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.

fmvsm_l_conf0.5_n_9		98.90 16	98.79 14	99.24 47	99.34 73	97.83 81	98.70 197	99.26 16	98.85 7	99.92 1	99.51 29	93.91 108	99.95 10	99.86 1	99.79 36	99.92 3

fmvsm_s_conf0.5_n_9		98.63 30	98.66 22	98.54 111	99.40 68	95.83 206	98.79 173	99.17 37	98.94 3	99.92 1	99.61 6	92.49 126	99.93 35	99.86 1	99.76 49	99.86 14

fmvsm_l_mol_unc0.5_1		99.24 1	99.14 1	99.53 14	99.37 69	98.68 30	98.41 270	98.86 91	99.00 1	99.90 3	99.79 1	97.24 13	99.97 1	99.85 5	99.86 2	99.94 1

fmvsm_l_conf0.5_n_3		98.90 16	98.74 19	99.37 29	99.36 70	98.25 58	98.89 125	99.24 20	98.77 11	99.89 4	99.59 14	93.39 114	99.96 5	99.78 11	99.76 49	99.89 9

fmvsm_s_conf0.5_n_11		98.58 37	98.57 27	98.62 101	99.42 65	97.16 120	98.97 98	98.86 91	98.91 5	99.87 5	99.66 4	91.82 155	99.95 10	99.82 7	99.82 15	98.75 265

fmvsm_s_conf0.5_n_5		98.53 47	98.35 49	99.08 65	99.07 129	97.46 96	98.68 203	99.20 33	97.50 53	99.87 5	99.50 32	91.96 152	99.96 5	99.76 12	99.65 82	99.82 24

fmvsm_s_conf0.5_n_3		98.53 47	98.45 40	98.79 87	99.23 106	97.32 101	98.80 165	99.26 16	98.82 8	99.87 5	99.60 11	90.95 199	99.93 35	99.76 12	99.73 63	99.12 209

test_vis1_n_1920		96.71 195	96.84 168	96.31 346	99.11 125	89.74 435	99.05 76	98.58 178	98.08 25	99.87 5	99.37 57	78.48 432	99.93 35	99.29 28	99.69 73	99.27 176

fmvsm_s_conf0.5_n_6		98.65 27	98.55 30	98.95 79	98.50 189	97.30 104	98.79 173	99.16 39	98.14 24	99.86 9	99.41 49	93.71 111	99.91 58	99.71 16	99.64 87	99.65 84

fmvsm_l_conf0.5_n		99.07 6	99.05 3	99.14 59	99.41 67	97.54 90	98.89 125	99.31 13	98.49 18	99.86 9	99.42 47	96.45 30	99.96 5	99.86 1	99.74 59	99.90 6

test_fmvsm_n_1920		98.87 19	99.01 4	98.45 125	99.42 65	96.43 158	98.96 104	99.36 10	98.63 14	99.86 9	99.51 29	95.91 48	99.97 1	99.72 15	99.75 55	98.94 241

fmvsm_l_conf0.5_n_a		99.09 3	99.08 2	99.11 63	99.43 64	97.48 92	98.88 132	99.30 14	98.47 19	99.85 12	99.43 46	96.71 19	99.96 5	99.86 1	99.80 26	99.89 9

fmvsm_s_conf0.5_n_10		98.66 26	98.54 32	99.02 70	99.36 70	97.21 117	98.86 143	99.23 27	98.90 6	99.83 13	99.59 14	91.57 164	99.94 15	99.79 10	99.74 59	99.89 9

fmvsm_s_conf0.5_n_4		98.35 69	98.50 35	97.90 197	99.16 117	95.08 258	98.75 178	99.24 20	98.39 20	99.81 14	99.52 26	92.35 131	99.90 66	99.74 14	99.51 116	98.71 271

test_fmvsmconf_n		98.92 14	98.87 8	99.04 69	98.88 149	97.25 114	98.82 156	99.34 11	98.75 12	99.80 15	99.61 6	95.16 79	99.95 10	99.70 18	99.80 26	99.93 2

fmvsm_s_conf0.5_n_8		98.73 24	98.62 23	99.05 68	99.35 72	97.27 108	98.80 165	99.23 27	98.93 4	99.79 16	99.59 14	92.34 132	99.95 10	99.82 7	99.71 70	99.92 3

fmvsm_s_conf0.5_n_2		98.30 76	98.21 70	98.57 106	99.25 98	97.11 123	98.66 210	99.20 33	98.82 8	99.79 16	99.60 11	89.38 248	99.92 44	99.80 9	99.38 135	98.69 273

fmvsm_s_conf0.5_n_a		98.38 64	98.42 42	98.27 140	99.09 127	95.41 233	98.86 143	99.37 9	97.69 41	99.78 18	99.61 6	92.38 130	99.91 58	99.58 24	99.43 128	99.49 113

fmvsm_s_conf0.1_n_2		98.14 82	98.02 82	98.53 114	98.88 149	97.07 125	98.69 200	98.82 103	98.78 10	99.77 19	99.61 6	88.83 270	99.91 58	99.71 16	99.07 152	98.61 283

test_cas_vis1_n_1920		97.38 146	97.36 121	97.45 240	98.95 144	93.25 352	99.00 91	98.53 190	97.70 40	99.77 19	99.35 63	84.71 363	99.85 86	98.57 54	99.66 79	99.26 183

fmvsm_s_conf0.1_n_a		98.08 83	98.04 81	98.21 148	97.66 320	95.39 238	98.89 125	99.17 37	97.24 75	99.76 21	99.67 2	91.13 188	99.88 79	99.39 27	99.41 130	99.35 149

TestfortrainingZip a		99.05 7	98.85 10	99.65 2	99.77 2	99.13 12	99.32 22	99.01 52	97.87 32	99.74 22	99.54 21	96.71 19	99.92 44	98.35 74	99.33 141	99.90 6

fmvsm_s_conf0.5_n		98.42 61	98.51 33	98.13 165	99.30 85	95.25 247	98.85 148	99.39 7	97.94 30	99.74 22	99.62 5	92.59 125	99.91 58	99.65 19	99.52 114	99.25 185

fmvsm_s_conf0.5_n_7		98.23 77	98.35 49	97.89 199	98.86 153	94.99 264	98.58 226	99.00 53	98.29 21	99.73 24	99.60 11	91.70 158	99.92 44	99.63 22	99.73 63	98.76 264

SED-MVS		99.09 3	98.91 6	99.63 5	99.71 24	99.24 5	99.02 86	98.87 85	97.65 42	99.73 24	99.48 36	97.53 8	99.94 15	98.43 69	99.81 17	99.70 68

test_241102_ONE					99.71 24	99.24 5		98.87 85	97.62 44	99.73 24	99.39 51	97.53 8	99.74 136

SD-MVS		98.64 29	98.68 20	98.53 114	99.33 76	98.36 51	98.90 121	98.85 96	97.28 70	99.72 27	99.39 51	96.63 23	97.60 454	98.17 86	99.85 7	99.64 87
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
fmvsm_s_conf0.1_n		98.18 81	98.21 70	98.11 170	98.54 187	95.24 248	98.87 135	99.24 20	97.50 53	99.70 28	99.67 2	91.33 176	99.89 70	99.47 26	99.54 111	99.21 191

test_fmvs1_n		95.90 237	95.99 218	95.63 384	98.67 174	88.32 466	99.26 33	98.22 295	96.40 127	99.67 29	99.26 81	73.91 475	99.70 145	99.02 35	99.50 117	98.87 247

test_vis1_n		95.47 259	95.13 260	96.49 328	97.77 309	90.41 423	99.27 32	98.11 320	96.58 116	99.66 30	99.18 106	67.00 490	99.62 166	99.21 29	99.40 133	99.44 127

mvsany_test1		97.69 106	97.70 93	97.66 227	98.24 242	94.18 308	97.53 386	97.53 383	95.52 185	99.66 30	99.51 29	94.30 100	99.56 176	98.38 72	98.62 181	99.23 187

test_fmvs1		96.42 210	96.67 183	95.66 383	98.82 158	88.53 462	98.80 165	98.20 298	96.39 128	99.64 32	99.20 96	80.35 417	99.67 152	99.04 33	99.57 100	98.78 260

IU-MVS					99.71 24	99.23 7		98.64 160	95.28 203	99.63 33				98.35 74	99.81 17	99.83 20

PC_three_1452									95.08 220	99.60 34	99.16 111	97.86 2	98.47 363	97.52 144	99.72 68	99.74 51

lecture		98.95 10	98.78 15	99.45 20	99.75 6	98.63 33	99.43 10	99.38 8	97.60 47	99.58 35	99.47 38	95.36 66	99.93 35	98.87 40	99.57 100	99.78 34

test0726					99.72 17	99.25 2	99.06 74	98.88 78	97.62 44	99.56 36	99.50 32	97.42 10

TSAR-MVS + MP.		98.78 21	98.62 23	99.24 47	99.69 29	98.28 56	99.14 60	98.66 155	96.84 100	99.56 36	99.31 72	96.34 34	99.70 145	98.32 76	99.73 63	99.73 56
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPE-MVS		98.92 14	98.67 21	99.65 2	99.58 38	99.20 9	98.42 269	98.91 72	97.58 48	99.54 38	99.46 43	97.10 14	99.94 15	97.64 127	99.84 12	99.83 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		99.08 5	98.89 7	99.64 4	99.17 113	99.23 7	99.69 1	98.88 78	97.32 66	99.53 39	99.47 38	97.81 3	99.94 15	98.47 65	99.72 68	99.74 51

test_241102_TWO								98.87 85	97.65 42	99.53 39	99.48 36	97.34 12	99.94 15	98.43 69	99.80 26	99.83 20

DVP-MVS		99.03 8	98.83 12	99.63 5	99.72 17	99.25 2	98.97 98	98.58 178	97.62 44	99.45 41	99.46 43	97.42 10	99.94 15	98.47 65	99.81 17	99.69 71
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									97.32 66	99.45 41	99.46 43	97.88 1	99.94 15	98.47 65	99.86 2	99.85 17

test_fmvsmconf0.1_n		98.58 37	98.44 41	98.99 72	97.73 314	97.15 121	98.84 152	98.97 57	98.75 12	99.43 43	99.54 21	93.29 116	99.93 35	99.64 21	99.79 36	99.89 9

TestfortrainingZip				99.43 22	99.13 121	99.06 16	99.32 22	98.57 180	96.88 98	99.42 44	99.05 146	96.54 25	99.73 138		98.59 183	99.51 105

MSP-MVS		98.74 23	98.55 30	99.29 40	99.75 6	98.23 59	99.26 33	98.88 78	97.52 51	99.41 45	98.78 195	96.00 44	99.79 123	97.79 114	99.59 96	99.85 17
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
APDe-MVS		99.02 9	98.84 11	99.55 11	99.57 40	98.96 19	99.39 11	98.93 65	97.38 63	99.41 45	99.54 21	96.66 21	99.84 90	98.86 41	99.85 7	99.87 13
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
FOURS1					99.82 1	98.66 31	99.69 1	98.95 61	97.46 58	99.39 47

SMA-MVS		98.58 37	98.25 64	99.56 9	99.51 47	99.04 18	98.95 105	98.80 116	93.67 312	99.37 48	99.52 26	96.52 27	99.89 70	98.06 92	99.81 17	99.76 48
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
reproduce_model		98.94 11	98.81 13	99.34 33	99.52 46	98.26 57	98.94 108	98.84 97	98.06 26	99.35 49	99.61 6	96.39 33	99.94 15	98.77 44	99.82 15	99.83 20

BridgeMVS		98.45 57	98.35 49	98.74 91	98.65 178	97.55 88	99.19 50	98.60 166	96.72 110	99.35 49	98.77 198	95.06 84	99.55 183	98.95 36	99.87 1	99.12 209

SteuartSystems-ACMMP		98.90 16	98.75 18	99.36 31	99.22 108	98.43 41	99.10 69	98.87 85	97.38 63	99.35 49	99.40 50	97.78 5	99.87 81	97.77 115	99.85 7	99.78 34
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		98.59 35	98.32 60	99.41 24	99.54 42	98.71 28	99.04 80	98.81 109	95.12 215	99.32 52	99.39 51	96.22 35	99.84 90	97.72 118	99.73 63	99.67 80

aaatest				99.52 15	99.77 2	98.86 24	99.32 22	99.24 20	96.41 126	99.30 53	99.35 63		99.92 44	98.30 77	99.80 26	99.79 30

MED-MVS		99.12 2	98.97 5	99.56 9	99.77 2	98.86 24	99.32 22	99.24 20	97.87 32	99.30 53	99.54 21	97.61 6	99.92 44	98.30 77	99.80 26	99.90 6

reproduce-ours		98.93 12	98.78 15	99.38 25	99.49 53	98.38 43	98.86 143	98.83 99	98.06 26	99.29 55	99.58 17	96.40 31	99.94 15	98.68 47	99.81 17	99.81 26

our_new_method		98.93 12	98.78 15	99.38 25	99.49 53	98.38 43	98.86 143	98.83 99	98.06 26	99.29 55	99.58 17	96.40 31	99.94 15	98.68 47	99.81 17	99.81 26

dcpmvs_2		98.08 83	98.59 26	96.56 319	99.57 40	90.34 426	99.15 57	98.38 251	96.82 102	99.29 55	99.49 35	95.78 52	99.57 173	98.94 37	99.86 2	99.77 41

test_part2					99.63 35	99.18 10				99.27 58

DeepPCF-MVS	96.37 2	97.93 91	98.48 39	96.30 347	99.00 137	89.54 442	97.43 395	98.87 85	98.16 23	99.26 59	99.38 56	96.12 40	99.64 159	98.30 77	99.77 43	99.72 60

APD-MVS		98.35 69	98.00 84	99.42 23	99.51 47	98.72 27	98.80 165	98.82 103	94.52 258	99.23 60	99.25 87	95.54 59	99.80 111	96.52 205	99.77 43	99.74 51
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_one_0601					99.66 31	99.25 2		98.86 91	97.55 50	99.20 61	99.47 38	97.57 7

APD-MVS_3200maxsize		98.53 47	98.33 59	99.15 58	99.50 49	97.92 76	99.15 57	98.81 109	96.24 135	99.20 61	99.37 57	95.30 70	99.80 111	97.73 117	99.67 76	99.72 60

patch_mono-2		98.36 67	98.87 8	96.82 289	99.53 43	90.68 414	98.64 213	99.29 15	97.88 31	99.19 63	99.52 26	96.80 17	99.97 1	99.11 31	99.86 2	99.82 24

aaEdge-Enhanced		98.83 20	98.60 25	99.52 15	99.58 38	98.86 24	98.69 200	98.93 65	97.00 92	99.17 64	99.35 63	96.62 24	99.90 66	98.30 77	99.80 26	99.79 30

MM		98.51 50	98.24 66	99.33 37	99.12 123	98.14 68	98.93 115	97.02 435	98.96 2	99.17 64	99.47 38	91.97 151	99.94 15	99.85 5	99.69 73	99.91 5

SR-MVS-dyc-post		98.54 46	98.35 49	99.13 60	99.49 53	97.86 77	99.11 66	98.80 116	96.49 121	99.17 64	99.35 63	95.34 68	99.82 99	97.72 118	99.65 82	99.71 64

RE-MVS-def			98.34 55		99.49 53	97.86 77	99.11 66	98.80 116	96.49 121	99.17 64	99.35 63	95.29 71		97.72 118	99.65 82	99.71 64

9.14			98.06 79		99.47 57		98.71 193	98.82 103	94.36 268	99.16 68	99.29 76	96.05 42	99.81 104	97.00 174	99.71 70

ACMMP_NAP		98.61 32	98.30 61	99.55 11	99.62 36	98.95 20	98.82 156	98.81 109	95.80 161	99.16 68	99.47 38	95.37 65	99.92 44	97.89 105	99.75 55	99.79 30

test-260524					99.64 33	99.18 10		98.83 99		99.13 70		96.51 28	99.92 44	99.03 34	99.80 26

SR-MVS		98.57 42	98.35 49	99.24 47	99.53 43	98.18 63	99.09 70	98.82 103	96.58 116	99.10 71	99.32 70	95.39 63	99.82 99	97.70 123	99.63 89	99.72 60

PGM-MVS		98.49 52	98.23 68	99.27 45	99.72 17	98.08 70	98.99 94	99.49 5	95.43 190	99.03 72	99.32 70	95.56 57	99.94 15	96.80 196	99.77 43	99.78 34

KinetiMVS		97.48 132	97.05 154	98.78 88	98.37 212	97.30 104	98.99 94	98.70 142	97.18 80	99.02 73	99.01 153	87.50 307	99.67 152	95.33 250	99.33 141	99.37 144

VNet		97.79 99	97.40 117	98.96 77	98.88 149	97.55 88	98.63 216	98.93 65	96.74 107	99.02 73	98.84 182	90.33 220	99.83 92	98.53 57	96.66 287	99.50 108

xiu_mvs_v1_base_debu		97.60 115	97.56 101	97.72 216	98.35 214	95.98 182	97.86 358	98.51 196	97.13 85	99.01 75	98.40 241	91.56 165	99.80 111	98.53 57	98.68 176	97.37 338

xiu_mvs_v1_base		97.60 115	97.56 101	97.72 216	98.35 214	95.98 182	97.86 358	98.51 196	97.13 85	99.01 75	98.40 241	91.56 165	99.80 111	98.53 57	98.68 176	97.37 338

xiu_mvs_v1_base_debi		97.60 115	97.56 101	97.72 216	98.35 214	95.98 182	97.86 358	98.51 196	97.13 85	99.01 75	98.40 241	91.56 165	99.80 111	98.53 57	98.68 176	97.37 338

MVSMamba_PlusPlus		98.31 74	98.19 74	98.67 97	98.96 143	97.36 99	99.24 36	98.57 180	94.81 239	98.99 78	98.90 174	95.22 77	99.59 169	99.15 30	99.84 12	99.07 226

TSAR-MVS + GP.		98.38 64	98.24 66	98.81 86	99.22 108	97.25 114	98.11 323	98.29 282	97.19 79	98.99 78	99.02 149	96.22 35	99.67 152	98.52 63	98.56 187	99.51 105

CS-MVS		98.44 58	98.49 37	98.31 138	99.08 128	96.73 140	99.67 3	98.47 208	97.17 81	98.94 80	99.10 128	95.73 53	99.13 270	98.71 46	99.49 119	99.09 218

HFP-MVS		98.63 30	98.40 43	99.32 39	99.72 17	98.29 55	99.23 38	98.96 60	96.10 145	98.94 80	99.17 108	96.06 41	99.92 44	97.62 128	99.78 41	99.75 49

region2R		98.61 32	98.38 45	99.29 40	99.74 12	98.16 65	99.23 38	98.93 65	96.15 139	98.94 80	99.17 108	95.91 48	99.94 15	97.55 140	99.79 36	99.78 34

HPM-MVS_fast		98.38 64	98.13 75	99.12 62	99.75 6	97.86 77	99.44 9	98.82 103	94.46 264	98.94 80	99.20 96	95.16 79	99.74 136	97.58 135	99.85 7	99.77 41

test_fmvsmconf0.01_n		97.86 93	97.54 104	98.83 85	95.48 449	96.83 135	98.95 105	98.60 166	98.58 15	98.93 84	99.55 19	88.57 275	99.91 58	99.54 25	99.61 92	99.77 41

ACMMPR		98.59 35	98.36 47	99.29 40	99.74 12	98.15 66	99.23 38	98.95 61	96.10 145	98.93 84	99.19 103	95.70 54	99.94 15	97.62 128	99.79 36	99.78 34

DeepC-MVS_fast	96.70 1	98.55 45	98.34 55	99.18 54	99.25 98	98.04 71	98.50 250	98.78 123	97.72 37	98.92 86	99.28 77	95.27 72	99.82 99	97.55 140	99.77 43	99.69 71
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SPE-MVS-test		98.49 52	98.50 35	98.46 124	99.20 111	97.05 126	99.64 4	98.50 201	97.45 59	98.88 87	99.14 116	95.25 74	99.15 265	98.83 42	99.56 108	99.20 192

MGCNet		98.23 77	97.91 87	99.21 51	98.06 276	97.96 75	98.58 226	95.51 478	98.58 15	98.87 88	99.26 81	92.99 120	99.95 10	99.62 23	99.67 76	99.73 56

EC-MVSNet		98.21 80	98.11 77	98.49 121	98.34 219	97.26 113	99.61 5	98.43 229	96.78 103	98.87 88	98.84 182	93.72 110	99.01 301	98.91 39	99.50 117	99.19 196

diffmvs_AUTHOR		97.59 118	97.44 113	98.01 185	98.26 237	95.47 229	98.12 319	98.36 257	96.38 129	98.84 90	99.10 128	91.13 188	99.26 231	98.24 85	98.56 187	99.30 165

EI-MVSNet-Vis-set		98.47 55	98.39 44	98.69 95	99.46 59	96.49 155	98.30 285	98.69 144	97.21 77	98.84 90	99.36 61	95.41 62	99.78 126	98.62 51	99.65 82	99.80 29

MSLP-MVS++		98.56 44	98.57 27	98.55 109	99.26 97	96.80 136	98.71 193	99.05 49	97.28 70	98.84 90	99.28 77	96.47 29	99.40 209	98.52 63	99.70 72	99.47 117

PHI-MVS		98.34 71	98.06 79	99.18 54	99.15 120	98.12 69	99.04 80	99.09 44	93.32 331	98.83 93	99.10 128	96.54 25	99.83 92	97.70 123	99.76 49	99.59 95

GDP-MVS		97.64 110	97.28 128	98.71 94	98.30 228	97.33 100	99.05 76	98.52 193	96.34 131	98.80 94	99.05 146	89.74 235	99.51 189	96.86 192	98.86 168	99.28 175

MVSFormer		97.57 120	97.49 107	97.84 203	98.07 272	95.76 214	99.47 7	98.40 238	94.98 228	98.79 95	98.83 186	92.34 132	98.41 376	96.91 180	99.59 96	99.34 151

lupinMVS		97.44 140	97.22 137	98.12 168	98.07 272	95.76 214	97.68 375	97.76 359	94.50 262	98.79 95	98.61 217	92.34 132	99.30 223	97.58 135	99.59 96	99.31 160

CDPH-MVS		97.94 90	97.49 107	99.28 43	99.47 57	98.44 39	97.91 348	98.67 152	92.57 365	98.77 97	98.85 181	95.93 47	99.72 139	95.56 243	99.69 73	99.68 76

CNVR-MVS		98.78 21	98.56 29	99.45 20	99.32 79	98.87 22	98.47 256	98.81 109	97.72 37	98.76 98	99.16 111	97.05 15	99.78 126	98.06 92	99.66 79	99.69 71

EI-MVSNet-UG-set		98.41 62	98.34 55	98.61 103	99.45 62	96.32 165	98.28 288	98.68 147	97.17 81	98.74 99	99.37 57	95.25 74	99.79 123	98.57 54	99.54 111	99.73 56

diffmvs		97.58 119	97.40 117	98.13 165	98.32 226	95.81 210	98.06 329	98.37 253	96.20 137	98.74 99	98.89 176	91.31 178	99.25 235	98.16 87	98.52 191	99.34 151
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
guyue		97.57 120	97.37 120	98.20 150	98.50 189	95.86 203	98.89 125	97.03 432	97.29 68	98.73 101	98.90 174	89.41 247	99.32 218	98.68 47	98.86 168	99.42 134

GST-MVS		98.43 60	98.12 76	99.34 33	99.72 17	98.38 43	99.09 70	98.82 103	95.71 167	98.73 101	99.06 144	95.27 72	99.93 35	97.07 172	99.63 89	99.72 60

PRO-TEST		97.77 100	97.67 95	98.06 177	98.15 264	96.06 179	98.94 108	98.46 209	96.88 98	98.72 103	98.59 222	92.46 128	99.03 294	97.89 105	98.97 160	99.10 214

UA-Net		97.96 88	97.62 96	98.98 74	98.86 153	97.47 94	98.89 125	99.08 45	96.67 113	98.72 103	99.54 21	93.15 118	99.81 104	94.87 265	98.83 171	99.65 84

NormalMVS		98.07 85	97.90 88	98.59 105	99.75 6	96.60 146	98.94 108	98.60 166	97.86 34	98.71 105	99.08 139	91.22 183	99.80 111	97.40 159	99.57 100	99.37 144

SymmetryMVS		97.84 96	97.58 98	98.62 101	99.01 135	96.60 146	98.94 108	98.44 218	97.86 34	98.71 105	99.08 139	91.22 183	99.80 111	97.40 159	97.53 263	99.47 117

LuminaMVS		97.49 131	97.18 140	98.42 131	97.50 335	97.15 121	98.45 258	97.68 362	96.56 120	98.68 107	98.78 195	89.84 232	99.32 218	98.60 52	98.57 186	98.79 256

h-mvs33		96.17 223	95.62 237	97.81 207	99.03 132	94.45 291	98.64 213	98.75 129	97.48 55	98.67 108	98.72 208	89.76 233	99.86 85	97.95 98	81.59 475	99.11 212

hse-mvs2		95.71 247	95.30 254	96.93 280	98.50 189	93.53 332	98.36 273	98.10 323	97.48 55	98.67 108	97.99 282	89.76 233	99.02 299	97.95 98	80.91 481	98.22 307

ZD-MVS					99.46 59	98.70 29		98.79 121	93.21 336	98.67 108	98.97 157	95.70 54	99.83 92	96.07 217	99.58 99

旧先验2							97.57 385		91.30 408	98.67 108			99.80 111	95.70 238

PS-MVSNAJ		97.73 102	97.77 90	97.62 231	98.68 173	95.58 221	97.34 404	98.51 196	97.29 68	98.66 112	97.88 294	94.51 93	99.90 66	97.87 108	99.17 150	97.39 336

onestephybrid01		97.54 127	97.36 121	98.06 177	98.25 239	95.63 219	98.26 291	98.33 264	96.13 140	98.65 113	99.13 119	91.02 195	99.25 235	98.07 91	98.42 209	99.31 160

xiu_mvs_v2_base		97.66 109	97.70 93	97.56 235	98.61 182	95.46 230	97.44 392	98.46 209	97.15 83	98.65 113	98.15 269	94.33 99	99.80 111	97.84 111	98.66 180	97.41 334

LFMVS		95.86 239	94.98 270	98.47 123	98.87 152	96.32 165	98.84 152	96.02 469	93.40 328	98.62 115	99.20 96	74.99 467	99.63 162	97.72 118	97.20 268	99.46 122

HPM-MVS		98.36 67	98.10 78	99.13 60	99.74 12	97.82 82	99.53 6	98.80 116	94.63 251	98.61 116	98.97 157	95.13 81	99.77 131	97.65 126	99.83 14	99.79 30
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
AstraMVS		97.34 154	97.24 134	97.65 228	98.13 266	94.15 309	98.94 108	96.25 468	97.47 57	98.60 117	99.28 77	89.67 237	99.41 208	98.73 45	98.07 236	99.38 143

testdata				98.26 143	99.20 111	95.36 240		98.68 147	91.89 388	98.60 117	99.10 128	94.44 98	99.82 99	94.27 296	99.44 127	99.58 99

CP-MVS		98.57 42	98.36 47	99.19 52	99.66 31	97.86 77	99.34 17	98.87 85	95.96 152	98.60 117	99.13 119	96.05 42	99.94 15	97.77 115	99.86 2	99.77 41

jason		97.32 156	97.08 151	98.06 177	97.45 341	95.59 220	97.87 356	97.91 346	94.79 241	98.55 120	98.83 186	91.12 190	99.23 247	97.58 135	99.60 94	99.34 151
jason: jason.
MCST-MVS		98.65 27	98.37 46	99.48 18	99.60 37	98.87 22	98.41 270	98.68 147	97.04 89	98.52 121	98.80 189	96.78 18	99.83 92	97.93 100	99.61 92	99.74 51

BP-MVS1		97.82 97	97.51 106	98.76 90	98.25 239	97.39 98	99.15 57	97.68 362	96.69 111	98.47 122	99.10 128	90.29 221	99.51 189	98.60 52	99.35 138	99.37 144

XVS		98.70 25	98.49 37	99.34 33	99.70 27	98.35 52	99.29 28	98.88 78	97.40 60	98.46 123	99.20 96	95.90 50	99.89 70	97.85 109	99.74 59	99.78 34

X-MVStestdata		94.06 370	92.30 396	99.34 33	99.70 27	98.35 52	99.29 28	98.88 78	97.40 60	98.46 123	43.50 554	95.90 50	99.89 70	97.85 109	99.74 59	99.78 34

MG-MVS		97.81 98	97.60 97	98.44 127	99.12 123	95.97 187	97.75 370	98.78 123	96.89 97	98.46 123	99.22 91	93.90 109	99.68 151	94.81 269	99.52 114	99.67 80

viewmamba		97.55 123	97.45 112	97.87 201	98.22 246	95.13 255	98.35 274	98.35 258	96.57 118	98.45 126	99.15 115	91.60 162	99.18 256	97.99 96	98.36 216	99.29 168

test_fmvsmvis_n_1920		98.44 58	98.51 33	98.23 147	98.33 223	96.15 173	98.97 98	99.15 41	98.55 17	98.45 126	99.55 19	94.26 102	99.97 1	99.65 19	99.66 79	98.57 290

NCCC		98.61 32	98.35 49	99.38 25	99.28 94	98.61 34	98.45 258	98.76 127	97.82 36	98.45 126	98.93 167	96.65 22	99.83 92	97.38 162	99.41 130	99.71 64

MVS_Test		97.28 158	97.00 157	98.13 165	98.33 223	95.97 187	98.74 182	98.07 330	94.27 271	98.44 129	98.07 274	92.48 127	99.26 231	96.43 208	98.19 231	99.16 202

MVS_111021_LR		98.34 71	98.23 68	98.67 97	99.27 95	96.90 132	97.95 341	99.58 3	97.14 84	98.44 129	99.01 153	95.03 85	99.62 166	97.91 103	99.75 55	99.50 108

balanced_ft_v1		97.54 127	97.38 119	98.02 183	98.34 219	95.58 221	99.32 22	98.40 238	95.88 156	98.43 131	98.65 215	88.95 267	99.59 169	98.94 37	99.48 122	98.90 245

hybridnocas07		97.41 143	97.21 138	97.99 187	98.24 242	95.42 232	98.21 296	98.32 268	95.97 151	98.38 132	98.93 167	90.48 212	99.21 252	97.92 102	98.46 198	99.34 151

ETV-MVS		97.96 88	97.81 89	98.40 133	98.42 202	97.27 108	98.73 188	98.55 186	96.84 100	98.38 132	97.44 336	95.39 63	99.35 214	97.62 128	98.89 164	98.58 289

test2506		94.44 341	93.91 339	96.04 356	99.02 133	88.99 453	99.06 74	79.47 529	96.96 94	98.36 134	99.26 81	77.21 447	99.52 188	96.78 197	99.04 154	99.59 95

VDDNet		95.36 271	94.53 292	97.86 202	98.10 269	95.13 255	98.85 148	97.75 360	90.46 425	98.36 134	99.39 51	73.27 477	99.64 159	97.98 97	96.58 290	98.81 254

hybrid		97.34 154	97.16 142	97.88 200	98.25 239	95.18 251	98.18 309	98.33 264	95.36 198	98.35 136	99.06 144	90.61 208	99.18 256	97.88 107	98.40 212	99.27 176

mPP-MVS		98.51 50	98.26 63	99.25 46	99.75 6	98.04 71	99.28 30	98.81 109	96.24 135	98.35 136	99.23 88	95.46 60	99.94 15	97.42 157	99.81 17	99.77 41

DELS-MVS		98.40 63	98.20 72	98.99 72	99.00 137	97.66 83	97.75 370	98.89 75	97.71 39	98.33 138	98.97 157	94.97 86	99.88 79	98.42 71	99.76 49	99.42 134
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
MVS_111021_HR		98.47 55	98.34 55	98.88 84	99.22 108	97.32 101	97.91 348	99.58 3	97.20 78	98.33 138	99.00 155	95.99 45	99.64 159	98.05 94	99.76 49	99.69 71

ZNCC-MVS		98.49 52	98.20 72	99.35 32	99.73 16	98.39 42	99.19 50	98.86 91	95.77 163	98.31 140	99.10 128	95.46 60	99.93 35	97.57 139	99.81 17	99.74 51

HPM-MVS++		98.58 37	98.25 64	99.55 11	99.50 49	99.08 13	98.72 192	98.66 155	97.51 52	98.15 141	98.83 186	95.70 54	99.92 44	97.53 143	99.67 76	99.66 83

mvsmamba		97.25 161	96.99 159	98.02 183	98.34 219	95.54 226	99.18 54	97.47 389	95.04 221	98.15 141	98.57 226	89.46 244	99.31 222	97.68 125	99.01 157	99.22 189

新几何1				99.16 57	99.34 73	98.01 73		98.69 144	90.06 433	98.13 143	98.95 164	94.60 91	99.89 70	91.97 377	99.47 123	99.59 95

API-MVS		97.41 143	97.25 130	97.91 196	98.70 168	96.80 136	98.82 156	98.69 144	94.53 256	98.11 144	98.28 256	94.50 96	99.57 173	94.12 303	99.49 119	97.37 338

ECVR-MVS		95.95 231	95.71 231	96.65 304	99.02 133	90.86 409	99.03 83	91.80 512	96.96 94	98.10 145	99.26 81	81.31 403	99.51 189	96.90 183	99.04 154	99.59 95

Casviewmamba		97.62 113	97.43 115	98.19 154	98.48 194	95.83 206	99.07 72	98.42 233	96.27 134	98.09 146	99.26 81	91.00 196	99.30 223	97.81 113	98.48 196	99.44 127

CPTT-MVS		97.72 103	97.32 125	98.92 80	99.64 33	97.10 124	99.12 64	98.81 109	92.34 373	98.09 146	99.08 139	93.01 119	99.92 44	96.06 220	99.77 43	99.75 49

viewcassd2359sk11		97.53 129	97.32 125	98.16 156	98.45 198	95.83 206	98.57 235	98.42 233	95.52 185	98.07 148	99.12 123	91.81 156	99.25 235	97.46 153	98.48 196	99.41 137

test12				99.18 54	99.16 117	98.19 62		98.53 190		98.07 148		95.13 81	99.72 139		99.56 108	99.63 89

E3new		97.55 123	97.35 123	98.16 156	98.48 194	95.85 204	98.55 239	98.41 235	95.42 192	98.06 150	99.12 123	92.23 139	99.24 243	97.43 155	98.45 199	99.39 139

RRT-MVS		97.03 176	96.78 175	97.77 212	97.90 300	94.34 298	99.12 64	98.35 258	95.87 158	98.06 150	98.70 209	86.45 326	99.63 162	98.04 95	98.54 189	99.35 149

test222					99.23 106	97.17 119	97.40 396	98.66 155	88.68 454	98.05 152	98.96 162	94.14 104			99.53 113	99.61 91

DP-MVS Recon		97.86 93	97.46 110	99.06 67	99.53 43	98.35 52	98.33 277	98.89 75	92.62 362	98.05 152	98.94 165	95.34 68	99.65 156	96.04 221	99.42 129	99.19 196

Vis-MVSNet		97.42 142	97.11 149	98.34 136	98.66 175	96.23 169	99.22 42	99.00 53	96.63 115	98.04 154	99.21 94	88.05 293	99.35 214	96.01 223	99.21 147	99.45 124
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test1111		95.94 234	95.78 225	96.41 338	98.99 140	90.12 428	99.04 80	92.45 511	96.99 93	98.03 155	99.27 80	81.40 402	99.48 198	96.87 189	99.04 154	99.63 89

baseline		97.64 110	97.44 113	98.25 144	98.35 214	96.20 170	99.00 91	98.32 268	96.33 133	98.03 155	99.17 108	91.35 175	99.16 261	98.10 89	98.29 223	99.39 139

test_yl		97.22 163	96.78 175	98.54 111	98.73 163	96.60 146	98.45 258	98.31 273	94.70 245	98.02 157	98.42 239	90.80 201	99.70 145	96.81 193	96.79 282	99.34 151

DCV-MVSNet		97.22 163	96.78 175	98.54 111	98.73 163	96.60 146	98.45 258	98.31 273	94.70 245	98.02 157	98.42 239	90.80 201	99.70 145	96.81 193	96.79 282	99.34 151

MTAPA		98.58 37	98.29 62	99.46 19	99.76 5	98.64 32	98.90 121	98.74 131	97.27 74	98.02 157	99.39 51	94.81 89	99.96 5	97.91 103	99.79 36	99.77 41

sss		97.39 145	96.98 161	98.61 103	98.60 183	96.61 145	98.22 295	98.93 65	93.97 286	98.01 160	98.48 234	91.98 149	99.85 86	96.45 207	98.15 232	99.39 139

E2		97.48 132	97.25 130	98.16 156	98.40 206	95.79 211	98.58 226	98.44 218	95.58 174	98.00 161	99.14 116	91.21 187	99.24 243	97.50 148	98.43 203	99.45 124

E3		97.48 132	97.25 130	98.16 156	98.38 209	95.79 211	98.58 226	98.44 218	95.58 174	98.00 161	99.14 116	91.25 181	99.24 243	97.50 148	98.44 200	99.45 124

alignmvs		97.56 122	97.07 152	99.01 71	98.66 175	98.37 50	98.83 154	98.06 335	96.74 107	98.00 161	97.65 317	90.80 201	99.48 198	98.37 73	96.56 291	99.19 196

viewmanbaseed2359cas		97.47 135	97.25 130	98.14 160	98.41 204	95.84 205	98.57 235	98.43 229	95.55 181	97.97 164	99.12 123	91.26 180	99.15 265	97.42 157	98.53 190	99.43 131

OMC-MVS		97.55 123	97.34 124	98.20 150	99.33 76	95.92 194	98.28 288	98.59 173	95.52 185	97.97 164	99.10 128	93.28 117	99.49 193	95.09 260	98.88 165	99.19 196

VDD-MVS		95.82 242	95.23 256	97.61 232	98.84 157	93.98 313	98.68 203	97.40 398	95.02 225	97.95 166	99.34 69	74.37 473	99.78 126	98.64 50	96.80 281	99.08 222

casdiffmvs		97.63 112	97.41 116	98.28 139	98.33 223	96.14 174	98.82 156	98.32 268	96.38 129	97.95 166	99.21 94	91.23 182	99.23 247	98.12 88	98.37 214	99.48 115
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		96.73 194	96.60 187	97.12 263	99.25 98	95.35 242	98.26 291	99.26 16	94.28 270	97.94 168	97.46 333	92.74 123	99.81 104	96.88 186	93.32 359	96.20 440

PVSNet_Blended		97.38 146	97.12 148	98.14 160	99.25 98	95.35 242	97.28 410	99.26 16	93.13 341	97.94 168	98.21 264	92.74 123	99.81 104	96.88 186	99.40 133	99.27 176

DPM-MVS		97.55 123	96.99 159	99.23 50	99.04 131	98.55 35	97.17 424	98.35 258	94.85 238	97.93 170	98.58 223	95.07 83	99.71 144	92.60 356	99.34 139	99.43 131

MP-MVS		98.33 73	98.01 83	99.28 43	99.75 6	98.18 63	99.22 42	98.79 121	96.13 140	97.92 171	99.23 88	94.54 92	99.94 15	96.74 199	99.78 41	99.73 56
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Elysia		96.64 198	96.02 215	98.51 116	98.04 280	97.30 104	98.74 182	98.60 166	95.04 221	97.91 172	98.84 182	83.59 387	99.48 198	94.20 299	99.25 145	98.75 265

StellarMVS		96.64 198	96.02 215	98.51 116	98.04 280	97.30 104	98.74 182	98.60 166	95.04 221	97.91 172	98.84 182	83.59 387	99.48 198	94.20 299	99.25 145	98.75 265

MDTV_nov1_ep13_2view						84.26 488	96.89 447		90.97 417	97.90 174		89.89 231		93.91 310		99.18 201

test_prior2							97.80 365		96.12 143	97.89 175	98.69 210	95.96 46		96.89 184	99.60 94

viewmacassd2359aftdt		97.32 156	97.07 152	98.08 173	98.30 228	95.69 217	98.62 219	98.44 218	95.56 176	97.86 176	99.22 91	89.91 230	99.14 268	97.29 165	98.43 203	99.42 134

E5new		97.37 148	97.16 142	97.98 189	98.30 228	95.41 233	98.87 135	98.45 214	95.56 176	97.84 177	99.19 103	90.39 216	99.25 235	97.61 131	98.22 227	99.29 168

E6new		97.37 148	97.16 142	97.98 189	98.28 234	95.40 236	98.87 135	98.45 214	95.55 181	97.84 177	99.20 96	90.44 214	99.25 235	97.61 131	98.22 227	99.29 168

E6		97.37 148	97.16 142	97.98 189	98.28 234	95.40 236	98.87 135	98.45 214	95.55 181	97.84 177	99.20 96	90.44 214	99.25 235	97.61 131	98.22 227	99.29 168

E5		97.37 148	97.16 142	97.98 189	98.30 228	95.41 233	98.87 135	98.45 214	95.56 176	97.84 177	99.19 103	90.39 216	99.25 235	97.61 131	98.22 227	99.29 168

原ACMM1				98.65 99	99.32 79	96.62 143		98.67 152	93.27 335	97.81 181	98.97 157	95.18 78	99.83 92	93.84 312	99.46 126	99.50 108

E4		97.37 148	97.13 147	98.12 168	98.27 236	95.70 216	98.59 222	98.44 218	95.56 176	97.80 182	99.18 106	90.57 210	99.26 231	97.45 154	98.28 225	99.40 138

viewmambaseed2359dif		97.01 178	96.84 168	97.51 237	98.19 252	94.21 306	98.16 312	98.23 294	93.61 318	97.78 183	99.13 119	90.79 204	99.18 256	97.24 166	98.40 212	99.15 203

114514_t		96.93 183	96.27 203	98.92 80	99.50 49	97.63 85	98.85 148	98.90 73	84.80 484	97.77 184	99.11 126	92.84 121	99.66 155	94.85 266	99.77 43	99.47 117

casdiffmvs_mvg		97.72 103	97.48 109	98.44 127	98.42 202	96.59 150	98.92 118	98.44 218	96.20 137	97.76 185	99.20 96	91.66 161	99.23 247	98.27 84	98.41 211	99.49 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PMMVS		96.60 201	96.33 201	97.41 244	97.90 300	93.93 315	97.35 403	98.41 235	92.84 354	97.76 185	97.45 335	91.10 192	99.20 253	96.26 213	97.91 241	99.11 212

PVSNet	91.96 18	96.35 214	96.15 207	96.96 278	99.17 113	92.05 387	96.08 469	98.68 147	93.69 308	97.75 187	97.80 304	88.86 269	99.69 150	94.26 297	99.01 157	99.15 203

TEST9					99.31 81	98.50 37	97.92 346	98.73 134	92.63 361	97.74 188	98.68 211	96.20 37	99.80 111

train_agg		97.97 87	97.52 105	99.33 37	99.31 81	98.50 37	97.92 346	98.73 134	92.98 347	97.74 188	98.68 211	96.20 37	99.80 111	96.59 200	99.57 100	99.68 76

FE-MVS		95.62 253	94.90 274	97.78 209	98.37 212	94.92 269	97.17 424	97.38 400	90.95 418	97.73 190	97.70 310	85.32 351	99.63 162	91.18 392	98.33 219	98.79 256

mmtdpeth		93.12 392	92.61 388	94.63 425	97.60 324	89.68 439	99.21 45	97.32 404	94.02 280	97.72 191	94.42 467	77.01 452	99.44 205	99.05 32	77.18 493	94.78 476

CANet		98.05 86	97.76 91	98.90 83	98.73 163	97.27 108	98.35 274	98.78 123	97.37 65	97.72 191	98.96 162	91.53 169	99.92 44	98.79 43	99.65 82	99.51 105

test_8					99.29 90	98.44 39	97.89 354	98.72 136	92.98 347	97.70 193	98.66 214	96.20 37	99.80 111

hybridcas		97.52 130	97.29 127	98.20 150	98.44 199	96.00 180	99.02 86	98.39 244	96.12 143	97.69 194	99.23 88	90.77 206	99.17 259	97.55 140	98.42 209	99.44 127

MP-MVS-pluss		98.31 74	97.92 86	99.49 17	99.72 17	98.88 21	98.43 266	98.78 123	94.10 276	97.69 194	99.42 47	95.25 74	99.92 44	98.09 90	99.80 26	99.67 80
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
sasdasda		97.67 107	97.23 135	98.98 74	98.70 168	98.38 43	99.34 17	98.39 244	96.76 105	97.67 196	97.40 340	92.26 136	99.49 193	98.28 81	96.28 306	99.08 222

canonicalmvs		97.67 107	97.23 135	98.98 74	98.70 168	98.38 43	99.34 17	98.39 244	96.76 105	97.67 196	97.40 340	92.26 136	99.49 193	98.28 81	96.28 306	99.08 222

PVSNet_Blended_VisFu		97.70 105	97.46 110	98.44 127	99.27 95	95.91 195	98.63 216	99.16 39	94.48 263	97.67 196	98.88 177	92.80 122	99.91 58	97.11 170	99.12 151	99.50 108

WTY-MVS		97.37 148	96.92 164	98.72 93	98.86 153	96.89 134	98.31 282	98.71 139	95.26 204	97.67 196	98.56 227	92.21 141	99.78 126	95.89 225	96.85 280	99.48 115

dtuplus		97.00 179	96.83 170	97.51 237	98.18 258	94.21 306	98.21 296	98.20 298	94.42 267	97.66 200	99.22 91	90.18 225	99.17 259	97.01 173	98.36 216	99.13 208

viewdifsd2359ckpt07		97.20 166	97.05 154	97.65 228	98.40 206	94.33 300	98.39 272	98.43 229	95.67 169	97.66 200	99.08 139	90.04 227	99.32 218	97.47 152	98.29 223	99.31 160

Effi-MVS+		97.12 173	96.69 181	98.39 134	98.19 252	96.72 141	97.37 400	98.43 229	93.71 305	97.65 202	98.02 278	92.20 142	99.25 235	96.87 189	97.79 246	99.19 196

thisisatest0530		96.01 228	95.36 247	97.97 193	98.38 209	95.52 227	98.88 132	94.19 499	94.04 278	97.64 203	98.31 254	83.82 385	99.46 203	95.29 254	97.70 252	98.93 242

tttt0517		96.07 226	95.51 240	97.78 209	98.41 204	94.84 272	99.28 30	94.33 495	94.26 272	97.64 203	98.64 216	84.05 378	99.47 202	95.34 249	97.60 255	99.03 230

viewdifsd2359ckpt11		96.30 216	96.13 208	96.81 290	98.10 269	92.10 383	98.49 253	98.40 238	96.02 147	97.61 205	99.31 72	86.37 328	99.29 226	97.52 144	93.36 358	99.04 228

viewmsd2359difaftdt		96.30 216	96.13 208	96.81 290	98.10 269	92.10 383	98.49 253	98.40 238	96.02 147	97.61 205	99.31 72	86.37 328	99.30 223	97.52 144	93.37 357	99.04 228

HyFIR lowres test		96.90 185	96.49 194	98.14 160	99.33 76	95.56 223	97.38 398	99.65 2	92.34 373	97.61 205	98.20 265	89.29 251	99.10 279	96.97 176	97.60 255	99.77 41

viewdifsd2359ckpt13		97.24 162	96.97 162	98.06 177	98.43 200	95.77 213	98.59 222	98.34 262	94.81 239	97.60 208	98.94 165	90.78 205	99.09 280	96.93 179	98.33 219	99.32 159

ACMMP		98.23 77	97.95 85	99.09 64	99.74 12	97.62 86	99.03 83	99.41 6	95.98 150	97.60 208	99.36 61	94.45 97	99.93 35	97.14 169	98.85 170	99.70 68
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
MGCFI-Net		97.62 113	97.19 139	98.92 80	98.66 175	98.20 61	99.32 22	98.38 251	96.69 111	97.58 210	97.42 339	92.10 145	99.50 192	98.28 81	96.25 309	99.08 222

agg_prior					99.30 85	98.38 43		98.72 136		97.57 211			99.81 104

tpmrst		95.63 252	95.69 234	95.44 392	97.54 331	88.54 461	96.97 436	97.56 376	93.50 322	97.52 212	96.93 391	89.49 240	99.16 261	95.25 256	96.42 297	98.64 281

MDTV_nov1_ep13			95.40 242		97.48 336	88.34 465	96.85 452	97.29 408	93.74 301	97.48 213	97.26 350	89.18 254	99.05 288	91.92 378	97.43 265

FA-MVS(test-final)		96.41 213	95.94 219	97.82 206	98.21 248	95.20 250	97.80 365	97.58 373	93.21 336	97.36 214	97.70 310	89.47 242	99.56 176	94.12 303	97.99 238	98.71 271

viewdifsd2359ckpt09		97.13 172	96.79 173	98.14 160	98.43 200	95.90 196	98.52 242	98.37 253	94.32 269	97.33 215	98.86 180	90.23 224	99.16 261	96.81 193	98.25 226	99.36 148

icg_test_0407_2		96.56 205	96.50 193	96.73 295	97.99 287	92.82 366	97.18 421	98.27 283	95.16 209	97.30 216	98.79 191	91.53 169	98.10 410	94.74 271	97.54 259	99.27 176

IMVS_0407		96.74 192	96.64 185	97.05 269	97.99 287	92.82 366	98.45 258	98.27 283	95.16 209	97.30 216	98.79 191	91.53 169	99.06 287	94.74 271	97.54 259	99.27 176

EPMVS		94.99 296	94.48 295	96.52 325	97.22 356	91.75 392	97.23 412	91.66 513	94.11 275	97.28 218	96.81 400	85.70 341	98.84 327	93.04 337	97.28 267	98.97 236

EIA-MVS		97.75 101	97.58 98	98.27 140	98.38 209	96.44 157	99.01 89	98.60 166	95.88 156	97.26 219	97.53 330	94.97 86	99.33 217	97.38 162	99.20 148	99.05 227

SSM_0404		97.26 160	97.00 157	98.03 181	98.46 196	95.99 181	98.62 219	98.44 218	94.77 242	97.24 220	98.93 167	91.22 183	99.28 228	96.54 202	98.74 175	98.84 251

IS-MVSNet		97.22 163	96.88 165	98.25 144	98.85 156	96.36 163	99.19 50	97.97 340	95.39 194	97.23 221	98.99 156	91.11 191	98.93 314	94.60 283	98.59 183	99.47 117

testing3-2		95.45 262	95.34 248	95.77 379	98.69 171	88.75 457	98.87 135	97.21 417	96.13 140	97.22 222	97.68 315	77.95 440	99.65 156	97.58 135	96.77 284	98.91 244

EPP-MVSNet		97.46 136	97.28 128	97.99 187	98.64 179	95.38 239	99.33 21	98.31 273	93.61 318	97.19 223	99.07 143	94.05 105	99.23 247	96.89 184	98.43 203	99.37 144

thisisatest0515		95.61 256	94.89 275	97.76 213	98.15 264	95.15 254	96.77 455	94.41 493	92.95 349	97.18 224	97.43 337	84.78 360	99.45 204	94.63 279	97.73 251	98.68 275

IMVS_0403		96.74 192	96.61 186	97.12 263	97.99 287	92.82 366	98.47 256	98.27 283	95.16 209	97.13 225	98.79 191	91.44 172	99.26 231	94.74 271	97.54 259	99.27 176

CANet_DTU		96.96 182	96.55 189	98.21 148	98.17 262	96.07 178	97.98 339	98.21 296	97.24 75	97.13 225	98.93 167	86.88 318	99.91 58	95.00 263	99.37 137	98.66 279

CHOSEN 1792x2688		97.12 173	96.80 171	98.08 173	99.30 85	94.56 289	98.05 330	99.71 1	93.57 320	97.09 227	98.91 173	88.17 287	99.89 70	96.87 189	99.56 108	99.81 26

PatchT		93.06 393	91.97 400	96.35 343	96.69 392	92.67 371	94.48 501	97.08 426	86.62 470	97.08 228	92.23 496	87.94 295	97.90 435	78.89 497	96.69 285	98.49 294

PatchmatchNet		95.71 247	95.52 238	96.29 348	97.58 326	90.72 413	96.84 453	97.52 384	94.06 277	97.08 228	96.96 386	89.24 253	98.90 320	92.03 374	98.37 214	99.26 183
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MAR-MVS		96.91 184	96.40 197	98.45 125	98.69 171	96.90 132	98.66 210	98.68 147	92.40 372	97.07 230	97.96 285	91.54 168	99.75 134	93.68 316	98.92 162	98.69 273
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
PAPM_NR		97.46 136	97.11 149	98.50 119	99.50 49	96.41 160	98.63 216	98.60 166	95.18 208	97.06 231	98.06 275	94.26 102	99.57 173	93.80 314	98.87 167	99.52 102

TAMVS		97.02 177	96.79 173	97.70 219	98.06 276	95.31 245	98.52 242	98.31 273	93.95 287	97.05 232	98.61 217	93.49 113	98.52 358	95.33 250	97.81 245	99.29 168

CSCG		97.85 95	97.74 92	98.20 150	99.67 30	95.16 252	99.22 42	99.32 12	93.04 345	97.02 233	98.92 172	95.36 66	99.91 58	97.43 155	99.64 87	99.52 102

CDS-MVSNet		96.99 180	96.69 181	97.90 197	98.05 278	95.98 182	98.20 300	98.33 264	93.67 312	96.95 234	98.49 233	93.54 112	98.42 369	95.24 257	97.74 250	99.31 160
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
XVG-OURS-SEG-HR		96.51 207	96.34 200	97.02 271	98.77 161	93.76 320	97.79 367	98.50 201	95.45 189	96.94 235	99.09 136	87.87 298	99.55 183	96.76 198	95.83 320	97.74 324

CR-MVSNet		94.76 315	94.15 319	96.59 315	97.00 370	93.43 335	94.96 490	97.56 376	92.46 366	96.93 236	96.24 424	88.15 288	97.88 440	87.38 451	96.65 288	98.46 296

RPMNet		92.81 395	91.34 406	97.24 252	97.00 370	93.43 335	94.96 490	98.80 116	82.27 491	96.93 236	92.12 497	86.98 316	99.82 99	76.32 505	96.65 288	98.46 296

SCA		95.46 260	95.13 260	96.46 334	97.67 318	91.29 401	97.33 405	97.60 372	94.68 248	96.92 238	97.10 361	83.97 380	98.89 321	92.59 358	98.32 222	99.20 192

PatchMatch-RL		96.59 202	96.03 214	98.27 140	99.31 81	96.51 154	97.91 348	99.06 47	93.72 304	96.92 238	98.06 275	88.50 280	99.65 156	91.77 382	99.00 159	98.66 279

DeepC-MVS	95.98 3	97.88 92	97.58 98	98.77 89	99.25 98	96.93 130	98.83 154	98.75 129	96.96 94	96.89 240	99.50 32	90.46 213	99.87 81	97.84 111	99.76 49	99.52 102
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
casdiffseed414692147		96.97 181	96.55 189	98.25 144	98.26 237	96.28 168	98.93 115	98.33 264	94.99 226	96.87 241	99.09 136	88.97 265	99.07 284	95.70 238	97.77 248	99.39 139

XVG-OURS		96.55 206	96.41 196	96.99 272	98.75 162	93.76 320	97.50 389	98.52 193	95.67 169	96.83 242	99.30 75	88.95 267	99.53 185	95.88 226	96.26 308	97.69 327

AdaColmap		97.15 171	96.70 180	98.48 122	99.16 117	96.69 142	98.01 335	98.89 75	94.44 265	96.83 242	98.68 211	90.69 207	99.76 132	94.36 291	99.29 144	98.98 235

CostFormer		94.95 304	94.73 281	95.60 386	97.28 352	89.06 450	97.53 386	96.89 445	89.66 440	96.82 244	96.72 404	86.05 335	98.95 313	95.53 245	96.13 314	98.79 256

UGNet		96.78 191	96.30 202	98.19 154	98.24 242	95.89 201	98.88 132	98.93 65	97.39 62	96.81 245	97.84 298	82.60 392	99.90 66	96.53 204	99.49 119	98.79 256
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
CNLPA		97.45 139	97.03 156	98.73 92	99.05 130	97.44 97	98.07 328	98.53 190	95.32 201	96.80 246	98.53 228	93.32 115	99.72 139	94.31 295	99.31 143	99.02 231

CHOSEN 280x420		97.18 168	97.18 140	97.20 254	98.81 159	93.27 349	95.78 476	99.15 41	95.25 205	96.79 247	98.11 272	92.29 135	99.07 284	98.56 56	99.85 7	99.25 185

mamba_0408		96.81 190	96.38 198	98.09 172	98.19 252	95.90 196	95.69 477	98.32 268	94.51 259	96.75 248	98.73 205	90.99 197	99.27 230	95.83 228	98.43 203	99.10 214

SSM_04072		96.71 195	96.38 198	97.68 222	98.19 252	95.90 196	95.69 477	98.32 268	94.51 259	96.75 248	98.73 205	90.99 197	98.02 425	95.83 228	98.43 203	99.10 214

SSM_0407		97.17 169	96.87 166	98.08 173	98.19 252	95.90 196	98.52 242	98.44 218	94.77 242	96.75 248	98.93 167	91.22 183	99.22 251	96.54 202	98.43 203	99.10 214

HY-MVS	93.96 8	96.82 189	96.23 206	98.57 106	98.46 196	97.00 127	98.14 316	98.21 296	93.95 287	96.72 251	97.99 282	91.58 163	99.76 132	94.51 287	96.54 292	98.95 240

PAPR		96.84 188	96.24 205	98.65 99	98.72 167	96.92 131	97.36 402	98.57 180	93.33 330	96.67 252	97.57 326	94.30 100	99.56 176	91.05 400	98.59 183	99.47 117

Anonymous20240529		95.10 288	94.22 313	97.75 214	99.01 135	94.26 303	98.87 135	98.83 99	85.79 478	96.64 253	98.97 157	78.73 429	99.85 86	96.27 212	94.89 326	99.12 209

UWE-MVS		94.30 348	93.89 342	95.53 387	97.83 304	88.95 454	97.52 388	93.25 504	94.44 265	96.63 254	97.07 368	78.70 430	99.28 228	91.99 375	97.56 258	98.36 301

thres600view7		95.49 258	94.77 278	97.67 224	98.98 141	95.02 260	98.85 148	96.90 443	95.38 195	96.63 254	96.90 393	84.29 370	99.59 169	88.65 438	96.33 299	98.40 298

thres100view900		95.38 268	94.70 283	97.41 244	98.98 141	94.92 269	98.87 135	96.90 443	95.38 195	96.61 256	96.88 394	84.29 370	99.56 176	88.11 442	96.29 303	97.76 322

Vis-MVSNet (Re-imp)		96.87 186	96.55 189	97.83 204	98.73 163	95.46 230	99.20 48	98.30 280	94.96 230	96.60 257	98.87 178	90.05 226	98.59 353	93.67 318	98.60 182	99.46 122

CVMVSNet		95.43 264	96.04 213	93.57 446	97.93 298	83.62 491	98.12 319	98.59 173	95.68 168	96.56 258	99.02 149	87.51 305	97.51 459	93.56 322	97.44 264	99.60 93

RPSCF		94.87 309	95.40 242	93.26 452	98.89 148	82.06 498	98.33 277	98.06 335	90.30 430	96.56 258	99.26 81	87.09 313	99.49 193	93.82 313	96.32 300	98.24 305

tfpn200view9		95.32 275	94.62 287	97.43 242	98.94 145	94.98 265	98.68 203	96.93 441	95.33 199	96.55 260	96.53 413	84.23 374	99.56 176	88.11 442	96.29 303	97.76 322

thres400		95.38 268	94.62 287	97.65 228	98.94 145	94.98 265	98.68 203	96.93 441	95.33 199	96.55 260	96.53 413	84.23 374	99.56 176	88.11 442	96.29 303	98.40 298

thres200		95.25 278	94.57 290	97.28 250	98.81 159	94.92 269	98.20 300	97.11 424	95.24 207	96.54 262	96.22 428	84.58 367	99.53 185	87.93 448	96.50 294	97.39 336

ab-mvs		96.42 210	95.71 231	98.55 109	98.63 180	96.75 139	97.88 355	98.74 131	93.84 294	96.54 262	98.18 267	85.34 349	99.75 134	95.93 224	96.35 298	99.15 203

Anonymous202405211		95.28 277	94.49 294	97.67 224	99.00 137	93.75 322	98.70 197	97.04 431	90.66 421	96.49 264	98.80 189	78.13 436	99.83 92	96.21 216	95.36 325	99.44 127

ADS-MVSNet2		94.58 327	94.40 304	95.11 402	98.00 285	88.74 458	96.04 470	97.30 407	90.15 431	96.47 265	96.64 410	87.89 296	97.56 457	90.08 412	97.06 272	99.02 231

ADS-MVSNet		95.00 294	94.45 300	96.63 309	98.00 285	91.91 389	96.04 470	97.74 361	90.15 431	96.47 265	96.64 410	87.89 296	98.96 308	90.08 412	97.06 272	99.02 231

Effi-MVS+-dtu		96.29 218	96.56 188	95.51 388	97.89 302	90.22 427	98.80 165	98.10 323	96.57 118	96.45 267	96.66 407	90.81 200	98.91 317	95.72 235	97.99 238	97.40 335

ETVMVS		94.50 335	93.44 369	97.68 222	98.18 258	95.35 242	98.19 303	97.11 424	93.73 302	96.40 268	95.39 456	74.53 470	98.84 327	91.10 394	96.31 301	98.84 251

PLC	95.07 4	97.20 166	96.78 175	98.44 127	99.29 90	96.31 167	98.14 316	98.76 127	92.41 371	96.39 269	98.31 254	94.92 88	99.78 126	94.06 306	98.77 174	99.23 187
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		94.13 362	93.80 348	95.12 401	96.50 402	87.91 472	97.44 392	95.89 475	92.62 362	96.37 270	96.30 423	84.13 377	98.30 392	93.24 329	91.66 383	99.14 206

TAPA-MVS	93.98 7	95.35 272	94.56 291	97.74 215	99.13 121	94.83 274	98.33 277	98.64 160	86.62 470	96.29 271	98.61 217	94.00 107	99.29 226	80.00 491	99.41 130	99.09 218
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FBQ-MVS		94.89 308	94.10 323	97.26 251	98.07 272	93.75 322	98.48 255	97.26 412	94.51 259	96.28 272	95.64 453	76.88 454	99.07 284	93.29 328	96.47 296	98.96 239

dtuonly		95.08 291	95.10 264	95.02 406	96.53 399	87.27 477	96.33 468	97.21 417	93.41 327	96.28 272	98.51 232	87.71 300	98.99 303	91.88 379	98.01 237	98.80 255

myMVS_eth3d28		95.12 286	94.62 287	96.64 308	98.17 262	92.17 379	98.02 334	97.32 404	95.41 193	96.22 274	96.05 434	78.01 438	99.13 270	95.22 258	97.16 269	98.60 284

baseline1		95.84 240	95.12 262	98.01 185	98.49 193	95.98 182	98.73 188	97.03 432	95.37 197	96.22 274	98.19 266	89.96 229	99.16 261	94.60 283	87.48 438	98.90 245

tpm2		94.19 357	93.76 353	95.46 391	97.23 355	89.04 451	97.31 408	96.85 449	87.08 463	96.21 276	96.79 401	83.75 386	98.74 338	92.43 366	96.23 311	98.59 287

UBG		95.32 275	94.72 282	97.13 261	98.05 278	93.26 350	97.87 356	97.20 420	94.96 230	96.18 277	95.66 452	80.97 409	99.35 214	94.47 289	97.08 271	98.78 260

F-COLMAP		97.09 175	96.80 171	97.97 193	99.45 62	94.95 268	98.55 239	98.62 165	93.02 346	96.17 278	98.58 223	94.01 106	99.81 104	93.95 308	98.90 163	99.14 206

GeoE		96.58 204	96.07 211	98.10 171	98.35 214	95.89 201	99.34 17	98.12 317	93.12 342	96.09 279	98.87 178	89.71 236	98.97 304	92.95 340	98.08 235	99.43 131

JIA-IIPM		93.35 382	92.49 392	95.92 367	96.48 404	90.65 415	95.01 488	96.96 439	85.93 476	96.08 280	87.33 516	87.70 303	98.78 336	91.35 390	95.58 323	98.34 302

BH-RMVSNet		95.92 236	95.32 252	97.69 220	98.32 226	94.64 281	98.19 303	97.45 394	94.56 254	96.03 281	98.61 217	85.02 354	99.12 273	90.68 405	99.06 153	99.30 165

dp		94.15 361	93.90 340	94.90 411	97.31 351	86.82 479	96.97 436	97.19 421	91.22 413	96.02 282	96.61 412	85.51 345	99.02 299	90.00 416	94.30 328	98.85 249

EPNet		97.28 158	96.87 166	98.51 116	94.98 458	96.14 174	98.90 121	97.02 435	98.28 22	95.99 283	99.11 126	91.36 174	99.89 70	96.98 175	99.19 149	99.50 108
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LS3D		97.16 170	96.66 184	98.68 96	98.53 188	97.19 118	98.93 115	98.90 73	92.83 355	95.99 283	99.37 57	92.12 144	99.87 81	93.67 318	99.57 100	98.97 236

SDMVSNet		96.85 187	96.42 195	98.14 160	99.30 85	96.38 161	99.21 45	99.23 27	95.92 153	95.96 285	98.76 203	85.88 338	99.44 205	97.93 100	95.59 321	98.60 284

sd_testset		96.17 223	95.76 226	97.42 243	99.30 85	94.34 298	98.82 156	99.08 45	95.92 153	95.96 285	98.76 203	82.83 391	99.32 218	95.56 243	95.59 321	98.60 284

AUN-MVS		94.53 332	93.73 355	96.92 283	98.50 189	93.52 333	98.34 276	98.10 323	93.83 296	95.94 287	97.98 284	85.59 344	99.03 294	94.35 292	80.94 480	98.22 307

testing222		94.12 364	93.03 379	97.37 249	98.02 283	94.66 279	97.94 344	96.65 459	94.63 251	95.78 288	95.76 443	71.49 480	98.92 315	91.17 393	95.88 318	98.52 292

TR-MVS		94.94 306	94.20 314	97.17 258	97.75 310	94.14 310	97.59 383	97.02 435	92.28 377	95.75 289	97.64 320	83.88 382	98.96 308	89.77 418	96.15 313	98.40 298

WB-MVSnew		94.19 357	94.04 326	94.66 423	96.82 384	92.14 380	97.86 358	95.96 472	93.50 322	95.64 290	96.77 402	88.06 292	97.99 429	84.87 470	96.86 278	93.85 493

MonoMVSNet		95.51 257	95.45 241	95.68 381	95.54 445	90.87 408	98.92 118	97.37 401	95.79 162	95.53 291	97.38 342	89.58 239	97.68 450	96.40 209	92.59 369	98.49 294

VPA-MVSNet		95.75 245	95.11 263	97.69 220	97.24 354	97.27 108	98.94 108	99.23 27	95.13 214	95.51 292	97.32 347	85.73 340	98.91 317	97.33 164	89.55 412	96.89 362

testing91		94.98 298	94.25 312	97.20 254	97.94 296	93.41 337	98.00 337	97.58 373	94.99 226	95.45 293	96.04 436	77.20 448	99.42 207	94.97 264	96.02 316	98.78 260

testing99		94.83 310	94.08 324	97.07 268	97.94 296	93.13 356	98.10 325	97.17 422	94.86 236	95.34 294	96.00 440	76.31 457	99.40 209	95.08 261	95.90 317	98.68 275

HQP_MVS		96.14 225	95.90 221	96.85 287	97.42 343	94.60 287	98.80 165	98.56 184	97.28 70	95.34 294	98.28 256	87.09 313	99.03 294	96.07 217	94.27 329	96.92 354

plane_prior3						94.61 285			97.02 90	95.34 294

testing11		95.00 294	94.28 308	97.16 259	97.96 295	93.36 343	98.09 326	97.06 430	94.94 234	95.33 297	96.15 430	76.89 453	99.40 209	95.77 234	96.30 302	98.72 268

Fast-Effi-MVS+		96.28 220	95.70 233	98.03 181	98.29 232	95.97 187	98.58 226	98.25 292	91.74 391	95.29 298	97.23 354	91.03 194	99.15 265	92.90 342	97.96 240	98.97 236

test_fmvs2		93.43 380	93.58 362	92.95 459	96.97 373	83.91 490	99.19 50	97.24 414	95.74 164	95.20 299	98.27 259	69.65 482	98.72 340	96.26 213	93.73 346	96.24 438

EI-MVSNet		95.96 230	95.83 223	96.36 342	97.93 298	93.70 327	98.12 319	98.27 283	93.70 307	95.07 300	99.02 149	92.23 139	98.54 356	94.68 276	93.46 352	96.84 369

MVSTER		96.06 227	95.72 228	97.08 267	98.23 245	95.93 193	98.73 188	98.27 283	94.86 236	95.07 300	98.09 273	88.21 286	98.54 356	96.59 200	93.46 352	96.79 373

OPM-MVS		95.69 250	95.33 251	96.76 294	96.16 419	94.63 282	98.43 266	98.39 244	96.64 114	95.02 302	98.78 195	85.15 353	99.05 288	95.21 259	94.20 332	96.60 399
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+-dtu		95.87 238	95.85 222	95.91 368	97.74 313	91.74 393	98.69 200	98.15 313	95.56 176	94.92 303	97.68 315	88.98 264	98.79 335	93.19 331	97.78 247	97.20 342

TESTMET0.1,1		94.18 360	93.69 358	95.63 384	96.92 376	89.12 449	96.91 442	94.78 490	93.17 338	94.88 304	96.45 417	78.52 431	98.92 315	93.09 334	98.50 193	98.85 249

VPNet		94.99 296	94.19 315	97.40 246	97.16 363	96.57 151	98.71 193	98.97 57	95.67 169	94.84 305	98.24 263	80.36 416	98.67 345	96.46 206	87.32 442	96.96 349

1112_ss		96.63 200	96.00 217	98.50 119	98.56 184	96.37 162	98.18 309	98.10 323	92.92 350	94.84 305	98.43 237	92.14 143	99.58 172	94.35 292	96.51 293	99.56 101

test-LLR		95.10 288	94.87 276	95.80 376	96.77 386	89.70 437	96.91 442	95.21 482	95.11 216	94.83 307	95.72 448	87.71 300	98.97 304	93.06 335	98.50 193	98.72 268

test-mter		94.08 368	93.51 366	95.80 376	96.77 386	89.70 437	96.91 442	95.21 482	92.89 352	94.83 307	95.72 448	77.69 442	98.97 304	93.06 335	98.50 193	98.72 268

Test_1112_low_res		96.34 215	95.66 236	98.36 135	98.56 184	95.94 190	97.71 373	98.07 330	92.10 383	94.79 309	97.29 349	91.75 157	99.56 176	94.17 301	96.50 294	99.58 99

UWE-MVS-28		92.79 396	92.51 391	93.62 445	96.46 405	86.28 481	97.93 345	92.71 509	94.17 273	94.78 310	97.16 358	81.05 408	96.43 482	81.45 485	96.86 278	98.14 312

GA-MVS		94.81 311	94.03 328	97.14 260	97.15 364	93.86 317	96.76 456	97.58 373	94.00 284	94.76 311	97.04 376	80.91 410	98.48 360	91.79 381	96.25 309	99.09 218

nomal-1		94.97 300	94.34 306	96.86 286	97.79 307	92.62 372	98.19 303	96.71 455	93.89 290	94.74 312	96.05 434	79.44 424	99.09 280	95.58 242	96.68 286	98.86 248

BH-untuned		95.95 231	95.72 228	96.65 304	98.55 186	92.26 378	98.23 294	97.79 358	93.73 302	94.62 313	98.01 280	88.97 265	99.00 302	93.04 337	98.51 192	98.68 275

test_djsdf		96.00 229	95.69 234	96.93 280	95.72 439	95.49 228	99.47 7	98.40 238	94.98 228	94.58 314	97.86 295	89.16 255	98.41 376	96.91 180	94.12 337	96.88 363

cascas		94.63 323	93.86 344	96.93 280	96.91 378	94.27 302	96.00 473	98.51 196	85.55 481	94.54 315	96.23 426	84.20 376	98.87 324	95.80 232	96.98 277	97.66 328

DP-MVS		96.59 202	95.93 220	98.57 106	99.34 73	96.19 172	98.70 197	98.39 244	89.45 444	94.52 316	99.35 63	91.85 153	99.85 86	92.89 344	98.88 165	99.68 76

gg-mvs-nofinetune		92.21 404	90.58 413	97.13 261	96.75 389	95.09 257	95.85 474	89.40 519	85.43 482	94.50 317	81.98 523	80.80 413	98.40 382	92.16 368	98.33 219	97.88 319

mvs_anonymous		96.70 197	96.53 192	97.18 257	98.19 252	93.78 319	98.31 282	98.19 301	94.01 283	94.47 318	98.27 259	92.08 147	98.46 364	97.39 161	97.91 241	99.31 160

HQP-NCC					97.20 358		98.05 330		96.43 123	94.45 319

ACMP_Plane					97.20 358		98.05 330		96.43 123	94.45 319

HQP4-MVS										94.45 319			98.96 308			96.87 366

HQP-MVS		95.72 246	95.40 242	96.69 301	97.20 358	94.25 304	98.05 330	98.46 209	96.43 123	94.45 319	97.73 307	86.75 319	98.96 308	95.30 252	94.18 333	96.86 368

MSDG		95.93 235	95.30 254	97.83 204	98.90 147	95.36 240	96.83 454	98.37 253	91.32 407	94.43 323	98.73 205	90.27 222	99.60 168	90.05 414	98.82 172	98.52 292

dmvs_re		94.48 338	94.18 317	95.37 394	97.68 317	90.11 429	98.54 241	97.08 426	94.56 254	94.42 324	97.24 353	84.25 372	97.76 447	91.02 401	92.83 366	98.24 305

nrg030		96.28 220	95.72 228	97.96 195	96.90 379	98.15 66	99.39 11	98.31 273	95.47 188	94.42 324	98.35 247	92.09 146	98.69 341	97.50 148	89.05 421	97.04 345

CLD-MVS		95.62 253	95.34 248	96.46 334	97.52 334	93.75 322	97.27 411	98.46 209	95.53 184	94.42 324	98.00 281	86.21 332	98.97 304	96.25 215	94.37 327	96.66 391
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LPG-MVS_test		95.62 253	95.34 248	96.47 331	97.46 338	93.54 330	98.99 94	98.54 188	94.67 249	94.36 327	98.77 198	85.39 346	99.11 275	95.71 236	94.15 335	96.76 376

LGP-MVS_train				96.47 331	97.46 338	93.54 330		98.54 188	94.67 249	94.36 327	98.77 198	85.39 346	99.11 275	95.71 236	94.15 335	96.76 376

v144192		94.39 344	93.70 357	96.48 330	96.06 423	94.35 297	98.58 226	98.16 312	91.45 400	94.33 329	97.02 379	87.50 307	98.45 365	91.08 397	89.11 420	96.63 393

IMVS_0404		95.82 242	95.52 238	96.73 295	97.99 287	92.82 366	97.23 412	98.27 283	95.16 209	94.31 330	98.79 191	85.63 342	98.10 410	94.74 271	97.54 259	99.27 176

V42		94.78 313	94.14 320	96.70 300	96.33 411	95.22 249	98.97 98	98.09 327	92.32 375	94.31 330	97.06 372	88.39 281	98.55 355	92.90 342	88.87 425	96.34 433

VortexMVS		95.95 231	95.79 224	96.42 337	98.29 232	93.96 314	98.68 203	98.31 273	96.02 147	94.29 332	97.57 326	89.47 242	98.37 383	97.51 147	91.93 377	96.94 352

ACMM	93.85 9	95.69 250	95.38 246	96.61 312	97.61 323	93.84 318	98.91 120	98.44 218	95.25 205	94.28 333	98.47 235	86.04 337	99.12 273	95.50 246	93.95 342	96.87 366
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS-LS		95.46 260	95.21 257	96.22 350	98.12 267	93.72 326	98.32 281	98.13 316	93.71 305	94.26 334	97.31 348	92.24 138	98.10 410	94.63 279	90.12 403	96.84 369
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		94.20 356	93.47 368	96.40 340	95.98 427	94.08 311	98.52 242	98.15 313	91.33 406	94.25 335	97.20 357	86.41 327	98.42 369	90.04 415	89.39 417	96.69 390

BH-w/o		95.38 268	95.08 265	96.26 349	98.34 219	91.79 390	97.70 374	97.43 396	92.87 353	94.24 336	97.22 355	88.66 273	98.84 327	91.55 388	97.70 252	98.16 311

XVG-ACMP-BASELINE		94.54 330	94.14 320	95.75 380	96.55 398	91.65 395	98.11 323	98.44 218	94.96 230	94.22 337	97.90 291	79.18 427	99.11 275	94.05 307	93.85 344	96.48 427

v1144		94.59 326	93.92 337	96.60 314	96.21 413	94.78 278	98.59 222	98.14 315	91.86 390	94.21 338	97.02 379	87.97 294	98.41 376	91.72 383	89.57 410	96.61 397

v1192		94.32 347	93.58 362	96.53 324	96.10 421	94.45 291	98.50 250	98.17 310	91.54 398	94.19 339	97.06 372	86.95 317	98.43 368	90.14 410	89.57 410	96.70 385

PAPM		94.95 304	94.00 332	97.78 209	97.04 369	95.65 218	96.03 472	98.25 292	91.23 412	94.19 339	97.80 304	91.27 179	98.86 326	82.61 481	97.61 254	98.84 251

Patchmatch-test		94.42 342	93.68 359	96.63 309	97.60 324	91.76 391	94.83 494	97.49 388	89.45 444	94.14 341	97.10 361	88.99 261	98.83 330	85.37 467	98.13 233	99.29 168

v1240		94.06 370	93.29 374	96.34 344	96.03 425	93.90 316	98.44 264	98.17 310	91.18 415	94.13 342	97.01 381	86.05 335	98.42 369	89.13 432	89.50 414	96.70 385

GBi-Net		94.49 336	93.80 348	96.56 319	98.21 248	95.00 261	98.82 156	98.18 304	92.46 366	94.09 343	97.07 368	81.16 405	97.95 431	92.08 370	92.14 374	96.72 381

test1		94.49 336	93.80 348	96.56 319	98.21 248	95.00 261	98.82 156	98.18 304	92.46 366	94.09 343	97.07 368	81.16 405	97.95 431	92.08 370	92.14 374	96.72 381

FMVSNet3		94.97 300	94.26 311	97.11 265	98.18 258	96.62 143	98.56 238	98.26 291	93.67 312	94.09 343	97.10 361	84.25 372	98.01 426	92.08 370	92.14 374	96.70 385

MIMVSNet		93.26 386	92.21 397	96.41 338	97.73 314	93.13 356	95.65 479	97.03 432	91.27 411	94.04 346	96.06 433	75.33 463	97.19 464	86.56 457	96.23 311	98.92 243

FIs		96.51 207	96.12 210	97.67 224	97.13 365	97.54 90	99.36 14	99.22 32	95.89 155	94.03 347	98.35 247	91.98 149	98.44 367	96.40 209	92.76 367	97.01 346

v2v482		94.69 316	94.03 328	96.65 304	96.17 417	94.79 277	98.67 208	98.08 328	92.72 357	94.00 348	97.16 358	87.69 304	98.45 365	92.91 341	88.87 425	96.72 381

testing3		93.19 389	92.48 393	95.30 397	98.07 272	92.27 376	98.64 213	97.17 422	93.94 289	93.98 349	97.04 376	67.97 487	96.01 488	88.40 440	97.14 270	97.63 329

FC-MVSNet-test		96.42 210	96.05 212	97.53 236	96.95 374	97.27 108	99.36 14	99.23 27	95.83 160	93.93 350	98.37 245	92.00 148	98.32 388	96.02 222	92.72 368	97.00 347

UniMVSNet (Re)		95.78 244	95.19 258	97.58 233	96.99 372	97.47 94	98.79 173	99.18 36	95.60 172	93.92 351	97.04 376	91.68 159	98.48 360	95.80 232	87.66 437	96.79 373

miper_enhance_ethall		95.10 288	94.75 280	96.12 354	97.53 333	93.73 325	96.61 461	98.08 328	92.20 381	93.89 352	96.65 409	92.44 129	98.30 392	94.21 298	91.16 389	96.34 433

UniMVSNet_NR-MVSNet		95.71 247	95.15 259	97.40 246	96.84 382	96.97 128	98.74 182	99.24 20	95.16 209	93.88 353	97.72 309	91.68 159	98.31 390	95.81 230	87.25 443	96.92 354

DU-MVS		95.42 265	94.76 279	97.40 246	96.53 399	96.97 128	98.66 210	98.99 56	95.43 190	93.88 353	97.69 312	88.57 275	98.31 390	95.81 230	87.25 443	96.92 354

usedtu_dtu_shiyan1		94.96 302	94.28 308	96.98 275	95.93 430	96.11 176	97.08 430	98.39 244	93.62 316	93.86 355	96.40 419	88.28 283	98.21 399	92.61 353	92.36 372	96.63 393

FE-MVSNET3		94.96 302	94.28 308	96.98 275	95.93 430	96.11 176	97.08 430	98.39 244	93.62 316	93.86 355	96.40 419	88.28 283	98.21 399	92.61 353	92.36 372	96.63 393

Baseline_NR-MVSNet		94.35 345	93.81 347	95.96 366	96.20 414	94.05 312	98.61 221	96.67 457	91.44 401	93.85 357	97.60 323	88.57 275	98.14 406	94.39 290	86.93 446	95.68 455

PS-MVSNAJss		96.43 209	96.26 204	96.92 283	95.84 436	95.08 258	99.16 56	98.50 201	95.87 158	93.84 358	98.34 251	94.51 93	98.61 349	96.88 186	93.45 354	97.06 344

UniMVSNet_ETH3D		94.24 354	93.33 372	96.97 277	97.19 361	93.38 341	98.74 182	98.57 180	91.21 414	93.81 359	98.58 223	72.85 479	98.77 337	95.05 262	93.93 343	98.77 263

tt0805		94.54 330	93.85 345	96.63 309	97.98 293	93.06 361	98.77 177	97.84 349	93.67 312	93.80 360	98.04 277	76.88 454	98.96 308	94.79 270	92.86 365	97.86 321

tpmvs		94.60 324	94.36 305	95.33 396	97.46 338	88.60 460	96.88 450	97.68 362	91.29 409	93.80 360	96.42 418	88.58 274	99.24 243	91.06 398	96.04 315	98.17 310

WBMVS		94.56 328	94.04 326	96.10 355	98.03 282	93.08 360	97.82 364	98.18 304	94.02 280	93.77 362	96.82 399	81.28 404	98.34 385	95.47 248	91.00 392	96.88 363

3Dnovator	94.51 5	97.46 136	96.93 163	99.07 66	97.78 308	97.64 84	99.35 16	99.06 47	97.02 90	93.75 363	99.16 111	89.25 252	99.92 44	97.22 168	99.75 55	99.64 87

eth_miper_zixun_eth		94.68 318	94.41 303	95.47 390	97.64 321	91.71 394	96.73 458	98.07 330	92.71 358	93.64 364	97.21 356	90.54 211	98.17 403	93.38 324	89.76 407	96.54 413

SD_0403		94.28 352	94.46 297	93.73 443	98.02 283	85.32 486	98.31 282	98.40 238	94.75 244	93.59 365	98.16 268	89.01 260	96.54 479	82.32 482	97.58 257	99.34 151

ITE_SJBPF				95.44 392	97.42 343	91.32 400		97.50 386	95.09 219	93.59 365	98.35 247	81.70 400	98.88 323	89.71 420	93.39 356	96.12 443

TranMVSNet+NR-MVSNet		95.14 285	94.48 295	97.11 265	96.45 406	96.36 163	99.03 83	99.03 50	95.04 221	93.58 367	97.93 288	88.27 285	98.03 424	94.13 302	86.90 448	96.95 351

COLMAP_ROB	93.27 12	95.33 274	94.87 276	96.71 298	99.29 90	93.24 353	98.58 226	98.11 320	89.92 435	93.57 368	99.10 128	86.37 328	99.79 123	90.78 403	98.10 234	97.09 343
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tpm cat1		93.36 381	92.80 383	95.07 405	97.58 326	87.97 471	96.76 456	97.86 348	82.17 492	93.53 369	96.04 436	86.13 333	99.13 270	89.24 430	95.87 319	98.10 313

AllTest		95.24 279	94.65 286	96.99 272	99.25 98	93.21 354	98.59 222	98.18 304	91.36 403	93.52 370	98.77 198	84.67 364	99.72 139	89.70 421	97.87 243	98.02 316

TestCases				96.99 272	99.25 98	93.21 354		98.18 304	91.36 403	93.52 370	98.77 198	84.67 364	99.72 139	89.70 421	97.87 243	98.02 316

miper_ehance_all_eth		95.01 293	94.69 284	95.97 365	97.70 316	93.31 346	97.02 434	98.07 330	92.23 378	93.51 372	96.96 386	91.85 153	98.15 405	93.68 316	91.16 389	96.44 430

SSC-MVS3.2		93.59 379	93.13 377	94.97 408	96.81 385	89.71 436	97.95 341	98.49 206	94.59 253	93.50 373	96.91 392	77.74 441	98.37 383	91.69 384	90.47 398	96.83 371

FMVSNet2		94.47 339	93.61 361	97.04 270	98.21 248	96.43 158	98.79 173	98.27 283	92.46 366	93.50 373	97.09 365	81.16 405	98.00 428	91.09 395	91.93 377	96.70 385

v148		94.29 350	93.76 353	95.91 368	96.10 421	92.93 364	98.58 226	97.97 340	92.59 364	93.47 375	96.95 388	88.53 279	98.32 388	92.56 360	87.06 445	96.49 425

c3_l		94.79 312	94.43 302	95.89 370	97.75 310	93.12 358	97.16 426	98.03 337	92.23 378	93.46 376	97.05 375	91.39 173	98.01 426	93.58 321	89.21 419	96.53 415

Syy-MVS		92.55 400	92.61 388	92.38 462	97.39 347	83.41 492	97.91 348	97.46 390	93.16 339	93.42 377	95.37 457	84.75 361	96.12 486	77.00 503	96.99 274	97.60 330

myMVS_eth3d		92.73 397	92.01 399	94.89 412	97.39 347	90.94 406	97.91 348	97.46 390	93.16 339	93.42 377	95.37 457	68.09 486	96.12 486	88.34 441	96.99 274	97.60 330

pmmvs4		94.69 316	93.99 334	96.81 290	95.74 438	95.94 190	97.40 396	97.67 365	90.42 427	93.37 379	97.59 324	89.08 258	98.20 401	92.97 339	91.67 382	96.30 436

PCF-MVS	93.45 11	94.68 318	93.43 370	98.42 131	98.62 181	96.77 138	95.48 483	98.20 298	84.63 485	93.34 380	98.32 253	88.55 278	99.81 104	84.80 473	98.96 161	98.68 275
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
cl22		94.68 318	94.19 315	96.13 353	98.11 268	93.60 328	96.94 438	98.31 273	92.43 370	93.32 381	96.87 396	86.51 322	98.28 396	94.10 305	91.16 389	96.51 422

XXY-MVS		95.20 282	94.45 300	97.46 239	96.75 389	96.56 152	98.86 143	98.65 159	93.30 333	93.27 382	98.27 259	84.85 358	98.87 324	94.82 268	91.26 388	96.96 349

jajsoiax		95.45 262	95.03 267	96.73 295	95.42 453	94.63 282	99.14 60	98.52 193	95.74 164	93.22 383	98.36 246	83.87 383	98.65 346	96.95 178	94.04 338	96.91 359

reproduce_monomvs		94.77 314	94.67 285	95.08 404	98.40 206	89.48 443	98.80 165	98.64 160	97.57 49	93.21 384	97.65 317	80.57 415	98.83 330	97.72 118	89.47 415	96.93 353

mvs_tets		95.41 267	95.00 268	96.65 304	95.58 444	94.42 293	99.00 91	98.55 186	95.73 166	93.21 384	98.38 244	83.45 389	98.63 347	97.09 171	94.00 340	96.91 359

anonymousdsp		95.42 265	94.91 273	96.94 279	95.10 457	95.90 196	99.14 60	98.41 235	93.75 299	93.16 386	97.46 333	87.50 307	98.41 376	95.63 241	94.03 339	96.50 424

v8		94.47 339	93.77 351	96.57 318	96.36 409	94.83 274	99.05 76	98.19 301	91.92 387	93.16 386	96.97 384	88.82 272	98.48 360	91.69 384	87.79 434	96.39 431

WR-MVS		95.15 284	94.46 297	97.22 253	96.67 394	96.45 156	98.21 296	98.81 109	94.15 274	93.16 386	97.69 312	87.51 305	98.30 392	95.29 254	88.62 427	96.90 361

EPNet_dtu		95.21 281	94.95 272	95.99 361	96.17 417	90.45 421	98.16 312	97.27 411	96.77 104	93.14 389	98.33 252	90.34 219	98.42 369	85.57 464	98.81 173	99.09 218
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
QAPM		96.29 218	95.40 242	98.96 77	97.85 303	97.60 87	99.23 38	98.93 65	89.76 438	93.11 390	99.02 149	89.11 257	99.93 35	91.99 375	99.62 91	99.34 151

GG-mvs-BLEND				96.59 315	96.34 410	94.98 265	96.51 465	88.58 521		93.10 391	94.34 473	80.34 418	98.05 422	89.53 424	96.99 274	96.74 378

v10		94.29 350	93.55 364	96.51 326	96.39 408	94.80 276	98.99 94	98.19 301	91.35 405	93.02 392	96.99 382	88.09 290	98.41 376	90.50 407	88.41 429	96.33 435

3Dnovator+	94.38 6	97.43 141	96.78 175	99.38 25	97.83 304	98.52 36	99.37 13	98.71 139	97.09 88	92.99 393	99.13 119	89.36 249	99.89 70	96.97 176	99.57 100	99.71 64

D2MVS		95.18 283	95.08 265	95.48 389	97.10 367	92.07 386	98.30 285	99.13 43	94.02 280	92.90 394	96.73 403	89.48 241	98.73 339	94.48 288	93.60 351	95.65 456

Patchmtry		93.22 387	92.35 395	95.84 375	96.77 386	93.09 359	94.66 497	97.56 376	87.37 462	92.90 394	96.24 424	88.15 288	97.90 435	87.37 452	90.10 404	96.53 415

DIV-MVS_self_test		94.52 333	94.03 328	95.99 361	97.57 330	93.38 341	97.05 432	97.94 343	91.74 391	92.81 396	97.10 361	89.12 256	98.07 418	92.60 356	90.30 400	96.53 415

Anonymous20231211		94.10 366	93.26 375	96.61 312	99.11 125	94.28 301	99.01 89	98.88 78	86.43 472	92.81 396	97.57 326	81.66 401	98.68 344	94.83 267	89.02 423	96.88 363

cl____		94.51 334	94.01 331	96.02 357	97.58 326	93.40 340	97.05 432	97.96 342	91.73 393	92.76 398	97.08 367	89.06 259	98.13 407	92.61 353	90.29 401	96.52 418

miper_lstm_enhance		94.33 346	94.07 325	95.11 402	97.75 310	90.97 405	97.22 414	98.03 337	91.67 395	92.76 398	96.97 384	90.03 228	97.78 445	92.51 363	89.64 409	96.56 410

v7n		94.19 357	93.43 370	96.47 331	95.90 433	94.38 296	99.26 33	98.34 262	91.99 385	92.76 398	97.13 360	88.31 282	98.52 358	89.48 426	87.70 435	96.52 418

MVS		94.67 321	93.54 365	98.08 173	96.88 380	96.56 152	98.19 303	98.50 201	78.05 503	92.69 401	98.02 278	91.07 193	99.63 162	90.09 411	98.36 216	98.04 315

DSMNet-mixed		92.52 402	92.58 390	92.33 463	94.15 469	82.65 496	98.30 285	94.26 497	89.08 450	92.65 402	95.73 446	85.01 355	95.76 490	86.24 459	97.76 249	98.59 287

EU-MVSNet		93.66 375	94.14 320	92.25 466	95.96 429	83.38 493	98.52 242	98.12 317	94.69 247	92.61 403	98.13 271	87.36 311	96.39 484	91.82 380	90.00 405	96.98 348

IterMVS-SCA-FT		94.11 365	93.87 343	94.85 415	97.98 293	90.56 420	97.18 421	98.11 320	93.75 299	92.58 404	97.48 332	83.97 380	97.41 461	92.48 365	91.30 386	96.58 406

pmmvs5		93.65 377	92.97 381	95.68 381	95.49 448	92.37 375	98.20 300	97.28 410	89.66 440	92.58 404	97.26 350	82.14 395	98.09 414	93.18 332	90.95 393	96.58 406

blended_shiyan8		91.42 409	89.89 422	96.01 358	91.50 496	93.30 347	97.48 390	97.83 350	86.93 465	92.57 406	92.37 494	82.46 393	98.13 407	92.86 347	74.99 501	96.61 397

WR-MVS_H		95.05 292	94.46 297	96.81 290	96.86 381	95.82 209	99.24 36	99.24 20	93.87 293	92.53 407	96.84 398	90.37 218	98.24 398	93.24 329	87.93 433	96.38 432

ACMP	93.49 10	95.34 273	94.98 270	96.43 336	97.67 318	93.48 334	98.73 188	98.44 218	94.94 234	92.53 407	98.53 228	84.50 369	99.14 268	95.48 247	94.00 340	96.66 391
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test0.0.03 1		94.08 368	93.51 366	95.80 376	95.53 447	92.89 365	97.38 398	95.97 471	95.11 216	92.51 409	96.66 407	87.71 300	96.94 469	87.03 454	93.67 347	97.57 332

IB-MVS	91.98 17	93.27 385	91.97 400	97.19 256	97.47 337	93.41 337	97.09 429	95.99 470	93.32 331	92.47 410	95.73 446	78.06 437	99.53 185	94.59 285	82.98 468	98.62 282
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
IterMVS		94.09 367	93.85 345	94.80 419	97.99 287	90.35 425	97.18 421	98.12 317	93.68 310	92.46 411	97.34 344	84.05 378	97.41 461	92.51 363	91.33 385	96.62 396
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
blended_shiyan6		91.37 410	89.84 423	95.98 364	91.49 497	93.28 348	97.48 390	97.83 350	86.93 465	92.43 412	92.36 495	82.44 394	98.06 419	92.74 352	74.82 504	96.59 402

CP-MVSNet		94.94 306	94.30 307	96.83 288	96.72 391	95.56 223	99.11 66	98.95 61	93.89 290	92.42 413	97.90 291	87.19 312	98.12 409	94.32 294	88.21 430	96.82 372

wanda-best-256-512		91.17 417	89.60 427	95.88 371	91.33 500	92.99 362	96.89 447	97.82 353	86.89 468	92.36 414	91.75 501	81.83 397	98.06 419	92.75 349	74.82 504	96.59 402

FE-blended-shiyan7		91.17 417	89.60 427	95.88 371	91.33 500	92.99 362	96.89 447	97.82 353	86.89 468	92.36 414	91.75 501	81.83 397	98.06 419	92.75 349	74.82 504	96.59 402

usedtu_blend_shiyan5		90.87 427	89.15 434	96.01 358	91.33 500	93.35 344	98.12 319	97.36 402	81.93 494	92.36 414	91.75 501	81.83 397	98.09 414	92.88 345	74.82 504	96.59 402

PS-CasMVS		94.67 321	93.99 334	96.71 298	96.68 393	95.26 246	99.13 63	99.03 50	93.68 310	92.33 417	97.95 286	85.35 348	98.10 410	93.59 320	88.16 432	96.79 373

FMVSNet1		93.19 389	92.07 398	96.56 319	97.54 331	95.00 261	98.82 156	98.18 304	90.38 428	92.27 418	97.07 368	73.68 476	97.95 431	89.36 428	91.30 386	96.72 381

blend_shiyan4		90.76 428	89.01 437	95.99 361	91.69 495	93.35 344	97.44 392	97.83 350	86.93 465	92.23 419	91.98 498	75.19 465	98.09 414	92.88 345	74.96 502	96.52 418

PEN-MVS		94.42 342	93.73 355	96.49 328	96.28 412	94.84 272	99.17 55	99.00 53	93.51 321	92.23 419	97.83 301	86.10 334	97.90 435	92.55 361	86.92 447	96.74 378

sc_t1		91.01 422	89.39 429	95.85 374	95.99 426	90.39 424	98.43 266	97.64 368	78.79 500	92.20 421	97.94 287	66.00 493	98.60 352	91.59 387	85.94 456	98.57 290

gbinet_0.2-2-1-0.02		91.03 421	89.37 433	96.01 358	91.39 498	93.41 337	97.19 419	97.82 353	87.00 464	92.18 422	91.87 500	78.97 428	98.04 423	93.13 333	74.75 508	96.60 399

OurMVSNet-221017-0		94.21 355	94.00 332	94.85 415	95.60 443	89.22 448	98.89 125	97.43 396	95.29 202	92.18 422	98.52 231	82.86 390	98.59 353	93.46 323	91.76 380	96.74 378

MS-PatchMatch		93.84 374	93.63 360	94.46 433	96.18 416	89.45 444	97.76 369	98.27 283	92.23 378	92.13 424	97.49 331	79.50 423	98.69 341	89.75 419	99.38 135	95.25 463

ppachtmachnet_test		93.22 387	92.63 387	94.97 408	95.45 451	90.84 410	96.88 450	97.88 347	90.60 422	92.08 425	97.26 350	88.08 291	97.86 441	85.12 469	90.33 399	96.22 439

1314		96.25 222	95.73 227	97.79 208	97.13 365	95.55 225	98.19 303	98.59 173	93.47 324	92.03 426	97.82 302	91.33 176	99.49 193	94.62 281	98.44 200	98.32 304

baseline2		95.11 287	94.52 293	96.87 285	96.65 395	93.56 329	98.27 290	94.10 501	93.45 325	92.02 427	97.43 337	87.45 310	99.19 254	93.88 311	97.41 266	97.87 320

DTE-MVSNet		93.98 372	93.26 375	96.14 352	96.06 423	94.39 295	99.20 48	98.86 91	93.06 344	91.78 428	97.81 303	85.87 339	97.58 456	90.53 406	86.17 452	96.46 429

LF4IMVS		93.14 391	92.79 384	94.20 438	95.88 434	88.67 459	97.66 377	97.07 428	93.81 297	91.71 429	97.65 317	77.96 439	98.81 333	91.47 389	91.92 379	95.12 466

mvs5depth		91.23 415	90.17 418	94.41 435	92.09 491	89.79 433	95.26 486	96.50 462	90.73 420	91.69 430	97.06 372	76.12 459	98.62 348	88.02 446	84.11 464	94.82 473

our_test_3		93.65 377	93.30 373	94.69 421	95.45 451	89.68 439	96.91 442	97.65 366	91.97 386	91.66 431	96.88 394	89.67 237	97.93 434	88.02 446	91.49 384	96.48 427

testgi		93.06 393	92.45 394	94.88 413	96.43 407	89.90 431	98.75 178	97.54 382	95.60 172	91.63 432	97.91 290	74.46 472	97.02 467	86.10 460	93.67 347	97.72 326

ArgMatch-SfM		90.55 431	89.69 424	93.14 455	95.91 432	86.12 483	97.20 416	96.81 451	92.91 351	91.39 433	96.95 388	65.65 495	97.72 449	88.03 445	82.36 469	95.57 457

tfpnnormal		93.66 375	92.70 386	96.55 323	96.94 375	95.94 190	98.97 98	99.19 35	91.04 416	91.38 434	97.34 344	84.94 356	98.61 349	85.45 466	89.02 423	95.11 467

LTVRE_ROB	92.95 15	94.60 324	93.90 340	96.68 302	97.41 346	94.42 293	98.52 242	98.59 173	91.69 394	91.21 435	98.35 247	84.87 357	99.04 291	91.06 398	93.44 355	96.60 399
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
OpenMVS	93.04 13	95.83 241	95.00 268	98.32 137	97.18 362	97.32 101	99.21 45	98.97 57	89.96 434	91.14 436	99.05 146	86.64 321	99.92 44	93.38 324	99.47 123	97.73 325

pm-mvs1		93.94 373	93.06 378	96.59 315	96.49 403	95.16 252	98.95 105	98.03 337	92.32 375	91.08 437	97.84 298	84.54 368	98.41 376	92.16 368	86.13 455	96.19 441

ArgMatch-Sym		90.92 424	90.22 417	93.02 456	95.81 437	86.50 480	97.32 406	97.01 438	92.67 359	91.02 438	97.35 343	66.90 491	97.17 465	88.53 439	85.40 458	95.39 460

MVS-HIRNet		89.46 447	88.40 444	92.64 460	97.58 326	82.15 497	94.16 506	93.05 508	75.73 510	90.90 439	82.52 521	79.42 425	98.33 387	83.53 478	98.68 176	97.43 333

FMVSNet5		91.81 405	90.92 409	94.49 430	97.21 357	92.09 385	98.00 337	97.55 381	89.31 447	90.86 440	95.61 454	74.48 471	95.32 494	85.57 464	89.70 408	96.07 445

USDC		93.33 384	92.71 385	95.21 398	96.83 383	90.83 411	96.91 442	97.50 386	93.84 294	90.72 441	98.14 270	77.69 442	98.82 332	89.51 425	93.21 362	95.97 447

MVP-Stereo		94.28 352	93.92 337	95.35 395	94.95 459	92.60 373	97.97 340	97.65 366	91.61 396	90.68 442	97.09 365	86.32 331	98.42 369	89.70 421	99.34 139	95.02 471
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	92.99 14	94.30 348	93.77 351	95.88 371	97.81 306	92.04 388	98.71 193	98.37 253	93.99 285	90.60 443	98.47 235	80.86 412	99.05 288	92.75 349	92.40 371	96.55 412

CL-MVSNet_self_test		90.11 438	89.14 435	93.02 456	91.86 493	88.23 468	96.51 465	98.07 330	90.49 423	90.49 444	94.41 468	84.75 361	95.34 493	80.79 487	74.95 503	95.50 458

0.4-1-1-0.1		90.89 425	88.97 439	96.67 303	94.15 469	92.76 370	95.28 485	95.03 487	89.11 449	90.43 445	89.57 511	75.41 462	99.04 291	94.70 275	77.06 494	98.20 309

KD-MVS_self_test		90.38 433	89.38 431	93.40 449	92.85 486	88.94 455	97.95 341	97.94 343	90.35 429	90.25 446	93.96 476	79.82 419	95.94 489	84.62 475	76.69 498	95.33 461

ttmdpeth		92.61 399	91.96 402	94.55 427	94.10 471	90.60 419	98.52 242	97.29 408	92.67 359	90.18 447	97.92 289	79.75 421	97.79 443	91.09 395	86.15 454	95.26 462

Anonymous20231206		91.66 407	91.10 408	93.33 450	94.02 475	87.35 475	98.58 226	97.26 412	90.48 424	90.16 448	96.31 422	83.83 384	96.53 480	79.36 494	89.90 406	96.12 443

SixPastTwentyTwo		93.34 383	92.86 382	94.75 420	95.67 440	89.41 446	98.75 178	96.67 457	93.89 290	90.15 449	98.25 262	80.87 411	98.27 397	90.90 402	90.64 395	96.57 408

0.4-1-1-0.2		90.43 432	88.45 443	96.38 341	93.34 481	92.12 381	93.88 507	95.04 486	88.62 455	90.00 450	88.31 514	75.31 464	99.03 294	94.61 282	76.91 496	98.01 318

PVSNet_0	88.72 19	91.28 414	90.03 420	95.00 407	97.99 287	87.29 476	94.84 493	98.50 201	92.06 384	89.86 451	95.19 459	79.81 420	99.39 212	92.27 367	69.79 519	98.33 303

ACMH	92.88 16	94.55 329	93.95 336	96.34 344	97.63 322	93.26 350	98.81 164	98.49 206	93.43 326	89.74 452	98.53 228	81.91 396	99.08 283	93.69 315	93.30 360	96.70 385
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		90.26 437	88.73 442	94.86 414	96.12 420	90.62 417	98.17 311	97.63 369	77.46 504	89.68 453	96.04 436	69.19 484	97.79 443	88.98 433	85.29 459	96.16 442

pmmvs6		91.77 406	90.63 412	95.17 400	94.69 465	91.24 402	98.67 208	97.92 345	86.14 474	89.62 454	97.56 329	75.79 461	98.34 385	90.75 404	84.56 461	95.94 448

TinyColmap		92.31 403	91.53 404	94.65 424	96.92 376	89.75 434	96.92 440	96.68 456	90.45 426	89.62 454	97.85 297	76.06 460	98.81 333	86.74 455	92.51 370	95.41 459

Anonymous20240521		91.18 416	90.44 414	93.42 447	93.70 476	88.47 463	98.94 108	97.56 376	88.46 456	89.56 456	95.08 462	77.15 450	96.97 468	83.92 476	89.55 412	94.82 473

TransMVSNet (Re)		92.67 398	91.51 405	96.15 351	96.58 397	94.65 280	98.90 121	96.73 452	90.86 419	89.46 457	97.86 295	85.62 343	98.09 414	86.45 458	81.12 478	95.71 454

NR-MVSNet		94.98 298	94.16 318	97.44 241	96.53 399	97.22 116	98.74 182	98.95 61	94.96 230	89.25 458	97.69 312	89.32 250	98.18 402	94.59 285	87.40 440	96.92 354

0.3-1-1-0.015		90.29 435	88.21 447	96.51 326	93.56 478	92.44 374	94.41 502	95.03 487	88.71 453	89.20 459	88.50 513	73.12 478	99.04 291	94.67 278	76.70 497	98.05 314

LCM-MVSNet-Re		95.22 280	95.32 252	94.91 410	98.18 258	87.85 473	98.75 178	95.66 476	95.11 216	88.96 460	96.85 397	90.26 223	97.65 451	95.65 240	98.44 200	99.22 189

KD-MVS_2432*1600		89.61 444	87.96 452	94.54 428	94.06 473	91.59 396	95.59 480	97.63 369	89.87 436	88.95 461	94.38 470	78.28 434	96.82 471	84.83 471	68.05 520	95.21 464

miper_refine_blended		89.61 444	87.96 452	94.54 428	94.06 473	91.59 396	95.59 480	97.63 369	89.87 436	88.95 461	94.38 470	78.28 434	96.82 471	84.83 471	68.05 520	95.21 464

test_fmvs3		87.17 455	87.06 458	87.50 481	91.21 503	75.66 508	99.05 76	96.61 460	92.79 356	88.85 463	92.78 490	43.72 512	93.49 506	93.95 308	84.56 461	93.34 497

TDRefinement		91.06 420	89.68 425	95.21 398	85.35 528	91.49 398	98.51 249	97.07 428	91.47 399	88.83 464	97.84 298	77.31 446	99.09 280	92.79 348	77.98 491	95.04 470

MASt3R-SfM		85.54 460	85.89 460	84.50 490	90.13 514	66.13 526	92.89 509	95.33 481	85.73 479	88.77 465	96.36 421	52.50 506	94.89 500	86.66 456	84.65 460	92.50 503

tt0320-xc		89.79 441	88.11 448	94.84 417	96.19 415	90.61 418	98.16 312	97.22 415	77.35 505	88.75 466	96.70 406	65.94 494	97.63 453	89.31 429	83.39 466	96.28 437

N_pmnet		87.12 457	87.77 454	85.17 487	95.46 450	61.92 532	97.37 400	70.66 544	85.83 477	88.73 467	96.04 436	85.33 350	97.76 447	80.02 489	90.48 397	95.84 451

dtuonlycased		91.29 412	91.26 407	91.36 470	95.63 442	84.25 489	96.93 439	97.21 417	92.16 382	88.34 468	96.47 415	79.56 422	95.18 497	87.37 452	87.70 435	94.64 477

test_0402		91.32 411	90.27 416	94.48 431	96.60 396	91.12 403	98.50 250	97.22 415	86.10 475	88.30 469	96.98 383	77.65 444	97.99 429	78.13 499	92.94 364	94.34 479

test20.03		90.89 425	90.38 415	92.43 461	93.48 479	88.14 469	98.33 277	97.56 376	93.40 328	87.96 470	96.71 405	80.69 414	94.13 504	79.15 495	86.17 452	95.01 472

MIMVSNet1		89.67 443	88.28 446	93.82 442	92.81 487	91.08 404	98.01 335	97.45 394	87.95 459	87.90 471	95.87 442	67.63 489	94.56 502	78.73 498	88.18 431	95.83 452

mvsany_test3		88.80 449	88.04 449	91.09 471	89.78 516	81.57 499	97.83 363	95.49 479	93.81 297	87.53 472	93.95 477	56.14 503	97.43 460	94.68 276	83.13 467	94.26 480

Patchmatch-RL test		91.49 408	90.85 410	93.41 448	91.37 499	84.40 487	92.81 510	95.93 474	91.87 389	87.25 473	94.87 463	88.99 261	96.53 480	92.54 362	82.00 472	99.30 165

pmmvs3		86.67 458	84.86 464	92.11 467	88.16 520	87.19 478	96.63 460	94.75 491	79.88 497	87.22 474	92.75 492	66.56 492	95.20 496	81.24 486	76.56 499	93.96 490

dongtai		82.47 467	81.88 469	84.22 491	95.19 456	76.03 506	94.59 500	74.14 534	82.63 489	87.19 475	96.09 432	64.10 497	87.85 522	58.91 524	84.11 464	88.78 516

test_vis1_rt		91.29 412	90.65 411	93.19 454	97.45 341	86.25 482	98.57 235	90.90 517	93.30 333	86.94 476	93.59 479	62.07 500	99.11 275	97.48 151	95.58 323	94.22 483

K. test v3		92.55 400	91.91 403	94.48 431	95.64 441	89.24 447	99.07 72	94.88 489	94.04 278	86.78 477	97.59 324	77.64 445	97.64 452	92.08 370	89.43 416	96.57 408

lessismore_v0				94.45 434	94.93 460	88.44 464		91.03 516		86.77 478	97.64 320	76.23 458	98.42 369	90.31 409	85.64 457	96.51 422

APD_test1		88.22 452	88.01 450	88.86 478	95.98 427	74.66 515	97.21 415	96.44 464	83.96 487	86.66 479	97.90 291	60.95 501	97.84 442	82.73 479	90.23 402	94.09 486

ambc				89.49 475	86.66 523	75.78 507	92.66 511	96.72 453		86.55 480	92.50 493	46.01 510	97.90 435	90.32 408	82.09 471	94.80 475

PM-MVS		87.77 453	86.55 459	91.40 469	91.03 507	83.36 494	96.92 440	95.18 484	91.28 410	86.48 481	93.42 481	53.27 505	96.74 473	89.43 427	81.97 473	94.11 485

OpenMVS_ROB	86.42 20	89.00 448	87.43 456	93.69 444	93.08 485	89.42 445	97.91 348	96.89 445	78.58 501	85.86 482	94.69 464	69.48 483	98.29 395	77.13 502	93.29 361	93.36 496

UnsupCasMVSNet_eth		90.99 423	89.92 421	94.19 439	94.08 472	89.83 432	97.13 428	98.67 152	93.69 308	85.83 483	96.19 429	75.15 466	96.74 473	89.14 431	79.41 485	96.00 446

new_pmnet		90.06 439	89.00 438	93.22 453	94.18 467	88.32 466	96.42 467	96.89 445	86.19 473	85.67 484	93.62 478	77.18 449	97.10 466	81.61 484	89.29 418	94.23 482

dmvs_testset		87.64 454	88.93 441	83.79 492	95.25 454	63.36 528	97.20 416	91.17 514	93.07 343	85.64 485	95.98 441	85.30 352	91.52 514	69.42 516	87.33 441	96.49 425

test_f		86.07 459	85.39 461	88.10 479	89.28 518	75.57 509	97.73 372	96.33 466	89.41 446	85.35 486	91.56 504	43.31 514	95.53 491	91.32 391	84.23 463	93.21 498

EG-PatchMatch MVS		91.13 419	90.12 419	94.17 440	94.73 464	89.00 452	98.13 318	97.81 357	89.22 448	85.32 487	96.46 416	67.71 488	98.42 369	87.89 450	93.82 345	95.08 468

pmmvs-eth3d		90.36 434	89.05 436	94.32 437	91.10 505	92.12 381	97.63 382	96.95 440	88.86 452	84.91 488	93.13 485	78.32 433	96.74 473	88.70 436	81.81 474	94.09 486

FE-MVSNET2		90.29 435	88.94 440	94.36 436	90.48 511	92.27 376	98.45 258	97.82 353	91.59 397	84.90 489	93.10 486	73.92 474	96.42 483	87.92 449	82.26 470	94.39 478

FE-MVSNET		88.56 450	87.09 457	92.99 458	89.93 515	89.99 430	98.15 315	95.59 477	88.42 457	84.87 490	92.90 488	74.82 468	94.99 499	77.88 500	81.21 477	93.99 489

DeepMVS_CX				86.78 482	97.09 368	72.30 516		95.17 485	75.92 509	84.34 491	95.19 459	70.58 481	95.35 492	79.98 492	89.04 422	92.68 500

usedtu_dtu_shiyan2		84.80 462	82.31 467	92.27 465	86.38 525	85.55 485	97.77 368	96.56 461	78.34 502	83.90 492	93.50 480	54.16 504	95.32 494	77.55 501	72.62 512	95.92 449

new-patchmatchnet		88.50 451	87.45 455	91.67 468	90.31 513	85.89 484	97.16 426	97.33 403	89.47 443	83.63 493	92.77 491	76.38 456	95.06 498	82.70 480	77.29 492	94.06 488

UnsupCasMVSNet_bld		87.17 455	85.12 463	93.31 451	91.94 492	88.77 456	94.92 492	98.30 280	84.30 486	82.30 494	90.04 509	63.96 498	97.25 463	85.85 463	74.47 511	93.93 491

WB-MVS		84.86 461	85.33 462	83.46 493	89.48 517	69.56 520	98.19 303	96.42 465	89.55 442	81.79 495	94.67 465	84.80 359	90.12 517	52.44 526	80.64 482	90.69 509

CMPMVS	66.06 21	89.70 442	89.67 426	89.78 474	93.19 484	76.56 505	97.00 435	98.35 258	80.97 495	81.57 496	97.75 306	74.75 469	98.61 349	89.85 417	93.63 349	94.17 484
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SSC-MVS		84.27 464	84.71 465	82.96 498	89.19 519	68.83 521	98.08 327	96.30 467	89.04 451	81.37 497	94.47 466	84.60 366	89.89 518	49.80 529	79.52 484	90.15 510

MVStest1		89.53 446	87.99 451	94.14 441	94.39 466	90.42 422	98.25 293	96.84 450	82.81 488	81.18 498	97.33 346	77.09 451	96.94 469	85.27 468	78.79 486	95.06 469

test_method		79.03 473	78.17 472	81.63 499	86.06 526	54.40 543	82.75 530	96.89 445	39.54 535	80.98 499	95.57 455	58.37 502	94.73 501	84.74 474	78.61 487	95.75 453

kuosan		78.45 477	77.69 476	80.72 500	92.73 488	75.32 510	94.63 499	74.51 533	75.96 507	80.87 500	93.19 484	63.23 499	79.99 532	42.56 536	81.56 476	86.85 523

RoMa-SfM		83.81 465	82.08 468	89.00 477	93.33 482	79.94 502	95.51 482	92.48 510	79.75 498	79.89 501	95.69 451	46.23 509	93.20 509	78.90 496	76.93 495	93.87 492

DenseAffine		84.37 463	82.38 466	90.31 473	94.17 468	82.89 495	94.98 489	94.23 498	82.16 493	79.68 502	94.33 474	46.28 508	94.25 503	80.01 490	75.62 500	93.78 494

ET-MVSNet_ETH3D		94.13 362	92.98 380	97.58 233	98.22 246	96.20 170	97.31 408	95.37 480	94.53 256	79.56 503	97.63 322	86.51 322	97.53 458	96.91 180	90.74 394	99.02 231

RoMa-HiRes		79.77 470	77.89 473	85.41 486	90.81 508	74.77 514	94.26 504	86.78 523	75.97 506	77.00 504	94.37 472	39.39 519	90.60 515	74.98 508	67.46 522	90.84 508

LCM-MVSNet		78.70 476	76.24 482	86.08 483	77.26 544	71.99 517	94.34 503	96.72 453	61.62 521	76.53 505	89.33 512	33.91 533	92.78 511	81.85 483	74.60 509	93.46 495

DKM		81.60 468	79.57 471	87.68 480	92.65 489	78.36 503	94.65 498	91.17 514	79.69 499	76.11 506	93.98 475	37.88 524	91.54 513	79.64 493	70.38 516	93.15 499

PMMVS2		77.95 479	75.44 483	85.46 485	82.54 532	74.95 512	94.23 505	93.08 507	72.80 512	74.68 507	87.38 515	36.36 527	91.56 512	73.95 510	63.94 524	89.87 511

testf1		79.02 474	77.70 474	82.99 496	88.10 521	66.90 524	94.67 495	93.11 505	71.08 516	74.02 508	93.41 482	34.15 530	93.25 507	72.25 512	78.50 488	88.82 514

APD_test2		79.02 474	77.70 474	82.99 496	88.10 521	66.90 524	94.67 495	93.11 505	71.08 516	74.02 508	93.41 482	34.15 530	93.25 507	72.25 512	78.50 488	88.82 514

Gipuma		78.40 478	76.75 481	83.38 494	95.54 445	80.43 500	79.42 531	97.40 398	64.67 520	73.46 510	80.82 525	45.65 511	93.14 510	66.32 519	87.43 439	76.56 529
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DKM-HiRes		79.25 471	77.01 480	85.98 484	91.20 504	75.07 511	93.65 508	87.84 522	75.94 508	73.36 511	92.80 489	34.20 529	90.26 516	76.66 504	67.44 523	92.62 501

YYNet1		90.70 430	89.39 429	94.62 426	94.79 463	90.65 415	97.20 416	97.46 390	87.54 461	72.54 512	95.74 444	86.51 322	96.66 477	86.00 461	86.76 450	96.54 413

MDA-MVSNet_test_wron		90.71 429	89.38 431	94.68 422	94.83 461	90.78 412	97.19 419	97.46 390	87.60 460	72.41 513	95.72 448	86.51 322	96.71 476	85.92 462	86.80 449	96.56 410

MVS_clip		51.49 504	54.55 507	42.29 533	67.55 557	32.35 560	60.25 550	21.09 563	22.72 554	71.30 514	91.13 505	33.91 533	28.07 558	61.97 523	61.05 527	66.44 533

MDA-MVSNet-bldmvs		89.97 440	88.35 445	94.83 418	95.21 455	91.34 399	97.64 379	97.51 385	88.36 458	71.17 515	96.13 431	79.22 426	96.63 478	83.65 477	86.27 451	96.52 418

LoFTR		83.16 466	80.62 470	90.80 472	92.28 490	80.01 501	95.35 484	94.33 495	80.44 496	70.79 516	92.93 487	46.38 507	98.17 403	75.01 507	78.03 490	94.24 481

FPMVS		77.62 480	77.14 479	79.05 504	79.25 539	60.97 534	95.79 475	95.94 473	65.96 519	67.93 517	94.40 469	37.73 525	88.88 521	68.83 517	88.46 428	87.29 520

test_vis3_rt		79.22 472	77.40 477	84.67 488	86.44 524	74.85 513	97.66 377	81.43 527	84.98 483	67.12 518	81.91 524	28.09 538	97.60 454	88.96 434	80.04 483	81.55 526

MatchFormer		80.21 469	77.20 478	89.24 476	91.79 494	77.21 504	95.16 487	93.59 503	72.46 514	67.08 519	89.93 510	43.14 515	97.90 435	67.07 518	74.55 510	92.61 502

SP-DiffGlue		70.13 485	69.16 488	73.04 513	77.73 542	57.48 538	88.44 524	74.91 532	50.96 527	66.64 520	85.99 517	41.44 516	73.46 538	64.21 520	72.15 513	88.19 519

PDCNetPlus		71.79 484	69.26 487	79.39 503	85.67 527	69.92 519	90.34 519	62.32 546	72.62 513	65.36 521	90.26 506	39.20 521	86.38 524	75.32 506	42.24 541	81.88 525

PMatch-SfM		73.49 483	70.32 485	83.00 495	85.01 529	68.63 522	90.17 521	79.05 530	71.64 515	63.27 522	91.93 499	17.27 549	89.10 520	74.59 509	59.95 529	91.26 504

ELoFTR		75.37 481	72.33 484	84.51 489	84.48 530	68.41 523	91.57 514	88.78 520	73.84 511	62.84 523	90.14 507	27.38 539	94.11 505	71.45 515	60.46 528	91.00 506

tmp_tt		68.90 488	66.97 489	74.68 506	50.78 560	59.95 535	87.13 527	83.47 526	38.80 536	62.21 524	96.23 426	64.70 496	76.91 534	88.91 435	30.49 549	87.19 521

SP-SuperGlue		68.14 490	66.58 490	72.81 514	90.65 510	55.53 540	91.37 515	73.04 536	49.07 530	61.03 525	80.24 528	38.13 523	74.06 537	45.46 532	70.26 517	88.84 513

VLMVS_CLIP		53.81 503	55.23 505	49.55 521	44.37 561	26.59 564	64.46 548	73.52 535	28.42 550	60.82 526	83.22 519	22.09 542	59.35 547	62.16 522	58.00 531	62.70 534

SP-LightGlue		68.17 489	66.54 491	73.06 512	91.08 506	55.79 539	91.09 516	72.78 537	48.55 531	60.77 527	79.95 529	38.55 522	74.10 536	45.47 531	70.64 515	89.28 512

E-PMN		64.94 497	64.25 498	67.02 517	82.28 533	59.36 536	91.83 513	85.63 524	52.69 524	60.22 528	77.28 533	41.06 517	80.12 531	46.15 530	41.14 542	61.57 537

PMatch-Up-SfM		70.03 486	66.48 492	80.70 501	82.00 534	63.20 529	88.10 525	71.07 540	67.59 518	60.07 529	90.10 508	14.49 554	87.80 523	71.95 514	52.95 534	91.09 505

ALIKED-NN		66.93 493	64.81 496	73.32 510	93.41 480	62.03 531	87.55 526	71.25 539	50.21 528	59.98 530	82.57 520	39.72 518	84.03 528	34.94 540	63.64 525	73.90 531

ALIKED-LG		67.40 491	65.16 495	74.11 508	93.21 483	62.30 530	88.98 522	71.99 538	55.04 522	59.47 531	82.33 522	39.27 520	85.49 526	32.61 543	63.58 526	74.55 530

SP-NN		67.39 492	65.69 493	72.49 516	90.68 509	55.34 541	90.33 520	71.01 542	46.77 533	59.09 532	79.83 530	37.26 526	73.38 539	44.68 533	71.51 514	88.74 517

EMVS		64.07 498	63.26 500	66.53 518	81.73 535	58.81 537	91.85 512	84.75 525	51.93 526	59.09 532	75.13 536	43.32 513	79.09 533	42.03 537	39.47 543	61.69 536

ALIKED-MNN		65.35 496	62.68 501	73.35 509	93.70 476	61.07 533	88.63 523	70.76 543	47.76 532	57.06 534	80.59 526	34.03 532	85.39 527	32.73 542	58.87 530	73.59 532

SP-MNN		66.66 494	64.70 497	72.53 515	90.32 512	55.08 542	91.01 517	71.05 541	44.81 534	56.48 535	79.62 531	35.87 528	74.11 535	43.13 535	69.98 518	88.39 518

XFeat-NN		56.16 501	56.10 504	56.36 520	72.10 551	42.54 555	76.45 534	61.18 547	38.16 537	53.08 536	76.48 534	32.95 535	65.67 541	44.15 534	50.31 538	60.87 538

VLMVS		37.31 517	39.19 518	31.67 537	40.61 562	24.46 565	44.56 552	28.63 561	5.66 558	51.94 537	71.15 538	25.03 540	27.90 559	33.30 541	51.87 535	42.64 539

MVE	62.14 22	63.28 499	59.38 502	74.99 505	74.33 549	65.47 527	85.55 528	80.50 528	52.02 525	51.10 538	75.00 537	10.91 561	80.50 530	51.60 528	53.40 533	78.99 527
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
XFeat-MNN		55.84 502	55.19 506	57.82 519	69.33 555	43.25 550	78.25 533	62.64 545	37.53 538	50.90 539	76.32 535	32.43 536	68.13 540	42.00 538	47.26 540	62.07 535

ANet_high		69.08 487	65.37 494	80.22 502	65.99 558	71.96 518	90.91 518	90.09 518	82.62 490	49.93 540	78.39 532	29.36 537	81.75 529	62.49 521	38.52 545	86.95 522

GLUNet-SfM		61.12 500	56.63 503	74.58 507	69.78 554	53.99 544	78.71 532	76.81 531	49.09 529	49.42 541	80.47 527	24.43 541	85.82 525	51.80 527	29.17 550	83.92 524

PMVS	61.03 23	65.95 495	63.57 499	73.09 511	57.90 559	51.22 545	85.05 529	93.93 502	54.45 523	44.32 542	83.57 518	13.22 556	89.15 519	58.68 525	81.00 479	78.91 528
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-NN		49.27 505	49.25 508	49.32 522	83.88 531	45.20 546	74.57 535	53.44 548	32.44 539	42.88 543	64.93 540	20.60 543	61.35 542	16.59 546	53.96 532	41.40 540

SIFT-MNN		47.78 506	47.47 509	48.69 523	81.04 536	44.17 547	73.46 536	53.36 549	31.82 540	38.54 544	63.76 541	18.11 547	61.27 543	15.96 548	51.17 536	40.64 543

SIFT-NN-NCMNet		47.55 507	47.18 510	48.67 524	79.60 538	44.09 548	73.43 537	52.90 550	31.82 540	38.38 545	63.56 544	18.47 544	61.19 544	15.91 549	50.50 537	40.74 542

SIFT-NN-CMatch		45.31 508	44.49 511	47.75 525	76.46 545	42.98 553	70.17 541	49.20 553	31.63 543	37.94 546	63.68 543	18.19 546	59.32 548	15.91 549	37.27 546	40.95 541

MVS_baseline		19.65 524	22.57 527	10.89 541	26.60 563	2.25 568	14.08 553	3.93 567	1.15 560	37.00 547	69.35 539	4.91 564	0.00 562	17.88 544	28.24 551	30.42 553

SIFT-NN-PointCN		43.09 512	42.61 514	44.51 531	72.48 550	37.95 559	70.10 542	46.55 555	30.16 549	34.48 548	61.93 548	18.02 548	55.90 553	15.40 552	34.41 547	39.69 545

SIFT-ConvMatch		43.26 511	42.18 515	46.50 528	78.34 541	43.05 551	68.67 543	47.17 554	31.06 544	30.28 549	62.56 546	15.43 551	58.95 550	14.92 553	31.22 548	37.51 548

SIFT-NN-UMatch		44.69 510	43.84 513	47.24 527	74.56 548	42.59 554	71.89 539	49.78 551	31.80 542	29.27 550	63.70 542	18.26 545	59.43 546	15.86 551	39.43 544	39.71 544

SIFT-CM-Cal		41.25 514	40.03 517	44.88 530	77.37 543	41.08 557	65.71 547	41.18 558	30.42 548	28.83 551	61.42 550	14.88 553	56.40 551	14.13 556	26.37 554	37.16 549

SIFT-UMatch		42.35 513	41.04 516	46.29 529	76.09 546	41.80 556	70.21 540	45.21 556	30.75 546	27.33 552	62.62 545	15.13 552	59.11 549	14.72 554	27.30 552	37.95 547

SIFT-NCM-Cal		44.98 509	44.20 512	47.33 526	79.81 537	43.05 551	72.12 538	49.31 552	30.81 545	25.90 553	61.87 549	15.80 550	60.28 545	14.09 557	48.07 539	38.66 546

SIFT-PCN-Cal		36.85 518	36.40 521	38.19 535	71.43 553	30.42 562	64.34 549	37.72 560	27.48 552	22.98 554	57.03 551	12.99 557	51.22 554	12.51 558	21.13 556	32.92 552

SIFT-UM-Cal		39.93 515	38.61 519	43.88 532	76.08 547	39.30 558	68.10 544	37.89 559	30.49 547	22.74 555	62.27 547	13.89 555	56.16 552	14.17 555	21.90 555	36.17 550

SIFT-PointCN		37.89 516	37.50 520	39.07 534	71.45 552	31.31 561	66.27 546	41.69 557	27.82 551	22.63 556	56.73 552	12.00 559	50.56 555	12.18 559	26.71 553	35.34 551

SIFT-NCMNet		32.45 519	31.84 523	34.30 536	68.74 556	28.10 563	57.85 551	24.54 562	27.25 553	19.31 557	52.59 553	9.75 562	45.69 556	10.92 560	15.56 558	29.13 554

testmvs		21.48 522	24.95 525	11.09 540	14.89 564	6.47 567	96.56 462	9.87 565	7.55 556	17.93 558	39.02 555	9.43 563	5.90 561	16.56 547	12.72 559	20.91 556

test123		20.95 523	23.72 526	12.64 539	13.54 565	8.19 566	96.55 464	6.13 566	7.48 557	16.74 559	37.98 556	12.97 558	6.05 560	16.69 545	5.43 560	23.68 555

wuyk23d		30.17 520	30.18 524	30.16 538	78.61 540	43.29 549	66.79 545	14.21 564	17.31 555	14.82 560	11.93 559	11.55 560	41.43 557	37.08 539	19.30 557	5.76 557

EGC-MVSNET		75.22 482	69.54 486	92.28 464	94.81 462	89.58 441	97.64 379	96.50 462	1.82 559	5.57 561	95.74 444	68.21 485	96.26 485	73.80 511	91.71 381	90.99 507

mmdepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet_test		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

cdsmvs_eth3d_5k		23.98 521	31.98 522	0.00 542	0.00 566	0.00 569	0.00 554	98.59 173	0.00 561	0.00 562	98.61 217	90.60 209	0.00 562	0.00 561	0.00 561	0.00 558

pcd_1.5k_mvsjas		7.88 526	10.50 529	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	94.51 93	0.00 562	0.00 561	0.00 561	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

ab-mvs-re		8.20 525	10.94 528	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	98.43 237	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Meshroom													0.00 562
: In preparation.
AliceVision / Meshro													0.00 562
: In preparation.
AliceVision_Meshroom													0.00 562
: In preparation.
PatchmatchNet2					0.00 566	88.11 470	96.56 462	97.31 406	85.66 480
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														80.13 488	90.51 396	95.88 450
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													97.78 445
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						90.94 406								88.66 437

MSC_two_6792asdad				99.62 7	99.17 113	99.08 13		98.63 163					99.94 15	98.53 57	99.80 26	99.86 14

No_MVS				99.62 7	99.17 113	99.08 13		98.63 163					99.94 15	98.53 57	99.80 26	99.86 14

eth-test2					0.00 566

eth-test					0.00 566

OPU-MVS				99.37 29	99.24 105	99.05 17	99.02 86				99.16 111	97.81 3	99.37 213	97.24 166	99.73 63	99.70 68

save fliter					99.46 59	98.38 43	98.21 296	98.71 139	97.95 29

test_0728_SECOND				99.71 1	99.72 17	99.35 1	98.97 98	98.88 78					99.94 15	98.47 65	99.81 17	99.84 19

GSMVS																99.20 192

sam_mvs1												89.45 245				99.20 192

sam_mvs												88.99 261

MTGPA								98.74 131

test_post1							96.68 459				30.43 558	87.85 299	98.69 341	92.59 358

test_post											31.83 557	88.83 270	98.91 317

patchmatchnet-post											95.10 461	89.42 246	98.89 321

MTMP							98.89 125	94.14 500

gm-plane-assit					95.88 434	87.47 474			89.74 439		96.94 390		99.19 254	93.32 327

test9_res														96.39 211	99.57 100	99.69 71

agg_prior2														95.87 227	99.57 100	99.68 76

test_prior4						98.01 73	97.86 358

test_prior				99.19 52	99.31 81	98.22 60		98.84 97					99.70 145			99.65 84

新几何2							97.64 379

旧先验1					99.29 90	97.48 92		98.70 142			99.09 136	95.56 57			99.47 123	99.61 91

无先验							97.58 384	98.72 136	91.38 402				99.87 81	93.36 326		99.60 93

原ACMM2							97.67 376

testdata2													99.89 70	91.65 386

segment_acmp												96.85 16

testdata1							97.32 406		96.34 131

plane_prior7					97.42 343	94.63 282

plane_prior6					97.35 350	94.61 285						87.09 313

plane_prior5								98.56 184					99.03 294	96.07 217	94.27 329	96.92 354

plane_prior4											98.28 256

plane_prior2							98.80 165		97.28 70

plane_prior1					97.37 349

plane_prior						94.60 287	98.44 264		96.74 107						94.22 331

n2								0.00 568

nn								0.00 568

door-mid								94.37 494

test11								98.66 155

door								94.64 492

HQP5-MVS						94.25 304

BP-MVS														95.30 252

HQP3-MVS								98.46 209							94.18 333

HQP2-MVS												86.75 319

NP-MVS					97.28 352	94.51 290					97.73 307

ACMMP++_ref															92.97 363

ACMMP++															93.61 350

Test By Simon												94.64 90

High-resolution multi-view benchmark