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 99	99.01 114	99.61 101	99.81 49	98.86 195	99.65 83	99.64 38	99.39 18	99.97 21	99.94 6	93.20 299	99.98 16	99.55 46	99.91 42	99.99 1

fmvsm_s_conf0.1_n_a		99.26 84	99.06 98	99.85 37	99.52 190	99.62 76	99.54 157	99.62 46	98.69 98	99.99 2	99.96 1	94.47 260	99.94 84	99.88 22	99.92 35	99.98 2

test_vis1_n_1920		98.63 186	98.40 193	99.31 170	99.86 21	97.94 272	99.67 70	99.62 46	99.43 13	99.99 2	99.91 23	87.29 398	100.00 1	99.92 20	99.92 35	99.98 2

fmvsm_s_conf0.1_n		99.29 78	99.10 91	99.86 29	99.70 113	99.65 68	99.53 166	99.62 46	98.74 92	99.99 2	99.95 3	94.53 258	99.94 84	99.89 21	99.96 14	99.97 4

test_fmvsmconf0.1_n		99.55 19	99.45 26	99.86 29	99.44 224	99.65 68	99.50 184	99.61 54	99.45 10	99.87 42	99.92 17	97.31 127	99.97 25	99.95 12	99.99 1	99.97 4

test_vis1_n		97.92 257	97.44 297	99.34 163	99.53 184	98.08 259	99.74 47	99.49 164	99.15 30	100.00 1	99.94 6	79.51 433	99.98 16	99.88 22	99.76 131	99.97 4

fmvsm_s_conf0.5_n_8		99.54 20	99.42 28	99.89 8	99.83 41	99.74 48	99.51 176	99.62 46	99.46 7	99.99 2	99.90 30	96.60 155	99.98 16	99.95 12	99.95 19	99.96 7

test_fmvsmconf_n		99.70 3	99.64 4	99.87 18	99.80 55	99.66 64	99.48 201	99.64 38	99.45 10	99.92 26	99.92 17	98.62 73	99.99 4	99.96 10	99.99 1	99.96 7

test_fmvs1_n		98.41 197	98.14 209	99.21 191	99.82 45	97.71 285	99.74 47	99.49 164	99.32 23	99.99 2	99.95 3	85.32 411	99.97 25	99.82 25	99.84 94	99.96 7

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 33	99.82 26	99.54 157	99.66 28	99.46 7	99.98 10	99.89 36	97.27 130	99.99 4	99.97 1	99.95 19	99.95 10

fmvsm_s_conf0.5_n_3		99.37 62	99.20 80	99.87 18	99.75 83	99.70 54	99.48 201	99.66 28	99.45 10	99.99 2	99.93 10	94.64 250	99.97 25	99.94 17	99.97 8	99.95 10

fmvsm_s_conf0.5_n_a		99.56 18	99.47 22	99.85 37	99.83 41	99.64 74	99.52 167	99.65 35	99.10 40	99.98 10	99.92 17	97.35 126	99.96 37	99.94 17	99.92 35	99.95 10

fmvsm_s_conf0.5_n		99.51 25	99.40 34	99.85 37	99.84 33	99.65 68	99.51 176	99.67 23	99.13 33	99.98 10	99.92 17	96.60 155	99.96 37	99.95 12	99.96 14	99.95 10

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 37	99.86 21	99.61 78	99.56 138	99.63 42	99.48 3	99.98 10	99.83 87	98.75 58	99.99 4	99.97 1	99.96 14	99.94 14

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 37	99.84 33	99.63 75	99.56 138	99.63 42	99.47 4	99.98 10	99.82 96	98.75 58	99.99 4	99.97 1	99.97 8	99.94 14

MM		99.40 58	99.28 65	99.74 72	99.67 125	99.31 127	99.52 167	98.87 374	99.55 1	99.74 85	99.80 124	96.47 162	99.98 16	99.97 1	99.97 8	99.94 14

test_fmvsmconf0.01_n		99.22 92	99.03 104	99.79 60	98.42 404	99.48 103	99.55 152	99.51 134	99.39 18	99.78 71	99.93 10	94.80 234	99.95 71	99.93 19	99.95 19	99.94 14

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 66	99.38 242	99.37 115	99.58 124	99.62 46	99.41 17	99.87 42	99.92 17	98.81 47	100.00 1	99.97 1	99.93 29	99.94 14

fmvsm_s_conf0.5_n_2		99.32 73	99.13 87	99.89 8	99.80 55	99.77 42	99.44 221	99.58 72	99.47 4	99.99 2	99.93 10	94.04 275	99.96 37	99.96 10	99.93 29	99.93 19

fmvsm_s_conf0.5_n_6		99.54 20	99.44 27	99.85 37	99.51 193	99.67 61	99.50 184	99.64 38	99.43 13	99.98 10	99.78 143	97.26 132	99.95 71	99.95 12	99.93 29	99.92 20

fmvsm_s_conf0.5_n_5		99.37 62	99.21 78	99.86 29	99.80 55	99.68 57	99.42 233	99.61 54	99.37 20	99.97 21	99.86 63	94.96 223	99.99 4	99.97 1	99.93 29	99.92 20

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 63	99.84 33	99.44 108	99.58 124	99.69 18	99.43 13	99.98 10	99.91 23	98.62 73	100.00 1	99.97 1	99.95 19	99.90 22

test_fmvs1		98.88 150	98.79 151	99.16 196	99.69 118	97.61 289	99.55 152	99.49 164	99.32 23	99.98 10	99.91 23	91.41 347	99.96 37	99.82 25	99.92 35	99.90 22

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 69	99.89 5	99.75 42	99.56 82	99.02 53	99.88 36	99.85 70	99.18 10	99.96 37	99.22 89	99.92 35	99.90 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
patch_mono-2		99.26 84	99.62 5	98.16 326	99.81 49	94.59 398	99.52 167	99.64 38	99.33 22	99.73 87	99.90 30	99.00 22	99.99 4	99.69 31	99.98 4	99.89 25

MSC_two_6792asdad				99.87 18	99.51 193	99.76 43		99.33 284					99.96 37	98.87 131	99.84 94	99.89 25

No_MVS				99.87 18	99.51 193	99.76 43		99.33 284					99.96 37	98.87 131	99.84 94	99.89 25

IU-MVS					99.84 33	99.88 9		99.32 294	98.30 138	99.84 49				98.86 136	99.85 86	99.89 25

UA-Net		99.42 51	99.29 62	99.80 57	99.62 154	99.55 89	99.50 184	99.70 15	98.79 86	99.77 75	99.96 1	97.45 121	99.96 37	98.92 124	99.90 53	99.89 25

CHOSEN 1792x2688		99.19 93	99.10 91	99.45 148	99.89 8	98.52 232	99.39 250	99.94 1	98.73 93	99.11 246	99.89 36	95.50 202	99.94 84	99.50 53	99.97 8	99.89 25

test_241102_TWO								99.48 176	99.08 47	99.88 36	99.81 110	98.94 32	99.96 37	98.91 125	99.84 94	99.88 31

test_0728_THIRD									98.99 60	99.81 60	99.80 124	99.09 14	99.96 37	98.85 138	99.90 53	99.88 31

test_0728_SECOND				99.91 3	99.84 33	99.89 5	99.57 131	99.51 134					99.96 37	98.93 122	99.86 79	99.88 31

DPE-MVS		99.46 38	99.32 50	99.91 3	99.78 61	99.88 9	99.36 262	99.51 134	98.73 93	99.88 36	99.84 82	98.72 64	99.96 37	98.16 225	99.87 71	99.88 31
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		99.42 51	99.27 68	99.88 12	99.89 8	99.80 32	99.67 70	99.50 154	98.70 97	99.77 75	99.49 277	98.21 99	99.95 71	98.46 196	99.77 128	99.88 31
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 90	99.58 7	98.16 326	99.83 41	94.68 395	99.76 37	99.52 117	99.07 49	99.98 10	99.88 45	98.56 77	99.93 102	99.67 33	99.98 4	99.87 36

DP-MVS		99.16 99	98.95 126	99.78 63	99.77 69	99.53 94	99.41 238	99.50 154	97.03 298	99.04 263	99.88 45	97.39 122	99.92 114	98.66 165	99.90 53	99.87 36

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 61	99.88 9	99.56 138	99.55 90	99.15 30	99.90 30	99.90 30	99.00 22	99.97 25	99.11 99	99.91 42	99.86 38

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 93	99.78 61	99.14 152	99.60 107	99.45 217	99.01 55	99.90 30	99.83 87	98.98 24	99.93 102	99.59 41	99.95 19	99.86 38

Test_1112_low_res		98.89 149	98.66 165	99.57 112	99.69 118	98.95 181	99.03 354	99.47 197	96.98 300	99.15 240	99.23 347	96.77 149	99.89 154	98.83 144	98.78 225	99.86 38

HyFIR lowres test		99.11 120	98.92 129	99.65 87	99.90 4	99.37 115	99.02 357	99.91 3	97.67 228	99.59 137	99.75 160	95.90 186	99.73 239	99.53 49	99.02 208	99.86 38

fmvsm_s_conf0.5_n_7		99.34 69	99.29 62	99.48 141	99.70 113	98.63 218	99.42 233	99.63 42	99.46 7	99.98 10	99.88 45	95.59 199	99.96 37	99.97 1	99.98 4	99.85 42

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 73	99.88 9	99.52 167	99.54 99	99.13 33	99.89 33	99.89 36	98.96 25	99.96 37	99.04 107	99.90 53	99.85 42

our_new_method		99.61 8	99.52 12	99.90 5	99.76 73	99.88 9	99.52 167	99.54 99	99.13 33	99.89 33	99.89 36	98.96 25	99.96 37	99.04 107	99.90 53	99.85 42

EI-MVSNet-Vis-set		99.58 14	99.56 10	99.64 93	99.78 61	99.15 151	99.61 106	99.45 217	99.01 55	99.89 33	99.82 96	99.01 18	99.92 114	99.56 45	99.95 19	99.85 42

CVMVSNet		98.57 188	98.67 162	98.30 314	99.35 249	95.59 370	99.50 184	99.55 90	98.60 106	99.39 183	99.83 87	94.48 259	99.45 297	98.75 152	98.56 238	99.85 42

HPM-MVS_fast		99.51 25	99.40 34	99.85 37	99.91 1	99.79 35	99.76 37	99.56 82	97.72 220	99.76 81	99.75 160	99.13 12	99.92 114	99.07 105	99.92 35	99.85 42

MG-MVS		99.13 108	99.02 109	99.45 148	99.57 172	98.63 218	99.07 344	99.34 276	98.99 60	99.61 131	99.82 96	97.98 110	99.87 165	97.00 322	99.80 116	99.85 42

MVS_0304		99.15 102	98.96 124	99.73 75	98.92 350	99.37 115	99.37 257	96.92 430	99.51 2	99.66 109	99.78 143	96.69 152	99.97 25	99.84 24	99.97 8	99.84 49

ACMMP_NAP		99.47 36	99.34 46	99.88 12	99.87 16	99.86 17	99.47 209	99.48 176	98.05 183	99.76 81	99.86 63	98.82 46	99.93 102	98.82 148	99.91 42	99.84 49

HFP-MVS		99.49 29	99.37 40	99.86 29	99.87 16	99.80 32	99.66 77	99.67 23	98.15 160	99.68 100	99.69 193	99.06 16	99.96 37	98.69 161	99.87 71	99.84 49

region2R		99.48 33	99.35 44	99.87 18	99.88 12	99.80 32	99.65 83	99.66 28	98.13 165	99.66 109	99.68 200	98.96 25	99.96 37	98.62 170	99.87 71	99.84 49

XVS		99.53 23	99.42 28	99.87 18	99.85 27	99.83 20	99.69 61	99.68 20	98.98 63	99.37 187	99.74 165	98.81 47	99.94 84	98.79 149	99.86 79	99.84 49

X-MVStestdata		96.55 353	95.45 372	99.87 18	99.85 27	99.83 20	99.69 61	99.68 20	98.98 63	99.37 187	64.01 449	98.81 47	99.94 84	98.79 149	99.86 79	99.84 49

ACMMPR		99.49 29	99.36 42	99.86 29	99.87 16	99.79 35	99.66 77	99.67 23	98.15 160	99.67 104	99.69 193	98.95 30	99.96 37	98.69 161	99.87 71	99.84 49

HPM-MVS		99.42 51	99.28 65	99.83 50	99.90 4	99.72 50	99.81 20	99.54 99	97.59 235	99.68 100	99.63 225	98.91 37	99.94 84	98.58 179	99.91 42	99.84 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SteuartSystems-ACMMP		99.54 20	99.42 28	99.87 18	99.82 45	99.81 30	99.59 114	99.51 134	98.62 103	99.79 66	99.83 87	99.28 4	99.97 25	98.48 192	99.90 53	99.84 49
Skip Steuart: Steuart Systems R&D Blog.
1112_ss		98.98 142	98.77 152	99.59 105	99.68 123	99.02 167	99.25 305	99.48 176	97.23 277	99.13 242	99.58 243	96.93 145	99.90 139	98.87 131	98.78 225	99.84 49

lecture		99.60 12	99.50 17	99.89 8	99.89 8	99.90 2	99.75 42	99.59 67	99.06 52	99.88 36	99.85 70	98.41 90	99.96 37	99.28 82	99.84 94	99.83 59

MP-MVS-pluss		99.37 62	99.20 80	99.88 12	99.90 4	99.87 16	99.30 279	99.52 117	97.18 280	99.60 134	99.79 136	98.79 50	99.95 71	98.83 144	99.91 42	99.83 59
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MTAPA		99.52 24	99.39 36	99.89 8	99.90 4	99.86 17	99.66 77	99.47 197	98.79 86	99.68 100	99.81 110	98.43 86	99.97 25	98.88 128	99.90 53	99.83 59

PGM-MVS		99.45 42	99.31 56	99.86 29	99.87 16	99.78 41	99.58 124	99.65 35	97.84 206	99.71 94	99.80 124	99.12 13	99.97 25	98.33 210	99.87 71	99.83 59

mPP-MVS		99.44 46	99.30 58	99.86 29	99.88 12	99.79 35	99.69 61	99.48 176	98.12 167	99.50 154	99.75 160	98.78 51	99.97 25	98.57 182	99.89 64	99.83 59

CP-MVS		99.45 42	99.32 50	99.85 37	99.83 41	99.75 45	99.69 61	99.52 117	98.07 177	99.53 149	99.63 225	98.93 36	99.97 25	98.74 153	99.91 42	99.83 59

mvsany_test1		99.50 27	99.46 25	99.62 100	99.61 159	99.09 157	98.94 377	99.48 176	99.10 40	99.96 23	99.91 23	98.85 42	99.96 37	99.72 28	99.58 160	99.82 65

test1111		98.04 237	98.11 213	97.83 355	99.74 91	93.82 407	99.58 124	95.40 440	99.12 38	99.65 116	99.93 10	90.73 357	99.84 181	99.43 63	99.38 174	99.82 65

ZNCC-MVS		99.47 36	99.33 48	99.87 18	99.87 16	99.81 30	99.64 89	99.67 23	98.08 176	99.55 146	99.64 219	98.91 37	99.96 37	98.72 156	99.90 53	99.82 65

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 54	99.91 1	99.66 64	99.63 95	99.39 247	98.91 73	99.78 71	99.85 70	99.36 2	99.94 84	98.84 141	99.88 68	99.82 65
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 71	99.15 85	99.87 18	99.88 12	99.82 26	99.66 77	99.46 206	98.09 172	99.48 158	99.74 165	98.29 96	99.96 37	97.93 243	99.87 71	99.82 65
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		99.43 49	99.30 58	99.82 51	99.79 59	99.74 48	99.29 284	99.40 244	98.79 86	99.52 151	99.62 230	98.91 37	99.90 139	98.64 167	99.75 133	99.82 65

DeepC-MVS_fast	98.69 1	99.49 29	99.39 36	99.77 66	99.63 148	99.59 81	99.36 262	99.46 206	99.07 49	99.79 66	99.82 96	98.85 42	99.92 114	98.68 163	99.87 71	99.82 65
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 12	99.51 193	99.88 9	99.87 8	99.51 134	98.99 60	99.88 36	99.81 110	99.27 5	99.96 37	98.85 138	99.80 116	99.81 72

PC_three_1452									98.18 158	99.84 49	99.70 182	99.31 3	98.52 408	98.30 214	99.80 116	99.81 72

DVP-MVS		99.57 17	99.47 22	99.88 12	99.85 27	99.89 5	99.57 131	99.37 263	99.10 40	99.81 60	99.80 124	98.94 32	99.96 37	98.93 122	99.86 79	99.81 72
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 58	99.24 73	99.85 37	99.86 21	99.79 35	99.60 107	99.67 23	97.97 191	99.63 124	99.68 200	98.52 80	99.95 71	98.38 203	99.86 79	99.81 72

SMA-MVS		99.44 46	99.30 58	99.85 37	99.73 98	99.83 20	99.56 138	99.47 197	97.45 254	99.78 71	99.82 96	99.18 10	99.91 126	98.79 149	99.89 64	99.81 72
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		99.11 120	98.90 133	99.74 72	99.80 55	99.46 106	99.59 114	99.49 164	97.03 298	99.63 124	99.69 193	97.27 130	99.96 37	97.82 254	99.84 94	99.81 72

ACMMP		99.45 42	99.32 50	99.82 51	99.89 8	99.67 61	99.62 100	99.69 18	98.12 167	99.63 124	99.84 82	98.73 63	99.96 37	98.55 188	99.83 104	99.81 72
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	98.81 167	99.37 40	97.12 383	99.60 164	91.75 423	98.61 408	99.44 226	99.35 21	99.83 56	99.85 70	98.70 66	99.81 207	99.02 111	99.91 42	99.81 72

3Dnovator+	97.12 13	99.18 95	98.97 120	99.82 51	99.17 305	99.68 57	99.81 20	99.51 134	99.20 27	98.72 310	99.89 36	95.68 196	99.97 25	98.86 136	99.86 79	99.81 72

test2506		96.81 349	96.65 345	97.29 379	99.74 91	92.21 422	99.60 107	85.06 453	99.13 33	99.77 75	99.93 10	87.82 396	99.85 174	99.38 66	99.38 174	99.80 81

ECVR-MVS		98.04 237	98.05 222	98.00 339	99.74 91	94.37 402	99.59 114	94.98 441	99.13 33	99.66 109	99.93 10	90.67 358	99.84 181	99.40 64	99.38 174	99.80 81

APD-MVS		99.27 82	99.08 96	99.84 49	99.75 83	99.79 35	99.50 184	99.50 154	97.16 282	99.77 75	99.82 96	98.78 51	99.94 84	97.56 284	99.86 79	99.80 81
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		99.34 69	99.19 82	99.79 60	99.61 159	99.65 68	99.30 279	99.48 176	98.86 75	99.21 227	99.63 225	98.72 64	99.90 139	98.25 217	99.63 155	99.80 81

SED-MVS		99.61 8	99.52 12	99.88 12	99.84 33	99.90 2	99.60 107	99.48 176	99.08 47	99.91 27	99.81 110	99.20 7	99.96 37	98.91 125	99.85 86	99.79 85

OPU-MVS				99.64 93	99.56 176	99.72 50	99.60 107				99.70 182	99.27 5	99.42 308	98.24 218	99.80 116	99.79 85

SR-MVS		99.43 49	99.29 62	99.86 29	99.75 83	99.83 20	99.59 114	99.62 46	98.21 153	99.73 87	99.79 136	98.68 67	99.96 37	98.44 198	99.77 128	99.79 85

HPM-MVS++		99.39 60	99.23 76	99.87 18	99.75 83	99.84 19	99.43 226	99.51 134	98.68 100	99.27 212	99.53 263	98.64 72	99.96 37	98.44 198	99.80 116	99.79 85

PVSNet_Blended_VisFu		99.36 66	99.28 65	99.61 101	99.86 21	99.07 162	99.47 209	99.93 2	97.66 229	99.71 94	99.86 63	97.73 116	99.96 37	99.47 60	99.82 108	99.79 85

3Dnovator	97.25 9	99.24 89	99.05 99	99.81 54	99.12 313	99.66 64	99.84 12	99.74 10	99.09 46	98.92 282	99.90 30	95.94 183	99.98 16	98.95 118	99.92 35	99.79 85

APD-MVS_3200maxsize		99.48 33	99.35 44	99.85 37	99.76 73	99.83 20	99.63 95	99.54 99	98.36 131	99.79 66	99.82 96	98.86 41	99.95 71	98.62 170	99.81 111	99.78 91

CDPH-MVS		99.13 108	98.91 132	99.80 57	99.75 83	99.71 52	99.15 328	99.41 237	96.60 330	99.60 134	99.55 254	98.83 45	99.90 139	97.48 291	99.83 104	99.78 91

SR-MVS-dyc-post		99.45 42	99.31 56	99.85 37	99.76 73	99.82 26	99.63 95	99.52 117	98.38 127	99.76 81	99.82 96	98.53 79	99.95 71	98.61 173	99.81 111	99.77 93

RE-MVS-def			99.34 46		99.76 73	99.82 26	99.63 95	99.52 117	98.38 127	99.76 81	99.82 96	98.75 58		98.61 173	99.81 111	99.77 93

SD-MVS		99.41 55	99.52 12	99.05 208	99.74 91	99.68 57	99.46 212	99.52 117	99.11 39	99.88 36	99.91 23	99.43 1	97.70 425	98.72 156	99.93 29	99.77 93
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 51	99.30 58	99.78 63	99.62 154	99.71 52	99.26 303	99.52 117	98.82 80	99.39 183	99.71 178	98.96 25	99.85 174	98.59 178	99.80 116	99.77 93

MVS_111021_HR		99.41 55	99.32 50	99.66 83	99.72 102	99.47 105	98.95 375	99.85 6	98.82 80	99.54 147	99.73 171	98.51 81	99.74 233	98.91 125	99.88 68	99.77 93

QAPM		98.67 181	98.30 200	99.80 57	99.20 291	99.67 61	99.77 34	99.72 11	94.74 393	98.73 309	99.90 30	95.78 192	99.98 16	96.96 326	99.88 68	99.76 98

GeoE		98.85 163	98.62 175	99.53 125	99.61 159	99.08 160	99.80 25	99.51 134	97.10 290	99.31 199	99.78 143	95.23 216	99.77 224	98.21 219	99.03 206	99.75 99

test9_res														97.49 290	99.72 139	99.75 99

train_agg		99.02 136	98.77 152	99.77 66	99.67 125	99.65 68	99.05 349	99.41 237	96.28 350	98.95 278	99.49 277	98.76 55	99.91 126	97.63 275	99.72 139	99.75 99

agg_prior2														97.21 308	99.73 138	99.75 99

KinetiMVS		99.12 114	98.92 129	99.70 79	99.67 125	99.40 113	99.67 70	99.63 42	98.73 93	99.94 24	99.81 110	94.54 256	99.96 37	98.40 201	99.93 29	99.74 103

AstraMVS		99.09 125	99.03 104	99.25 185	99.66 136	98.13 256	99.57 131	98.24 413	98.82 80	99.91 27	99.88 45	95.81 190	99.90 139	99.72 28	99.67 149	99.74 103

guyue		99.16 99	99.04 101	99.52 131	99.69 118	98.92 188	99.59 114	98.81 381	98.73 93	99.90 30	99.87 56	95.34 209	99.88 159	99.66 36	99.81 111	99.74 103

SF-MVS		99.38 61	99.24 73	99.79 60	99.79 59	99.68 57	99.57 131	99.54 99	97.82 211	99.71 94	99.80 124	98.95 30	99.93 102	98.19 221	99.84 94	99.74 103

test_prior				99.68 81	99.67 125	99.48 103		99.56 82					99.83 194			99.74 103

test12				99.75 69	99.64 145	99.61 78		99.29 307		99.21 227		98.38 92	99.89 154		99.74 136	99.74 103

114514_t		98.93 146	98.67 162	99.72 78	99.85 27	99.53 94	99.62 100	99.59 67	92.65 415	99.71 94	99.78 143	98.06 107	99.90 139	98.84 141	99.91 42	99.74 103

Vis-MVSNet		99.12 114	98.97 120	99.56 114	99.78 61	99.10 156	99.68 67	99.66 28	98.49 115	99.86 46	99.87 56	94.77 239	99.84 181	99.19 91	99.41 173	99.74 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SymmetryMVS		99.15 102	99.02 109	99.52 131	99.72 102	98.83 200	99.65 83	99.34 276	99.10 40	99.84 49	99.76 156	95.80 191	99.99 4	99.30 80	98.72 228	99.73 111

fmvsm_s_conf0.5_n_4		99.36 66	99.24 73	99.73 75	99.78 61	99.53 94	99.49 196	99.60 61	99.42 16	99.99 2	99.86 63	95.15 218	99.95 71	99.95 12	99.89 64	99.73 111

fmvsm_s_conf0.1_n_2		99.37 62	99.22 77	99.81 54	99.77 69	99.75 45	99.46 212	99.60 61	99.47 4	99.98 10	99.94 6	94.98 222	99.95 71	99.97 1	99.79 123	99.73 111

旧先验1					99.74 91	99.59 81		99.54 99			99.69 193	98.47 83			99.68 147	99.73 111

casdiffmvs_mvg		99.15 102	99.02 109	99.55 116	99.66 136	99.09 157	99.64 89	99.56 82	98.26 143	99.45 162	99.87 56	96.03 178	99.81 207	99.54 47	99.15 194	99.73 111
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		98.86 156	98.71 158	99.30 175	97.20 424	98.18 252	99.62 100	98.91 367	99.28 25	98.63 329	99.81 110	95.96 180	99.99 4	99.24 88	99.72 139	99.73 111
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IS-MVSNet		99.05 132	98.87 139	99.57 112	99.73 98	99.32 123	99.75 42	99.20 325	98.02 188	99.56 142	99.86 63	96.54 159	99.67 263	98.09 228	99.13 196	99.73 111

F-COLMAP		99.19 93	99.04 101	99.64 93	99.78 61	99.27 135	99.42 233	99.54 99	97.29 271	99.41 176	99.59 239	98.42 88	99.93 102	98.19 221	99.69 144	99.73 111

DeepC-MVS	98.35 2	99.30 76	99.19 82	99.64 93	99.82 45	99.23 140	99.62 100	99.55 90	98.94 69	99.63 124	99.95 3	95.82 189	99.94 84	99.37 67	99.97 8	99.73 111
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SDMVSNet		99.11 120	98.90 133	99.75 69	99.81 49	99.59 81	99.81 20	99.65 35	98.78 89	99.64 121	99.88 45	94.56 253	99.93 102	99.67 33	98.26 256	99.72 120

sd_testset		98.75 174	98.57 182	99.29 178	99.81 49	98.26 249	99.56 138	99.62 46	98.78 89	99.64 121	99.88 45	92.02 331	99.88 159	99.54 47	98.26 256	99.72 120

新几何1				99.75 69	99.75 83	99.59 81		99.54 99	96.76 314	99.29 206	99.64 219	98.43 86	99.94 84	96.92 331	99.66 150	99.72 120

无先验							98.99 365	99.51 134	96.89 308				99.93 102	97.53 287		99.72 120

test222					99.75 83	99.49 101	98.91 381	99.49 164	96.42 344	99.34 196	99.65 213	98.28 97			99.69 144	99.72 120

testdata				99.54 117	99.75 83	98.95 181		99.51 134	97.07 292	99.43 169	99.70 182	98.87 40	99.94 84	97.76 263	99.64 153	99.72 120

VNet		99.11 120	98.90 133	99.73 75	99.52 190	99.56 87	99.41 238	99.39 247	99.01 55	99.74 85	99.78 143	95.56 200	99.92 114	99.52 51	98.18 264	99.72 120

WTY-MVS		99.06 130	98.88 138	99.61 101	99.62 154	99.16 147	99.37 257	99.56 82	98.04 184	99.53 149	99.62 230	96.84 146	99.94 84	98.85 138	98.49 243	99.72 120

CSCG		99.32 73	99.32 50	99.32 169	99.85 27	98.29 247	99.71 56	99.66 28	98.11 169	99.41 176	99.80 124	98.37 93	99.96 37	98.99 113	99.96 14	99.72 120

BP-MVS1		99.12 114	98.94 128	99.65 87	99.51 193	99.30 130	99.67 70	98.92 362	98.48 116	99.84 49	99.69 193	94.96 223	99.92 114	99.62 40	99.79 123	99.71 129

原ACMM1				99.65 87	99.73 98	99.33 122		99.47 197	97.46 251	99.12 244	99.66 211	98.67 69	99.91 126	97.70 272	99.69 144	99.71 129

Anonymous202405211		98.30 208	97.98 229	99.26 184	99.57 172	98.16 253	99.41 238	98.55 406	96.03 371	99.19 233	99.74 165	91.87 334	99.92 114	99.16 96	98.29 255	99.70 131

casdiffmvs		99.13 108	98.98 119	99.56 114	99.65 143	99.16 147	99.56 138	99.50 154	98.33 135	99.41 176	99.86 63	95.92 184	99.83 194	99.45 62	99.16 191	99.70 131
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		97.90 260	97.35 309	99.54 117	99.52 190	99.01 169	99.39 250	98.24 413	97.10 290	99.65 116	99.79 136	84.79 414	99.91 126	99.28 82	98.38 247	99.69 133

EPNet_dtu		98.03 239	97.96 231	98.23 322	98.27 406	95.54 373	99.23 311	98.75 388	99.02 53	97.82 377	99.71 178	96.11 175	99.48 292	93.04 406	99.65 152	99.69 133
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PAPM_NR		99.04 133	98.84 145	99.66 83	99.74 91	99.44 108	99.39 250	99.38 255	97.70 224	99.28 207	99.28 339	98.34 94	99.85 174	96.96 326	99.45 170	99.69 133

EPP-MVSNet		99.13 108	98.99 116	99.53 125	99.65 143	99.06 163	99.81 20	99.33 284	97.43 258	99.60 134	99.88 45	97.14 134	99.84 181	99.13 97	98.94 211	99.69 133

sss		99.17 97	99.05 99	99.53 125	99.62 154	98.97 174	99.36 262	99.62 46	97.83 207	99.67 104	99.65 213	97.37 125	99.95 71	99.19 91	99.19 190	99.68 137

PHI-MVS		99.30 76	99.17 84	99.70 79	99.56 176	99.52 98	99.58 124	99.80 8	97.12 286	99.62 128	99.73 171	98.58 75	99.90 139	98.61 173	99.91 42	99.68 137

PVSNet_0	94.43 19	96.09 364	95.47 371	97.94 344	99.31 263	94.34 404	97.81 433	99.70 15	97.12 286	97.46 383	98.75 394	89.71 369	99.79 217	97.69 273	81.69 436	99.68 137

diffmvs		99.14 106	99.02 109	99.51 135	99.61 159	98.96 178	99.28 289	99.49 164	98.46 118	99.72 92	99.71 178	96.50 161	99.88 159	99.31 77	99.11 197	99.67 140
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		99.15 102	99.02 109	99.53 125	99.66 136	99.14 152	99.72 53	99.48 176	98.35 132	99.42 172	99.84 82	96.07 176	99.79 217	99.51 52	99.14 195	99.67 140

TAMVS		99.12 114	99.08 96	99.24 188	99.46 217	98.55 226	99.51 176	99.46 206	98.09 172	99.45 162	99.82 96	98.34 94	99.51 291	98.70 158	98.93 212	99.67 140

Anonymous20240529		98.09 227	97.68 265	99.34 163	99.66 136	98.44 241	99.40 246	99.43 232	93.67 403	99.22 224	99.89 36	90.23 364	99.93 102	99.26 87	98.33 250	99.66 143

CHOSEN 280x420		99.12 114	99.13 87	99.08 203	99.66 136	97.89 273	98.43 418	99.71 13	98.88 74	99.62 128	99.76 156	96.63 154	99.70 255	99.46 61	99.99 1	99.66 143

CDS-MVSNet		99.09 125	99.03 104	99.25 185	99.42 227	98.73 209	99.45 215	99.46 206	98.11 169	99.46 161	99.77 152	98.01 109	99.37 315	98.70 158	98.92 214	99.66 143
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		98.63 186	98.34 196	99.51 135	99.40 237	99.03 166	98.80 391	99.36 264	96.33 347	99.00 270	99.12 361	98.46 84	99.84 181	95.23 378	99.37 181	99.66 143

h-mvs33		97.70 299	97.28 321	98.97 218	99.70 113	97.27 300	99.36 262	99.45 217	98.94 69	99.66 109	99.64 219	94.93 226	99.99 4	99.48 58	84.36 432	99.65 147

CANet		99.25 88	99.14 86	99.59 105	99.41 232	99.16 147	99.35 267	99.57 77	98.82 80	99.51 153	99.61 234	96.46 163	99.95 71	99.59 41	99.98 4	99.65 147

TSAR-MVS + GP.		99.36 66	99.36 42	99.36 161	99.67 125	98.61 222	99.07 344	99.33 284	99.00 58	99.82 59	99.81 110	99.06 16	99.84 181	99.09 103	99.42 172	99.65 147

MVSFormer		99.17 97	99.12 89	99.29 178	99.51 193	98.94 184	99.88 4	99.46 206	97.55 241	99.80 64	99.65 213	97.39 122	99.28 332	99.03 109	99.85 86	99.65 147

jason		99.13 108	99.03 104	99.45 148	99.46 217	98.87 192	99.12 334	99.26 313	98.03 186	99.79 66	99.65 213	97.02 141	99.85 174	99.02 111	99.90 53	99.65 147
jason: jason.
PLC	97.94 4	99.02 136	98.85 143	99.53 125	99.66 136	99.01 169	99.24 308	99.52 117	96.85 310	99.27 212	99.48 283	98.25 98	99.91 126	97.76 263	99.62 156	99.65 147
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TAPA-MVS	97.07 15	97.74 291	97.34 312	98.94 223	99.70 113	97.53 290	99.25 305	99.51 134	91.90 417	99.30 203	99.63 225	98.78 51	99.64 274	88.09 429	99.87 71	99.65 147
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GDP-MVS		99.08 127	98.89 136	99.64 93	99.53 184	99.34 119	99.64 89	99.48 176	98.32 136	99.77 75	99.66 211	95.14 219	99.93 102	98.97 117	99.50 167	99.64 154

dmvs_re		98.08 229	98.16 206	97.85 352	99.55 180	94.67 396	99.70 57	98.92 362	98.15 160	99.06 260	99.35 320	93.67 290	99.25 339	97.77 262	97.25 317	99.64 154

LCM-MVSNet-Re		97.83 274	98.15 208	96.87 391	99.30 264	92.25 421	99.59 114	98.26 411	97.43 258	96.20 407	99.13 358	96.27 171	98.73 404	98.17 224	98.99 209	99.64 154

BH-RMVSNet		98.41 197	98.08 218	99.40 155	99.41 232	98.83 200	99.30 279	98.77 387	97.70 224	98.94 280	99.65 213	92.91 305	99.74 233	96.52 346	99.55 163	99.64 154

MVS_111021_LR		99.41 55	99.33 48	99.65 87	99.77 69	99.51 99	98.94 377	99.85 6	98.82 80	99.65 116	99.74 165	98.51 81	99.80 214	98.83 144	99.89 64	99.64 154

LuminaMVS		99.23 90	99.10 91	99.61 101	99.35 249	99.31 127	99.46 212	99.13 334	98.61 104	99.86 46	99.89 36	96.41 167	99.91 126	99.67 33	99.51 165	99.63 159

MVS		97.28 334	96.55 347	99.48 141	98.78 371	98.95 181	99.27 294	99.39 247	83.53 436	98.08 363	99.54 259	96.97 143	99.87 165	94.23 392	99.16 191	99.63 159

MSLP-MVS++		99.46 38	99.47 22	99.44 152	99.60 164	99.16 147	99.41 238	99.71 13	98.98 63	99.45 162	99.78 143	99.19 9	99.54 289	99.28 82	99.84 94	99.63 159

GA-MVS		97.85 267	97.47 289	99.00 214	99.38 242	97.99 264	98.57 411	99.15 331	97.04 297	98.90 285	99.30 335	89.83 368	99.38 312	96.70 339	98.33 250	99.62 162

Vis-MVSNet (Re-imp)		98.87 153	98.72 156	99.31 170	99.71 108	98.88 191	99.80 25	99.44 226	97.91 196	99.36 190	99.78 143	95.49 203	99.43 306	97.91 244	99.11 197	99.62 162

DPM-MVS		98.95 145	98.71 158	99.66 83	99.63 148	99.55 89	98.64 407	99.10 337	97.93 194	99.42 172	99.55 254	98.67 69	99.80 214	95.80 363	99.68 147	99.61 164

RRT-MVS		98.91 148	98.75 154	99.39 159	99.46 217	98.61 222	99.76 37	99.50 154	98.06 181	99.81 60	99.88 45	93.91 282	99.94 84	99.11 99	99.27 185	99.61 164

baseline1		98.31 206	97.95 233	99.38 160	99.50 205	98.74 208	99.59 114	98.93 359	98.41 125	99.14 241	99.60 237	94.59 251	99.79 217	98.48 192	93.29 399	99.61 164

VDD-MVS		97.73 293	97.35 309	98.88 238	99.47 215	97.12 308	99.34 270	98.85 376	98.19 155	99.67 104	99.85 70	82.98 422	99.92 114	99.49 57	98.32 254	99.60 167

DELS-MVS		99.48 33	99.42 28	99.65 87	99.72 102	99.40 113	99.05 349	99.66 28	99.14 32	99.57 141	99.80 124	98.46 84	99.94 84	99.57 44	99.84 94	99.60 167
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		99.08 127	98.97 120	99.42 153	99.76 73	98.79 205	98.78 393	99.91 3	96.74 315	99.67 104	99.49 277	97.53 119	99.88 159	98.98 114	99.85 86	99.60 167

OMC-MVS		99.08 127	99.04 101	99.20 192	99.67 125	98.22 251	99.28 289	99.52 117	98.07 177	99.66 109	99.81 110	97.79 114	99.78 222	97.79 258	99.81 111	99.60 167

test_yl		98.86 156	98.63 170	99.54 117	99.49 207	99.18 144	99.50 184	99.07 343	98.22 151	99.61 131	99.51 271	95.37 207	99.84 181	98.60 176	98.33 250	99.59 171

DCV-MVSNet		98.86 156	98.63 170	99.54 117	99.49 207	99.18 144	99.50 184	99.07 343	98.22 151	99.61 131	99.51 271	95.37 207	99.84 181	98.60 176	98.33 250	99.59 171

AllTest		98.87 153	98.72 156	99.31 170	99.86 21	98.48 238	99.56 138	99.61 54	97.85 204	99.36 190	99.85 70	95.95 181	99.85 174	96.66 342	99.83 104	99.59 171

TestCases				99.31 170	99.86 21	98.48 238		99.61 54	97.85 204	99.36 190	99.85 70	95.95 181	99.85 174	96.66 342	99.83 104	99.59 171

dongtai		93.26 392	92.93 396	94.25 404	99.39 240	85.68 432	97.68 435	93.27 446	92.87 412	96.85 401	99.39 309	82.33 426	97.48 427	76.78 440	97.80 281	99.58 175

testing3		97.28 334	96.76 343	98.82 251	99.37 245	98.07 260	99.45 215	99.36 264	97.56 240	97.89 374	98.95 379	83.70 419	98.82 399	96.03 357	98.56 238	99.58 175

lupinMVS		99.13 108	99.01 114	99.46 147	99.51 193	98.94 184	99.05 349	99.16 330	97.86 201	99.80 64	99.56 251	97.39 122	99.86 168	98.94 119	99.85 86	99.58 175

sc_t1		95.75 370	95.05 377	97.87 350	98.83 365	94.61 397	99.21 317	99.45 217	87.45 430	97.97 370	99.85 70	81.19 430	99.43 306	98.27 215	93.20 401	99.57 178

tttt0517		98.42 195	98.14 209	99.28 182	99.66 136	98.38 245	99.74 47	96.85 431	97.68 226	99.79 66	99.74 165	91.39 348	99.89 154	98.83 144	99.56 161	99.57 178

RPSCF		98.22 212	98.62 175	96.99 385	99.82 45	91.58 424	99.72 53	99.44 226	96.61 327	99.66 109	99.89 36	95.92 184	99.82 202	97.46 294	99.10 200	99.57 178

dmvs_testset		95.02 379	96.12 357	91.72 414	99.10 318	80.43 442	99.58 124	97.87 421	97.47 250	95.22 414	98.82 388	93.99 277	95.18 439	88.09 429	94.91 375	99.56 181

DSMNet-mixed		97.25 336	97.35 309	96.95 388	97.84 412	93.61 413	99.57 131	96.63 435	96.13 365	98.87 291	98.61 399	94.59 251	97.70 425	95.08 380	98.86 218	99.55 182

AdaColmap		99.01 140	98.80 148	99.66 83	99.56 176	99.54 91	99.18 323	99.70 15	98.18 158	99.35 193	99.63 225	96.32 169	99.90 139	97.48 291	99.77 128	99.55 182

alignmvs		98.81 167	98.56 184	99.58 108	99.43 225	99.42 110	99.51 176	98.96 357	98.61 104	99.35 193	98.92 384	94.78 236	99.77 224	99.35 68	98.11 269	99.54 184

mamv4		99.33 71	99.42 28	99.07 204	99.67 125	97.73 280	99.42 233	99.60 61	98.15 160	99.94 24	99.91 23	98.42 88	99.94 84	99.72 28	99.96 14	99.54 184

EC-MVSNet		99.44 46	99.39 36	99.58 108	99.56 176	99.49 101	99.88 4	99.58 72	98.38 127	99.73 87	99.69 193	98.20 100	99.70 255	99.64 39	99.82 108	99.54 184

PatchmatchNet		98.31 206	98.36 194	98.19 324	99.16 307	95.32 381	99.27 294	98.92 362	97.37 264	99.37 187	99.58 243	94.90 229	99.70 255	97.43 297	99.21 188	99.54 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PVSNet	96.02 17	98.85 163	98.84 145	98.89 236	99.73 98	97.28 299	98.32 424	99.60 61	97.86 201	99.50 154	99.57 248	96.75 150	99.86 168	98.56 185	99.70 143	99.54 184

MSDG		98.98 142	98.80 148	99.53 125	99.76 73	99.19 142	98.75 396	99.55 90	97.25 274	99.47 159	99.77 152	97.82 113	99.87 165	96.93 329	99.90 53	99.54 184

UGNet		98.87 153	98.69 160	99.40 155	99.22 288	98.72 210	99.44 221	99.68 20	99.24 26	99.18 237	99.42 297	92.74 309	99.96 37	99.34 73	99.94 27	99.53 190
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
testing3-2		97.84 271	97.70 263	98.24 321	99.53 184	95.37 380	99.55 152	98.67 401	98.46 118	99.27 212	99.34 324	86.58 402	99.83 194	99.32 76	98.63 231	99.52 191

balanced_conf03		99.46 38	99.39 36	99.67 82	99.55 180	99.58 86	99.74 47	99.51 134	98.42 124	99.87 42	99.84 82	98.05 108	99.91 126	99.58 43	99.94 27	99.52 191

GSMVS																99.52 191

sam_mvs1												94.86 231				99.52 191

SCA		98.19 216	98.16 206	98.27 320	99.30 264	95.55 371	99.07 344	98.97 355	97.57 238	99.43 169	99.57 248	92.72 310	99.74 233	97.58 279	99.20 189	99.52 191

Patchmatch-test		97.93 254	97.65 268	98.77 259	99.18 297	97.07 313	99.03 354	99.14 333	96.16 361	98.74 308	99.57 248	94.56 253	99.72 243	93.36 402	99.11 197	99.52 191

PMMVS		98.80 170	98.62 175	99.34 163	99.27 273	98.70 211	98.76 395	99.31 298	97.34 266	99.21 227	99.07 363	97.20 133	99.82 202	98.56 185	98.87 217	99.52 191

LS3D		99.27 82	99.12 89	99.74 72	99.18 297	99.75 45	99.56 138	99.57 77	98.45 120	99.49 157	99.85 70	97.77 115	99.94 84	98.33 210	99.84 94	99.52 191

Effi-MVS+		98.81 167	98.59 181	99.48 141	99.46 217	99.12 155	98.08 431	99.50 154	97.50 249	99.38 185	99.41 301	96.37 168	99.81 207	99.11 99	98.54 240	99.51 199

Patchmatch-RL test		95.84 368	95.81 366	95.95 400	95.61 433	90.57 426	98.24 426	98.39 409	95.10 385	95.20 415	98.67 396	94.78 236	97.77 423	96.28 354	90.02 422	99.51 199

mvs_anonymous		99.03 135	98.99 116	99.16 196	99.38 242	98.52 232	99.51 176	99.38 255	97.79 212	99.38 185	99.81 110	97.30 128	99.45 297	99.35 68	98.99 209	99.51 199

mvsmamba		99.06 130	98.96 124	99.36 161	99.47 215	98.64 217	99.70 57	99.05 346	97.61 234	99.65 116	99.83 87	96.54 159	99.92 114	99.19 91	99.62 156	99.51 199

UniMVSNet_ETH3D		97.32 333	96.81 341	98.87 242	99.40 237	97.46 293	99.51 176	99.53 112	95.86 374	98.54 338	99.77 152	82.44 425	99.66 266	98.68 163	97.52 298	99.50 203

Elysia		98.88 150	98.65 167	99.58 108	99.58 168	99.34 119	99.65 83	99.52 117	98.26 143	99.83 56	99.87 56	93.37 293	99.90 139	97.81 256	99.91 42	99.49 204

StellarMVS		98.88 150	98.65 167	99.58 108	99.58 168	99.34 119	99.65 83	99.52 117	98.26 143	99.83 56	99.87 56	93.37 293	99.90 139	97.81 256	99.91 42	99.49 204

ab-mvs		98.86 156	98.63 170	99.54 117	99.64 145	99.19 142	99.44 221	99.54 99	97.77 215	99.30 203	99.81 110	94.20 268	99.93 102	99.17 95	98.82 222	99.49 204

thisisatest0530		98.35 204	98.03 224	99.31 170	99.63 148	98.56 225	99.54 157	96.75 433	97.53 245	99.73 87	99.65 213	91.25 352	99.89 154	98.62 170	99.56 161	99.48 207

SPE-MVS-test		99.49 29	99.48 20	99.54 117	99.78 61	99.30 130	99.89 2	99.58 72	98.56 109	99.73 87	99.69 193	98.55 78	99.82 202	99.69 31	99.85 86	99.48 207

ADS-MVSNet2		98.02 241	98.07 221	97.87 350	99.33 255	95.19 384	99.23 311	99.08 340	96.24 354	99.10 249	99.67 206	94.11 272	98.93 394	96.81 334	99.05 204	99.48 207

ADS-MVSNet		98.20 215	98.08 218	98.56 281	99.33 255	96.48 347	99.23 311	99.15 331	96.24 354	99.10 249	99.67 206	94.11 272	99.71 249	96.81 334	99.05 204	99.48 207

tpm		97.67 306	97.55 277	98.03 334	99.02 334	95.01 388	99.43 226	98.54 407	96.44 342	99.12 244	99.34 324	91.83 336	99.60 283	97.75 265	96.46 332	99.48 207

CNLPA		99.14 106	98.99 116	99.59 105	99.58 168	99.41 112	99.16 325	99.44 226	98.45 120	99.19 233	99.49 277	98.08 106	99.89 154	97.73 267	99.75 133	99.48 207

MVSMamba_PlusPlus		99.46 38	99.41 33	99.64 93	99.68 123	99.50 100	99.75 42	99.50 154	98.27 141	99.87 42	99.92 17	98.09 105	99.94 84	99.65 37	99.95 19	99.47 213

MGCFI-Net		99.01 140	98.85 143	99.50 140	99.42 227	99.26 136	99.82 16	99.48 176	98.60 106	99.28 207	98.81 389	97.04 140	99.76 228	99.29 81	97.87 278	99.47 213

sasdasda		99.02 136	98.86 141	99.51 135	99.42 227	99.32 123	99.80 25	99.48 176	98.63 101	99.31 199	98.81 389	97.09 136	99.75 231	99.27 85	97.90 275	99.47 213

canonicalmvs		99.02 136	98.86 141	99.51 135	99.42 227	99.32 123	99.80 25	99.48 176	98.63 101	99.31 199	98.81 389	97.09 136	99.75 231	99.27 85	97.90 275	99.47 213

MIMVSNet		97.73 293	97.45 292	98.57 278	99.45 223	97.50 292	99.02 357	98.98 354	96.11 366	99.41 176	99.14 357	90.28 360	98.74 403	95.74 364	98.93 212	99.47 213

MVS_Test		99.10 124	98.97 120	99.48 141	99.49 207	99.14 152	99.67 70	99.34 276	97.31 269	99.58 138	99.76 156	97.65 118	99.82 202	98.87 131	99.07 203	99.46 218

MDTV_nov1_ep13_2view						95.18 385	99.35 267		96.84 311	99.58 138		95.19 217		97.82 254		99.46 218

MVS-HIRNet		95.75 370	95.16 375	97.51 372	99.30 264	93.69 411	98.88 383	95.78 438	85.09 435	98.78 305	92.65 438	91.29 351	99.37 315	94.85 384	99.85 86	99.46 218

Syy-MVS		97.09 343	97.14 329	96.95 388	99.00 337	92.73 419	99.29 284	99.39 247	97.06 294	97.41 384	98.15 415	93.92 281	98.68 405	91.71 415	98.34 248	99.45 221

myMVS_eth3d		96.89 346	96.37 351	98.43 302	99.00 337	97.16 306	99.29 284	99.39 247	97.06 294	97.41 384	98.15 415	83.46 421	98.68 405	95.27 377	98.34 248	99.45 221

DP-MVS Recon		99.12 114	98.95 126	99.65 87	99.74 91	99.70 54	99.27 294	99.57 77	96.40 346	99.42 172	99.68 200	98.75 58	99.80 214	97.98 240	99.72 139	99.44 223

PatchMatch-RL		98.84 166	98.62 175	99.52 131	99.71 108	99.28 133	99.06 347	99.77 9	97.74 219	99.50 154	99.53 263	95.41 205	99.84 181	97.17 315	99.64 153	99.44 223

UBG		97.85 267	97.48 286	98.95 221	99.25 280	97.64 287	99.24 308	98.74 391	97.90 197	98.64 327	98.20 414	88.65 383	99.81 207	98.27 215	98.40 245	99.42 225

VDDNet		97.55 314	97.02 335	99.16 196	99.49 207	98.12 258	99.38 255	99.30 303	95.35 379	99.68 100	99.90 30	82.62 424	99.93 102	99.31 77	98.13 268	99.42 225

PCF-MVS	97.08 14	97.66 307	97.06 334	99.47 145	99.61 159	99.09 157	98.04 432	99.25 315	91.24 420	98.51 339	99.70 182	94.55 255	99.91 126	92.76 411	99.85 86	99.42 225
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ET-MVSNet_ETH3D		96.49 355	95.64 369	99.05 208	99.53 184	98.82 202	98.84 387	97.51 427	97.63 231	84.77 436	99.21 351	92.09 330	98.91 395	98.98 114	92.21 411	99.41 228

CS-MVS		99.50 27	99.48 20	99.54 117	99.76 73	99.42 110	99.90 1	99.55 90	98.56 109	99.78 71	99.70 182	98.65 71	99.79 217	99.65 37	99.78 125	99.41 228

HY-MVS	97.30 7	98.85 163	98.64 169	99.47 145	99.42 227	99.08 160	99.62 100	99.36 264	97.39 263	99.28 207	99.68 200	96.44 165	99.92 114	98.37 205	98.22 259	99.40 230

testing91		97.44 326	97.02 335	98.71 265	99.18 297	96.89 330	99.19 321	99.04 347	97.78 214	98.31 350	98.29 411	85.41 410	99.85 174	98.01 238	97.95 273	99.39 231

ETVMVS		97.50 319	96.90 339	99.29 178	99.23 284	98.78 207	99.32 274	98.90 369	97.52 247	98.56 336	98.09 420	84.72 415	99.69 260	97.86 249	97.88 277	99.39 231

tt0805		97.97 251	97.77 253	98.57 278	99.59 166	96.61 343	99.45 215	99.08 340	98.21 153	98.88 288	99.80 124	88.66 382	99.70 255	98.58 179	97.72 284	99.39 231

Fast-Effi-MVS+		98.70 178	98.43 190	99.51 135	99.51 193	99.28 133	99.52 167	99.47 197	96.11 366	99.01 266	99.34 324	96.20 173	99.84 181	97.88 246	98.82 222	99.39 231

testing11		97.50 319	97.10 332	98.71 265	99.20 291	96.91 328	99.29 284	98.82 379	97.89 198	98.21 358	98.40 406	85.63 408	99.83 194	98.45 197	98.04 271	99.37 235

CANet_DTU		98.97 144	98.87 139	99.25 185	99.33 255	98.42 244	99.08 343	99.30 303	99.16 29	99.43 169	99.75 160	95.27 212	99.97 25	98.56 185	99.95 19	99.36 236

testing99		97.36 329	96.94 338	98.63 271	99.18 297	96.70 336	99.30 279	98.93 359	97.71 221	98.23 355	98.26 412	84.92 413	99.84 181	98.04 237	97.85 280	99.35 237

EIA-MVS		99.18 95	99.09 95	99.45 148	99.49 207	99.18 144	99.67 70	99.53 112	97.66 229	99.40 181	99.44 293	98.10 104	99.81 207	98.94 119	99.62 156	99.35 237

EPMVS		97.82 277	97.65 268	98.35 309	98.88 355	95.98 362	99.49 196	94.71 443	97.57 238	99.26 217	99.48 283	92.46 324	99.71 249	97.87 248	99.08 202	99.35 237

CostFormer		97.72 295	97.73 260	97.71 363	99.15 311	94.02 406	99.54 157	99.02 350	94.67 394	99.04 263	99.35 320	92.35 327	99.77 224	98.50 191	97.94 274	99.34 240

BH-untuned		98.42 195	98.36 194	98.59 274	99.49 207	96.70 336	99.27 294	99.13 334	97.24 276	98.80 302	99.38 311	95.75 193	99.74 233	97.07 320	99.16 191	99.33 241

FE-MVS		98.48 190	98.17 205	99.40 155	99.54 183	98.96 178	99.68 67	98.81 381	95.54 377	99.62 128	99.70 182	93.82 285	99.93 102	97.35 302	99.46 169	99.32 242

PAPM		97.59 312	97.09 333	99.07 204	99.06 327	98.26 249	98.30 425	99.10 337	94.88 389	98.08 363	99.34 324	96.27 171	99.64 274	89.87 422	98.92 214	99.31 243

tpm2		97.44 326	97.34 312	97.74 362	99.15 311	94.36 403	99.45 215	98.94 358	93.45 408	98.90 285	99.44 293	91.35 349	99.59 284	97.31 303	98.07 270	99.29 244

UWE-MVS		97.58 313	97.29 320	98.48 289	99.09 321	96.25 356	99.01 362	96.61 436	97.86 201	99.19 233	99.01 371	88.72 379	99.90 139	97.38 300	98.69 229	99.28 245

FA-MVS(test-final)		98.75 174	98.53 186	99.41 154	99.55 180	99.05 165	99.80 25	99.01 351	96.59 332	99.58 138	99.59 239	95.39 206	99.90 139	97.78 259	99.49 168	99.28 245

MonoMVSNet		98.38 201	98.47 189	98.12 331	98.59 397	96.19 359	99.72 53	98.79 385	97.89 198	99.44 167	99.52 267	96.13 174	98.90 397	98.64 167	97.54 296	99.28 245

JIA-IIPM		97.50 319	97.02 335	98.93 225	98.73 380	97.80 278	99.30 279	98.97 355	91.73 418	98.91 283	94.86 436	95.10 220	99.71 249	97.58 279	97.98 272	99.28 245

UWE-MVS-28		97.36 329	97.24 325	97.75 360	98.84 364	94.44 400	99.24 308	97.58 426	97.98 190	99.00 270	99.00 372	91.35 349	99.53 290	93.75 397	98.39 246	99.27 249

kuosan		90.92 400	90.11 405	93.34 408	98.78 371	85.59 433	98.15 430	93.16 448	89.37 426	92.07 429	98.38 407	81.48 429	95.19 438	62.54 447	97.04 323	99.25 250

dp		97.75 289	97.80 247	97.59 370	99.10 318	93.71 410	99.32 274	98.88 372	96.48 339	99.08 254	99.55 254	92.67 315	99.82 202	96.52 346	98.58 235	99.24 251

myMVS_eth3d28		97.69 300	97.34 312	98.73 261	99.27 273	97.52 291	99.33 272	98.78 386	98.03 186	98.82 299	98.49 402	86.64 401	99.46 295	98.44 198	98.24 258	99.23 252

thisisatest0515		98.14 222	97.79 248	99.19 193	99.50 205	98.50 235	98.61 408	96.82 432	96.95 304	99.54 147	99.43 295	91.66 343	99.86 168	98.08 232	99.51 165	99.22 253

TESTMET0.1,1		97.55 314	97.27 324	98.40 305	98.93 348	96.53 345	98.67 402	97.61 425	96.96 302	98.64 327	99.28 339	88.63 385	99.45 297	97.30 304	99.38 174	99.21 254

testing222		97.16 339	96.50 348	99.16 196	99.16 307	98.47 240	99.27 294	98.66 402	97.71 221	98.23 355	98.15 415	82.28 427	99.84 181	97.36 301	97.66 286	99.18 255

CR-MVSNet		98.17 219	97.93 236	98.87 242	99.18 297	98.49 236	99.22 315	99.33 284	96.96 302	99.56 142	99.38 311	94.33 264	99.00 380	94.83 385	98.58 235	99.14 256

RPMNet		96.72 350	95.90 363	99.19 193	99.18 297	98.49 236	99.22 315	99.52 117	88.72 429	99.56 142	97.38 426	94.08 274	99.95 71	86.87 434	98.58 235	99.14 256

testgi		97.65 308	97.50 284	98.13 330	99.36 248	96.45 348	99.42 233	99.48 176	97.76 216	97.87 375	99.45 292	91.09 353	98.81 400	94.53 387	98.52 241	99.13 258

test-LLR		98.06 231	97.90 238	98.55 283	98.79 368	97.10 309	98.67 402	97.75 422	97.34 266	98.61 332	98.85 386	94.45 261	99.45 297	97.25 306	99.38 174	99.10 259

test-mter		97.49 324	97.13 331	98.55 283	98.79 368	97.10 309	98.67 402	97.75 422	96.65 322	98.61 332	98.85 386	88.23 389	99.45 297	97.25 306	99.38 174	99.10 259

IB-MVS	95.67 18	96.22 359	95.44 373	98.57 278	99.21 289	96.70 336	98.65 406	97.74 424	96.71 317	97.27 389	98.54 401	86.03 405	99.92 114	98.47 195	86.30 430	99.10 259
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		98.86 156	98.63 170	99.54 117	99.37 245	99.66 64	99.45 215	99.54 99	96.61 327	99.01 266	99.40 305	97.09 136	99.86 168	97.68 274	99.53 164	99.10 259
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		98.33 205	98.48 188	97.90 348	99.16 307	94.78 392	99.31 277	99.11 336	97.27 272	99.45 162	99.59 239	95.33 210	99.84 181	98.48 192	98.61 232	99.09 263

hse-mvs2		97.50 319	97.14 329	98.59 274	99.49 207	97.05 315	99.28 289	99.22 321	98.94 69	99.66 109	99.42 297	94.93 226	99.65 271	99.48 58	83.80 434	99.08 264

xiu_mvs_v1_base_debu		99.29 78	99.27 68	99.34 163	99.63 148	98.97 174	99.12 334	99.51 134	98.86 75	99.84 49	99.47 286	98.18 101	99.99 4	99.50 53	99.31 182	99.08 264

xiu_mvs_v1_base		99.29 78	99.27 68	99.34 163	99.63 148	98.97 174	99.12 334	99.51 134	98.86 75	99.84 49	99.47 286	98.18 101	99.99 4	99.50 53	99.31 182	99.08 264

xiu_mvs_v1_base_debi		99.29 78	99.27 68	99.34 163	99.63 148	98.97 174	99.12 334	99.51 134	98.86 75	99.84 49	99.47 286	98.18 101	99.99 4	99.50 53	99.31 182	99.08 264

COLMAP_ROB	97.56 6	98.86 156	98.75 154	99.17 195	99.88 12	98.53 228	99.34 270	99.59 67	97.55 241	98.70 317	99.89 36	95.83 188	99.90 139	98.10 227	99.90 53	99.08 264
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AUN-MVS		96.88 347	96.31 353	98.59 274	99.48 214	97.04 318	99.27 294	99.22 321	97.44 257	98.51 339	99.41 301	91.97 332	99.66 266	97.71 270	83.83 433	99.07 269

OpenMVS	96.50 16	98.47 191	98.12 212	99.52 131	99.04 332	99.53 94	99.82 16	99.72 11	94.56 396	98.08 363	99.88 45	94.73 242	99.98 16	97.47 293	99.76 131	99.06 270

ETV-MVS		99.26 84	99.21 78	99.40 155	99.46 217	99.30 130	99.56 138	99.52 117	98.52 113	99.44 167	99.27 342	98.41 90	99.86 168	99.10 102	99.59 159	99.04 271

PatchT		97.03 344	96.44 350	98.79 257	98.99 340	98.34 246	99.16 325	99.07 343	92.13 416	99.52 151	97.31 429	94.54 256	98.98 382	88.54 427	98.73 227	99.03 272

BH-w/o		98.00 246	97.89 242	98.32 312	99.35 249	96.20 358	99.01 362	98.90 369	96.42 344	98.38 346	99.00 372	95.26 214	99.72 243	96.06 356	98.61 232	99.03 272

Fast-Effi-MVS+-dtu		98.77 173	98.83 147	98.60 273	99.41 232	96.99 322	99.52 167	99.49 164	98.11 169	99.24 219	99.34 324	96.96 144	99.79 217	97.95 242	99.45 170	99.02 274

XVG-OURS-SEG-HR		98.69 179	98.62 175	98.89 236	99.71 108	97.74 279	99.12 334	99.54 99	98.44 123	99.42 172	99.71 178	94.20 268	99.92 114	98.54 189	98.90 216	99.00 275

XVG-OURS		98.73 177	98.68 161	98.88 238	99.70 113	97.73 280	98.92 379	99.55 90	98.52 113	99.45 162	99.84 82	95.27 212	99.91 126	98.08 232	98.84 220	99.00 275

tpm cat1		97.39 328	97.36 307	97.50 373	99.17 305	93.73 409	99.43 226	99.31 298	91.27 419	98.71 311	99.08 362	94.31 266	99.77 224	96.41 351	98.50 242	99.00 275

xiu_mvs_v2_base		99.26 84	99.25 72	99.29 178	99.53 184	98.91 189	99.02 357	99.45 217	98.80 85	99.71 94	99.26 344	98.94 32	99.98 16	99.34 73	99.23 187	98.98 278

PS-MVSNAJ		99.32 73	99.32 50	99.30 175	99.57 172	98.94 184	98.97 371	99.46 206	98.92 72	99.71 94	99.24 346	99.01 18	99.98 16	99.35 68	99.66 150	98.97 279

tpmvs		97.98 248	98.02 226	97.84 354	99.04 332	94.73 393	99.31 277	99.20 325	96.10 370	98.76 307	99.42 297	94.94 225	99.81 207	96.97 325	98.45 244	98.97 279

thres600view7		97.86 266	97.51 283	98.92 227	99.72 102	97.95 270	99.59 114	98.74 391	97.94 193	99.27 212	98.62 397	91.75 337	99.86 168	93.73 398	98.19 263	98.96 281

thres400		97.77 284	97.38 305	98.92 227	99.69 118	97.96 267	99.50 184	98.73 397	97.83 207	99.17 238	98.45 404	91.67 341	99.83 194	93.22 403	98.18 264	98.96 281

TR-MVS		97.76 285	97.41 303	98.82 251	99.06 327	97.87 274	98.87 385	98.56 405	96.63 326	98.68 319	99.22 348	92.49 320	99.65 271	95.40 374	97.79 282	98.95 283

test0.0.03 1		97.71 298	97.42 302	98.56 281	98.41 405	97.82 277	98.78 393	98.63 403	97.34 266	98.05 367	98.98 376	94.45 261	98.98 382	95.04 381	97.15 322	98.89 284

baseline2		97.87 264	97.55 277	98.82 251	99.18 297	98.02 262	99.41 238	96.58 437	96.97 301	96.51 403	99.17 353	93.43 291	99.57 285	97.71 270	99.03 206	98.86 285

cascas		97.69 300	97.43 301	98.48 289	98.60 395	97.30 298	98.18 429	99.39 247	92.96 411	98.41 344	98.78 393	93.77 287	99.27 335	98.16 225	98.61 232	98.86 285

1314		98.68 180	98.54 185	99.11 202	98.89 354	98.65 215	99.27 294	99.49 164	96.89 308	97.99 368	99.56 251	97.72 117	99.83 194	97.74 266	99.27 185	98.84 287

PS-MVSNAJss		98.92 147	98.92 129	98.90 233	98.78 371	98.53 228	99.78 32	99.54 99	98.07 177	99.00 270	99.76 156	99.01 18	99.37 315	99.13 97	97.23 318	98.81 288

VortexMVS		98.67 181	98.66 165	98.68 268	99.62 154	97.96 267	99.59 114	99.41 237	98.13 165	99.31 199	99.70 182	95.48 204	99.27 335	99.40 64	97.32 315	98.79 289

FC-MVSNet-test		98.75 174	98.62 175	99.15 200	99.08 324	99.45 107	99.86 11	99.60 61	98.23 150	98.70 317	99.82 96	96.80 147	99.22 346	99.07 105	96.38 334	98.79 289

reproduce_monomvs		97.89 261	97.87 243	97.96 343	99.51 193	95.45 376	99.60 107	99.25 315	99.17 28	98.85 296	99.49 277	89.29 374	99.64 274	99.35 68	96.31 337	98.78 291

nrg030		98.64 185	98.42 191	99.28 182	99.05 330	99.69 56	99.81 20	99.46 206	98.04 184	99.01 266	99.82 96	96.69 152	99.38 312	99.34 73	94.59 379	98.78 291

FIs		98.78 171	98.63 170	99.23 190	99.18 297	99.54 91	99.83 15	99.59 67	98.28 139	98.79 304	99.81 110	96.75 150	99.37 315	99.08 104	96.38 334	98.78 291

EU-MVSNet		97.98 248	98.03 224	97.81 358	98.72 382	96.65 341	99.66 77	99.66 28	98.09 172	98.35 348	99.82 96	95.25 215	98.01 418	97.41 298	95.30 365	98.78 291

jajsoiax		98.43 194	98.28 201	98.88 238	98.60 395	98.43 242	99.82 16	99.53 112	98.19 155	98.63 329	99.80 124	93.22 298	99.44 302	99.22 89	97.50 301	98.77 295

mvs_tets		98.40 200	98.23 203	98.91 231	98.67 388	98.51 234	99.66 77	99.53 112	98.19 155	98.65 326	99.81 110	92.75 307	99.44 302	99.31 77	97.48 305	98.77 295

Anonymous20231211		97.88 262	97.54 280	98.90 233	99.71 108	98.53 228	99.48 201	99.57 77	94.16 399	98.81 300	99.68 200	93.23 296	99.42 308	98.84 141	94.42 382	98.76 297

XXY-MVS		98.38 201	98.09 217	99.24 188	99.26 276	99.32 123	99.56 138	99.55 90	97.45 254	98.71 311	99.83 87	93.23 296	99.63 280	98.88 128	96.32 336	98.76 297

SSC-MVS3.2		97.34 331	97.15 328	97.93 345	99.02 334	95.76 367	99.48 201	99.58 72	97.62 233	99.09 252	99.53 263	87.95 392	99.27 335	96.42 349	95.66 356	98.75 299

v7n		97.87 264	97.52 281	98.92 227	98.76 378	98.58 224	99.84 12	99.46 206	96.20 357	98.91 283	99.70 182	94.89 230	99.44 302	96.03 357	93.89 392	98.75 299

PS-CasMVS		97.93 254	97.59 276	98.95 221	98.99 340	99.06 163	99.68 67	99.52 117	97.13 284	98.31 350	99.68 200	92.44 325	99.05 372	98.51 190	94.08 389	98.75 299

test_djsdf		98.67 181	98.57 182	98.98 216	98.70 385	98.91 189	99.88 4	99.46 206	97.55 241	99.22 224	99.88 45	95.73 194	99.28 332	99.03 109	97.62 289	98.75 299

Effi-MVS+-dtu		98.78 171	98.89 136	98.47 294	99.33 255	96.91 328	99.57 131	99.30 303	98.47 117	99.41 176	98.99 374	96.78 148	99.74 233	98.73 155	99.38 174	98.74 303

CP-MVSNet		98.09 227	97.78 251	99.01 212	98.97 345	99.24 139	99.67 70	99.46 206	97.25 274	98.48 342	99.64 219	93.79 286	99.06 371	98.63 169	94.10 388	98.74 303

VPA-MVSNet		98.29 209	97.95 233	99.30 175	99.16 307	99.54 91	99.50 184	99.58 72	98.27 141	99.35 193	99.37 314	92.53 319	99.65 271	99.35 68	94.46 380	98.72 305

PEN-MVS		97.76 285	97.44 297	98.72 263	98.77 376	98.54 227	99.78 32	99.51 134	97.06 294	98.29 353	99.64 219	92.63 316	98.89 398	98.09 228	93.16 402	98.72 305

WBMVS		97.74 291	97.50 284	98.46 295	99.24 282	97.43 294	99.21 317	99.42 234	97.45 254	98.96 277	99.41 301	88.83 378	99.23 342	98.94 119	96.02 342	98.71 307

VPNet		97.84 271	97.44 297	99.01 212	99.21 289	98.94 184	99.48 201	99.57 77	98.38 127	99.28 207	99.73 171	88.89 377	99.39 310	99.19 91	93.27 400	98.71 307

EI-MVSNet		98.67 181	98.67 162	98.68 268	99.35 249	97.97 265	99.50 184	99.38 255	96.93 307	99.20 230	99.83 87	97.87 111	99.36 319	98.38 203	97.56 294	98.71 307

WR-MVS		98.06 231	97.73 260	99.06 206	98.86 361	99.25 138	99.19 321	99.35 271	97.30 270	98.66 320	99.43 295	93.94 279	99.21 351	98.58 179	94.28 384	98.71 307

IterMVS-LS		98.46 192	98.42 191	98.58 277	99.59 166	98.00 263	99.37 257	99.43 232	96.94 306	99.07 255	99.59 239	97.87 111	99.03 375	98.32 212	95.62 357	98.71 307
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v144192		97.92 257	97.60 275	98.87 242	98.83 365	98.65 215	99.55 152	99.34 276	96.20 357	99.32 198	99.40 305	94.36 263	99.26 338	96.37 353	95.03 371	98.70 312

v1240		97.69 300	97.32 316	98.79 257	98.85 362	98.43 242	99.48 201	99.36 264	96.11 366	99.27 212	99.36 317	93.76 288	99.24 341	94.46 388	95.23 366	98.70 312

DTE-MVSNet		97.51 318	97.19 327	98.46 295	98.63 391	98.13 256	99.84 12	99.48 176	96.68 319	97.97 370	99.67 206	92.92 303	98.56 407	96.88 333	92.60 410	98.70 312

TranMVSNet+NR-MVSNet		97.93 254	97.66 267	98.76 260	98.78 371	98.62 220	99.65 83	99.49 164	97.76 216	98.49 341	99.60 237	94.23 267	98.97 389	98.00 239	92.90 404	98.70 312

v1921920		97.80 281	97.45 292	98.84 249	98.80 367	98.53 228	99.52 167	99.34 276	96.15 363	99.24 219	99.47 286	93.98 278	99.29 331	95.40 374	95.13 369	98.69 316

v1192		97.81 279	97.44 297	98.91 231	98.88 355	98.68 212	99.51 176	99.34 276	96.18 359	99.20 230	99.34 324	94.03 276	99.36 319	95.32 376	95.18 367	98.69 316

v2v482		98.06 231	97.77 253	98.92 227	98.90 353	98.82 202	99.57 131	99.36 264	96.65 322	99.19 233	99.35 320	94.20 268	99.25 339	97.72 269	94.97 372	98.69 316

UniMVSNet_NR-MVSNet		98.22 212	97.97 230	98.96 219	98.92 350	98.98 171	99.48 201	99.53 112	97.76 216	98.71 311	99.46 290	96.43 166	99.22 346	98.57 182	92.87 406	98.69 316

OurMVSNet-221017-0		97.88 262	97.77 253	98.19 324	98.71 384	96.53 345	99.88 4	99.00 352	97.79 212	98.78 305	99.94 6	91.68 340	99.35 322	97.21 308	96.99 325	98.69 316

tt0320		95.71 372	95.07 376	97.62 367	99.05 330	95.02 387	99.25 305	99.52 117	86.81 431	97.97 370	99.72 175	83.58 420	99.15 356	96.38 352	93.35 397	98.68 321

gg-mvs-nofinetune		96.17 362	95.32 374	98.73 261	98.79 368	98.14 255	99.38 255	94.09 444	91.07 422	98.07 366	91.04 442	89.62 372	99.35 322	96.75 336	99.09 201	98.68 321

v1144		97.98 248	97.69 264	98.85 248	98.87 358	98.66 214	99.54 157	99.35 271	96.27 352	99.23 223	99.35 320	94.67 247	99.23 342	96.73 337	95.16 368	98.68 321

DU-MVS		98.08 229	97.79 248	98.96 219	98.87 358	98.98 171	99.41 238	99.45 217	97.87 200	98.71 311	99.50 274	94.82 232	99.22 346	98.57 182	92.87 406	98.68 321

NR-MVSNet		97.97 251	97.61 274	99.02 211	98.87 358	99.26 136	99.47 209	99.42 234	97.63 231	97.08 396	99.50 274	95.07 221	99.13 361	97.86 249	93.59 395	98.68 321

LPG-MVS_test		98.22 212	98.13 211	98.49 287	99.33 255	97.05 315	99.58 124	99.55 90	97.46 251	99.24 219	99.83 87	92.58 317	99.72 243	98.09 228	97.51 299	98.68 321

LGP-MVS_train				98.49 287	99.33 255	97.05 315		99.55 90	97.46 251	99.24 219	99.83 87	92.58 317	99.72 243	98.09 228	97.51 299	98.68 321

LTVRE_ROB	97.16 12	98.02 241	97.90 238	98.40 305	99.23 284	96.80 334	99.70 57	99.60 61	97.12 286	98.18 360	99.70 182	91.73 339	99.72 243	98.39 202	97.45 306	98.68 321
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		95.31 378	94.59 382	97.45 374	98.92 350	94.73 393	99.20 320	99.31 298	86.74 432	97.23 390	99.72 175	81.14 431	98.95 392	97.08 319	91.98 412	98.67 329

IterMVS-SCA-FT		97.82 277	97.75 258	98.06 333	99.57 172	96.36 351	99.02 357	99.49 164	97.18 280	98.71 311	99.72 175	92.72 310	99.14 358	97.44 296	95.86 350	98.67 329

pm-mvs1		97.68 303	97.28 321	98.88 238	99.06 327	98.62 220	99.50 184	99.45 217	96.32 348	97.87 375	99.79 136	92.47 321	99.35 322	97.54 286	93.54 396	98.67 329

v10		97.85 267	97.52 281	98.86 245	98.99 340	98.67 213	99.75 42	99.41 237	95.70 375	98.98 273	99.41 301	94.75 241	99.23 342	96.01 359	94.63 378	98.67 329

HQP_MVS		98.27 211	98.22 204	98.44 300	99.29 268	96.97 324	99.39 250	99.47 197	98.97 66	99.11 246	99.61 234	92.71 312	99.69 260	97.78 259	97.63 287	98.67 329

plane_prior5								99.47 197					99.69 260	97.78 259	97.63 287	98.67 329

SixPastTwentyTwo		97.50 319	97.33 315	98.03 334	98.65 389	96.23 357	99.77 34	98.68 400	97.14 283	97.90 373	99.93 10	90.45 359	99.18 354	97.00 322	96.43 333	98.67 329

IterMVS		97.83 274	97.77 253	98.02 336	99.58 168	96.27 355	99.02 357	99.48 176	97.22 278	98.71 311	99.70 182	92.75 307	99.13 361	97.46 294	96.00 344	98.67 329
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	97.28 8	98.10 226	97.99 228	98.44 300	99.41 232	96.96 326	99.60 107	99.56 82	98.09 172	98.15 361	99.91 23	90.87 356	99.70 255	98.88 128	97.45 306	98.67 329
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v8		97.95 253	97.63 272	98.93 225	98.95 347	98.81 204	99.80 25	99.41 237	96.03 371	99.10 249	99.42 297	94.92 228	99.30 330	96.94 328	94.08 389	98.66 338

UniMVSNet (Re)		98.29 209	98.00 227	99.13 201	99.00 337	99.36 118	99.49 196	99.51 134	97.95 192	98.97 275	99.13 358	96.30 170	99.38 312	98.36 207	93.34 398	98.66 338

pmmvs6		96.53 354	96.09 359	97.82 357	98.69 386	95.47 375	99.37 257	99.47 197	93.46 407	97.41 384	99.78 143	87.06 400	99.33 325	96.92 331	92.70 408	98.65 340

K. test v3		97.10 342	96.79 342	98.01 337	98.72 382	96.33 352	99.87 8	97.05 429	97.59 235	96.16 408	99.80 124	88.71 380	99.04 373	96.69 340	96.55 331	98.65 340

our_test_3		97.65 308	97.68 265	97.55 371	98.62 392	94.97 389	98.84 387	99.30 303	96.83 313	98.19 359	99.34 324	97.01 142	99.02 377	95.00 382	96.01 343	98.64 342

YYNet1		95.36 376	94.51 384	97.92 346	97.89 411	97.10 309	99.10 342	99.23 319	93.26 409	80.77 441	99.04 367	92.81 306	98.02 417	94.30 389	94.18 386	98.64 342

MDA-MVSNet_test_wron		95.45 374	94.60 381	98.01 337	98.16 408	97.21 305	99.11 340	99.24 318	93.49 406	80.73 442	98.98 376	93.02 300	98.18 413	94.22 393	94.45 381	98.64 342

Baseline_NR-MVSNet		97.76 285	97.45 292	98.68 268	99.09 321	98.29 247	99.41 238	98.85 376	95.65 376	98.63 329	99.67 206	94.82 232	99.10 368	98.07 235	92.89 405	98.64 342

HQP4-MVS										98.66 320			99.64 274			98.64 342

HQP-MVS		98.02 241	97.90 238	98.37 308	99.19 294	96.83 331	98.98 368	99.39 247	98.24 147	98.66 320	99.40 305	92.47 321	99.64 274	97.19 312	97.58 292	98.64 342

ACMM	97.58 5	98.37 203	98.34 196	98.48 289	99.41 232	97.10 309	99.56 138	99.45 217	98.53 112	99.04 263	99.85 70	93.00 301	99.71 249	98.74 153	97.45 306	98.64 342
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs5		97.52 316	97.30 318	98.16 326	98.57 398	96.73 335	99.27 294	98.90 369	96.14 364	98.37 347	99.53 263	91.54 346	99.14 358	97.51 288	95.87 349	98.63 349

v148		97.79 283	97.55 277	98.50 286	98.74 379	97.72 282	99.54 157	99.33 284	96.26 353	98.90 285	99.51 271	94.68 246	99.14 358	97.83 253	93.15 403	98.63 349

MDA-MVSNet-bldmvs		94.96 381	93.98 388	97.92 346	98.24 407	97.27 300	99.15 328	99.33 284	93.80 402	80.09 443	99.03 368	88.31 388	97.86 422	93.49 401	94.36 383	98.62 351

TransMVSNet (Re)		97.15 340	96.58 346	98.86 245	99.12 313	98.85 196	99.49 196	98.91 367	95.48 378	97.16 394	99.80 124	93.38 292	99.11 366	94.16 394	91.73 413	98.62 351

lessismore_v0				97.79 359	98.69 386	95.44 378		94.75 442		95.71 412	99.87 56	88.69 381	99.32 327	95.89 360	94.93 374	98.62 351

MVSTER		98.49 189	98.32 198	99.00 214	99.35 249	99.02 167	99.54 157	99.38 255	97.41 261	99.20 230	99.73 171	93.86 284	99.36 319	98.87 131	97.56 294	98.62 351

GBi-Net		97.68 303	97.48 286	98.29 315	99.51 193	97.26 302	99.43 226	99.48 176	96.49 336	99.07 255	99.32 332	90.26 361	98.98 382	97.10 316	96.65 327	98.62 351

test1		97.68 303	97.48 286	98.29 315	99.51 193	97.26 302	99.43 226	99.48 176	96.49 336	99.07 255	99.32 332	90.26 361	98.98 382	97.10 316	96.65 327	98.62 351

FMVSNet1		96.84 348	96.36 352	98.29 315	99.32 262	97.26 302	99.43 226	99.48 176	95.11 383	98.55 337	99.32 332	83.95 418	98.98 382	95.81 362	96.26 338	98.62 351

ACMP	97.20 11	98.06 231	97.94 235	98.45 297	99.37 245	97.01 320	99.44 221	99.49 164	97.54 244	98.45 343	99.79 136	91.95 333	99.72 243	97.91 244	97.49 304	98.62 351
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMH+	97.24 10	97.92 257	97.78 251	98.32 312	99.46 217	96.68 340	99.56 138	99.54 99	98.41 125	97.79 379	99.87 56	90.18 365	99.66 266	98.05 236	97.18 321	98.62 351

ppachtmachnet_test		97.49 324	97.45 292	97.61 369	98.62 392	95.24 382	98.80 391	99.46 206	96.11 366	98.22 357	99.62 230	96.45 164	98.97 389	93.77 396	95.97 348	98.61 360

OPM-MVS		98.19 216	98.10 214	98.45 297	98.88 355	97.07 313	99.28 289	99.38 255	98.57 108	99.22 224	99.81 110	92.12 329	99.66 266	98.08 232	97.54 296	98.61 360
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
WR-MVS_H		98.13 223	97.87 243	98.90 233	99.02 334	98.84 197	99.70 57	99.59 67	97.27 272	98.40 345	99.19 352	95.53 201	99.23 342	98.34 209	93.78 394	98.61 360

MIMVSNet1		95.51 373	95.04 378	96.92 390	97.38 419	95.60 369	99.52 167	99.50 154	93.65 404	96.97 399	99.17 353	85.28 412	96.56 434	88.36 428	95.55 360	98.60 363

N_pmnet		94.95 382	95.83 365	92.31 412	98.47 402	79.33 444	99.12 334	92.81 450	93.87 401	97.68 380	99.13 358	93.87 283	99.01 379	91.38 417	96.19 339	98.59 364

FMVSNet2		97.72 295	97.36 307	98.80 256	99.51 193	98.84 197	99.45 215	99.42 234	96.49 336	98.86 295	99.29 337	90.26 361	98.98 382	96.44 348	96.56 330	98.58 365

anonymousdsp		98.44 193	98.28 201	98.94 223	98.50 401	98.96 178	99.77 34	99.50 154	97.07 292	98.87 291	99.77 152	94.76 240	99.28 332	98.66 165	97.60 290	98.57 366

FMVSNet3		98.03 239	97.76 257	98.84 249	99.39 240	98.98 171	99.40 246	99.38 255	96.67 320	99.07 255	99.28 339	92.93 302	98.98 382	97.10 316	96.65 327	98.56 367

XVG-ACMP-BASELINE		97.83 274	97.71 262	98.20 323	99.11 315	96.33 352	99.41 238	99.52 117	98.06 181	99.05 262	99.50 274	89.64 371	99.73 239	97.73 267	97.38 313	98.53 368

Patchmtry		97.75 289	97.40 304	98.81 254	99.10 318	98.87 192	99.11 340	99.33 284	94.83 391	98.81 300	99.38 311	94.33 264	99.02 377	96.10 355	95.57 359	98.53 368

miper_lstm_enhance		98.00 246	97.91 237	98.28 319	99.34 254	97.43 294	98.88 383	99.36 264	96.48 339	98.80 302	99.55 254	95.98 179	98.91 395	97.27 305	95.50 362	98.51 370

USDC		97.34 331	97.20 326	97.75 360	99.07 325	95.20 383	98.51 415	99.04 347	97.99 189	98.31 350	99.86 63	89.02 375	99.55 288	95.67 368	97.36 314	98.49 371

c3_l		98.12 225	98.04 223	98.38 307	99.30 264	97.69 286	98.81 390	99.33 284	96.67 320	98.83 297	99.34 324	97.11 135	98.99 381	97.58 279	95.34 364	98.48 372

CLD-MVS		98.16 220	98.10 214	98.33 310	99.29 268	96.82 333	98.75 396	99.44 226	97.83 207	99.13 242	99.55 254	92.92 303	99.67 263	98.32 212	97.69 285	98.48 372
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		98.05 236	97.96 231	98.33 310	99.26 276	97.38 296	98.56 413	99.31 298	96.65 322	98.88 288	99.52 267	96.58 157	99.12 365	97.39 299	95.53 361	98.47 374

Anonymous20231206		96.22 359	96.03 360	96.79 393	97.31 422	94.14 405	99.63 95	99.08 340	96.17 360	97.04 397	99.06 365	93.94 279	97.76 424	86.96 433	95.06 370	98.47 374

FMVSNet5		96.43 357	96.19 356	97.15 380	99.11 315	95.89 364	99.32 274	99.52 117	94.47 398	98.34 349	99.07 363	87.54 397	97.07 430	92.61 412	95.72 354	98.47 374

cl____		98.01 244	97.84 246	98.55 283	99.25 280	97.97 265	98.71 400	99.34 276	96.47 341	98.59 335	99.54 259	95.65 197	99.21 351	97.21 308	95.77 351	98.46 377

DIV-MVS_self_test		98.01 244	97.85 245	98.48 289	99.24 282	97.95 270	98.71 400	99.35 271	96.50 335	98.60 334	99.54 259	95.72 195	99.03 375	97.21 308	95.77 351	98.46 377

pmmvs4		98.13 223	97.90 238	98.81 254	98.61 394	98.87 192	98.99 365	99.21 324	96.44 342	99.06 260	99.58 243	95.90 186	99.11 366	97.18 314	96.11 341	98.46 377

cl22		97.85 267	97.64 271	98.48 289	99.09 321	97.87 274	98.60 410	99.33 284	97.11 289	98.87 291	99.22 348	92.38 326	99.17 355	98.21 219	95.99 345	98.42 380

V42		98.06 231	97.79 248	98.86 245	98.98 343	98.84 197	99.69 61	99.34 276	96.53 334	99.30 203	99.37 314	94.67 247	99.32 327	97.57 283	94.66 377	98.42 380

PVSNet_BlendedMVS		98.86 156	98.80 148	99.03 210	99.76 73	98.79 205	99.28 289	99.91 3	97.42 260	99.67 104	99.37 314	97.53 119	99.88 159	98.98 114	97.29 316	98.42 380

UnsupCasMVSNet_eth		96.44 356	96.12 357	97.40 376	98.65 389	95.65 368	99.36 262	99.51 134	97.13 284	96.04 410	98.99 374	88.40 387	98.17 414	96.71 338	90.27 421	98.40 383

TinyColmap		97.12 341	96.89 340	97.83 355	99.07 325	95.52 374	98.57 411	98.74 391	97.58 237	97.81 378	99.79 136	88.16 390	99.56 286	95.10 379	97.21 319	98.39 384

miper_ehance_all_eth		98.18 218	98.10 214	98.41 303	99.23 284	97.72 282	98.72 399	99.31 298	96.60 330	98.88 288	99.29 337	97.29 129	99.13 361	97.60 277	95.99 345	98.38 385

thres100view900		97.76 285	97.45 292	98.69 267	99.72 102	97.86 276	99.59 114	98.74 391	97.93 194	99.26 217	98.62 397	91.75 337	99.83 194	93.22 403	98.18 264	98.37 386

tfpn200view9		97.72 295	97.38 305	98.72 263	99.69 118	97.96 267	99.50 184	98.73 397	97.83 207	99.17 238	98.45 404	91.67 341	99.83 194	93.22 403	98.18 264	98.37 386

test_fmvs2		97.25 336	97.30 318	97.09 384	99.43 225	93.31 415	99.73 51	98.87 374	98.83 79	99.28 207	99.80 124	84.45 416	99.66 266	97.88 246	97.45 306	98.30 388

miper_enhance_ethall		98.16 220	98.08 218	98.41 303	98.96 346	97.72 282	98.45 417	99.32 294	96.95 304	98.97 275	99.17 353	97.06 139	99.22 346	97.86 249	95.99 345	98.29 389

tfpnnormal		97.84 271	97.47 289	98.98 216	99.20 291	99.22 141	99.64 89	99.61 54	96.32 348	98.27 354	99.70 182	93.35 295	99.44 302	95.69 366	95.40 363	98.27 390

test20.03		96.12 363	95.96 362	96.63 394	97.44 418	95.45 376	99.51 176	99.38 255	96.55 333	96.16 408	99.25 345	93.76 288	96.17 435	87.35 432	94.22 385	98.27 390

test_method		91.10 398	91.36 400	90.31 418	95.85 431	73.72 451	94.89 439	99.25 315	68.39 442	95.82 411	99.02 370	80.50 432	98.95 392	93.64 399	94.89 376	98.25 392

ITE_SJBPF				98.08 332	99.29 268	96.37 350		98.92 362	98.34 133	98.83 297	99.75 160	91.09 353	99.62 281	95.82 361	97.40 312	98.25 392

KD-MVS_self_test		95.00 380	94.34 385	96.96 387	97.07 427	95.39 379	99.56 138	99.44 226	95.11 383	97.13 395	97.32 428	91.86 335	97.27 429	90.35 421	81.23 437	98.23 394

mmtdpeth		96.95 345	96.71 344	97.67 365	99.33 255	94.90 391	99.89 2	99.28 309	98.15 160	99.72 92	98.57 400	86.56 403	99.90 139	99.82 25	89.02 425	98.20 395

EG-PatchMatch MVS		95.97 366	95.69 367	96.81 392	97.78 413	92.79 418	99.16 325	98.93 359	96.16 361	94.08 421	99.22 348	82.72 423	99.47 293	95.67 368	97.50 301	98.17 396

mvs5depth		96.66 351	96.22 355	97.97 341	97.00 428	96.28 354	98.66 405	99.03 349	96.61 327	96.93 400	99.79 136	87.20 399	99.47 293	96.65 344	94.13 387	98.16 397

D2MVS		98.41 197	98.50 187	98.15 329	99.26 276	96.62 342	99.40 246	99.61 54	97.71 221	98.98 273	99.36 317	96.04 177	99.67 263	98.70 158	97.41 311	98.15 398

APD_test1		95.87 367	96.49 349	94.00 405	99.53 184	84.01 434	99.54 157	99.32 294	95.91 373	97.99 368	99.85 70	85.49 409	99.88 159	91.96 414	98.84 220	98.12 399

ttmdpeth		97.80 281	97.63 272	98.29 315	98.77 376	97.38 296	99.64 89	99.36 264	98.78 89	96.30 406	99.58 243	92.34 328	99.39 310	98.36 207	95.58 358	98.10 400

TDRefinement		95.42 375	94.57 383	97.97 341	89.83 446	96.11 361	99.48 201	98.75 388	96.74 315	96.68 402	99.88 45	88.65 383	99.71 249	98.37 205	82.74 435	98.09 401

Anonymous20240521		96.20 361	95.89 364	97.13 382	97.72 416	94.96 390	99.79 31	99.29 307	93.01 410	97.20 393	99.03 368	89.69 370	98.36 411	91.16 418	96.13 340	98.07 402

API-MVS		99.04 133	99.03 104	99.06 206	99.40 237	99.31 127	99.55 152	99.56 82	98.54 111	99.33 197	99.39 309	98.76 55	99.78 222	96.98 324	99.78 125	98.07 402

new_pmnet		96.38 358	96.03 360	97.41 375	98.13 409	95.16 386	99.05 349	99.20 325	93.94 400	97.39 387	98.79 392	91.61 345	99.04 373	90.43 420	95.77 351	98.05 404

thres200		97.61 311	97.28 321	98.62 272	99.64 145	98.03 261	99.26 303	98.74 391	97.68 226	99.09 252	98.32 410	91.66 343	99.81 207	92.88 408	98.22 259	98.03 405

KD-MVS_2432*1600		94.62 383	93.72 391	97.31 377	97.19 425	95.82 365	98.34 421	99.20 325	95.00 387	97.57 381	98.35 408	87.95 392	98.10 415	92.87 409	77.00 440	98.01 406

miper_refine_blended		94.62 383	93.72 391	97.31 377	97.19 425	95.82 365	98.34 421	99.20 325	95.00 387	97.57 381	98.35 408	87.95 392	98.10 415	92.87 409	77.00 440	98.01 406

DeepMVS_CX				93.34 408	99.29 268	82.27 437		99.22 321	85.15 434	96.33 405	99.05 366	90.97 355	99.73 239	93.57 400	97.77 283	98.01 406

MVStest1		96.08 365	95.48 370	97.89 349	98.93 348	96.70 336	99.56 138	99.35 271	92.69 414	91.81 431	99.46 290	89.90 367	98.96 391	95.00 382	92.61 409	98.00 409

CL-MVSNet_self_test		94.49 385	93.97 389	96.08 399	96.16 430	93.67 412	98.33 423	99.38 255	95.13 381	97.33 388	98.15 415	92.69 314	96.57 433	88.67 426	79.87 438	97.99 410

GG-mvs-BLEND				98.45 297	98.55 399	98.16 253	99.43 226	93.68 445		97.23 390	98.46 403	89.30 373	99.22 346	95.43 373	98.22 259	97.98 411

pmmvs3		94.09 389	93.25 395	96.60 395	94.76 440	94.49 399	98.92 379	98.18 417	89.66 423	96.48 404	98.06 421	86.28 404	97.33 428	89.68 423	87.20 429	97.97 412

LF4IMVS		97.52 316	97.46 291	97.70 364	98.98 343	95.55 371	99.29 284	98.82 379	98.07 177	98.66 320	99.64 219	89.97 366	99.61 282	97.01 321	96.68 326	97.94 413

test_0402		96.64 352	96.24 354	97.85 352	98.85 362	96.43 349	99.44 221	99.26 313	93.52 405	96.98 398	99.52 267	88.52 386	99.20 353	92.58 413	97.50 301	97.93 414

MVP-Stereo		97.81 279	97.75 258	97.99 340	97.53 417	96.60 344	98.96 372	98.85 376	97.22 278	97.23 390	99.36 317	95.28 211	99.46 295	95.51 370	99.78 125	97.92 415
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MS-PatchMatch		97.24 338	97.32 316	96.99 385	98.45 403	93.51 414	98.82 389	99.32 294	97.41 261	98.13 362	99.30 335	88.99 376	99.56 286	95.68 367	99.80 116	97.90 416

mvsany_test3		93.77 390	93.45 394	94.74 403	95.78 432	88.01 429	99.64 89	98.25 412	98.28 139	94.31 420	97.97 422	68.89 437	98.51 409	97.50 289	90.37 420	97.71 417

ambc				93.06 411	92.68 442	82.36 436	98.47 416	98.73 397		95.09 417	97.41 425	55.55 443	99.10 368	96.42 349	91.32 414	97.71 417

test_vis1_rt		95.81 369	95.65 368	96.32 398	99.67 125	91.35 425	99.49 196	96.74 434	98.25 146	95.24 413	98.10 419	74.96 434	99.90 139	99.53 49	98.85 219	97.70 419

new-patchmatchnet		94.48 386	94.08 387	95.67 401	95.08 438	92.41 420	99.18 323	99.28 309	94.55 397	93.49 424	97.37 427	87.86 395	97.01 431	91.57 416	88.36 426	97.61 420

pmmvs-eth3d		95.34 377	94.73 380	97.15 380	95.53 435	95.94 363	99.35 267	99.10 337	95.13 381	93.55 423	97.54 424	88.15 391	97.91 420	94.58 386	89.69 424	97.61 420

UnsupCasMVSNet_bld		93.53 391	92.51 397	96.58 396	97.38 419	93.82 407	98.24 426	99.48 176	91.10 421	93.10 425	96.66 431	74.89 435	98.37 410	94.03 395	87.71 428	97.56 422

PM-MVS		92.96 394	92.23 398	95.14 402	95.61 433	89.98 428	99.37 257	98.21 415	94.80 392	95.04 418	97.69 423	65.06 438	97.90 421	94.30 389	89.98 423	97.54 423

EGC-MVSNET		82.80 407	77.86 413	97.62 367	97.91 410	96.12 360	99.33 272	99.28 309	8.40 450	25.05 451	99.27 342	84.11 417	99.33 325	89.20 424	98.22 259	97.42 424

test_f		91.90 397	91.26 401	93.84 406	95.52 436	85.92 431	99.69 61	98.53 408	95.31 380	93.87 422	96.37 433	55.33 444	98.27 412	95.70 365	90.98 418	97.32 425

test_fmvs3		92.10 396	91.77 399	93.08 410	96.19 429	86.25 430	99.82 16	98.62 404	96.65 322	95.19 416	96.90 430	55.05 445	95.93 437	96.63 345	90.92 419	97.06 426

LCM-MVSNet		86.80 405	85.22 409	91.53 415	87.81 447	80.96 441	98.23 428	98.99 353	71.05 440	90.13 435	96.51 432	48.45 448	96.88 432	90.51 419	85.30 431	96.76 427

OpenMVS_ROB	92.34 20	94.38 387	93.70 393	96.41 397	97.38 419	93.17 416	99.06 347	98.75 388	86.58 433	94.84 419	98.26 412	81.53 428	99.32 327	89.01 425	97.87 278	96.76 427

WB-MVS		93.10 393	94.10 386	90.12 419	95.51 437	81.88 439	99.73 51	99.27 312	95.05 386	93.09 426	98.91 385	94.70 245	91.89 443	76.62 441	94.02 391	96.58 429

SSC-MVS		92.73 395	93.73 390	89.72 420	95.02 439	81.38 440	99.76 37	99.23 319	94.87 390	92.80 427	98.93 381	94.71 244	91.37 444	74.49 443	93.80 393	96.42 430

CMPMVS	69.68 23	94.13 388	94.90 379	91.84 413	97.24 423	80.01 443	98.52 414	99.48 176	89.01 427	91.99 430	99.67 206	85.67 407	99.13 361	95.44 372	97.03 324	96.39 431
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testf1		90.42 401	90.68 402	89.65 421	97.78 413	73.97 449	99.13 331	98.81 381	89.62 424	91.80 432	98.93 381	62.23 441	98.80 401	86.61 435	91.17 415	96.19 432

APD_test2		90.42 401	90.68 402	89.65 421	97.78 413	73.97 449	99.13 331	98.81 381	89.62 424	91.80 432	98.93 381	62.23 441	98.80 401	86.61 435	91.17 415	96.19 432

WB-MVSnew		97.65 308	97.65 268	97.63 366	98.78 371	97.62 288	99.13 331	98.33 410	97.36 265	99.07 255	98.94 380	95.64 198	99.15 356	92.95 407	98.68 230	96.12 434

PMMVS2		86.87 404	85.37 408	91.35 416	90.21 445	83.80 435	98.89 382	97.45 428	83.13 437	91.67 434	95.03 434	48.49 447	94.70 440	85.86 437	77.62 439	95.54 435

tmp_tt		82.80 407	81.52 410	86.66 423	66.61 453	68.44 452	92.79 442	97.92 419	68.96 441	80.04 444	99.85 70	85.77 406	96.15 436	97.86 249	43.89 446	95.39 436

FPMVS		84.93 406	85.65 407	82.75 427	86.77 448	63.39 453	98.35 420	98.92 362	74.11 439	83.39 438	98.98 376	50.85 446	92.40 442	84.54 438	94.97 372	92.46 437

Gipuma		90.99 399	90.15 404	93.51 407	98.73 380	90.12 427	93.98 440	99.45 217	79.32 438	92.28 428	94.91 435	69.61 436	97.98 419	87.42 431	95.67 355	92.45 438
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ANet_high		77.30 411	74.86 415	84.62 425	75.88 451	77.61 445	97.63 436	93.15 449	88.81 428	64.27 446	89.29 443	36.51 450	83.93 448	75.89 442	52.31 445	92.33 439

test_vis3_rt		87.04 403	85.81 406	90.73 417	93.99 441	81.96 438	99.76 37	90.23 452	92.81 413	81.35 440	91.56 440	40.06 449	99.07 370	94.27 391	88.23 427	91.15 440

MVE	76.82 21	76.91 412	74.31 416	84.70 424	85.38 450	76.05 448	96.88 438	93.17 447	67.39 443	71.28 445	89.01 444	21.66 455	87.69 445	71.74 444	72.29 442	90.35 441
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 413	74.97 414	79.01 429	70.98 452	55.18 454	93.37 441	98.21 415	65.08 446	61.78 447	93.83 437	21.74 454	92.53 441	78.59 439	91.12 417	89.34 442
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		80.02 410	79.22 412	82.43 428	91.19 443	76.40 446	97.55 437	92.49 451	66.36 445	83.01 439	91.27 441	64.63 439	85.79 447	65.82 446	60.65 444	85.08 443

E-PMN		80.61 409	79.88 411	82.81 426	90.75 444	76.38 447	97.69 434	95.76 439	66.44 444	83.52 437	92.25 439	62.54 440	87.16 446	68.53 445	61.40 443	84.89 444

test123		39.01 416	42.50 418	28.53 431	39.17 454	20.91 456	98.75 396	19.17 456	19.83 449	38.57 448	66.67 446	33.16 451	15.42 450	37.50 450	29.66 448	49.26 445

testmvs		39.17 415	43.78 417	25.37 432	36.04 455	16.84 457	98.36 419	26.56 454	20.06 448	38.51 449	67.32 445	29.64 452	15.30 451	37.59 449	39.90 447	43.98 446

wuyk23d		40.18 414	41.29 419	36.84 430	86.18 449	49.12 455	79.73 443	22.81 455	27.64 447	25.46 450	28.45 450	21.98 453	48.89 449	55.80 448	23.56 449	12.51 447

mmdepth		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.13 420	0.17 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	1.57 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		24.64 417	32.85 420	0.00 433	0.00 456	0.00 458	0.00 444	99.51 134	0.00 451	0.00 452	99.56 251	96.58 157	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		8.27 419	11.03 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	99.01 18	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		8.30 418	11.06 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	99.58 243	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.02 421	0.03 424	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.27 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						97.16 306								95.47 371

FOURS1					99.91 1	99.93 1	99.87 8	99.56 82	99.10 40	99.81 60

test_one_0601					99.81 49	99.88 9		99.49 164	98.97 66	99.65 116	99.81 110	99.09 14

eth-test2					0.00 456

eth-test					0.00 456

ZD-MVS					99.71 108	99.79 35		99.61 54	96.84 311	99.56 142	99.54 259	98.58 75	99.96 37	96.93 329	99.75 133

test_241102_ONE					99.84 33	99.90 2		99.48 176	99.07 49	99.91 27	99.74 165	99.20 7	99.76 228

9.14			99.10 91		99.72 102		99.40 246	99.51 134	97.53 245	99.64 121	99.78 143	98.84 44	99.91 126	97.63 275	99.82 108

save fliter					99.76 73	99.59 81	99.14 330	99.40 244	99.00 58

test0726					99.85 27	99.89 5	99.62 100	99.50 154	99.10 40	99.86 46	99.82 96	98.94 32

test_part2					99.81 49	99.83 20				99.77 75

sam_mvs												94.72 243

MTGPA								99.47 197

test_post1							99.23 311				65.14 448	94.18 271	99.71 249	97.58 279

test_post											65.99 447	94.65 249	99.73 239

patchmatchnet-post											98.70 395	94.79 235	99.74 233

MTMP							99.54 157	98.88 372

gm-plane-assit					98.54 400	92.96 417			94.65 395		99.15 356		99.64 274	97.56 284

TEST9					99.67 125	99.65 68	99.05 349	99.41 237	96.22 356	98.95 278	99.49 277	98.77 54	99.91 126

test_8					99.67 125	99.61 78	99.03 354	99.41 237	96.28 350	98.93 281	99.48 283	98.76 55	99.91 126

agg_prior					99.67 125	99.62 76		99.40 244		98.87 291			99.91 126

test_prior4						99.56 87	98.99 365

test_prior2							98.96 372		98.34 133	99.01 266	99.52 267	98.68 67		97.96 241	99.74 136

旧先验2							98.96 372		96.70 318	99.47 159			99.94 84	98.19 221

新几何2							99.01 362

原ACMM2							98.95 375

testdata2													99.95 71	96.67 341

segment_acmp												98.96 25

testdata1							98.85 386		98.32 136

plane_prior7					99.29 268	97.03 319

plane_prior6					99.27 273	96.98 323						92.71 312

plane_prior4											99.61 234

plane_prior3						97.00 321			98.69 98	99.11 246

plane_prior2							99.39 250		98.97 66

plane_prior1					99.26 276

plane_prior						96.97 324	99.21 317		98.45 120						97.60 290

n2								0.00 457

nn								0.00 457

door-mid								98.05 418

test11								99.35 271

door								97.92 419

HQP5-MVS						96.83 331

HQP-NCC					99.19 294		98.98 368		98.24 147	98.66 320

ACMP_Plane					99.19 294		98.98 368		98.24 147	98.66 320

BP-MVS														97.19 312

HQP3-MVS								99.39 247							97.58 292

HQP2-MVS												92.47 321

NP-MVS					99.23 284	96.92 327					99.40 305

MDTV_nov1_ep13			98.32 198		99.11 315	94.44 400	99.27 294	98.74 391	97.51 248	99.40 181	99.62 230	94.78 236	99.76 228	97.59 278	98.81 224

ACMMP++_ref															97.19 320

ACMMP++															97.43 310

Test By Simon												98.75 58

High-resolution multi-view benchmark