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.

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 17	98.69 75	98.20 9	99.93 1	99.98 2	96.82 24	100.00 1	99.75 35	100.00 1	99.99 23

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 47	99.21 108	97.91 85	99.98 17	98.85 59	98.25 5	99.92 2	99.75 75	94.72 71	99.97 58	99.87 20	99.64 92	99.95 76

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 49	99.17 112	97.81 89	99.98 17	98.86 56	98.25 5	99.90 3	99.76 67	94.21 94	99.97 58	99.87 20	99.52 106	99.98 51

patch_mono-2		98.24 65	99.12 5	95.59 256	99.67 82	86.91 377	99.95 64	98.89 52	97.60 30	99.90 3	99.76 67	96.54 32	99.98 47	99.94 11	99.82 81	99.88 91

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 35	98.62 91	98.02 18	99.90 3	99.95 3	97.33 17	100.00 1	99.54 51	100.00 1	100.00 1

fmvsm_s_conf0.5_n_5		98.08 71	97.71 84	99.17 59	98.67 156	97.69 96	99.99 5	98.57 100	97.40 36	99.89 6	99.69 97	85.99 251	99.96 69	99.80 26	99.40 123	99.85 96

fmvsm_s_conf0.5_n_3		97.95 74	97.66 86	98.81 94	98.99 126	98.07 74	99.98 17	98.81 64	98.18 10	99.89 6	99.70 93	84.15 269	99.97 58	99.76 34	99.50 111	98.39 248

TSAR-MVS + MP.		98.93 17	98.77 19	99.41 38	99.74 71	98.67 49	99.77 162	98.38 176	96.73 65	99.88 8	99.74 82	94.89 66	99.59 164	99.80 26	99.98 32	99.97 61
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.5_n_6		98.27 59	97.96 70	99.23 51	97.66 239	98.11 72	99.98 17	98.64 84	97.85 23	99.87 9	99.72 87	88.86 211	99.93 95	99.64 47	99.36 126	99.63 134

fmvsm_s_conf0.5_n_4		97.75 94	97.86 77	97.42 199	99.01 121	94.69 224	99.97 35	98.76 69	97.91 21	99.87 9	99.76 67	86.70 241	99.93 95	99.67 45	99.12 139	97.64 269

fmvsm_l_conf0.5_n_3		98.41 49	98.08 60	99.39 40	99.12 115	98.29 64	99.98 17	98.64 84	98.14 13	99.86 11	99.76 67	87.99 220	99.97 58	99.72 40	99.54 104	99.91 88

test0726					99.93 24	99.29 15	99.96 45	98.42 160	97.28 41	99.86 11	99.94 4	97.22 19

xiu_mvs_v2_base		98.23 66	97.97 67	99.02 81	98.69 154	98.66 51	99.52 226	98.08 225	97.05 52	99.86 11	99.86 29	90.65 182	99.71 151	99.39 63	98.63 156	98.69 241

test_vis1_n_1920		95.44 198	95.31 189	95.82 252	98.50 174	88.74 355	99.98 17	97.30 311	97.84 24	99.85 14	99.19 159	66.82 394	99.97 58	98.82 94	99.46 117	98.76 236

PS-MVSNAJ		98.44 45	98.20 50	99.16 62	98.80 148	98.92 29	99.54 224	98.17 211	97.34 38	99.85 14	99.85 33	91.20 169	99.89 109	99.41 61	99.67 90	98.69 241

旧先验2							99.46 240		94.21 154	99.85 14			99.95 78	96.96 181

IU-MVS					99.93 24	99.31 10		98.41 165	97.71 27	99.84 17				100.00 1	100.00 1	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 64	98.32 189	97.28 41	99.83 18	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 90
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									96.48 73	99.83 18	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

SF-MVS		98.67 30	98.40 36	99.50 30	99.77 66	98.67 49	99.90 105	98.21 206	93.53 182	99.81 20	99.89 22	94.70 73	99.86 120	99.84 23	99.93 61	99.96 69

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 79	98.73 46	99.94 81	98.34 186	96.38 79	99.81 20	99.76 67	94.59 74	99.98 47	99.84 23	99.96 46	99.97 61
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
fmvsm_s_conf0.5_n_8		98.38 53	98.05 62	99.35 44	99.20 109	98.12 71	99.98 17	98.81 64	98.22 7	99.80 22	99.71 90	87.37 231	99.97 58	99.91 16	99.48 113	99.97 61

test_fmvsm_n_1920		98.44 45	98.61 27	97.92 163	99.27 107	95.18 210	100.00 1	98.90 50	98.05 16	99.80 22	99.73 84	92.64 140	99.99 36	99.58 50	99.51 109	98.59 244

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 64	98.43 148	96.48 73	99.80 22	99.93 11	97.44 14	100.00 1	99.92 13	99.98 32	100.00 1

PC_three_1452									96.96 56	99.80 22	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 45	98.43 148	97.27 43	99.80 22	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 148	97.27 43	99.80 22	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 148	97.26 45	99.80 22	99.88 24	96.71 27	100.00 1

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 17	98.86 56	97.10 49	99.80 22	99.94 4	95.92 40	100.00 1	99.51 52	100.00 1	100.00 1

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 56	98.72 153	97.71 92	99.98 17	98.44 140	96.85 58	99.80 22	99.91 14	97.57 8	99.85 121	99.44 59	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
lecture		98.67 30	98.46 33	99.28 47	99.86 53	97.88 86	99.97 35	99.25 30	96.07 89	99.79 31	99.70 93	92.53 145	99.98 47	99.51 52	99.48 113	99.97 61

testdata				98.42 133	99.47 97	95.33 202		98.56 105	93.78 175	99.79 31	99.85 33	93.64 111	99.94 86	94.97 212	99.94 55	100.00 1

9.14			98.38 38		99.87 51		99.91 99	98.33 187	93.22 193	99.78 33	99.89 22	94.57 77	99.85 121	99.84 23	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 132	98.38 176	93.19 194	99.77 34	99.94 4	95.54 46	100.00 1	99.74 37	99.99 21	100.00 1
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
CDPH-MVS		98.65 32	98.36 42	99.49 32	99.94 13	98.73 46	99.87 121	98.33 187	93.97 165	99.76 35	99.87 27	94.99 64	99.75 145	98.55 111	100.00 1	99.98 51

fmvsm_s_conf0.5_n_2		97.59 104	97.28 107	98.53 122	99.01 121	98.15 66	99.98 17	98.59 96	98.17 11	99.75 36	99.63 113	81.83 286	99.94 86	99.78 29	98.79 152	97.51 277

fmvsm_s_conf0.5_n_a		97.73 97	97.72 82	97.77 176	98.63 162	94.26 236	99.96 45	98.92 49	97.18 48	99.75 36	99.69 97	87.00 237	99.97 58	99.46 57	98.89 146	99.08 218

test_one_0601					99.94 13	99.30 12		98.41 165	96.63 69	99.75 36	99.93 11	97.49 10

balanced_conf03		98.27 59	97.99 65	99.11 71	98.64 161	98.43 62	99.47 236	97.79 253	94.56 132	99.74 39	98.35 240	94.33 88	99.25 185	99.12 71	99.96 46	99.64 128

APD-MVS		98.62 33	98.35 43	99.41 38	99.90 42	98.51 59	99.87 121	98.36 180	94.08 158	99.74 39	99.73 84	94.08 97	99.74 147	99.42 60	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_fmvs1		95.35 201	95.68 180	94.36 304	98.99 126	84.98 388	99.96 45	96.65 374	97.60 30	99.73 41	98.96 180	71.58 373	99.93 95	98.31 126	99.37 125	98.17 253

test_prior2							99.95 64		95.78 95	99.73 41	99.76 67	96.00 37		99.78 29	100.00 1

TEST9					99.92 31	98.92 29	99.96 45	98.43 148	93.90 171	99.71 43	99.86 29	95.88 41	99.85 121

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 45	98.43 148	94.35 145	99.71 43	99.86 29	95.94 38	99.85 121	99.69 43	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 45	98.43 148	94.35 145	99.69 45	99.85 33	95.94 38	99.85 121

CS-MVS		97.79 91	97.91 74	97.43 198	99.10 116	94.42 229	99.99 5	97.10 333	95.07 113	99.68 46	99.75 75	92.95 131	98.34 259	98.38 121	99.14 136	99.54 156

test_fmvsmconf_n		98.43 47	98.32 44	98.78 96	98.12 205	96.41 153	99.99 5	98.83 63	98.22 7	99.67 47	99.64 110	91.11 173	99.94 86	99.67 45	99.62 95	99.98 51

test_fmvs1_n		94.25 238	94.36 215	93.92 320	97.68 236	83.70 395	99.90 105	96.57 377	97.40 36	99.67 47	98.88 192	61.82 413	99.92 101	98.23 131	99.13 137	98.14 256

fmvsm_s_conf0.1_n_2		97.25 120	96.85 127	98.43 131	98.08 206	98.08 73	99.92 91	97.76 258	98.05 16	99.65 49	99.58 119	80.88 299	99.93 95	99.59 49	98.17 171	97.29 278

fmvsm_s_conf0.1_n_a		97.09 130	96.90 123	97.63 186	95.65 329	94.21 238	99.83 147	98.50 129	96.27 84	99.65 49	99.64 110	84.72 263	99.93 95	99.04 77	98.84 149	98.74 238

test12				99.43 35	99.74 71	98.56 57		98.40 169		99.65 49		94.76 69	99.75 145		99.98 32	99.99 23

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 121	98.44 140	97.48 35	99.64 52	99.94 4	96.68 29	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.5_n		97.80 89	97.85 78	97.67 182	99.06 118	94.41 230	99.98 17	98.97 43	97.34 38	99.63 53	99.69 97	87.27 232	99.97 58	99.62 48	99.06 141	98.62 243

agg_prior					99.93 24	98.77 42		98.43 148		99.63 53			99.85 121

EC-MVSNet		97.38 116	97.24 109	97.80 171	97.41 255	95.64 189	99.99 5	97.06 339	94.59 131	99.63 53	99.32 145	89.20 207	98.14 275	98.76 99	99.23 133	99.62 135

fmvsm_s_conf0.5_n_7		97.70 100	97.74 81	97.59 189	98.44 178	95.16 212	99.97 35	98.65 81	97.95 20	99.62 56	99.78 62	86.09 249	99.94 86	99.69 43	99.50 111	97.66 268

xiu_mvs_v1_base_debu		97.43 109	97.06 115	98.55 117	97.74 227	98.14 68	99.31 260	97.86 247	96.43 76	99.62 56	99.69 97	85.56 254	99.68 156	99.05 74	98.31 166	97.83 263

SPE-MVS-test		97.88 78	97.94 72	97.70 181	99.28 106	95.20 209	99.98 17	97.15 328	95.53 104	99.62 56	99.79 58	92.08 158	98.38 255	98.75 100	99.28 130	99.52 162

xiu_mvs_v1_base		97.43 109	97.06 115	98.55 117	97.74 227	98.14 68	99.31 260	97.86 247	96.43 76	99.62 56	99.69 97	85.56 254	99.68 156	99.05 74	98.31 166	97.83 263

xiu_mvs_v1_base_debi		97.43 109	97.06 115	98.55 117	97.74 227	98.14 68	99.31 260	97.86 247	96.43 76	99.62 56	99.69 97	85.56 254	99.68 156	99.05 74	98.31 166	97.83 263

原ACMM1				98.96 87	99.73 74	96.99 128		98.51 123	94.06 161	99.62 56	99.85 33	94.97 65	99.96 69	95.11 208	99.95 50	99.92 86

PHI-MVS		98.41 49	98.21 49	99.03 78	99.86 53	97.10 124	99.98 17	98.80 68	90.78 287	99.62 56	99.78 62	95.30 53	100.00 1	99.80 26	99.93 61	99.99 23

mvsany_test1		97.82 87	97.90 75	97.55 190	98.77 150	93.04 268	99.80 156	97.93 238	96.95 57	99.61 63	99.68 104	90.92 177	99.83 131	99.18 69	98.29 169	99.80 103

test_cas_vis1_n_1920		96.59 158	96.23 153	97.65 183	98.22 195	94.23 237	99.99 5	97.25 318	97.77 25	99.58 64	99.08 165	77.10 331	99.97 58	97.64 163	99.45 118	98.74 238

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 103	99.92 1	99.96 45	98.44 140	97.96 19	99.55 65	99.94 4	97.18 21	100.00 1	93.81 243	99.94 55	99.98 51

新几何1				99.42 37	99.75 70	98.27 65		98.63 90	92.69 217	99.55 65	99.82 49	94.40 81	100.00 1	91.21 281	99.94 55	99.99 23

test_vis1_n		93.61 254	93.03 255	95.35 263	95.86 314	86.94 375	99.87 121	96.36 383	96.85 58	99.54 67	98.79 202	52.41 427	99.83 131	98.64 107	98.97 144	99.29 198

ACMMP_NAP		98.49 41	98.14 55	99.54 27	99.66 83	98.62 55	99.85 135	98.37 179	94.68 129	99.53 68	99.83 46	92.87 133	100.00 1	98.66 106	99.84 76	99.99 23

PMMVS		96.76 148	96.76 132	96.76 223	98.28 191	92.10 290	99.91 99	97.98 233	94.12 156	99.53 68	99.39 140	86.93 238	98.73 224	96.95 182	97.73 184	99.45 173

FOURS1					99.92 31	97.66 97	99.95 64	98.36 180	95.58 102	99.52 70

MSP-MVS		99.09 9	99.12 5	98.98 85	99.93 24	97.24 114	99.95 64	98.42 160	97.50 34	99.52 70	99.88 24	97.43 16	99.71 151	99.50 54	99.98 32	100.00 1
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
fmvsm_s_conf0.1_n		97.30 117	97.21 111	97.60 188	97.38 257	94.40 232	99.90 105	98.64 84	96.47 75	99.51 72	99.65 109	84.99 262	99.93 95	99.22 68	99.09 140	98.46 245

test_part2					99.89 45	99.25 18				99.49 73

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 99	98.39 172	97.20 47	99.46 74	99.85 33	95.53 48	99.79 136	99.86 22	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
region2R		98.54 37	98.37 40	99.05 76	99.96 8	97.18 117	99.96 45	98.55 111	94.87 121	99.45 75	99.85 33	94.07 98	100.00 1	98.67 104	100.00 1	99.98 51

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 67	99.21 21	99.99 5	99.34 25	98.70 2	99.44 76	99.75 75	93.24 123	99.99 36	99.94 11	99.41 122	99.95 76

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 64	98.56 105	97.56 33	99.44 76	99.85 33	95.38 52	100.00 1	99.31 64	99.99 21	99.87 93

MVSFormer		96.94 138	96.60 140	97.95 159	97.28 266	97.70 94	99.55 222	97.27 316	91.17 271	99.43 78	99.54 125	90.92 177	96.89 344	94.67 224	99.62 95	99.25 203

lupinMVS		97.85 82	97.60 90	98.62 109	97.28 266	97.70 94	99.99 5	97.55 281	95.50 106	99.43 78	99.67 105	90.92 177	98.71 227	98.40 120	99.62 95	99.45 173

XVS		98.70 29	98.55 28	99.15 64	99.94 13	97.50 103	99.94 81	98.42 160	96.22 85	99.41 80	99.78 62	94.34 86	99.96 69	98.92 87	99.95 50	99.99 23

X-MVStestdata		93.83 244	92.06 277	99.15 64	99.94 13	97.50 103	99.94 81	98.42 160	96.22 85	99.41 80	41.37 449	94.34 86	99.96 69	98.92 87	99.95 50	99.99 23

SR-MVS-dyc-post		98.31 56	98.17 53	98.71 101	99.79 63	96.37 157	99.76 167	98.31 191	94.43 140	99.40 82	99.75 75	93.28 121	99.78 138	98.90 90	99.92 64	99.97 61

RE-MVS-def			98.13 56		99.79 63	96.37 157	99.76 167	98.31 191	94.43 140	99.40 82	99.75 75	92.95 131		98.90 90	99.92 64	99.97 61

MM		98.83 21	98.53 30	99.76 10	99.59 86	99.33 8	99.99 5	99.76 6	98.39 4	99.39 84	99.80 54	90.49 187	99.96 69	99.89 18	99.43 120	99.98 51

APD-MVS_3200maxsize		98.25 64	98.08 60	98.78 96	99.81 61	96.60 146	99.82 150	98.30 194	93.95 167	99.37 85	99.77 65	92.84 134	99.76 144	98.95 83	99.92 64	99.97 61

PGM-MVS		98.34 54	98.13 56	98.99 83	99.92 31	97.00 127	99.75 171	99.50 17	93.90 171	99.37 85	99.76 67	93.24 123	100.00 1	97.75 162	99.96 46	99.98 51

SR-MVS		98.46 43	98.30 47	98.93 89	99.88 49	97.04 126	99.84 140	98.35 182	94.92 118	99.32 87	99.80 54	93.35 116	99.78 138	99.30 65	99.95 50	99.96 69

ZD-MVS					99.92 31	98.57 56		98.52 120	92.34 236	99.31 88	99.83 46	95.06 59	99.80 134	99.70 42	99.97 42

HFP-MVS		98.56 36	98.37 40	99.14 66	99.96 8	97.43 107	99.95 64	98.61 92	94.77 124	99.31 88	99.85 33	94.22 92	100.00 1	98.70 102	99.98 32	99.98 51

ACMMPR		98.50 40	98.32 44	99.05 76	99.96 8	97.18 117	99.95 64	98.60 94	94.77 124	99.31 88	99.84 44	93.73 108	100.00 1	98.70 102	99.98 32	99.98 51

ETV-MVS		97.92 77	97.80 80	98.25 142	98.14 203	96.48 150	99.98 17	97.63 269	95.61 101	99.29 91	99.46 131	92.55 144	98.82 215	99.02 81	98.54 160	99.46 171

test222					99.55 91	97.41 109	99.34 256	98.55 111	91.86 249	99.27 92	99.83 46	93.84 106			99.95 50	99.99 23

MVSMamba_PlusPlus		97.83 84	97.45 98	98.99 83	98.60 163	98.15 66	99.58 214	97.74 259	90.34 296	99.26 93	98.32 243	94.29 90	99.23 186	99.03 80	99.89 70	99.58 148

CANet_DTU		96.76 148	96.15 157	98.60 111	98.78 149	97.53 100	99.84 140	97.63 269	97.25 46	99.20 94	99.64 110	81.36 292	99.98 47	92.77 264	98.89 146	98.28 252

EPNet		98.49 41	98.40 36	98.77 98	99.62 85	96.80 137	99.90 105	99.51 16	97.60 30	99.20 94	99.36 143	93.71 109	99.91 102	97.99 145	98.71 155	99.61 139
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	95.94 2	97.71 99	98.98 12	93.92 320	99.63 84	81.76 411	99.96 45	98.56 105	99.47 1	99.19 96	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

reproduce_model		98.75 27	98.66 23	99.03 78	99.71 77	97.10 124	99.73 181	98.23 204	97.02 54	99.18 97	99.90 18	94.54 78	99.99 36	99.77 31	99.90 69	99.99 23

VNet		97.21 123	96.57 142	99.13 70	98.97 129	97.82 88	99.03 295	99.21 32	94.31 148	99.18 97	98.88 192	86.26 248	99.89 109	98.93 85	94.32 258	99.69 119

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 35	98.64 84	98.47 3	99.13 99	99.92 13	96.38 34	100.00 1	99.74 37	100.00 1	100.00 1

reproduce-ours		98.78 24	98.67 21	99.09 73	99.70 79	97.30 111	99.74 174	98.25 200	97.10 49	99.10 100	99.90 18	94.59 74	99.99 36	99.77 31	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 73	99.70 79	97.30 111	99.74 174	98.25 200	97.10 49	99.10 100	99.90 18	94.59 74	99.99 36	99.77 31	99.91 67	99.99 23

GDP-MVS		97.88 78	97.59 92	98.75 99	97.59 244	97.81 89	99.95 64	97.37 303	94.44 139	99.08 102	99.58 119	97.13 23	99.08 200	94.99 211	98.17 171	99.37 183

DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 270	98.47 132	98.14 13	99.08 102	99.91 14	93.09 127	100.00 1	99.04 77	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
114514_t		97.41 114	96.83 128	99.14 66	99.51 95	97.83 87	99.89 115	98.27 198	88.48 333	99.06 104	99.66 107	90.30 190	99.64 163	96.32 191	99.97 42	99.96 69

PVSNet	91.05 13	97.13 127	96.69 137	98.45 129	99.52 93	95.81 178	99.95 64	99.65 12	94.73 126	99.04 105	99.21 158	84.48 266	99.95 78	94.92 214	98.74 154	99.58 148

CHOSEN 280x420		99.01 14	99.03 10	98.95 88	99.38 101	98.87 33	98.46 346	99.42 21	97.03 53	99.02 106	99.09 164	99.35 2	98.21 272	99.73 39	99.78 84	99.77 108

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 204	99.44 19	97.33 40	99.00 107	99.72 87	94.03 99	99.98 47	98.73 101	100.00 1	100.00 1

diffmvs		97.00 135	96.64 138	98.09 153	97.64 241	96.17 169	99.81 152	97.19 321	94.67 130	98.95 108	99.28 148	86.43 244	98.76 221	98.37 123	97.42 192	99.33 192
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HPM-MVS_fast		97.80 89	97.50 95	98.68 103	99.79 63	96.42 152	99.88 118	98.16 216	91.75 254	98.94 109	99.54 125	91.82 164	99.65 162	97.62 165	99.99 21	99.99 23

dcpmvs_2		97.42 113	98.09 59	95.42 261	99.58 90	87.24 373	99.23 271	96.95 351	94.28 151	98.93 110	99.73 84	94.39 84	99.16 196	99.89 18	99.82 81	99.86 95

CP-MVS		98.45 44	98.32 44	98.87 91	99.96 8	96.62 144	99.97 35	98.39 172	94.43 140	98.90 111	99.87 27	94.30 89	100.00 1	99.04 77	99.99 21	99.99 23

test_fmvsmconf0.1_n		97.74 95	97.44 99	98.64 108	95.76 319	96.20 166	99.94 81	98.05 228	98.17 11	98.89 112	99.42 133	87.65 223	99.90 104	99.50 54	99.60 101	99.82 99

testing222		97.08 133	96.75 133	98.06 155	98.56 164	96.82 134	99.85 135	98.61 92	92.53 228	98.84 113	98.84 201	93.36 115	98.30 263	95.84 199	94.30 259	99.05 221

MVS_Test		96.46 163	95.74 176	98.61 110	98.18 199	97.23 115	99.31 260	97.15 328	91.07 276	98.84 113	97.05 285	88.17 218	98.97 207	94.39 228	97.50 189	99.61 139

API-MVS		97.86 80	97.66 86	98.47 127	99.52 93	95.41 198	99.47 236	98.87 55	91.68 255	98.84 113	99.85 33	92.34 152	99.99 36	98.44 119	99.96 46	100.00 1

GST-MVS		98.27 59	97.97 67	99.17 59	99.92 31	97.57 99	99.93 88	98.39 172	94.04 163	98.80 116	99.74 82	92.98 130	100.00 1	98.16 134	99.76 85	99.93 81

MVS_111021_LR		98.42 48	98.38 38	98.53 122	99.39 100	95.79 179	99.87 121	99.86 2	96.70 66	98.78 117	99.79 58	92.03 159	99.90 104	99.17 70	99.86 75	99.88 91

BP-MVS1		98.33 55	98.18 52	98.81 94	97.44 253	97.98 80	99.96 45	98.17 211	94.88 120	98.77 118	99.59 116	97.59 7	99.08 200	98.24 130	98.93 145	99.36 185

h-mvs33		94.92 210	94.36 215	96.59 229	98.85 145	91.29 311	98.93 308	98.94 44	95.90 92	98.77 118	98.42 238	90.89 180	99.77 141	97.80 155	70.76 414	98.72 240

hse-mvs2		94.38 232	94.08 223	95.31 266	98.27 192	90.02 338	99.29 265	98.56 105	95.90 92	98.77 118	98.00 255	90.89 180	98.26 270	97.80 155	69.20 420	97.64 269

TSAR-MVS + GP.		98.60 34	98.51 31	98.86 92	99.73 74	96.63 143	99.97 35	97.92 241	98.07 15	98.76 121	99.55 123	95.00 63	99.94 86	99.91 16	97.68 186	99.99 23

sss		97.57 105	97.03 119	99.18 56	98.37 183	98.04 77	99.73 181	99.38 22	93.46 185	98.76 121	99.06 167	91.21 168	99.89 109	96.33 190	97.01 204	99.62 135

CostFormer		96.10 177	95.88 173	96.78 222	97.03 273	92.55 281	97.08 388	97.83 251	90.04 303	98.72 123	94.89 371	95.01 62	98.29 264	96.54 189	95.77 233	99.50 167

tpmrst		96.27 175	95.98 163	97.13 211	97.96 213	93.15 264	96.34 402	98.17 211	92.07 242	98.71 124	95.12 361	93.91 102	98.73 224	94.91 216	96.62 209	99.50 167

MVS_111021_HR		98.72 28	98.62 26	99.01 82	99.36 102	97.18 117	99.93 88	99.90 1	96.81 63	98.67 125	99.77 65	93.92 101	99.89 109	99.27 66	99.94 55	99.96 69

MAR-MVS		97.43 109	97.19 112	98.15 149	99.47 97	94.79 222	99.05 292	98.76 69	92.65 220	98.66 126	99.82 49	88.52 215	99.98 47	98.12 136	99.63 94	99.67 122
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
Effi-MVS+		96.30 172	95.69 178	98.16 146	97.85 220	96.26 160	97.41 379	97.21 320	90.37 294	98.65 127	98.58 223	86.61 243	98.70 229	97.11 174	97.37 194	99.52 162

HPM-MVS		97.96 73	97.72 82	98.68 103	99.84 57	96.39 156	99.90 105	98.17 211	92.61 222	98.62 128	99.57 122	91.87 162	99.67 159	98.87 92	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SymmetryMVS		97.64 102	97.46 96	98.17 145	98.74 152	95.39 200	99.61 209	99.26 29	96.52 72	98.61 129	99.31 147	92.73 138	99.67 159	96.77 186	95.63 237	99.45 173

mPP-MVS		98.39 52	98.20 50	98.97 86	99.97 3	96.92 131	99.95 64	98.38 176	95.04 114	98.61 129	99.80 54	93.39 114	100.00 1	98.64 107	100.00 1	99.98 51

jason		97.24 121	96.86 126	98.38 136	95.73 322	97.32 110	99.97 35	97.40 299	95.34 109	98.60 131	99.54 125	87.70 222	98.56 236	97.94 148	99.47 115	99.25 203
jason: jason.
UBG		97.84 83	97.69 85	98.29 140	98.38 181	96.59 148	99.90 105	98.53 118	93.91 170	98.52 132	98.42 238	96.77 25	99.17 194	98.54 112	96.20 219	99.11 215

CANet		98.27 59	97.82 79	99.63 17	99.72 76	99.10 23	99.98 17	98.51 123	97.00 55	98.52 132	99.71 90	87.80 221	99.95 78	99.75 35	99.38 124	99.83 98

EI-MVSNet-Vis-set		98.27 59	98.11 58	98.75 99	99.83 58	96.59 148	99.40 244	98.51 123	95.29 110	98.51 134	99.76 67	93.60 112	99.71 151	98.53 114	99.52 106	99.95 76

ZNCC-MVS		98.31 56	98.03 63	99.17 59	99.88 49	97.59 98	99.94 81	98.44 140	94.31 148	98.50 135	99.82 49	93.06 128	99.99 36	98.30 127	99.99 21	99.93 81

LFMVS		94.75 217	93.56 238	98.30 139	99.03 120	95.70 185	98.74 328	97.98 233	87.81 344	98.47 136	99.39 140	67.43 392	99.53 165	98.01 143	95.20 248	99.67 122

KinetiMVS		96.10 177	95.29 191	98.53 122	97.08 270	97.12 121	99.56 219	98.12 222	94.78 123	98.44 137	98.94 187	80.30 309	99.39 181	91.56 278	98.79 152	99.06 220

tpm2		95.47 197	95.18 195	96.35 237	96.91 280	91.70 304	96.96 391	97.93 238	88.04 340	98.44 137	95.40 345	93.32 118	97.97 285	94.00 236	95.61 238	99.38 181

mvsmamba		96.94 138	96.73 134	97.55 190	97.99 211	94.37 233	99.62 207	97.70 261	93.13 198	98.42 139	97.92 260	88.02 219	98.75 223	98.78 97	99.01 143	99.52 162

alignmvs		97.81 88	97.33 105	99.25 49	98.77 150	98.66 51	99.99 5	98.44 140	94.40 144	98.41 140	99.47 129	93.65 110	99.42 180	98.57 110	94.26 260	99.67 122

UA-Net		96.54 160	95.96 167	98.27 141	98.23 194	95.71 184	98.00 370	98.45 135	93.72 179	98.41 140	99.27 151	88.71 214	99.66 161	91.19 282	97.69 185	99.44 176

DP-MVS Recon		98.41 49	98.02 64	99.56 25	99.97 3	98.70 48	99.92 91	98.44 140	92.06 244	98.40 142	99.84 44	95.68 44	100.00 1	98.19 132	99.71 88	99.97 61

CPTT-MVS		97.64 102	97.32 106	98.58 115	99.97 3	95.77 180	99.96 45	98.35 182	89.90 305	98.36 143	99.79 58	91.18 172	99.99 36	98.37 123	99.99 21	99.99 23

PAPM		98.60 34	98.42 35	99.14 66	96.05 308	98.96 26	99.90 105	99.35 24	96.68 67	98.35 144	99.66 107	96.45 33	98.51 239	99.45 58	99.89 70	99.96 69

HY-MVS	92.50 7	97.79 91	97.17 114	99.63 17	98.98 128	99.32 9	97.49 377	99.52 14	95.69 99	98.32 145	97.41 272	93.32 118	99.77 141	98.08 140	95.75 235	99.81 101

EI-MVSNet-UG-set		98.14 68	97.99 65	98.60 111	99.80 62	96.27 159	99.36 254	98.50 129	95.21 112	98.30 146	99.75 75	93.29 120	99.73 150	98.37 123	99.30 129	99.81 101

PVSNet_BlendedMVS		96.05 179	95.82 175	96.72 225	99.59 86	96.99 128	99.95 64	99.10 34	94.06 161	98.27 147	95.80 324	89.00 209	99.95 78	99.12 71	87.53 316	93.24 378

PVSNet_Blended		97.94 75	97.64 88	98.83 93	99.59 86	96.99 128	100.00 1	99.10 34	95.38 107	98.27 147	99.08 165	89.00 209	99.95 78	99.12 71	99.25 131	99.57 150

myMVS_eth3d28		97.86 80	97.59 92	98.68 103	98.50 174	97.26 113	99.92 91	98.55 111	93.79 174	98.26 149	98.75 204	95.20 54	99.48 176	98.93 85	96.40 215	99.29 198

MP-MVS		98.23 66	97.97 67	99.03 78	99.94 13	97.17 120	99.95 64	98.39 172	94.70 128	98.26 149	99.81 53	91.84 163	100.00 1	98.85 93	99.97 42	99.93 81
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
WTY-MVS		98.10 70	97.60 90	99.60 22	98.92 136	99.28 17	99.89 115	99.52 14	95.58 102	98.24 151	99.39 140	93.33 117	99.74 147	97.98 147	95.58 239	99.78 107

DELS-MVS		98.54 37	98.22 48	99.50 30	99.15 114	98.65 53	100.00 1	98.58 98	97.70 28	98.21 152	99.24 156	92.58 143	99.94 86	98.63 109	99.94 55	99.92 86
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
ETVMVS		97.03 134	96.64 138	98.20 144	98.67 156	97.12 121	99.89 115	98.57 100	91.10 275	98.17 153	98.59 220	93.86 105	98.19 273	95.64 203	95.24 247	99.28 200

testing11		97.48 108	97.27 108	98.10 152	98.36 184	96.02 173	99.92 91	98.45 135	93.45 187	98.15 154	98.70 209	95.48 50	99.22 187	97.85 153	95.05 249	99.07 219

guyue		97.15 126	96.82 129	98.15 149	97.56 246	96.25 164	99.71 188	97.84 250	95.75 97	98.13 155	98.65 214	87.58 225	98.82 215	98.29 128	97.91 183	99.36 185

MDTV_nov1_ep13_2view						96.26 160	96.11 407		91.89 248	98.06 156		94.40 81		94.30 232		99.67 122

PAPR		98.52 39	98.16 54	99.58 24	99.97 3	98.77 42	99.95 64	98.43 148	95.35 108	98.03 157	99.75 75	94.03 99	99.98 47	98.11 137	99.83 77	99.99 23

MDTV_nov1_ep13			95.69 178		97.90 216	94.15 239	95.98 410	98.44 140	93.12 199	97.98 158	95.74 326	95.10 57	98.58 235	90.02 306	96.92 206

test2506		97.53 106	97.19 112	98.58 115	98.66 158	96.90 132	98.81 323	99.77 5	94.93 116	97.95 159	98.96 180	92.51 146	99.20 191	94.93 213	98.15 173	99.64 128

GG-mvs-BLEND				98.54 120	98.21 196	98.01 78	93.87 420	98.52 120		97.92 160	97.92 260	99.02 3	97.94 290	98.17 133	99.58 102	99.67 122

testing3-2		97.72 98	97.43 101	98.60 111	98.55 167	97.11 123	100.00 1	99.23 31	93.78 175	97.90 161	98.73 206	95.50 49	99.69 155	98.53 114	94.63 252	98.99 225

EIA-MVS		97.53 106	97.46 96	97.76 178	98.04 209	94.84 219	99.98 17	97.61 275	94.41 143	97.90 161	99.59 116	92.40 150	98.87 212	98.04 142	99.13 137	99.59 142

test_fmvsmconf0.01_n		96.39 167	95.74 176	98.32 138	91.47 404	95.56 192	99.84 140	97.30 311	97.74 26	97.89 163	99.35 144	79.62 313	99.85 121	99.25 67	99.24 132	99.55 152

LuminaMVS		96.63 156	96.21 155	97.87 168	95.58 333	96.82 134	99.12 278	97.67 264	94.47 135	97.88 164	98.31 245	87.50 227	98.71 227	98.07 141	97.29 195	98.10 257

sasdasda		97.09 130	96.32 150	99.39 40	98.93 133	98.95 27	99.72 185	97.35 304	94.45 136	97.88 164	99.42 133	86.71 239	99.52 166	98.48 116	93.97 264	99.72 114

test_yl		97.83 84	97.37 103	99.21 53	99.18 110	97.98 80	99.64 204	99.27 27	91.43 264	97.88 164	98.99 174	95.84 42	99.84 129	98.82 94	95.32 245	99.79 104

DCV-MVSNet		97.83 84	97.37 103	99.21 53	99.18 110	97.98 80	99.64 204	99.27 27	91.43 264	97.88 164	98.99 174	95.84 42	99.84 129	98.82 94	95.32 245	99.79 104

canonicalmvs		97.09 130	96.32 150	99.39 40	98.93 133	98.95 27	99.72 185	97.35 304	94.45 136	97.88 164	99.42 133	86.71 239	99.52 166	98.48 116	93.97 264	99.72 114

AstraMVS		96.57 159	96.46 147	96.91 217	96.79 291	92.50 282	99.90 105	97.38 300	96.02 91	97.79 169	99.32 145	86.36 246	98.99 204	98.26 129	96.33 218	99.23 206

MGCFI-Net		97.00 135	96.22 154	99.34 45	98.86 144	98.80 39	99.67 198	97.30 311	94.31 148	97.77 170	99.41 137	86.36 246	99.50 170	98.38 121	93.90 266	99.72 114

VDDNet		93.12 265	91.91 280	96.76 223	96.67 296	92.65 279	98.69 334	98.21 206	82.81 397	97.75 171	99.28 148	61.57 414	99.48 176	98.09 139	94.09 262	98.15 254

EPMVS		96.53 161	96.01 160	98.09 153	98.43 179	96.12 172	96.36 401	99.43 20	93.53 182	97.64 172	95.04 364	94.41 80	98.38 255	91.13 283	98.11 176	99.75 110

JIA-IIPM		91.76 298	90.70 299	94.94 276	96.11 306	87.51 370	93.16 423	98.13 221	75.79 419	97.58 173	77.68 437	92.84 134	97.97 285	88.47 324	96.54 210	99.33 192

EPNet_dtu		95.71 190	95.39 186	96.66 227	98.92 136	93.41 260	99.57 217	98.90 50	96.19 87	97.52 174	98.56 225	92.65 139	97.36 308	77.89 403	98.33 165	99.20 207
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PAPM_NR		98.12 69	97.93 73	98.70 102	99.94 13	96.13 170	99.82 150	98.43 148	94.56 132	97.52 174	99.70 93	94.40 81	99.98 47	97.00 177	99.98 32	99.99 23

FE-MVS		95.70 192	95.01 202	97.79 173	98.21 196	94.57 225	95.03 415	98.69 75	88.90 323	97.50 176	96.19 313	92.60 142	99.49 175	89.99 307	97.94 182	99.31 194

thisisatest0515		97.41 114	97.02 120	98.59 114	97.71 234	97.52 101	99.97 35	98.54 115	91.83 250	97.45 177	99.04 168	97.50 9	99.10 199	94.75 221	96.37 217	99.16 209

RRT-MVS		96.24 176	95.68 180	97.94 162	97.65 240	94.92 217	99.27 268	97.10 333	92.79 212	97.43 178	97.99 257	81.85 285	99.37 182	98.46 118	98.57 157	99.53 160

OMC-MVS		97.28 118	97.23 110	97.41 200	99.76 67	93.36 263	99.65 200	97.95 236	96.03 90	97.41 179	99.70 93	89.61 198	99.51 168	96.73 187	98.25 170	99.38 181

testing99		97.17 124	96.91 122	97.95 159	98.35 186	95.70 185	99.91 99	98.43 148	92.94 203	97.36 180	98.72 207	94.83 67	99.21 188	97.00 177	94.64 251	98.95 226

UWE-MVS-28		95.95 182	96.49 144	94.34 305	98.51 172	89.99 339	99.39 248	98.57 100	93.14 197	97.33 181	98.31 245	93.44 113	94.68 405	93.69 250	95.98 225	98.34 251

testing91		97.16 125	96.90 123	97.97 158	98.35 186	95.67 188	99.91 99	98.42 160	92.91 205	97.33 181	98.72 207	94.81 68	99.21 188	96.98 179	94.63 252	99.03 222

gg-mvs-nofinetune		93.51 256	91.86 282	98.47 127	97.72 232	97.96 83	92.62 424	98.51 123	74.70 423	97.33 181	69.59 440	98.91 4	97.79 294	97.77 160	99.56 103	99.67 122

PatchT		90.38 324	88.75 340	95.25 268	95.99 310	90.16 335	91.22 431	97.54 283	76.80 415	97.26 184	86.01 431	91.88 161	96.07 381	66.16 430	95.91 230	99.51 165

PLC	95.54 3	97.93 76	97.89 76	98.05 156	99.82 59	94.77 223	99.92 91	98.46 134	93.93 168	97.20 185	99.27 151	95.44 51	99.97 58	97.41 167	99.51 109	99.41 179
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
mmtdpeth		88.52 351	87.75 353	90.85 372	95.71 325	83.47 399	98.94 306	94.85 413	88.78 326	97.19 186	89.58 417	63.29 407	98.97 207	98.54 112	62.86 433	90.10 416

MTAPA		98.29 58	97.96 70	99.30 46	99.85 55	97.93 84	99.39 248	98.28 196	95.76 96	97.18 187	99.88 24	92.74 137	100.00 1	98.67 104	99.88 73	99.99 23

UWE-MVS		96.79 145	96.72 135	97.00 214	98.51 172	93.70 251	99.71 188	98.60 94	92.96 202	97.09 188	98.34 242	96.67 31	98.85 214	92.11 270	96.50 212	98.44 246

PatchmatchNet		95.94 183	95.45 184	97.39 202	97.83 221	94.41 230	96.05 408	98.40 169	92.86 206	97.09 188	95.28 356	94.21 94	98.07 281	89.26 315	98.11 176	99.70 117
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0530		97.10 128	96.72 135	98.22 143	97.60 243	96.70 138	99.92 91	98.54 115	91.11 274	97.07 190	98.97 178	97.47 12	99.03 202	93.73 248	96.09 222	98.92 227

test_fmvsmvis_n_1920		97.67 101	97.59 92	97.91 165	97.02 274	95.34 201	99.95 64	98.45 135	97.87 22	97.02 191	99.59 116	89.64 197	99.98 47	99.41 61	99.34 128	98.42 247

CR-MVSNet		93.45 259	92.62 263	95.94 247	96.29 301	92.66 277	92.01 427	96.23 385	92.62 221	96.94 192	93.31 397	91.04 174	96.03 382	79.23 395	95.96 226	99.13 213

RPMNet		89.76 339	87.28 356	97.19 210	96.29 301	92.66 277	92.01 427	98.31 191	70.19 430	96.94 192	85.87 432	87.25 233	99.78 138	62.69 434	95.96 226	99.13 213

baseline		96.43 164	95.98 163	97.76 178	97.34 260	95.17 211	99.51 228	97.17 325	93.92 169	96.90 194	99.28 148	85.37 258	98.64 233	97.50 166	96.86 208	99.46 171

ECVR-MVS		95.66 193	95.05 200	97.51 194	98.66 158	93.71 250	98.85 320	98.45 135	94.93 116	96.86 195	98.96 180	75.22 354	99.20 191	95.34 205	98.15 173	99.64 128

Vis-MVSNet		95.72 188	95.15 196	97.45 196	97.62 242	94.28 235	99.28 266	98.24 202	94.27 153	96.84 196	98.94 187	79.39 315	98.76 221	93.25 254	98.49 161	99.30 196
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
VDD-MVS		93.77 248	92.94 256	96.27 239	98.55 167	90.22 334	98.77 327	97.79 253	90.85 281	96.82 197	99.42 133	61.18 416	99.77 141	98.95 83	94.13 261	98.82 233

UGNet		95.33 202	94.57 211	97.62 187	98.55 167	94.85 218	98.67 336	99.32 26	95.75 97	96.80 198	96.27 311	72.18 370	99.96 69	94.58 226	99.05 142	98.04 258
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
AdaColmap		97.23 122	96.80 131	98.51 125	99.99 1	95.60 191	99.09 281	98.84 62	93.32 190	96.74 199	99.72 87	86.04 250	100.00 1	98.01 143	99.43 120	99.94 80

tpm		93.70 252	93.41 245	94.58 291	95.36 336	87.41 371	97.01 389	96.90 358	90.85 281	96.72 200	94.14 388	90.40 188	96.84 348	90.75 294	88.54 303	99.51 165

test1111		95.57 195	94.98 203	97.37 203	98.56 164	93.37 262	98.86 318	98.45 135	94.95 115	96.63 201	98.95 185	75.21 355	99.11 197	95.02 210	98.14 175	99.64 128

tttt0517		96.85 142	96.49 144	97.92 163	97.48 252	95.89 177	99.85 135	98.54 115	90.72 289	96.63 201	98.93 190	97.47 12	99.02 203	93.03 261	95.76 234	98.85 231

casdiffmvs		96.42 166	95.97 166	97.77 176	97.30 264	94.98 214	99.84 140	97.09 336	93.75 178	96.58 203	99.26 154	85.07 260	98.78 219	97.77 160	97.04 202	99.54 156
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CNLPA		97.76 93	97.38 102	98.92 90	99.53 92	96.84 133	99.87 121	98.14 220	93.78 175	96.55 204	99.69 97	92.28 153	99.98 47	97.13 173	99.44 119	99.93 81

PatchMatch-RL		96.04 180	95.40 185	97.95 159	99.59 86	95.22 208	99.52 226	99.07 37	93.96 166	96.49 205	98.35 240	82.28 281	99.82 133	90.15 305	99.22 134	98.81 234

MP-MVS-pluss		98.07 72	97.64 88	99.38 43	99.74 71	98.41 63	99.74 174	98.18 210	93.35 188	96.45 206	99.85 33	92.64 140	99.97 58	98.91 89	99.89 70	99.77 108
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ADS-MVSNet2		93.80 247	93.88 230	93.55 333	97.87 218	85.94 382	94.24 416	96.84 362	90.07 301	96.43 207	94.48 382	90.29 191	95.37 394	87.44 334	97.23 196	99.36 185

ADS-MVSNet		94.79 214	94.02 225	97.11 213	97.87 218	93.79 247	94.24 416	98.16 216	90.07 301	96.43 207	94.48 382	90.29 191	98.19 273	87.44 334	97.23 196	99.36 185

ACMMP		97.74 95	97.44 99	98.66 106	99.92 31	96.13 170	99.18 275	99.45 18	94.84 122	96.41 209	99.71 90	91.40 166	99.99 36	97.99 145	98.03 180	99.87 93
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
PVSNet_Blended_VisFu		97.27 119	96.81 130	98.66 106	98.81 147	96.67 142	99.92 91	98.64 84	94.51 134	96.38 210	98.49 231	89.05 208	99.88 115	97.10 175	98.34 164	99.43 177

AUN-MVS		93.28 260	92.60 264	95.34 264	98.29 189	90.09 337	99.31 260	98.56 105	91.80 253	96.35 211	98.00 255	89.38 201	98.28 266	92.46 265	69.22 419	97.64 269

FA-MVS(test-final)		95.86 184	95.09 198	98.15 149	97.74 227	95.62 190	96.31 403	98.17 211	91.42 266	96.26 212	96.13 317	90.56 185	99.47 178	92.18 269	97.07 200	99.35 189

thres200		96.96 137	96.21 155	99.22 52	98.97 129	98.84 36	99.85 135	99.71 7	93.17 195	96.26 212	98.88 192	89.87 195	99.51 168	94.26 233	94.91 250	99.31 194

HyFIR lowres test		96.66 155	96.43 148	97.36 205	99.05 119	93.91 246	99.70 193	99.80 3	90.54 291	96.26 212	98.08 252	92.15 156	98.23 271	96.84 185	95.46 240	99.93 81

Elysia		94.50 227	93.38 247	97.85 169	96.49 298	96.70 138	98.98 299	97.78 255	90.81 283	96.19 215	98.55 227	73.63 365	98.98 205	89.41 311	98.56 158	97.88 261

StellarMVS		94.50 227	93.38 247	97.85 169	96.49 298	96.70 138	98.98 299	97.78 255	90.81 283	96.19 215	98.55 227	73.63 365	98.98 205	89.41 311	98.56 158	97.88 261

SCA		94.69 218	93.81 232	97.33 207	97.10 269	94.44 227	98.86 318	98.32 189	93.30 191	96.17 217	95.59 334	76.48 341	97.95 288	91.06 285	97.43 190	99.59 142

casdiffmvs_mvg		96.43 164	95.94 169	97.89 167	97.44 253	95.47 194	99.86 132	97.29 314	93.35 188	96.03 218	99.19 159	85.39 257	98.72 226	97.89 152	97.04 202	99.49 169
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tfpn200view9		96.79 145	95.99 161	99.19 55	98.94 131	98.82 37	99.78 159	99.71 7	92.86 206	96.02 219	98.87 195	89.33 202	99.50 170	93.84 240	94.57 254	99.27 201

thres400		96.78 147	95.99 161	99.16 62	98.94 131	98.82 37	99.78 159	99.71 7	92.86 206	96.02 219	98.87 195	89.33 202	99.50 170	93.84 240	94.57 254	99.16 209

mamv4		95.24 203	96.90 123	90.25 381	98.65 160	72.11 428	98.28 357	97.64 268	89.99 304	95.93 221	98.25 247	94.74 70	99.11 197	99.01 82	99.64 92	99.53 160

dp		95.05 207	94.43 213	96.91 217	97.99 211	92.73 275	96.29 404	97.98 233	89.70 308	95.93 221	94.67 377	93.83 107	98.45 244	86.91 347	96.53 211	99.54 156

thres100view900		96.74 150	95.92 171	99.18 56	98.90 141	98.77 42	99.74 174	99.71 7	92.59 224	95.84 223	98.86 197	89.25 204	99.50 170	93.84 240	94.57 254	99.27 201

thres600view7		96.69 153	95.87 174	99.14 66	98.90 141	98.78 41	99.74 174	99.71 7	92.59 224	95.84 223	98.86 197	89.25 204	99.50 170	93.44 253	94.50 257	99.16 209

EPP-MVSNet		96.69 153	96.60 140	96.96 216	97.74 227	93.05 267	99.37 252	98.56 105	88.75 327	95.83 225	99.01 171	96.01 36	98.56 236	96.92 183	97.20 198	99.25 203

TESTMET0.1,1		96.74 150	96.26 152	98.16 146	97.36 259	96.48 150	99.96 45	98.29 195	91.93 247	95.77 226	98.07 253	95.54 46	98.29 264	90.55 297	98.89 146	99.70 117

F-COLMAP		96.93 140	96.95 121	96.87 220	99.71 77	91.74 300	99.85 135	97.95 236	93.11 200	95.72 227	99.16 162	92.35 151	99.94 86	95.32 206	99.35 127	98.92 227

test-LLR		96.47 162	96.04 159	97.78 174	97.02 274	95.44 195	99.96 45	98.21 206	94.07 159	95.55 228	96.38 306	93.90 103	98.27 268	90.42 300	98.83 150	99.64 128

test-mter		96.39 167	95.93 170	97.78 174	97.02 274	95.44 195	99.96 45	98.21 206	91.81 252	95.55 228	96.38 306	95.17 55	98.27 268	90.42 300	98.83 150	99.64 128

IS-MVSNet		96.29 173	95.90 172	97.45 196	98.13 204	94.80 221	99.08 283	97.61 275	92.02 246	95.54 230	98.96 180	90.64 183	98.08 279	93.73 248	97.41 193	99.47 170

CHOSEN 1792x2688		96.81 144	96.53 143	97.64 184	98.91 140	93.07 265	99.65 200	99.80 3	95.64 100	95.39 231	98.86 197	84.35 268	99.90 104	96.98 179	99.16 135	99.95 76

CDS-MVSNet		96.34 169	96.07 158	97.13 211	97.37 258	94.96 215	99.53 225	97.91 242	91.55 258	95.37 232	98.32 243	95.05 60	97.13 325	93.80 244	95.75 235	99.30 196
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		94.53 225	95.30 190	92.22 358	97.77 225	82.54 404	99.59 212	97.06 339	94.92 118	95.29 233	95.37 349	85.81 252	97.89 291	94.80 219	97.07 200	96.23 289

CSCG		97.10 128	97.04 118	97.27 209	99.89 45	91.92 295	99.90 105	99.07 37	88.67 329	95.26 234	99.82 49	93.17 126	99.98 47	98.15 135	99.47 115	99.90 89

Vis-MVSNet (Re-imp)		96.32 170	95.98 163	97.35 206	97.93 215	94.82 220	99.47 236	98.15 219	91.83 250	95.09 235	99.11 163	91.37 167	97.47 306	93.47 252	97.43 190	99.74 111

TAMVS		95.85 185	95.58 182	96.65 228	97.07 271	93.50 257	99.17 276	97.82 252	91.39 268	95.02 236	98.01 254	92.20 154	97.30 315	93.75 247	95.83 232	99.14 212

XVG-OURS-SEG-HR		94.79 214	94.70 210	95.08 271	98.05 208	89.19 349	99.08 283	97.54 283	93.66 180	94.87 237	99.58 119	78.78 322	99.79 136	97.31 169	93.40 271	96.25 287

XVG-OURS		94.82 211	94.74 209	95.06 272	98.00 210	89.19 349	99.08 283	97.55 281	94.10 157	94.71 238	99.62 114	80.51 305	99.74 147	96.04 195	93.06 276	96.25 287

ab-mvs		94.69 218	93.42 243	98.51 125	98.07 207	96.26 160	96.49 399	98.68 77	90.31 297	94.54 239	97.00 287	76.30 343	99.71 151	95.98 196	93.38 272	99.56 151

TAPA-MVS	92.12 8	94.42 231	93.60 235	96.90 219	99.33 103	91.78 299	99.78 159	98.00 230	89.89 306	94.52 240	99.47 129	91.97 160	99.18 193	69.90 422	99.52 106	99.73 112
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TR-MVS		94.54 223	93.56 238	97.49 195	97.96 213	94.34 234	98.71 331	97.51 288	90.30 298	94.51 241	98.69 210	75.56 349	98.77 220	92.82 263	95.99 224	99.35 189

Fast-Effi-MVS+		95.02 208	94.19 220	97.52 193	97.88 217	94.55 226	99.97 35	97.08 337	88.85 325	94.47 242	97.96 259	84.59 265	98.41 247	89.84 309	97.10 199	99.59 142

DeepC-MVS	94.51 4	96.92 141	96.40 149	98.45 129	99.16 113	95.90 176	99.66 199	98.06 226	96.37 82	94.37 243	99.49 128	83.29 276	99.90 104	97.63 164	99.61 99	99.55 152
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RPSCF		91.80 295	92.79 260	88.83 392	98.15 202	69.87 430	98.11 366	96.60 376	83.93 387	94.33 244	99.27 151	79.60 314	99.46 179	91.99 271	93.16 274	97.18 280

WB-MVSnew		92.90 270	92.77 261	93.26 340	96.95 278	93.63 253	99.71 188	98.16 216	91.49 259	94.28 245	98.14 250	81.33 293	96.48 363	79.47 394	95.46 240	89.68 420

BH-RMVSNet		95.18 204	94.31 218	97.80 171	98.17 200	95.23 207	99.76 167	97.53 285	92.52 229	94.27 246	99.25 155	76.84 336	98.80 217	90.89 291	99.54 104	99.35 189

CVMVSNet		94.68 220	94.94 204	93.89 323	96.80 288	86.92 376	99.06 288	98.98 41	94.45 136	94.23 247	99.02 169	85.60 253	95.31 396	90.91 290	95.39 243	99.43 177

baseline1		95.78 187	94.86 205	98.54 120	98.47 177	98.07 74	99.06 288	97.99 231	92.68 218	94.13 248	98.62 219	93.28 121	98.69 230	93.79 245	85.76 324	98.84 232

Anonymous202405211		93.10 266	91.99 278	96.40 234	99.10 116	89.65 345	98.88 314	97.93 238	83.71 389	94.00 249	98.75 204	68.79 383	99.88 115	95.08 209	91.71 278	99.68 120

cascas		94.64 221	93.61 233	97.74 180	97.82 222	96.26 160	99.96 45	97.78 255	85.76 369	94.00 249	97.54 269	76.95 335	99.21 188	97.23 171	95.43 242	97.76 267

Anonymous20240529		92.10 288	90.65 300	96.47 230	98.82 146	90.61 325	98.72 330	98.67 80	75.54 420	93.90 251	98.58 223	66.23 396	99.90 104	94.70 223	90.67 282	98.90 230

LS3D		95.84 186	95.11 197	98.02 157	99.85 55	95.10 213	98.74 328	98.50 129	87.22 351	93.66 252	99.86 29	87.45 229	99.95 78	90.94 289	99.81 83	99.02 223

GeoE		94.36 235	93.48 241	96.99 215	97.29 265	93.54 256	99.96 45	96.72 371	88.35 336	93.43 253	98.94 187	82.05 282	98.05 282	88.12 329	96.48 214	99.37 183

HQP-NCC					95.78 315		99.87 121		96.82 60	93.37 254

ACMP_Plane					95.78 315		99.87 121		96.82 60	93.37 254

HQP4-MVS										93.37 254			98.39 251			94.53 295

HQP-MVS		94.61 222	94.50 212	94.92 277	95.78 315	91.85 296	99.87 121	97.89 243	96.82 60	93.37 254	98.65 214	80.65 303	98.39 251	97.92 149	89.60 284	94.53 295

MonoMVSNet		94.82 211	94.43 213	95.98 245	94.54 348	90.73 321	99.03 295	97.06 339	93.16 196	93.15 258	95.47 342	88.29 216	97.57 302	97.85 153	91.33 281	99.62 135

HQP_MVS		94.49 229	94.36 215	94.87 278	95.71 325	91.74 300	99.84 140	97.87 245	96.38 79	93.01 259	98.59 220	80.47 307	98.37 257	97.79 158	89.55 287	94.52 297

plane_prior3						91.64 306			96.63 69	93.01 259

GA-MVS		93.83 244	92.84 257	96.80 221	95.73 322	93.57 254	99.88 118	97.24 319	92.57 226	92.92 261	96.66 298	78.73 323	97.67 299	87.75 332	94.06 263	99.17 208

tpm cat1		93.51 256	92.52 270	96.47 230	97.77 225	91.47 310	96.13 406	98.06 226	80.98 405	92.91 262	93.78 391	89.66 196	98.87 212	87.03 343	96.39 216	99.09 216

1112_ss		96.01 181	95.20 194	98.42 133	97.80 223	96.41 153	99.65 200	96.66 373	92.71 215	92.88 263	99.40 138	92.16 155	99.30 183	91.92 273	93.66 267	99.55 152

Test_1112_low_res		95.72 188	94.83 206	98.42 133	97.79 224	96.41 153	99.65 200	96.65 374	92.70 216	92.86 264	96.13 317	92.15 156	99.30 183	91.88 274	93.64 268	99.55 152

IB-MVS	92.85 6	94.99 209	93.94 228	98.16 146	97.72 232	95.69 187	99.99 5	98.81 64	94.28 151	92.70 265	96.90 289	95.08 58	99.17 194	96.07 194	73.88 407	99.60 141
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
Fast-Effi-MVS+-dtu		93.72 251	93.86 231	93.29 338	97.06 272	86.16 379	99.80 156	96.83 363	92.66 219	92.58 266	97.83 265	81.39 291	97.67 299	89.75 310	96.87 207	96.05 292

SDMVSNet		94.80 213	93.96 227	97.33 207	98.92 136	95.42 197	99.59 212	98.99 40	92.41 233	92.55 267	97.85 263	75.81 348	98.93 211	97.90 151	91.62 279	97.64 269

sd_testset		93.55 255	92.83 258	95.74 254	98.92 136	90.89 319	98.24 359	98.85 59	92.41 233	92.55 267	97.85 263	71.07 378	98.68 231	93.93 237	91.62 279	97.64 269

dmvs_re		93.20 262	93.15 253	93.34 336	96.54 297	83.81 394	98.71 331	98.51 123	91.39 268	92.37 269	98.56 225	78.66 324	97.83 293	93.89 238	89.74 283	98.38 249

tpmvs		94.28 237	93.57 237	96.40 234	98.55 167	91.50 309	95.70 414	98.55 111	87.47 346	92.15 270	94.26 387	91.42 165	98.95 210	88.15 327	95.85 231	98.76 236

Syy-MVS		90.00 335	90.63 301	88.11 399	97.68 236	74.66 426	99.71 188	98.35 182	90.79 285	92.10 271	98.67 211	79.10 320	93.09 419	63.35 433	95.95 228	96.59 285

myMVS_eth3d		94.46 230	94.76 208	93.55 333	97.68 236	90.97 314	99.71 188	98.35 182	90.79 285	92.10 271	98.67 211	92.46 149	93.09 419	87.13 340	95.95 228	96.59 285

BH-w/o		95.71 190	95.38 187	96.68 226	98.49 176	92.28 286	99.84 140	97.50 289	92.12 241	92.06 273	98.79 202	84.69 264	98.67 232	95.29 207	99.66 91	99.09 216

VPA-MVSNet		92.70 275	91.55 287	96.16 241	95.09 338	96.20 166	98.88 314	99.00 39	91.02 278	91.82 274	95.29 355	76.05 347	97.96 287	95.62 204	81.19 361	94.30 314

baseline2		96.71 152	96.49 144	97.37 203	95.63 331	95.96 175	99.74 174	98.88 54	92.94 203	91.61 275	98.97 178	97.72 6	98.62 234	94.83 218	98.08 179	97.53 276

OPM-MVS		93.21 261	92.80 259	94.44 300	93.12 374	90.85 320	99.77 162	97.61 275	96.19 87	91.56 276	98.65 214	75.16 356	98.47 240	93.78 246	89.39 290	93.99 347
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EI-MVSNet		93.73 250	93.40 246	94.74 283	96.80 288	92.69 276	99.06 288	97.67 264	88.96 320	91.39 277	99.02 169	88.75 213	97.30 315	91.07 284	87.85 311	94.22 321

MVSTER		95.53 196	95.22 193	96.45 232	98.56 164	97.72 91	99.91 99	97.67 264	92.38 235	91.39 277	97.14 279	97.24 18	97.30 315	94.80 219	87.85 311	94.34 313

testing3		93.92 242	94.23 219	92.99 347	97.54 247	90.23 333	99.99 5	99.16 33	90.57 290	91.33 279	98.63 218	92.99 129	92.52 423	82.46 377	95.39 243	96.22 290

test_fmvs2		89.47 344	89.70 320	88.77 395	94.54 348	75.74 423	99.83 147	94.70 419	94.71 127	91.08 280	96.82 297	54.46 423	97.78 296	92.87 262	88.27 306	92.80 388

BH-untuned		95.18 204	94.83 206	96.22 240	98.36 184	91.22 312	99.80 156	97.32 309	90.91 279	91.08 280	98.67 211	83.51 273	98.54 238	94.23 234	99.61 99	98.92 227

CLD-MVS		94.06 241	93.90 229	94.55 293	96.02 309	90.69 322	99.98 17	97.72 260	96.62 71	91.05 282	98.85 200	77.21 330	98.47 240	98.11 137	89.51 289	94.48 299
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS		96.60 157	95.56 183	99.72 13	96.85 285	99.22 20	98.31 355	98.94 44	91.57 257	90.90 283	99.61 115	86.66 242	99.96 69	97.36 168	99.88 73	99.99 23

MSDG		94.37 233	93.36 249	97.40 201	98.88 143	93.95 245	99.37 252	97.38 300	85.75 371	90.80 284	99.17 161	84.11 271	99.88 115	86.35 348	98.43 163	98.36 250

VPNet		91.81 292	90.46 303	95.85 251	94.74 344	95.54 193	98.98 299	98.59 96	92.14 240	90.77 285	97.44 271	68.73 385	97.54 304	94.89 217	77.89 387	94.46 300

MIMVSNet		90.30 327	88.67 341	95.17 270	96.45 300	91.64 306	92.39 425	97.15 328	85.99 366	90.50 286	93.19 399	66.95 393	94.86 403	82.01 381	93.43 270	99.01 224

mvs_anonymous		95.65 194	95.03 201	97.53 192	98.19 198	95.74 182	99.33 257	97.49 290	90.87 280	90.47 287	97.10 281	88.23 217	97.16 322	95.92 197	97.66 187	99.68 120

Patchmatch-test		92.65 278	91.50 288	96.10 243	96.85 285	90.49 328	91.50 429	97.19 321	82.76 398	90.23 288	95.59 334	95.02 61	98.00 284	77.41 405	96.98 205	99.82 99

LPG-MVS_test		92.96 268	92.71 262	93.71 327	95.43 334	88.67 357	99.75 171	97.62 272	92.81 209	90.05 289	98.49 231	75.24 352	98.40 249	95.84 199	89.12 291	94.07 339

LGP-MVS_train				93.71 327	95.43 334	88.67 357		97.62 272	92.81 209	90.05 289	98.49 231	75.24 352	98.40 249	95.84 199	89.12 291	94.07 339

DP-MVS		94.54 223	93.42 243	97.91 165	99.46 99	94.04 241	98.93 308	97.48 291	81.15 404	90.04 291	99.55 123	87.02 236	99.95 78	88.97 317	98.11 176	99.73 112

test_djsdf		92.83 272	92.29 273	94.47 298	91.90 398	92.46 283	99.55 222	97.27 316	91.17 271	89.96 292	96.07 320	81.10 295	96.89 344	94.67 224	88.91 293	94.05 341

ACMM	91.95 10	92.88 271	92.52 270	93.98 319	95.75 321	89.08 353	99.77 162	97.52 287	93.00 201	89.95 293	97.99 257	76.17 345	98.46 243	93.63 251	88.87 295	94.39 307
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
1314		96.84 143	95.96 167	99.48 34	96.74 293	98.52 58	98.31 355	98.86 56	95.82 94	89.91 294	98.98 176	87.49 228	99.96 69	97.80 155	99.73 87	99.96 69

XVG-ACMP-BASELINE		91.22 307	90.75 298	92.63 354	93.73 363	85.61 383	98.52 345	97.44 293	92.77 213	89.90 295	96.85 293	66.64 395	98.39 251	92.29 267	88.61 300	93.89 355

miper_enhance_ethall		94.36 235	93.98 226	95.49 257	98.68 155	95.24 206	99.73 181	97.29 314	93.28 192	89.86 296	95.97 322	94.37 85	97.05 331	92.20 268	84.45 337	94.19 324

nrg030		93.51 256	92.53 269	96.45 232	94.36 351	97.20 116	99.81 152	97.16 327	91.60 256	89.86 296	97.46 270	86.37 245	97.68 298	95.88 198	80.31 374	94.46 300

V42		91.28 304	90.12 315	94.74 283	93.42 369	93.46 258	99.68 196	97.02 343	87.36 348	89.85 298	95.05 363	81.31 294	97.34 310	87.34 337	80.07 376	93.40 373

v144192		90.79 315	89.52 325	94.59 290	93.11 375	92.77 271	99.56 219	96.99 346	86.38 362	89.82 299	94.95 370	80.50 306	97.10 328	83.98 367	80.41 372	93.90 354

GBi-Net		90.88 312	89.82 318	94.08 312	97.53 248	91.97 291	98.43 349	96.95 351	87.05 352	89.68 300	94.72 373	71.34 374	96.11 377	87.01 344	85.65 325	94.17 325

test1		90.88 312	89.82 318	94.08 312	97.53 248	91.97 291	98.43 349	96.95 351	87.05 352	89.68 300	94.72 373	71.34 374	96.11 377	87.01 344	85.65 325	94.17 325

FMVSNet3		92.69 276	91.58 285	95.99 244	98.29 189	97.42 108	99.26 269	97.62 272	89.80 307	89.68 300	95.32 351	81.62 290	96.27 372	87.01 344	85.65 325	94.29 315

IterMVS-LS		92.69 276	92.11 275	94.43 302	96.80 288	92.74 273	99.45 241	96.89 359	88.98 318	89.65 303	95.38 348	88.77 212	96.34 369	90.98 288	82.04 355	94.22 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		94.52 226	94.03 224	95.98 245	98.38 181	96.68 141	99.92 91	97.63 269	90.75 288	89.64 304	95.25 357	96.77 25	96.90 343	94.35 231	83.57 344	94.35 311

v1144		91.09 308	89.83 317	94.87 278	93.25 371	93.69 252	99.62 207	96.98 348	86.83 358	89.64 304	94.99 368	80.94 297	97.05 331	85.08 360	81.16 362	93.87 357

v1921920		90.46 322	89.12 332	94.50 296	92.96 379	92.46 283	99.49 232	96.98 348	86.10 365	89.61 306	95.30 352	78.55 326	97.03 336	82.17 380	80.89 370	94.01 344

VortexMVS		94.11 239	93.50 240	95.94 247	97.70 235	96.61 145	99.35 255	97.18 323	93.52 184	89.57 307	95.74 326	87.55 226	96.97 339	95.76 202	85.13 332	94.23 320

v1192		90.62 320	89.25 330	94.72 285	93.13 372	93.07 265	99.50 230	97.02 343	86.33 363	89.56 308	95.01 365	79.22 317	97.09 330	82.34 379	81.16 362	94.01 344

PCF-MVS	94.20 5	95.18 204	94.10 222	98.43 131	98.55 167	95.99 174	97.91 372	97.31 310	90.35 295	89.48 309	99.22 157	85.19 259	99.89 109	90.40 302	98.47 162	99.41 179
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
3Dnovator	91.47 12	96.28 174	95.34 188	99.08 75	96.82 287	97.47 106	99.45 241	98.81 64	95.52 105	89.39 310	99.00 173	81.97 283	99.95 78	97.27 170	99.83 77	99.84 97

v1240		90.20 330	88.79 339	94.44 300	93.05 377	92.27 287	99.38 250	96.92 357	85.89 367	89.36 311	94.87 372	77.89 329	97.03 336	80.66 388	81.08 365	94.01 344

FIs		94.10 240	93.43 242	96.11 242	94.70 345	96.82 134	99.58 214	98.93 48	92.54 227	89.34 312	97.31 275	87.62 224	97.10 328	94.22 235	86.58 320	94.40 306

ITE_SJBPF				92.38 355	95.69 328	85.14 386		95.71 397	92.81 209	89.33 313	98.11 251	70.23 380	98.42 246	85.91 354	88.16 308	93.59 370

v2v482		91.30 302	90.07 316	95.01 273	93.13 372	93.79 247	99.77 162	97.02 343	88.05 339	89.25 314	95.37 349	80.73 301	97.15 323	87.28 338	80.04 377	94.09 338

UniMVSNet (Re)		93.07 267	92.13 274	95.88 249	94.84 342	96.24 165	99.88 118	98.98 41	92.49 231	89.25 314	95.40 345	87.09 235	97.14 324	93.13 259	78.16 385	94.26 316

tt0805		91.28 304	90.18 312	94.60 289	96.26 303	87.55 369	98.39 353	98.72 72	89.00 317	89.22 316	98.47 235	62.98 409	98.96 209	90.57 296	88.00 310	97.28 279

UniMVSNet_NR-MVSNet		92.95 269	92.11 275	95.49 257	94.61 347	95.28 204	99.83 147	99.08 36	91.49 259	89.21 317	96.86 292	87.14 234	96.73 354	93.20 255	77.52 390	94.46 300

DU-MVS		92.46 281	91.45 290	95.49 257	94.05 357	95.28 204	99.81 152	98.74 71	92.25 239	89.21 317	96.64 300	81.66 288	96.73 354	93.20 255	77.52 390	94.46 300

eth_miper_zixun_eth		92.41 282	91.93 279	93.84 324	97.28 266	90.68 323	98.83 321	96.97 350	88.57 332	89.19 319	95.73 329	89.24 206	96.69 356	89.97 308	81.55 358	94.15 331

cl22		93.77 248	93.25 252	95.33 265	99.49 96	94.43 228	99.61 209	98.09 223	90.38 293	89.16 320	95.61 332	90.56 185	97.34 310	91.93 272	84.45 337	94.21 323

Baseline_NR-MVSNet		90.33 326	89.51 326	92.81 351	92.84 382	89.95 341	99.77 162	93.94 426	84.69 383	89.04 321	95.66 331	81.66 288	96.52 361	90.99 287	76.98 396	91.97 399

FC-MVSNet-test		93.81 246	93.15 253	95.80 253	94.30 353	96.20 166	99.42 243	98.89 52	92.33 237	89.03 322	97.27 277	87.39 230	96.83 350	93.20 255	86.48 321	94.36 308

QAPM		95.40 199	94.17 221	99.10 72	96.92 279	97.71 92	99.40 244	98.68 77	89.31 311	88.94 323	98.89 191	82.48 280	99.96 69	93.12 260	99.83 77	99.62 135

miper_ehance_all_eth		93.16 264	92.60 264	94.82 282	97.57 245	93.56 255	99.50 230	97.07 338	88.75 327	88.85 324	95.52 338	90.97 176	96.74 353	90.77 293	84.45 337	94.17 325

AllTest		92.48 280	91.64 283	95.00 274	99.01 121	88.43 361	98.94 306	96.82 365	86.50 360	88.71 325	98.47 235	74.73 358	99.88 115	85.39 356	96.18 220	96.71 283

TestCases				95.00 274	99.01 121	88.43 361		96.82 365	86.50 360	88.71 325	98.47 235	74.73 358	99.88 115	85.39 356	96.18 220	96.71 283

c3_l		92.53 279	91.87 281	94.52 294	97.40 256	92.99 269	99.40 244	96.93 356	87.86 342	88.69 327	95.44 343	89.95 194	96.44 365	90.45 299	80.69 371	94.14 334

pmmvs4		92.10 288	91.07 296	95.18 269	92.82 384	94.96 215	99.48 235	96.83 363	87.45 347	88.66 328	96.56 304	83.78 272	96.83 350	89.29 314	84.77 335	93.75 363

SSC-MVS3.2		89.59 342	88.66 342	92.38 355	94.29 354	86.12 380	99.49 232	97.66 267	90.28 299	88.63 329	95.18 359	64.46 403	96.88 346	85.30 358	82.66 349	94.14 334

kuosan		93.17 263	92.60 264	94.86 281	98.40 180	89.54 347	98.44 348	98.53 118	84.46 384	88.49 330	97.92 260	90.57 184	97.05 331	83.10 373	93.49 269	97.99 259

PS-MVSNAJss		93.64 253	93.31 250	94.61 288	92.11 395	92.19 288	99.12 278	97.38 300	92.51 230	88.45 331	96.99 288	91.20 169	97.29 318	94.36 229	87.71 313	94.36 308

UniMVSNet_ETH3D		90.06 334	88.58 343	94.49 297	94.67 346	88.09 366	97.81 375	97.57 280	83.91 388	88.44 332	97.41 272	57.44 420	97.62 301	91.41 279	88.59 302	97.77 266

TranMVSNet+NR-MVSNet		91.68 299	90.61 302	94.87 278	93.69 364	93.98 244	99.69 194	98.65 81	91.03 277	88.44 332	96.83 296	80.05 311	96.18 375	90.26 304	76.89 398	94.45 305

FMVSNet2		91.02 309	89.56 323	95.41 262	97.53 248	95.74 182	98.98 299	97.41 298	87.05 352	88.43 334	95.00 367	71.34 374	96.24 374	85.12 359	85.21 330	94.25 318

COLMAP_ROB	90.47 14	92.18 287	91.49 289	94.25 308	99.00 125	88.04 367	98.42 352	96.70 372	82.30 400	88.43 334	99.01 171	76.97 334	99.85 121	86.11 352	96.50 212	94.86 294
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
3Dnovator+	91.53 11	96.31 171	95.24 192	99.52 28	96.88 284	98.64 54	99.72 185	98.24 202	95.27 111	88.42 336	98.98 176	82.76 279	99.94 86	97.10 175	99.83 77	99.96 69

v148		90.70 316	89.63 321	93.92 320	92.97 378	90.97 314	99.75 171	96.89 359	87.51 345	88.27 337	95.01 365	81.67 287	97.04 334	87.40 336	77.17 395	93.75 363

DSMNet-mixed		88.28 354	88.24 348	88.42 397	89.64 418	75.38 425	98.06 368	89.86 440	85.59 373	88.20 338	92.14 408	76.15 346	91.95 426	78.46 401	96.05 223	97.92 260

WR-MVS		92.31 284	91.25 292	95.48 260	94.45 350	95.29 203	99.60 211	98.68 77	90.10 300	88.07 339	96.89 290	80.68 302	96.80 352	93.14 258	79.67 378	94.36 308

test0.0.03 1		93.86 243	93.61 233	94.64 287	95.02 341	92.18 289	99.93 88	98.58 98	94.07 159	87.96 340	98.50 230	93.90 103	94.96 400	81.33 384	93.17 273	96.78 282

XXY-MVS		91.82 291	90.46 303	95.88 249	93.91 360	95.40 199	98.87 317	97.69 263	88.63 331	87.87 341	97.08 282	74.38 361	97.89 291	91.66 276	84.07 341	94.35 311

reproduce_monomvs		95.38 200	95.07 199	96.32 238	99.32 105	96.60 146	99.76 167	98.85 59	96.65 68	87.83 342	96.05 321	99.52 1	98.11 277	96.58 188	81.07 366	94.25 318

Patchmtry		89.70 340	88.49 344	93.33 337	96.24 304	89.94 343	91.37 430	96.23 385	78.22 413	87.69 343	93.31 397	91.04 174	96.03 382	80.18 393	82.10 354	94.02 342

DIV-MVS_self_test		92.32 283	91.60 284	94.47 298	97.31 263	92.74 273	99.58 214	96.75 369	86.99 355	87.64 344	95.54 336	89.55 199	96.50 362	88.58 321	82.44 352	94.17 325

D2MVS		92.76 273	92.59 268	93.27 339	95.13 337	89.54 347	99.69 194	99.38 22	92.26 238	87.59 345	94.61 379	85.05 261	97.79 294	91.59 277	88.01 309	92.47 393

cl____		92.31 284	91.58 285	94.52 294	97.33 262	92.77 271	99.57 217	96.78 368	86.97 356	87.56 346	95.51 339	89.43 200	96.62 358	88.60 320	82.44 352	94.16 330

v8		90.54 321	89.17 331	94.66 286	93.43 368	93.40 261	99.20 273	96.94 355	85.76 369	87.56 346	94.51 380	81.96 284	97.19 321	84.94 361	78.25 384	93.38 375

miper_lstm_enhance		91.81 292	91.39 291	93.06 346	97.34 260	89.18 351	99.38 250	96.79 367	86.70 359	87.47 348	95.22 358	90.00 193	95.86 386	88.26 325	81.37 360	94.15 331

anonymousdsp		91.79 297	90.92 297	94.41 303	90.76 410	92.93 270	98.93 308	97.17 325	89.08 313	87.46 349	95.30 352	78.43 328	96.92 342	92.38 266	88.73 298	93.39 374

jajsoiax		91.92 290	91.18 293	94.15 309	91.35 405	90.95 317	99.00 298	97.42 296	92.61 222	87.38 350	97.08 282	72.46 369	97.36 308	94.53 227	88.77 297	94.13 336

mvs_tets		91.81 292	91.08 295	94.00 317	91.63 402	90.58 326	98.67 336	97.43 294	92.43 232	87.37 351	97.05 285	71.76 371	97.32 313	94.75 221	88.68 299	94.11 337

v10		90.25 329	88.82 338	94.57 292	93.53 366	93.43 259	99.08 283	96.87 361	85.00 378	87.34 352	94.51 380	80.93 298	97.02 338	82.85 375	79.23 379	93.26 377

pmmvs5		90.17 332	89.09 333	93.40 335	92.10 396	89.77 344	99.74 174	95.58 401	85.88 368	87.24 353	95.74 326	73.41 367	96.48 363	88.54 322	83.56 345	93.95 350

ACMP	92.05 9	92.74 274	92.42 272	93.73 325	95.91 313	88.72 356	99.81 152	97.53 285	94.13 155	87.00 354	98.23 248	74.07 362	98.47 240	96.22 193	88.86 296	93.99 347
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS-HIRNet		86.22 364	83.19 377	95.31 266	96.71 295	90.29 332	92.12 426	97.33 308	62.85 434	86.82 355	70.37 439	69.37 382	97.49 305	75.12 413	97.99 181	98.15 254

Anonymous20231211		89.86 337	88.44 345	94.13 311	98.93 133	90.68 323	98.54 343	98.26 199	76.28 416	86.73 356	95.54 336	70.60 379	97.56 303	90.82 292	80.27 375	94.15 331

v7n		89.65 341	88.29 347	93.72 326	92.22 393	90.56 327	99.07 287	97.10 333	85.42 376	86.73 356	94.72 373	80.06 310	97.13 325	81.14 385	78.12 386	93.49 371

IterMVS-SCA-FT		90.85 314	90.16 314	92.93 348	96.72 294	89.96 340	98.89 312	96.99 346	88.95 321	86.63 358	95.67 330	76.48 341	95.00 399	87.04 342	84.04 343	93.84 359

EU-MVSNet		90.14 333	90.34 307	89.54 387	92.55 388	81.06 415	98.69 334	98.04 229	91.41 267	86.59 359	96.84 295	80.83 300	93.31 418	86.20 350	81.91 356	94.26 316

OpenMVS	90.15 15	94.77 216	93.59 236	98.33 137	96.07 307	97.48 105	99.56 219	98.57 100	90.46 292	86.51 360	98.95 185	78.57 325	99.94 86	93.86 239	99.74 86	97.57 274

IterMVS		90.91 311	90.17 313	93.12 343	96.78 292	90.42 331	98.89 312	97.05 342	89.03 315	86.49 361	95.42 344	76.59 339	95.02 398	87.22 339	84.09 340	93.93 352
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WR-MVS_H		91.30 302	90.35 306	94.15 309	94.17 356	92.62 280	99.17 276	98.94 44	88.87 324	86.48 362	94.46 384	84.36 267	96.61 359	88.19 326	78.51 383	93.21 379

MS-PatchMatch		90.65 317	90.30 308	91.71 366	94.22 355	85.50 385	98.24 359	97.70 261	88.67 329	86.42 363	96.37 308	67.82 390	98.03 283	83.62 370	99.62 95	91.60 401

CP-MVSNet		91.23 306	90.22 310	94.26 307	93.96 359	92.39 285	99.09 281	98.57 100	88.95 321	86.42 363	96.57 303	79.19 318	96.37 367	90.29 303	78.95 380	94.02 342

LF4IMVS		89.25 348	88.85 337	90.45 380	92.81 385	81.19 414	98.12 365	94.79 415	91.44 263	86.29 365	97.11 280	65.30 401	98.11 277	88.53 323	85.25 329	92.07 396

PVSNet_0	88.03 19	91.80 295	90.27 309	96.38 236	98.27 192	90.46 329	99.94 81	99.61 13	93.99 164	86.26 366	97.39 274	71.13 377	99.89 109	98.77 98	67.05 425	98.79 235

PS-CasMVS		90.63 319	89.51 326	93.99 318	93.83 361	91.70 304	98.98 299	98.52 120	88.48 333	86.15 367	96.53 305	75.46 350	96.31 371	88.83 318	78.86 382	93.95 350

FMVSNet1		88.50 352	86.64 359	94.08 312	95.62 332	91.97 291	98.43 349	96.95 351	83.00 395	86.08 368	94.72 373	59.09 418	96.11 377	81.82 383	84.07 341	94.17 325

PEN-MVS		90.19 331	89.06 334	93.57 332	93.06 376	90.90 318	99.06 288	98.47 132	88.11 338	85.91 369	96.30 310	76.67 337	95.94 385	87.07 341	76.91 397	93.89 355

ppachtmachnet_test		89.58 343	88.35 346	93.25 341	92.40 391	90.44 330	99.33 257	96.73 370	85.49 374	85.90 370	95.77 325	81.09 296	96.00 384	76.00 412	82.49 351	93.30 376

OurMVSNet-221017-0		89.81 338	89.48 328	90.83 373	91.64 401	81.21 413	98.17 364	95.38 406	91.48 261	85.65 371	97.31 275	72.66 368	97.29 318	88.15 327	84.83 334	93.97 349

sc_t1		85.01 373	82.46 383	92.67 353	92.44 390	83.09 400	97.39 380	95.72 396	65.06 431	85.64 372	96.16 314	49.50 430	97.34 310	84.86 362	75.39 404	97.57 274

our_test_3		90.39 323	89.48 328	93.12 343	92.40 391	89.57 346	99.33 257	96.35 384	87.84 343	85.30 373	94.99 368	84.14 270	96.09 380	80.38 390	84.56 336	93.71 368

testgi		89.01 349	88.04 350	91.90 362	93.49 367	84.89 389	99.73 181	95.66 399	93.89 173	85.14 374	98.17 249	59.68 417	94.66 406	77.73 404	88.88 294	96.16 291

DTE-MVSNet		89.40 345	88.24 348	92.88 349	92.66 387	89.95 341	99.10 280	98.22 205	87.29 349	85.12 375	96.22 312	76.27 344	95.30 397	83.56 371	75.74 402	93.41 372

mvs5depth		84.87 374	82.90 380	90.77 374	85.59 428	84.84 390	91.10 432	93.29 431	83.14 393	85.07 376	94.33 386	62.17 411	97.32 313	78.83 400	72.59 411	90.14 415

dongtai		91.55 301	91.13 294	92.82 350	98.16 201	86.35 378	99.47 236	98.51 123	83.24 392	85.07 376	97.56 268	90.33 189	94.94 401	76.09 411	91.73 277	97.18 280

FMVSNet5		88.32 353	87.47 355	90.88 370	96.90 283	88.39 363	97.28 382	95.68 398	82.60 399	84.67 378	92.40 406	79.83 312	91.16 428	76.39 410	81.51 359	93.09 381

tfpnnormal		89.29 347	87.61 354	94.34 305	94.35 352	94.13 240	98.95 305	98.94 44	83.94 386	84.47 379	95.51 339	74.84 357	97.39 307	77.05 408	80.41 372	91.48 403

MVP-Stereo		90.93 310	90.45 305	92.37 357	91.25 407	88.76 354	98.05 369	96.17 387	87.27 350	84.04 380	95.30 352	78.46 327	97.27 320	83.78 369	99.70 89	91.09 404
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ttmdpeth		88.23 355	87.06 358	91.75 365	89.91 417	87.35 372	98.92 311	95.73 395	87.92 341	84.02 381	96.31 309	68.23 389	96.84 348	86.33 349	76.12 400	91.06 405

LTVRE_ROB	88.28 18	90.29 328	89.05 335	94.02 315	95.08 339	90.15 336	97.19 384	97.43 294	84.91 381	83.99 382	97.06 284	74.00 363	98.28 266	84.08 365	87.71 313	93.62 369
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
pm-mvs1		89.36 346	87.81 352	94.01 316	93.40 370	91.93 294	98.62 339	96.48 381	86.25 364	83.86 383	96.14 316	73.68 364	97.04 334	86.16 351	75.73 403	93.04 383

USDC		90.00 335	88.96 336	93.10 345	94.81 343	88.16 365	98.71 331	95.54 402	93.66 180	83.75 384	97.20 278	65.58 398	98.31 262	83.96 368	87.49 317	92.85 387

CL-MVSNet_self_test		84.50 378	83.15 378	88.53 396	86.00 426	81.79 410	98.82 322	97.35 304	85.12 377	83.62 385	90.91 413	76.66 338	91.40 427	69.53 423	60.36 436	92.40 394

ACMH+	89.98 16	90.35 325	89.54 324	92.78 352	95.99 310	86.12 380	98.81 323	97.18 323	89.38 310	83.14 386	97.76 266	68.42 387	98.43 245	89.11 316	86.05 323	93.78 362

Anonymous20231206		86.32 363	85.42 366	89.02 391	89.11 420	80.53 419	99.05 292	95.28 407	85.43 375	82.82 387	93.92 389	74.40 360	93.44 417	66.99 427	81.83 357	93.08 382

KD-MVS_self_test		83.59 384	82.06 384	88.20 398	86.93 424	80.70 417	97.21 383	96.38 382	82.87 396	82.49 388	88.97 420	67.63 391	92.32 424	73.75 416	62.30 435	91.58 402

SixPastTwentyTwo		88.73 350	88.01 351	90.88 370	91.85 399	82.24 406	98.22 362	95.18 411	88.97 319	82.26 389	96.89 290	71.75 372	96.67 357	84.00 366	82.98 346	93.72 367

KD-MVS_2432*1600		88.00 357	86.10 361	93.70 329	96.91 280	94.04 241	97.17 385	97.12 331	84.93 379	81.96 390	92.41 404	92.48 147	94.51 407	79.23 395	52.68 439	92.56 390

miper_refine_blended		88.00 357	86.10 361	93.70 329	96.91 280	94.04 241	97.17 385	97.12 331	84.93 379	81.96 390	92.41 404	92.48 147	94.51 407	79.23 395	52.68 439	92.56 390

TinyColmap		87.87 359	86.51 360	91.94 361	95.05 340	85.57 384	97.65 376	94.08 423	84.40 385	81.82 392	96.85 293	62.14 412	98.33 260	80.25 392	86.37 322	91.91 400

ACMH	89.72 17	90.64 318	89.63 321	93.66 331	95.64 330	88.64 359	98.55 341	97.45 292	89.03 315	81.62 393	97.61 267	69.75 381	98.41 247	89.37 313	87.62 315	93.92 353
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		85.15 371	83.81 373	89.16 390	88.32 421	82.69 402	98.80 325	95.74 394	79.72 409	81.53 394	90.99 411	65.38 400	94.16 409	72.69 417	81.11 364	90.63 411

tt0320		83.56 385	81.15 388	90.77 374	92.77 386	83.58 396	96.83 395	95.52 403	63.26 432	81.36 395	92.54 402	53.26 425	95.77 387	80.45 389	74.38 406	92.96 384

pmmvs6		85.69 365	83.84 372	91.26 369	90.00 416	84.41 392	97.82 374	96.15 388	75.86 418	81.29 396	95.39 347	61.21 415	96.87 347	83.52 372	73.29 408	92.50 392

TransMVSNet (Re)		87.25 360	85.28 367	93.16 342	93.56 365	91.03 313	98.54 343	94.05 425	83.69 390	81.09 397	96.16 314	75.32 351	96.40 366	76.69 409	68.41 421	92.06 397

test_method		80.79 391	79.70 395	84.08 406	92.83 383	67.06 432	99.51 228	95.42 404	54.34 438	81.07 398	93.53 394	44.48 434	92.22 425	78.90 399	77.23 394	92.94 385

NR-MVSNet		91.56 300	90.22 310	95.60 255	94.05 357	95.76 181	98.25 358	98.70 74	91.16 273	80.78 399	96.64 300	83.23 277	96.57 360	91.41 279	77.73 389	94.46 300

LCM-MVSNet-Re		92.31 284	92.60 264	91.43 367	97.53 248	79.27 421	99.02 297	91.83 436	92.07 242	80.31 400	94.38 385	83.50 274	95.48 391	97.22 172	97.58 188	99.54 156

TDRefinement		84.76 375	82.56 382	91.38 368	74.58 443	84.80 391	97.36 381	94.56 420	84.73 382	80.21 401	96.12 319	63.56 406	98.39 251	87.92 330	63.97 431	90.95 408

N_pmnet		80.06 394	80.78 391	77.89 413	91.94 397	45.28 451	98.80 325	56.82 453	78.10 414	80.08 402	93.33 395	77.03 332	95.76 388	68.14 426	82.81 347	92.64 389

test_fmvs3		79.99 395	80.17 394	79.45 412	84.02 431	62.83 433	99.05 292	93.49 430	88.29 337	80.06 403	86.65 429	28.09 441	88.00 433	88.63 319	73.27 409	87.54 429

tt0320-xc		82.94 386	80.35 393	90.72 376	92.90 381	83.54 397	96.85 394	94.73 417	63.12 433	79.85 404	93.77 392	49.43 431	95.46 392	80.98 387	71.54 412	93.16 380

test_0402		85.58 366	83.94 371	90.50 378	93.81 362	85.04 387	98.55 341	95.20 410	76.01 417	79.72 405	95.13 360	64.15 405	96.26 373	66.04 431	86.88 319	90.21 414

test20.03		84.72 377	83.99 369	86.91 401	88.19 423	80.62 418	98.88 314	95.94 391	88.36 335	78.87 406	94.62 378	68.75 384	89.11 432	66.52 429	75.82 401	91.00 406

pmmvs3		80.27 393	77.77 398	87.76 400	80.32 438	82.43 405	98.23 361	91.97 435	72.74 427	78.75 407	87.97 425	57.30 421	90.99 429	70.31 421	62.37 434	89.87 418

dmvs_testset		83.79 382	86.07 363	76.94 414	92.14 394	48.60 449	96.75 396	90.27 439	89.48 309	78.65 408	98.55 227	79.25 316	86.65 437	66.85 428	82.69 348	95.57 293

MIMVSNet1		82.58 387	80.51 392	88.78 393	86.68 425	84.20 393	96.65 397	95.41 405	78.75 412	78.59 409	92.44 403	51.88 428	89.76 431	65.26 432	78.95 380	92.38 395

DeepMVS_CX				82.92 409	95.98 312	58.66 440		96.01 390	92.72 214	78.34 410	95.51 339	58.29 419	98.08 279	82.57 376	85.29 328	92.03 398

test_vis1_rt		86.87 362	86.05 364	89.34 388	96.12 305	78.07 422	99.87 121	83.54 447	92.03 245	78.21 411	89.51 418	45.80 433	99.91 102	96.25 192	93.11 275	90.03 417

mvsany_test3		82.12 388	81.14 389	85.06 405	81.87 434	70.41 429	97.09 387	92.14 434	91.27 270	77.84 412	88.73 421	39.31 436	95.49 390	90.75 294	71.24 413	89.29 425

Patchmatch-RL test		86.90 361	85.98 365	89.67 386	84.45 429	75.59 424	89.71 435	92.43 433	86.89 357	77.83 413	90.94 412	94.22 92	93.63 415	87.75 332	69.61 416	99.79 104

APD_test1		81.15 390	80.92 390	81.86 410	92.45 389	59.76 439	96.04 409	93.61 429	73.29 426	77.06 414	96.64 300	44.28 435	96.16 376	72.35 418	82.52 350	89.67 421

lessismore_v0				90.53 377	90.58 411	80.90 416		95.80 393		77.01 415	95.84 323	66.15 397	96.95 340	83.03 374	75.05 405	93.74 366

K. test v3		88.05 356	87.24 357	90.47 379	91.82 400	82.23 407	98.96 304	97.42 296	89.05 314	76.93 416	95.60 333	68.49 386	95.42 393	85.87 355	81.01 368	93.75 363

ambc				83.23 408	77.17 441	62.61 434	87.38 437	94.55 421		76.72 417	86.65 429	30.16 438	96.36 368	84.85 363	69.86 415	90.73 409

PM-MVS		80.47 392	78.88 397	85.26 404	83.79 432	72.22 427	95.89 412	91.08 437	85.71 372	76.56 418	88.30 422	36.64 437	93.90 412	82.39 378	69.57 417	89.66 422

OpenMVS_ROB	79.82 20	83.77 383	81.68 386	90.03 384	88.30 422	82.82 401	98.46 346	95.22 409	73.92 425	76.00 419	91.29 410	55.00 422	96.94 341	68.40 425	88.51 304	90.34 412

UnsupCasMVSNet_eth		85.52 367	83.99 369	90.10 383	89.36 419	83.51 398	96.65 397	97.99 231	89.14 312	75.89 420	93.83 390	63.25 408	93.92 411	81.92 382	67.90 424	92.88 386

new_pmnet		84.49 379	82.92 379	89.21 389	90.03 415	82.60 403	96.89 393	95.62 400	80.59 406	75.77 421	89.17 419	65.04 402	94.79 404	72.12 419	81.02 367	90.23 413

EG-PatchMatch MVS		85.35 370	83.81 373	89.99 385	90.39 412	81.89 409	98.21 363	96.09 389	81.78 402	74.73 422	93.72 393	51.56 429	97.12 327	79.16 398	88.61 300	90.96 407

test_f		78.40 397	77.59 399	80.81 411	80.82 436	62.48 436	96.96 391	93.08 432	83.44 391	74.57 423	84.57 433	27.95 442	92.63 422	84.15 364	72.79 410	87.32 430

pmmvs-eth3d		84.03 381	81.97 385	90.20 382	84.15 430	87.09 374	98.10 367	94.73 417	83.05 394	74.10 424	87.77 426	65.56 399	94.01 410	81.08 386	69.24 418	89.49 423

new-patchmatchnet		81.19 389	79.34 396	86.76 402	82.86 433	80.36 420	97.92 371	95.27 408	82.09 401	72.02 425	86.87 428	62.81 410	90.74 430	71.10 420	63.08 432	89.19 426

ET-MVSNet_ETH3D		94.37 233	93.28 251	97.64 184	98.30 188	97.99 79	99.99 5	97.61 275	94.35 145	71.57 426	99.45 132	96.23 35	95.34 395	96.91 184	85.14 331	99.59 142

UnsupCasMVSNet_bld		79.97 396	77.03 401	88.78 393	85.62 427	81.98 408	93.66 421	97.35 304	75.51 421	70.79 427	83.05 434	48.70 432	94.91 402	78.31 402	60.29 437	89.46 424

CMPMVS	61.59 21	84.75 376	85.14 368	83.57 407	90.32 413	62.54 435	96.98 390	97.59 279	74.33 424	69.95 428	96.66 298	64.17 404	98.32 261	87.88 331	88.41 305	89.84 419
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WB-MVS		76.28 398	77.28 400	73.29 418	81.18 435	54.68 443	97.87 373	94.19 422	81.30 403	69.43 429	90.70 414	77.02 333	82.06 441	35.71 446	68.11 423	83.13 432

SSC-MVS		75.42 399	76.40 402	72.49 422	80.68 437	53.62 444	97.42 378	94.06 424	80.42 407	68.75 430	90.14 416	76.54 340	81.66 442	33.25 447	66.34 427	82.19 433

MVStest1		85.03 372	82.76 381	91.83 363	92.95 380	89.16 352	98.57 340	94.82 414	71.68 428	68.54 431	95.11 362	83.17 278	95.66 389	74.69 414	65.32 428	90.65 410

testmvs		40.60 414	44.45 417	29.05 431	19.49 455	14.11 457	99.68 196	18.47 454	20.74 447	64.59 432	98.48 234	10.95 452	17.09 451	56.66 440	11.01 447	55.94 444

LCM-MVSNet		67.77 405	64.73 408	76.87 415	62.95 449	56.25 442	89.37 436	93.74 428	44.53 441	61.99 433	80.74 435	20.42 448	86.53 438	69.37 424	59.50 438	87.84 427

PMMVS2		67.15 406	64.15 409	76.14 416	70.56 446	62.07 437	93.89 419	87.52 444	58.09 435	60.02 434	78.32 436	22.38 445	84.54 439	59.56 436	47.03 441	81.80 434

testf1		68.38 403	66.92 404	72.78 420	78.80 439	50.36 446	90.95 433	87.35 445	55.47 436	58.95 435	88.14 423	20.64 446	87.60 434	57.28 438	64.69 429	80.39 435

APD_test2		68.38 403	66.92 404	72.78 420	78.80 439	50.36 446	90.95 433	87.35 445	55.47 436	58.95 435	88.14 423	20.64 446	87.60 434	57.28 438	64.69 429	80.39 435

Gipuma		66.95 407	65.00 407	72.79 419	91.52 403	67.96 431	66.16 442	95.15 412	47.89 440	58.54 437	67.99 442	29.74 439	87.54 436	50.20 441	77.83 388	62.87 442
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		85.50 369	83.33 375	92.00 360	90.89 409	88.38 364	99.22 272	96.55 378	79.60 411	57.26 438	92.72 400	79.09 321	93.78 414	77.25 406	77.37 393	93.84 359

MDA-MVSNet_test_wron		85.51 368	83.32 376	92.10 359	90.96 408	88.58 360	99.20 273	96.52 379	79.70 410	57.12 439	92.69 401	79.11 319	93.86 413	77.10 407	77.46 392	93.86 358

MDA-MVSNet-bldmvs		84.09 380	81.52 387	91.81 364	91.32 406	88.00 368	98.67 336	95.92 392	80.22 408	55.60 440	93.32 396	68.29 388	93.60 416	73.76 415	76.61 399	93.82 361

FPMVS		68.72 402	68.72 403	68.71 424	65.95 447	44.27 453	95.97 411	94.74 416	51.13 439	53.26 441	90.50 415	25.11 444	83.00 440	60.80 435	80.97 369	78.87 437

test123		37.68 415	39.14 418	33.31 430	19.94 454	24.83 456	98.36 354	9.75 455	15.53 448	51.31 442	87.14 427	19.62 449	17.74 450	47.10 442	3.47 449	57.36 443

test_vis3_rt		68.82 401	66.69 406	75.21 417	76.24 442	60.41 438	96.44 400	68.71 452	75.13 422	50.54 443	69.52 441	16.42 451	96.32 370	80.27 391	66.92 426	68.89 439

tmp_tt		65.23 408	62.94 411	72.13 423	44.90 452	50.03 448	81.05 439	89.42 443	38.45 442	48.51 444	99.90 18	54.09 424	78.70 444	91.84 275	18.26 446	87.64 428

E-PMN		52.30 411	52.18 413	52.67 428	71.51 444	45.40 450	93.62 422	76.60 450	36.01 444	43.50 445	64.13 444	27.11 443	67.31 447	31.06 448	26.06 443	45.30 446

EMVS		51.44 413	51.22 415	52.11 429	70.71 445	44.97 452	94.04 418	75.66 451	35.34 446	42.40 446	61.56 447	28.93 440	65.87 448	27.64 449	24.73 444	45.49 445

MVE	53.74 22	51.54 412	47.86 416	62.60 426	59.56 450	50.93 445	79.41 440	77.69 449	35.69 445	36.27 447	61.76 446	5.79 455	69.63 445	37.97 445	36.61 442	67.24 440
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 409	52.24 412	67.66 425	49.27 451	56.82 441	83.94 438	82.02 448	70.47 429	33.28 448	64.54 443	17.23 450	69.16 446	45.59 443	23.85 445	77.02 438

PMVS	49.05 23	53.75 410	51.34 414	60.97 427	40.80 453	34.68 454	74.82 441	89.62 442	37.55 443	28.67 449	72.12 438	7.09 453	81.63 443	43.17 444	68.21 422	66.59 441
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		20.37 417	20.84 420	18.99 432	65.34 448	27.73 455	50.43 443	7.67 456	9.50 449	8.01 450	6.34 450	6.13 454	26.24 449	23.40 450	10.69 448	2.99 447

EGC-MVSNET		69.38 400	63.76 410	86.26 403	90.32 413	81.66 412	96.24 405	93.85 427	0.99 450	3.22 451	92.33 407	52.44 426	92.92 421	59.53 437	84.90 333	84.21 431

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.02 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		23.43 416	31.24 419	0.00 433	0.00 456	0.00 458	0.00 444	98.09 223	0.00 451	0.00 452	99.67 105	83.37 275	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		7.60 419	10.13 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	91.20 169	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		8.28 418	11.04 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	99.40 138	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 452	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						90.97 314								86.10 353

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 165					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 165					100.00 1	99.96 9	100.00 1	100.00 1

eth-test2					0.00 456

eth-test					0.00 456

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 45				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

save fliter					99.82 59	98.79 40	99.96 45	98.40 169	97.66 29

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 64	98.43 148					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 142

sam_mvs1												94.72 71				99.59 142

sam_mvs												94.25 91

MTGPA								98.28 196

test_post1							95.78 413				59.23 448	93.20 125	97.74 297	91.06 285

test_post											63.35 445	94.43 79	98.13 276

patchmatchnet-post											91.70 409	95.12 56	97.95 288

MTMP							99.87 121	96.49 380

gm-plane-assit					96.97 277	93.76 249			91.47 262		98.96 180		98.79 218	94.92 214

test9_res														99.71 41	99.99 21	100.00 1

agg_prior2														99.48 56	100.00 1	100.00 1

test_prior4						98.05 76	99.94 81

test_prior				99.43 35	99.94 13	98.49 60		98.65 81					99.80 134			99.99 23

新几何2							99.40 244

旧先验1					99.76 67	97.52 101		98.64 84			99.85 33	95.63 45			99.94 55	99.99 23

无先验							99.49 232	98.71 73	93.46 185				100.00 1	94.36 229		99.99 23

原ACMM2							99.90 105

testdata2													99.99 36	90.54 298

segment_acmp												96.68 29

testdata1							99.28 266		96.35 83

plane_prior7					95.71 325	91.59 308

plane_prior6					95.76 319	91.72 303						80.47 307

plane_prior5								97.87 245					98.37 257	97.79 158	89.55 287	94.52 297

plane_prior4											98.59 220

plane_prior2							99.84 140		96.38 79

plane_prior1					95.73 322

plane_prior						91.74 300	99.86 132		96.76 64						89.59 286

n2								0.00 457

nn								0.00 457

door-mid								89.69 441

test11								98.44 140

door								90.31 438

HQP5-MVS						91.85 296

BP-MVS														97.92 149

HQP3-MVS								97.89 243							89.60 284

HQP2-MVS												80.65 303

NP-MVS					95.77 318	91.79 298					98.65 214

ACMMP++_ref															87.04 318

ACMMP++															88.23 307

Test By Simon												92.82 136

High-resolution multi-view benchmark