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 15	98.79 13	99.24 46	99.34 72	97.83 80	98.70 197	99.26 16	98.85 6	99.92 1	99.51 28	93.91 107	99.95 9	99.86 1	99.79 35	99.92 2

fmvsm_s_conf0.5_n_9		98.63 29	98.66 21	98.54 110	99.40 68	95.83 204	98.79 173	99.17 37	98.94 2	99.92 1	99.61 5	92.49 125	99.93 34	99.86 1	99.76 48	99.86 13

fmvsm_l_conf0.5_n_3		98.90 15	98.74 18	99.37 28	99.36 69	98.25 57	98.89 125	99.24 20	98.77 10	99.89 3	99.59 13	93.39 113	99.96 4	99.78 10	99.76 48	99.89 8

fmvsm_s_conf0.5_n_11		98.58 36	98.57 26	98.62 100	99.42 65	97.16 119	98.97 99	98.86 91	98.91 4	99.87 4	99.66 3	91.82 153	99.95 9	99.82 6	99.82 14	98.75 262

fmvsm_s_conf0.5_n_5		98.53 46	98.35 48	99.08 64	99.07 128	97.46 95	98.68 203	99.20 33	97.50 52	99.87 4	99.50 31	91.96 150	99.96 4	99.76 11	99.65 81	99.82 23

fmvsm_s_conf0.5_n_3		98.53 46	98.45 39	98.79 86	99.23 105	97.32 100	98.80 165	99.26 16	98.82 7	99.87 4	99.60 10	90.95 197	99.93 34	99.76 11	99.73 62	99.12 208

test_vis1_n_1920		96.71 194	96.84 167	96.31 342	99.11 124	89.74 431	99.05 77	98.58 177	98.08 24	99.87 4	99.37 56	78.48 430	99.93 34	99.29 27	99.69 72	99.27 175

fmvsm_s_conf0.5_n_6		98.65 26	98.55 29	98.95 78	98.50 188	97.30 103	98.79 173	99.16 39	98.14 23	99.86 8	99.41 48	93.71 110	99.91 57	99.71 15	99.64 86	99.65 83

fmvsm_l_conf0.5_n		99.07 5	99.05 2	99.14 58	99.41 67	97.54 89	98.89 125	99.31 13	98.49 17	99.86 8	99.42 46	96.45 29	99.96 4	99.86 1	99.74 58	99.90 5

test_fmvsm_n_1920		98.87 18	99.01 3	98.45 124	99.42 65	96.43 157	98.96 105	99.36 10	98.63 13	99.86 8	99.51 28	95.91 47	99.97 1	99.72 14	99.75 54	98.94 238

fmvsm_l_conf0.5_n_a		99.09 2	99.08 1	99.11 62	99.43 64	97.48 91	98.88 132	99.30 14	98.47 18	99.85 11	99.43 45	96.71 18	99.96 4	99.86 1	99.80 25	99.89 8

fmvsm_s_conf0.5_n_10		98.66 25	98.54 31	99.02 69	99.36 69	97.21 116	98.86 143	99.23 27	98.90 5	99.83 12	99.59 13	91.57 162	99.94 14	99.79 9	99.74 58	99.89 8

fmvsm_s_conf0.5_n_4		98.35 68	98.50 34	97.90 195	99.16 116	95.08 256	98.75 178	99.24 20	98.39 19	99.81 13	99.52 25	92.35 129	99.90 65	99.74 13	99.51 115	98.71 268

test_fmvsmconf_n		98.92 13	98.87 7	99.04 68	98.88 148	97.25 113	98.82 156	99.34 11	98.75 11	99.80 14	99.61 5	95.16 78	99.95 9	99.70 17	99.80 25	99.93 1

fmvsm_s_conf0.5_n_8		98.73 23	98.62 22	99.05 67	99.35 71	97.27 107	98.80 165	99.23 27	98.93 3	99.79 15	99.59 13	92.34 130	99.95 9	99.82 6	99.71 69	99.92 2

fmvsm_s_conf0.5_n_2		98.30 75	98.21 69	98.57 105	99.25 97	97.11 122	98.66 210	99.20 33	98.82 7	99.79 15	99.60 10	89.38 246	99.92 43	99.80 8	99.38 135	98.69 270

fmvsm_s_conf0.5_n_a		98.38 63	98.42 41	98.27 139	99.09 126	95.41 231	98.86 143	99.37 9	97.69 40	99.78 17	99.61 5	92.38 128	99.91 57	99.58 23	99.43 127	99.49 112

fmvsm_s_conf0.1_n_2		98.14 81	98.02 81	98.53 113	98.88 148	97.07 124	98.69 200	98.82 102	98.78 9	99.77 18	99.61 5	88.83 268	99.91 57	99.71 15	99.07 152	98.61 280

test_cas_vis1_n_1920		97.38 144	97.36 119	97.45 238	98.95 143	93.25 349	99.00 92	98.53 189	97.70 39	99.77 18	99.35 62	84.71 362	99.85 85	98.57 53	99.66 78	99.26 182

fmvsm_s_conf0.1_n_a		98.08 82	98.04 80	98.21 147	97.66 317	95.39 236	98.89 125	99.17 37	97.24 74	99.76 20	99.67 1	91.13 186	99.88 78	99.39 26	99.41 129	99.35 148

TestfortrainingZip a		99.05 6	98.85 9	99.65 2	99.77 2	99.13 12	99.32 22	99.01 52	97.87 31	99.74 21	99.54 20	96.71 18	99.92 43	98.35 74	99.33 141	99.90 5

fmvsm_s_conf0.5_n		98.42 60	98.51 32	98.13 164	99.30 84	95.25 245	98.85 148	99.39 7	97.94 29	99.74 21	99.62 4	92.59 124	99.91 57	99.65 18	99.52 113	99.25 184

fmvsm_s_conf0.5_n_7		98.23 76	98.35 48	97.89 197	98.86 152	94.99 262	98.58 226	99.00 53	98.29 20	99.73 23	99.60 10	91.70 156	99.92 43	99.63 21	99.73 62	98.76 261

SED-MVS		99.09 2	98.91 5	99.63 5	99.71 24	99.24 5	99.02 87	98.87 85	97.65 41	99.73 23	99.48 35	97.53 8	99.94 14	98.43 68	99.81 16	99.70 67

test_241102_ONE					99.71 24	99.24 5		98.87 85	97.62 43	99.73 23	99.39 50	97.53 8	99.74 135

SD-MVS		98.64 28	98.68 19	98.53 113	99.33 75	98.36 50	98.90 121	98.85 95	97.28 69	99.72 26	99.39 50	96.63 22	97.60 450	98.17 86	99.85 6	99.64 86
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 80	98.21 69	98.11 169	98.54 186	95.24 246	98.87 135	99.24 20	97.50 52	99.70 27	99.67 1	91.33 174	99.89 69	99.47 25	99.54 110	99.21 190

test_fmvs1_n		95.90 236	95.99 217	95.63 381	98.67 173	88.32 463	99.26 33	98.22 293	96.40 125	99.67 28	99.26 80	73.91 472	99.70 144	99.02 34	99.50 116	98.87 245

test_vis1_n		95.47 258	95.13 259	96.49 324	97.77 306	90.41 419	99.27 32	98.11 318	96.58 114	99.66 29	99.18 105	67.00 487	99.62 165	99.21 28	99.40 132	99.44 126

mvsany_test1		97.69 104	97.70 92	97.66 225	98.24 242	94.18 306	97.53 383	97.53 382	95.52 184	99.66 29	99.51 28	94.30 99	99.56 175	98.38 72	98.62 180	99.23 186

test_fmvs1		96.42 209	96.67 182	95.66 380	98.82 157	88.53 459	98.80 165	98.20 296	96.39 126	99.64 31	99.20 95	80.35 416	99.67 151	99.04 32	99.57 99	98.78 257

IU-MVS					99.71 24	99.23 7		98.64 159	95.28 202	99.63 32				98.35 74	99.81 16	99.83 19

PC_three_1452									95.08 219	99.60 33	99.16 110	97.86 2	98.47 360	97.52 143	99.72 67	99.74 50

lecture		98.95 9	98.78 14	99.45 19	99.75 6	98.63 32	99.43 10	99.38 8	97.60 46	99.58 34	99.47 37	95.36 65	99.93 34	98.87 39	99.57 99	99.78 33

test0726					99.72 17	99.25 2	99.06 74	98.88 78	97.62 43	99.56 35	99.50 31	97.42 10

TSAR-MVS + MP.		98.78 20	98.62 22	99.24 46	99.69 29	98.28 55	99.14 60	98.66 154	96.84 98	99.56 35	99.31 71	96.34 33	99.70 144	98.32 76	99.73 62	99.73 55
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 13	98.67 20	99.65 2	99.58 38	99.20 9	98.42 268	98.91 72	97.58 47	99.54 37	99.46 42	97.10 13	99.94 14	97.64 126	99.84 11	99.83 19
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		99.08 4	98.89 6	99.64 4	99.17 112	99.23 7	99.69 1	98.88 78	97.32 65	99.53 38	99.47 37	97.81 3	99.94 14	98.47 64	99.72 67	99.74 50

test_241102_TWO								98.87 85	97.65 41	99.53 38	99.48 35	97.34 12	99.94 14	98.43 68	99.80 25	99.83 19

DVP-MVS		99.03 7	98.83 11	99.63 5	99.72 17	99.25 2	98.97 99	98.58 177	97.62 43	99.45 40	99.46 42	97.42 10	99.94 14	98.47 64	99.81 16	99.69 70
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 65	99.45 40	99.46 42	97.88 1	99.94 14	98.47 64	99.86 2	99.85 16

test_fmvsmconf0.1_n		98.58 36	98.44 40	98.99 71	97.73 311	97.15 120	98.84 152	98.97 57	98.75 11	99.43 42	99.54 20	93.29 115	99.93 34	99.64 20	99.79 35	99.89 8

TestfortrainingZip				99.43 21	99.13 120	99.06 16	99.32 22	98.57 179	96.88 97	99.42 43	99.05 145	96.54 24	99.73 137		98.59 182	99.51 104

MSP-MVS		98.74 22	98.55 29	99.29 39	99.75 6	98.23 58	99.26 33	98.88 78	97.52 50	99.41 44	98.78 194	96.00 43	99.79 122	97.79 113	99.59 95	99.85 16
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 8	98.84 10	99.55 11	99.57 40	98.96 19	99.39 11	98.93 65	97.38 62	99.41 44	99.54 20	96.66 20	99.84 89	98.86 40	99.85 6	99.87 12
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
FOURS1					99.82 1	98.66 30	99.69 1	98.95 61	97.46 57	99.39 46

SMA-MVS		98.58 36	98.25 63	99.56 9	99.51 47	99.04 18	98.95 106	98.80 115	93.67 309	99.37 47	99.52 25	96.52 26	99.89 69	98.06 92	99.81 16	99.76 47
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 10	98.81 12	99.34 32	99.52 46	98.26 56	98.94 109	98.84 96	98.06 25	99.35 48	99.61 5	96.39 32	99.94 14	98.77 43	99.82 14	99.83 19

BridgeMVS		98.45 56	98.35 48	98.74 90	98.65 177	97.55 87	99.19 50	98.60 165	96.72 108	99.35 48	98.77 197	95.06 83	99.55 182	98.95 35	99.87 1	99.12 208

SteuartSystems-ACMMP		98.90 15	98.75 17	99.36 30	99.22 107	98.43 40	99.10 69	98.87 85	97.38 62	99.35 48	99.40 49	97.78 5	99.87 80	97.77 114	99.85 6	99.78 33
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		98.59 34	98.32 59	99.41 23	99.54 42	98.71 28	99.04 81	98.81 108	95.12 214	99.32 51	99.39 50	96.22 34	99.84 89	97.72 117	99.73 62	99.67 79

MED-MVS test				99.52 14	99.77 2	98.86 24	99.32 22	99.24 20	96.41 124	99.30 52	99.35 62		99.92 43	98.30 77	99.80 25	99.79 29

MED-MVS		99.12 1	98.97 4	99.56 9	99.77 2	98.86 24	99.32 22	99.24 20	97.87 31	99.30 52	99.54 20	97.61 6	99.92 43	98.30 77	99.80 25	99.90 5

reproduce-ours		98.93 11	98.78 14	99.38 24	99.49 53	98.38 42	98.86 143	98.83 98	98.06 25	99.29 54	99.58 16	96.40 30	99.94 14	98.68 46	99.81 16	99.81 25

our_new_method		98.93 11	98.78 14	99.38 24	99.49 53	98.38 42	98.86 143	98.83 98	98.06 25	99.29 54	99.58 16	96.40 30	99.94 14	98.68 46	99.81 16	99.81 25

dcpmvs_2		98.08 82	98.59 25	96.56 315	99.57 40	90.34 422	99.15 57	98.38 249	96.82 100	99.29 54	99.49 34	95.78 51	99.57 172	98.94 36	99.86 2	99.77 40

test_part2					99.63 35	99.18 10				99.27 57

DeepPCF-MVS	96.37 2	97.93 90	98.48 38	96.30 343	99.00 136	89.54 438	97.43 392	98.87 85	98.16 22	99.26 58	99.38 55	96.12 39	99.64 158	98.30 77	99.77 42	99.72 59

APD-MVS		98.35 68	98.00 83	99.42 22	99.51 47	98.72 27	98.80 165	98.82 102	94.52 257	99.23 59	99.25 86	95.54 58	99.80 110	96.52 204	99.77 42	99.74 50
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 49	99.20 60	99.47 37	97.57 7

APD-MVS_3200maxsize		98.53 46	98.33 58	99.15 57	99.50 49	97.92 75	99.15 57	98.81 108	96.24 134	99.20 60	99.37 56	95.30 69	99.80 110	97.73 116	99.67 75	99.72 59

patch_mono-2		98.36 66	98.87 7	96.82 285	99.53 43	90.68 410	98.64 213	99.29 15	97.88 30	99.19 62	99.52 25	96.80 16	99.97 1	99.11 30	99.86 2	99.82 23

ME-MVS		98.83 19	98.60 24	99.52 14	99.58 38	98.86 24	98.69 200	98.93 65	97.00 91	99.17 63	99.35 62	96.62 23	99.90 65	98.30 77	99.80 25	99.79 29

MM		98.51 49	98.24 65	99.33 36	99.12 122	98.14 67	98.93 115	97.02 432	98.96 1	99.17 63	99.47 37	91.97 149	99.94 14	99.85 5	99.69 72	99.91 4

SR-MVS-dyc-post		98.54 45	98.35 48	99.13 59	99.49 53	97.86 76	99.11 66	98.80 115	96.49 119	99.17 63	99.35 62	95.34 67	99.82 98	97.72 117	99.65 81	99.71 63

RE-MVS-def			98.34 54		99.49 53	97.86 76	99.11 66	98.80 115	96.49 119	99.17 63	99.35 62	95.29 70		97.72 117	99.65 81	99.71 63

9.14			98.06 78		99.47 57		98.71 193	98.82 102	94.36 266	99.16 67	99.29 75	96.05 41	99.81 103	97.00 173	99.71 69

ACMMP_NAP		98.61 31	98.30 60	99.55 11	99.62 36	98.95 20	98.82 156	98.81 108	95.80 160	99.16 67	99.47 37	95.37 64	99.92 43	97.89 105	99.75 54	99.79 29

test-260524					99.64 33	99.18 10		98.83 98		99.13 69		96.51 27	99.92 43	99.03 33	99.80 25

SR-MVS		98.57 41	98.35 48	99.24 46	99.53 43	98.18 62	99.09 70	98.82 102	96.58 114	99.10 70	99.32 69	95.39 62	99.82 98	97.70 122	99.63 88	99.72 59

PGM-MVS		98.49 51	98.23 67	99.27 44	99.72 17	98.08 69	98.99 95	99.49 5	95.43 189	99.03 71	99.32 69	95.56 56	99.94 14	96.80 195	99.77 42	99.78 33

KinetiMVS		97.48 130	97.05 153	98.78 87	98.37 211	97.30 103	98.99 95	98.70 141	97.18 79	99.02 72	99.01 152	87.50 305	99.67 151	95.33 248	99.33 141	99.37 143

VNet		97.79 98	97.40 115	98.96 76	98.88 148	97.55 87	98.63 216	98.93 65	96.74 105	99.02 72	98.84 181	90.33 218	99.83 91	98.53 56	96.66 285	99.50 107

xiu_mvs_v1_base_debu		97.60 113	97.56 99	97.72 214	98.35 214	95.98 180	97.86 355	98.51 195	97.13 84	99.01 74	98.40 240	91.56 163	99.80 110	98.53 56	98.68 175	97.37 335

xiu_mvs_v1_base		97.60 113	97.56 99	97.72 214	98.35 214	95.98 180	97.86 355	98.51 195	97.13 84	99.01 74	98.40 240	91.56 163	99.80 110	98.53 56	98.68 175	97.37 335

xiu_mvs_v1_base_debi		97.60 113	97.56 99	97.72 214	98.35 214	95.98 180	97.86 355	98.51 195	97.13 84	99.01 74	98.40 240	91.56 163	99.80 110	98.53 56	98.68 175	97.37 335

MVSMamba_PlusPlus		98.31 73	98.19 73	98.67 96	98.96 142	97.36 98	99.24 36	98.57 179	94.81 238	98.99 77	98.90 173	95.22 76	99.59 168	99.15 29	99.84 11	99.07 224

TSAR-MVS + GP.		98.38 63	98.24 65	98.81 85	99.22 107	97.25 113	98.11 320	98.29 280	97.19 78	98.99 77	99.02 148	96.22 34	99.67 151	98.52 62	98.56 186	99.51 104

CS-MVS		98.44 57	98.49 36	98.31 137	99.08 127	96.73 139	99.67 3	98.47 207	97.17 80	98.94 79	99.10 127	95.73 52	99.13 270	98.71 45	99.49 118	99.09 216

HFP-MVS		98.63 29	98.40 42	99.32 38	99.72 17	98.29 54	99.23 38	98.96 60	96.10 144	98.94 79	99.17 107	96.06 40	99.92 43	97.62 127	99.78 40	99.75 48

region2R		98.61 31	98.38 44	99.29 39	99.74 12	98.16 64	99.23 38	98.93 65	96.15 138	98.94 79	99.17 107	95.91 47	99.94 14	97.55 139	99.79 35	99.78 33

HPM-MVS_fast		98.38 63	98.13 74	99.12 61	99.75 6	97.86 76	99.44 9	98.82 102	94.46 262	98.94 79	99.20 95	95.16 78	99.74 135	97.58 134	99.85 6	99.77 40

test_fmvsmconf0.01_n		97.86 92	97.54 102	98.83 84	95.48 446	96.83 134	98.95 106	98.60 165	98.58 14	98.93 83	99.55 18	88.57 273	99.91 57	99.54 24	99.61 91	99.77 40

ACMMPR		98.59 34	98.36 46	99.29 39	99.74 12	98.15 65	99.23 38	98.95 61	96.10 144	98.93 83	99.19 102	95.70 53	99.94 14	97.62 127	99.79 35	99.78 33

DeepC-MVS_fast	96.70 1	98.55 44	98.34 54	99.18 53	99.25 97	98.04 70	98.50 250	98.78 122	97.72 36	98.92 85	99.28 76	95.27 71	99.82 98	97.55 139	99.77 42	99.69 70
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 51	98.50 34	98.46 123	99.20 110	97.05 125	99.64 4	98.50 200	97.45 58	98.88 86	99.14 115	95.25 73	99.15 265	98.83 41	99.56 107	99.20 191

MGCNet		98.23 76	97.91 86	99.21 50	98.06 274	97.96 74	98.58 226	95.51 474	98.58 14	98.87 87	99.26 80	92.99 119	99.95 9	99.62 22	99.67 75	99.73 55

EC-MVSNet		98.21 79	98.11 76	98.49 120	98.34 219	97.26 112	99.61 5	98.43 227	96.78 101	98.87 87	98.84 181	93.72 109	99.01 298	98.91 38	99.50 116	99.19 195

diffmvs_AUTHOR		97.59 116	97.44 111	98.01 183	98.26 237	95.47 227	98.12 316	98.36 255	96.38 127	98.84 89	99.10 127	91.13 186	99.26 231	98.24 85	98.56 186	99.30 164

EI-MVSNet-Vis-set		98.47 54	98.39 43	98.69 94	99.46 59	96.49 154	98.30 283	98.69 143	97.21 76	98.84 89	99.36 60	95.41 61	99.78 125	98.62 50	99.65 81	99.80 28

MSLP-MVS++		98.56 43	98.57 26	98.55 108	99.26 96	96.80 135	98.71 193	99.05 49	97.28 69	98.84 89	99.28 76	96.47 28	99.40 209	98.52 62	99.70 71	99.47 116

PHI-MVS		98.34 70	98.06 78	99.18 53	99.15 119	98.12 68	99.04 81	99.09 44	93.32 328	98.83 92	99.10 127	96.54 24	99.83 91	97.70 122	99.76 48	99.59 94

GDP-MVS		97.64 108	97.28 126	98.71 93	98.30 228	97.33 99	99.05 77	98.52 192	96.34 130	98.80 93	99.05 145	89.74 233	99.51 188	96.86 191	98.86 167	99.28 174

MVSFormer		97.57 118	97.49 105	97.84 201	98.07 271	95.76 212	99.47 7	98.40 236	94.98 227	98.79 94	98.83 185	92.34 130	98.41 373	96.91 179	99.59 95	99.34 150

lupinMVS		97.44 138	97.22 135	98.12 167	98.07 271	95.76 212	97.68 372	97.76 358	94.50 260	98.79 94	98.61 217	92.34 130	99.30 223	97.58 134	99.59 95	99.31 159

CDPH-MVS		97.94 89	97.49 105	99.28 42	99.47 57	98.44 38	97.91 345	98.67 151	92.57 362	98.77 96	98.85 180	95.93 46	99.72 138	95.56 241	99.69 72	99.68 75

CNVR-MVS		98.78 20	98.56 28	99.45 19	99.32 78	98.87 22	98.47 255	98.81 108	97.72 36	98.76 97	99.16 110	97.05 14	99.78 125	98.06 92	99.66 78	99.69 70

EI-MVSNet-UG-set		98.41 61	98.34 54	98.61 102	99.45 62	96.32 164	98.28 286	98.68 146	97.17 80	98.74 98	99.37 56	95.25 73	99.79 122	98.57 53	99.54 110	99.73 55

diffmvs		97.58 117	97.40 115	98.13 164	98.32 226	95.81 208	98.06 326	98.37 251	96.20 136	98.74 98	98.89 175	91.31 176	99.25 235	98.16 87	98.52 190	99.34 150
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		97.57 118	97.37 118	98.20 149	98.50 188	95.86 201	98.89 125	97.03 429	97.29 67	98.73 100	98.90 173	89.41 245	99.32 218	98.68 46	98.86 167	99.42 133

GST-MVS		98.43 59	98.12 75	99.34 32	99.72 17	98.38 42	99.09 70	98.82 102	95.71 166	98.73 100	99.06 143	95.27 71	99.93 34	97.07 171	99.63 88	99.72 59

UA-Net		97.96 87	97.62 94	98.98 73	98.86 152	97.47 93	98.89 125	99.08 45	96.67 111	98.72 102	99.54 20	93.15 117	99.81 103	94.87 263	98.83 170	99.65 83

NormalMVS		98.07 84	97.90 87	98.59 104	99.75 6	96.60 145	98.94 109	98.60 165	97.86 33	98.71 103	99.08 138	91.22 181	99.80 110	97.40 158	99.57 99	99.37 143

SymmetryMVS		97.84 95	97.58 96	98.62 100	99.01 134	96.60 145	98.94 109	98.44 216	97.86 33	98.71 103	99.08 138	91.22 181	99.80 110	97.40 158	97.53 262	99.47 116

LuminaMVS		97.49 129	97.18 138	98.42 130	97.50 332	97.15 120	98.45 257	97.68 361	96.56 118	98.68 105	98.78 194	89.84 230	99.32 218	98.60 51	98.57 185	98.79 253

h-mvs33		96.17 222	95.62 236	97.81 205	99.03 131	94.45 289	98.64 213	98.75 128	97.48 54	98.67 106	98.72 208	89.76 231	99.86 84	97.95 98	81.59 471	99.11 211

hse-mvs2		95.71 246	95.30 253	96.93 277	98.50 188	93.53 329	98.36 271	98.10 321	97.48 54	98.67 106	97.99 281	89.76 231	99.02 296	97.95 98	80.91 477	98.22 304

ZD-MVS					99.46 59	98.70 29		98.79 120	93.21 333	98.67 106	98.97 156	95.70 53	99.83 91	96.07 216	99.58 98

旧先验2							97.57 382		91.30 405	98.67 106			99.80 110	95.70 237

PS-MVSNAJ		97.73 100	97.77 89	97.62 229	98.68 172	95.58 219	97.34 401	98.51 195	97.29 67	98.66 110	97.88 293	94.51 92	99.90 65	97.87 107	99.17 150	97.39 333

onestephybrid01		97.54 125	97.36 119	98.06 176	98.25 239	95.63 217	98.26 289	98.33 262	96.13 139	98.65 111	99.13 118	91.02 193	99.25 235	98.07 91	98.42 208	99.31 159

xiu_mvs_v2_base		97.66 107	97.70 92	97.56 233	98.61 181	95.46 228	97.44 389	98.46 208	97.15 82	98.65 111	98.15 268	94.33 98	99.80 110	97.84 110	98.66 179	97.41 331

LFMVS		95.86 238	94.98 269	98.47 122	98.87 151	96.32 164	98.84 152	96.02 465	93.40 325	98.62 113	99.20 95	74.99 464	99.63 161	97.72 117	97.20 267	99.46 121

HPM-MVS		98.36 66	98.10 77	99.13 59	99.74 12	97.82 81	99.53 6	98.80 115	94.63 250	98.61 114	98.97 156	95.13 80	99.77 130	97.65 125	99.83 13	99.79 29
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
AstraMVS		97.34 152	97.24 132	97.65 226	98.13 265	94.15 307	98.94 109	96.25 464	97.47 56	98.60 115	99.28 76	89.67 235	99.41 208	98.73 44	98.07 235	99.38 142

testdata				98.26 142	99.20 110	95.36 238		98.68 146	91.89 385	98.60 115	99.10 127	94.44 97	99.82 98	94.27 294	99.44 126	99.58 98

CP-MVS		98.57 41	98.36 46	99.19 51	99.66 31	97.86 76	99.34 17	98.87 85	95.96 151	98.60 115	99.13 118	96.05 41	99.94 14	97.77 114	99.86 2	99.77 40

jason		97.32 154	97.08 149	98.06 176	97.45 338	95.59 218	97.87 353	97.91 345	94.79 240	98.55 118	98.83 185	91.12 188	99.23 247	97.58 134	99.60 93	99.34 150
jason: jason.
MCST-MVS		98.65 26	98.37 45	99.48 17	99.60 37	98.87 22	98.41 269	98.68 146	97.04 88	98.52 119	98.80 188	96.78 17	99.83 91	97.93 100	99.61 91	99.74 50

BP-MVS1		97.82 96	97.51 104	98.76 89	98.25 239	97.39 97	99.15 57	97.68 361	96.69 109	98.47 120	99.10 127	90.29 219	99.51 188	98.60 51	99.35 138	99.37 143

XVS		98.70 24	98.49 36	99.34 32	99.70 27	98.35 51	99.29 28	98.88 78	97.40 59	98.46 121	99.20 95	95.90 49	99.89 69	97.85 108	99.74 58	99.78 33

X-MVStestdata		94.06 367	92.30 393	99.34 32	99.70 27	98.35 51	99.29 28	98.88 78	97.40 59	98.46 121	43.50 547	95.90 49	99.89 69	97.85 108	99.74 58	99.78 33

MG-MVS		97.81 97	97.60 95	98.44 126	99.12 122	95.97 185	97.75 367	98.78 122	96.89 96	98.46 121	99.22 90	93.90 108	99.68 150	94.81 267	99.52 113	99.67 79

viewmamba		97.55 121	97.45 110	97.87 199	98.22 246	95.13 253	98.35 272	98.35 256	96.57 116	98.45 124	99.15 114	91.60 160	99.18 256	97.99 96	98.36 215	99.29 167

test_fmvsmvis_n_1920		98.44 57	98.51 32	98.23 146	98.33 223	96.15 172	98.97 99	99.15 41	98.55 16	98.45 124	99.55 18	94.26 101	99.97 1	99.65 18	99.66 78	98.57 287

NCCC		98.61 31	98.35 48	99.38 24	99.28 93	98.61 33	98.45 257	98.76 126	97.82 35	98.45 124	98.93 166	96.65 21	99.83 91	97.38 161	99.41 129	99.71 63

MVS_Test		97.28 156	97.00 156	98.13 164	98.33 223	95.97 185	98.74 182	98.07 328	94.27 269	98.44 127	98.07 273	92.48 126	99.26 231	96.43 207	98.19 230	99.16 201

MVS_111021_LR		98.34 70	98.23 67	98.67 96	99.27 94	96.90 131	97.95 338	99.58 3	97.14 83	98.44 127	99.01 152	95.03 84	99.62 165	97.91 103	99.75 54	99.50 107

balanced_ft_v1		97.54 125	97.38 117	98.02 181	98.34 219	95.58 219	99.32 22	98.40 236	95.88 155	98.43 129	98.65 215	88.95 265	99.59 168	98.94 36	99.48 121	98.90 243

hybridnocas07		97.41 141	97.21 136	97.99 185	98.24 242	95.42 230	98.21 294	98.32 266	95.97 150	98.38 130	98.93 166	90.48 210	99.21 252	97.92 102	98.46 197	99.34 150

ETV-MVS		97.96 87	97.81 88	98.40 132	98.42 201	97.27 107	98.73 188	98.55 185	96.84 98	98.38 130	97.44 335	95.39 62	99.35 214	97.62 127	98.89 163	98.58 286

test2506		94.44 338	93.91 336	96.04 352	99.02 132	88.99 449	99.06 74	79.47 525	96.96 93	98.36 132	99.26 80	77.21 445	99.52 187	96.78 196	99.04 154	99.59 94

VDDNet		95.36 270	94.53 291	97.86 200	98.10 268	95.13 253	98.85 148	97.75 359	90.46 422	98.36 132	99.39 50	73.27 474	99.64 158	97.98 97	96.58 288	98.81 251

hybrid		97.34 152	97.16 140	97.88 198	98.25 239	95.18 249	98.18 306	98.33 262	95.36 197	98.35 134	99.06 143	90.61 206	99.18 256	97.88 106	98.40 211	99.27 175

mPP-MVS		98.51 49	98.26 62	99.25 45	99.75 6	98.04 70	99.28 30	98.81 108	96.24 134	98.35 134	99.23 87	95.46 59	99.94 14	97.42 156	99.81 16	99.77 40

DELS-MVS		98.40 62	98.20 71	98.99 71	99.00 136	97.66 82	97.75 367	98.89 75	97.71 38	98.33 136	98.97 156	94.97 85	99.88 78	98.42 70	99.76 48	99.42 133
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 54	98.34 54	98.88 83	99.22 107	97.32 100	97.91 345	99.58 3	97.20 77	98.33 136	99.00 154	95.99 44	99.64 158	98.05 94	99.76 48	99.69 70

ZNCC-MVS		98.49 51	98.20 71	99.35 31	99.73 16	98.39 41	99.19 50	98.86 91	95.77 162	98.31 138	99.10 127	95.46 59	99.93 34	97.57 138	99.81 16	99.74 50

HPM-MVS++		98.58 36	98.25 63	99.55 11	99.50 49	99.08 13	98.72 192	98.66 154	97.51 51	98.15 139	98.83 185	95.70 53	99.92 43	97.53 142	99.67 75	99.66 82

mvsmamba		97.25 159	96.99 158	98.02 181	98.34 219	95.54 224	99.18 54	97.47 388	95.04 220	98.15 139	98.57 225	89.46 242	99.31 222	97.68 124	99.01 157	99.22 188

新几何1				99.16 56	99.34 72	98.01 72		98.69 143	90.06 430	98.13 141	98.95 163	94.60 90	99.89 69	91.97 374	99.47 122	99.59 94

API-MVS		97.41 141	97.25 128	97.91 194	98.70 167	96.80 135	98.82 156	98.69 143	94.53 255	98.11 142	98.28 255	94.50 95	99.57 172	94.12 301	99.49 118	97.37 335

ECVR-MVS		95.95 230	95.71 230	96.65 300	99.02 132	90.86 405	99.03 84	91.80 508	96.96 93	98.10 143	99.26 80	81.31 402	99.51 188	96.90 182	99.04 154	99.59 94

Casviewmamba		97.62 111	97.43 113	98.19 153	98.48 193	95.83 204	99.07 72	98.42 231	96.27 133	98.09 144	99.26 80	91.00 194	99.30 223	97.81 112	98.48 195	99.44 126

CPTT-MVS		97.72 101	97.32 123	98.92 79	99.64 33	97.10 123	99.12 64	98.81 108	92.34 370	98.09 144	99.08 138	93.01 118	99.92 43	96.06 219	99.77 42	99.75 48

viewcassd2359sk11		97.53 127	97.32 123	98.16 155	98.45 197	95.83 204	98.57 235	98.42 231	95.52 184	98.07 146	99.12 122	91.81 154	99.25 235	97.46 152	98.48 195	99.41 136

test12				99.18 53	99.16 116	98.19 61		98.53 189		98.07 146		95.13 80	99.72 138		99.56 107	99.63 88

E3new		97.55 121	97.35 121	98.16 155	98.48 193	95.85 202	98.55 239	98.41 233	95.42 191	98.06 148	99.12 122	92.23 137	99.24 243	97.43 154	98.45 198	99.39 138

RRT-MVS		97.03 174	96.78 174	97.77 210	97.90 298	94.34 296	99.12 64	98.35 256	95.87 157	98.06 148	98.70 209	86.45 325	99.63 161	98.04 95	98.54 188	99.35 148

test222					99.23 105	97.17 118	97.40 393	98.66 154	88.68 451	98.05 150	98.96 161	94.14 103			99.53 112	99.61 90

DP-MVS Recon		97.86 92	97.46 108	99.06 66	99.53 43	98.35 51	98.33 275	98.89 75	92.62 359	98.05 150	98.94 164	95.34 67	99.65 155	96.04 220	99.42 128	99.19 195

Vis-MVSNet		97.42 140	97.11 147	98.34 135	98.66 174	96.23 168	99.22 42	99.00 53	96.63 113	98.04 152	99.21 93	88.05 291	99.35 214	96.01 222	99.21 147	99.45 123
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test1111		95.94 233	95.78 224	96.41 334	98.99 139	90.12 424	99.04 81	92.45 507	96.99 92	98.03 153	99.27 79	81.40 401	99.48 198	96.87 188	99.04 154	99.63 88

baseline		97.64 108	97.44 111	98.25 143	98.35 214	96.20 169	99.00 92	98.32 266	96.33 132	98.03 153	99.17 107	91.35 173	99.16 261	98.10 89	98.29 222	99.39 138

test_yl		97.22 161	96.78 174	98.54 110	98.73 162	96.60 145	98.45 257	98.31 271	94.70 244	98.02 155	98.42 238	90.80 199	99.70 144	96.81 192	96.79 281	99.34 150

DCV-MVSNet		97.22 161	96.78 174	98.54 110	98.73 162	96.60 145	98.45 257	98.31 271	94.70 244	98.02 155	98.42 238	90.80 199	99.70 144	96.81 192	96.79 281	99.34 150

MTAPA		98.58 36	98.29 61	99.46 18	99.76 5	98.64 31	98.90 121	98.74 130	97.27 73	98.02 155	99.39 50	94.81 88	99.96 4	97.91 103	99.79 35	99.77 40

sss		97.39 143	96.98 160	98.61 102	98.60 182	96.61 144	98.22 293	98.93 65	93.97 284	98.01 158	98.48 233	91.98 147	99.85 85	96.45 206	98.15 231	99.39 138

E2		97.48 130	97.25 128	98.16 155	98.40 205	95.79 209	98.58 226	98.44 216	95.58 173	98.00 159	99.14 115	91.21 185	99.24 243	97.50 147	98.43 202	99.45 123

E3		97.48 130	97.25 128	98.16 155	98.38 208	95.79 209	98.58 226	98.44 216	95.58 173	98.00 159	99.14 115	91.25 179	99.24 243	97.50 147	98.44 199	99.45 123

alignmvs		97.56 120	97.07 150	99.01 70	98.66 174	98.37 49	98.83 154	98.06 333	96.74 105	98.00 159	97.65 316	90.80 199	99.48 198	98.37 73	96.56 289	99.19 195

viewmanbaseed2359cas		97.47 133	97.25 128	98.14 159	98.41 203	95.84 203	98.57 235	98.43 227	95.55 180	97.97 162	99.12 122	91.26 178	99.15 265	97.42 156	98.53 189	99.43 130

OMC-MVS		97.55 121	97.34 122	98.20 149	99.33 75	95.92 192	98.28 286	98.59 172	95.52 184	97.97 162	99.10 127	93.28 116	99.49 192	95.09 258	98.88 164	99.19 195

VDD-MVS		95.82 241	95.23 255	97.61 230	98.84 156	93.98 311	98.68 203	97.40 397	95.02 224	97.95 164	99.34 68	74.37 470	99.78 125	98.64 49	96.80 280	99.08 220

casdiffmvs		97.63 110	97.41 114	98.28 138	98.33 223	96.14 173	98.82 156	98.32 266	96.38 127	97.95 164	99.21 93	91.23 180	99.23 247	98.12 88	98.37 213	99.48 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PRO-TEST		96.74 190	97.06 152	95.76 376	98.37 211	88.85 452	99.06 74	98.02 338	96.35 129	97.94 166	98.76 202	87.22 310	99.49 192	98.42 70	99.40 132	98.94 238

PVSNet_BlendedMVS		96.73 193	96.60 186	97.12 260	99.25 97	95.35 240	98.26 289	99.26 16	94.28 268	97.94 166	97.46 332	92.74 122	99.81 103	96.88 185	93.32 356	96.20 437

PVSNet_Blended		97.38 144	97.12 146	98.14 159	99.25 97	95.35 240	97.28 407	99.26 16	93.13 338	97.94 166	98.21 263	92.74 122	99.81 103	96.88 185	99.40 132	99.27 175

DPM-MVS		97.55 121	96.99 158	99.23 49	99.04 130	98.55 34	97.17 421	98.35 256	94.85 237	97.93 169	98.58 222	95.07 82	99.71 143	92.60 353	99.34 139	99.43 130

MP-MVS		98.33 72	98.01 82	99.28 42	99.75 6	98.18 62	99.22 42	98.79 120	96.13 139	97.92 170	99.23 87	94.54 91	99.94 14	96.74 198	99.78 40	99.73 55
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Elysia		96.64 197	96.02 214	98.51 115	98.04 278	97.30 103	98.74 182	98.60 165	95.04 220	97.91 171	98.84 181	83.59 386	99.48 198	94.20 297	99.25 145	98.75 262

StellarMVS		96.64 197	96.02 214	98.51 115	98.04 278	97.30 103	98.74 182	98.60 165	95.04 220	97.91 171	98.84 181	83.59 386	99.48 198	94.20 297	99.25 145	98.75 262

MDTV_nov1_ep13_2view						84.26 484	96.89 444		90.97 414	97.90 173		89.89 229		93.91 308		99.18 200

test_prior2							97.80 362		96.12 142	97.89 174	98.69 210	95.96 45		96.89 183	99.60 93

viewmacassd2359aftdt		97.32 154	97.07 150	98.08 172	98.30 228	95.69 215	98.62 219	98.44 216	95.56 175	97.86 175	99.22 90	89.91 228	99.14 268	97.29 164	98.43 202	99.42 133

E5new		97.37 146	97.16 140	97.98 187	98.30 228	95.41 231	98.87 135	98.45 212	95.56 175	97.84 176	99.19 102	90.39 214	99.25 235	97.61 130	98.22 226	99.29 167

E6new		97.37 146	97.16 140	97.98 187	98.28 234	95.40 234	98.87 135	98.45 212	95.55 180	97.84 176	99.20 95	90.44 212	99.25 235	97.61 130	98.22 226	99.29 167

E6		97.37 146	97.16 140	97.98 187	98.28 234	95.40 234	98.87 135	98.45 212	95.55 180	97.84 176	99.20 95	90.44 212	99.25 235	97.61 130	98.22 226	99.29 167

E5		97.37 146	97.16 140	97.98 187	98.30 228	95.41 231	98.87 135	98.45 212	95.56 175	97.84 176	99.19 102	90.39 214	99.25 235	97.61 130	98.22 226	99.29 167

原ACMM1				98.65 98	99.32 78	96.62 142		98.67 151	93.27 332	97.81 180	98.97 156	95.18 77	99.83 91	93.84 310	99.46 125	99.50 107

E4		97.37 146	97.13 145	98.12 167	98.27 236	95.70 214	98.59 222	98.44 216	95.56 175	97.80 181	99.18 105	90.57 208	99.26 231	97.45 153	98.28 224	99.40 137

viewmambaseed2359dif		97.01 176	96.84 167	97.51 235	98.19 252	94.21 304	98.16 309	98.23 292	93.61 315	97.78 182	99.13 118	90.79 202	99.18 256	97.24 165	98.40 211	99.15 202

114514_t		96.93 181	96.27 202	98.92 79	99.50 49	97.63 84	98.85 148	98.90 73	84.80 480	97.77 183	99.11 125	92.84 120	99.66 154	94.85 264	99.77 42	99.47 116

casdiffmvs_mvg		97.72 101	97.48 107	98.44 126	98.42 201	96.59 149	98.92 118	98.44 216	96.20 136	97.76 184	99.20 95	91.66 159	99.23 247	98.27 84	98.41 210	99.49 112
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		96.60 200	96.33 200	97.41 242	97.90 298	93.93 313	97.35 400	98.41 233	92.84 351	97.76 184	97.45 334	91.10 190	99.20 253	96.26 212	97.91 240	99.11 211

PVSNet	91.96 18	96.35 213	96.15 206	96.96 275	99.17 112	92.05 383	96.08 465	98.68 146	93.69 305	97.75 186	97.80 303	88.86 267	99.69 149	94.26 295	99.01 157	99.15 202

TEST9					99.31 80	98.50 36	97.92 343	98.73 133	92.63 358	97.74 187	98.68 211	96.20 36	99.80 110

train_agg		97.97 86	97.52 103	99.33 36	99.31 80	98.50 36	97.92 343	98.73 133	92.98 344	97.74 187	98.68 211	96.20 36	99.80 110	96.59 199	99.57 99	99.68 75

FE-MVS		95.62 252	94.90 273	97.78 207	98.37 211	94.92 267	97.17 421	97.38 399	90.95 415	97.73 189	97.70 309	85.32 350	99.63 161	91.18 389	98.33 218	98.79 253

mmtdpeth		93.12 389	92.61 385	94.63 422	97.60 321	89.68 435	99.21 45	97.32 403	94.02 278	97.72 190	94.42 464	77.01 450	99.44 205	99.05 31	77.18 489	94.78 472

CANet		98.05 85	97.76 90	98.90 82	98.73 162	97.27 107	98.35 272	98.78 122	97.37 64	97.72 190	98.96 161	91.53 167	99.92 43	98.79 42	99.65 81	99.51 104

test_8					99.29 89	98.44 38	97.89 351	98.72 135	92.98 344	97.70 192	98.66 214	96.20 36	99.80 110

hybridcas		97.52 128	97.29 125	98.20 149	98.44 198	96.00 178	99.02 87	98.39 242	96.12 142	97.69 193	99.23 87	90.77 204	99.17 259	97.55 139	98.42 208	99.44 126

MP-MVS-pluss		98.31 73	97.92 85	99.49 16	99.72 17	98.88 21	98.43 265	98.78 122	94.10 274	97.69 193	99.42 46	95.25 73	99.92 43	98.09 90	99.80 25	99.67 79
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
sasdasda		97.67 105	97.23 133	98.98 73	98.70 167	98.38 42	99.34 17	98.39 242	96.76 103	97.67 195	97.40 339	92.26 134	99.49 192	98.28 81	96.28 303	99.08 220

canonicalmvs		97.67 105	97.23 133	98.98 73	98.70 167	98.38 42	99.34 17	98.39 242	96.76 103	97.67 195	97.40 339	92.26 134	99.49 192	98.28 81	96.28 303	99.08 220

PVSNet_Blended_VisFu		97.70 103	97.46 108	98.44 126	99.27 94	95.91 193	98.63 216	99.16 39	94.48 261	97.67 195	98.88 176	92.80 121	99.91 57	97.11 169	99.12 151	99.50 107

WTY-MVS		97.37 146	96.92 163	98.72 92	98.86 152	96.89 133	98.31 280	98.71 138	95.26 203	97.67 195	98.56 226	92.21 139	99.78 125	95.89 224	96.85 279	99.48 114

dtuplus		97.00 177	96.83 169	97.51 235	98.18 258	94.21 304	98.21 294	98.20 296	94.42 265	97.66 199	99.22 90	90.18 223	99.17 259	97.01 172	98.36 215	99.13 207

viewdifsd2359ckpt07		97.20 164	97.05 153	97.65 226	98.40 205	94.33 298	98.39 270	98.43 227	95.67 168	97.66 199	99.08 138	90.04 225	99.32 218	97.47 151	98.29 222	99.31 159

Effi-MVS+		97.12 171	96.69 180	98.39 133	98.19 252	96.72 140	97.37 397	98.43 227	93.71 302	97.65 201	98.02 277	92.20 140	99.25 235	96.87 188	97.79 245	99.19 195

thisisatest0530		96.01 227	95.36 246	97.97 191	98.38 208	95.52 225	98.88 132	94.19 495	94.04 276	97.64 202	98.31 253	83.82 384	99.46 203	95.29 252	97.70 251	98.93 240

tttt0517		96.07 225	95.51 239	97.78 207	98.41 203	94.84 270	99.28 30	94.33 491	94.26 270	97.64 202	98.64 216	84.05 377	99.47 202	95.34 247	97.60 254	99.03 228

viewdifsd2359ckpt11		96.30 215	96.13 207	96.81 286	98.10 268	92.10 379	98.49 253	98.40 236	96.02 146	97.61 204	99.31 71	86.37 327	99.29 226	97.52 143	93.36 355	99.04 226

viewmsd2359difaftdt		96.30 215	96.13 207	96.81 286	98.10 268	92.10 379	98.49 253	98.40 236	96.02 146	97.61 204	99.31 71	86.37 327	99.30 223	97.52 143	93.37 354	99.04 226

HyFIR lowres test		96.90 183	96.49 193	98.14 159	99.33 75	95.56 221	97.38 395	99.65 2	92.34 370	97.61 204	98.20 264	89.29 249	99.10 279	96.97 175	97.60 254	99.77 40

viewdifsd2359ckpt13		97.24 160	96.97 161	98.06 176	98.43 199	95.77 211	98.59 222	98.34 260	94.81 238	97.60 207	98.94 164	90.78 203	99.09 280	96.93 178	98.33 218	99.32 158

ACMMP		98.23 76	97.95 84	99.09 63	99.74 12	97.62 85	99.03 84	99.41 6	95.98 149	97.60 207	99.36 60	94.45 96	99.93 34	97.14 168	98.85 169	99.70 67
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MGCFI-Net		97.62 111	97.19 137	98.92 79	98.66 174	98.20 60	99.32 22	98.38 249	96.69 109	97.58 209	97.42 338	92.10 143	99.50 191	98.28 81	96.25 306	99.08 220

agg_prior					99.30 84	98.38 42		98.72 135		97.57 210			99.81 103

tpmrst		95.63 251	95.69 233	95.44 389	97.54 328	88.54 458	96.97 433	97.56 375	93.50 319	97.52 211	96.93 390	89.49 238	99.16 261	95.25 254	96.42 294	98.64 278

MDTV_nov1_ep13			95.40 241		97.48 333	88.34 462	96.85 449	97.29 406	93.74 298	97.48 212	97.26 349	89.18 252	99.05 286	91.92 375	97.43 264

FA-MVS(test-final)		96.41 212	95.94 218	97.82 204	98.21 248	95.20 248	97.80 362	97.58 372	93.21 333	97.36 213	97.70 309	89.47 240	99.56 175	94.12 301	97.99 237	98.71 268

viewdifsd2359ckpt09		97.13 170	96.79 172	98.14 159	98.43 199	95.90 194	98.52 242	98.37 251	94.32 267	97.33 214	98.86 179	90.23 222	99.16 261	96.81 192	98.25 225	99.36 147

icg_test_0407_2		96.56 204	96.50 192	96.73 291	97.99 285	92.82 363	97.18 418	98.27 281	95.16 208	97.30 215	98.79 190	91.53 167	98.10 407	94.74 269	97.54 258	99.27 175

IMVS_0407		96.74 190	96.64 184	97.05 266	97.99 285	92.82 363	98.45 257	98.27 281	95.16 208	97.30 215	98.79 190	91.53 167	99.06 285	94.74 269	97.54 258	99.27 175

EPMVS		94.99 295	94.48 294	96.52 321	97.22 353	91.75 388	97.23 409	91.66 509	94.11 273	97.28 217	96.81 399	85.70 340	98.84 324	93.04 334	97.28 266	98.97 234

EIA-MVS		97.75 99	97.58 96	98.27 139	98.38 208	96.44 156	99.01 90	98.60 165	95.88 155	97.26 218	97.53 329	94.97 85	99.33 217	97.38 161	99.20 148	99.05 225

SSM_0404		97.26 158	97.00 156	98.03 179	98.46 195	95.99 179	98.62 219	98.44 216	94.77 241	97.24 219	98.93 166	91.22 181	99.28 228	96.54 201	98.74 174	98.84 248

IS-MVSNet		97.22 161	96.88 164	98.25 143	98.85 155	96.36 162	99.19 50	97.97 339	95.39 193	97.23 220	98.99 155	91.11 189	98.93 311	94.60 281	98.59 182	99.47 116

testing3-2		95.45 261	95.34 247	95.77 375	98.69 170	88.75 454	98.87 135	97.21 414	96.13 139	97.22 221	97.68 314	77.95 438	99.65 155	97.58 134	96.77 283	98.91 242

EPP-MVSNet		97.46 134	97.28 126	97.99 185	98.64 178	95.38 237	99.33 21	98.31 271	93.61 315	97.19 222	99.07 142	94.05 104	99.23 247	96.89 183	98.43 202	99.37 143

thisisatest0515		95.61 255	94.89 274	97.76 211	98.15 264	95.15 252	96.77 452	94.41 489	92.95 346	97.18 223	97.43 336	84.78 359	99.45 204	94.63 277	97.73 250	98.68 272

IMVS_0403		96.74 190	96.61 185	97.12 260	97.99 285	92.82 363	98.47 255	98.27 281	95.16 208	97.13 224	98.79 190	91.44 170	99.26 231	94.74 269	97.54 258	99.27 175

CANet_DTU		96.96 180	96.55 188	98.21 147	98.17 262	96.07 177	97.98 336	98.21 294	97.24 74	97.13 224	98.93 166	86.88 317	99.91 57	95.00 261	99.37 137	98.66 276

CHOSEN 1792x2688		97.12 171	96.80 170	98.08 172	99.30 84	94.56 287	98.05 327	99.71 1	93.57 317	97.09 226	98.91 172	88.17 285	99.89 69	96.87 188	99.56 107	99.81 25

PatchT		93.06 390	91.97 397	96.35 339	96.69 389	92.67 368	94.48 497	97.08 423	86.62 467	97.08 227	92.23 493	87.94 293	97.90 432	78.89 493	96.69 284	98.49 291

PatchmatchNet		95.71 246	95.52 237	96.29 344	97.58 323	90.72 409	96.84 450	97.52 383	94.06 275	97.08 227	96.96 385	89.24 251	98.90 317	92.03 371	98.37 213	99.26 182
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MAR-MVS		96.91 182	96.40 196	98.45 124	98.69 170	96.90 131	98.66 210	98.68 146	92.40 369	97.07 229	97.96 284	91.54 166	99.75 133	93.68 314	98.92 161	98.69 270
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		97.46 134	97.11 147	98.50 118	99.50 49	96.41 159	98.63 216	98.60 165	95.18 207	97.06 230	98.06 274	94.26 101	99.57 172	93.80 312	98.87 166	99.52 101

TAMVS		97.02 175	96.79 172	97.70 217	98.06 274	95.31 243	98.52 242	98.31 271	93.95 285	97.05 231	98.61 217	93.49 112	98.52 355	95.33 248	97.81 244	99.29 167

CSCG		97.85 94	97.74 91	98.20 149	99.67 30	95.16 250	99.22 42	99.32 12	93.04 342	97.02 232	98.92 171	95.36 65	99.91 57	97.43 154	99.64 86	99.52 101

CDS-MVSNet		96.99 178	96.69 180	97.90 195	98.05 276	95.98 180	98.20 298	98.33 262	93.67 309	96.95 233	98.49 232	93.54 111	98.42 366	95.24 255	97.74 249	99.31 159
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
XVG-OURS-SEG-HR		96.51 206	96.34 199	97.02 268	98.77 160	93.76 318	97.79 364	98.50 200	95.45 188	96.94 234	99.09 135	87.87 296	99.55 182	96.76 197	95.83 317	97.74 321

CR-MVSNet		94.76 312	94.15 317	96.59 311	97.00 367	93.43 332	94.96 486	97.56 375	92.46 363	96.93 235	96.24 423	88.15 286	97.88 437	87.38 448	96.65 286	98.46 293

RPMNet		92.81 392	91.34 403	97.24 249	97.00 367	93.43 332	94.96 486	98.80 115	82.27 487	96.93 235	92.12 494	86.98 315	99.82 98	76.32 501	96.65 286	98.46 293

SCA		95.46 259	95.13 259	96.46 330	97.67 315	91.29 397	97.33 402	97.60 371	94.68 247	96.92 237	97.10 360	83.97 379	98.89 318	92.59 355	98.32 221	99.20 191

PatchMatch-RL		96.59 201	96.03 213	98.27 139	99.31 80	96.51 153	97.91 345	99.06 47	93.72 301	96.92 237	98.06 274	88.50 278	99.65 155	91.77 379	99.00 159	98.66 276

DeepC-MVS	95.98 3	97.88 91	97.58 96	98.77 88	99.25 97	96.93 129	98.83 154	98.75 128	96.96 93	96.89 239	99.50 31	90.46 211	99.87 80	97.84 110	99.76 48	99.52 101
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
casdiffseed414692147		96.97 179	96.55 188	98.25 143	98.26 237	96.28 167	98.93 115	98.33 262	94.99 225	96.87 240	99.09 135	88.97 263	99.07 283	95.70 237	97.77 247	99.39 138

XVG-OURS		96.55 205	96.41 195	96.99 269	98.75 161	93.76 318	97.50 386	98.52 192	95.67 168	96.83 241	99.30 74	88.95 265	99.53 184	95.88 225	96.26 305	97.69 324

AdaColmap		97.15 169	96.70 179	98.48 121	99.16 116	96.69 141	98.01 332	98.89 75	94.44 263	96.83 241	98.68 211	90.69 205	99.76 131	94.36 289	99.29 144	98.98 233

CostFormer		94.95 302	94.73 280	95.60 383	97.28 349	89.06 446	97.53 383	96.89 442	89.66 437	96.82 243	96.72 403	86.05 334	98.95 310	95.53 243	96.13 311	98.79 253

UGNet		96.78 189	96.30 201	98.19 153	98.24 242	95.89 199	98.88 132	98.93 65	97.39 61	96.81 244	97.84 297	82.60 391	99.90 65	96.53 203	99.49 118	98.79 253
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		97.45 137	97.03 155	98.73 91	99.05 129	97.44 96	98.07 325	98.53 189	95.32 200	96.80 245	98.53 227	93.32 114	99.72 138	94.31 293	99.31 143	99.02 229

CHOSEN 280x420		97.18 166	97.18 138	97.20 251	98.81 158	93.27 346	95.78 472	99.15 41	95.25 204	96.79 246	98.11 271	92.29 133	99.07 283	98.56 55	99.85 6	99.25 184

mamba_0408		96.81 188	96.38 197	98.09 171	98.19 252	95.90 194	95.69 473	98.32 266	94.51 258	96.75 247	98.73 205	90.99 195	99.27 230	95.83 227	98.43 202	99.10 213

SSM_04072		96.71 194	96.38 197	97.68 220	98.19 252	95.90 194	95.69 473	98.32 266	94.51 258	96.75 247	98.73 205	90.99 195	98.02 422	95.83 227	98.43 202	99.10 213

SSM_0407		97.17 167	96.87 165	98.08 172	98.19 252	95.90 194	98.52 242	98.44 216	94.77 241	96.75 247	98.93 166	91.22 181	99.22 251	96.54 201	98.43 202	99.10 213

HY-MVS	93.96 8	96.82 187	96.23 205	98.57 105	98.46 195	97.00 126	98.14 313	98.21 294	93.95 285	96.72 250	97.99 281	91.58 161	99.76 131	94.51 285	96.54 290	98.95 237

PAPR		96.84 186	96.24 204	98.65 98	98.72 166	96.92 130	97.36 399	98.57 179	93.33 327	96.67 251	97.57 325	94.30 99	99.56 175	91.05 397	98.59 182	99.47 116

Anonymous20240529		95.10 287	94.22 311	97.75 212	99.01 134	94.26 301	98.87 135	98.83 98	85.79 475	96.64 252	98.97 156	78.73 427	99.85 85	96.27 211	94.89 323	99.12 208

UWE-MVS		94.30 345	93.89 339	95.53 384	97.83 302	88.95 450	97.52 385	93.25 500	94.44 263	96.63 253	97.07 367	78.70 428	99.28 228	91.99 372	97.56 257	98.36 298

thres600view7		95.49 257	94.77 277	97.67 222	98.98 140	95.02 258	98.85 148	96.90 440	95.38 194	96.63 253	96.90 392	84.29 369	99.59 168	88.65 435	96.33 296	98.40 295

thres100view900		95.38 267	94.70 282	97.41 242	98.98 140	94.92 267	98.87 135	96.90 440	95.38 194	96.61 255	96.88 393	84.29 369	99.56 175	88.11 439	96.29 300	97.76 319

Vis-MVSNet (Re-imp)		96.87 184	96.55 188	97.83 202	98.73 162	95.46 228	99.20 48	98.30 278	94.96 229	96.60 256	98.87 177	90.05 224	98.59 350	93.67 316	98.60 181	99.46 121

CVMVSNet		95.43 263	96.04 212	93.57 443	97.93 296	83.62 487	98.12 316	98.59 172	95.68 167	96.56 257	99.02 148	87.51 303	97.51 455	93.56 320	97.44 263	99.60 92

RPSCF		94.87 306	95.40 241	93.26 449	98.89 147	82.06 494	98.33 275	98.06 333	90.30 427	96.56 257	99.26 80	87.09 312	99.49 192	93.82 311	96.32 297	98.24 302

tfpn200view9		95.32 274	94.62 286	97.43 240	98.94 144	94.98 263	98.68 203	96.93 438	95.33 198	96.55 259	96.53 412	84.23 373	99.56 175	88.11 439	96.29 300	97.76 319

thres400		95.38 267	94.62 286	97.65 226	98.94 144	94.98 263	98.68 203	96.93 438	95.33 198	96.55 259	96.53 412	84.23 373	99.56 175	88.11 439	96.29 300	98.40 295

thres200		95.25 277	94.57 289	97.28 248	98.81 158	94.92 267	98.20 298	97.11 421	95.24 206	96.54 261	96.22 427	84.58 366	99.53 184	87.93 445	96.50 292	97.39 333

ab-mvs		96.42 209	95.71 230	98.55 108	98.63 179	96.75 138	97.88 352	98.74 130	93.84 291	96.54 261	98.18 266	85.34 348	99.75 133	95.93 223	96.35 295	99.15 202

Anonymous202405211		95.28 276	94.49 293	97.67 222	99.00 136	93.75 320	98.70 197	97.04 428	90.66 418	96.49 263	98.80 188	78.13 434	99.83 91	96.21 215	95.36 322	99.44 126

ADS-MVSNet2		94.58 324	94.40 303	95.11 399	98.00 283	88.74 455	96.04 466	97.30 405	90.15 428	96.47 264	96.64 409	87.89 294	97.56 453	90.08 409	97.06 271	99.02 229

ADS-MVSNet		95.00 293	94.45 299	96.63 305	98.00 283	91.91 385	96.04 466	97.74 360	90.15 428	96.47 264	96.64 409	87.89 294	98.96 305	90.08 409	97.06 271	99.02 229

Effi-MVS+-dtu		96.29 217	96.56 187	95.51 385	97.89 300	90.22 423	98.80 165	98.10 321	96.57 116	96.45 266	96.66 406	90.81 198	98.91 314	95.72 234	97.99 237	97.40 332

ETVMVS		94.50 332	93.44 366	97.68 220	98.18 258	95.35 240	98.19 301	97.11 421	93.73 299	96.40 267	95.39 453	74.53 467	98.84 324	91.10 391	96.31 298	98.84 248

PLC	95.07 4	97.20 164	96.78 174	98.44 126	99.29 89	96.31 166	98.14 313	98.76 126	92.41 368	96.39 268	98.31 253	94.92 87	99.78 125	94.06 304	98.77 173	99.23 186
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		94.13 359	93.80 345	95.12 398	96.50 399	87.91 468	97.44 389	95.89 471	92.62 359	96.37 269	96.30 422	84.13 376	98.30 389	93.24 326	91.66 380	99.14 205

TAPA-MVS	93.98 7	95.35 271	94.56 290	97.74 213	99.13 120	94.83 272	98.33 275	98.64 159	86.62 467	96.29 270	98.61 217	94.00 106	99.29 226	80.00 487	99.41 129	99.09 216
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dtuonly		95.08 290	95.10 263	95.02 403	96.53 396	87.27 473	96.33 464	97.21 414	93.41 324	96.28 271	98.51 231	87.71 298	98.99 300	91.88 376	98.01 236	98.80 252

myMVS_eth3d28		95.12 285	94.62 286	96.64 304	98.17 262	92.17 375	98.02 331	97.32 403	95.41 192	96.22 272	96.05 433	78.01 436	99.13 270	95.22 256	97.16 268	98.60 281

baseline1		95.84 239	95.12 261	98.01 183	98.49 192	95.98 180	98.73 188	97.03 429	95.37 196	96.22 272	98.19 265	89.96 227	99.16 261	94.60 281	87.48 434	98.90 243

tpm2		94.19 354	93.76 350	95.46 388	97.23 352	89.04 447	97.31 405	96.85 446	87.08 460	96.21 274	96.79 400	83.75 385	98.74 335	92.43 363	96.23 308	98.59 284

UBG		95.32 274	94.72 281	97.13 258	98.05 276	93.26 347	97.87 353	97.20 417	94.96 229	96.18 275	95.66 450	80.97 408	99.35 214	94.47 287	97.08 270	98.78 257

F-COLMAP		97.09 173	96.80 170	97.97 191	99.45 62	94.95 266	98.55 239	98.62 164	93.02 343	96.17 276	98.58 222	94.01 105	99.81 103	93.95 306	98.90 162	99.14 205

GeoE		96.58 203	96.07 210	98.10 170	98.35 214	95.89 199	99.34 17	98.12 315	93.12 339	96.09 277	98.87 177	89.71 234	98.97 301	92.95 337	98.08 234	99.43 130

JIA-IIPM		93.35 379	92.49 389	95.92 363	96.48 401	90.65 411	95.01 484	96.96 436	85.93 473	96.08 278	87.33 512	87.70 301	98.78 333	91.35 387	95.58 320	98.34 299

BH-RMVSNet		95.92 235	95.32 251	97.69 218	98.32 226	94.64 279	98.19 301	97.45 393	94.56 253	96.03 279	98.61 217	85.02 353	99.12 273	90.68 402	99.06 153	99.30 164

dp		94.15 358	93.90 337	94.90 408	97.31 348	86.82 475	96.97 433	97.19 418	91.22 410	96.02 280	96.61 411	85.51 344	99.02 296	90.00 413	94.30 325	98.85 246

EPNet		97.28 156	96.87 165	98.51 115	94.98 455	96.14 173	98.90 121	97.02 432	98.28 21	95.99 281	99.11 125	91.36 172	99.89 69	96.98 174	99.19 149	99.50 107
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LS3D		97.16 168	96.66 183	98.68 95	98.53 187	97.19 117	98.93 115	98.90 73	92.83 352	95.99 281	99.37 56	92.12 142	99.87 80	93.67 316	99.57 99	98.97 234

SDMVSNet		96.85 185	96.42 194	98.14 159	99.30 84	96.38 160	99.21 45	99.23 27	95.92 152	95.96 283	98.76 202	85.88 337	99.44 205	97.93 100	95.59 318	98.60 281

sd_testset		96.17 222	95.76 225	97.42 241	99.30 84	94.34 296	98.82 156	99.08 45	95.92 152	95.96 283	98.76 202	82.83 390	99.32 218	95.56 241	95.59 318	98.60 281

AUN-MVS		94.53 329	93.73 352	96.92 280	98.50 188	93.52 330	98.34 274	98.10 321	93.83 293	95.94 285	97.98 283	85.59 343	99.03 292	94.35 290	80.94 476	98.22 304

testing222		94.12 361	93.03 376	97.37 247	98.02 281	94.66 277	97.94 341	96.65 455	94.63 250	95.78 286	95.76 441	71.49 477	98.92 312	91.17 390	95.88 315	98.52 289

TR-MVS		94.94 304	94.20 312	97.17 255	97.75 307	94.14 308	97.59 380	97.02 432	92.28 374	95.75 287	97.64 319	83.88 381	98.96 305	89.77 415	96.15 310	98.40 295

WB-MVSnew		94.19 354	94.04 323	94.66 420	96.82 381	92.14 376	97.86 355	95.96 468	93.50 319	95.64 288	96.77 401	88.06 290	97.99 426	84.87 467	96.86 277	93.85 489

MonoMVSNet		95.51 256	95.45 240	95.68 378	95.54 442	90.87 404	98.92 118	97.37 400	95.79 161	95.53 289	97.38 341	89.58 237	97.68 446	96.40 208	92.59 366	98.49 291

VPA-MVSNet		95.75 244	95.11 262	97.69 218	97.24 351	97.27 107	98.94 109	99.23 27	95.13 213	95.51 290	97.32 346	85.73 339	98.91 314	97.33 163	89.55 408	96.89 359

testing91		94.98 297	94.25 310	97.20 251	97.94 294	93.41 334	98.00 334	97.58 372	94.99 225	95.45 291	96.04 434	77.20 446	99.42 207	94.97 262	96.02 313	98.78 257

testing99		94.83 307	94.08 321	97.07 265	97.94 294	93.13 353	98.10 322	97.17 419	94.86 235	95.34 292	96.00 438	76.31 454	99.40 209	95.08 259	95.90 314	98.68 272

HQP_MVS		96.14 224	95.90 220	96.85 283	97.42 340	94.60 285	98.80 165	98.56 183	97.28 69	95.34 292	98.28 255	87.09 312	99.03 292	96.07 216	94.27 326	96.92 351

plane_prior3						94.61 283			97.02 89	95.34 292

testing11		95.00 293	94.28 306	97.16 256	97.96 293	93.36 340	98.09 323	97.06 427	94.94 233	95.33 295	96.15 429	76.89 451	99.40 209	95.77 233	96.30 299	98.72 265

Fast-Effi-MVS+		96.28 219	95.70 232	98.03 179	98.29 232	95.97 185	98.58 226	98.25 290	91.74 388	95.29 296	97.23 353	91.03 192	99.15 265	92.90 339	97.96 239	98.97 234

test_fmvs2		93.43 377	93.58 359	92.95 456	96.97 370	83.91 486	99.19 50	97.24 411	95.74 163	95.20 297	98.27 258	69.65 479	98.72 337	96.26 212	93.73 343	96.24 435

EI-MVSNet		95.96 229	95.83 222	96.36 338	97.93 296	93.70 324	98.12 316	98.27 281	93.70 304	95.07 298	99.02 148	92.23 137	98.54 353	94.68 274	93.46 349	96.84 366

MVSTER		96.06 226	95.72 227	97.08 264	98.23 245	95.93 191	98.73 188	98.27 281	94.86 235	95.07 298	98.09 272	88.21 284	98.54 353	96.59 199	93.46 349	96.79 370

OPM-MVS		95.69 249	95.33 250	96.76 290	96.16 416	94.63 280	98.43 265	98.39 242	96.64 112	95.02 300	98.78 194	85.15 352	99.05 286	95.21 257	94.20 329	96.60 396
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+-dtu		95.87 237	95.85 221	95.91 364	97.74 310	91.74 389	98.69 200	98.15 311	95.56 175	94.92 301	97.68 314	88.98 262	98.79 332	93.19 328	97.78 246	97.20 339

TESTMET0.1,1		94.18 357	93.69 355	95.63 381	96.92 373	89.12 445	96.91 439	94.78 486	93.17 335	94.88 302	96.45 416	78.52 429	98.92 312	93.09 331	98.50 192	98.85 246

VPNet		94.99 295	94.19 313	97.40 244	97.16 360	96.57 150	98.71 193	98.97 57	95.67 168	94.84 303	98.24 262	80.36 415	98.67 342	96.46 205	87.32 438	96.96 346

1112_ss		96.63 199	96.00 216	98.50 118	98.56 183	96.37 161	98.18 306	98.10 321	92.92 347	94.84 303	98.43 236	92.14 141	99.58 171	94.35 290	96.51 291	99.56 100

test-LLR		95.10 287	94.87 275	95.80 372	96.77 383	89.70 433	96.91 439	95.21 478	95.11 215	94.83 305	95.72 446	87.71 298	98.97 301	93.06 332	98.50 192	98.72 265

test-mter		94.08 365	93.51 363	95.80 372	96.77 383	89.70 433	96.91 439	95.21 478	92.89 349	94.83 305	95.72 446	77.69 440	98.97 301	93.06 332	98.50 192	98.72 265

Test_1112_low_res		96.34 214	95.66 235	98.36 134	98.56 183	95.94 188	97.71 370	98.07 328	92.10 380	94.79 307	97.29 348	91.75 155	99.56 175	94.17 299	96.50 292	99.58 98

UWE-MVS-28		92.79 393	92.51 388	93.62 442	96.46 402	86.28 477	97.93 342	92.71 505	94.17 271	94.78 308	97.16 357	81.05 407	96.43 478	81.45 482	96.86 277	98.14 309

GA-MVS		94.81 308	94.03 325	97.14 257	97.15 361	93.86 315	96.76 453	97.58 372	94.00 282	94.76 309	97.04 375	80.91 409	98.48 357	91.79 378	96.25 306	99.09 216

BH-untuned		95.95 230	95.72 227	96.65 300	98.55 185	92.26 374	98.23 292	97.79 357	93.73 299	94.62 310	98.01 279	88.97 263	99.00 299	93.04 334	98.51 191	98.68 272

test_djsdf		96.00 228	95.69 233	96.93 277	95.72 436	95.49 226	99.47 7	98.40 236	94.98 227	94.58 311	97.86 294	89.16 253	98.41 373	96.91 179	94.12 334	96.88 360

cascas		94.63 320	93.86 341	96.93 277	96.91 375	94.27 300	96.00 469	98.51 195	85.55 477	94.54 312	96.23 425	84.20 375	98.87 321	95.80 231	96.98 276	97.66 325

DP-MVS		96.59 201	95.93 219	98.57 105	99.34 72	96.19 171	98.70 197	98.39 242	89.45 441	94.52 313	99.35 62	91.85 151	99.85 85	92.89 341	98.88 164	99.68 75

gg-mvs-nofinetune		92.21 401	90.58 410	97.13 258	96.75 386	95.09 255	95.85 470	89.40 515	85.43 478	94.50 314	81.98 518	80.80 412	98.40 379	92.16 365	98.33 218	97.88 316

mvs_anonymous		96.70 196	96.53 191	97.18 254	98.19 252	93.78 317	98.31 280	98.19 299	94.01 281	94.47 315	98.27 258	92.08 145	98.46 361	97.39 160	97.91 240	99.31 159

HQP-NCC					97.20 355		98.05 327		96.43 121	94.45 316

ACMP_Plane					97.20 355		98.05 327		96.43 121	94.45 316

HQP4-MVS										94.45 316			98.96 305			96.87 363

HQP-MVS		95.72 245	95.40 241	96.69 297	97.20 355	94.25 302	98.05 327	98.46 208	96.43 121	94.45 316	97.73 306	86.75 318	98.96 305	95.30 250	94.18 330	96.86 365

MSDG		95.93 234	95.30 253	97.83 202	98.90 146	95.36 238	96.83 451	98.37 251	91.32 404	94.43 320	98.73 205	90.27 220	99.60 167	90.05 411	98.82 171	98.52 289

dmvs_re		94.48 335	94.18 315	95.37 391	97.68 314	90.11 425	98.54 241	97.08 423	94.56 253	94.42 321	97.24 352	84.25 371	97.76 443	91.02 398	92.83 363	98.24 302

nrg030		96.28 219	95.72 227	97.96 193	96.90 376	98.15 65	99.39 11	98.31 271	95.47 187	94.42 321	98.35 246	92.09 144	98.69 338	97.50 147	89.05 417	97.04 342

CLD-MVS		95.62 252	95.34 247	96.46 330	97.52 331	93.75 320	97.27 408	98.46 208	95.53 183	94.42 321	98.00 280	86.21 331	98.97 301	96.25 214	94.37 324	96.66 388
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		95.62 252	95.34 247	96.47 327	97.46 335	93.54 327	98.99 95	98.54 187	94.67 248	94.36 324	98.77 197	85.39 345	99.11 275	95.71 235	94.15 332	96.76 373

LGP-MVS_train				96.47 327	97.46 335	93.54 327		98.54 187	94.67 248	94.36 324	98.77 197	85.39 345	99.11 275	95.71 235	94.15 332	96.76 373

v144192		94.39 341	93.70 354	96.48 326	96.06 420	94.35 295	98.58 226	98.16 310	91.45 397	94.33 326	97.02 378	87.50 305	98.45 362	91.08 394	89.11 416	96.63 390

IMVS_0404		95.82 241	95.52 237	96.73 291	97.99 285	92.82 363	97.23 409	98.27 281	95.16 208	94.31 327	98.79 190	85.63 341	98.10 407	94.74 269	97.54 258	99.27 175

V42		94.78 310	94.14 318	96.70 296	96.33 408	95.22 247	98.97 99	98.09 325	92.32 372	94.31 327	97.06 371	88.39 279	98.55 352	92.90 339	88.87 421	96.34 430

VortexMVS		95.95 230	95.79 223	96.42 333	98.29 232	93.96 312	98.68 203	98.31 271	96.02 146	94.29 329	97.57 325	89.47 240	98.37 380	97.51 146	91.93 374	96.94 349

ACMM	93.85 9	95.69 249	95.38 245	96.61 308	97.61 320	93.84 316	98.91 120	98.44 216	95.25 204	94.28 330	98.47 234	86.04 336	99.12 273	95.50 244	93.95 339	96.87 363
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS-LS		95.46 259	95.21 256	96.22 346	98.12 266	93.72 323	98.32 279	98.13 314	93.71 302	94.26 331	97.31 347	92.24 136	98.10 407	94.63 277	90.12 399	96.84 366
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		94.20 353	93.47 365	96.40 336	95.98 424	94.08 309	98.52 242	98.15 311	91.33 403	94.25 332	97.20 356	86.41 326	98.42 366	90.04 412	89.39 413	96.69 387

BH-w/o		95.38 267	95.08 264	96.26 345	98.34 219	91.79 386	97.70 371	97.43 395	92.87 350	94.24 333	97.22 354	88.66 271	98.84 324	91.55 385	97.70 251	98.16 308

XVG-ACMP-BASELINE		94.54 327	94.14 318	95.75 377	96.55 395	91.65 391	98.11 320	98.44 216	94.96 229	94.22 334	97.90 290	79.18 425	99.11 275	94.05 305	93.85 341	96.48 424

v1144		94.59 323	93.92 334	96.60 310	96.21 410	94.78 276	98.59 222	98.14 313	91.86 387	94.21 335	97.02 378	87.97 292	98.41 373	91.72 380	89.57 406	96.61 394

v1192		94.32 344	93.58 359	96.53 320	96.10 418	94.45 289	98.50 250	98.17 308	91.54 395	94.19 336	97.06 371	86.95 316	98.43 365	90.14 407	89.57 406	96.70 382

PAPM		94.95 302	94.00 329	97.78 207	97.04 366	95.65 216	96.03 468	98.25 290	91.23 409	94.19 336	97.80 303	91.27 177	98.86 323	82.61 478	97.61 253	98.84 248

Patchmatch-test		94.42 339	93.68 356	96.63 305	97.60 321	91.76 387	94.83 490	97.49 387	89.45 441	94.14 338	97.10 360	88.99 259	98.83 327	85.37 464	98.13 232	99.29 167

v1240		94.06 367	93.29 371	96.34 340	96.03 422	93.90 314	98.44 263	98.17 308	91.18 412	94.13 339	97.01 380	86.05 334	98.42 366	89.13 429	89.50 410	96.70 382

GBi-Net		94.49 333	93.80 345	96.56 315	98.21 248	95.00 259	98.82 156	98.18 302	92.46 363	94.09 340	97.07 367	81.16 404	97.95 428	92.08 367	92.14 371	96.72 378

test1		94.49 333	93.80 345	96.56 315	98.21 248	95.00 259	98.82 156	98.18 302	92.46 363	94.09 340	97.07 367	81.16 404	97.95 428	92.08 367	92.14 371	96.72 378

FMVSNet3		94.97 299	94.26 309	97.11 262	98.18 258	96.62 142	98.56 238	98.26 289	93.67 309	94.09 340	97.10 360	84.25 371	98.01 423	92.08 367	92.14 371	96.70 382

MIMVSNet		93.26 383	92.21 394	96.41 334	97.73 311	93.13 353	95.65 475	97.03 429	91.27 408	94.04 343	96.06 432	75.33 460	97.19 460	86.56 454	96.23 308	98.92 241

FIs		96.51 206	96.12 209	97.67 222	97.13 362	97.54 89	99.36 14	99.22 32	95.89 154	94.03 344	98.35 246	91.98 147	98.44 364	96.40 208	92.76 364	97.01 343

v2v482		94.69 313	94.03 325	96.65 300	96.17 414	94.79 275	98.67 208	98.08 326	92.72 354	94.00 345	97.16 357	87.69 302	98.45 362	92.91 338	88.87 421	96.72 378

testing3		93.19 386	92.48 390	95.30 394	98.07 271	92.27 372	98.64 213	97.17 419	93.94 287	93.98 346	97.04 375	67.97 484	96.01 484	88.40 437	97.14 269	97.63 326

FC-MVSNet-test		96.42 209	96.05 211	97.53 234	96.95 371	97.27 107	99.36 14	99.23 27	95.83 159	93.93 347	98.37 244	92.00 146	98.32 385	96.02 221	92.72 365	97.00 344

UniMVSNet (Re)		95.78 243	95.19 257	97.58 231	96.99 369	97.47 93	98.79 173	99.18 36	95.60 171	93.92 348	97.04 375	91.68 157	98.48 357	95.80 231	87.66 433	96.79 370

miper_enhance_ethall		95.10 287	94.75 279	96.12 350	97.53 330	93.73 322	96.61 458	98.08 326	92.20 378	93.89 349	96.65 408	92.44 127	98.30 389	94.21 296	91.16 386	96.34 430

UniMVSNet_NR-MVSNet		95.71 246	95.15 258	97.40 244	96.84 379	96.97 127	98.74 182	99.24 20	95.16 208	93.88 350	97.72 308	91.68 157	98.31 387	95.81 229	87.25 439	96.92 351

DU-MVS		95.42 264	94.76 278	97.40 244	96.53 396	96.97 127	98.66 210	98.99 56	95.43 189	93.88 350	97.69 311	88.57 273	98.31 387	95.81 229	87.25 439	96.92 351

usedtu_dtu_shiyan1		94.96 300	94.28 306	96.98 272	95.93 427	96.11 175	97.08 427	98.39 242	93.62 313	93.86 352	96.40 418	88.28 281	98.21 396	92.61 350	92.36 369	96.63 390

FE-MVSNET3		94.96 300	94.28 306	96.98 272	95.93 427	96.11 175	97.08 427	98.39 242	93.62 313	93.86 352	96.40 418	88.28 281	98.21 396	92.61 350	92.36 369	96.63 390

Baseline_NR-MVSNet		94.35 342	93.81 344	95.96 362	96.20 411	94.05 310	98.61 221	96.67 453	91.44 398	93.85 354	97.60 322	88.57 273	98.14 403	94.39 288	86.93 442	95.68 451

PS-MVSNAJss		96.43 208	96.26 203	96.92 280	95.84 433	95.08 256	99.16 56	98.50 200	95.87 157	93.84 355	98.34 250	94.51 92	98.61 346	96.88 185	93.45 351	97.06 341

UniMVSNet_ETH3D		94.24 351	93.33 369	96.97 274	97.19 358	93.38 338	98.74 182	98.57 179	91.21 411	93.81 356	98.58 222	72.85 476	98.77 334	95.05 260	93.93 340	98.77 260

tt0805		94.54 327	93.85 342	96.63 305	97.98 291	93.06 358	98.77 177	97.84 348	93.67 309	93.80 357	98.04 276	76.88 452	98.96 305	94.79 268	92.86 362	97.86 318

tpmvs		94.60 321	94.36 304	95.33 393	97.46 335	88.60 457	96.88 447	97.68 361	91.29 406	93.80 357	96.42 417	88.58 272	99.24 243	91.06 395	96.04 312	98.17 307

WBMVS		94.56 325	94.04 323	96.10 351	98.03 280	93.08 357	97.82 361	98.18 302	94.02 278	93.77 359	96.82 398	81.28 403	98.34 382	95.47 246	91.00 389	96.88 360

3Dnovator	94.51 5	97.46 134	96.93 162	99.07 65	97.78 305	97.64 83	99.35 16	99.06 47	97.02 89	93.75 360	99.16 110	89.25 250	99.92 43	97.22 167	99.75 54	99.64 86

eth_miper_zixun_eth		94.68 315	94.41 302	95.47 387	97.64 318	91.71 390	96.73 455	98.07 328	92.71 355	93.64 361	97.21 355	90.54 209	98.17 400	93.38 322	89.76 403	96.54 410

SD_0403		94.28 349	94.46 296	93.73 440	98.02 281	85.32 482	98.31 280	98.40 236	94.75 243	93.59 362	98.16 267	89.01 258	96.54 475	82.32 479	97.58 256	99.34 150

ITE_SJBPF				95.44 389	97.42 340	91.32 396		97.50 385	95.09 218	93.59 362	98.35 246	81.70 399	98.88 320	89.71 417	93.39 353	96.12 440

TranMVSNet+NR-MVSNet		95.14 284	94.48 294	97.11 262	96.45 403	96.36 162	99.03 84	99.03 50	95.04 220	93.58 364	97.93 287	88.27 283	98.03 421	94.13 300	86.90 444	96.95 348

COLMAP_ROB	93.27 12	95.33 273	94.87 275	96.71 294	99.29 89	93.24 350	98.58 226	98.11 318	89.92 432	93.57 365	99.10 127	86.37 327	99.79 122	90.78 400	98.10 233	97.09 340
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tpm cat1		93.36 378	92.80 380	95.07 402	97.58 323	87.97 467	96.76 453	97.86 347	82.17 488	93.53 366	96.04 434	86.13 332	99.13 270	89.24 427	95.87 316	98.10 310

AllTest		95.24 278	94.65 285	96.99 269	99.25 97	93.21 351	98.59 222	98.18 302	91.36 400	93.52 367	98.77 197	84.67 363	99.72 138	89.70 418	97.87 242	98.02 313

TestCases				96.99 269	99.25 97	93.21 351		98.18 302	91.36 400	93.52 367	98.77 197	84.67 363	99.72 138	89.70 418	97.87 242	98.02 313

miper_ehance_all_eth		95.01 292	94.69 283	95.97 361	97.70 313	93.31 343	97.02 431	98.07 328	92.23 375	93.51 369	96.96 385	91.85 151	98.15 402	93.68 314	91.16 386	96.44 427

SSC-MVS3.2		93.59 376	93.13 374	94.97 405	96.81 382	89.71 432	97.95 338	98.49 205	94.59 252	93.50 370	96.91 391	77.74 439	98.37 380	91.69 381	90.47 394	96.83 368

FMVSNet2		94.47 336	93.61 358	97.04 267	98.21 248	96.43 157	98.79 173	98.27 281	92.46 363	93.50 370	97.09 364	81.16 404	98.00 425	91.09 392	91.93 374	96.70 382

v148		94.29 347	93.76 350	95.91 364	96.10 418	92.93 361	98.58 226	97.97 339	92.59 361	93.47 372	96.95 387	88.53 277	98.32 385	92.56 357	87.06 441	96.49 422

c3_l		94.79 309	94.43 301	95.89 366	97.75 307	93.12 355	97.16 423	98.03 335	92.23 375	93.46 373	97.05 374	91.39 171	98.01 423	93.58 319	89.21 415	96.53 412

Syy-MVS		92.55 397	92.61 385	92.38 459	97.39 344	83.41 488	97.91 345	97.46 389	93.16 336	93.42 374	95.37 454	84.75 360	96.12 482	77.00 499	96.99 273	97.60 327

myMVS_eth3d		92.73 394	92.01 396	94.89 409	97.39 344	90.94 402	97.91 345	97.46 389	93.16 336	93.42 374	95.37 454	68.09 483	96.12 482	88.34 438	96.99 273	97.60 327

pmmvs4		94.69 313	93.99 331	96.81 286	95.74 435	95.94 188	97.40 393	97.67 364	90.42 424	93.37 376	97.59 323	89.08 256	98.20 398	92.97 336	91.67 379	96.30 433

PCF-MVS	93.45 11	94.68 315	93.43 367	98.42 130	98.62 180	96.77 137	95.48 479	98.20 296	84.63 481	93.34 377	98.32 252	88.55 276	99.81 103	84.80 470	98.96 160	98.68 272
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
cl22		94.68 315	94.19 313	96.13 349	98.11 267	93.60 325	96.94 435	98.31 271	92.43 367	93.32 378	96.87 395	86.51 321	98.28 393	94.10 303	91.16 386	96.51 419

XXY-MVS		95.20 281	94.45 299	97.46 237	96.75 386	96.56 151	98.86 143	98.65 158	93.30 330	93.27 379	98.27 258	84.85 357	98.87 321	94.82 266	91.26 385	96.96 346

jajsoiax		95.45 261	95.03 266	96.73 291	95.42 450	94.63 280	99.14 60	98.52 192	95.74 163	93.22 380	98.36 245	83.87 382	98.65 343	96.95 177	94.04 335	96.91 356

reproduce_monomvs		94.77 311	94.67 284	95.08 401	98.40 205	89.48 439	98.80 165	98.64 159	97.57 48	93.21 381	97.65 316	80.57 414	98.83 327	97.72 117	89.47 411	96.93 350

mvs_tets		95.41 266	95.00 267	96.65 300	95.58 441	94.42 291	99.00 92	98.55 185	95.73 165	93.21 381	98.38 243	83.45 388	98.63 344	97.09 170	94.00 337	96.91 356

anonymousdsp		95.42 264	94.91 272	96.94 276	95.10 454	95.90 194	99.14 60	98.41 233	93.75 296	93.16 383	97.46 332	87.50 305	98.41 373	95.63 240	94.03 336	96.50 421

v8		94.47 336	93.77 348	96.57 314	96.36 406	94.83 272	99.05 77	98.19 299	91.92 384	93.16 383	96.97 383	88.82 270	98.48 357	91.69 381	87.79 430	96.39 428

WR-MVS		95.15 283	94.46 296	97.22 250	96.67 391	96.45 155	98.21 294	98.81 108	94.15 272	93.16 383	97.69 311	87.51 303	98.30 389	95.29 252	88.62 423	96.90 358

EPNet_dtu		95.21 280	94.95 271	95.99 357	96.17 414	90.45 417	98.16 309	97.27 409	96.77 102	93.14 386	98.33 251	90.34 217	98.42 366	85.57 461	98.81 172	99.09 216
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
QAPM		96.29 217	95.40 241	98.96 76	97.85 301	97.60 86	99.23 38	98.93 65	89.76 435	93.11 387	99.02 148	89.11 255	99.93 34	91.99 372	99.62 90	99.34 150

GG-mvs-BLEND				96.59 311	96.34 407	94.98 263	96.51 461	88.58 517		93.10 388	94.34 470	80.34 417	98.05 419	89.53 421	96.99 273	96.74 375

v10		94.29 347	93.55 361	96.51 322	96.39 405	94.80 274	98.99 95	98.19 299	91.35 402	93.02 389	96.99 381	88.09 288	98.41 373	90.50 404	88.41 425	96.33 432

3Dnovator+	94.38 6	97.43 139	96.78 174	99.38 24	97.83 302	98.52 35	99.37 13	98.71 138	97.09 87	92.99 390	99.13 118	89.36 247	99.89 69	96.97 175	99.57 99	99.71 63

D2MVS		95.18 282	95.08 264	95.48 386	97.10 364	92.07 382	98.30 283	99.13 43	94.02 278	92.90 391	96.73 402	89.48 239	98.73 336	94.48 286	93.60 348	95.65 452

Patchmtry		93.22 384	92.35 392	95.84 371	96.77 383	93.09 356	94.66 493	97.56 375	87.37 459	92.90 391	96.24 423	88.15 286	97.90 432	87.37 449	90.10 400	96.53 412

DIV-MVS_self_test		94.52 330	94.03 325	95.99 357	97.57 327	93.38 338	97.05 429	97.94 342	91.74 388	92.81 393	97.10 360	89.12 254	98.07 415	92.60 353	90.30 396	96.53 412

Anonymous20231211		94.10 363	93.26 372	96.61 308	99.11 124	94.28 299	99.01 90	98.88 78	86.43 469	92.81 393	97.57 325	81.66 400	98.68 341	94.83 265	89.02 419	96.88 360

cl____		94.51 331	94.01 328	96.02 353	97.58 323	93.40 337	97.05 429	97.96 341	91.73 390	92.76 395	97.08 366	89.06 257	98.13 404	92.61 350	90.29 397	96.52 415

miper_lstm_enhance		94.33 343	94.07 322	95.11 399	97.75 307	90.97 401	97.22 411	98.03 335	91.67 392	92.76 395	96.97 383	90.03 226	97.78 442	92.51 360	89.64 405	96.56 407

v7n		94.19 354	93.43 367	96.47 327	95.90 430	94.38 294	99.26 33	98.34 260	91.99 382	92.76 395	97.13 359	88.31 280	98.52 355	89.48 423	87.70 431	96.52 415

MVS		94.67 318	93.54 362	98.08 172	96.88 377	96.56 151	98.19 301	98.50 200	78.05 499	92.69 398	98.02 277	91.07 191	99.63 161	90.09 408	98.36 215	98.04 312

DSMNet-mixed		92.52 399	92.58 387	92.33 460	94.15 466	82.65 492	98.30 283	94.26 493	89.08 447	92.65 399	95.73 444	85.01 354	95.76 486	86.24 456	97.76 248	98.59 284

EU-MVSNet		93.66 372	94.14 318	92.25 463	95.96 426	83.38 489	98.52 242	98.12 315	94.69 246	92.61 400	98.13 270	87.36 309	96.39 480	91.82 377	90.00 401	96.98 345

IterMVS-SCA-FT		94.11 362	93.87 340	94.85 412	97.98 291	90.56 416	97.18 418	98.11 318	93.75 296	92.58 401	97.48 331	83.97 379	97.41 457	92.48 362	91.30 383	96.58 403

pmmvs5		93.65 374	92.97 378	95.68 378	95.49 445	92.37 371	98.20 298	97.28 408	89.66 437	92.58 401	97.26 349	82.14 394	98.09 411	93.18 329	90.95 390	96.58 403

blended_shiyan8		91.42 406	89.89 419	96.01 354	91.50 493	93.30 344	97.48 387	97.83 349	86.93 462	92.57 403	92.37 491	82.46 392	98.13 404	92.86 344	74.99 497	96.61 394

WR-MVS_H		95.05 291	94.46 296	96.81 286	96.86 378	95.82 207	99.24 36	99.24 20	93.87 290	92.53 404	96.84 397	90.37 216	98.24 395	93.24 326	87.93 429	96.38 429

ACMP	93.49 10	95.34 272	94.98 269	96.43 332	97.67 315	93.48 331	98.73 188	98.44 216	94.94 233	92.53 404	98.53 227	84.50 368	99.14 268	95.48 245	94.00 337	96.66 388
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test0.0.03 1		94.08 365	93.51 363	95.80 372	95.53 444	92.89 362	97.38 395	95.97 467	95.11 215	92.51 406	96.66 406	87.71 298	96.94 465	87.03 451	93.67 344	97.57 329

IB-MVS	91.98 17	93.27 382	91.97 397	97.19 253	97.47 334	93.41 334	97.09 426	95.99 466	93.32 328	92.47 407	95.73 444	78.06 435	99.53 184	94.59 283	82.98 464	98.62 279
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		94.09 364	93.85 342	94.80 416	97.99 285	90.35 421	97.18 418	98.12 315	93.68 307	92.46 408	97.34 343	84.05 377	97.41 457	92.51 360	91.33 382	96.62 393
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
blended_shiyan6		91.37 407	89.84 420	95.98 360	91.49 494	93.28 345	97.48 387	97.83 349	86.93 462	92.43 409	92.36 492	82.44 393	98.06 416	92.74 349	74.82 500	96.59 399

CP-MVSNet		94.94 304	94.30 305	96.83 284	96.72 388	95.56 221	99.11 66	98.95 61	93.89 288	92.42 410	97.90 290	87.19 311	98.12 406	94.32 292	88.21 426	96.82 369

wanda-best-256-512		91.17 414	89.60 424	95.88 367	91.33 497	92.99 359	96.89 444	97.82 352	86.89 465	92.36 411	91.75 498	81.83 396	98.06 416	92.75 346	74.82 500	96.59 399

FE-blended-shiyan7		91.17 414	89.60 424	95.88 367	91.33 497	92.99 359	96.89 444	97.82 352	86.89 465	92.36 411	91.75 498	81.83 396	98.06 416	92.75 346	74.82 500	96.59 399

usedtu_blend_shiyan5		90.87 424	89.15 431	96.01 354	91.33 497	93.35 341	98.12 316	97.36 401	81.93 490	92.36 411	91.75 498	81.83 396	98.09 411	92.88 342	74.82 500	96.59 399

PS-CasMVS		94.67 318	93.99 331	96.71 294	96.68 390	95.26 244	99.13 63	99.03 50	93.68 307	92.33 414	97.95 285	85.35 347	98.10 407	93.59 318	88.16 428	96.79 370

FMVSNet1		93.19 386	92.07 395	96.56 315	97.54 328	95.00 259	98.82 156	98.18 302	90.38 425	92.27 415	97.07 367	73.68 473	97.95 428	89.36 425	91.30 383	96.72 378

blend_shiyan4		90.76 425	89.01 434	95.99 357	91.69 492	93.35 341	97.44 389	97.83 349	86.93 462	92.23 416	91.98 495	75.19 462	98.09 411	92.88 342	74.96 498	96.52 415

PEN-MVS		94.42 339	93.73 352	96.49 324	96.28 409	94.84 270	99.17 55	99.00 53	93.51 318	92.23 416	97.83 300	86.10 333	97.90 432	92.55 358	86.92 443	96.74 375

sc_t1		91.01 419	89.39 426	95.85 370	95.99 423	90.39 420	98.43 265	97.64 367	78.79 496	92.20 418	97.94 286	66.00 490	98.60 349	91.59 384	85.94 452	98.57 287

gbinet_0.2-2-1-0.02		91.03 418	89.37 430	96.01 354	91.39 495	93.41 334	97.19 416	97.82 352	87.00 461	92.18 419	91.87 497	78.97 426	98.04 420	93.13 330	74.75 504	96.60 396

OurMVSNet-221017-0		94.21 352	94.00 329	94.85 412	95.60 440	89.22 444	98.89 125	97.43 395	95.29 201	92.18 419	98.52 230	82.86 389	98.59 350	93.46 321	91.76 377	96.74 375

MS-PatchMatch		93.84 371	93.63 357	94.46 430	96.18 413	89.45 440	97.76 366	98.27 281	92.23 375	92.13 421	97.49 330	79.50 422	98.69 338	89.75 416	99.38 135	95.25 459

ppachtmachnet_test		93.22 384	92.63 384	94.97 405	95.45 448	90.84 406	96.88 447	97.88 346	90.60 419	92.08 422	97.26 349	88.08 289	97.86 438	85.12 466	90.33 395	96.22 436

1314		96.25 221	95.73 226	97.79 206	97.13 362	95.55 223	98.19 301	98.59 172	93.47 321	92.03 423	97.82 301	91.33 174	99.49 192	94.62 279	98.44 199	98.32 301

baseline2		95.11 286	94.52 292	96.87 282	96.65 392	93.56 326	98.27 288	94.10 497	93.45 322	92.02 424	97.43 336	87.45 308	99.19 254	93.88 309	97.41 265	97.87 317

DTE-MVSNet		93.98 369	93.26 372	96.14 348	96.06 420	94.39 293	99.20 48	98.86 91	93.06 341	91.78 425	97.81 302	85.87 338	97.58 452	90.53 403	86.17 448	96.46 426

LF4IMVS		93.14 388	92.79 381	94.20 435	95.88 431	88.67 456	97.66 374	97.07 425	93.81 294	91.71 426	97.65 316	77.96 437	98.81 330	91.47 386	91.92 376	95.12 462

mvs5depth		91.23 412	90.17 415	94.41 432	92.09 488	89.79 429	95.26 482	96.50 458	90.73 417	91.69 427	97.06 371	76.12 456	98.62 345	88.02 443	84.11 460	94.82 469

our_test_3		93.65 374	93.30 370	94.69 418	95.45 448	89.68 435	96.91 439	97.65 365	91.97 383	91.66 428	96.88 393	89.67 235	97.93 431	88.02 443	91.49 381	96.48 424

testgi		93.06 390	92.45 391	94.88 410	96.43 404	89.90 427	98.75 178	97.54 381	95.60 171	91.63 429	97.91 289	74.46 469	97.02 463	86.10 457	93.67 344	97.72 323

ArgMatch-SfM		90.55 428	89.69 421	93.14 452	95.91 429	86.12 479	97.20 413	96.81 448	92.91 348	91.39 430	96.95 387	65.65 492	97.72 445	88.03 442	82.36 465	95.57 453

tfpnnormal		93.66 372	92.70 383	96.55 319	96.94 372	95.94 188	98.97 99	99.19 35	91.04 413	91.38 431	97.34 343	84.94 355	98.61 346	85.45 463	89.02 419	95.11 463

LTVRE_ROB	92.95 15	94.60 321	93.90 337	96.68 298	97.41 343	94.42 291	98.52 242	98.59 172	91.69 391	91.21 432	98.35 246	84.87 356	99.04 289	91.06 395	93.44 352	96.60 396
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	95.83 240	95.00 267	98.32 136	97.18 359	97.32 100	99.21 45	98.97 57	89.96 431	91.14 433	99.05 145	86.64 320	99.92 43	93.38 322	99.47 122	97.73 322

pm-mvs1		93.94 370	93.06 375	96.59 311	96.49 400	95.16 250	98.95 106	98.03 335	92.32 372	91.08 434	97.84 297	84.54 367	98.41 373	92.16 365	86.13 451	96.19 438

ArgMatch-Sym		90.92 421	90.22 414	93.02 453	95.81 434	86.50 476	97.32 403	97.01 435	92.67 356	91.02 435	97.35 342	66.90 488	97.17 461	88.53 436	85.40 454	95.39 456

MVS-HIRNet		89.46 444	88.40 441	92.64 457	97.58 323	82.15 493	94.16 502	93.05 504	75.73 506	90.90 436	82.52 516	79.42 423	98.33 384	83.53 475	98.68 175	97.43 330

FMVSNet5		91.81 402	90.92 406	94.49 427	97.21 354	92.09 381	98.00 334	97.55 380	89.31 444	90.86 437	95.61 451	74.48 468	95.32 490	85.57 461	89.70 404	96.07 442

USDC		93.33 381	92.71 382	95.21 395	96.83 380	90.83 407	96.91 439	97.50 385	93.84 291	90.72 438	98.14 269	77.69 440	98.82 329	89.51 422	93.21 359	95.97 444

MVP-Stereo		94.28 349	93.92 334	95.35 392	94.95 456	92.60 369	97.97 337	97.65 365	91.61 393	90.68 439	97.09 364	86.32 330	98.42 366	89.70 418	99.34 139	95.02 467
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	92.99 14	94.30 345	93.77 348	95.88 367	97.81 304	92.04 384	98.71 193	98.37 251	93.99 283	90.60 440	98.47 234	80.86 411	99.05 286	92.75 346	92.40 368	96.55 409

CL-MVSNet_self_test		90.11 435	89.14 432	93.02 453	91.86 490	88.23 465	96.51 461	98.07 328	90.49 420	90.49 441	94.41 465	84.75 360	95.34 489	80.79 484	74.95 499	95.50 454

0.4-1-1-0.1		90.89 422	88.97 436	96.67 299	94.15 466	92.76 367	95.28 481	95.03 483	89.11 446	90.43 442	89.57 507	75.41 459	99.04 289	94.70 273	77.06 490	98.20 306

KD-MVS_self_test		90.38 430	89.38 428	93.40 446	92.85 483	88.94 451	97.95 338	97.94 342	90.35 426	90.25 443	93.96 473	79.82 418	95.94 485	84.62 472	76.69 494	95.33 457

ttmdpeth		92.61 396	91.96 399	94.55 424	94.10 468	90.60 415	98.52 242	97.29 406	92.67 356	90.18 444	97.92 288	79.75 420	97.79 440	91.09 392	86.15 450	95.26 458

Anonymous20231206		91.66 404	91.10 405	93.33 447	94.02 472	87.35 471	98.58 226	97.26 410	90.48 421	90.16 445	96.31 421	83.83 383	96.53 476	79.36 490	89.90 402	96.12 440

SixPastTwentyTwo		93.34 380	92.86 379	94.75 417	95.67 437	89.41 442	98.75 178	96.67 453	93.89 288	90.15 446	98.25 261	80.87 410	98.27 394	90.90 399	90.64 392	96.57 405

0.4-1-1-0.2		90.43 429	88.45 440	96.38 337	93.34 478	92.12 377	93.88 503	95.04 482	88.62 452	90.00 447	88.31 510	75.31 461	99.03 292	94.61 280	76.91 492	98.01 315

PVSNet_0	88.72 19	91.28 411	90.03 417	95.00 404	97.99 285	87.29 472	94.84 489	98.50 200	92.06 381	89.86 448	95.19 456	79.81 419	99.39 212	92.27 364	69.79 515	98.33 300

ACMH	92.88 16	94.55 326	93.95 333	96.34 340	97.63 319	93.26 347	98.81 164	98.49 205	93.43 323	89.74 449	98.53 227	81.91 395	99.08 282	93.69 313	93.30 357	96.70 382
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		90.26 434	88.73 439	94.86 411	96.12 417	90.62 413	98.17 308	97.63 368	77.46 500	89.68 450	96.04 434	69.19 481	97.79 440	88.98 430	85.29 455	96.16 439

pmmvs6		91.77 403	90.63 409	95.17 397	94.69 462	91.24 398	98.67 208	97.92 344	86.14 471	89.62 451	97.56 328	75.79 458	98.34 382	90.75 401	84.56 457	95.94 445

TinyColmap		92.31 400	91.53 401	94.65 421	96.92 373	89.75 430	96.92 437	96.68 452	90.45 423	89.62 451	97.85 296	76.06 457	98.81 330	86.74 452	92.51 367	95.41 455

Anonymous20240521		91.18 413	90.44 411	93.42 444	93.70 473	88.47 460	98.94 109	97.56 375	88.46 453	89.56 453	95.08 459	77.15 448	96.97 464	83.92 473	89.55 408	94.82 469

TransMVSNet (Re)		92.67 395	91.51 402	96.15 347	96.58 394	94.65 278	98.90 121	96.73 449	90.86 416	89.46 454	97.86 294	85.62 342	98.09 411	86.45 455	81.12 474	95.71 450

NR-MVSNet		94.98 297	94.16 316	97.44 239	96.53 396	97.22 115	98.74 182	98.95 61	94.96 229	89.25 455	97.69 311	89.32 248	98.18 399	94.59 283	87.40 436	96.92 351

0.3-1-1-0.015		90.29 432	88.21 444	96.51 322	93.56 475	92.44 370	94.41 498	95.03 483	88.71 450	89.20 456	88.50 509	73.12 475	99.04 289	94.67 276	76.70 493	98.05 311

LCM-MVSNet-Re		95.22 279	95.32 251	94.91 407	98.18 258	87.85 469	98.75 178	95.66 472	95.11 215	88.96 457	96.85 396	90.26 221	97.65 447	95.65 239	98.44 199	99.22 188

KD-MVS_2432*1600		89.61 441	87.96 449	94.54 425	94.06 470	91.59 392	95.59 476	97.63 368	89.87 433	88.95 458	94.38 467	78.28 432	96.82 467	84.83 468	68.05 516	95.21 460

miper_refine_blended		89.61 441	87.96 449	94.54 425	94.06 470	91.59 392	95.59 476	97.63 368	89.87 433	88.95 458	94.38 467	78.28 432	96.82 467	84.83 468	68.05 516	95.21 460

test_fmvs3		87.17 452	87.06 455	87.50 478	91.21 500	75.66 504	99.05 77	96.61 456	92.79 353	88.85 460	92.78 487	43.72 509	93.49 502	93.95 306	84.56 457	93.34 493

TDRefinement		91.06 417	89.68 422	95.21 395	85.35 525	91.49 394	98.51 249	97.07 425	91.47 396	88.83 461	97.84 297	77.31 444	99.09 280	92.79 345	77.98 487	95.04 466

MASt3R-SfM		85.54 457	85.89 457	84.50 487	90.13 511	66.13 522	92.89 505	95.33 477	85.73 476	88.77 462	96.36 420	52.50 503	94.89 496	86.66 453	84.65 456	92.50 499

tt0320-xc		89.79 438	88.11 445	94.84 414	96.19 412	90.61 414	98.16 309	97.22 412	77.35 501	88.75 463	96.70 405	65.94 491	97.63 449	89.31 426	83.39 462	96.28 434

N_pmnet		87.12 454	87.77 451	85.17 484	95.46 447	61.92 528	97.37 397	70.66 539	85.83 474	88.73 464	96.04 434	85.33 349	97.76 443	80.02 485	90.48 393	95.84 447

dtuonlycased		91.29 409	91.26 404	91.36 467	95.63 439	84.25 485	96.93 436	97.21 414	92.16 379	88.34 465	96.47 414	79.56 421	95.18 493	87.37 449	87.70 431	94.64 473

test_0402		91.32 408	90.27 413	94.48 428	96.60 393	91.12 399	98.50 250	97.22 412	86.10 472	88.30 466	96.98 382	77.65 442	97.99 426	78.13 495	92.94 361	94.34 475

test20.03		90.89 422	90.38 412	92.43 458	93.48 476	88.14 466	98.33 275	97.56 375	93.40 325	87.96 467	96.71 404	80.69 413	94.13 500	79.15 491	86.17 448	95.01 468

MIMVSNet1		89.67 440	88.28 443	93.82 439	92.81 484	91.08 400	98.01 332	97.45 393	87.95 456	87.90 468	95.87 440	67.63 486	94.56 498	78.73 494	88.18 427	95.83 448

mvsany_test3		88.80 446	88.04 446	91.09 468	89.78 513	81.57 495	97.83 360	95.49 475	93.81 294	87.53 469	93.95 474	56.14 500	97.43 456	94.68 274	83.13 463	94.26 476

Patchmatch-RL test		91.49 405	90.85 407	93.41 445	91.37 496	84.40 483	92.81 506	95.93 470	91.87 386	87.25 470	94.87 460	88.99 259	96.53 476	92.54 359	82.00 468	99.30 164

pmmvs3		86.67 455	84.86 461	92.11 464	88.16 517	87.19 474	96.63 457	94.75 487	79.88 493	87.22 471	92.75 489	66.56 489	95.20 492	81.24 483	76.56 495	93.96 486

dongtai		82.47 464	81.88 466	84.22 488	95.19 453	76.03 502	94.59 496	74.14 530	82.63 485	87.19 472	96.09 431	64.10 494	87.85 518	58.91 518	84.11 460	88.78 512

test_vis1_rt		91.29 409	90.65 408	93.19 451	97.45 338	86.25 478	98.57 235	90.90 513	93.30 330	86.94 473	93.59 476	62.07 497	99.11 275	97.48 150	95.58 320	94.22 479

K. test v3		92.55 397	91.91 400	94.48 428	95.64 438	89.24 443	99.07 72	94.88 485	94.04 276	86.78 474	97.59 323	77.64 443	97.64 448	92.08 367	89.43 412	96.57 405

lessismore_v0				94.45 431	94.93 457	88.44 461		91.03 512		86.77 475	97.64 319	76.23 455	98.42 366	90.31 406	85.64 453	96.51 419

APD_test1		88.22 449	88.01 447	88.86 475	95.98 424	74.66 511	97.21 412	96.44 460	83.96 483	86.66 476	97.90 290	60.95 498	97.84 439	82.73 476	90.23 398	94.09 482

ambc				89.49 472	86.66 520	75.78 503	92.66 507	96.72 450		86.55 477	92.50 490	46.01 507	97.90 432	90.32 405	82.09 467	94.80 471

PM-MVS		87.77 450	86.55 456	91.40 466	91.03 504	83.36 490	96.92 437	95.18 480	91.28 407	86.48 478	93.42 478	53.27 502	96.74 469	89.43 424	81.97 469	94.11 481

OpenMVS_ROB	86.42 20	89.00 445	87.43 453	93.69 441	93.08 482	89.42 441	97.91 345	96.89 442	78.58 497	85.86 479	94.69 461	69.48 480	98.29 392	77.13 498	93.29 358	93.36 492

UnsupCasMVSNet_eth		90.99 420	89.92 418	94.19 436	94.08 469	89.83 428	97.13 425	98.67 151	93.69 305	85.83 480	96.19 428	75.15 463	96.74 469	89.14 428	79.41 481	96.00 443

new_pmnet		90.06 436	89.00 435	93.22 450	94.18 464	88.32 463	96.42 463	96.89 442	86.19 470	85.67 481	93.62 475	77.18 447	97.10 462	81.61 481	89.29 414	94.23 478

dmvs_testset		87.64 451	88.93 438	83.79 489	95.25 451	63.36 524	97.20 413	91.17 510	93.07 340	85.64 482	95.98 439	85.30 351	91.52 510	69.42 512	87.33 437	96.49 422

test_f		86.07 456	85.39 458	88.10 476	89.28 515	75.57 505	97.73 369	96.33 462	89.41 443	85.35 483	91.56 501	43.31 511	95.53 487	91.32 388	84.23 459	93.21 494

EG-PatchMatch MVS		91.13 416	90.12 416	94.17 437	94.73 461	89.00 448	98.13 315	97.81 356	89.22 445	85.32 484	96.46 415	67.71 485	98.42 366	87.89 447	93.82 342	95.08 464

pmmvs-eth3d		90.36 431	89.05 433	94.32 434	91.10 502	92.12 377	97.63 379	96.95 437	88.86 449	84.91 485	93.13 482	78.32 431	96.74 469	88.70 433	81.81 470	94.09 482

FE-MVSNET2		90.29 432	88.94 437	94.36 433	90.48 508	92.27 372	98.45 257	97.82 352	91.59 394	84.90 486	93.10 483	73.92 471	96.42 479	87.92 446	82.26 466	94.39 474

FE-MVSNET		88.56 447	87.09 454	92.99 455	89.93 512	89.99 426	98.15 312	95.59 473	88.42 454	84.87 487	92.90 485	74.82 465	94.99 495	77.88 496	81.21 473	93.99 485

DeepMVS_CX				86.78 479	97.09 365	72.30 512		95.17 481	75.92 505	84.34 488	95.19 456	70.58 478	95.35 488	79.98 488	89.04 418	92.68 496

usedtu_dtu_shiyan2		84.80 459	82.31 464	92.27 462	86.38 522	85.55 481	97.77 365	96.56 457	78.34 498	83.90 489	93.50 477	54.16 501	95.32 490	77.55 497	72.62 508	95.92 446

new-patchmatchnet		88.50 448	87.45 452	91.67 465	90.31 510	85.89 480	97.16 423	97.33 402	89.47 440	83.63 490	92.77 488	76.38 453	95.06 494	82.70 477	77.29 488	94.06 484

UnsupCasMVSNet_bld		87.17 452	85.12 460	93.31 448	91.94 489	88.77 453	94.92 488	98.30 278	84.30 482	82.30 491	90.04 505	63.96 495	97.25 459	85.85 460	74.47 507	93.93 487

WB-MVS		84.86 458	85.33 459	83.46 490	89.48 514	69.56 516	98.19 301	96.42 461	89.55 439	81.79 492	94.67 462	84.80 358	90.12 513	52.44 520	80.64 478	90.69 505

CMPMVS	66.06 21	89.70 439	89.67 423	89.78 471	93.19 481	76.56 501	97.00 432	98.35 256	80.97 491	81.57 493	97.75 305	74.75 466	98.61 346	89.85 414	93.63 346	94.17 480
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SSC-MVS		84.27 461	84.71 462	82.96 495	89.19 516	68.83 517	98.08 324	96.30 463	89.04 448	81.37 494	94.47 463	84.60 365	89.89 514	49.80 523	79.52 480	90.15 506

MVStest1		89.53 443	87.99 448	94.14 438	94.39 463	90.42 418	98.25 291	96.84 447	82.81 484	81.18 495	97.33 345	77.09 449	96.94 465	85.27 465	78.79 482	95.06 465

test_method		79.03 470	78.17 469	81.63 496	86.06 523	54.40 539	82.75 526	96.89 442	39.54 531	80.98 496	95.57 452	58.37 499	94.73 497	84.74 471	78.61 483	95.75 449

kuosan		78.45 474	77.69 473	80.72 497	92.73 485	75.32 506	94.63 495	74.51 529	75.96 503	80.87 497	93.19 481	63.23 496	79.99 528	42.56 530	81.56 472	86.85 519

RoMa-SfM		83.81 462	82.08 465	89.00 474	93.33 479	79.94 498	95.51 478	92.48 506	79.75 494	79.89 498	95.69 449	46.23 506	93.20 505	78.90 492	76.93 491	93.87 488

DenseAffine		84.37 460	82.38 463	90.31 470	94.17 465	82.89 491	94.98 485	94.23 494	82.16 489	79.68 499	94.33 471	46.28 505	94.25 499	80.01 486	75.62 496	93.78 490

ET-MVSNet_ETH3D		94.13 359	92.98 377	97.58 231	98.22 246	96.20 169	97.31 405	95.37 476	94.53 255	79.56 500	97.63 321	86.51 321	97.53 454	96.91 179	90.74 391	99.02 229

RoMa-HiRes		79.77 467	77.89 470	85.41 483	90.81 505	74.77 510	94.26 500	86.78 519	75.97 502	77.00 501	94.37 469	39.39 516	90.60 511	74.98 504	67.46 518	90.84 504

LCM-MVSNet		78.70 473	76.24 479	86.08 480	77.26 541	71.99 513	94.34 499	96.72 450	61.62 517	76.53 502	89.33 508	33.91 530	92.78 507	81.85 480	74.60 505	93.46 491

DKM		81.60 465	79.57 468	87.68 477	92.65 486	78.36 499	94.65 494	91.17 510	79.69 495	76.11 503	93.98 472	37.88 521	91.54 509	79.64 489	70.38 512	93.15 495

PMMVS2		77.95 476	75.44 480	85.46 482	82.54 529	74.95 508	94.23 501	93.08 503	72.80 508	74.68 504	87.38 511	36.36 524	91.56 508	73.95 506	63.94 520	89.87 507

testf1		79.02 471	77.70 471	82.99 493	88.10 518	66.90 520	94.67 491	93.11 501	71.08 512	74.02 505	93.41 479	34.15 527	93.25 503	72.25 508	78.50 484	88.82 510

APD_test2		79.02 471	77.70 471	82.99 493	88.10 518	66.90 520	94.67 491	93.11 501	71.08 512	74.02 505	93.41 479	34.15 527	93.25 503	72.25 508	78.50 484	88.82 510

Gipuma		78.40 475	76.75 478	83.38 491	95.54 442	80.43 496	79.42 527	97.40 397	64.67 516	73.46 507	80.82 520	45.65 508	93.14 506	66.32 515	87.43 435	76.56 525
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DKM-HiRes		79.25 468	77.01 477	85.98 481	91.20 501	75.07 507	93.65 504	87.84 518	75.94 504	73.36 508	92.80 486	34.20 526	90.26 512	76.66 500	67.44 519	92.62 497

YYNet1		90.70 427	89.39 426	94.62 423	94.79 460	90.65 411	97.20 413	97.46 389	87.54 458	72.54 509	95.74 442	86.51 321	96.66 473	86.00 458	86.76 446	96.54 410

MDA-MVSNet_test_wron		90.71 426	89.38 428	94.68 419	94.83 458	90.78 408	97.19 416	97.46 389	87.60 457	72.41 510	95.72 446	86.51 321	96.71 472	85.92 459	86.80 445	96.56 407

MDA-MVSNet-bldmvs		89.97 437	88.35 442	94.83 415	95.21 452	91.34 395	97.64 376	97.51 384	88.36 455	71.17 511	96.13 430	79.22 424	96.63 474	83.65 474	86.27 447	96.52 415

LoFTR		83.16 463	80.62 467	90.80 469	92.28 487	80.01 497	95.35 480	94.33 491	80.44 492	70.79 512	92.93 484	46.38 504	98.17 400	75.01 503	78.03 486	94.24 477

FPMVS		77.62 477	77.14 476	79.05 501	79.25 536	60.97 530	95.79 471	95.94 469	65.96 515	67.93 513	94.40 466	37.73 522	88.88 517	68.83 513	88.46 424	87.29 516

test_vis3_rt		79.22 469	77.40 474	84.67 485	86.44 521	74.85 509	97.66 374	81.43 523	84.98 479	67.12 514	81.91 519	28.09 534	97.60 450	88.96 431	80.04 479	81.55 522

MatchFormer		80.21 466	77.20 475	89.24 473	91.79 491	77.21 500	95.16 483	93.59 499	72.46 510	67.08 515	89.93 506	43.14 512	97.90 432	67.07 514	74.55 506	92.61 498

SP-DiffGlue		70.13 482	69.16 485	73.04 510	77.73 539	57.48 534	88.44 520	74.91 528	50.96 523	66.64 516	85.99 513	41.44 513	73.46 534	64.21 516	72.15 509	88.19 515

PDCNetPlus		71.79 481	69.26 484	79.39 500	85.67 524	69.92 515	90.34 515	62.32 541	72.62 509	65.36 517	90.26 502	39.20 518	86.38 520	75.32 502	42.24 534	81.88 521

PMatch-SfM		73.49 480	70.32 482	83.00 492	85.01 526	68.63 518	90.17 517	79.05 526	71.64 511	63.27 518	91.93 496	17.27 543	89.10 516	74.59 505	59.95 524	91.26 500

ELoFTR		75.37 478	72.33 481	84.51 486	84.48 527	68.41 519	91.57 510	88.78 516	73.84 507	62.84 519	90.14 503	27.38 535	94.11 501	71.45 511	60.46 523	91.00 502

tmp_tt		68.90 485	66.97 486	74.68 503	50.78 556	59.95 531	87.13 523	83.47 522	38.80 532	62.21 520	96.23 425	64.70 493	76.91 530	88.91 432	30.49 542	87.19 517

SP-SuperGlue		68.14 487	66.58 487	72.81 511	90.65 507	55.53 536	91.37 511	73.04 531	49.07 526	61.03 521	80.24 523	38.13 520	74.06 533	45.46 526	70.26 513	88.84 509

SP-LightGlue		68.17 486	66.54 488	73.06 509	91.08 503	55.79 535	91.09 512	72.78 532	48.55 527	60.77 522	79.95 524	38.55 519	74.10 532	45.47 525	70.64 511	89.28 508

E-PMN		64.94 494	64.25 495	67.02 514	82.28 530	59.36 532	91.83 509	85.63 520	52.69 520	60.22 523	77.28 528	41.06 514	80.12 527	46.15 524	41.14 535	61.57 531

PMatch-Up-SfM		70.03 483	66.48 489	80.70 498	82.00 531	63.20 525	88.10 521	71.07 535	67.59 514	60.07 524	90.10 504	14.49 548	87.80 519	71.95 510	52.95 528	91.09 501

ALIKED-NN		66.93 490	64.81 493	73.32 507	93.41 477	62.03 527	87.55 522	71.25 534	50.21 524	59.98 525	82.57 515	39.72 515	84.03 524	34.94 534	63.64 521	73.90 527

ALIKED-LG		67.40 488	65.16 492	74.11 505	93.21 480	62.30 526	88.98 518	71.99 533	55.04 518	59.47 526	82.33 517	39.27 517	85.49 522	32.61 536	63.58 522	74.55 526

SP-NN		67.39 489	65.69 490	72.49 513	90.68 506	55.34 537	90.33 516	71.01 537	46.77 529	59.09 527	79.83 525	37.26 523	73.38 535	44.68 527	71.51 510	88.74 513

EMVS		64.07 495	63.26 497	66.53 515	81.73 532	58.81 533	91.85 508	84.75 521	51.93 522	59.09 527	75.13 531	43.32 510	79.09 529	42.03 531	39.47 536	61.69 530

ALIKED-MNN		65.35 493	62.68 498	73.35 506	93.70 473	61.07 529	88.63 519	70.76 538	47.76 528	57.06 529	80.59 521	34.03 529	85.39 523	32.73 535	58.87 525	73.59 528

SP-MNN		66.66 491	64.70 494	72.53 512	90.32 509	55.08 538	91.01 513	71.05 536	44.81 530	56.48 530	79.62 526	35.87 525	74.11 531	43.13 529	69.98 514	88.39 514

XFeat-NN		56.16 498	56.10 501	56.36 517	72.10 548	42.54 551	76.45 530	61.18 542	38.16 533	53.08 531	76.48 529	32.95 531	65.67 537	44.15 528	50.31 531	60.87 532

MVE	62.14 22	63.28 496	59.38 499	74.99 502	74.33 546	65.47 523	85.55 524	80.50 524	52.02 521	51.10 532	75.00 532	10.91 555	80.50 526	51.60 522	53.40 527	78.99 523
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
XFeat-MNN		55.84 499	55.19 502	57.82 516	69.33 552	43.25 546	78.25 529	62.64 540	37.53 534	50.90 533	76.32 530	32.43 532	68.13 536	42.00 532	47.26 533	62.07 529

ANet_high		69.08 484	65.37 491	80.22 499	65.99 554	71.96 514	90.91 514	90.09 514	82.62 486	49.93 534	78.39 527	29.36 533	81.75 525	62.49 517	38.52 538	86.95 518

GLUNet-SfM		61.12 497	56.63 500	74.58 504	69.78 551	53.99 540	78.71 528	76.81 527	49.09 525	49.42 535	80.47 522	24.43 536	85.82 521	51.80 521	29.17 543	83.92 520

PMVS	61.03 23	65.95 492	63.57 496	73.09 508	57.90 555	51.22 541	85.05 525	93.93 498	54.45 519	44.32 536	83.57 514	13.22 550	89.15 515	58.68 519	81.00 475	78.91 524
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-NN		49.27 500	49.25 503	49.32 518	83.88 528	45.20 542	74.57 531	53.44 543	32.44 535	42.88 537	64.93 533	20.60 537	61.35 538	16.59 538	53.96 526	41.40 533

SIFT-MNN		47.78 501	47.47 504	48.69 519	81.04 533	44.17 543	73.46 532	53.36 544	31.82 536	38.54 538	63.76 534	18.11 541	61.27 539	15.96 540	51.17 529	40.64 536

SIFT-NN-NCMNet		47.55 502	47.18 505	48.67 520	79.60 535	44.09 544	73.43 533	52.90 545	31.82 536	38.38 539	63.56 537	18.47 538	61.19 540	15.91 541	50.50 530	40.74 535

SIFT-NN-CMatch		45.31 503	44.49 506	47.75 521	76.46 542	42.98 549	70.17 537	49.20 548	31.63 539	37.94 540	63.68 536	18.19 540	59.32 543	15.91 541	37.27 539	40.95 534

SIFT-NN-PointCN		43.09 507	42.61 509	44.51 527	72.48 547	37.95 555	70.10 538	46.55 550	30.16 545	34.48 541	61.93 541	18.02 542	55.90 548	15.40 544	34.41 540	39.69 538

SIFT-ConvMatch		43.26 506	42.18 510	46.50 524	78.34 538	43.05 547	68.67 539	47.17 549	31.06 540	30.28 542	62.56 539	15.43 545	58.95 545	14.92 545	31.22 541	37.51 541

SIFT-NN-UMatch		44.69 505	43.84 508	47.24 523	74.56 545	42.59 550	71.89 535	49.78 546	31.80 538	29.27 543	63.70 535	18.26 539	59.43 542	15.86 543	39.43 537	39.71 537

SIFT-CM-Cal		41.25 509	40.03 512	44.88 526	77.37 540	41.08 553	65.71 543	41.18 553	30.42 544	28.83 544	61.42 543	14.88 547	56.40 546	14.13 548	26.37 546	37.16 542

SIFT-UMatch		42.35 508	41.04 511	46.29 525	76.09 543	41.80 552	70.21 536	45.21 551	30.75 542	27.33 545	62.62 538	15.13 546	59.11 544	14.72 546	27.30 544	37.95 540

SIFT-NCM-Cal		44.98 504	44.20 507	47.33 522	79.81 534	43.05 547	72.12 534	49.31 547	30.81 541	25.90 546	61.87 542	15.80 544	60.28 541	14.09 549	48.07 532	38.66 539

SIFT-PCN-Cal		36.85 512	36.40 515	38.19 530	71.43 550	30.42 557	64.34 544	37.72 555	27.48 547	22.98 547	57.03 544	12.99 551	51.22 549	12.51 550	21.13 548	32.92 545

SIFT-UM-Cal		39.93 510	38.61 513	43.88 528	76.08 544	39.30 554	68.10 540	37.89 554	30.49 543	22.74 548	62.27 540	13.89 549	56.16 547	14.17 547	21.90 547	36.17 543

SIFT-PointCN		37.89 511	37.50 514	39.07 529	71.45 549	31.31 556	66.27 542	41.69 552	27.82 546	22.63 549	56.73 545	12.00 553	50.56 550	12.18 551	26.71 545	35.34 544

SIFT-NCMNet		32.45 513	31.84 517	34.30 531	68.74 553	28.10 558	57.85 545	24.54 556	27.25 548	19.31 550	52.59 546	9.75 556	45.69 551	10.92 552	15.56 550	29.13 546

testmvs		21.48 516	24.95 519	11.09 534	14.89 557	6.47 560	96.56 459	9.87 558	7.55 550	17.93 551	39.02 548	9.43 557	5.90 554	16.56 539	12.72 551	20.91 548

test123		20.95 517	23.72 520	12.64 533	13.54 558	8.19 559	96.55 460	6.13 559	7.48 551	16.74 552	37.98 549	12.97 552	6.05 553	16.69 537	5.43 552	23.68 547

wuyk23d		30.17 514	30.18 518	30.16 532	78.61 537	43.29 545	66.79 541	14.21 557	17.31 549	14.82 553	11.93 552	11.55 554	41.43 552	37.08 533	19.30 549	5.76 549

EGC-MVSNET		75.22 479	69.54 483	92.28 461	94.81 459	89.58 437	97.64 376	96.50 458	1.82 552	5.57 554	95.74 442	68.21 482	96.26 481	73.80 507	91.71 378	90.99 503

mmdepth		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

monomultidepth		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

test_blank		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

uanet_test		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

DCPMVS		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

cdsmvs_eth3d_5k		23.98 515	31.98 516	0.00 535	0.00 559	0.00 561	0.00 546	98.59 172	0.00 553	0.00 555	98.61 217	90.60 207	0.00 555	0.00 553	0.00 553	0.00 550

pcd_1.5k_mvsjas		7.88 519	10.50 522	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	94.51 92	0.00 555	0.00 553	0.00 553	0.00 550

sosnet-low-res		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

sosnet		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

uncertanet		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

Regformer		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

ab-mvs-re		8.20 518	10.94 521	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	98.43 236	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

uanet		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

WAC-MVS						90.94 402								88.66 434

MSC_two_6792asdad				99.62 7	99.17 112	99.08 13		98.63 162					99.94 14	98.53 56	99.80 25	99.86 13

No_MVS				99.62 7	99.17 112	99.08 13		98.63 162					99.94 14	98.53 56	99.80 25	99.86 13

eth-test2					0.00 559

eth-test					0.00 559

OPU-MVS				99.37 28	99.24 104	99.05 17	99.02 87				99.16 110	97.81 3	99.37 213	97.24 165	99.73 62	99.70 67

save fliter					99.46 59	98.38 42	98.21 294	98.71 138	97.95 28

test_0728_SECOND				99.71 1	99.72 17	99.35 1	98.97 99	98.88 78					99.94 14	98.47 64	99.81 16	99.84 18

GSMVS																99.20 191

sam_mvs1												89.45 243				99.20 191

sam_mvs												88.99 259

MTGPA								98.74 130

test_post1							96.68 456				30.43 551	87.85 297	98.69 338	92.59 355

test_post											31.83 550	88.83 268	98.91 314

patchmatchnet-post											95.10 458	89.42 244	98.89 318

MTMP							98.89 125	94.14 496

gm-plane-assit					95.88 431	87.47 470			89.74 436		96.94 389		99.19 254	93.32 325

test9_res														96.39 210	99.57 99	99.69 70

agg_prior2														95.87 226	99.57 99	99.68 75

test_prior4						98.01 72	97.86 355

test_prior				99.19 51	99.31 80	98.22 59		98.84 96					99.70 144			99.65 83

新几何2							97.64 376

旧先验1					99.29 89	97.48 91		98.70 141			99.09 135	95.56 56			99.47 122	99.61 90

无先验							97.58 381	98.72 135	91.38 399				99.87 80	93.36 324		99.60 92

原ACMM2							97.67 373

testdata2													99.89 69	91.65 383

segment_acmp												96.85 15

testdata1							97.32 403		96.34 130

plane_prior7					97.42 340	94.63 280

plane_prior6					97.35 347	94.61 283						87.09 312

plane_prior5								98.56 183					99.03 292	96.07 216	94.27 326	96.92 351

plane_prior4											98.28 255

plane_prior2							98.80 165		97.28 69

plane_prior1					97.37 346

plane_prior						94.60 285	98.44 263		96.74 105						94.22 328

n2								0.00 560

nn								0.00 560

door-mid								94.37 490

test11								98.66 154

door								94.64 488

HQP5-MVS						94.25 302

BP-MVS														95.30 250

HQP3-MVS								98.46 208							94.18 330

HQP2-MVS												86.75 318

NP-MVS					97.28 349	94.51 288					97.73 306

ACMMP++_ref															92.97 360

ACMMP++															93.61 347

Test By Simon												94.64 89

High-resolution multi-view benchmark