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	98.70 196	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	98.79 172	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	98.89 124	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 98	98.86 91	98.91 4	99.87 4	99.66 3	91.82 153	99.95 9	99.82 6	99.82 14	98.75 261

fmvsm_s_conf0.5_n_5		98.53 46	98.35 48	99.08 64	99.07 128	97.46 95	98.68 202	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	98.80 164	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		96.71 193	96.84 166	96.31 342	99.11 124	89.74 431	99.05 76	98.58 177	98.08 24	99.87 4	99.37 56	78.48 429	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	98.79 172	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	98.89 124	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	98.96 104	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	98.88 131	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	98.86 142	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	98.75 177	99.24 20	98.39 19	99.81 13	99.52 25	92.35 129	99.90 65	99.74 13	99.51 115	98.71 267

test_fmvsmconf_n		98.92 13	98.87 7	99.04 68	98.88 148	97.25 113	98.82 155	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	98.80 164	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	98.66 209	99.20 33	98.82 7	99.79 15	99.60 10	89.38 246	99.92 43	99.80 8	99.38 134	98.69 269

fmvsm_s_conf0.5_n_a		98.38 63	98.42 41	98.27 139	99.09 126	95.41 231	98.86 142	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	98.69 199	98.82 102	98.78 9	99.77 18	99.61 5	88.83 268	99.91 57	99.71 15	99.07 151	98.61 279

test_cas_vis1_n_1920		97.38 144	97.36 119	97.45 238	98.95 143	93.25 349	99.00 91	98.53 189	97.70 39	99.77 18	99.35 62	84.71 361	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	97.66 316	95.39 236	98.89 124	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 73	99.33 140	99.90 5

fmvsm_s_conf0.5_n		98.42 60	98.51 32	98.13 164	99.30 84	95.25 245	98.85 147	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	98.58 225	99.00 53	98.29 20	99.73 23	99.60 10	91.70 156	99.92 43	99.63 21	99.73 62	98.76 260

SED-MVS		99.09 2	98.91 5	99.63 5	99.71 24	99.24 5	99.02 86	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	98.90 120	98.85 95	97.28 69	99.72 26	99.39 50	96.63 22	97.60 449	98.17 85	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	98.87 134	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		95.90 235	95.99 216	95.63 380	98.67 173	88.32 462	99.26 33	98.22 293	96.40 125	99.67 28	99.26 80	73.91 471	99.70 144	99.02 34	99.50 116	98.87 244

test_vis1_n		95.47 257	95.13 258	96.49 324	97.77 305	90.41 419	99.27 32	98.11 318	96.58 114	99.66 29	99.18 105	67.00 486	99.62 165	99.21 28	99.40 132	99.44 126

mvsany_test1		97.69 104	97.70 92	97.66 225	98.24 241	94.18 306	97.53 382	97.53 381	95.52 183	99.66 29	99.51 28	94.30 99	99.56 175	98.38 71	98.62 179	99.23 186

test_fmvs1		96.42 208	96.67 181	95.66 379	98.82 157	88.53 458	98.80 164	98.20 296	96.39 126	99.64 31	99.20 95	80.35 415	99.67 151	99.04 32	99.57 99	98.78 256

IU-MVS					99.71 24	99.23 7		98.64 159	95.28 201	99.63 32				98.35 73	99.81 16	99.83 19

PC_three_1452									95.08 218	99.60 33	99.16 110	97.86 2	98.47 359	97.52 142	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 75	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	98.42 267	98.91 72	97.58 47	99.54 37	99.46 42	97.10 13	99.94 14	97.64 125	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 98	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	97.73 310	97.15 120	98.84 151	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		98.59 181	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	97.79 112	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	98.95 105	98.80 115	93.67 308	99.37 47	99.52 25	96.52 26	99.89 69	98.06 91	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	98.94 108	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	97.77 113	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 80	98.81 108	95.12 213	99.32 51	99.39 50	96.22 34	99.84 89	97.72 116	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 76	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 76	99.80 25	99.90 5

reproduce-ours		98.93 11	98.78 14	99.38 24	99.49 53	98.38 42	98.86 142	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	98.86 142	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	97.43 391	98.87 85	98.16 22	99.26 58	99.38 55	96.12 39	99.64 158	98.30 76	99.77 42	99.72 59

APD-MVS		98.35 68	98.00 83	99.42 22	99.51 47	98.72 27	98.80 164	98.82 102	94.52 256	99.23 59	99.25 86	95.54 58	99.80 110	96.52 203	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	96.24 133	99.20 60	99.37 56	95.30 69	99.80 110	97.73 115	99.67 75	99.72 59

patch_mono-2		98.36 66	98.87 7	96.82 285	99.53 43	90.68 410	98.64 212	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	98.69 199	98.93 65	97.00 91	99.17 63	99.35 62	96.62 23	99.90 65	98.30 76	99.80 25	99.79 29

MM		98.51 49	98.24 65	99.33 36	99.12 122	98.14 67	98.93 114	97.02 431	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	97.72 116	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		97.72 116	99.65 81	99.71 63

9.14			98.06 78		99.47 57		98.71 192	98.82 102	94.36 265	99.16 67	99.29 75	96.05 41	99.81 103	97.00 172	99.71 69

ACMMP_NAP		98.61 31	98.30 60	99.55 11	99.62 36	98.95 20	98.82 155	98.81 108	95.80 159	99.16 67	99.47 37	95.37 64	99.92 43	97.89 104	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	97.70 121	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 94	99.49 5	95.43 188	99.03 71	99.32 69	95.56 56	99.94 14	96.80 194	99.77 42	99.78 33

KinetiMVS		97.48 130	97.05 152	98.78 87	98.37 211	97.30 103	98.99 94	98.70 141	97.18 79	99.02 72	99.01 152	87.50 305	99.67 151	95.33 247	99.33 140	99.37 143

VNet		97.79 98	97.40 115	98.96 76	98.88 148	97.55 87	98.63 215	98.93 65	96.74 105	99.02 72	98.84 181	90.33 218	99.83 91	98.53 56	96.66 284	99.50 107

xiu_mvs_v1_base_debu		97.60 113	97.56 99	97.72 214	98.35 213	95.98 180	97.86 354	98.51 195	97.13 84	99.01 74	98.40 239	91.56 163	99.80 110	98.53 56	98.68 174	97.37 334

xiu_mvs_v1_base		97.60 113	97.56 99	97.72 214	98.35 213	95.98 180	97.86 354	98.51 195	97.13 84	99.01 74	98.40 239	91.56 163	99.80 110	98.53 56	98.68 174	97.37 334

xiu_mvs_v1_base_debi		97.60 113	97.56 99	97.72 214	98.35 213	95.98 180	97.86 354	98.51 195	97.13 84	99.01 74	98.40 239	91.56 163	99.80 110	98.53 56	98.68 174	97.37 334

MVSMamba_PlusPlus		98.31 73	98.19 73	98.67 96	98.96 142	97.36 98	99.24 36	98.57 179	94.81 237	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	98.11 319	98.29 280	97.19 78	98.99 77	99.02 148	96.22 34	99.67 151	98.52 62	98.56 185	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	99.13 269	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	96.10 143	98.94 79	99.17 107	96.06 40	99.92 43	97.62 126	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	96.15 137	98.94 79	99.17 107	95.91 47	99.94 14	97.55 138	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	94.46 261	98.94 79	99.20 95	95.16 78	99.74 135	97.58 133	99.85 6	99.77 40

test_fmvsmconf0.01_n		97.86 92	97.54 102	98.83 84	95.48 445	96.83 134	98.95 105	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	96.10 143	98.93 83	99.19 102	95.70 53	99.94 14	97.62 126	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	98.50 249	98.78 122	97.72 36	98.92 85	99.28 76	95.27 71	99.82 98	97.55 138	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	99.15 264	98.83 41	99.56 107	99.20 191

MGCNet		98.23 76	97.91 86	99.21 50	98.06 273	97.96 74	98.58 225	95.51 473	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	98.34 218	97.26 112	99.61 5	98.43 227	96.78 101	98.87 87	98.84 181	93.72 109	99.01 297	98.91 38	99.50 116	99.19 195

diffmvs_AUTHOR		97.59 116	97.44 111	98.01 183	98.26 236	95.47 227	98.12 315	98.36 255	96.38 127	98.84 89	99.10 127	91.13 186	99.26 230	98.24 84	98.56 185	99.30 164

EI-MVSNet-Vis-set		98.47 54	98.39 43	98.69 94	99.46 59	96.49 154	98.30 282	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	98.71 192	99.05 49	97.28 69	98.84 89	99.28 76	96.47 28	99.40 208	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 80	99.09 44	93.32 327	98.83 92	99.10 127	96.54 24	99.83 91	97.70 121	99.76 48	99.59 94

GDP-MVS		97.64 108	97.28 126	98.71 93	98.30 227	97.33 99	99.05 76	98.52 192	96.34 129	98.80 93	99.05 145	89.74 233	99.51 188	96.86 190	98.86 166	99.28 174

MVSFormer		97.57 118	97.49 105	97.84 201	98.07 270	95.76 212	99.47 7	98.40 236	94.98 226	98.79 94	98.83 185	92.34 130	98.41 372	96.91 178	99.59 95	99.34 150

lupinMVS		97.44 138	97.22 135	98.12 167	98.07 270	95.76 212	97.68 371	97.76 357	94.50 259	98.79 94	98.61 216	92.34 130	99.30 222	97.58 133	99.59 95	99.31 159

CDPH-MVS		97.94 89	97.49 105	99.28 42	99.47 57	98.44 38	97.91 344	98.67 151	92.57 361	98.77 96	98.85 180	95.93 46	99.72 138	95.56 240	99.69 72	99.68 75

CNVR-MVS		98.78 20	98.56 28	99.45 19	99.32 78	98.87 22	98.47 254	98.81 108	97.72 36	98.76 97	99.16 110	97.05 14	99.78 125	98.06 91	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	98.28 285	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	98.32 225	95.81 208	98.06 325	98.37 251	96.20 135	98.74 98	98.89 175	91.31 176	99.25 234	98.16 86	98.52 189	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	98.89 124	97.03 428	97.29 67	98.73 100	98.90 173	89.41 245	99.32 217	98.68 46	98.86 166	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	95.71 165	98.73 100	99.06 143	95.27 71	99.93 34	97.07 170	99.63 88	99.72 59

UA-Net		97.96 87	97.62 94	98.98 73	98.86 152	97.47 93	98.89 124	99.08 45	96.67 111	98.72 102	99.54 20	93.15 117	99.81 103	94.87 262	98.83 169	99.65 83

NormalMVS		98.07 84	97.90 87	98.59 104	99.75 6	96.60 145	98.94 108	98.60 165	97.86 33	98.71 103	99.08 138	91.22 181	99.80 110	97.40 157	99.57 99	99.37 143

SymmetryMVS		97.84 95	97.58 96	98.62 100	99.01 134	96.60 145	98.94 108	98.44 216	97.86 33	98.71 103	99.08 138	91.22 181	99.80 110	97.40 157	97.53 261	99.47 116

LuminaMVS		97.49 129	97.18 138	98.42 130	97.50 331	97.15 120	98.45 256	97.68 360	96.56 118	98.68 105	98.78 194	89.84 230	99.32 217	98.60 51	98.57 184	98.79 252

h-mvs33		96.17 221	95.62 235	97.81 205	99.03 131	94.45 289	98.64 212	98.75 128	97.48 54	98.67 106	98.72 207	89.76 231	99.86 84	97.95 97	81.59 470	99.11 211

hse-mvs2		95.71 245	95.30 252	96.93 277	98.50 188	93.53 329	98.36 270	98.10 321	97.48 54	98.67 106	97.99 280	89.76 231	99.02 295	97.95 97	80.91 476	98.22 303

ZD-MVS					99.46 59	98.70 29		98.79 120	93.21 332	98.67 106	98.97 156	95.70 53	99.83 91	96.07 215	99.58 98

旧先验2							97.57 381		91.30 404	98.67 106			99.80 110	95.70 236

PS-MVSNAJ		97.73 100	97.77 89	97.62 229	98.68 172	95.58 219	97.34 400	98.51 195	97.29 67	98.66 110	97.88 292	94.51 92	99.90 65	97.87 106	99.17 149	97.39 332

onestephybrid01		97.54 125	97.36 119	98.06 176	98.25 238	95.63 217	98.26 288	98.33 262	96.13 138	98.65 111	99.13 118	91.02 193	99.25 234	98.07 90	98.42 207	99.31 159

xiu_mvs_v2_base		97.66 107	97.70 92	97.56 233	98.61 181	95.46 228	97.44 388	98.46 208	97.15 82	98.65 111	98.15 267	94.33 98	99.80 110	97.84 109	98.66 178	97.41 330

LFMVS		95.86 237	94.98 268	98.47 122	98.87 151	96.32 164	98.84 151	96.02 464	93.40 324	98.62 113	99.20 95	74.99 463	99.63 161	97.72 116	97.20 266	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	94.63 249	98.61 114	98.97 156	95.13 80	99.77 130	97.65 124	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	98.13 264	94.15 307	98.94 108	96.25 463	97.47 56	98.60 115	99.28 76	89.67 235	99.41 207	98.73 44	98.07 234	99.38 142

testdata				98.26 142	99.20 110	95.36 238		98.68 146	91.89 384	98.60 115	99.10 127	94.44 97	99.82 98	94.27 293	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	95.96 150	98.60 115	99.13 118	96.05 41	99.94 14	97.77 113	99.86 2	99.77 40

jason		97.32 154	97.08 149	98.06 176	97.45 337	95.59 218	97.87 352	97.91 344	94.79 239	98.55 118	98.83 185	91.12 188	99.23 246	97.58 133	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	98.41 268	98.68 146	97.04 88	98.52 119	98.80 188	96.78 17	99.83 91	97.93 99	99.61 91	99.74 50

BP-MVS1		97.82 96	97.51 104	98.76 89	98.25 238	97.39 97	99.15 57	97.68 360	96.69 109	98.47 120	99.10 127	90.29 219	99.51 188	98.60 51	99.35 137	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	97.85 107	99.74 58	99.78 33

X-MVStestdata		94.06 366	92.30 392	99.34 32	99.70 27	98.35 51	99.29 28	98.88 78	97.40 59	98.46 121	43.50 546	95.90 49	99.89 69	97.85 107	99.74 58	99.78 33

MG-MVS		97.81 97	97.60 95	98.44 126	99.12 122	95.97 185	97.75 366	98.78 122	96.89 96	98.46 121	99.22 90	93.90 108	99.68 150	94.81 266	99.52 113	99.67 79

viewmamba		97.55 121	97.45 110	97.87 199	98.22 245	95.13 253	98.35 271	98.35 256	96.57 116	98.45 124	99.15 114	91.60 160	99.18 255	97.99 95	98.36 214	99.29 167

test_fmvsmvis_n_1920		98.44 57	98.51 32	98.23 146	98.33 222	96.15 172	98.97 98	99.15 41	98.55 16	98.45 124	99.55 18	94.26 101	99.97 1	99.65 18	99.66 78	98.57 286

NCCC		98.61 31	98.35 48	99.38 24	99.28 93	98.61 33	98.45 256	98.76 126	97.82 35	98.45 124	98.93 166	96.65 21	99.83 91	97.38 160	99.41 129	99.71 63

MVS_Test		97.28 156	97.00 155	98.13 164	98.33 222	95.97 185	98.74 181	98.07 328	94.27 268	98.44 127	98.07 272	92.48 126	99.26 230	96.43 206	98.19 229	99.16 201

MVS_111021_LR		98.34 70	98.23 67	98.67 96	99.27 94	96.90 131	97.95 337	99.58 3	97.14 83	98.44 127	99.01 152	95.03 84	99.62 165	97.91 102	99.75 54	99.50 107

balanced_ft_v1		97.54 125	97.38 117	98.02 181	98.34 218	95.58 219	99.32 22	98.40 236	95.88 154	98.43 129	98.65 214	88.95 265	99.59 168	98.94 36	99.48 121	98.90 242

hybridnocas07		97.41 141	97.21 136	97.99 185	98.24 241	95.42 230	98.21 293	98.32 266	95.97 149	98.38 130	98.93 166	90.48 210	99.21 251	97.92 101	98.46 196	99.34 150

ETV-MVS		97.96 87	97.81 88	98.40 132	98.42 201	97.27 107	98.73 187	98.55 185	96.84 98	98.38 130	97.44 334	95.39 62	99.35 213	97.62 126	98.89 162	98.58 285

test2506		94.44 337	93.91 335	96.04 352	99.02 132	88.99 449	99.06 74	79.47 524	96.96 93	98.36 132	99.26 80	77.21 444	99.52 187	96.78 195	99.04 153	99.59 94

VDDNet		95.36 269	94.53 290	97.86 200	98.10 267	95.13 253	98.85 147	97.75 358	90.46 421	98.36 132	99.39 50	73.27 473	99.64 158	97.98 96	96.58 287	98.81 250

hybrid		97.34 152	97.16 140	97.88 198	98.25 238	95.18 249	98.18 305	98.33 262	95.36 196	98.35 134	99.06 143	90.61 206	99.18 255	97.88 105	98.40 210	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	96.24 133	98.35 134	99.23 87	95.46 59	99.94 14	97.42 155	99.81 16	99.77 40

DELS-MVS		98.40 62	98.20 71	98.99 71	99.00 136	97.66 82	97.75 366	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	97.91 344	99.58 3	97.20 77	98.33 136	99.00 154	95.99 44	99.64 158	98.05 93	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	95.77 161	98.31 138	99.10 127	95.46 59	99.93 34	97.57 137	99.81 16	99.74 50

HPM-MVS++		98.58 36	98.25 63	99.55 11	99.50 49	99.08 13	98.72 191	98.66 154	97.51 51	98.15 139	98.83 185	95.70 53	99.92 43	97.53 141	99.67 75	99.66 82

mvsmamba		97.25 159	96.99 157	98.02 181	98.34 218	95.54 224	99.18 54	97.47 387	95.04 219	98.15 139	98.57 224	89.46 242	99.31 221	97.68 123	99.01 156	99.22 188

新几何1				99.16 56	99.34 72	98.01 72		98.69 143	90.06 429	98.13 141	98.95 163	94.60 90	99.89 69	91.97 373	99.47 122	99.59 94

API-MVS		97.41 141	97.25 128	97.91 194	98.70 167	96.80 135	98.82 155	98.69 143	94.53 254	98.11 142	98.28 254	94.50 95	99.57 172	94.12 300	99.49 118	97.37 334

ECVR-MVS		95.95 229	95.71 229	96.65 300	99.02 132	90.86 405	99.03 83	91.80 507	96.96 93	98.10 143	99.26 80	81.31 401	99.51 188	96.90 181	99.04 153	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	96.27 132	98.09 144	99.26 80	91.00 194	99.30 222	97.81 111	98.48 194	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	92.34 369	98.09 144	99.08 138	93.01 118	99.92 43	96.06 218	99.77 42	99.75 48

viewcassd2359sk11		97.53 127	97.32 123	98.16 155	98.45 197	95.83 204	98.57 234	98.42 231	95.52 183	98.07 146	99.12 122	91.81 154	99.25 234	97.46 151	98.48 194	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	98.55 238	98.41 233	95.42 190	98.06 148	99.12 122	92.23 137	99.24 242	97.43 153	98.45 197	99.39 138

RRT-MVS		97.03 174	96.78 173	97.77 210	97.90 297	94.34 296	99.12 64	98.35 256	95.87 156	98.06 148	98.70 208	86.45 324	99.63 161	98.04 94	98.54 187	99.35 148

test222					99.23 105	97.17 118	97.40 392	98.66 154	88.68 450	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	98.33 274	98.89 75	92.62 358	98.05 150	98.94 164	95.34 67	99.65 155	96.04 219	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	99.35 213	96.01 221	99.21 146	99.45 123
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test1111		95.94 232	95.78 223	96.41 334	98.99 139	90.12 424	99.04 80	92.45 506	96.99 92	98.03 153	99.27 79	81.40 400	99.48 197	96.87 187	99.04 153	99.63 88

baseline		97.64 108	97.44 111	98.25 143	98.35 213	96.20 169	99.00 91	98.32 266	96.33 131	98.03 153	99.17 107	91.35 173	99.16 260	98.10 88	98.29 221	99.39 138

test_yl		97.22 161	96.78 173	98.54 110	98.73 162	96.60 145	98.45 256	98.31 271	94.70 243	98.02 155	98.42 237	90.80 199	99.70 144	96.81 191	96.79 280	99.34 150

DCV-MVSNet		97.22 161	96.78 173	98.54 110	98.73 162	96.60 145	98.45 256	98.31 271	94.70 243	98.02 155	98.42 237	90.80 199	99.70 144	96.81 191	96.79 280	99.34 150

MTAPA		98.58 36	98.29 61	99.46 18	99.76 5	98.64 31	98.90 120	98.74 130	97.27 73	98.02 155	99.39 50	94.81 88	99.96 4	97.91 102	99.79 35	99.77 40

sss		97.39 143	96.98 159	98.61 102	98.60 182	96.61 144	98.22 292	98.93 65	93.97 283	98.01 158	98.48 232	91.98 147	99.85 85	96.45 205	98.15 230	99.39 138

E2		97.48 130	97.25 128	98.16 155	98.40 205	95.79 209	98.58 225	98.44 216	95.58 172	98.00 159	99.14 115	91.21 185	99.24 242	97.50 146	98.43 201	99.45 123

E3		97.48 130	97.25 128	98.16 155	98.38 208	95.79 209	98.58 225	98.44 216	95.58 172	98.00 159	99.14 115	91.25 179	99.24 242	97.50 146	98.44 198	99.45 123

alignmvs		97.56 120	97.07 150	99.01 70	98.66 174	98.37 49	98.83 153	98.06 333	96.74 105	98.00 159	97.65 315	90.80 199	99.48 197	98.37 72	96.56 288	99.19 195

viewmanbaseed2359cas		97.47 133	97.25 128	98.14 159	98.41 203	95.84 203	98.57 234	98.43 227	95.55 179	97.97 162	99.12 122	91.26 178	99.15 264	97.42 155	98.53 188	99.43 130

OMC-MVS		97.55 121	97.34 122	98.20 149	99.33 75	95.92 192	98.28 285	98.59 172	95.52 183	97.97 162	99.10 127	93.28 116	99.49 192	95.09 257	98.88 163	99.19 195

VDD-MVS		95.82 240	95.23 254	97.61 230	98.84 156	93.98 311	98.68 202	97.40 396	95.02 223	97.95 164	99.34 68	74.37 469	99.78 125	98.64 49	96.80 279	99.08 220

casdiffmvs		97.63 110	97.41 114	98.28 138	98.33 222	96.14 173	98.82 155	98.32 266	96.38 127	97.95 164	99.21 93	91.23 180	99.23 246	98.12 87	98.37 212	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
PVSNet_BlendedMVS		96.73 192	96.60 185	97.12 260	99.25 97	95.35 240	98.26 288	99.26 16	94.28 267	97.94 166	97.46 331	92.74 122	99.81 103	96.88 184	93.32 355	96.20 436

PVSNet_Blended		97.38 144	97.12 146	98.14 159	99.25 97	95.35 240	97.28 406	99.26 16	93.13 337	97.94 166	98.21 262	92.74 122	99.81 103	96.88 184	99.40 132	99.27 175

DPM-MVS		97.55 121	96.99 157	99.23 49	99.04 130	98.55 34	97.17 420	98.35 256	94.85 236	97.93 168	98.58 221	95.07 82	99.71 143	92.60 352	99.34 138	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	96.13 138	97.92 169	99.23 87	94.54 91	99.94 14	96.74 197	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		96.64 196	96.02 213	98.51 115	98.04 277	97.30 103	98.74 181	98.60 165	95.04 219	97.91 170	98.84 181	83.59 385	99.48 197	94.20 296	99.25 144	98.75 261

StellarMVS		96.64 196	96.02 213	98.51 115	98.04 277	97.30 103	98.74 181	98.60 165	95.04 219	97.91 170	98.84 181	83.59 385	99.48 197	94.20 296	99.25 144	98.75 261

MDTV_nov1_ep13_2view						84.26 483	96.89 443		90.97 413	97.90 172		89.89 229		93.91 307		99.18 200

test_prior2							97.80 361		96.12 141	97.89 173	98.69 209	95.96 45		96.89 182	99.60 93

viewmacassd2359aftdt		97.32 154	97.07 150	98.08 172	98.30 227	95.69 215	98.62 218	98.44 216	95.56 174	97.86 174	99.22 90	89.91 228	99.14 267	97.29 163	98.43 201	99.42 133

E5new		97.37 146	97.16 140	97.98 187	98.30 227	95.41 231	98.87 134	98.45 212	95.56 174	97.84 175	99.19 102	90.39 214	99.25 234	97.61 129	98.22 225	99.29 167

E6new		97.37 146	97.16 140	97.98 187	98.28 233	95.40 234	98.87 134	98.45 212	95.55 179	97.84 175	99.20 95	90.44 212	99.25 234	97.61 129	98.22 225	99.29 167

E6		97.37 146	97.16 140	97.98 187	98.28 233	95.40 234	98.87 134	98.45 212	95.55 179	97.84 175	99.20 95	90.44 212	99.25 234	97.61 129	98.22 225	99.29 167

E5		97.37 146	97.16 140	97.98 187	98.30 227	95.41 231	98.87 134	98.45 212	95.56 174	97.84 175	99.19 102	90.39 214	99.25 234	97.61 129	98.22 225	99.29 167

原ACMM1				98.65 98	99.32 78	96.62 142		98.67 151	93.27 331	97.81 179	98.97 156	95.18 77	99.83 91	93.84 309	99.46 125	99.50 107

E4		97.37 146	97.13 145	98.12 167	98.27 235	95.70 214	98.59 221	98.44 216	95.56 174	97.80 180	99.18 105	90.57 208	99.26 230	97.45 152	98.28 223	99.40 137

viewmambaseed2359dif		97.01 176	96.84 166	97.51 235	98.19 251	94.21 304	98.16 308	98.23 292	93.61 314	97.78 181	99.13 118	90.79 202	99.18 255	97.24 164	98.40 210	99.15 202

114514_t		96.93 181	96.27 201	98.92 79	99.50 49	97.63 84	98.85 147	98.90 73	84.80 479	97.77 182	99.11 125	92.84 120	99.66 154	94.85 263	99.77 42	99.47 116

casdiffmvs_mvg		97.72 101	97.48 107	98.44 126	98.42 201	96.59 149	98.92 117	98.44 216	96.20 135	97.76 183	99.20 95	91.66 159	99.23 246	98.27 83	98.41 209	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		96.60 199	96.33 199	97.41 242	97.90 297	93.93 313	97.35 399	98.41 233	92.84 350	97.76 183	97.45 333	91.10 190	99.20 252	96.26 211	97.91 239	99.11 211

PVSNet	91.96 18	96.35 212	96.15 205	96.96 275	99.17 112	92.05 383	96.08 464	98.68 146	93.69 304	97.75 185	97.80 302	88.86 267	99.69 149	94.26 294	99.01 156	99.15 202

TEST9					99.31 80	98.50 36	97.92 342	98.73 133	92.63 357	97.74 186	98.68 210	96.20 36	99.80 110

train_agg		97.97 86	97.52 103	99.33 36	99.31 80	98.50 36	97.92 342	98.73 133	92.98 343	97.74 186	98.68 210	96.20 36	99.80 110	96.59 198	99.57 99	99.68 75

FE-MVS		95.62 251	94.90 272	97.78 207	98.37 211	94.92 267	97.17 420	97.38 398	90.95 414	97.73 188	97.70 308	85.32 349	99.63 161	91.18 388	98.33 217	98.79 252

mmtdpeth		93.12 388	92.61 384	94.63 421	97.60 320	89.68 435	99.21 45	97.32 402	94.02 277	97.72 189	94.42 463	77.01 449	99.44 204	99.05 31	77.18 488	94.78 471

CANet		98.05 85	97.76 90	98.90 82	98.73 162	97.27 107	98.35 271	98.78 122	97.37 64	97.72 189	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	97.89 350	98.72 135	92.98 343	97.70 191	98.66 213	96.20 36	99.80 110

hybridcas		97.52 128	97.29 125	98.20 149	98.44 198	96.00 178	99.02 86	98.39 242	96.12 141	97.69 192	99.23 87	90.77 204	99.17 258	97.55 138	98.42 207	99.44 126

MP-MVS-pluss		98.31 73	97.92 85	99.49 16	99.72 17	98.88 21	98.43 264	98.78 122	94.10 273	97.69 192	99.42 46	95.25 73	99.92 43	98.09 89	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	97.67 194	97.40 338	92.26 134	99.49 192	98.28 80	96.28 302	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	97.67 194	97.40 338	92.26 134	99.49 192	98.28 80	96.28 302	99.08 220

PVSNet_Blended_VisFu		97.70 103	97.46 108	98.44 126	99.27 94	95.91 193	98.63 215	99.16 39	94.48 260	97.67 194	98.88 176	92.80 121	99.91 57	97.11 168	99.12 150	99.50 107

WTY-MVS		97.37 146	96.92 162	98.72 92	98.86 152	96.89 133	98.31 279	98.71 138	95.26 202	97.67 194	98.56 225	92.21 139	99.78 125	95.89 223	96.85 278	99.48 114

dtuplus		97.00 177	96.83 168	97.51 235	98.18 257	94.21 304	98.21 293	98.20 296	94.42 264	97.66 198	99.22 90	90.18 223	99.17 258	97.01 171	98.36 214	99.13 207

viewdifsd2359ckpt07		97.20 164	97.05 152	97.65 226	98.40 205	94.33 298	98.39 269	98.43 227	95.67 167	97.66 198	99.08 138	90.04 225	99.32 217	97.47 150	98.29 221	99.31 159

Effi-MVS+		97.12 171	96.69 179	98.39 133	98.19 251	96.72 140	97.37 396	98.43 227	93.71 301	97.65 200	98.02 276	92.20 140	99.25 234	96.87 187	97.79 244	99.19 195

thisisatest0530		96.01 226	95.36 245	97.97 191	98.38 208	95.52 225	98.88 131	94.19 494	94.04 275	97.64 201	98.31 252	83.82 383	99.46 202	95.29 251	97.70 250	98.93 239

tttt0517		96.07 224	95.51 238	97.78 207	98.41 203	94.84 270	99.28 30	94.33 490	94.26 269	97.64 201	98.64 215	84.05 376	99.47 201	95.34 246	97.60 253	99.03 228

viewdifsd2359ckpt11		96.30 214	96.13 206	96.81 286	98.10 267	92.10 379	98.49 252	98.40 236	96.02 145	97.61 203	99.31 71	86.37 326	99.29 225	97.52 142	93.36 354	99.04 226

viewmsd2359difaftdt		96.30 214	96.13 206	96.81 286	98.10 267	92.10 379	98.49 252	98.40 236	96.02 145	97.61 203	99.31 71	86.37 326	99.30 222	97.52 142	93.37 353	99.04 226

HyFIR lowres test		96.90 183	96.49 192	98.14 159	99.33 75	95.56 221	97.38 394	99.65 2	92.34 369	97.61 203	98.20 263	89.29 249	99.10 278	96.97 174	97.60 253	99.77 40

viewdifsd2359ckpt13		97.24 160	96.97 160	98.06 176	98.43 199	95.77 211	98.59 221	98.34 260	94.81 237	97.60 206	98.94 164	90.78 203	99.09 279	96.93 177	98.33 217	99.32 158

ACMMP		98.23 76	97.95 84	99.09 63	99.74 12	97.62 85	99.03 83	99.41 6	95.98 148	97.60 206	99.36 60	94.45 96	99.93 34	97.14 167	98.85 168	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	97.58 208	97.42 337	92.10 143	99.50 191	98.28 80	96.25 305	99.08 220

agg_prior					99.30 84	98.38 42		98.72 135		97.57 209			99.81 103

tpmrst		95.63 250	95.69 232	95.44 388	97.54 327	88.54 457	96.97 432	97.56 374	93.50 318	97.52 210	96.93 389	89.49 238	99.16 260	95.25 253	96.42 293	98.64 277

MDTV_nov1_ep13			95.40 240		97.48 332	88.34 461	96.85 448	97.29 405	93.74 297	97.48 211	97.26 348	89.18 252	99.05 285	91.92 374	97.43 263

FA-MVS(test-final)		96.41 211	95.94 217	97.82 204	98.21 247	95.20 248	97.80 361	97.58 371	93.21 332	97.36 212	97.70 308	89.47 240	99.56 175	94.12 300	97.99 236	98.71 267

viewdifsd2359ckpt09		97.13 170	96.79 171	98.14 159	98.43 199	95.90 194	98.52 241	98.37 251	94.32 266	97.33 213	98.86 179	90.23 222	99.16 260	96.81 191	98.25 224	99.36 147

icg_test_0407_2		96.56 203	96.50 191	96.73 291	97.99 284	92.82 363	97.18 417	98.27 281	95.16 207	97.30 214	98.79 190	91.53 167	98.10 406	94.74 268	97.54 257	99.27 175

IMVS_0407		96.74 190	96.64 183	97.05 266	97.99 284	92.82 363	98.45 256	98.27 281	95.16 207	97.30 214	98.79 190	91.53 167	99.06 284	94.74 268	97.54 257	99.27 175

EPMVS		94.99 294	94.48 293	96.52 321	97.22 352	91.75 388	97.23 408	91.66 508	94.11 272	97.28 216	96.81 398	85.70 339	98.84 323	93.04 333	97.28 265	98.97 234

EIA-MVS		97.75 99	97.58 96	98.27 139	98.38 208	96.44 156	99.01 89	98.60 165	95.88 154	97.26 217	97.53 328	94.97 85	99.33 216	97.38 160	99.20 147	99.05 225

SSM_0404		97.26 158	97.00 155	98.03 179	98.46 195	95.99 179	98.62 218	98.44 216	94.77 240	97.24 218	98.93 166	91.22 181	99.28 227	96.54 200	98.74 173	98.84 247

IS-MVSNet		97.22 161	96.88 163	98.25 143	98.85 155	96.36 162	99.19 50	97.97 338	95.39 192	97.23 219	98.99 155	91.11 189	98.93 310	94.60 280	98.59 181	99.47 116

testing3-2		95.45 260	95.34 246	95.77 375	98.69 170	88.75 453	98.87 134	97.21 413	96.13 138	97.22 220	97.68 313	77.95 437	99.65 155	97.58 133	96.77 282	98.91 241

EPP-MVSNet		97.46 134	97.28 126	97.99 185	98.64 178	95.38 237	99.33 21	98.31 271	93.61 314	97.19 221	99.07 142	94.05 104	99.23 246	96.89 182	98.43 201	99.37 143

thisisatest0515		95.61 254	94.89 273	97.76 211	98.15 263	95.15 252	96.77 451	94.41 488	92.95 345	97.18 222	97.43 335	84.78 358	99.45 203	94.63 276	97.73 249	98.68 271

IMVS_0403		96.74 190	96.61 184	97.12 260	97.99 284	92.82 363	98.47 254	98.27 281	95.16 207	97.13 223	98.79 190	91.44 170	99.26 230	94.74 268	97.54 257	99.27 175

CANet_DTU		96.96 180	96.55 187	98.21 147	98.17 261	96.07 177	97.98 335	98.21 294	97.24 74	97.13 223	98.93 166	86.88 316	99.91 57	95.00 260	99.37 136	98.66 275

CHOSEN 1792x2688		97.12 171	96.80 169	98.08 172	99.30 84	94.56 287	98.05 326	99.71 1	93.57 316	97.09 225	98.91 172	88.17 285	99.89 69	96.87 187	99.56 107	99.81 25

PatchT		93.06 389	91.97 396	96.35 339	96.69 388	92.67 368	94.48 496	97.08 422	86.62 466	97.08 226	92.23 492	87.94 293	97.90 431	78.89 492	96.69 283	98.49 290

PatchmatchNet		95.71 245	95.52 236	96.29 344	97.58 322	90.72 409	96.84 449	97.52 382	94.06 274	97.08 226	96.96 384	89.24 251	98.90 316	92.03 370	98.37 212	99.26 182
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MAR-MVS		96.91 182	96.40 195	98.45 124	98.69 170	96.90 131	98.66 209	98.68 146	92.40 368	97.07 228	97.96 283	91.54 166	99.75 133	93.68 313	98.92 160	98.69 269
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	98.63 215	98.60 165	95.18 206	97.06 229	98.06 273	94.26 101	99.57 172	93.80 311	98.87 165	99.52 101

TAMVS		97.02 175	96.79 171	97.70 217	98.06 273	95.31 243	98.52 241	98.31 271	93.95 284	97.05 230	98.61 216	93.49 112	98.52 354	95.33 247	97.81 243	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	93.04 341	97.02 231	98.92 171	95.36 65	99.91 57	97.43 153	99.64 86	99.52 101

CDS-MVSNet		96.99 178	96.69 179	97.90 195	98.05 275	95.98 180	98.20 297	98.33 262	93.67 308	96.95 232	98.49 231	93.54 111	98.42 365	95.24 254	97.74 248	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		96.51 205	96.34 198	97.02 268	98.77 160	93.76 318	97.79 363	98.50 200	95.45 187	96.94 233	99.09 135	87.87 296	99.55 182	96.76 196	95.83 316	97.74 320

CR-MVSNet		94.76 311	94.15 316	96.59 311	97.00 366	93.43 332	94.96 485	97.56 374	92.46 362	96.93 234	96.24 422	88.15 286	97.88 436	87.38 447	96.65 285	98.46 292

RPMNet		92.81 391	91.34 402	97.24 249	97.00 366	93.43 332	94.96 485	98.80 115	82.27 486	96.93 234	92.12 493	86.98 314	99.82 98	76.32 500	96.65 285	98.46 292

SCA		95.46 258	95.13 258	96.46 330	97.67 314	91.29 397	97.33 401	97.60 370	94.68 246	96.92 236	97.10 359	83.97 378	98.89 317	92.59 354	98.32 220	99.20 191

PatchMatch-RL		96.59 200	96.03 212	98.27 139	99.31 80	96.51 153	97.91 344	99.06 47	93.72 300	96.92 236	98.06 273	88.50 278	99.65 155	91.77 378	99.00 158	98.66 275

DeepC-MVS	95.98 3	97.88 91	97.58 96	98.77 88	99.25 97	96.93 129	98.83 153	98.75 128	96.96 93	96.89 238	99.50 31	90.46 211	99.87 80	97.84 109	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	96.55 187	98.25 143	98.26 236	96.28 167	98.93 114	98.33 262	94.99 224	96.87 239	99.09 135	88.97 263	99.07 282	95.70 236	97.77 246	99.39 138

XVG-OURS		96.55 204	96.41 194	96.99 269	98.75 161	93.76 318	97.50 385	98.52 192	95.67 167	96.83 240	99.30 74	88.95 265	99.53 184	95.88 224	96.26 304	97.69 323

AdaColmap		97.15 169	96.70 178	98.48 121	99.16 116	96.69 141	98.01 331	98.89 75	94.44 262	96.83 240	98.68 210	90.69 205	99.76 131	94.36 288	99.29 143	98.98 233

CostFormer		94.95 301	94.73 279	95.60 382	97.28 348	89.06 446	97.53 382	96.89 441	89.66 436	96.82 242	96.72 402	86.05 333	98.95 309	95.53 242	96.13 310	98.79 252

UGNet		96.78 189	96.30 200	98.19 153	98.24 241	95.89 199	98.88 131	98.93 65	97.39 61	96.81 243	97.84 296	82.60 390	99.90 65	96.53 202	99.49 118	98.79 252
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	97.03 154	98.73 91	99.05 129	97.44 96	98.07 324	98.53 189	95.32 199	96.80 244	98.53 226	93.32 114	99.72 138	94.31 292	99.31 142	99.02 229

CHOSEN 280x420		97.18 166	97.18 138	97.20 251	98.81 158	93.27 346	95.78 471	99.15 41	95.25 203	96.79 245	98.11 270	92.29 133	99.07 282	98.56 55	99.85 6	99.25 184

mamba_0408		96.81 188	96.38 196	98.09 171	98.19 251	95.90 194	95.69 472	98.32 266	94.51 257	96.75 246	98.73 204	90.99 195	99.27 229	95.83 226	98.43 201	99.10 213

SSM_04072		96.71 193	96.38 196	97.68 220	98.19 251	95.90 194	95.69 472	98.32 266	94.51 257	96.75 246	98.73 204	90.99 195	98.02 421	95.83 226	98.43 201	99.10 213

SSM_0407		97.17 167	96.87 164	98.08 172	98.19 251	95.90 194	98.52 241	98.44 216	94.77 240	96.75 246	98.93 166	91.22 181	99.22 250	96.54 200	98.43 201	99.10 213

HY-MVS	93.96 8	96.82 187	96.23 204	98.57 105	98.46 195	97.00 126	98.14 312	98.21 294	93.95 284	96.72 249	97.99 280	91.58 161	99.76 131	94.51 284	96.54 289	98.95 237

PAPR		96.84 186	96.24 203	98.65 98	98.72 166	96.92 130	97.36 398	98.57 179	93.33 326	96.67 250	97.57 324	94.30 99	99.56 175	91.05 396	98.59 181	99.47 116

Anonymous20240529		95.10 286	94.22 310	97.75 212	99.01 134	94.26 301	98.87 134	98.83 98	85.79 474	96.64 251	98.97 156	78.73 426	99.85 85	96.27 210	94.89 322	99.12 208

UWE-MVS		94.30 344	93.89 338	95.53 383	97.83 301	88.95 450	97.52 384	93.25 499	94.44 262	96.63 252	97.07 366	78.70 427	99.28 227	91.99 371	97.56 256	98.36 297

thres600view7		95.49 256	94.77 276	97.67 222	98.98 140	95.02 258	98.85 147	96.90 439	95.38 193	96.63 252	96.90 391	84.29 368	99.59 168	88.65 434	96.33 295	98.40 294

thres100view900		95.38 266	94.70 281	97.41 242	98.98 140	94.92 267	98.87 134	96.90 439	95.38 193	96.61 254	96.88 392	84.29 368	99.56 175	88.11 438	96.29 299	97.76 318

Vis-MVSNet (Re-imp)		96.87 184	96.55 187	97.83 202	98.73 162	95.46 228	99.20 48	98.30 278	94.96 228	96.60 255	98.87 177	90.05 224	98.59 349	93.67 315	98.60 180	99.46 121

CVMVSNet		95.43 262	96.04 211	93.57 442	97.93 295	83.62 486	98.12 315	98.59 172	95.68 166	96.56 256	99.02 148	87.51 303	97.51 454	93.56 319	97.44 262	99.60 92

RPSCF		94.87 305	95.40 240	93.26 448	98.89 147	82.06 493	98.33 274	98.06 333	90.30 426	96.56 256	99.26 80	87.09 311	99.49 192	93.82 310	96.32 296	98.24 301

tfpn200view9		95.32 273	94.62 285	97.43 240	98.94 144	94.98 263	98.68 202	96.93 437	95.33 197	96.55 258	96.53 411	84.23 372	99.56 175	88.11 438	96.29 299	97.76 318

thres400		95.38 266	94.62 285	97.65 226	98.94 144	94.98 263	98.68 202	96.93 437	95.33 197	96.55 258	96.53 411	84.23 372	99.56 175	88.11 438	96.29 299	98.40 294

thres200		95.25 276	94.57 288	97.28 248	98.81 158	94.92 267	98.20 297	97.11 420	95.24 205	96.54 260	96.22 426	84.58 365	99.53 184	87.93 444	96.50 291	97.39 332

ab-mvs		96.42 208	95.71 229	98.55 108	98.63 179	96.75 138	97.88 351	98.74 130	93.84 290	96.54 260	98.18 265	85.34 347	99.75 133	95.93 222	96.35 294	99.15 202

Anonymous202405211		95.28 275	94.49 292	97.67 222	99.00 136	93.75 320	98.70 196	97.04 427	90.66 417	96.49 262	98.80 188	78.13 433	99.83 91	96.21 214	95.36 321	99.44 126

ADS-MVSNet2		94.58 323	94.40 302	95.11 398	98.00 282	88.74 454	96.04 465	97.30 404	90.15 427	96.47 263	96.64 408	87.89 294	97.56 452	90.08 408	97.06 270	99.02 229

ADS-MVSNet		95.00 292	94.45 298	96.63 305	98.00 282	91.91 385	96.04 465	97.74 359	90.15 427	96.47 263	96.64 408	87.89 294	98.96 304	90.08 408	97.06 270	99.02 229

Effi-MVS+-dtu		96.29 216	96.56 186	95.51 384	97.89 299	90.22 423	98.80 164	98.10 321	96.57 116	96.45 265	96.66 405	90.81 198	98.91 313	95.72 233	97.99 236	97.40 331

ETVMVS		94.50 331	93.44 365	97.68 220	98.18 257	95.35 240	98.19 300	97.11 420	93.73 298	96.40 266	95.39 452	74.53 466	98.84 323	91.10 390	96.31 297	98.84 247

PLC	95.07 4	97.20 164	96.78 173	98.44 126	99.29 89	96.31 166	98.14 312	98.76 126	92.41 367	96.39 267	98.31 252	94.92 87	99.78 125	94.06 303	98.77 172	99.23 186
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		94.13 358	93.80 344	95.12 397	96.50 398	87.91 467	97.44 388	95.89 470	92.62 358	96.37 268	96.30 421	84.13 375	98.30 388	93.24 325	91.66 379	99.14 205

TAPA-MVS	93.98 7	95.35 270	94.56 289	97.74 213	99.13 120	94.83 272	98.33 274	98.64 159	86.62 466	96.29 269	98.61 216	94.00 106	99.29 225	80.00 486	99.41 129	99.09 216
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dtuonly		95.08 289	95.10 262	95.02 402	96.53 395	87.27 472	96.33 463	97.21 413	93.41 323	96.28 270	98.51 230	87.71 298	98.99 299	91.88 375	98.01 235	98.80 251

myMVS_eth3d28		95.12 284	94.62 285	96.64 304	98.17 261	92.17 375	98.02 330	97.32 402	95.41 191	96.22 271	96.05 432	78.01 435	99.13 269	95.22 255	97.16 267	98.60 280

baseline1		95.84 238	95.12 260	98.01 183	98.49 192	95.98 180	98.73 187	97.03 428	95.37 195	96.22 271	98.19 264	89.96 227	99.16 260	94.60 280	87.48 433	98.90 242

tpm2		94.19 353	93.76 349	95.46 387	97.23 351	89.04 447	97.31 404	96.85 445	87.08 459	96.21 273	96.79 399	83.75 384	98.74 334	92.43 362	96.23 307	98.59 283

UBG		95.32 273	94.72 280	97.13 258	98.05 275	93.26 347	97.87 352	97.20 416	94.96 228	96.18 274	95.66 449	80.97 407	99.35 213	94.47 286	97.08 269	98.78 256

F-COLMAP		97.09 173	96.80 169	97.97 191	99.45 62	94.95 266	98.55 238	98.62 164	93.02 342	96.17 275	98.58 221	94.01 105	99.81 103	93.95 305	98.90 161	99.14 205

GeoE		96.58 202	96.07 209	98.10 170	98.35 213	95.89 199	99.34 17	98.12 315	93.12 338	96.09 276	98.87 177	89.71 234	98.97 300	92.95 336	98.08 233	99.43 130

JIA-IIPM		93.35 378	92.49 388	95.92 363	96.48 400	90.65 411	95.01 483	96.96 435	85.93 472	96.08 277	87.33 511	87.70 301	98.78 332	91.35 386	95.58 319	98.34 298

BH-RMVSNet		95.92 234	95.32 250	97.69 218	98.32 225	94.64 279	98.19 300	97.45 392	94.56 252	96.03 278	98.61 216	85.02 352	99.12 272	90.68 401	99.06 152	99.30 164

dp		94.15 357	93.90 336	94.90 407	97.31 347	86.82 474	96.97 432	97.19 417	91.22 409	96.02 279	96.61 410	85.51 343	99.02 295	90.00 412	94.30 324	98.85 245

EPNet		97.28 156	96.87 164	98.51 115	94.98 454	96.14 173	98.90 120	97.02 431	98.28 21	95.99 280	99.11 125	91.36 172	99.89 69	96.98 173	99.19 148	99.50 107
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LS3D		97.16 168	96.66 182	98.68 95	98.53 187	97.19 117	98.93 114	98.90 73	92.83 351	95.99 280	99.37 56	92.12 142	99.87 80	93.67 315	99.57 99	98.97 234

SDMVSNet		96.85 185	96.42 193	98.14 159	99.30 84	96.38 160	99.21 45	99.23 27	95.92 151	95.96 282	98.76 202	85.88 336	99.44 204	97.93 99	95.59 317	98.60 280

sd_testset		96.17 221	95.76 224	97.42 241	99.30 84	94.34 296	98.82 155	99.08 45	95.92 151	95.96 282	98.76 202	82.83 389	99.32 217	95.56 240	95.59 317	98.60 280

AUN-MVS		94.53 328	93.73 351	96.92 280	98.50 188	93.52 330	98.34 273	98.10 321	93.83 292	95.94 284	97.98 282	85.59 342	99.03 291	94.35 289	80.94 475	98.22 303

testing222		94.12 360	93.03 375	97.37 247	98.02 280	94.66 277	97.94 340	96.65 454	94.63 249	95.78 285	95.76 440	71.49 476	98.92 311	91.17 389	95.88 314	98.52 288

TR-MVS		94.94 303	94.20 311	97.17 255	97.75 306	94.14 308	97.59 379	97.02 431	92.28 373	95.75 286	97.64 318	83.88 380	98.96 304	89.77 414	96.15 309	98.40 294

WB-MVSnew		94.19 353	94.04 322	94.66 419	96.82 380	92.14 376	97.86 354	95.96 467	93.50 318	95.64 287	96.77 400	88.06 290	97.99 425	84.87 466	96.86 276	93.85 488

MonoMVSNet		95.51 255	95.45 239	95.68 377	95.54 441	90.87 404	98.92 117	97.37 399	95.79 160	95.53 288	97.38 340	89.58 237	97.68 445	96.40 207	92.59 365	98.49 290

VPA-MVSNet		95.75 243	95.11 261	97.69 218	97.24 350	97.27 107	98.94 108	99.23 27	95.13 212	95.51 289	97.32 345	85.73 338	98.91 313	97.33 162	89.55 407	96.89 358

testing91		94.98 296	94.25 309	97.20 251	97.94 293	93.41 334	98.00 333	97.58 371	94.99 224	95.45 290	96.04 433	77.20 445	99.42 206	94.97 261	96.02 312	98.78 256

testing99		94.83 306	94.08 320	97.07 265	97.94 293	93.13 353	98.10 321	97.17 418	94.86 234	95.34 291	96.00 437	76.31 453	99.40 208	95.08 258	95.90 313	98.68 271

HQP_MVS		96.14 223	95.90 219	96.85 283	97.42 339	94.60 285	98.80 164	98.56 183	97.28 69	95.34 291	98.28 254	87.09 311	99.03 291	96.07 215	94.27 325	96.92 350

plane_prior3						94.61 283			97.02 89	95.34 291

testing11		95.00 292	94.28 305	97.16 256	97.96 292	93.36 340	98.09 322	97.06 426	94.94 232	95.33 294	96.15 428	76.89 450	99.40 208	95.77 232	96.30 298	98.72 264

Fast-Effi-MVS+		96.28 218	95.70 231	98.03 179	98.29 231	95.97 185	98.58 225	98.25 290	91.74 387	95.29 295	97.23 352	91.03 192	99.15 264	92.90 338	97.96 238	98.97 234

test_fmvs2		93.43 376	93.58 358	92.95 455	96.97 369	83.91 485	99.19 50	97.24 410	95.74 162	95.20 296	98.27 257	69.65 478	98.72 336	96.26 211	93.73 342	96.24 434

EI-MVSNet		95.96 228	95.83 221	96.36 338	97.93 295	93.70 324	98.12 315	98.27 281	93.70 303	95.07 297	99.02 148	92.23 137	98.54 352	94.68 273	93.46 348	96.84 365

MVSTER		96.06 225	95.72 226	97.08 264	98.23 244	95.93 191	98.73 187	98.27 281	94.86 234	95.07 297	98.09 271	88.21 284	98.54 352	96.59 198	93.46 348	96.79 369

OPM-MVS		95.69 248	95.33 249	96.76 290	96.16 415	94.63 280	98.43 264	98.39 242	96.64 112	95.02 299	98.78 194	85.15 351	99.05 285	95.21 256	94.20 328	96.60 395
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+-dtu		95.87 236	95.85 220	95.91 364	97.74 309	91.74 389	98.69 199	98.15 311	95.56 174	94.92 300	97.68 313	88.98 262	98.79 331	93.19 327	97.78 245	97.20 338

TESTMET0.1,1		94.18 356	93.69 354	95.63 380	96.92 372	89.12 445	96.91 438	94.78 485	93.17 334	94.88 301	96.45 415	78.52 428	98.92 311	93.09 330	98.50 191	98.85 245

VPNet		94.99 294	94.19 312	97.40 244	97.16 359	96.57 150	98.71 192	98.97 57	95.67 167	94.84 302	98.24 261	80.36 414	98.67 341	96.46 204	87.32 437	96.96 345

1112_ss		96.63 198	96.00 215	98.50 118	98.56 183	96.37 161	98.18 305	98.10 321	92.92 346	94.84 302	98.43 235	92.14 141	99.58 171	94.35 289	96.51 290	99.56 100

test-LLR		95.10 286	94.87 274	95.80 372	96.77 382	89.70 433	96.91 438	95.21 477	95.11 214	94.83 304	95.72 445	87.71 298	98.97 300	93.06 331	98.50 191	98.72 264

test-mter		94.08 364	93.51 362	95.80 372	96.77 382	89.70 433	96.91 438	95.21 477	92.89 348	94.83 304	95.72 445	77.69 439	98.97 300	93.06 331	98.50 191	98.72 264

Test_1112_low_res		96.34 213	95.66 234	98.36 134	98.56 183	95.94 188	97.71 369	98.07 328	92.10 379	94.79 306	97.29 347	91.75 155	99.56 175	94.17 298	96.50 291	99.58 98

UWE-MVS-28		92.79 392	92.51 387	93.62 441	96.46 401	86.28 476	97.93 341	92.71 504	94.17 270	94.78 307	97.16 356	81.05 406	96.43 477	81.45 481	96.86 276	98.14 308

GA-MVS		94.81 307	94.03 324	97.14 257	97.15 360	93.86 315	96.76 452	97.58 371	94.00 281	94.76 308	97.04 374	80.91 408	98.48 356	91.79 377	96.25 305	99.09 216

BH-untuned		95.95 229	95.72 226	96.65 300	98.55 185	92.26 374	98.23 291	97.79 356	93.73 298	94.62 309	98.01 278	88.97 263	99.00 298	93.04 333	98.51 190	98.68 271

test_djsdf		96.00 227	95.69 232	96.93 277	95.72 435	95.49 226	99.47 7	98.40 236	94.98 226	94.58 310	97.86 293	89.16 253	98.41 372	96.91 178	94.12 333	96.88 359

cascas		94.63 319	93.86 340	96.93 277	96.91 374	94.27 300	96.00 468	98.51 195	85.55 476	94.54 311	96.23 424	84.20 374	98.87 320	95.80 230	96.98 275	97.66 324

DP-MVS		96.59 200	95.93 218	98.57 105	99.34 72	96.19 171	98.70 196	98.39 242	89.45 440	94.52 312	99.35 62	91.85 151	99.85 85	92.89 340	98.88 163	99.68 75

gg-mvs-nofinetune		92.21 400	90.58 409	97.13 258	96.75 385	95.09 255	95.85 469	89.40 514	85.43 477	94.50 313	81.98 517	80.80 411	98.40 378	92.16 364	98.33 217	97.88 315

mvs_anonymous		96.70 195	96.53 190	97.18 254	98.19 251	93.78 317	98.31 279	98.19 299	94.01 280	94.47 314	98.27 257	92.08 145	98.46 360	97.39 159	97.91 239	99.31 159

HQP-NCC					97.20 354		98.05 326		96.43 121	94.45 315

ACMP_Plane					97.20 354		98.05 326		96.43 121	94.45 315

HQP4-MVS										94.45 315			98.96 304			96.87 362

HQP-MVS		95.72 244	95.40 240	96.69 297	97.20 354	94.25 302	98.05 326	98.46 208	96.43 121	94.45 315	97.73 305	86.75 317	98.96 304	95.30 249	94.18 329	96.86 364

MSDG		95.93 233	95.30 252	97.83 202	98.90 146	95.36 238	96.83 450	98.37 251	91.32 403	94.43 319	98.73 204	90.27 220	99.60 167	90.05 410	98.82 170	98.52 288

dmvs_re		94.48 334	94.18 314	95.37 390	97.68 313	90.11 425	98.54 240	97.08 422	94.56 252	94.42 320	97.24 351	84.25 370	97.76 442	91.02 397	92.83 362	98.24 301

nrg030		96.28 218	95.72 226	97.96 193	96.90 375	98.15 65	99.39 11	98.31 271	95.47 186	94.42 320	98.35 245	92.09 144	98.69 337	97.50 146	89.05 416	97.04 341

CLD-MVS		95.62 251	95.34 246	96.46 330	97.52 330	93.75 320	97.27 407	98.46 208	95.53 182	94.42 320	98.00 279	86.21 330	98.97 300	96.25 213	94.37 323	96.66 387
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		95.62 251	95.34 246	96.47 327	97.46 334	93.54 327	98.99 94	98.54 187	94.67 247	94.36 323	98.77 197	85.39 344	99.11 274	95.71 234	94.15 331	96.76 372

LGP-MVS_train				96.47 327	97.46 334	93.54 327		98.54 187	94.67 247	94.36 323	98.77 197	85.39 344	99.11 274	95.71 234	94.15 331	96.76 372

v144192		94.39 340	93.70 353	96.48 326	96.06 419	94.35 295	98.58 225	98.16 310	91.45 396	94.33 325	97.02 377	87.50 305	98.45 361	91.08 393	89.11 415	96.63 389

IMVS_0404		95.82 240	95.52 236	96.73 291	97.99 284	92.82 363	97.23 408	98.27 281	95.16 207	94.31 326	98.79 190	85.63 340	98.10 406	94.74 268	97.54 257	99.27 175

V42		94.78 309	94.14 317	96.70 296	96.33 407	95.22 247	98.97 98	98.09 325	92.32 371	94.31 326	97.06 370	88.39 279	98.55 351	92.90 338	88.87 420	96.34 429

VortexMVS		95.95 229	95.79 222	96.42 333	98.29 231	93.96 312	98.68 202	98.31 271	96.02 145	94.29 328	97.57 324	89.47 240	98.37 379	97.51 145	91.93 373	96.94 348

ACMM	93.85 9	95.69 248	95.38 244	96.61 308	97.61 319	93.84 316	98.91 119	98.44 216	95.25 203	94.28 329	98.47 233	86.04 335	99.12 272	95.50 243	93.95 338	96.87 362
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS-LS		95.46 258	95.21 255	96.22 346	98.12 265	93.72 323	98.32 278	98.13 314	93.71 301	94.26 330	97.31 346	92.24 136	98.10 406	94.63 276	90.12 398	96.84 365
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		94.20 352	93.47 364	96.40 336	95.98 423	94.08 309	98.52 241	98.15 311	91.33 402	94.25 331	97.20 355	86.41 325	98.42 365	90.04 411	89.39 412	96.69 386

BH-w/o		95.38 266	95.08 263	96.26 345	98.34 218	91.79 386	97.70 370	97.43 394	92.87 349	94.24 332	97.22 353	88.66 271	98.84 323	91.55 384	97.70 250	98.16 307

XVG-ACMP-BASELINE		94.54 326	94.14 317	95.75 376	96.55 394	91.65 391	98.11 319	98.44 216	94.96 228	94.22 333	97.90 289	79.18 424	99.11 274	94.05 304	93.85 340	96.48 423

v1144		94.59 322	93.92 333	96.60 310	96.21 409	94.78 276	98.59 221	98.14 313	91.86 386	94.21 334	97.02 377	87.97 292	98.41 372	91.72 379	89.57 405	96.61 393

v1192		94.32 343	93.58 358	96.53 320	96.10 417	94.45 289	98.50 249	98.17 308	91.54 394	94.19 335	97.06 370	86.95 315	98.43 364	90.14 406	89.57 405	96.70 381

PAPM		94.95 301	94.00 328	97.78 207	97.04 365	95.65 216	96.03 467	98.25 290	91.23 408	94.19 335	97.80 302	91.27 177	98.86 322	82.61 477	97.61 252	98.84 247

Patchmatch-test		94.42 338	93.68 355	96.63 305	97.60 320	91.76 387	94.83 489	97.49 386	89.45 440	94.14 337	97.10 359	88.99 259	98.83 326	85.37 463	98.13 231	99.29 167

v1240		94.06 366	93.29 370	96.34 340	96.03 421	93.90 314	98.44 262	98.17 308	91.18 411	94.13 338	97.01 379	86.05 333	98.42 365	89.13 428	89.50 409	96.70 381

GBi-Net		94.49 332	93.80 344	96.56 315	98.21 247	95.00 259	98.82 155	98.18 302	92.46 362	94.09 339	97.07 366	81.16 403	97.95 427	92.08 366	92.14 370	96.72 377

test1		94.49 332	93.80 344	96.56 315	98.21 247	95.00 259	98.82 155	98.18 302	92.46 362	94.09 339	97.07 366	81.16 403	97.95 427	92.08 366	92.14 370	96.72 377

FMVSNet3		94.97 298	94.26 308	97.11 262	98.18 257	96.62 142	98.56 237	98.26 289	93.67 308	94.09 339	97.10 359	84.25 370	98.01 422	92.08 366	92.14 370	96.70 381

MIMVSNet		93.26 382	92.21 393	96.41 334	97.73 310	93.13 353	95.65 474	97.03 428	91.27 407	94.04 342	96.06 431	75.33 459	97.19 459	86.56 453	96.23 307	98.92 240

FIs		96.51 205	96.12 208	97.67 222	97.13 361	97.54 89	99.36 14	99.22 32	95.89 153	94.03 343	98.35 245	91.98 147	98.44 363	96.40 207	92.76 363	97.01 342

v2v482		94.69 312	94.03 324	96.65 300	96.17 413	94.79 275	98.67 207	98.08 326	92.72 353	94.00 344	97.16 356	87.69 302	98.45 361	92.91 337	88.87 420	96.72 377

testing3		93.19 385	92.48 389	95.30 393	98.07 270	92.27 372	98.64 212	97.17 418	93.94 286	93.98 345	97.04 374	67.97 483	96.01 483	88.40 436	97.14 268	97.63 325

FC-MVSNet-test		96.42 208	96.05 210	97.53 234	96.95 370	97.27 107	99.36 14	99.23 27	95.83 158	93.93 346	98.37 243	92.00 146	98.32 384	96.02 220	92.72 364	97.00 343

UniMVSNet (Re)		95.78 242	95.19 256	97.58 231	96.99 368	97.47 93	98.79 172	99.18 36	95.60 170	93.92 347	97.04 374	91.68 157	98.48 356	95.80 230	87.66 432	96.79 369

miper_enhance_ethall		95.10 286	94.75 278	96.12 350	97.53 329	93.73 322	96.61 457	98.08 326	92.20 377	93.89 348	96.65 407	92.44 127	98.30 388	94.21 295	91.16 385	96.34 429

UniMVSNet_NR-MVSNet		95.71 245	95.15 257	97.40 244	96.84 378	96.97 127	98.74 181	99.24 20	95.16 207	93.88 349	97.72 307	91.68 157	98.31 386	95.81 228	87.25 438	96.92 350

DU-MVS		95.42 263	94.76 277	97.40 244	96.53 395	96.97 127	98.66 209	98.99 56	95.43 188	93.88 349	97.69 310	88.57 273	98.31 386	95.81 228	87.25 438	96.92 350

usedtu_dtu_shiyan1		94.96 299	94.28 305	96.98 272	95.93 426	96.11 175	97.08 426	98.39 242	93.62 312	93.86 351	96.40 417	88.28 281	98.21 395	92.61 349	92.36 368	96.63 389

FE-MVSNET3		94.96 299	94.28 305	96.98 272	95.93 426	96.11 175	97.08 426	98.39 242	93.62 312	93.86 351	96.40 417	88.28 281	98.21 395	92.61 349	92.36 368	96.63 389

Baseline_NR-MVSNet		94.35 341	93.81 343	95.96 362	96.20 410	94.05 310	98.61 220	96.67 452	91.44 397	93.85 353	97.60 321	88.57 273	98.14 402	94.39 287	86.93 441	95.68 450

PS-MVSNAJss		96.43 207	96.26 202	96.92 280	95.84 432	95.08 256	99.16 56	98.50 200	95.87 156	93.84 354	98.34 249	94.51 92	98.61 345	96.88 184	93.45 350	97.06 340

UniMVSNet_ETH3D		94.24 350	93.33 368	96.97 274	97.19 357	93.38 338	98.74 181	98.57 179	91.21 410	93.81 355	98.58 221	72.85 475	98.77 333	95.05 259	93.93 339	98.77 259

tt0805		94.54 326	93.85 341	96.63 305	97.98 290	93.06 358	98.77 176	97.84 347	93.67 308	93.80 356	98.04 275	76.88 451	98.96 304	94.79 267	92.86 361	97.86 317

tpmvs		94.60 320	94.36 303	95.33 392	97.46 334	88.60 456	96.88 446	97.68 360	91.29 405	93.80 356	96.42 416	88.58 272	99.24 242	91.06 394	96.04 311	98.17 306

WBMVS		94.56 324	94.04 322	96.10 351	98.03 279	93.08 357	97.82 360	98.18 302	94.02 277	93.77 358	96.82 397	81.28 402	98.34 381	95.47 245	91.00 388	96.88 359

3Dnovator	94.51 5	97.46 134	96.93 161	99.07 65	97.78 304	97.64 83	99.35 16	99.06 47	97.02 89	93.75 359	99.16 110	89.25 250	99.92 43	97.22 166	99.75 54	99.64 86

eth_miper_zixun_eth		94.68 314	94.41 301	95.47 386	97.64 317	91.71 390	96.73 454	98.07 328	92.71 354	93.64 360	97.21 354	90.54 209	98.17 399	93.38 321	89.76 402	96.54 409

SD_0403		94.28 348	94.46 295	93.73 439	98.02 280	85.32 481	98.31 279	98.40 236	94.75 242	93.59 361	98.16 266	89.01 258	96.54 474	82.32 478	97.58 255	99.34 150

ITE_SJBPF				95.44 388	97.42 339	91.32 396		97.50 384	95.09 217	93.59 361	98.35 245	81.70 398	98.88 319	89.71 416	93.39 352	96.12 439

TranMVSNet+NR-MVSNet		95.14 283	94.48 293	97.11 262	96.45 402	96.36 162	99.03 83	99.03 50	95.04 219	93.58 363	97.93 286	88.27 283	98.03 420	94.13 299	86.90 443	96.95 347

COLMAP_ROB	93.27 12	95.33 272	94.87 274	96.71 294	99.29 89	93.24 350	98.58 225	98.11 318	89.92 431	93.57 364	99.10 127	86.37 326	99.79 122	90.78 399	98.10 232	97.09 339
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tpm cat1		93.36 377	92.80 379	95.07 401	97.58 322	87.97 466	96.76 452	97.86 346	82.17 487	93.53 365	96.04 433	86.13 331	99.13 269	89.24 426	95.87 315	98.10 309

AllTest		95.24 277	94.65 284	96.99 269	99.25 97	93.21 351	98.59 221	98.18 302	91.36 399	93.52 366	98.77 197	84.67 362	99.72 138	89.70 417	97.87 241	98.02 312

TestCases				96.99 269	99.25 97	93.21 351		98.18 302	91.36 399	93.52 366	98.77 197	84.67 362	99.72 138	89.70 417	97.87 241	98.02 312

miper_ehance_all_eth		95.01 291	94.69 282	95.97 361	97.70 312	93.31 343	97.02 430	98.07 328	92.23 374	93.51 368	96.96 384	91.85 151	98.15 401	93.68 313	91.16 385	96.44 426

SSC-MVS3.2		93.59 375	93.13 373	94.97 404	96.81 381	89.71 432	97.95 337	98.49 205	94.59 251	93.50 369	96.91 390	77.74 438	98.37 379	91.69 380	90.47 393	96.83 367

FMVSNet2		94.47 335	93.61 357	97.04 267	98.21 247	96.43 157	98.79 172	98.27 281	92.46 362	93.50 369	97.09 363	81.16 403	98.00 424	91.09 391	91.93 373	96.70 381

v148		94.29 346	93.76 349	95.91 364	96.10 417	92.93 361	98.58 225	97.97 338	92.59 360	93.47 371	96.95 386	88.53 277	98.32 384	92.56 356	87.06 440	96.49 421

c3_l		94.79 308	94.43 300	95.89 366	97.75 306	93.12 355	97.16 422	98.03 335	92.23 374	93.46 372	97.05 373	91.39 171	98.01 422	93.58 318	89.21 414	96.53 411

Syy-MVS		92.55 396	92.61 384	92.38 458	97.39 343	83.41 487	97.91 344	97.46 388	93.16 335	93.42 373	95.37 453	84.75 359	96.12 481	77.00 498	96.99 272	97.60 326

myMVS_eth3d		92.73 393	92.01 395	94.89 408	97.39 343	90.94 402	97.91 344	97.46 388	93.16 335	93.42 373	95.37 453	68.09 482	96.12 481	88.34 437	96.99 272	97.60 326

pmmvs4		94.69 312	93.99 330	96.81 286	95.74 434	95.94 188	97.40 392	97.67 363	90.42 423	93.37 375	97.59 322	89.08 256	98.20 397	92.97 335	91.67 378	96.30 432

PCF-MVS	93.45 11	94.68 314	93.43 366	98.42 130	98.62 180	96.77 137	95.48 478	98.20 296	84.63 480	93.34 376	98.32 251	88.55 276	99.81 103	84.80 469	98.96 159	98.68 271
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
cl22		94.68 314	94.19 312	96.13 349	98.11 266	93.60 325	96.94 434	98.31 271	92.43 366	93.32 377	96.87 394	86.51 320	98.28 392	94.10 302	91.16 385	96.51 418

XXY-MVS		95.20 280	94.45 298	97.46 237	96.75 385	96.56 151	98.86 142	98.65 158	93.30 329	93.27 378	98.27 257	84.85 356	98.87 320	94.82 265	91.26 384	96.96 345

jajsoiax		95.45 260	95.03 265	96.73 291	95.42 449	94.63 280	99.14 60	98.52 192	95.74 162	93.22 379	98.36 244	83.87 381	98.65 342	96.95 176	94.04 334	96.91 355

reproduce_monomvs		94.77 310	94.67 283	95.08 400	98.40 205	89.48 439	98.80 164	98.64 159	97.57 48	93.21 380	97.65 315	80.57 413	98.83 326	97.72 116	89.47 410	96.93 349

mvs_tets		95.41 265	95.00 266	96.65 300	95.58 440	94.42 291	99.00 91	98.55 185	95.73 164	93.21 380	98.38 242	83.45 387	98.63 343	97.09 169	94.00 336	96.91 355

anonymousdsp		95.42 263	94.91 271	96.94 276	95.10 453	95.90 194	99.14 60	98.41 233	93.75 295	93.16 382	97.46 331	87.50 305	98.41 372	95.63 239	94.03 335	96.50 420

v8		94.47 335	93.77 347	96.57 314	96.36 405	94.83 272	99.05 76	98.19 299	91.92 383	93.16 382	96.97 382	88.82 270	98.48 356	91.69 380	87.79 429	96.39 427

WR-MVS		95.15 282	94.46 295	97.22 250	96.67 390	96.45 155	98.21 293	98.81 108	94.15 271	93.16 382	97.69 310	87.51 303	98.30 388	95.29 251	88.62 422	96.90 357

EPNet_dtu		95.21 279	94.95 270	95.99 357	96.17 413	90.45 417	98.16 308	97.27 408	96.77 102	93.14 385	98.33 250	90.34 217	98.42 365	85.57 460	98.81 171	99.09 216
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
QAPM		96.29 216	95.40 240	98.96 76	97.85 300	97.60 86	99.23 38	98.93 65	89.76 434	93.11 386	99.02 148	89.11 255	99.93 34	91.99 371	99.62 90	99.34 150

GG-mvs-BLEND				96.59 311	96.34 406	94.98 263	96.51 460	88.58 516		93.10 387	94.34 469	80.34 416	98.05 418	89.53 420	96.99 272	96.74 374

v10		94.29 346	93.55 360	96.51 322	96.39 404	94.80 274	98.99 94	98.19 299	91.35 401	93.02 388	96.99 380	88.09 288	98.41 372	90.50 403	88.41 424	96.33 431

3Dnovator+	94.38 6	97.43 139	96.78 173	99.38 24	97.83 301	98.52 35	99.37 13	98.71 138	97.09 87	92.99 389	99.13 118	89.36 247	99.89 69	96.97 174	99.57 99	99.71 63

D2MVS		95.18 281	95.08 263	95.48 385	97.10 363	92.07 382	98.30 282	99.13 43	94.02 277	92.90 390	96.73 401	89.48 239	98.73 335	94.48 285	93.60 347	95.65 451

Patchmtry		93.22 383	92.35 391	95.84 371	96.77 382	93.09 356	94.66 492	97.56 374	87.37 458	92.90 390	96.24 422	88.15 286	97.90 431	87.37 448	90.10 399	96.53 411

DIV-MVS_self_test		94.52 329	94.03 324	95.99 357	97.57 326	93.38 338	97.05 428	97.94 341	91.74 387	92.81 392	97.10 359	89.12 254	98.07 414	92.60 352	90.30 395	96.53 411

Anonymous20231211		94.10 362	93.26 371	96.61 308	99.11 124	94.28 299	99.01 89	98.88 78	86.43 468	92.81 392	97.57 324	81.66 399	98.68 340	94.83 264	89.02 418	96.88 359

cl____		94.51 330	94.01 327	96.02 353	97.58 322	93.40 337	97.05 428	97.96 340	91.73 389	92.76 394	97.08 365	89.06 257	98.13 403	92.61 349	90.29 396	96.52 414

miper_lstm_enhance		94.33 342	94.07 321	95.11 398	97.75 306	90.97 401	97.22 410	98.03 335	91.67 391	92.76 394	96.97 382	90.03 226	97.78 441	92.51 359	89.64 404	96.56 406

v7n		94.19 353	93.43 366	96.47 327	95.90 429	94.38 294	99.26 33	98.34 260	91.99 381	92.76 394	97.13 358	88.31 280	98.52 354	89.48 422	87.70 430	96.52 414

MVS		94.67 317	93.54 361	98.08 172	96.88 376	96.56 151	98.19 300	98.50 200	78.05 498	92.69 397	98.02 276	91.07 191	99.63 161	90.09 407	98.36 214	98.04 311

DSMNet-mixed		92.52 398	92.58 386	92.33 459	94.15 465	82.65 491	98.30 282	94.26 492	89.08 446	92.65 398	95.73 443	85.01 353	95.76 485	86.24 455	97.76 247	98.59 283

EU-MVSNet		93.66 371	94.14 317	92.25 462	95.96 425	83.38 488	98.52 241	98.12 315	94.69 245	92.61 399	98.13 269	87.36 309	96.39 479	91.82 376	90.00 400	96.98 344

IterMVS-SCA-FT		94.11 361	93.87 339	94.85 411	97.98 290	90.56 416	97.18 417	98.11 318	93.75 295	92.58 400	97.48 330	83.97 378	97.41 456	92.48 361	91.30 382	96.58 402

pmmvs5		93.65 373	92.97 377	95.68 377	95.49 444	92.37 371	98.20 297	97.28 407	89.66 436	92.58 400	97.26 348	82.14 393	98.09 410	93.18 328	90.95 389	96.58 402

blended_shiyan8		91.42 405	89.89 418	96.01 354	91.50 492	93.30 344	97.48 386	97.83 348	86.93 461	92.57 402	92.37 490	82.46 391	98.13 403	92.86 343	74.99 496	96.61 393

WR-MVS_H		95.05 290	94.46 295	96.81 286	96.86 377	95.82 207	99.24 36	99.24 20	93.87 289	92.53 403	96.84 396	90.37 216	98.24 394	93.24 325	87.93 428	96.38 428

ACMP	93.49 10	95.34 271	94.98 268	96.43 332	97.67 314	93.48 331	98.73 187	98.44 216	94.94 232	92.53 403	98.53 226	84.50 367	99.14 267	95.48 244	94.00 336	96.66 387
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test0.0.03 1		94.08 364	93.51 362	95.80 372	95.53 443	92.89 362	97.38 394	95.97 466	95.11 214	92.51 405	96.66 405	87.71 298	96.94 464	87.03 450	93.67 343	97.57 328

IB-MVS	91.98 17	93.27 381	91.97 396	97.19 253	97.47 333	93.41 334	97.09 425	95.99 465	93.32 327	92.47 406	95.73 443	78.06 434	99.53 184	94.59 282	82.98 463	98.62 278
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		94.09 363	93.85 341	94.80 415	97.99 284	90.35 421	97.18 417	98.12 315	93.68 306	92.46 407	97.34 342	84.05 376	97.41 456	92.51 359	91.33 381	96.62 392
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
blended_shiyan6		91.37 406	89.84 419	95.98 360	91.49 493	93.28 345	97.48 386	97.83 348	86.93 461	92.43 408	92.36 491	82.44 392	98.06 415	92.74 348	74.82 499	96.59 398

CP-MVSNet		94.94 303	94.30 304	96.83 284	96.72 387	95.56 221	99.11 66	98.95 61	93.89 287	92.42 409	97.90 289	87.19 310	98.12 405	94.32 291	88.21 425	96.82 368

wanda-best-256-512		91.17 413	89.60 423	95.88 367	91.33 496	92.99 359	96.89 443	97.82 351	86.89 464	92.36 410	91.75 497	81.83 395	98.06 415	92.75 345	74.82 499	96.59 398

FE-blended-shiyan7		91.17 413	89.60 423	95.88 367	91.33 496	92.99 359	96.89 443	97.82 351	86.89 464	92.36 410	91.75 497	81.83 395	98.06 415	92.75 345	74.82 499	96.59 398

usedtu_blend_shiyan5		90.87 423	89.15 430	96.01 354	91.33 496	93.35 341	98.12 315	97.36 400	81.93 489	92.36 410	91.75 497	81.83 395	98.09 410	92.88 341	74.82 499	96.59 398

PS-CasMVS		94.67 317	93.99 330	96.71 294	96.68 389	95.26 244	99.13 63	99.03 50	93.68 306	92.33 413	97.95 284	85.35 346	98.10 406	93.59 317	88.16 427	96.79 369

FMVSNet1		93.19 385	92.07 394	96.56 315	97.54 327	95.00 259	98.82 155	98.18 302	90.38 424	92.27 414	97.07 366	73.68 472	97.95 427	89.36 424	91.30 382	96.72 377

blend_shiyan4		90.76 424	89.01 433	95.99 357	91.69 491	93.35 341	97.44 388	97.83 348	86.93 461	92.23 415	91.98 494	75.19 461	98.09 410	92.88 341	74.96 497	96.52 414

PEN-MVS		94.42 338	93.73 351	96.49 324	96.28 408	94.84 270	99.17 55	99.00 53	93.51 317	92.23 415	97.83 299	86.10 332	97.90 431	92.55 357	86.92 442	96.74 374

sc_t1		91.01 418	89.39 425	95.85 370	95.99 422	90.39 420	98.43 264	97.64 366	78.79 495	92.20 417	97.94 285	66.00 489	98.60 348	91.59 383	85.94 451	98.57 286

gbinet_0.2-2-1-0.02		91.03 417	89.37 429	96.01 354	91.39 494	93.41 334	97.19 415	97.82 351	87.00 460	92.18 418	91.87 496	78.97 425	98.04 419	93.13 329	74.75 503	96.60 395

OurMVSNet-221017-0		94.21 351	94.00 328	94.85 411	95.60 439	89.22 444	98.89 124	97.43 394	95.29 200	92.18 418	98.52 229	82.86 388	98.59 349	93.46 320	91.76 376	96.74 374

MS-PatchMatch		93.84 370	93.63 356	94.46 429	96.18 412	89.45 440	97.76 365	98.27 281	92.23 374	92.13 420	97.49 329	79.50 421	98.69 337	89.75 415	99.38 134	95.25 458

ppachtmachnet_test		93.22 383	92.63 383	94.97 404	95.45 447	90.84 406	96.88 446	97.88 345	90.60 418	92.08 421	97.26 348	88.08 289	97.86 437	85.12 465	90.33 394	96.22 435

1314		96.25 220	95.73 225	97.79 206	97.13 361	95.55 223	98.19 300	98.59 172	93.47 320	92.03 422	97.82 300	91.33 174	99.49 192	94.62 278	98.44 198	98.32 300

baseline2		95.11 285	94.52 291	96.87 282	96.65 391	93.56 326	98.27 287	94.10 496	93.45 321	92.02 423	97.43 335	87.45 308	99.19 253	93.88 308	97.41 264	97.87 316

DTE-MVSNet		93.98 368	93.26 371	96.14 348	96.06 419	94.39 293	99.20 48	98.86 91	93.06 340	91.78 424	97.81 301	85.87 337	97.58 451	90.53 402	86.17 447	96.46 425

LF4IMVS		93.14 387	92.79 380	94.20 434	95.88 430	88.67 455	97.66 373	97.07 424	93.81 293	91.71 425	97.65 315	77.96 436	98.81 329	91.47 385	91.92 375	95.12 461

mvs5depth		91.23 411	90.17 414	94.41 431	92.09 487	89.79 429	95.26 481	96.50 457	90.73 416	91.69 426	97.06 370	76.12 455	98.62 344	88.02 442	84.11 459	94.82 468

our_test_3		93.65 373	93.30 369	94.69 417	95.45 447	89.68 435	96.91 438	97.65 364	91.97 382	91.66 427	96.88 392	89.67 235	97.93 430	88.02 442	91.49 380	96.48 423

testgi		93.06 389	92.45 390	94.88 409	96.43 403	89.90 427	98.75 177	97.54 380	95.60 170	91.63 428	97.91 288	74.46 468	97.02 462	86.10 456	93.67 343	97.72 322

ArgMatch-SfM		90.55 427	89.69 420	93.14 451	95.91 428	86.12 478	97.20 412	96.81 447	92.91 347	91.39 429	96.95 386	65.65 491	97.72 444	88.03 441	82.36 464	95.57 452

tfpnnormal		93.66 371	92.70 382	96.55 319	96.94 371	95.94 188	98.97 98	99.19 35	91.04 412	91.38 430	97.34 342	84.94 354	98.61 345	85.45 462	89.02 418	95.11 462

LTVRE_ROB	92.95 15	94.60 320	93.90 336	96.68 298	97.41 342	94.42 291	98.52 241	98.59 172	91.69 390	91.21 431	98.35 245	84.87 355	99.04 288	91.06 394	93.44 351	96.60 395
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	95.83 239	95.00 266	98.32 136	97.18 358	97.32 100	99.21 45	98.97 57	89.96 430	91.14 432	99.05 145	86.64 319	99.92 43	93.38 321	99.47 122	97.73 321

pm-mvs1		93.94 369	93.06 374	96.59 311	96.49 399	95.16 250	98.95 105	98.03 335	92.32 371	91.08 433	97.84 296	84.54 366	98.41 372	92.16 364	86.13 450	96.19 437

ArgMatch-Sym		90.92 420	90.22 413	93.02 452	95.81 433	86.50 475	97.32 402	97.01 434	92.67 355	91.02 434	97.35 341	66.90 487	97.17 460	88.53 435	85.40 453	95.39 455

MVS-HIRNet		89.46 443	88.40 440	92.64 456	97.58 322	82.15 492	94.16 501	93.05 503	75.73 505	90.90 435	82.52 515	79.42 422	98.33 383	83.53 474	98.68 174	97.43 329

FMVSNet5		91.81 401	90.92 405	94.49 426	97.21 353	92.09 381	98.00 333	97.55 379	89.31 443	90.86 436	95.61 450	74.48 467	95.32 489	85.57 460	89.70 403	96.07 441

USDC		93.33 380	92.71 381	95.21 394	96.83 379	90.83 407	96.91 438	97.50 384	93.84 290	90.72 437	98.14 268	77.69 439	98.82 328	89.51 421	93.21 358	95.97 443

MVP-Stereo		94.28 348	93.92 333	95.35 391	94.95 455	92.60 369	97.97 336	97.65 364	91.61 392	90.68 438	97.09 363	86.32 329	98.42 365	89.70 417	99.34 138	95.02 466
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	92.99 14	94.30 344	93.77 347	95.88 367	97.81 303	92.04 384	98.71 192	98.37 251	93.99 282	90.60 439	98.47 233	80.86 410	99.05 285	92.75 345	92.40 367	96.55 408

CL-MVSNet_self_test		90.11 434	89.14 431	93.02 452	91.86 489	88.23 464	96.51 460	98.07 328	90.49 419	90.49 440	94.41 464	84.75 359	95.34 488	80.79 483	74.95 498	95.50 453

0.4-1-1-0.1		90.89 421	88.97 435	96.67 299	94.15 465	92.76 367	95.28 480	95.03 482	89.11 445	90.43 441	89.57 506	75.41 458	99.04 288	94.70 272	77.06 489	98.20 305

KD-MVS_self_test		90.38 429	89.38 427	93.40 445	92.85 482	88.94 451	97.95 337	97.94 341	90.35 425	90.25 442	93.96 472	79.82 417	95.94 484	84.62 471	76.69 493	95.33 456

ttmdpeth		92.61 395	91.96 398	94.55 423	94.10 467	90.60 415	98.52 241	97.29 405	92.67 355	90.18 443	97.92 287	79.75 419	97.79 439	91.09 391	86.15 449	95.26 457

Anonymous20231206		91.66 403	91.10 404	93.33 446	94.02 471	87.35 470	98.58 225	97.26 409	90.48 420	90.16 444	96.31 420	83.83 382	96.53 475	79.36 489	89.90 401	96.12 439

SixPastTwentyTwo		93.34 379	92.86 378	94.75 416	95.67 436	89.41 442	98.75 177	96.67 452	93.89 287	90.15 445	98.25 260	80.87 409	98.27 393	90.90 398	90.64 391	96.57 404

0.4-1-1-0.2		90.43 428	88.45 439	96.38 337	93.34 477	92.12 377	93.88 502	95.04 481	88.62 451	90.00 446	88.31 509	75.31 460	99.03 291	94.61 279	76.91 491	98.01 314

PVSNet_0	88.72 19	91.28 410	90.03 416	95.00 403	97.99 284	87.29 471	94.84 488	98.50 200	92.06 380	89.86 447	95.19 455	79.81 418	99.39 211	92.27 363	69.79 514	98.33 299

ACMH	92.88 16	94.55 325	93.95 332	96.34 340	97.63 318	93.26 347	98.81 163	98.49 205	93.43 322	89.74 448	98.53 226	81.91 394	99.08 281	93.69 312	93.30 356	96.70 381
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		90.26 433	88.73 438	94.86 410	96.12 416	90.62 413	98.17 307	97.63 367	77.46 499	89.68 449	96.04 433	69.19 480	97.79 439	88.98 429	85.29 454	96.16 438

pmmvs6		91.77 402	90.63 408	95.17 396	94.69 461	91.24 398	98.67 207	97.92 343	86.14 470	89.62 450	97.56 327	75.79 457	98.34 381	90.75 400	84.56 456	95.94 444

TinyColmap		92.31 399	91.53 400	94.65 420	96.92 372	89.75 430	96.92 436	96.68 451	90.45 422	89.62 450	97.85 295	76.06 456	98.81 329	86.74 451	92.51 366	95.41 454

Anonymous20240521		91.18 412	90.44 410	93.42 443	93.70 472	88.47 459	98.94 108	97.56 374	88.46 452	89.56 452	95.08 458	77.15 447	96.97 463	83.92 472	89.55 407	94.82 468

TransMVSNet (Re)		92.67 394	91.51 401	96.15 347	96.58 393	94.65 278	98.90 120	96.73 448	90.86 415	89.46 453	97.86 293	85.62 341	98.09 410	86.45 454	81.12 473	95.71 449

NR-MVSNet		94.98 296	94.16 315	97.44 239	96.53 395	97.22 115	98.74 181	98.95 61	94.96 228	89.25 454	97.69 310	89.32 248	98.18 398	94.59 282	87.40 435	96.92 350

0.3-1-1-0.015		90.29 431	88.21 443	96.51 322	93.56 474	92.44 370	94.41 497	95.03 482	88.71 449	89.20 455	88.50 508	73.12 474	99.04 288	94.67 275	76.70 492	98.05 310

LCM-MVSNet-Re		95.22 278	95.32 250	94.91 406	98.18 257	87.85 468	98.75 177	95.66 471	95.11 214	88.96 456	96.85 395	90.26 221	97.65 446	95.65 238	98.44 198	99.22 188

KD-MVS_2432*1600		89.61 440	87.96 448	94.54 424	94.06 469	91.59 392	95.59 475	97.63 367	89.87 432	88.95 457	94.38 466	78.28 431	96.82 466	84.83 467	68.05 515	95.21 459

miper_refine_blended		89.61 440	87.96 448	94.54 424	94.06 469	91.59 392	95.59 475	97.63 367	89.87 432	88.95 457	94.38 466	78.28 431	96.82 466	84.83 467	68.05 515	95.21 459

test_fmvs3		87.17 451	87.06 454	87.50 477	91.21 499	75.66 503	99.05 76	96.61 455	92.79 352	88.85 459	92.78 486	43.72 508	93.49 501	93.95 305	84.56 456	93.34 492

TDRefinement		91.06 416	89.68 421	95.21 394	85.35 524	91.49 394	98.51 248	97.07 424	91.47 395	88.83 460	97.84 296	77.31 443	99.09 279	92.79 344	77.98 486	95.04 465

MASt3R-SfM		85.54 456	85.89 456	84.50 486	90.13 510	66.13 521	92.89 504	95.33 476	85.73 475	88.77 461	96.36 419	52.50 502	94.89 495	86.66 452	84.65 455	92.50 498

tt0320-xc		89.79 437	88.11 444	94.84 413	96.19 411	90.61 414	98.16 308	97.22 411	77.35 500	88.75 462	96.70 404	65.94 490	97.63 448	89.31 425	83.39 461	96.28 433

N_pmnet		87.12 453	87.77 450	85.17 483	95.46 446	61.92 527	97.37 396	70.66 538	85.83 473	88.73 463	96.04 433	85.33 348	97.76 442	80.02 484	90.48 392	95.84 446

dtuonlycased		91.29 408	91.26 403	91.36 466	95.63 438	84.25 484	96.93 435	97.21 413	92.16 378	88.34 464	96.47 413	79.56 420	95.18 492	87.37 448	87.70 430	94.64 472

test_0402		91.32 407	90.27 412	94.48 427	96.60 392	91.12 399	98.50 249	97.22 411	86.10 471	88.30 465	96.98 381	77.65 441	97.99 425	78.13 494	92.94 360	94.34 474

test20.03		90.89 421	90.38 411	92.43 457	93.48 475	88.14 465	98.33 274	97.56 374	93.40 324	87.96 466	96.71 403	80.69 412	94.13 499	79.15 490	86.17 447	95.01 467

MIMVSNet1		89.67 439	88.28 442	93.82 438	92.81 483	91.08 400	98.01 331	97.45 392	87.95 455	87.90 467	95.87 439	67.63 485	94.56 497	78.73 493	88.18 426	95.83 447

mvsany_test3		88.80 445	88.04 445	91.09 467	89.78 512	81.57 494	97.83 359	95.49 474	93.81 293	87.53 468	93.95 473	56.14 499	97.43 455	94.68 273	83.13 462	94.26 475

Patchmatch-RL test		91.49 404	90.85 406	93.41 444	91.37 495	84.40 482	92.81 505	95.93 469	91.87 385	87.25 469	94.87 459	88.99 259	96.53 475	92.54 358	82.00 467	99.30 164

pmmvs3		86.67 454	84.86 460	92.11 463	88.16 516	87.19 473	96.63 456	94.75 486	79.88 492	87.22 470	92.75 488	66.56 488	95.20 491	81.24 482	76.56 494	93.96 485

dongtai		82.47 463	81.88 465	84.22 487	95.19 452	76.03 501	94.59 495	74.14 529	82.63 484	87.19 471	96.09 430	64.10 493	87.85 517	58.91 517	84.11 459	88.78 511

test_vis1_rt		91.29 408	90.65 407	93.19 450	97.45 337	86.25 477	98.57 234	90.90 512	93.30 329	86.94 472	93.59 475	62.07 496	99.11 274	97.48 149	95.58 319	94.22 478

K. test v3		92.55 396	91.91 399	94.48 427	95.64 437	89.24 443	99.07 72	94.88 484	94.04 275	86.78 473	97.59 322	77.64 442	97.64 447	92.08 366	89.43 411	96.57 404

lessismore_v0				94.45 430	94.93 456	88.44 460		91.03 511		86.77 474	97.64 318	76.23 454	98.42 365	90.31 405	85.64 452	96.51 418

APD_test1		88.22 448	88.01 446	88.86 474	95.98 423	74.66 510	97.21 411	96.44 459	83.96 482	86.66 475	97.90 289	60.95 497	97.84 438	82.73 475	90.23 397	94.09 481

ambc				89.49 471	86.66 519	75.78 502	92.66 506	96.72 449		86.55 476	92.50 489	46.01 506	97.90 431	90.32 404	82.09 466	94.80 470

PM-MVS		87.77 449	86.55 455	91.40 465	91.03 503	83.36 489	96.92 436	95.18 479	91.28 406	86.48 477	93.42 477	53.27 501	96.74 468	89.43 423	81.97 468	94.11 480

OpenMVS_ROB	86.42 20	89.00 444	87.43 452	93.69 440	93.08 481	89.42 441	97.91 344	96.89 441	78.58 496	85.86 478	94.69 460	69.48 479	98.29 391	77.13 497	93.29 357	93.36 491

UnsupCasMVSNet_eth		90.99 419	89.92 417	94.19 435	94.08 468	89.83 428	97.13 424	98.67 151	93.69 304	85.83 479	96.19 427	75.15 462	96.74 468	89.14 427	79.41 480	96.00 442

new_pmnet		90.06 435	89.00 434	93.22 449	94.18 463	88.32 462	96.42 462	96.89 441	86.19 469	85.67 480	93.62 474	77.18 446	97.10 461	81.61 480	89.29 413	94.23 477

dmvs_testset		87.64 450	88.93 437	83.79 488	95.25 450	63.36 523	97.20 412	91.17 509	93.07 339	85.64 481	95.98 438	85.30 350	91.52 509	69.42 511	87.33 436	96.49 421

test_f		86.07 455	85.39 457	88.10 475	89.28 514	75.57 504	97.73 368	96.33 461	89.41 442	85.35 482	91.56 500	43.31 510	95.53 486	91.32 387	84.23 458	93.21 493

EG-PatchMatch MVS		91.13 415	90.12 415	94.17 436	94.73 460	89.00 448	98.13 314	97.81 355	89.22 444	85.32 483	96.46 414	67.71 484	98.42 365	87.89 446	93.82 341	95.08 463

pmmvs-eth3d		90.36 430	89.05 432	94.32 433	91.10 501	92.12 377	97.63 378	96.95 436	88.86 448	84.91 484	93.13 481	78.32 430	96.74 468	88.70 432	81.81 469	94.09 481

FE-MVSNET2		90.29 431	88.94 436	94.36 432	90.48 507	92.27 372	98.45 256	97.82 351	91.59 393	84.90 485	93.10 482	73.92 470	96.42 478	87.92 445	82.26 465	94.39 473

FE-MVSNET		88.56 446	87.09 453	92.99 454	89.93 511	89.99 426	98.15 311	95.59 472	88.42 453	84.87 486	92.90 484	74.82 464	94.99 494	77.88 495	81.21 472	93.99 484

DeepMVS_CX				86.78 478	97.09 364	72.30 511		95.17 480	75.92 504	84.34 487	95.19 455	70.58 477	95.35 487	79.98 487	89.04 417	92.68 495

usedtu_dtu_shiyan2		84.80 458	82.31 463	92.27 461	86.38 521	85.55 480	97.77 364	96.56 456	78.34 497	83.90 488	93.50 476	54.16 500	95.32 489	77.55 496	72.62 507	95.92 445

new-patchmatchnet		88.50 447	87.45 451	91.67 464	90.31 509	85.89 479	97.16 422	97.33 401	89.47 439	83.63 489	92.77 487	76.38 452	95.06 493	82.70 476	77.29 487	94.06 483

UnsupCasMVSNet_bld		87.17 451	85.12 459	93.31 447	91.94 488	88.77 452	94.92 487	98.30 278	84.30 481	82.30 490	90.04 504	63.96 494	97.25 458	85.85 459	74.47 506	93.93 486

WB-MVS		84.86 457	85.33 458	83.46 489	89.48 513	69.56 515	98.19 300	96.42 460	89.55 438	81.79 491	94.67 461	84.80 357	90.12 512	52.44 519	80.64 477	90.69 504

CMPMVS	66.06 21	89.70 438	89.67 422	89.78 470	93.19 480	76.56 500	97.00 431	98.35 256	80.97 490	81.57 492	97.75 304	74.75 465	98.61 345	89.85 413	93.63 345	94.17 479
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SSC-MVS		84.27 460	84.71 461	82.96 494	89.19 515	68.83 516	98.08 323	96.30 462	89.04 447	81.37 493	94.47 462	84.60 364	89.89 513	49.80 522	79.52 479	90.15 505

MVStest1		89.53 442	87.99 447	94.14 437	94.39 462	90.42 418	98.25 290	96.84 446	82.81 483	81.18 494	97.33 344	77.09 448	96.94 464	85.27 464	78.79 481	95.06 464

test_method		79.03 469	78.17 468	81.63 495	86.06 522	54.40 538	82.75 525	96.89 441	39.54 530	80.98 495	95.57 451	58.37 498	94.73 496	84.74 470	78.61 482	95.75 448

kuosan		78.45 473	77.69 472	80.72 496	92.73 484	75.32 505	94.63 494	74.51 528	75.96 502	80.87 496	93.19 480	63.23 495	79.99 527	42.56 529	81.56 471	86.85 518

RoMa-SfM		83.81 461	82.08 464	89.00 473	93.33 478	79.94 497	95.51 477	92.48 505	79.75 493	79.89 497	95.69 448	46.23 505	93.20 504	78.90 491	76.93 490	93.87 487

DenseAffine		84.37 459	82.38 462	90.31 469	94.17 464	82.89 490	94.98 484	94.23 493	82.16 488	79.68 498	94.33 470	46.28 504	94.25 498	80.01 485	75.62 495	93.78 489

ET-MVSNet_ETH3D		94.13 358	92.98 376	97.58 231	98.22 245	96.20 169	97.31 404	95.37 475	94.53 254	79.56 499	97.63 320	86.51 320	97.53 453	96.91 178	90.74 390	99.02 229

RoMa-HiRes		79.77 466	77.89 469	85.41 482	90.81 504	74.77 509	94.26 499	86.78 518	75.97 501	77.00 500	94.37 468	39.39 515	90.60 510	74.98 503	67.46 517	90.84 503

LCM-MVSNet		78.70 472	76.24 478	86.08 479	77.26 540	71.99 512	94.34 498	96.72 449	61.62 516	76.53 501	89.33 507	33.91 529	92.78 506	81.85 479	74.60 504	93.46 490

DKM		81.60 464	79.57 467	87.68 476	92.65 485	78.36 498	94.65 493	91.17 509	79.69 494	76.11 502	93.98 471	37.88 520	91.54 508	79.64 488	70.38 511	93.15 494

PMMVS2		77.95 475	75.44 479	85.46 481	82.54 528	74.95 507	94.23 500	93.08 502	72.80 507	74.68 503	87.38 510	36.36 523	91.56 507	73.95 505	63.94 519	89.87 506

testf1		79.02 470	77.70 470	82.99 492	88.10 517	66.90 519	94.67 490	93.11 500	71.08 511	74.02 504	93.41 478	34.15 526	93.25 502	72.25 507	78.50 483	88.82 509

APD_test2		79.02 470	77.70 470	82.99 492	88.10 517	66.90 519	94.67 490	93.11 500	71.08 511	74.02 504	93.41 478	34.15 526	93.25 502	72.25 507	78.50 483	88.82 509

Gipuma		78.40 474	76.75 477	83.38 490	95.54 441	80.43 495	79.42 526	97.40 396	64.67 515	73.46 506	80.82 519	45.65 507	93.14 505	66.32 514	87.43 434	76.56 524
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DKM-HiRes		79.25 467	77.01 476	85.98 480	91.20 500	75.07 506	93.65 503	87.84 517	75.94 503	73.36 507	92.80 485	34.20 525	90.26 511	76.66 499	67.44 518	92.62 496

YYNet1		90.70 426	89.39 425	94.62 422	94.79 459	90.65 411	97.20 412	97.46 388	87.54 457	72.54 508	95.74 441	86.51 320	96.66 472	86.00 457	86.76 445	96.54 409

MDA-MVSNet_test_wron		90.71 425	89.38 427	94.68 418	94.83 457	90.78 408	97.19 415	97.46 388	87.60 456	72.41 509	95.72 445	86.51 320	96.71 471	85.92 458	86.80 444	96.56 406

MDA-MVSNet-bldmvs		89.97 436	88.35 441	94.83 414	95.21 451	91.34 395	97.64 375	97.51 383	88.36 454	71.17 510	96.13 429	79.22 423	96.63 473	83.65 473	86.27 446	96.52 414

LoFTR		83.16 462	80.62 466	90.80 468	92.28 486	80.01 496	95.35 479	94.33 490	80.44 491	70.79 511	92.93 483	46.38 503	98.17 399	75.01 502	78.03 485	94.24 476

FPMVS		77.62 476	77.14 475	79.05 500	79.25 535	60.97 529	95.79 470	95.94 468	65.96 514	67.93 512	94.40 465	37.73 521	88.88 516	68.83 512	88.46 423	87.29 515

test_vis3_rt		79.22 468	77.40 473	84.67 484	86.44 520	74.85 508	97.66 373	81.43 522	84.98 478	67.12 513	81.91 518	28.09 533	97.60 449	88.96 430	80.04 478	81.55 521

MatchFormer		80.21 465	77.20 474	89.24 472	91.79 490	77.21 499	95.16 482	93.59 498	72.46 509	67.08 514	89.93 505	43.14 511	97.90 431	67.07 513	74.55 505	92.61 497

SP-DiffGlue		70.13 481	69.16 484	73.04 509	77.73 538	57.48 533	88.44 519	74.91 527	50.96 522	66.64 515	85.99 512	41.44 512	73.46 533	64.21 515	72.15 508	88.19 514

PDCNetPlus		71.79 480	69.26 483	79.39 499	85.67 523	69.92 514	90.34 514	62.32 540	72.62 508	65.36 516	90.26 501	39.20 517	86.38 519	75.32 501	42.24 533	81.88 520

PMatch-SfM		73.49 479	70.32 481	83.00 491	85.01 525	68.63 517	90.17 516	79.05 525	71.64 510	63.27 517	91.93 495	17.27 542	89.10 515	74.59 504	59.95 523	91.26 499

ELoFTR		75.37 477	72.33 480	84.51 485	84.48 526	68.41 518	91.57 509	88.78 515	73.84 506	62.84 518	90.14 502	27.38 534	94.11 500	71.45 510	60.46 522	91.00 501

tmp_tt		68.90 484	66.97 485	74.68 502	50.78 555	59.95 530	87.13 522	83.47 521	38.80 531	62.21 519	96.23 424	64.70 492	76.91 529	88.91 431	30.49 541	87.19 516

SP-SuperGlue		68.14 486	66.58 486	72.81 510	90.65 506	55.53 535	91.37 510	73.04 530	49.07 525	61.03 520	80.24 522	38.13 519	74.06 532	45.46 525	70.26 512	88.84 508

SP-LightGlue		68.17 485	66.54 487	73.06 508	91.08 502	55.79 534	91.09 511	72.78 531	48.55 526	60.77 521	79.95 523	38.55 518	74.10 531	45.47 524	70.64 510	89.28 507

E-PMN		64.94 493	64.25 494	67.02 513	82.28 529	59.36 531	91.83 508	85.63 519	52.69 519	60.22 522	77.28 527	41.06 513	80.12 526	46.15 523	41.14 534	61.57 530

PMatch-Up-SfM		70.03 482	66.48 488	80.70 497	82.00 530	63.20 524	88.10 520	71.07 534	67.59 513	60.07 523	90.10 503	14.49 547	87.80 518	71.95 509	52.95 527	91.09 500

ALIKED-NN		66.93 489	64.81 492	73.32 506	93.41 476	62.03 526	87.55 521	71.25 533	50.21 523	59.98 524	82.57 514	39.72 514	84.03 523	34.94 533	63.64 520	73.90 526

ALIKED-LG		67.40 487	65.16 491	74.11 504	93.21 479	62.30 525	88.98 517	71.99 532	55.04 517	59.47 525	82.33 516	39.27 516	85.49 521	32.61 535	63.58 521	74.55 525

SP-NN		67.39 488	65.69 489	72.49 512	90.68 505	55.34 536	90.33 515	71.01 536	46.77 528	59.09 526	79.83 524	37.26 522	73.38 534	44.68 526	71.51 509	88.74 512

EMVS		64.07 494	63.26 496	66.53 514	81.73 531	58.81 532	91.85 507	84.75 520	51.93 521	59.09 526	75.13 530	43.32 509	79.09 528	42.03 530	39.47 535	61.69 529

ALIKED-MNN		65.35 492	62.68 497	73.35 505	93.70 472	61.07 528	88.63 518	70.76 537	47.76 527	57.06 528	80.59 520	34.03 528	85.39 522	32.73 534	58.87 524	73.59 527

SP-MNN		66.66 490	64.70 493	72.53 511	90.32 508	55.08 537	91.01 512	71.05 535	44.81 529	56.48 529	79.62 525	35.87 524	74.11 530	43.13 528	69.98 513	88.39 513

XFeat-NN		56.16 497	56.10 500	56.36 516	72.10 547	42.54 550	76.45 529	61.18 541	38.16 532	53.08 530	76.48 528	32.95 530	65.67 536	44.15 527	50.31 530	60.87 531

MVE	62.14 22	63.28 495	59.38 498	74.99 501	74.33 545	65.47 522	85.55 523	80.50 523	52.02 520	51.10 531	75.00 531	10.91 554	80.50 525	51.60 521	53.40 526	78.99 522
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
XFeat-MNN		55.84 498	55.19 501	57.82 515	69.33 551	43.25 545	78.25 528	62.64 539	37.53 533	50.90 532	76.32 529	32.43 531	68.13 535	42.00 531	47.26 532	62.07 528

ANet_high		69.08 483	65.37 490	80.22 498	65.99 553	71.96 513	90.91 513	90.09 513	82.62 485	49.93 533	78.39 526	29.36 532	81.75 524	62.49 516	38.52 537	86.95 517

GLUNet-SfM		61.12 496	56.63 499	74.58 503	69.78 550	53.99 539	78.71 527	76.81 526	49.09 524	49.42 534	80.47 521	24.43 535	85.82 520	51.80 520	29.17 542	83.92 519

PMVS	61.03 23	65.95 491	63.57 495	73.09 507	57.90 554	51.22 540	85.05 524	93.93 497	54.45 518	44.32 535	83.57 513	13.22 549	89.15 514	58.68 518	81.00 474	78.91 523
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-NN		49.27 499	49.25 502	49.32 517	83.88 527	45.20 541	74.57 530	53.44 542	32.44 534	42.88 536	64.93 532	20.60 536	61.35 537	16.59 537	53.96 525	41.40 532

SIFT-MNN		47.78 500	47.47 503	48.69 518	81.04 532	44.17 542	73.46 531	53.36 543	31.82 535	38.54 537	63.76 533	18.11 540	61.27 538	15.96 539	51.17 528	40.64 535

SIFT-NN-NCMNet		47.55 501	47.18 504	48.67 519	79.60 534	44.09 543	73.43 532	52.90 544	31.82 535	38.38 538	63.56 536	18.47 537	61.19 539	15.91 540	50.50 529	40.74 534

SIFT-NN-CMatch		45.31 502	44.49 505	47.75 520	76.46 541	42.98 548	70.17 536	49.20 547	31.63 538	37.94 539	63.68 535	18.19 539	59.32 542	15.91 540	37.27 538	40.95 533

SIFT-NN-PointCN		43.09 506	42.61 508	44.51 526	72.48 546	37.95 554	70.10 537	46.55 549	30.16 544	34.48 540	61.93 540	18.02 541	55.90 547	15.40 543	34.41 539	39.69 537

SIFT-ConvMatch		43.26 505	42.18 509	46.50 523	78.34 537	43.05 546	68.67 538	47.17 548	31.06 539	30.28 541	62.56 538	15.43 544	58.95 544	14.92 544	31.22 540	37.51 540

SIFT-NN-UMatch		44.69 504	43.84 507	47.24 522	74.56 544	42.59 549	71.89 534	49.78 545	31.80 537	29.27 542	63.70 534	18.26 538	59.43 541	15.86 542	39.43 536	39.71 536

SIFT-CM-Cal		41.25 508	40.03 511	44.88 525	77.37 539	41.08 552	65.71 542	41.18 552	30.42 543	28.83 543	61.42 542	14.88 546	56.40 545	14.13 547	26.37 545	37.16 541

SIFT-UMatch		42.35 507	41.04 510	46.29 524	76.09 542	41.80 551	70.21 535	45.21 550	30.75 541	27.33 544	62.62 537	15.13 545	59.11 543	14.72 545	27.30 543	37.95 539

SIFT-NCM-Cal		44.98 503	44.20 506	47.33 521	79.81 533	43.05 546	72.12 533	49.31 546	30.81 540	25.90 545	61.87 541	15.80 543	60.28 540	14.09 548	48.07 531	38.66 538

SIFT-PCN-Cal		36.85 511	36.40 514	38.19 529	71.43 549	30.42 556	64.34 543	37.72 554	27.48 546	22.98 546	57.03 543	12.99 550	51.22 548	12.51 549	21.13 547	32.92 544

SIFT-UM-Cal		39.93 509	38.61 512	43.88 527	76.08 543	39.30 553	68.10 539	37.89 553	30.49 542	22.74 547	62.27 539	13.89 548	56.16 546	14.17 546	21.90 546	36.17 542

SIFT-PointCN		37.89 510	37.50 513	39.07 528	71.45 548	31.31 555	66.27 541	41.69 551	27.82 545	22.63 548	56.73 544	12.00 552	50.56 549	12.18 550	26.71 544	35.34 543

SIFT-NCMNet		32.45 512	31.84 516	34.30 530	68.74 552	28.10 557	57.85 544	24.54 555	27.25 547	19.31 549	52.59 545	9.75 555	45.69 550	10.92 551	15.56 549	29.13 545

testmvs		21.48 515	24.95 518	11.09 533	14.89 556	6.47 559	96.56 458	9.87 557	7.55 549	17.93 550	39.02 547	9.43 556	5.90 553	16.56 538	12.72 550	20.91 547

test123		20.95 516	23.72 519	12.64 532	13.54 557	8.19 558	96.55 459	6.13 558	7.48 550	16.74 551	37.98 548	12.97 551	6.05 552	16.69 536	5.43 551	23.68 546

wuyk23d		30.17 513	30.18 517	30.16 531	78.61 536	43.29 544	66.79 540	14.21 556	17.31 548	14.82 552	11.93 551	11.55 553	41.43 551	37.08 532	19.30 548	5.76 548

EGC-MVSNET		75.22 478	69.54 482	92.28 460	94.81 458	89.58 437	97.64 375	96.50 457	1.82 551	5.57 553	95.74 441	68.21 481	96.26 480	73.80 506	91.71 377	90.99 502

mmdepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet_test		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

cdsmvs_eth3d_5k		23.98 514	31.98 515	0.00 534	0.00 558	0.00 560	0.00 545	98.59 172	0.00 552	0.00 554	98.61 216	90.60 207	0.00 554	0.00 552	0.00 552	0.00 549

pcd_1.5k_mvsjas		7.88 518	10.50 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	94.51 92	0.00 554	0.00 552	0.00 552	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

ab-mvs-re		8.20 517	10.94 520	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	98.43 235	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

WAC-MVS						90.94 402								88.66 433

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					0.00 558

eth-test					0.00 558

OPU-MVS				99.37 28	99.24 104	99.05 17	99.02 86				99.16 110	97.81 3	99.37 212	97.24 164	99.73 62	99.70 67

save fliter					99.46 59	98.38 42	98.21 293	98.71 138	97.95 28

test_0728_SECOND				99.71 1	99.72 17	99.35 1	98.97 98	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							96.68 455				30.43 550	87.85 297	98.69 337	92.59 354

test_post											31.83 549	88.83 268	98.91 313

patchmatchnet-post											95.10 457	89.42 244	98.89 317

MTMP							98.89 124	94.14 495

gm-plane-assit					95.88 430	87.47 469			89.74 435		96.94 388		99.19 253	93.32 324

test9_res														96.39 209	99.57 99	99.69 70

agg_prior2														95.87 225	99.57 99	99.68 75

test_prior4						98.01 72	97.86 354

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

新几何2							97.64 375

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							97.58 380	98.72 135	91.38 398				99.87 80	93.36 323		99.60 92

原ACMM2							97.67 372

testdata2													99.89 69	91.65 382

segment_acmp												96.85 15

testdata1							97.32 402		96.34 129

plane_prior7					97.42 339	94.63 280

plane_prior6					97.35 346	94.61 283						87.09 311

plane_prior5								98.56 183					99.03 291	96.07 215	94.27 325	96.92 350

plane_prior4											98.28 254

plane_prior2							98.80 164		97.28 69

plane_prior1					97.37 345

plane_prior						94.60 285	98.44 262		96.74 105						94.22 327

n2								0.00 559

nn								0.00 559

door-mid								94.37 489

test11								98.66 154

door								94.64 487

HQP5-MVS						94.25 302

BP-MVS														95.30 249

HQP3-MVS								98.46 208							94.18 329

HQP2-MVS												86.75 317

NP-MVS					97.28 348	94.51 288					97.73 305

ACMMP++_ref															92.97 359

ACMMP++															93.61 346

Test By Simon												94.64 89

High-resolution multi-view benchmark