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.

APDe-MVS		99.66 1	99.57 3	99.92 1	99.77 54	99.89 4	99.75 37	99.56 58	99.02 21	99.88 6	99.85 38	99.18 10	99.96 20	99.22 49	99.92 13	99.90 1

test_0728_SECOND				99.91 2	99.84 33	99.89 4	99.57 104	99.51 107					99.96 20	98.93 79	99.86 53	99.88 8

DPE-MVS		99.46 27	99.32 36	99.91 2	99.78 48	99.88 8	99.36 207	99.51 107	98.73 61	99.88 6	99.84 47	98.72 64	99.96 20	98.16 181	99.87 42	99.88 8
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
zzz-MVS		99.49 17	99.36 27	99.89 4	99.90 4	99.86 13	99.36 207	99.47 166	98.79 57	99.68 62	99.81 71	98.43 88	99.97 12	98.88 85	99.90 25	99.83 33

MTAPA		99.52 14	99.39 22	99.89 4	99.90 4	99.86 13	99.66 57	99.47 166	98.79 57	99.68 62	99.81 71	98.43 88	99.97 12	98.88 85	99.90 25	99.83 33

DVP-MVS++		99.59 3	99.50 10	99.88 6	99.51 161	99.88 8	99.87 9	99.51 107	98.99 31	99.88 6	99.81 71	99.27 5	99.96 20	98.85 96	99.80 90	99.81 46

SED-MVS		99.61 2	99.52 8	99.88 6	99.84 33	99.90 2	99.60 83	99.48 148	99.08 16	99.91 2	99.81 71	99.20 7	99.96 20	98.91 82	99.85 60	99.79 62

DVP-MVS		99.57 8	99.47 14	99.88 6	99.85 26	99.89 4	99.57 104	99.37 237	99.10 12	99.81 25	99.80 86	98.94 35	99.96 20	98.93 79	99.86 53	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
MP-MVS-pluss		99.37 52	99.20 65	99.88 6	99.90 4	99.87 12	99.30 223	99.52 93	97.18 224	99.60 94	99.79 98	98.79 51	99.95 47	98.83 102	99.91 18	99.83 33
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 42	99.27 56	99.88 6	99.89 9	99.80 29	99.67 53	99.50 128	98.70 63	99.77 38	99.49 238	98.21 102	99.95 47	98.46 155	99.77 101	99.88 8
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
ACMMP_NAP		99.47 25	99.34 32	99.88 6	99.87 16	99.86 13	99.47 160	99.48 148	98.05 137	99.76 43	99.86 33	98.82 48	99.93 73	98.82 106	99.91 18	99.84 22

MSC_two_6792asdad				99.87 12	99.51 161	99.76 41		99.33 254					99.96 20	98.87 89	99.84 68	99.89 2

No_MVS				99.87 12	99.51 161	99.76 41		99.33 254					99.96 20	98.87 89	99.84 68	99.89 2

ZNCC-MVS		99.47 25	99.33 34	99.87 12	99.87 16	99.81 27	99.64 68	99.67 22	98.08 131	99.55 106	99.64 182	98.91 40	99.96 20	98.72 115	99.90 25	99.82 40

region2R		99.48 22	99.35 30	99.87 12	99.88 12	99.80 29	99.65 65	99.66 27	98.13 120	99.66 73	99.68 162	98.96 29	99.96 20	98.62 129	99.87 42	99.84 22

HPM-MVS++		99.39 50	99.23 63	99.87 12	99.75 68	99.84 16	99.43 174	99.51 107	98.68 65	99.27 172	99.53 225	98.64 73	99.96 20	98.44 157	99.80 90	99.79 62

XVS		99.53 12	99.42 18	99.87 12	99.85 26	99.83 17	99.69 46	99.68 19	98.98 34	99.37 148	99.74 129	98.81 49	99.94 58	98.79 107	99.86 53	99.84 22

X-MVStestdata		96.55 301	95.45 316	99.87 12	99.85 26	99.83 17	99.69 46	99.68 19	98.98 34	99.37 148	64.01 380	98.81 49	99.94 58	98.79 107	99.86 53	99.84 22

MP-MVS		99.33 56	99.15 69	99.87 12	99.88 12	99.82 23	99.66 57	99.46 176	98.09 127	99.48 118	99.74 129	98.29 99	99.96 20	97.93 198	99.87 42	99.82 40
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SteuartSystems-ACMMP		99.54 10	99.42 18	99.87 12	99.82 39	99.81 27	99.59 90	99.51 107	98.62 67	99.79 30	99.83 51	99.28 4	99.97 12	98.48 151	99.90 25	99.84 22
Skip Steuart: Steuart Systems R&D Blog.
testtj		99.12 90	98.87 109	99.86 21	99.72 89	99.79 33	99.44 168	99.51 107	97.29 214	99.59 97	99.74 129	98.15 107	99.96 20	96.74 286	99.69 118	99.81 46

SR-MVS		99.43 37	99.29 50	99.86 21	99.75 68	99.83 17	99.59 90	99.62 34	98.21 108	99.73 49	99.79 98	98.68 67	99.96 20	98.44 157	99.77 101	99.79 62

HFP-MVS		99.49 17	99.37 25	99.86 21	99.87 16	99.80 29	99.66 57	99.67 22	98.15 116	99.68 62	99.69 154	99.06 16	99.96 20	98.69 120	99.87 42	99.84 22

#test#		99.43 37	99.29 50	99.86 21	99.87 16	99.80 29	99.55 119	99.67 22	97.83 156	99.68 62	99.69 154	99.06 16	99.96 20	98.39 159	99.87 42	99.84 22

ACMMPR		99.49 17	99.36 27	99.86 21	99.87 16	99.79 33	99.66 57	99.67 22	98.15 116	99.67 68	99.69 154	98.95 32	99.96 20	98.69 120	99.87 42	99.84 22

PGM-MVS		99.45 29	99.31 43	99.86 21	99.87 16	99.78 40	99.58 98	99.65 32	97.84 155	99.71 55	99.80 86	99.12 13	99.97 12	98.33 167	99.87 42	99.83 33

mPP-MVS		99.44 33	99.30 46	99.86 21	99.88 12	99.79 33	99.69 46	99.48 148	98.12 122	99.50 114	99.75 123	98.78 52	99.97 12	98.57 140	99.89 35	99.83 33

test1172		99.43 37	99.29 50	99.85 28	99.75 68	99.82 23	99.60 83	99.56 58	98.28 99	99.74 47	99.79 98	98.53 79	99.95 47	98.55 146	99.78 97	99.79 62

SR-MVS-dyc-post		99.45 29	99.31 43	99.85 28	99.76 57	99.82 23	99.63 70	99.52 93	98.38 87	99.76 43	99.82 58	98.53 79	99.95 47	98.61 132	99.81 86	99.77 72

GST-MVS		99.40 49	99.24 61	99.85 28	99.86 22	99.79 33	99.60 83	99.67 22	97.97 143	99.63 84	99.68 162	98.52 81	99.95 47	98.38 161	99.86 53	99.81 46

SMA-MVS		99.44 33	99.30 46	99.85 28	99.73 84	99.83 17	99.56 110	99.47 166	97.45 198	99.78 35	99.82 58	99.18 10	99.91 96	98.79 107	99.89 35	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
APD-MVS_3200maxsize		99.48 22	99.35 30	99.85 28	99.76 57	99.83 17	99.63 70	99.54 76	98.36 91	99.79 30	99.82 58	98.86 44	99.95 47	98.62 129	99.81 86	99.78 70

HPM-MVS_fast		99.51 15	99.40 21	99.85 28	99.91 1	99.79 33	99.76 35	99.56 58	97.72 171	99.76 43	99.75 123	99.13 12	99.92 85	99.07 65	99.92 13	99.85 18

CP-MVS		99.45 29	99.32 36	99.85 28	99.83 37	99.75 43	99.69 46	99.52 93	98.07 132	99.53 109	99.63 188	98.93 39	99.97 12	98.74 111	99.91 18	99.83 33

APD-MVS		99.27 64	99.08 77	99.84 35	99.75 68	99.79 33	99.50 140	99.50 128	97.16 226	99.77 38	99.82 58	98.78 52	99.94 58	97.56 234	99.86 53	99.80 56
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
abl_6		99.44 33	99.31 43	99.83 36	99.85 26	99.75 43	99.66 57	99.59 44	98.13 120	99.82 23	99.81 71	98.60 74	99.96 20	98.46 155	99.88 38	99.79 62

HPM-MVS		99.42 42	99.28 54	99.83 36	99.90 4	99.72 47	99.81 20	99.54 76	97.59 182	99.68 62	99.63 188	98.91 40	99.94 58	98.58 138	99.91 18	99.84 22
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MCST-MVS		99.43 37	99.30 46	99.82 38	99.79 46	99.74 46	99.29 227	99.40 219	98.79 57	99.52 111	99.62 193	98.91 40	99.90 111	98.64 127	99.75 105	99.82 40

ACMMP		99.45 29	99.32 36	99.82 38	99.89 9	99.67 57	99.62 76	99.69 18	98.12 122	99.63 84	99.84 47	98.73 63	99.96 20	98.55 146	99.83 77	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
3Dnovator+	97.12 13	99.18 76	98.97 96	99.82 38	99.17 257	99.68 54	99.81 20	99.51 107	99.20 5	98.72 267	99.89 17	95.68 188	99.97 12	98.86 94	99.86 53	99.81 46

TSAR-MVS + MP.		99.58 5	99.50 10	99.81 41	99.91 1	99.66 59	99.63 70	99.39 223	98.91 46	99.78 35	99.85 38	99.36 2	99.94 58	98.84 99	99.88 38	99.82 40
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
3Dnovator	97.25 9	99.24 70	99.05 79	99.81 41	99.12 264	99.66 59	99.84 14	99.74 10	99.09 15	98.92 241	99.90 13	95.94 176	99.98 7	98.95 76	99.92 13	99.79 62

UA-Net		99.42 42	99.29 50	99.80 43	99.62 135	99.55 80	99.50 140	99.70 15	98.79 57	99.77 38	99.96 1	97.45 123	99.96 20	98.92 81	99.90 25	99.89 2

CDPH-MVS		99.13 84	98.91 104	99.80 43	99.75 68	99.71 49	99.15 263	99.41 210	96.60 272	99.60 94	99.55 216	98.83 47	99.90 111	97.48 241	99.83 77	99.78 70

QAPM		98.67 154	98.30 172	99.80 43	99.20 246	99.67 57	99.77 32	99.72 11	94.74 333	98.73 266	99.90 13	95.78 183	99.98 7	96.96 275	99.88 38	99.76 77

SF-MVS		99.38 51	99.24 61	99.79 46	99.79 46	99.68 54	99.57 104	99.54 76	97.82 161	99.71 55	99.80 86	98.95 32	99.93 73	98.19 176	99.84 68	99.74 83

NCCC		99.34 55	99.19 66	99.79 46	99.61 139	99.65 62	99.30 223	99.48 148	98.86 48	99.21 188	99.63 188	98.72 64	99.90 111	98.25 172	99.63 131	99.80 56

CNVR-MVS		99.42 42	99.30 46	99.78 48	99.62 135	99.71 49	99.26 243	99.52 93	98.82 52	99.39 142	99.71 141	98.96 29	99.85 136	98.59 137	99.80 90	99.77 72

DP-MVS		99.16 80	98.95 100	99.78 48	99.77 54	99.53 85	99.41 183	99.50 128	97.03 241	99.04 221	99.88 23	97.39 124	99.92 85	98.66 125	99.90 25	99.87 13

ETH3D-3000-0.1		99.21 72	99.02 87	99.77 50	99.73 84	99.69 52	99.38 200	99.51 107	97.45 198	99.61 90	99.75 123	98.51 82	99.91 96	97.45 246	99.83 77	99.71 103

train_agg		99.02 109	98.77 124	99.77 50	99.67 110	99.65 62	99.05 282	99.41 210	96.28 292	98.95 235	99.49 238	98.76 57	99.91 96	97.63 225	99.72 112	99.75 78

DeepC-MVS_fast	98.69 1	99.49 17	99.39 22	99.77 50	99.63 129	99.59 73	99.36 207	99.46 176	99.07 18	99.79 30	99.82 58	98.85 45	99.92 85	98.68 122	99.87 42	99.82 40
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
agg_prior1		99.01 112	98.76 126	99.76 53	99.67 110	99.62 66	98.99 298	99.40 219	96.26 295	98.87 249	99.49 238	98.77 55	99.91 96	97.69 222	99.72 112	99.75 78

xxxxxxxxxxxxxcwj		99.43 37	99.32 36	99.75 54	99.76 57	99.59 73	99.14 265	99.53 87	99.00 28	99.71 55	99.80 86	98.95 32	99.93 73	98.19 176	99.84 68	99.74 83

Regformer-2		99.54 10	99.47 14	99.75 54	99.71 95	99.52 88	99.49 150	99.49 136	98.94 41	99.83 20	99.76 118	99.01 19	99.94 58	99.15 57	99.87 42	99.80 56

新几何1				99.75 54	99.75 68	99.59 73		99.54 76	96.76 258	99.29 168	99.64 182	98.43 88	99.94 58	96.92 280	99.66 126	99.72 96

1121		99.09 99	98.87 109	99.75 54	99.74 76	99.60 70	99.27 234	99.48 148	96.82 257	99.25 179	99.65 175	98.38 93	99.93 73	97.53 237	99.67 125	99.73 90

test12				99.75 54	99.64 126	99.61 68		99.29 276		99.21 188		98.38 93	99.89 119		99.74 108	99.74 83

CPTT-MVS		99.11 95	98.90 105	99.74 59	99.80 45	99.46 96	99.59 90	99.49 136	97.03 241	99.63 84	99.69 154	97.27 131	99.96 20	97.82 207	99.84 68	99.81 46

LS3D		99.27 64	99.12 72	99.74 59	99.18 251	99.75 43	99.56 110	99.57 53	98.45 81	99.49 117	99.85 38	97.77 117	99.94 58	98.33 167	99.84 68	99.52 158

ETH3 D test6400		98.70 148	98.35 167	99.73 61	99.69 105	99.60 70	99.16 259	99.45 188	95.42 321	99.27 172	99.60 200	97.39 124	99.91 96	95.36 319	99.83 77	99.70 105

Regformer-4		99.59 3	99.54 6	99.73 61	99.76 57	99.41 102	99.58 98	99.49 136	99.02 21	99.88 6	99.80 86	99.00 25	99.94 58	99.45 22	99.92 13	99.84 22

VNet		99.11 95	98.90 105	99.73 61	99.52 159	99.56 78	99.41 183	99.39 223	99.01 24	99.74 47	99.78 105	95.56 190	99.92 85	99.52 11	98.18 220	99.72 96

ETH3D cwj APD-0.16		99.06 103	98.84 116	99.72 64	99.51 161	99.60 70	99.23 248	99.44 197	97.04 239	99.39 142	99.67 168	98.30 98	99.92 85	97.27 253	99.69 118	99.64 129

Regformer-1		99.53 12	99.47 14	99.72 64	99.71 95	99.44 98	99.49 150	99.46 176	98.95 40	99.83 20	99.76 118	99.01 19	99.93 73	99.17 54	99.87 42	99.80 56

114514_t		98.93 118	98.67 135	99.72 64	99.85 26	99.53 85	99.62 76	99.59 44	92.65 352	99.71 55	99.78 105	98.06 110	99.90 111	98.84 99	99.91 18	99.74 83

PHI-MVS		99.30 59	99.17 68	99.70 67	99.56 153	99.52 88	99.58 98	99.80 8	97.12 230	99.62 88	99.73 136	98.58 75	99.90 111	98.61 132	99.91 18	99.68 112

Regformer-3		99.57 8	99.53 7	99.68 68	99.76 57	99.29 114	99.58 98	99.44 197	99.01 24	99.87 12	99.80 86	98.97 28	99.91 96	99.44 24	99.92 13	99.83 33

test_prior3		99.21 72	99.05 79	99.68 68	99.67 110	99.48 93	98.96 306	99.56 58	98.34 93	99.01 224	99.52 228	98.68 67	99.83 153	97.96 195	99.74 108	99.74 83

test_prior				99.68 68	99.67 110	99.48 93		99.56 58					99.83 153			99.74 83

DPM-MVS		98.95 117	98.71 130	99.66 71	99.63 129	99.55 80	98.64 340	99.10 302	97.93 146	99.42 130	99.55 216	98.67 70	99.80 170	95.80 308	99.68 123	99.61 137

PAPM_NR		99.04 106	98.84 116	99.66 71	99.74 76	99.44 98	99.39 195	99.38 229	97.70 173	99.28 169	99.28 296	98.34 96	99.85 136	96.96 275	99.45 140	99.69 108

MVS_111021_HR		99.41 46	99.32 36	99.66 71	99.72 89	99.47 95	98.95 310	99.85 6	98.82 52	99.54 107	99.73 136	98.51 82	99.74 187	98.91 82	99.88 38	99.77 72

AdaColmap		99.01 112	98.80 121	99.66 71	99.56 153	99.54 82	99.18 257	99.70 15	98.18 114	99.35 155	99.63 188	96.32 164	99.90 111	97.48 241	99.77 101	99.55 150

原ACMM1				99.65 75	99.73 84	99.33 107		99.47 166	97.46 195	99.12 204	99.66 174	98.67 70	99.91 96	97.70 221	99.69 118	99.71 103

DELS-MVS		99.48 22	99.42 18	99.65 75	99.72 89	99.40 104	99.05 282	99.66 27	99.14 7	99.57 101	99.80 86	98.46 86	99.94 58	99.57 8	99.84 68	99.60 139
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
DP-MVS Recon		99.12 90	98.95 100	99.65 75	99.74 76	99.70 51	99.27 234	99.57 53	96.40 288	99.42 130	99.68 162	98.75 60	99.80 170	97.98 194	99.72 112	99.44 180

MVS_111021_LR		99.41 46	99.33 34	99.65 75	99.77 54	99.51 90	98.94 312	99.85 6	98.82 52	99.65 79	99.74 129	98.51 82	99.80 170	98.83 102	99.89 35	99.64 129

HyFIR lowres test		99.11 95	98.92 102	99.65 75	99.90 4	99.37 105	99.02 291	99.91 3	97.67 177	99.59 97	99.75 123	95.90 179	99.73 193	99.53 10	99.02 177	99.86 15

OPU-MVS				99.64 80	99.56 153	99.72 47	99.60 83				99.70 145	99.27 5	99.42 255	98.24 173	99.80 90	99.79 62

EI-MVSNet-UG-set		99.58 5	99.57 3	99.64 80	99.78 48	99.14 134	99.60 83	99.45 188	99.01 24	99.90 4	99.83 51	98.98 27	99.93 73	99.59 6	99.95 8	99.86 15

EI-MVSNet-Vis-set		99.58 5	99.56 5	99.64 80	99.78 48	99.15 133	99.61 82	99.45 188	99.01 24	99.89 5	99.82 58	99.01 19	99.92 85	99.56 9	99.95 8	99.85 18

F-COLMAP		99.19 74	99.04 82	99.64 80	99.78 48	99.27 117	99.42 181	99.54 76	97.29 214	99.41 134	99.59 203	98.42 91	99.93 73	98.19 176	99.69 118	99.73 90

DeepC-MVS	98.35 2	99.30 59	99.19 66	99.64 80	99.82 39	99.23 121	99.62 76	99.55 67	98.94 41	99.63 84	99.95 2	95.82 182	99.94 58	99.37 29	99.97 5	99.73 90
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		99.36 53	99.28 54	99.61 85	99.86 22	99.07 142	99.47 160	99.93 2	97.66 178	99.71 55	99.86 33	97.73 118	99.96 20	99.47 20	99.82 83	99.79 62

WTY-MVS		99.06 103	98.88 108	99.61 85	99.62 135	99.16 128	99.37 203	99.56 58	98.04 138	99.53 109	99.62 193	96.84 145	99.94 58	98.85 96	98.49 206	99.72 96

CANet		99.25 69	99.14 70	99.59 87	99.41 193	99.16 128	99.35 213	99.57 53	98.82 52	99.51 113	99.61 197	96.46 159	99.95 47	99.59 6	99.98 2	99.65 122

1112_ss		98.98 114	98.77 124	99.59 87	99.68 109	99.02 146	99.25 245	99.48 148	97.23 221	99.13 202	99.58 206	96.93 144	99.90 111	98.87 89	98.78 193	99.84 22

CNLPA		99.14 82	98.99 92	99.59 87	99.58 147	99.41 102	99.16 259	99.44 197	98.45 81	99.19 194	99.49 238	98.08 109	99.89 119	97.73 216	99.75 105	99.48 169

alignmvs		98.81 137	98.56 156	99.58 90	99.43 189	99.42 100	99.51 134	98.96 317	98.61 68	99.35 155	98.92 335	94.78 218	99.77 180	99.35 31	98.11 225	99.54 152

DROMVSNet		99.44 33	99.39 22	99.58 90	99.56 153	99.49 91	99.88 4	99.58 50	98.38 87	99.73 49	99.69 154	98.20 103	99.70 209	99.64 5	99.82 83	99.54 152

Test_1112_low_res		98.89 121	98.66 138	99.57 92	99.69 105	98.95 161	99.03 288	99.47 166	96.98 243	99.15 200	99.23 304	96.77 149	99.89 119	98.83 102	98.78 193	99.86 15

IS-MVSNet		99.05 105	98.87 109	99.57 92	99.73 84	99.32 108	99.75 37	99.20 291	98.02 141	99.56 102	99.86 33	96.54 157	99.67 215	98.09 184	99.13 165	99.73 90

casdiffmvs		99.13 84	98.98 95	99.56 94	99.65 124	99.16 128	99.56 110	99.50 128	98.33 96	99.41 134	99.86 33	95.92 177	99.83 153	99.45 22	99.16 161	99.70 105

Vis-MVSNet		99.12 90	98.97 96	99.56 94	99.78 48	99.10 138	99.68 51	99.66 27	98.49 77	99.86 13	99.87 29	94.77 221	99.84 142	99.19 51	99.41 143	99.74 83
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		99.50 16	99.48 12	99.54 96	99.76 57	99.42 100	99.90 1	99.55 67	98.56 71	99.78 35	99.70 145	98.65 72	99.79 173	99.65 4	99.78 97	99.41 184

test_yl		98.86 125	98.63 141	99.54 96	99.49 173	99.18 125	99.50 140	99.07 307	98.22 106	99.61 90	99.51 232	95.37 195	99.84 142	98.60 135	98.33 209	99.59 143

DCV-MVSNet		98.86 125	98.63 141	99.54 96	99.49 173	99.18 125	99.50 140	99.07 307	98.22 106	99.61 90	99.51 232	95.37 195	99.84 142	98.60 135	98.33 209	99.59 143

CS-MVS-test		99.49 17	99.48 12	99.54 96	99.78 48	99.30 112	99.89 2	99.58 50	98.56 71	99.73 49	99.69 154	98.55 78	99.82 160	99.69 1	99.85 60	99.48 169

testdata				99.54 96	99.75 68	98.95 161		99.51 107	97.07 236	99.43 127	99.70 145	98.87 43	99.94 58	97.76 212	99.64 129	99.72 96

LFMVS		97.90 227	97.35 270	99.54 96	99.52 159	99.01 148	99.39 195	98.24 353	97.10 234	99.65 79	99.79 98	84.79 362	99.91 96	99.28 43	98.38 208	99.69 108

ab-mvs		98.86 125	98.63 141	99.54 96	99.64 126	99.19 123	99.44 168	99.54 76	97.77 165	99.30 165	99.81 71	94.20 244	99.93 73	99.17 54	98.82 190	99.49 168

MAR-MVS		98.86 125	98.63 141	99.54 96	99.37 204	99.66 59	99.45 164	99.54 76	96.61 270	99.01 224	99.40 265	97.09 136	99.86 130	97.68 224	99.53 138	99.10 202
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
GeoE		98.85 133	98.62 146	99.53 104	99.61 139	99.08 140	99.80 24	99.51 107	97.10 234	99.31 163	99.78 105	95.23 203	99.77 180	98.21 174	99.03 175	99.75 78

baseline		99.15 81	99.02 87	99.53 104	99.66 119	99.14 134	99.72 41	99.48 148	98.35 92	99.42 130	99.84 47	96.07 170	99.79 173	99.51 12	99.14 164	99.67 115

sss		99.17 78	99.05 79	99.53 104	99.62 135	98.97 153	99.36 207	99.62 34	97.83 156	99.67 68	99.65 175	97.37 128	99.95 47	99.19 51	99.19 160	99.68 112

EPP-MVSNet		99.13 84	98.99 92	99.53 104	99.65 124	99.06 143	99.81 20	99.33 254	97.43 202	99.60 94	99.88 23	97.14 133	99.84 142	99.13 58	98.94 181	99.69 108

PLC	97.94 4	99.02 109	98.85 115	99.53 104	99.66 119	99.01 148	99.24 247	99.52 93	96.85 253	99.27 172	99.48 244	98.25 101	99.91 96	97.76 212	99.62 132	99.65 122
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSDG		98.98 114	98.80 121	99.53 104	99.76 57	99.19 123	98.75 330	99.55 67	97.25 218	99.47 119	99.77 112	97.82 115	99.87 127	96.93 278	99.90 25	99.54 152

PatchMatch-RL		98.84 136	98.62 146	99.52 110	99.71 95	99.28 115	99.06 280	99.77 9	97.74 170	99.50 114	99.53 225	95.41 194	99.84 142	97.17 264	99.64 129	99.44 180

OpenMVS	96.50 16	98.47 163	98.12 181	99.52 110	99.04 281	99.53 85	99.82 18	99.72 11	94.56 336	98.08 316	99.88 23	94.73 224	99.98 7	97.47 243	99.76 104	99.06 213

Fast-Effi-MVS+		98.70 148	98.43 162	99.51 112	99.51 161	99.28 115	99.52 129	99.47 166	96.11 310	99.01 224	99.34 282	96.20 168	99.84 142	97.88 201	98.82 190	99.39 187

canonicalmvs		99.02 109	98.86 114	99.51 112	99.42 190	99.32 108	99.80 24	99.48 148	98.63 66	99.31 163	98.81 338	97.09 136	99.75 186	99.27 46	97.90 229	99.47 175

diffmvs		99.14 82	99.02 87	99.51 112	99.61 139	98.96 157	99.28 229	99.49 136	98.46 80	99.72 54	99.71 141	96.50 158	99.88 124	99.31 38	99.11 166	99.67 115

PAPR		98.63 158	98.34 168	99.51 112	99.40 198	99.03 145	98.80 325	99.36 238	96.33 289	99.00 229	99.12 318	98.46 86	99.84 142	95.23 321	99.37 151	99.66 118

Effi-MVS+		98.81 137	98.59 153	99.48 116	99.46 183	99.12 137	98.08 363	99.50 128	97.50 194	99.38 146	99.41 262	96.37 163	99.81 165	99.11 60	98.54 203	99.51 164

MVS		97.28 288	96.55 297	99.48 116	98.78 316	98.95 161	99.27 234	99.39 223	83.53 367	98.08 316	99.54 221	96.97 142	99.87 127	94.23 333	99.16 161	99.63 133

MVS_Test		99.10 98	98.97 96	99.48 116	99.49 173	99.14 134	99.67 53	99.34 247	97.31 212	99.58 99	99.76 118	97.65 120	99.82 160	98.87 89	99.07 172	99.46 177

HY-MVS	97.30 7	98.85 133	98.64 140	99.47 119	99.42 190	99.08 140	99.62 76	99.36 238	97.39 207	99.28 169	99.68 162	96.44 161	99.92 85	98.37 163	98.22 215	99.40 186

PCF-MVS	97.08 14	97.66 269	97.06 289	99.47 119	99.61 139	99.09 139	98.04 364	99.25 283	91.24 357	98.51 294	99.70 145	94.55 233	99.91 96	92.76 350	99.85 60	99.42 182
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
lupinMVS		99.13 84	99.01 91	99.46 121	99.51 161	98.94 164	99.05 282	99.16 296	97.86 151	99.80 28	99.56 213	97.39 124	99.86 130	98.94 77	99.85 60	99.58 147

EIA-MVS		99.18 76	99.09 76	99.45 122	99.49 173	99.18 125	99.67 53	99.53 87	97.66 178	99.40 139	99.44 253	98.10 108	99.81 165	98.94 77	99.62 132	99.35 189

jason		99.13 84	99.03 84	99.45 122	99.46 183	98.87 171	99.12 267	99.26 281	98.03 140	99.79 30	99.65 175	97.02 139	99.85 136	99.02 70	99.90 25	99.65 122
jason: jason.
CHOSEN 1792x2688		99.19 74	99.10 74	99.45 122	99.89 9	98.52 208	99.39 195	99.94 1	98.73 61	99.11 206	99.89 17	95.50 192	99.94 58	99.50 13	99.97 5	99.89 2

MG-MVS		99.13 84	99.02 87	99.45 122	99.57 149	98.63 195	99.07 277	99.34 247	98.99 31	99.61 90	99.82 58	97.98 112	99.87 127	97.00 271	99.80 90	99.85 18

MSLP-MVS++		99.46 27	99.47 14	99.44 126	99.60 143	99.16 128	99.41 183	99.71 13	98.98 34	99.45 122	99.78 105	99.19 9	99.54 239	99.28 43	99.84 68	99.63 133

PVSNet_Blended		99.08 101	98.97 96	99.42 127	99.76 57	98.79 182	98.78 327	99.91 3	96.74 259	99.67 68	99.49 238	97.53 121	99.88 124	98.98 73	99.85 60	99.60 139

ETV-MVS		99.26 66	99.21 64	99.40 128	99.46 183	99.30 112	99.56 110	99.52 93	98.52 75	99.44 126	99.27 299	98.41 92	99.86 130	99.10 61	99.59 134	99.04 214

BH-RMVSNet		98.41 169	98.08 187	99.40 128	99.41 193	98.83 178	99.30 223	98.77 334	97.70 173	98.94 238	99.65 175	92.91 273	99.74 187	96.52 294	99.55 137	99.64 129

UGNet		98.87 122	98.69 133	99.40 128	99.22 242	98.72 187	99.44 168	99.68 19	99.24 4	99.18 197	99.42 258	92.74 277	99.96 20	99.34 35	99.94 11	99.53 157
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		98.31 176	97.95 202	99.38 131	99.50 171	98.74 185	99.59 90	98.93 319	98.41 85	99.14 201	99.60 200	94.59 230	99.79 173	98.48 151	93.29 340	99.61 137

TSAR-MVS + GP.		99.36 53	99.36 27	99.36 132	99.67 110	98.61 198	99.07 277	99.33 254	99.00 28	99.82 23	99.81 71	99.06 16	99.84 142	99.09 62	99.42 142	99.65 122

Anonymous20240529		98.09 197	97.68 231	99.34 133	99.66 119	98.44 217	99.40 191	99.43 205	93.67 343	99.22 185	99.89 17	90.23 328	99.93 73	99.26 47	98.33 209	99.66 118

xiu_mvs_v1_base_debu		99.29 61	99.27 56	99.34 133	99.63 129	98.97 153	99.12 267	99.51 107	98.86 48	99.84 15	99.47 247	98.18 104	99.99 1	99.50 13	99.31 152	99.08 207

xiu_mvs_v1_base		99.29 61	99.27 56	99.34 133	99.63 129	98.97 153	99.12 267	99.51 107	98.86 48	99.84 15	99.47 247	98.18 104	99.99 1	99.50 13	99.31 152	99.08 207

xiu_mvs_v1_base_debi		99.29 61	99.27 56	99.34 133	99.63 129	98.97 153	99.12 267	99.51 107	98.86 48	99.84 15	99.47 247	98.18 104	99.99 1	99.50 13	99.31 152	99.08 207

PMMVS		98.80 140	98.62 146	99.34 133	99.27 231	98.70 189	98.76 329	99.31 267	97.34 209	99.21 188	99.07 320	97.20 132	99.82 160	98.56 143	98.87 187	99.52 158

CSCG		99.32 57	99.32 36	99.32 138	99.85 26	98.29 223	99.71 43	99.66 27	98.11 124	99.41 134	99.80 86	98.37 95	99.96 20	98.99 72	99.96 7	99.72 96

thisisatest0530		98.35 174	98.03 193	99.31 139	99.63 129	98.56 201	99.54 123	96.75 369	97.53 191	99.73 49	99.65 175	91.25 316	99.89 119	98.62 129	99.56 135	99.48 169

AllTest		98.87 122	98.72 128	99.31 139	99.86 22	98.48 214	99.56 110	99.61 36	97.85 153	99.36 152	99.85 38	95.95 174	99.85 136	96.66 292	99.83 77	99.59 143

TestCases				99.31 139	99.86 22	98.48 214		99.61 36	97.85 153	99.36 152	99.85 38	95.95 174	99.85 136	96.66 292	99.83 77	99.59 143

Vis-MVSNet (Re-imp)		98.87 122	98.72 128	99.31 139	99.71 95	98.88 170	99.80 24	99.44 197	97.91 148	99.36 152	99.78 105	95.49 193	99.43 254	97.91 199	99.11 166	99.62 135

PS-MVSNAJ		99.32 57	99.32 36	99.30 143	99.57 149	98.94 164	98.97 305	99.46 176	98.92 45	99.71 55	99.24 303	99.01 19	99.98 7	99.35 31	99.66 126	98.97 222

VPA-MVSNet		98.29 179	97.95 202	99.30 143	99.16 259	99.54 82	99.50 140	99.58 50	98.27 101	99.35 155	99.37 273	92.53 287	99.65 222	99.35 31	94.46 324	98.72 251

EPNet		98.86 125	98.71 130	99.30 143	97.20 362	98.18 227	99.62 76	98.91 324	99.28 3	98.63 285	99.81 71	95.96 173	99.99 1	99.24 48	99.72 112	99.73 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_part1		97.75 252	97.24 283	99.29 146	99.59 145	99.63 65	99.65 65	99.49 136	96.17 303	98.44 299	99.69 154	89.80 332	99.47 242	98.68 122	93.66 336	98.78 235

xiu_mvs_v2_base		99.26 66	99.25 60	99.29 146	99.53 157	98.91 168	99.02 291	99.45 188	98.80 56	99.71 55	99.26 301	98.94 35	99.98 7	99.34 35	99.23 157	98.98 221

MVSFormer		99.17 78	99.12 72	99.29 146	99.51 161	98.94 164	99.88 4	99.46 176	97.55 187	99.80 28	99.65 175	97.39 124	99.28 284	99.03 67	99.85 60	99.65 122

tttt0517		98.42 167	98.14 179	99.28 149	99.66 119	98.38 221	99.74 40	96.85 367	97.68 175	99.79 30	99.74 129	91.39 313	99.89 119	98.83 102	99.56 135	99.57 148

nrg030		98.64 157	98.42 163	99.28 149	99.05 280	99.69 52	99.81 20	99.46 176	98.04 138	99.01 224	99.82 58	96.69 152	99.38 259	99.34 35	94.59 323	98.78 235

Anonymous202405211		98.30 178	97.98 198	99.26 151	99.57 149	98.16 228	99.41 183	98.55 349	96.03 315	99.19 194	99.74 129	91.87 300	99.92 85	99.16 56	98.29 214	99.70 105

CANet_DTU		98.97 116	98.87 109	99.25 152	99.33 213	98.42 220	99.08 276	99.30 271	99.16 6	99.43 127	99.75 123	95.27 199	99.97 12	98.56 143	99.95 8	99.36 188

CDS-MVSNet		99.09 99	99.03 84	99.25 152	99.42 190	98.73 186	99.45 164	99.46 176	98.11 124	99.46 121	99.77 112	98.01 111	99.37 264	98.70 117	98.92 184	99.66 118
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
XXY-MVS		98.38 172	98.09 186	99.24 154	99.26 233	99.32 108	99.56 110	99.55 67	97.45 198	98.71 268	99.83 51	93.23 265	99.63 230	98.88 85	96.32 285	98.76 242

TAMVS		99.12 90	99.08 77	99.24 154	99.46 183	98.55 202	99.51 134	99.46 176	98.09 127	99.45 122	99.82 58	98.34 96	99.51 240	98.70 117	98.93 182	99.67 115

FIs		98.78 141	98.63 141	99.23 156	99.18 251	99.54 82	99.83 17	99.59 44	98.28 99	98.79 261	99.81 71	96.75 150	99.37 264	99.08 64	96.38 283	98.78 235

OMC-MVS		99.08 101	99.04 82	99.20 157	99.67 110	98.22 226	99.28 229	99.52 93	98.07 132	99.66 73	99.81 71	97.79 116	99.78 178	97.79 209	99.81 86	99.60 139

thisisatest0515		98.14 192	97.79 216	99.19 158	99.50 171	98.50 211	98.61 341	96.82 368	96.95 247	99.54 107	99.43 255	91.66 309	99.86 130	98.08 188	99.51 139	99.22 197

RPMNet		96.72 299	95.90 309	99.19 158	99.18 251	98.49 212	99.22 253	99.52 93	88.72 363	99.56 102	97.38 360	94.08 250	99.95 47	86.87 370	98.58 199	99.14 199

COLMAP_ROB	97.56 6	98.86 125	98.75 127	99.17 160	99.88 12	98.53 204	99.34 216	99.59 44	97.55 187	98.70 274	99.89 17	95.83 181	99.90 111	98.10 183	99.90 25	99.08 207
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDDNet		97.55 274	97.02 290	99.16 161	99.49 173	98.12 232	99.38 200	99.30 271	95.35 322	99.68 62	99.90 13	82.62 367	99.93 73	99.31 38	98.13 224	99.42 182

mvs_anonymous		99.03 108	98.99 92	99.16 161	99.38 202	98.52 208	99.51 134	99.38 229	97.79 163	99.38 146	99.81 71	97.30 129	99.45 245	99.35 31	98.99 179	99.51 164

FC-MVSNet-test		98.75 145	98.62 146	99.15 163	99.08 273	99.45 97	99.86 13	99.60 41	98.23 105	98.70 274	99.82 58	96.80 146	99.22 296	99.07 65	96.38 283	98.79 234

UniMVSNet (Re)		98.29 179	98.00 196	99.13 164	99.00 286	99.36 106	99.49 150	99.51 107	97.95 144	98.97 233	99.13 315	96.30 165	99.38 259	98.36 165	93.34 339	98.66 282

1314		98.68 153	98.54 157	99.11 165	98.89 300	98.65 193	99.27 234	99.49 136	96.89 251	97.99 321	99.56 213	97.72 119	99.83 153	97.74 215	99.27 155	98.84 231

CHOSEN 280x420		99.12 90	99.13 71	99.08 166	99.66 119	97.89 243	98.43 351	99.71 13	98.88 47	99.62 88	99.76 118	96.63 153	99.70 209	99.46 21	99.99 1	99.66 118

mvsmamba		98.92 119	98.87 109	99.08 166	99.07 274	99.16 128	99.88 4	99.51 107	98.15 116	99.40 139	99.89 17	97.12 134	99.33 274	99.38 27	97.40 260	98.73 250

PAPM		97.59 273	97.09 288	99.07 168	99.06 277	98.26 225	98.30 358	99.10 302	94.88 330	98.08 316	99.34 282	96.27 166	99.64 225	89.87 359	98.92 184	99.31 193

WR-MVS		98.06 200	97.73 227	99.06 169	98.86 308	99.25 119	99.19 256	99.35 243	97.30 213	98.66 277	99.43 255	93.94 253	99.21 301	98.58 138	94.28 328	98.71 253

API-MVS		99.04 106	99.03 84	99.06 169	99.40 198	99.31 111	99.55 119	99.56 58	98.54 73	99.33 160	99.39 269	98.76 57	99.78 178	96.98 273	99.78 97	98.07 344

ET-MVSNet_ETH3D		96.49 303	95.64 314	99.05 171	99.53 157	98.82 179	98.84 321	97.51 364	97.63 180	84.77 368	99.21 308	92.09 297	98.91 340	98.98 73	92.21 350	99.41 184

SD-MVS		99.41 46	99.52 8	99.05 171	99.74 76	99.68 54	99.46 163	99.52 93	99.11 11	99.88 6	99.91 10	99.43 1	97.70 362	98.72 115	99.93 12	99.77 72
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
PVSNet_BlendedMVS		98.86 125	98.80 121	99.03 173	99.76 57	98.79 182	99.28 229	99.91 3	97.42 204	99.67 68	99.37 273	97.53 121	99.88 124	98.98 73	97.29 265	98.42 327

NR-MVSNet		97.97 220	97.61 238	99.02 174	98.87 305	99.26 118	99.47 160	99.42 207	97.63 180	97.08 342	99.50 235	95.07 206	99.13 309	97.86 203	93.59 337	98.68 267

VPNet		97.84 236	97.44 259	99.01 175	99.21 244	98.94 164	99.48 155	99.57 53	98.38 87	99.28 169	99.73 136	88.89 340	99.39 257	99.19 51	93.27 341	98.71 253

CP-MVSNet		98.09 197	97.78 219	99.01 175	98.97 292	99.24 120	99.67 53	99.46 176	97.25 218	98.48 297	99.64 182	93.79 257	99.06 318	98.63 128	94.10 331	98.74 247

GA-MVS		97.85 233	97.47 251	99.00 177	99.38 202	97.99 236	98.57 344	99.15 297	97.04 239	98.90 244	99.30 292	89.83 331	99.38 259	96.70 289	98.33 209	99.62 135

MVSTER		98.49 162	98.32 170	99.00 177	99.35 207	99.02 146	99.54 123	99.38 229	97.41 205	99.20 191	99.73 136	93.86 256	99.36 268	98.87 89	97.56 241	98.62 297

iter_conf_final		98.71 147	98.61 152	98.99 179	99.49 173	98.96 157	99.63 70	99.41 210	98.19 110	99.39 142	99.77 112	94.82 214	99.38 259	99.30 41	97.52 244	98.64 286

bld_raw_dy_0_64		98.69 151	98.58 154	98.99 179	98.88 301	98.96 157	99.80 24	99.41 210	97.91 148	99.32 161	99.87 29	95.70 187	99.31 281	99.09 62	97.27 266	98.71 253

tfpnnormal		97.84 236	97.47 251	98.98 181	99.20 246	99.22 122	99.64 68	99.61 36	96.32 290	98.27 310	99.70 145	93.35 264	99.44 250	95.69 310	95.40 308	98.27 336

test_djsdf		98.67 154	98.57 155	98.98 181	98.70 327	98.91 168	99.88 4	99.46 176	97.55 187	99.22 185	99.88 23	95.73 185	99.28 284	99.03 67	97.62 236	98.75 244

h-mvs33		97.70 262	97.28 279	98.97 183	99.70 102	97.27 263	99.36 207	99.45 188	98.94 41	99.66 73	99.64 182	94.93 208	99.99 1	99.48 18	84.36 363	99.65 122

UniMVSNet_NR-MVSNet		98.22 182	97.97 199	98.96 184	98.92 296	98.98 150	99.48 155	99.53 87	97.76 166	98.71 268	99.46 251	96.43 162	99.22 296	98.57 140	92.87 346	98.69 262

DU-MVS		98.08 199	97.79 216	98.96 184	98.87 305	98.98 150	99.41 183	99.45 188	97.87 150	98.71 268	99.50 235	94.82 214	99.22 296	98.57 140	92.87 346	98.68 267

PS-CasMVS		97.93 222	97.59 240	98.95 186	98.99 287	99.06 143	99.68 51	99.52 93	97.13 228	98.31 307	99.68 162	92.44 293	99.05 319	98.51 149	94.08 332	98.75 244

bld_raw_conf005		98.62 159	98.50 158	98.95 186	99.02 283	98.79 182	99.66 57	99.55 67	98.14 119	98.95 235	99.91 10	94.54 234	99.33 274	99.36 30	97.39 262	98.74 247

anonymousdsp		98.44 165	98.28 173	98.94 188	98.50 342	98.96 157	99.77 32	99.50 128	97.07 236	98.87 249	99.77 112	94.76 222	99.28 284	98.66 125	97.60 237	98.57 312

TAPA-MVS	97.07 15	97.74 255	97.34 273	98.94 188	99.70 102	97.53 256	99.25 245	99.51 107	91.90 354	99.30 165	99.63 188	98.78 52	99.64 225	88.09 366	99.87 42	99.65 122
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
v8		97.95 221	97.63 237	98.93 190	98.95 294	98.81 181	99.80 24	99.41 210	96.03 315	99.10 209	99.42 258	94.92 210	99.30 282	96.94 277	94.08 332	98.66 282

JIA-IIPM		97.50 279	97.02 290	98.93 190	98.73 322	97.80 248	99.30 223	98.97 315	91.73 355	98.91 242	94.86 368	95.10 205	99.71 203	97.58 229	97.98 227	99.28 195

test_low_dy_conf_001		98.76 144	98.71 130	98.92 192	98.92 296	98.71 188	99.87 9	99.41 210	97.81 162	99.35 155	99.93 4	96.63 153	99.28 284	99.03 67	97.44 257	98.78 235

v7n		97.87 230	97.52 245	98.92 192	98.76 320	98.58 200	99.84 14	99.46 176	96.20 300	98.91 242	99.70 145	94.89 212	99.44 250	96.03 303	93.89 334	98.75 244

v2v482		98.06 200	97.77 221	98.92 192	98.90 298	98.82 179	99.57 104	99.36 238	96.65 266	99.19 194	99.35 279	94.20 244	99.25 290	97.72 218	94.97 317	98.69 262

thres600view7		97.86 232	97.51 247	98.92 192	99.72 89	97.95 241	99.59 90	98.74 338	97.94 145	99.27 172	98.62 344	91.75 303	99.86 130	93.73 338	98.19 219	98.96 224

thres400		97.77 247	97.38 266	98.92 192	99.69 105	97.96 239	99.50 140	98.73 343	97.83 156	99.17 198	98.45 349	91.67 307	99.83 153	93.22 343	98.18 220	98.96 224

v1192		97.81 243	97.44 259	98.91 197	98.88 301	98.68 190	99.51 134	99.34 247	96.18 302	99.20 191	99.34 282	94.03 251	99.36 268	95.32 320	95.18 312	98.69 262

mvs_tets		98.40 171	98.23 175	98.91 197	98.67 330	98.51 210	99.66 57	99.53 87	98.19 110	98.65 283	99.81 71	92.75 275	99.44 250	99.31 38	97.48 252	98.77 240

Anonymous20231211		97.88 228	97.54 244	98.90 199	99.71 95	98.53 204	99.48 155	99.57 53	94.16 339	98.81 257	99.68 162	93.23 265	99.42 255	98.84 99	94.42 326	98.76 242

PS-MVSNAJss		98.92 119	98.92 102	98.90 199	98.78 316	98.53 204	99.78 30	99.54 76	98.07 132	99.00 229	99.76 118	99.01 19	99.37 264	99.13 58	97.23 267	98.81 232

WR-MVS_H		98.13 193	97.87 212	98.90 199	99.02 283	98.84 175	99.70 44	99.59 44	97.27 216	98.40 302	99.19 309	95.53 191	99.23 293	98.34 166	93.78 335	98.61 306

mvs-test1		98.86 125	98.84 116	98.89 202	99.33 213	97.77 249	99.44 168	99.30 271	98.47 78	99.10 209	99.43 255	96.78 147	99.95 47	98.73 113	99.02 177	98.96 224

XVG-OURS-SEG-HR		98.69 151	98.62 146	98.89 202	99.71 95	97.74 250	99.12 267	99.54 76	98.44 84	99.42 130	99.71 141	94.20 244	99.92 85	98.54 148	98.90 186	99.00 218

PVSNet	96.02 17	98.85 133	98.84 116	98.89 202	99.73 84	97.28 262	98.32 357	99.60 41	97.86 151	99.50 114	99.57 210	96.75 150	99.86 130	98.56 143	99.70 117	99.54 152

jajsoiax		98.43 166	98.28 173	98.88 205	98.60 337	98.43 218	99.82 18	99.53 87	98.19 110	98.63 285	99.80 86	93.22 267	99.44 250	99.22 49	97.50 248	98.77 240

pm-mvs1		97.68 265	97.28 279	98.88 205	99.06 277	98.62 196	99.50 140	99.45 188	96.32 290	97.87 324	99.79 98	92.47 289	99.35 271	97.54 236	93.54 338	98.67 274

VDD-MVS		97.73 256	97.35 270	98.88 205	99.47 182	97.12 269	99.34 216	98.85 330	98.19 110	99.67 68	99.85 38	82.98 365	99.92 85	99.49 17	98.32 213	99.60 139

XVG-OURS		98.73 146	98.68 134	98.88 205	99.70 102	97.73 251	98.92 313	99.55 67	98.52 75	99.45 122	99.84 47	95.27 199	99.91 96	98.08 188	98.84 189	99.00 218

UniMVSNet_ETH3D		97.32 287	96.81 293	98.87 209	99.40 198	97.46 258	99.51 134	99.53 87	95.86 317	98.54 293	99.77 112	82.44 368	99.66 218	98.68 122	97.52 244	99.50 167

v144192		97.92 225	97.60 239	98.87 209	98.83 311	98.65 193	99.55 119	99.34 247	96.20 300	99.32 161	99.40 265	94.36 239	99.26 289	96.37 299	95.03 316	98.70 258

iter_conf05		98.55 161	98.44 161	98.87 209	99.34 211	98.60 199	99.55 119	99.42 207	98.21 108	99.37 148	99.77 112	93.55 261	99.38 259	99.30 41	97.48 252	98.63 294

CR-MVSNet		98.17 189	97.93 205	98.87 209	99.18 251	98.49 212	99.22 253	99.33 254	96.96 245	99.56 102	99.38 270	94.33 240	99.00 327	94.83 327	98.58 199	99.14 199

v10		97.85 233	97.52 245	98.86 213	98.99 287	98.67 191	99.75 37	99.41 210	95.70 318	98.98 231	99.41 262	94.75 223	99.23 293	96.01 304	94.63 322	98.67 274

V42		98.06 200	97.79 216	98.86 213	98.98 290	98.84 175	99.69 46	99.34 247	96.53 275	99.30 165	99.37 273	94.67 227	99.32 278	97.57 233	94.66 321	98.42 327

TransMVSNet (Re)		97.15 291	96.58 296	98.86 213	99.12 264	98.85 174	99.49 150	98.91 324	95.48 320	97.16 340	99.80 86	93.38 263	99.11 314	94.16 335	91.73 351	98.62 297

v1144		97.98 217	97.69 230	98.85 216	98.87 305	98.66 192	99.54 123	99.35 243	96.27 294	99.23 184	99.35 279	94.67 227	99.23 293	96.73 287	95.16 313	98.68 267

v1921920		97.80 245	97.45 254	98.84 217	98.80 312	98.53 204	99.52 129	99.34 247	96.15 307	99.24 180	99.47 247	93.98 252	99.29 283	95.40 317	95.13 314	98.69 262

FMVSNet3		98.03 208	97.76 224	98.84 217	99.39 201	98.98 150	99.40 191	99.38 229	96.67 264	99.07 215	99.28 296	92.93 270	98.98 329	97.10 266	96.65 276	98.56 313

RRT_MVS		98.70 148	98.66 138	98.83 219	98.90 298	98.45 216	99.89 2	99.28 278	97.76 166	98.94 238	99.92 9	96.98 141	99.25 290	99.28 43	97.00 273	98.80 233

baseline2		97.87 230	97.55 241	98.82 220	99.18 251	98.02 234	99.41 183	96.58 371	96.97 244	96.51 347	99.17 310	93.43 262	99.57 235	97.71 219	99.03 175	98.86 229

TR-MVS		97.76 248	97.41 264	98.82 220	99.06 277	97.87 244	98.87 319	98.56 348	96.63 269	98.68 276	99.22 305	92.49 288	99.65 222	95.40 317	97.79 231	98.95 227

pmmvs4		98.13 193	97.90 207	98.81 222	98.61 336	98.87 171	98.99 298	99.21 290	96.44 284	99.06 219	99.58 206	95.90 179	99.11 314	97.18 263	96.11 289	98.46 324

Patchmtry		97.75 252	97.40 265	98.81 222	99.10 269	98.87 171	99.11 273	99.33 254	94.83 331	98.81 257	99.38 270	94.33 240	99.02 324	96.10 301	95.57 304	98.53 314

FMVSNet2		97.72 258	97.36 268	98.80 224	99.51 161	98.84 175	99.45 164	99.42 207	96.49 277	98.86 254	99.29 294	90.26 325	98.98 329	96.44 296	96.56 279	98.58 311

v1240		97.69 263	97.32 276	98.79 225	98.85 309	98.43 218	99.48 155	99.36 238	96.11 310	99.27 172	99.36 276	93.76 259	99.24 292	94.46 330	95.23 311	98.70 258

PatchT		97.03 294	96.44 299	98.79 225	98.99 287	98.34 222	99.16 259	99.07 307	92.13 353	99.52 111	97.31 363	94.54 234	98.98 329	88.54 364	98.73 195	99.03 215

Patchmatch-test		97.93 222	97.65 234	98.77 227	99.18 251	97.07 274	99.03 288	99.14 299	96.16 305	98.74 265	99.57 210	94.56 232	99.72 197	93.36 342	99.11 166	99.52 158

TranMVSNet+NR-MVSNet		97.93 222	97.66 233	98.76 228	98.78 316	98.62 196	99.65 65	99.49 136	97.76 166	98.49 296	99.60 200	94.23 243	98.97 336	98.00 193	92.90 344	98.70 258

gg-mvs-nofinetune		96.17 310	95.32 318	98.73 229	98.79 313	98.14 230	99.38 200	94.09 378	91.07 359	98.07 319	91.04 373	89.62 336	99.35 271	96.75 285	99.09 170	98.68 267

tfpn200view9		97.72 258	97.38 266	98.72 230	99.69 105	97.96 239	99.50 140	98.73 343	97.83 156	99.17 198	98.45 349	91.67 307	99.83 153	93.22 343	98.18 220	98.37 333

PEN-MVS		97.76 248	97.44 259	98.72 230	98.77 319	98.54 203	99.78 30	99.51 107	97.06 238	98.29 309	99.64 182	92.63 284	98.89 342	98.09 184	93.16 342	98.72 251

thres100view900		97.76 248	97.45 254	98.69 232	99.72 89	97.86 246	99.59 90	98.74 338	97.93 146	99.26 177	98.62 344	91.75 303	99.83 153	93.22 343	98.18 220	98.37 333

EI-MVSNet		98.67 154	98.67 135	98.68 233	99.35 207	97.97 237	99.50 140	99.38 229	96.93 250	99.20 191	99.83 51	97.87 113	99.36 268	98.38 161	97.56 241	98.71 253

Baseline_NR-MVSNet		97.76 248	97.45 254	98.68 233	99.09 271	98.29 223	99.41 183	98.85 330	95.65 319	98.63 285	99.67 168	94.82 214	99.10 316	98.07 191	92.89 345	98.64 286

thres200		97.61 272	97.28 279	98.62 235	99.64 126	98.03 233	99.26 243	98.74 338	97.68 175	99.09 213	98.32 353	91.66 309	99.81 165	92.88 347	98.22 215	98.03 347

Fast-Effi-MVS+-dtu		98.77 143	98.83 120	98.60 236	99.41 193	96.99 283	99.52 129	99.49 136	98.11 124	99.24 180	99.34 282	96.96 143	99.79 173	97.95 197	99.45 140	99.02 217

hse-mvs2		97.50 279	97.14 286	98.59 237	99.49 173	97.05 276	99.28 229	99.22 287	98.94 41	99.66 73	99.42 258	94.93 208	99.65 222	99.48 18	83.80 365	99.08 207

AUN-MVS		96.88 295	96.31 301	98.59 237	99.48 181	97.04 279	99.27 234	99.22 287	97.44 201	98.51 294	99.41 262	91.97 298	99.66 218	97.71 219	83.83 364	99.07 212

BH-untuned		98.42 167	98.36 165	98.59 237	99.49 173	96.70 295	99.27 234	99.13 300	97.24 220	98.80 259	99.38 270	95.75 184	99.74 187	97.07 269	99.16 161	99.33 192

IterMVS-LS		98.46 164	98.42 163	98.58 240	99.59 145	98.00 235	99.37 203	99.43 205	96.94 249	99.07 215	99.59 203	97.87 113	99.03 322	98.32 169	95.62 303	98.71 253
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MIMVSNet		97.73 256	97.45 254	98.57 241	99.45 188	97.50 257	99.02 291	98.98 314	96.11 310	99.41 134	99.14 314	90.28 324	98.74 344	95.74 309	98.93 182	99.47 175

IB-MVS	95.67 18	96.22 307	95.44 317	98.57 241	99.21 244	96.70 295	98.65 339	97.74 362	96.71 261	97.27 336	98.54 347	86.03 358	99.92 85	98.47 154	86.30 361	99.10 202
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
ADS-MVSNet		98.20 185	98.08 187	98.56 243	99.33 213	96.48 303	99.23 248	99.15 297	96.24 297	99.10 209	99.67 168	94.11 248	99.71 203	96.81 283	99.05 173	99.48 169

test0.0.03 1		97.71 261	97.42 263	98.56 243	98.41 345	97.82 247	98.78 327	98.63 347	97.34 209	98.05 320	98.98 332	94.45 237	98.98 329	95.04 324	97.15 271	98.89 228

cl____		98.01 213	97.84 214	98.55 245	99.25 237	97.97 237	98.71 334	99.34 247	96.47 283	98.59 291	99.54 221	95.65 189	99.21 301	97.21 257	95.77 298	98.46 324

test-LLR		98.06 200	97.90 207	98.55 245	98.79 313	97.10 270	98.67 336	97.75 360	97.34 209	98.61 288	98.85 336	94.45 237	99.45 245	97.25 255	99.38 144	99.10 202

test-mter		97.49 282	97.13 287	98.55 245	98.79 313	97.10 270	98.67 336	97.75 360	96.65 266	98.61 288	98.85 336	88.23 348	99.45 245	97.25 255	99.38 144	99.10 202

v148		97.79 246	97.55 241	98.50 248	98.74 321	97.72 252	99.54 123	99.33 254	96.26 295	98.90 244	99.51 232	94.68 226	99.14 306	97.83 206	93.15 343	98.63 294

LPG-MVS_test		98.22 182	98.13 180	98.49 249	99.33 213	97.05 276	99.58 98	99.55 67	97.46 195	99.24 180	99.83 51	92.58 285	99.72 197	98.09 184	97.51 246	98.68 267

LGP-MVS_train				98.49 249	99.33 213	97.05 276		99.55 67	97.46 195	99.24 180	99.83 51	92.58 285	99.72 197	98.09 184	97.51 246	98.68 267

cl22		97.85 233	97.64 236	98.48 251	99.09 271	97.87 244	98.60 343	99.33 254	97.11 233	98.87 249	99.22 305	92.38 294	99.17 305	98.21 174	95.99 292	98.42 327

DIV-MVS_self_test		98.01 213	97.85 213	98.48 251	99.24 238	97.95 241	98.71 334	99.35 243	96.50 276	98.60 290	99.54 221	95.72 186	99.03 322	97.21 257	95.77 298	98.46 324

cascas		97.69 263	97.43 262	98.48 251	98.60 337	97.30 261	98.18 362	99.39 223	92.96 351	98.41 301	98.78 340	93.77 258	99.27 288	98.16 181	98.61 196	98.86 229

ACMM	97.58 5	98.37 173	98.34 168	98.48 251	99.41 193	97.10 270	99.56 110	99.45 188	98.53 74	99.04 221	99.85 38	93.00 269	99.71 203	98.74 111	97.45 254	98.64 286
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+-dtu		98.78 141	98.89 107	98.47 255	99.33 213	96.91 289	99.57 104	99.30 271	98.47 78	99.41 134	98.99 329	96.78 147	99.74 187	98.73 113	99.38 144	98.74 247

DTE-MVSNet		97.51 278	97.19 285	98.46 256	98.63 333	98.13 231	99.84 14	99.48 148	96.68 263	97.97 322	99.67 168	92.92 271	98.56 346	96.88 282	92.60 349	98.70 258

OPM-MVS		98.19 186	98.10 183	98.45 257	98.88 301	97.07 274	99.28 229	99.38 229	98.57 70	99.22 185	99.81 71	92.12 296	99.66 218	98.08 188	97.54 243	98.61 306
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
GG-mvs-BLEND				98.45 257	98.55 340	98.16 228	99.43 174	93.68 379		97.23 337	98.46 348	89.30 337	99.22 296	95.43 316	98.22 215	97.98 352

ACMP	97.20 11	98.06 200	97.94 204	98.45 257	99.37 204	97.01 281	99.44 168	99.49 136	97.54 190	98.45 298	99.79 98	91.95 299	99.72 197	97.91 199	97.49 251	98.62 297
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HQP_MVS		98.27 181	98.22 176	98.44 260	99.29 226	96.97 285	99.39 195	99.47 166	98.97 37	99.11 206	99.61 197	92.71 280	99.69 213	97.78 210	97.63 234	98.67 274

ACMH	97.28 8	98.10 196	97.99 197	98.44 260	99.41 193	96.96 287	99.60 83	99.56 58	98.09 127	98.15 314	99.91 10	90.87 320	99.70 209	98.88 85	97.45 254	98.67 274
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
miper_ehance_all_eth		98.18 188	98.10 183	98.41 262	99.23 239	97.72 252	98.72 333	99.31 267	96.60 272	98.88 247	99.29 294	97.29 130	99.13 309	97.60 227	95.99 292	98.38 332

miper_enhance_ethall		98.16 190	98.08 187	98.41 262	98.96 293	97.72 252	98.45 350	99.32 264	96.95 247	98.97 233	99.17 310	97.06 138	99.22 296	97.86 203	95.99 292	98.29 335

TESTMET0.1,1		97.55 274	97.27 282	98.40 264	98.93 295	96.53 301	98.67 336	97.61 363	96.96 245	98.64 284	99.28 296	88.63 344	99.45 245	97.30 252	99.38 144	99.21 198

LTVRE_ROB	97.16 12	98.02 210	97.90 207	98.40 264	99.23 239	96.80 293	99.70 44	99.60 41	97.12 230	98.18 313	99.70 145	91.73 305	99.72 197	98.39 159	97.45 254	98.68 267
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
c3_l		98.12 195	98.04 192	98.38 266	99.30 222	97.69 255	98.81 324	99.33 254	96.67 264	98.83 255	99.34 282	97.11 135	98.99 328	97.58 229	95.34 309	98.48 318

HQP-MVS		98.02 210	97.90 207	98.37 267	99.19 248	96.83 290	98.98 302	99.39 223	98.24 102	98.66 277	99.40 265	92.47 289	99.64 225	97.19 261	97.58 239	98.64 286

EPMVS		97.82 241	97.65 234	98.35 268	98.88 301	95.98 315	99.49 150	94.71 377	97.57 185	99.26 177	99.48 244	92.46 292	99.71 203	97.87 202	99.08 171	99.35 189

eth_miper_zixun_eth		98.05 205	97.96 200	98.33 269	99.26 233	97.38 260	98.56 346	99.31 267	96.65 266	98.88 247	99.52 228	96.58 155	99.12 313	97.39 250	95.53 306	98.47 320

CLD-MVS		98.16 190	98.10 183	98.33 269	99.29 226	96.82 292	98.75 330	99.44 197	97.83 156	99.13 202	99.55 216	92.92 271	99.67 215	98.32 169	97.69 233	98.48 318
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
BH-w/o		98.00 215	97.89 211	98.32 271	99.35 207	96.20 312	99.01 296	98.90 326	96.42 286	98.38 303	99.00 328	95.26 201	99.72 197	96.06 302	98.61 196	99.03 215

ACMH+	97.24 10	97.92 225	97.78 219	98.32 271	99.46 183	96.68 297	99.56 110	99.54 76	98.41 85	97.79 328	99.87 29	90.18 329	99.66 218	98.05 192	97.18 270	98.62 297

CVMVSNet		98.57 160	98.67 135	98.30 273	99.35 207	95.59 322	99.50 140	99.55 67	98.60 69	99.39 142	99.83 51	94.48 236	99.45 245	98.75 110	98.56 202	99.85 18

GBi-Net		97.68 265	97.48 249	98.29 274	99.51 161	97.26 265	99.43 174	99.48 148	96.49 277	99.07 215	99.32 289	90.26 325	98.98 329	97.10 266	96.65 276	98.62 297

test1		97.68 265	97.48 249	98.29 274	99.51 161	97.26 265	99.43 174	99.48 148	96.49 277	99.07 215	99.32 289	90.26 325	98.98 329	97.10 266	96.65 276	98.62 297

FMVSNet1		96.84 296	96.36 300	98.29 274	99.32 220	97.26 265	99.43 174	99.48 148	95.11 325	98.55 292	99.32 289	83.95 364	98.98 329	95.81 307	96.26 286	98.62 297

miper_lstm_enhance		98.00 215	97.91 206	98.28 277	99.34 211	97.43 259	98.88 317	99.36 238	96.48 281	98.80 259	99.55 216	95.98 172	98.91 340	97.27 253	95.50 307	98.51 316

SCA		98.19 186	98.16 177	98.27 278	99.30 222	95.55 323	99.07 277	98.97 315	97.57 185	99.43 127	99.57 210	92.72 278	99.74 187	97.58 229	99.20 159	99.52 158

EPNet_dtu		98.03 208	97.96 200	98.23 279	98.27 346	95.54 325	99.23 248	98.75 335	99.02 21	97.82 326	99.71 141	96.11 169	99.48 241	93.04 346	99.65 128	99.69 108
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XVG-ACMP-BASELINE		97.83 238	97.71 229	98.20 280	99.11 266	96.33 308	99.41 183	99.52 93	98.06 136	99.05 220	99.50 235	89.64 335	99.73 193	97.73 216	97.38 263	98.53 314

OurMVSNet-221017-0		97.88 228	97.77 221	98.19 281	98.71 326	96.53 301	99.88 4	99.00 312	97.79 163	98.78 262	99.94 3	91.68 306	99.35 271	97.21 257	96.99 274	98.69 262

PatchmatchNet		98.31 176	98.36 165	98.19 281	99.16 259	95.32 331	99.27 234	98.92 321	97.37 208	99.37 148	99.58 206	94.90 211	99.70 209	97.43 248	99.21 158	99.54 152
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
patch_mono-2		99.26 66	99.62 1	98.16 283	99.81 42	94.59 344	99.52 129	99.64 33	99.33 2	99.73 49	99.90 13	99.00 25	99.99 1	99.69 1	99.98 2	99.89 2

dcpmvs_2		99.23 71	99.58 2	98.16 283	99.83 37	94.68 343	99.76 35	99.52 93	99.07 18	99.98 1	99.88 23	98.56 77	99.93 73	99.67 3	99.98 2	99.87 13

pmmvs5		97.52 276	97.30 278	98.16 283	98.57 339	96.73 294	99.27 234	98.90 326	96.14 308	98.37 304	99.53 225	91.54 312	99.14 306	97.51 239	95.87 296	98.63 294

D2MVS		98.41 169	98.50 158	98.15 286	99.26 233	96.62 299	99.40 191	99.61 36	97.71 172	98.98 231	99.36 276	96.04 171	99.67 215	98.70 117	97.41 259	98.15 342

testgi		97.65 270	97.50 248	98.13 287	99.36 206	96.45 304	99.42 181	99.48 148	97.76 166	97.87 324	99.45 252	91.09 317	98.81 343	94.53 329	98.52 204	99.13 201

ITE_SJBPF				98.08 288	99.29 226	96.37 306		98.92 321	98.34 93	98.83 255	99.75 123	91.09 317	99.62 231	95.82 306	97.40 260	98.25 338

IterMVS-SCA-FT		97.82 241	97.75 225	98.06 289	99.57 149	96.36 307	99.02 291	99.49 136	97.18 224	98.71 268	99.72 140	92.72 278	99.14 306	97.44 247	95.86 297	98.67 274

SixPastTwentyTwo		97.50 279	97.33 275	98.03 290	98.65 331	96.23 311	99.77 32	98.68 346	97.14 227	97.90 323	99.93 4	90.45 323	99.18 304	97.00 271	96.43 282	98.67 274

tpm		97.67 268	97.55 241	98.03 290	99.02 283	95.01 337	99.43 174	98.54 350	96.44 284	99.12 204	99.34 282	91.83 302	99.60 233	97.75 214	96.46 281	99.48 169

IterMVS		97.83 238	97.77 221	98.02 292	99.58 147	96.27 310	99.02 291	99.48 148	97.22 222	98.71 268	99.70 145	92.75 275	99.13 309	97.46 244	96.00 291	98.67 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDA-MVSNet_test_wron		95.45 317	94.60 323	98.01 293	98.16 348	97.21 268	99.11 273	99.24 285	93.49 346	80.73 373	98.98 332	93.02 268	98.18 350	94.22 334	94.45 325	98.64 286

K. test v3		97.10 293	96.79 294	98.01 293	98.72 324	96.33 308	99.87 9	97.05 366	97.59 182	96.16 351	99.80 86	88.71 341	99.04 320	96.69 290	96.55 280	98.65 284

ECVR-MVS		98.04 206	98.05 191	98.00 295	99.74 76	94.37 347	99.59 90	94.98 375	99.13 8	99.66 73	99.93 4	90.67 322	99.84 142	99.40 26	99.38 144	99.80 56

MVP-Stereo		97.81 243	97.75 225	97.99 296	97.53 355	96.60 300	98.96 306	98.85 330	97.22 222	97.23 337	99.36 276	95.28 198	99.46 244	95.51 314	99.78 97	97.92 356
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TDRefinement		95.42 318	94.57 324	97.97 297	89.83 377	96.11 314	99.48 155	98.75 335	96.74 259	96.68 346	99.88 23	88.65 343	99.71 203	98.37 163	82.74 366	98.09 343

PVSNet_0	94.43 19	96.09 312	95.47 315	97.94 298	99.31 221	94.34 349	97.81 365	99.70 15	97.12 230	97.46 332	98.75 341	89.71 333	99.79 173	97.69 222	81.69 367	99.68 112

MDA-MVSNet-bldmvs		94.96 322	93.98 328	97.92 299	98.24 347	97.27 263	99.15 263	99.33 254	93.80 342	80.09 374	99.03 325	88.31 347	97.86 359	93.49 341	94.36 327	98.62 297

YYNet1		95.36 319	94.51 325	97.92 299	97.89 351	97.10 270	99.10 275	99.23 286	93.26 349	80.77 372	99.04 324	92.81 274	98.02 354	94.30 331	94.18 330	98.64 286

tpmrst		98.33 175	98.48 160	97.90 301	99.16 259	94.78 341	99.31 221	99.11 301	97.27 216	99.45 122	99.59 203	95.33 197	99.84 142	98.48 151	98.61 196	99.09 206

ADS-MVSNet2		98.02 210	98.07 190	97.87 302	99.33 213	95.19 334	99.23 248	99.08 305	96.24 297	99.10 209	99.67 168	94.11 248	98.93 339	96.81 283	99.05 173	99.48 169

test_0402		96.64 300	96.24 302	97.85 303	98.85 309	96.43 305	99.44 168	99.26 281	93.52 345	96.98 344	99.52 228	88.52 345	99.20 303	92.58 352	97.50 248	97.93 355

tpmvs		97.98 217	98.02 195	97.84 304	99.04 281	94.73 342	99.31 221	99.20 291	96.10 314	98.76 264	99.42 258	94.94 207	99.81 165	96.97 274	98.45 207	98.97 222

test1111		98.04 206	98.11 182	97.83 305	99.74 76	93.82 352	99.58 98	95.40 374	99.12 10	99.65 79	99.93 4	90.73 321	99.84 142	99.43 25	99.38 144	99.82 40

TinyColmap		97.12 292	96.89 292	97.83 305	99.07 274	95.52 326	98.57 344	98.74 338	97.58 184	97.81 327	99.79 98	88.16 349	99.56 236	95.10 322	97.21 268	98.39 331

pmmvs6		96.53 302	96.09 305	97.82 307	98.69 328	95.47 327	99.37 203	99.47 166	93.46 347	97.41 333	99.78 105	87.06 356	99.33 274	96.92 280	92.70 348	98.65 284

EU-MVSNet		97.98 217	98.03 193	97.81 308	98.72 324	96.65 298	99.66 57	99.66 27	98.09 127	98.35 305	99.82 58	95.25 202	98.01 355	97.41 249	95.30 310	98.78 235

lessismore_v0				97.79 309	98.69 328	95.44 329		94.75 376		95.71 355	99.87 29	88.69 342	99.32 278	95.89 305	94.93 319	98.62 297

USDC		97.34 286	97.20 284	97.75 310	99.07 274	95.20 333	98.51 348	99.04 310	97.99 142	98.31 307	99.86 33	89.02 338	99.55 238	95.67 312	97.36 264	98.49 317

tpm2		97.44 284	97.34 273	97.74 311	99.15 262	94.36 348	99.45 164	98.94 318	93.45 348	98.90 244	99.44 253	91.35 314	99.59 234	97.31 251	98.07 226	99.29 194

CostFormer		97.72 258	97.73 227	97.71 312	99.15 262	94.02 351	99.54 123	99.02 311	94.67 334	99.04 221	99.35 279	92.35 295	99.77 180	98.50 150	97.94 228	99.34 191

LF4IMVS		97.52 276	97.46 253	97.70 313	98.98 290	95.55 323	99.29 227	98.82 333	98.07 132	98.66 277	99.64 182	89.97 330	99.61 232	97.01 270	96.68 275	97.94 354

EGC-MVSNET		82.80 338	77.86 344	97.62 314	97.91 350	96.12 313	99.33 218	99.28 278	8.40 381	25.05 382	99.27 299	84.11 363	99.33 274	89.20 361	98.22 215	97.42 363

ppachtmachnet_test		97.49 282	97.45 254	97.61 315	98.62 334	95.24 332	98.80 325	99.46 176	96.11 310	98.22 311	99.62 193	96.45 160	98.97 336	93.77 337	95.97 295	98.61 306

MVS_0304		96.79 298	96.52 298	97.59 316	99.22 242	94.92 340	99.04 287	99.59 44	96.49 277	98.43 300	98.99 329	80.48 371	99.39 257	97.15 265	99.27 155	98.47 320

dp		97.75 252	97.80 215	97.59 316	99.10 269	93.71 355	99.32 219	98.88 328	96.48 281	99.08 214	99.55 216	92.67 283	99.82 160	96.52 294	98.58 199	99.24 196

our_test_3		97.65 270	97.68 231	97.55 318	98.62 334	94.97 338	98.84 321	99.30 271	96.83 256	98.19 312	99.34 282	97.01 140	99.02 324	95.00 325	96.01 290	98.64 286

MVS-HIRNet		95.75 315	95.16 319	97.51 319	99.30 222	93.69 356	98.88 317	95.78 372	85.09 366	98.78 262	92.65 370	91.29 315	99.37 264	94.85 326	99.85 60	99.46 177

tpm cat1		97.39 285	97.36 268	97.50 320	99.17 257	93.73 354	99.43 174	99.31 267	91.27 356	98.71 268	99.08 319	94.31 242	99.77 180	96.41 298	98.50 205	99.00 218

new_pmnet		96.38 306	96.03 306	97.41 321	98.13 349	95.16 336	99.05 282	99.20 291	93.94 340	97.39 334	98.79 339	91.61 311	99.04 320	90.43 357	95.77 298	98.05 346

UnsupCasMVSNet_eth		96.44 304	96.12 304	97.40 322	98.65 331	95.65 320	99.36 207	99.51 107	97.13 228	96.04 353	98.99 329	88.40 346	98.17 351	96.71 288	90.27 354	98.40 330

KD-MVS_2432*1600		94.62 324	93.72 330	97.31 323	97.19 363	95.82 318	98.34 354	99.20 291	95.00 328	97.57 330	98.35 351	87.95 351	98.10 352	92.87 348	77.00 371	98.01 348

miper_refine_blended		94.62 324	93.72 330	97.31 323	97.19 363	95.82 318	98.34 354	99.20 291	95.00 328	97.57 330	98.35 351	87.95 351	98.10 352	92.87 348	77.00 371	98.01 348

test2506		96.81 297	96.65 295	97.29 325	99.74 76	92.21 365	99.60 83	85.06 384	99.13 8	99.77 38	99.93 4	87.82 354	99.85 136	99.38 27	99.38 144	99.80 56

pmmvs-eth3d		95.34 320	94.73 322	97.15 326	95.53 370	95.94 316	99.35 213	99.10 302	95.13 323	93.55 361	97.54 358	88.15 350	97.91 357	94.58 328	89.69 357	97.61 359

FMVSNet5		96.43 305	96.19 303	97.15 326	99.11 266	95.89 317	99.32 219	99.52 93	94.47 338	98.34 306	99.07 320	87.54 355	97.07 366	92.61 351	95.72 301	98.47 320

Anonymous20240521		96.20 309	95.89 310	97.13 328	97.72 354	94.96 339	99.79 29	99.29 276	93.01 350	97.20 339	99.03 325	89.69 334	98.36 349	91.16 355	96.13 288	98.07 344

DeepPCF-MVS	98.18 3	98.81 137	99.37 25	97.12 329	99.60 143	91.75 366	98.61 341	99.44 197	99.35 1	99.83 20	99.85 38	98.70 66	99.81 165	99.02 70	99.91 18	99.81 46

MS-PatchMatch		97.24 290	97.32 276	96.99 330	98.45 344	93.51 359	98.82 323	99.32 264	97.41 205	98.13 315	99.30 292	88.99 339	99.56 236	95.68 311	99.80 90	97.90 357

RPSCF		98.22 182	98.62 146	96.99 330	99.82 39	91.58 367	99.72 41	99.44 197	96.61 270	99.66 73	99.89 17	95.92 177	99.82 160	97.46 244	99.10 169	99.57 148

KD-MVS_self_test		95.00 321	94.34 326	96.96 332	97.07 365	95.39 330	99.56 110	99.44 197	95.11 325	97.13 341	97.32 362	91.86 301	97.27 365	90.35 358	81.23 368	98.23 340

DSMNet-mixed		97.25 289	97.35 270	96.95 333	97.84 352	93.61 358	99.57 104	96.63 370	96.13 309	98.87 249	98.61 346	94.59 230	97.70 362	95.08 323	98.86 188	99.55 150

MIMVSNet1		95.51 316	95.04 320	96.92 334	97.38 357	95.60 321	99.52 129	99.50 128	93.65 344	96.97 345	99.17 310	85.28 361	96.56 370	88.36 365	95.55 305	98.60 309

LCM-MVSNet-Re		97.83 238	98.15 178	96.87 335	99.30 222	92.25 364	99.59 90	98.26 352	97.43 202	96.20 350	99.13 315	96.27 166	98.73 345	98.17 180	98.99 179	99.64 129

EG-PatchMatch MVS		95.97 313	95.69 313	96.81 336	97.78 353	92.79 362	99.16 259	98.93 319	96.16 305	94.08 360	99.22 305	82.72 366	99.47 242	95.67 312	97.50 248	98.17 341

Anonymous20231206		96.22 307	96.03 306	96.79 337	97.31 360	94.14 350	99.63 70	99.08 305	96.17 303	97.04 343	99.06 322	93.94 253	97.76 361	86.96 369	95.06 315	98.47 320

test20.03		96.12 311	95.96 308	96.63 338	97.44 356	95.45 328	99.51 134	99.38 229	96.55 274	96.16 351	99.25 302	93.76 259	96.17 371	87.35 368	94.22 329	98.27 336

pmmvs3		94.09 330	93.25 333	96.60 339	94.76 372	94.49 345	98.92 313	98.18 356	89.66 360	96.48 348	98.06 356	86.28 357	97.33 364	89.68 360	87.20 360	97.97 353

UnsupCasMVSNet_bld		93.53 331	92.51 334	96.58 340	97.38 357	93.82 352	98.24 359	99.48 148	91.10 358	93.10 363	96.66 364	74.89 372	98.37 348	94.03 336	87.71 359	97.56 361

OpenMVS_ROB	92.34 20	94.38 328	93.70 332	96.41 341	97.38 357	93.17 360	99.06 280	98.75 335	86.58 364	94.84 359	98.26 354	81.53 369	99.32 278	89.01 362	97.87 230	96.76 364

CL-MVSNet_self_test		94.49 326	93.97 329	96.08 342	96.16 366	93.67 357	98.33 356	99.38 229	95.13 323	97.33 335	98.15 355	92.69 282	96.57 369	88.67 363	79.87 369	97.99 351

Patchmatch-RL test		95.84 314	95.81 312	95.95 343	95.61 368	90.57 368	98.24 359	98.39 351	95.10 327	95.20 356	98.67 343	94.78 218	97.77 360	96.28 300	90.02 355	99.51 164

new-patchmatchnet		94.48 327	94.08 327	95.67 344	95.08 371	92.41 363	99.18 257	99.28 278	94.55 337	93.49 362	97.37 361	87.86 353	97.01 367	91.57 353	88.36 358	97.61 359

PM-MVS		92.96 332	92.23 335	95.14 345	95.61 368	89.98 370	99.37 203	98.21 354	94.80 332	95.04 358	97.69 357	65.06 374	97.90 358	94.30 331	89.98 356	97.54 362

Gipuma		90.99 334	90.15 337	93.51 346	98.73 322	90.12 369	93.98 371	99.45 188	79.32 369	92.28 364	94.91 367	69.61 373	97.98 356	87.42 367	95.67 302	92.45 370
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX				93.34 347	99.29 226	82.27 373		99.22 287	85.15 365	96.33 349	99.05 323	90.97 319	99.73 193	93.57 340	97.77 232	98.01 348

ambc				93.06 348	92.68 373	82.36 372	98.47 349	98.73 343		95.09 357	97.41 359	55.55 377	99.10 316	96.42 297	91.32 352	97.71 358

N_pmnet		94.95 323	95.83 311	92.31 349	98.47 343	79.33 376	99.12 267	92.81 382	93.87 341	97.68 329	99.13 315	93.87 255	99.01 326	91.38 354	96.19 287	98.59 310

CMPMVS	69.68 23	94.13 329	94.90 321	91.84 350	97.24 361	80.01 375	98.52 347	99.48 148	89.01 361	91.99 365	99.67 168	85.67 360	99.13 309	95.44 315	97.03 272	96.39 366
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet		86.80 336	85.22 340	91.53 351	87.81 378	80.96 374	98.23 361	98.99 313	71.05 371	90.13 367	96.51 365	48.45 380	96.88 368	90.51 356	85.30 362	96.76 364

PMMVS2		86.87 335	85.37 339	91.35 352	90.21 376	83.80 371	98.89 316	97.45 365	83.13 368	91.67 366	95.03 366	48.49 379	94.70 373	85.86 371	77.62 370	95.54 367

test_method		91.10 333	91.36 336	90.31 353	95.85 367	73.72 381	94.89 370	99.25 283	68.39 373	95.82 354	99.02 327	80.50 370	98.95 338	93.64 339	94.89 320	98.25 338

tmp_tt		82.80 338	81.52 341	86.66 354	66.61 384	68.44 382	92.79 373	97.92 358	68.96 372	80.04 375	99.85 38	85.77 359	96.15 372	97.86 203	43.89 377	95.39 368

MVE	76.82 21	76.91 343	74.31 347	84.70 355	85.38 381	76.05 380	96.88 369	93.17 380	67.39 374	71.28 376	89.01 375	21.66 386	87.69 376	71.74 375	72.29 373	90.35 372
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		77.30 342	74.86 346	84.62 356	75.88 382	77.61 377	97.63 367	93.15 381	88.81 362	64.27 377	89.29 374	36.51 381	83.93 379	75.89 374	52.31 376	92.33 371

E-PMN		80.61 340	79.88 342	82.81 357	90.75 375	76.38 379	97.69 366	95.76 373	66.44 375	83.52 369	92.25 371	62.54 376	87.16 377	68.53 376	61.40 374	84.89 375

FPMVS		84.93 337	85.65 338	82.75 358	86.77 379	63.39 383	98.35 353	98.92 321	74.11 370	83.39 370	98.98 332	50.85 378	92.40 375	84.54 372	94.97 317	92.46 369

EMVS		80.02 341	79.22 343	82.43 359	91.19 374	76.40 378	97.55 368	92.49 383	66.36 376	83.01 371	91.27 372	64.63 375	85.79 378	65.82 377	60.65 375	85.08 374

PMVS	70.75 22	75.98 344	74.97 345	79.01 360	70.98 383	55.18 384	93.37 372	98.21 354	65.08 377	61.78 378	93.83 369	21.74 385	92.53 374	78.59 373	91.12 353	89.34 373
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		40.18 345	41.29 350	36.84 361	86.18 380	49.12 385	79.73 374	22.81 386	27.64 378	25.46 381	28.45 381	21.98 384	48.89 380	55.80 378	23.56 380	12.51 378

test123		39.01 347	42.50 349	28.53 362	39.17 385	20.91 386	98.75 330	19.17 387	19.83 380	38.57 379	66.67 377	33.16 382	15.42 381	37.50 380	29.66 379	49.26 376

testmvs		39.17 346	43.78 348	25.37 363	36.04 386	16.84 387	98.36 352	26.56 385	20.06 379	38.51 380	67.32 376	29.64 383	15.30 382	37.59 379	39.90 378	43.98 377

test_blank		0.13 351	0.17 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	1.57 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet_test		0.02 352	0.03 355	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.27 383	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

DCPMVS		0.02 352	0.03 355	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.27 383	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

cdsmvs_eth3d_5k		24.64 348	32.85 351	0.00 364	0.00 387	0.00 388	0.00 375	99.51 107	0.00 382	0.00 383	99.56 213	96.58 155	0.00 383	0.00 381	0.00 381	0.00 379

pcd_1.5k_mvsjas		8.27 350	11.03 353	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.27 383	99.01 19	0.00 383	0.00 381	0.00 381	0.00 379

sosnet-low-res		0.02 352	0.03 355	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.27 383	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

sosnet		0.02 352	0.03 355	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.27 383	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uncertanet		0.02 352	0.03 355	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.27 383	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

Regformer		0.02 352	0.03 355	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.27 383	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

ab-mvs-re		8.30 349	11.06 352	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	99.58 206	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet		0.02 352	0.03 355	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.27 383	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

FOURS1					99.91 1	99.93 1	99.87 9	99.56 58	99.10 12	99.81 25

PC_three_1452									98.18 114	99.84 15	99.70 145	99.31 3	98.52 347	98.30 171	99.80 90	99.81 46

test_one_0601					99.81 42	99.88 8		99.49 136	98.97 37	99.65 79	99.81 71	99.09 14

eth-test2					0.00 387

eth-test					0.00 387

ZD-MVS					99.71 95	99.79 33		99.61 36	96.84 254	99.56 102	99.54 221	98.58 75	99.96 20	96.93 278	99.75 105

RE-MVS-def			99.34 32		99.76 57	99.82 23	99.63 70	99.52 93	98.38 87	99.76 43	99.82 58	98.75 60		98.61 132	99.81 86	99.77 72

IU-MVS					99.84 33	99.88 8		99.32 264	98.30 98	99.84 15				98.86 94	99.85 60	99.89 2

test_241102_TWO								99.48 148	99.08 16	99.88 6	99.81 71	98.94 35	99.96 20	98.91 82	99.84 68	99.88 8

test_241102_ONE					99.84 33	99.90 2		99.48 148	99.07 18	99.91 2	99.74 129	99.20 7	99.76 184

9.14			99.10 74		99.72 89		99.40 191	99.51 107	97.53 191	99.64 83	99.78 105	98.84 46	99.91 96	97.63 225	99.82 83

save fliter					99.76 57	99.59 73	99.14 265	99.40 219	99.00 28

test_0728_THIRD									98.99 31	99.81 25	99.80 86	99.09 14	99.96 20	98.85 96	99.90 25	99.88 8

test0726					99.85 26	99.89 4	99.62 76	99.50 128	99.10 12	99.86 13	99.82 58	98.94 35

GSMVS																99.52 158

test_part2					99.81 42	99.83 17				99.77 38

sam_mvs1												94.86 213				99.52 158

sam_mvs												94.72 225

MTGPA								99.47 166

test_post1							99.23 248				65.14 379	94.18 247	99.71 203	97.58 229

test_post											65.99 378	94.65 229	99.73 193

patchmatchnet-post											98.70 342	94.79 217	99.74 187

MTMP							99.54 123	98.88 328

gm-plane-assit					98.54 341	92.96 361			94.65 335		99.15 313		99.64 225	97.56 234

test9_res														97.49 240	99.72 112	99.75 78

TEST9					99.67 110	99.65 62	99.05 282	99.41 210	96.22 299	98.95 235	99.49 238	98.77 55	99.91 96

test_8					99.67 110	99.61 68	99.03 288	99.41 210	96.28 292	98.93 240	99.48 244	98.76 57	99.91 96

agg_prior2														97.21 257	99.73 111	99.75 78

agg_prior					99.67 110	99.62 66		99.40 219		98.87 249			99.91 96

test_prior4						99.56 78	98.99 298

test_prior2							98.96 306		98.34 93	99.01 224	99.52 228	98.68 67		97.96 195	99.74 108

旧先验2							98.96 306		96.70 262	99.47 119			99.94 58	98.19 176

新几何2							99.01 296

旧先验1					99.74 76	99.59 73		99.54 76			99.69 154	98.47 85			99.68 123	99.73 90

无先验							98.99 298	99.51 107	96.89 251				99.93 73	97.53 237		99.72 96

原ACMM2							98.95 310

test222					99.75 68	99.49 91	98.91 315	99.49 136	96.42 286	99.34 159	99.65 175	98.28 100			99.69 118	99.72 96

testdata2													99.95 47	96.67 291

segment_acmp												98.96 29

testdata1							98.85 320		98.32 97

plane_prior7					99.29 226	97.03 280

plane_prior6					99.27 231	96.98 284						92.71 280

plane_prior5								99.47 166					99.69 213	97.78 210	97.63 234	98.67 274

plane_prior4											99.61 197

plane_prior3						97.00 282			98.69 64	99.11 206

plane_prior2							99.39 195		98.97 37

plane_prior1					99.26 233

plane_prior						96.97 285	99.21 255		98.45 81						97.60 237

n2								0.00 388

nn								0.00 388

door-mid								98.05 357

test11								99.35 243

door								97.92 358

HQP5-MVS						96.83 290

HQP-NCC					99.19 248		98.98 302		98.24 102	98.66 277

ACMP_Plane					99.19 248		98.98 302		98.24 102	98.66 277

BP-MVS														97.19 261

HQP4-MVS										98.66 277			99.64 225			98.64 286

HQP3-MVS								99.39 223							97.58 239

HQP2-MVS												92.47 289

NP-MVS					99.23 239	96.92 288					99.40 265

MDTV_nov1_ep13_2view						95.18 335	99.35 213		96.84 254	99.58 99		95.19 204		97.82 207		99.46 177

MDTV_nov1_ep13			98.32 170		99.11 266	94.44 346	99.27 234	98.74 338	97.51 193	99.40 139	99.62 193	94.78 218	99.76 184	97.59 228	98.81 192

ACMMP++_ref															97.19 269

ACMMP++															97.43 258

Test By Simon												98.75 60

High-resolution multi-view benchmark