.14 117	99.67 60	99.34 233	97.31 207	99.58 93	99.76 118	97.65 106	99.82 151	98.87 88	99.07 163	99.46 166

dp		97.75 241	97.80 202	97.59 304	99.10 262	93.71 343	99.32 219	98.88 316	96.48 275	99.08 206	99.55 209	92.67 268	99.82 151	96.52 287	98.58 191	99.24 188

RPSCF		98.22 169	98.62 132	96.99 319	99.82 36	91.58 356	99.72 46	99.44 187	96.61 263	99.66 68	99.89 19	95.92 161	99.82 151	97.46 238	99.10 160	99.57 137

PMMVS		98.80 127	98.62 132	99.34 121	99.27 224	98.70 174	98.76 326	99.31 254	97.34 204	99.21 181	99.07 310	97.20 117	99.82 151	98.56 141	98.87 177	99.52 147

EIA-MVS		99.18 66	99.09 68	99.45 108	99.49 166	99.18 108	99.67 60	99.53 83	97.66 174	99.40 135	99.44 244	98.10 94	99.81 156	98.94 77	99.62 119	99.35 179

Effi-MVS+		98.81 124	98.59 139	99.48 102	99.46 176	99.12 120	98.08 360	99.50 121	97.50 190	99.38 141	99.41 252	96.37 146	99.81 156	99.11 61	98.54 195	99.51 153

thres200		97.61 260	97.28 269	98.62 222	99.64 115	98.03 219	99.26 242	98.74 330	97.68 171	99.09 205	98.32 345	91.66 294	99.81 156	92.88 341	98.22 207	98.03 337

tpmvs		97.98 204	98.02 182	97.84 292	99.04 274	94.73 330	99.31 221	99.20 277	96.10 306	98.76 254	99.42 248	94.94 192	99.81 156	96.97 267	98.45 199	98.97 214

casdiffmvs_mvg		99.15 71	99.02 78	99.55 81	99.66 107	99.09 122	99.64 72	99.56 56	98.26 99	99.45 117	99.87 31	96.03 155	99.81 156	99.54 14	99.15 154	99.73 82
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepPCF-MVS	98.18 3	98.81 124	99.37 22	97.12 317	99.60 133	91.75 355	98.61 338	99.44 187	99.35 1	99.83 22	99.85 41	98.70 60	99.81 156	99.02 70	99.91 17	99.81 46

DPM-MVS		98.95 104	98.71 117	99.66 55	99.63 118	99.55 68	98.64 337	99.10 288	97.93 144	99.42 126	99.55 209	98.67 63	99.80 162	95.80 301	99.68 111	99.61 126

DP-MVS Recon		99.12 81	98.95 91	99.65 59	99.74 70	99.70 46	99.27 234	99.57 51	96.40 282	99.42 126	99.68 157	98.75 54	99.80 162	97.98 188	99.72 103	99.44 169

MVS_111021_LR		99.41 38	99.33 30	99.65 59	99.77 52	99.51 77	98.94 308	99.85 6	98.82 52	99.65 74	99.74 126	98.51 73	99.80 162	98.83 101	99.89 33	99.64 119

CS-MVS		99.50 12	99.48 10	99.54 82	99.76 55	99.42 85	99.90 1	99.55 64	98.56 70	99.78 34	99.70 141	98.65 65	99.79 165	99.65 8	99.78 89	99.41 173

Fast-Effi-MVS+-dtu		98.77 130	98.83 107	98.60 223	99.41 187	96.99 270	99.52 133	99.49 129	98.11 122	99.24 173	99.34 272	96.96 128	99.79 165	97.95 190	99.45 130	99.02 209

baseline1		98.31 163	97.95 189	99.38 119	99.50 164	98.74 171	99.59 95	98.93 307	98.41 83	99.14 194	99.60 193	94.59 215	99.79 165	98.48 148	93.29 331	99.61 126

baseline		99.15 71	99.02 78	99.53 90	99.66 107	99.14 117	99.72 46	99.48 141	98.35 90	99.42 126	99.84 51	96.07 153	99.79 165	99.51 18	99.14 155	99.67 105

PVSNet_0	94.43 19	96.09 301	95.47 306	97.94 286	99.31 214	94.34 337	97.81 362	99.70 15	97.12 224	97.46 322	98.75 333	89.71 318	99.79 165	97.69 217	81.69 364	99.68 102

API-MVS		99.04 94	99.03 75	99.06 159	99.40 192	99.31 95	99.55 122	99.56 56	98.54 72	99.33 154	99.39 259	98.76 51	99.78 170	96.98 266	99.78 89	98.07 334

OMC-MVS		99.08 90	99.04 73	99.20 146	99.67 99	98.22 211	99.28 229	99.52 88	98.07 130	99.66 68	99.81 75	97.79 102	99.78 170	97.79 203	99.81 78	99.60 128

GeoE		98.85 120	98.62 132	99.53 90	99.61 128	99.08 125	99.80 24	99.51 102	97.10 228	99.31 157	99.78 105	95.23 188	99.77 172	98.21 169	99.03 166	99.75 73

alignmvs		98.81 124	98.56 142	99.58 75	99.43 182	99.42 85	99.51 138	98.96 305	98.61 67	99.35 150	98.92 327	94.78 203	99.77 172	99.35 34	98.11 217	99.54 141

tpm cat1		97.39 273	97.36 257	97.50 308	99.17 250	93.73 342	99.43 176	99.31 254	91.27 351	98.71 258	99.08 309	94.31 226	99.77 172	96.41 291	98.50 197	99.00 210

CostFormer		97.72 246	97.73 215	97.71 300	99.15 255	94.02 339	99.54 126	99.02 298	94.67 328	99.04 213	99.35 269	92.35 280	99.77 172	98.50 147	97.94 220	99.34 181

test_241102_ONE					99.84 30	99.90 2		99.48 141	99.07 22	99.91 6	99.74 126	99.20 7	99.76 176

MDTV_nov1_ep13			98.32 155		99.11 259	94.44 334	99.27 234	98.74 330	97.51 189	99.40 135	99.62 186	94.78 203	99.76 176	97.59 222	98.81 184

canonicalmvs		99.02 97	98.86 103	99.51 98	99.42 184	99.32 92	99.80 24	99.48 141	98.63 65	99.31 157	98.81 330	97.09 121	99.75 178	99.27 49	97.90 221	99.47 164

Effi-MVS+-dtu		98.78 128	98.89 98	98.47 243	99.33 207	96.91 276	99.57 107	99.30 258	98.47 77	99.41 130	98.99 319	96.78 132	99.74 179	98.73 112	99.38 134	98.74 236

patchmatchnet-post											98.70 334	94.79 202	99.74 179

SCA		98.19 173	98.16 163	98.27 266	99.30 215	95.55 311	99.07 275	98.97 303	97.57 181	99.43 123	99.57 203	92.72 263	99.74 179	97.58 223	99.20 149	99.52 147

BH-untuned		98.42 153	98.36 151	98.59 224	99.49 166	96.70 282	99.27 234	99.13 286	97.24 214	98.80 249	99.38 260	95.75 168	99.74 179	97.07 262	99.16 151	99.33 182

BH-RMVSNet		98.41 155	98.08 174	99.40 115	99.41 187	98.83 165	99.30 223	98.77 326	97.70 169	98.94 228	99.65 169	92.91 258	99.74 179	96.52 287	99.55 125	99.64 119

MVS_111021_HR		99.41 38	99.32 32	99.66 55	99.72 81	99.47 81	98.95 306	99.85 6	98.82 52	99.54 102	99.73 132	98.51 73	99.74 179	98.91 82	99.88 36	99.77 67

test_post											65.99 375	94.65 214	99.73 185

XVG-ACMP-BASELINE		97.83 227	97.71 217	98.20 268	99.11 259	96.33 296	99.41 185	99.52 88	98.06 134	99.05 212	99.50 227	89.64 320	99.73 185	97.73 211	97.38 255	98.53 302

HyFIR lowres test		99.11 85	98.92 93	99.65 59	99.90 4	99.37 89	99.02 289	99.91 3	97.67 173	99.59 92	99.75 121	95.90 163	99.73 185	99.53 15	99.02 168	99.86 18

DeepMVS_CX				93.34 340	99.29 219	82.27 367		99.22 273	85.15 362	96.33 339	99.05 313	90.97 305	99.73 185	93.57 334	97.77 224	98.01 338

Patchmatch-test		97.93 210	97.65 222	98.77 214	99.18 244	97.07 261	99.03 286	99.14 285	96.16 297	98.74 255	99.57 203	94.56 217	99.72 189	93.36 336	99.11 157	99.52 147

LPG-MVS_test		98.22 169	98.13 167	98.49 237	99.33 207	97.05 263	99.58 103	99.55 64	97.46 191	99.24 173	99.83 55	92.58 270	99.72 189	98.09 178	97.51 239	98.68 255

LGP-MVS_train				98.49 237	99.33 207	97.05 263		99.55 64	97.46 191	99.24 173	99.83 55	92.58 270	99.72 189	98.09 178	97.51 239	98.68 255

BH-w/o		98.00 202	97.89 198	98.32 259	99.35 201	96.20 300	99.01 294	98.90 314	96.42 280	98.38 292	99.00 318	95.26 186	99.72 189	96.06 295	98.61 188	99.03 207

ACMP	97.20 11	98.06 187	97.94 191	98.45 245	99.37 198	97.01 268	99.44 172	99.49 129	97.54 186	98.45 288	99.79 99	91.95 284	99.72 189	97.91 192	97.49 244	98.62 285
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 197	97.90 194	98.40 252	99.23 232	96.80 280	99.70 49	99.60 40	97.12 224	98.18 302	99.70 141	91.73 290	99.72 189	98.39 155	97.45 247	98.68 255
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
test_post1							99.23 247				65.14 376	94.18 231	99.71 195	97.58 223

ADS-MVSNet		98.20 172	98.08 174	98.56 231	99.33 207	96.48 291	99.23 247	99.15 283	96.24 290	99.10 202	99.67 163	94.11 232	99.71 195	96.81 276	99.05 164	99.48 158

JIA-IIPM		97.50 267	97.02 279	98.93 179	98.73 313	97.80 234	99.30 223	98.97 303	91.73 350	98.91 232	94.86 364	95.10 190	99.71 195	97.58 223	97.98 219	99.28 186

EPMVS		97.82 230	97.65 222	98.35 256	98.88 292	95.98 303	99.49 154	94.71 373	97.57 181	99.26 171	99.48 235	92.46 277	99.71 195	97.87 196	99.08 162	99.35 179

TDRefinement		95.42 309	94.57 315	97.97 285	89.83 374	96.11 302	99.48 158	98.75 327	96.74 251	96.68 336	99.88 25	88.65 329	99.71 195	98.37 158	82.74 363	98.09 333

ACMM	97.58 5	98.37 160	98.34 153	98.48 239	99.41 187	97.10 257	99.56 113	99.45 179	98.53 73	99.04 213	99.85 41	93.00 254	99.71 195	98.74 110	97.45 247	98.64 274
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 207	97.77 208	98.57 228	99.59 135	96.61 287	99.45 167	99.08 291	98.21 107	98.88 237	99.80 88	88.66 328	99.70 201	98.58 135	97.72 225	99.39 176

CHOSEN 280x420		99.12 81	99.13 63	99.08 156	99.66 107	97.89 229	98.43 348	99.71 13	98.88 46	99.62 83	99.76 118	96.63 137	99.70 201	99.46 27	99.99 1	99.66 108

DROMVSNet		99.44 29	99.39 19	99.58 75	99.56 143	99.49 78	99.88 4	99.58 48	98.38 85	99.73 47	99.69 151	98.20 90	99.70 201	99.64 9	99.82 75	99.54 141

PatchmatchNet		98.31 163	98.36 151	98.19 269	99.16 252	95.32 319	99.27 234	98.92 309	97.37 203	99.37 143	99.58 199	94.90 196	99.70 201	97.43 241	99.21 148	99.54 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 183	97.99 184	98.44 248	99.41 187	96.96 274	99.60 89	99.56 56	98.09 125	98.15 303	99.91 11	90.87 306	99.70 201	98.88 85	97.45 247	98.67 262
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP_MVS		98.27 168	98.22 161	98.44 248	99.29 219	96.97 272	99.39 197	99.47 159	98.97 38	99.11 199	99.61 190	92.71 265	99.69 206	97.78 204	97.63 227	98.67 262

plane_prior5								99.47 159					99.69 206	97.78 204	97.63 227	98.67 262

D2MVS		98.41 155	98.50 145	98.15 274	99.26 226	96.62 286	99.40 193	99.61 35	97.71 168	98.98 222	99.36 266	96.04 154	99.67 208	98.70 115	97.41 252	98.15 331

IS-MVSNet		99.05 93	98.87 100	99.57 77	99.73 77	99.32 92	99.75 39	99.20 277	98.02 139	99.56 97	99.86 36	96.54 140	99.67 208	98.09 178	99.13 156	99.73 82

CLD-MVS		98.16 177	98.10 170	98.33 257	99.29 219	96.82 279	98.75 327	99.44 187	97.83 154	99.13 195	99.55 209	92.92 256	99.67 208	98.32 164	97.69 226	98.48 306
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 277	97.30 267	97.09 318	99.43 182	93.31 348	99.73 45	98.87 318	98.83 51	99.28 163	99.80 88	84.45 351	99.66 211	97.88 194	97.45 247	98.30 323

AUN-MVS		96.88 284	96.31 291	98.59 224	99.48 174	97.04 266	99.27 234	99.22 273	97.44 196	98.51 284	99.41 252	91.97 283	99.66 211	97.71 214	83.83 361	99.07 204

UniMVSNet_ETH3D		97.32 275	96.81 282	98.87 196	99.40 192	97.46 245	99.51 138	99.53 83	95.86 310	98.54 283	99.77 112	82.44 357	99.66 211	98.68 120	97.52 237	99.50 156

OPM-MVS		98.19 173	98.10 170	98.45 245	98.88 292	97.07 261	99.28 229	99.38 215	98.57 69	99.22 178	99.81 75	92.12 281	99.66 211	98.08 182	97.54 236	98.61 294
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 213	97.78 206	98.32 259	99.46 176	96.68 284	99.56 113	99.54 72	98.41 83	97.79 318	99.87 31	90.18 315	99.66 211	98.05 186	97.18 262	98.62 285

hse-mvs2		97.50 267	97.14 275	98.59 224	99.49 166	97.05 263	99.28 229	99.22 273	98.94 41	99.66 68	99.42 248	94.93 193	99.65 216	99.48 24	83.80 362	99.08 199

VPA-MVSNet		98.29 166	97.95 189	99.30 132	99.16 252	99.54 70	99.50 144	99.58 48	98.27 98	99.35 150	99.37 263	92.53 272	99.65 216	99.35 34	94.46 316	98.72 239

TR-MVS		97.76 237	97.41 253	98.82 207	99.06 270	97.87 230	98.87 316	98.56 341	96.63 262	98.68 266	99.22 295	92.49 273	99.65 216	95.40 311	97.79 223	98.95 218

gm-plane-assit					98.54 332	92.96 350			94.65 329		99.15 303		99.64 219	97.56 228

HQP4-MVS										98.66 267			99.64 219			98.64 274

HQP-MVS		98.02 197	97.90 194	98.37 255	99.19 241	96.83 277	98.98 299	99.39 209	98.24 101	98.66 267	99.40 255	92.47 274	99.64 219	97.19 254	97.58 232	98.64 274

PAPM		97.59 261	97.09 277	99.07 158	99.06 270	98.26 210	98.30 355	99.10 288	94.88 324	98.08 305	99.34 272	96.27 149	99.64 219	89.87 354	98.92 174	99.31 184

TAPA-MVS	97.07 15	97.74 243	97.34 262	98.94 177	99.70 91	97.53 243	99.25 244	99.51 102	91.90 349	99.30 159	99.63 181	98.78 47	99.64 219	88.09 361	99.87 39	99.65 112
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 159	98.09 173	99.24 142	99.26 226	99.32 92	99.56 113	99.55 64	97.45 194	98.71 258	99.83 55	93.23 250	99.63 224	98.88 85	96.32 277	98.76 231

ITE_SJBPF				98.08 276	99.29 219	96.37 294		98.92 309	98.34 91	98.83 245	99.75 121	91.09 303	99.62 225	95.82 299	97.40 253	98.25 327

LF4IMVS		97.52 264	97.46 241	97.70 301	98.98 282	95.55 311	99.29 227	98.82 322	98.07 130	98.66 267	99.64 175	89.97 316	99.61 226	97.01 263	96.68 267	97.94 344

tpm		97.67 256	97.55 229	98.03 278	99.02 276	95.01 325	99.43 176	98.54 343	96.44 278	99.12 197	99.34 272	91.83 287	99.60 227	97.75 209	96.46 273	99.48 158

tpm2		97.44 272	97.34 262	97.74 299	99.15 255	94.36 336	99.45 167	98.94 306	93.45 342	98.90 234	99.44 244	91.35 300	99.59 228	97.31 245	98.07 218	99.29 185

baseline2		97.87 219	97.55 229	98.82 207	99.18 244	98.02 220	99.41 185	96.58 367	96.97 237	96.51 337	99.17 300	93.43 247	99.57 229	97.71 214	99.03 166	98.86 220

MS-PatchMatch		97.24 279	97.32 265	96.99 319	98.45 335	93.51 347	98.82 320	99.32 250	97.41 200	98.13 304	99.30 282	88.99 324	99.56 230	95.68 305	99.80 82	97.90 347

TinyColmap		97.12 281	96.89 281	97.83 293	99.07 267	95.52 314	98.57 341	98.74 330	97.58 180	97.81 317	99.79 99	88.16 335	99.56 230	95.10 315	97.21 260	98.39 319

USDC		97.34 274	97.20 273	97.75 298	99.07 267	95.20 321	98.51 345	99.04 297	97.99 140	98.31 296	99.86 36	89.02 323	99.55 232	95.67 306	97.36 256	98.49 305

MSLP-MVS++		99.46 23	99.47 12	99.44 112	99.60 133	99.16 111	99.41 185	99.71 13	98.98 35	99.45 117	99.78 105	99.19 9	99.54 233	99.28 46	99.84 62	99.63 122

TAMVS		99.12 81	99.08 69	99.24 142	99.46 176	98.55 187	99.51 138	99.46 168	98.09 125	99.45 117	99.82 62	98.34 84	99.51 234	98.70 115	98.93 172	99.67 105

EPNet_dtu		98.03 195	97.96 187	98.23 267	98.27 337	95.54 313	99.23 247	98.75 327	99.02 25	97.82 316	99.71 137	96.11 152	99.48 235	93.04 340	99.65 115	99.69 98
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EG-PatchMatch MVS		95.97 302	95.69 303	96.81 325	97.78 344	92.79 351	99.16 257	98.93 307	96.16 297	94.08 353	99.22 295	82.72 355	99.47 236	95.67 306	97.50 241	98.17 330

MVP-Stereo		97.81 232	97.75 213	97.99 284	97.53 348	96.60 288	98.96 303	98.85 319	97.22 216	97.23 327	99.36 266	95.28 183	99.46 237	95.51 308	99.78 89	97.92 346
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 145	98.67 121	98.30 261	99.35 201	95.59 310	99.50 144	99.55 64	98.60 68	99.39 138	99.83 55	94.48 220	99.45 238	98.75 109	98.56 194	99.85 21

test-LLR		98.06 187	97.90 194	98.55 233	98.79 304	97.10 257	98.67 333	97.75 355	97.34 204	98.61 278	98.85 328	94.45 221	99.45 238	97.25 248	99.38 134	99.10 194

TESTMET0.1,1		97.55 262	97.27 272	98.40 252	98.93 287	96.53 289	98.67 333	97.61 358	96.96 238	98.64 274	99.28 286	88.63 330	99.45 238	97.30 246	99.38 134	99.21 190

test-mter		97.49 270	97.13 276	98.55 233	98.79 304	97.10 257	98.67 333	97.75 355	96.65 258	98.61 278	98.85 328	88.23 334	99.45 238	97.25 248	99.38 134	99.10 194

mvs_anonymous		99.03 96	98.99 83	99.16 150	99.38 196	98.52 193	99.51 138	99.38 215	97.79 159	99.38 141	99.81 75	97.30 114	99.45 238	99.35 34	98.99 169	99.51 153

tfpnnormal		97.84 225	97.47 239	98.98 171	99.20 239	99.22 105	99.64 72	99.61 35	96.32 284	98.27 299	99.70 141	93.35 249	99.44 243	95.69 304	95.40 300	98.27 325

v7n		97.87 219	97.52 233	98.92 181	98.76 311	98.58 185	99.84 13	99.46 168	96.20 293	98.91 232	99.70 141	94.89 197	99.44 243	96.03 296	93.89 326	98.75 233

jajsoiax		98.43 152	98.28 158	98.88 192	98.60 328	98.43 203	99.82 17	99.53 83	98.19 110	98.63 275	99.80 88	93.22 252	99.44 243	99.22 52	97.50 241	98.77 229

mvs_tets		98.40 158	98.23 160	98.91 185	98.67 321	98.51 195	99.66 64	99.53 83	98.19 110	98.65 273	99.81 75	92.75 260	99.44 243	99.31 41	97.48 245	98.77 229

Vis-MVSNet (Re-imp)		98.87 110	98.72 115	99.31 128	99.71 86	98.88 157	99.80 24	99.44 187	97.91 146	99.36 147	99.78 105	95.49 177	99.43 247	97.91 192	99.11 157	99.62 124

OPU-MVS				99.64 64	99.56 143	99.72 42	99.60 89				99.70 141	99.27 5	99.42 248	98.24 168	99.80 82	99.79 59

Anonymous20231211		97.88 217	97.54 232	98.90 187	99.71 86	98.53 189	99.48 158	99.57 51	94.16 333	98.81 247	99.68 157	93.23 250	99.42 248	98.84 98	94.42 318	98.76 231

MVS_0304		96.79 287	96.52 287	97.59 304	99.22 235	94.92 328	99.04 285	99.59 43	96.49 271	98.43 289	98.99 319	80.48 360	99.39 250	97.15 258	99.27 145	98.47 308

VPNet		97.84 225	97.44 247	99.01 165	99.21 237	98.94 151	99.48 158	99.57 51	98.38 85	99.28 163	99.73 132	88.89 325	99.39 250	99.19 54	93.27 332	98.71 241

iter_conf_final		98.71 134	98.61 138	98.99 169	99.49 166	98.96 143	99.63 76	99.41 198	98.19 110	99.39 138	99.77 112	94.82 199	99.38 252	99.30 44	97.52 237	98.64 274

nrg030		98.64 143	98.42 149	99.28 137	99.05 273	99.69 47	99.81 20	99.46 168	98.04 136	99.01 216	99.82 62	96.69 136	99.38 252	99.34 38	94.59 315	98.78 226

iter_conf05		98.55 146	98.44 147	98.87 196	99.34 205	98.60 184	99.55 122	99.42 195	98.21 107	99.37 143	99.77 112	93.55 246	99.38 252	99.30 44	97.48 245	98.63 282

GA-MVS		97.85 222	97.47 239	99.00 167	99.38 196	97.99 222	98.57 341	99.15 283	97.04 233	98.90 234	99.30 282	89.83 317	99.38 252	96.70 281	98.33 201	99.62 124

UniMVSNet (Re)		98.29 166	98.00 183	99.13 154	99.00 278	99.36 90	99.49 154	99.51 102	97.95 142	98.97 224	99.13 305	96.30 148	99.38 252	98.36 160	93.34 330	98.66 270

FIs		98.78 128	98.63 127	99.23 144	99.18 244	99.54 70	99.83 16	99.59 43	98.28 96	98.79 251	99.81 75	96.75 134	99.37 257	99.08 65	96.38 275	98.78 226

PS-MVSNAJss		98.92 106	98.92 93	98.90 187	98.78 307	98.53 189	99.78 31	99.54 72	98.07 130	99.00 220	99.76 118	99.01 18	99.37 257	99.13 59	97.23 259	98.81 223

CDS-MVSNet		99.09 89	99.03 75	99.25 140	99.42 184	98.73 172	99.45 167	99.46 168	98.11 122	99.46 116	99.77 112	98.01 97	99.37 257	98.70 115	98.92 174	99.66 108
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 306	95.16 310	97.51 307	99.30 215	93.69 344	98.88 314	95.78 368	85.09 363	98.78 252	92.65 366	91.29 301	99.37 257	94.85 319	99.85 54	99.46 166

v1192		97.81 232	97.44 247	98.91 185	98.88 292	98.68 175	99.51 138	99.34 233	96.18 295	99.20 184	99.34 272	94.03 235	99.36 261	95.32 313	95.18 304	98.69 250

EI-MVSNet		98.67 140	98.67 121	98.68 220	99.35 201	97.97 223	99.50 144	99.38 215	96.93 243	99.20 184	99.83 55	97.87 99	99.36 261	98.38 156	97.56 234	98.71 241

MVSTER		98.49 147	98.32 155	99.00 167	99.35 201	99.02 132	99.54 126	99.38 215	97.41 200	99.20 184	99.73 132	93.86 240	99.36 261	98.87 88	97.56 234	98.62 285

gg-mvs-nofinetune		96.17 299	95.32 309	98.73 216	98.79 304	98.14 215	99.38 202	94.09 374	91.07 354	98.07 308	91.04 370	89.62 321	99.35 264	96.75 278	99.09 161	98.68 255

pm-mvs1		97.68 253	97.28 269	98.88 192	99.06 270	98.62 181	99.50 144	99.45 179	96.32 284	97.87 314	99.79 99	92.47 274	99.35 264	97.54 230	93.54 329	98.67 262

OurMVSNet-221017-0		97.88 217	97.77 208	98.19 269	98.71 317	96.53 289	99.88 4	99.00 300	97.79 159	98.78 252	99.94 4	91.68 291	99.35 264	97.21 250	96.99 266	98.69 250

EGC-MVSNET		82.80 335	77.86 341	97.62 302	97.91 341	96.12 301	99.33 218	99.28 264	8.40 378	25.05 379	99.27 289	84.11 352	99.33 267	89.20 356	98.22 207	97.42 355

pmmvs6		96.53 291	96.09 295	97.82 295	98.69 319	95.47 315	99.37 204	99.47 159	93.46 341	97.41 323	99.78 105	87.06 342	99.33 267	96.92 273	92.70 339	98.65 272

mvsmamba		98.92 106	98.87 100	99.08 156	99.07 267	99.16 111	99.88 4	99.51 102	98.15 116	99.40 135	99.89 19	97.12 119	99.33 267	99.38 31	97.40 253	98.73 238

V42		98.06 187	97.79 203	98.86 200	98.98 282	98.84 162	99.69 51	99.34 233	96.53 269	99.30 159	99.37 263	94.67 212	99.32 270	97.57 227	94.66 313	98.42 315

lessismore_v0				97.79 297	98.69 319	95.44 317		94.75 372		95.71 345	99.87 31	88.69 327	99.32 270	95.89 298	94.93 311	98.62 285

OpenMVS_ROB	92.34 20	94.38 319	93.70 323	96.41 330	97.38 350	93.17 349	99.06 278	98.75 327	86.58 361	94.84 351	98.26 346	81.53 358	99.32 270	89.01 357	97.87 222	96.76 358

bld_raw_dy_0_64		98.69 137	98.58 140	98.99 169	98.88 292	98.96 143	99.80 24	99.41 198	97.91 146	99.32 155	99.87 31	95.70 171	99.31 273	99.09 63	97.27 258	98.71 241

v8		97.95 209	97.63 225	98.93 179	98.95 286	98.81 168	99.80 24	99.41 198	96.03 307	99.10 202	99.42 248	94.92 195	99.30 274	96.94 270	94.08 324	98.66 270

v1921920		97.80 234	97.45 242	98.84 204	98.80 303	98.53 189	99.52 133	99.34 233	96.15 299	99.24 173	99.47 238	93.98 236	99.29 275	95.40 311	95.13 306	98.69 250

anonymousdsp		98.44 151	98.28 158	98.94 177	98.50 333	98.96 143	99.77 33	99.50 121	97.07 230	98.87 240	99.77 112	94.76 207	99.28 276	98.66 122	97.60 230	98.57 300

MVSFormer		99.17 68	99.12 64	99.29 135	99.51 155	98.94 151	99.88 4	99.46 168	97.55 183	99.80 27	99.65 169	97.39 110	99.28 276	99.03 68	99.85 54	99.65 112

test_djsdf		98.67 140	98.57 141	98.98 171	98.70 318	98.91 155	99.88 4	99.46 168	97.55 183	99.22 178	99.88 25	95.73 169	99.28 276	99.03 68	97.62 229	98.75 233

cascas		97.69 251	97.43 251	98.48 239	98.60 328	97.30 248	98.18 359	99.39 209	92.96 345	98.41 290	98.78 332	93.77 243	99.27 279	98.16 175	98.61 188	98.86 220

v144192		97.92 213	97.60 227	98.87 196	98.83 302	98.65 178	99.55 122	99.34 233	96.20 293	99.32 155	99.40 255	94.36 223	99.26 280	96.37 292	95.03 308	98.70 246

RRT_MVS		98.70 135	98.66 124	98.83 206	98.90 289	98.45 201	99.89 2	99.28 264	97.76 162	98.94 228	99.92 10	96.98 126	99.25 281	99.28 46	97.00 265	98.80 224

v2v482		98.06 187	97.77 208	98.92 181	98.90 289	98.82 166	99.57 107	99.36 224	96.65 258	99.19 187	99.35 269	94.20 228	99.25 281	97.72 213	94.97 309	98.69 250

v1240		97.69 251	97.32 265	98.79 212	98.85 300	98.43 203	99.48 158	99.36 224	96.11 302	99.27 167	99.36 266	93.76 244	99.24 283	94.46 323	95.23 303	98.70 246

v1144		97.98 204	97.69 218	98.85 203	98.87 296	98.66 177	99.54 126	99.35 229	96.27 288	99.23 177	99.35 269	94.67 212	99.23 284	96.73 279	95.16 305	98.68 255

v10		97.85 222	97.52 233	98.86 200	98.99 279	98.67 176	99.75 39	99.41 198	95.70 311	98.98 222	99.41 252	94.75 208	99.23 284	96.01 297	94.63 314	98.67 262

WR-MVS_H		98.13 180	97.87 199	98.90 187	99.02 276	98.84 162	99.70 49	99.59 43	97.27 210	98.40 291	99.19 299	95.53 175	99.23 284	98.34 161	93.78 327	98.61 294

miper_enhance_ethall		98.16 177	98.08 174	98.41 250	98.96 285	97.72 237	98.45 347	99.32 250	96.95 240	98.97 224	99.17 300	97.06 123	99.22 287	97.86 197	95.99 284	98.29 324

GG-mvs-BLEND				98.45 245	98.55 331	98.16 213	99.43 176	93.68 375		97.23 327	98.46 340	89.30 322	99.22 287	95.43 310	98.22 207	97.98 342

FC-MVSNet-test		98.75 131	98.62 132	99.15 153	99.08 266	99.45 83	99.86 12	99.60 40	98.23 104	98.70 264	99.82 62	96.80 131	99.22 287	99.07 66	96.38 275	98.79 225

UniMVSNet_NR-MVSNet		98.22 169	97.97 186	98.96 174	98.92 288	98.98 136	99.48 158	99.53 83	97.76 162	98.71 258	99.46 242	96.43 145	99.22 287	98.57 138	92.87 337	98.69 250

DU-MVS		98.08 186	97.79 203	98.96 174	98.87 296	98.98 136	99.41 185	99.45 179	97.87 148	98.71 258	99.50 227	94.82 199	99.22 287	98.57 138	92.87 337	98.68 255

cl____		98.01 200	97.84 201	98.55 233	99.25 230	97.97 223	98.71 331	99.34 233	96.47 277	98.59 281	99.54 214	95.65 173	99.21 292	97.21 250	95.77 290	98.46 312

WR-MVS		98.06 187	97.73 215	99.06 159	98.86 299	99.25 102	99.19 254	99.35 229	97.30 208	98.66 267	99.43 246	93.94 237	99.21 292	98.58 135	94.28 320	98.71 241

test_0402		96.64 289	96.24 292	97.85 291	98.85 300	96.43 293	99.44 172	99.26 267	93.52 339	96.98 334	99.52 221	88.52 331	99.20 294	92.58 346	97.50 241	97.93 345

SixPastTwentyTwo		97.50 267	97.33 264	98.03 278	98.65 322	96.23 299	99.77 33	98.68 338	97.14 221	97.90 313	99.93 6	90.45 309	99.18 295	97.00 264	96.43 274	98.67 262

cl22		97.85 222	97.64 224	98.48 239	99.09 264	97.87 230	98.60 340	99.33 240	97.11 227	98.87 240	99.22 295	92.38 279	99.17 296	98.21 169	95.99 284	98.42 315

IterMVS-SCA-FT		97.82 230	97.75 213	98.06 277	99.57 139	96.36 295	99.02 289	99.49 129	97.18 218	98.71 258	99.72 136	92.72 263	99.14 297	97.44 240	95.86 289	98.67 262

pmmvs5		97.52 264	97.30 267	98.16 271	98.57 330	96.73 281	99.27 234	98.90 314	96.14 300	98.37 293	99.53 218	91.54 297	99.14 297	97.51 232	95.87 288	98.63 282

v148		97.79 235	97.55 229	98.50 236	98.74 312	97.72 237	99.54 126	99.33 240	96.26 289	98.90 234	99.51 224	94.68 211	99.14 297	97.83 200	93.15 334	98.63 282

miper_ehance_all_eth		98.18 175	98.10 170	98.41 250	99.23 232	97.72 237	98.72 330	99.31 254	96.60 265	98.88 237	99.29 284	97.29 115	99.13 300	97.60 221	95.99 284	98.38 320

NR-MVSNet		97.97 207	97.61 226	99.02 164	98.87 296	99.26 101	99.47 163	99.42 195	97.63 176	97.08 332	99.50 227	95.07 191	99.13 300	97.86 197	93.59 328	98.68 255

IterMVS		97.83 227	97.77 208	98.02 280	99.58 137	96.27 298	99.02 289	99.48 141	97.22 216	98.71 258	99.70 141	92.75 260	99.13 300	97.46 238	96.00 283	98.67 262
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 320	94.90 312	91.84 344	97.24 354	80.01 370	98.52 344	99.48 141	89.01 358	91.99 359	99.67 163	85.67 346	99.13 300	95.44 309	97.03 264	96.39 360
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 192	97.96 187	98.33 257	99.26 226	97.38 247	98.56 343	99.31 254	96.65 258	98.88 237	99.52 221	96.58 138	99.12 304	97.39 243	95.53 298	98.47 308

pmmvs4		98.13 180	97.90 194	98.81 209	98.61 327	98.87 158	98.99 296	99.21 276	96.44 278	99.06 211	99.58 199	95.90 163	99.11 305	97.18 256	96.11 281	98.46 312

TransMVSNet (Re)		97.15 280	96.58 285	98.86 200	99.12 257	98.85 161	99.49 154	98.91 312	95.48 314	97.16 330	99.80 88	93.38 248	99.11 305	94.16 329	91.73 342	98.62 285

ambc				93.06 342	92.68 370	82.36 366	98.47 346	98.73 335		95.09 349	97.41 353	55.55 371	99.10 307	96.42 290	91.32 343	97.71 348

Baseline_NR-MVSNet		97.76 237	97.45 242	98.68 220	99.09 264	98.29 208	99.41 185	98.85 319	95.65 312	98.63 275	99.67 163	94.82 199	99.10 307	98.07 185	92.89 336	98.64 274

test_vis3_rt		87.04 331	85.81 334	90.73 347	93.99 369	81.96 368	99.76 36	90.23 380	92.81 346	81.35 368	91.56 368	40.06 377	99.07 309	94.27 326	88.23 355	91.15 368

CP-MVSNet		98.09 184	97.78 206	99.01 165	98.97 284	99.24 103	99.67 60	99.46 168	97.25 212	98.48 287	99.64 175	93.79 242	99.06 310	98.63 125	94.10 323	98.74 236

PS-CasMVS		97.93 210	97.59 228	98.95 176	98.99 279	99.06 128	99.68 57	99.52 88	97.13 222	98.31 296	99.68 157	92.44 278	99.05 311	98.51 146	94.08 324	98.75 233

K. test v3		97.10 282	96.79 283	98.01 281	98.72 315	96.33 296	99.87 9	97.05 361	97.59 178	96.16 341	99.80 88	88.71 326	99.04 312	96.69 282	96.55 272	98.65 272

new_pmnet		96.38 295	96.03 296	97.41 309	98.13 340	95.16 324	99.05 280	99.20 277	93.94 334	97.39 324	98.79 331	91.61 296	99.04 312	90.43 352	95.77 290	98.05 336

DIV-MVS_self_test		98.01 200	97.85 200	98.48 239	99.24 231	97.95 227	98.71 331	99.35 229	96.50 270	98.60 280	99.54 214	95.72 170	99.03 314	97.21 250	95.77 290	98.46 312

IterMVS-LS		98.46 150	98.42 149	98.58 227	99.59 135	98.00 221	99.37 204	99.43 193	96.94 242	99.07 207	99.59 195	97.87 99	99.03 314	98.32 164	95.62 295	98.71 241
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 258	97.68 219	97.55 306	98.62 325	94.97 326	98.84 318	99.30 258	96.83 249	98.19 301	99.34 272	97.01 125	99.02 316	95.00 318	96.01 282	98.64 274

Patchmtry		97.75 241	97.40 254	98.81 209	99.10 262	98.87 158	99.11 271	99.33 240	94.83 325	98.81 247	99.38 260	94.33 224	99.02 316	96.10 294	95.57 296	98.53 302

N_pmnet		94.95 314	95.83 301	92.31 343	98.47 334	79.33 371	99.12 265	92.81 378	93.87 335	97.68 319	99.13 305	93.87 239	99.01 318	91.38 349	96.19 279	98.59 298

CR-MVSNet		98.17 176	97.93 192	98.87 196	99.18 244	98.49 197	99.22 251	99.33 240	96.96 238	99.56 97	99.38 260	94.33 224	99.00 319	94.83 320	98.58 191	99.14 191

c3_l		98.12 182	98.04 179	98.38 254	99.30 215	97.69 241	98.81 321	99.33 240	96.67 256	98.83 245	99.34 272	97.11 120	98.99 320	97.58 223	95.34 301	98.48 306

test0.0.03 1		97.71 249	97.42 252	98.56 231	98.41 336	97.82 233	98.78 324	98.63 339	97.34 204	98.05 309	98.98 322	94.45 221	98.98 321	95.04 317	97.15 263	98.89 219

PatchT		97.03 283	96.44 289	98.79 212	98.99 279	98.34 207	99.16 257	99.07 294	92.13 348	99.52 106	97.31 357	94.54 219	98.98 321	88.54 359	98.73 187	99.03 207

GBi-Net		97.68 253	97.48 237	98.29 262	99.51 155	97.26 252	99.43 176	99.48 141	96.49 271	99.07 207	99.32 279	90.26 311	98.98 321	97.10 259	96.65 268	98.62 285

test1		97.68 253	97.48 237	98.29 262	99.51 155	97.26 252	99.43 176	99.48 141	96.49 271	99.07 207	99.32 279	90.26 311	98.98 321	97.10 259	96.65 268	98.62 285

FMVSNet3		98.03 195	97.76 212	98.84 204	99.39 195	98.98 136	99.40 193	99.38 215	96.67 256	99.07 207	99.28 286	92.93 255	98.98 321	97.10 259	96.65 268	98.56 301

FMVSNet2		97.72 246	97.36 257	98.80 211	99.51 155	98.84 162	99.45 167	99.42 195	96.49 271	98.86 244	99.29 284	90.26 311	98.98 321	96.44 289	96.56 271	98.58 299

FMVSNet1		96.84 285	96.36 290	98.29 262	99.32 213	97.26 252	99.43 176	99.48 141	95.11 319	98.55 282	99.32 279	83.95 353	98.98 321	95.81 300	96.26 278	98.62 285

ppachtmachnet_test		97.49 270	97.45 242	97.61 303	98.62 325	95.24 320	98.80 322	99.46 168	96.11 302	98.22 300	99.62 186	96.45 143	98.97 328	93.77 331	95.97 287	98.61 294

TranMVSNet+NR-MVSNet		97.93 210	97.66 221	98.76 215	98.78 307	98.62 181	99.65 70	99.49 129	97.76 162	98.49 286	99.60 193	94.23 227	98.97 328	98.00 187	92.90 335	98.70 246

test_method		91.10 327	91.36 329	90.31 348	95.85 361	73.72 378	94.89 367	99.25 269	68.39 370	95.82 344	99.02 317	80.50 359	98.95 330	93.64 333	94.89 312	98.25 327

ADS-MVSNet2		98.02 197	98.07 177	97.87 290	99.33 207	95.19 322	99.23 247	99.08 291	96.24 290	99.10 202	99.67 163	94.11 232	98.93 331	96.81 276	99.05 164	99.48 158

ET-MVSNet_ETH3D		96.49 292	95.64 305	99.05 161	99.53 149	98.82 166	98.84 318	97.51 359	97.63 176	84.77 364	99.21 298	92.09 282	98.91 332	98.98 73	92.21 341	99.41 173

miper_lstm_enhance		98.00 202	97.91 193	98.28 265	99.34 205	97.43 246	98.88 314	99.36 224	96.48 275	98.80 249	99.55 209	95.98 156	98.91 332	97.27 247	95.50 299	98.51 304

PEN-MVS		97.76 237	97.44 247	98.72 217	98.77 310	98.54 188	99.78 31	99.51 102	97.06 232	98.29 298	99.64 175	92.63 269	98.89 334	98.09 178	93.16 333	98.72 239

testgi		97.65 258	97.50 236	98.13 275	99.36 200	96.45 292	99.42 183	99.48 141	97.76 162	97.87 314	99.45 243	91.09 303	98.81 335	94.53 322	98.52 196	99.13 193

testf1		90.42 329	90.68 331	89.65 349	97.78 344	73.97 376	99.13 263	98.81 323	89.62 356	91.80 360	98.93 325	62.23 369	98.80 336	86.61 366	91.17 344	96.19 361

APD_test2		90.42 329	90.68 331	89.65 349	97.78 344	73.97 376	99.13 263	98.81 323	89.62 356	91.80 360	98.93 325	62.23 369	98.80 336	86.61 366	91.17 344	96.19 361

MIMVSNet		97.73 244	97.45 242	98.57 228	99.45 181	97.50 244	99.02 289	98.98 302	96.11 302	99.41 130	99.14 304	90.28 310	98.74 338	95.74 302	98.93 172	99.47 164

LCM-MVSNet-Re		97.83 227	98.15 164	96.87 324	99.30 215	92.25 353	99.59 95	98.26 346	97.43 197	96.20 340	99.13 305	96.27 149	98.73 339	98.17 174	98.99 169	99.64 119

DTE-MVSNet		97.51 266	97.19 274	98.46 244	98.63 324	98.13 216	99.84 13	99.48 141	96.68 255	97.97 312	99.67 163	92.92 256	98.56 340	96.88 275	92.60 340	98.70 246

PC_three_1452									98.18 114	99.84 17	99.70 141	99.31 3	98.52 341	98.30 166	99.80 82	99.81 46

mvsany_test3		93.77 322	93.45 324	94.74 336	95.78 362	88.01 361	99.64 72	98.25 347	98.28 96	94.31 352	97.97 350	68.89 365	98.51 342	97.50 233	90.37 349	97.71 348

UnsupCasMVSNet_bld		93.53 323	92.51 326	96.58 329	97.38 350	93.82 340	98.24 356	99.48 141	91.10 353	93.10 357	96.66 359	74.89 363	98.37 343	94.03 330	87.71 356	97.56 353

Anonymous20240521		96.20 298	95.89 300	97.13 316	97.72 347	94.96 327	99.79 30	99.29 262	93.01 344	97.20 329	99.03 315	89.69 319	98.36 344	91.16 350	96.13 280	98.07 334

test_f		91.90 326	91.26 330	93.84 338	95.52 366	85.92 363	99.69 51	98.53 344	95.31 316	93.87 354	96.37 361	55.33 372	98.27 345	95.70 303	90.98 347	97.32 356

MDA-MVSNet_test_wron		95.45 308	94.60 314	98.01 281	98.16 339	97.21 255	99.11 271	99.24 271	93.49 340	80.73 370	98.98 322	93.02 253	98.18 346	94.22 328	94.45 317	98.64 274

UnsupCasMVSNet_eth		96.44 293	96.12 294	97.40 310	98.65 322	95.65 308	99.36 208	99.51 102	97.13 222	96.04 343	98.99 319	88.40 332	98.17 347	96.71 280	90.27 350	98.40 318

KD-MVS_2432*1600		94.62 315	93.72 321	97.31 311	97.19 356	95.82 306	98.34 351	99.20 277	95.00 322	97.57 320	98.35 343	87.95 337	98.10 348	92.87 342	77.00 368	98.01 338

miper_refine_blended		94.62 315	93.72 321	97.31 311	97.19 356	95.82 306	98.34 351	99.20 277	95.00 322	97.57 320	98.35 343	87.95 337	98.10 348	92.87 342	77.00 368	98.01 338

YYNet1		95.36 310	94.51 316	97.92 287	97.89 342	97.10 257	99.10 273	99.23 272	93.26 343	80.77 369	99.04 314	92.81 259	98.02 350	94.30 324	94.18 322	98.64 274

EU-MVSNet		97.98 204	98.03 180	97.81 296	98.72 315	96.65 285	99.66 64	99.66 26	98.09 125	98.35 294	99.82 62	95.25 187	98.01 351	97.41 242	95.30 302	98.78 226

Gipuma		90.99 328	90.15 333	93.51 339	98.73 313	90.12 359	93.98 368	99.45 179	79.32 366	92.28 358	94.91 363	69.61 364	97.98 352	87.42 362	95.67 294	92.45 366
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 311	94.73 313	97.15 314	95.53 365	95.94 304	99.35 213	99.10 288	95.13 317	93.55 355	97.54 352	88.15 336	97.91 353	94.58 321	89.69 353	97.61 351

PM-MVS		92.96 324	92.23 327	95.14 335	95.61 363	89.98 360	99.37 204	98.21 349	94.80 326	95.04 350	97.69 351	65.06 366	97.90 354	94.30 324	89.98 352	97.54 354

MDA-MVSNet-bldmvs		94.96 313	93.98 319	97.92 287	98.24 338	97.27 250	99.15 260	99.33 240	93.80 336	80.09 371	99.03 315	88.31 333	97.86 355	93.49 335	94.36 319	98.62 285

Patchmatch-RL test		95.84 304	95.81 302	95.95 333	95.61 363	90.57 358	98.24 356	98.39 345	95.10 321	95.20 347	98.67 335	94.78 203	97.77 356	96.28 293	90.02 351	99.51 153

Anonymous20231206		96.22 296	96.03 296	96.79 326	97.31 353	94.14 338	99.63 76	99.08 291	96.17 296	97.04 333	99.06 312	93.94 237	97.76 357	86.96 364	95.06 307	98.47 308

SD-MVS		99.41 38	99.52 6	99.05 161	99.74 70	99.68 48	99.46 166	99.52 88	99.11 14	99.88 10	99.91 11	99.43 1	97.70 358	98.72 113	99.93 12	99.77 67
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
DSMNet-mixed		97.25 277	97.35 259	96.95 322	97.84 343	93.61 346	99.57 107	96.63 366	96.13 301	98.87 240	98.61 338	94.59 215	97.70 358	95.08 316	98.86 178	99.55 139

pmmvs3		94.09 321	93.25 325	96.60 328	94.76 368	94.49 333	98.92 310	98.18 351	89.66 355	96.48 338	98.06 349	86.28 343	97.33 360	89.68 355	87.20 357	97.97 343

KD-MVS_self_test		95.00 312	94.34 317	96.96 321	97.07 358	95.39 318	99.56 113	99.44 187	95.11 319	97.13 331	97.32 356	91.86 286	97.27 361	90.35 353	81.23 365	98.23 329

FMVSNet5		96.43 294	96.19 293	97.15 314	99.11 259	95.89 305	99.32 219	99.52 88	94.47 332	98.34 295	99.07 310	87.54 341	97.07 362	92.61 345	95.72 293	98.47 308

new-patchmatchnet		94.48 318	94.08 318	95.67 334	95.08 367	92.41 352	99.18 255	99.28 264	94.55 331	93.49 356	97.37 355	87.86 339	97.01 363	91.57 348	88.36 354	97.61 351

LCM-MVSNet		86.80 333	85.22 337	91.53 345	87.81 375	80.96 369	98.23 358	98.99 301	71.05 368	90.13 363	96.51 360	48.45 376	96.88 364	90.51 351	85.30 359	96.76 358

CL-MVSNet_self_test		94.49 317	93.97 320	96.08 332	96.16 360	93.67 345	98.33 353	99.38 215	95.13 317	97.33 325	98.15 347	92.69 267	96.57 365	88.67 358	79.87 366	97.99 341

MIMVSNet1		95.51 307	95.04 311	96.92 323	97.38 350	95.60 309	99.52 133	99.50 121	93.65 338	96.97 335	99.17 300	85.28 349	96.56 366	88.36 360	95.55 297	98.60 297

test20.03		96.12 300	95.96 298	96.63 327	97.44 349	95.45 316	99.51 138	99.38 215	96.55 268	96.16 341	99.25 292	93.76 244	96.17 367	87.35 363	94.22 321	98.27 325

tmp_tt		82.80 335	81.52 338	86.66 351	66.61 381	68.44 379	92.79 370	97.92 353	68.96 369	80.04 372	99.85 41	85.77 345	96.15 368	97.86 197	43.89 374	95.39 364

test_fmvs3		92.10 325	91.77 328	93.08 341	96.19 359	86.25 362	99.82 17	98.62 340	96.65 258	95.19 348	96.90 358	55.05 373	95.93 369	96.63 286	90.92 348	97.06 357

PMMVS2		86.87 332	85.37 336	91.35 346	90.21 373	83.80 365	98.89 313	97.45 360	83.13 365	91.67 362	95.03 362	48.49 375	94.70 370	85.86 368	77.62 367	95.54 363

PMVS	70.75 22	75.98 341	74.97 342	79.01 357	70.98 380	55.18 381	93.37 369	98.21 349	65.08 374	61.78 375	93.83 365	21.74 382	92.53 371	78.59 370	91.12 346	89.34 370
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 334	85.65 335	82.75 355	86.77 376	63.39 380	98.35 350	98.92 309	74.11 367	83.39 366	98.98 322	50.85 374	92.40 372	84.54 369	94.97 309	92.46 365

MVE	76.82 21	76.91 340	74.31 344	84.70 352	85.38 378	76.05 375	96.88 366	93.17 376	67.39 371	71.28 373	89.01 372	21.66 383	87.69 373	71.74 372	72.29 370	90.35 369
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 337	79.88 339	82.81 354	90.75 372	76.38 374	97.69 363	95.76 369	66.44 372	83.52 365	92.25 367	62.54 368	87.16 374	68.53 373	61.40 371	84.89 372

EMVS		80.02 338	79.22 340	82.43 356	91.19 371	76.40 373	97.55 365	92.49 379	66.36 373	83.01 367	91.27 369	64.63 367	85.79 375	65.82 374	60.65 372	85.08 371

ANet_high		77.30 339	74.86 343	84.62 353	75.88 379	77.61 372	97.63 364	93.15 377	88.81 359	64.27 374	89.29 371	36.51 378	83.93 376	75.89 371	52.31 373	92.33 367

wuyk23d		40.18 342	41.29 347	36.84 358	86.18 377	49.12 382	79.73 371	22.81 383	27.64 375	25.46 378	28.45 378	21.98 381	48.89 377	55.80 375	23.56 377	12.51 375

test123		39.01 344	42.50 346	28.53 359	39.17 382	20.91 383	98.75 327	19.17 384	19.83 377	38.57 376	66.67 374	33.16 379	15.42 378	37.50 377	29.66 376	49.26 373

testmvs		39.17 343	43.78 345	25.37 360	36.04 383	16.84 384	98.36 349	26.56 382	20.06 376	38.51 377	67.32 373	29.64 380	15.30 379	37.59 376	39.90 375	43.98 374

test_blank		0.13 348	0.17 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	1.57 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet_test		0.02 349	0.03 352	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.27 380	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

DCPMVS		0.02 349	0.03 352	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.27 380	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

cdsmvs_eth3d_5k		24.64 345	32.85 348	0.00 361	0.00 384	0.00 385	0.00 372	99.51 102	0.00 379	0.00 380	99.56 206	96.58 138	0.00 380	0.00 378	0.00 378	0.00 376

pcd_1.5k_mvsjas		8.27 347	11.03 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.27 380	99.01 18	0.00 380	0.00 378	0.00 378	0.00 376

sosnet-low-res		0.02 349	0.03 352	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.27 380	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

sosnet		0.02 349	0.03 352	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.27 380	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uncertanet		0.02 349	0.03 352	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.27 380	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

Regformer		0.02 349	0.03 352	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.27 380	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

ab-mvs-re		8.30 346	11.06 349	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	99.58 199	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet		0.02 349	0.03 352	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.27 380	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

FOURS1					99.91 1	99.93 1	99.87 9	99.56 56	99.10 15	99.81 24

test_one_0601					99.81 40	99.88 8		99.49 129	98.97 38	99.65 74	99.81 75	99.09 14

eth-test2					0.00 384

eth-test					0.00 384

RE-MVS-def			99.34 28		99.76 55	99.82 22	99.63 76	99.52 88	98.38 85	99.76 42	99.82 62	98.75 54		98.61 129	99.81 78	99.77 67

IU-MVS					99.84 30	99.88 8		99.32 250	98.30 95	99.84 17				98.86 93	99.85 54	99.89 5

save fliter					99.76 55	99.59 62	99.14 262	99.40 206	99.00 30

test0726					99.85 24	99.89 4	99.62 82	99.50 121	99.10 15	99.86 15	99.82 62	98.94 29

GSMVS																99.52 147

test_part2					99.81 40	99.83 16				99.77 37

sam_mvs1												94.86 198				99.52 147

sam_mvs												94.72 210

MTGPA								99.47 159

MTMP							99.54 126	98.88 316

test9_res														97.49 234	99.72 103	99.75 73

agg_prior2														97.21 250	99.73 102	99.75 73

test_prior4						99.56 66	98.99 296

test_prior2							98.96 303		98.34 91	99.01 216	99.52 221	98.68 61		97.96 189	99.74 100

新几何2							99.01 294

旧先验1					99.74 70	99.59 62		99.54 72			99.69 151	98.47 75			99.68 111	99.73 82

原ACMM2							98.95 306

test222					99.75 63	99.49 78	98.91 312	99.49 129	96.42 280	99.34 153	99.65 169	98.28 87			99.69 108	99.72 88

segment_acmp												98.96 24

testdata1							98.85 317		98.32 94

plane_prior7					99.29 219	97.03 267

plane_prior6					99.27 224	96.98 271						92.71 265

plane_prior4											99.61 190

plane_prior3						97.00 269			98.69 63	99.11 199

plane_prior2							99.39 197		98.97 38

plane_prior1					99.26 226

plane_prior						96.97 272	99.21 253		98.45 79						97.60 230

n2								0.00 385

nn								0.00 385

door-mid								98.05 352

test11								99.35 229

door								97.92 353

HQP5-MVS						96.83 277

HQP-NCC					99.19 241		98.98 299		98.24 101	98.66 267

ACMP_Plane					99.19 241		98.98 299		98.24 101	98.66 267

BP-MVS														97.19 254

HQP3-MVS								99.39 209							97.58 232

HQP2-MVS												92.47 274

NP-MVS					99.23 232	96.92 275					99.40 255

MDTV_nov1_ep13_2view						95.18 323	99.35 213		96.84 247	99.58 93		95.19 189		97.82 201		99.46 166

ACMMP++_ref															97.19 261

ACMMP++															97.43 251

Test By Simon												98.75 54

High-resolution multi-view benchmark