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.

test_vis1_n		97.92 243	97.44 283	99.34 151	99.53 172	98.08 246	99.74 46	99.49 154	99.15 25	100.00 1	99.94 6	79.51 416	99.98 14	99.88 17	99.76 121	99.97 4

fmvsm_s_conf0.5_n_3		99.37 59	99.20 74	99.87 16	99.75 79	99.70 52	99.48 190	99.66 28	99.45 8	99.99 2	99.93 10	94.64 239	99.97 22	99.94 12	99.97 7	99.95 9

fmvsm_s_conf0.5_n_2		99.32 67	99.13 81	99.89 8	99.80 53	99.77 41	99.44 209	99.58 65	99.47 4	99.99 2	99.93 10	94.04 263	99.96 34	99.96 8	99.93 27	99.93 18

fmvsm_s_conf0.1_n_a		99.26 78	99.06 91	99.85 34	99.52 178	99.62 72	99.54 149	99.62 43	98.69 88	99.99 2	99.96 1	94.47 248	99.94 76	99.88 17	99.92 30	99.98 2

fmvsm_s_conf0.1_n		99.29 72	99.10 85	99.86 27	99.70 108	99.65 64	99.53 158	99.62 43	98.74 84	99.99 2	99.95 3	94.53 246	99.94 76	99.89 16	99.96 13	99.97 4

test_vis1_n_1920		98.63 172	98.40 179	99.31 158	99.86 20	97.94 258	99.67 69	99.62 43	99.43 11	99.99 2	99.91 23	87.29 384	100.00 1	99.92 15	99.92 30	99.98 2

test_fmvs1_n		98.41 183	98.14 195	99.21 178	99.82 43	97.71 271	99.74 46	99.49 154	99.32 18	99.99 2	99.95 3	85.32 397	99.97 22	99.82 20	99.84 86	99.96 7

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 32	99.82 25	99.54 149	99.66 28	99.46 7	99.98 8	99.89 35	97.27 129	99.99 4	99.97 1	99.95 18	99.95 9

fmvsm_s_conf0.1_n_2		99.37 59	99.22 72	99.81 50	99.77 65	99.75 44	99.46 201	99.60 56	99.47 4	99.98 8	99.94 6	94.98 212	99.95 65	99.97 1	99.79 113	99.73 103

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 34	99.86 20	99.61 74	99.56 130	99.63 41	99.48 3	99.98 8	99.83 76	98.75 58	99.99 4	99.97 1	99.96 13	99.94 13

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 34	99.84 32	99.63 71	99.56 130	99.63 41	99.47 4	99.98 8	99.82 85	98.75 58	99.99 4	99.97 1	99.97 7	99.94 13

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 34	99.83 40	99.64 70	99.52 159	99.65 35	99.10 35	99.98 8	99.92 17	97.35 125	99.96 34	99.94 12	99.92 30	99.95 9

fmvsm_s_conf0.5_n		99.51 22	99.40 31	99.85 34	99.84 32	99.65 64	99.51 168	99.67 23	99.13 28	99.98 8	99.92 17	96.60 153	99.96 34	99.95 10	99.96 13	99.95 9

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 59	99.84 32	99.44 103	99.58 117	99.69 18	99.43 11	99.98 8	99.91 23	98.62 73	100.00 1	99.97 1	99.95 18	99.90 19

test_fmvs1		98.88 139	98.79 140	99.16 183	99.69 112	97.61 275	99.55 144	99.49 154	99.32 18	99.98 8	99.91 23	91.41 333	99.96 34	99.82 20	99.92 30	99.90 19

dcpmvs_2		99.23 84	99.58 7	98.16 312	99.83 40	94.68 379	99.76 37	99.52 110	99.07 43	99.98 8	99.88 43	98.56 77	99.93 94	99.67 27	99.98 4	99.87 33

test_cas_vis1_n_1920		99.16 92	99.01 104	99.61 95	99.81 47	98.86 185	99.65 81	99.64 38	99.39 14	99.97 17	99.94 6	93.20 285	99.98 14	99.55 38	99.91 37	99.99 1

mvsany_test1		99.50 24	99.46 24	99.62 94	99.61 149	99.09 148	98.94 360	99.48 166	99.10 35	99.96 18	99.91 23	98.85 42	99.96 34	99.72 23	99.58 149	99.82 60

mamv4		99.33 65	99.42 26	99.07 191	99.67 118	97.73 266	99.42 221	99.60 56	98.15 147	99.94 19	99.91 23	98.42 88	99.94 76	99.72 23	99.96 13	99.54 172

test_fmvsmconf_n		99.70 3	99.64 4	99.87 16	99.80 53	99.66 60	99.48 190	99.64 38	99.45 8	99.92 20	99.92 17	98.62 73	99.99 4	99.96 8	99.99 1	99.96 7

SED-MVS		99.61 8	99.52 12	99.88 10	99.84 32	99.90 2	99.60 102	99.48 166	99.08 41	99.91 21	99.81 99	99.20 7	99.96 34	98.91 114	99.85 78	99.79 80

test_241102_ONE					99.84 32	99.90 2		99.48 166	99.07 43	99.91 21	99.74 151	99.20 7	99.76 215

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 58	99.88 8	99.56 130	99.55 83	99.15 25	99.90 23	99.90 30	99.00 22	99.97 22	99.11 88	99.91 37	99.86 35

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 87	99.78 58	99.14 143	99.60 102	99.45 207	99.01 48	99.90 23	99.83 76	98.98 24	99.93 94	99.59 33	99.95 18	99.86 35

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 69	99.88 8	99.52 159	99.54 92	99.13 28	99.89 25	99.89 35	98.96 25	99.96 34	99.04 96	99.90 46	99.85 39

our_new_method		99.61 8	99.52 12	99.90 5	99.76 69	99.88 8	99.52 159	99.54 92	99.13 28	99.89 25	99.89 35	98.96 25	99.96 34	99.04 96	99.90 46	99.85 39

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 87	99.78 58	99.15 142	99.61 101	99.45 207	99.01 48	99.89 25	99.82 85	99.01 18	99.92 106	99.56 37	99.95 18	99.85 39

DVP-MVS++		99.59 12	99.50 17	99.88 10	99.51 181	99.88 8	99.87 8	99.51 124	98.99 53	99.88 28	99.81 99	99.27 5	99.96 34	98.85 127	99.80 106	99.81 67

test_241102_TWO								99.48 166	99.08 41	99.88 28	99.81 99	98.94 32	99.96 34	98.91 114	99.84 86	99.88 28

DPE-MVS		99.46 35	99.32 47	99.91 3	99.78 58	99.88 8	99.36 248	99.51 124	98.73 85	99.88 28	99.84 71	98.72 64	99.96 34	98.16 212	99.87 63	99.88 28
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SD-MVS		99.41 52	99.52 12	99.05 195	99.74 87	99.68 55	99.46 201	99.52 110	99.11 34	99.88 28	99.91 23	99.43 1	97.70 408	98.72 145	99.93 27	99.77 88
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
APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 65	99.89 4	99.75 42	99.56 75	99.02 46	99.88 28	99.85 61	99.18 10	99.96 34	99.22 78	99.92 30	99.90 19
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVSMamba_PlusPlus		99.46 35	99.41 30	99.64 87	99.68 116	99.50 95	99.75 42	99.50 144	98.27 130	99.87 33	99.92 17	98.09 104	99.94 76	99.65 29	99.95 18	99.47 199

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 27	99.44 211	99.65 64	99.50 175	99.61 50	99.45 8	99.87 33	99.92 17	97.31 126	99.97 22	99.95 10	99.99 1	99.97 4

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 62	99.38 229	99.37 109	99.58 117	99.62 43	99.41 13	99.87 33	99.92 17	98.81 47	100.00 1	99.97 1	99.93 27	99.94 13

balanced_conf03		99.46 35	99.39 33	99.67 76	99.55 168	99.58 82	99.74 46	99.51 124	98.42 113	99.87 33	99.84 71	98.05 107	99.91 118	99.58 35	99.94 25	99.52 179

test0726					99.85 26	99.89 4	99.62 95	99.50 144	99.10 35	99.86 37	99.82 85	98.94 32

Vis-MVSNet		99.12 105	98.97 110	99.56 105	99.78 58	99.10 147	99.68 66	99.66 28	98.49 104	99.86 37	99.87 52	94.77 228	99.84 168	99.19 80	99.41 161	99.74 98
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
BP-MVS1		99.12 105	98.94 118	99.65 81	99.51 181	99.30 121	99.67 69	98.92 347	98.48 105	99.84 39	99.69 176	94.96 213	99.92 106	99.62 32	99.79 113	99.71 119

PC_three_1452									98.18 145	99.84 39	99.70 166	99.31 3	98.52 391	98.30 202	99.80 106	99.81 67

IU-MVS					99.84 32	99.88 8		99.32 281	98.30 127	99.84 39				98.86 125	99.85 78	99.89 22

xiu_mvs_v1_base_debu		99.29 72	99.27 64	99.34 151	99.63 139	98.97 165	99.12 317	99.51 124	98.86 68	99.84 39	99.47 269	98.18 100	99.99 4	99.50 45	99.31 170	99.08 250

xiu_mvs_v1_base		99.29 72	99.27 64	99.34 151	99.63 139	98.97 165	99.12 317	99.51 124	98.86 68	99.84 39	99.47 269	98.18 100	99.99 4	99.50 45	99.31 170	99.08 250

xiu_mvs_v1_base_debi		99.29 72	99.27 64	99.34 151	99.63 139	98.97 165	99.12 317	99.51 124	98.86 68	99.84 39	99.47 269	98.18 100	99.99 4	99.50 45	99.31 170	99.08 250

DeepPCF-MVS	98.18 3	98.81 154	99.37 37	97.12 366	99.60 154	91.75 406	98.61 391	99.44 215	99.35 16	99.83 45	99.85 61	98.70 66	99.81 194	99.02 100	99.91 37	99.81 67

TSAR-MVS + GP.		99.36 62	99.36 39	99.36 149	99.67 118	98.61 210	99.07 327	99.33 271	99.00 51	99.82 46	99.81 99	99.06 16	99.84 168	99.09 92	99.42 160	99.65 137

FOURS1					99.91 1	99.93 1	99.87 8	99.56 75	99.10 35	99.81 47

DVP-MVS		99.57 16	99.47 21	99.88 10	99.85 26	99.89 4	99.57 124	99.37 251	99.10 35	99.81 47	99.80 112	98.94 32	99.96 34	98.93 111	99.86 71	99.81 67
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 53	99.81 47	99.80 112	99.09 14	99.96 34	98.85 127	99.90 46	99.88 28

RRT-MVS		98.91 137	98.75 143	99.39 147	99.46 204	98.61 210	99.76 37	99.50 144	98.06 167	99.81 47	99.88 43	93.91 270	99.94 76	99.11 88	99.27 173	99.61 153

MVSFormer		99.17 90	99.12 83	99.29 166	99.51 181	98.94 175	99.88 4	99.46 196	97.55 227	99.80 51	99.65 196	97.39 121	99.28 318	99.03 98	99.85 78	99.65 137

lupinMVS		99.13 99	99.01 104	99.46 135	99.51 181	98.94 175	99.05 332	99.16 316	97.86 187	99.80 51	99.56 234	97.39 121	99.86 155	98.94 108	99.85 78	99.58 164

tttt0517		98.42 181	98.14 195	99.28 170	99.66 128	98.38 233	99.74 46	96.85 414	97.68 212	99.79 53	99.74 151	91.39 334	99.89 142	98.83 133	99.56 150	99.57 167

APD-MVS_3200maxsize		99.48 30	99.35 41	99.85 34	99.76 69	99.83 19	99.63 90	99.54 92	98.36 120	99.79 53	99.82 85	98.86 41	99.95 65	98.62 159	99.81 102	99.78 86

jason		99.13 99	99.03 96	99.45 136	99.46 204	98.87 182	99.12 317	99.26 299	98.03 172	99.79 53	99.65 196	97.02 139	99.85 161	99.02 100	99.90 46	99.65 137
jason: jason.
SteuartSystems-ACMMP		99.54 19	99.42 26	99.87 16	99.82 43	99.81 29	99.59 109	99.51 124	98.62 93	99.79 53	99.83 76	99.28 4	99.97 22	98.48 181	99.90 46	99.84 45
Skip Steuart: Steuart Systems R&D Blog.
DeepC-MVS_fast	98.69 1	99.49 26	99.39 33	99.77 62	99.63 139	99.59 77	99.36 248	99.46 196	99.07 43	99.79 53	99.82 85	98.85 42	99.92 106	98.68 152	99.87 63	99.82 60
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf0.01_n		99.22 85	99.03 96	99.79 56	98.42 387	99.48 98	99.55 144	99.51 124	99.39 14	99.78 58	99.93 10	94.80 223	99.95 65	99.93 14	99.95 18	99.94 13

CS-MVS		99.50 24	99.48 19	99.54 108	99.76 69	99.42 105	99.90 1	99.55 83	98.56 98	99.78 58	99.70 166	98.65 71	99.79 204	99.65 29	99.78 115	99.41 214

SMA-MVS		99.44 43	99.30 55	99.85 34	99.73 94	99.83 19	99.56 130	99.47 187	97.45 240	99.78 58	99.82 85	99.18 10	99.91 118	98.79 138	99.89 57	99.81 67
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
TSAR-MVS + MP.		99.58 13	99.50 17	99.81 50	99.91 1	99.66 60	99.63 90	99.39 235	98.91 66	99.78 58	99.85 61	99.36 2	99.94 76	98.84 130	99.88 60	99.82 60
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
GDP-MVS		99.08 116	98.89 125	99.64 87	99.53 172	99.34 113	99.64 84	99.48 166	98.32 125	99.77 62	99.66 194	95.14 209	99.93 94	98.97 106	99.50 155	99.64 144

test2506		96.81 335	96.65 331	97.29 362	99.74 87	92.21 405	99.60 102	85.06 436	99.13 28	99.77 62	99.93 10	87.82 382	99.85 161	99.38 57	99.38 162	99.80 76

test_part2					99.81 47	99.83 19				99.77 62

MSP-MVS		99.42 48	99.27 64	99.88 10	99.89 8	99.80 31	99.67 69	99.50 144	98.70 87	99.77 62	99.49 260	98.21 98	99.95 65	98.46 185	99.77 118	99.88 28
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
UA-Net		99.42 48	99.29 59	99.80 53	99.62 145	99.55 85	99.50 175	99.70 15	98.79 78	99.77 62	99.96 1	97.45 120	99.96 34	98.92 113	99.90 46	99.89 22

APD-MVS		99.27 76	99.08 89	99.84 45	99.75 79	99.79 34	99.50 175	99.50 144	97.16 268	99.77 62	99.82 85	98.78 51	99.94 76	97.56 269	99.86 71	99.80 76
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SR-MVS-dyc-post		99.45 39	99.31 53	99.85 34	99.76 69	99.82 25	99.63 90	99.52 110	98.38 116	99.76 68	99.82 85	98.53 79	99.95 65	98.61 162	99.81 102	99.77 88

RE-MVS-def			99.34 43		99.76 69	99.82 25	99.63 90	99.52 110	98.38 116	99.76 68	99.82 85	98.75 58		98.61 162	99.81 102	99.77 88

ACMMP_NAP		99.47 33	99.34 43	99.88 10	99.87 15	99.86 16	99.47 198	99.48 166	98.05 169	99.76 68	99.86 56	98.82 46	99.93 94	98.82 137	99.91 37	99.84 45

HPM-MVS_fast		99.51 22	99.40 31	99.85 34	99.91 1	99.79 34	99.76 37	99.56 75	97.72 206	99.76 68	99.75 146	99.13 12	99.92 106	99.07 94	99.92 30	99.85 39

MM		99.40 55	99.28 61	99.74 68	99.67 118	99.31 119	99.52 159	98.87 359	99.55 1	99.74 72	99.80 112	96.47 159	99.98 14	99.97 1	99.97 7	99.94 13

VNet		99.11 110	98.90 122	99.73 71	99.52 178	99.56 83	99.41 224	99.39 235	99.01 48	99.74 72	99.78 131	95.56 193	99.92 106	99.52 43	98.18 251	99.72 110

patch_mono-2		99.26 78	99.62 5	98.16 312	99.81 47	94.59 381	99.52 159	99.64 38	99.33 17	99.73 74	99.90 30	99.00 22	99.99 4	99.69 25	99.98 4	99.89 22

SR-MVS		99.43 46	99.29 59	99.86 27	99.75 79	99.83 19	99.59 109	99.62 43	98.21 140	99.73 74	99.79 124	98.68 67	99.96 34	98.44 187	99.77 118	99.79 80

thisisatest0530		98.35 190	98.03 210	99.31 158	99.63 139	98.56 213	99.54 149	96.75 416	97.53 231	99.73 74	99.65 196	91.25 338	99.89 142	98.62 159	99.56 150	99.48 193

SPE-MVS-test		99.49 26	99.48 19	99.54 108	99.78 58	99.30 121	99.89 2	99.58 65	98.56 98	99.73 74	99.69 176	98.55 78	99.82 189	99.69 25	99.85 78	99.48 193

EC-MVSNet		99.44 43	99.39 33	99.58 101	99.56 164	99.49 96	99.88 4	99.58 65	98.38 116	99.73 74	99.69 176	98.20 99	99.70 242	99.64 31	99.82 99	99.54 172

mmtdpeth		96.95 331	96.71 330	97.67 350	99.33 241	94.90 376	99.89 2	99.28 295	98.15 147	99.72 79	98.57 383	86.56 389	99.90 130	99.82 20	89.02 408	98.20 378

diffmvs		99.14 97	99.02 100	99.51 124	99.61 149	98.96 169	99.28 275	99.49 154	98.46 107	99.72 79	99.71 162	96.50 158	99.88 147	99.31 68	99.11 185	99.67 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SF-MVS		99.38 58	99.24 69	99.79 56	99.79 56	99.68 55	99.57 124	99.54 92	97.82 197	99.71 81	99.80 112	98.95 30	99.93 94	98.19 208	99.84 86	99.74 98

xiu_mvs_v2_base		99.26 78	99.25 68	99.29 166	99.53 172	98.91 179	99.02 340	99.45 207	98.80 77	99.71 81	99.26 327	98.94 32	99.98 14	99.34 64	99.23 175	98.98 264

PS-MVSNAJ		99.32 67	99.32 47	99.30 163	99.57 160	98.94 175	98.97 354	99.46 196	98.92 65	99.71 81	99.24 329	99.01 18	99.98 14	99.35 59	99.66 139	98.97 265

PGM-MVS		99.45 39	99.31 53	99.86 27	99.87 15	99.78 40	99.58 117	99.65 35	97.84 192	99.71 81	99.80 112	99.12 13	99.97 22	98.33 198	99.87 63	99.83 55

114514_t		98.93 135	98.67 151	99.72 73	99.85 26	99.53 90	99.62 95	99.59 61	92.65 401	99.71 81	99.78 131	98.06 106	99.90 130	98.84 130	99.91 37	99.74 98

PVSNet_Blended_VisFu		99.36 62	99.28 61	99.61 95	99.86 20	99.07 153	99.47 198	99.93 2	97.66 215	99.71 81	99.86 56	97.73 115	99.96 34	99.47 52	99.82 99	99.79 80

MTAPA		99.52 21	99.39 33	99.89 8	99.90 4	99.86 16	99.66 75	99.47 187	98.79 78	99.68 87	99.81 99	98.43 86	99.97 22	98.88 117	99.90 46	99.83 55

HFP-MVS		99.49 26	99.37 37	99.86 27	99.87 15	99.80 31	99.66 75	99.67 23	98.15 147	99.68 87	99.69 176	99.06 16	99.96 34	98.69 150	99.87 63	99.84 45

VDDNet		97.55 300	97.02 321	99.16 183	99.49 194	98.12 245	99.38 241	99.30 289	95.35 365	99.68 87	99.90 30	82.62 409	99.93 94	99.31 68	98.13 255	99.42 211

HPM-MVS		99.42 48	99.28 61	99.83 46	99.90 4	99.72 48	99.81 20	99.54 92	97.59 221	99.68 87	99.63 208	98.91 37	99.94 76	98.58 168	99.91 37	99.84 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
VDD-MVS		97.73 279	97.35 295	98.88 225	99.47 202	97.12 294	99.34 256	98.85 361	98.19 142	99.67 91	99.85 61	82.98 407	99.92 106	99.49 49	98.32 241	99.60 156

ACMMPR		99.49 26	99.36 39	99.86 27	99.87 15	99.79 34	99.66 75	99.67 23	98.15 147	99.67 91	99.69 176	98.95 30	99.96 34	98.69 150	99.87 63	99.84 45

PVSNet_BlendedMVS		98.86 143	98.80 137	99.03 197	99.76 69	98.79 194	99.28 275	99.91 3	97.42 246	99.67 91	99.37 297	97.53 118	99.88 147	98.98 103	97.29 302	98.42 363

PVSNet_Blended		99.08 116	98.97 110	99.42 141	99.76 69	98.79 194	98.78 376	99.91 3	96.74 301	99.67 91	99.49 260	97.53 118	99.88 147	98.98 103	99.85 78	99.60 156

sss		99.17 90	99.05 92	99.53 116	99.62 145	98.97 165	99.36 248	99.62 43	97.83 193	99.67 91	99.65 196	97.37 124	99.95 65	99.19 80	99.19 178	99.68 127

ECVR-MVS		98.04 223	98.05 208	98.00 325	99.74 87	94.37 385	99.59 109	94.98 424	99.13 28	99.66 96	99.93 10	90.67 344	99.84 168	99.40 56	99.38 162	99.80 76

h-mvs33		97.70 285	97.28 307	98.97 205	99.70 108	97.27 286	99.36 248	99.45 207	98.94 62	99.66 96	99.64 202	94.93 215	99.99 4	99.48 50	84.36 415	99.65 137

hse-mvs2		97.50 305	97.14 315	98.59 260	99.49 194	97.05 301	99.28 275	99.22 307	98.94 62	99.66 96	99.42 280	94.93 215	99.65 258	99.48 50	83.80 417	99.08 250

MVS_0304		99.15 94	98.96 114	99.73 71	98.92 335	99.37 109	99.37 243	96.92 413	99.51 2	99.66 96	99.78 131	96.69 150	99.97 22	99.84 19	99.97 7	99.84 45

region2R		99.48 30	99.35 41	99.87 16	99.88 11	99.80 31	99.65 81	99.66 28	98.13 152	99.66 96	99.68 183	98.96 25	99.96 34	98.62 159	99.87 63	99.84 45

RPSCF		98.22 198	98.62 161	96.99 368	99.82 43	91.58 407	99.72 52	99.44 215	96.61 313	99.66 96	99.89 35	95.92 180	99.82 189	97.46 279	99.10 188	99.57 167

OMC-MVS		99.08 116	99.04 94	99.20 179	99.67 118	98.22 239	99.28 275	99.52 110	98.07 163	99.66 96	99.81 99	97.79 113	99.78 209	97.79 243	99.81 102	99.60 156

test1111		98.04 223	98.11 199	97.83 340	99.74 87	93.82 390	99.58 117	95.40 423	99.12 33	99.65 103	99.93 10	90.73 343	99.84 168	99.43 55	99.38 162	99.82 60

test_one_0601					99.81 47	99.88 8		99.49 154	98.97 59	99.65 103	99.81 99	99.09 14

LFMVS		97.90 246	97.35 295	99.54 108	99.52 178	99.01 160	99.39 236	98.24 397	97.10 276	99.65 103	99.79 124	84.79 400	99.91 118	99.28 72	98.38 234	99.69 123

mvsmamba		99.06 119	98.96 114	99.36 149	99.47 202	98.64 206	99.70 56	99.05 331	97.61 220	99.65 103	99.83 76	96.54 156	99.92 106	99.19 80	99.62 145	99.51 187

MVS_111021_LR		99.41 52	99.33 45	99.65 81	99.77 65	99.51 94	98.94 360	99.85 6	98.82 73	99.65 103	99.74 151	98.51 81	99.80 201	98.83 133	99.89 57	99.64 144

SDMVSNet		99.11 110	98.90 122	99.75 65	99.81 47	99.59 77	99.81 20	99.65 35	98.78 81	99.64 108	99.88 43	94.56 242	99.93 94	99.67 27	98.26 243	99.72 110

sd_testset		98.75 161	98.57 168	99.29 166	99.81 47	98.26 237	99.56 130	99.62 43	98.78 81	99.64 108	99.88 43	92.02 317	99.88 147	99.54 39	98.26 243	99.72 110

9.14			99.10 85		99.72 98		99.40 232	99.51 124	97.53 231	99.64 108	99.78 131	98.84 44	99.91 118	97.63 260	99.82 99

GST-MVS		99.40 55	99.24 69	99.85 34	99.86 20	99.79 34	99.60 102	99.67 23	97.97 177	99.63 111	99.68 183	98.52 80	99.95 65	98.38 191	99.86 71	99.81 67

CPTT-MVS		99.11 110	98.90 122	99.74 68	99.80 53	99.46 101	99.59 109	99.49 154	97.03 284	99.63 111	99.69 176	97.27 129	99.96 34	97.82 241	99.84 86	99.81 67

ACMMP		99.45 39	99.32 47	99.82 47	99.89 8	99.67 58	99.62 95	99.69 18	98.12 153	99.63 111	99.84 71	98.73 63	99.96 34	98.55 177	99.83 95	99.81 67
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
DeepC-MVS	98.35 2	99.30 70	99.19 76	99.64 87	99.82 43	99.23 131	99.62 95	99.55 83	98.94 62	99.63 111	99.95 3	95.82 185	99.94 76	99.37 58	99.97 7	99.73 103
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FE-MVS		98.48 176	98.17 191	99.40 143	99.54 171	98.96 169	99.68 66	98.81 366	95.54 363	99.62 115	99.70 166	93.82 273	99.93 94	97.35 287	99.46 157	99.32 228

CHOSEN 280x420		99.12 105	99.13 81	99.08 190	99.66 128	97.89 259	98.43 401	99.71 13	98.88 67	99.62 115	99.76 143	96.63 152	99.70 242	99.46 53	99.99 1	99.66 133

PHI-MVS		99.30 70	99.17 78	99.70 74	99.56 164	99.52 93	99.58 117	99.80 8	97.12 272	99.62 115	99.73 157	98.58 75	99.90 130	98.61 162	99.91 37	99.68 127

test_yl		98.86 143	98.63 156	99.54 108	99.49 194	99.18 135	99.50 175	99.07 328	98.22 138	99.61 118	99.51 254	95.37 199	99.84 168	98.60 165	98.33 237	99.59 160

DCV-MVSNet		98.86 143	98.63 156	99.54 108	99.49 194	99.18 135	99.50 175	99.07 328	98.22 138	99.61 118	99.51 254	95.37 199	99.84 168	98.60 165	98.33 237	99.59 160

MG-MVS		99.13 99	99.02 100	99.45 136	99.57 160	98.63 207	99.07 327	99.34 264	98.99 53	99.61 118	99.82 85	97.98 109	99.87 152	97.00 306	99.80 106	99.85 39

MP-MVS-pluss		99.37 59	99.20 74	99.88 10	99.90 4	99.87 15	99.30 265	99.52 110	97.18 266	99.60 121	99.79 124	98.79 50	99.95 65	98.83 133	99.91 37	99.83 55
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CDPH-MVS		99.13 99	98.91 121	99.80 53	99.75 79	99.71 50	99.15 311	99.41 226	96.60 316	99.60 121	99.55 237	98.83 45	99.90 130	97.48 276	99.83 95	99.78 86

EPP-MVSNet		99.13 99	98.99 106	99.53 116	99.65 134	99.06 154	99.81 20	99.33 271	97.43 244	99.60 121	99.88 43	97.14 132	99.84 168	99.13 86	98.94 199	99.69 123

HyFIR lowres test		99.11 110	98.92 119	99.65 81	99.90 4	99.37 109	99.02 340	99.91 3	97.67 214	99.59 124	99.75 146	95.90 182	99.73 226	99.53 41	99.02 196	99.86 35

FA-MVS(test-final)		98.75 161	98.53 172	99.41 142	99.55 168	99.05 156	99.80 25	99.01 336	96.59 318	99.58 125	99.59 222	95.39 198	99.90 130	97.78 244	99.49 156	99.28 231

MVS_Test		99.10 114	98.97 110	99.48 130	99.49 194	99.14 143	99.67 69	99.34 264	97.31 255	99.58 125	99.76 143	97.65 117	99.82 189	98.87 120	99.07 191	99.46 204

MDTV_nov1_ep13_2view						95.18 371	99.35 253		96.84 297	99.58 125		95.19 208		97.82 241		99.46 204

DELS-MVS		99.48 30	99.42 26	99.65 81	99.72 98	99.40 108	99.05 332	99.66 28	99.14 27	99.57 128	99.80 112	98.46 84	99.94 76	99.57 36	99.84 86	99.60 156
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
ZD-MVS					99.71 103	99.79 34		99.61 50	96.84 297	99.56 129	99.54 242	98.58 75	99.96 34	96.93 313	99.75 123

CR-MVSNet		98.17 205	97.93 222	98.87 229	99.18 283	98.49 224	99.22 300	99.33 271	96.96 288	99.56 129	99.38 294	94.33 252	99.00 364	94.83 368	98.58 222	99.14 242

RPMNet		96.72 336	95.90 349	99.19 180	99.18 283	98.49 224	99.22 300	99.52 110	88.72 415	99.56 129	97.38 409	94.08 262	99.95 65	86.87 417	98.58 222	99.14 242

IS-MVSNet		99.05 121	98.87 128	99.57 103	99.73 94	99.32 115	99.75 42	99.20 311	98.02 174	99.56 129	99.86 56	96.54 156	99.67 250	98.09 215	99.13 184	99.73 103

ZNCC-MVS		99.47 33	99.33 45	99.87 16	99.87 15	99.81 29	99.64 84	99.67 23	98.08 162	99.55 133	99.64 202	98.91 37	99.96 34	98.72 145	99.90 46	99.82 60

thisisatest0515		98.14 208	97.79 234	99.19 180	99.50 192	98.50 223	98.61 391	96.82 415	96.95 290	99.54 134	99.43 278	91.66 329	99.86 155	98.08 219	99.51 154	99.22 239

MVS_111021_HR		99.41 52	99.32 47	99.66 77	99.72 98	99.47 100	98.95 358	99.85 6	98.82 73	99.54 134	99.73 157	98.51 81	99.74 220	98.91 114	99.88 60	99.77 88

CP-MVS		99.45 39	99.32 47	99.85 34	99.83 40	99.75 44	99.69 60	99.52 110	98.07 163	99.53 136	99.63 208	98.93 36	99.97 22	98.74 142	99.91 37	99.83 55

WTY-MVS		99.06 119	98.88 127	99.61 95	99.62 145	99.16 138	99.37 243	99.56 75	98.04 170	99.53 136	99.62 213	96.84 144	99.94 76	98.85 127	98.49 230	99.72 110

MCST-MVS		99.43 46	99.30 55	99.82 47	99.79 56	99.74 47	99.29 270	99.40 232	98.79 78	99.52 138	99.62 213	98.91 37	99.90 130	98.64 156	99.75 123	99.82 60

PatchT		97.03 330	96.44 336	98.79 244	98.99 325	98.34 234	99.16 308	99.07 328	92.13 402	99.52 138	97.31 412	94.54 245	98.98 366	88.54 410	98.73 215	99.03 258

CANet		99.25 82	99.14 80	99.59 98	99.41 219	99.16 138	99.35 253	99.57 70	98.82 73	99.51 140	99.61 217	96.46 160	99.95 65	99.59 33	99.98 4	99.65 137

mPP-MVS		99.44 43	99.30 55	99.86 27	99.88 11	99.79 34	99.69 60	99.48 166	98.12 153	99.50 141	99.75 146	98.78 51	99.97 22	98.57 171	99.89 57	99.83 55

PatchMatch-RL		98.84 153	98.62 161	99.52 122	99.71 103	99.28 124	99.06 330	99.77 9	97.74 205	99.50 141	99.53 246	95.41 197	99.84 168	97.17 300	99.64 142	99.44 209

PVSNet	96.02 17	98.85 150	98.84 134	98.89 223	99.73 94	97.28 285	98.32 407	99.60 56	97.86 187	99.50 141	99.57 231	96.75 148	99.86 155	98.56 174	99.70 133	99.54 172

LS3D		99.27 76	99.12 83	99.74 68	99.18 283	99.75 44	99.56 130	99.57 70	98.45 109	99.49 144	99.85 61	97.77 114	99.94 76	98.33 198	99.84 86	99.52 179

MP-MVS		99.33 65	99.15 79	99.87 16	99.88 11	99.82 25	99.66 75	99.46 196	98.09 158	99.48 145	99.74 151	98.29 95	99.96 34	97.93 230	99.87 63	99.82 60
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
旧先验2							98.96 355		96.70 304	99.47 146			99.94 76	98.19 208

MSDG		98.98 131	98.80 137	99.53 116	99.76 69	99.19 133	98.75 379	99.55 83	97.25 260	99.47 146	99.77 139	97.82 112	99.87 152	96.93 313	99.90 46	99.54 172

CDS-MVSNet		99.09 115	99.03 96	99.25 173	99.42 214	98.73 198	99.45 203	99.46 196	98.11 155	99.46 148	99.77 139	98.01 108	99.37 301	98.70 147	98.92 202	99.66 133
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MSLP-MVS++		99.46 35	99.47 21	99.44 140	99.60 154	99.16 138	99.41 224	99.71 13	98.98 56	99.45 149	99.78 131	99.19 9	99.54 276	99.28 72	99.84 86	99.63 149

XVG-OURS		98.73 164	98.68 150	98.88 225	99.70 108	97.73 266	98.92 362	99.55 83	98.52 102	99.45 149	99.84 71	95.27 203	99.91 118	98.08 219	98.84 208	99.00 261

casdiffmvs_mvg		99.15 94	99.02 100	99.55 107	99.66 128	99.09 148	99.64 84	99.56 75	98.26 132	99.45 149	99.87 52	96.03 174	99.81 194	99.54 39	99.15 182	99.73 103
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tpmrst		98.33 191	98.48 174	97.90 334	99.16 293	94.78 377	99.31 263	99.11 321	97.27 258	99.45 149	99.59 222	95.33 201	99.84 168	98.48 181	98.61 219	99.09 249

TAMVS		99.12 105	99.08 89	99.24 175	99.46 204	98.55 214	99.51 168	99.46 196	98.09 158	99.45 149	99.82 85	98.34 93	99.51 278	98.70 147	98.93 200	99.67 130

MonoMVSNet		98.38 187	98.47 175	98.12 317	98.59 380	96.19 345	99.72 52	98.79 369	97.89 184	99.44 154	99.52 250	96.13 170	98.90 380	98.64 156	97.54 283	99.28 231

ETV-MVS		99.26 78	99.21 73	99.40 143	99.46 204	99.30 121	99.56 130	99.52 110	98.52 102	99.44 154	99.27 325	98.41 90	99.86 155	99.10 91	99.59 148	99.04 257

CANet_DTU		98.97 133	98.87 128	99.25 173	99.33 241	98.42 232	99.08 326	99.30 289	99.16 24	99.43 156	99.75 146	95.27 203	99.97 22	98.56 174	99.95 18	99.36 222

SCA		98.19 202	98.16 192	98.27 306	99.30 250	95.55 357	99.07 327	98.97 340	97.57 224	99.43 156	99.57 231	92.72 296	99.74 220	97.58 264	99.20 177	99.52 179

testdata				99.54 108	99.75 79	98.95 172		99.51 124	97.07 278	99.43 156	99.70 166	98.87 40	99.94 76	97.76 248	99.64 142	99.72 110

DPM-MVS		98.95 134	98.71 147	99.66 77	99.63 139	99.55 85	98.64 390	99.10 322	97.93 180	99.42 159	99.55 237	98.67 69	99.80 201	95.80 346	99.68 137	99.61 153

XVG-OURS-SEG-HR		98.69 166	98.62 161	98.89 223	99.71 103	97.74 265	99.12 317	99.54 92	98.44 112	99.42 159	99.71 162	94.20 256	99.92 106	98.54 178	98.90 204	99.00 261

baseline		99.15 94	99.02 100	99.53 116	99.66 128	99.14 143	99.72 52	99.48 166	98.35 121	99.42 159	99.84 71	96.07 172	99.79 204	99.51 44	99.14 183	99.67 130

DP-MVS Recon		99.12 105	98.95 116	99.65 81	99.74 87	99.70 52	99.27 280	99.57 70	96.40 332	99.42 159	99.68 183	98.75 58	99.80 201	97.98 227	99.72 129	99.44 209

Effi-MVS+-dtu		98.78 158	98.89 125	98.47 280	99.33 241	96.91 314	99.57 124	99.30 289	98.47 106	99.41 163	98.99 357	96.78 146	99.74 220	98.73 144	99.38 162	98.74 288

casdiffmvs		99.13 99	98.98 109	99.56 105	99.65 134	99.16 138	99.56 130	99.50 144	98.33 124	99.41 163	99.86 56	95.92 180	99.83 181	99.45 54	99.16 179	99.70 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MIMVSNet		97.73 279	97.45 278	98.57 264	99.45 210	97.50 278	99.02 340	98.98 339	96.11 352	99.41 163	99.14 340	90.28 346	98.74 386	95.74 347	98.93 200	99.47 199

CSCG		99.32 67	99.32 47	99.32 157	99.85 26	98.29 235	99.71 55	99.66 28	98.11 155	99.41 163	99.80 112	98.37 92	99.96 34	98.99 102	99.96 13	99.72 110

F-COLMAP		99.19 86	99.04 94	99.64 87	99.78 58	99.27 126	99.42 221	99.54 92	97.29 257	99.41 163	99.59 222	98.42 88	99.93 94	98.19 208	99.69 134	99.73 103

EIA-MVS		99.18 88	99.09 88	99.45 136	99.49 194	99.18 135	99.67 69	99.53 105	97.66 215	99.40 168	99.44 276	98.10 103	99.81 194	98.94 108	99.62 145	99.35 223

MDTV_nov1_ep13			98.32 184		99.11 301	94.44 383	99.27 280	98.74 375	97.51 234	99.40 168	99.62 213	94.78 225	99.76 215	97.59 263	98.81 212

CVMVSNet		98.57 174	98.67 151	98.30 300	99.35 236	95.59 356	99.50 175	99.55 83	98.60 95	99.39 170	99.83 76	94.48 247	99.45 284	98.75 141	98.56 225	99.85 39

CNVR-MVS		99.42 48	99.30 55	99.78 59	99.62 145	99.71 50	99.26 289	99.52 110	98.82 73	99.39 170	99.71 162	98.96 25	99.85 161	98.59 167	99.80 106	99.77 88

Effi-MVS+		98.81 154	98.59 167	99.48 130	99.46 204	99.12 146	98.08 414	99.50 144	97.50 235	99.38 172	99.41 284	96.37 164	99.81 194	99.11 88	98.54 227	99.51 187

mvs_anonymous		99.03 124	98.99 106	99.16 183	99.38 229	98.52 220	99.51 168	99.38 243	97.79 198	99.38 172	99.81 99	97.30 127	99.45 284	99.35 59	98.99 197	99.51 187

XVS		99.53 20	99.42 26	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 56	99.37 174	99.74 151	98.81 47	99.94 76	98.79 138	99.86 71	99.84 45

X-MVStestdata		96.55 339	95.45 358	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 56	99.37 174	64.01 432	98.81 47	99.94 76	98.79 138	99.86 71	99.84 45

PatchmatchNet		98.31 192	98.36 180	98.19 310	99.16 293	95.32 367	99.27 280	98.92 347	97.37 250	99.37 174	99.58 226	94.90 218	99.70 242	97.43 282	99.21 176	99.54 172
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
AllTest		98.87 140	98.72 145	99.31 158	99.86 20	98.48 226	99.56 130	99.61 50	97.85 190	99.36 177	99.85 61	95.95 177	99.85 161	96.66 326	99.83 95	99.59 160

TestCases				99.31 158	99.86 20	98.48 226		99.61 50	97.85 190	99.36 177	99.85 61	95.95 177	99.85 161	96.66 326	99.83 95	99.59 160

Vis-MVSNet (Re-imp)		98.87 140	98.72 145	99.31 158	99.71 103	98.88 181	99.80 25	99.44 215	97.91 182	99.36 177	99.78 131	95.49 196	99.43 293	97.91 231	99.11 185	99.62 151

alignmvs		98.81 154	98.56 170	99.58 101	99.43 212	99.42 105	99.51 168	98.96 342	98.61 94	99.35 180	98.92 367	94.78 225	99.77 211	99.35 59	98.11 256	99.54 172

VPA-MVSNet		98.29 195	97.95 219	99.30 163	99.16 293	99.54 87	99.50 175	99.58 65	98.27 130	99.35 180	99.37 297	92.53 305	99.65 258	99.35 59	94.46 366	98.72 290

AdaColmap		99.01 129	98.80 137	99.66 77	99.56 164	99.54 87	99.18 306	99.70 15	98.18 145	99.35 180	99.63 208	96.32 165	99.90 130	97.48 276	99.77 118	99.55 170

test222					99.75 79	99.49 96	98.91 364	99.49 154	96.42 330	99.34 183	99.65 196	98.28 96			99.69 134	99.72 110

API-MVS		99.04 122	99.03 96	99.06 193	99.40 224	99.31 119	99.55 144	99.56 75	98.54 100	99.33 184	99.39 292	98.76 55	99.78 209	96.98 308	99.78 115	98.07 385

v144192		97.92 243	97.60 261	98.87 229	98.83 349	98.65 204	99.55 144	99.34 264	96.20 343	99.32 185	99.40 288	94.36 251	99.26 323	96.37 336	95.03 357	98.70 297

sasdasda		99.02 125	98.86 130	99.51 124	99.42 214	99.32 115	99.80 25	99.48 166	98.63 91	99.31 186	98.81 372	97.09 134	99.75 218	99.27 74	97.90 262	99.47 199

GeoE		98.85 150	98.62 161	99.53 116	99.61 149	99.08 151	99.80 25	99.51 124	97.10 276	99.31 186	99.78 131	95.23 207	99.77 211	98.21 206	99.03 194	99.75 94

canonicalmvs		99.02 125	98.86 130	99.51 124	99.42 214	99.32 115	99.80 25	99.48 166	98.63 91	99.31 186	98.81 372	97.09 134	99.75 218	99.27 74	97.90 262	99.47 199

V42		98.06 217	97.79 234	98.86 232	98.98 328	98.84 187	99.69 60	99.34 264	96.53 320	99.30 189	99.37 297	94.67 236	99.32 313	97.57 268	94.66 363	98.42 363

ab-mvs		98.86 143	98.63 156	99.54 108	99.64 136	99.19 133	99.44 209	99.54 92	97.77 201	99.30 189	99.81 99	94.20 256	99.93 94	99.17 84	98.82 210	99.49 192

TAPA-MVS	97.07 15	97.74 277	97.34 298	98.94 210	99.70 108	97.53 276	99.25 291	99.51 124	91.90 403	99.30 189	99.63 208	98.78 51	99.64 261	88.09 412	99.87 63	99.65 137
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
新几何1				99.75 65	99.75 79	99.59 77		99.54 92	96.76 300	99.29 192	99.64 202	98.43 86	99.94 76	96.92 315	99.66 139	99.72 110

MGCFI-Net		99.01 129	98.85 132	99.50 129	99.42 214	99.26 127	99.82 16	99.48 166	98.60 95	99.28 193	98.81 372	97.04 138	99.76 215	99.29 71	97.87 265	99.47 199

test_fmvs2		97.25 322	97.30 304	97.09 367	99.43 212	93.31 398	99.73 50	98.87 359	98.83 72	99.28 193	99.80 112	84.45 402	99.66 253	97.88 233	97.45 293	98.30 371

VPNet		97.84 257	97.44 283	99.01 199	99.21 275	98.94 175	99.48 190	99.57 70	98.38 116	99.28 193	99.73 157	88.89 363	99.39 296	99.19 80	93.27 385	98.71 292

HY-MVS	97.30 7	98.85 150	98.64 155	99.47 133	99.42 214	99.08 151	99.62 95	99.36 252	97.39 249	99.28 193	99.68 183	96.44 162	99.92 106	98.37 193	98.22 246	99.40 216

PAPM_NR		99.04 122	98.84 134	99.66 77	99.74 87	99.44 103	99.39 236	99.38 243	97.70 210	99.28 193	99.28 322	98.34 93	99.85 161	96.96 310	99.45 158	99.69 123

testing3-2		97.84 257	97.70 249	98.24 307	99.53 172	95.37 366	99.55 144	98.67 385	98.46 107	99.27 198	99.34 307	86.58 388	99.83 181	99.32 67	98.63 218	99.52 179

HPM-MVS++		99.39 57	99.23 71	99.87 16	99.75 79	99.84 18	99.43 214	99.51 124	98.68 90	99.27 198	99.53 246	98.64 72	99.96 34	98.44 187	99.80 106	99.79 80

v1240		97.69 286	97.32 302	98.79 244	98.85 346	98.43 230	99.48 190	99.36 252	96.11 352	99.27 198	99.36 300	93.76 276	99.24 326	94.46 371	95.23 352	98.70 297

thres600view7		97.86 252	97.51 269	98.92 214	99.72 98	97.95 256	99.59 109	98.74 375	97.94 179	99.27 198	98.62 380	91.75 323	99.86 155	93.73 381	98.19 250	98.96 267

PLC	97.94 4	99.02 125	98.85 132	99.53 116	99.66 128	99.01 160	99.24 293	99.52 110	96.85 296	99.27 198	99.48 266	98.25 97	99.91 118	97.76 248	99.62 145	99.65 137
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thres100view900		97.76 271	97.45 278	98.69 254	99.72 98	97.86 262	99.59 109	98.74 375	97.93 180	99.26 203	98.62 380	91.75 323	99.83 181	93.22 386	98.18 251	98.37 369

EPMVS		97.82 263	97.65 254	98.35 295	98.88 339	95.98 348	99.49 186	94.71 426	97.57 224	99.26 203	99.48 266	92.46 310	99.71 236	97.87 235	99.08 190	99.35 223

Fast-Effi-MVS+-dtu		98.77 160	98.83 136	98.60 259	99.41 219	96.99 308	99.52 159	99.49 154	98.11 155	99.24 205	99.34 307	96.96 142	99.79 204	97.95 229	99.45 158	99.02 260

v1921920		97.80 267	97.45 278	98.84 236	98.80 350	98.53 216	99.52 159	99.34 264	96.15 349	99.24 205	99.47 269	93.98 266	99.29 317	95.40 357	95.13 355	98.69 301

LPG-MVS_test		98.22 198	98.13 197	98.49 273	99.33 241	97.05 301	99.58 117	99.55 83	97.46 237	99.24 205	99.83 76	92.58 303	99.72 230	98.09 215	97.51 286	98.68 306

LGP-MVS_train				98.49 273	99.33 241	97.05 301		99.55 83	97.46 237	99.24 205	99.83 76	92.58 303	99.72 230	98.09 215	97.51 286	98.68 306

v1144		97.98 234	97.69 250	98.85 235	98.87 342	98.66 203	99.54 149	99.35 259	96.27 338	99.23 209	99.35 303	94.67 236	99.23 327	96.73 321	95.16 354	98.68 306

Anonymous20240529		98.09 213	97.68 251	99.34 151	99.66 128	98.44 229	99.40 232	99.43 221	93.67 389	99.22 210	99.89 35	90.23 350	99.93 94	99.26 76	98.33 237	99.66 133

OPM-MVS		98.19 202	98.10 200	98.45 283	98.88 339	97.07 299	99.28 275	99.38 243	98.57 97	99.22 210	99.81 99	92.12 315	99.66 253	98.08 219	97.54 283	98.61 343
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test_djsdf		98.67 168	98.57 168	98.98 203	98.70 368	98.91 179	99.88 4	99.46 196	97.55 227	99.22 210	99.88 43	95.73 188	99.28 318	99.03 98	97.62 276	98.75 284

test12				99.75 65	99.64 136	99.61 74		99.29 293		99.21 213		98.38 91	99.89 142		99.74 126	99.74 98

NCCC		99.34 64	99.19 76	99.79 56	99.61 149	99.65 64	99.30 265	99.48 166	98.86 68	99.21 213	99.63 208	98.72 64	99.90 130	98.25 204	99.63 144	99.80 76

PMMVS		98.80 157	98.62 161	99.34 151	99.27 259	98.70 200	98.76 378	99.31 285	97.34 252	99.21 213	99.07 346	97.20 131	99.82 189	98.56 174	98.87 205	99.52 179

v1192		97.81 265	97.44 283	98.91 218	98.88 339	98.68 201	99.51 168	99.34 264	96.18 345	99.20 216	99.34 307	94.03 264	99.36 305	95.32 359	95.18 353	98.69 301

EI-MVSNet		98.67 168	98.67 151	98.68 255	99.35 236	97.97 252	99.50 175	99.38 243	96.93 293	99.20 216	99.83 76	97.87 110	99.36 305	98.38 191	97.56 281	98.71 292

MVSTER		98.49 175	98.32 184	99.00 201	99.35 236	99.02 158	99.54 149	99.38 243	97.41 247	99.20 216	99.73 157	93.86 272	99.36 305	98.87 120	97.56 281	98.62 334

UWE-MVS		97.58 299	97.29 306	98.48 275	99.09 307	96.25 342	99.01 345	96.61 419	97.86 187	99.19 219	99.01 354	88.72 365	99.90 130	97.38 285	98.69 216	99.28 231

Anonymous202405211		98.30 194	97.98 215	99.26 172	99.57 160	98.16 241	99.41 224	98.55 390	96.03 357	99.19 219	99.74 151	91.87 320	99.92 106	99.16 85	98.29 242	99.70 121

v2v482		98.06 217	97.77 239	98.92 214	98.90 337	98.82 191	99.57 124	99.36 252	96.65 308	99.19 219	99.35 303	94.20 256	99.25 324	97.72 254	94.97 358	98.69 301

CNLPA		99.14 97	98.99 106	99.59 98	99.58 158	99.41 107	99.16 308	99.44 215	98.45 109	99.19 219	99.49 260	98.08 105	99.89 142	97.73 252	99.75 123	99.48 193

UGNet		98.87 140	98.69 149	99.40 143	99.22 274	98.72 199	99.44 209	99.68 20	99.24 21	99.18 223	99.42 280	92.74 295	99.96 34	99.34 64	99.94 25	99.53 178
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
tfpn200view9		97.72 281	97.38 291	98.72 250	99.69 112	97.96 254	99.50 175	98.73 381	97.83 193	99.17 224	98.45 387	91.67 327	99.83 181	93.22 386	98.18 251	98.37 369

thres400		97.77 270	97.38 291	98.92 214	99.69 112	97.96 254	99.50 175	98.73 381	97.83 193	99.17 224	98.45 387	91.67 327	99.83 181	93.22 386	98.18 251	98.96 267

Test_1112_low_res		98.89 138	98.66 154	99.57 103	99.69 112	98.95 172	99.03 337	99.47 187	96.98 286	99.15 226	99.23 330	96.77 147	99.89 142	98.83 133	98.78 213	99.86 35

baseline1		98.31 192	97.95 219	99.38 148	99.50 192	98.74 197	99.59 109	98.93 344	98.41 114	99.14 227	99.60 220	94.59 240	99.79 204	98.48 181	93.29 384	99.61 153

1112_ss		98.98 131	98.77 141	99.59 98	99.68 116	99.02 158	99.25 291	99.48 166	97.23 263	99.13 228	99.58 226	96.93 143	99.90 130	98.87 120	98.78 213	99.84 45

CLD-MVS		98.16 206	98.10 200	98.33 296	99.29 254	96.82 319	98.75 379	99.44 215	97.83 193	99.13 228	99.55 237	92.92 289	99.67 250	98.32 200	97.69 272	98.48 355
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
原ACMM1				99.65 81	99.73 94	99.33 114		99.47 187	97.46 237	99.12 230	99.66 194	98.67 69	99.91 118	97.70 257	99.69 134	99.71 119

tpm		97.67 292	97.55 263	98.03 320	99.02 319	95.01 373	99.43 214	98.54 391	96.44 328	99.12 230	99.34 307	91.83 322	99.60 270	97.75 250	96.46 318	99.48 193

HQP_MVS		98.27 197	98.22 190	98.44 286	99.29 254	96.97 310	99.39 236	99.47 187	98.97 59	99.11 232	99.61 217	92.71 298	99.69 247	97.78 244	97.63 274	98.67 313

plane_prior3						97.00 307			98.69 88	99.11 232

CHOSEN 1792x2688		99.19 86	99.10 85	99.45 136	99.89 8	98.52 220	99.39 236	99.94 1	98.73 85	99.11 232	99.89 35	95.50 195	99.94 76	99.50 45	99.97 7	99.89 22

v8		97.95 239	97.63 258	98.93 212	98.95 332	98.81 193	99.80 25	99.41 226	96.03 357	99.10 235	99.42 280	94.92 217	99.30 316	96.94 312	94.08 375	98.66 321

ADS-MVSNet2		98.02 227	98.07 207	97.87 336	99.33 241	95.19 370	99.23 296	99.08 325	96.24 340	99.10 235	99.67 189	94.11 260	98.93 377	96.81 318	99.05 192	99.48 193

ADS-MVSNet		98.20 201	98.08 204	98.56 267	99.33 241	96.48 333	99.23 296	99.15 317	96.24 340	99.10 235	99.67 189	94.11 260	99.71 236	96.81 318	99.05 192	99.48 193

SSC-MVS3.2		97.34 317	97.15 314	97.93 331	99.02 319	95.76 353	99.48 190	99.58 65	97.62 219	99.09 238	99.53 246	87.95 378	99.27 321	96.42 333	95.66 342	98.75 284

thres200		97.61 297	97.28 307	98.62 258	99.64 136	98.03 248	99.26 289	98.74 375	97.68 212	99.09 238	98.32 393	91.66 329	99.81 194	92.88 391	98.22 246	98.03 388

dp		97.75 275	97.80 233	97.59 354	99.10 304	93.71 393	99.32 260	98.88 357	96.48 325	99.08 240	99.55 237	92.67 301	99.82 189	96.52 330	98.58 222	99.24 237

WB-MVSnew		97.65 294	97.65 254	97.63 351	98.78 354	97.62 274	99.13 314	98.33 394	97.36 251	99.07 241	98.94 363	95.64 192	99.15 341	92.95 390	98.68 217	96.12 417

GBi-Net		97.68 289	97.48 272	98.29 301	99.51 181	97.26 288	99.43 214	99.48 166	96.49 322	99.07 241	99.32 315	90.26 347	98.98 366	97.10 301	96.65 313	98.62 334

test1		97.68 289	97.48 272	98.29 301	99.51 181	97.26 288	99.43 214	99.48 166	96.49 322	99.07 241	99.32 315	90.26 347	98.98 366	97.10 301	96.65 313	98.62 334

FMVSNet3		98.03 225	97.76 243	98.84 236	99.39 227	98.98 162	99.40 232	99.38 243	96.67 306	99.07 241	99.28 322	92.93 288	98.98 366	97.10 301	96.65 313	98.56 350

IterMVS-LS		98.46 178	98.42 177	98.58 263	99.59 156	98.00 250	99.37 243	99.43 221	96.94 292	99.07 241	99.59 222	97.87 110	99.03 359	98.32 200	95.62 343	98.71 292
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		98.08 215	98.16 192	97.85 337	99.55 168	94.67 380	99.70 56	98.92 347	98.15 147	99.06 246	99.35 303	93.67 278	99.25 324	97.77 247	97.25 303	99.64 144

pmmvs4		98.13 209	97.90 224	98.81 241	98.61 377	98.87 182	98.99 348	99.21 310	96.44 328	99.06 246	99.58 226	95.90 182	99.11 350	97.18 299	96.11 327	98.46 360

XVG-ACMP-BASELINE		97.83 260	97.71 248	98.20 309	99.11 301	96.33 338	99.41 224	99.52 110	98.06 167	99.05 248	99.50 257	89.64 357	99.73 226	97.73 252	97.38 300	98.53 351

CostFormer		97.72 281	97.73 246	97.71 348	99.15 297	94.02 389	99.54 149	99.02 335	94.67 380	99.04 249	99.35 303	92.35 313	99.77 211	98.50 180	97.94 261	99.34 226

DP-MVS		99.16 92	98.95 116	99.78 59	99.77 65	99.53 90	99.41 224	99.50 144	97.03 284	99.04 249	99.88 43	97.39 121	99.92 106	98.66 154	99.90 46	99.87 33

ACMM	97.58 5	98.37 189	98.34 182	98.48 275	99.41 219	97.10 295	99.56 130	99.45 207	98.53 101	99.04 249	99.85 61	93.00 287	99.71 236	98.74 142	97.45 293	98.64 325
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+		98.70 165	98.43 176	99.51 124	99.51 181	99.28 124	99.52 159	99.47 187	96.11 352	99.01 252	99.34 307	96.20 169	99.84 168	97.88 233	98.82 210	99.39 217

nrg030		98.64 171	98.42 177	99.28 170	99.05 316	99.69 54	99.81 20	99.46 196	98.04 170	99.01 252	99.82 85	96.69 150	99.38 298	99.34 64	94.59 365	98.78 276

test_prior2							98.96 355		98.34 122	99.01 252	99.52 250	98.68 67		97.96 228	99.74 126

MAR-MVS		98.86 143	98.63 156	99.54 108	99.37 232	99.66 60	99.45 203	99.54 92	96.61 313	99.01 252	99.40 288	97.09 134	99.86 155	97.68 259	99.53 153	99.10 245
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
UWE-MVS-28		97.36 315	97.24 311	97.75 345	98.84 348	94.44 383	99.24 293	97.58 409	97.98 176	99.00 256	99.00 355	91.35 335	99.53 277	93.75 380	98.39 233	99.27 235

PS-MVSNAJss		98.92 136	98.92 119	98.90 220	98.78 354	98.53 216	99.78 32	99.54 92	98.07 163	99.00 256	99.76 143	99.01 18	99.37 301	99.13 86	97.23 304	98.81 274

PAPR		98.63 172	98.34 182	99.51 124	99.40 224	99.03 157	98.80 374	99.36 252	96.33 333	99.00 256	99.12 344	98.46 84	99.84 168	95.23 361	99.37 169	99.66 133

D2MVS		98.41 183	98.50 173	98.15 315	99.26 262	96.62 328	99.40 232	99.61 50	97.71 207	98.98 259	99.36 300	96.04 173	99.67 250	98.70 147	97.41 298	98.15 381

v10		97.85 253	97.52 267	98.86 232	98.99 325	98.67 202	99.75 42	99.41 226	95.70 361	98.98 259	99.41 284	94.75 230	99.23 327	96.01 342	94.63 364	98.67 313

miper_enhance_ethall		98.16 206	98.08 204	98.41 289	98.96 331	97.72 268	98.45 400	99.32 281	96.95 290	98.97 261	99.17 336	97.06 137	99.22 331	97.86 236	95.99 331	98.29 372

UniMVSNet (Re)		98.29 195	98.00 213	99.13 188	99.00 322	99.36 112	99.49 186	99.51 124	97.95 178	98.97 261	99.13 341	96.30 166	99.38 298	98.36 195	93.34 383	98.66 321

WBMVS		97.74 277	97.50 270	98.46 281	99.24 268	97.43 280	99.21 302	99.42 223	97.45 240	98.96 263	99.41 284	88.83 364	99.23 327	98.94 108	96.02 328	98.71 292

TEST9					99.67 118	99.65 64	99.05 332	99.41 226	96.22 342	98.95 264	99.49 260	98.77 54	99.91 118

train_agg		99.02 125	98.77 141	99.77 62	99.67 118	99.65 64	99.05 332	99.41 226	96.28 336	98.95 264	99.49 260	98.76 55	99.91 118	97.63 260	99.72 129	99.75 94

BH-RMVSNet		98.41 183	98.08 204	99.40 143	99.41 219	98.83 190	99.30 265	98.77 371	97.70 210	98.94 266	99.65 196	92.91 291	99.74 220	96.52 330	99.55 152	99.64 144

test_8					99.67 118	99.61 74	99.03 337	99.41 226	96.28 336	98.93 267	99.48 266	98.76 55	99.91 118

3Dnovator	97.25 9	99.24 83	99.05 92	99.81 50	99.12 299	99.66 60	99.84 12	99.74 10	99.09 40	98.92 268	99.90 30	95.94 179	99.98 14	98.95 107	99.92 30	99.79 80

v7n		97.87 250	97.52 267	98.92 214	98.76 361	98.58 212	99.84 12	99.46 196	96.20 343	98.91 269	99.70 166	94.89 219	99.44 289	96.03 340	93.89 378	98.75 284

JIA-IIPM		97.50 305	97.02 321	98.93 212	98.73 363	97.80 264	99.30 265	98.97 340	91.73 404	98.91 269	94.86 419	95.10 210	99.71 236	97.58 264	97.98 259	99.28 231

v148		97.79 269	97.55 263	98.50 272	98.74 362	97.72 268	99.54 149	99.33 271	96.26 339	98.90 271	99.51 254	94.68 235	99.14 342	97.83 240	93.15 387	98.63 332

GA-MVS		97.85 253	97.47 275	99.00 201	99.38 229	97.99 251	98.57 394	99.15 317	97.04 283	98.90 271	99.30 318	89.83 354	99.38 298	96.70 323	98.33 237	99.62 151

tpm2		97.44 312	97.34 298	97.74 347	99.15 297	94.36 386	99.45 203	98.94 343	93.45 394	98.90 271	99.44 276	91.35 335	99.59 271	97.31 288	98.07 257	99.29 230

tt0805		97.97 237	97.77 239	98.57 264	99.59 156	96.61 329	99.45 203	99.08 325	98.21 140	98.88 274	99.80 112	88.66 368	99.70 242	98.58 168	97.72 271	99.39 217

miper_ehance_all_eth		98.18 204	98.10 200	98.41 289	99.23 270	97.72 268	98.72 382	99.31 285	96.60 316	98.88 274	99.29 320	97.29 128	99.13 345	97.60 262	95.99 331	98.38 368

eth_miper_zixun_eth		98.05 222	97.96 217	98.33 296	99.26 262	97.38 282	98.56 396	99.31 285	96.65 308	98.88 274	99.52 250	96.58 154	99.12 349	97.39 284	95.53 347	98.47 357

cl22		97.85 253	97.64 257	98.48 275	99.09 307	97.87 260	98.60 393	99.33 271	97.11 275	98.87 277	99.22 331	92.38 312	99.17 340	98.21 206	95.99 331	98.42 363

agg_prior					99.67 118	99.62 72		99.40 232		98.87 277			99.91 118

anonymousdsp		98.44 179	98.28 187	98.94 210	98.50 384	98.96 169	99.77 34	99.50 144	97.07 278	98.87 277	99.77 139	94.76 229	99.28 318	98.66 154	97.60 277	98.57 349

DSMNet-mixed		97.25 322	97.35 295	96.95 371	97.84 395	93.61 396	99.57 124	96.63 418	96.13 351	98.87 277	98.61 382	94.59 240	97.70 408	95.08 363	98.86 206	99.55 170

FMVSNet2		97.72 281	97.36 293	98.80 243	99.51 181	98.84 187	99.45 203	99.42 223	96.49 322	98.86 281	99.29 320	90.26 347	98.98 366	96.44 332	96.56 316	98.58 348

reproduce_monomvs		97.89 247	97.87 229	97.96 329	99.51 181	95.45 362	99.60 102	99.25 301	99.17 23	98.85 282	99.49 260	89.29 360	99.64 261	99.35 59	96.31 323	98.78 276

c3_l		98.12 211	98.04 209	98.38 293	99.30 250	97.69 272	98.81 373	99.33 271	96.67 306	98.83 283	99.34 307	97.11 133	98.99 365	97.58 264	95.34 350	98.48 355

ITE_SJBPF				98.08 318	99.29 254	96.37 336		98.92 347	98.34 122	98.83 283	99.75 146	91.09 339	99.62 268	95.82 344	97.40 299	98.25 375

myMVS_eth3d28		97.69 286	97.34 298	98.73 248	99.27 259	97.52 277	99.33 258	98.78 370	98.03 172	98.82 285	98.49 385	86.64 387	99.46 282	98.44 187	98.24 245	99.23 238

Anonymous20231211		97.88 248	97.54 266	98.90 220	99.71 103	98.53 216	99.48 190	99.57 70	94.16 385	98.81 286	99.68 183	93.23 282	99.42 294	98.84 130	94.42 368	98.76 282

Patchmtry		97.75 275	97.40 290	98.81 241	99.10 304	98.87 182	99.11 323	99.33 271	94.83 377	98.81 286	99.38 294	94.33 252	99.02 361	96.10 338	95.57 345	98.53 351

miper_lstm_enhance		98.00 232	97.91 223	98.28 305	99.34 240	97.43 280	98.88 366	99.36 252	96.48 325	98.80 288	99.55 237	95.98 175	98.91 378	97.27 290	95.50 348	98.51 353

BH-untuned		98.42 181	98.36 180	98.59 260	99.49 194	96.70 322	99.27 280	99.13 320	97.24 262	98.80 288	99.38 294	95.75 187	99.74 220	97.07 304	99.16 179	99.33 227

FIs		98.78 158	98.63 156	99.23 177	99.18 283	99.54 87	99.83 15	99.59 61	98.28 128	98.79 290	99.81 99	96.75 148	99.37 301	99.08 93	96.38 320	98.78 276

OurMVSNet-221017-0		97.88 248	97.77 239	98.19 310	98.71 367	96.53 331	99.88 4	99.00 337	97.79 198	98.78 291	99.94 6	91.68 326	99.35 308	97.21 293	96.99 311	98.69 301

MVS-HIRNet		95.75 356	95.16 361	97.51 356	99.30 250	93.69 394	98.88 366	95.78 421	85.09 418	98.78 291	92.65 421	91.29 337	99.37 301	94.85 367	99.85 78	99.46 204

tpmvs		97.98 234	98.02 212	97.84 339	99.04 317	94.73 378	99.31 263	99.20 311	96.10 356	98.76 293	99.42 280	94.94 214	99.81 194	96.97 309	98.45 231	98.97 265

Patchmatch-test		97.93 240	97.65 254	98.77 246	99.18 283	97.07 299	99.03 337	99.14 319	96.16 347	98.74 294	99.57 231	94.56 242	99.72 230	93.36 385	99.11 185	99.52 179

QAPM		98.67 168	98.30 186	99.80 53	99.20 277	99.67 58	99.77 34	99.72 11	94.74 379	98.73 295	99.90 30	95.78 186	99.98 14	96.96 310	99.88 60	99.76 93

3Dnovator+	97.12 13	99.18 88	98.97 110	99.82 47	99.17 291	99.68 55	99.81 20	99.51 124	99.20 22	98.72 296	99.89 35	95.68 190	99.97 22	98.86 125	99.86 71	99.81 67

IterMVS-SCA-FT		97.82 263	97.75 244	98.06 319	99.57 160	96.36 337	99.02 340	99.49 154	97.18 266	98.71 297	99.72 161	92.72 296	99.14 342	97.44 281	95.86 336	98.67 313

UniMVSNet_NR-MVSNet		98.22 198	97.97 216	98.96 206	98.92 335	98.98 162	99.48 190	99.53 105	97.76 202	98.71 297	99.46 273	96.43 163	99.22 331	98.57 171	92.87 390	98.69 301

DU-MVS		98.08 215	97.79 234	98.96 206	98.87 342	98.98 162	99.41 224	99.45 207	97.87 186	98.71 297	99.50 257	94.82 221	99.22 331	98.57 171	92.87 390	98.68 306

tpm cat1		97.39 314	97.36 293	97.50 357	99.17 291	93.73 392	99.43 214	99.31 285	91.27 405	98.71 297	99.08 345	94.31 254	99.77 211	96.41 335	98.50 229	99.00 261

XXY-MVS		98.38 187	98.09 203	99.24 175	99.26 262	99.32 115	99.56 130	99.55 83	97.45 240	98.71 297	99.83 76	93.23 282	99.63 267	98.88 117	96.32 322	98.76 282

IterMVS		97.83 260	97.77 239	98.02 322	99.58 158	96.27 341	99.02 340	99.48 166	97.22 264	98.71 297	99.70 166	92.75 293	99.13 345	97.46 279	96.00 330	98.67 313
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		98.75 161	98.62 161	99.15 187	99.08 310	99.45 102	99.86 11	99.60 56	98.23 137	98.70 303	99.82 85	96.80 145	99.22 331	99.07 94	96.38 320	98.79 275

COLMAP_ROB	97.56 6	98.86 143	98.75 143	99.17 182	99.88 11	98.53 216	99.34 256	99.59 61	97.55 227	98.70 303	99.89 35	95.83 184	99.90 130	98.10 214	99.90 46	99.08 250
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TR-MVS		97.76 271	97.41 289	98.82 238	99.06 313	97.87 260	98.87 368	98.56 389	96.63 312	98.68 305	99.22 331	92.49 306	99.65 258	95.40 357	97.79 269	98.95 269

WR-MVS		98.06 217	97.73 246	99.06 193	98.86 345	99.25 129	99.19 304	99.35 259	97.30 256	98.66 306	99.43 278	93.94 267	99.21 336	98.58 168	94.28 370	98.71 292

HQP-NCC					99.19 280		98.98 351		98.24 134	98.66 306

ACMP_Plane					99.19 280		98.98 351		98.24 134	98.66 306

HQP4-MVS										98.66 306			99.64 261			98.64 325

HQP-MVS		98.02 227	97.90 224	98.37 294	99.19 280	96.83 317	98.98 351	99.39 235	98.24 134	98.66 306	99.40 288	92.47 307	99.64 261	97.19 297	97.58 279	98.64 325

LF4IMVS		97.52 302	97.46 277	97.70 349	98.98 328	95.55 357	99.29 270	98.82 364	98.07 163	98.66 306	99.64 202	89.97 352	99.61 269	97.01 305	96.68 312	97.94 396

mvs_tets		98.40 186	98.23 189	98.91 218	98.67 371	98.51 222	99.66 75	99.53 105	98.19 142	98.65 312	99.81 99	92.75 293	99.44 289	99.31 68	97.48 292	98.77 280

UBG		97.85 253	97.48 272	98.95 208	99.25 266	97.64 273	99.24 293	98.74 375	97.90 183	98.64 313	98.20 397	88.65 369	99.81 194	98.27 203	98.40 232	99.42 211

TESTMET0.1,1		97.55 300	97.27 310	98.40 291	98.93 333	96.53 331	98.67 385	97.61 408	96.96 288	98.64 313	99.28 322	88.63 371	99.45 284	97.30 289	99.38 162	99.21 240

jajsoiax		98.43 180	98.28 187	98.88 225	98.60 378	98.43 230	99.82 16	99.53 105	98.19 142	98.63 315	99.80 112	93.22 284	99.44 289	99.22 78	97.50 288	98.77 280

Baseline_NR-MVSNet		97.76 271	97.45 278	98.68 255	99.09 307	98.29 235	99.41 224	98.85 361	95.65 362	98.63 315	99.67 189	94.82 221	99.10 352	98.07 222	92.89 389	98.64 325

EPNet		98.86 143	98.71 147	99.30 163	97.20 407	98.18 240	99.62 95	98.91 352	99.28 20	98.63 315	99.81 99	95.96 176	99.99 4	99.24 77	99.72 129	99.73 103
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test-LLR		98.06 217	97.90 224	98.55 269	98.79 351	97.10 295	98.67 385	97.75 405	97.34 252	98.61 318	98.85 369	94.45 249	99.45 284	97.25 291	99.38 162	99.10 245

test-mter		97.49 310	97.13 317	98.55 269	98.79 351	97.10 295	98.67 385	97.75 405	96.65 308	98.61 318	98.85 369	88.23 375	99.45 284	97.25 291	99.38 162	99.10 245

DIV-MVS_self_test		98.01 230	97.85 231	98.48 275	99.24 268	97.95 256	98.71 383	99.35 259	96.50 321	98.60 320	99.54 242	95.72 189	99.03 359	97.21 293	95.77 337	98.46 360

cl____		98.01 230	97.84 232	98.55 269	99.25 266	97.97 252	98.71 383	99.34 264	96.47 327	98.59 321	99.54 242	95.65 191	99.21 336	97.21 293	95.77 337	98.46 360

ETVMVS		97.50 305	96.90 325	99.29 166	99.23 270	98.78 196	99.32 260	98.90 354	97.52 233	98.56 322	98.09 403	84.72 401	99.69 247	97.86 236	97.88 264	99.39 217

FMVSNet1		96.84 334	96.36 338	98.29 301	99.32 248	97.26 288	99.43 214	99.48 166	95.11 369	98.55 323	99.32 315	83.95 404	98.98 366	95.81 345	96.26 324	98.62 334

UniMVSNet_ETH3D		97.32 319	96.81 327	98.87 229	99.40 224	97.46 279	99.51 168	99.53 105	95.86 360	98.54 324	99.77 139	82.44 410	99.66 253	98.68 152	97.52 285	99.50 191

AUN-MVS		96.88 333	96.31 339	98.59 260	99.48 201	97.04 304	99.27 280	99.22 307	97.44 243	98.51 325	99.41 284	91.97 318	99.66 253	97.71 255	83.83 416	99.07 255

PCF-MVS	97.08 14	97.66 293	97.06 320	99.47 133	99.61 149	99.09 148	98.04 415	99.25 301	91.24 406	98.51 325	99.70 166	94.55 244	99.91 118	92.76 394	99.85 78	99.42 211
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TranMVSNet+NR-MVSNet		97.93 240	97.66 253	98.76 247	98.78 354	98.62 208	99.65 81	99.49 154	97.76 202	98.49 327	99.60 220	94.23 255	98.97 373	98.00 226	92.90 388	98.70 297

CP-MVSNet		98.09 213	97.78 237	99.01 199	98.97 330	99.24 130	99.67 69	99.46 196	97.25 260	98.48 328	99.64 202	93.79 274	99.06 355	98.63 158	94.10 374	98.74 288

ACMP	97.20 11	98.06 217	97.94 221	98.45 283	99.37 232	97.01 306	99.44 209	99.49 154	97.54 230	98.45 329	99.79 124	91.95 319	99.72 230	97.91 231	97.49 291	98.62 334
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cascas		97.69 286	97.43 287	98.48 275	98.60 378	97.30 284	98.18 412	99.39 235	92.96 397	98.41 330	98.78 376	93.77 275	99.27 321	98.16 212	98.61 219	98.86 271

WR-MVS_H		98.13 209	97.87 229	98.90 220	99.02 319	98.84 187	99.70 56	99.59 61	97.27 258	98.40 331	99.19 335	95.53 194	99.23 327	98.34 197	93.78 380	98.61 343

BH-w/o		98.00 232	97.89 228	98.32 298	99.35 236	96.20 344	99.01 345	98.90 354	96.42 330	98.38 332	99.00 355	95.26 205	99.72 230	96.06 339	98.61 219	99.03 258

pmmvs5		97.52 302	97.30 304	98.16 312	98.57 381	96.73 321	99.27 280	98.90 354	96.14 350	98.37 333	99.53 246	91.54 332	99.14 342	97.51 273	95.87 335	98.63 332

EU-MVSNet		97.98 234	98.03 210	97.81 343	98.72 365	96.65 327	99.66 75	99.66 28	98.09 158	98.35 334	99.82 85	95.25 206	98.01 401	97.41 283	95.30 351	98.78 276

FMVSNet5		96.43 343	96.19 342	97.15 363	99.11 301	95.89 350	99.32 260	99.52 110	94.47 384	98.34 335	99.07 346	87.54 383	97.07 413	92.61 395	95.72 340	98.47 357

testing91		97.44 312	97.02 321	98.71 252	99.18 283	96.89 316	99.19 304	99.04 332	97.78 200	98.31 336	98.29 394	85.41 396	99.85 161	98.01 225	97.95 260	99.39 217

PS-CasMVS		97.93 240	97.59 262	98.95 208	98.99 325	99.06 154	99.68 66	99.52 110	97.13 270	98.31 336	99.68 183	92.44 311	99.05 356	98.51 179	94.08 375	98.75 284

USDC		97.34 317	97.20 312	97.75 345	99.07 311	95.20 369	98.51 398	99.04 332	97.99 175	98.31 336	99.86 56	89.02 361	99.55 275	95.67 351	97.36 301	98.49 354

PEN-MVS		97.76 271	97.44 283	98.72 250	98.77 359	98.54 215	99.78 32	99.51 124	97.06 280	98.29 339	99.64 202	92.63 302	98.89 381	98.09 215	93.16 386	98.72 290

tfpnnormal		97.84 257	97.47 275	98.98 203	99.20 277	99.22 132	99.64 84	99.61 50	96.32 334	98.27 340	99.70 166	93.35 281	99.44 289	95.69 349	95.40 349	98.27 373

testing99		97.36 315	96.94 324	98.63 257	99.18 283	96.70 322	99.30 265	98.93 344	97.71 207	98.23 341	98.26 395	84.92 399	99.84 168	98.04 224	97.85 267	99.35 223

testing222		97.16 325	96.50 334	99.16 183	99.16 293	98.47 228	99.27 280	98.66 386	97.71 207	98.23 341	98.15 398	82.28 412	99.84 168	97.36 286	97.66 273	99.18 241

ppachtmachnet_test		97.49 310	97.45 278	97.61 353	98.62 375	95.24 368	98.80 374	99.46 196	96.11 352	98.22 343	99.62 213	96.45 161	98.97 373	93.77 379	95.97 334	98.61 343

testing11		97.50 305	97.10 318	98.71 252	99.20 277	96.91 314	99.29 270	98.82 364	97.89 184	98.21 344	98.40 389	85.63 394	99.83 181	98.45 186	98.04 258	99.37 221

our_test_3		97.65 294	97.68 251	97.55 355	98.62 375	94.97 374	98.84 370	99.30 289	96.83 299	98.19 345	99.34 307	97.01 140	99.02 361	95.00 365	96.01 329	98.64 325

LTVRE_ROB	97.16 12	98.02 227	97.90 224	98.40 291	99.23 270	96.80 320	99.70 56	99.60 56	97.12 272	98.18 346	99.70 166	91.73 325	99.72 230	98.39 190	97.45 293	98.68 306
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
ACMH	97.28 8	98.10 212	97.99 214	98.44 286	99.41 219	96.96 312	99.60 102	99.56 75	98.09 158	98.15 347	99.91 23	90.87 342	99.70 242	98.88 117	97.45 293	98.67 313
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		97.24 324	97.32 302	96.99 368	98.45 386	93.51 397	98.82 372	99.32 281	97.41 247	98.13 348	99.30 318	88.99 362	99.56 273	95.68 350	99.80 106	97.90 399

MVS		97.28 320	96.55 333	99.48 130	98.78 354	98.95 172	99.27 280	99.39 235	83.53 419	98.08 349	99.54 242	96.97 141	99.87 152	94.23 375	99.16 179	99.63 149

PAPM		97.59 298	97.09 319	99.07 191	99.06 313	98.26 237	98.30 408	99.10 322	94.88 375	98.08 349	99.34 307	96.27 167	99.64 261	89.87 405	98.92 202	99.31 229

OpenMVS	96.50 16	98.47 177	98.12 198	99.52 122	99.04 317	99.53 90	99.82 16	99.72 11	94.56 382	98.08 349	99.88 43	94.73 231	99.98 14	97.47 278	99.76 121	99.06 256

gg-mvs-nofinetune		96.17 348	95.32 360	98.73 248	98.79 351	98.14 243	99.38 241	94.09 427	91.07 408	98.07 352	91.04 425	89.62 358	99.35 308	96.75 320	99.09 189	98.68 306

test0.0.03 1		97.71 284	97.42 288	98.56 267	98.41 388	97.82 263	98.78 376	98.63 387	97.34 252	98.05 353	98.98 359	94.45 249	98.98 366	95.04 364	97.15 308	98.89 270

APD_test1		95.87 353	96.49 335	94.00 388	99.53 172	84.01 417	99.54 149	99.32 281	95.91 359	97.99 354	99.85 61	85.49 395	99.88 147	91.96 397	98.84 208	98.12 382

1314		98.68 167	98.54 171	99.11 189	98.89 338	98.65 204	99.27 280	99.49 154	96.89 294	97.99 354	99.56 234	97.72 116	99.83 181	97.74 251	99.27 173	98.84 273

DTE-MVSNet		97.51 304	97.19 313	98.46 281	98.63 374	98.13 244	99.84 12	99.48 166	96.68 305	97.97 356	99.67 189	92.92 289	98.56 390	96.88 317	92.60 394	98.70 297

SixPastTwentyTwo		97.50 305	97.33 301	98.03 320	98.65 372	96.23 343	99.77 34	98.68 384	97.14 269	97.90 357	99.93 10	90.45 345	99.18 339	97.00 306	96.43 319	98.67 313

testing3		97.28 320	96.76 329	98.82 238	99.37 232	98.07 247	99.45 203	99.36 252	97.56 226	97.89 358	98.95 362	83.70 405	98.82 382	96.03 340	98.56 225	99.58 164

pm-mvs1		97.68 289	97.28 307	98.88 225	99.06 313	98.62 208	99.50 175	99.45 207	96.32 334	97.87 359	99.79 124	92.47 307	99.35 308	97.54 271	93.54 382	98.67 313

testgi		97.65 294	97.50 270	98.13 316	99.36 235	96.45 334	99.42 221	99.48 166	97.76 202	97.87 359	99.45 275	91.09 339	98.81 383	94.53 370	98.52 228	99.13 244

EPNet_dtu		98.03 225	97.96 217	98.23 308	98.27 389	95.54 359	99.23 296	98.75 372	99.02 46	97.82 361	99.71 162	96.11 171	99.48 279	93.04 389	99.65 141	99.69 123
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		97.12 327	96.89 326	97.83 340	99.07 311	95.52 360	98.57 394	98.74 375	97.58 223	97.81 362	99.79 124	88.16 376	99.56 273	95.10 362	97.21 305	98.39 367

ACMH+	97.24 10	97.92 243	97.78 237	98.32 298	99.46 204	96.68 326	99.56 130	99.54 92	98.41 114	97.79 363	99.87 52	90.18 351	99.66 253	98.05 223	97.18 307	98.62 334

N_pmnet		94.95 365	95.83 351	92.31 395	98.47 385	79.33 427	99.12 317	92.81 433	93.87 387	97.68 364	99.13 341	93.87 271	99.01 363	91.38 400	96.19 325	98.59 347

KD-MVS_2432*1600		94.62 366	93.72 374	97.31 360	97.19 408	95.82 351	98.34 404	99.20 311	95.00 373	97.57 365	98.35 391	87.95 378	98.10 398	92.87 392	77.00 423	98.01 389

miper_refine_blended		94.62 366	93.72 374	97.31 360	97.19 408	95.82 351	98.34 404	99.20 311	95.00 373	97.57 365	98.35 391	87.95 378	98.10 398	92.87 392	77.00 423	98.01 389

PVSNet_0	94.43 19	96.09 350	95.47 357	97.94 330	99.31 249	94.34 387	97.81 416	99.70 15	97.12 272	97.46 367	98.75 377	89.71 355	99.79 204	97.69 258	81.69 419	99.68 127

Syy-MVS		97.09 329	97.14 315	96.95 371	99.00 322	92.73 402	99.29 270	99.39 235	97.06 280	97.41 368	98.15 398	93.92 269	98.68 388	91.71 398	98.34 235	99.45 207

myMVS_eth3d		96.89 332	96.37 337	98.43 288	99.00 322	97.16 292	99.29 270	99.39 235	97.06 280	97.41 368	98.15 398	83.46 406	98.68 388	95.27 360	98.34 235	99.45 207

pmmvs6		96.53 340	96.09 345	97.82 342	98.69 369	95.47 361	99.37 243	99.47 187	93.46 393	97.41 368	99.78 131	87.06 386	99.33 311	96.92 315	92.70 392	98.65 323

new_pmnet		96.38 344	96.03 346	97.41 358	98.13 392	95.16 372	99.05 332	99.20 311	93.94 386	97.39 371	98.79 375	91.61 331	99.04 357	90.43 403	95.77 337	98.05 387

CL-MVSNet_self_test		94.49 368	93.97 372	96.08 382	96.16 413	93.67 395	98.33 406	99.38 243	95.13 367	97.33 372	98.15 398	92.69 300	96.57 416	88.67 409	79.87 421	97.99 393

IB-MVS	95.67 18	96.22 345	95.44 359	98.57 264	99.21 275	96.70 322	98.65 389	97.74 407	96.71 303	97.27 373	98.54 384	86.03 391	99.92 106	98.47 184	86.30 413	99.10 245
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
GG-mvs-BLEND				98.45 283	98.55 382	98.16 241	99.43 214	93.68 428		97.23 374	98.46 386	89.30 359	99.22 331	95.43 356	98.22 246	97.98 394

MVP-Stereo		97.81 265	97.75 244	97.99 326	97.53 400	96.60 330	98.96 355	98.85 361	97.22 264	97.23 374	99.36 300	95.28 202	99.46 282	95.51 353	99.78 115	97.92 398
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Anonymous20240521		96.20 347	95.89 350	97.13 365	97.72 399	94.96 375	99.79 31	99.29 293	93.01 396	97.20 376	99.03 351	89.69 356	98.36 394	91.16 401	96.13 326	98.07 385

TransMVSNet (Re)		97.15 326	96.58 332	98.86 232	99.12 299	98.85 186	99.49 186	98.91 352	95.48 364	97.16 377	99.80 112	93.38 280	99.11 350	94.16 377	91.73 396	98.62 334

KD-MVS_self_test		95.00 363	94.34 368	96.96 370	97.07 410	95.39 365	99.56 130	99.44 215	95.11 369	97.13 378	97.32 411	91.86 321	97.27 412	90.35 404	81.23 420	98.23 377

NR-MVSNet		97.97 237	97.61 260	99.02 198	98.87 342	99.26 127	99.47 198	99.42 223	97.63 217	97.08 379	99.50 257	95.07 211	99.13 345	97.86 236	93.59 381	98.68 306

Anonymous20231206		96.22 345	96.03 346	96.79 376	97.31 405	94.14 388	99.63 90	99.08 325	96.17 346	97.04 380	99.06 348	93.94 267	97.76 407	86.96 416	95.06 356	98.47 357

test_0402		96.64 338	96.24 340	97.85 337	98.85 346	96.43 335	99.44 209	99.26 299	93.52 391	96.98 381	99.52 250	88.52 372	99.20 338	92.58 396	97.50 288	97.93 397

MIMVSNet1		95.51 357	95.04 362	96.92 373	97.38 402	95.60 355	99.52 159	99.50 144	93.65 390	96.97 382	99.17 336	85.28 398	96.56 417	88.36 411	95.55 346	98.60 346

mvs5depth		96.66 337	96.22 341	97.97 327	97.00 411	96.28 340	98.66 388	99.03 334	96.61 313	96.93 383	99.79 124	87.20 385	99.47 280	96.65 328	94.13 373	98.16 380

dongtai		93.26 375	92.93 379	94.25 387	99.39 227	85.68 415	97.68 418	93.27 429	92.87 398	96.85 384	99.39 292	82.33 411	97.48 410	76.78 423	97.80 268	99.58 164

TDRefinement		95.42 359	94.57 366	97.97 327	89.83 429	96.11 347	99.48 190	98.75 372	96.74 301	96.68 385	99.88 43	88.65 369	99.71 236	98.37 193	82.74 418	98.09 384

baseline2		97.87 250	97.55 263	98.82 238	99.18 283	98.02 249	99.41 224	96.58 420	96.97 287	96.51 386	99.17 336	93.43 279	99.57 272	97.71 255	99.03 194	98.86 271

pmmvs3		94.09 372	93.25 378	96.60 378	94.76 423	94.49 382	98.92 362	98.18 400	89.66 409	96.48 387	98.06 404	86.28 390	97.33 411	89.68 406	87.20 412	97.97 395

DeepMVS_CX				93.34 391	99.29 254	82.27 420		99.22 307	85.15 417	96.33 388	99.05 349	90.97 341	99.73 226	93.57 383	97.77 270	98.01 389

ttmdpeth		97.80 267	97.63 258	98.29 301	98.77 359	97.38 282	99.64 84	99.36 252	98.78 81	96.30 389	99.58 226	92.34 314	99.39 296	98.36 195	95.58 344	98.10 383

LCM-MVSNet-Re		97.83 260	98.15 194	96.87 374	99.30 250	92.25 404	99.59 109	98.26 395	97.43 244	96.20 390	99.13 341	96.27 167	98.73 387	98.17 211	98.99 197	99.64 144

test20.03		96.12 349	95.96 348	96.63 377	97.44 401	95.45 362	99.51 168	99.38 243	96.55 319	96.16 391	99.25 328	93.76 276	96.17 418	87.35 415	94.22 371	98.27 373

K. test v3		97.10 328	96.79 328	98.01 323	98.72 365	96.33 338	99.87 8	97.05 412	97.59 221	96.16 391	99.80 112	88.71 366	99.04 357	96.69 324	96.55 317	98.65 323

UnsupCasMVSNet_eth		96.44 342	96.12 343	97.40 359	98.65 372	95.65 354	99.36 248	99.51 124	97.13 270	96.04 393	98.99 357	88.40 373	98.17 397	96.71 322	90.27 404	98.40 366

test_method		91.10 381	91.36 383	90.31 401	95.85 414	73.72 434	94.89 422	99.25 301	68.39 425	95.82 394	99.02 353	80.50 415	98.95 376	93.64 382	94.89 362	98.25 375

lessismore_v0				97.79 344	98.69 369	95.44 364		94.75 425		95.71 395	99.87 52	88.69 367	99.32 313	95.89 343	94.93 360	98.62 334

test_vis1_rt		95.81 355	95.65 354	96.32 381	99.67 118	91.35 408	99.49 186	96.74 417	98.25 133	95.24 396	98.10 402	74.96 417	99.90 130	99.53 41	98.85 207	97.70 402

dmvs_testset		95.02 362	96.12 343	91.72 397	99.10 304	80.43 425	99.58 117	97.87 404	97.47 236	95.22 397	98.82 371	93.99 265	95.18 422	88.09 412	94.91 361	99.56 169

Patchmatch-RL test		95.84 354	95.81 352	95.95 383	95.61 416	90.57 409	98.24 409	98.39 393	95.10 371	95.20 398	98.67 379	94.78 225	97.77 406	96.28 337	90.02 405	99.51 187

test_fmvs3		92.10 379	91.77 382	93.08 393	96.19 412	86.25 413	99.82 16	98.62 388	96.65 308	95.19 399	96.90 413	55.05 428	95.93 420	96.63 329	90.92 402	97.06 409

ambc				93.06 394	92.68 425	82.36 419	98.47 399	98.73 381		95.09 400	97.41 408	55.55 426	99.10 352	96.42 333	91.32 397	97.71 400

PM-MVS		92.96 377	92.23 381	95.14 385	95.61 416	89.98 411	99.37 243	98.21 398	94.80 378	95.04 401	97.69 406	65.06 421	97.90 404	94.30 372	89.98 406	97.54 406

OpenMVS_ROB	92.34 20	94.38 370	93.70 376	96.41 380	97.38 402	93.17 399	99.06 330	98.75 372	86.58 416	94.84 402	98.26 395	81.53 413	99.32 313	89.01 408	97.87 265	96.76 410

mvsany_test3		93.77 373	93.45 377	94.74 386	95.78 415	88.01 412	99.64 84	98.25 396	98.28 128	94.31 403	97.97 405	68.89 420	98.51 392	97.50 274	90.37 403	97.71 400

EG-PatchMatch MVS		95.97 352	95.69 353	96.81 375	97.78 396	92.79 401	99.16 308	98.93 344	96.16 347	94.08 404	99.22 331	82.72 408	99.47 280	95.67 351	97.50 288	98.17 379

test_f		91.90 380	91.26 384	93.84 389	95.52 419	85.92 414	99.69 60	98.53 392	95.31 366	93.87 405	96.37 416	55.33 427	98.27 395	95.70 348	90.98 401	97.32 408

pmmvs-eth3d		95.34 361	94.73 364	97.15 363	95.53 418	95.94 349	99.35 253	99.10 322	95.13 367	93.55 406	97.54 407	88.15 377	97.91 403	94.58 369	89.69 407	97.61 403

new-patchmatchnet		94.48 369	94.08 370	95.67 384	95.08 421	92.41 403	99.18 306	99.28 295	94.55 383	93.49 407	97.37 410	87.86 381	97.01 414	91.57 399	88.36 409	97.61 403

UnsupCasMVSNet_bld		93.53 374	92.51 380	96.58 379	97.38 402	93.82 390	98.24 409	99.48 166	91.10 407	93.10 408	96.66 414	74.89 418	98.37 393	94.03 378	87.71 411	97.56 405

WB-MVS		93.10 376	94.10 369	90.12 402	95.51 420	81.88 422	99.73 50	99.27 298	95.05 372	93.09 409	98.91 368	94.70 234	91.89 426	76.62 424	94.02 377	96.58 412

SSC-MVS		92.73 378	93.73 373	89.72 403	95.02 422	81.38 423	99.76 37	99.23 305	94.87 376	92.80 410	98.93 364	94.71 233	91.37 427	74.49 426	93.80 379	96.42 413

Gipuma		90.99 382	90.15 387	93.51 390	98.73 363	90.12 410	93.98 423	99.45 207	79.32 421	92.28 411	94.91 418	69.61 419	97.98 402	87.42 414	95.67 341	92.45 421
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 383	90.11 388	93.34 391	98.78 354	85.59 416	98.15 413	93.16 431	89.37 412	92.07 412	98.38 390	81.48 414	95.19 421	62.54 430	97.04 309	99.25 236

CMPMVS	69.68 23	94.13 371	94.90 363	91.84 396	97.24 406	80.01 426	98.52 397	99.48 166	89.01 413	91.99 413	99.67 189	85.67 393	99.13 345	95.44 355	97.03 310	96.39 414
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVStest1		96.08 351	95.48 356	97.89 335	98.93 333	96.70 322	99.56 130	99.35 259	92.69 400	91.81 414	99.46 273	89.90 353	98.96 375	95.00 365	92.61 393	98.00 392

testf1		90.42 384	90.68 385	89.65 404	97.78 396	73.97 432	99.13 314	98.81 366	89.62 410	91.80 415	98.93 364	62.23 424	98.80 384	86.61 418	91.17 398	96.19 415

APD_test2		90.42 384	90.68 385	89.65 404	97.78 396	73.97 432	99.13 314	98.81 366	89.62 410	91.80 415	98.93 364	62.23 424	98.80 384	86.61 418	91.17 398	96.19 415

PMMVS2		86.87 387	85.37 391	91.35 399	90.21 428	83.80 418	98.89 365	97.45 411	83.13 420	91.67 417	95.03 417	48.49 430	94.70 423	85.86 420	77.62 422	95.54 418

LCM-MVSNet		86.80 388	85.22 392	91.53 398	87.81 430	80.96 424	98.23 411	98.99 338	71.05 423	90.13 418	96.51 415	48.45 431	96.88 415	90.51 402	85.30 414	96.76 410

ET-MVSNet_ETH3D		96.49 341	95.64 355	99.05 195	99.53 172	98.82 191	98.84 370	97.51 410	97.63 217	84.77 419	99.21 334	92.09 316	98.91 378	98.98 103	92.21 395	99.41 214

E-PMN		80.61 392	79.88 394	82.81 409	90.75 427	76.38 430	97.69 417	95.76 422	66.44 427	83.52 420	92.25 422	62.54 423	87.16 429	68.53 428	61.40 426	84.89 427

FPMVS		84.93 389	85.65 390	82.75 410	86.77 431	63.39 436	98.35 403	98.92 347	74.11 422	83.39 421	98.98 359	50.85 429	92.40 425	84.54 421	94.97 358	92.46 420

EMVS		80.02 393	79.22 395	82.43 411	91.19 426	76.40 429	97.55 420	92.49 434	66.36 428	83.01 422	91.27 424	64.63 422	85.79 430	65.82 429	60.65 427	85.08 426

test_vis3_rt		87.04 386	85.81 389	90.73 400	93.99 424	81.96 421	99.76 37	90.23 435	92.81 399	81.35 423	91.56 423	40.06 432	99.07 354	94.27 374	88.23 410	91.15 423

YYNet1		95.36 360	94.51 367	97.92 332	97.89 394	97.10 295	99.10 325	99.23 305	93.26 395	80.77 424	99.04 350	92.81 292	98.02 400	94.30 372	94.18 372	98.64 325

MDA-MVSNet_test_wron		95.45 358	94.60 365	98.01 323	98.16 391	97.21 291	99.11 323	99.24 304	93.49 392	80.73 425	98.98 359	93.02 286	98.18 396	94.22 376	94.45 367	98.64 325

MDA-MVSNet-bldmvs		94.96 364	93.98 371	97.92 332	98.24 390	97.27 286	99.15 311	99.33 271	93.80 388	80.09 426	99.03 351	88.31 374	97.86 405	93.49 384	94.36 369	98.62 334

tmp_tt		82.80 390	81.52 393	86.66 406	66.61 436	68.44 435	92.79 425	97.92 402	68.96 424	80.04 427	99.85 61	85.77 392	96.15 419	97.86 236	43.89 429	95.39 419

MVE	76.82 21	76.91 395	74.31 399	84.70 407	85.38 433	76.05 431	96.88 421	93.17 430	67.39 426	71.28 428	89.01 427	21.66 438	87.69 428	71.74 427	72.29 425	90.35 424
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		77.30 394	74.86 398	84.62 408	75.88 434	77.61 428	97.63 419	93.15 432	88.81 414	64.27 429	89.29 426	36.51 433	83.93 431	75.89 425	52.31 428	92.33 422

PMVS	70.75 22	75.98 396	74.97 397	79.01 412	70.98 435	55.18 437	93.37 424	98.21 398	65.08 429	61.78 430	93.83 420	21.74 437	92.53 424	78.59 422	91.12 400	89.34 425
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		39.01 399	42.50 401	28.53 414	39.17 437	20.91 439	98.75 379	19.17 439	19.83 432	38.57 431	66.67 429	33.16 434	15.42 433	37.50 433	29.66 431	49.26 428

testmvs		39.17 398	43.78 400	25.37 415	36.04 438	16.84 440	98.36 402	26.56 437	20.06 431	38.51 432	67.32 428	29.64 435	15.30 434	37.59 432	39.90 430	43.98 429

wuyk23d		40.18 397	41.29 402	36.84 413	86.18 432	49.12 438	79.73 426	22.81 438	27.64 430	25.46 433	28.45 433	21.98 436	48.89 432	55.80 431	23.56 432	12.51 430

EGC-MVSNET		82.80 390	77.86 396	97.62 352	97.91 393	96.12 346	99.33 258	99.28 295	8.40 433	25.05 434	99.27 325	84.11 403	99.33 311	89.20 407	98.22 246	97.42 407

mmdepth		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

monomultidepth		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

test_blank		0.13 403	0.17 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	1.57 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet_test		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

DCPMVS		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

cdsmvs_eth3d_5k		24.64 400	32.85 403	0.00 416	0.00 439	0.00 441	0.00 427	99.51 124	0.00 434	0.00 435	99.56 234	96.58 154	0.00 435	0.00 434	0.00 433	0.00 431

pcd_1.5k_mvsjas		8.27 402	11.03 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	99.01 18	0.00 435	0.00 434	0.00 433	0.00 431

sosnet-low-res		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uncertanet		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

Regformer		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

ab-mvs-re		8.30 401	11.06 404	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	99.58 226	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet		0.02 404	0.03 407	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.27 435	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

WAC-MVS						97.16 292								95.47 354

MSC_two_6792asdad				99.87 16	99.51 181	99.76 42		99.33 271					99.96 34	98.87 120	99.84 86	99.89 22

No_MVS				99.87 16	99.51 181	99.76 42		99.33 271					99.96 34	98.87 120	99.84 86	99.89 22

eth-test2					0.00 439

eth-test					0.00 439

OPU-MVS				99.64 87	99.56 164	99.72 48	99.60 102				99.70 166	99.27 5	99.42 294	98.24 205	99.80 106	99.79 80

save fliter					99.76 69	99.59 77	99.14 313	99.40 232	99.00 51

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 124	99.51 124					99.96 34	98.93 111	99.86 71	99.88 28

GSMVS																99.52 179

sam_mvs1												94.86 220				99.52 179

sam_mvs												94.72 232

MTGPA								99.47 187

test_post1							99.23 296				65.14 431	94.18 259	99.71 236	97.58 264

test_post											65.99 430	94.65 238	99.73 226

patchmatchnet-post											98.70 378	94.79 224	99.74 220

MTMP							99.54 149	98.88 357

gm-plane-assit					98.54 383	92.96 400			94.65 381		99.15 339		99.64 261	97.56 269

test9_res														97.49 275	99.72 129	99.75 94

agg_prior2														97.21 293	99.73 128	99.75 94

test_prior4						99.56 83	98.99 348

test_prior				99.68 75	99.67 118	99.48 98		99.56 75					99.83 181			99.74 98

新几何2							99.01 345

旧先验1					99.74 87	99.59 77		99.54 92			99.69 176	98.47 83			99.68 137	99.73 103

无先验							98.99 348	99.51 124	96.89 294				99.93 94	97.53 272		99.72 110

原ACMM2							98.95 358

testdata2													99.95 65	96.67 325

segment_acmp												98.96 25

testdata1							98.85 369		98.32 125

plane_prior7					99.29 254	97.03 305

plane_prior6					99.27 259	96.98 309						92.71 298

plane_prior5								99.47 187					99.69 247	97.78 244	97.63 274	98.67 313

plane_prior4											99.61 217

plane_prior2							99.39 236		98.97 59

plane_prior1					99.26 262

plane_prior						96.97 310	99.21 302		98.45 109						97.60 277

n2								0.00 440

nn								0.00 440

door-mid								98.05 401

test11								99.35 259

door								97.92 402

HQP5-MVS						96.83 317

BP-MVS														97.19 297

HQP3-MVS								99.39 235							97.58 279

HQP2-MVS												92.47 307

NP-MVS					99.23 270	96.92 313					99.40 288

ACMMP++_ref															97.19 306

ACMMP++															97.43 297

Test By Simon												98.75 58

High-resolution multi-view benchmark