High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_cas_vis1_n_1920		99.16 104	99.01 121	99.61 103	99.81 52	98.86 203	99.65 84	99.64 38	99.39 20	99.97 23	99.94 6	93.20 316	99.98 18	99.55 48	99.91 44	99.99 1

fmvsm_s_conf0.1_n_a		99.26 87	99.06 103	99.85 38	99.52 207	99.62 77	99.54 160	99.62 47	98.69 101	99.99 2	99.96 1	94.47 276	99.94 87	99.88 24	99.92 37	99.98 2

test_vis1_n_1920		98.63 201	98.40 209	99.31 181	99.86 22	97.94 283	99.67 71	99.62 47	99.43 15	99.99 2	99.91 24	87.29 415	100.00 1	99.92 22	99.92 37	99.98 2

fmvsm_s_conf0.1_n		99.29 80	99.10 94	99.86 30	99.70 116	99.65 69	99.53 169	99.62 47	98.74 95	99.99 2	99.95 3	94.53 274	99.94 87	99.89 23	99.96 15	99.97 4

test_fmvsmconf0.1_n		99.55 20	99.45 27	99.86 30	99.44 241	99.65 69	99.50 189	99.61 56	99.45 11	99.87 44	99.92 17	97.31 127	99.97 27	99.95 14	99.99 1	99.97 4

test_vis1_n		97.92 273	97.44 314	99.34 173	99.53 201	98.08 270	99.74 47	99.49 173	99.15 32	100.00 1	99.94 6	79.51 450	99.98 18	99.88 24	99.76 134	99.97 4

fmvsm_s_conf0.5_n_9		99.41 56	99.28 66	99.81 55	99.84 35	99.52 99	99.48 210	99.62 47	99.46 7	99.99 2	99.92 17	95.24 230	99.96 39	99.97 2	99.97 8	99.96 7

fmvsm_s_conf0.5_n_8		99.54 21	99.42 29	99.89 9	99.83 44	99.74 49	99.51 179	99.62 47	99.46 7	99.99 2	99.90 31	96.60 165	99.98 18	99.95 14	99.95 21	99.96 7

test_fmvsmconf_n		99.70 3	99.64 4	99.87 19	99.80 58	99.66 65	99.48 210	99.64 38	99.45 11	99.92 28	99.92 17	98.62 73	99.99 4	99.96 12	99.99 1	99.96 7

test_fmvs1_n		98.41 213	98.14 225	99.21 202	99.82 48	97.71 296	99.74 47	99.49 173	99.32 25	99.99 2	99.95 3	85.32 428	99.97 27	99.82 27	99.84 96	99.96 7

fmvsm_l_conf0.5_n_9		99.58 14	99.47 22	99.92 1	99.85 28	99.82 26	99.47 219	99.63 42	99.45 11	99.98 11	99.89 38	97.02 143	99.99 4	99.98 1	99.96 15	99.95 11

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 35	99.82 26	99.54 160	99.66 28	99.46 7	99.98 11	99.89 38	97.27 130	99.99 4	99.97 2	99.95 21	99.95 11

fmvsm_s_conf0.5_n_3		99.37 64	99.20 82	99.87 19	99.75 86	99.70 55	99.48 210	99.66 28	99.45 11	99.99 2	99.93 10	94.64 266	99.97 27	99.94 19	99.97 8	99.95 11

fmvsm_s_conf0.5_n_a		99.56 19	99.47 22	99.85 38	99.83 44	99.64 75	99.52 170	99.65 35	99.10 42	99.98 11	99.92 17	97.35 126	99.96 39	99.94 19	99.92 37	99.95 11

fmvsm_s_conf0.5_n		99.51 26	99.40 35	99.85 38	99.84 35	99.65 69	99.51 179	99.67 23	99.13 35	99.98 11	99.92 17	96.60 165	99.96 39	99.95 14	99.96 15	99.95 11

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 38	99.86 22	99.61 79	99.56 141	99.63 42	99.48 3	99.98 11	99.83 94	98.75 58	99.99 4	99.97 2	99.96 15	99.94 16

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 38	99.84 35	99.63 76	99.56 141	99.63 42	99.47 4	99.98 11	99.82 103	98.75 58	99.99 4	99.97 2	99.97 8	99.94 16

MM		99.40 60	99.28 66	99.74 74	99.67 128	99.31 129	99.52 170	98.87 391	99.55 1	99.74 89	99.80 135	96.47 172	99.98 18	99.97 2	99.97 8	99.94 16

test_fmvsmconf0.01_n		99.22 95	99.03 110	99.79 62	98.42 421	99.48 105	99.55 155	99.51 141	99.39 20	99.78 75	99.93 10	94.80 249	99.95 74	99.93 21	99.95 21	99.94 16

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 68	99.38 259	99.37 117	99.58 126	99.62 47	99.41 19	99.87 44	99.92 17	98.81 47	100.00 1	99.97 2	99.93 31	99.94 16

fmvsm_s_conf0.5_n_2		99.32 75	99.13 90	99.89 9	99.80 58	99.77 43	99.44 232	99.58 74	99.47 4	99.99 2	99.93 10	94.04 292	99.96 39	99.96 12	99.93 31	99.93 21

fmvsm_s_conf0.5_n_6		99.54 21	99.44 28	99.85 38	99.51 210	99.67 62	99.50 189	99.64 38	99.43 15	99.98 11	99.78 158	97.26 132	99.95 74	99.95 14	99.93 31	99.92 22

fmvsm_s_conf0.5_n_5		99.37 64	99.21 80	99.86 30	99.80 58	99.68 58	99.42 244	99.61 56	99.37 22	99.97 23	99.86 67	94.96 238	99.99 4	99.97 2	99.93 31	99.92 22

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 65	99.84 35	99.44 110	99.58 126	99.69 18	99.43 15	99.98 11	99.91 24	98.62 73	100.00 1	99.97 2	99.95 21	99.90 24

test_fmvs1		98.88 161	98.79 165	99.16 207	99.69 121	97.61 300	99.55 155	99.49 173	99.32 25	99.98 11	99.91 24	91.41 364	99.96 39	99.82 27	99.92 37	99.90 24

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 72	99.89 5	99.75 42	99.56 85	99.02 56	99.88 38	99.85 74	99.18 10	99.96 39	99.22 95	99.92 37	99.90 24
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
patch_mono-2		99.26 87	99.62 5	98.16 342	99.81 52	94.59 414	99.52 170	99.64 38	99.33 24	99.73 91	99.90 31	99.00 22	99.99 4	99.69 33	99.98 4	99.89 27

MSC_two_6792asdad				99.87 19	99.51 210	99.76 44		99.33 301					99.96 39	98.87 143	99.84 96	99.89 27

No_MVS				99.87 19	99.51 210	99.76 44		99.33 301					99.96 39	98.87 143	99.84 96	99.89 27

IU-MVS					99.84 35	99.88 9		99.32 311	98.30 142	99.84 51				98.86 148	99.85 88	99.89 27

UA-Net		99.42 52	99.29 63	99.80 59	99.62 161	99.55 90	99.50 189	99.70 15	98.79 89	99.77 79	99.96 1	97.45 121	99.96 39	98.92 136	99.90 55	99.89 27

CHOSEN 1792x2688		99.19 96	99.10 94	99.45 154	99.89 8	98.52 242	99.39 261	99.94 1	98.73 96	99.11 261	99.89 38	95.50 216	99.94 87	99.50 55	99.97 8	99.89 27

test_241102_TWO								99.48 185	99.08 50	99.88 38	99.81 118	98.94 32	99.96 39	98.91 137	99.84 96	99.88 33

test_0728_THIRD									98.99 63	99.81 63	99.80 135	99.09 14	99.96 39	98.85 150	99.90 55	99.88 33

test_0728_SECOND				99.91 4	99.84 35	99.89 5	99.57 134	99.51 141					99.96 39	98.93 134	99.86 81	99.88 33

DPE-MVS		99.46 39	99.32 51	99.91 4	99.78 64	99.88 9	99.36 273	99.51 141	98.73 96	99.88 38	99.84 89	98.72 64	99.96 39	98.16 237	99.87 73	99.88 33
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		99.42 52	99.27 70	99.88 13	99.89 8	99.80 33	99.67 71	99.50 161	98.70 100	99.77 79	99.49 293	98.21 99	99.95 74	98.46 208	99.77 131	99.88 33
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
dcpmvs_2		99.23 93	99.58 7	98.16 342	99.83 44	94.68 411	99.76 37	99.52 122	99.07 52	99.98 11	99.88 49	98.56 77	99.93 105	99.67 35	99.98 4	99.87 38

DP-MVS		99.16 104	98.95 135	99.78 65	99.77 72	99.53 95	99.41 249	99.50 161	97.03 315	99.04 278	99.88 49	97.39 122	99.92 117	98.66 177	99.90 55	99.87 38

reproduce_model		99.63 7	99.54 11	99.90 6	99.78 64	99.88 9	99.56 141	99.55 93	99.15 32	99.90 32	99.90 31	99.00 22	99.97 27	99.11 109	99.91 44	99.86 40

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 95	99.78 64	99.14 154	99.60 109	99.45 229	99.01 58	99.90 32	99.83 94	98.98 24	99.93 105	99.59 43	99.95 21	99.86 40

Test_1112_low_res		98.89 160	98.66 180	99.57 114	99.69 121	98.95 186	99.03 371	99.47 207	96.98 317	99.15 255	99.23 364	96.77 159	99.89 157	98.83 156	98.78 241	99.86 40

HyFIR lowres test		99.11 127	98.92 139	99.65 89	99.90 4	99.37 117	99.02 374	99.91 3	97.67 245	99.59 146	99.75 176	95.90 198	99.73 251	99.53 51	99.02 219	99.86 40

fmvsm_s_conf0.5_n_7		99.34 71	99.29 63	99.48 146	99.70 116	98.63 228	99.42 244	99.63 42	99.46 7	99.98 11	99.88 49	95.59 213	99.96 39	99.97 2	99.98 4	99.85 44

reproduce-ours		99.61 8	99.52 12	99.90 6	99.76 76	99.88 9	99.52 170	99.54 102	99.13 35	99.89 35	99.89 38	98.96 25	99.96 39	99.04 117	99.90 55	99.85 44

our_new_method		99.61 8	99.52 12	99.90 6	99.76 76	99.88 9	99.52 170	99.54 102	99.13 35	99.89 35	99.89 38	98.96 25	99.96 39	99.04 117	99.90 55	99.85 44

EI-MVSNet-Vis-set		99.58 14	99.56 10	99.64 95	99.78 64	99.15 153	99.61 108	99.45 229	99.01 58	99.89 35	99.82 103	99.01 18	99.92 117	99.56 47	99.95 21	99.85 44

CVMVSNet		98.57 203	98.67 177	98.30 330	99.35 266	95.59 386	99.50 189	99.55 93	98.60 109	99.39 195	99.83 94	94.48 275	99.45 312	98.75 164	98.56 254	99.85 44

HPM-MVS_fast		99.51 26	99.40 35	99.85 38	99.91 1	99.79 36	99.76 37	99.56 85	97.72 237	99.76 85	99.75 176	99.13 12	99.92 117	99.07 115	99.92 37	99.85 44

MG-MVS		99.13 114	99.02 116	99.45 154	99.57 185	98.63 228	99.07 360	99.34 293	98.99 63	99.61 140	99.82 103	97.98 110	99.87 169	97.00 338	99.80 119	99.85 44

MVS_0304		99.15 108	98.96 131	99.73 77	98.92 367	99.37 117	99.37 268	96.92 447	99.51 2	99.66 115	99.78 158	96.69 162	99.97 27	99.84 26	99.97 8	99.84 51

ACMMP_NAP		99.47 37	99.34 47	99.88 13	99.87 17	99.86 17	99.47 219	99.48 185	98.05 192	99.76 85	99.86 67	98.82 46	99.93 105	98.82 160	99.91 44	99.84 51

HFP-MVS		99.49 30	99.37 41	99.86 30	99.87 17	99.80 33	99.66 78	99.67 23	98.15 167	99.68 104	99.69 209	99.06 16	99.96 39	98.69 173	99.87 73	99.84 51

region2R		99.48 34	99.35 45	99.87 19	99.88 13	99.80 33	99.65 84	99.66 28	98.13 174	99.66 115	99.68 216	98.96 25	99.96 39	98.62 182	99.87 73	99.84 51

XVS		99.53 24	99.42 29	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 199	99.74 181	98.81 47	99.94 87	98.79 161	99.86 81	99.84 51

X-MVStestdata		96.55 370	95.45 389	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 199	64.01 466	98.81 47	99.94 87	98.79 161	99.86 81	99.84 51

ACMMPR		99.49 30	99.36 43	99.86 30	99.87 17	99.79 36	99.66 78	99.67 23	98.15 167	99.67 110	99.69 209	98.95 30	99.96 39	98.69 173	99.87 73	99.84 51

HPM-MVS		99.42 52	99.28 66	99.83 51	99.90 4	99.72 51	99.81 20	99.54 102	97.59 252	99.68 104	99.63 241	98.91 37	99.94 87	98.58 191	99.91 44	99.84 51
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SteuartSystems-ACMMP		99.54 21	99.42 29	99.87 19	99.82 48	99.81 31	99.59 116	99.51 141	98.62 106	99.79 70	99.83 94	99.28 4	99.97 27	98.48 204	99.90 55	99.84 51
Skip Steuart: Steuart Systems R&D Blog.
1112_ss		98.98 153	98.77 166	99.59 107	99.68 126	99.02 169	99.25 318	99.48 185	97.23 294	99.13 257	99.58 259	96.93 148	99.90 142	98.87 143	98.78 241	99.84 51

lecture		99.60 12	99.50 17	99.89 9	99.89 8	99.90 2	99.75 42	99.59 69	99.06 55	99.88 38	99.85 74	98.41 90	99.96 39	99.28 88	99.84 96	99.83 61

MP-MVS-pluss		99.37 64	99.20 82	99.88 13	99.90 4	99.87 16	99.30 292	99.52 122	97.18 297	99.60 143	99.79 151	98.79 50	99.95 74	98.83 156	99.91 44	99.83 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MTAPA		99.52 25	99.39 37	99.89 9	99.90 4	99.86 17	99.66 78	99.47 207	98.79 89	99.68 104	99.81 118	98.43 86	99.97 27	98.88 140	99.90 55	99.83 61

PGM-MVS		99.45 43	99.31 57	99.86 30	99.87 17	99.78 42	99.58 126	99.65 35	97.84 223	99.71 98	99.80 135	99.12 13	99.97 27	98.33 222	99.87 73	99.83 61

mPP-MVS		99.44 47	99.30 59	99.86 30	99.88 13	99.79 36	99.69 62	99.48 185	98.12 176	99.50 164	99.75 176	98.78 51	99.97 27	98.57 194	99.89 66	99.83 61

CP-MVS		99.45 43	99.32 51	99.85 38	99.83 44	99.75 46	99.69 62	99.52 122	98.07 186	99.53 159	99.63 241	98.93 36	99.97 27	98.74 165	99.91 44	99.83 61

mvsany_test1		99.50 28	99.46 26	99.62 102	99.61 170	99.09 159	98.94 394	99.48 185	99.10 42	99.96 25	99.91 24	98.85 42	99.96 39	99.72 30	99.58 163	99.82 67

test1111		98.04 253	98.11 229	97.83 371	99.74 94	93.82 423	99.58 126	95.40 457	99.12 40	99.65 124	99.93 10	90.73 374	99.84 188	99.43 66	99.38 177	99.82 67

ZNCC-MVS		99.47 37	99.33 49	99.87 19	99.87 17	99.81 31	99.64 91	99.67 23	98.08 185	99.55 156	99.64 235	98.91 37	99.96 39	98.72 168	99.90 55	99.82 67

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 55	99.91 1	99.66 65	99.63 97	99.39 264	98.91 76	99.78 75	99.85 74	99.36 2	99.94 87	98.84 153	99.88 70	99.82 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MP-MVS		99.33 73	99.15 88	99.87 19	99.88 13	99.82 26	99.66 78	99.46 218	98.09 181	99.48 168	99.74 181	98.29 96	99.96 39	97.93 259	99.87 73	99.82 67
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		99.43 50	99.30 59	99.82 52	99.79 62	99.74 49	99.29 297	99.40 261	98.79 89	99.52 161	99.62 246	98.91 37	99.90 142	98.64 179	99.75 136	99.82 67

DeepC-MVS_fast	98.69 1	99.49 30	99.39 37	99.77 68	99.63 155	99.59 82	99.36 273	99.46 218	99.07 52	99.79 70	99.82 103	98.85 42	99.92 117	98.68 175	99.87 73	99.82 67
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DVP-MVS++		99.59 13	99.50 17	99.88 13	99.51 210	99.88 9	99.87 8	99.51 141	98.99 63	99.88 38	99.81 118	99.27 5	99.96 39	98.85 150	99.80 119	99.81 74

PC_three_1452									98.18 165	99.84 51	99.70 198	99.31 3	98.52 425	98.30 226	99.80 119	99.81 74

DVP-MVS		99.57 18	99.47 22	99.88 13	99.85 28	99.89 5	99.57 134	99.37 280	99.10 42	99.81 63	99.80 135	98.94 32	99.96 39	98.93 134	99.86 81	99.81 74
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
GST-MVS		99.40 60	99.24 75	99.85 38	99.86 22	99.79 36	99.60 109	99.67 23	97.97 207	99.63 132	99.68 216	98.52 80	99.95 74	98.38 215	99.86 81	99.81 74

SMA-MVS		99.44 47	99.30 59	99.85 38	99.73 101	99.83 20	99.56 141	99.47 207	97.45 271	99.78 75	99.82 103	99.18 10	99.91 129	98.79 161	99.89 66	99.81 74
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
CPTT-MVS		99.11 127	98.90 144	99.74 74	99.80 58	99.46 108	99.59 116	99.49 173	97.03 315	99.63 132	99.69 209	97.27 130	99.96 39	97.82 270	99.84 96	99.81 74

ACMMP		99.45 43	99.32 51	99.82 52	99.89 8	99.67 62	99.62 102	99.69 18	98.12 176	99.63 132	99.84 89	98.73 63	99.96 39	98.55 200	99.83 107	99.81 74
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
DeepPCF-MVS	98.18 3	98.81 180	99.37 41	97.12 400	99.60 176	91.75 440	98.61 425	99.44 238	99.35 23	99.83 59	99.85 74	98.70 66	99.81 215	99.02 121	99.91 44	99.81 74

3Dnovator+	97.12 13	99.18 99	98.97 127	99.82 52	99.17 322	99.68 58	99.81 20	99.51 141	99.20 29	98.72 326	99.89 38	95.68 210	99.97 27	98.86 148	99.86 81	99.81 74

test2506		96.81 366	96.65 362	97.29 396	99.74 94	92.21 439	99.60 109	85.06 470	99.13 35	99.77 79	99.93 10	87.82 413	99.85 179	99.38 71	99.38 177	99.80 83

ECVR-MVS		98.04 253	98.05 238	98.00 355	99.74 94	94.37 418	99.59 116	94.98 458	99.13 35	99.66 115	99.93 10	90.67 375	99.84 188	99.40 68	99.38 177	99.80 83

APD-MVS		99.27 84	99.08 100	99.84 50	99.75 86	99.79 36	99.50 189	99.50 161	97.16 299	99.77 79	99.82 103	98.78 51	99.94 87	97.56 300	99.86 81	99.80 83
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		99.34 71	99.19 84	99.79 62	99.61 170	99.65 69	99.30 292	99.48 185	98.86 78	99.21 242	99.63 241	98.72 64	99.90 142	98.25 229	99.63 158	99.80 83

SED-MVS		99.61 8	99.52 12	99.88 13	99.84 35	99.90 2	99.60 109	99.48 185	99.08 50	99.91 29	99.81 118	99.20 7	99.96 39	98.91 137	99.85 88	99.79 87

OPU-MVS				99.64 95	99.56 189	99.72 51	99.60 109				99.70 198	99.27 5	99.42 323	98.24 230	99.80 119	99.79 87

SR-MVS		99.43 50	99.29 63	99.86 30	99.75 86	99.83 20	99.59 116	99.62 47	98.21 160	99.73 91	99.79 151	98.68 67	99.96 39	98.44 210	99.77 131	99.79 87

HPM-MVS++		99.39 62	99.23 78	99.87 19	99.75 86	99.84 19	99.43 237	99.51 141	98.68 103	99.27 227	99.53 279	98.64 72	99.96 39	98.44 210	99.80 119	99.79 87

PVSNet_Blended_VisFu		99.36 68	99.28 66	99.61 103	99.86 22	99.07 164	99.47 219	99.93 2	97.66 246	99.71 98	99.86 67	97.73 116	99.96 39	99.47 63	99.82 111	99.79 87

3Dnovator	97.25 9	99.24 92	99.05 105	99.81 55	99.12 330	99.66 65	99.84 12	99.74 10	99.09 49	98.92 298	99.90 31	95.94 195	99.98 18	98.95 130	99.92 37	99.79 87

APD-MVS_3200maxsize		99.48 34	99.35 45	99.85 38	99.76 76	99.83 20	99.63 97	99.54 102	98.36 135	99.79 70	99.82 103	98.86 41	99.95 74	98.62 182	99.81 114	99.78 93

CDPH-MVS		99.13 114	98.91 142	99.80 59	99.75 86	99.71 53	99.15 344	99.41 254	96.60 347	99.60 143	99.55 270	98.83 45	99.90 142	97.48 307	99.83 107	99.78 93

viewmsd2359difaftdt		98.78 185	98.74 170	98.90 244	99.67 128	97.04 329	99.50 189	99.58 74	98.26 148	99.56 151	99.90 31	94.36 279	99.87 169	99.49 59	98.32 270	99.77 95

SR-MVS-dyc-post		99.45 43	99.31 57	99.85 38	99.76 76	99.82 26	99.63 97	99.52 122	98.38 131	99.76 85	99.82 103	98.53 79	99.95 74	98.61 185	99.81 114	99.77 95

RE-MVS-def			99.34 47		99.76 76	99.82 26	99.63 97	99.52 122	98.38 131	99.76 85	99.82 103	98.75 58		98.61 185	99.81 114	99.77 95

SD-MVS		99.41 56	99.52 12	99.05 219	99.74 94	99.68 58	99.46 223	99.52 122	99.11 41	99.88 38	99.91 24	99.43 1	97.70 442	98.72 168	99.93 31	99.77 95
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
CNVR-MVS		99.42 52	99.30 59	99.78 65	99.62 161	99.71 53	99.26 316	99.52 122	98.82 83	99.39 195	99.71 194	98.96 25	99.85 179	98.59 190	99.80 119	99.77 95

MVS_111021_HR		99.41 56	99.32 51	99.66 85	99.72 105	99.47 107	98.95 392	99.85 6	98.82 83	99.54 157	99.73 187	98.51 81	99.74 245	98.91 137	99.88 70	99.77 95

viewmacassd2359aftdt		99.08 134	98.94 137	99.50 143	99.66 140	98.96 181	99.51 179	99.54 102	98.27 145	99.42 183	99.89 38	95.88 200	99.80 222	99.20 97	99.11 206	99.76 101

QAPM		98.67 196	98.30 216	99.80 59	99.20 308	99.67 62	99.77 34	99.72 11	94.74 410	98.73 325	99.90 31	95.78 206	99.98 18	96.96 342	99.88 70	99.76 101

GeoE		98.85 176	98.62 190	99.53 127	99.61 170	99.08 162	99.80 25	99.51 141	97.10 307	99.31 214	99.78 158	95.23 231	99.77 236	98.21 231	99.03 217	99.75 103

test9_res														97.49 306	99.72 142	99.75 103

train_agg		99.02 146	98.77 166	99.77 68	99.67 128	99.65 69	99.05 366	99.41 254	96.28 367	98.95 294	99.49 293	98.76 55	99.91 129	97.63 291	99.72 142	99.75 103

agg_prior2														97.21 324	99.73 141	99.75 103

NormalMVS		99.27 84	99.19 84	99.52 133	99.89 8	98.83 209	99.65 84	99.52 122	99.10 42	99.84 51	99.76 171	95.80 204	99.99 4	99.30 85	99.84 96	99.74 107

KinetiMVS		99.12 121	98.92 139	99.70 81	99.67 128	99.40 115	99.67 71	99.63 42	98.73 96	99.94 26	99.81 118	94.54 272	99.96 39	98.40 213	99.93 31	99.74 107

AstraMVS		99.09 132	99.03 110	99.25 196	99.66 140	98.13 267	99.57 134	98.24 430	98.82 83	99.91 29	99.88 49	95.81 203	99.90 142	99.72 30	99.67 152	99.74 107

guyue		99.16 104	99.04 107	99.52 133	99.69 121	98.92 193	99.59 116	98.81 398	98.73 96	99.90 32	99.87 60	95.34 223	99.88 162	99.66 38	99.81 114	99.74 107

SF-MVS		99.38 63	99.24 75	99.79 62	99.79 62	99.68 58	99.57 134	99.54 102	97.82 228	99.71 98	99.80 135	98.95 30	99.93 105	98.19 233	99.84 96	99.74 107

test_prior				99.68 83	99.67 128	99.48 105		99.56 85					99.83 201			99.74 107

test12				99.75 71	99.64 151	99.61 79		99.29 324		99.21 242		98.38 92	99.89 157		99.74 139	99.74 107

114514_t		98.93 157	98.67 177	99.72 80	99.85 28	99.53 95	99.62 102	99.59 69	92.65 432	99.71 98	99.78 158	98.06 107	99.90 142	98.84 153	99.91 44	99.74 107

Vis-MVSNet		99.12 121	98.97 127	99.56 116	99.78 64	99.10 158	99.68 68	99.66 28	98.49 119	99.86 48	99.87 60	94.77 254	99.84 188	99.19 98	99.41 176	99.74 107
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SymmetryMVS		99.15 108	99.02 116	99.52 133	99.72 105	98.83 209	99.65 84	99.34 293	99.10 42	99.84 51	99.76 171	95.80 204	99.99 4	99.30 85	98.72 244	99.73 116

fmvsm_s_conf0.5_n_4		99.36 68	99.24 75	99.73 77	99.78 64	99.53 95	99.49 204	99.60 63	99.42 18	99.99 2	99.86 67	95.15 233	99.95 74	99.95 14	99.89 66	99.73 116

fmvsm_s_conf0.1_n_2		99.37 64	99.22 79	99.81 55	99.77 72	99.75 46	99.46 223	99.60 63	99.47 4	99.98 11	99.94 6	94.98 237	99.95 74	99.97 2	99.79 126	99.73 116

旧先验1					99.74 94	99.59 82		99.54 102			99.69 209	98.47 83			99.68 150	99.73 116

casdiffmvs_mvg		99.15 108	99.02 116	99.55 118	99.66 140	99.09 159	99.64 91	99.56 85	98.26 148	99.45 172	99.87 60	96.03 189	99.81 215	99.54 49	99.15 201	99.73 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPNet		98.86 167	98.71 173	99.30 186	97.20 441	98.18 263	99.62 102	98.91 384	99.28 27	98.63 345	99.81 118	95.96 192	99.99 4	99.24 94	99.72 142	99.73 116
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IS-MVSNet		99.05 142	98.87 152	99.57 114	99.73 101	99.32 125	99.75 42	99.20 342	98.02 204	99.56 151	99.86 67	96.54 169	99.67 275	98.09 244	99.13 203	99.73 116

F-COLMAP		99.19 96	99.04 107	99.64 95	99.78 64	99.27 137	99.42 244	99.54 102	97.29 288	99.41 188	99.59 255	98.42 88	99.93 105	98.19 233	99.69 147	99.73 116

DeepC-MVS	98.35 2	99.30 78	99.19 84	99.64 95	99.82 48	99.23 142	99.62 102	99.55 93	98.94 72	99.63 132	99.95 3	95.82 202	99.94 87	99.37 72	99.97 8	99.73 116
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SDMVSNet		99.11 127	98.90 144	99.75 71	99.81 52	99.59 82	99.81 20	99.65 35	98.78 92	99.64 129	99.88 49	94.56 269	99.93 105	99.67 35	98.26 273	99.72 125

sd_testset		98.75 189	98.57 197	99.29 189	99.81 52	98.26 260	99.56 141	99.62 47	98.78 92	99.64 129	99.88 49	92.02 348	99.88 162	99.54 49	98.26 273	99.72 125

新几何1				99.75 71	99.75 86	99.59 82		99.54 102	96.76 331	99.29 221	99.64 235	98.43 86	99.94 87	96.92 347	99.66 153	99.72 125

无先验							98.99 382	99.51 141	96.89 325				99.93 105	97.53 303		99.72 125

test222					99.75 86	99.49 103	98.91 398	99.49 173	96.42 361	99.34 211	99.65 229	98.28 97			99.69 147	99.72 125

testdata				99.54 119	99.75 86	98.95 186		99.51 141	97.07 309	99.43 180	99.70 198	98.87 40	99.94 87	97.76 279	99.64 156	99.72 125

VNet		99.11 127	98.90 144	99.73 77	99.52 207	99.56 88	99.41 249	99.39 264	99.01 58	99.74 89	99.78 158	95.56 214	99.92 117	99.52 53	98.18 281	99.72 125

WTY-MVS		99.06 139	98.88 151	99.61 103	99.62 161	99.16 149	99.37 268	99.56 85	98.04 199	99.53 159	99.62 246	96.84 154	99.94 87	98.85 150	98.49 259	99.72 125

CSCG		99.32 75	99.32 51	99.32 179	99.85 28	98.29 258	99.71 57	99.66 28	98.11 178	99.41 188	99.80 135	98.37 93	99.96 39	98.99 123	99.96 15	99.72 125

diffmvs_AUTHOR		99.19 96	99.10 94	99.48 146	99.64 151	98.85 204	99.32 286	99.48 185	98.50 118	99.81 63	99.81 118	96.82 155	99.88 162	99.40 68	99.12 205	99.71 134

BP-MVS1		99.12 121	98.94 137	99.65 89	99.51 210	99.30 132	99.67 71	98.92 379	98.48 120	99.84 51	99.69 209	94.96 238	99.92 117	99.62 42	99.79 126	99.71 134

原ACMM1				99.65 89	99.73 101	99.33 124		99.47 207	97.46 268	99.12 259	99.66 227	98.67 69	99.91 129	97.70 288	99.69 147	99.71 134

viewmanbaseed2359cas		99.18 99	99.07 102	99.50 143	99.62 161	99.01 171	99.50 189	99.52 122	98.25 152	99.68 104	99.82 103	96.93 148	99.80 222	99.15 106	99.11 206	99.70 137

Anonymous202405211		98.30 224	97.98 245	99.26 195	99.57 185	98.16 264	99.41 249	98.55 423	96.03 388	99.19 248	99.74 181	91.87 351	99.92 117	99.16 105	98.29 272	99.70 137

casdiffmvs		99.13 114	98.98 126	99.56 116	99.65 148	99.16 149	99.56 141	99.50 161	98.33 139	99.41 188	99.86 67	95.92 196	99.83 201	99.45 65	99.16 198	99.70 137
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LFMVS		97.90 276	97.35 326	99.54 119	99.52 207	99.01 171	99.39 261	98.24 430	97.10 307	99.65 124	99.79 151	84.79 431	99.91 129	99.28 88	98.38 263	99.69 140

EPNet_dtu		98.03 255	97.96 247	98.23 338	98.27 423	95.54 389	99.23 326	98.75 405	99.02 56	97.82 394	99.71 194	96.11 185	99.48 307	93.04 422	99.65 155	99.69 140
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PAPM_NR		99.04 143	98.84 159	99.66 85	99.74 94	99.44 110	99.39 261	99.38 272	97.70 241	99.28 222	99.28 356	98.34 94	99.85 179	96.96 342	99.45 173	99.69 140

EPP-MVSNet		99.13 114	98.99 123	99.53 127	99.65 148	99.06 165	99.81 20	99.33 301	97.43 275	99.60 143	99.88 49	97.14 134	99.84 188	99.13 107	98.94 223	99.69 140

sss		99.17 102	99.05 105	99.53 127	99.62 161	98.97 177	99.36 273	99.62 47	97.83 224	99.67 110	99.65 229	97.37 125	99.95 74	99.19 98	99.19 197	99.68 144

PHI-MVS		99.30 78	99.17 87	99.70 81	99.56 189	99.52 99	99.58 126	99.80 8	97.12 303	99.62 136	99.73 187	98.58 75	99.90 142	98.61 185	99.91 44	99.68 144

PVSNet_0	94.43 19	96.09 381	95.47 388	97.94 360	99.31 280	94.34 420	97.81 450	99.70 15	97.12 303	97.46 400	98.75 411	89.71 386	99.79 228	97.69 289	81.69 453	99.68 144

viewmambaseed2359dif		99.01 150	98.90 144	99.32 179	99.58 180	98.51 244	99.33 283	99.54 102	97.85 220	99.44 177	99.85 74	96.01 190	99.79 228	99.41 67	99.13 203	99.67 147

diffmvs		99.14 112	99.02 116	99.51 138	99.61 170	98.96 181	99.28 302	99.49 173	98.46 122	99.72 96	99.71 194	96.50 171	99.88 162	99.31 82	99.11 206	99.67 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.15 108	99.02 116	99.53 127	99.66 140	99.14 154	99.72 53	99.48 185	98.35 136	99.42 183	99.84 89	96.07 186	99.79 228	99.51 54	99.14 202	99.67 147

TAMVS		99.12 121	99.08 100	99.24 199	99.46 234	98.55 236	99.51 179	99.46 218	98.09 181	99.45 172	99.82 103	98.34 94	99.51 306	98.70 170	98.93 224	99.67 147

SD_0403		97.55 330	97.53 297	97.62 383	99.61 170	93.64 429	99.72 53	99.44 238	98.03 201	98.62 348	99.39 325	96.06 187	99.57 299	87.88 447	99.01 220	99.66 151

Anonymous20240529		98.09 243	97.68 281	99.34 173	99.66 140	98.44 252	99.40 257	99.43 249	93.67 420	99.22 239	99.89 38	90.23 381	99.93 105	99.26 93	98.33 266	99.66 151

CHOSEN 280x420		99.12 121	99.13 90	99.08 214	99.66 140	97.89 284	98.43 435	99.71 13	98.88 77	99.62 136	99.76 171	96.63 164	99.70 267	99.46 64	99.99 1	99.66 151

CDS-MVSNet		99.09 132	99.03 110	99.25 196	99.42 244	98.73 219	99.45 226	99.46 218	98.11 178	99.46 171	99.77 167	98.01 109	99.37 330	98.70 170	98.92 226	99.66 151
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		98.63 201	98.34 212	99.51 138	99.40 254	99.03 168	98.80 408	99.36 281	96.33 364	99.00 285	99.12 378	98.46 84	99.84 188	95.23 394	99.37 184	99.66 151

h-mvs33		97.70 315	97.28 338	98.97 229	99.70 116	97.27 311	99.36 273	99.45 229	98.94 72	99.66 115	99.64 235	94.93 241	99.99 4	99.48 61	84.36 449	99.65 156

CANet		99.25 91	99.14 89	99.59 107	99.41 249	99.16 149	99.35 278	99.57 80	98.82 83	99.51 163	99.61 250	96.46 173	99.95 74	99.59 43	99.98 4	99.65 156

TSAR-MVS + GP.		99.36 68	99.36 43	99.36 170	99.67 128	98.61 232	99.07 360	99.33 301	99.00 61	99.82 62	99.81 118	99.06 16	99.84 188	99.09 113	99.42 175	99.65 156

MVSFormer		99.17 102	99.12 92	99.29 189	99.51 210	98.94 189	99.88 4	99.46 218	97.55 258	99.80 68	99.65 229	97.39 122	99.28 347	99.03 119	99.85 88	99.65 156

jason		99.13 114	99.03 110	99.45 154	99.46 234	98.87 200	99.12 350	99.26 330	98.03 201	99.79 70	99.65 229	97.02 143	99.85 179	99.02 121	99.90 55	99.65 156
jason: jason.
PLC	97.94 4	99.02 146	98.85 157	99.53 127	99.66 140	99.01 171	99.24 323	99.52 122	96.85 327	99.27 227	99.48 299	98.25 98	99.91 129	97.76 279	99.62 159	99.65 156
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TAPA-MVS	97.07 15	97.74 307	97.34 329	98.94 234	99.70 116	97.53 301	99.25 318	99.51 141	91.90 434	99.30 218	99.63 241	98.78 51	99.64 287	88.09 445	99.87 73	99.65 156
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GDP-MVS		99.08 134	98.89 148	99.64 95	99.53 201	99.34 121	99.64 91	99.48 185	98.32 140	99.77 79	99.66 227	95.14 234	99.93 105	98.97 129	99.50 170	99.64 163

dmvs_re		98.08 245	98.16 222	97.85 368	99.55 193	94.67 412	99.70 58	98.92 379	98.15 167	99.06 275	99.35 337	93.67 307	99.25 354	97.77 278	97.25 334	99.64 163

LCM-MVSNet-Re		97.83 290	98.15 224	96.87 408	99.30 281	92.25 438	99.59 116	98.26 428	97.43 275	96.20 424	99.13 375	96.27 181	98.73 421	98.17 236	98.99 221	99.64 163

BH-RMVSNet		98.41 213	98.08 234	99.40 164	99.41 249	98.83 209	99.30 292	98.77 404	97.70 241	98.94 296	99.65 229	92.91 322	99.74 245	96.52 362	99.55 166	99.64 163

MVS_111021_LR		99.41 56	99.33 49	99.65 89	99.77 72	99.51 101	98.94 394	99.85 6	98.82 83	99.65 124	99.74 181	98.51 81	99.80 222	98.83 156	99.89 66	99.64 163

LuminaMVS		99.23 93	99.10 94	99.61 103	99.35 266	99.31 129	99.46 223	99.13 351	98.61 107	99.86 48	99.89 38	96.41 177	99.91 129	99.67 35	99.51 168	99.63 168

MVS		97.28 351	96.55 364	99.48 146	98.78 388	98.95 186	99.27 307	99.39 264	83.53 453	98.08 380	99.54 275	96.97 146	99.87 169	94.23 408	99.16 198	99.63 168

MSLP-MVS++		99.46 39	99.47 22	99.44 158	99.60 176	99.16 149	99.41 249	99.71 13	98.98 66	99.45 172	99.78 158	99.19 9	99.54 304	99.28 88	99.84 96	99.63 168

GA-MVS		97.85 283	97.47 306	99.00 225	99.38 259	97.99 275	98.57 428	99.15 348	97.04 314	98.90 301	99.30 352	89.83 385	99.38 327	96.70 355	98.33 266	99.62 171

Vis-MVSNet (Re-imp)		98.87 164	98.72 171	99.31 181	99.71 111	98.88 196	99.80 25	99.44 238	97.91 212	99.36 205	99.78 158	95.49 217	99.43 321	97.91 260	99.11 206	99.62 171

DPM-MVS		98.95 156	98.71 173	99.66 85	99.63 155	99.55 90	98.64 424	99.10 354	97.93 210	99.42 183	99.55 270	98.67 69	99.80 222	95.80 379	99.68 150	99.61 173

RRT-MVS		98.91 159	98.75 168	99.39 168	99.46 234	98.61 232	99.76 37	99.50 161	98.06 190	99.81 63	99.88 49	93.91 299	99.94 87	99.11 109	99.27 188	99.61 173

baseline1		98.31 222	97.95 249	99.38 169	99.50 222	98.74 218	99.59 116	98.93 376	98.41 129	99.14 256	99.60 253	94.59 267	99.79 228	98.48 204	93.29 416	99.61 173

mamba_0408		99.08 134	98.96 131	99.44 158	99.62 161	98.88 196	99.25 318	99.47 207	98.05 192	99.37 199	99.81 118	96.85 150	99.85 179	98.98 124	99.25 191	99.60 176

icg_test_0407_2		98.79 184	98.86 154	98.57 292	99.55 193	96.93 339	99.07 360	99.44 238	98.05 192	99.66 115	99.80 135	97.13 135	99.18 369	98.15 239	98.92 226	99.60 176

SSM_04072		99.06 139	98.96 131	99.35 172	99.62 161	98.88 196	99.25 318	99.47 207	98.05 192	99.37 199	99.81 118	96.85 150	99.58 298	98.98 124	99.25 191	99.60 176

SSM_0407		99.13 114	99.03 110	99.43 161	99.62 161	98.88 196	99.51 179	99.50 161	98.14 172	99.37 199	99.85 74	96.85 150	99.83 201	99.19 98	99.25 191	99.60 176

IMVS_0407		98.86 167	98.91 142	98.72 276	99.55 193	96.93 339	99.50 189	99.44 238	98.05 192	99.66 115	99.80 135	97.13 135	99.65 283	98.15 239	98.92 226	99.60 176

IMVS_0404		98.53 204	98.52 202	98.55 298	99.55 193	96.93 339	99.20 335	99.44 238	98.05 192	98.96 292	99.80 135	94.66 264	99.13 377	98.15 239	98.92 226	99.60 176

IMVS_0403		98.86 167	98.89 148	98.78 271	99.55 193	96.93 339	99.58 126	99.44 238	98.05 192	99.68 104	99.80 135	96.81 156	99.80 222	98.15 239	98.92 226	99.60 176

VDD-MVS		97.73 309	97.35 326	98.88 250	99.47 232	97.12 319	99.34 281	98.85 393	98.19 162	99.67 110	99.85 74	82.98 439	99.92 117	99.49 59	98.32 270	99.60 176

DELS-MVS		99.48 34	99.42 29	99.65 89	99.72 105	99.40 115	99.05 366	99.66 28	99.14 34	99.57 150	99.80 135	98.46 84	99.94 87	99.57 46	99.84 96	99.60 176
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
PVSNet_Blended		99.08 134	98.97 127	99.42 162	99.76 76	98.79 215	98.78 410	99.91 3	96.74 332	99.67 110	99.49 293	97.53 119	99.88 162	98.98 124	99.85 88	99.60 176

OMC-MVS		99.08 134	99.04 107	99.20 203	99.67 128	98.22 262	99.28 302	99.52 122	98.07 186	99.66 115	99.81 118	97.79 114	99.78 234	97.79 274	99.81 114	99.60 176

test_yl		98.86 167	98.63 185	99.54 119	99.49 224	99.18 146	99.50 189	99.07 360	98.22 158	99.61 140	99.51 287	95.37 221	99.84 188	98.60 188	98.33 266	99.59 187

DCV-MVSNet		98.86 167	98.63 185	99.54 119	99.49 224	99.18 146	99.50 189	99.07 360	98.22 158	99.61 140	99.51 287	95.37 221	99.84 188	98.60 188	98.33 266	99.59 187

AllTest		98.87 164	98.72 171	99.31 181	99.86 22	98.48 249	99.56 141	99.61 56	97.85 220	99.36 205	99.85 74	95.95 193	99.85 179	96.66 358	99.83 107	99.59 187

TestCases				99.31 181	99.86 22	98.48 249		99.61 56	97.85 220	99.36 205	99.85 74	95.95 193	99.85 179	96.66 358	99.83 107	99.59 187

dongtai		93.26 409	92.93 413	94.25 421	99.39 257	85.68 449	97.68 452	93.27 463	92.87 429	96.85 418	99.39 325	82.33 443	97.48 444	76.78 457	97.80 298	99.58 191

testing3		97.28 351	96.76 360	98.82 263	99.37 262	98.07 271	99.45 226	99.36 281	97.56 257	97.89 391	98.95 396	83.70 436	98.82 416	96.03 373	98.56 254	99.58 191

lupinMVS		99.13 114	99.01 121	99.46 153	99.51 210	98.94 189	99.05 366	99.16 347	97.86 217	99.80 68	99.56 267	97.39 122	99.86 173	98.94 131	99.85 88	99.58 191

sc_t1		95.75 387	95.05 394	97.87 366	98.83 382	94.61 413	99.21 332	99.45 229	87.45 447	97.97 387	99.85 74	81.19 447	99.43 321	98.27 227	93.20 418	99.57 194

tttt0517		98.42 211	98.14 225	99.28 193	99.66 140	98.38 256	99.74 47	96.85 448	97.68 243	99.79 70	99.74 181	91.39 365	99.89 157	98.83 156	99.56 164	99.57 194

RPSCF		98.22 228	98.62 190	96.99 402	99.82 48	91.58 441	99.72 53	99.44 238	96.61 344	99.66 115	99.89 38	95.92 196	99.82 210	97.46 310	99.10 211	99.57 194

dmvs_testset		95.02 396	96.12 374	91.72 431	99.10 335	80.43 459	99.58 126	97.87 438	97.47 267	95.22 431	98.82 405	93.99 294	95.18 456	88.09 445	94.91 392	99.56 197

DSMNet-mixed		97.25 353	97.35 326	96.95 405	97.84 429	93.61 430	99.57 134	96.63 452	96.13 382	98.87 307	98.61 416	94.59 267	97.70 442	95.08 396	98.86 234	99.55 198

AdaColmap		99.01 150	98.80 162	99.66 85	99.56 189	99.54 92	99.18 339	99.70 15	98.18 165	99.35 208	99.63 241	96.32 179	99.90 142	97.48 307	99.77 131	99.55 198

alignmvs		98.81 180	98.56 199	99.58 110	99.43 242	99.42 112	99.51 179	98.96 374	98.61 107	99.35 208	98.92 401	94.78 251	99.77 236	99.35 73	98.11 286	99.54 200

mamv4		99.33 73	99.42 29	99.07 215	99.67 128	97.73 291	99.42 244	99.60 63	98.15 167	99.94 26	99.91 24	98.42 88	99.94 87	99.72 30	99.96 15	99.54 200

EC-MVSNet		99.44 47	99.39 37	99.58 110	99.56 189	99.49 103	99.88 4	99.58 74	98.38 131	99.73 91	99.69 209	98.20 100	99.70 267	99.64 41	99.82 111	99.54 200

PatchmatchNet		98.31 222	98.36 210	98.19 340	99.16 324	95.32 397	99.27 307	98.92 379	97.37 281	99.37 199	99.58 259	94.90 244	99.70 267	97.43 313	99.21 195	99.54 200
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PVSNet	96.02 17	98.85 176	98.84 159	98.89 248	99.73 101	97.28 310	98.32 441	99.60 63	97.86 217	99.50 164	99.57 264	96.75 160	99.86 173	98.56 197	99.70 146	99.54 200

MSDG		98.98 153	98.80 162	99.53 127	99.76 76	99.19 144	98.75 413	99.55 93	97.25 291	99.47 169	99.77 167	97.82 113	99.87 169	96.93 345	99.90 55	99.54 200

UGNet		98.87 164	98.69 175	99.40 164	99.22 305	98.72 220	99.44 232	99.68 20	99.24 28	99.18 252	99.42 313	92.74 326	99.96 39	99.34 78	99.94 29	99.53 206
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
SSM_0404		99.16 104	99.06 103	99.44 158	99.65 148	98.96 181	99.49 204	99.50 161	98.14 172	99.62 136	99.85 74	96.85 150	99.85 179	99.19 98	99.26 190	99.52 207

testing3-2		97.84 287	97.70 279	98.24 337	99.53 201	95.37 396	99.55 155	98.67 418	98.46 122	99.27 227	99.34 341	86.58 419	99.83 201	99.32 81	98.63 247	99.52 207

balanced_conf03		99.46 39	99.39 37	99.67 84	99.55 193	99.58 87	99.74 47	99.51 141	98.42 128	99.87 44	99.84 89	98.05 108	99.91 129	99.58 45	99.94 29	99.52 207

GSMVS																99.52 207

sam_mvs1												94.86 246				99.52 207

SCA		98.19 232	98.16 222	98.27 336	99.30 281	95.55 387	99.07 360	98.97 372	97.57 255	99.43 180	99.57 264	92.72 327	99.74 245	97.58 295	99.20 196	99.52 207

Patchmatch-test		97.93 270	97.65 284	98.77 272	99.18 314	97.07 324	99.03 371	99.14 350	96.16 378	98.74 324	99.57 264	94.56 269	99.72 255	93.36 418	99.11 206	99.52 207

PMMVS		98.80 183	98.62 190	99.34 173	99.27 290	98.70 221	98.76 412	99.31 315	97.34 283	99.21 242	99.07 380	97.20 133	99.82 210	98.56 197	98.87 233	99.52 207

LS3D		99.27 84	99.12 92	99.74 74	99.18 314	99.75 46	99.56 141	99.57 80	98.45 124	99.49 167	99.85 74	97.77 115	99.94 87	98.33 222	99.84 96	99.52 207

Effi-MVS+		98.81 180	98.59 196	99.48 146	99.46 234	99.12 157	98.08 448	99.50 161	97.50 266	99.38 197	99.41 317	96.37 178	99.81 215	99.11 109	98.54 256	99.51 216

Patchmatch-RL test		95.84 385	95.81 383	95.95 417	95.61 450	90.57 443	98.24 443	98.39 426	95.10 402	95.20 432	98.67 413	94.78 251	97.77 440	96.28 370	90.02 439	99.51 216

mvs_anonymous		99.03 145	98.99 123	99.16 207	99.38 259	98.52 242	99.51 179	99.38 272	97.79 229	99.38 197	99.81 118	97.30 128	99.45 312	99.35 73	98.99 221	99.51 216

mvsmamba		99.06 139	98.96 131	99.36 170	99.47 232	98.64 227	99.70 58	99.05 363	97.61 251	99.65 124	99.83 94	96.54 169	99.92 117	99.19 98	99.62 159	99.51 216

UniMVSNet_ETH3D		97.32 350	96.81 358	98.87 254	99.40 254	97.46 304	99.51 179	99.53 117	95.86 391	98.54 355	99.77 167	82.44 442	99.66 278	98.68 175	97.52 315	99.50 220

Elysia		98.88 161	98.65 182	99.58 110	99.58 180	99.34 121	99.65 84	99.52 122	98.26 148	99.83 59	99.87 60	93.37 310	99.90 142	97.81 272	99.91 44	99.49 221

StellarMVS		98.88 161	98.65 182	99.58 110	99.58 180	99.34 121	99.65 84	99.52 122	98.26 148	99.83 59	99.87 60	93.37 310	99.90 142	97.81 272	99.91 44	99.49 221

ab-mvs		98.86 167	98.63 185	99.54 119	99.64 151	99.19 144	99.44 232	99.54 102	97.77 232	99.30 218	99.81 118	94.20 285	99.93 105	99.17 104	98.82 238	99.49 221

thisisatest0530		98.35 220	98.03 240	99.31 181	99.63 155	98.56 235	99.54 160	96.75 450	97.53 262	99.73 91	99.65 229	91.25 369	99.89 157	98.62 182	99.56 164	99.48 224

SPE-MVS-test		99.49 30	99.48 20	99.54 119	99.78 64	99.30 132	99.89 2	99.58 74	98.56 112	99.73 91	99.69 209	98.55 78	99.82 210	99.69 33	99.85 88	99.48 224

ADS-MVSNet2		98.02 257	98.07 237	97.87 366	99.33 272	95.19 400	99.23 326	99.08 357	96.24 371	99.10 264	99.67 222	94.11 289	98.93 411	96.81 350	99.05 215	99.48 224

ADS-MVSNet		98.20 231	98.08 234	98.56 296	99.33 272	96.48 363	99.23 326	99.15 348	96.24 371	99.10 264	99.67 222	94.11 289	99.71 261	96.81 350	99.05 215	99.48 224

tpm		97.67 322	97.55 293	98.03 350	99.02 351	95.01 404	99.43 237	98.54 424	96.44 359	99.12 259	99.34 341	91.83 353	99.60 296	97.75 281	96.46 349	99.48 224

CNLPA		99.14 112	98.99 123	99.59 107	99.58 180	99.41 114	99.16 341	99.44 238	98.45 124	99.19 248	99.49 293	98.08 106	99.89 157	97.73 283	99.75 136	99.48 224

MVSMamba_PlusPlus		99.46 39	99.41 34	99.64 95	99.68 126	99.50 102	99.75 42	99.50 161	98.27 145	99.87 44	99.92 17	98.09 105	99.94 87	99.65 39	99.95 21	99.47 230

MGCFI-Net		99.01 150	98.85 157	99.50 143	99.42 244	99.26 138	99.82 16	99.48 185	98.60 109	99.28 222	98.81 406	97.04 142	99.76 240	99.29 87	97.87 295	99.47 230

sasdasda		99.02 146	98.86 154	99.51 138	99.42 244	99.32 125	99.80 25	99.48 185	98.63 104	99.31 214	98.81 406	97.09 138	99.75 243	99.27 91	97.90 292	99.47 230

canonicalmvs		99.02 146	98.86 154	99.51 138	99.42 244	99.32 125	99.80 25	99.48 185	98.63 104	99.31 214	98.81 406	97.09 138	99.75 243	99.27 91	97.90 292	99.47 230

MIMVSNet		97.73 309	97.45 309	98.57 292	99.45 240	97.50 303	99.02 374	98.98 371	96.11 383	99.41 188	99.14 374	90.28 377	98.74 420	95.74 380	98.93 224	99.47 230

MVS_Test		99.10 131	98.97 127	99.48 146	99.49 224	99.14 154	99.67 71	99.34 293	97.31 286	99.58 147	99.76 171	97.65 118	99.82 210	98.87 143	99.07 214	99.46 235

MDTV_nov1_ep13_2view						95.18 401	99.35 278		96.84 328	99.58 147		95.19 232		97.82 270		99.46 235

MVS-HIRNet		95.75 387	95.16 392	97.51 389	99.30 281	93.69 427	98.88 400	95.78 455	85.09 452	98.78 321	92.65 455	91.29 368	99.37 330	94.85 400	99.85 88	99.46 235

Syy-MVS		97.09 360	97.14 346	96.95 405	99.00 354	92.73 436	99.29 297	99.39 264	97.06 311	97.41 401	98.15 432	93.92 298	98.68 422	91.71 431	98.34 264	99.45 238

myMVS_eth3d		96.89 363	96.37 368	98.43 318	99.00 354	97.16 317	99.29 297	99.39 264	97.06 311	97.41 401	98.15 432	83.46 438	98.68 422	95.27 393	98.34 264	99.45 238

DP-MVS Recon		99.12 121	98.95 135	99.65 89	99.74 94	99.70 55	99.27 307	99.57 80	96.40 363	99.42 183	99.68 216	98.75 58	99.80 222	97.98 256	99.72 142	99.44 240

PatchMatch-RL		98.84 179	98.62 190	99.52 133	99.71 111	99.28 135	99.06 364	99.77 9	97.74 236	99.50 164	99.53 279	95.41 219	99.84 188	97.17 331	99.64 156	99.44 240

UBG		97.85 283	97.48 303	98.95 232	99.25 297	97.64 298	99.24 323	98.74 408	97.90 213	98.64 343	98.20 431	88.65 400	99.81 215	98.27 227	98.40 261	99.42 242

VDDNet		97.55 330	97.02 352	99.16 207	99.49 224	98.12 269	99.38 266	99.30 320	95.35 396	99.68 104	99.90 31	82.62 441	99.93 105	99.31 82	98.13 285	99.42 242

PCF-MVS	97.08 14	97.66 323	97.06 351	99.47 151	99.61 170	99.09 159	98.04 449	99.25 332	91.24 437	98.51 356	99.70 198	94.55 271	99.91 129	92.76 427	99.85 88	99.42 242
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ET-MVSNet_ETH3D		96.49 372	95.64 386	99.05 219	99.53 201	98.82 212	98.84 404	97.51 444	97.63 248	84.77 453	99.21 368	92.09 347	98.91 412	98.98 124	92.21 428	99.41 245

CS-MVS		99.50 28	99.48 20	99.54 119	99.76 76	99.42 112	99.90 1	99.55 93	98.56 112	99.78 75	99.70 198	98.65 71	99.79 228	99.65 39	99.78 128	99.41 245

HY-MVS	97.30 7	98.85 176	98.64 184	99.47 151	99.42 244	99.08 162	99.62 102	99.36 281	97.39 280	99.28 222	99.68 216	96.44 175	99.92 117	98.37 217	98.22 276	99.40 247

testing91		97.44 343	97.02 352	98.71 279	99.18 314	96.89 346	99.19 337	99.04 364	97.78 231	98.31 367	98.29 428	85.41 427	99.85 179	98.01 254	97.95 290	99.39 248

ETVMVS		97.50 336	96.90 356	99.29 189	99.23 301	98.78 217	99.32 286	98.90 386	97.52 264	98.56 353	98.09 437	84.72 432	99.69 272	97.86 265	97.88 294	99.39 248

tt0805		97.97 267	97.77 269	98.57 292	99.59 178	96.61 359	99.45 226	99.08 357	98.21 160	98.88 304	99.80 135	88.66 399	99.70 267	98.58 191	97.72 301	99.39 248

Fast-Effi-MVS+		98.70 193	98.43 206	99.51 138	99.51 210	99.28 135	99.52 170	99.47 207	96.11 383	99.01 281	99.34 341	96.20 183	99.84 188	97.88 262	98.82 238	99.39 248

testing11		97.50 336	97.10 349	98.71 279	99.20 308	96.91 344	99.29 297	98.82 396	97.89 214	98.21 375	98.40 423	85.63 425	99.83 201	98.45 209	98.04 288	99.37 252

CANet_DTU		98.97 155	98.87 152	99.25 196	99.33 272	98.42 255	99.08 359	99.30 320	99.16 31	99.43 180	99.75 176	95.27 226	99.97 27	98.56 197	99.95 21	99.36 253

testing99		97.36 346	96.94 355	98.63 285	99.18 314	96.70 352	99.30 292	98.93 376	97.71 238	98.23 372	98.26 429	84.92 430	99.84 188	98.04 253	97.85 297	99.35 254

EIA-MVS		99.18 99	99.09 99	99.45 154	99.49 224	99.18 146	99.67 71	99.53 117	97.66 246	99.40 193	99.44 309	98.10 104	99.81 215	98.94 131	99.62 159	99.35 254

EPMVS		97.82 293	97.65 284	98.35 325	98.88 372	95.98 378	99.49 204	94.71 460	97.57 255	99.26 232	99.48 299	92.46 341	99.71 261	97.87 264	99.08 213	99.35 254

CostFormer		97.72 311	97.73 276	97.71 379	99.15 328	94.02 422	99.54 160	99.02 367	94.67 411	99.04 278	99.35 337	92.35 344	99.77 236	98.50 203	97.94 291	99.34 257

BH-untuned		98.42 211	98.36 210	98.59 288	99.49 224	96.70 352	99.27 307	99.13 351	97.24 293	98.80 318	99.38 328	95.75 207	99.74 245	97.07 336	99.16 198	99.33 258

FE-MVS		98.48 206	98.17 221	99.40 164	99.54 200	98.96 181	99.68 68	98.81 398	95.54 394	99.62 136	99.70 198	93.82 302	99.93 105	97.35 318	99.46 172	99.32 259

PAPM		97.59 328	97.09 350	99.07 215	99.06 344	98.26 260	98.30 442	99.10 354	94.88 406	98.08 380	99.34 341	96.27 181	99.64 287	89.87 438	98.92 226	99.31 260

tpm2		97.44 343	97.34 329	97.74 378	99.15 328	94.36 419	99.45 226	98.94 375	93.45 425	98.90 301	99.44 309	91.35 366	99.59 297	97.31 319	98.07 287	99.29 261

UWE-MVS		97.58 329	97.29 337	98.48 305	99.09 338	96.25 372	99.01 379	96.61 453	97.86 217	99.19 248	99.01 388	88.72 396	99.90 142	97.38 316	98.69 245	99.28 262

FA-MVS(test-final)		98.75 189	98.53 201	99.41 163	99.55 193	99.05 167	99.80 25	99.01 368	96.59 349	99.58 147	99.59 255	95.39 220	99.90 142	97.78 275	99.49 171	99.28 262

MonoMVSNet		98.38 217	98.47 205	98.12 347	98.59 414	96.19 375	99.72 53	98.79 402	97.89 214	99.44 177	99.52 283	96.13 184	98.90 414	98.64 179	97.54 313	99.28 262

JIA-IIPM		97.50 336	97.02 352	98.93 236	98.73 397	97.80 289	99.30 292	98.97 372	91.73 435	98.91 299	94.86 453	95.10 235	99.71 261	97.58 295	97.98 289	99.28 262

UWE-MVS-28		97.36 346	97.24 342	97.75 376	98.84 381	94.44 416	99.24 323	97.58 443	97.98 206	99.00 285	99.00 389	91.35 366	99.53 305	93.75 413	98.39 262	99.27 266

kuosan		90.92 417	90.11 422	93.34 425	98.78 388	85.59 450	98.15 447	93.16 465	89.37 443	92.07 446	98.38 424	81.48 446	95.19 455	62.54 464	97.04 340	99.25 267

dp		97.75 305	97.80 263	97.59 387	99.10 335	93.71 426	99.32 286	98.88 389	96.48 356	99.08 269	99.55 270	92.67 332	99.82 210	96.52 362	98.58 251	99.24 268

myMVS_eth3d28		97.69 316	97.34 329	98.73 274	99.27 290	97.52 302	99.33 283	98.78 403	98.03 201	98.82 315	98.49 419	86.64 418	99.46 310	98.44 210	98.24 275	99.23 269

thisisatest0515		98.14 238	97.79 264	99.19 204	99.50 222	98.50 246	98.61 425	96.82 449	96.95 321	99.54 157	99.43 311	91.66 360	99.86 173	98.08 248	99.51 168	99.22 270

TESTMET0.1,1		97.55 330	97.27 341	98.40 321	98.93 365	96.53 361	98.67 419	97.61 442	96.96 319	98.64 343	99.28 356	88.63 402	99.45 312	97.30 320	99.38 177	99.21 271

testing222		97.16 356	96.50 365	99.16 207	99.16 324	98.47 251	99.27 307	98.66 419	97.71 238	98.23 372	98.15 432	82.28 444	99.84 188	97.36 317	97.66 303	99.18 272

CR-MVSNet		98.17 235	97.93 252	98.87 254	99.18 314	98.49 247	99.22 330	99.33 301	96.96 319	99.56 151	99.38 328	94.33 281	99.00 397	94.83 401	98.58 251	99.14 273

RPMNet		96.72 367	95.90 380	99.19 204	99.18 314	98.49 247	99.22 330	99.52 122	88.72 446	99.56 151	97.38 443	94.08 291	99.95 74	86.87 451	98.58 251	99.14 273

testgi		97.65 324	97.50 301	98.13 346	99.36 265	96.45 364	99.42 244	99.48 185	97.76 233	97.87 392	99.45 308	91.09 370	98.81 417	94.53 403	98.52 257	99.13 275

test-LLR		98.06 247	97.90 254	98.55 298	98.79 385	97.10 320	98.67 419	97.75 439	97.34 283	98.61 349	98.85 403	94.45 277	99.45 312	97.25 322	99.38 177	99.10 276

test-mter		97.49 341	97.13 348	98.55 298	98.79 385	97.10 320	98.67 419	97.75 439	96.65 339	98.61 349	98.85 403	88.23 406	99.45 312	97.25 322	99.38 177	99.10 276

IB-MVS	95.67 18	96.22 376	95.44 390	98.57 292	99.21 306	96.70 352	98.65 423	97.74 441	96.71 334	97.27 406	98.54 418	86.03 422	99.92 117	98.47 207	86.30 447	99.10 276
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
MAR-MVS		98.86 167	98.63 185	99.54 119	99.37 262	99.66 65	99.45 226	99.54 102	96.61 344	99.01 281	99.40 321	97.09 138	99.86 173	97.68 290	99.53 167	99.10 276
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
tpmrst		98.33 221	98.48 204	97.90 364	99.16 324	94.78 408	99.31 290	99.11 353	97.27 289	99.45 172	99.59 255	95.33 224	99.84 188	98.48 204	98.61 248	99.09 280

hse-mvs2		97.50 336	97.14 346	98.59 288	99.49 224	97.05 326	99.28 302	99.22 338	98.94 72	99.66 115	99.42 313	94.93 241	99.65 283	99.48 61	83.80 451	99.08 281

xiu_mvs_v1_base_debu		99.29 80	99.27 70	99.34 173	99.63 155	98.97 177	99.12 350	99.51 141	98.86 78	99.84 51	99.47 302	98.18 101	99.99 4	99.50 55	99.31 185	99.08 281

xiu_mvs_v1_base		99.29 80	99.27 70	99.34 173	99.63 155	98.97 177	99.12 350	99.51 141	98.86 78	99.84 51	99.47 302	98.18 101	99.99 4	99.50 55	99.31 185	99.08 281

xiu_mvs_v1_base_debi		99.29 80	99.27 70	99.34 173	99.63 155	98.97 177	99.12 350	99.51 141	98.86 78	99.84 51	99.47 302	98.18 101	99.99 4	99.50 55	99.31 185	99.08 281

COLMAP_ROB	97.56 6	98.86 167	98.75 168	99.17 206	99.88 13	98.53 238	99.34 281	99.59 69	97.55 258	98.70 333	99.89 38	95.83 201	99.90 142	98.10 243	99.90 55	99.08 281
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AUN-MVS		96.88 364	96.31 370	98.59 288	99.48 231	97.04 329	99.27 307	99.22 338	97.44 274	98.51 356	99.41 317	91.97 349	99.66 278	97.71 286	83.83 450	99.07 286

OpenMVS	96.50 16	98.47 207	98.12 228	99.52 133	99.04 349	99.53 95	99.82 16	99.72 11	94.56 413	98.08 380	99.88 49	94.73 257	99.98 18	97.47 309	99.76 134	99.06 287

ETV-MVS		99.26 87	99.21 80	99.40 164	99.46 234	99.30 132	99.56 141	99.52 122	98.52 116	99.44 177	99.27 359	98.41 90	99.86 173	99.10 112	99.59 162	99.04 288

PatchT		97.03 361	96.44 367	98.79 269	98.99 357	98.34 257	99.16 341	99.07 360	92.13 433	99.52 161	97.31 446	94.54 272	98.98 399	88.54 443	98.73 243	99.03 289

BH-w/o		98.00 262	97.89 258	98.32 328	99.35 266	96.20 374	99.01 379	98.90 386	96.42 361	98.38 363	99.00 389	95.26 228	99.72 255	96.06 372	98.61 248	99.03 289

Fast-Effi-MVS+-dtu		98.77 188	98.83 161	98.60 287	99.41 249	96.99 334	99.52 170	99.49 173	98.11 178	99.24 234	99.34 341	96.96 147	99.79 228	97.95 258	99.45 173	99.02 291

XVG-OURS-SEG-HR		98.69 194	98.62 190	98.89 248	99.71 111	97.74 290	99.12 350	99.54 102	98.44 127	99.42 183	99.71 194	94.20 285	99.92 117	98.54 201	98.90 232	99.00 292

XVG-OURS		98.73 192	98.68 176	98.88 250	99.70 116	97.73 291	98.92 396	99.55 93	98.52 116	99.45 172	99.84 89	95.27 226	99.91 129	98.08 248	98.84 236	99.00 292

tpm cat1		97.39 345	97.36 324	97.50 390	99.17 322	93.73 425	99.43 237	99.31 315	91.27 436	98.71 327	99.08 379	94.31 283	99.77 236	96.41 367	98.50 258	99.00 292

xiu_mvs_v2_base		99.26 87	99.25 74	99.29 189	99.53 201	98.91 194	99.02 374	99.45 229	98.80 88	99.71 98	99.26 361	98.94 32	99.98 18	99.34 78	99.23 194	98.98 295

PS-MVSNAJ		99.32 75	99.32 51	99.30 186	99.57 185	98.94 189	98.97 388	99.46 218	98.92 75	99.71 98	99.24 363	99.01 18	99.98 18	99.35 73	99.66 153	98.97 296

tpmvs		97.98 264	98.02 242	97.84 370	99.04 349	94.73 409	99.31 290	99.20 342	96.10 387	98.76 323	99.42 313	94.94 240	99.81 215	96.97 341	98.45 260	98.97 296

thres600view7		97.86 282	97.51 300	98.92 238	99.72 105	97.95 281	99.59 116	98.74 408	97.94 209	99.27 227	98.62 414	91.75 354	99.86 173	93.73 414	98.19 280	98.96 298

thres400		97.77 300	97.38 322	98.92 238	99.69 121	97.96 278	99.50 189	98.73 414	97.83 224	99.17 253	98.45 421	91.67 358	99.83 201	93.22 419	98.18 281	98.96 298

TR-MVS		97.76 301	97.41 320	98.82 263	99.06 344	97.87 285	98.87 402	98.56 422	96.63 343	98.68 335	99.22 365	92.49 337	99.65 283	95.40 390	97.79 299	98.95 300

test0.0.03 1		97.71 314	97.42 319	98.56 296	98.41 422	97.82 288	98.78 410	98.63 420	97.34 283	98.05 384	98.98 393	94.45 277	98.98 399	95.04 397	97.15 339	98.89 301

baseline2		97.87 280	97.55 293	98.82 263	99.18 314	98.02 273	99.41 249	96.58 454	96.97 318	96.51 420	99.17 370	93.43 308	99.57 299	97.71 286	99.03 217	98.86 302

cascas		97.69 316	97.43 318	98.48 305	98.60 412	97.30 309	98.18 446	99.39 264	92.96 428	98.41 361	98.78 410	93.77 304	99.27 350	98.16 237	98.61 248	98.86 302

1314		98.68 195	98.54 200	99.11 213	98.89 371	98.65 225	99.27 307	99.49 173	96.89 325	97.99 385	99.56 267	97.72 117	99.83 201	97.74 282	99.27 188	98.84 304

PS-MVSNAJss		98.92 158	98.92 139	98.90 244	98.78 388	98.53 238	99.78 32	99.54 102	98.07 186	99.00 285	99.76 171	99.01 18	99.37 330	99.13 107	97.23 335	98.81 305

VortexMVS		98.67 196	98.66 180	98.68 282	99.62 161	97.96 278	99.59 116	99.41 254	98.13 174	99.31 214	99.70 198	95.48 218	99.27 350	99.40 68	97.32 332	98.79 306

FC-MVSNet-test		98.75 189	98.62 190	99.15 211	99.08 341	99.45 109	99.86 11	99.60 63	98.23 157	98.70 333	99.82 103	96.80 157	99.22 361	99.07 115	96.38 351	98.79 306

reproduce_monomvs		97.89 277	97.87 259	97.96 359	99.51 210	95.45 392	99.60 109	99.25 332	99.17 30	98.85 312	99.49 293	89.29 391	99.64 287	99.35 73	96.31 354	98.78 308

nrg030		98.64 200	98.42 207	99.28 193	99.05 347	99.69 57	99.81 20	99.46 218	98.04 199	99.01 281	99.82 103	96.69 162	99.38 327	99.34 78	94.59 396	98.78 308

FIs		98.78 185	98.63 185	99.23 201	99.18 314	99.54 92	99.83 15	99.59 69	98.28 143	98.79 320	99.81 118	96.75 160	99.37 330	99.08 114	96.38 351	98.78 308

EU-MVSNet		97.98 264	98.03 240	97.81 374	98.72 399	96.65 357	99.66 78	99.66 28	98.09 181	98.35 365	99.82 103	95.25 229	98.01 435	97.41 314	95.30 382	98.78 308

jajsoiax		98.43 210	98.28 217	98.88 250	98.60 412	98.43 253	99.82 16	99.53 117	98.19 162	98.63 345	99.80 135	93.22 315	99.44 317	99.22 95	97.50 318	98.77 312

mvs_tets		98.40 216	98.23 219	98.91 242	98.67 405	98.51 244	99.66 78	99.53 117	98.19 162	98.65 342	99.81 118	92.75 324	99.44 317	99.31 82	97.48 322	98.77 312

Anonymous20231211		97.88 278	97.54 296	98.90 244	99.71 111	98.53 238	99.48 210	99.57 80	94.16 416	98.81 316	99.68 216	93.23 313	99.42 323	98.84 153	94.42 399	98.76 314

XXY-MVS		98.38 217	98.09 233	99.24 199	99.26 293	99.32 125	99.56 141	99.55 93	97.45 271	98.71 327	99.83 94	93.23 313	99.63 293	98.88 140	96.32 353	98.76 314

SSC-MVS3.2		97.34 348	97.15 345	97.93 361	99.02 351	95.76 383	99.48 210	99.58 74	97.62 250	99.09 267	99.53 279	87.95 409	99.27 350	96.42 365	95.66 373	98.75 316

v7n		97.87 280	97.52 298	98.92 238	98.76 395	98.58 234	99.84 12	99.46 218	96.20 374	98.91 299	99.70 198	94.89 245	99.44 317	96.03 373	93.89 409	98.75 316

PS-CasMVS		97.93 270	97.59 292	98.95 232	98.99 357	99.06 165	99.68 68	99.52 122	97.13 301	98.31 367	99.68 216	92.44 342	99.05 389	98.51 202	94.08 406	98.75 316

test_djsdf		98.67 196	98.57 197	98.98 227	98.70 402	98.91 194	99.88 4	99.46 218	97.55 258	99.22 239	99.88 49	95.73 208	99.28 347	99.03 119	97.62 306	98.75 316

Effi-MVS+-dtu		98.78 185	98.89 148	98.47 310	99.33 272	96.91 344	99.57 134	99.30 320	98.47 121	99.41 188	98.99 391	96.78 158	99.74 245	98.73 167	99.38 177	98.74 320

CP-MVSNet		98.09 243	97.78 267	99.01 223	98.97 362	99.24 141	99.67 71	99.46 218	97.25 291	98.48 359	99.64 235	93.79 303	99.06 388	98.63 181	94.10 405	98.74 320

VPA-MVSNet		98.29 225	97.95 249	99.30 186	99.16 324	99.54 92	99.50 189	99.58 74	98.27 145	99.35 208	99.37 331	92.53 336	99.65 283	99.35 73	94.46 397	98.72 322

PEN-MVS		97.76 301	97.44 314	98.72 276	98.77 393	98.54 237	99.78 32	99.51 141	97.06 311	98.29 370	99.64 235	92.63 333	98.89 415	98.09 244	93.16 419	98.72 322

WBMVS		97.74 307	97.50 301	98.46 311	99.24 299	97.43 305	99.21 332	99.42 251	97.45 271	98.96 292	99.41 317	88.83 395	99.23 357	98.94 131	96.02 359	98.71 324

VPNet		97.84 287	97.44 314	99.01 223	99.21 306	98.94 189	99.48 210	99.57 80	98.38 131	99.28 222	99.73 187	88.89 394	99.39 325	99.19 98	93.27 417	98.71 324

EI-MVSNet		98.67 196	98.67 177	98.68 282	99.35 266	97.97 276	99.50 189	99.38 272	96.93 324	99.20 245	99.83 94	97.87 111	99.36 334	98.38 215	97.56 311	98.71 324

WR-MVS		98.06 247	97.73 276	99.06 217	98.86 378	99.25 140	99.19 337	99.35 288	97.30 287	98.66 336	99.43 311	93.94 296	99.21 366	98.58 191	94.28 401	98.71 324

IterMVS-LS		98.46 208	98.42 207	98.58 291	99.59 178	98.00 274	99.37 268	99.43 249	96.94 323	99.07 270	99.59 255	97.87 111	99.03 392	98.32 224	95.62 374	98.71 324
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v144192		97.92 273	97.60 291	98.87 254	98.83 382	98.65 225	99.55 155	99.34 293	96.20 374	99.32 213	99.40 321	94.36 279	99.26 353	96.37 369	95.03 388	98.70 329

v1240		97.69 316	97.32 333	98.79 269	98.85 379	98.43 253	99.48 210	99.36 281	96.11 383	99.27 227	99.36 334	93.76 305	99.24 356	94.46 404	95.23 383	98.70 329

DTE-MVSNet		97.51 335	97.19 344	98.46 311	98.63 408	98.13 267	99.84 12	99.48 185	96.68 336	97.97 387	99.67 222	92.92 320	98.56 424	96.88 349	92.60 427	98.70 329

TranMVSNet+NR-MVSNet		97.93 270	97.66 283	98.76 273	98.78 388	98.62 230	99.65 84	99.49 173	97.76 233	98.49 358	99.60 253	94.23 284	98.97 406	98.00 255	92.90 421	98.70 329

v1921920		97.80 297	97.45 309	98.84 261	98.80 384	98.53 238	99.52 170	99.34 293	96.15 380	99.24 234	99.47 302	93.98 295	99.29 346	95.40 390	95.13 386	98.69 333

v1192		97.81 295	97.44 314	98.91 242	98.88 372	98.68 222	99.51 179	99.34 293	96.18 376	99.20 245	99.34 341	94.03 293	99.36 334	95.32 392	95.18 384	98.69 333

v2v482		98.06 247	97.77 269	98.92 238	98.90 370	98.82 212	99.57 134	99.36 281	96.65 339	99.19 248	99.35 337	94.20 285	99.25 354	97.72 285	94.97 389	98.69 333

UniMVSNet_NR-MVSNet		98.22 228	97.97 246	98.96 230	98.92 367	98.98 174	99.48 210	99.53 117	97.76 233	98.71 327	99.46 306	96.43 176	99.22 361	98.57 194	92.87 423	98.69 333

OurMVSNet-221017-0		97.88 278	97.77 269	98.19 340	98.71 401	96.53 361	99.88 4	99.00 369	97.79 229	98.78 321	99.94 6	91.68 357	99.35 337	97.21 324	96.99 342	98.69 333

tt0320		95.71 389	95.07 393	97.62 383	99.05 347	95.02 403	99.25 318	99.52 122	86.81 448	97.97 387	99.72 191	83.58 437	99.15 372	96.38 368	93.35 414	98.68 338

gg-mvs-nofinetune		96.17 379	95.32 391	98.73 274	98.79 385	98.14 266	99.38 266	94.09 461	91.07 439	98.07 383	91.04 459	89.62 389	99.35 337	96.75 352	99.09 212	98.68 338

v1144		97.98 264	97.69 280	98.85 260	98.87 375	98.66 224	99.54 160	99.35 288	96.27 369	99.23 238	99.35 337	94.67 262	99.23 357	96.73 353	95.16 385	98.68 338

DU-MVS		98.08 245	97.79 264	98.96 230	98.87 375	98.98 174	99.41 249	99.45 229	97.87 216	98.71 327	99.50 290	94.82 247	99.22 361	98.57 194	92.87 423	98.68 338

NR-MVSNet		97.97 267	97.61 290	99.02 222	98.87 375	99.26 138	99.47 219	99.42 251	97.63 248	97.08 413	99.50 290	95.07 236	99.13 377	97.86 265	93.59 412	98.68 338

LPG-MVS_test		98.22 228	98.13 227	98.49 303	99.33 272	97.05 326	99.58 126	99.55 93	97.46 268	99.24 234	99.83 94	92.58 334	99.72 255	98.09 244	97.51 316	98.68 338

LGP-MVS_train				98.49 303	99.33 272	97.05 326		99.55 93	97.46 268	99.24 234	99.83 94	92.58 334	99.72 255	98.09 244	97.51 316	98.68 338

LTVRE_ROB	97.16 12	98.02 257	97.90 254	98.40 321	99.23 301	96.80 350	99.70 58	99.60 63	97.12 303	98.18 377	99.70 198	91.73 356	99.72 255	98.39 214	97.45 323	98.68 338
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
tt0320-xc		95.31 395	94.59 399	97.45 391	98.92 367	94.73 409	99.20 335	99.31 315	86.74 449	97.23 407	99.72 191	81.14 448	98.95 409	97.08 335	91.98 429	98.67 346

IterMVS-SCA-FT		97.82 293	97.75 274	98.06 349	99.57 185	96.36 367	99.02 374	99.49 173	97.18 297	98.71 327	99.72 191	92.72 327	99.14 374	97.44 312	95.86 367	98.67 346

pm-mvs1		97.68 319	97.28 338	98.88 250	99.06 344	98.62 230	99.50 189	99.45 229	96.32 365	97.87 392	99.79 151	92.47 338	99.35 337	97.54 302	93.54 413	98.67 346

v10		97.85 283	97.52 298	98.86 257	98.99 357	98.67 223	99.75 42	99.41 254	95.70 392	98.98 288	99.41 317	94.75 256	99.23 357	96.01 375	94.63 395	98.67 346

HQP_MVS		98.27 227	98.22 220	98.44 316	99.29 285	96.97 336	99.39 261	99.47 207	98.97 69	99.11 261	99.61 250	92.71 329	99.69 272	97.78 275	97.63 304	98.67 346

plane_prior5								99.47 207					99.69 272	97.78 275	97.63 304	98.67 346

SixPastTwentyTwo		97.50 336	97.33 332	98.03 350	98.65 406	96.23 373	99.77 34	98.68 417	97.14 300	97.90 390	99.93 10	90.45 376	99.18 369	97.00 338	96.43 350	98.67 346

IterMVS		97.83 290	97.77 269	98.02 352	99.58 180	96.27 371	99.02 374	99.48 185	97.22 295	98.71 327	99.70 198	92.75 324	99.13 377	97.46 310	96.00 361	98.67 346
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	97.28 8	98.10 242	97.99 244	98.44 316	99.41 249	96.96 338	99.60 109	99.56 85	98.09 181	98.15 378	99.91 24	90.87 373	99.70 267	98.88 140	97.45 323	98.67 346
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v8		97.95 269	97.63 288	98.93 236	98.95 364	98.81 214	99.80 25	99.41 254	96.03 388	99.10 264	99.42 313	94.92 243	99.30 345	96.94 344	94.08 406	98.66 355

UniMVSNet (Re)		98.29 225	98.00 243	99.13 212	99.00 354	99.36 120	99.49 204	99.51 141	97.95 208	98.97 290	99.13 375	96.30 180	99.38 327	98.36 219	93.34 415	98.66 355

pmmvs6		96.53 371	96.09 376	97.82 373	98.69 403	95.47 391	99.37 268	99.47 207	93.46 424	97.41 401	99.78 158	87.06 417	99.33 340	96.92 347	92.70 425	98.65 357

K. test v3		97.10 359	96.79 359	98.01 353	98.72 399	96.33 368	99.87 8	97.05 446	97.59 252	96.16 425	99.80 135	88.71 397	99.04 390	96.69 356	96.55 348	98.65 357

our_test_3		97.65 324	97.68 281	97.55 388	98.62 409	94.97 405	98.84 404	99.30 320	96.83 330	98.19 376	99.34 341	97.01 145	99.02 394	95.00 398	96.01 360	98.64 359

YYNet1		95.36 393	94.51 401	97.92 362	97.89 428	97.10 320	99.10 358	99.23 336	93.26 426	80.77 458	99.04 384	92.81 323	98.02 434	94.30 405	94.18 403	98.64 359

MDA-MVSNet_test_wron		95.45 391	94.60 398	98.01 353	98.16 425	97.21 316	99.11 356	99.24 335	93.49 423	80.73 459	98.98 393	93.02 317	98.18 430	94.22 409	94.45 398	98.64 359

Baseline_NR-MVSNet		97.76 301	97.45 309	98.68 282	99.09 338	98.29 258	99.41 249	98.85 393	95.65 393	98.63 345	99.67 222	94.82 247	99.10 385	98.07 251	92.89 422	98.64 359

HQP4-MVS										98.66 336			99.64 287			98.64 359

HQP-MVS		98.02 257	97.90 254	98.37 324	99.19 311	96.83 347	98.98 385	99.39 264	98.24 154	98.66 336	99.40 321	92.47 338	99.64 287	97.19 328	97.58 309	98.64 359

ACMM	97.58 5	98.37 219	98.34 212	98.48 305	99.41 249	97.10 320	99.56 141	99.45 229	98.53 115	99.04 278	99.85 74	93.00 318	99.71 261	98.74 165	97.45 323	98.64 359
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs5		97.52 333	97.30 335	98.16 342	98.57 415	96.73 351	99.27 307	98.90 386	96.14 381	98.37 364	99.53 279	91.54 363	99.14 374	97.51 304	95.87 366	98.63 366

v148		97.79 299	97.55 293	98.50 302	98.74 396	97.72 293	99.54 160	99.33 301	96.26 370	98.90 301	99.51 287	94.68 261	99.14 374	97.83 269	93.15 420	98.63 366

MDA-MVSNet-bldmvs		94.96 398	93.98 405	97.92 362	98.24 424	97.27 311	99.15 344	99.33 301	93.80 419	80.09 460	99.03 385	88.31 405	97.86 439	93.49 417	94.36 400	98.62 368

TransMVSNet (Re)		97.15 357	96.58 363	98.86 257	99.12 330	98.85 204	99.49 204	98.91 384	95.48 395	97.16 411	99.80 135	93.38 309	99.11 383	94.16 410	91.73 430	98.62 368

lessismore_v0				97.79 375	98.69 403	95.44 394		94.75 459		95.71 429	99.87 60	88.69 398	99.32 342	95.89 376	94.93 391	98.62 368

MVSTER		98.49 205	98.32 214	99.00 225	99.35 266	99.02 169	99.54 160	99.38 272	97.41 278	99.20 245	99.73 187	93.86 301	99.36 334	98.87 143	97.56 311	98.62 368

GBi-Net		97.68 319	97.48 303	98.29 331	99.51 210	97.26 313	99.43 237	99.48 185	96.49 353	99.07 270	99.32 349	90.26 378	98.98 399	97.10 332	96.65 344	98.62 368

test1		97.68 319	97.48 303	98.29 331	99.51 210	97.26 313	99.43 237	99.48 185	96.49 353	99.07 270	99.32 349	90.26 378	98.98 399	97.10 332	96.65 344	98.62 368

FMVSNet1		96.84 365	96.36 369	98.29 331	99.32 279	97.26 313	99.43 237	99.48 185	95.11 400	98.55 354	99.32 349	83.95 435	98.98 399	95.81 378	96.26 355	98.62 368

ACMP	97.20 11	98.06 247	97.94 251	98.45 313	99.37 262	97.01 332	99.44 232	99.49 173	97.54 261	98.45 360	99.79 151	91.95 350	99.72 255	97.91 260	97.49 321	98.62 368
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMH+	97.24 10	97.92 273	97.78 267	98.32 328	99.46 234	96.68 356	99.56 141	99.54 102	98.41 129	97.79 396	99.87 60	90.18 382	99.66 278	98.05 252	97.18 338	98.62 368

ppachtmachnet_test		97.49 341	97.45 309	97.61 386	98.62 409	95.24 398	98.80 408	99.46 218	96.11 383	98.22 374	99.62 246	96.45 174	98.97 406	93.77 412	95.97 365	98.61 377

OPM-MVS		98.19 232	98.10 230	98.45 313	98.88 372	97.07 324	99.28 302	99.38 272	98.57 111	99.22 239	99.81 118	92.12 346	99.66 278	98.08 248	97.54 313	98.61 377
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
WR-MVS_H		98.13 239	97.87 259	98.90 244	99.02 351	98.84 206	99.70 58	99.59 69	97.27 289	98.40 362	99.19 369	95.53 215	99.23 357	98.34 221	93.78 411	98.61 377

MIMVSNet1		95.51 390	95.04 395	96.92 407	97.38 436	95.60 385	99.52 170	99.50 161	93.65 421	96.97 416	99.17 370	85.28 429	96.56 451	88.36 444	95.55 377	98.60 380

N_pmnet		94.95 399	95.83 382	92.31 429	98.47 419	79.33 461	99.12 350	92.81 467	93.87 418	97.68 397	99.13 375	93.87 300	99.01 396	91.38 433	96.19 356	98.59 381

FMVSNet2		97.72 311	97.36 324	98.80 268	99.51 210	98.84 206	99.45 226	99.42 251	96.49 353	98.86 311	99.29 354	90.26 378	98.98 399	96.44 364	96.56 347	98.58 382

anonymousdsp		98.44 209	98.28 217	98.94 234	98.50 418	98.96 181	99.77 34	99.50 161	97.07 309	98.87 307	99.77 167	94.76 255	99.28 347	98.66 177	97.60 307	98.57 383

FMVSNet3		98.03 255	97.76 273	98.84 261	99.39 257	98.98 174	99.40 257	99.38 272	96.67 337	99.07 270	99.28 356	92.93 319	98.98 399	97.10 332	96.65 344	98.56 384

XVG-ACMP-BASELINE		97.83 290	97.71 278	98.20 339	99.11 332	96.33 368	99.41 249	99.52 122	98.06 190	99.05 277	99.50 290	89.64 388	99.73 251	97.73 283	97.38 330	98.53 385

Patchmtry		97.75 305	97.40 321	98.81 266	99.10 335	98.87 200	99.11 356	99.33 301	94.83 408	98.81 316	99.38 328	94.33 281	99.02 394	96.10 371	95.57 376	98.53 385

miper_lstm_enhance		98.00 262	97.91 253	98.28 335	99.34 271	97.43 305	98.88 400	99.36 281	96.48 356	98.80 318	99.55 270	95.98 191	98.91 412	97.27 321	95.50 379	98.51 387

USDC		97.34 348	97.20 343	97.75 376	99.07 342	95.20 399	98.51 432	99.04 364	97.99 205	98.31 367	99.86 67	89.02 392	99.55 303	95.67 384	97.36 331	98.49 388

c3_l		98.12 241	98.04 239	98.38 323	99.30 281	97.69 297	98.81 407	99.33 301	96.67 337	98.83 313	99.34 341	97.11 137	98.99 398	97.58 295	95.34 381	98.48 389

CLD-MVS		98.16 236	98.10 230	98.33 326	99.29 285	96.82 349	98.75 413	99.44 238	97.83 224	99.13 257	99.55 270	92.92 320	99.67 275	98.32 224	97.69 302	98.48 389
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
eth_miper_zixun_eth		98.05 252	97.96 247	98.33 326	99.26 293	97.38 307	98.56 430	99.31 315	96.65 339	98.88 304	99.52 283	96.58 167	99.12 382	97.39 315	95.53 378	98.47 391

Anonymous20231206		96.22 376	96.03 377	96.79 410	97.31 439	94.14 421	99.63 97	99.08 357	96.17 377	97.04 414	99.06 382	93.94 296	97.76 441	86.96 450	95.06 387	98.47 391

FMVSNet5		96.43 374	96.19 373	97.15 397	99.11 332	95.89 380	99.32 286	99.52 122	94.47 415	98.34 366	99.07 380	87.54 414	97.07 447	92.61 428	95.72 371	98.47 391

cl____		98.01 260	97.84 262	98.55 298	99.25 297	97.97 276	98.71 417	99.34 293	96.47 358	98.59 352	99.54 275	95.65 211	99.21 366	97.21 324	95.77 368	98.46 394

DIV-MVS_self_test		98.01 260	97.85 261	98.48 305	99.24 299	97.95 281	98.71 417	99.35 288	96.50 352	98.60 351	99.54 275	95.72 209	99.03 392	97.21 324	95.77 368	98.46 394

pmmvs4		98.13 239	97.90 254	98.81 266	98.61 411	98.87 200	98.99 382	99.21 341	96.44 359	99.06 275	99.58 259	95.90 198	99.11 383	97.18 330	96.11 358	98.46 394

cl22		97.85 283	97.64 287	98.48 305	99.09 338	97.87 285	98.60 427	99.33 301	97.11 306	98.87 307	99.22 365	92.38 343	99.17 371	98.21 231	95.99 362	98.42 397

V42		98.06 247	97.79 264	98.86 257	98.98 360	98.84 206	99.69 62	99.34 293	96.53 351	99.30 218	99.37 331	94.67 262	99.32 342	97.57 299	94.66 394	98.42 397

PVSNet_BlendedMVS		98.86 167	98.80 162	99.03 221	99.76 76	98.79 215	99.28 302	99.91 3	97.42 277	99.67 110	99.37 331	97.53 119	99.88 162	98.98 124	97.29 333	98.42 397

UnsupCasMVSNet_eth		96.44 373	96.12 374	97.40 393	98.65 406	95.65 384	99.36 273	99.51 141	97.13 301	96.04 427	98.99 391	88.40 404	98.17 431	96.71 354	90.27 438	98.40 400

TinyColmap		97.12 358	96.89 357	97.83 371	99.07 342	95.52 390	98.57 428	98.74 408	97.58 254	97.81 395	99.79 151	88.16 407	99.56 301	95.10 395	97.21 336	98.39 401

miper_ehance_all_eth		98.18 234	98.10 230	98.41 319	99.23 301	97.72 293	98.72 416	99.31 315	96.60 347	98.88 304	99.29 354	97.29 129	99.13 377	97.60 293	95.99 362	98.38 402

thres100view900		97.76 301	97.45 309	98.69 281	99.72 105	97.86 287	99.59 116	98.74 408	97.93 210	99.26 232	98.62 414	91.75 354	99.83 201	93.22 419	98.18 281	98.37 403

tfpn200view9		97.72 311	97.38 322	98.72 276	99.69 121	97.96 278	99.50 189	98.73 414	97.83 224	99.17 253	98.45 421	91.67 358	99.83 201	93.22 419	98.18 281	98.37 403

test_fmvs2		97.25 353	97.30 335	97.09 401	99.43 242	93.31 432	99.73 51	98.87 391	98.83 82	99.28 222	99.80 135	84.45 433	99.66 278	97.88 262	97.45 323	98.30 405

miper_enhance_ethall		98.16 236	98.08 234	98.41 319	98.96 363	97.72 293	98.45 434	99.32 311	96.95 321	98.97 290	99.17 370	97.06 141	99.22 361	97.86 265	95.99 362	98.29 406

tfpnnormal		97.84 287	97.47 306	98.98 227	99.20 308	99.22 143	99.64 91	99.61 56	96.32 365	98.27 371	99.70 198	93.35 312	99.44 317	95.69 382	95.40 380	98.27 407

test20.03		96.12 380	95.96 379	96.63 411	97.44 435	95.45 392	99.51 179	99.38 272	96.55 350	96.16 425	99.25 362	93.76 305	96.17 452	87.35 449	94.22 402	98.27 407

test_method		91.10 415	91.36 417	90.31 435	95.85 448	73.72 468	94.89 456	99.25 332	68.39 459	95.82 428	99.02 387	80.50 449	98.95 409	93.64 415	94.89 393	98.25 409

ITE_SJBPF				98.08 348	99.29 285	96.37 366		98.92 379	98.34 137	98.83 313	99.75 176	91.09 370	99.62 294	95.82 377	97.40 329	98.25 409

KD-MVS_self_test		95.00 397	94.34 402	96.96 404	97.07 444	95.39 395	99.56 141	99.44 238	95.11 400	97.13 412	97.32 445	91.86 352	97.27 446	90.35 437	81.23 454	98.23 411

mmtdpeth		96.95 362	96.71 361	97.67 381	99.33 272	94.90 407	99.89 2	99.28 326	98.15 167	99.72 96	98.57 417	86.56 420	99.90 142	99.82 27	89.02 442	98.20 412

EG-PatchMatch MVS		95.97 383	95.69 384	96.81 409	97.78 430	92.79 435	99.16 341	98.93 376	96.16 378	94.08 438	99.22 365	82.72 440	99.47 308	95.67 384	97.50 318	98.17 413

mvs5depth		96.66 368	96.22 372	97.97 357	97.00 445	96.28 370	98.66 422	99.03 366	96.61 344	96.93 417	99.79 151	87.20 416	99.47 308	96.65 360	94.13 404	98.16 414

D2MVS		98.41 213	98.50 203	98.15 345	99.26 293	96.62 358	99.40 257	99.61 56	97.71 238	98.98 288	99.36 334	96.04 188	99.67 275	98.70 170	97.41 328	98.15 415

APD_test1		95.87 384	96.49 366	94.00 422	99.53 201	84.01 451	99.54 160	99.32 311	95.91 390	97.99 385	99.85 74	85.49 426	99.88 162	91.96 430	98.84 236	98.12 416

ttmdpeth		97.80 297	97.63 288	98.29 331	98.77 393	97.38 307	99.64 91	99.36 281	98.78 92	96.30 423	99.58 259	92.34 345	99.39 325	98.36 219	95.58 375	98.10 417

TDRefinement		95.42 392	94.57 400	97.97 357	89.83 463	96.11 377	99.48 210	98.75 405	96.74 332	96.68 419	99.88 49	88.65 400	99.71 261	98.37 217	82.74 452	98.09 418

Anonymous20240521		96.20 378	95.89 381	97.13 399	97.72 433	94.96 406	99.79 31	99.29 324	93.01 427	97.20 410	99.03 385	89.69 387	98.36 428	91.16 434	96.13 357	98.07 419

API-MVS		99.04 143	99.03 110	99.06 217	99.40 254	99.31 129	99.55 155	99.56 85	98.54 114	99.33 212	99.39 325	98.76 55	99.78 234	96.98 340	99.78 128	98.07 419

new_pmnet		96.38 375	96.03 377	97.41 392	98.13 426	95.16 402	99.05 366	99.20 342	93.94 417	97.39 404	98.79 409	91.61 362	99.04 390	90.43 436	95.77 368	98.05 421

thres200		97.61 327	97.28 338	98.62 286	99.64 151	98.03 272	99.26 316	98.74 408	97.68 243	99.09 267	98.32 427	91.66 360	99.81 215	92.88 424	98.22 276	98.03 422

KD-MVS_2432*1600		94.62 400	93.72 408	97.31 394	97.19 442	95.82 381	98.34 438	99.20 342	95.00 404	97.57 398	98.35 425	87.95 409	98.10 432	92.87 425	77.00 457	98.01 423

miper_refine_blended		94.62 400	93.72 408	97.31 394	97.19 442	95.82 381	98.34 438	99.20 342	95.00 404	97.57 398	98.35 425	87.95 409	98.10 432	92.87 425	77.00 457	98.01 423

DeepMVS_CX				93.34 425	99.29 285	82.27 454		99.22 338	85.15 451	96.33 422	99.05 383	90.97 372	99.73 251	93.57 416	97.77 300	98.01 423

MVStest1		96.08 382	95.48 387	97.89 365	98.93 365	96.70 352	99.56 141	99.35 288	92.69 431	91.81 448	99.46 306	89.90 384	98.96 408	95.00 398	92.61 426	98.00 426

CL-MVSNet_self_test		94.49 402	93.97 406	96.08 416	96.16 447	93.67 428	98.33 440	99.38 272	95.13 398	97.33 405	98.15 432	92.69 331	96.57 450	88.67 442	79.87 455	97.99 427

GG-mvs-BLEND				98.45 313	98.55 416	98.16 264	99.43 237	93.68 462		97.23 407	98.46 420	89.30 390	99.22 361	95.43 389	98.22 276	97.98 428

pmmvs3		94.09 406	93.25 412	96.60 412	94.76 457	94.49 415	98.92 396	98.18 434	89.66 440	96.48 421	98.06 438	86.28 421	97.33 445	89.68 439	87.20 446	97.97 429

LF4IMVS		97.52 333	97.46 308	97.70 380	98.98 360	95.55 387	99.29 297	98.82 396	98.07 186	98.66 336	99.64 235	89.97 383	99.61 295	97.01 337	96.68 343	97.94 430

test_0402		96.64 369	96.24 371	97.85 368	98.85 379	96.43 365	99.44 232	99.26 330	93.52 422	96.98 415	99.52 283	88.52 403	99.20 368	92.58 429	97.50 318	97.93 431

MVP-Stereo		97.81 295	97.75 274	97.99 356	97.53 434	96.60 360	98.96 389	98.85 393	97.22 295	97.23 407	99.36 334	95.28 225	99.46 310	95.51 386	99.78 128	97.92 432
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MS-PatchMatch		97.24 355	97.32 333	96.99 402	98.45 420	93.51 431	98.82 406	99.32 311	97.41 278	98.13 379	99.30 352	88.99 393	99.56 301	95.68 383	99.80 119	97.90 433

mvsany_test3		93.77 407	93.45 411	94.74 420	95.78 449	88.01 446	99.64 91	98.25 429	98.28 143	94.31 437	97.97 439	68.89 454	98.51 426	97.50 305	90.37 437	97.71 434

ambc				93.06 428	92.68 459	82.36 453	98.47 433	98.73 414		95.09 434	97.41 442	55.55 460	99.10 385	96.42 365	91.32 431	97.71 434

test_vis1_rt		95.81 386	95.65 385	96.32 415	99.67 128	91.35 442	99.49 204	96.74 451	98.25 152	95.24 430	98.10 436	74.96 451	99.90 142	99.53 51	98.85 235	97.70 436

new-patchmatchnet		94.48 403	94.08 404	95.67 418	95.08 455	92.41 437	99.18 339	99.28 326	94.55 414	93.49 441	97.37 444	87.86 412	97.01 448	91.57 432	88.36 443	97.61 437

pmmvs-eth3d		95.34 394	94.73 397	97.15 397	95.53 452	95.94 379	99.35 278	99.10 354	95.13 398	93.55 440	97.54 441	88.15 408	97.91 437	94.58 402	89.69 441	97.61 437

UnsupCasMVSNet_bld		93.53 408	92.51 414	96.58 413	97.38 436	93.82 423	98.24 443	99.48 185	91.10 438	93.10 442	96.66 448	74.89 452	98.37 427	94.03 411	87.71 445	97.56 439

PM-MVS		92.96 411	92.23 415	95.14 419	95.61 450	89.98 445	99.37 268	98.21 432	94.80 409	95.04 435	97.69 440	65.06 455	97.90 438	94.30 405	89.98 440	97.54 440

EGC-MVSNET		82.80 424	77.86 430	97.62 383	97.91 427	96.12 376	99.33 283	99.28 326	8.40 467	25.05 468	99.27 359	84.11 434	99.33 340	89.20 440	98.22 276	97.42 441

test_f		91.90 414	91.26 418	93.84 423	95.52 453	85.92 448	99.69 62	98.53 425	95.31 397	93.87 439	96.37 450	55.33 461	98.27 429	95.70 381	90.98 435	97.32 442

test_fmvs3		92.10 413	91.77 416	93.08 427	96.19 446	86.25 447	99.82 16	98.62 421	96.65 339	95.19 433	96.90 447	55.05 462	95.93 454	96.63 361	90.92 436	97.06 443

LCM-MVSNet		86.80 422	85.22 426	91.53 432	87.81 464	80.96 458	98.23 445	98.99 370	71.05 457	90.13 452	96.51 449	48.45 465	96.88 449	90.51 435	85.30 448	96.76 444

OpenMVS_ROB	92.34 20	94.38 404	93.70 410	96.41 414	97.38 436	93.17 433	99.06 364	98.75 405	86.58 450	94.84 436	98.26 429	81.53 445	99.32 342	89.01 441	97.87 295	96.76 444

WB-MVS		93.10 410	94.10 403	90.12 436	95.51 454	81.88 456	99.73 51	99.27 329	95.05 403	93.09 443	98.91 402	94.70 260	91.89 460	76.62 458	94.02 408	96.58 446

SSC-MVS		92.73 412	93.73 407	89.72 437	95.02 456	81.38 457	99.76 37	99.23 336	94.87 407	92.80 444	98.93 398	94.71 259	91.37 461	74.49 460	93.80 410	96.42 447

CMPMVS	69.68 23	94.13 405	94.90 396	91.84 430	97.24 440	80.01 460	98.52 431	99.48 185	89.01 444	91.99 447	99.67 222	85.67 424	99.13 377	95.44 388	97.03 341	96.39 448
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testf1		90.42 418	90.68 419	89.65 438	97.78 430	73.97 466	99.13 347	98.81 398	89.62 441	91.80 449	98.93 398	62.23 458	98.80 418	86.61 452	91.17 432	96.19 449

APD_test2		90.42 418	90.68 419	89.65 438	97.78 430	73.97 466	99.13 347	98.81 398	89.62 441	91.80 449	98.93 398	62.23 458	98.80 418	86.61 452	91.17 432	96.19 449

WB-MVSnew		97.65 324	97.65 284	97.63 382	98.78 388	97.62 299	99.13 347	98.33 427	97.36 282	99.07 270	98.94 397	95.64 212	99.15 372	92.95 423	98.68 246	96.12 451

PMMVS2		86.87 421	85.37 425	91.35 433	90.21 462	83.80 452	98.89 399	97.45 445	83.13 454	91.67 451	95.03 451	48.49 464	94.70 457	85.86 454	77.62 456	95.54 452

tmp_tt		82.80 424	81.52 427	86.66 440	66.61 470	68.44 469	92.79 459	97.92 436	68.96 458	80.04 461	99.85 74	85.77 423	96.15 453	97.86 265	43.89 463	95.39 453

FPMVS		84.93 423	85.65 424	82.75 444	86.77 465	63.39 470	98.35 437	98.92 379	74.11 456	83.39 455	98.98 393	50.85 463	92.40 459	84.54 455	94.97 389	92.46 454

Gipuma		90.99 416	90.15 421	93.51 424	98.73 397	90.12 444	93.98 457	99.45 229	79.32 455	92.28 445	94.91 452	69.61 453	97.98 436	87.42 448	95.67 372	92.45 455
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ANet_high		77.30 428	74.86 432	84.62 442	75.88 468	77.61 462	97.63 453	93.15 466	88.81 445	64.27 463	89.29 460	36.51 467	83.93 465	75.89 459	52.31 462	92.33 456

test_vis3_rt		87.04 420	85.81 423	90.73 434	93.99 458	81.96 455	99.76 37	90.23 469	92.81 430	81.35 457	91.56 457	40.06 466	99.07 387	94.27 407	88.23 444	91.15 457

MVE	76.82 21	76.91 429	74.31 433	84.70 441	85.38 467	76.05 465	96.88 455	93.17 464	67.39 460	71.28 462	89.01 461	21.66 472	87.69 462	71.74 461	72.29 459	90.35 458
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 430	74.97 431	79.01 446	70.98 469	55.18 471	93.37 458	98.21 432	65.08 463	61.78 464	93.83 454	21.74 471	92.53 458	78.59 456	91.12 434	89.34 459
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		80.02 427	79.22 429	82.43 445	91.19 460	76.40 463	97.55 454	92.49 468	66.36 462	83.01 456	91.27 458	64.63 456	85.79 464	65.82 463	60.65 461	85.08 460

E-PMN		80.61 426	79.88 428	82.81 443	90.75 461	76.38 464	97.69 451	95.76 456	66.44 461	83.52 454	92.25 456	62.54 457	87.16 463	68.53 462	61.40 460	84.89 461

test123		39.01 433	42.50 435	28.53 448	39.17 471	20.91 473	98.75 413	19.17 473	19.83 466	38.57 465	66.67 463	33.16 468	15.42 467	37.50 467	29.66 465	49.26 462

testmvs		39.17 432	43.78 434	25.37 449	36.04 472	16.84 474	98.36 436	26.56 471	20.06 465	38.51 466	67.32 462	29.64 469	15.30 468	37.59 466	39.90 464	43.98 463

wuyk23d		40.18 431	41.29 436	36.84 447	86.18 466	49.12 472	79.73 460	22.81 472	27.64 464	25.46 467	28.45 467	21.98 470	48.89 466	55.80 465	23.56 466	12.51 464

mmdepth		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

monomultidepth		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

test_blank		0.13 437	0.17 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	1.57 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet_test		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

DCPMVS		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

cdsmvs_eth3d_5k		24.64 434	32.85 437	0.00 450	0.00 473	0.00 475	0.00 461	99.51 141	0.00 468	0.00 469	99.56 267	96.58 167	0.00 469	0.00 468	0.00 467	0.00 465

pcd_1.5k_mvsjas		8.27 436	11.03 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	99.01 18	0.00 469	0.00 468	0.00 467	0.00 465

sosnet-low-res		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uncertanet		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

Regformer		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

ab-mvs-re		8.30 435	11.06 438	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	99.58 259	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet		0.02 438	0.03 441	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.27 469	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

WAC-MVS						97.16 317								95.47 387

FOURS1					99.91 1	99.93 1	99.87 8	99.56 85	99.10 42	99.81 63

test_one_0601					99.81 52	99.88 9		99.49 173	98.97 69	99.65 124	99.81 118	99.09 14

eth-test2					0.00 473

eth-test					0.00 473

ZD-MVS					99.71 111	99.79 36		99.61 56	96.84 328	99.56 151	99.54 275	98.58 75	99.96 39	96.93 345	99.75 136

test_241102_ONE					99.84 35	99.90 2		99.48 185	99.07 52	99.91 29	99.74 181	99.20 7	99.76 240

9.14			99.10 94		99.72 105		99.40 257	99.51 141	97.53 262	99.64 129	99.78 158	98.84 44	99.91 129	97.63 291	99.82 111

save fliter					99.76 76	99.59 82	99.14 346	99.40 261	99.00 61

test0726					99.85 28	99.89 5	99.62 102	99.50 161	99.10 42	99.86 48	99.82 103	98.94 32

test_part2					99.81 52	99.83 20				99.77 79

sam_mvs												94.72 258

MTGPA								99.47 207

test_post1							99.23 326				65.14 465	94.18 288	99.71 261	97.58 295

test_post											65.99 464	94.65 265	99.73 251

patchmatchnet-post											98.70 412	94.79 250	99.74 245

MTMP							99.54 160	98.88 389

gm-plane-assit					98.54 417	92.96 434			94.65 412		99.15 373		99.64 287	97.56 300

TEST9					99.67 128	99.65 69	99.05 366	99.41 254	96.22 373	98.95 294	99.49 293	98.77 54	99.91 129

test_8					99.67 128	99.61 79	99.03 371	99.41 254	96.28 367	98.93 297	99.48 299	98.76 55	99.91 129

agg_prior					99.67 128	99.62 77		99.40 261		98.87 307			99.91 129

test_prior4						99.56 88	98.99 382

test_prior2							98.96 389		98.34 137	99.01 281	99.52 283	98.68 67		97.96 257	99.74 139

旧先验2							98.96 389		96.70 335	99.47 169			99.94 87	98.19 233

新几何2							99.01 379

原ACMM2							98.95 392

testdata2													99.95 74	96.67 357

segment_acmp												98.96 25

testdata1							98.85 403		98.32 140

plane_prior7					99.29 285	97.03 331

plane_prior6					99.27 290	96.98 335						92.71 329

plane_prior4											99.61 250

plane_prior3						97.00 333			98.69 101	99.11 261

plane_prior2							99.39 261		98.97 69

plane_prior1					99.26 293

plane_prior						96.97 336	99.21 332		98.45 124						97.60 307

n2								0.00 474

nn								0.00 474

door-mid								98.05 435

test11								99.35 288

door								97.92 436

HQP5-MVS						96.83 347

HQP-NCC					99.19 311		98.98 385		98.24 154	98.66 336

ACMP_Plane					99.19 311		98.98 385		98.24 154	98.66 336

BP-MVS														97.19 328

HQP3-MVS								99.39 264							97.58 309

HQP2-MVS												92.47 338

NP-MVS					99.23 301	96.92 343					99.40 321

MDTV_nov1_ep13			98.32 214		99.11 332	94.44 416	99.27 307	98.74 408	97.51 265	99.40 193	99.62 246	94.78 251	99.76 240	97.59 294	98.81 240

ACMMP++_ref															97.19 337

ACMMP++															97.43 327

Test By Simon												98.75 58

High-resolution multi-view benchmark