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.

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 10	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 11	100.00 1	99.85 19

Gipuma		99.03 60	99.16 45	98.64 182	99.94 2	98.51 102	99.32 23	99.75 31	99.58 25	98.60 212	99.62 34	98.22 74	99.51 328	97.70 142	99.73 142	97.89 354
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 24	99.31 30	99.53 34	99.91 3	98.98 65	99.63 6	99.58 54	99.44 38	99.78 26	99.76 10	96.39 195	99.92 51	99.44 36	99.92 55	99.68 55

pmmvs6		99.67 3	99.70 3	99.60 11	99.90 4	99.27 22	99.53 7	99.76 28	99.64 15	99.84 20	99.83 3	99.50 8	99.87 101	99.36 38	99.92 55	99.64 64

PS-MVSNAJss		99.46 14	99.49 12	99.35 70	99.90 4	98.15 129	99.20 45	99.65 45	99.48 32	99.92 8	99.71 17	98.07 86	99.96 12	99.53 30	100.00 1	99.93 8

testf1		99.25 33	99.16 45	99.51 43	99.89 6	99.63 3	98.71 92	99.69 36	98.90 99	99.43 76	99.35 84	98.86 28	99.67 266	97.81 134	99.81 100	99.24 224

APD_test2		99.25 33	99.16 45	99.51 43	99.89 6	99.63 3	98.71 92	99.69 36	98.90 99	99.43 76	99.35 84	98.86 28	99.67 266	97.81 134	99.81 100	99.24 224

ANet_high		99.57 7	99.67 5	99.28 86	99.89 6	98.09 136	99.14 54	99.93 4	99.82 3	99.93 6	99.81 5	99.17 18	99.94 36	99.31 41	100.00 1	99.82 25

anonymousdsp		99.51 11	99.47 16	99.62 6	99.88 9	99.08 63	99.34 20	99.69 36	98.93 97	99.65 45	99.72 16	98.93 26	99.95 23	99.11 53	100.00 1	99.82 25

v7n		99.53 9	99.57 9	99.41 60	99.88 9	98.54 100	99.45 10	99.61 50	99.66 13	99.68 39	99.66 27	98.44 59	99.95 23	99.73 19	99.96 25	99.75 43

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 9	98.61 92	99.34 20	99.71 33	99.27 58	99.90 12	99.74 13	99.68 4	99.97 4	99.55 29	99.99 5	99.88 14

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 64	99.87 12	98.13 132	98.08 160	99.95 1	99.45 36	99.98 2	99.75 11	99.80 1	99.97 4	99.82 8	99.99 5	99.99 1

RRT_MVS		99.09 54	98.94 67	99.55 23	99.87 12	98.82 78	99.48 9	98.16 317	99.49 31	99.59 52	99.65 30	94.79 257	99.95 23	99.45 35	99.96 25	99.88 14

jajsoiax		99.58 6	99.61 8	99.48 51	99.87 12	98.61 92	99.28 37	99.66 44	99.09 82	99.89 15	99.68 20	99.53 7	99.97 4	99.50 32	99.99 5	99.87 16

test_djsdf		99.52 10	99.51 11	99.53 34	99.86 15	98.74 82	99.39 17	99.56 68	99.11 72	99.70 35	99.73 15	99.00 22	99.97 4	99.26 44	99.98 12	99.89 11

MIMVSNet1		99.38 23	99.32 28	99.55 23	99.86 15	99.19 37	99.41 13	99.59 52	99.59 23	99.71 33	99.57 42	97.12 155	99.90 65	99.21 49	99.87 78	99.54 109

bld_raw_dy_0_64		99.07 58	99.00 62	99.29 84	99.85 17	98.18 126	99.11 58	99.40 123	99.33 50	99.38 87	99.44 71	95.21 240	99.97 4	99.31 41	99.98 12	99.73 45

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 21	99.85 17	99.11 59	99.90 1	99.78 26	99.63 17	99.78 26	99.67 25	99.48 9	99.81 179	99.30 43	99.97 20	99.77 35
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
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 19	99.34 15	99.69 4	99.58 54	99.90 2	99.86 18	99.78 8	99.58 6	99.95 23	99.00 62	99.95 32	99.78 33

mvsmamba		99.24 37	99.15 50	99.49 48	99.83 20	98.85 74	99.41 13	99.55 72	99.54 27	99.40 83	99.52 57	95.86 223	99.91 60	99.32 40	99.95 32	99.70 52

SixPastTwentyTwo		98.75 96	98.62 105	99.16 106	99.83 20	97.96 156	99.28 37	98.20 314	99.37 45	99.70 35	99.65 30	92.65 298	99.93 41	99.04 59	99.84 86	99.60 75

Baseline_NR-MVSNet		98.98 66	98.86 75	99.36 64	99.82 22	98.55 97	97.47 242	99.57 61	99.37 45	99.21 120	99.61 37	96.76 179	99.83 156	98.06 118	99.83 93	99.71 47

pm-mvs1		99.44 15	99.48 14	99.33 78	99.80 23	98.63 89	99.29 33	99.63 46	99.30 55	99.65 45	99.60 39	99.16 20	99.82 166	99.07 56	99.83 93	99.56 98

TransMVSNet (Re)		99.44 15	99.47 16	99.36 64	99.80 23	98.58 95	99.27 39	99.57 61	99.39 43	99.75 30	99.62 34	99.17 18	99.83 156	99.06 57	99.62 187	99.66 59

K. test v3		98.00 191	97.66 213	99.03 131	99.79 25	97.56 186	99.19 49	92.47 388	99.62 20	99.52 62	99.66 27	89.61 321	99.96 12	99.25 46	99.81 100	99.56 98

test_fmvsmconf0.1_n		99.49 12	99.54 10	99.34 73	99.78 26	98.11 133	97.77 204	99.90 9	99.33 50	99.97 3	99.66 27	99.71 3	99.96 12	99.79 13	99.99 5	99.96 5

APD_test1		98.83 84	98.66 99	99.34 73	99.78 26	99.47 6	98.42 129	99.45 107	98.28 138	98.98 150	99.19 114	97.76 108	99.58 305	96.57 219	99.55 213	98.97 269

test_vis3_rt		99.14 46	99.17 43	99.07 121	99.78 26	98.38 109	98.92 76	99.94 2	97.80 174	99.91 11	99.67 25	97.15 154	98.91 384	99.76 16	99.56 210	99.92 9

EGC-MVSNET		85.24 366	80.54 369	99.34 73	99.77 29	99.20 34	99.08 59	99.29 175	12.08 402	20.84 403	99.42 74	97.55 126	99.85 122	97.08 174	99.72 149	98.96 271

Anonymous20240521		98.69 107	98.87 72	98.16 239	99.77 29	95.11 281	99.08 59	99.44 111	99.34 49	99.33 97	99.55 48	94.10 275	99.94 36	99.25 46	99.96 25	99.42 162

FC-MVSNet-test		99.27 30	99.25 38	99.34 73	99.77 29	98.37 111	99.30 32	99.57 61	99.61 22	99.40 83	99.50 59	97.12 155	99.85 122	99.02 61	99.94 40	99.80 29

test_vis1_n		98.31 162	98.50 121	97.73 272	99.76 32	94.17 307	98.68 95	99.91 7	96.31 275	99.79 25	99.57 42	92.85 295	99.42 345	99.79 13	99.84 86	99.60 75

test_fmvs3		99.12 51	99.41 19	98.25 231	99.76 32	95.07 282	99.05 65	99.94 2	97.78 176	99.82 21	99.84 2	98.56 52	99.71 247	99.96 1	99.96 25	99.97 3

XXY-MVS		99.14 46	99.15 50	99.10 115	99.76 32	97.74 176	98.85 82	99.62 47	98.48 125	99.37 90	99.49 63	98.75 36	99.86 110	98.20 110	99.80 110	99.71 47

TDRefinement		99.42 19	99.38 21	99.55 23	99.76 32	99.33 16	99.68 5	99.71 33	99.38 44	99.53 60	99.61 37	98.64 43	99.80 186	98.24 107	99.84 86	99.52 119

fmvsm_s_conf0.1_n_a		99.17 42	99.30 32	98.80 161	99.75 36	96.59 233	97.97 180	99.86 13	98.22 141	99.88 17	99.71 17	98.59 49	99.84 139	99.73 19	99.98 12	99.98 2

tt0805		98.69 107	98.62 105	98.90 151	99.75 36	99.30 17	99.15 53	96.97 347	98.86 102	98.87 178	97.62 325	98.63 45	98.96 381	99.41 37	98.29 335	98.45 327

test_vis1_n_1920		98.40 151	98.92 69	96.81 326	99.74 38	90.76 373	98.15 152	99.91 7	98.33 130	99.89 15	99.55 48	95.07 245	99.88 84	99.76 16	99.93 44	99.79 30

FOURS1					99.73 39	99.67 2	99.43 11	99.54 77	99.43 40	99.26 112

PEN-MVS		99.41 20	99.34 25	99.62 6	99.73 39	99.14 52	99.29 33	99.54 77	99.62 20	99.56 53	99.42 74	98.16 82	99.96 12	98.78 73	99.93 44	99.77 35

lessismore_v0				98.97 139	99.73 39	97.53 188		86.71 401		99.37 90	99.52 57	89.93 319	99.92 51	98.99 63	99.72 149	99.44 155

SteuartSystems-ACMMP		98.79 89	98.54 116	99.54 27	99.73 39	99.16 43	98.23 143	99.31 159	97.92 165	98.90 168	98.90 189	98.00 92	99.88 84	96.15 250	99.72 149	99.58 87
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 180	98.15 171	98.22 234	99.73 39	95.15 278	97.36 248	99.68 41	94.45 327	98.99 149	99.27 99	96.87 169	99.94 36	97.13 171	99.91 63	99.57 92

Vis-MVSNet		99.34 25	99.36 22	99.27 89	99.73 39	98.26 118	99.17 50	99.78 26	99.11 72	99.27 108	99.48 64	98.82 31	99.95 23	98.94 65	99.93 44	99.59 81
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 100	98.74 84	98.62 187	99.72 45	96.08 249	98.74 86	98.64 295	99.74 6	99.67 41	99.24 106	94.57 261	99.95 23	99.11 53	99.24 267	99.82 25

test_f		98.67 115	98.87 72	98.05 248	99.72 45	95.59 260	98.51 116	99.81 23	96.30 277	99.78 26	99.82 4	96.14 204	98.63 389	99.82 8	99.93 44	99.95 6

ACMH	96.65 7	99.25 33	99.24 39	99.26 91	99.72 45	98.38 109	99.07 62	99.55 72	98.30 133	99.65 45	99.45 70	99.22 15	99.76 222	98.44 98	99.77 124	99.64 64
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 45	99.33 26	98.64 182	99.71 48	96.10 244	97.87 192	99.85 15	98.56 122	99.90 12	99.68 20	98.69 41	99.85 122	99.72 21	99.98 12	99.97 3

PS-CasMVS		99.40 21	99.33 26	99.62 6	99.71 48	99.10 60	99.29 33	99.53 80	99.53 29	99.46 71	99.41 77	98.23 71	99.95 23	98.89 69	99.95 32	99.81 28

DTE-MVSNet		99.43 18	99.35 23	99.66 4	99.71 48	99.30 17	99.31 27	99.51 84	99.64 15	99.56 53	99.46 66	98.23 71	99.97 4	98.78 73	99.93 44	99.72 46

WR-MVS_H		99.33 26	99.22 40	99.65 5	99.71 48	99.24 25	99.32 23	99.55 72	99.46 35	99.50 67	99.34 88	97.30 144	99.93 41	98.90 67	99.93 44	99.77 35

HPM-MVS_fast		99.01 61	98.82 78	99.57 16	99.71 48	99.35 12	99.00 69	99.50 86	97.33 218	98.94 164	98.86 199	98.75 36	99.82 166	97.53 149	99.71 154	99.56 98

ACMH+	96.62 9	99.08 57	99.00 62	99.33 78	99.71 48	98.83 76	98.60 102	99.58 54	99.11 72	99.53 60	99.18 117	98.81 32	99.67 266	96.71 211	99.77 124	99.50 124

PMVS	91.26 20	97.86 202	97.94 191	97.65 276	99.71 48	97.94 158	98.52 111	98.68 291	98.99 91	97.52 296	99.35 84	97.41 139	98.18 393	91.59 358	99.67 173	96.82 381
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 46	99.09 55	99.29 84	99.70 55	98.28 117	99.13 55	99.52 83	99.48 32	99.24 117	99.41 77	96.79 176	99.82 166	98.69 82	99.88 75	99.76 39

VPNet		98.87 79	98.83 77	99.01 134	99.70 55	97.62 185	98.43 127	99.35 141	99.47 34	99.28 106	99.05 148	96.72 182	99.82 166	98.09 116	99.36 247	99.59 81

test_cas_vis1_n_1920		98.33 159	98.68 96	97.27 303	99.69 57	92.29 352	98.03 168	99.85 15	97.62 186	99.96 4	99.62 34	93.98 276	99.74 234	99.52 31	99.86 81	99.79 30

MP-MVS-pluss		98.57 128	98.23 161	99.60 11	99.69 57	99.35 12	97.16 265	99.38 128	94.87 317	98.97 154	98.99 166	98.01 91	99.88 84	97.29 159	99.70 159	99.58 87
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 38	99.32 28	98.96 140	99.68 59	97.35 197	98.84 84	99.48 95	99.69 9	99.63 48	99.68 20	99.03 21	99.96 12	97.97 125	99.92 55	99.57 92

sd_testset		99.28 29	99.31 30	99.19 102	99.68 59	98.06 145	99.41 13	99.30 167	99.69 9	99.63 48	99.68 20	99.25 14	99.96 12	97.25 162	99.92 55	99.57 92

test_fmvs1_n		98.09 185	98.28 155	97.52 289	99.68 59	93.47 331	98.63 98	99.93 4	95.41 306	99.68 39	99.64 32	91.88 307	99.48 334	99.82 8	99.87 78	99.62 68

CHOSEN 1792x2688		97.49 229	97.14 245	98.54 204	99.68 59	96.09 247	96.50 297	99.62 47	91.58 365	98.84 182	98.97 172	92.36 300	99.88 84	96.76 204	99.95 32	99.67 58

tfpnnormal		98.90 76	98.90 71	98.91 148	99.67 63	97.82 169	99.00 69	99.44 111	99.45 36	99.51 66	99.24 106	98.20 77	99.86 110	95.92 259	99.69 162	99.04 257

MTAPA		98.88 78	98.64 102	99.61 9	99.67 63	99.36 11	98.43 127	99.20 198	98.83 106	98.89 170	98.90 189	96.98 165	99.92 51	97.16 166	99.70 159	99.56 98

test_fmvsmvis_n_1920		99.26 32	99.49 12	98.54 204	99.66 65	96.97 219	98.00 174	99.85 15	99.24 60	99.92 8	99.50 59	99.39 11	99.95 23	99.89 3	99.98 12	98.71 308

fmvsm_l_conf0.5_n_a		99.19 41	99.27 35	98.94 143	99.65 66	97.05 215	97.80 200	99.76 28	98.70 110	99.78 26	99.11 134	98.79 34	99.95 23	99.85 5	99.96 25	99.83 22

WB-MVS		98.52 140	98.55 114	98.43 216	99.65 66	95.59 260	98.52 111	98.77 282	99.65 14	99.52 62	99.00 165	94.34 267	99.93 41	98.65 85	98.83 311	99.76 39

CP-MVSNet		99.21 39	99.09 55	99.56 21	99.65 66	98.96 70	99.13 55	99.34 147	99.42 41	99.33 97	99.26 101	97.01 163	99.94 36	98.74 77	99.93 44	99.79 30

HPM-MVS		98.79 89	98.53 117	99.59 15	99.65 66	99.29 19	99.16 51	99.43 117	96.74 258	98.61 210	98.38 271	98.62 46	99.87 101	96.47 231	99.67 173	99.59 81
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 123	98.36 145	99.42 58	99.65 66	99.42 7	98.55 107	99.57 61	97.72 180	98.90 168	99.26 101	96.12 206	99.52 324	95.72 270	99.71 154	99.32 205

fmvsm_l_conf0.5_n		99.21 39	99.28 34	99.02 133	99.64 71	97.28 201	97.82 197	99.76 28	98.73 107	99.82 21	99.09 140	98.81 32	99.95 23	99.86 4	99.96 25	99.83 22

test_fmvsmconf_n		99.44 15	99.48 14	99.31 83	99.64 71	98.10 135	97.68 215	99.84 18	99.29 56	99.92 8	99.57 42	99.60 5	99.96 12	99.74 18	99.98 12	99.89 11

TSAR-MVS + MP.		98.63 121	98.49 125	99.06 127	99.64 71	97.90 160	98.51 116	98.94 249	96.96 246	99.24 117	98.89 195	97.83 102	99.81 179	96.88 194	99.49 232	99.48 138
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 85	98.72 88	99.12 111	99.64 71	98.54 100	97.98 177	99.68 41	97.62 186	99.34 96	99.18 117	97.54 127	99.77 216	97.79 136	99.74 139	99.04 257

KD-MVS_self_test		99.25 33	99.18 42	99.44 57	99.63 75	99.06 64	98.69 94	99.54 77	99.31 53	99.62 51	99.53 54	97.36 142	99.86 110	99.24 48	99.71 154	99.39 177

EU-MVSNet		97.66 219	98.50 121	95.13 361	99.63 75	85.84 391	98.35 135	98.21 313	98.23 140	99.54 56	99.46 66	95.02 246	99.68 263	98.24 107	99.87 78	99.87 16

HyFIR lowres test		97.19 253	96.60 278	98.96 140	99.62 77	97.28 201	95.17 353	99.50 86	94.21 332	99.01 147	98.32 279	86.61 339	99.99 2	97.10 173	99.84 86	99.60 75

ACMMP_NAP		98.75 96	98.48 126	99.57 16	99.58 78	99.29 19	97.82 197	99.25 187	96.94 248	98.78 189	99.12 133	98.02 90	99.84 139	97.13 171	99.67 173	99.59 81

nrg030		99.40 21	99.35 23	99.54 27	99.58 78	99.13 55	98.98 72	99.48 95	99.68 11	99.46 71	99.26 101	98.62 46	99.73 239	99.17 52	99.92 55	99.76 39

VDDNet		98.21 175	97.95 189	99.01 134	99.58 78	97.74 176	99.01 67	97.29 340	99.67 12	98.97 154	99.50 59	90.45 316	99.80 186	97.88 131	99.20 273	99.48 138

COLMAP_ROB	96.50 10	98.99 63	98.85 76	99.41 60	99.58 78	99.10 60	98.74 86	99.56 68	99.09 82	99.33 97	99.19 114	98.40 61	99.72 246	95.98 257	99.76 135	99.42 162
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 26	99.45 18	98.99 136	99.57 82	97.73 178	97.93 181	99.83 20	99.22 61	99.93 6	99.30 95	99.42 10	99.96 12	99.85 5	99.99 5	99.29 214

ZNCC-MVS		98.68 112	98.40 138	99.54 27	99.57 82	99.21 28	98.46 124	99.29 175	97.28 224	98.11 255	98.39 269	98.00 92	99.87 101	96.86 197	99.64 181	99.55 105

MSP-MVS		98.40 151	98.00 185	99.61 9	99.57 82	99.25 24	98.57 105	99.35 141	97.55 196	99.31 105	97.71 318	94.61 260	99.88 84	96.14 251	99.19 276	99.70 52
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
testgi		98.32 160	98.39 141	98.13 240	99.57 82	95.54 263	97.78 202	99.49 93	97.37 215	99.19 122	97.65 322	98.96 24	99.49 331	96.50 230	98.99 300	99.34 198

MP-MVS		98.46 145	98.09 176	99.54 27	99.57 82	99.22 27	98.50 118	99.19 202	97.61 189	97.58 290	98.66 235	97.40 140	99.88 84	94.72 295	99.60 194	99.54 109
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 100	98.46 130	99.47 54	99.57 82	98.97 66	98.23 143	99.48 95	96.60 263	99.10 132	99.06 141	98.71 39	99.83 156	95.58 277	99.78 120	99.62 68

LGP-MVS_train				99.47 54	99.57 82	98.97 66		99.48 95	96.60 263	99.10 132	99.06 141	98.71 39	99.83 156	95.58 277	99.78 120	99.62 68

IS-MVSNet		98.19 177	97.90 195	99.08 119	99.57 82	97.97 153	99.31 27	98.32 309	99.01 90	98.98 150	99.03 152	91.59 308	99.79 199	95.49 279	99.80 110	99.48 138

dcpmvs_2		98.78 91	99.11 52	97.78 263	99.56 90	93.67 327	99.06 63	99.86 13	99.50 30	99.66 42	99.26 101	97.21 152	99.99 2	98.00 123	99.91 63	99.68 55

test_0402		98.76 95	98.71 90	98.93 145	99.56 90	98.14 131	98.45 126	99.34 147	99.28 57	98.95 157	98.91 186	98.34 67	99.79 199	95.63 274	99.91 63	98.86 287

EPP-MVSNet		98.30 163	98.04 182	99.07 121	99.56 90	97.83 166	99.29 33	98.07 321	99.03 88	98.59 214	99.13 131	92.16 303	99.90 65	96.87 195	99.68 167	99.49 128

ACMMP		98.75 96	98.50 121	99.52 39	99.56 90	99.16 43	98.87 79	99.37 132	97.16 238	98.82 186	99.01 162	97.71 111	99.87 101	96.29 242	99.69 162	99.54 109
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
fmvsm_s_conf0.5_n_a		99.10 53	99.20 41	98.78 167	99.55 94	96.59 233	97.79 201	99.82 22	98.21 142	99.81 23	99.53 54	98.46 58	99.84 139	99.70 22	99.97 20	99.90 10

fmvsm_s_conf0.5_n		99.09 54	99.26 37	98.61 190	99.55 94	96.09 247	97.74 209	99.81 23	98.55 123	99.85 19	99.55 48	98.60 48	99.84 139	99.69 24	99.98 12	99.89 11

FMVSNet1		99.17 42	99.17 43	99.17 103	99.55 94	98.24 120	99.20 45	99.44 111	99.21 63	99.43 76	99.55 48	97.82 105	99.86 110	98.42 100	99.89 74	99.41 165

Vis-MVSNet (Re-imp)		97.46 231	97.16 242	98.34 224	99.55 94	96.10 244	98.94 74	98.44 304	98.32 132	98.16 249	98.62 244	88.76 326	99.73 239	93.88 321	99.79 115	99.18 238

ACMM	96.08 12	98.91 74	98.73 86	99.48 51	99.55 94	99.14 52	98.07 162	99.37 132	97.62 186	99.04 143	98.96 175	98.84 30	99.79 199	97.43 153	99.65 179	99.49 128
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 104	98.97 66	97.89 256	99.54 99	94.05 309	98.55 107	99.92 6	96.78 256	99.72 31	99.78 8	96.60 187	99.67 266	99.91 2	99.90 70	99.94 7

mPP-MVS		98.64 119	98.34 148	99.54 27	99.54 99	99.17 39	98.63 98	99.24 192	97.47 202	98.09 257	98.68 230	97.62 120	99.89 75	96.22 245	99.62 187	99.57 92

XVG-ACMP-BASELINE		98.56 129	98.34 148	99.22 99	99.54 99	98.59 94	97.71 212	99.46 104	97.25 227	98.98 150	98.99 166	97.54 127	99.84 139	95.88 260	99.74 139	99.23 226

region2R		98.69 107	98.40 138	99.54 27	99.53 102	99.17 39	98.52 111	99.31 159	97.46 207	98.44 231	98.51 256	97.83 102	99.88 84	96.46 232	99.58 203	99.58 87

PGM-MVS		98.66 116	98.37 144	99.55 23	99.53 102	99.18 38	98.23 143	99.49 93	97.01 245	98.69 199	98.88 196	98.00 92	99.89 75	95.87 263	99.59 198	99.58 87

Patchmatch-RL test		97.26 246	97.02 249	97.99 252	99.52 104	95.53 264	96.13 317	99.71 33	97.47 202	99.27 108	99.16 123	84.30 360	99.62 290	97.89 128	99.77 124	98.81 294

ACMMPR		98.70 104	98.42 136	99.54 27	99.52 104	99.14 52	98.52 111	99.31 159	97.47 202	98.56 219	98.54 252	97.75 109	99.88 84	96.57 219	99.59 198	99.58 87

GST-MVS		98.61 124	98.30 153	99.52 39	99.51 106	99.20 34	98.26 141	99.25 187	97.44 210	98.67 201	98.39 269	97.68 112	99.85 122	96.00 255	99.51 224	99.52 119

Anonymous20231206		98.21 175	98.21 162	98.20 235	99.51 106	95.43 269	98.13 153	99.32 154	96.16 280	98.93 165	98.82 208	96.00 212	99.83 156	97.32 158	99.73 142	99.36 192

ACMP	95.32 15	98.41 149	98.09 176	99.36 64	99.51 106	98.79 80	97.68 215	99.38 128	95.76 293	98.81 188	98.82 208	98.36 63	99.82 166	94.75 292	99.77 124	99.48 138
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 94	98.52 118	99.52 39	99.50 109	99.21 28	98.02 170	98.84 271	97.97 160	99.08 134	99.02 153	97.61 121	99.88 84	96.99 181	99.63 184	99.48 138
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.60 11	99.50 109	99.23 26	98.02 170	99.32 154					99.88 84	96.99 181	99.63 184	99.68 55

test0726					99.50 109	99.21 28	98.17 151	99.35 141	97.97 160	99.26 112	99.06 141	97.61 121

AllTest		98.44 147	98.20 163	99.16 106	99.50 109	98.55 97	98.25 142	99.58 54	96.80 254	98.88 174	99.06 141	97.65 115	99.57 307	94.45 302	99.61 192	99.37 186

TestCases				99.16 106	99.50 109	98.55 97		99.58 54	96.80 254	98.88 174	99.06 141	97.65 115	99.57 307	94.45 302	99.61 192	99.37 186

XVG-OURS		98.53 137	98.34 148	99.11 113	99.50 109	98.82 78	95.97 323	99.50 86	97.30 222	99.05 141	98.98 170	99.35 12	99.32 359	95.72 270	99.68 167	99.18 238

EG-PatchMatch MVS		98.99 63	99.01 61	98.94 143	99.50 109	97.47 190	98.04 167	99.59 52	98.15 153	99.40 83	99.36 83	98.58 51	99.76 222	98.78 73	99.68 167	99.59 81

SED-MVS		98.91 74	98.72 88	99.49 48	99.49 116	99.17 39	98.10 158	99.31 159	98.03 157	99.66 42	99.02 153	98.36 63	99.88 84	96.91 187	99.62 187	99.41 165

IU-MVS					99.49 116	99.15 47		98.87 262	92.97 350	99.41 80				96.76 204	99.62 187	99.66 59

test_241102_ONE					99.49 116	99.17 39		99.31 159	97.98 159	99.66 42	98.90 189	98.36 63	99.48 334

UA-Net		99.47 13	99.40 20	99.70 2	99.49 116	99.29 19	99.80 3	99.72 32	99.82 3	99.04 143	99.81 5	98.05 89	99.96 12	98.85 70	99.99 5	99.86 18

HFP-MVS		98.71 100	98.44 133	99.51 43	99.49 116	99.16 43	98.52 111	99.31 159	97.47 202	98.58 216	98.50 260	97.97 96	99.85 122	96.57 219	99.59 198	99.53 116

VPA-MVSNet		99.30 28	99.30 32	99.28 86	99.49 116	98.36 114	99.00 69	99.45 107	99.63 17	99.52 62	99.44 71	98.25 69	99.88 84	99.09 55	99.84 86	99.62 68

XVG-OURS-SEG-HR		98.49 142	98.28 155	99.14 109	99.49 116	98.83 76	96.54 294	99.48 95	97.32 220	99.11 129	98.61 246	99.33 13	99.30 362	96.23 244	98.38 331	99.28 216

114514_t		96.50 288	95.77 295	98.69 179	99.48 123	97.43 194	97.84 196	99.55 72	81.42 396	96.51 344	98.58 249	95.53 231	99.67 266	93.41 333	99.58 203	98.98 266

IterMVS-LS		98.55 133	98.70 93	98.09 241	99.48 123	94.73 290	97.22 261	99.39 126	98.97 93	99.38 87	99.31 94	96.00 212	99.93 41	98.58 88	99.97 20	99.60 75
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 61	99.16 45	98.57 196	99.47 125	96.31 241	98.90 77	99.47 102	99.03 88	99.52 62	99.57 42	96.93 166	99.81 179	99.60 25	99.98 12	99.60 75

XVS		98.72 99	98.45 131	99.53 34	99.46 126	99.21 28	98.65 96	99.34 147	98.62 115	97.54 294	98.63 242	97.50 133	99.83 156	96.79 200	99.53 219	99.56 98

X-MVStestdata		94.32 332	92.59 350	99.53 34	99.46 126	99.21 28	98.65 96	99.34 147	98.62 115	97.54 294	45.85 400	97.50 133	99.83 156	96.79 200	99.53 219	99.56 98

test20.03		98.78 91	98.77 83	98.78 167	99.46 126	97.20 208	97.78 202	99.24 192	99.04 87	99.41 80	98.90 189	97.65 115	99.76 222	97.70 142	99.79 115	99.39 177

CSCG		98.68 112	98.50 121	99.20 100	99.45 129	98.63 89	98.56 106	99.57 61	97.87 169	98.85 179	98.04 300	97.66 114	99.84 139	96.72 209	99.81 100	99.13 246

GeoE		99.05 59	98.99 65	99.25 94	99.44 130	98.35 115	98.73 89	99.56 68	98.42 126	98.91 167	98.81 210	98.94 25	99.91 60	98.35 102	99.73 142	99.49 128

v148		98.45 146	98.60 110	98.00 251	99.44 130	94.98 283	97.44 244	99.06 230	98.30 133	99.32 103	98.97 172	96.65 185	99.62 290	98.37 101	99.85 82	99.39 177

v10		98.97 67	99.11 52	98.55 201	99.44 130	96.21 243	98.90 77	99.55 72	98.73 107	99.48 68	99.60 39	96.63 186	99.83 156	99.70 22	99.99 5	99.61 74

V42		98.78 91	98.78 82	98.76 171	99.44 130	97.04 216	98.27 140	99.19 202	97.87 169	99.25 116	99.16 123	96.84 170	99.78 210	99.21 49	99.84 86	99.46 147

MDA-MVSNet-bldmvs		97.94 195	97.91 194	98.06 246	99.44 130	94.96 284	96.63 292	99.15 218	98.35 128	98.83 183	99.11 134	94.31 268	99.85 122	96.60 216	98.72 317	99.37 186

casdiffmvs_mvg		99.12 51	99.16 45	98.99 136	99.43 135	97.73 178	98.00 174	99.62 47	99.22 61	99.55 55	99.22 110	98.93 26	99.75 229	98.66 84	99.81 100	99.50 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		96.49 289	96.82 261	95.52 355	99.42 136	87.08 388	99.22 42	87.14 400	99.11 72	99.46 71	99.58 41	88.69 327	99.86 110	98.80 72	99.95 32	99.62 68

v2v482		98.56 129	98.62 105	98.37 222	99.42 136	95.81 257	97.58 230	99.16 213	97.90 167	99.28 106	99.01 162	95.98 217	99.79 199	99.33 39	99.90 70	99.51 121

OPM-MVS		98.56 129	98.32 152	99.25 94	99.41 138	98.73 85	97.13 267	99.18 206	97.10 241	98.75 195	98.92 185	98.18 78	99.65 282	96.68 213	99.56 210	99.37 186
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 187	98.08 179	98.04 249	99.41 138	94.59 296	94.59 371	99.40 123	97.50 199	98.82 186	98.83 205	96.83 172	99.84 139	97.50 151	99.81 100	99.71 47

test_one_0601					99.39 140	99.20 34		99.31 159	98.49 124	98.66 203	99.02 153	97.64 118

mvsany_test3		98.87 79	98.92 69	98.74 178	99.38 141	96.94 223	98.58 104	99.10 225	96.49 268	99.96 4	99.81 5	98.18 78	99.45 340	98.97 64	99.79 115	99.83 22

patch_mono-2		98.51 141	98.63 103	98.17 237	99.38 141	94.78 287	97.36 248	99.69 36	98.16 152	98.49 227	99.29 96	97.06 158	99.97 4	98.29 106	99.91 63	99.76 39

test2506		92.39 357	91.89 359	93.89 372	99.38 141	82.28 402	99.32 23	66.03 408	99.08 84	98.77 192	99.57 42	66.26 401	99.84 139	98.71 80	99.95 32	99.54 109

ECVR-MVS		96.42 291	96.61 276	95.85 347	99.38 141	88.18 384	99.22 42	86.00 402	99.08 84	99.36 92	99.57 42	88.47 332	99.82 166	98.52 94	99.95 32	99.54 109

casdiffmvs		98.95 70	99.00 62	98.81 159	99.38 141	97.33 198	97.82 197	99.57 61	99.17 70	99.35 94	99.17 121	98.35 66	99.69 254	98.46 97	99.73 142	99.41 165
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		98.96 69	99.02 60	98.76 171	99.38 141	97.26 203	98.49 119	99.50 86	98.86 102	99.19 122	99.06 141	98.23 71	99.69 254	98.71 80	99.76 135	99.33 203

TranMVSNet+NR-MVSNet		99.17 42	99.07 58	99.46 56	99.37 147	98.87 73	98.39 131	99.42 120	99.42 41	99.36 92	99.06 141	98.38 62	99.95 23	98.34 103	99.90 70	99.57 92

tttt0517		95.64 313	94.98 322	97.64 278	99.36 148	93.81 323	98.72 90	90.47 396	98.08 156	98.67 201	98.34 276	73.88 393	99.92 51	97.77 137	99.51 224	99.20 231

test_part2					99.36 148	99.10 60				99.05 141

v1144		98.60 125	98.66 99	98.41 218	99.36 148	95.90 253	97.58 230	99.34 147	97.51 198	99.27 108	99.15 127	96.34 200	99.80 186	99.47 34	99.93 44	99.51 121

CP-MVS		98.70 104	98.42 136	99.52 39	99.36 148	99.12 57	98.72 90	99.36 136	97.54 197	98.30 241	98.40 268	97.86 101	99.89 75	96.53 228	99.72 149	99.56 98

Test_1112_low_res		96.99 269	96.55 280	98.31 227	99.35 152	95.47 267	95.84 334	99.53 80	91.51 367	96.80 333	98.48 263	91.36 310	99.83 156	96.58 217	99.53 219	99.62 68

DeepC-MVS	97.60 4	98.97 67	98.93 68	99.10 115	99.35 152	97.98 152	98.01 173	99.46 104	97.56 194	99.54 56	99.50 59	98.97 23	99.84 139	98.06 118	99.92 55	99.49 128
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 245	96.86 257	98.58 194	99.34 154	96.32 240	96.75 286	99.58 54	93.14 348	96.89 328	97.48 332	92.11 304	99.86 110	96.91 187	99.54 215	99.57 92

SF-MVS		98.53 137	98.27 157	99.32 80	99.31 155	98.75 81	98.19 147	99.41 121	96.77 257	98.83 183	98.90 189	97.80 106	99.82 166	95.68 273	99.52 222	99.38 184

CPTT-MVS		97.84 208	97.36 232	99.27 89	99.31 155	98.46 105	98.29 138	99.27 181	94.90 316	97.83 274	98.37 272	94.90 248	99.84 139	93.85 323	99.54 215	99.51 121

UnsupCasMVSNet_eth		97.89 198	97.60 218	98.75 174	99.31 155	97.17 211	97.62 224	99.35 141	98.72 109	98.76 194	98.68 230	92.57 299	99.74 234	97.76 141	95.60 387	99.34 198

pmmvs-eth3d		98.47 144	98.34 148	98.86 153	99.30 158	97.76 174	97.16 265	99.28 178	95.54 299	99.42 79	99.19 114	97.27 147	99.63 288	97.89 128	99.97 20	99.20 231

Anonymous20231211		99.27 30	99.27 35	99.26 91	99.29 159	98.18 126	99.49 8	99.51 84	99.70 8	99.80 24	99.68 20	96.84 170	99.83 156	99.21 49	99.91 63	99.77 35

UnsupCasMVSNet_bld		97.30 243	96.92 253	98.45 213	99.28 160	96.78 230	96.20 313	99.27 181	95.42 303	98.28 243	98.30 280	93.16 286	99.71 247	94.99 287	97.37 364	98.87 286

EC-MVSNet		99.09 54	99.05 59	99.20 100	99.28 160	98.93 71	99.24 41	99.84 18	99.08 84	98.12 254	98.37 272	98.72 38	99.90 65	99.05 58	99.77 124	98.77 302

DPE-MVS		98.59 127	98.26 158	99.57 16	99.27 162	99.15 47	97.01 270	99.39 126	97.67 182	99.44 75	98.99 166	97.53 129	99.89 75	95.40 281	99.68 167	99.66 59
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 207	98.18 166	96.87 322	99.27 162	91.16 369	95.53 342	99.25 187	99.10 79	99.41 80	99.35 84	93.10 288	99.96 12	98.65 85	99.94 40	99.49 128

v1192		98.60 125	98.66 99	98.41 218	99.27 162	95.88 254	97.52 236	99.36 136	97.41 211	99.33 97	99.20 113	96.37 198	99.82 166	99.57 27	99.92 55	99.55 105

N_pmnet		97.63 221	97.17 241	98.99 136	99.27 162	97.86 163	95.98 322	93.41 385	95.25 308	99.47 70	98.90 189	95.63 228	99.85 122	96.91 187	99.73 142	99.27 217

FPMVS		93.44 348	92.23 352	97.08 311	99.25 166	97.86 163	95.61 339	97.16 342	92.90 352	93.76 389	98.65 237	75.94 390	95.66 399	79.30 399	97.49 358	97.73 364

new-patchmatchnet		98.35 157	98.74 84	97.18 306	99.24 167	92.23 354	96.42 302	99.48 95	98.30 133	99.69 37	99.53 54	97.44 138	99.82 166	98.84 71	99.77 124	99.49 128

MCST-MVS		98.00 191	97.63 216	99.10 115	99.24 167	98.17 128	96.89 279	98.73 289	95.66 294	97.92 266	97.70 320	97.17 153	99.66 277	96.18 249	99.23 269	99.47 145

UniMVSNet (Re)		98.87 79	98.71 90	99.35 70	99.24 167	98.73 85	97.73 211	99.38 128	98.93 97	99.12 128	98.73 221	96.77 177	99.86 110	98.63 87	99.80 110	99.46 147

jason		97.45 233	97.35 233	97.76 267	99.24 167	93.93 317	95.86 331	98.42 305	94.24 331	98.50 226	98.13 290	94.82 252	99.91 60	97.22 163	99.73 142	99.43 159
jason: jason.
IterMVS		97.73 213	98.11 175	96.57 331	99.24 167	90.28 375	95.52 344	99.21 196	98.86 102	99.33 97	99.33 90	93.11 287	99.94 36	98.49 96	99.94 40	99.48 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 133	98.62 105	98.32 225	99.22 172	95.58 262	97.51 238	99.45 107	97.16 238	99.45 74	99.24 106	96.12 206	99.85 122	99.60 25	99.88 75	99.55 105

ITE_SJBPF				98.87 152	99.22 172	98.48 104		99.35 141	97.50 199	98.28 243	98.60 247	97.64 118	99.35 355	93.86 322	99.27 262	98.79 300

h-mvs33		97.77 211	97.33 235	99.10 115	99.21 174	97.84 165	98.35 135	98.57 298	99.11 72	98.58 216	99.02 153	88.65 330	99.96 12	98.11 114	96.34 379	99.49 128

v144192		98.54 135	98.57 113	98.45 213	99.21 174	95.98 251	97.63 223	99.36 136	97.15 240	99.32 103	99.18 117	95.84 224	99.84 139	99.50 32	99.91 63	99.54 109

APDe-MVS		98.99 63	98.79 81	99.60 11	99.21 174	99.15 47	98.87 79	99.48 95	97.57 192	99.35 94	99.24 106	97.83 102	99.89 75	97.88 131	99.70 159	99.75 43
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 72	98.81 80	99.28 86	99.21 174	98.45 106	98.46 124	99.33 152	99.63 17	99.48 68	99.15 127	97.23 150	99.75 229	97.17 165	99.66 178	99.63 67

SR-MVS-dyc-post		98.81 87	98.55 114	99.57 16	99.20 178	99.38 8	98.48 122	99.30 167	98.64 111	98.95 157	98.96 175	97.49 136	99.86 110	96.56 223	99.39 243	99.45 151

RE-MVS-def			98.58 112		99.20 178	99.38 8	98.48 122	99.30 167	98.64 111	98.95 157	98.96 175	97.75 109		96.56 223	99.39 243	99.45 151

v1921920		98.54 135	98.60 110	98.38 221	99.20 178	95.76 259	97.56 232	99.36 136	97.23 233	99.38 87	99.17 121	96.02 210	99.84 139	99.57 27	99.90 70	99.54 109

thisisatest0530		95.27 320	94.45 329	97.74 270	99.19 181	94.37 301	97.86 194	90.20 397	97.17 237	98.22 245	97.65 322	73.53 394	99.90 65	96.90 192	99.35 249	98.95 272

Anonymous20240529		98.93 72	98.87 72	99.12 111	99.19 181	98.22 125	99.01 67	98.99 247	99.25 59	99.54 56	99.37 80	97.04 159	99.80 186	97.89 128	99.52 222	99.35 196

APD-MVS_3200maxsize		98.84 83	98.61 109	99.53 34	99.19 181	99.27 22	98.49 119	99.33 152	98.64 111	99.03 146	98.98 170	97.89 99	99.85 122	96.54 227	99.42 240	99.46 147

HQP_MVS		97.99 194	97.67 210	98.93 145	99.19 181	97.65 182	97.77 204	99.27 181	98.20 146	97.79 277	97.98 303	94.90 248	99.70 250	94.42 304	99.51 224	99.45 151

plane_prior7					99.19 181	97.87 162

ab-mvs		98.41 149	98.36 145	98.59 193	99.19 181	97.23 204	99.32 23	98.81 276	97.66 183	98.62 208	99.40 79	96.82 173	99.80 186	95.88 260	99.51 224	98.75 305

F-COLMAP		97.30 243	96.68 270	99.14 109	99.19 181	98.39 108	97.27 257	99.30 167	92.93 351	96.62 339	98.00 301	95.73 226	99.68 263	92.62 347	98.46 330	99.35 196

SR-MVS		98.71 100	98.43 134	99.57 16	99.18 188	99.35 12	98.36 134	99.29 175	98.29 136	98.88 174	98.85 202	97.53 129	99.87 101	96.14 251	99.31 255	99.48 138

UniMVSNet_NR-MVSNet		98.86 82	98.68 96	99.40 62	99.17 189	98.74 82	97.68 215	99.40 123	99.14 71	99.06 136	98.59 248	96.71 183	99.93 41	98.57 90	99.77 124	99.53 116

LF4IMVS		97.90 196	97.69 209	98.52 206	99.17 189	97.66 181	97.19 264	99.47 102	96.31 275	97.85 273	98.20 287	96.71 183	99.52 324	94.62 296	99.72 149	98.38 334

SMA-MVS		98.40 151	98.03 183	99.51 43	99.16 191	99.21 28	98.05 165	99.22 195	94.16 333	98.98 150	99.10 137	97.52 131	99.79 199	96.45 233	99.64 181	99.53 116
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
DU-MVS		98.82 85	98.63 103	99.39 63	99.16 191	98.74 82	97.54 234	99.25 187	98.84 105	99.06 136	98.76 218	96.76 179	99.93 41	98.57 90	99.77 124	99.50 124

NR-MVSNet		98.95 70	98.82 78	99.36 64	99.16 191	98.72 87	99.22 42	99.20 198	99.10 79	99.72 31	98.76 218	96.38 197	99.86 110	98.00 123	99.82 96	99.50 124

MVS_111021_LR		98.30 163	98.12 174	98.83 156	99.16 191	98.03 147	96.09 319	99.30 167	97.58 191	98.10 256	98.24 283	98.25 69	99.34 356	96.69 212	99.65 179	99.12 247

DSMNet-mixed		97.42 235	97.60 218	96.87 322	99.15 195	91.46 360	98.54 109	99.12 221	92.87 353	97.58 290	99.63 33	96.21 203	99.90 65	95.74 269	99.54 215	99.27 217

D2MVS		97.84 208	97.84 200	97.83 259	99.14 196	94.74 289	96.94 274	98.88 260	95.84 291	98.89 170	98.96 175	94.40 265	99.69 254	97.55 146	99.95 32	99.05 253

pmmvs5		97.64 220	97.49 224	98.08 244	99.14 196	95.12 280	96.70 289	99.05 233	93.77 340	98.62 208	98.83 205	93.23 284	99.75 229	98.33 105	99.76 135	99.36 192

CS-MVS-test		99.13 49	99.09 55	99.26 91	99.13 198	98.97 66	99.31 27	99.88 11	99.44 38	98.16 249	98.51 256	98.64 43	99.93 41	98.91 66	99.85 82	98.88 285

VDD-MVS		98.56 129	98.39 141	99.07 121	99.13 198	98.07 142	98.59 103	97.01 345	99.59 23	99.11 129	99.27 99	94.82 252	99.79 199	98.34 103	99.63 184	99.34 198

save fliter					99.11 200	97.97 153	96.53 296	99.02 241	98.24 139

APD-MVS		98.10 182	97.67 210	99.42 58	99.11 200	98.93 71	97.76 207	99.28 178	94.97 314	98.72 198	98.77 216	97.04 159	99.85 122	93.79 324	99.54 215	99.49 128
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 107	98.71 90	98.62 187	99.10 202	96.37 238	97.23 258	98.87 262	99.20 65	99.19 122	98.99 166	97.30 144	99.85 122	98.77 76	99.79 115	99.65 63

EI-MVSNet		98.40 151	98.51 119	98.04 249	99.10 202	94.73 290	97.20 262	98.87 262	98.97 93	99.06 136	99.02 153	96.00 212	99.80 186	98.58 88	99.82 96	99.60 75

CVMVSNet		96.25 296	97.21 240	93.38 378	99.10 202	80.56 405	97.20 262	98.19 316	96.94 248	99.00 148	99.02 153	89.50 323	99.80 186	96.36 238	99.59 198	99.78 33

EI-MVSNet-Vis-set		98.68 112	98.70 93	98.63 186	99.09 205	96.40 237	97.23 258	98.86 267	99.20 65	99.18 126	98.97 172	97.29 146	99.85 122	98.72 79	99.78 120	99.64 64

HPM-MVS++		98.10 182	97.64 215	99.48 51	99.09 205	99.13 55	97.52 236	98.75 286	97.46 207	96.90 327	97.83 313	96.01 211	99.84 139	95.82 267	99.35 249	99.46 147

DP-MVS Recon		97.33 241	96.92 253	98.57 196	99.09 205	97.99 149	96.79 282	99.35 141	93.18 347	97.71 281	98.07 298	95.00 247	99.31 360	93.97 317	99.13 284	98.42 332

MVS_111021_HR		98.25 171	98.08 179	98.75 174	99.09 205	97.46 191	95.97 323	99.27 181	97.60 190	97.99 264	98.25 282	98.15 84	99.38 351	96.87 195	99.57 207	99.42 162

9.14			97.78 202		99.07 209		97.53 235	99.32 154	95.53 300	98.54 223	98.70 227	97.58 123	99.76 222	94.32 309	99.46 234

PAPM_NR		96.82 276	96.32 286	98.30 228	99.07 209	96.69 232	97.48 240	98.76 283	95.81 292	96.61 340	96.47 357	94.12 274	99.17 373	90.82 372	97.78 354	99.06 252

TAMVS		98.24 172	98.05 181	98.80 161	99.07 209	97.18 210	97.88 189	98.81 276	96.66 262	99.17 127	99.21 111	94.81 254	99.77 216	96.96 185	99.88 75	99.44 155

CLD-MVS		97.49 229	97.16 242	98.48 210	99.07 209	97.03 217	94.71 364	99.21 196	94.46 325	98.06 259	97.16 344	97.57 124	99.48 334	94.46 301	99.78 120	98.95 272
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 49	99.10 54	99.24 96	99.06 213	99.15 47	99.36 19	99.88 11	99.36 48	98.21 246	98.46 264	98.68 42	99.93 41	99.03 60	99.85 82	98.64 317

thres100view900		94.19 335	93.67 339	95.75 350	99.06 213	91.35 363	98.03 168	94.24 380	98.33 130	97.40 305	94.98 383	79.84 376	99.62 290	83.05 392	98.08 347	96.29 385

thres600view7		94.45 330	93.83 336	96.29 337	99.06 213	91.53 359	97.99 176	94.24 380	98.34 129	97.44 303	95.01 381	79.84 376	99.67 266	84.33 390	98.23 336	97.66 367

plane_prior1					99.05 216

YYNet1		97.60 222	97.67 210	97.39 299	99.04 217	93.04 338	95.27 350	98.38 308	97.25 227	98.92 166	98.95 179	95.48 235	99.73 239	96.99 181	98.74 315	99.41 165

MDA-MVSNet_test_wron		97.60 222	97.66 213	97.41 298	99.04 217	93.09 334	95.27 350	98.42 305	97.26 226	98.88 174	98.95 179	95.43 236	99.73 239	97.02 178	98.72 317	99.41 165

MIMVSNet		96.62 283	96.25 290	97.71 273	99.04 217	94.66 293	99.16 51	96.92 351	97.23 233	97.87 270	99.10 137	86.11 345	99.65 282	91.65 356	99.21 272	98.82 290

PatchMatch-RL		97.24 249	96.78 264	98.61 190	99.03 220	97.83 166	96.36 305	99.06 230	93.49 345	97.36 308	97.78 314	95.75 225	99.49 331	93.44 332	98.77 314	98.52 323

ZD-MVS					99.01 221	98.84 75		99.07 229	94.10 335	98.05 261	98.12 292	96.36 199	99.86 110	92.70 346	99.19 276

CDPH-MVS		97.26 246	96.66 273	99.07 121	99.00 222	98.15 129	96.03 321	99.01 244	91.21 371	97.79 277	97.85 312	96.89 168	99.69 254	92.75 344	99.38 246	99.39 177

diffmvs		98.22 173	98.24 160	98.17 237	99.00 222	95.44 268	96.38 304	99.58 54	97.79 175	98.53 224	98.50 260	96.76 179	99.74 234	97.95 127	99.64 181	99.34 198
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 151	98.19 165	99.03 131	99.00 222	97.65 182	96.85 280	98.94 249	98.57 120	98.89 170	98.50 260	95.60 229	99.85 122	97.54 148	99.85 82	99.59 81

plane_prior6					98.99 225	97.70 180						94.90 248

xiu_mvs_v1_base_debu		97.86 202	98.17 167	96.92 319	98.98 226	93.91 318	96.45 299	99.17 210	97.85 171	98.41 234	97.14 346	98.47 55	99.92 51	98.02 120	99.05 290	96.92 378

xiu_mvs_v1_base		97.86 202	98.17 167	96.92 319	98.98 226	93.91 318	96.45 299	99.17 210	97.85 171	98.41 234	97.14 346	98.47 55	99.92 51	98.02 120	99.05 290	96.92 378

xiu_mvs_v1_base_debi		97.86 202	98.17 167	96.92 319	98.98 226	93.91 318	96.45 299	99.17 210	97.85 171	98.41 234	97.14 346	98.47 55	99.92 51	98.02 120	99.05 290	96.92 378

MVP-Stereo		98.08 186	97.92 193	98.57 196	98.96 229	96.79 227	97.90 186	99.18 206	96.41 271	98.46 229	98.95 179	95.93 220	99.60 297	96.51 229	98.98 302	99.31 209
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 151	98.68 96	97.54 287	98.96 229	97.99 149	97.88 189	99.36 136	98.20 146	99.63 48	99.04 150	98.76 35	95.33 401	96.56 223	99.74 139	99.31 209
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
新几何1				98.91 148	98.94 231	97.76 174		98.76 283	87.58 388	96.75 335	98.10 294	94.80 255	99.78 210	92.73 345	99.00 299	99.20 231

USDC		97.41 236	97.40 228	97.44 296	98.94 231	93.67 327	95.17 353	99.53 80	94.03 337	98.97 154	99.10 137	95.29 238	99.34 356	95.84 266	99.73 142	99.30 212

tfpn200view9		94.03 339	93.44 341	95.78 349	98.93 233	91.44 361	97.60 227	94.29 378	97.94 163	97.10 313	94.31 389	79.67 378	99.62 290	83.05 392	98.08 347	96.29 385

testdata				98.09 241	98.93 233	95.40 270		98.80 278	90.08 379	97.45 302	98.37 272	95.26 239	99.70 250	93.58 328	98.95 305	99.17 242

thres400		94.14 337	93.44 341	96.24 339	98.93 233	91.44 361	97.60 227	94.29 378	97.94 163	97.10 313	94.31 389	79.67 378	99.62 290	83.05 392	98.08 347	97.66 367

TAPA-MVS	96.21 11	96.63 282	95.95 293	98.65 181	98.93 233	98.09 136	96.93 276	99.28 178	83.58 394	98.13 253	97.78 314	96.13 205	99.40 347	93.52 329	99.29 260	98.45 327
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 237	96.93 224	95.54 341	98.78 281	85.72 391	96.86 330	98.11 293	94.43 263			99.10 289	99.23 226

PVSNet_BlendedMVS		97.55 226	97.53 221	97.60 280	98.92 237	93.77 325	96.64 291	99.43 117	94.49 323	97.62 286	99.18 117	96.82 173	99.67 266	94.73 293	99.93 44	99.36 192

PVSNet_Blended		96.88 272	96.68 270	97.47 294	98.92 237	93.77 325	94.71 364	99.43 117	90.98 373	97.62 286	97.36 340	96.82 173	99.67 266	94.73 293	99.56 210	98.98 266

MSDG		97.71 215	97.52 222	98.28 230	98.91 240	96.82 226	94.42 374	99.37 132	97.65 184	98.37 239	98.29 281	97.40 140	99.33 358	94.09 315	99.22 270	98.68 315

Anonymous202405211		97.90 196	97.50 223	99.08 119	98.90 241	98.25 119	98.53 110	96.16 361	98.87 101	99.11 129	98.86 199	90.40 317	99.78 210	97.36 156	99.31 255	99.19 236

原ACMM1				98.35 223	98.90 241	96.25 242		98.83 275	92.48 357	96.07 354	98.10 294	95.39 237	99.71 247	92.61 348	98.99 300	99.08 249

GBi-Net		98.65 117	98.47 128	99.17 103	98.90 241	98.24 120	99.20 45	99.44 111	98.59 117	98.95 157	99.55 48	94.14 271	99.86 110	97.77 137	99.69 162	99.41 165

test1		98.65 117	98.47 128	99.17 103	98.90 241	98.24 120	99.20 45	99.44 111	98.59 117	98.95 157	99.55 48	94.14 271	99.86 110	97.77 137	99.69 162	99.41 165

FMVSNet2		98.49 142	98.40 138	98.75 174	98.90 241	97.14 214	98.61 101	99.13 220	98.59 117	99.19 122	99.28 97	94.14 271	99.82 166	97.97 125	99.80 110	99.29 214

OMC-MVS		97.88 200	97.49 224	99.04 130	98.89 246	98.63 89	96.94 274	99.25 187	95.02 312	98.53 224	98.51 256	97.27 147	99.47 337	93.50 331	99.51 224	99.01 261

MVSFormer		98.26 169	98.43 134	97.77 264	98.88 247	93.89 321	99.39 17	99.56 68	99.11 72	98.16 249	98.13 290	93.81 279	99.97 4	99.26 44	99.57 207	99.43 159

lupinMVS		97.06 262	96.86 257	97.65 276	98.88 247	93.89 321	95.48 345	97.97 323	93.53 343	98.16 249	97.58 326	93.81 279	99.91 60	96.77 203	99.57 207	99.17 242

dmvs_re		95.98 303	95.39 312	97.74 270	98.86 249	97.45 192	98.37 133	95.69 369	97.95 162	96.56 341	95.95 365	90.70 314	97.68 395	88.32 380	96.13 383	98.11 344

DELS-MVS		98.27 167	98.20 163	98.48 210	98.86 249	96.70 231	95.60 340	99.20 198	97.73 178	98.45 230	98.71 224	97.50 133	99.82 166	98.21 109	99.59 198	98.93 277
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
TinyColmap		97.89 198	97.98 187	97.60 280	98.86 249	94.35 302	96.21 312	99.44 111	97.45 209	99.06 136	98.88 196	97.99 95	99.28 366	94.38 308	99.58 203	99.18 238

LCM-MVSNet-Re		98.64 119	98.48 126	99.11 113	98.85 252	98.51 102	98.49 119	99.83 20	98.37 127	99.69 37	99.46 66	98.21 76	99.92 51	94.13 314	99.30 258	98.91 281

pmmvs4		97.58 225	97.28 236	98.51 207	98.84 253	96.93 224	95.40 348	98.52 301	93.60 342	98.61 210	98.65 237	95.10 244	99.60 297	96.97 184	99.79 115	98.99 265

NP-MVS					98.84 253	97.39 196					96.84 349

sss		97.21 251	96.93 251	98.06 246	98.83 255	95.22 276	96.75 286	98.48 303	94.49 323	97.27 309	97.90 309	92.77 296	99.80 186	96.57 219	99.32 253	99.16 245

PVSNet	93.40 17	95.67 311	95.70 298	95.57 354	98.83 255	88.57 380	92.50 391	97.72 328	92.69 355	96.49 347	96.44 358	93.72 282	99.43 343	93.61 326	99.28 261	98.71 308

MVE	83.40 22	92.50 356	91.92 358	94.25 368	98.83 255	91.64 358	92.71 390	83.52 404	95.92 289	86.46 401	95.46 376	95.20 241	95.40 400	80.51 397	98.64 324	95.73 393
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MVS_0304		98.10 182	97.88 197	98.76 171	98.82 258	96.50 235	97.90 186	91.35 394	99.56 26	98.32 240	99.13 131	96.06 208	99.93 41	99.84 7	99.97 20	99.85 19

ambc				98.24 233	98.82 258	95.97 252	98.62 100	99.00 246		99.27 108	99.21 111	96.99 164	99.50 329	96.55 226	99.50 231	99.26 220

旧先验1					98.82 258	97.45 192		98.76 283			98.34 276	95.50 234			99.01 298	99.23 226

test_vis1_rt		97.75 212	97.72 208	97.83 259	98.81 261	96.35 239	97.30 253	99.69 36	94.61 321	97.87 270	98.05 299	96.26 202	98.32 392	98.74 77	98.18 339	98.82 290

WTY-MVS		96.67 280	96.27 289	97.87 257	98.81 261	94.61 295	96.77 284	97.92 325	94.94 315	97.12 312	97.74 317	91.11 312	99.82 166	93.89 320	98.15 343	99.18 238

3Dnovator+	97.89 3	98.69 107	98.51 119	99.24 96	98.81 261	98.40 107	99.02 66	99.19 202	98.99 91	98.07 258	99.28 97	97.11 157	99.84 139	96.84 198	99.32 253	99.47 145

QAPM		97.31 242	96.81 263	98.82 157	98.80 264	97.49 189	99.06 63	99.19 202	90.22 377	97.69 283	99.16 123	96.91 167	99.90 65	90.89 371	99.41 241	99.07 251

VNet		98.42 148	98.30 153	98.79 164	98.79 265	97.29 200	98.23 143	98.66 292	99.31 53	98.85 179	98.80 211	94.80 255	99.78 210	98.13 113	99.13 284	99.31 209

DPM-MVS		96.32 293	95.59 303	98.51 207	98.76 266	97.21 207	94.54 373	98.26 311	91.94 362	96.37 348	97.25 342	93.06 290	99.43 343	91.42 361	98.74 315	98.89 282

3Dnovator	98.27 2	98.81 87	98.73 86	99.05 128	98.76 266	97.81 171	99.25 40	99.30 167	98.57 120	98.55 221	99.33 90	97.95 97	99.90 65	97.16 166	99.67 173	99.44 155

PLC	94.65 16	96.51 286	95.73 297	98.85 154	98.75 268	97.91 159	96.42 302	99.06 230	90.94 374	95.59 360	97.38 338	94.41 264	99.59 301	90.93 369	98.04 352	99.05 253
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 274	96.75 266	97.08 311	98.74 269	93.33 332	96.71 288	98.26 311	96.72 259	98.44 231	97.37 339	95.20 241	99.47 337	91.89 353	97.43 361	98.44 329

hse-mvs2		97.46 231	97.07 246	98.64 182	98.73 270	97.33 198	97.45 243	97.64 333	99.11 72	98.58 216	97.98 303	88.65 330	99.79 199	98.11 114	97.39 363	98.81 294

CDS-MVSNet		97.69 216	97.35 233	98.69 179	98.73 270	97.02 218	96.92 278	98.75 286	95.89 290	98.59 214	98.67 232	92.08 305	99.74 234	96.72 209	99.81 100	99.32 205
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 191	97.74 205	98.80 161	98.72 272	98.09 136	98.05 165	99.60 51	97.39 213	96.63 338	95.55 372	97.68 112	99.80 186	96.73 208	99.27 262	98.52 323

LFMVS		97.20 252	96.72 267	98.64 182	98.72 272	96.95 222	98.93 75	94.14 382	99.74 6	98.78 189	99.01 162	84.45 357	99.73 239	97.44 152	99.27 262	99.25 221

new_pmnet		96.99 269	96.76 265	97.67 274	98.72 272	94.89 285	95.95 327	98.20 314	92.62 356	98.55 221	98.54 252	94.88 251	99.52 324	93.96 318	99.44 239	98.59 322

Fast-Effi-MVS+		97.67 218	97.38 230	98.57 196	98.71 275	97.43 194	97.23 258	99.45 107	94.82 318	96.13 351	96.51 354	98.52 54	99.91 60	96.19 247	98.83 311	98.37 336

TEST9					98.71 275	98.08 140	95.96 325	99.03 238	91.40 368	95.85 357	97.53 328	96.52 190	99.76 222

train_agg		97.10 258	96.45 283	99.07 121	98.71 275	98.08 140	95.96 325	99.03 238	91.64 363	95.85 357	97.53 328	96.47 192	99.76 222	93.67 325	99.16 279	99.36 192

TSAR-MVS + GP.		98.18 178	97.98 187	98.77 170	98.71 275	97.88 161	96.32 307	98.66 292	96.33 273	99.23 119	98.51 256	97.48 137	99.40 347	97.16 166	99.46 234	99.02 260

FA-MVS(test-final)		96.99 269	96.82 261	97.50 291	98.70 279	94.78 287	99.34 20	96.99 346	95.07 311	98.48 228	99.33 90	88.41 333	99.65 282	96.13 253	98.92 308	98.07 347

AUN-MVS		96.24 297	95.45 308	98.60 192	98.70 279	97.22 206	97.38 246	97.65 331	95.95 288	95.53 367	97.96 307	82.11 372	99.79 199	96.31 240	97.44 360	98.80 299

our_test_3		97.39 237	97.73 207	96.34 335	98.70 279	89.78 377	94.61 370	98.97 248	96.50 267	99.04 143	98.85 202	95.98 217	99.84 139	97.26 161	99.67 173	99.41 165

ppachtmachnet_test		97.50 227	97.74 205	96.78 328	98.70 279	91.23 368	94.55 372	99.05 233	96.36 272	99.21 120	98.79 213	96.39 195	99.78 210	96.74 206	99.82 96	99.34 198

PCF-MVS	92.86 18	94.36 331	93.00 348	98.42 217	98.70 279	97.56 186	93.16 389	99.11 223	79.59 397	97.55 293	97.43 335	92.19 302	99.73 239	79.85 398	99.45 236	97.97 353
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		98.03 188	97.86 199	98.56 200	98.69 284	98.07 142	97.51 238	99.50 86	98.10 154	97.50 298	95.51 373	98.41 60	99.88 84	96.27 243	99.24 267	97.71 366

test_prior				98.95 142	98.69 284	97.95 157		99.03 238					99.59 301			99.30 212

agg_prior					98.68 286	97.99 149		99.01 244		95.59 360			99.77 216

test_8					98.67 287	98.01 148	95.91 330	99.02 241	91.64 363	95.79 359	97.50 331	96.47 192	99.76 222

HQP-NCC					98.67 287		96.29 308		96.05 283	95.55 363

ACMP_Plane					98.67 287		96.29 308		96.05 283	95.55 363

CNVR-MVS		98.17 180	97.87 198	99.07 121	98.67 287	98.24 120	97.01 270	98.93 251	97.25 227	97.62 286	98.34 276	97.27 147	99.57 307	96.42 234	99.33 252	99.39 177

HQP-MVS		97.00 268	96.49 282	98.55 201	98.67 287	96.79 227	96.29 308	99.04 236	96.05 283	95.55 363	96.84 349	93.84 277	99.54 318	92.82 341	99.26 265	99.32 205

MM		98.22 173	97.99 186	98.91 148	98.66 292	96.97 219	97.89 188	94.44 376	99.54 27	98.95 157	99.14 130	93.50 283	99.92 51	99.80 12	99.96 25	99.85 19

test_fmvs1		97.72 214	97.94 191	97.07 313	98.66 292	92.39 349	97.68 215	99.81 23	95.20 310	99.54 56	99.44 71	91.56 309	99.41 346	99.78 15	99.77 124	99.40 174

thres200		93.72 344	93.14 346	95.46 358	98.66 292	91.29 365	96.61 293	94.63 375	97.39 213	96.83 331	93.71 391	79.88 375	99.56 310	82.40 395	98.13 344	95.54 394

wuyk23d		96.06 299	97.62 217	91.38 381	98.65 295	98.57 96	98.85 82	96.95 349	96.86 252	99.90 12	99.16 123	99.18 17	98.40 391	89.23 378	99.77 124	77.18 399

NCCC		97.86 202	97.47 227	99.05 128	98.61 296	98.07 142	96.98 272	98.90 257	97.63 185	97.04 317	97.93 308	95.99 216	99.66 277	95.31 282	98.82 313	99.43 159

DeepC-MVS_fast	96.85 6	98.30 163	98.15 171	98.75 174	98.61 296	97.23 204	97.76 207	99.09 227	97.31 221	98.75 195	98.66 235	97.56 125	99.64 285	96.10 254	99.55 213	99.39 177
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 346	92.09 354	97.75 268	98.60 298	94.40 300	97.32 251	95.26 371	97.56 194	96.79 334	95.50 374	53.57 407	99.77 216	95.26 283	98.97 303	99.08 249

thisisatest0515		94.12 338	93.16 345	96.97 317	98.60 298	92.90 339	93.77 385	90.61 395	94.10 335	96.91 324	95.87 368	74.99 392	99.80 186	94.52 299	99.12 287	98.20 340

GA-MVS		95.86 306	95.32 315	97.49 292	98.60 298	94.15 308	93.83 384	97.93 324	95.49 301	96.68 336	97.42 336	83.21 365	99.30 362	96.22 245	98.55 329	99.01 261

dmvs_testset		92.94 352	92.21 353	95.13 361	98.59 301	90.99 370	97.65 221	92.09 391	96.95 247	94.00 386	93.55 392	92.34 301	96.97 398	72.20 401	92.52 396	97.43 374

OPU-MVS				98.82 157	98.59 301	98.30 116	98.10 158				98.52 255	98.18 78	98.75 388	94.62 296	99.48 233	99.41 165

MSLP-MVS++		98.02 189	98.14 173	97.64 278	98.58 303	95.19 277	97.48 240	99.23 194	97.47 202	97.90 268	98.62 244	97.04 159	98.81 387	97.55 146	99.41 241	98.94 276

test12				98.93 145	98.58 303	97.83 166		98.66 292		96.53 342		95.51 233	99.69 254		99.13 284	99.27 217

CL-MVSNet_self_test		97.44 234	97.22 239	98.08 244	98.57 305	95.78 258	94.30 377	98.79 279	96.58 265	98.60 212	98.19 288	94.74 259	99.64 285	96.41 235	98.84 310	98.82 290

PS-MVSNAJ		97.08 261	97.39 229	96.16 344	98.56 306	92.46 347	95.24 352	98.85 270	97.25 227	97.49 299	95.99 364	98.07 86	99.90 65	96.37 236	98.67 323	96.12 390

CNLPA		97.17 255	96.71 268	98.55 201	98.56 306	98.05 146	96.33 306	98.93 251	96.91 250	97.06 316	97.39 337	94.38 266	99.45 340	91.66 355	99.18 278	98.14 343

xiu_mvs_v2_base		97.16 256	97.49 224	96.17 342	98.54 308	92.46 347	95.45 346	98.84 271	97.25 227	97.48 300	96.49 355	98.31 68	99.90 65	96.34 239	98.68 322	96.15 389

alignmvs		97.35 239	96.88 256	98.78 167	98.54 308	98.09 136	97.71 212	97.69 330	99.20 65	97.59 289	95.90 367	88.12 335	99.55 313	98.18 111	98.96 304	98.70 311

FE-MVS		95.66 312	94.95 324	97.77 264	98.53 310	95.28 273	99.40 16	96.09 363	93.11 349	97.96 265	99.26 101	79.10 383	99.77 216	92.40 350	98.71 319	98.27 338

iter_conf_final		97.10 258	96.65 275	98.45 213	98.53 310	96.08 249	98.30 137	99.11 223	98.10 154	98.85 179	98.95 179	79.38 381	99.87 101	98.68 83	99.91 63	99.40 174

Effi-MVS+		98.02 189	97.82 201	98.62 187	98.53 310	97.19 209	97.33 250	99.68 41	97.30 222	96.68 336	97.46 334	98.56 52	99.80 186	96.63 215	98.20 338	98.86 287

baseline1		95.96 304	95.44 309	97.52 289	98.51 313	93.99 315	98.39 131	96.09 363	98.21 142	98.40 238	97.76 316	86.88 337	99.63 288	95.42 280	89.27 399	98.95 272

MVS_Test		98.18 178	98.36 145	97.67 274	98.48 314	94.73 290	98.18 148	99.02 241	97.69 181	98.04 262	99.11 134	97.22 151	99.56 310	98.57 90	98.90 309	98.71 308

BH-RMVSNet		96.83 274	96.58 279	97.58 282	98.47 315	94.05 309	96.67 290	97.36 336	96.70 261	97.87 270	97.98 303	95.14 243	99.44 342	90.47 373	98.58 328	99.25 221

canonicalmvs		98.34 158	98.26 158	98.58 194	98.46 316	97.82 169	98.96 73	99.46 104	99.19 69	97.46 301	95.46 376	98.59 49	99.46 339	98.08 117	98.71 319	98.46 325

MVS-HIRNet		94.32 332	95.62 301	90.42 382	98.46 316	75.36 406	96.29 308	89.13 399	95.25 308	95.38 369	99.75 11	92.88 293	99.19 372	94.07 316	99.39 243	96.72 383

PHI-MVS		98.29 166	97.95 189	99.34 73	98.44 318	99.16 43	98.12 155	99.38 128	96.01 286	98.06 259	98.43 266	97.80 106	99.67 266	95.69 272	99.58 203	99.20 231

DVP-MVS++		98.90 76	98.70 93	99.51 43	98.43 319	99.15 47	99.43 11	99.32 154	98.17 149	99.26 112	99.02 153	98.18 78	99.88 84	97.07 175	99.45 236	99.49 128

MSC_two_6792asdad				99.32 80	98.43 319	98.37 111		98.86 267					99.89 75	97.14 169	99.60 194	99.71 47

No_MVS				99.32 80	98.43 319	98.37 111		98.86 267					99.89 75	97.14 169	99.60 194	99.71 47

Fast-Effi-MVS+-dtu		98.27 167	98.09 176	98.81 159	98.43 319	98.11 133	97.61 226	99.50 86	98.64 111	97.39 306	97.52 330	98.12 85	99.95 23	96.90 192	98.71 319	98.38 334

OpenMVS_ROB	95.38 14	95.84 307	95.18 319	97.81 261	98.41 323	97.15 213	97.37 247	98.62 296	83.86 393	98.65 204	98.37 272	94.29 269	99.68 263	88.41 379	98.62 326	96.60 384

DeepPCF-MVS	96.93 5	98.32 160	98.01 184	99.23 98	98.39 324	98.97 66	95.03 357	99.18 206	96.88 251	99.33 97	98.78 214	98.16 82	99.28 366	96.74 206	99.62 187	99.44 155

Patchmatch-test		96.55 284	96.34 285	97.17 308	98.35 325	93.06 335	98.40 130	97.79 326	97.33 218	98.41 234	98.67 232	83.68 364	99.69 254	95.16 285	99.31 255	98.77 302

AdaColmap		97.14 257	96.71 268	98.46 212	98.34 326	97.80 172	96.95 273	98.93 251	95.58 298	96.92 322	97.66 321	95.87 222	99.53 320	90.97 368	99.14 282	98.04 348

OpenMVS	96.65 7	97.09 260	96.68 270	98.32 225	98.32 327	97.16 212	98.86 81	99.37 132	89.48 381	96.29 350	99.15 127	96.56 188	99.90 65	92.90 338	99.20 273	97.89 354

MG-MVS		96.77 277	96.61 276	97.26 304	98.31 328	93.06 335	95.93 328	98.12 320	96.45 270	97.92 266	98.73 221	93.77 281	99.39 349	91.19 366	99.04 293	99.33 203

test_yl		96.69 278	96.29 287	97.90 254	98.28 329	95.24 274	97.29 254	97.36 336	98.21 142	98.17 247	97.86 310	86.27 341	99.55 313	94.87 290	98.32 332	98.89 282

DCV-MVSNet		96.69 278	96.29 287	97.90 254	98.28 329	95.24 274	97.29 254	97.36 336	98.21 142	98.17 247	97.86 310	86.27 341	99.55 313	94.87 290	98.32 332	98.89 282

CHOSEN 280x420		95.51 317	95.47 306	95.65 353	98.25 331	88.27 383	93.25 388	98.88 260	93.53 343	94.65 378	97.15 345	86.17 343	99.93 41	97.41 154	99.93 44	98.73 307

SCA		96.41 292	96.66 273	95.67 351	98.24 332	88.35 382	95.85 333	96.88 352	96.11 281	97.67 284	98.67 232	93.10 288	99.85 122	94.16 310	99.22 270	98.81 294

DeepMVS_CX				93.44 377	98.24 332	94.21 305		94.34 377	64.28 399	91.34 395	94.87 387	89.45 324	92.77 402	77.54 400	93.14 395	93.35 397

MS-PatchMatch		97.68 217	97.75 204	97.45 295	98.23 334	93.78 324	97.29 254	98.84 271	96.10 282	98.64 205	98.65 237	96.04 209	99.36 352	96.84 198	99.14 282	99.20 231

BH-w/o		95.13 322	94.89 326	95.86 346	98.20 335	91.31 364	95.65 338	97.37 335	93.64 341	96.52 343	95.70 370	93.04 291	99.02 378	88.10 381	95.82 386	97.24 376

mvs_anonymous		97.83 210	98.16 170	96.87 322	98.18 336	91.89 356	97.31 252	98.90 257	97.37 215	98.83 183	99.46 66	96.28 201	99.79 199	98.90 67	98.16 342	98.95 272

miper_lstm_enhance		97.18 254	97.16 242	97.25 305	98.16 337	92.85 340	95.15 355	99.31 159	97.25 227	98.74 197	98.78 214	90.07 318	99.78 210	97.19 164	99.80 110	99.11 248

ET-MVSNet_ETH3D		94.30 334	93.21 344	97.58 282	98.14 338	94.47 299	94.78 363	93.24 387	94.72 319	89.56 397	95.87 368	78.57 386	99.81 179	96.91 187	97.11 371	98.46 325

ADS-MVSNet2		95.43 318	94.98 322	96.76 329	98.14 338	91.74 357	97.92 183	97.76 327	90.23 375	96.51 344	98.91 186	85.61 348	99.85 122	92.88 339	96.90 372	98.69 312

ADS-MVSNet		95.24 321	94.93 325	96.18 341	98.14 338	90.10 376	97.92 183	97.32 339	90.23 375	96.51 344	98.91 186	85.61 348	99.74 234	92.88 339	96.90 372	98.69 312

c3_l		97.36 238	97.37 231	97.31 300	98.09 341	93.25 333	95.01 358	99.16 213	97.05 242	98.77 192	98.72 223	92.88 293	99.64 285	96.93 186	99.76 135	99.05 253

FMVSNet3		97.50 227	97.24 238	98.29 229	98.08 342	95.83 256	97.86 194	98.91 256	97.89 168	98.95 157	98.95 179	87.06 336	99.81 179	97.77 137	99.69 162	99.23 226

PAPM		91.88 364	90.34 367	96.51 332	98.06 343	92.56 345	92.44 392	97.17 341	86.35 389	90.38 396	96.01 363	86.61 339	99.21 371	70.65 402	95.43 388	97.75 363

Effi-MVS+-dtu		98.26 169	97.90 195	99.35 70	98.02 344	99.49 5	98.02 170	99.16 213	98.29 136	97.64 285	97.99 302	96.44 194	99.95 23	96.66 214	98.93 307	98.60 320

eth_miper_zixun_eth		97.23 250	97.25 237	97.17 308	98.00 345	92.77 342	94.71 364	99.18 206	97.27 225	98.56 219	98.74 220	91.89 306	99.69 254	97.06 177	99.81 100	99.05 253

HY-MVS	95.94 13	95.90 305	95.35 314	97.55 286	97.95 346	94.79 286	98.81 85	96.94 350	92.28 360	95.17 371	98.57 250	89.90 320	99.75 229	91.20 365	97.33 368	98.10 345

UGNet		98.53 137	98.45 131	98.79 164	97.94 347	96.96 221	99.08 59	98.54 299	99.10 79	96.82 332	99.47 65	96.55 189	99.84 139	98.56 93	99.94 40	99.55 105
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
MAR-MVS		96.47 290	95.70 298	98.79 164	97.92 348	99.12 57	98.28 139	98.60 297	92.16 361	95.54 366	96.17 362	94.77 258	99.52 324	89.62 376	98.23 336	97.72 365
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
MVSTER		96.86 273	96.55 280	97.79 262	97.91 349	94.21 305	97.56 232	98.87 262	97.49 201	99.06 136	99.05 148	80.72 373	99.80 186	98.44 98	99.82 96	99.37 186

iter_conf05		96.54 285	96.07 291	97.92 253	97.90 350	94.50 297	97.87 192	99.14 219	97.73 178	98.89 170	98.95 179	75.75 391	99.87 101	98.50 95	99.92 55	99.40 174

API-MVS		97.04 264	96.91 255	97.42 297	97.88 351	98.23 124	98.18 148	98.50 302	97.57 192	97.39 306	96.75 351	96.77 177	99.15 375	90.16 374	99.02 297	94.88 395

miper_ehance_all_eth		97.06 262	97.03 248	97.16 310	97.83 352	93.06 335	94.66 367	99.09 227	95.99 287	98.69 199	98.45 265	92.73 297	99.61 296	96.79 200	99.03 294	98.82 290

cl____		97.02 265	96.83 260	97.58 282	97.82 353	94.04 311	94.66 367	99.16 213	97.04 243	98.63 206	98.71 224	88.68 329	99.69 254	97.00 179	99.81 100	99.00 264

DIV-MVS_self_test		97.02 265	96.84 259	97.58 282	97.82 353	94.03 312	94.66 367	99.16 213	97.04 243	98.63 206	98.71 224	88.69 327	99.69 254	97.00 179	99.81 100	99.01 261

CANet		97.87 201	97.76 203	98.19 236	97.75 355	95.51 265	96.76 285	99.05 233	97.74 177	96.93 321	98.21 286	95.59 230	99.89 75	97.86 133	99.93 44	99.19 236

mvsany_test1		97.60 222	97.54 220	97.77 264	97.72 356	95.35 271	95.36 349	97.13 343	94.13 334	99.71 33	99.33 90	97.93 98	99.30 362	97.60 145	98.94 306	98.67 316

PVSNet_0	89.98 21	91.15 365	90.30 368	93.70 374	97.72 356	84.34 399	90.24 394	97.42 334	90.20 378	93.79 388	93.09 393	90.90 313	98.89 386	86.57 387	72.76 401	97.87 356

CR-MVSNet		96.28 295	95.95 293	97.28 302	97.71 358	94.22 303	98.11 156	98.92 254	92.31 359	96.91 324	99.37 80	85.44 351	99.81 179	97.39 155	97.36 366	97.81 359

RPMNet		97.02 265	96.93 251	97.30 301	97.71 358	94.22 303	98.11 156	99.30 167	99.37 45	96.91 324	99.34 88	86.72 338	99.87 101	97.53 149	97.36 366	97.81 359

ETVMVS		92.60 355	91.08 363	97.18 306	97.70 360	93.65 329	96.54 294	95.70 368	96.51 266	94.68 377	92.39 396	61.80 404	99.50 329	86.97 384	97.41 362	98.40 333

pmmvs3		95.03 324	94.40 330	96.93 318	97.70 360	92.53 346	95.08 356	97.71 329	88.57 385	97.71 281	98.08 297	79.39 380	99.82 166	96.19 247	99.11 288	98.43 330

baseline2		93.73 343	92.83 349	96.42 334	97.70 360	91.28 366	96.84 281	89.77 398	93.96 339	92.44 392	95.93 366	79.14 382	99.77 216	92.94 337	96.76 376	98.21 339

tpm		94.67 328	94.34 332	95.66 352	97.68 363	88.42 381	97.88 189	94.90 372	94.46 325	96.03 356	98.56 251	78.66 384	99.79 199	95.88 260	95.01 390	98.78 301

CANet_DTU		97.26 246	97.06 247	97.84 258	97.57 364	94.65 294	96.19 314	98.79 279	97.23 233	95.14 372	98.24 283	93.22 285	99.84 139	97.34 157	99.84 86	99.04 257

tpm2		93.09 351	92.58 351	94.62 365	97.56 365	86.53 389	97.66 219	95.79 367	86.15 390	94.07 385	98.23 285	75.95 389	99.53 320	90.91 370	96.86 375	97.81 359

TR-MVS		95.55 315	95.12 320	96.86 325	97.54 366	93.94 316	96.49 298	96.53 358	94.36 330	97.03 319	96.61 353	94.26 270	99.16 374	86.91 386	96.31 380	97.47 373

1314		95.74 309	95.60 302	96.17 342	97.53 367	92.75 343	98.07 162	98.31 310	91.22 370	94.25 381	96.68 352	95.53 231	99.03 377	91.64 357	97.18 369	96.74 382

CostFormer		93.97 340	93.78 337	94.51 366	97.53 367	85.83 392	97.98 177	95.96 365	89.29 383	94.99 374	98.63 242	78.63 385	99.62 290	94.54 298	96.50 377	98.09 346

FMVSNet5		96.01 301	95.20 318	98.41 218	97.53 367	96.10 244	98.74 86	99.50 86	97.22 236	98.03 263	99.04 150	69.80 395	99.88 84	97.27 160	99.71 154	99.25 221

PMMVS		96.51 286	95.98 292	98.09 241	97.53 367	95.84 255	94.92 360	98.84 271	91.58 365	96.05 355	95.58 371	95.68 227	99.66 277	95.59 276	98.09 346	98.76 304

PAPR		95.29 319	94.47 328	97.75 268	97.50 371	95.14 279	94.89 361	98.71 290	91.39 369	95.35 370	95.48 375	94.57 261	99.14 376	84.95 389	97.37 364	98.97 269

testing222		91.96 362	90.37 366	96.72 330	97.47 372	92.59 344	96.11 318	94.76 373	96.83 253	92.90 391	92.87 394	57.92 405	99.55 313	86.93 385	97.52 357	98.00 352

PatchT		96.65 281	96.35 284	97.54 287	97.40 373	95.32 272	97.98 177	96.64 355	99.33 50	96.89 328	99.42 74	84.32 359	99.81 179	97.69 144	97.49 358	97.48 372

tpm cat1		93.29 349	93.13 347	93.75 373	97.39 374	84.74 395	97.39 245	97.65 331	83.39 395	94.16 382	98.41 267	82.86 368	99.39 349	91.56 359	95.35 389	97.14 377

PatchmatchNet		95.58 314	95.67 300	95.30 360	97.34 375	87.32 387	97.65 221	96.65 354	95.30 307	97.07 315	98.69 228	84.77 354	99.75 229	94.97 288	98.64 324	98.83 289
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 239	96.97 250	98.50 209	97.31 376	96.47 236	98.18 148	98.92 254	98.95 96	98.78 189	99.37 80	85.44 351	99.85 122	95.96 258	99.83 93	99.17 242

LS3D		98.63 121	98.38 143	99.36 64	97.25 377	99.38 8	99.12 57	99.32 154	99.21 63	98.44 231	98.88 196	97.31 143	99.80 186	96.58 217	99.34 251	98.92 278

IB-MVS	91.63 19	92.24 360	90.90 364	96.27 338	97.22 378	91.24 367	94.36 376	93.33 386	92.37 358	92.24 393	94.58 388	66.20 402	99.89 75	93.16 336	94.63 392	97.66 367
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
tpmrst		95.07 323	95.46 307	93.91 371	97.11 379	84.36 398	97.62 224	96.96 348	94.98 313	96.35 349	98.80 211	85.46 350	99.59 301	95.60 275	96.23 381	97.79 362

Syy-MVS		96.04 300	95.56 305	97.49 292	97.10 380	94.48 298	96.18 315	96.58 356	95.65 295	94.77 375	92.29 397	91.27 311	99.36 352	98.17 112	98.05 350	98.63 318

myMVS_eth3d		91.92 363	90.45 365	96.30 336	97.10 380	90.90 371	96.18 315	96.58 356	95.65 295	94.77 375	92.29 397	53.88 406	99.36 352	89.59 377	98.05 350	98.63 318

MDTV_nov1_ep13			95.22 317		97.06 382	83.20 400	97.74 209	96.16 361	94.37 329	96.99 320	98.83 205	83.95 362	99.53 320	93.90 319	97.95 353

MVS		93.19 350	92.09 354	96.50 333	96.91 383	94.03 312	98.07 162	98.06 322	68.01 398	94.56 380	96.48 356	95.96 219	99.30 362	83.84 391	96.89 374	96.17 387

E-PMN		94.17 336	94.37 331	93.58 375	96.86 384	85.71 393	90.11 395	97.07 344	98.17 149	97.82 276	97.19 343	84.62 356	98.94 382	89.77 375	97.68 356	96.09 391

JIA-IIPM		95.52 316	95.03 321	97.00 314	96.85 385	94.03 312	96.93 276	95.82 366	99.20 65	94.63 379	99.71 17	83.09 366	99.60 297	94.42 304	94.64 391	97.36 375

EMVS		93.83 342	94.02 334	93.23 379	96.83 386	84.96 394	89.77 396	96.32 360	97.92 165	97.43 304	96.36 361	86.17 343	98.93 383	87.68 382	97.73 355	95.81 392

cl22		95.79 308	95.39 312	96.98 316	96.77 387	92.79 341	94.40 375	98.53 300	94.59 322	97.89 269	98.17 289	82.82 369	99.24 368	96.37 236	99.03 294	98.92 278

WB-MVSnew		95.73 310	95.57 304	96.23 340	96.70 388	90.70 374	96.07 320	93.86 383	95.60 297	97.04 317	95.45 378	96.00 212	99.55 313	91.04 367	98.31 334	98.43 330

dp		93.47 347	93.59 340	93.13 380	96.64 389	81.62 404	97.66 219	96.42 359	92.80 354	96.11 352	98.64 240	78.55 387	99.59 301	93.31 334	92.18 398	98.16 342

test-LLR		93.90 341	93.85 335	94.04 369	96.53 390	84.62 396	94.05 381	92.39 389	96.17 278	94.12 383	95.07 379	82.30 370	99.67 266	95.87 263	98.18 339	97.82 357

test-mter		92.33 359	91.76 361	94.04 369	96.53 390	84.62 396	94.05 381	92.39 389	94.00 338	94.12 383	95.07 379	65.63 403	99.67 266	95.87 263	98.18 339	97.82 357

TESTMET0.1,1		92.19 361	91.77 360	93.46 376	96.48 392	82.80 401	94.05 381	91.52 393	94.45 327	94.00 386	94.88 385	66.65 400	99.56 310	95.78 268	98.11 345	98.02 349

miper_enhance_ethall		96.01 301	95.74 296	96.81 326	96.41 393	92.27 353	93.69 386	98.89 259	91.14 372	98.30 241	97.35 341	90.58 315	99.58 305	96.31 240	99.03 294	98.60 320

tpmvs		95.02 325	95.25 316	94.33 367	96.39 394	85.87 390	98.08 160	96.83 353	95.46 302	95.51 368	98.69 228	85.91 346	99.53 320	94.16 310	96.23 381	97.58 370

CMPMVS	75.91 23	96.29 294	95.44 309	98.84 155	96.25 395	98.69 88	97.02 269	99.12 221	88.90 384	97.83 274	98.86 199	89.51 322	98.90 385	91.92 352	99.51 224	98.92 278
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 329	93.69 338	96.99 315	96.05 396	93.61 330	94.97 359	93.49 384	96.17 278	97.57 292	94.88 385	82.30 370	99.01 380	93.60 327	94.17 394	98.37 336

EPMVS		93.72 344	93.27 343	95.09 363	96.04 397	87.76 385	98.13 153	85.01 403	94.69 320	96.92 322	98.64 240	78.47 388	99.31 360	95.04 286	96.46 378	98.20 340

cascas		94.79 327	94.33 333	96.15 345	96.02 398	92.36 351	92.34 393	99.26 186	85.34 392	95.08 373	94.96 384	92.96 292	98.53 390	94.41 307	98.59 327	97.56 371

gg-mvs-nofinetune		92.37 358	91.20 362	95.85 347	95.80 399	92.38 350	99.31 27	81.84 405	99.75 5	91.83 394	99.74 13	68.29 396	99.02 378	87.15 383	97.12 370	96.16 388

gm-plane-assit					94.83 400	81.97 403			88.07 387		94.99 382		99.60 297	91.76 354

GG-mvs-BLEND				94.76 364	94.54 401	92.13 355	99.31 27	80.47 406		88.73 399	91.01 399	67.59 399	98.16 394	82.30 396	94.53 393	93.98 396

EPNet_dtu		94.93 326	94.78 327	95.38 359	93.58 402	87.68 386	96.78 283	95.69 369	97.35 217	89.14 398	98.09 296	88.15 334	99.49 331	94.95 289	99.30 258	98.98 266
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
KD-MVS_2432*1600		92.87 353	91.99 356	95.51 356	91.37 403	89.27 378	94.07 379	98.14 318	95.42 303	97.25 310	96.44 358	67.86 397	99.24 368	91.28 363	96.08 384	98.02 349

miper_refine_blended		92.87 353	91.99 356	95.51 356	91.37 403	89.27 378	94.07 379	98.14 318	95.42 303	97.25 310	96.44 358	67.86 397	99.24 368	91.28 363	96.08 384	98.02 349

EPNet		96.14 298	95.44 309	98.25 231	90.76 405	95.50 266	97.92 183	94.65 374	98.97 93	92.98 390	98.85 202	89.12 325	99.87 101	95.99 256	99.68 167	99.39 177
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_method		79.78 367	79.50 370	80.62 383	80.21 406	45.76 409	70.82 397	98.41 307	31.08 401	80.89 402	97.71 318	84.85 353	97.37 396	91.51 360	80.03 400	98.75 305

tmp_tt		78.77 368	78.73 371	78.90 384	58.45 407	74.76 408	94.20 378	78.26 407	39.16 400	86.71 400	92.82 395	80.50 374	75.19 403	86.16 388	92.29 397	86.74 398

testmvs		17.12 370	20.53 373	6.87 386	12.05 408	4.20 411	93.62 387	6.73 409	4.62 404	10.41 404	24.33 401	8.28 409	3.56 405	9.69 404	15.07 402	12.86 401

test123		17.04 371	20.11 374	7.82 385	10.25 409	4.91 410	94.80 362	4.47 410	4.93 403	10.00 405	24.28 402	9.69 408	3.64 404	10.14 403	12.43 403	14.92 400

test_blank		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

eth-test2					0.00 410

eth-test					0.00 410

uanet_test		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

DCPMVS		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

cdsmvs_eth3d_5k		24.66 369	32.88 372	0.00 387	0.00 410	0.00 412	0.00 398	99.10 225	0.00 405	0.00 406	97.58 326	99.21 16	0.00 406	0.00 405	0.00 404	0.00 402

pcd_1.5k_mvsjas		8.17 372	10.90 375	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	98.07 86	0.00 406	0.00 405	0.00 404	0.00 402

sosnet-low-res		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

sosnet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uncertanet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

Regformer		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

ab-mvs-re		8.12 373	10.83 376	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	97.48 332	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uanet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

WAC-MVS						90.90 371								91.37 362

PC_three_1452									93.27 346	99.40 83	98.54 252	98.22 74	97.00 397	95.17 284	99.45 236	99.49 128

test_241102_TWO								99.30 167	98.03 157	99.26 112	99.02 153	97.51 132	99.88 84	96.91 187	99.60 194	99.66 59

test_0728_THIRD									98.17 149	99.08 134	99.02 153	97.89 99	99.88 84	97.07 175	99.71 154	99.70 52

GSMVS																98.81 294

sam_mvs1												84.74 355				98.81 294

sam_mvs												84.29 361

MTGPA								99.20 198

test_post1							97.59 229				20.48 404	83.07 367	99.66 277	94.16 310

test_post											21.25 403	83.86 363	99.70 250

patchmatchnet-post											98.77 216	84.37 358	99.85 122

MTMP							97.93 181	91.91 392

test9_res														93.28 335	99.15 281	99.38 184

agg_prior2														92.50 349	99.16 279	99.37 186

test_prior4						97.97 153	95.86 331

test_prior2							95.74 336		96.48 269	96.11 352	97.63 324	95.92 221		94.16 310	99.20 273

旧先验2							95.76 335		88.56 386	97.52 296			99.66 277	94.48 300

新几何2							95.93 328

无先验							95.74 336	98.74 288	89.38 382				99.73 239	92.38 351		99.22 230

原ACMM2							95.53 342

testdata2													99.79 199	92.80 343

segment_acmp												97.02 162

testdata1							95.44 347		96.32 274

plane_prior5								99.27 181					99.70 250	94.42 304	99.51 224	99.45 151

plane_prior4											97.98 303

plane_prior3						97.78 173			97.41 211	97.79 277

plane_prior2							97.77 204		98.20 146

plane_prior						97.65 182	97.07 268		96.72 259						99.36 247

n2								0.00 411

nn								0.00 411

door-mid								99.57 61

test11								98.87 262

door								99.41 121

HQP5-MVS						96.79 227

BP-MVS														92.82 341

HQP4-MVS										95.56 362			99.54 318			99.32 205

HQP3-MVS								99.04 236							99.26 265

HQP2-MVS												93.84 277

MDTV_nov1_ep13_2view						74.92 407	97.69 214		90.06 380	97.75 280		85.78 347		93.52 329		98.69 312

ACMMP++_ref															99.77 124

ACMMP++															99.68 167

Test By Simon												96.52 190

High-resolution multi-view benchmark