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.

TestfortrainingZip				99.90 5	99.97 3	99.70 5	99.97 43	98.89 52	96.02 100	99.99 1	99.96 3	97.97 5	100.00 1		99.65 98	100.00 1

fmvsm_l_mol_unc0.5_1		99.14 9	98.92 15	99.81 9	99.03 131	99.54 7	99.98 24	97.90 259	98.36 5	99.94 2	99.78 67	95.70 49	99.97 65	99.83 33	99.75 90	99.92 93

fmvsm_l_conf0.5_n_9		98.55 41	98.23 52	99.49 38	99.10 126	98.50 67	99.99 8	98.70 80	98.14 17	99.94 2	99.68 113	89.02 221	99.98 52	99.89 22	99.61 106	99.99 26

fmvsm_s_conf0.5_n_9		98.15 74	98.02 69	98.55 125	99.28 114	95.84 191	99.99 8	98.57 108	98.17 14	99.93 4	99.74 89	87.04 251	99.97 65	99.86 28	99.59 110	99.83 106

CNVR-MVS		99.40 1	99.26 1	99.84 7	99.98 2	99.51 8	99.98 24	98.69 82	98.20 10	99.93 4	99.98 2	96.82 26	100.00 1	99.75 43	100.00 1	99.99 26

fmvsm_s_conf0.5_n_10		98.24 70	97.90 81	99.26 56	99.24 117	97.88 94	99.99 8	98.76 73	98.20 10	99.92 6	99.74 89	85.97 271	99.94 96	99.72 48	99.53 115	99.96 75

fmvsm_l_conf0.5_n_a		99.00 19	98.91 16	99.28 54	99.21 118	97.91 93	99.98 24	98.85 62	98.25 6	99.92 6	99.75 82	94.72 76	99.97 65	99.87 26	99.64 99	99.95 83

fmvsm_s_conf0.5_n_11		98.03 80	97.89 83	98.46 138	99.35 110	97.76 100	99.99 8	98.04 243	98.20 10	99.90 8	99.78 67	86.21 267	99.95 87	99.89 22	99.68 95	97.65 321

fmvsm_l_conf0.5_n		98.94 20	98.84 20	99.25 57	99.17 122	97.81 98	99.98 24	98.86 59	98.25 6	99.90 8	99.76 74	94.21 99	99.97 65	99.87 26	99.52 116	99.98 57

patch_mono-2		98.24 70	99.12 5	95.59 309	99.67 89	86.91 441	99.95 76	98.89 52	97.60 35	99.90 8	99.76 74	96.54 34	99.98 52	99.94 15	99.82 85	99.88 99

NCCC		99.37 2	99.25 2	99.71 17	99.96 9	99.15 25	99.97 43	98.62 98	98.02 23	99.90 8	99.95 4	97.33 19	100.00 1	99.54 60	100.00 1	100.00 1

fmvsm_s_conf0.5_n_5		98.08 78	97.71 93	99.17 67	98.67 168	97.69 106	99.99 8	98.57 108	97.40 41	99.89 12	99.69 106	85.99 270	99.96 78	99.80 34	99.40 134	99.85 104

fmvsm_s_conf0.5_n_3		97.95 82	97.66 95	98.81 102	98.99 138	98.07 82	99.98 24	98.81 67	98.18 13	99.89 12	99.70 102	84.15 310	99.97 65	99.76 42	99.50 121	98.39 299

TSAR-MVS + MP.		98.93 21	98.77 23	99.41 45	99.74 78	98.67 56	99.77 190	98.38 186	96.73 72	99.88 14	99.74 89	94.89 72	99.59 176	99.80 34	99.98 32	99.97 67
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 64	97.96 76	99.23 59	97.66 255	98.11 80	99.98 24	98.64 91	97.85 28	99.87 15	99.72 96	88.86 225	99.93 106	99.64 56	99.36 137	99.63 148

fmvsm_s_conf0.5_n_4		97.75 103	97.86 85	97.42 232	99.01 133	94.69 251	99.97 43	98.76 73	97.91 26	99.87 15	99.76 74	86.70 258	99.93 106	99.67 54	99.12 150	97.64 322

TestfortrainingZip a		99.01 17	98.78 22	99.69 18	99.96 9	99.09 27	99.97 43	98.74 76	96.91 63	99.86 17	99.92 16	96.29 38	99.99 40	98.32 137	99.09 151	100.00 1

fmvsm_l_conf0.5_n_3		98.41 54	98.08 65	99.39 47	99.12 125	98.29 72	99.98 24	98.64 91	98.14 17	99.86 17	99.76 74	87.99 234	99.97 65	99.72 48	99.54 113	99.91 96

test0726					99.93 29	99.29 18	99.96 57	98.42 169	97.28 46	99.86 17	99.94 5	97.22 21

xiu_mvs_v2_base		98.23 72	97.97 73	99.02 89	98.69 166	98.66 58	99.52 273	98.08 239	97.05 57	99.86 17	99.86 34	90.65 194	99.71 162	99.39 72	98.63 169	98.69 289

test_vis1_n_1920		95.44 236	95.31 224	95.82 304	98.50 186	88.74 418	99.98 24	97.30 338	97.84 29	99.85 21	99.19 183	66.82 457	99.97 65	98.82 104	99.46 128	98.76 284

PS-MVSNAJ		98.44 50	98.20 55	99.16 70	98.80 160	98.92 33	99.54 271	98.17 224	97.34 43	99.85 21	99.85 38	91.20 181	99.89 120	99.41 70	99.67 96	98.69 289

旧先验2							99.46 287		94.21 168	99.85 21			99.95 87	96.96 204

IU-MVS					99.93 29	99.31 13		98.41 175	97.71 32	99.84 24				100.00 1	100.00 1	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 14	99.93 29	99.29 18	99.95 76	98.32 199	97.28 46	99.83 25	99.91 19	97.22 21	100.00 1	99.99 5	100.00 1	99.89 98
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 81	99.83 25	99.91 19	97.87 6	100.00 1	99.92 17	100.00 1	100.00 1

SF-MVS		98.67 34	98.40 40	99.50 36	99.77 73	98.67 56	99.90 118	98.21 219	93.53 199	99.81 27	99.89 27	94.70 78	99.86 131	99.84 30	99.93 65	99.96 75

SD-MVS		98.92 22	98.70 24	99.56 31	99.70 86	98.73 53	99.94 94	98.34 196	96.38 87	99.81 27	99.76 74	94.59 79	99.98 52	99.84 30	99.96 48	99.97 67
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 58	98.05 67	99.35 51	99.20 119	98.12 79	99.98 24	98.81 67	98.22 8	99.80 29	99.71 99	87.37 246	99.97 65	99.91 20	99.48 123	99.97 67

test_fmvsm_n_1920		98.44 50	98.61 31	97.92 176	99.27 116	95.18 231	100.00 1	98.90 50	98.05 21	99.80 29	99.73 93	92.64 149	99.99 40	99.58 59	99.51 119	98.59 292

DVP-MVS++		99.26 6	99.09 10	99.77 10	99.91 45	99.31 13	99.95 76	98.43 157	96.48 81	99.80 29	99.93 12	97.44 15	100.00 1	99.92 17	99.98 32	100.00 1

PC_three_1452									96.96 61	99.80 29	99.79 63	97.49 11	100.00 1	99.99 5	99.98 32	100.00 1

SED-MVS		99.28 5	99.11 8	99.77 10	99.93 29	99.30 15	99.96 57	98.43 157	97.27 48	99.80 29	99.94 5	96.71 29	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 157	97.27 48	99.80 29	99.94 5	97.18 23	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 29	99.30 15		98.43 157	97.26 50	99.80 29	99.88 29	96.71 29	100.00 1

MSLP-MVS++		99.13 10	99.01 12	99.49 38	99.94 18	98.46 69	99.98 24	98.86 59	97.10 54	99.80 29	99.94 5	95.92 45	100.00 1	99.51 61	100.00 1	100.00 1

SteuartSystems-ACMMP		99.02 16	98.97 14	99.18 64	98.72 165	97.71 102	99.98 24	98.44 149	96.85 65	99.80 29	99.91 19	97.57 9	99.85 132	99.44 68	99.99 21	99.99 26
Skip Steuart: Steuart Systems R&D Blog.
lecture		98.67 34	98.46 37	99.28 54	99.86 59	97.88 94	99.97 43	99.25 30	96.07 98	99.79 38	99.70 102	92.53 154	99.98 52	99.51 61	99.48 123	99.97 67

testdata				98.42 143	99.47 104	95.33 219		98.56 114	93.78 191	99.79 38	99.85 38	93.64 117	99.94 96	94.97 256	99.94 59	100.00 1

9.14			98.38 42		99.87 57		99.91 112	98.33 197	93.22 216	99.78 40	99.89 27	94.57 82	99.85 132	99.84 30	99.97 44

SMA-MVS		98.76 30	98.48 36	99.62 23	99.87 57	98.87 37	99.86 147	98.38 186	93.19 218	99.77 41	99.94 5	95.54 52	100.00 1	99.74 45	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 36	98.36 46	99.49 38	99.94 18	98.73 53	99.87 135	98.33 197	93.97 181	99.76 42	99.87 32	94.99 70	99.75 156	98.55 121	100.00 1	99.98 57

fmvsm_s_conf0.5_n_2		97.59 114	97.28 117	98.53 131	99.01 133	98.15 74	99.98 24	98.59 104	98.17 14	99.75 43	99.63 123	81.83 337	99.94 96	99.78 37	98.79 165	97.51 330

fmvsm_s_conf0.5_n_a		97.73 106	97.72 91	97.77 191	98.63 173	94.26 271	99.96 57	98.92 49	97.18 53	99.75 43	99.69 106	87.00 253	99.97 65	99.46 66	98.89 158	99.08 256

test_one_0601					99.94 18	99.30 15		98.41 175	96.63 76	99.75 43	99.93 12	97.49 11

BridgeMVS		98.27 64	97.99 71	99.11 79	98.64 172	98.43 70	99.47 283	97.79 270	94.56 144	99.74 46	98.35 288	94.33 93	99.25 198	99.12 81	99.96 48	99.64 140

APD-MVS		98.62 37	98.35 47	99.41 45	99.90 48	98.51 66	99.87 135	98.36 190	94.08 174	99.74 46	99.73 93	94.08 102	99.74 158	99.42 69	99.99 21	99.99 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_fmvs1		95.35 239	95.68 205	94.36 359	98.99 138	84.98 453	99.96 57	96.65 435	97.60 35	99.73 48	98.96 216	71.58 435	99.93 106	98.31 138	99.37 136	98.17 305

test_prior2							99.95 76		95.78 107	99.73 48	99.76 74	96.00 42		99.78 37	100.00 1

TEST9					99.92 37	98.92 33	99.96 57	98.43 157	93.90 187	99.71 50	99.86 34	95.88 46	99.85 132

train_agg		98.88 24	98.65 28	99.59 28	99.92 37	98.92 33	99.96 57	98.43 157	94.35 159	99.71 50	99.86 34	95.94 43	99.85 132	99.69 52	99.98 32	99.99 26

test_8					99.92 37	98.88 36	99.96 57	98.43 157	94.35 159	99.69 52	99.85 38	95.94 43	99.85 132

CS-MVS		97.79 100	97.91 80	97.43 231	99.10 126	94.42 262	99.99 8	97.10 384	95.07 125	99.68 53	99.75 82	92.95 138	98.34 307	98.38 132	99.14 147	99.54 170

test_fmvsmconf_n		98.43 52	98.32 48	98.78 104	98.12 219	96.41 166	99.99 8	98.83 66	98.22 8	99.67 54	99.64 120	91.11 185	99.94 96	99.67 54	99.62 101	99.98 57

test_fmvs1_n		94.25 281	94.36 255	93.92 382	97.68 252	83.70 460	99.90 118	96.57 438	97.40 41	99.67 54	98.88 229	61.82 476	99.92 112	98.23 144	99.13 148	98.14 308

fmvsm_s_conf0.1_n_2		97.25 130	96.85 137	98.43 141	98.08 220	98.08 81	99.92 104	97.76 278	98.05 21	99.65 56	99.58 129	80.88 351	99.93 106	99.59 58	98.17 184	97.29 331

fmvsm_s_conf0.1_n_a		97.09 141	96.90 134	97.63 207	95.65 379	94.21 275	99.83 163	98.50 138	96.27 93	99.65 56	99.64 120	84.72 300	99.93 106	99.04 88	98.84 162	98.74 286

test12				99.43 42	99.74 78	98.56 64		98.40 179		99.65 56		94.76 75	99.75 156		99.98 32	99.99 26

DPE-MVS		99.26 6	99.10 9	99.74 13	99.89 51	99.24 22	99.87 135	98.44 149	97.48 40	99.64 59	99.94 5	96.68 31	99.99 40	99.99 5	100.00 1	99.99 26
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 98	97.85 86	97.67 200	99.06 129	94.41 263	99.98 24	98.97 43	97.34 43	99.63 60	99.69 106	87.27 247	99.97 65	99.62 57	99.06 153	98.62 291

agg_prior					99.93 29	98.77 49		98.43 157		99.63 60			99.85 132

EC-MVSNet		97.38 126	97.24 119	97.80 185	97.41 278	95.64 203	99.99 8	97.06 397	94.59 143	99.63 60	99.32 156	89.20 219	98.14 325	98.76 109	99.23 144	99.62 149

PRO-TEST		97.72 107	97.51 104	98.33 147	98.30 201	97.18 127	99.90 118	97.46 312	95.98 102	99.62 63	99.42 143	88.95 224	98.28 315	99.12 81	98.88 161	99.52 175

fmvsm_s_conf0.5_n_7		97.70 110	97.74 90	97.59 213	98.44 190	95.16 233	99.97 43	98.65 88	97.95 25	99.62 63	99.78 67	86.09 268	99.94 96	99.69 52	99.50 121	97.66 320

xiu_mvs_v1_base_debu		97.43 119	97.06 125	98.55 125	97.74 242	98.14 76	99.31 310	97.86 264	96.43 84	99.62 63	99.69 106	85.56 280	99.68 167	99.05 85	98.31 179	97.83 315

SPE-MVS-test		97.88 87	97.94 78	97.70 199	99.28 114	95.20 230	99.98 24	97.15 370	95.53 116	99.62 63	99.79 63	92.08 170	98.38 303	98.75 110	99.28 141	99.52 175

xiu_mvs_v1_base		97.43 119	97.06 125	98.55 125	97.74 242	98.14 76	99.31 310	97.86 264	96.43 84	99.62 63	99.69 106	85.56 280	99.68 167	99.05 85	98.31 179	97.83 315

xiu_mvs_v1_base_debi		97.43 119	97.06 125	98.55 125	97.74 242	98.14 76	99.31 310	97.86 264	96.43 84	99.62 63	99.69 106	85.56 280	99.68 167	99.05 85	98.31 179	97.83 315

原ACMM1				98.96 95	99.73 81	96.99 139		98.51 132	94.06 177	99.62 63	99.85 38	94.97 71	99.96 78	95.11 252	99.95 54	99.92 93

PHI-MVS		98.41 54	98.21 54	99.03 86	99.86 59	97.10 135	99.98 24	98.80 71	90.78 336	99.62 63	99.78 67	95.30 59	100.00 1	99.80 34	99.93 65	99.99 26

mvsany_test1		97.82 96	97.90 81	97.55 215	98.77 162	93.04 315	99.80 178	97.93 254	96.95 62	99.61 71	99.68 113	90.92 189	99.83 142	99.18 79	98.29 182	99.80 112

test_cas_vis1_n_1920		96.59 174	96.23 168	97.65 203	98.22 209	94.23 273	99.99 8	97.25 352	97.77 30	99.58 72	99.08 193	77.10 389	99.97 65	97.64 179	99.45 129	98.74 286

DPM-MVS		98.83 25	98.46 37	99.97 1	99.33 111	99.92 1	99.96 57	98.44 149	97.96 24	99.55 73	99.94 5	97.18 23	100.00 1	93.81 289	99.94 59	99.98 57

新几何1				99.42 44	99.75 77	98.27 73		98.63 97	92.69 249	99.55 73	99.82 54	94.40 86	100.00 1	91.21 332	99.94 59	99.99 26

test_vis1_n		93.61 304	93.03 304	95.35 318	95.86 364	86.94 439	99.87 135	96.36 445	96.85 65	99.54 75	98.79 246	52.41 492	99.83 142	98.64 117	98.97 156	99.29 227

ACMMP_NAP		98.49 46	98.14 60	99.54 33	99.66 90	98.62 62	99.85 150	98.37 189	94.68 141	99.53 76	99.83 51	92.87 140	100.00 1	98.66 116	99.84 80	99.99 26

PMMVS		96.76 160	96.76 142	96.76 268	98.28 205	92.10 339	99.91 112	97.98 249	94.12 172	99.53 76	99.39 151	86.93 254	98.73 255	96.95 205	97.73 197	99.45 193

FOURS1					99.92 37	97.66 107	99.95 76	98.36 190	95.58 114	99.52 78

MSP-MVS		99.09 11	99.12 5	98.98 93	99.93 29	97.24 124	99.95 76	98.42 169	97.50 39	99.52 78	99.88 29	97.43 17	99.71 162	99.50 63	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		97.30 127	97.21 121	97.60 210	97.38 283	94.40 265	99.90 118	98.64 91	96.47 83	99.51 80	99.65 119	84.99 292	99.93 106	99.22 78	99.09 151	98.46 295

test_part2					99.89 51	99.25 21				99.49 81

APDe-MVS		99.06 14	98.91 16	99.51 35	99.94 18	98.76 52	99.91 112	98.39 182	97.20 52	99.46 82	99.85 38	95.53 54	99.79 147	99.86 28	100.00 1	99.99 26
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
region2R		98.54 42	98.37 44	99.05 84	99.96 9	97.18 127	99.96 57	98.55 120	94.87 133	99.45 83	99.85 38	94.07 103	100.00 1	98.67 114	100.00 1	99.98 57

MGCNet		99.06 14	98.84 20	99.72 15	99.76 74	99.21 24	99.99 8	99.34 25	98.70 2	99.44 84	99.75 82	93.24 130	99.99 40	99.94 15	99.41 133	99.95 83

HPM-MVS++		99.07 12	98.88 19	99.63 20	99.90 48	99.02 29	99.95 76	98.56 114	97.56 38	99.44 84	99.85 38	95.38 58	100.00 1	99.31 73	99.99 21	99.87 101

MVSFormer		96.94 149	96.60 150	97.95 172	97.28 297	97.70 104	99.55 269	97.27 348	91.17 317	99.43 86	99.54 135	90.92 189	96.89 395	94.67 268	99.62 101	99.25 236

lupinMVS		97.85 91	97.60 99	98.62 117	97.28 297	97.70 104	99.99 8	97.55 301	95.50 118	99.43 86	99.67 115	90.92 189	98.71 259	98.40 131	99.62 101	99.45 193

balanced_ft_v1		96.88 153	96.52 154	97.96 171	98.60 174	94.94 240	99.41 291	97.56 300	93.53 199	99.42 88	97.89 311	83.33 323	99.31 195	99.29 75	99.62 101	99.64 140

XVS		98.70 33	98.55 32	99.15 72	99.94 18	97.50 113	99.94 94	98.42 169	96.22 94	99.41 89	99.78 67	94.34 91	99.96 78	98.92 97	99.95 54	99.99 26

X-MVStestdata		93.83 293	92.06 328	99.15 72	99.94 18	97.50 113	99.94 94	98.42 169	96.22 94	99.41 89	41.37 555	94.34 91	99.96 78	98.92 97	99.95 54	99.99 26

SR-MVS-dyc-post		98.31 61	98.17 58	98.71 109	99.79 70	96.37 170	99.76 196	98.31 201	94.43 154	99.40 91	99.75 82	93.28 128	99.78 149	98.90 100	99.92 68	99.97 67

RE-MVS-def			98.13 61		99.79 70	96.37 170	99.76 196	98.31 201	94.43 154	99.40 91	99.75 82	92.95 138		98.90 100	99.92 68	99.97 67

MM		98.83 25	98.53 34	99.76 12	99.59 93	99.33 10	99.99 8	99.76 6	98.39 4	99.39 93	99.80 59	90.49 199	99.96 78	99.89 22	99.43 131	99.98 57

APD-MVS_3200maxsize		98.25 69	98.08 65	98.78 104	99.81 68	96.60 159	99.82 170	98.30 204	93.95 183	99.37 94	99.77 72	92.84 141	99.76 155	98.95 93	99.92 68	99.97 67

PGM-MVS		98.34 59	98.13 61	98.99 91	99.92 37	97.00 138	99.75 203	99.50 17	93.90 187	99.37 94	99.76 74	93.24 130	100.00 1	97.75 177	99.96 48	99.98 57

SR-MVS		98.46 48	98.30 51	98.93 97	99.88 55	97.04 137	99.84 155	98.35 192	94.92 130	99.32 96	99.80 59	93.35 122	99.78 149	99.30 74	99.95 54	99.96 75

ZD-MVS					99.92 37	98.57 63		98.52 129	92.34 273	99.31 97	99.83 51	95.06 65	99.80 145	99.70 51	99.97 44

HFP-MVS		98.56 40	98.37 44	99.14 74	99.96 9	97.43 117	99.95 76	98.61 100	94.77 136	99.31 97	99.85 38	94.22 97	100.00 1	98.70 112	99.98 32	99.98 57

ACMMPR		98.50 45	98.32 48	99.05 84	99.96 9	97.18 127	99.95 76	98.60 102	94.77 136	99.31 97	99.84 49	93.73 113	100.00 1	98.70 112	99.98 32	99.98 57

ETV-MVS		97.92 85	97.80 89	98.25 153	98.14 217	96.48 163	99.98 24	97.63 288	95.61 113	99.29 100	99.46 141	92.55 153	98.82 235	99.02 92	98.54 173	99.46 188

aaEdge-Enhanced		99.07 12	98.89 18	99.59 28	99.93 29	98.79 44	99.95 76	98.80 71	95.89 105	99.28 101	99.93 12	96.28 39	99.98 52	99.98 9	99.96 48	99.99 26

test222					99.55 98	97.41 119	99.34 304	98.55 120	91.86 291	99.27 102	99.83 51	93.84 111			99.95 54	99.99 26

MVSMamba_PlusPlus		97.83 93	97.45 108	98.99 91	98.60 174	98.15 74	99.58 258	97.74 279	90.34 350	99.26 103	98.32 291	94.29 95	99.23 199	99.03 91	99.89 74	99.58 162

CANet_DTU		96.76 160	96.15 174	98.60 119	98.78 161	97.53 110	99.84 155	97.63 288	97.25 51	99.20 104	99.64 120	81.36 343	99.98 52	92.77 311	98.89 158	98.28 303

EPNet		98.49 46	98.40 40	98.77 106	99.62 92	96.80 150	99.90 118	99.51 16	97.60 35	99.20 104	99.36 154	93.71 114	99.91 113	97.99 158	98.71 168	99.61 153
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	95.94 2	97.71 109	98.98 13	93.92 382	99.63 91	81.76 477	99.96 57	98.56 114	99.47 1	99.19 106	99.99 1	94.16 101	100.00 1	99.92 17	99.93 65	100.00 1

reproduce_model		98.75 31	98.66 27	99.03 86	99.71 84	97.10 135	99.73 214	98.23 214	97.02 59	99.18 107	99.90 23	94.54 83	99.99 40	99.77 39	99.90 73	99.99 26

VNet		97.21 133	96.57 152	99.13 78	98.97 141	97.82 97	99.03 350	99.21 32	94.31 162	99.18 107	98.88 229	86.26 266	99.89 120	98.93 95	94.32 307	99.69 131

MCST-MVS		99.32 3	99.14 4	99.86 6	99.97 3	99.59 6	99.97 43	98.64 91	98.47 3	99.13 109	99.92 16	96.38 37	100.00 1	99.74 45	100.00 1	100.00 1

reproduce-ours		98.78 28	98.67 25	99.09 81	99.70 86	97.30 121	99.74 207	98.25 210	97.10 54	99.10 110	99.90 23	94.59 79	99.99 40	99.77 39	99.91 71	99.99 26

our_new_method		98.78 28	98.67 25	99.09 81	99.70 86	97.30 121	99.74 207	98.25 210	97.10 54	99.10 110	99.90 23	94.59 79	99.99 40	99.77 39	99.91 71	99.99 26

GDP-MVS		97.88 87	97.59 101	98.75 107	97.59 263	97.81 98	99.95 76	97.37 324	94.44 153	99.08 112	99.58 129	97.13 25	99.08 212	94.99 255	98.17 184	99.37 206

DeepC-MVS_fast	96.59 1	98.81 27	98.54 33	99.62 23	99.90 48	98.85 39	99.24 323	98.47 141	98.14 17	99.08 112	99.91 19	93.09 134	100.00 1	99.04 88	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
aaatest				99.60 25	99.96 9	98.79 44	99.97 43	98.88 55	96.36 91	99.07 114	99.93 12		100.00 1	99.98 9	99.96 48	99.99 26

MED-MVS		99.24 8	99.12 5	99.60 25	99.96 9	98.79 44	99.97 43	98.88 55	96.91 63	99.07 114	99.92 16	97.36 18	100.00 1	99.98 9	99.98 32	100.00 1

114514_t		97.41 124	96.83 138	99.14 74	99.51 102	97.83 96	99.89 129	98.27 208	88.48 388	99.06 116	99.66 117	90.30 202	99.64 175	96.32 231	99.97 44	99.96 75

test-260524					99.95 17	99.33 10		98.42 169		99.04 117		96.44 36	100.00 1	99.98 9	99.98 32

PVSNet	91.05 13	97.13 137	96.69 147	98.45 139	99.52 100	95.81 192	99.95 76	99.65 12	94.73 138	99.04 117	99.21 180	84.48 306	99.95 87	94.92 258	98.74 167	99.58 162

CHOSEN 280x420		99.01 17	99.03 11	98.95 96	99.38 108	98.87 37	98.46 406	99.42 21	97.03 58	99.02 119	99.09 192	99.35 2	98.21 322	99.73 47	99.78 88	99.77 117

MG-MVS		98.91 23	98.65 28	99.68 19	99.94 18	99.07 28	99.64 244	99.44 19	97.33 45	99.00 120	99.72 96	94.03 104	99.98 52	98.73 111	100.00 1	100.00 1

diffmvs		97.00 146	96.64 148	98.09 164	97.64 257	96.17 182	99.81 172	97.19 361	94.67 142	98.95 121	99.28 163	86.43 261	98.76 251	98.37 134	97.42 206	99.33 215
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 98	97.50 105	98.68 111	99.79 70	96.42 165	99.88 132	98.16 229	91.75 297	98.94 122	99.54 135	91.82 176	99.65 174	97.62 181	99.99 21	99.99 26

dcpmvs_2		97.42 123	98.09 64	95.42 316	99.58 97	87.24 437	99.23 324	96.95 411	94.28 165	98.93 123	99.73 93	94.39 89	99.16 209	99.89 22	99.82 85	99.86 103

CP-MVS		98.45 49	98.32 48	98.87 99	99.96 9	96.62 157	99.97 43	98.39 182	94.43 154	98.90 124	99.87 32	94.30 94	100.00 1	99.04 88	99.99 21	99.99 26

test_fmvsmconf0.1_n		97.74 104	97.44 109	98.64 116	95.76 369	96.20 179	99.94 94	98.05 242	98.17 14	98.89 125	99.42 143	87.65 238	99.90 115	99.50 63	99.60 109	99.82 108

testing222		97.08 144	96.75 143	98.06 166	98.56 176	96.82 145	99.85 150	98.61 100	92.53 264	98.84 126	98.84 242	93.36 121	98.30 312	95.84 240	94.30 308	99.05 260

MVS_Test		96.46 182	95.74 201	98.61 118	98.18 213	97.23 125	99.31 310	97.15 370	91.07 323	98.84 126	97.05 335	88.17 232	98.97 219	94.39 272	97.50 203	99.61 153

API-MVS		97.86 89	97.66 95	98.47 136	99.52 100	95.41 213	99.47 283	98.87 58	91.68 300	98.84 126	99.85 38	92.34 161	99.99 40	98.44 129	99.96 48	100.00 1

GST-MVS		98.27 64	97.97 73	99.17 67	99.92 37	97.57 109	99.93 101	98.39 182	94.04 179	98.80 129	99.74 89	92.98 137	100.00 1	98.16 147	99.76 89	99.93 88

diffmvs_AUTHOR		96.75 162	96.41 162	97.79 187	97.20 302	95.46 209	99.69 233	97.15 370	94.46 149	98.78 130	99.21 180	85.64 277	98.77 249	98.27 141	97.31 213	99.13 249

MVS_111021_LR		98.42 53	98.38 42	98.53 131	99.39 107	95.79 193	99.87 135	99.86 2	96.70 73	98.78 130	99.79 63	92.03 171	99.90 115	99.17 80	99.86 79	99.88 99

BP-MVS1		98.33 60	98.18 57	98.81 102	97.44 276	97.98 88	99.96 57	98.17 224	94.88 132	98.77 132	99.59 126	97.59 8	99.08 212	98.24 143	98.93 157	99.36 208

h-mvs33		94.92 252	94.36 255	96.59 275	98.85 157	91.29 372	98.93 366	98.94 44	95.90 103	98.77 132	98.42 285	90.89 192	99.77 152	97.80 170	70.76 475	98.72 288

hse-mvs2		94.38 275	94.08 266	95.31 321	98.27 206	90.02 399	99.29 317	98.56 114	95.90 103	98.77 132	98.00 303	90.89 192	98.26 320	97.80 170	69.20 483	97.64 322

TSAR-MVS + GP.		98.60 38	98.51 35	98.86 100	99.73 81	96.63 156	99.97 43	97.92 257	98.07 20	98.76 135	99.55 133	95.00 69	99.94 96	99.91 20	97.68 200	99.99 26

sss		97.57 115	97.03 129	99.18 64	98.37 195	98.04 85	99.73 214	99.38 22	93.46 204	98.76 135	99.06 197	91.21 180	99.89 120	96.33 230	97.01 238	99.62 149

CostFormer		96.10 203	95.88 196	96.78 267	97.03 312	92.55 329	97.08 454	97.83 268	90.04 357	98.72 137	94.89 428	95.01 68	98.29 313	96.54 224	95.77 276	99.50 182

tpmrst		96.27 197	95.98 183	97.13 252	97.96 227	93.15 311	96.34 469	98.17 224	92.07 283	98.71 138	95.12 416	93.91 107	98.73 255	94.91 260	96.62 249	99.50 182

MVS_111021_HR		98.72 32	98.62 30	99.01 90	99.36 109	97.18 127	99.93 101	99.90 1	96.81 70	98.67 139	99.77 72	93.92 106	99.89 120	99.27 76	99.94 59	99.96 75

onestephybrid01		96.75 162	96.44 159	97.71 197	97.47 274	95.03 236	99.83 163	97.27 348	94.15 170	98.66 140	99.25 174	85.72 274	98.81 239	98.42 130	97.17 223	99.28 229

MAR-MVS		97.43 119	97.19 122	98.15 160	99.47 104	94.79 247	99.05 347	98.76 73	92.65 252	98.66 140	99.82 54	88.52 229	99.98 52	98.12 149	99.63 100	99.67 134
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+		96.30 194	95.69 203	98.16 157	97.85 234	96.26 173	97.41 445	97.21 360	90.37 348	98.65 142	98.58 270	86.61 260	98.70 262	97.11 196	97.37 209	99.52 175

HPM-MVS		97.96 81	97.72 91	98.68 111	99.84 64	96.39 169	99.90 118	98.17 224	92.61 254	98.62 143	99.57 132	91.87 174	99.67 170	98.87 102	99.99 21	99.99 26
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
NormalMVS		97.90 86	97.85 86	98.04 168	99.86 59	95.39 215	99.61 251	97.78 274	96.52 79	98.61 144	99.31 159	92.73 145	99.67 170	96.77 216	99.48 123	99.06 258

SymmetryMVS		97.64 112	97.46 106	98.17 156	98.74 164	95.39 215	99.61 251	99.26 29	96.52 79	98.61 144	99.31 159	92.73 145	99.67 170	96.77 216	95.63 285	99.45 193

mPP-MVS		98.39 57	98.20 55	98.97 94	99.97 3	96.92 142	99.95 76	98.38 186	95.04 126	98.61 144	99.80 59	93.39 120	100.00 1	98.64 117	100.00 1	99.98 57

FBQ-MVS		97.12 138	96.92 132	97.72 196	98.35 198	94.55 254	99.87 135	98.62 98	93.23 215	98.60 147	98.39 287	93.66 115	98.96 221	95.76 243	95.82 274	99.64 140

jason		97.24 131	96.86 136	98.38 146	95.73 372	97.32 120	99.97 43	97.40 320	95.34 121	98.60 147	99.54 135	87.70 237	98.56 280	97.94 161	99.47 126	99.25 236
jason: jason.
UBG		97.84 92	97.69 94	98.29 151	98.38 193	96.59 161	99.90 118	98.53 127	93.91 186	98.52 149	98.42 285	96.77 27	99.17 207	98.54 122	96.20 260	99.11 252

CANet		98.27 64	97.82 88	99.63 20	99.72 83	99.10 26	99.98 24	98.51 132	97.00 60	98.52 149	99.71 99	87.80 235	99.95 87	99.75 43	99.38 135	99.83 106

EI-MVSNet-Vis-set		98.27 64	98.11 63	98.75 107	99.83 65	96.59 161	99.40 292	98.51 132	95.29 122	98.51 151	99.76 74	93.60 118	99.71 162	98.53 124	99.52 116	99.95 83

ZNCC-MVS		98.31 61	98.03 68	99.17 67	99.88 55	97.59 108	99.94 94	98.44 149	94.31 162	98.50 152	99.82 54	93.06 135	99.99 40	98.30 139	99.99 21	99.93 88

LFMVS		94.75 260	93.56 283	98.30 150	99.03 131	95.70 199	98.74 387	97.98 249	87.81 401	98.47 153	99.39 151	67.43 454	99.53 177	98.01 156	95.20 297	99.67 134

KinetiMVS		96.10 203	95.29 226	98.53 131	97.08 308	97.12 132	99.56 266	98.12 235	94.78 135	98.44 154	98.94 223	80.30 362	99.39 193	91.56 329	98.79 165	99.06 258

tpm2		95.47 235	95.18 230	96.35 285	96.91 328	91.70 359	96.96 457	97.93 254	88.04 397	98.44 154	95.40 400	93.32 124	97.97 335	94.00 280	95.61 286	99.38 204

mvsmamba		96.94 149	96.73 144	97.55 215	97.99 225	94.37 267	99.62 247	97.70 281	93.13 224	98.42 156	97.92 308	88.02 233	98.75 253	98.78 107	99.01 155	99.52 175

alignmvs		97.81 97	97.33 115	99.25 57	98.77 162	98.66 58	99.99 8	98.44 149	94.40 158	98.41 157	99.47 139	93.65 116	99.42 192	98.57 120	94.26 309	99.67 134

UA-Net		96.54 178	95.96 187	98.27 152	98.23 208	95.71 198	98.00 432	98.45 144	93.72 195	98.41 157	99.27 167	88.71 228	99.66 173	91.19 333	97.69 198	99.44 196

DP-MVS Recon		98.41 54	98.02 69	99.56 31	99.97 3	98.70 55	99.92 104	98.44 149	92.06 285	98.40 159	99.84 49	95.68 50	100.00 1	98.19 145	99.71 93	99.97 67

CPTT-MVS		97.64 112	97.32 116	98.58 123	99.97 3	95.77 194	99.96 57	98.35 192	89.90 359	98.36 160	99.79 63	91.18 184	99.99 40	98.37 134	99.99 21	99.99 26

PAPM		98.60 38	98.42 39	99.14 74	96.05 358	98.96 30	99.90 118	99.35 24	96.68 74	98.35 161	99.66 117	96.45 35	98.51 285	99.45 67	99.89 74	99.96 75

HY-MVS	92.50 7	97.79 100	97.17 124	99.63 20	98.98 140	99.32 12	97.49 442	99.52 14	95.69 111	98.32 162	97.41 322	93.32 124	99.77 152	98.08 153	95.75 278	99.81 110

EI-MVSNet-UG-set		98.14 75	97.99 71	98.60 119	99.80 69	96.27 172	99.36 302	98.50 138	95.21 124	98.30 163	99.75 82	93.29 127	99.73 161	98.37 134	99.30 140	99.81 110

PVSNet_BlendedMVS		96.05 206	95.82 198	96.72 270	99.59 93	96.99 139	99.95 76	99.10 34	94.06 177	98.27 164	95.80 378	89.00 222	99.95 87	99.12 81	87.53 367	93.24 440

PVSNet_Blended		97.94 83	97.64 97	98.83 101	99.59 93	96.99 139	100.00 1	99.10 34	95.38 119	98.27 164	99.08 193	89.00 222	99.95 87	99.12 81	99.25 142	99.57 164

myMVS_eth3d28		97.86 89	97.59 101	98.68 111	98.50 186	97.26 123	99.92 104	98.55 120	93.79 190	98.26 166	98.75 248	95.20 60	99.48 188	98.93 95	96.40 255	99.29 227

MP-MVS		98.23 72	97.97 73	99.03 86	99.94 18	97.17 131	99.95 76	98.39 182	94.70 140	98.26 166	99.81 58	91.84 175	100.00 1	98.85 103	99.97 44	99.93 88
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
WTY-MVS		98.10 77	97.60 99	99.60 25	98.92 148	99.28 20	99.89 129	99.52 14	95.58 114	98.24 168	99.39 151	93.33 123	99.74 158	97.98 160	95.58 287	99.78 116

hybrid		96.53 179	96.15 174	97.67 200	97.39 282	95.12 234	99.80 178	97.15 370	93.38 208	98.23 169	99.16 188	85.20 287	98.70 262	97.92 162	97.15 224	99.20 242

DELS-MVS		98.54 42	98.22 53	99.50 36	99.15 124	98.65 60	100.00 1	98.58 106	97.70 33	98.21 170	99.24 176	92.58 152	99.94 96	98.63 119	99.94 59	99.92 93
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		97.03 145	96.64 148	98.20 155	98.67 168	97.12 132	99.89 129	98.57 108	91.10 322	98.17 171	98.59 267	93.86 110	98.19 323	95.64 245	95.24 296	99.28 229

testing11		97.48 118	97.27 118	98.10 163	98.36 196	96.02 186	99.92 104	98.45 144	93.45 206	98.15 172	98.70 254	95.48 56	99.22 200	97.85 167	95.05 298	99.07 257

guyue		97.15 136	96.82 139	98.15 160	97.56 265	96.25 177	99.71 223	97.84 267	95.75 109	98.13 173	98.65 259	87.58 240	98.82 235	98.29 140	97.91 196	99.36 208

MDTV_nov1_ep13_2view						96.26 173	96.11 474		91.89 289	98.06 174		94.40 86		94.30 276		99.67 134

PAPR		98.52 44	98.16 59	99.58 30	99.97 3	98.77 49	99.95 76	98.43 157	95.35 120	98.03 175	99.75 82	94.03 104	99.98 52	98.11 150	99.83 81	99.99 26

hybridnocas07		96.57 176	96.16 173	97.81 184	97.36 288	95.32 220	99.81 172	97.12 376	94.17 169	98.02 176	98.90 227	85.05 290	98.80 244	97.85 167	97.18 219	99.32 217

MDTV_nov1_ep13			95.69 203		97.90 230	94.15 277	95.98 477	98.44 149	93.12 225	97.98 177	95.74 380	95.10 63	98.58 277	90.02 357	96.92 240

test2506		97.53 116	97.19 122	98.58 123	98.66 170	96.90 143	98.81 381	99.77 5	94.93 128	97.95 178	98.96 216	92.51 155	99.20 204	94.93 257	98.15 186	99.64 140

GG-mvs-BLEND				98.54 129	98.21 210	98.01 86	93.87 487	98.52 129		97.92 179	97.92 308	99.02 3	97.94 340	98.17 146	99.58 111	99.67 134

testing3-2		97.72 107	97.43 111	98.60 119	98.55 179	97.11 134	100.00 1	99.23 31	93.78 191	97.90 180	98.73 250	95.50 55	99.69 166	98.53 124	94.63 301	98.99 268

EIA-MVS		97.53 116	97.46 106	97.76 193	98.04 223	94.84 243	99.98 24	97.61 294	94.41 157	97.90 180	99.59 126	92.40 159	98.87 228	98.04 155	99.13 148	99.59 156

viewmamba		96.61 172	96.34 164	97.42 232	97.26 300	94.37 267	99.83 163	97.16 367	94.51 146	97.89 182	99.26 171	86.38 262	98.66 270	97.70 178	97.06 232	99.23 239

test_fmvsmconf0.01_n		96.39 187	95.74 201	98.32 149	91.47 463	95.56 206	99.84 155	97.30 338	97.74 31	97.89 182	99.35 155	79.62 366	99.85 132	99.25 77	99.24 143	99.55 166

LuminaMVS		96.63 171	96.21 171	97.87 181	95.58 383	96.82 145	99.12 332	97.67 284	94.47 148	97.88 184	98.31 293	87.50 242	98.71 259	98.07 154	97.29 214	98.10 309

sasdasda		97.09 141	96.32 165	99.39 47	98.93 145	98.95 31	99.72 218	97.35 326	94.45 150	97.88 184	99.42 143	86.71 256	99.52 178	98.48 126	93.97 313	99.72 123

test_yl		97.83 93	97.37 113	99.21 61	99.18 120	97.98 88	99.64 244	99.27 27	91.43 309	97.88 184	98.99 210	95.84 47	99.84 140	98.82 104	95.32 294	99.79 113

DCV-MVSNet		97.83 93	97.37 113	99.21 61	99.18 120	97.98 88	99.64 244	99.27 27	91.43 309	97.88 184	98.99 210	95.84 47	99.84 140	98.82 104	95.32 294	99.79 113

canonicalmvs		97.09 141	96.32 165	99.39 47	98.93 145	98.95 31	99.72 218	97.35 326	94.45 150	97.88 184	99.42 143	86.71 256	99.52 178	98.48 126	93.97 313	99.72 123

AstraMVS		96.57 176	96.46 158	96.91 261	96.79 339	92.50 330	99.90 118	97.38 321	96.02 100	97.79 189	99.32 156	86.36 264	98.99 216	98.26 142	96.33 258	99.23 239

MGCFI-Net		97.00 146	96.22 170	99.34 52	98.86 156	98.80 43	99.67 238	97.30 338	94.31 162	97.77 190	99.41 148	86.36 264	99.50 182	98.38 132	93.90 315	99.72 123

VDDNet		93.12 315	91.91 331	96.76 268	96.67 346	92.65 327	98.69 393	98.21 219	82.81 457	97.75 191	99.28 163	61.57 477	99.48 188	98.09 152	94.09 311	98.15 306

EPMVS		96.53 179	96.01 180	98.09 164	98.43 191	96.12 185	96.36 468	99.43 20	93.53 199	97.64 192	95.04 419	94.41 85	98.38 303	91.13 334	98.11 189	99.75 119

JIA-IIPM		91.76 351	90.70 352	94.94 331	96.11 356	87.51 434	93.16 496	98.13 234	75.79 487	97.58 193	77.68 520	92.84 141	97.97 335	88.47 380	96.54 250	99.33 215

EPNet_dtu		95.71 227	95.39 217	96.66 272	98.92 148	93.41 305	99.57 262	98.90 50	96.19 96	97.52 194	98.56 272	92.65 148	97.36 358	77.89 470	98.33 178	99.20 242
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PAPM_NR		98.12 76	97.93 79	98.70 110	99.94 18	96.13 183	99.82 170	98.43 157	94.56 144	97.52 194	99.70 102	94.40 86	99.98 52	97.00 200	99.98 32	99.99 26

FE-MVS		95.70 229	95.01 238	97.79 187	98.21 210	94.57 253	95.03 482	98.69 82	88.90 377	97.50 196	96.19 367	92.60 151	99.49 187	89.99 358	97.94 195	99.31 222

E3new		96.75 162	96.43 160	97.71 197	97.79 238	94.83 244	99.80 178	97.33 330	93.52 202	97.49 197	99.31 159	87.73 236	98.83 232	97.52 182	97.40 208	99.48 185

thisisatest0515		97.41 124	97.02 130	98.59 122	97.71 249	97.52 111	99.97 43	98.54 124	91.83 292	97.45 198	99.04 199	97.50 10	99.10 211	94.75 265	96.37 257	99.16 245

RRT-MVS		96.24 199	95.68 205	97.94 175	97.65 256	94.92 241	99.27 320	97.10 384	92.79 242	97.43 199	97.99 305	81.85 336	99.37 194	98.46 128	98.57 170	99.53 174

OMC-MVS		97.28 128	97.23 120	97.41 235	99.76 74	93.36 309	99.65 240	97.95 252	96.03 99	97.41 200	99.70 102	89.61 210	99.51 180	96.73 219	98.25 183	99.38 204

testing99		97.17 134	96.91 133	97.95 172	98.35 198	95.70 199	99.91 112	98.43 157	92.94 232	97.36 201	98.72 251	94.83 73	99.21 201	97.00 200	94.64 300	98.95 270

viewcassd2359sk11		96.59 174	96.23 168	97.66 202	97.63 259	94.70 249	99.77 190	97.33 330	93.41 207	97.34 202	99.17 185	86.72 255	98.83 232	97.40 185	97.32 212	99.46 188

UWE-MVS-28		95.95 210	96.49 155	94.34 360	98.51 184	89.99 400	99.39 296	98.57 108	93.14 223	97.33 203	98.31 293	93.44 119	94.68 472	93.69 296	95.98 266	98.34 302

testing91		97.16 135	96.90 134	97.97 170	98.35 198	95.67 202	99.91 112	98.42 169	92.91 234	97.33 203	98.72 251	94.81 74	99.21 201	96.98 202	94.63 301	99.03 265

gg-mvs-nofinetune		93.51 306	91.86 333	98.47 136	97.72 247	97.96 91	92.62 498	98.51 132	74.70 491	97.33 203	69.59 527	98.91 4	97.79 344	97.77 175	99.56 112	99.67 134

PatchT		90.38 377	88.75 394	95.25 323	95.99 360	90.16 396	91.22 506	97.54 303	76.80 483	97.26 206	86.01 509	91.88 173	96.07 445	66.16 501	95.91 271	99.51 180

PLC	95.54 3	97.93 84	97.89 83	98.05 167	99.82 66	94.77 248	99.92 104	98.46 143	93.93 184	97.20 207	99.27 167	95.44 57	99.97 65	97.41 184	99.51 119	99.41 201
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
mmtdpeth		88.52 405	87.75 407	90.85 434	95.71 375	83.47 465	98.94 363	94.85 479	88.78 380	97.19 208	89.58 487	63.29 470	98.97 219	98.54 122	62.86 498	90.10 484

MTAPA		98.29 63	97.96 76	99.30 53	99.85 62	97.93 92	99.39 296	98.28 206	95.76 108	97.18 209	99.88 29	92.74 144	100.00 1	98.67 114	99.88 77	99.99 26

0.3-1-1-0.015		94.22 282	93.13 303	97.49 225	95.50 384	94.17 276	100.00 1	98.22 215	88.44 390	97.14 210	97.04 337	92.73 145	98.59 276	96.45 228	72.65 469	99.70 126

UWE-MVS		96.79 157	96.72 145	97.00 257	98.51 184	93.70 291	99.71 223	98.60 102	92.96 231	97.09 211	98.34 290	96.67 33	98.85 231	92.11 321	96.50 252	98.44 297

PatchmatchNet		95.94 211	95.45 212	97.39 237	97.83 235	94.41 263	96.05 475	98.40 179	92.86 236	97.09 211	95.28 411	94.21 99	98.07 331	89.26 369	98.11 189	99.70 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0530		97.10 139	96.72 145	98.22 154	97.60 262	96.70 151	99.92 104	98.54 124	91.11 321	97.07 213	98.97 214	97.47 13	99.03 214	93.73 294	96.09 263	98.92 274

E2		96.36 189	95.95 189	97.60 210	97.41 278	94.52 256	99.71 223	97.33 330	93.20 217	97.02 214	99.07 195	85.37 285	98.82 235	97.27 188	97.14 225	99.46 188

E3		96.36 189	95.95 189	97.60 210	97.37 285	94.52 256	99.71 223	97.33 330	93.18 219	97.02 214	99.07 195	85.45 283	98.82 235	97.27 188	97.14 225	99.46 188

test_fmvsmvis_n_1920		97.67 111	97.59 101	97.91 178	97.02 315	95.34 218	99.95 76	98.45 144	97.87 27	97.02 214	99.59 126	89.64 209	99.98 52	99.41 70	99.34 139	98.42 298

viewmanbaseed2359cas		96.45 183	96.07 177	97.59 213	97.55 266	94.59 252	99.70 230	97.33 330	93.62 198	97.00 217	99.32 156	85.57 279	98.71 259	97.26 191	97.33 211	99.47 186

CR-MVSNet		93.45 309	92.62 314	95.94 296	96.29 351	92.66 325	92.01 501	96.23 447	92.62 253	96.94 218	93.31 456	91.04 186	96.03 446	79.23 461	95.96 267	99.13 249

RPMNet		89.76 393	87.28 410	97.19 247	96.29 351	92.66 325	92.01 501	98.31 201	70.19 499	96.94 218	85.87 510	87.25 248	99.78 149	62.69 510	95.96 267	99.13 249

baseline		96.43 184	95.98 183	97.76 193	97.34 290	95.17 232	99.51 275	97.17 365	93.92 185	96.90 220	99.28 163	85.37 285	98.64 273	97.50 183	96.86 243	99.46 188

Casviewmamba		96.25 198	95.89 195	97.32 245	97.45 275	93.68 293	99.80 178	97.22 359	93.38 208	96.86 221	99.28 163	84.64 302	98.87 228	97.18 194	97.19 218	99.41 201

ECVR-MVS		95.66 230	95.05 236	97.51 220	98.66 170	93.71 290	98.85 378	98.45 144	94.93 128	96.86 221	98.96 216	75.22 415	99.20 204	95.34 247	98.15 186	99.64 140

Vis-MVSNet		95.72 225	95.15 232	97.45 227	97.62 260	94.28 270	99.28 318	98.24 212	94.27 167	96.84 223	98.94 223	79.39 368	98.76 251	93.25 301	98.49 174	99.30 225
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
0.4-1-1-0.2		94.14 283	93.02 305	97.51 220	95.45 385	94.25 272	100.00 1	98.22 215	88.53 387	96.83 224	96.95 340	92.25 164	98.57 279	96.34 229	72.65 469	99.70 126

VDD-MVS		93.77 298	92.94 307	96.27 287	98.55 179	90.22 395	98.77 386	97.79 270	90.85 328	96.82 225	99.42 143	61.18 479	99.77 152	98.95 93	94.13 310	98.82 281

0.4-1-1-0.1		94.07 288	92.95 306	97.42 232	95.24 389	94.00 283	100.00 1	98.22 215	88.27 394	96.81 226	96.93 341	92.27 163	98.56 280	96.21 234	72.63 471	99.70 126

UGNet		95.33 240	94.57 251	97.62 208	98.55 179	94.85 242	98.67 395	99.32 26	95.75 109	96.80 227	96.27 365	72.18 432	99.96 78	94.58 270	99.05 154	98.04 310
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		97.23 132	96.80 141	98.51 134	99.99 1	95.60 205	99.09 336	98.84 65	93.32 212	96.74 228	99.72 96	86.04 269	100.00 1	98.01 156	99.43 131	99.94 87

tpm		93.70 302	93.41 290	94.58 346	95.36 388	87.41 435	97.01 455	96.90 419	90.85 328	96.72 229	94.14 447	90.40 200	96.84 399	90.75 345	88.54 352	99.51 180

viewdifsd2359ckpt13		96.19 202	95.77 199	97.45 227	97.62 260	94.40 265	99.70 230	97.23 357	92.76 244	96.63 230	99.05 198	84.96 293	98.64 273	96.65 220	97.35 210	99.31 222

test1111		95.57 233	94.98 239	97.37 238	98.56 176	93.37 308	98.86 376	98.45 144	94.95 127	96.63 230	98.95 221	75.21 416	99.11 210	95.02 254	98.14 188	99.64 140

tttt0517		96.85 154	96.49 155	97.92 176	97.48 273	95.89 190	99.85 150	98.54 124	90.72 338	96.63 230	98.93 226	97.47 13	99.02 215	93.03 308	95.76 277	98.85 279

viewdifsd2359ckpt09		96.21 201	95.77 199	97.53 217	97.69 251	94.50 258	99.78 184	97.23 357	92.88 235	96.58 233	99.26 171	84.85 294	98.66 270	96.61 221	97.02 236	99.43 197

viewmambaseed2359dif		95.92 213	95.55 210	97.04 256	97.38 283	93.41 305	99.78 184	96.97 409	91.14 320	96.58 233	99.27 167	84.85 294	98.75 253	96.87 209	97.12 227	98.97 269

casdiffmvs		96.42 186	95.97 186	97.77 191	97.30 295	94.98 237	99.84 155	97.09 387	93.75 194	96.58 233	99.26 171	85.07 289	98.78 248	97.77 175	97.04 233	99.54 170
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		97.76 102	97.38 112	98.92 98	99.53 99	96.84 144	99.87 135	98.14 233	93.78 191	96.55 236	99.69 106	92.28 162	99.98 52	97.13 195	99.44 130	99.93 88

viewmacassd2359aftdt		95.93 212	95.45 212	97.36 240	97.09 307	94.12 279	99.57 262	97.26 351	93.05 229	96.50 237	99.17 185	82.76 328	98.68 265	96.61 221	97.04 233	99.28 229

PatchMatch-RL		96.04 207	95.40 216	97.95 172	99.59 93	95.22 229	99.52 273	99.07 37	93.96 182	96.49 238	98.35 288	82.28 331	99.82 144	90.15 356	99.22 145	98.81 282

E4		96.01 208	95.53 211	97.44 230	97.05 311	94.23 273	99.57 262	97.30 338	92.72 245	96.47 239	99.03 200	83.98 313	98.83 232	96.92 206	96.77 244	99.27 232

E5new		95.83 217	95.39 217	97.15 248	97.03 312	93.59 295	99.32 308	97.30 338	92.58 258	96.45 240	99.00 207	83.37 320	98.81 239	96.81 212	96.65 247	99.04 261

E6new		95.83 217	95.39 217	97.14 250	97.00 319	93.58 297	99.31 310	97.30 338	92.57 260	96.45 240	99.01 203	83.44 318	98.81 239	96.80 214	96.66 245	99.04 261

E6		95.83 217	95.39 217	97.14 250	97.00 319	93.58 297	99.31 310	97.30 338	92.57 260	96.45 240	99.01 203	83.44 318	98.81 239	96.80 214	96.66 245	99.04 261

E5		95.83 217	95.39 217	97.15 248	97.03 312	93.59 295	99.32 308	97.30 338	92.58 258	96.45 240	99.00 207	83.37 320	98.81 239	96.81 212	96.65 247	99.04 261

MP-MVS-pluss		98.07 79	97.64 97	99.38 50	99.74 78	98.41 71	99.74 207	98.18 223	93.35 210	96.45 240	99.85 38	92.64 149	99.97 65	98.91 99	99.89 74	99.77 117
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ADS-MVSNet2		93.80 297	93.88 273	93.55 395	97.87 232	85.94 447	94.24 483	96.84 423	90.07 355	96.43 245	94.48 439	90.29 203	95.37 460	87.44 395	97.23 215	99.36 208

ADS-MVSNet		94.79 256	94.02 268	97.11 254	97.87 232	93.79 287	94.24 483	98.16 229	90.07 355	96.43 245	94.48 439	90.29 203	98.19 323	87.44 395	97.23 215	99.36 208

ACMMP		97.74 104	97.44 109	98.66 114	99.92 37	96.13 183	99.18 328	99.45 18	94.84 134	96.41 247	99.71 99	91.40 178	99.99 40	97.99 158	98.03 193	99.87 101
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		97.27 129	96.81 140	98.66 114	98.81 159	96.67 155	99.92 104	98.64 91	94.51 146	96.38 248	98.49 278	89.05 220	99.88 126	97.10 197	98.34 177	99.43 197

AUN-MVS		93.28 310	92.60 315	95.34 319	98.29 203	90.09 398	99.31 310	98.56 114	91.80 295	96.35 249	98.00 303	89.38 213	98.28 315	92.46 312	69.22 482	97.64 322

FA-MVS(test-final)		95.86 214	95.09 234	98.15 160	97.74 242	95.62 204	96.31 470	98.17 224	91.42 311	96.26 250	96.13 371	90.56 197	99.47 190	92.18 316	97.07 229	99.35 212

thres200		96.96 148	96.21 171	99.22 60	98.97 141	98.84 40	99.85 150	99.71 7	93.17 220	96.26 250	98.88 229	89.87 207	99.51 180	94.26 277	94.91 299	99.31 222

HyFIR lowres test		96.66 170	96.43 160	97.36 240	99.05 130	93.91 286	99.70 230	99.80 3	90.54 342	96.26 250	98.08 300	92.15 168	98.23 321	96.84 210	95.46 289	99.93 88

Elysia		94.50 270	93.38 292	97.85 182	96.49 348	96.70 151	98.98 355	97.78 274	90.81 330	96.19 253	98.55 274	73.63 427	98.98 217	89.41 362	98.56 171	97.88 313

StellarMVS		94.50 270	93.38 292	97.85 182	96.49 348	96.70 151	98.98 355	97.78 274	90.81 330	96.19 253	98.55 274	73.63 427	98.98 217	89.41 362	98.56 171	97.88 313

dtuplus		95.79 222	95.42 214	96.93 260	97.24 301	93.16 310	99.78 184	96.93 416	91.69 299	96.18 255	99.29 162	83.80 314	98.73 255	96.83 211	97.02 236	98.89 278

SCA		94.69 261	93.81 275	97.33 243	97.10 306	94.44 259	98.86 376	98.32 199	93.30 213	96.17 256	95.59 389	76.48 402	97.95 338	91.06 336	97.43 204	99.59 156

viewdifsd2359ckpt07		95.83 217	95.42 214	97.07 255	97.40 280	93.04 315	99.60 254	97.24 355	92.39 271	96.09 257	99.14 190	83.07 327	98.93 224	97.02 199	96.87 241	99.23 239

hybridcas		96.09 205	95.62 207	97.50 222	97.37 285	94.44 259	99.84 155	97.16 367	93.16 221	96.03 258	99.21 180	84.19 309	98.65 272	96.53 225	97.07 229	99.42 200

casdiffmvs_mvg		96.43 184	95.94 191	97.89 180	97.44 276	95.47 208	99.86 147	97.29 346	93.35 210	96.03 258	99.19 183	85.39 284	98.72 258	97.89 166	97.04 233	99.49 184
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		96.79 157	95.99 181	99.19 63	98.94 143	98.82 41	99.78 184	99.71 7	92.86 236	96.02 260	98.87 236	89.33 214	99.50 182	93.84 286	94.57 303	99.27 232

thres400		96.78 159	95.99 181	99.16 70	98.94 143	98.82 41	99.78 184	99.71 7	92.86 236	96.02 260	98.87 236	89.33 214	99.50 182	93.84 286	94.57 303	99.16 245

dp		95.05 247	94.43 253	96.91 261	97.99 225	92.73 323	96.29 471	97.98 249	89.70 362	95.93 262	94.67 434	93.83 112	98.45 290	86.91 409	96.53 251	99.54 170

thres100view900		96.74 165	95.92 193	99.18 64	98.90 153	98.77 49	99.74 207	99.71 7	92.59 256	95.84 263	98.86 238	89.25 216	99.50 182	93.84 286	94.57 303	99.27 232

thres600view7		96.69 168	95.87 197	99.14 74	98.90 153	98.78 48	99.74 207	99.71 7	92.59 256	95.84 263	98.86 238	89.25 216	99.50 182	93.44 299	94.50 306	99.16 245

EPP-MVSNet		96.69 168	96.60 150	96.96 259	97.74 242	93.05 314	99.37 300	98.56 114	88.75 381	95.83 265	99.01 203	96.01 41	98.56 280	96.92 206	97.20 217	99.25 236

TESTMET0.1,1		96.74 165	96.26 167	98.16 157	97.36 288	96.48 163	99.96 57	98.29 205	91.93 288	95.77 266	98.07 301	95.54 52	98.29 313	90.55 348	98.89 158	99.70 126

viewdifsd2359ckpt11		94.09 286	93.63 277	95.46 314	96.68 344	88.92 415	99.62 247	97.12 376	93.07 227	95.73 267	99.22 177	77.05 390	98.88 227	96.52 226	87.69 365	98.58 293

viewmsd2359difaftdt		94.09 286	93.64 276	95.46 314	96.68 344	88.92 415	99.62 247	97.13 375	93.07 227	95.73 267	99.22 177	77.05 390	98.89 226	96.52 226	87.70 364	98.58 293

F-COLMAP		96.93 151	96.95 131	96.87 264	99.71 84	91.74 354	99.85 150	97.95 252	93.11 226	95.72 269	99.16 188	92.35 160	99.94 96	95.32 248	99.35 138	98.92 274

icg_test_0407_2		95.04 248	94.78 247	95.84 303	96.97 321	91.64 362	98.63 398	97.12 376	92.33 274	95.60 270	98.88 229	85.65 275	96.56 415	92.12 317	95.70 281	99.32 217

IMVS_0407		95.21 242	94.80 246	96.46 279	96.97 321	91.64 362	98.81 381	97.12 376	92.33 274	95.60 270	98.88 229	85.65 275	98.42 293	92.12 317	95.70 281	99.32 217

test-LLR		96.47 181	96.04 179	97.78 189	97.02 315	95.44 210	99.96 57	98.21 219	94.07 175	95.55 272	96.38 360	93.90 108	98.27 318	90.42 351	98.83 163	99.64 140

test-mter		96.39 187	95.93 192	97.78 189	97.02 315	95.44 210	99.96 57	98.21 219	91.81 294	95.55 272	96.38 360	95.17 61	98.27 318	90.42 351	98.83 163	99.64 140

IS-MVSNet		96.29 195	95.90 194	97.45 227	98.13 218	94.80 246	99.08 338	97.61 294	92.02 287	95.54 274	98.96 216	90.64 195	98.08 329	93.73 294	97.41 207	99.47 186

IMVS_0403		95.25 241	94.81 245	96.58 276	96.97 321	91.64 362	98.97 360	97.12 376	92.33 274	95.43 275	98.88 229	85.78 273	98.79 246	92.12 317	95.70 281	99.32 217

CHOSEN 1792x2688		96.81 156	96.53 153	97.64 204	98.91 152	93.07 312	99.65 240	99.80 3	95.64 112	95.39 276	98.86 238	84.35 308	99.90 115	96.98 202	99.16 146	99.95 83

CDS-MVSNet		96.34 191	96.07 177	97.13 252	97.37 285	94.96 238	99.53 272	97.91 258	91.55 303	95.37 277	98.32 291	95.05 66	97.13 375	93.80 290	95.75 278	99.30 225
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		94.53 268	95.30 225	92.22 420	97.77 240	82.54 470	99.59 256	97.06 397	94.92 130	95.29 278	95.37 404	85.81 272	97.89 341	94.80 263	97.07 229	96.23 342

SSM_0404		95.75 224	95.16 231	97.50 222	97.53 268	95.39 215	99.11 334	97.25 352	90.81 330	95.27 279	98.83 243	84.74 298	98.67 267	95.24 250	97.69 198	98.45 296

CSCG		97.10 139	97.04 128	97.27 246	99.89 51	91.92 344	99.90 118	99.07 37	88.67 383	95.26 280	99.82 54	93.17 133	99.98 52	98.15 148	99.47 126	99.90 97

Vis-MVSNet (Re-imp)		96.32 192	95.98 183	97.35 242	97.93 229	94.82 245	99.47 283	98.15 232	91.83 292	95.09 281	99.11 191	91.37 179	97.47 356	93.47 298	97.43 204	99.74 120

TAMVS		95.85 215	95.58 208	96.65 273	97.07 309	93.50 302	99.17 329	97.82 269	91.39 313	95.02 282	98.01 302	92.20 166	97.30 365	93.75 293	95.83 273	99.14 248

XVG-OURS-SEG-HR		94.79 256	94.70 250	95.08 326	98.05 222	89.19 410	99.08 338	97.54 303	93.66 196	94.87 283	99.58 129	78.78 375	99.79 147	97.31 187	93.40 320	96.25 340

dtuonly		93.89 291	93.16 300	96.08 292	94.37 404	91.67 361	99.15 331	95.04 477	91.79 296	94.74 284	98.72 251	81.01 348	98.31 310	87.29 399	96.33 258	98.27 304

XVG-OURS		94.82 253	94.74 249	95.06 327	98.00 224	89.19 410	99.08 338	97.55 301	94.10 173	94.71 285	99.62 124	80.51 358	99.74 158	96.04 236	93.06 325	96.25 340

casdiffseed414692147		95.07 246	94.26 259	97.50 222	97.01 318	94.70 249	99.58 258	97.02 401	91.27 315	94.66 286	98.82 245	80.79 353	98.55 283	93.39 300	95.79 275	99.27 232

nomal-1		96.23 200	96.10 176	96.64 274	97.64 257	92.37 334	99.76 196	98.09 236	91.73 298	94.59 287	97.47 319	93.31 126	98.45 290	96.77 216	95.52 288	99.10 253

ab-mvs		94.69 261	93.42 288	98.51 134	98.07 221	96.26 173	96.49 466	98.68 84	90.31 351	94.54 288	97.00 338	76.30 404	99.71 162	95.98 237	93.38 321	99.56 165

TAPA-MVS	92.12 8	94.42 274	93.60 280	96.90 263	99.33 111	91.78 353	99.78 184	98.00 246	89.89 360	94.52 289	99.47 139	91.97 172	99.18 206	69.90 489	99.52 116	99.73 121
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TR-MVS		94.54 266	93.56 283	97.49 225	97.96 227	94.34 269	98.71 390	97.51 308	90.30 352	94.51 290	98.69 255	75.56 410	98.77 249	92.82 310	95.99 265	99.35 212

Fast-Effi-MVS+		95.02 249	94.19 261	97.52 219	97.88 231	94.55 254	99.97 43	97.08 388	88.85 379	94.47 291	97.96 307	84.59 303	98.41 295	89.84 360	97.10 228	99.59 156

mamba_0408		94.98 251	94.09 264	97.64 204	97.14 303	95.31 221	93.48 493	97.08 388	90.48 344	94.40 292	98.62 264	84.49 304	98.67 267	93.99 281	97.18 219	98.93 271

SSM_04072		94.77 258	94.09 264	96.82 265	97.14 303	95.31 221	93.48 493	97.08 388	90.48 344	94.40 292	98.62 264	84.49 304	96.21 438	93.99 281	97.18 219	98.93 271

SSM_0407		95.62 232	94.95 240	97.61 209	97.14 303	95.31 221	99.00 353	97.25 352	90.81 330	94.40 292	98.83 243	84.74 298	98.58 277	95.24 250	97.18 219	98.93 271

DeepC-MVS	94.51 4	96.92 152	96.40 163	98.45 139	99.16 123	95.90 189	99.66 239	98.06 240	96.37 90	94.37 295	99.49 138	83.29 324	99.90 115	97.63 180	99.61 106	99.55 166
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RPSCF		91.80 348	92.79 311	88.83 455	98.15 216	69.87 501	98.11 428	96.60 437	83.93 446	94.33 296	99.27 167	79.60 367	99.46 191	91.99 322	93.16 323	97.18 333

WB-MVSnew		92.90 320	92.77 312	93.26 402	96.95 326	93.63 294	99.71 223	98.16 229	91.49 304	94.28 297	98.14 298	81.33 344	96.48 421	79.47 459	95.46 289	89.68 489

BH-RMVSNet		95.18 243	94.31 258	97.80 185	98.17 214	95.23 228	99.76 196	97.53 305	92.52 265	94.27 298	99.25 174	76.84 396	98.80 244	90.89 342	99.54 113	99.35 212

CVMVSNet		94.68 263	94.94 241	93.89 385	96.80 336	86.92 440	99.06 343	98.98 41	94.45 150	94.23 299	99.02 201	85.60 278	95.31 462	90.91 341	95.39 292	99.43 197

baseline1		95.78 223	94.86 242	98.54 129	98.47 189	98.07 82	99.06 343	97.99 247	92.68 250	94.13 300	98.62 264	93.28 128	98.69 264	93.79 291	85.76 377	98.84 280

Anonymous202405211		93.10 316	91.99 329	96.40 282	99.10 126	89.65 406	98.88 372	97.93 254	83.71 448	94.00 301	98.75 248	68.79 445	99.88 126	95.08 253	91.71 327	99.68 132

cascas		94.64 264	93.61 278	97.74 195	97.82 236	96.26 173	99.96 57	97.78 274	85.76 427	94.00 301	97.54 318	76.95 395	99.21 201	97.23 192	95.43 291	97.76 319

Anonymous20240529		92.10 341	90.65 353	96.47 277	98.82 158	90.61 386	98.72 389	98.67 87	75.54 488	93.90 303	98.58 270	66.23 459	99.90 115	94.70 267	90.67 331	98.90 277

LS3D		95.84 216	95.11 233	98.02 169	99.85 62	95.10 235	98.74 387	98.50 138	87.22 408	93.66 304	99.86 34	87.45 244	99.95 87	90.94 340	99.81 87	99.02 266

GeoE		94.36 278	93.48 286	96.99 258	97.29 296	93.54 301	99.96 57	96.72 432	88.35 392	93.43 305	98.94 223	82.05 332	98.05 332	88.12 390	96.48 254	99.37 206

HQP-NCC					95.78 365		99.87 135		96.82 67	93.37 306

ACMP_Plane					95.78 365		99.87 135		96.82 67	93.37 306

HQP4-MVS										93.37 306			98.39 299			94.53 348

HQP-MVS		94.61 265	94.50 252	94.92 332	95.78 365	91.85 347	99.87 135	97.89 260	96.82 67	93.37 306	98.65 259	80.65 356	98.39 299	97.92 162	89.60 333	94.53 348

MonoMVSNet		94.82 253	94.43 253	95.98 294	94.54 401	90.73 382	99.03 350	97.06 397	93.16 221	93.15 310	95.47 397	88.29 230	97.57 352	97.85 167	91.33 330	99.62 149

HQP_MVS		94.49 272	94.36 255	94.87 333	95.71 375	91.74 354	99.84 155	97.87 262	96.38 87	93.01 311	98.59 267	80.47 360	98.37 305	97.79 173	89.55 336	94.52 350

plane_prior3						91.64 362			96.63 76	93.01 311

GA-MVS		93.83 293	92.84 308	96.80 266	95.73 372	93.57 299	99.88 132	97.24 355	92.57 260	92.92 313	96.66 352	78.73 376	97.67 349	87.75 393	94.06 312	99.17 244

tpm cat1		93.51 306	92.52 321	96.47 277	97.77 240	91.47 371	96.13 473	98.06 240	80.98 466	92.91 314	93.78 450	89.66 208	98.87 228	87.03 405	96.39 256	99.09 254

1112_ss		96.01 208	95.20 229	98.42 143	97.80 237	96.41 166	99.65 240	96.66 434	92.71 247	92.88 315	99.40 149	92.16 167	99.30 196	91.92 324	93.66 316	99.55 166

Test_1112_low_res		95.72 225	94.83 243	98.42 143	97.79 238	96.41 166	99.65 240	96.65 435	92.70 248	92.86 316	96.13 371	92.15 168	99.30 196	91.88 325	93.64 317	99.55 166

IB-MVS	92.85 6	94.99 250	93.94 271	98.16 157	97.72 247	95.69 201	99.99 8	98.81 67	94.28 165	92.70 317	96.90 342	95.08 64	99.17 207	96.07 235	73.88 463	99.60 155
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		93.72 301	93.86 274	93.29 400	97.06 310	86.16 444	99.80 178	96.83 424	92.66 251	92.58 318	97.83 314	81.39 342	97.67 349	89.75 361	96.87 241	96.05 345

SDMVSNet		94.80 255	93.96 270	97.33 243	98.92 148	95.42 212	99.59 256	98.99 40	92.41 269	92.55 319	97.85 312	75.81 409	98.93 224	97.90 165	91.62 328	97.64 322

sd_testset		93.55 305	92.83 309	95.74 307	98.92 148	90.89 380	98.24 420	98.85 62	92.41 269	92.55 319	97.85 312	71.07 440	98.68 265	93.93 283	91.62 328	97.64 322

dmvs_re		93.20 312	93.15 301	93.34 398	96.54 347	83.81 459	98.71 390	98.51 132	91.39 313	92.37 321	98.56 272	78.66 377	97.83 343	93.89 284	89.74 332	98.38 300

tpmvs		94.28 280	93.57 282	96.40 282	98.55 179	91.50 370	95.70 481	98.55 120	87.47 403	92.15 322	94.26 445	91.42 177	98.95 223	88.15 388	95.85 272	98.76 284

Syy-MVS		90.00 389	90.63 354	88.11 464	97.68 252	74.66 497	99.71 223	98.35 192	90.79 334	92.10 323	98.67 256	79.10 373	93.09 488	63.35 507	95.95 269	96.59 338

myMVS_eth3d		94.46 273	94.76 248	93.55 395	97.68 252	90.97 375	99.71 223	98.35 192	90.79 334	92.10 323	98.67 256	92.46 158	93.09 488	87.13 402	95.95 269	96.59 338

BH-w/o		95.71 227	95.38 222	96.68 271	98.49 188	92.28 335	99.84 155	97.50 309	92.12 282	92.06 325	98.79 246	84.69 301	98.67 267	95.29 249	99.66 97	99.09 254

VPA-MVSNet		92.70 327	91.55 340	96.16 289	95.09 391	96.20 179	98.88 372	99.00 39	91.02 325	91.82 326	95.29 410	76.05 408	97.96 337	95.62 246	81.19 415	94.30 367

baseline2		96.71 167	96.49 155	97.37 238	95.63 381	95.96 188	99.74 207	98.88 55	92.94 232	91.61 327	98.97 214	97.72 7	98.62 275	94.83 262	98.08 192	97.53 329

OPM-MVS		93.21 311	92.80 310	94.44 355	93.12 428	90.85 381	99.77 190	97.61 294	96.19 96	91.56 328	98.65 259	75.16 417	98.47 286	93.78 292	89.39 339	93.99 409
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EI-MVSNet		93.73 300	93.40 291	94.74 338	96.80 336	92.69 324	99.06 343	97.67 284	88.96 374	91.39 329	99.02 201	88.75 227	97.30 365	91.07 335	87.85 360	94.22 376

MVSTER		95.53 234	95.22 228	96.45 280	98.56 176	97.72 101	99.91 112	97.67 284	92.38 272	91.39 329	97.14 329	97.24 20	97.30 365	94.80 263	87.85 360	94.34 366

testing3		93.92 290	94.23 260	92.99 409	97.54 267	90.23 394	99.99 8	99.16 33	90.57 341	91.33 331	98.63 263	92.99 136	92.52 492	82.46 440	95.39 292	96.22 343

test_fmvs2		89.47 398	89.70 373	88.77 458	94.54 401	75.74 493	99.83 163	94.70 485	94.71 139	91.08 332	96.82 350	54.46 488	97.78 346	92.87 309	88.27 355	92.80 450

BH-untuned		95.18 243	94.83 243	96.22 288	98.36 196	91.22 373	99.80 178	97.32 336	90.91 326	91.08 332	98.67 256	83.51 316	98.54 284	94.23 278	99.61 106	98.92 274

CLD-MVS		94.06 289	93.90 272	94.55 348	96.02 359	90.69 383	99.98 24	97.72 280	96.62 78	91.05 334	98.85 241	77.21 388	98.47 286	98.11 150	89.51 338	94.48 352
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS		96.60 173	95.56 209	99.72 15	96.85 333	99.22 23	98.31 416	98.94 44	91.57 302	90.90 335	99.61 125	86.66 259	99.96 78	97.36 186	99.88 77	99.99 26

IMVS_0404		93.83 293	93.17 299	95.80 305	96.97 321	91.64 362	97.78 439	97.12 376	92.33 274	90.87 336	98.88 229	76.78 397	96.43 424	92.12 317	95.70 281	99.32 217

SD_0403		92.63 331	93.38 292	90.40 443	97.32 293	77.91 490	97.75 440	98.03 245	91.89 289	90.83 337	98.29 295	82.00 333	93.79 481	88.51 379	95.75 278	99.52 175

MSDG		94.37 276	93.36 295	97.40 236	98.88 155	93.95 285	99.37 300	97.38 321	85.75 429	90.80 338	99.17 185	84.11 312	99.88 126	86.35 410	98.43 176	98.36 301

VPNet		91.81 345	90.46 356	95.85 302	94.74 397	95.54 207	98.98 355	98.59 104	92.14 281	90.77 339	97.44 321	68.73 447	97.54 354	94.89 261	77.89 442	94.46 353

MIMVSNet		90.30 380	88.67 395	95.17 325	96.45 350	91.64 362	92.39 499	97.15 370	85.99 424	90.50 340	93.19 459	66.95 455	94.86 470	82.01 444	93.43 319	99.01 267

mvs_anonymous		95.65 231	95.03 237	97.53 217	98.19 212	95.74 196	99.33 305	97.49 310	90.87 327	90.47 341	97.10 331	88.23 231	97.16 372	95.92 238	97.66 201	99.68 132

Patchmatch-test		92.65 330	91.50 341	96.10 291	96.85 333	90.49 389	91.50 504	97.19 361	82.76 458	90.23 342	95.59 389	95.02 67	98.00 334	77.41 472	96.98 239	99.82 108

usedtu_dtu_shiyan1		92.78 323	91.73 334	95.92 298	93.03 432	96.82 145	99.83 163	97.79 270	90.58 339	90.09 343	95.04 419	84.75 296	96.72 408	88.19 386	86.23 374	94.23 373

FE-MVSNET3		92.78 323	91.73 334	95.92 298	93.03 432	96.82 145	99.83 163	97.79 270	90.58 339	90.09 343	95.04 419	84.75 296	96.72 408	88.20 385	86.23 374	94.23 373

LPG-MVS_test		92.96 318	92.71 313	93.71 389	95.43 386	88.67 420	99.75 203	97.62 291	92.81 239	90.05 345	98.49 278	75.24 413	98.40 297	95.84 240	89.12 340	94.07 400

LGP-MVS_train				93.71 389	95.43 386	88.67 420		97.62 291	92.81 239	90.05 345	98.49 278	75.24 413	98.40 297	95.84 240	89.12 340	94.07 400

DP-MVS		94.54 266	93.42 288	97.91 178	99.46 106	94.04 280	98.93 366	97.48 311	81.15 465	90.04 347	99.55 133	87.02 252	99.95 87	88.97 371	98.11 189	99.73 121

test_djsdf		92.83 322	92.29 324	94.47 353	91.90 456	92.46 331	99.55 269	97.27 348	91.17 317	89.96 348	96.07 374	81.10 346	96.89 395	94.67 268	88.91 342	94.05 403

ACMM	91.95 10	92.88 321	92.52 321	93.98 381	95.75 371	89.08 414	99.77 190	97.52 307	93.00 230	89.95 349	97.99 305	76.17 406	98.46 289	93.63 297	88.87 344	94.39 360
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
1314		96.84 155	95.96 187	99.48 41	96.74 341	98.52 65	98.31 416	98.86 59	95.82 106	89.91 350	98.98 212	87.49 243	99.96 78	97.80 170	99.73 92	99.96 75

XVG-ACMP-BASELINE		91.22 360	90.75 351	92.63 416	93.73 417	85.61 448	98.52 405	97.44 314	92.77 243	89.90 351	96.85 346	66.64 458	98.39 299	92.29 314	88.61 349	93.89 417

miper_enhance_ethall		94.36 278	93.98 269	95.49 310	98.68 167	95.24 227	99.73 214	97.29 346	93.28 214	89.86 352	95.97 376	94.37 90	97.05 381	92.20 315	84.45 390	94.19 379

nrg030		93.51 306	92.53 320	96.45 280	94.36 405	97.20 126	99.81 172	97.16 367	91.60 301	89.86 352	97.46 320	86.37 263	97.68 348	95.88 239	80.31 428	94.46 353

V42		91.28 357	90.12 368	94.74 338	93.42 423	93.46 303	99.68 236	97.02 401	87.36 405	89.85 354	95.05 418	81.31 345	97.34 360	87.34 398	80.07 430	93.40 435

v144192		90.79 368	89.52 378	94.59 345	93.11 429	92.77 319	99.56 266	96.99 405	86.38 420	89.82 355	94.95 427	80.50 359	97.10 378	83.98 429	80.41 426	93.90 416

GBi-Net		90.88 365	89.82 371	94.08 373	97.53 268	91.97 340	98.43 409	96.95 411	87.05 409	89.68 356	94.72 430	71.34 436	96.11 441	87.01 406	85.65 378	94.17 381

test1		90.88 365	89.82 371	94.08 373	97.53 268	91.97 340	98.43 409	96.95 411	87.05 409	89.68 356	94.72 430	71.34 436	96.11 441	87.01 406	85.65 378	94.17 381

FMVSNet3		92.69 328	91.58 338	95.99 293	98.29 203	97.42 118	99.26 322	97.62 291	89.80 361	89.68 356	95.32 406	81.62 341	96.27 435	87.01 406	85.65 378	94.29 368

IterMVS-LS		92.69 328	92.11 326	94.43 357	96.80 336	92.74 321	99.45 288	96.89 420	88.98 372	89.65 359	95.38 403	88.77 226	96.34 431	90.98 339	82.04 409	94.22 376
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		94.52 269	94.03 267	95.98 294	98.38 193	96.68 154	99.92 104	97.63 288	90.75 337	89.64 360	95.25 412	96.77 27	96.90 394	94.35 275	83.57 397	94.35 364

v1144		91.09 361	89.83 370	94.87 333	93.25 425	93.69 292	99.62 247	96.98 407	86.83 415	89.64 360	94.99 425	80.94 349	97.05 381	85.08 422	81.16 416	93.87 419

v1921920		90.46 375	89.12 385	94.50 351	92.96 436	92.46 331	99.49 279	96.98 407	86.10 423	89.61 362	95.30 407	78.55 379	97.03 386	82.17 443	80.89 424	94.01 406

VortexMVS		94.11 284	93.50 285	95.94 296	97.70 250	96.61 158	99.35 303	97.18 363	93.52 202	89.57 363	95.74 380	87.55 241	96.97 389	95.76 243	85.13 385	94.23 373

v1192		90.62 373	89.25 383	94.72 340	93.13 426	93.07 312	99.50 277	97.02 401	86.33 421	89.56 364	95.01 422	79.22 370	97.09 380	82.34 442	81.16 416	94.01 406

PCF-MVS	94.20 5	95.18 243	94.10 263	98.43 141	98.55 179	95.99 187	97.91 435	97.31 337	90.35 349	89.48 365	99.22 177	85.19 288	99.89 120	90.40 353	98.47 175	99.41 201
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
3Dnovator	91.47 12	96.28 196	95.34 223	99.08 83	96.82 335	97.47 116	99.45 288	98.81 67	95.52 117	89.39 366	99.00 207	81.97 334	99.95 87	97.27 188	99.83 81	99.84 105

v1240		90.20 383	88.79 392	94.44 355	93.05 431	92.27 336	99.38 298	96.92 418	85.89 425	89.36 367	94.87 429	77.89 385	97.03 386	80.66 452	81.08 419	94.01 406

FIs		94.10 285	93.43 287	96.11 290	94.70 398	96.82 145	99.58 258	98.93 48	92.54 263	89.34 368	97.31 325	87.62 239	97.10 378	94.22 279	86.58 371	94.40 359

ITE_SJBPF				92.38 417	95.69 378	85.14 451		95.71 460	92.81 239	89.33 369	98.11 299	70.23 442	98.42 293	85.91 416	88.16 357	93.59 432

v2v482		91.30 355	90.07 369	95.01 328	93.13 426	93.79 287	99.77 190	97.02 401	88.05 396	89.25 370	95.37 404	80.73 354	97.15 373	87.28 400	80.04 431	94.09 399

UniMVSNet (Re)		93.07 317	92.13 325	95.88 300	94.84 395	96.24 178	99.88 132	98.98 41	92.49 267	89.25 370	95.40 400	87.09 250	97.14 374	93.13 306	78.16 440	94.26 369

tt0805		91.28 357	90.18 365	94.60 344	96.26 353	87.55 433	98.39 414	98.72 78	89.00 371	89.22 372	98.47 282	62.98 472	98.96 221	90.57 347	88.00 359	97.28 332

UniMVSNet_NR-MVSNet		92.95 319	92.11 326	95.49 310	94.61 400	95.28 225	99.83 163	99.08 36	91.49 304	89.21 373	96.86 345	87.14 249	96.73 406	93.20 302	77.52 445	94.46 353

DU-MVS		92.46 334	91.45 343	95.49 310	94.05 411	95.28 225	99.81 172	98.74 76	92.25 280	89.21 373	96.64 354	81.66 339	96.73 406	93.20 302	77.52 445	94.46 353

eth_miper_zixun_eth		92.41 335	91.93 330	93.84 386	97.28 297	90.68 384	98.83 379	96.97 409	88.57 386	89.19 375	95.73 383	89.24 218	96.69 410	89.97 359	81.55 412	94.15 387

cl22		93.77 298	93.25 298	95.33 320	99.49 103	94.43 261	99.61 251	98.09 236	90.38 347	89.16 376	95.61 387	90.56 197	97.34 360	91.93 323	84.45 390	94.21 378

Baseline_NR-MVSNet		90.33 379	89.51 379	92.81 413	92.84 439	89.95 402	99.77 190	93.94 494	84.69 442	89.04 377	95.66 385	81.66 339	96.52 417	90.99 338	76.98 451	91.97 465

FC-MVSNet-test		93.81 296	93.15 301	95.80 305	94.30 407	96.20 179	99.42 290	98.89 52	92.33 274	89.03 378	97.27 327	87.39 245	96.83 401	93.20 302	86.48 372	94.36 361

QAPM		95.40 237	94.17 262	99.10 80	96.92 327	97.71 102	99.40 292	98.68 84	89.31 365	88.94 379	98.89 228	82.48 330	99.96 78	93.12 307	99.83 81	99.62 149

miper_ehance_all_eth		93.16 314	92.60 315	94.82 337	97.57 264	93.56 300	99.50 277	97.07 396	88.75 381	88.85 380	95.52 393	90.97 188	96.74 405	90.77 344	84.45 390	94.17 381

AllTest		92.48 333	91.64 336	95.00 329	99.01 133	88.43 424	98.94 363	96.82 426	86.50 418	88.71 381	98.47 282	74.73 419	99.88 126	85.39 418	96.18 261	96.71 336

TestCases				95.00 329	99.01 133	88.43 424		96.82 426	86.50 418	88.71 381	98.47 282	74.73 419	99.88 126	85.39 418	96.18 261	96.71 336

blend_shiyan4		90.13 387	88.79 392	94.17 364	87.12 489	91.83 349	99.75 203	97.08 388	79.27 478	88.69 383	92.53 464	92.25 164	96.50 418	89.35 365	73.04 467	94.18 380

c3_l		92.53 332	91.87 332	94.52 349	97.40 280	92.99 317	99.40 292	96.93 416	87.86 399	88.69 383	95.44 398	89.95 206	96.44 423	90.45 350	80.69 425	94.14 391

pmmvs4		92.10 341	91.07 349	95.18 324	92.82 442	94.96 238	99.48 282	96.83 424	87.45 404	88.66 385	96.56 358	83.78 315	96.83 401	89.29 367	84.77 388	93.75 425

SSC-MVS3.2		89.59 396	88.66 396	92.38 417	94.29 408	86.12 445	99.49 279	97.66 287	90.28 353	88.63 386	95.18 414	64.46 466	96.88 397	85.30 420	82.66 403	94.14 391

gbinet_0.2-2-1-0.02		87.63 418	85.51 425	93.99 379	87.22 488	91.56 369	99.81 172	97.36 325	79.54 473	88.60 387	93.29 458	73.76 425	96.34 431	89.27 368	60.78 508	94.06 402

kuosan		93.17 313	92.60 315	94.86 336	98.40 192	89.54 408	98.44 408	98.53 127	84.46 443	88.49 388	97.92 308	90.57 196	97.05 381	83.10 435	93.49 318	97.99 311

PS-MVSNAJss		93.64 303	93.31 296	94.61 343	92.11 453	92.19 337	99.12 332	97.38 321	92.51 266	88.45 389	96.99 339	91.20 181	97.29 368	94.36 273	87.71 362	94.36 361

blended_shiyan8		87.82 414	85.71 421	94.16 365	86.54 498	91.79 351	99.72 218	97.08 388	79.32 476	88.44 390	92.35 472	77.88 386	96.56 415	88.53 377	61.51 502	94.15 387

UniMVSNet_ETH3D		90.06 388	88.58 397	94.49 352	94.67 399	88.09 429	97.81 438	97.57 299	83.91 447	88.44 390	97.41 322	57.44 485	97.62 351	91.41 330	88.59 351	97.77 318

TranMVSNet+NR-MVSNet		91.68 352	90.61 355	94.87 333	93.69 418	93.98 284	99.69 233	98.65 88	91.03 324	88.44 390	96.83 349	80.05 364	96.18 439	90.26 355	76.89 453	94.45 358

FMVSNet2		91.02 362	89.56 376	95.41 317	97.53 268	95.74 196	98.98 355	97.41 319	87.05 409	88.43 393	95.00 424	71.34 436	96.24 437	85.12 421	85.21 383	94.25 371

COLMAP_ROB	90.47 14	92.18 340	91.49 342	94.25 363	99.00 137	88.04 430	98.42 412	96.70 433	82.30 460	88.43 393	99.01 203	76.97 394	99.85 132	86.11 414	96.50 252	94.86 347
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	96.31 193	95.24 227	99.52 34	96.88 332	98.64 61	99.72 218	98.24 212	95.27 123	88.42 395	98.98 212	82.76 328	99.94 96	97.10 197	99.83 81	99.96 75

wanda-best-256-512		87.82 414	85.71 421	94.15 367	86.66 493	91.88 345	99.76 196	97.08 388	79.46 474	88.37 396	92.36 469	78.01 382	96.43 424	88.39 381	61.26 503	94.14 391

FE-blended-shiyan7		87.82 414	85.71 421	94.15 367	86.66 493	91.88 345	99.76 196	97.08 388	79.46 474	88.37 396	92.36 469	78.01 382	96.43 424	88.39 381	61.26 503	94.14 391

usedtu_blend_shiyan5		86.75 422	84.29 430	94.16 365	86.66 493	91.83 349	97.42 443	95.23 472	69.94 500	88.37 396	92.36 469	78.01 382	96.50 418	89.35 365	61.26 503	94.14 391

v148		90.70 369	89.63 374	93.92 382	92.97 435	90.97 375	99.75 203	96.89 420	87.51 402	88.27 399	95.01 422	81.67 338	97.04 384	87.40 397	77.17 450	93.75 425

blended_shiyan6		87.74 417	85.62 424	94.09 372	86.53 499	91.73 357	99.72 218	97.08 388	79.32 476	88.22 400	92.31 474	77.82 387	96.43 424	88.31 383	61.26 503	94.13 396

DSMNet-mixed		88.28 408	88.24 402	88.42 461	89.64 479	75.38 496	98.06 430	89.86 511	85.59 431	88.20 401	92.14 475	76.15 407	91.95 496	78.46 468	96.05 264	97.92 312

WR-MVS		92.31 337	91.25 345	95.48 313	94.45 403	95.29 224	99.60 254	98.68 84	90.10 354	88.07 402	96.89 343	80.68 355	96.80 403	93.14 305	79.67 432	94.36 361

test0.0.03 1		93.86 292	93.61 278	94.64 342	95.02 394	92.18 338	99.93 101	98.58 106	94.07 175	87.96 403	98.50 277	93.90 108	94.96 466	81.33 447	93.17 322	96.78 335

XXY-MVS		91.82 344	90.46 356	95.88 300	93.91 414	95.40 214	98.87 375	97.69 283	88.63 385	87.87 404	97.08 332	74.38 422	97.89 341	91.66 327	84.07 394	94.35 364

reproduce_monomvs		95.38 238	95.07 235	96.32 286	99.32 113	96.60 159	99.76 196	98.85 62	96.65 75	87.83 405	96.05 375	99.52 1	98.11 327	96.58 223	81.07 420	94.25 371

Patchmtry		89.70 394	88.49 398	93.33 399	96.24 354	89.94 404	91.37 505	96.23 447	78.22 481	87.69 406	93.31 456	91.04 186	96.03 446	80.18 458	82.10 408	94.02 404

DIV-MVS_self_test		92.32 336	91.60 337	94.47 353	97.31 294	92.74 321	99.58 258	96.75 430	86.99 412	87.64 407	95.54 391	89.55 211	96.50 418	88.58 375	82.44 406	94.17 381

D2MVS		92.76 325	92.59 319	93.27 401	95.13 390	89.54 408	99.69 233	99.38 22	92.26 279	87.59 408	94.61 436	85.05 290	97.79 344	91.59 328	88.01 358	92.47 457

cl____		92.31 337	91.58 338	94.52 349	97.33 292	92.77 319	99.57 262	96.78 429	86.97 413	87.56 409	95.51 394	89.43 212	96.62 412	88.60 374	82.44 406	94.16 386

v8		90.54 374	89.17 384	94.66 341	93.43 422	93.40 307	99.20 326	96.94 415	85.76 427	87.56 409	94.51 437	81.96 335	97.19 371	84.94 423	78.25 439	93.38 437

miper_lstm_enhance		91.81 345	91.39 344	93.06 408	97.34 290	89.18 412	99.38 298	96.79 428	86.70 417	87.47 411	95.22 413	90.00 205	95.86 450	88.26 384	81.37 414	94.15 387

anonymousdsp		91.79 350	90.92 350	94.41 358	90.76 470	92.93 318	98.93 366	97.17 365	89.08 367	87.46 412	95.30 407	78.43 381	96.92 392	92.38 313	88.73 347	93.39 436

jajsoiax		91.92 343	91.18 346	94.15 367	91.35 464	90.95 378	99.00 353	97.42 317	92.61 254	87.38 413	97.08 332	72.46 431	97.36 358	94.53 271	88.77 346	94.13 396

mvs_tets		91.81 345	91.08 348	94.00 378	91.63 461	90.58 387	98.67 395	97.43 315	92.43 268	87.37 414	97.05 335	71.76 433	97.32 363	94.75 265	88.68 348	94.11 398

v10		90.25 382	88.82 391	94.57 347	93.53 420	93.43 304	99.08 338	96.87 422	85.00 437	87.34 415	94.51 437	80.93 350	97.02 388	82.85 437	79.23 433	93.26 439

pmmvs5		90.17 385	89.09 386	93.40 397	92.10 454	89.77 405	99.74 207	95.58 464	85.88 426	87.24 416	95.74 380	73.41 429	96.48 421	88.54 376	83.56 398	93.95 412

ACMP	92.05 9	92.74 326	92.42 323	93.73 387	95.91 363	88.72 419	99.81 172	97.53 305	94.13 171	87.00 417	98.23 296	74.07 423	98.47 286	96.22 233	88.86 345	93.99 409
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS-HIRNet		86.22 424	83.19 440	95.31 321	96.71 343	90.29 393	92.12 500	97.33 330	62.85 508	86.82 418	70.37 525	69.37 444	97.49 355	75.12 480	97.99 194	98.15 306

Anonymous20231211		89.86 391	88.44 399	94.13 371	98.93 145	90.68 384	98.54 403	98.26 209	76.28 484	86.73 419	95.54 391	70.60 441	97.56 353	90.82 343	80.27 429	94.15 387

v7n		89.65 395	88.29 401	93.72 388	92.22 451	90.56 388	99.07 342	97.10 384	85.42 434	86.73 419	94.72 430	80.06 363	97.13 375	81.14 448	78.12 441	93.49 433

IterMVS-SCA-FT		90.85 367	90.16 367	92.93 410	96.72 342	89.96 401	98.89 370	96.99 405	88.95 375	86.63 421	95.67 384	76.48 402	95.00 465	87.04 404	84.04 396	93.84 421

EU-MVSNet		90.14 386	90.34 360	89.54 450	92.55 446	81.06 481	98.69 393	98.04 243	91.41 312	86.59 422	96.84 348	80.83 352	93.31 486	86.20 412	81.91 410	94.26 369

OpenMVS	90.15 15	94.77 258	93.59 281	98.33 147	96.07 357	97.48 115	99.56 266	98.57 108	90.46 346	86.51 423	98.95 221	78.57 378	99.94 96	93.86 285	99.74 91	97.57 327

IterMVS		90.91 364	90.17 366	93.12 405	96.78 340	90.42 392	98.89 370	97.05 400	89.03 369	86.49 424	95.42 399	76.59 400	95.02 464	87.22 401	84.09 393	93.93 414
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WR-MVS_H		91.30 355	90.35 359	94.15 367	94.17 410	92.62 328	99.17 329	98.94 44	88.87 378	86.48 425	94.46 441	84.36 307	96.61 413	88.19 386	78.51 437	93.21 441

MS-PatchMatch		90.65 370	90.30 361	91.71 428	94.22 409	85.50 450	98.24 420	97.70 281	88.67 383	86.42 426	96.37 362	67.82 452	98.03 333	83.62 432	99.62 101	91.60 467

CP-MVSNet		91.23 359	90.22 363	94.26 362	93.96 413	92.39 333	99.09 336	98.57 108	88.95 375	86.42 426	96.57 357	79.19 371	96.37 429	90.29 354	78.95 434	94.02 404

LF4IMVS		89.25 402	88.85 390	90.45 442	92.81 443	81.19 480	98.12 427	94.79 481	91.44 308	86.29 428	97.11 330	65.30 464	98.11 327	88.53 377	85.25 382	92.07 462

PVSNet_0	88.03 19	91.80 348	90.27 362	96.38 284	98.27 206	90.46 390	99.94 94	99.61 13	93.99 180	86.26 429	97.39 324	71.13 439	99.89 120	98.77 108	67.05 489	98.79 283

PS-CasMVS		90.63 372	89.51 379	93.99 379	93.83 415	91.70 359	98.98 355	98.52 129	88.48 388	86.15 430	96.53 359	75.46 411	96.31 434	88.83 372	78.86 436	93.95 412

FMVSNet1		88.50 406	86.64 413	94.08 373	95.62 382	91.97 340	98.43 409	96.95 411	83.00 455	86.08 431	94.72 430	59.09 483	96.11 441	81.82 446	84.07 394	94.17 381

PEN-MVS		90.19 384	89.06 387	93.57 394	93.06 430	90.90 379	99.06 343	98.47 141	88.11 395	85.91 432	96.30 364	76.67 398	95.94 449	87.07 403	76.91 452	93.89 417

ppachtmachnet_test		89.58 397	88.35 400	93.25 403	92.40 449	90.44 391	99.33 305	96.73 431	85.49 432	85.90 433	95.77 379	81.09 347	96.00 448	76.00 479	82.49 405	93.30 438

OurMVSNet-221017-0		89.81 392	89.48 381	90.83 435	91.64 460	81.21 479	98.17 426	95.38 469	91.48 306	85.65 434	97.31 325	72.66 430	97.29 368	88.15 388	84.83 387	93.97 411

sc_t1		85.01 436	82.46 446	92.67 415	92.44 448	83.09 466	97.39 446	95.72 459	65.06 504	85.64 435	96.16 368	49.50 497	97.34 360	84.86 424	75.39 459	97.57 327

our_test_3		90.39 376	89.48 381	93.12 405	92.40 449	89.57 407	99.33 305	96.35 446	87.84 400	85.30 436	94.99 425	84.14 311	96.09 444	80.38 455	84.56 389	93.71 430

testgi		89.01 403	88.04 404	91.90 424	93.49 421	84.89 454	99.73 214	95.66 462	93.89 189	85.14 437	98.17 297	59.68 481	94.66 473	77.73 471	88.88 343	96.16 344

DTE-MVSNet		89.40 399	88.24 402	92.88 411	92.66 445	89.95 402	99.10 335	98.22 215	87.29 406	85.12 438	96.22 366	76.27 405	95.30 463	83.56 433	75.74 457	93.41 434

ArgMatch-SfM		85.25 433	84.17 431	88.48 460	92.99 434	77.23 492	97.92 433	94.24 489	90.50 343	85.08 439	95.65 386	49.84 496	95.83 451	81.06 450	70.22 476	92.39 459

mvs5depth		84.87 437	82.90 443	90.77 436	85.59 503	84.84 455	91.10 507	93.29 500	83.14 453	85.07 440	94.33 444	62.17 474	97.32 363	78.83 467	72.59 472	90.14 483

dongtai		91.55 354	91.13 347	92.82 412	98.16 215	86.35 442	99.47 283	98.51 132	83.24 451	85.07 440	97.56 317	90.33 201	94.94 467	76.09 478	91.73 326	97.18 333

FMVSNet5		88.32 407	87.47 409	90.88 432	96.90 331	88.39 426	97.28 448	95.68 461	82.60 459	84.67 442	92.40 468	79.83 365	91.16 498	76.39 477	81.51 413	93.09 443

tfpnnormal		89.29 401	87.61 408	94.34 360	94.35 406	94.13 278	98.95 362	98.94 44	83.94 445	84.47 443	95.51 394	74.84 418	97.39 357	77.05 475	80.41 426	91.48 469

ArgMatch-Sym		85.85 426	85.07 429	88.21 462	92.84 439	77.63 491	98.42 412	94.70 485	89.91 358	84.33 444	96.72 351	51.42 495	94.89 469	82.48 439	74.80 461	92.10 461

MVP-Stereo		90.93 363	90.45 358	92.37 419	91.25 466	88.76 417	98.05 431	96.17 449	87.27 407	84.04 445	95.30 407	78.46 380	97.27 370	83.78 431	99.70 94	91.09 470
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ttmdpeth		88.23 409	87.06 412	91.75 427	89.91 478	87.35 436	98.92 369	95.73 458	87.92 398	84.02 446	96.31 363	68.23 451	96.84 399	86.33 411	76.12 455	91.06 471

LTVRE_ROB	88.28 18	90.29 381	89.05 388	94.02 376	95.08 392	90.15 397	97.19 450	97.43 315	84.91 440	83.99 447	97.06 334	74.00 424	98.28 315	84.08 427	87.71 362	93.62 431
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		89.36 400	87.81 406	94.01 377	93.40 424	91.93 343	98.62 399	96.48 443	86.25 422	83.86 448	96.14 370	73.68 426	97.04 384	86.16 413	75.73 458	93.04 445

USDC		90.00 389	88.96 389	93.10 407	94.81 396	88.16 428	98.71 390	95.54 465	93.66 196	83.75 449	97.20 328	65.58 461	98.31 310	83.96 430	87.49 368	92.85 449

CL-MVSNet_self_test		84.50 441	83.15 441	88.53 459	86.00 500	81.79 476	98.82 380	97.35 326	85.12 436	83.62 450	90.91 480	76.66 399	91.40 497	69.53 490	60.36 509	92.40 458

ACMH+	89.98 16	90.35 378	89.54 377	92.78 414	95.99 360	86.12 445	98.81 381	97.18 363	89.38 364	83.14 451	97.76 315	68.42 449	98.43 292	89.11 370	86.05 376	93.78 424

Anonymous20231206		86.32 423	85.42 426	89.02 454	89.11 482	80.53 485	99.05 347	95.28 470	85.43 433	82.82 452	93.92 448	74.40 421	93.44 485	66.99 497	81.83 411	93.08 444

KD-MVS_self_test		83.59 447	82.06 447	88.20 463	86.93 490	80.70 483	97.21 449	96.38 444	82.87 456	82.49 453	88.97 491	67.63 453	92.32 493	73.75 483	62.30 501	91.58 468

SixPastTwentyTwo		88.73 404	88.01 405	90.88 432	91.85 457	82.24 472	98.22 424	95.18 475	88.97 373	82.26 454	96.89 343	71.75 434	96.67 411	84.00 428	82.98 399	93.72 429

KD-MVS_2432*1600		88.00 411	86.10 415	93.70 391	96.91 328	94.04 280	97.17 451	97.12 376	84.93 438	81.96 455	92.41 466	92.48 156	94.51 474	79.23 461	52.68 520	92.56 453

miper_refine_blended		88.00 411	86.10 415	93.70 391	96.91 328	94.04 280	97.17 451	97.12 376	84.93 438	81.96 455	92.41 466	92.48 156	94.51 474	79.23 461	52.68 520	92.56 453

TinyColmap		87.87 413	86.51 414	91.94 423	95.05 393	85.57 449	97.65 441	94.08 491	84.40 444	81.82 457	96.85 346	62.14 475	98.33 308	80.25 457	86.37 373	91.91 466

ACMH	89.72 17	90.64 371	89.63 374	93.66 393	95.64 380	88.64 422	98.55 401	97.45 313	89.03 369	81.62 458	97.61 316	69.75 443	98.41 295	89.37 364	87.62 366	93.92 415
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		85.15 434	83.81 436	89.16 453	88.32 484	82.69 468	98.80 384	95.74 457	79.72 470	81.53 459	90.99 478	65.38 463	94.16 476	72.69 484	81.11 418	90.63 477

tt0320		83.56 449	81.15 452	90.77 436	92.77 444	83.58 462	96.83 461	95.52 466	63.26 506	81.36 460	92.54 463	53.26 490	95.77 453	80.45 453	74.38 462	92.96 446

pmmvs6		85.69 427	83.84 435	91.26 431	90.00 477	84.41 457	97.82 437	96.15 450	75.86 486	81.29 461	95.39 402	61.21 478	96.87 398	83.52 434	73.29 465	92.50 456

TransMVSNet (Re)		87.25 419	85.28 427	93.16 404	93.56 419	91.03 374	98.54 403	94.05 493	83.69 449	81.09 462	96.16 368	75.32 412	96.40 428	76.69 476	68.41 485	92.06 463

test_method		80.79 456	79.70 459	84.08 475	92.83 441	67.06 505	99.51 275	95.42 467	54.34 518	81.07 463	93.53 453	44.48 501	92.22 495	78.90 466	77.23 449	92.94 447

MASt3R-SfM		78.94 462	79.57 460	77.07 487	84.15 509	50.74 526	91.56 503	92.34 503	83.22 452	80.84 464	94.16 446	36.67 505	92.30 494	79.45 460	73.71 464	88.16 500

NR-MVSNet		91.56 353	90.22 363	95.60 308	94.05 411	95.76 195	98.25 419	98.70 80	91.16 319	80.78 465	96.64 354	83.23 325	96.57 414	91.41 330	77.73 444	94.46 353

LCM-MVSNet-Re		92.31 337	92.60 315	91.43 429	97.53 268	79.27 488	99.02 352	91.83 506	92.07 283	80.31 466	94.38 443	83.50 317	95.48 457	97.22 193	97.58 202	99.54 170

TDRefinement		84.76 438	82.56 445	91.38 430	74.58 528	84.80 456	97.36 447	94.56 487	84.73 441	80.21 467	96.12 373	63.56 469	98.39 299	87.92 391	63.97 496	90.95 474

N_pmnet		80.06 459	80.78 455	77.89 486	91.94 455	45.28 535	98.80 384	56.82 538	78.10 482	80.08 468	93.33 454	77.03 392	95.76 454	68.14 495	82.81 401	92.64 452

test_fmvs3		79.99 460	80.17 458	79.45 484	84.02 511	62.83 508	99.05 347	93.49 499	88.29 393	80.06 469	86.65 506	28.09 513	88.00 508	88.63 373	73.27 466	87.54 504

tt0320-xc		82.94 450	80.35 457	90.72 438	92.90 438	83.54 463	96.85 460	94.73 483	63.12 507	79.85 470	93.77 451	49.43 498	95.46 458	80.98 451	71.54 473	93.16 442

test_0402		85.58 428	83.94 434	90.50 440	93.81 416	85.04 452	98.55 401	95.20 474	76.01 485	79.72 471	95.13 415	64.15 468	96.26 436	66.04 503	86.88 370	90.21 481

dtuonlycased		86.10 425	85.82 420	86.95 467	91.84 458	79.57 487	99.27 320	94.89 478	86.79 416	79.46 472	94.46 441	66.85 456	90.93 501	80.41 454	78.44 438	90.34 478

test20.03		84.72 440	83.99 432	86.91 468	88.19 486	80.62 484	98.88 372	95.94 454	88.36 391	78.87 473	94.62 435	68.75 446	89.11 507	66.52 500	75.82 456	91.00 472

pmmvs3		80.27 458	77.77 464	87.76 466	80.32 521	82.43 471	98.23 422	91.97 505	72.74 495	78.75 474	87.97 497	57.30 486	90.99 500	70.31 488	62.37 500	89.87 486

dmvs_testset		83.79 445	86.07 417	76.94 488	92.14 452	48.60 530	96.75 462	90.27 510	89.48 363	78.65 475	98.55 274	79.25 369	86.65 513	66.85 499	82.69 402	95.57 346

MIMVSNet1		82.58 451	80.51 456	88.78 456	86.68 492	84.20 458	96.65 463	95.41 468	78.75 479	78.59 476	92.44 465	51.88 493	89.76 504	65.26 504	78.95 434	92.38 460

DeepMVS_CX				82.92 480	95.98 362	58.66 517		96.01 453	92.72 245	78.34 477	95.51 394	58.29 484	98.08 329	82.57 438	85.29 381	92.03 464

test_vis1_rt		86.87 421	86.05 418	89.34 451	96.12 355	78.07 489	99.87 135	83.54 523	92.03 286	78.21 478	89.51 489	45.80 500	99.91 113	96.25 232	93.11 324	90.03 485

mvsany_test3		82.12 452	81.14 453	85.06 473	81.87 517	70.41 500	97.09 453	92.14 504	91.27 315	77.84 479	88.73 492	39.31 503	95.49 456	90.75 345	71.24 474	89.29 494

Patchmatch-RL test		86.90 420	85.98 419	89.67 449	84.45 507	75.59 494	89.71 512	92.43 502	86.89 414	77.83 480	90.94 479	94.22 97	93.63 483	87.75 393	69.61 479	99.79 113

APD_test1		81.15 454	80.92 454	81.86 481	92.45 447	59.76 516	96.04 476	93.61 498	73.29 494	77.06 481	96.64 354	44.28 502	96.16 440	72.35 485	82.52 404	89.67 490

lessismore_v0				90.53 439	90.58 471	80.90 482		95.80 456		77.01 482	95.84 377	66.15 460	96.95 390	83.03 436	75.05 460	93.74 428

K. test v3		88.05 410	87.24 411	90.47 441	91.82 459	82.23 473	98.96 361	97.42 317	89.05 368	76.93 483	95.60 388	68.49 448	95.42 459	85.87 417	81.01 422	93.75 425

ambc				83.23 478	77.17 524	62.61 509	87.38 514	94.55 488		76.72 484	86.65 506	30.16 510	96.36 430	84.85 425	69.86 478	90.73 475

PM-MVS		80.47 457	78.88 462	85.26 472	83.79 512	72.22 498	95.89 479	91.08 508	85.71 430	76.56 485	88.30 494	36.64 506	93.90 479	82.39 441	69.57 480	89.66 491

OpenMVS_ROB	79.82 20	83.77 446	81.68 449	90.03 447	88.30 485	82.82 467	98.46 406	95.22 473	73.92 493	76.00 486	91.29 477	55.00 487	96.94 391	68.40 492	88.51 353	90.34 478

UnsupCasMVSNet_eth		85.52 429	83.99 432	90.10 446	89.36 481	83.51 464	96.65 463	97.99 247	89.14 366	75.89 487	93.83 449	63.25 471	93.92 478	81.92 445	67.90 488	92.88 448

new_pmnet		84.49 442	82.92 442	89.21 452	90.03 476	82.60 469	96.89 459	95.62 463	80.59 467	75.77 488	89.17 490	65.04 465	94.79 471	72.12 486	81.02 421	90.23 480

EG-PatchMatch MVS		85.35 432	83.81 436	89.99 448	90.39 472	81.89 475	98.21 425	96.09 451	81.78 462	74.73 489	93.72 452	51.56 494	97.12 377	79.16 464	88.61 349	90.96 473

test_f		78.40 463	77.59 465	80.81 483	80.82 519	62.48 511	96.96 457	93.08 501	83.44 450	74.57 490	84.57 512	27.95 515	92.63 491	84.15 426	72.79 468	87.32 505

FE-MVSNET		81.05 455	78.81 463	87.79 465	81.98 516	83.70 460	98.23 422	91.78 507	81.27 464	74.29 491	87.44 501	60.92 480	90.67 503	64.92 505	68.43 484	89.01 497

FE-MVSNET2		83.57 448	81.36 451	90.20 444	82.83 515	87.59 432	98.28 418	96.04 452	85.33 435	74.13 492	87.45 500	59.16 482	93.26 487	79.12 465	69.91 477	89.77 488

pmmvs-eth3d		84.03 444	81.97 448	90.20 444	84.15 509	87.09 438	98.10 429	94.73 483	83.05 454	74.10 493	87.77 498	65.56 462	94.01 477	81.08 449	69.24 481	89.49 492

usedtu_dtu_shiyan2		75.87 466	72.37 471	86.39 470	76.18 526	75.49 495	96.53 465	93.82 496	64.74 505	72.53 494	88.48 493	37.67 504	91.12 499	64.13 506	57.22 513	92.56 453

new-patchmatchnet		81.19 453	79.34 461	86.76 469	82.86 514	80.36 486	97.92 433	95.27 471	82.09 461	72.02 495	86.87 505	62.81 473	90.74 502	71.10 487	63.08 497	89.19 495

ET-MVSNet_ETH3D		94.37 276	93.28 297	97.64 204	98.30 201	97.99 87	99.99 8	97.61 294	94.35 159	71.57 496	99.45 142	96.23 40	95.34 461	96.91 208	85.14 384	99.59 156

UnsupCasMVSNet_bld		79.97 461	77.03 467	88.78 456	85.62 502	81.98 474	93.66 489	97.35 326	75.51 489	70.79 497	83.05 513	48.70 499	94.91 468	78.31 469	60.29 510	89.46 493

CMPMVS	61.59 21	84.75 439	85.14 428	83.57 476	90.32 473	62.54 510	96.98 456	97.59 298	74.33 492	69.95 498	96.66 352	64.17 467	98.32 309	87.88 392	88.41 354	89.84 487
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WB-MVS		76.28 464	77.28 466	73.29 495	81.18 518	54.68 521	97.87 436	94.19 490	81.30 463	69.43 499	90.70 481	77.02 393	82.06 520	35.71 532	68.11 487	83.13 512

SSC-MVS		75.42 467	76.40 468	72.49 500	80.68 520	53.62 522	97.42 443	94.06 492	80.42 468	68.75 500	90.14 485	76.54 401	81.66 521	33.25 533	66.34 491	82.19 513

MVStest1		85.03 435	82.76 444	91.83 425	92.95 437	89.16 413	98.57 400	94.82 480	71.68 496	68.54 501	95.11 417	83.17 326	95.66 455	74.69 481	65.32 492	90.65 476

DenseAffine		75.91 465	73.39 469	83.47 477	89.52 480	71.86 499	93.39 495	89.29 516	71.44 497	66.83 502	90.32 484	30.65 508	89.67 505	68.20 494	60.88 507	88.88 498

RoMa-SfM		74.91 468	72.77 470	81.35 482	88.00 487	67.35 504	93.55 492	86.23 521	68.27 502	66.79 503	92.92 460	30.40 509	87.68 509	66.14 502	62.62 499	89.02 496

testmvs		40.60 506	44.45 507	29.05 535	19.49 565	14.11 567	99.68 236	18.47 563	20.74 540	64.59 504	98.48 281	10.95 545	17.09 561	56.66 522	11.01 557	55.94 537

VLMVS		51.63 499	52.90 495	47.80 520	47.64 559	20.83 562	69.98 532	55.61 543	20.15 541	63.34 505	87.24 503	19.48 538	43.90 546	62.94 509	49.76 526	78.65 524

RoMa-HiRes		69.18 473	67.02 475	75.65 492	83.52 513	60.31 515	90.80 510	76.82 528	62.46 509	62.85 506	90.44 483	24.75 523	83.07 517	60.58 515	50.97 525	83.58 511

LCM-MVSNet		67.77 479	64.73 482	76.87 489	62.95 545	56.25 520	89.37 513	93.74 497	44.53 522	61.99 507	80.74 518	20.42 535	86.53 514	69.37 491	59.50 511	87.84 501

DKM		72.18 470	69.80 473	79.34 485	86.79 491	65.15 506	92.70 497	84.00 522	67.67 503	61.97 508	89.63 486	23.69 526	85.17 515	67.39 496	54.35 518	87.70 502

MVS_clip		48.84 503	50.24 503	44.65 521	64.05 543	23.54 561	58.84 540	20.46 562	18.73 547	60.84 509	89.57 488	25.96 519	29.22 558	62.25 511	51.44 523	81.19 518

PMMVS2		67.15 480	64.15 483	76.14 491	70.56 534	62.07 512	93.89 486	87.52 518	58.09 514	60.02 510	78.32 519	22.38 528	84.54 516	59.56 517	47.03 528	81.80 515

testf1		68.38 477	66.92 476	72.78 497	78.80 522	50.36 527	90.95 508	87.35 519	55.47 516	58.95 511	88.14 495	20.64 533	87.60 510	57.28 519	64.69 493	80.39 521

APD_test2		68.38 477	66.92 476	72.78 497	78.80 522	50.36 527	90.95 508	87.35 519	55.47 516	58.95 511	88.14 495	20.64 533	87.60 510	57.28 519	64.69 493	80.39 521

DKM-HiRes		68.91 474	66.34 480	76.62 490	84.17 508	60.69 513	90.78 511	78.55 526	62.17 510	58.82 513	87.54 499	20.94 530	82.56 519	63.05 508	51.00 524	86.61 506

Gipuma		66.95 481	65.00 481	72.79 496	91.52 462	67.96 502	66.16 536	95.15 476	47.89 521	58.54 514	67.99 533	29.74 511	87.54 512	50.20 525	77.83 443	62.87 532
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		85.50 431	83.33 438	92.00 422	90.89 468	88.38 427	99.22 325	96.55 439	79.60 472	57.26 515	92.72 461	79.09 374	93.78 482	77.25 473	77.37 448	93.84 421

MDA-MVSNet_test_wron		85.51 430	83.32 439	92.10 421	90.96 467	88.58 423	99.20 326	96.52 440	79.70 471	57.12 516	92.69 462	79.11 372	93.86 480	77.10 474	77.46 447	93.86 420

VLMVS_CLIP		52.57 496	53.54 494	49.65 519	41.84 561	19.27 563	69.54 533	70.45 531	22.22 539	56.57 517	86.16 508	15.89 542	54.77 540	66.88 498	52.29 522	74.91 527

MDA-MVSNet-bldmvs		84.09 443	81.52 450	91.81 426	91.32 465	88.00 431	98.67 395	95.92 455	80.22 469	55.60 518	93.32 455	68.29 450	93.60 484	73.76 482	76.61 454	93.82 423

LoFTR		74.41 469	70.88 472	84.99 474	86.56 497	67.85 503	93.74 488	89.63 513	69.46 501	54.95 519	87.39 502	30.76 507	96.92 392	61.37 513	64.06 495	90.19 482

FPMVS		68.72 476	68.72 474	68.71 503	65.95 539	44.27 538	95.97 478	94.74 482	51.13 520	53.26 520	90.50 482	25.11 521	83.00 518	60.80 514	80.97 423	78.87 523

test123		37.68 507	39.14 510	33.31 525	19.94 564	24.83 558	98.36 415	9.75 565	15.53 557	51.31 521	87.14 504	19.62 537	17.74 560	47.10 527	3.47 560	57.36 536

MatchFormer		70.84 471	66.72 478	83.19 479	85.99 501	64.61 507	93.58 491	88.62 517	59.32 513	50.64 522	82.31 517	28.00 514	96.79 404	52.52 524	59.50 511	88.18 499

test_vis3_rt		68.82 475	66.69 479	75.21 494	76.24 525	60.41 514	96.44 467	68.71 532	75.13 490	50.54 523	69.52 528	16.42 540	96.32 433	80.27 456	66.92 490	68.89 529

SP-DiffGlue		56.84 487	55.72 489	60.19 512	65.70 540	40.86 539	81.89 523	60.28 535	34.62 531	50.39 524	76.88 521	26.61 518	58.81 539	48.21 526	56.94 514	80.90 520

PDCNetPlus		59.83 485	57.26 488	67.55 505	76.18 526	56.71 519	87.01 515	45.27 548	59.54 512	48.80 525	83.01 514	26.63 517	76.54 527	62.12 512	26.78 541	69.40 528

tmp_tt		65.23 482	62.94 485	72.13 501	44.90 560	50.03 529	81.05 528	89.42 515	38.45 524	48.51 526	99.90 23	54.09 489	78.70 525	91.84 326	18.26 550	87.64 503

PMatch-SfM		62.12 484	58.57 487	72.76 499	74.34 529	52.97 524	84.95 521	65.57 533	56.89 515	46.61 527	85.70 511	9.51 551	80.54 523	60.53 516	43.03 531	84.77 507

ELoFTR		64.32 483	60.56 486	75.60 493	73.46 531	53.20 523	86.50 519	80.09 525	60.74 511	45.95 528	82.48 516	16.05 541	89.20 506	56.48 523	43.34 530	84.38 509

ALIKED-NN		54.48 492	52.67 496	59.89 514	90.79 469	45.45 533	81.25 527	55.75 542	34.99 530	44.87 529	71.98 523	25.50 520	74.36 530	21.88 543	47.04 527	59.85 534

SP-SuperGlue		55.29 489	53.71 491	60.00 513	85.11 505	38.86 543	86.96 516	57.95 536	32.77 532	44.54 530	68.00 532	23.90 525	59.51 537	29.61 537	54.59 517	81.63 517

SP-LightGlue		55.29 489	53.65 492	60.20 511	85.58 504	39.12 541	86.36 520	57.52 537	32.34 534	44.34 531	67.75 534	24.36 524	59.32 538	29.62 536	54.98 516	82.17 514

SP-NN		55.28 491	53.59 493	60.34 509	86.63 496	39.01 542	86.70 517	56.31 540	31.08 535	43.77 532	68.45 531	23.39 527	60.24 535	29.19 538	56.76 515	81.77 516

E-PMN		52.30 498	52.18 499	52.67 517	71.51 532	45.40 534	93.62 490	76.60 529	36.01 527	43.50 533	64.13 538	27.11 516	67.31 533	31.06 534	26.06 542	45.30 542

PMatch-Up-SfM		57.92 486	53.93 490	69.90 502	69.97 535	46.69 531	81.36 526	55.29 544	51.90 519	43.17 534	82.54 515	7.86 556	78.44 526	57.13 521	36.17 535	84.58 508

ALIKED-LG		54.29 493	52.28 497	60.32 510	88.90 483	45.51 532	81.66 524	56.33 539	38.60 523	42.62 535	70.81 524	25.00 522	75.20 529	19.87 545	46.76 529	60.24 533

EMVS		51.44 501	51.22 502	52.11 518	70.71 533	44.97 536	94.04 485	75.66 530	35.34 529	42.40 536	61.56 542	28.93 512	65.87 534	27.64 540	24.73 543	45.49 539

ALIKED-MNN		52.51 497	50.15 504	59.60 516	90.05 475	44.33 537	81.60 525	54.93 545	32.36 533	40.96 537	68.77 529	20.90 531	75.30 528	20.00 544	41.78 532	59.18 535

SP-MNN		53.97 494	52.04 500	59.73 515	84.72 506	38.63 544	86.51 518	55.94 541	29.25 536	40.20 538	67.48 535	22.18 529	59.59 536	27.79 539	54.33 519	80.98 519

XFeat-NN		42.54 504	42.87 508	41.54 523	59.73 551	27.86 550	69.53 534	45.34 547	24.36 537	37.16 539	64.79 536	20.84 532	51.40 542	30.01 535	34.12 537	45.36 541

MVE	53.74 22	51.54 500	47.86 505	62.60 507	59.56 552	50.93 525	79.41 529	77.69 527	35.69 528	36.27 540	61.76 541	5.79 562	69.63 531	37.97 531	36.61 534	67.24 530
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
XFeat-MNN		41.51 505	41.24 509	42.32 522	55.40 556	28.19 549	69.39 535	46.53 546	23.57 538	34.47 541	63.21 540	20.04 536	52.41 541	27.43 541	31.08 540	46.37 538

GLUNet-SfM		51.10 502	46.61 506	64.56 506	61.54 549	39.88 540	79.38 530	65.13 534	36.09 526	33.36 542	69.94 526	14.50 543	78.76 524	42.46 530	17.10 551	75.02 526

ANet_high		56.10 488	52.24 498	67.66 504	49.27 558	56.82 518	83.94 522	82.02 524	70.47 498	33.28 543	64.54 537	17.23 539	69.16 532	45.59 528	23.85 545	77.02 525

PMVS	49.05 23	53.75 495	51.34 501	60.97 508	40.80 562	34.68 545	74.82 531	89.62 514	37.55 525	28.67 544	72.12 522	7.09 558	81.63 522	43.17 529	68.21 486	66.59 531
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-NN		35.94 508	36.54 511	34.16 524	73.93 530	29.52 546	62.74 537	37.28 549	19.65 542	27.91 545	49.19 544	11.66 544	46.35 543	9.19 547	37.30 533	26.61 543

MVS_baseline		18.28 524	19.10 527	15.85 541	22.71 563	1.80 568	10.32 553	3.08 567	1.00 559	27.16 546	68.73 530	2.83 564	0.36 562	17.05 546	18.98 548	45.38 540

SIFT-NN-NCMNet		33.88 510	34.14 513	33.10 527	66.88 538	28.42 548	60.42 538	36.72 551	19.15 543	24.06 547	47.14 548	10.24 546	44.77 545	8.72 548	33.94 538	26.10 545

SIFT-MNN		34.10 509	34.41 512	33.17 526	68.99 536	28.51 547	60.22 539	36.81 550	19.08 545	24.04 548	47.28 547	10.06 548	45.04 544	8.72 548	34.47 536	25.97 546

SIFT-NN-CMatch		31.71 512	31.56 515	32.16 528	62.58 546	27.53 554	56.45 543	33.28 553	19.00 546	23.65 549	47.34 545	10.05 549	42.72 549	8.71 550	22.96 546	26.24 544

SIFT-NN-PointCN		29.63 515	29.72 519	29.36 534	57.55 553	23.55 560	56.07 545	30.57 556	17.99 553	20.99 550	45.21 552	9.94 550	39.33 554	8.40 552	20.81 547	25.20 548

SIFT-ConvMatch		30.09 514	29.76 518	31.09 531	65.16 542	27.56 552	54.13 546	31.17 555	18.55 548	17.88 551	45.89 550	8.40 553	42.26 551	8.11 553	18.51 549	23.46 551

SIFT-NN-UMatch		31.23 513	31.05 517	31.79 530	60.08 550	27.23 555	58.49 541	33.65 552	19.14 544	17.30 552	47.31 546	10.12 547	42.88 548	8.67 551	24.67 544	25.27 547

SIFT-CM-Cal		28.34 517	27.90 521	29.63 533	63.75 544	25.98 557	50.66 549	26.18 559	18.12 552	16.88 553	44.64 554	8.08 555	39.70 552	7.65 556	15.19 554	23.22 552

SIFT-UMatch		29.40 516	28.87 520	30.98 532	62.08 548	26.57 556	56.09 544	29.45 557	18.31 550	15.86 554	46.00 549	8.23 554	42.54 550	7.99 554	15.81 552	23.85 550

SIFT-NCM-Cal		31.73 511	31.67 514	31.91 529	67.18 537	27.55 553	58.36 542	33.09 554	18.38 549	14.93 555	45.16 553	8.60 552	43.82 547	7.62 557	31.68 539	24.36 549

SIFT-PCN-Cal		24.67 520	24.81 524	24.24 538	56.13 555	18.04 565	49.05 551	23.39 561	16.07 555	12.99 556	40.17 556	6.97 559	34.68 555	6.71 558	11.81 556	19.99 555

SIFT-UM-Cal		27.47 518	27.02 522	28.83 536	62.12 547	24.58 559	53.60 547	23.46 560	18.14 551	12.85 557	45.56 551	7.49 557	39.45 553	7.68 555	12.30 555	22.45 553

SIFT-PointCN		25.49 519	25.71 523	24.84 537	56.17 554	18.65 564	51.37 548	26.53 558	16.31 554	12.78 558	39.87 557	6.41 560	34.09 556	6.51 559	15.42 553	21.77 554

SIFT-NCMNet		21.21 522	21.22 525	21.17 539	52.99 557	16.41 566	42.12 552	14.05 564	15.89 556	10.70 559	35.85 558	5.14 563	29.82 557	5.80 560	8.44 559	17.28 556

wuyk23d		20.37 523	20.84 526	18.99 540	65.34 541	27.73 551	50.43 550	7.67 566	9.50 558	8.01 560	6.34 559	6.13 561	26.24 559	23.40 542	10.69 558	2.99 557

EGC-MVSNET		69.38 472	63.76 484	86.26 471	90.32 473	81.66 478	96.24 472	93.85 495	0.99 560	3.22 561	92.33 473	52.44 491	92.92 490	59.53 518	84.90 386	84.21 510

mmdepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.02 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uanet_test		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

cdsmvs_eth3d_5k		23.43 521	31.24 516	0.00 542	0.00 566	0.00 569	0.00 554	98.09 236	0.00 561	0.00 562	99.67 115	83.37 320	0.00 563	0.00 561	0.00 561	0.00 558

pcd_1.5k_mvsjas		7.60 526	10.13 529	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	91.20 181	0.00 563	0.00 561	0.00 561	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

ab-mvs-re		8.28 525	11.04 528	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	99.40 149	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet2					0.00 566	86.19 443	98.94 363	96.51 441	78.40 480
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														68.29 493	82.87 400	92.70 451
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													95.80 452
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						90.97 375								86.10 415

MSC_two_6792asdad				99.93 2	99.91 45	99.80 2		98.41 175					100.00 1	99.96 13	100.00 1	100.00 1

No_MVS				99.93 2	99.91 45	99.80 2		98.41 175					100.00 1	99.96 13	100.00 1	100.00 1

eth-test2					0.00 566

eth-test					0.00 566

OPU-MVS				99.93 2	99.89 51	99.80 2	99.96 57				99.80 59	97.44 15	100.00 1	100.00 1	99.98 32	100.00 1

save fliter					99.82 66	98.79 44	99.96 57	98.40 179	97.66 34

test_0728_SECOND				99.82 8	99.94 18	99.47 9	99.95 76	98.43 157					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 156

sam_mvs1												94.72 76				99.59 156

sam_mvs												94.25 96

MTGPA								98.28 206

test_post1							95.78 480				59.23 543	93.20 132	97.74 347	91.06 336

test_post											63.35 539	94.43 84	98.13 326

patchmatchnet-post											91.70 476	95.12 62	97.95 338

MTMP							99.87 135	96.49 442

gm-plane-assit					96.97 321	93.76 289			91.47 307		98.96 216		98.79 246	94.92 258

test9_res														99.71 50	99.99 21	100.00 1

agg_prior2														99.48 65	100.00 1	100.00 1

test_prior4						98.05 84	99.94 94

test_prior				99.43 42	99.94 18	98.49 68		98.65 88					99.80 145			99.99 26

新几何2							99.40 292

旧先验1					99.76 74	97.52 111		98.64 91			99.85 38	95.63 51			99.94 59	99.99 26

无先验							99.49 279	98.71 79	93.46 204				100.00 1	94.36 273		99.99 26

原ACMM2							99.90 118

testdata2													99.99 40	90.54 349

segment_acmp												96.68 31

testdata1							99.28 318		96.35 92

plane_prior7					95.71 375	91.59 368

plane_prior6					95.76 369	91.72 358						80.47 360

plane_prior5								97.87 262					98.37 305	97.79 173	89.55 336	94.52 350

plane_prior4											98.59 267

plane_prior2							99.84 155		96.38 87

plane_prior1					95.73 372

plane_prior						91.74 354	99.86 147		96.76 71						89.59 335

n2								0.00 568

nn								0.00 568

door-mid								89.69 512

test11								98.44 149

door								90.31 509

HQP5-MVS						91.85 347

BP-MVS														97.92 162

HQP3-MVS								97.89 260							89.60 333

HQP2-MVS												80.65 356

NP-MVS					95.77 368	91.79 351					98.65 259

ACMMP++_ref															87.04 369

ACMMP++															88.23 356

Test By Simon												92.82 143

High-resolution multi-view benchmark