High-res multi-view results

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

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

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

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

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

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

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

fmvsm_s_conf0.1_n_a		99.85 11	99.83 20	99.91 2	99.95 15	99.82 35	99.10 202	99.98 11	99.99 2	99.98 13	99.91 24	99.68 26	99.93 93	99.93 18	99.99 16	99.99 1

test_fmvsmconf0.01_n		99.89 3	99.88 6	99.91 2	99.98 3	99.76 62	99.12 197	100.00 1	100.00 1	99.99 7	99.91 24	99.98 1	100.00 1	99.97 4	100.00 1	99.99 1

fmvsm_s_conf0.1_n		99.86 9	99.85 16	99.89 11	99.93 26	99.78 49	99.07 213	99.98 11	99.99 2	99.98 13	99.90 29	99.88 8	99.92 115	99.93 18	99.99 16	99.98 3

test_fmvsmconf0.1_n		99.87 8	99.86 12	99.91 2	99.97 6	99.74 74	99.01 226	99.99 10	99.99 2	99.98 13	99.88 42	99.97 2	99.99 8	99.96 9	100.00 1	99.98 3

test_vis3_rt		99.89 3	99.90 3	99.87 21	99.98 3	99.75 68	99.70 35	100.00 1	99.73 74	100.00 1	99.89 34	99.79 16	99.88 188	99.98 1	100.00 1	99.98 3

test_fmvs3		99.83 19	99.93 2	99.53 173	99.96 7	98.62 272	99.67 49	100.00 1	99.95 18	100.00 1	99.95 13	99.85 10	99.99 8	99.98 1	99.99 16	99.98 3

test_cas_vis1_n_1920		99.76 29	99.86 12	99.45 191	99.93 26	98.40 284	99.30 135	99.98 11	99.94 22	99.99 7	99.89 34	99.80 15	99.97 32	99.96 9	99.97 54	99.97 7

test_vis1_n_1920		99.72 34	99.88 6	99.27 245	99.93 26	97.84 320	99.34 122	100.00 1	99.99 2	99.99 7	99.82 73	99.87 9	99.99 8	99.97 4	99.99 16	99.97 7

test_f		99.75 30	99.88 6	99.37 219	99.96 7	98.21 296	99.51 90	100.00 1	99.94 22	100.00 1	99.93 17	99.58 34	99.94 76	99.97 4	99.99 16	99.97 7

test_fmvs2		99.72 34	99.85 16	99.34 226	99.91 32	98.08 309	99.48 96	100.00 1	99.90 28	99.99 7	99.91 24	99.50 44	99.98 19	99.98 1	99.99 16	99.96 10

test_vis1_n		99.68 44	99.79 27	99.36 223	99.94 19	98.18 299	99.52 86	100.00 1	99.86 44	100.00 1	99.88 42	98.99 100	99.96 53	99.97 4	99.96 69	99.95 11

tmp_tt		95.75 355	95.42 353	96.76 366	89.90 401	94.42 378	98.86 249	97.87 372	78.01 393	99.30 262	99.69 152	97.70 239	95.89 397	99.29 100	98.14 376	99.95 11

mvsany_test3		99.85 11	99.88 6	99.75 73	99.95 15	99.37 177	99.53 85	99.98 11	99.77 72	99.99 7	99.95 13	99.85 10	99.94 76	99.95 12	99.98 39	99.94 13

PS-MVSNAJss		99.84 15	99.82 22	99.89 11	99.96 7	99.77 54	99.68 45	99.85 51	99.95 18	99.98 13	99.92 21	99.28 64	99.98 19	99.75 37	100.00 1	99.94 13

fmvsm_s_conf0.5_n_a		99.82 21	99.79 27	99.89 11	99.85 57	99.82 35	99.03 221	99.96 23	99.99 2	99.97 19	99.84 62	99.58 34	99.93 93	99.92 20	99.98 39	99.93 15

test_fmvsmconf_n		99.85 11	99.84 19	99.88 17	99.91 32	99.73 77	98.97 238	99.98 11	99.99 2	99.96 23	99.85 56	99.93 7	99.99 8	99.94 15	99.99 16	99.93 15

test_fmvs1_n		99.68 44	99.81 23	99.28 242	99.95 15	97.93 318	99.49 95	100.00 1	99.82 57	99.99 7	99.89 34	99.21 73	99.98 19	99.97 4	99.98 39	99.93 15

fmvsm_s_conf0.5_n		99.83 19	99.81 23	99.87 21	99.85 57	99.78 49	99.03 221	99.96 23	99.99 2	99.97 19	99.84 62	99.78 17	99.92 115	99.92 20	99.99 16	99.92 18

mvs_tets		99.90 2	99.90 3	99.90 8	99.96 7	99.79 46	99.72 30	99.88 41	99.92 26	99.98 13	99.93 17	99.94 4	99.98 19	99.77 36	100.00 1	99.92 18

UA-Net		99.78 25	99.76 34	99.86 25	99.72 139	99.71 84	99.91 3	99.95 28	99.96 16	99.71 131	99.91 24	99.15 79	99.97 32	99.50 65	100.00 1	99.90 20

RRT_MVS		99.67 50	99.59 63	99.91 2	99.94 19	99.88 12	99.78 12	99.27 300	99.87 40	99.91 42	99.87 47	98.04 217	99.96 53	99.68 42	99.99 16	99.90 20

jajsoiax		99.89 3	99.89 5	99.89 11	99.96 7	99.78 49	99.70 35	99.86 46	99.89 34	99.98 13	99.90 29	99.94 4	99.98 19	99.75 37	100.00 1	99.90 20

EU-MVSNet		99.39 114	99.62 54	98.72 314	99.88 45	96.44 356	99.56 81	99.85 51	99.90 28	99.90 48	99.85 56	98.09 213	99.83 267	99.58 52	99.95 82	99.90 20

test_djsdf		99.84 15	99.81 23	99.91 2	99.94 19	99.84 24	99.77 15	99.80 77	99.73 74	99.97 19	99.92 21	99.77 19	99.98 19	99.43 71	100.00 1	99.90 20

MM				99.55 167		98.81 252	99.05 214	97.79 373	99.99 2	99.48 215	99.59 217	96.29 297	99.95 62	99.94 15	99.98 39	99.88 25

test_fmvsmvis_n_1920		99.84 15	99.86 12	99.81 39	99.88 45	99.55 137	99.17 177	99.98 11	99.99 2	99.96 23	99.84 62	99.96 3	99.99 8	99.96 9	99.99 16	99.88 25

MVS_0304		99.17 175	99.03 185	99.59 151	99.44 258	98.90 246	99.04 217	95.32 389	99.99 2	99.68 141	99.57 229	98.30 195	99.97 32	99.94 15	99.98 39	99.88 25

CVMVSNet		98.61 251	98.88 215	97.80 347	99.58 190	93.60 383	99.26 149	99.64 161	99.66 98	99.72 126	99.67 167	93.26 329	99.93 93	99.30 97	99.81 186	99.87 28

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 18	99.99 2	100.00 1	99.98 10	99.78 17	100.00 1	99.92 20	100.00 1	99.87 28

SSC-MVS		99.52 80	99.42 97	99.83 32	99.86 53	99.65 107	99.52 86	99.81 73	99.87 40	99.81 86	99.79 93	96.78 279	99.99 8	99.83 30	99.51 289	99.86 30

FC-MVSNet-test		99.70 38	99.65 48	99.86 25	99.88 45	99.86 18	99.72 30	99.78 89	99.90 28	99.82 79	99.83 66	98.45 175	99.87 202	99.51 63	99.97 54	99.86 30

PS-CasMVS		99.66 52	99.58 67	99.89 11	99.80 85	99.85 19	99.66 53	99.73 111	99.62 105	99.84 74	99.71 139	98.62 147	99.96 53	99.30 97	99.96 69	99.86 30

anonymousdsp		99.80 23	99.77 31	99.90 8	99.96 7	99.88 12	99.73 27	99.85 51	99.70 85	99.92 39	99.93 17	99.45 45	99.97 32	99.36 84	100.00 1	99.85 33

UniMVSNet_ETH3D		99.85 11	99.83 20	99.90 8	99.89 40	99.91 4	99.89 4	99.71 123	99.93 24	99.95 30	99.89 34	99.71 22	99.96 53	99.51 63	99.97 54	99.84 34

CP-MVSNet		99.54 77	99.43 95	99.87 21	99.76 116	99.82 35	99.57 79	99.61 173	99.54 118	99.80 90	99.64 178	97.79 236	99.95 62	99.21 107	99.94 93	99.84 34

Test_1112_low_res		98.95 219	98.73 229	99.63 134	99.68 162	99.15 219	98.09 325	99.80 77	97.14 344	99.46 221	99.40 276	96.11 300	99.89 174	99.01 135	99.84 160	99.84 34

ANet_high		99.88 6	99.87 10	99.91 2	99.99 1	99.91 4	99.65 59	100.00 1	99.90 28	100.00 1	99.97 11	99.61 31	99.97 32	99.75 37	100.00 1	99.84 34

patch_mono-2		99.51 81	99.46 88	99.64 127	99.70 150	99.11 222	99.04 217	99.87 43	99.71 80	99.47 217	99.79 93	98.24 200	99.98 19	99.38 79	99.96 69	99.83 38

nrg030		99.70 38	99.66 46	99.82 36	99.76 116	99.84 24	99.61 68	99.70 129	99.93 24	99.78 99	99.68 163	99.10 85	99.78 303	99.45 69	99.96 69	99.83 38

FIs		99.65 57	99.58 67	99.84 30	99.84 60	99.85 19	99.66 53	99.75 102	99.86 44	99.74 121	99.79 93	98.27 198	99.85 237	99.37 82	99.93 100	99.83 38

v7n		99.82 21	99.80 26	99.88 17	99.96 7	99.84 24	99.82 8	99.82 64	99.84 52	99.94 32	99.91 24	99.13 84	99.96 53	99.83 30	99.99 16	99.83 38

PEN-MVS		99.66 52	99.59 63	99.89 11	99.83 64	99.87 15	99.66 53	99.73 111	99.70 85	99.84 74	99.73 124	98.56 157	99.96 53	99.29 100	99.94 93	99.83 38

WR-MVS_H		99.61 66	99.53 80	99.87 21	99.80 85	99.83 29	99.67 49	99.75 102	99.58 117	99.85 71	99.69 152	98.18 209	99.94 76	99.28 102	99.95 82	99.83 38

WB-MVS		99.44 98	99.32 115	99.80 44	99.81 79	99.61 122	99.47 99	99.81 73	99.82 57	99.71 131	99.72 131	96.60 283	99.98 19	99.75 37	99.23 329	99.82 44

test_fmvsm_n_1920		99.84 15	99.85 16	99.83 32	99.82 71	99.70 91	99.17 177	99.97 18	99.99 2	99.96 23	99.82 73	99.94 4	100.00 1	99.95 12	100.00 1	99.80 45

Anonymous20231211		99.62 64	99.57 70	99.76 63	99.61 179	99.60 125	99.81 9	99.73 111	99.82 57	99.90 48	99.90 29	97.97 224	99.86 220	99.42 76	99.96 69	99.80 45

APDe-MVS		99.48 86	99.36 108	99.85 27	99.55 212	99.81 40	99.50 91	99.69 135	98.99 199	99.75 113	99.71 139	98.79 123	99.93 93	98.46 178	99.85 155	99.80 45
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DTE-MVSNet		99.68 44	99.61 58	99.88 17	99.80 85	99.87 15	99.67 49	99.71 123	99.72 78	99.84 74	99.78 101	98.67 141	99.97 32	99.30 97	99.95 82	99.80 45

XXY-MVS		99.71 37	99.67 45	99.81 39	99.89 40	99.72 82	99.59 74	99.82 64	99.39 144	99.82 79	99.84 62	99.38 52	99.91 139	99.38 79	99.93 100	99.80 45

1112_ss		99.05 197	98.84 220	99.67 108	99.66 168	99.29 193	98.52 292	99.82 64	97.65 318	99.43 227	99.16 325	96.42 290	99.91 139	99.07 131	99.84 160	99.80 45

LTVRE_ROB	99.19 1	99.88 6	99.87 10	99.88 17	99.91 32	99.90 7	99.96 1	99.92 29	99.90 28	99.97 19	99.87 47	99.81 14	99.95 62	99.54 58	99.99 16	99.80 45
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
test_fmvs1		99.48 86	99.65 48	98.97 285	99.54 214	97.16 342	99.11 200	99.98 11	99.78 68	99.96 23	99.81 79	98.72 135	99.97 32	99.95 12	99.97 54	99.79 52

bld_raw_dy_0_64		99.70 38	99.65 48	99.85 27	99.95 15	99.77 54	99.66 53	99.71 123	99.95 18	99.91 42	99.77 108	98.35 188	100.00 1	99.54 58	99.99 16	99.79 52

PMMVS2		99.48 86	99.45 90	99.57 161	99.76 116	98.99 234	98.09 325	99.90 35	98.95 204	99.78 99	99.58 220	99.57 36	99.93 93	99.48 66	99.95 82	99.79 52

MSC_two_6792asdad				99.74 78	99.03 346	99.53 140		99.23 310					99.92 115	97.77 234	99.69 236	99.78 55

No_MVS				99.74 78	99.03 346	99.53 140		99.23 310					99.92 115	97.77 234	99.69 236	99.78 55

dcpmvs_2		99.61 66	99.64 52	99.53 173	99.79 97	98.82 251	99.58 76	99.97 18	99.95 18	99.96 23	99.76 112	98.44 176	99.99 8	99.34 88	99.96 69	99.78 55

CHOSEN 1792x2688		99.39 114	99.30 122	99.65 120	99.88 45	99.25 202	98.78 266	99.88 41	98.66 239	99.96 23	99.79 93	97.45 253	99.93 93	99.34 88	99.99 16	99.78 55

test_vis1_rt		99.45 96	99.46 88	99.41 207	99.71 142	98.63 271	98.99 234	99.96 23	99.03 197	99.95 30	99.12 331	98.75 130	99.84 252	99.82 33	99.82 177	99.77 59

IU-MVS					99.69 154	99.77 54		99.22 313	97.50 326	99.69 138				97.75 238	99.70 232	99.77 59

test_0728_THIRD									99.18 173	99.62 167	99.61 204	98.58 154	99.91 139	97.72 240	99.80 191	99.77 59

test_0728_SECOND				99.83 32	99.70 150	99.79 46	99.14 187	99.61 173					99.92 115	97.88 223	99.72 227	99.77 59

MSP-MVS		99.04 200	98.79 227	99.81 39	99.78 104	99.73 77	99.35 121	99.57 203	98.54 252	99.54 198	98.99 348	96.81 278	99.93 93	96.97 293	99.53 285	99.77 59
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
mvsmamba		99.74 33	99.70 37	99.85 27	99.93 26	99.83 29	99.76 19	99.81 73	99.96 16	99.91 42	99.81 79	98.60 151	99.94 76	99.58 52	99.98 39	99.77 59

DPE-MVS		99.14 181	98.92 210	99.82 36	99.57 200	99.77 54	98.74 269	99.60 185	98.55 249	99.76 106	99.69 152	98.23 204	99.92 115	96.39 325	99.75 209	99.76 65
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
Baseline_NR-MVSNet		99.49 84	99.37 105	99.82 36	99.91 32	99.84 24	98.83 254	99.86 46	99.68 90	99.65 153	99.88 42	97.67 243	99.87 202	99.03 133	99.86 151	99.76 65

OurMVSNet-221017-0		99.75 30	99.71 36	99.84 30	99.96 7	99.83 29	99.83 6	99.85 51	99.80 63	99.93 35	99.93 17	98.54 160	99.93 93	99.59 49	99.98 39	99.76 65

test_241102_TWO								99.54 220	99.13 186	99.76 106	99.63 188	98.32 194	99.92 115	97.85 229	99.69 236	99.75 68

DP-MVS		99.48 86	99.39 100	99.74 78	99.57 200	99.62 116	99.29 142	99.61 173	99.87 40	99.74 121	99.76 112	98.69 137	99.87 202	98.20 196	99.80 191	99.75 68

tt0805		99.63 58	99.57 70	99.81 39	99.87 50	99.88 12	99.58 76	98.70 345	99.72 78	99.91 42	99.60 212	99.43 46	99.81 291	99.81 34	99.53 285	99.73 70

v10		99.69 41	99.69 41	99.66 115	99.81 79	99.39 172	99.66 53	99.75 102	99.60 114	99.92 39	99.87 47	98.75 130	99.86 220	99.90 23	99.99 16	99.73 70

EI-MVSNet-UG-set		99.48 86	99.50 82	99.42 200	99.57 200	98.65 269	99.24 157	99.46 253	99.68 90	99.80 90	99.66 171	98.99 100	99.89 174	99.19 111	99.90 114	99.72 72

Vis-MVSNet		99.75 30	99.74 35	99.79 50	99.88 45	99.66 102	99.69 42	99.92 29	99.67 94	99.77 104	99.75 117	99.61 31	99.98 19	99.35 87	99.98 39	99.72 72
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
HyFIR lowres test		98.91 222	98.64 235	99.73 87	99.85 57	99.47 146	98.07 328	99.83 59	98.64 241	99.89 52	99.60 212	92.57 336	100.00 1	99.33 91	99.97 54	99.72 72

EI-MVSNet-Vis-set		99.47 93	99.49 83	99.42 200	99.57 200	98.66 266	99.24 157	99.46 253	99.67 94	99.79 95	99.65 176	98.97 104	99.89 174	99.15 119	99.89 123	99.71 75

v8		99.68 44	99.69 41	99.65 120	99.80 85	99.40 170	99.66 53	99.76 97	99.64 102	99.93 35	99.85 56	98.66 143	99.84 252	99.88 27	99.99 16	99.71 75

TransMVSNet (Re)		99.78 25	99.77 31	99.81 39	99.91 32	99.85 19	99.75 22	99.86 46	99.70 85	99.91 42	99.89 34	99.60 33	99.87 202	99.59 49	99.74 216	99.71 75

test1111		97.74 308	98.16 283	96.49 371	99.60 181	89.86 401	99.71 34	91.21 397	99.89 34	99.88 60	99.87 47	93.73 325	99.90 157	99.56 55	99.99 16	99.70 78

VPA-MVSNet		99.66 52	99.62 54	99.79 50	99.68 162	99.75 68	99.62 63	99.69 135	99.85 49	99.80 90	99.81 79	98.81 118	99.91 139	99.47 67	99.88 132	99.70 78

WR-MVS		99.11 188	98.93 206	99.66 115	99.30 300	99.42 164	98.42 301	99.37 279	99.04 196	99.57 184	99.20 323	96.89 276	99.86 220	98.66 170	99.87 143	99.70 78

ACMH	98.42 6	99.59 68	99.54 76	99.72 93	99.86 53	99.62 116	99.56 81	99.79 83	98.77 230	99.80 90	99.85 56	99.64 27	99.85 237	98.70 166	99.89 123	99.70 78
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		99.86 9	99.86 12	99.83 32	99.94 19	99.90 7	99.83 6	99.91 32	99.85 49	99.94 32	99.95 13	99.73 21	99.90 157	99.65 44	99.97 54	99.69 82

HPM-MVS_fast		99.43 101	99.30 122	99.80 44	99.83 64	99.81 40	99.52 86	99.70 129	98.35 274	99.51 210	99.50 251	99.31 60	99.88 188	98.18 200	99.84 160	99.69 82

LPG-MVS_test		99.22 157	99.05 178	99.74 78	99.82 71	99.63 114	99.16 183	99.73 111	97.56 320	99.64 154	99.69 152	99.37 54	99.89 174	96.66 311	99.87 143	99.69 82

LGP-MVS_train				99.74 78	99.82 71	99.63 114		99.73 111	97.56 320	99.64 154	99.69 152	99.37 54	99.89 174	96.66 311	99.87 143	99.69 82

SteuartSystems-ACMMP		99.30 136	99.14 148	99.76 63	99.87 50	99.66 102	99.18 172	99.60 185	98.55 249	99.57 184	99.67 167	99.03 97	99.94 76	97.01 291	99.80 191	99.69 82
Skip Steuart: Steuart Systems R&D Blog.
MG-MVS		98.52 263	98.39 261	98.94 288	99.15 327	97.39 337	98.18 314	99.21 316	98.89 215	99.23 270	99.63 188	97.37 258	99.74 319	94.22 373	99.61 264	99.69 82

ACMMP_NAP		99.28 138	99.11 157	99.79 50	99.75 127	99.81 40	98.95 241	99.53 229	98.27 283	99.53 203	99.73 124	98.75 130	99.87 202	97.70 245	99.83 168	99.68 88

HFP-MVS		99.25 145	99.08 168	99.76 63	99.73 136	99.70 91	99.31 132	99.59 191	98.36 269	99.36 244	99.37 284	98.80 122	99.91 139	97.43 266	99.75 209	99.68 88

EI-MVSNet		99.38 116	99.44 93	99.21 255	99.58 190	98.09 306	99.26 149	99.46 253	99.62 105	99.75 113	99.67 167	98.54 160	99.85 237	99.15 119	99.92 104	99.68 88

TranMVSNet+NR-MVSNet		99.54 77	99.47 84	99.76 63	99.58 190	99.64 110	99.30 135	99.63 163	99.61 108	99.71 131	99.56 233	98.76 128	99.96 53	99.14 125	99.92 104	99.68 88

PVSNet_Blended_VisFu		99.40 110	99.38 102	99.44 194	99.90 38	98.66 266	98.94 243	99.91 32	97.97 300	99.79 95	99.73 124	99.05 95	99.97 32	99.15 119	99.99 16	99.68 88

IterMVS-LS		99.41 108	99.47 84	99.25 251	99.81 79	98.09 306	98.85 251	99.76 97	99.62 105	99.83 78	99.64 178	98.54 160	99.97 32	99.15 119	99.99 16	99.68 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MP-MVS-pluss		99.14 181	98.92 210	99.80 44	99.83 64	99.83 29	98.61 275	99.63 163	96.84 351	99.44 223	99.58 220	98.81 118	99.91 139	97.70 245	99.82 177	99.67 94
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		99.23 149	99.05 178	99.77 56	99.76 116	99.70 91	99.31 132	99.59 191	98.41 263	99.32 253	99.36 288	98.73 134	99.93 93	97.29 273	99.74 216	99.67 94

XVS		99.27 142	99.11 157	99.75 73	99.71 142	99.71 84	99.37 117	99.61 173	99.29 154	98.76 326	99.47 262	98.47 171	99.88 188	97.62 253	99.73 221	99.67 94

v1240		99.56 72	99.58 67	99.51 177	99.80 85	99.00 233	99.00 229	99.65 155	99.15 184	99.90 48	99.75 117	99.09 87	99.88 188	99.90 23	99.96 69	99.67 94

X-MVStestdata		96.09 349	94.87 358	99.75 73	99.71 142	99.71 84	99.37 117	99.61 173	99.29 154	98.76 326	61.30 404	98.47 171	99.88 188	97.62 253	99.73 221	99.67 94

VPNet		99.46 94	99.37 105	99.71 98	99.82 71	99.59 127	99.48 96	99.70 129	99.81 60	99.69 138	99.58 220	97.66 247	99.86 220	99.17 116	99.44 299	99.67 94

ACMMPR		99.23 149	99.06 174	99.76 63	99.74 133	99.69 95	99.31 132	99.59 191	98.36 269	99.35 245	99.38 282	98.61 149	99.93 93	97.43 266	99.75 209	99.67 94

SixPastTwentyTwo		99.42 104	99.30 122	99.76 63	99.92 31	99.67 100	99.70 35	99.14 324	99.65 100	99.89 52	99.90 29	96.20 299	99.94 76	99.42 76	99.92 104	99.67 94

HPM-MVS		99.25 145	99.07 172	99.78 53	99.81 79	99.75 68	99.61 68	99.67 142	97.72 315	99.35 245	99.25 312	99.23 71	99.92 115	97.21 284	99.82 177	99.67 94
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
v144192		99.55 75	99.54 76	99.58 155	99.78 104	99.20 214	99.11 200	99.62 166	99.18 173	99.89 52	99.72 131	98.66 143	99.87 202	99.88 27	99.97 54	99.66 103

v1921920		99.56 72	99.57 70	99.55 167	99.75 127	99.11 222	99.05 214	99.61 173	99.15 184	99.88 60	99.71 139	99.08 90	99.87 202	99.90 23	99.97 54	99.66 103

v1192		99.57 69	99.57 70	99.57 161	99.77 112	99.22 209	99.04 217	99.60 185	99.18 173	99.87 68	99.72 131	99.08 90	99.85 237	99.89 26	99.98 39	99.66 103

PGM-MVS		99.20 164	99.01 190	99.77 56	99.75 127	99.71 84	99.16 183	99.72 120	97.99 298	99.42 229	99.60 212	98.81 118	99.93 93	96.91 296	99.74 216	99.66 103

mPP-MVS		99.19 167	99.00 193	99.76 63	99.76 116	99.68 98	99.38 113	99.54 220	98.34 278	99.01 298	99.50 251	98.53 164	99.93 93	97.18 286	99.78 201	99.66 103

CP-MVS		99.23 149	99.05 178	99.75 73	99.66 168	99.66 102	99.38 113	99.62 166	98.38 267	99.06 296	99.27 307	98.79 123	99.94 76	97.51 262	99.82 177	99.66 103

EG-PatchMatch MVS		99.57 69	99.56 75	99.62 143	99.77 112	99.33 187	99.26 149	99.76 97	99.32 152	99.80 90	99.78 101	99.29 62	99.87 202	99.15 119	99.91 113	99.66 103

UGNet		99.38 116	99.34 110	99.49 180	98.90 356	98.90 246	99.70 35	99.35 283	99.86 44	98.57 341	99.81 79	98.50 170	99.93 93	99.38 79	99.98 39	99.66 103
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
SDMVSNet		99.77 28	99.77 31	99.76 63	99.80 85	99.65 107	99.63 61	99.86 46	99.97 14	99.89 52	99.89 34	99.52 42	99.99 8	99.42 76	99.96 69	99.65 111

sd_testset		99.78 25	99.78 30	99.80 44	99.80 85	99.76 62	99.80 10	99.79 83	99.97 14	99.89 52	99.89 34	99.53 41	99.99 8	99.36 84	99.96 69	99.65 111

test2506		94.73 360	94.59 362	95.15 377	99.59 185	85.90 403	99.75 22	74.01 403	99.89 34	99.71 131	99.86 54	79.00 399	99.90 157	99.52 62	99.99 16	99.65 111

ECVR-MVS		97.73 309	98.04 288	96.78 365	99.59 185	90.81 397	99.72 30	90.43 399	99.89 34	99.86 69	99.86 54	93.60 327	99.89 174	99.46 68	99.99 16	99.65 111

h-mvs33		98.61 251	98.34 267	99.44 194	99.60 181	98.67 263	99.27 147	99.44 258	99.68 90	99.32 253	99.49 255	92.50 339	100.00 1	99.24 104	96.51 390	99.65 111

TSAR-MVS + MP.		99.34 129	99.24 137	99.63 134	99.82 71	99.37 177	99.26 149	99.35 283	98.77 230	99.57 184	99.70 146	99.27 67	99.88 188	97.71 242	99.75 209	99.65 111
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MTAPA		99.35 124	99.20 140	99.80 44	99.81 79	99.81 40	99.33 125	99.53 229	99.27 158	99.42 229	99.63 188	98.21 205	99.95 62	97.83 233	99.79 196	99.65 111

MCST-MVS		99.02 203	98.81 224	99.65 120	99.58 190	99.49 144	98.58 281	99.07 328	98.40 265	99.04 297	99.25 312	98.51 169	99.80 297	97.31 272	99.51 289	99.65 111

UniMVSNet_NR-MVSNet		99.37 119	99.25 135	99.72 93	99.47 249	99.56 134	98.97 238	99.61 173	99.43 139	99.67 147	99.28 305	97.85 232	99.95 62	99.17 116	99.81 186	99.65 111

casdiffmvs_mvg		99.68 44	99.68 44	99.69 103	99.81 79	99.59 127	99.29 142	99.90 35	99.71 80	99.79 95	99.73 124	99.54 39	99.84 252	99.36 84	99.96 69	99.65 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ZNCC-MVS		99.22 157	99.04 183	99.77 56	99.76 116	99.73 77	99.28 144	99.56 208	98.19 288	99.14 285	99.29 304	98.84 117	99.92 115	97.53 261	99.80 191	99.64 121

v1144		99.54 77	99.53 80	99.59 151	99.79 97	99.28 195	99.10 202	99.61 173	99.20 171	99.84 74	99.73 124	98.67 141	99.84 252	99.86 29	99.98 39	99.64 121

v2v482		99.50 82	99.47 84	99.58 155	99.78 104	99.25 202	99.14 187	99.58 201	99.25 162	99.81 86	99.62 195	98.24 200	99.84 252	99.83 30	99.97 54	99.64 121

K. test v3		98.87 229	98.60 238	99.69 103	99.93 26	99.46 150	99.74 24	94.97 390	99.78 68	99.88 60	99.88 42	93.66 326	99.97 32	99.61 47	99.95 82	99.64 121

DeepC-MVS	98.90 4	99.62 64	99.61 58	99.67 108	99.72 139	99.44 157	99.24 157	99.71 123	99.27 158	99.93 35	99.90 29	99.70 24	99.93 93	98.99 136	99.99 16	99.64 121
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
mvsany_test1		99.44 98	99.45 90	99.40 209	99.37 275	98.64 270	97.90 347	99.59 191	99.27 158	99.92 39	99.82 73	99.74 20	99.93 93	99.55 57	99.87 143	99.63 126

SMA-MVS		99.19 167	99.00 193	99.73 87	99.46 253	99.73 77	99.13 193	99.52 234	97.40 331	99.57 184	99.64 178	98.93 107	99.83 267	97.61 255	99.79 196	99.63 126
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
IterMVS-SCA-FT		99.00 209	99.16 144	98.51 322	99.75 127	95.90 366	98.07 328	99.84 57	99.84 52	99.89 52	99.73 124	96.01 302	99.99 8	99.33 91	100.00 1	99.63 126

pm-mvs1		99.79 24	99.79 27	99.78 53	99.91 32	99.83 29	99.76 19	99.87 43	99.73 74	99.89 52	99.87 47	99.63 28	99.87 202	99.54 58	99.92 104	99.63 126

MP-MVS		99.06 194	98.83 222	99.76 63	99.76 116	99.71 84	99.32 127	99.50 242	98.35 274	98.97 300	99.48 258	98.37 186	99.92 115	95.95 345	99.75 209	99.63 126
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DU-MVS		99.33 132	99.21 139	99.71 98	99.43 262	99.56 134	98.83 254	99.53 229	99.38 145	99.67 147	99.36 288	97.67 243	99.95 62	99.17 116	99.81 186	99.63 126

NR-MVSNet		99.40 110	99.31 117	99.68 105	99.43 262	99.55 137	99.73 27	99.50 242	99.46 131	99.88 60	99.36 288	97.54 250	99.87 202	98.97 140	99.87 143	99.63 126

IterMVS		98.97 213	99.16 144	98.42 326	99.74 133	95.64 369	98.06 330	99.83 59	99.83 55	99.85 71	99.74 120	96.10 301	99.99 8	99.27 103	100.00 1	99.63 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EPP-MVSNet		99.17 175	99.00 193	99.66 115	99.80 85	99.43 161	99.70 35	99.24 309	99.48 124	99.56 191	99.77 108	94.89 311	99.93 93	98.72 165	99.89 123	99.63 126

ACMMP		99.25 145	99.08 168	99.74 78	99.79 97	99.68 98	99.50 91	99.65 155	98.07 294	99.52 205	99.69 152	98.57 155	99.92 115	97.18 286	99.79 196	99.63 126
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
DeepC-MVS_fast	98.47 5	99.23 149	99.12 154	99.56 164	99.28 305	99.22 209	98.99 234	99.40 271	99.08 191	99.58 181	99.64 178	98.90 113	99.83 267	97.44 265	99.75 209	99.63 126
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DVP-MVS++		99.38 116	99.25 135	99.77 56	99.03 346	99.77 54	99.74 24	99.61 173	99.18 173	99.76 106	99.61 204	99.00 98	99.92 115	97.72 240	99.60 267	99.62 137

PC_three_1452									97.56 320	99.68 141	99.41 272	99.09 87	97.09 396	96.66 311	99.60 267	99.62 137

GeoE		99.69 41	99.66 46	99.78 53	99.76 116	99.76 62	99.60 73	99.82 64	99.46 131	99.75 113	99.56 233	99.63 28	99.95 62	99.43 71	99.88 132	99.62 137

test_method		91.72 361	92.32 364	89.91 379	93.49 400	70.18 404	90.28 392	99.56 208	61.71 396	95.39 393	99.52 246	93.90 320	99.94 76	98.76 161	98.27 371	99.62 137

GST-MVS		99.16 177	98.96 204	99.75 73	99.73 136	99.73 77	99.20 167	99.55 214	98.22 285	99.32 253	99.35 293	98.65 145	99.91 139	96.86 299	99.74 216	99.62 137

new-patchmatchnet		99.35 124	99.57 70	98.71 316	99.82 71	96.62 354	98.55 287	99.75 102	99.50 122	99.88 60	99.87 47	99.31 60	99.88 188	99.43 71	100.00 1	99.62 137

CPTT-MVS		98.74 241	98.44 256	99.64 127	99.61 179	99.38 174	99.18 172	99.55 214	96.49 355	99.27 264	99.37 284	97.11 270	99.92 115	95.74 351	99.67 247	99.62 137

MIMVSNet1		99.66 52	99.62 54	99.80 44	99.94 19	99.87 15	99.69 42	99.77 92	99.78 68	99.93 35	99.89 34	97.94 225	99.92 115	99.65 44	99.98 39	99.62 137

DeepPCF-MVS	98.42 6	99.18 171	99.02 187	99.67 108	99.22 315	99.75 68	97.25 375	99.47 250	98.72 235	99.66 151	99.70 146	99.29 62	99.63 364	98.07 208	99.81 186	99.62 137

3Dnovator+	98.92 3	99.35 124	99.24 137	99.67 108	99.35 280	99.47 146	99.62 63	99.50 242	99.44 134	99.12 288	99.78 101	98.77 127	99.94 76	97.87 226	99.72 227	99.62 137

DVP-MVS		99.32 134	99.17 143	99.77 56	99.69 154	99.80 44	99.14 187	99.31 292	99.16 180	99.62 167	99.61 204	98.35 188	99.91 139	97.88 223	99.72 227	99.61 147
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
APD-MVS		98.87 229	98.59 240	99.71 98	99.50 233	99.62 116	99.01 226	99.57 203	96.80 353	99.54 198	99.63 188	98.29 196	99.91 139	95.24 360	99.71 230	99.61 147
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		98.82 233	98.57 244	99.58 155	99.21 317	99.31 190	98.61 275	99.25 306	98.65 240	98.43 347	99.26 310	97.86 230	99.81 291	96.55 316	99.27 324	99.61 147

TAMVS		99.49 84	99.45 90	99.63 134	99.48 243	99.42 164	99.45 103	99.57 203	99.66 98	99.78 99	99.83 66	97.85 232	99.86 220	99.44 70	99.96 69	99.61 147

HPM-MVS++		98.96 216	98.70 233	99.74 78	99.52 225	99.71 84	98.86 249	99.19 319	98.47 259	98.59 339	99.06 338	98.08 215	99.91 139	96.94 294	99.60 267	99.60 151

V42		99.56 72	99.54 76	99.63 134	99.79 97	99.46 150	99.39 111	99.59 191	99.24 164	99.86 69	99.70 146	98.55 158	99.82 276	99.79 35	99.95 82	99.60 151

HQP_MVS		98.90 224	98.68 234	99.55 167	99.58 190	99.24 206	98.80 262	99.54 220	98.94 205	99.14 285	99.25 312	97.24 262	99.82 276	95.84 348	99.78 201	99.60 151

plane_prior5								99.54 220					99.82 276	95.84 348	99.78 201	99.60 151

TDRefinement		99.72 34	99.70 37	99.77 56	99.90 38	99.85 19	99.86 5	99.92 29	99.69 88	99.78 99	99.92 21	99.37 54	99.88 188	98.93 148	99.95 82	99.60 151

ACMH+	98.40 8	99.50 82	99.43 95	99.71 98	99.86 53	99.76 62	99.32 127	99.77 92	99.53 120	99.77 104	99.76 112	99.26 68	99.78 303	97.77 234	99.88 132	99.60 151

ACMM	98.09 11	99.46 94	99.38 102	99.72 93	99.80 85	99.69 95	99.13 193	99.65 155	98.99 199	99.64 154	99.72 131	99.39 48	99.86 220	98.23 193	99.81 186	99.60 151
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VDDNet		98.97 213	98.82 223	99.42 200	99.71 142	98.81 252	99.62 63	98.68 346	99.81 60	99.38 242	99.80 83	94.25 318	99.85 237	98.79 157	99.32 316	99.59 158

casdiffmvs		99.63 58	99.61 58	99.67 108	99.79 97	99.59 127	99.13 193	99.85 51	99.79 66	99.76 106	99.72 131	99.33 59	99.82 276	99.21 107	99.94 93	99.59 158
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UniMVSNet (Re)		99.37 119	99.26 133	99.68 105	99.51 227	99.58 131	98.98 237	99.60 185	99.43 139	99.70 135	99.36 288	97.70 239	99.88 188	99.20 110	99.87 143	99.59 158

DSMNet-mixed		99.48 86	99.65 48	98.95 287	99.71 142	97.27 339	99.50 91	99.82 64	99.59 116	99.41 235	99.85 56	99.62 30	100.00 1	99.53 61	99.89 123	99.59 158

3Dnovator	99.15 2	99.43 101	99.36 108	99.65 120	99.39 270	99.42 164	99.70 35	99.56 208	99.23 166	99.35 245	99.80 83	99.17 77	99.95 62	98.21 195	99.84 160	99.59 158

SED-MVS		99.40 110	99.28 129	99.77 56	99.69 154	99.82 35	99.20 167	99.54 220	99.13 186	99.82 79	99.63 188	98.91 110	99.92 115	97.85 229	99.70 232	99.58 163

OPU-MVS				99.29 240	99.12 332	99.44 157	99.20 167				99.40 276	99.00 98	98.84 393	96.54 317	99.60 267	99.58 163

EPNet		98.13 294	97.77 309	99.18 260	94.57 399	97.99 311	99.24 157	97.96 369	99.74 73	97.29 380	99.62 195	93.13 331	99.97 32	98.59 172	99.83 168	99.58 163
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IS-MVSNet		99.03 201	98.85 218	99.55 167	99.80 85	99.25 202	99.73 27	99.15 323	99.37 146	99.61 173	99.71 139	94.73 314	99.81 291	97.70 245	99.88 132	99.58 163

ACMP	97.51 14	99.05 197	98.84 220	99.67 108	99.78 104	99.55 137	98.88 247	99.66 146	97.11 346	99.47 217	99.60 212	99.07 92	99.89 174	96.18 334	99.85 155	99.58 163
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SR-MVS		99.19 167	99.00 193	99.74 78	99.51 227	99.72 82	99.18 172	99.60 185	98.85 218	99.47 217	99.58 220	98.38 185	99.92 115	96.92 295	99.54 283	99.57 168

lessismore_v0				99.64 127	99.86 53	99.38 174		90.66 398		99.89 52	99.83 66	94.56 316	99.97 32	99.56 55	99.92 104	99.57 168

pmmvs5		99.19 167	99.11 157	99.42 200	99.76 116	98.88 248	98.55 287	99.73 111	98.82 222	99.72 126	99.62 195	96.56 284	99.82 276	99.32 93	99.95 82	99.56 170

APD-MVS_3200maxsize		99.31 135	99.16 144	99.74 78	99.53 220	99.75 68	99.27 147	99.61 173	99.19 172	99.57 184	99.64 178	98.76 128	99.90 157	97.29 273	99.62 257	99.56 170

CDPH-MVS		98.56 259	98.20 278	99.61 146	99.50 233	99.46 150	98.32 306	99.41 264	95.22 372	99.21 275	99.10 335	98.34 191	99.82 276	95.09 364	99.66 250	99.56 170

Anonymous20240521		99.44 98	99.42 97	99.49 180	99.89 40	98.96 239	99.62 63	99.76 97	99.85 49	99.82 79	99.88 42	96.39 293	99.97 32	99.59 49	99.98 39	99.55 173

our_test_3		98.85 231	99.09 166	98.13 339	99.66 168	94.90 376	97.72 353	99.58 201	99.07 193	99.64 154	99.62 195	98.19 207	99.93 93	98.41 180	99.95 82	99.55 173

YYNet1		98.95 219	98.99 198	98.84 304	99.64 172	97.14 344	98.22 313	99.32 288	98.92 210	99.59 179	99.66 171	97.40 255	99.83 267	98.27 190	99.90 114	99.55 173

MDA-MVSNet_test_wron		98.95 219	98.99 198	98.85 302	99.64 172	97.16 342	98.23 312	99.33 286	98.93 208	99.56 191	99.66 171	97.39 257	99.83 267	98.29 188	99.88 132	99.55 173

MVSFormer		99.41 108	99.44 93	99.31 236	99.57 200	98.40 284	99.77 15	99.80 77	99.73 74	99.63 158	99.30 301	98.02 219	99.98 19	99.43 71	99.69 236	99.55 173

jason		99.16 177	99.11 157	99.32 233	99.75 127	98.44 281	98.26 310	99.39 274	98.70 237	99.74 121	99.30 301	98.54 160	99.97 32	98.48 177	99.82 177	99.55 173
jason: jason.
CDS-MVSNet		99.22 157	99.13 150	99.50 179	99.35 280	99.11 222	98.96 240	99.54 220	99.46 131	99.61 173	99.70 146	96.31 295	99.83 267	99.34 88	99.88 132	99.55 173
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
COLMAP_ROB	98.06 12	99.45 96	99.37 105	99.70 102	99.83 64	99.70 91	99.38 113	99.78 89	99.53 120	99.67 147	99.78 101	99.19 75	99.86 220	97.32 271	99.87 143	99.55 173
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
iter_conf_final		98.75 239	98.54 248	99.40 209	99.33 293	98.75 258	99.26 149	99.59 191	99.80 63	99.76 106	99.58 220	90.17 365	99.92 115	99.37 82	99.97 54	99.54 181

SR-MVS-dyc-post		99.27 142	99.11 157	99.73 87	99.54 214	99.74 74	99.26 149	99.62 166	99.16 180	99.52 205	99.64 178	98.41 180	99.91 139	97.27 276	99.61 264	99.54 181

RE-MVS-def			99.13 150		99.54 214	99.74 74	99.26 149	99.62 166	99.16 180	99.52 205	99.64 178	98.57 155		97.27 276	99.61 264	99.54 181

SD-MVS		99.01 207	99.30 122	98.15 338	99.50 233	99.40 170	98.94 243	99.61 173	99.22 170	99.75 113	99.82 73	99.54 39	95.51 398	97.48 263	99.87 143	99.54 181
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		98.99 212	98.80 226	99.56 164	99.25 310	99.43 161	98.54 290	99.27 300	98.58 247	98.80 322	99.43 270	98.53 164	99.70 330	97.22 283	99.59 271	99.54 181

MVS_111021_HR		99.12 185	99.02 187	99.40 209	99.50 233	99.11 222	97.92 344	99.71 123	98.76 233	99.08 292	99.47 262	99.17 77	99.54 376	97.85 229	99.76 207	99.54 181

v148		99.40 110	99.41 99	99.39 213	99.76 116	98.94 240	99.09 207	99.59 191	99.17 178	99.81 86	99.61 204	98.41 180	99.69 336	99.32 93	99.94 93	99.53 187

iter_conf05		98.46 271	98.23 274	99.15 263	99.04 345	97.99 311	99.10 202	99.61 173	99.79 66	99.76 106	99.58 220	87.88 375	99.92 115	99.31 96	99.97 54	99.53 187

diffmvs		99.34 129	99.32 115	99.39 213	99.67 167	98.77 257	98.57 285	99.81 73	99.61 108	99.48 215	99.41 272	98.47 171	99.86 220	98.97 140	99.90 114	99.53 187
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		99.63 58	99.62 54	99.66 115	99.80 85	99.62 116	99.44 105	99.80 77	99.71 80	99.72 126	99.69 152	99.15 79	99.83 267	99.32 93	99.94 93	99.53 187

HQP4-MVS										98.15 356			99.70 330			99.53 187

GBi-Net		99.42 104	99.31 117	99.73 87	99.49 238	99.77 54	99.68 45	99.70 129	99.44 134	99.62 167	99.83 66	97.21 264	99.90 157	98.96 142	99.90 114	99.53 187

test1		99.42 104	99.31 117	99.73 87	99.49 238	99.77 54	99.68 45	99.70 129	99.44 134	99.62 167	99.83 66	97.21 264	99.90 157	98.96 142	99.90 114	99.53 187

FMVSNet1		99.66 52	99.63 53	99.73 87	99.78 104	99.77 54	99.68 45	99.70 129	99.67 94	99.82 79	99.83 66	98.98 102	99.90 157	99.24 104	99.97 54	99.53 187

HQP-MVS		98.36 280	98.02 290	99.39 213	99.31 296	98.94 240	97.98 337	99.37 279	97.45 328	98.15 356	98.83 364	96.67 281	99.70 330	94.73 366	99.67 247	99.53 187

QAPM		98.40 278	97.99 291	99.65 120	99.39 270	99.47 146	99.67 49	99.52 234	91.70 386	98.78 325	99.80 83	98.55 158	99.95 62	94.71 368	99.75 209	99.53 187

F-COLMAP		98.74 241	98.45 255	99.62 143	99.57 200	99.47 146	98.84 252	99.65 155	96.31 359	98.93 304	99.19 324	97.68 242	99.87 202	96.52 318	99.37 309	99.53 187

MVSTER		98.47 270	98.22 276	99.24 253	99.06 342	98.35 290	99.08 210	99.46 253	99.27 158	99.75 113	99.66 171	88.61 373	99.85 237	99.14 125	99.92 104	99.52 198

PVSNet_BlendedMVS		99.03 201	99.01 190	99.09 273	99.54 214	97.99 311	98.58 281	99.82 64	97.62 319	99.34 248	99.71 139	98.52 167	99.77 311	97.98 214	99.97 54	99.52 198

OPM-MVS		99.26 144	99.13 150	99.63 134	99.70 150	99.61 122	98.58 281	99.48 247	98.50 255	99.52 205	99.63 188	99.14 82	99.76 313	97.89 222	99.77 205	99.51 200
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
AllTest		99.21 162	99.07 172	99.63 134	99.78 104	99.64 110	99.12 197	99.83 59	98.63 242	99.63 158	99.72 131	98.68 138	99.75 317	96.38 326	99.83 168	99.51 200

TestCases				99.63 134	99.78 104	99.64 110		99.83 59	98.63 242	99.63 158	99.72 131	98.68 138	99.75 317	96.38 326	99.83 168	99.51 200

BH-RMVSNet		98.41 276	98.14 284	99.21 255	99.21 317	98.47 278	98.60 277	98.26 365	98.35 274	98.93 304	99.31 299	97.20 267	99.66 355	94.32 371	99.10 334	99.51 200

USDC		98.96 216	98.93 206	99.05 279	99.54 214	97.99 311	97.07 381	99.80 77	98.21 286	99.75 113	99.77 108	98.43 177	99.64 363	97.90 221	99.88 132	99.51 200

test9_res														95.10 363	99.44 299	99.50 205

train_agg		98.35 283	97.95 295	99.57 161	99.35 280	99.35 184	98.11 323	99.41 264	94.90 376	97.92 366	98.99 348	98.02 219	99.85 237	95.38 358	99.44 299	99.50 205

agg_prior2														94.58 369	99.46 298	99.50 205

VDD-MVS		99.20 164	99.11 157	99.44 194	99.43 262	98.98 235	99.50 91	98.32 364	99.80 63	99.56 191	99.69 152	96.99 274	99.85 237	98.99 136	99.73 221	99.50 205

MDA-MVSNet-bldmvs		99.06 194	99.05 178	99.07 277	99.80 85	97.83 321	98.89 246	99.72 120	99.29 154	99.63 158	99.70 146	96.47 288	99.89 174	98.17 202	99.82 177	99.50 205

KD-MVS_self_test		99.63 58	99.59 63	99.76 63	99.84 60	99.90 7	99.37 117	99.79 83	99.83 55	99.88 60	99.85 56	98.42 179	99.90 157	99.60 48	99.73 221	99.49 210

SF-MVS		99.10 191	98.93 206	99.62 143	99.58 190	99.51 142	99.13 193	99.65 155	97.97 300	99.42 229	99.61 204	98.86 115	99.87 202	96.45 323	99.68 241	99.49 210

Anonymous20240529		99.42 104	99.34 110	99.65 120	99.53 220	99.60 125	99.63 61	99.39 274	99.47 128	99.76 106	99.78 101	98.13 211	99.86 220	98.70 166	99.68 241	99.49 210

WTY-MVS		98.59 256	98.37 263	99.26 248	99.43 262	98.40 284	98.74 269	99.13 326	98.10 291	99.21 275	99.24 317	94.82 312	99.90 157	97.86 227	98.77 351	99.49 210

ppachtmachnet_test		98.89 227	99.12 154	98.20 337	99.66 168	95.24 373	97.63 357	99.68 138	99.08 191	99.78 99	99.62 195	98.65 145	99.88 188	98.02 209	99.96 69	99.48 214

Anonymous20231206		99.35 124	99.31 117	99.47 186	99.74 133	99.06 232	99.28 144	99.74 107	99.23 166	99.72 126	99.53 244	97.63 249	99.88 188	99.11 127	99.84 160	99.48 214

test_prior				99.46 188	99.35 280	99.22 209		99.39 274					99.69 336			99.48 214

test12				99.54 172	99.29 302	99.33 187		99.16 322		98.43 347		97.54 250	99.82 276		99.47 296	99.48 214

VNet		99.18 171	99.06 174	99.56 164	99.24 312	99.36 181	99.33 125	99.31 292	99.67 94	99.47 217	99.57 229	96.48 287	99.84 252	99.15 119	99.30 318	99.47 218

test20.03		99.55 75	99.54 76	99.58 155	99.79 97	99.37 177	99.02 224	99.89 37	99.60 114	99.82 79	99.62 195	98.81 118	99.89 174	99.43 71	99.86 151	99.47 218

114514_t		98.49 268	98.11 285	99.64 127	99.73 136	99.58 131	99.24 157	99.76 97	89.94 389	99.42 229	99.56 233	97.76 238	99.86 220	97.74 239	99.82 177	99.47 218

sss		98.90 224	98.77 228	99.27 245	99.48 243	98.44 281	98.72 271	99.32 288	97.94 304	99.37 243	99.35 293	96.31 295	99.91 139	98.85 150	99.63 256	99.47 218

旧先验1					99.49 238	99.29 193		99.26 303			99.39 280	97.67 243			99.36 310	99.46 222

MVP-Stereo		99.16 177	99.08 168	99.43 198	99.48 243	99.07 230	99.08 210	99.55 214	98.63 242	99.31 257	99.68 163	98.19 207	99.78 303	98.18 200	99.58 272	99.45 223
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
新几何1				99.52 175	99.50 233	99.22 209		99.26 303	95.66 368	98.60 338	99.28 305	97.67 243	99.89 174	95.95 345	99.32 316	99.45 223

LFMVS		98.46 271	98.19 281	99.26 248	99.24 312	98.52 277	99.62 63	96.94 381	99.87 40	99.31 257	99.58 220	91.04 352	99.81 291	98.68 169	99.42 303	99.45 223

testgi		99.29 137	99.26 133	99.37 219	99.75 127	98.81 252	98.84 252	99.89 37	98.38 267	99.75 113	99.04 341	99.36 57	99.86 220	99.08 130	99.25 325	99.45 223

UnsupCasMVSNet_eth		98.83 232	98.57 244	99.59 151	99.68 162	99.45 155	98.99 234	99.67 142	99.48 124	99.55 196	99.36 288	94.92 310	99.86 220	98.95 146	96.57 389	99.45 223

无先验							98.01 333	99.23 310	95.83 365				99.85 237	95.79 350		99.44 228

testdata				99.42 200	99.51 227	98.93 243		99.30 295	96.20 360	98.87 314	99.40 276	98.33 193	99.89 174	96.29 329	99.28 321	99.44 228

XVG-OURS-SEG-HR		99.16 177	98.99 198	99.66 115	99.84 60	99.64 110	98.25 311	99.73 111	98.39 266	99.63 158	99.43 270	99.70 24	99.90 157	97.34 270	98.64 361	99.44 228

FMVSNet2		99.35 124	99.28 129	99.55 167	99.49 238	99.35 184	99.45 103	99.57 203	99.44 134	99.70 135	99.74 120	97.21 264	99.87 202	99.03 133	99.94 93	99.44 228

N_pmnet		98.73 243	98.53 250	99.35 225	99.72 139	98.67 263	98.34 304	94.65 391	98.35 274	99.79 95	99.68 163	98.03 218	99.93 93	98.28 189	99.92 104	99.44 228

RPSCF		99.18 171	99.02 187	99.64 127	99.83 64	99.85 19	99.44 105	99.82 64	98.33 279	99.50 212	99.78 101	97.90 227	99.65 361	96.78 304	99.83 168	99.44 228

原ACMM1				99.37 219	99.47 249	98.87 250		99.27 300	96.74 354	98.26 351	99.32 297	97.93 226	99.82 276	95.96 344	99.38 307	99.43 234

test222					99.51 227	99.08 229	97.83 350	99.29 296	95.21 373	98.68 333	99.31 299	97.28 261			99.38 307	99.43 234

XVG-OURS		99.21 162	99.06 174	99.65 120	99.82 71	99.62 116	97.87 348	99.74 107	98.36 269	99.66 151	99.68 163	99.71 22	99.90 157	96.84 302	99.88 132	99.43 234

CSCG		99.37 119	99.29 127	99.60 149	99.71 142	99.46 150	99.43 107	99.85 51	98.79 226	99.41 235	99.60 212	98.92 108	99.92 115	98.02 209	99.92 104	99.43 234

TinyColmap		98.97 213	98.93 206	99.07 277	99.46 253	98.19 297	97.75 352	99.75 102	98.79 226	99.54 198	99.70 146	98.97 104	99.62 365	96.63 314	99.83 168	99.41 238

Anonymous202405211		98.75 239	98.46 254	99.63 134	99.34 288	99.66 102	99.47 99	97.65 374	99.28 157	99.56 191	99.50 251	93.15 330	99.84 252	98.62 171	99.58 272	99.40 239

XVG-ACMP-BASELINE		99.23 149	99.10 165	99.63 134	99.82 71	99.58 131	98.83 254	99.72 120	98.36 269	99.60 176	99.71 139	98.92 108	99.91 139	97.08 289	99.84 160	99.40 239

MS-PatchMatch		99.00 209	98.97 202	99.09 273	99.11 337	98.19 297	98.76 268	99.33 286	98.49 257	99.44 223	99.58 220	98.21 205	99.69 336	98.20 196	99.62 257	99.39 241

FMVSNet3		98.80 235	98.63 237	99.32 233	99.13 330	98.72 261	99.10 202	99.48 247	99.23 166	99.62 167	99.64 178	92.57 336	99.86 220	98.96 142	99.90 114	99.39 241

ambc				99.20 257	99.35 280	98.53 275	99.17 177	99.46 253		99.67 147	99.80 83	98.46 174	99.70 330	97.92 219	99.70 232	99.38 243

FMVSNet5		97.80 306	97.25 322	99.42 200	98.83 363	98.97 237	99.38 113	99.80 77	98.87 216	99.25 266	99.69 152	80.60 394	99.91 139	98.96 142	99.90 114	99.38 243

PAPM_NR		98.36 280	98.04 288	99.33 229	99.48 243	98.93 243	98.79 265	99.28 299	97.54 323	98.56 342	98.57 375	97.12 269	99.69 336	94.09 375	98.90 346	99.38 243

EPNet_dtu		97.62 314	97.79 308	97.11 364	96.67 396	92.31 388	98.51 293	98.04 367	99.24 164	95.77 391	99.47 262	93.78 324	99.66 355	98.98 138	99.62 257	99.37 246
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PHI-MVS		99.11 188	98.95 205	99.59 151	99.13 330	99.59 127	99.17 177	99.65 155	97.88 308	99.25 266	99.46 265	98.97 104	99.80 297	97.26 278	99.82 177	99.37 246

PLC	97.35 16	98.36 280	97.99 291	99.48 184	99.32 295	99.24 206	98.50 294	99.51 238	95.19 374	98.58 340	98.96 355	96.95 275	99.83 267	95.63 352	99.25 325	99.37 246
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tttt0517		97.62 314	97.20 323	98.90 300	99.76 116	97.40 336	99.48 96	94.36 392	99.06 195	99.70 135	99.49 255	84.55 389	99.94 76	98.73 164	99.65 252	99.36 249

pmmvs-eth3d		99.48 86	99.47 84	99.51 177	99.77 112	99.41 169	98.81 259	99.66 146	99.42 143	99.75 113	99.66 171	99.20 74	99.76 313	98.98 138	99.99 16	99.36 249

PVSNet_0	95.53 19	95.85 354	95.31 356	97.47 354	98.78 370	93.48 384	95.72 389	99.40 271	96.18 361	97.37 378	97.73 391	95.73 304	99.58 372	95.49 355	81.40 396	99.36 249

testing3		96.48 341	95.63 351	99.01 282	99.23 314	97.81 322	98.90 245	99.10 327	98.72 235	97.84 372	97.92 389	72.44 401	99.85 237	97.21 284	99.33 314	99.35 252

lupinMVS		98.96 216	98.87 216	99.24 253	99.57 200	98.40 284	98.12 321	99.18 320	98.28 282	99.63 158	99.13 327	98.02 219	99.97 32	98.22 194	99.69 236	99.35 252

Vis-MVSNet (Re-imp)		98.77 237	98.58 243	99.34 226	99.78 104	98.88 248	99.61 68	99.56 208	99.11 190	99.24 269	99.56 233	93.00 334	99.78 303	97.43 266	99.89 123	99.35 252

GA-MVS		97.99 302	97.68 312	98.93 291	99.52 225	98.04 310	97.19 377	99.05 331	98.32 280	98.81 320	98.97 353	89.89 369	99.41 386	98.33 186	99.05 336	99.34 255

CANet		99.11 188	99.05 178	99.28 242	98.83 363	98.56 274	98.71 273	99.41 264	99.25 162	99.23 270	99.22 319	97.66 247	99.94 76	99.19 111	99.97 54	99.33 256

Patchmtry		98.78 236	98.54 248	99.49 180	98.89 359	99.19 215	99.32 127	99.67 142	99.65 100	99.72 126	99.79 93	91.87 344	99.95 62	98.00 213	99.97 54	99.33 256

PAPR		97.56 317	97.07 325	99.04 280	98.80 367	98.11 304	97.63 357	99.25 306	94.56 381	98.02 364	98.25 385	97.43 254	99.68 346	90.90 386	98.74 355	99.33 256

testf1		99.63 58	99.60 61	99.72 93	99.94 19	99.95 2	99.47 99	99.89 37	99.43 139	99.88 60	99.80 83	99.26 68	99.90 157	98.81 155	99.88 132	99.32 259

APD_test2		99.63 58	99.60 61	99.72 93	99.94 19	99.95 2	99.47 99	99.89 37	99.43 139	99.88 60	99.80 83	99.26 68	99.90 157	98.81 155	99.88 132	99.32 259

CHOSEN 280x420		98.41 276	98.41 259	98.40 327	99.34 288	95.89 367	96.94 383	99.44 258	98.80 225	99.25 266	99.52 246	93.51 328	99.98 19	98.94 147	99.98 39	99.32 259

baseline1		97.73 309	97.33 319	98.96 286	99.30 300	97.73 326	99.40 109	98.42 359	99.33 151	99.46 221	99.21 321	91.18 350	99.82 276	98.35 184	91.26 395	99.32 259

dmvs_re		98.69 247	98.48 252	99.31 236	99.55 212	99.42 164	99.54 84	98.38 362	99.32 152	98.72 329	98.71 370	96.76 280	99.21 388	96.01 339	99.35 312	99.31 263

TAPA-MVS	97.92 13	98.03 299	97.55 315	99.46 188	99.47 249	99.44 157	98.50 294	99.62 166	86.79 390	99.07 295	99.26 310	98.26 199	99.62 365	97.28 275	99.73 221	99.31 263
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LCM-MVSNet-Re		99.28 138	99.15 147	99.67 108	99.33 293	99.76 62	99.34 122	99.97 18	98.93 208	99.91 42	99.79 93	98.68 138	99.93 93	96.80 303	99.56 274	99.30 265

TSAR-MVS + GP.		99.12 185	99.04 183	99.38 216	99.34 288	99.16 217	98.15 317	99.29 296	98.18 289	99.63 158	99.62 195	99.18 76	99.68 346	98.20 196	99.74 216	99.30 265

PVSNet_Blended		98.70 246	98.59 240	99.02 281	99.54 214	97.99 311	97.58 360	99.82 64	95.70 367	99.34 248	98.98 351	98.52 167	99.77 311	97.98 214	99.83 168	99.30 265

MVS_111021_LR		99.13 183	99.03 185	99.42 200	99.58 190	99.32 189	97.91 346	99.73 111	98.68 238	99.31 257	99.48 258	99.09 87	99.66 355	97.70 245	99.77 205	99.29 268

dmvs_testset		97.27 324	96.83 334	98.59 319	99.46 253	97.55 331	99.25 156	96.84 382	98.78 228	97.24 381	97.67 392	97.11 270	98.97 392	86.59 396	98.54 365	99.27 269

miper_lstm_enhance		98.65 250	98.60 238	98.82 309	99.20 320	97.33 338	97.78 351	99.66 146	99.01 198	99.59 179	99.50 251	94.62 315	99.85 237	98.12 205	99.90 114	99.26 270

MVS		95.72 356	94.63 361	98.99 283	98.56 378	97.98 317	99.30 135	98.86 337	72.71 395	97.30 379	99.08 336	98.34 191	99.74 319	89.21 387	98.33 369	99.26 270

MSLP-MVS++		99.05 197	99.09 166	98.91 294	99.21 317	98.36 289	98.82 258	99.47 250	98.85 218	98.90 310	99.56 233	98.78 125	99.09 390	98.57 173	99.68 241	99.26 270

D2MVS		99.22 157	99.19 141	99.29 240	99.69 154	98.74 260	98.81 259	99.41 264	98.55 249	99.68 141	99.69 152	98.13 211	99.87 202	98.82 153	99.98 39	99.24 273

test_yl		98.25 287	97.95 295	99.13 268	99.17 325	98.47 278	99.00 229	98.67 348	98.97 201	99.22 273	99.02 346	91.31 348	99.69 336	97.26 278	98.93 342	99.24 273

DCV-MVSNet		98.25 287	97.95 295	99.13 268	99.17 325	98.47 278	99.00 229	98.67 348	98.97 201	99.22 273	99.02 346	91.31 348	99.69 336	97.26 278	98.93 342	99.24 273

DPM-MVS		98.28 285	97.94 299	99.32 233	99.36 278	99.11 222	97.31 373	98.78 342	96.88 349	98.84 317	99.11 334	97.77 237	99.61 369	94.03 377	99.36 310	99.23 276

CLD-MVS		98.76 238	98.57 244	99.33 229	99.57 200	98.97 237	97.53 363	99.55 214	96.41 356	99.27 264	99.13 327	99.07 92	99.78 303	96.73 307	99.89 123	99.23 276
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
pmmvs4		99.13 183	99.06 174	99.36 223	99.57 200	99.10 227	98.01 333	99.25 306	98.78 228	99.58 181	99.44 269	98.24 200	99.76 313	98.74 163	99.93 100	99.22 278

OMC-MVS		98.90 224	98.72 230	99.44 194	99.39 270	99.42 164	98.58 281	99.64 161	97.31 336	99.44 223	99.62 195	98.59 152	99.69 336	96.17 335	99.79 196	99.22 278

EGC-MVSNET		89.05 362	85.52 365	99.64 127	99.89 40	99.78 49	99.56 81	99.52 234	24.19 397	49.96 398	99.83 66	99.15 79	99.92 115	97.71 242	99.85 155	99.21 280

eth_miper_zixun_eth		98.68 248	98.71 231	98.60 318	99.10 338	96.84 351	97.52 365	99.54 220	98.94 205	99.58 181	99.48 258	96.25 298	99.76 313	98.01 212	99.93 100	99.21 280

c3_l		98.72 244	98.71 231	98.72 314	99.12 332	97.22 341	97.68 356	99.56 208	98.90 212	99.54 198	99.48 258	96.37 294	99.73 322	97.88 223	99.88 132	99.21 280

CMPMVS	77.52 23	98.50 266	98.19 281	99.41 207	98.33 385	99.56 134	99.01 226	99.59 191	95.44 369	99.57 184	99.80 83	95.64 305	99.46 385	96.47 322	99.92 104	99.21 280
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Effi-MVS+		99.06 194	98.97 202	99.34 226	99.31 296	98.98 235	98.31 307	99.91 32	98.81 223	98.79 323	98.94 357	99.14 82	99.84 252	98.79 157	98.74 355	99.20 284

DELS-MVS		99.34 129	99.30 122	99.48 184	99.51 227	99.36 181	98.12 321	99.53 229	99.36 148	99.41 235	99.61 204	99.22 72	99.87 202	99.21 107	99.68 241	99.20 284
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
EC-MVSNet		99.69 41	99.69 41	99.68 105	99.71 142	99.91 4	99.76 19	99.96 23	99.86 44	99.51 210	99.39 280	99.57 36	99.93 93	99.64 46	99.86 151	99.20 284

CANet_DTU		98.91 222	98.85 218	99.09 273	98.79 368	98.13 301	98.18 314	99.31 292	99.48 124	98.86 315	99.51 248	96.56 284	99.95 62	99.05 132	99.95 82	99.19 287

alignmvs		98.28 285	97.96 294	99.25 251	99.12 332	98.93 243	99.03 221	98.42 359	99.64 102	98.72 329	97.85 390	90.86 357	99.62 365	98.88 149	99.13 331	99.19 287

DIV-MVS_self_test		98.54 261	98.42 258	98.92 292	99.03 346	97.80 324	97.46 367	99.59 191	98.90 212	99.60 176	99.46 265	93.87 321	99.78 303	97.97 216	99.89 123	99.18 289

MSDG		99.08 192	98.98 201	99.37 219	99.60 181	99.13 220	97.54 361	99.74 107	98.84 221	99.53 203	99.55 240	99.10 85	99.79 300	97.07 290	99.86 151	99.18 289

cl____		98.54 261	98.41 259	98.92 292	99.03 346	97.80 324	97.46 367	99.59 191	98.90 212	99.60 176	99.46 265	93.85 322	99.78 303	97.97 216	99.89 123	99.17 291

PM-MVS		99.36 122	99.29 127	99.58 155	99.83 64	99.66 102	98.95 241	99.86 46	98.85 218	99.81 86	99.73 124	98.40 184	99.92 115	98.36 183	99.83 168	99.17 291

thisisatest0530		97.45 319	96.95 329	98.94 288	99.68 162	97.73 326	99.09 207	94.19 394	98.61 245	99.56 191	99.30 301	84.30 390	99.93 93	98.27 190	99.54 283	99.16 293

PatchmatchNet		97.65 313	97.80 306	97.18 362	98.82 366	92.49 387	99.17 177	98.39 361	98.12 290	98.79 323	99.58 220	90.71 359	99.89 174	97.23 282	99.41 304	99.16 293
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tfpnnormal		99.43 101	99.38 102	99.60 149	99.87 50	99.75 68	99.59 74	99.78 89	99.71 80	99.90 48	99.69 152	98.85 116	99.90 157	97.25 281	99.78 201	99.15 295

CS-MVS-test		99.68 44	99.70 37	99.64 127	99.57 200	99.83 29	99.78 12	99.97 18	99.92 26	99.50 212	99.38 282	99.57 36	99.95 62	99.69 41	99.90 114	99.15 295

mvs_anonymous		99.28 138	99.39 100	98.94 288	99.19 322	97.81 322	99.02 224	99.55 214	99.78 68	99.85 71	99.80 83	98.24 200	99.86 220	99.57 54	99.50 292	99.15 295

ab-mvs		99.33 132	99.28 129	99.47 186	99.57 200	99.39 172	99.78 12	99.43 261	98.87 216	99.57 184	99.82 73	98.06 216	99.87 202	98.69 168	99.73 221	99.15 295

MIMVSNet		98.43 274	98.20 278	99.11 270	99.53 220	98.38 288	99.58 76	98.61 350	98.96 203	99.33 250	99.76 112	90.92 354	99.81 291	97.38 269	99.76 207	99.15 295

GSMVS																99.14 300

sam_mvs1												90.81 358				99.14 300

SCA		98.11 295	98.36 264	97.36 357	99.20 320	92.99 385	98.17 316	98.49 357	98.24 284	99.10 291	99.57 229	96.01 302	99.94 76	96.86 299	99.62 257	99.14 300

LS3D		99.24 148	99.11 157	99.61 146	98.38 383	99.79 46	99.57 79	99.68 138	99.61 108	99.15 283	99.71 139	98.70 136	99.91 139	97.54 259	99.68 241	99.13 303

Patchmatch-RL test		98.60 253	98.36 264	99.33 229	99.77 112	99.07 230	98.27 309	99.87 43	98.91 211	99.74 121	99.72 131	90.57 361	99.79 300	98.55 174	99.85 155	99.11 304

test_0402		99.22 157	99.14 148	99.45 191	99.79 97	99.43 161	99.28 144	99.68 138	99.54 118	99.40 240	99.56 233	99.07 92	99.82 276	96.01 339	99.96 69	99.11 304

APD_test1		99.36 122	99.28 129	99.61 146	99.89 40	99.89 10	99.32 127	99.74 107	99.18 173	99.69 138	99.75 117	98.41 180	99.84 252	97.85 229	99.70 232	99.10 306

MVS_Test		99.28 138	99.31 117	99.19 258	99.35 280	98.79 255	99.36 120	99.49 246	99.17 178	99.21 275	99.67 167	98.78 125	99.66 355	99.09 129	99.66 250	99.10 306

AdaColmap		98.60 253	98.35 266	99.38 216	99.12 332	99.22 209	98.67 274	99.42 263	97.84 312	98.81 320	99.27 307	97.32 260	99.81 291	95.14 362	99.53 285	99.10 306

FPMVS		96.32 345	95.50 352	98.79 310	99.60 181	98.17 300	98.46 300	98.80 341	97.16 343	96.28 387	99.63 188	82.19 391	99.09 390	88.45 389	98.89 347	99.10 306

Syy-MVS		98.17 293	97.85 305	99.15 263	98.50 380	98.79 255	98.60 277	99.21 316	97.89 306	96.76 385	96.37 402	95.47 308	99.57 373	99.10 128	98.73 357	99.09 310

myMVS_eth3d		95.63 357	94.73 359	98.34 331	98.50 380	96.36 358	98.60 277	99.21 316	97.89 306	96.76 385	96.37 402	72.10 402	99.57 373	94.38 370	98.73 357	99.09 310

Patchmatch-test		98.10 296	97.98 293	98.48 324	99.27 307	96.48 355	99.40 109	99.07 328	98.81 223	99.23 270	99.57 229	90.11 366	99.87 202	96.69 308	99.64 254	99.09 310

tpm		97.15 326	96.95 329	97.75 349	98.91 355	94.24 379	99.32 127	97.96 369	97.71 316	98.29 350	99.32 297	86.72 384	99.92 115	98.10 207	96.24 392	99.09 310

PMMVS		98.49 268	98.29 272	99.11 270	98.96 353	98.42 283	97.54 361	99.32 288	97.53 324	98.47 346	98.15 386	97.88 229	99.82 276	97.46 264	99.24 327	99.09 310

cl22		97.56 317	97.28 320	98.40 327	98.37 384	96.75 352	97.24 376	99.37 279	97.31 336	99.41 235	99.22 319	87.30 376	99.37 387	97.70 245	99.62 257	99.08 315

ADS-MVSNet2		97.78 307	97.66 314	98.12 340	99.14 328	95.36 371	99.22 164	98.75 343	96.97 347	98.25 352	99.64 178	90.90 355	99.94 76	96.51 319	99.56 274	99.08 315

ADS-MVSNet		97.72 312	97.67 313	97.86 345	99.14 328	94.65 377	99.22 164	98.86 337	96.97 347	98.25 352	99.64 178	90.90 355	99.84 252	96.51 319	99.56 274	99.08 315

pmmvs3		98.08 297	97.80 306	98.91 294	99.41 268	97.69 328	97.87 348	99.66 146	95.87 363	99.50 212	99.51 248	90.35 363	99.97 32	98.55 174	99.47 296	99.08 315

PVSNet	97.47 15	98.42 275	98.44 256	98.35 329	99.46 253	96.26 360	96.70 386	99.34 285	97.68 317	99.00 299	99.13 327	97.40 255	99.72 324	97.59 257	99.68 241	99.08 315

MVS-HIRNet		97.86 303	98.22 276	96.76 366	99.28 305	91.53 393	98.38 303	92.60 396	99.13 186	99.31 257	99.96 12	97.18 268	99.68 346	98.34 185	99.83 168	99.07 320

PMVS	92.94 21	98.82 233	98.81 224	98.85 302	99.84 60	97.99 311	99.20 167	99.47 250	99.71 80	99.42 229	99.82 73	98.09 213	99.47 383	93.88 379	99.85 155	99.07 320
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		99.57 69	99.59 63	99.49 180	99.98 3	99.71 84	99.72 30	99.84 57	99.81 60	99.94 32	99.78 101	98.91 110	99.71 328	98.41 180	99.95 82	99.05 322
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
canonicalmvs		99.02 203	99.00 193	99.09 273	99.10 338	98.70 262	99.61 68	99.66 146	99.63 104	98.64 335	97.65 393	99.04 96	99.54 376	98.79 157	98.92 344	99.04 323

hse-mvs2		98.52 263	98.30 271	99.16 261	99.29 302	98.60 273	98.77 267	99.02 332	99.68 90	99.32 253	99.04 341	92.50 339	99.85 237	99.24 104	97.87 381	99.03 324

CL-MVSNet_self_test		98.71 245	98.56 247	99.15 263	99.22 315	98.66 266	97.14 378	99.51 238	98.09 293	99.54 198	99.27 307	96.87 277	99.74 319	98.43 179	98.96 341	99.03 324

AUN-MVS		97.82 305	97.38 318	99.14 267	99.27 307	98.53 275	98.72 271	99.02 332	98.10 291	97.18 383	99.03 345	89.26 371	99.85 237	97.94 218	97.91 379	99.03 324

MDTV_nov1_ep13_2view						91.44 394	99.14 187		97.37 333	99.21 275		91.78 346		96.75 305		99.03 324

ITE_SJBPF				99.38 216	99.63 174	99.44 157		99.73 111	98.56 248	99.33 250	99.53 244	98.88 114	99.68 346	96.01 339	99.65 252	99.02 328

UnsupCasMVSNet_bld		98.55 260	98.27 273	99.40 209	99.56 211	99.37 177	97.97 340	99.68 138	97.49 327	99.08 292	99.35 293	95.41 309	99.82 276	97.70 245	98.19 374	99.01 329

miper_ehance_all_eth		98.59 256	98.59 240	98.59 319	98.98 352	97.07 345	97.49 366	99.52 234	98.50 255	99.52 205	99.37 284	96.41 292	99.71 328	97.86 227	99.62 257	99.00 330

CS-MVS		99.67 50	99.70 37	99.58 155	99.53 220	99.84 24	99.79 11	99.96 23	99.90 28	99.61 173	99.41 272	99.51 43	99.95 62	99.66 43	99.89 123	98.96 331

CNLPA		98.57 258	98.34 267	99.28 242	99.18 324	99.10 227	98.34 304	99.41 264	98.48 258	98.52 343	98.98 351	97.05 272	99.78 303	95.59 353	99.50 292	98.96 331

new_pmnet		98.88 228	98.89 214	98.84 304	99.70 150	97.62 329	98.15 317	99.50 242	97.98 299	99.62 167	99.54 242	98.15 210	99.94 76	97.55 258	99.84 160	98.95 333

PCF-MVS	96.03 18	96.73 336	95.86 347	99.33 229	99.44 258	99.16 217	96.87 384	99.44 258	86.58 391	98.95 302	99.40 276	94.38 317	99.88 188	87.93 390	99.80 191	98.95 333
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PatchMatch-RL		98.68 248	98.47 253	99.30 239	99.44 258	99.28 195	98.14 319	99.54 220	97.12 345	99.11 289	99.25 312	97.80 235	99.70 330	96.51 319	99.30 318	98.93 335

Fast-Effi-MVS+		99.02 203	98.87 216	99.46 188	99.38 273	99.50 143	99.04 217	99.79 83	97.17 342	98.62 336	98.74 369	99.34 58	99.95 62	98.32 187	99.41 304	98.92 336

ET-MVSNet_ETH3D		96.78 334	96.07 343	98.91 294	99.26 309	97.92 319	97.70 355	96.05 386	97.96 303	92.37 396	98.43 381	87.06 378	99.90 157	98.27 190	97.56 384	98.91 337

EIA-MVS		99.12 185	99.01 190	99.45 191	99.36 278	99.62 116	99.34 122	99.79 83	98.41 263	98.84 317	98.89 361	98.75 130	99.84 252	98.15 204	99.51 289	98.89 338

CostFormer		96.71 337	96.79 336	96.46 372	98.90 356	90.71 398	99.41 108	98.68 346	94.69 380	98.14 360	99.34 296	86.32 386	99.80 297	97.60 256	98.07 378	98.88 339

DP-MVS Recon		98.50 266	98.23 274	99.31 236	99.49 238	99.46 150	98.56 286	99.63 163	94.86 378	98.85 316	99.37 284	97.81 234	99.59 371	96.08 336	99.44 299	98.88 339

test0.0.03 1		97.37 322	96.91 332	98.74 313	97.72 392	97.57 330	97.60 359	97.36 380	98.00 296	99.21 275	98.02 387	90.04 367	99.79 300	98.37 182	95.89 393	98.86 341

BH-untuned		98.22 291	98.09 286	98.58 321	99.38 273	97.24 340	98.55 287	98.98 335	97.81 313	99.20 280	98.76 368	97.01 273	99.65 361	94.83 365	98.33 369	98.86 341

HY-MVS	98.23 9	98.21 292	97.95 295	98.99 283	99.03 346	98.24 292	99.61 68	98.72 344	96.81 352	98.73 328	99.51 248	94.06 319	99.86 220	96.91 296	98.20 372	98.86 341

miper_enhance_ethall		98.03 299	97.94 299	98.32 332	98.27 386	96.43 357	96.95 382	99.41 264	96.37 358	99.43 227	98.96 355	94.74 313	99.69 336	97.71 242	99.62 257	98.83 344

FE-MVS		97.85 304	97.42 317	99.15 263	99.44 258	98.75 258	99.77 15	98.20 366	95.85 364	99.33 250	99.80 83	88.86 372	99.88 188	96.40 324	99.12 332	98.81 345

Effi-MVS+-dtu		99.07 193	98.92 210	99.52 175	98.89 359	99.78 49	99.15 185	99.66 146	99.34 149	98.92 307	99.24 317	97.69 241	99.98 19	98.11 206	99.28 321	98.81 345

EPMVS		96.53 340	96.32 338	97.17 363	98.18 389	92.97 386	99.39 111	89.95 400	98.21 286	98.61 337	99.59 217	86.69 385	99.72 324	96.99 292	99.23 329	98.81 345

FA-MVS(test-final)		98.52 263	98.32 269	99.10 272	99.48 243	98.67 263	99.77 15	98.60 352	97.35 334	99.63 158	99.80 83	93.07 332	99.84 252	97.92 219	99.30 318	98.78 348

MVE	92.54 22	96.66 338	96.11 342	98.31 334	99.68 162	97.55 331	97.94 342	95.60 388	99.37 146	90.68 397	98.70 371	96.56 284	98.61 395	86.94 395	99.55 278	98.77 349
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tpm2		96.35 344	96.22 340	96.73 368	98.88 361	91.75 391	99.21 166	98.51 355	93.27 383	97.89 368	99.21 321	84.83 388	99.70 330	96.04 338	98.18 375	98.75 350

LF4IMVS		99.01 207	98.92 210	99.27 245	99.71 142	99.28 195	98.59 280	99.77 92	98.32 280	99.39 241	99.41 272	98.62 147	99.84 252	96.62 315	99.84 160	98.69 351

thisisatest0515		96.98 330	96.42 337	98.66 317	99.42 267	97.47 333	97.27 374	94.30 393	97.24 338	99.15 283	98.86 363	85.01 387	99.87 202	97.10 288	99.39 306	98.63 352

Fast-Effi-MVS+-dtu		99.20 164	99.12 154	99.43 198	99.25 310	99.69 95	99.05 214	99.82 64	99.50 122	98.97 300	99.05 339	98.98 102	99.98 19	98.20 196	99.24 327	98.62 353

PAPM		95.61 358	94.71 360	98.31 334	99.12 332	96.63 353	96.66 387	98.46 358	90.77 388	96.25 388	98.68 372	93.01 333	99.69 336	81.60 397	97.86 382	98.62 353

JIA-IIPM		98.06 298	97.92 301	98.50 323	98.59 377	97.02 346	98.80 262	98.51 355	99.88 39	97.89 368	99.87 47	91.89 343	99.90 157	98.16 203	97.68 383	98.59 355

dp		96.86 332	97.07 325	96.24 374	98.68 376	90.30 400	99.19 171	98.38 362	97.35 334	98.23 354	99.59 217	87.23 377	99.82 276	96.27 330	98.73 357	98.59 355

OpenMVS	98.12 10	98.23 290	97.89 304	99.26 248	99.19 322	99.26 199	99.65 59	99.69 135	91.33 387	98.14 360	99.77 108	98.28 197	99.96 53	95.41 357	99.55 278	98.58 357

baseline2		96.83 333	96.28 339	98.46 325	99.09 340	96.91 349	98.83 254	93.87 395	97.23 339	96.23 390	98.36 382	88.12 374	99.90 157	96.68 309	98.14 376	98.57 358

TESTMET0.1,1		96.24 347	95.84 348	97.41 356	98.24 387	93.84 382	97.38 369	95.84 387	98.43 260	97.81 373	98.56 376	79.77 395	99.89 174	97.77 234	98.77 351	98.52 359

xiu_mvs_v1_base_debu		99.23 149	99.34 110	98.91 294	99.59 185	98.23 293	98.47 296	99.66 146	99.61 108	99.68 141	98.94 357	99.39 48	99.97 32	99.18 113	99.55 278	98.51 360

xiu_mvs_v1_base		99.23 149	99.34 110	98.91 294	99.59 185	98.23 293	98.47 296	99.66 146	99.61 108	99.68 141	98.94 357	99.39 48	99.97 32	99.18 113	99.55 278	98.51 360

xiu_mvs_v1_base_debi		99.23 149	99.34 110	98.91 294	99.59 185	98.23 293	98.47 296	99.66 146	99.61 108	99.68 141	98.94 357	99.39 48	99.97 32	99.18 113	99.55 278	98.51 360

KD-MVS_2432*1600		95.89 351	95.41 354	97.31 360	94.96 397	93.89 380	97.09 379	99.22 313	97.23 339	98.88 311	99.04 341	79.23 396	99.54 376	96.24 332	96.81 387	98.50 363

miper_refine_blended		95.89 351	95.41 354	97.31 360	94.96 397	93.89 380	97.09 379	99.22 313	97.23 339	98.88 311	99.04 341	79.23 396	99.54 376	96.24 332	96.81 387	98.50 363

CR-MVSNet		98.35 283	98.20 278	98.83 306	99.05 343	98.12 302	99.30 135	99.67 142	97.39 332	99.16 281	99.79 93	91.87 344	99.91 139	98.78 160	98.77 351	98.44 365

RPMNet		98.60 253	98.53 250	98.83 306	99.05 343	98.12 302	99.30 135	99.62 166	99.86 44	99.16 281	99.74 120	92.53 338	99.92 115	98.75 162	98.77 351	98.44 365

tpmrst		97.73 309	98.07 287	96.73 368	98.71 374	92.00 389	99.10 202	98.86 337	98.52 253	98.92 307	99.54 242	91.90 342	99.82 276	98.02 209	99.03 338	98.37 367

test-LLR		97.15 326	96.95 329	97.74 350	98.18 389	95.02 374	97.38 369	96.10 383	98.00 296	97.81 373	98.58 373	90.04 367	99.91 139	97.69 251	98.78 349	98.31 368

test-mter		96.23 348	95.73 349	97.74 350	98.18 389	95.02 374	97.38 369	96.10 383	97.90 305	97.81 373	98.58 373	79.12 398	99.91 139	97.69 251	98.78 349	98.31 368

ETV-MVS		99.18 171	99.18 142	99.16 261	99.34 288	99.28 195	99.12 197	99.79 83	99.48 124	98.93 304	98.55 377	99.40 47	99.93 93	98.51 176	99.52 288	98.28 370

PatchT		98.45 273	98.32 269	98.83 306	98.94 354	98.29 291	99.24 157	98.82 340	99.84 52	99.08 292	99.76 112	91.37 347	99.94 76	98.82 153	99.00 340	98.26 371

xiu_mvs_v2_base		99.02 203	99.11 157	98.77 311	99.37 275	98.09 306	98.13 320	99.51 238	99.47 128	99.42 229	98.54 378	99.38 52	99.97 32	98.83 151	99.33 314	98.24 372

IB-MVS	95.41 20	95.30 359	94.46 363	97.84 346	98.76 372	95.33 372	97.33 372	96.07 385	96.02 362	95.37 394	97.41 395	76.17 400	99.96 53	97.54 259	95.44 394	98.22 373
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
tpm cat1		96.78 334	96.98 328	96.16 375	98.85 362	90.59 399	99.08 210	99.32 288	92.37 384	97.73 377	99.46 265	91.15 351	99.69 336	96.07 337	98.80 348	98.21 374

MAR-MVS		98.24 289	97.92 301	99.19 258	98.78 370	99.65 107	99.17 177	99.14 324	95.36 370	98.04 363	98.81 366	97.47 252	99.72 324	95.47 356	99.06 335	98.21 374
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
PS-MVSNAJ		99.00 209	99.08 168	98.76 312	99.37 275	98.10 305	98.00 335	99.51 238	99.47 128	99.41 235	98.50 380	99.28 64	99.97 32	98.83 151	99.34 313	98.20 376

cascas		96.99 329	96.82 335	97.48 353	97.57 395	95.64 369	96.43 388	99.56 208	91.75 385	97.13 384	97.61 394	95.58 307	98.63 394	96.68 309	99.11 333	98.18 377

BH-w/o		97.20 325	97.01 327	97.76 348	99.08 341	95.69 368	98.03 332	98.52 354	95.76 366	97.96 365	98.02 387	95.62 306	99.47 383	92.82 381	97.25 386	98.12 378

tpmvs		97.39 321	97.69 311	96.52 370	98.41 382	91.76 390	99.30 135	98.94 336	97.74 314	97.85 371	99.55 240	92.40 341	99.73 322	96.25 331	98.73 357	98.06 379

thres600view7		96.60 339	96.16 341	97.93 343	99.63 174	96.09 364	99.18 172	97.57 375	98.77 230	98.72 329	97.32 396	87.04 379	99.72 324	88.57 388	98.62 362	97.98 380

thres400		96.40 342	95.89 345	97.92 344	99.58 190	96.11 362	99.00 229	97.54 378	98.43 260	98.52 343	96.98 399	86.85 381	99.67 351	87.62 391	98.51 366	97.98 380

TR-MVS		97.44 320	97.15 324	98.32 332	98.53 379	97.46 334	98.47 296	97.91 371	96.85 350	98.21 355	98.51 379	96.42 290	99.51 381	92.16 382	97.29 385	97.98 380

1314		98.00 301	97.90 303	98.27 336	98.90 356	97.45 335	99.30 135	99.06 330	94.98 375	97.21 382	99.12 331	98.43 177	99.67 351	95.58 354	98.56 364	97.71 383

E-PMN		97.14 328	97.43 316	96.27 373	98.79 368	91.62 392	95.54 390	99.01 334	99.44 134	98.88 311	99.12 331	92.78 335	99.68 346	94.30 372	99.03 338	97.50 384

gg-mvs-nofinetune		95.87 353	95.17 357	97.97 342	98.19 388	96.95 347	99.69 42	89.23 401	99.89 34	96.24 389	99.94 16	81.19 392	99.51 381	93.99 378	98.20 372	97.44 385

DeepMVS_CX				97.98 341	99.69 154	96.95 347		99.26 303	75.51 394	95.74 392	98.28 384	96.47 288	99.62 365	91.23 385	97.89 380	97.38 386

OpenMVS_ROB	97.31 17	97.36 323	96.84 333	98.89 301	99.29 302	99.45 155	98.87 248	99.48 247	86.54 392	99.44 223	99.74 120	97.34 259	99.86 220	91.61 383	99.28 321	97.37 387

EMVS		96.96 331	97.28 320	95.99 376	98.76 372	91.03 395	95.26 391	98.61 350	99.34 149	98.92 307	98.88 362	93.79 323	99.66 355	92.87 380	99.05 336	97.30 388

thres100view900		96.39 343	96.03 344	97.47 354	99.63 174	95.93 365	99.18 172	97.57 375	98.75 234	98.70 332	97.31 397	87.04 379	99.67 351	87.62 391	98.51 366	96.81 389

tfpn200view9		96.30 346	95.89 345	97.53 352	99.58 190	96.11 362	99.00 229	97.54 378	98.43 260	98.52 343	96.98 399	86.85 381	99.67 351	87.62 391	98.51 366	96.81 389

API-MVS		98.38 279	98.39 261	98.35 329	98.83 363	99.26 199	99.14 187	99.18 320	98.59 246	98.66 334	98.78 367	98.61 149	99.57 373	94.14 374	99.56 274	96.21 391

thres200		96.09 349	95.68 350	97.33 359	99.48 243	96.22 361	98.53 291	97.57 375	98.06 295	98.37 349	96.73 401	86.84 383	99.61 369	86.99 394	98.57 363	96.16 392

GG-mvs-BLEND				97.36 357	97.59 393	96.87 350	99.70 35	88.49 402		94.64 395	97.26 398	80.66 393	99.12 389	91.50 384	96.50 391	96.08 393

wuyk23d		97.58 316	99.13 150	92.93 378	99.69 154	99.49 144	99.52 86	99.77 92	97.97 300	99.96 23	99.79 93	99.84 12	99.94 76	95.85 347	99.82 177	79.36 394

test123		29.31 363	33.05 368	18.08 380	25.93 403	12.24 405	97.53 363	10.93 405	11.78 398	24.21 399	50.08 408	21.04 403	8.60 399	23.51 398	32.43 398	33.39 395

testmvs		28.94 364	33.33 366	15.79 381	26.03 402	9.81 406	96.77 385	15.67 404	11.55 399	23.87 400	50.74 407	19.03 404	8.53 400	23.21 399	33.07 397	29.03 396

test_blank		8.33 367	11.11 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		8.33 367	11.11 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		8.33 367	11.11 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

cdsmvs_eth3d_5k		24.88 365	33.17 367	0.00 382	0.00 404	0.00 407	0.00 393	99.62 166	0.00 400	0.00 401	99.13 327	99.82 13	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		16.61 366	22.14 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	99.28 64	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		8.33 367	11.11 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		8.33 367	11.11 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		8.33 367	11.11 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		8.33 367	11.11 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

ab-mvs-re		8.26 375	11.02 378	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	99.16 325	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		8.33 367	11.11 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	100.00 1	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

WAC-MVS						96.36 358								95.20 361

FOURS1					99.83 64	99.89 10	99.74 24	99.71 123	99.69 88	99.63 158

test_one_0601					99.63 174	99.76 62		99.55 214	99.23 166	99.31 257	99.61 204	98.59 152

eth-test2					0.00 404

eth-test					0.00 404

ZD-MVS					99.43 262	99.61 122		99.43 261	96.38 357	99.11 289	99.07 337	97.86 230	99.92 115	94.04 376	99.49 294

test_241102_ONE					99.69 154	99.82 35		99.54 220	99.12 189	99.82 79	99.49 255	98.91 110	99.52 380

9.14			98.64 235		99.45 257		98.81 259	99.60 185	97.52 325	99.28 263	99.56 233	98.53 164	99.83 267	95.36 359	99.64 254

save fliter					99.53 220	99.25 202	98.29 308	99.38 278	99.07 193

test0726					99.69 154	99.80 44	99.24 157	99.57 203	99.16 180	99.73 125	99.65 176	98.35 188

test_part2					99.62 178	99.67 100				99.55 196

sam_mvs												90.52 362

MTGPA								99.53 229

test_post1							99.14 187				51.63 406	89.54 370	99.82 276	96.86 299

test_post											52.41 405	90.25 364	99.86 220

patchmatchnet-post											99.62 195	90.58 360	99.94 76

MTMP							99.09 207	98.59 353

gm-plane-assit					97.59 393	89.02 402			93.47 382		98.30 383		99.84 252	96.38 326

TEST9					99.35 280	99.35 184	98.11 323	99.41 264	94.83 379	97.92 366	98.99 348	98.02 219	99.85 237

test_8					99.34 288	99.31 190	98.08 327	99.40 271	94.90 376	97.87 370	98.97 353	98.02 219	99.84 252

agg_prior					99.35 280	99.36 181		99.39 274		97.76 376			99.85 237

test_prior4						99.19 215	98.00 335

test_prior2							97.95 341		97.87 309	98.05 362	99.05 339	97.90 227		95.99 342	99.49 294

旧先验2							97.94 342		95.33 371	98.94 303			99.88 188	96.75 305

新几何2							98.04 331

原ACMM2							97.92 344

testdata2													99.89 174	95.99 342

segment_acmp												98.37 186

testdata1							97.72 353		97.86 311

plane_prior7					99.58 190	99.38 174

plane_prior6					99.47 249	99.26 199						97.24 262

plane_prior4											99.25 312

plane_prior3						99.31 190			98.36 269	99.14 285

plane_prior2							98.80 262		98.94 205

plane_prior1					99.51 227

plane_prior						99.24 206	98.42 301		97.87 309						99.71 230

n2								0.00 406

nn								0.00 406

door-mid								99.83 59

test11								99.29 296

door								99.77 92

HQP5-MVS						98.94 240

HQP-NCC					99.31 296		97.98 337		97.45 328	98.15 356

ACMP_Plane					99.31 296		97.98 337		97.45 328	98.15 356

BP-MVS														94.73 366

HQP3-MVS								99.37 279							99.67 247

HQP2-MVS												96.67 281

NP-MVS					99.40 269	99.13 220					98.83 364

MDTV_nov1_ep13			97.73 310		98.70 375	90.83 396	99.15 185	98.02 368	98.51 254	98.82 319	99.61 204	90.98 353	99.66 355	96.89 298	98.92 344

ACMMP++_ref															99.94 93

ACMMP++															99.79 196

Test By Simon												98.41 180

High-resolution multi-view benchmark