High-res multi-view results

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

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

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

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

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

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

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

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 13	100.00 1	99.85 28

mamv4		99.44 16	99.39 24	99.58 19	99.30 168	99.74 2	99.04 65	99.81 28	99.77 7	99.82 28	99.57 46	97.82 122	99.98 4	99.53 40	99.89 81	99.01 278

FOURS1					99.73 36	99.67 3	99.43 12	99.54 89	99.43 45	99.26 125

testf1		99.25 37	99.16 55	99.51 46	99.89 6	99.63 4	98.71 99	99.69 46	98.90 112	99.43 89	99.35 95	98.86 31	99.67 285	97.81 150	99.81 109	99.24 239

APD_test2		99.25 37	99.16 55	99.51 46	99.89 6	99.63 4	98.71 99	99.69 46	98.90 112	99.43 89	99.35 95	98.86 31	99.67 285	97.81 150	99.81 109	99.24 239

reproduce-ours		99.09 62	98.90 82	99.67 4	99.27 174	99.49 6	98.00 184	99.42 135	99.05 97	99.48 79	99.27 113	98.29 80	99.89 85	97.61 163	99.71 168	99.62 80

our_new_method		99.09 62	98.90 82	99.67 4	99.27 174	99.49 6	98.00 184	99.42 135	99.05 97	99.48 79	99.27 113	98.29 80	99.89 85	97.61 163	99.71 168	99.62 80

Effi-MVS+-dtu		98.26 186	97.90 214	99.35 72	98.02 365	99.49 6	98.02 180	99.16 233	98.29 158	97.64 306	97.99 324	96.44 212	99.95 24	96.66 234	98.93 328	98.60 340

APD_test1		98.83 95	98.66 114	99.34 75	99.78 23	99.47 9	98.42 136	99.45 122	98.28 160	98.98 163	99.19 132	97.76 126	99.58 328	96.57 242	99.55 230	98.97 287

reproduce_model		99.15 51	98.97 77	99.67 4	99.33 162	99.44 10	98.15 160	99.47 115	99.12 81	99.52 72	99.32 105	98.31 78	99.90 72	97.78 153	99.73 155	99.66 70

RPSCF		98.62 137	98.36 160	99.42 60	99.65 64	99.42 11	98.55 114	99.57 74	97.72 202	98.90 183	99.26 118	96.12 225	99.52 348	95.72 294	99.71 168	99.32 220

SR-MVS-dyc-post		98.81 100	98.55 129	99.57 20	99.20 192	99.38 12	98.48 129	99.30 187	98.64 125	98.95 171	98.96 194	97.49 154	99.86 125	96.56 246	99.39 260	99.45 167

RE-MVS-def			98.58 127		99.20 192	99.38 12	98.48 129	99.30 187	98.64 125	98.95 171	98.96 194	97.75 127		96.56 246	99.39 260	99.45 167

LS3D		98.63 134	98.38 158	99.36 66	97.25 404	99.38 12	99.12 57	99.32 174	99.21 69	98.44 247	98.88 213	97.31 161	99.80 204	96.58 240	99.34 268	98.92 296

MTAPA		98.88 89	98.64 117	99.61 12	99.67 61	99.36 15	98.43 134	99.20 218	98.83 120	98.89 185	98.90 206	96.98 183	99.92 56	97.16 186	99.70 175	99.56 112

SR-MVS		98.71 113	98.43 149	99.57 20	99.18 202	99.35 16	98.36 141	99.29 195	98.29 158	98.88 188	98.85 219	97.53 147	99.87 117	96.14 275	99.31 272	99.48 154

MP-MVS-pluss		98.57 142	98.23 178	99.60 14	99.69 54	99.35 16	97.16 288	99.38 146	94.87 349	98.97 167	98.99 185	98.01 106	99.88 99	97.29 179	99.70 175	99.58 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HPM-MVS_fast		99.01 71	98.82 91	99.57 20	99.71 45	99.35 16	99.00 69	99.50 98	97.33 242	98.94 178	98.86 216	98.75 41	99.82 183	97.53 169	99.71 168	99.56 112

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 19	99.69 5	99.58 67	99.90 3	99.86 20	99.78 10	99.58 6	99.95 24	99.00 74	99.95 35	99.78 42

TDRefinement		99.42 21	99.38 25	99.55 27	99.76 29	99.33 20	99.68 6	99.71 42	99.38 50	99.53 70	99.61 40	98.64 49	99.80 204	98.24 121	99.84 95	99.52 134

tt0805		98.69 120	98.62 120	98.90 155	99.75 33	99.30 21	99.15 53	96.97 371	98.86 116	98.87 192	97.62 347	98.63 51	98.96 408	99.41 47	98.29 360	98.45 351

DTE-MVSNet		99.43 20	99.35 29	99.66 7	99.71 45	99.30 21	99.31 27	99.51 96	99.64 20	99.56 62	99.46 74	98.23 84	99.97 5	98.78 88	99.93 49	99.72 56

ACMMP_NAP		98.75 109	98.48 141	99.57 20	99.58 78	99.29 23	97.82 209	99.25 207	96.94 275	98.78 202	99.12 151	98.02 105	99.84 156	97.13 191	99.67 189	99.59 95

UA-Net		99.47 13	99.40 23	99.70 2	99.49 118	99.29 23	99.80 4	99.72 40	99.82 5	99.04 156	99.81 6	98.05 104	99.96 12	98.85 84	99.99 5	99.86 26

HPM-MVS		98.79 102	98.53 132	99.59 18	99.65 64	99.29 23	99.16 51	99.43 132	96.74 286	98.61 225	98.38 293	98.62 52	99.87 117	96.47 254	99.67 189	99.59 95
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 35	99.64 20	99.84 25	99.83 4	99.50 9	99.87 117	99.36 48	99.92 60	99.64 76

APD-MVS_3200maxsize		98.84 94	98.61 124	99.53 37	99.19 195	99.27 26	98.49 126	99.33 172	98.64 125	99.03 159	98.98 189	97.89 116	99.85 138	96.54 250	99.42 257	99.46 163

MSP-MVS		98.40 166	98.00 203	99.61 12	99.57 83	99.25 28	98.57 112	99.35 160	97.55 219	99.31 117	97.71 340	94.61 277	99.88 99	96.14 275	99.19 295	99.70 62
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
WR-MVS_H		99.33 28	99.22 48	99.65 8	99.71 45	99.24 29	99.32 23	99.55 85	99.46 40	99.50 78	99.34 99	97.30 162	99.93 46	98.90 80	99.93 49	99.77 45

test_0728_SECOND				99.60 14	99.50 111	99.23 30	98.02 180	99.32 174					99.88 99	96.99 201	99.63 200	99.68 65

MP-MVS		98.46 160	98.09 193	99.54 30	99.57 83	99.22 31	98.50 125	99.19 222	97.61 211	97.58 311	98.66 254	97.40 158	99.88 99	94.72 320	99.60 210	99.54 123
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		98.68 125	98.40 153	99.54 30	99.57 83	99.21 32	98.46 131	99.29 195	97.28 248	98.11 274	98.39 291	98.00 107	99.87 117	96.86 217	99.64 197	99.55 119

DVP-MVS		98.77 107	98.52 133	99.52 42	99.50 111	99.21 32	98.02 180	98.84 291	97.97 182	99.08 147	99.02 172	97.61 139	99.88 99	96.99 201	99.63 200	99.48 154
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
test0726					99.50 111	99.21 32	98.17 158	99.35 160	97.97 182	99.26 125	99.06 160	97.61 139

SMA-MVS		98.40 166	98.03 200	99.51 46	99.16 205	99.21 32	98.05 175	99.22 215	94.16 365	98.98 163	99.10 155	97.52 149	99.79 217	96.45 256	99.64 197	99.53 131
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
XVS		98.72 112	98.45 146	99.53 37	99.46 130	99.21 32	98.65 103	99.34 166	98.62 130	97.54 315	98.63 261	97.50 151	99.83 173	96.79 220	99.53 236	99.56 112

X-MVStestdata		94.32 356	92.59 375	99.53 37	99.46 130	99.21 32	98.65 103	99.34 166	98.62 130	97.54 315	45.85 434	97.50 151	99.83 173	96.79 220	99.53 236	99.56 112

EGC-MVSNET		85.24 398	80.54 401	99.34 75	99.77 26	99.20 38	99.08 58	99.29 195	12.08 436	20.84 437	99.42 82	97.55 144	99.85 138	97.08 194	99.72 163	98.96 289

test_one_0601					99.39 146	99.20 38		99.31 179	98.49 143	98.66 218	99.02 172	97.64 136

GST-MVS		98.61 138	98.30 168	99.52 42	99.51 107	99.20 38	98.26 148	99.25 207	97.44 234	98.67 216	98.39 291	97.68 130	99.85 138	96.00 279	99.51 241	99.52 134

MIMVSNet1		99.38 25	99.32 34	99.55 27	99.86 14	99.19 41	99.41 14	99.59 65	99.59 28	99.71 43	99.57 46	97.12 173	99.90 72	99.21 60	99.87 86	99.54 123

PGM-MVS		98.66 129	98.37 159	99.55 27	99.53 103	99.18 42	98.23 150	99.49 105	97.01 272	98.69 213	98.88 213	98.00 107	99.89 85	95.87 287	99.59 214	99.58 101

SED-MVS		98.91 85	98.72 102	99.49 51	99.49 118	99.17 43	98.10 168	99.31 179	98.03 178	99.66 52	99.02 172	98.36 72	99.88 99	96.91 207	99.62 203	99.41 181

test_241102_ONE					99.49 118	99.17 43		99.31 179	97.98 181	99.66 52	98.90 206	98.36 72	99.48 360

region2R		98.69 120	98.40 153	99.54 30	99.53 103	99.17 43	98.52 118	99.31 179	97.46 231	98.44 247	98.51 277	97.83 119	99.88 99	96.46 255	99.58 219	99.58 101

mPP-MVS		98.64 132	98.34 163	99.54 30	99.54 100	99.17 43	98.63 105	99.24 212	97.47 226	98.09 276	98.68 249	97.62 138	99.89 85	96.22 269	99.62 203	99.57 106

HFP-MVS		98.71 113	98.44 148	99.51 46	99.49 118	99.16 47	98.52 118	99.31 179	97.47 226	98.58 231	98.50 281	97.97 111	99.85 138	96.57 242	99.59 214	99.53 131

SteuartSystems-ACMMP		98.79 102	98.54 131	99.54 30	99.73 36	99.16 47	98.23 150	99.31 179	97.92 188	98.90 183	98.90 206	98.00 107	99.88 99	96.15 274	99.72 163	99.58 101
Skip Steuart: Steuart Systems R&D Blog.
ACMMP		98.75 109	98.50 136	99.52 42	99.56 91	99.16 47	98.87 84	99.37 150	97.16 263	98.82 199	99.01 181	97.71 129	99.87 117	96.29 266	99.69 178	99.54 123
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
PHI-MVS		98.29 183	97.95 208	99.34 75	98.44 338	99.16 47	98.12 165	99.38 146	96.01 316	98.06 278	98.43 288	97.80 124	99.67 285	95.69 296	99.58 219	99.20 246

DVP-MVS++		98.90 87	98.70 108	99.51 46	98.43 339	99.15 51	99.43 12	99.32 174	98.17 171	99.26 125	99.02 172	98.18 91	99.88 99	97.07 195	99.45 253	99.49 144

IU-MVS					99.49 118	99.15 51		98.87 282	92.97 382	99.41 94				96.76 224	99.62 203	99.66 70

CS-MVS		99.13 56	99.10 63	99.24 98	99.06 228	99.15 51	99.36 19	99.88 14	99.36 54	98.21 264	98.46 285	98.68 47	99.93 46	99.03 72	99.85 91	98.64 337

DPE-MVS		98.59 141	98.26 174	99.57 20	99.27 174	99.15 51	97.01 293	99.39 144	97.67 204	99.44 88	98.99 185	97.53 147	99.89 85	95.40 305	99.68 183	99.66 70
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		98.99 74	98.79 94	99.60 14	99.21 188	99.15 51	98.87 84	99.48 107	97.57 215	99.35 106	99.24 123	97.83 119	99.89 85	97.88 147	99.70 175	99.75 54
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		98.70 117	98.42 151	99.54 30	99.52 105	99.14 56	98.52 118	99.31 179	97.47 226	98.56 234	98.54 272	97.75 127	99.88 99	96.57 242	99.59 214	99.58 101

PEN-MVS		99.41 22	99.34 31	99.62 9	99.73 36	99.14 56	99.29 33	99.54 89	99.62 25	99.56 62	99.42 82	98.16 95	99.96 12	98.78 88	99.93 49	99.77 45

ACMM	96.08 12	98.91 85	98.73 100	99.48 53	99.55 95	99.14 56	98.07 172	99.37 150	97.62 208	99.04 156	98.96 194	98.84 33	99.79 217	97.43 173	99.65 195	99.49 144
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
nrg030		99.40 23	99.35 29	99.54 30	99.58 78	99.13 59	98.98 72	99.48 107	99.68 15	99.46 84	99.26 118	98.62 52	99.73 257	99.17 63	99.92 60	99.76 50

HPM-MVS++		98.10 199	97.64 233	99.48 53	99.09 219	99.13 59	97.52 254	98.75 306	97.46 231	96.90 351	97.83 335	96.01 229	99.84 156	95.82 291	99.35 266	99.46 163

CP-MVS		98.70 117	98.42 151	99.52 42	99.36 154	99.12 61	98.72 97	99.36 154	97.54 220	98.30 256	98.40 290	97.86 118	99.89 85	96.53 251	99.72 163	99.56 112

MAR-MVS		96.47 310	95.70 319	98.79 168	97.92 369	99.12 61	98.28 146	98.60 318	92.16 393	95.54 392	96.17 385	94.77 275	99.52 348	89.62 407	98.23 361	97.72 396
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
LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 25	99.85 16	99.11 63	99.90 1	99.78 33	99.63 22	99.78 34	99.67 27	99.48 10	99.81 197	99.30 52	99.97 20	99.77 45
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test_part2					99.36 154	99.10 64				99.05 154

PS-CasMVS		99.40 23	99.33 32	99.62 9	99.71 45	99.10 64	99.29 33	99.53 92	99.53 32	99.46 84	99.41 86	98.23 84	99.95 24	98.89 82	99.95 35	99.81 36

COLMAP_ROB	96.50 10	98.99 74	98.85 89	99.41 62	99.58 78	99.10 64	98.74 92	99.56 81	99.09 92	99.33 109	99.19 132	98.40 70	99.72 264	95.98 281	99.76 148	99.42 178
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
anonymousdsp		99.51 11	99.47 18	99.62 9	99.88 9	99.08 67	99.34 20	99.69 46	98.93 110	99.65 55	99.72 18	98.93 29	99.95 24	99.11 65	100.00 1	99.82 33

KD-MVS_self_test		99.25 37	99.18 52	99.44 59	99.63 74	99.06 68	98.69 101	99.54 89	99.31 59	99.62 61	99.53 60	97.36 160	99.86 125	99.24 59	99.71 168	99.39 191

OurMVSNet-221017-0		99.37 26	99.31 36	99.53 37	99.91 3	98.98 69	99.63 7	99.58 67	99.44 43	99.78 34	99.76 12	96.39 213	99.92 56	99.44 46	99.92 60	99.68 65

SPE-MVS-test		99.13 56	99.09 65	99.26 93	99.13 212	98.97 70	99.31 27	99.88 14	99.44 43	98.16 268	98.51 277	98.64 49	99.93 46	98.91 79	99.85 91	98.88 304

LPG-MVS_test		98.71 113	98.46 145	99.47 56	99.57 83	98.97 70	98.23 150	99.48 107	96.60 291	99.10 145	99.06 160	98.71 44	99.83 173	95.58 301	99.78 130	99.62 80

LGP-MVS_train				99.47 56	99.57 83	98.97 70		99.48 107	96.60 291	99.10 145	99.06 160	98.71 44	99.83 173	95.58 301	99.78 130	99.62 80

DeepPCF-MVS	96.93 5	98.32 177	98.01 202	99.23 100	98.39 344	98.97 70	95.03 389	99.18 226	96.88 278	99.33 109	98.78 232	98.16 95	99.28 393	96.74 226	99.62 203	99.44 171

CP-MVSNet		99.21 43	99.09 65	99.56 25	99.65 64	98.96 74	99.13 55	99.34 166	99.42 46	99.33 109	99.26 118	97.01 181	99.94 39	98.74 93	99.93 49	99.79 39

APD-MVS		98.10 199	97.67 228	99.42 60	99.11 214	98.93 75	97.76 220	99.28 198	94.97 346	98.72 211	98.77 234	97.04 177	99.85 138	93.79 349	99.54 232	99.49 144
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EC-MVSNet		99.09 62	99.05 69	99.20 102	99.28 172	98.93 75	99.24 41	99.84 21	99.08 94	98.12 273	98.37 294	98.72 43	99.90 72	99.05 70	99.77 136	98.77 322

TranMVSNet+NR-MVSNet		99.17 47	99.07 68	99.46 58	99.37 153	98.87 77	98.39 138	99.42 135	99.42 46	99.36 104	99.06 160	98.38 71	99.95 24	98.34 117	99.90 75	99.57 106

ZD-MVS					99.01 237	98.84 78		99.07 247	94.10 367	98.05 280	98.12 314	96.36 217	99.86 125	92.70 374	99.19 295

XVG-OURS-SEG-HR		98.49 157	98.28 170	99.14 111	99.49 118	98.83 79	96.54 317	99.48 107	97.32 244	99.11 142	98.61 265	99.33 14	99.30 389	96.23 268	98.38 356	99.28 231

ACMH+	96.62 9	99.08 66	99.00 73	99.33 81	99.71 45	98.83 79	98.60 109	99.58 67	99.11 82	99.53 70	99.18 136	98.81 35	99.67 285	96.71 231	99.77 136	99.50 140

XVG-OURS		98.53 151	98.34 163	99.11 115	99.50 111	98.82 81	95.97 352	99.50 98	97.30 246	99.05 154	98.98 189	99.35 13	99.32 386	95.72 294	99.68 183	99.18 254

ACMP	95.32 15	98.41 164	98.09 193	99.36 66	99.51 107	98.79 82	97.68 229	99.38 146	95.76 324	98.81 201	98.82 225	98.36 72	99.82 183	94.75 317	99.77 136	99.48 154
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SF-MVS		98.53 151	98.27 173	99.32 83	99.31 164	98.75 83	98.19 154	99.41 139	96.77 285	98.83 196	98.90 206	97.80 124	99.82 183	95.68 297	99.52 239	99.38 198

UniMVSNet_NR-MVSNet		98.86 93	98.68 111	99.40 64	99.17 203	98.74 84	97.68 229	99.40 142	99.14 80	99.06 149	98.59 268	96.71 201	99.93 46	98.57 105	99.77 136	99.53 131

DU-MVS		98.82 98	98.63 118	99.39 65	99.16 205	98.74 84	97.54 252	99.25 207	98.84 119	99.06 149	98.76 236	96.76 197	99.93 46	98.57 105	99.77 136	99.50 140

test_djsdf		99.52 10	99.51 12	99.53 37	99.86 14	98.74 84	99.39 17	99.56 81	99.11 82	99.70 45	99.73 17	99.00 24	99.97 5	99.26 55	99.98 12	99.89 16

OPM-MVS		98.56 143	98.32 167	99.25 96	99.41 144	98.73 87	97.13 290	99.18 226	97.10 266	98.75 208	98.92 202	98.18 91	99.65 301	96.68 233	99.56 226	99.37 200
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UniMVSNet (Re)		98.87 90	98.71 105	99.35 72	99.24 181	98.73 87	97.73 225	99.38 146	98.93 110	99.12 141	98.73 239	96.77 195	99.86 125	98.63 102	99.80 120	99.46 163

NR-MVSNet		98.95 81	98.82 91	99.36 66	99.16 205	98.72 89	99.22 42	99.20 218	99.10 89	99.72 41	98.76 236	96.38 215	99.86 125	98.00 139	99.82 105	99.50 140

CMPMVS	75.91 23	96.29 314	95.44 331	98.84 159	96.25 425	98.69 90	97.02 292	99.12 240	88.90 416	97.83 295	98.86 216	89.51 343	98.90 412	91.92 380	99.51 241	98.92 296
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pm-mvs1		99.44 16	99.48 15	99.33 81	99.80 20	98.63 91	99.29 33	99.63 59	99.30 61	99.65 55	99.60 42	99.16 21	99.82 183	99.07 68	99.83 102	99.56 112

CSCG		98.68 125	98.50 136	99.20 102	99.45 135	98.63 91	98.56 113	99.57 74	97.87 192	98.85 193	98.04 322	97.66 132	99.84 156	96.72 229	99.81 109	99.13 263

OMC-MVS		97.88 217	97.49 242	99.04 132	98.89 262	98.63 91	96.94 297	99.25 207	95.02 344	98.53 239	98.51 277	97.27 165	99.47 363	93.50 357	99.51 241	99.01 278

jajsoiax		99.58 6	99.61 8	99.48 53	99.87 12	98.61 94	99.28 37	99.66 55	99.09 92	99.89 16	99.68 22	99.53 7	99.97 5	99.50 43	99.99 5	99.87 20

mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 42	99.27 64	99.90 13	99.74 15	99.68 4	99.97 5	99.55 39	99.99 5	99.88 19

XVG-ACMP-BASELINE		98.56 143	98.34 163	99.22 101	99.54 100	98.59 96	97.71 226	99.46 118	97.25 251	98.98 163	98.99 185	97.54 145	99.84 156	95.88 284	99.74 152	99.23 241

TransMVSNet (Re)		99.44 16	99.47 18	99.36 66	99.80 20	98.58 97	99.27 39	99.57 74	99.39 49	99.75 39	99.62 37	99.17 19	99.83 173	99.06 69	99.62 203	99.66 70

wuyk23d		96.06 320	97.62 235	91.38 413	98.65 314	98.57 98	98.85 87	96.95 373	96.86 280	99.90 13	99.16 142	99.18 18	98.40 420	89.23 409	99.77 136	77.18 433

AllTest		98.44 162	98.20 180	99.16 108	99.50 111	98.55 99	98.25 149	99.58 67	96.80 282	98.88 188	99.06 160	97.65 133	99.57 330	94.45 327	99.61 208	99.37 200

TestCases				99.16 108	99.50 111	98.55 99		99.58 67	96.80 282	98.88 188	99.06 160	97.65 133	99.57 330	94.45 327	99.61 208	99.37 200

Baseline_NR-MVSNet		98.98 77	98.86 88	99.36 66	99.82 19	98.55 99	97.47 261	99.57 74	99.37 51	99.21 133	99.61 40	96.76 197	99.83 173	98.06 134	99.83 102	99.71 57

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 63	99.66 17	99.68 49	99.66 29	98.44 68	99.95 24	99.73 24	99.96 27	99.75 54

PM-MVS		98.82 98	98.72 102	99.12 113	99.64 70	98.54 102	97.98 189	99.68 51	97.62 208	99.34 108	99.18 136	97.54 145	99.77 234	97.79 152	99.74 152	99.04 274

LCM-MVSNet-Re		98.64 132	98.48 141	99.11 115	98.85 268	98.51 104	98.49 126	99.83 24	98.37 148	99.69 47	99.46 74	98.21 89	99.92 56	94.13 339	99.30 275	98.91 299

Gipuma		99.03 70	99.16 55	98.64 192	99.94 2	98.51 104	99.32 23	99.75 38	99.58 30	98.60 227	99.62 37	98.22 87	99.51 353	97.70 159	99.73 155	97.89 385
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ITE_SJBPF				98.87 156	99.22 186	98.48 106		99.35 160	97.50 223	98.28 260	98.60 267	97.64 136	99.35 382	93.86 347	99.27 279	98.79 320

CPTT-MVS		97.84 226	97.36 250	99.27 91	99.31 164	98.46 107	98.29 145	99.27 201	94.90 348	97.83 295	98.37 294	94.90 266	99.84 156	93.85 348	99.54 232	99.51 137

DP-MVS		98.93 83	98.81 93	99.28 88	99.21 188	98.45 108	98.46 131	99.33 172	99.63 22	99.48 79	99.15 146	97.23 168	99.75 247	97.17 185	99.66 194	99.63 79

3Dnovator+	97.89 3	98.69 120	98.51 134	99.24 98	98.81 277	98.40 109	99.02 66	99.19 222	98.99 103	98.07 277	99.28 111	97.11 175	99.84 156	96.84 218	99.32 270	99.47 161

F-COLMAP		97.30 265	96.68 292	99.14 111	99.19 195	98.39 110	97.27 278	99.30 187	92.93 383	96.62 363	98.00 323	95.73 245	99.68 282	92.62 375	98.46 355	99.35 211

test_vis3_rt		99.14 52	99.17 53	99.07 123	99.78 23	98.38 111	98.92 79	99.94 2	97.80 197	99.91 12	99.67 27	97.15 172	98.91 411	99.76 20	99.56 226	99.92 12

ACMH	96.65 7	99.25 37	99.24 47	99.26 93	99.72 42	98.38 111	99.07 61	99.55 85	98.30 155	99.65 55	99.45 78	99.22 16	99.76 240	98.44 112	99.77 136	99.64 76
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSC_two_6792asdad				99.32 83	98.43 339	98.37 113		98.86 287					99.89 85	97.14 189	99.60 210	99.71 57

No_MVS				99.32 83	98.43 339	98.37 113		98.86 287					99.89 85	97.14 189	99.60 210	99.71 57

FC-MVSNet-test		99.27 34	99.25 46	99.34 75	99.77 26	98.37 113	99.30 32	99.57 74	99.61 27	99.40 97	99.50 64	97.12 173	99.85 138	99.02 73	99.94 44	99.80 38

VPA-MVSNet		99.30 30	99.30 39	99.28 88	99.49 118	98.36 116	99.00 69	99.45 122	99.63 22	99.52 72	99.44 79	98.25 82	99.88 99	99.09 67	99.84 95	99.62 80

GeoE		99.05 69	98.99 75	99.25 96	99.44 136	98.35 117	98.73 96	99.56 81	98.42 147	98.91 182	98.81 227	98.94 27	99.91 65	98.35 116	99.73 155	99.49 144

OPU-MVS				98.82 161	98.59 320	98.30 118	98.10 168				98.52 276	98.18 91	98.75 416	94.62 321	99.48 250	99.41 181

FIs		99.14 52	99.09 65	99.29 87	99.70 52	98.28 119	99.13 55	99.52 95	99.48 35	99.24 130	99.41 86	96.79 194	99.82 183	98.69 98	99.88 83	99.76 50

Vis-MVSNet		99.34 27	99.36 28	99.27 91	99.73 36	98.26 120	99.17 50	99.78 33	99.11 82	99.27 121	99.48 71	98.82 34	99.95 24	98.94 78	99.93 49	99.59 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Anonymous202405211		97.90 213	97.50 241	99.08 121	98.90 257	98.25 121	98.53 117	96.16 386	98.87 114	99.11 142	98.86 216	90.40 338	99.78 228	97.36 176	99.31 272	99.19 251

CNVR-MVS		98.17 197	97.87 216	99.07 123	98.67 305	98.24 122	97.01 293	98.93 270	97.25 251	97.62 307	98.34 298	97.27 165	99.57 330	96.42 257	99.33 269	99.39 191

GBi-Net		98.65 130	98.47 143	99.17 105	98.90 257	98.24 122	99.20 45	99.44 126	98.59 133	98.95 171	99.55 54	94.14 288	99.86 125	97.77 154	99.69 178	99.41 181

test1		98.65 130	98.47 143	99.17 105	98.90 257	98.24 122	99.20 45	99.44 126	98.59 133	98.95 171	99.55 54	94.14 288	99.86 125	97.77 154	99.69 178	99.41 181

FMVSNet1		99.17 47	99.17 53	99.17 105	99.55 95	98.24 122	99.20 45	99.44 126	99.21 69	99.43 89	99.55 54	97.82 122	99.86 125	98.42 114	99.89 81	99.41 181

API-MVS		97.04 285	96.91 277	97.42 317	97.88 371	98.23 126	98.18 155	98.50 323	97.57 215	97.39 329	96.75 373	96.77 195	99.15 402	90.16 405	99.02 316	94.88 427

Anonymous20240529		98.93 83	98.87 85	99.12 113	99.19 195	98.22 127	99.01 67	98.99 265	99.25 65	99.54 66	99.37 90	97.04 177	99.80 204	97.89 144	99.52 239	99.35 211

fmvsm_l_conf0.5_n_3		99.45 15	99.48 15	99.34 75	99.59 77	98.21 128	97.82 209	99.84 21	99.41 48	99.92 8	99.41 86	99.51 8	99.95 24	99.84 7	99.97 20	99.87 20

Anonymous20231211		99.27 34	99.27 42	99.26 93	99.29 171	98.18 129	99.49 9	99.51 96	99.70 12	99.80 32	99.68 22	96.84 188	99.83 173	99.21 60	99.91 69	99.77 45

MCST-MVS		98.00 207	97.63 234	99.10 117	99.24 181	98.17 130	96.89 302	98.73 309	95.66 325	97.92 286	97.70 342	97.17 171	99.66 296	96.18 273	99.23 287	99.47 161

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 131	99.20 45	99.65 56	99.48 35	99.92 8	99.71 19	98.07 101	99.96 12	99.53 40	100.00 1	99.93 11

CDPH-MVS		97.26 268	96.66 295	99.07 123	99.00 238	98.15 131	96.03 350	99.01 262	91.21 403	97.79 298	97.85 334	96.89 186	99.69 273	92.75 372	99.38 263	99.39 191

test_0402		98.76 108	98.71 105	98.93 148	99.56 91	98.14 133	98.45 133	99.34 166	99.28 63	98.95 171	98.91 203	98.34 76	99.79 217	95.63 298	99.91 69	98.86 306

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 66	99.87 12	98.13 134	98.08 170	99.95 1	99.45 41	99.98 2	99.75 13	99.80 1	99.97 5	99.82 9	99.99 5	99.99 2

test_fmvsmconf0.1_n		99.49 12	99.54 11	99.34 75	99.78 23	98.11 135	97.77 217	99.90 11	99.33 56	99.97 3	99.66 29	99.71 3	99.96 12	99.79 16	99.99 5	99.96 8

Fast-Effi-MVS+-dtu		98.27 184	98.09 193	98.81 163	98.43 339	98.11 135	97.61 243	99.50 98	98.64 125	97.39 329	97.52 352	98.12 99	99.95 24	96.90 212	98.71 340	98.38 361

test_fmvsmconf_n		99.44 16	99.48 15	99.31 86	99.64 70	98.10 137	97.68 229	99.84 21	99.29 62	99.92 8	99.57 46	99.60 5	99.96 12	99.74 23	99.98 12	99.89 16

EIA-MVS		98.00 207	97.74 223	98.80 165	98.72 288	98.09 138	98.05 175	99.60 64	97.39 237	96.63 362	95.55 397	97.68 130	99.80 204	96.73 228	99.27 279	98.52 346

alignmvs		97.35 261	96.88 278	98.78 171	98.54 327	98.09 138	97.71 226	97.69 351	99.20 71	97.59 310	95.90 391	88.12 356	99.55 337	98.18 125	98.96 325	98.70 331

ANet_high		99.57 7	99.67 5	99.28 88	99.89 6	98.09 138	99.14 54	99.93 5	99.82 5	99.93 6	99.81 6	99.17 19	99.94 39	99.31 51	100.00 1	99.82 33

TAPA-MVS	96.21 11	96.63 303	95.95 314	98.65 190	98.93 249	98.09 138	96.93 299	99.28 198	83.58 426	98.13 272	97.78 336	96.13 224	99.40 374	93.52 355	99.29 277	98.45 351
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TEST9					98.71 291	98.08 142	95.96 354	99.03 256	91.40 400	95.85 383	97.53 350	96.52 208	99.76 240

train_agg		97.10 280	96.45 305	99.07 123	98.71 291	98.08 142	95.96 354	99.03 256	91.64 395	95.85 383	97.53 350	96.47 210	99.76 240	93.67 351	99.16 298	99.36 207

ETV-MVS		98.03 204	97.86 217	98.56 212	98.69 300	98.07 144	97.51 256	99.50 98	98.10 176	97.50 319	95.51 398	98.41 69	99.88 99	96.27 267	99.24 284	97.71 397

VDD-MVS		98.56 143	98.39 156	99.07 123	99.13 212	98.07 144	98.59 110	97.01 369	99.59 28	99.11 142	99.27 113	94.82 270	99.79 217	98.34 117	99.63 200	99.34 213

NCCC		97.86 220	97.47 245	99.05 130	98.61 315	98.07 144	96.98 295	98.90 276	97.63 207	97.04 341	97.93 330	95.99 234	99.66 296	95.31 306	98.82 334	99.43 175

sd_testset		99.28 33	99.31 36	99.19 104	99.68 57	98.06 147	99.41 14	99.30 187	99.69 13	99.63 58	99.68 22	99.25 15	99.96 12	97.25 182	99.92 60	99.57 106

CNLPA		97.17 277	96.71 290	98.55 213	98.56 325	98.05 148	96.33 332	98.93 270	96.91 277	97.06 340	97.39 359	94.38 283	99.45 367	91.66 385	99.18 297	98.14 372

MVS_111021_LR		98.30 180	98.12 191	98.83 160	99.16 205	98.03 149	96.09 348	99.30 187	97.58 214	98.10 275	98.24 305	98.25 82	99.34 383	96.69 232	99.65 195	99.12 264

test_8					98.67 305	98.01 150	95.91 360	99.02 259	91.64 395	95.79 385	97.50 353	96.47 210	99.76 240

agg_prior					98.68 304	97.99 151		99.01 262		95.59 386			99.77 234

SD-MVS		98.40 166	98.68 111	97.54 307	98.96 245	97.99 151	97.88 201	99.36 154	98.20 168	99.63 58	99.04 169	98.76 40	95.33 433	96.56 246	99.74 152	99.31 224
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
DP-MVS Recon		97.33 263	96.92 275	98.57 208	99.09 219	97.99 151	96.79 305	99.35 160	93.18 379	97.71 302	98.07 320	95.00 265	99.31 387	93.97 342	99.13 303	98.42 358

DeepC-MVS	97.60 4	98.97 78	98.93 79	99.10 117	99.35 159	97.98 154	98.01 183	99.46 118	97.56 217	99.54 66	99.50 64	98.97 25	99.84 156	98.06 134	99.92 60	99.49 144
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
save fliter					99.11 214	97.97 155	96.53 319	99.02 259	98.24 161

test_prior4						97.97 155	95.86 361

IS-MVSNet		98.19 194	97.90 214	99.08 121	99.57 83	97.97 155	99.31 27	98.32 331	99.01 102	98.98 163	99.03 171	91.59 327	99.79 217	95.49 303	99.80 120	99.48 154

SixPastTwentyTwo		98.75 109	98.62 120	99.16 108	99.83 18	97.96 158	99.28 37	98.20 336	99.37 51	99.70 45	99.65 33	92.65 316	99.93 46	99.04 71	99.84 95	99.60 89

test_prior				98.95 145	98.69 300	97.95 159		99.03 256					99.59 322			99.30 227

PMVS	91.26 20	97.86 220	97.94 210	97.65 294	99.71 45	97.94 160	98.52 118	98.68 312	98.99 103	97.52 317	99.35 95	97.41 157	98.18 424	91.59 388	99.67 189	96.82 413
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PLC	94.65 16	96.51 306	95.73 318	98.85 158	98.75 284	97.91 161	96.42 327	99.06 248	90.94 406	95.59 386	97.38 360	94.41 281	99.59 322	90.93 399	98.04 377	99.05 270
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + MP.		98.63 134	98.49 140	99.06 129	99.64 70	97.90 162	98.51 123	98.94 267	96.96 273	99.24 130	98.89 212	97.83 119	99.81 197	96.88 214	99.49 249	99.48 154
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TSAR-MVS + GP.		98.18 195	97.98 205	98.77 175	98.71 291	97.88 163	96.32 333	98.66 313	96.33 302	99.23 132	98.51 277	97.48 155	99.40 374	97.16 186	99.46 251	99.02 277

plane_prior7					99.19 195	97.87 164

N_pmnet		97.63 239	97.17 260	98.99 138	99.27 174	97.86 165	95.98 351	93.41 415	95.25 339	99.47 83	98.90 206	95.63 247	99.85 138	96.91 207	99.73 155	99.27 232

FPMVS		93.44 373	92.23 380	97.08 331	99.25 180	97.86 165	95.61 370	97.16 366	92.90 384	93.76 417	98.65 256	75.94 412	95.66 431	79.30 430	97.49 387	97.73 395

h-mvs33		97.77 229	97.33 253	99.10 117	99.21 188	97.84 167	98.35 142	98.57 319	99.11 82	98.58 231	99.02 172	88.65 351	99.96 12	98.11 129	96.34 410	99.49 144

test12				98.93 148	98.58 322	97.83 168		98.66 313		96.53 367		95.51 252	99.69 273		99.13 303	99.27 232

PatchMatch-RL		97.24 271	96.78 286	98.61 201	99.03 235	97.83 168	96.36 330	99.06 248	93.49 377	97.36 331	97.78 336	95.75 244	99.49 357	93.44 358	98.77 335	98.52 346

EPP-MVSNet		98.30 180	98.04 199	99.07 123	99.56 91	97.83 168	99.29 33	98.07 342	99.03 100	98.59 229	99.13 150	92.16 321	99.90 72	96.87 215	99.68 183	99.49 144

sasdasda		98.34 173	98.26 174	98.58 205	98.46 335	97.82 171	98.96 74	99.46 118	99.19 75	97.46 322	95.46 402	98.59 55	99.46 365	98.08 132	98.71 340	98.46 348

tfpnnormal		98.90 87	98.90 82	98.91 152	99.67 61	97.82 171	99.00 69	99.44 126	99.45 41	99.51 77	99.24 123	98.20 90	99.86 125	95.92 283	99.69 178	99.04 274

canonicalmvs		98.34 173	98.26 174	98.58 205	98.46 335	97.82 171	98.96 74	99.46 118	99.19 75	97.46 322	95.46 402	98.59 55	99.46 365	98.08 132	98.71 340	98.46 348

3Dnovator	98.27 2	98.81 100	98.73 100	99.05 130	98.76 282	97.81 174	99.25 40	99.30 187	98.57 137	98.55 236	99.33 101	97.95 112	99.90 72	97.16 186	99.67 189	99.44 171

AdaColmap		97.14 279	96.71 290	98.46 226	98.34 346	97.80 175	96.95 296	98.93 270	95.58 329	96.92 346	97.66 343	95.87 241	99.53 344	90.97 398	99.14 301	98.04 377

plane_prior3						97.78 176			97.41 235	97.79 298

pmmvs-eth3d		98.47 159	98.34 163	98.86 157	99.30 168	97.76 177	97.16 288	99.28 198	95.54 330	99.42 92	99.19 132	97.27 165	99.63 307	97.89 144	99.97 20	99.20 246

新几何1				98.91 152	98.94 247	97.76 177		98.76 303	87.58 420	96.75 359	98.10 316	94.80 273	99.78 228	92.73 373	99.00 318	99.20 246

VDDNet		98.21 192	97.95 208	99.01 136	99.58 78	97.74 179	99.01 67	97.29 362	99.67 16	98.97 167	99.50 64	90.45 337	99.80 204	97.88 147	99.20 292	99.48 154

XXY-MVS		99.14 52	99.15 60	99.10 117	99.76 29	97.74 179	98.85 87	99.62 60	98.48 144	99.37 102	99.49 70	98.75 41	99.86 125	98.20 124	99.80 120	99.71 57

test_fmvsm_n_1920		99.33 28	99.45 20	98.99 138	99.57 83	97.73 181	97.93 193	99.83 24	99.22 67	99.93 6	99.30 107	99.42 11	99.96 12	99.85 5	99.99 5	99.29 229

casdiffmvs_mvg		99.12 59	99.16 55	98.99 138	99.43 141	97.73 181	98.00 184	99.62 60	99.22 67	99.55 65	99.22 128	98.93 29	99.75 247	98.66 99	99.81 109	99.50 140
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
plane_prior6					98.99 241	97.70 183						94.90 266

LF4IMVS		97.90 213	97.69 227	98.52 218	99.17 203	97.66 184	97.19 287	99.47 115	96.31 304	97.85 294	98.20 309	96.71 201	99.52 348	94.62 321	99.72 163	98.38 361

HQP_MVS		97.99 210	97.67 228	98.93 148	99.19 195	97.65 185	97.77 217	99.27 201	98.20 168	97.79 298	97.98 325	94.90 266	99.70 269	94.42 329	99.51 241	99.45 167

plane_prior						97.65 185	97.07 291		96.72 287						99.36 264

WR-MVS		98.40 166	98.19 182	99.03 133	99.00 238	97.65 185	96.85 303	98.94 267	98.57 137	98.89 185	98.50 281	95.60 248	99.85 138	97.54 168	99.85 91	99.59 95

VPNet		98.87 90	98.83 90	99.01 136	99.70 52	97.62 188	98.43 134	99.35 160	99.47 38	99.28 119	99.05 167	96.72 200	99.82 183	98.09 131	99.36 264	99.59 95

MGCFI-Net		98.34 173	98.28 170	98.51 219	98.47 333	97.59 189	98.96 74	99.48 107	99.18 77	97.40 327	95.50 399	98.66 48	99.50 354	98.18 125	98.71 340	98.44 354

K. test v3		98.00 207	97.66 231	99.03 133	99.79 22	97.56 190	99.19 49	92.47 418	99.62 25	99.52 72	99.66 29	89.61 342	99.96 12	99.25 57	99.81 109	99.56 112

PCF-MVS	92.86 18	94.36 355	93.00 373	98.42 231	98.70 295	97.56 190	93.16 421	99.11 242	79.59 430	97.55 314	97.43 357	92.19 320	99.73 257	79.85 429	99.45 253	97.97 382
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
lessismore_v0				98.97 142	99.73 36	97.53 192		86.71 433		99.37 102	99.52 63	89.93 340	99.92 56	98.99 75	99.72 163	99.44 171

QAPM		97.31 264	96.81 285	98.82 161	98.80 280	97.49 193	99.06 62	99.19 222	90.22 409	97.69 304	99.16 142	96.91 185	99.90 72	90.89 401	99.41 258	99.07 268

EG-PatchMatch MVS		98.99 74	99.01 72	98.94 146	99.50 111	97.47 194	98.04 177	99.59 65	98.15 175	99.40 97	99.36 94	98.58 58	99.76 240	98.78 88	99.68 183	99.59 95

MVS_111021_HR		98.25 188	98.08 196	98.75 178	99.09 219	97.46 195	95.97 352	99.27 201	97.60 213	97.99 284	98.25 304	98.15 97	99.38 378	96.87 215	99.57 223	99.42 178

dmvs_re		95.98 324	95.39 334	97.74 287	98.86 265	97.45 196	98.37 140	95.69 398	97.95 184	96.56 365	95.95 389	90.70 335	97.68 427	88.32 411	96.13 414	98.11 373

旧先验1					98.82 274	97.45 196		98.76 303			98.34 298	95.50 253			99.01 317	99.23 241

Fast-Effi-MVS+		97.67 236	97.38 248	98.57 208	98.71 291	97.43 198	97.23 279	99.45 122	94.82 350	96.13 377	96.51 377	98.52 61	99.91 65	96.19 271	98.83 332	98.37 363

114514_t		96.50 308	95.77 316	98.69 186	99.48 126	97.43 198	97.84 208	99.55 85	81.42 429	96.51 369	98.58 269	95.53 250	99.67 285	93.41 359	99.58 219	98.98 284

NP-MVS					98.84 269	97.39 200					96.84 371

SDMVSNet		99.23 41	99.32 34	98.96 143	99.68 57	97.35 201	98.84 89	99.48 107	99.69 13	99.63 58	99.68 22	99.03 23	99.96 12	97.97 141	99.92 60	99.57 106

hse-mvs2		97.46 251	97.07 266	98.64 192	98.73 286	97.33 202	97.45 262	97.64 355	99.11 82	98.58 231	97.98 325	88.65 351	99.79 217	98.11 129	97.39 393	98.81 314

casdiffmvs		98.95 81	99.00 73	98.81 163	99.38 147	97.33 202	97.82 209	99.57 74	99.17 78	99.35 106	99.17 140	98.35 75	99.69 273	98.46 111	99.73 155	99.41 181
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
VNet		98.42 163	98.30 168	98.79 168	98.79 281	97.29 204	98.23 150	98.66 313	99.31 59	98.85 193	98.80 228	94.80 273	99.78 228	98.13 128	99.13 303	99.31 224

fmvsm_l_conf0.5_n		99.21 43	99.28 41	99.02 135	99.64 70	97.28 205	97.82 209	99.76 35	98.73 121	99.82 28	99.09 159	98.81 35	99.95 24	99.86 4	99.96 27	99.83 30

HyFIR lowres test		97.19 275	96.60 299	98.96 143	99.62 76	97.28 205	95.17 385	99.50 98	94.21 364	99.01 160	98.32 301	86.61 360	99.99 2	97.10 193	99.84 95	99.60 89

baseline		98.96 80	99.02 71	98.76 176	99.38 147	97.26 207	98.49 126	99.50 98	98.86 116	99.19 135	99.06 160	98.23 84	99.69 273	98.71 96	99.76 148	99.33 218

ab-mvs		98.41 164	98.36 160	98.59 204	99.19 195	97.23 208	99.32 23	98.81 296	97.66 205	98.62 223	99.40 89	96.82 191	99.80 204	95.88 284	99.51 241	98.75 325

DeepC-MVS_fast	96.85 6	98.30 180	98.15 188	98.75 178	98.61 315	97.23 208	97.76 220	99.09 245	97.31 245	98.75 208	98.66 254	97.56 143	99.64 304	96.10 278	99.55 230	99.39 191
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.5_n_5		99.07 68	99.10 63	98.99 138	99.47 128	97.22 210	97.40 264	99.83 24	97.61 211	99.85 22	99.30 107	98.80 37	99.95 24	99.71 28	99.90 75	99.78 42

AUN-MVS		96.24 318	95.45 330	98.60 203	98.70 295	97.22 210	97.38 266	97.65 353	95.95 319	95.53 393	97.96 329	82.11 395	99.79 217	96.31 264	97.44 390	98.80 319

DPM-MVS		96.32 313	95.59 325	98.51 219	98.76 282	97.21 212	94.54 405	98.26 333	91.94 394	96.37 373	97.25 364	93.06 307	99.43 370	91.42 391	98.74 336	98.89 301

test20.03		98.78 104	98.77 97	98.78 171	99.46 130	97.20 213	97.78 215	99.24 212	99.04 99	99.41 94	98.90 206	97.65 133	99.76 240	97.70 159	99.79 125	99.39 191

Effi-MVS+		98.02 205	97.82 219	98.62 198	98.53 329	97.19 214	97.33 271	99.68 51	97.30 246	96.68 360	97.46 356	98.56 59	99.80 204	96.63 236	98.20 363	98.86 306

TAMVS		98.24 189	98.05 198	98.80 165	99.07 223	97.18 215	97.88 201	98.81 296	96.66 290	99.17 140	99.21 129	94.81 272	99.77 234	96.96 205	99.88 83	99.44 171

UnsupCasMVSNet_eth		97.89 215	97.60 236	98.75 178	99.31 164	97.17 216	97.62 240	99.35 160	98.72 123	98.76 207	98.68 249	92.57 317	99.74 252	97.76 158	95.60 418	99.34 213

OpenMVS	96.65 7	97.09 281	96.68 292	98.32 242	98.32 347	97.16 217	98.86 86	99.37 150	89.48 413	96.29 375	99.15 146	96.56 206	99.90 72	92.90 366	99.20 292	97.89 385

OpenMVS_ROB	95.38 14	95.84 329	95.18 342	97.81 278	98.41 343	97.15 218	97.37 268	98.62 317	83.86 425	98.65 219	98.37 294	94.29 286	99.68 282	88.41 410	98.62 350	96.60 416

FMVSNet2		98.49 157	98.40 153	98.75 178	98.90 257	97.14 219	98.61 108	99.13 239	98.59 133	99.19 135	99.28 111	94.14 288	99.82 183	97.97 141	99.80 120	99.29 229

fmvsm_l_conf0.5_n_a		99.19 46	99.27 42	98.94 146	99.65 64	97.05 220	97.80 213	99.76 35	98.70 124	99.78 34	99.11 152	98.79 39	99.95 24	99.85 5	99.96 27	99.83 30

V42		98.78 104	98.78 96	98.76 176	99.44 136	97.04 221	98.27 147	99.19 222	97.87 192	99.25 129	99.16 142	96.84 188	99.78 228	99.21 60	99.84 95	99.46 163

CLD-MVS		97.49 249	97.16 261	98.48 224	99.07 223	97.03 222	94.71 396	99.21 216	94.46 357	98.06 278	97.16 366	97.57 142	99.48 360	94.46 326	99.78 130	98.95 290
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CDS-MVSNet		97.69 234	97.35 251	98.69 186	98.73 286	97.02 223	96.92 301	98.75 306	95.89 321	98.59 229	98.67 251	92.08 323	99.74 252	96.72 229	99.81 109	99.32 220
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MM		98.22 190	97.99 204	98.91 152	98.66 310	96.97 224	97.89 200	94.44 406	99.54 31	98.95 171	99.14 149	93.50 300	99.92 56	99.80 14	99.96 27	99.85 28

test_fmvsmvis_n_1920		99.26 36	99.49 13	98.54 216	99.66 63	96.97 224	98.00 184	99.85 18	99.24 66	99.92 8	99.50 64	99.39 12	99.95 24	99.89 3	99.98 12	98.71 328

UGNet		98.53 151	98.45 146	98.79 168	97.94 368	96.96 226	99.08 58	98.54 320	99.10 89	96.82 356	99.47 73	96.55 207	99.84 156	98.56 108	99.94 44	99.55 119
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
LFMVS		97.20 274	96.72 289	98.64 192	98.72 288	96.95 227	98.93 78	94.14 412	99.74 10	98.78 202	99.01 181	84.45 378	99.73 257	97.44 172	99.27 279	99.25 236

mvsany_test3		98.87 90	98.92 80	98.74 182	99.38 147	96.94 228	98.58 111	99.10 243	96.49 296	99.96 4	99.81 6	98.18 91	99.45 367	98.97 76	99.79 125	99.83 30

test222					98.92 253	96.93 229	95.54 372	98.78 301	85.72 423	96.86 354	98.11 315	94.43 280			99.10 308	99.23 241

pmmvs4		97.58 243	97.28 254	98.51 219	98.84 269	96.93 229	95.40 380	98.52 322	93.60 374	98.61 225	98.65 256	95.10 262	99.60 318	96.97 204	99.79 125	98.99 283

mmtdpeth		99.30 30	99.42 21	98.92 151	99.58 78	96.89 231	99.48 10	99.92 7	99.92 2	98.26 262	99.80 9	98.33 77	99.91 65	99.56 37	99.95 35	99.97 4

GDP-MVS		97.50 246	97.11 265	98.67 189	99.02 236	96.85 232	98.16 159	99.71 42	98.32 153	98.52 241	98.54 272	83.39 387	99.95 24	98.79 87	99.56 226	99.19 251

MSDG		97.71 233	97.52 240	98.28 247	98.91 256	96.82 233	94.42 406	99.37 150	97.65 206	98.37 255	98.29 303	97.40 158	99.33 385	94.09 340	99.22 288	98.68 335

BP-MVS1		97.40 258	96.97 271	98.71 185	99.07 223	96.81 234	98.34 144	97.18 364	98.58 136	98.17 265	98.61 265	84.01 383	99.94 39	98.97 76	99.78 130	99.37 200

MVP-Stereo		98.08 202	97.92 212	98.57 208	98.96 245	96.79 235	97.90 199	99.18 226	96.41 300	98.46 245	98.95 198	95.93 239	99.60 318	96.51 252	98.98 323	99.31 224
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HQP5-MVS						96.79 235

HQP-MVS		97.00 289	96.49 304	98.55 213	98.67 305	96.79 235	96.29 335	99.04 254	96.05 312	95.55 389	96.84 371	93.84 294	99.54 342	92.82 369	99.26 282	99.32 220

UnsupCasMVSNet_bld		97.30 265	96.92 275	98.45 227	99.28 172	96.78 238	96.20 340	99.27 201	95.42 334	98.28 260	98.30 302	93.16 303	99.71 265	94.99 311	97.37 394	98.87 305

MVS_0304		97.44 254	97.01 270	98.72 184	96.42 422	96.74 239	97.20 284	91.97 422	98.46 145	98.30 256	98.79 230	92.74 314	99.91 65	99.30 52	99.94 44	99.52 134

mvsmamba		97.57 244	97.26 255	98.51 219	98.69 300	96.73 240	98.74 92	97.25 363	97.03 271	97.88 290	99.23 127	90.95 332	99.87 117	96.61 238	99.00 318	98.91 299

DELS-MVS		98.27 184	98.20 180	98.48 224	98.86 265	96.70 241	95.60 371	99.20 218	97.73 201	98.45 246	98.71 242	97.50 151	99.82 183	98.21 123	99.59 214	98.93 295
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
PAPM_NR		96.82 297	96.32 308	98.30 245	99.07 223	96.69 242	97.48 259	98.76 303	95.81 323	96.61 364	96.47 380	94.12 291	99.17 400	90.82 402	97.78 381	99.06 269

balanced_conf03		98.63 134	98.72 102	98.38 235	98.66 310	96.68 243	98.90 80	99.42 135	98.99 103	98.97 167	99.19 132	95.81 243	99.85 138	98.77 91	99.77 136	98.60 340

fmvsm_s_conf0.1_n_a		99.17 47	99.30 39	98.80 165	99.75 33	96.59 244	97.97 192	99.86 16	98.22 163	99.88 18	99.71 19	98.59 55	99.84 156	99.73 24	99.98 12	99.98 3

fmvsm_s_conf0.5_n_a		99.10 61	99.20 51	98.78 171	99.55 95	96.59 244	97.79 214	99.82 27	98.21 164	99.81 31	99.53 60	98.46 66	99.84 156	99.70 29	99.97 20	99.90 15

fmvsm_s_conf0.5_n_3		99.22 42	99.37 27	98.78 171	99.46 130	96.58 246	97.65 235	99.72 40	99.47 38	99.86 20	99.50 64	98.94 27	99.89 85	99.75 22	99.97 20	99.86 26

MVSMamba_PlusPlus		98.83 95	98.98 76	98.36 239	99.32 163	96.58 246	98.90 80	99.41 139	99.75 8	98.72 211	99.50 64	96.17 222	99.94 39	99.27 54	99.78 130	98.57 344

fmvsm_s_conf0.5_n_6		99.08 66	99.21 50	98.69 186	99.36 154	96.51 248	97.62 240	99.68 51	98.43 146	99.85 22	99.10 155	99.12 22	99.88 99	99.77 19	99.92 60	99.67 68

Patchmtry		97.35 261	96.97 271	98.50 223	97.31 403	96.47 249	98.18 155	98.92 273	98.95 109	98.78 202	99.37 90	85.44 372	99.85 138	95.96 282	99.83 102	99.17 258

fmvsm_s_conf0.5_n_8		99.13 56	99.26 44	98.74 182	99.51 107	96.44 250	97.65 235	99.65 56	99.66 17	99.78 34	99.48 71	97.92 114	99.93 46	99.72 26	99.95 35	99.87 20

EI-MVSNet-Vis-set		98.68 125	98.70 108	98.63 196	99.09 219	96.40 251	97.23 279	98.86 287	99.20 71	99.18 139	98.97 191	97.29 164	99.85 138	98.72 95	99.78 130	99.64 76

EI-MVSNet-UG-set		98.69 120	98.71 105	98.62 198	99.10 216	96.37 252	97.23 279	98.87 282	99.20 71	99.19 135	98.99 185	97.30 162	99.85 138	98.77 91	99.79 125	99.65 75

test_vis1_rt		97.75 230	97.72 226	97.83 276	98.81 277	96.35 253	97.30 274	99.69 46	94.61 353	97.87 291	98.05 321	96.26 220	98.32 421	98.74 93	98.18 364	98.82 309

1112_ss		97.29 267	96.86 279	98.58 205	99.34 161	96.32 254	96.75 309	99.58 67	93.14 380	96.89 352	97.48 354	92.11 322	99.86 125	96.91 207	99.54 232	99.57 106

v8		99.01 71	99.16 55	98.57 208	99.47 128	96.31 255	98.90 80	99.47 115	99.03 100	99.52 72	99.57 46	96.93 184	99.81 197	99.60 33	99.98 12	99.60 89

原ACMM1				98.35 240	98.90 257	96.25 256		98.83 295	92.48 389	96.07 380	98.10 316	95.39 256	99.71 265	92.61 376	98.99 320	99.08 266

v10		98.97 78	99.11 61	98.55 213	99.44 136	96.21 257	98.90 80	99.55 85	98.73 121	99.48 79	99.60 42	96.63 204	99.83 173	99.70 29	99.99 5	99.61 88

fmvsm_s_conf0.1_n		99.16 50	99.33 32	98.64 192	99.71 45	96.10 258	97.87 204	99.85 18	98.56 140	99.90 13	99.68 22	98.69 46	99.85 138	99.72 26	99.98 12	99.97 4

FMVSNet5		96.01 322	95.20 341	98.41 232	97.53 392	96.10 258	98.74 92	99.50 98	97.22 260	98.03 282	99.04 169	69.80 419	99.88 99	97.27 180	99.71 168	99.25 236

Vis-MVSNet (Re-imp)		97.46 251	97.16 261	98.34 241	99.55 95	96.10 258	98.94 77	98.44 325	98.32 153	98.16 268	98.62 263	88.76 347	99.73 257	93.88 346	99.79 125	99.18 254

fmvsm_s_conf0.5_n		99.09 62	99.26 44	98.61 201	99.55 95	96.09 261	97.74 223	99.81 28	98.55 141	99.85 22	99.55 54	98.60 54	99.84 156	99.69 31	99.98 12	99.89 16

CHOSEN 1792x2688		97.49 249	97.14 264	98.54 216	99.68 57	96.09 261	96.50 321	99.62 60	91.58 397	98.84 195	98.97 191	92.36 318	99.88 99	96.76 224	99.95 35	99.67 68

fmvsm_s_conf0.5_n_2		99.14 52	99.31 36	98.63 196	99.49 118	96.08 263	97.38 266	99.81 28	99.48 35	99.84 25	99.57 46	98.46 66	99.89 85	99.82 9	99.97 20	99.91 13

fmvsm_s_conf0.1_n_2		99.20 45	99.38 25	98.65 190	99.69 54	96.08 263	97.49 258	99.90 11	99.53 32	99.88 18	99.64 34	98.51 62	99.90 72	99.83 8	99.98 12	99.97 4

SSC-MVS		98.71 113	98.74 98	98.62 198	99.72 42	96.08 263	98.74 92	98.64 316	99.74 10	99.67 51	99.24 123	94.57 278	99.95 24	99.11 65	99.24 284	99.82 33

v144192		98.54 149	98.57 128	98.45 227	99.21 188	95.98 266	97.63 239	99.36 154	97.15 265	99.32 115	99.18 136	95.84 242	99.84 156	99.50 43	99.91 69	99.54 123

ambc				98.24 250	98.82 274	95.97 267	98.62 107	99.00 264		99.27 121	99.21 129	96.99 182	99.50 354	96.55 249	99.50 248	99.26 235

v1144		98.60 139	98.66 114	98.41 232	99.36 154	95.90 268	97.58 247	99.34 166	97.51 222	99.27 121	99.15 146	96.34 218	99.80 204	99.47 45	99.93 49	99.51 137

v1192		98.60 139	98.66 114	98.41 232	99.27 174	95.88 269	97.52 254	99.36 154	97.41 235	99.33 109	99.20 131	96.37 216	99.82 183	99.57 35	99.92 60	99.55 119

PMMVS		96.51 306	95.98 313	98.09 259	97.53 392	95.84 270	94.92 392	98.84 291	91.58 397	96.05 381	95.58 396	95.68 246	99.66 296	95.59 300	98.09 371	98.76 324

FMVSNet3		97.50 246	97.24 257	98.29 246	98.08 363	95.83 271	97.86 205	98.91 275	97.89 191	98.95 171	98.95 198	87.06 357	99.81 197	97.77 154	99.69 178	99.23 241

v2v482		98.56 143	98.62 120	98.37 238	99.42 142	95.81 272	97.58 247	99.16 233	97.90 190	99.28 119	99.01 181	95.98 235	99.79 217	99.33 50	99.90 75	99.51 137

CL-MVSNet_self_test		97.44 254	97.22 258	98.08 262	98.57 324	95.78 273	94.30 409	98.79 299	96.58 293	98.60 227	98.19 310	94.74 276	99.64 304	96.41 258	98.84 331	98.82 309

v1921920		98.54 149	98.60 125	98.38 235	99.20 192	95.76 274	97.56 249	99.36 154	97.23 257	99.38 100	99.17 140	96.02 228	99.84 156	99.57 35	99.90 75	99.54 123

WB-MVS		98.52 155	98.55 129	98.43 230	99.65 64	95.59 275	98.52 118	98.77 302	99.65 19	99.52 72	99.00 184	94.34 284	99.93 46	98.65 100	98.83 332	99.76 50

test_f		98.67 128	98.87 85	98.05 266	99.72 42	95.59 275	98.51 123	99.81 28	96.30 306	99.78 34	99.82 5	96.14 223	98.63 418	99.82 9	99.93 49	99.95 9

v1240		98.55 147	98.62 120	98.32 242	99.22 186	95.58 277	97.51 256	99.45 122	97.16 263	99.45 87	99.24 123	96.12 225	99.85 138	99.60 33	99.88 83	99.55 119

testgi		98.32 177	98.39 156	98.13 258	99.57 83	95.54 278	97.78 215	99.49 105	97.37 239	99.19 135	97.65 344	98.96 26	99.49 357	96.50 253	98.99 320	99.34 213

Patchmatch-RL test		97.26 268	97.02 269	97.99 270	99.52 105	95.53 279	96.13 346	99.71 42	97.47 226	99.27 121	99.16 142	84.30 381	99.62 310	97.89 144	99.77 136	98.81 314

CANet		97.87 219	97.76 221	98.19 254	97.75 376	95.51 280	96.76 308	99.05 251	97.74 200	96.93 345	98.21 308	95.59 249	99.89 85	97.86 149	99.93 49	99.19 251

EPNet		96.14 319	95.44 331	98.25 248	90.76 438	95.50 281	97.92 196	94.65 404	98.97 106	92.98 420	98.85 219	89.12 346	99.87 117	95.99 280	99.68 183	99.39 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_4		99.01 71	99.22 48	98.38 235	99.31 164	95.48 282	97.56 249	99.73 39	98.87 114	99.75 39	99.27 113	98.80 37	99.86 125	99.80 14	99.90 75	99.81 36

Test_1112_low_res		96.99 290	96.55 301	98.31 244	99.35 159	95.47 283	95.84 364	99.53 92	91.51 399	96.80 357	98.48 284	91.36 329	99.83 173	96.58 240	99.53 236	99.62 80

diffmvs		98.22 190	98.24 177	98.17 255	99.00 238	95.44 284	96.38 329	99.58 67	97.79 198	98.53 239	98.50 281	96.76 197	99.74 252	97.95 143	99.64 197	99.34 213
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Anonymous20231206		98.21 192	98.21 179	98.20 252	99.51 107	95.43 285	98.13 162	99.32 174	96.16 309	98.93 179	98.82 225	96.00 230	99.83 173	97.32 178	99.73 155	99.36 207

testdata				98.09 259	98.93 249	95.40 286		98.80 298	90.08 411	97.45 324	98.37 294	95.26 258	99.70 269	93.58 354	98.95 326	99.17 258

mvs5depth		99.30 30	99.59 9	98.44 229	99.65 64	95.35 287	99.82 3	99.94 2	99.83 4	99.42 92	99.94 2	98.13 98	99.96 12	99.63 32	99.96 27	100.00 1

mvsany_test1		97.60 240	97.54 238	97.77 281	97.72 377	95.35 287	95.36 381	97.13 367	94.13 366	99.71 43	99.33 101	97.93 113	99.30 389	97.60 165	98.94 327	98.67 336

PatchT		96.65 302	96.35 306	97.54 307	97.40 400	95.32 289	97.98 189	96.64 380	99.33 56	96.89 352	99.42 82	84.32 380	99.81 197	97.69 161	97.49 387	97.48 403

FE-MVS		95.66 334	94.95 347	97.77 281	98.53 329	95.28 290	99.40 16	96.09 389	93.11 381	97.96 285	99.26 118	79.10 405	99.77 234	92.40 378	98.71 340	98.27 367

test_yl		96.69 299	96.29 309	97.90 271	98.28 349	95.24 291	97.29 275	97.36 358	98.21 164	98.17 265	97.86 332	86.27 362	99.55 337	94.87 315	98.32 357	98.89 301

DCV-MVSNet		96.69 299	96.29 309	97.90 271	98.28 349	95.24 291	97.29 275	97.36 358	98.21 164	98.17 265	97.86 332	86.27 362	99.55 337	94.87 315	98.32 357	98.89 301

sss		97.21 273	96.93 273	98.06 264	98.83 271	95.22 293	96.75 309	98.48 324	94.49 355	97.27 333	97.90 331	92.77 313	99.80 204	96.57 242	99.32 270	99.16 261

MSLP-MVS++		98.02 205	98.14 190	97.64 296	98.58 322	95.19 294	97.48 259	99.23 214	97.47 226	97.90 288	98.62 263	97.04 177	98.81 414	97.55 166	99.41 258	98.94 294

PVSNet_Blended_VisFu		98.17 197	98.15 188	98.22 251	99.73 36	95.15 295	97.36 269	99.68 51	94.45 359	98.99 162	99.27 113	96.87 187	99.94 39	97.13 191	99.91 69	99.57 106

PAPR		95.29 341	94.47 352	97.75 285	97.50 398	95.14 296	94.89 393	98.71 311	91.39 401	95.35 396	95.48 401	94.57 278	99.14 403	84.95 420	97.37 394	98.97 287

pmmvs5		97.64 238	97.49 242	98.08 262	99.14 210	95.12 297	96.70 312	99.05 251	93.77 372	98.62 223	98.83 222	93.23 301	99.75 247	98.33 119	99.76 148	99.36 207

Anonymous20240521		98.69 120	98.87 85	98.16 257	99.77 26	95.11 298	99.08 58	99.44 126	99.34 55	99.33 109	99.55 54	94.10 292	99.94 39	99.25 57	99.96 27	99.42 178

test_fmvs3		99.12 59	99.41 22	98.25 248	99.76 29	95.07 299	99.05 64	99.94 2	97.78 199	99.82 28	99.84 3	98.56 59	99.71 265	99.96 1	99.96 27	99.97 4

v148		98.45 161	98.60 125	98.00 269	99.44 136	94.98 300	97.44 263	99.06 248	98.30 155	99.32 115	98.97 191	96.65 203	99.62 310	98.37 115	99.85 91	99.39 191

MDA-MVSNet-bldmvs		97.94 211	97.91 213	98.06 264	99.44 136	94.96 301	96.63 315	99.15 238	98.35 149	98.83 196	99.11 152	94.31 285	99.85 138	96.60 239	98.72 338	99.37 200

new_pmnet		96.99 290	96.76 287	97.67 292	98.72 288	94.89 302	95.95 356	98.20 336	92.62 388	98.55 236	98.54 272	94.88 269	99.52 348	93.96 343	99.44 256	98.59 343

fmvsm_s_conf0.5_n_7		98.83 95	99.04 70	98.20 252	99.30 168	94.83 303	97.23 279	99.36 154	98.64 125	99.84 25	99.43 81	98.10 100	99.91 65	99.56 37	99.96 27	99.87 20

HY-MVS	95.94 13	95.90 326	95.35 336	97.55 306	97.95 367	94.79 304	98.81 91	96.94 374	92.28 392	95.17 397	98.57 270	89.90 341	99.75 247	91.20 395	97.33 398	98.10 374

FA-MVS(test-final)		96.99 290	96.82 283	97.50 311	98.70 295	94.78 305	99.34 20	96.99 370	95.07 343	98.48 244	99.33 101	88.41 354	99.65 301	96.13 277	98.92 329	98.07 376

patch_mono-2		98.51 156	98.63 118	98.17 255	99.38 147	94.78 305	97.36 269	99.69 46	98.16 174	98.49 243	99.29 110	97.06 176	99.97 5	98.29 120	99.91 69	99.76 50

D2MVS		97.84 226	97.84 218	97.83 276	99.14 210	94.74 307	96.94 297	98.88 280	95.84 322	98.89 185	98.96 194	94.40 282	99.69 273	97.55 166	99.95 35	99.05 270

EI-MVSNet		98.40 166	98.51 134	98.04 267	99.10 216	94.73 308	97.20 284	98.87 282	98.97 106	99.06 149	99.02 172	96.00 230	99.80 204	98.58 103	99.82 105	99.60 89

MVS_Test		98.18 195	98.36 160	97.67 292	98.48 332	94.73 308	98.18 155	99.02 259	97.69 203	98.04 281	99.11 152	97.22 169	99.56 333	98.57 105	98.90 330	98.71 328

IterMVS-LS		98.55 147	98.70 108	98.09 259	99.48 126	94.73 308	97.22 283	99.39 144	98.97 106	99.38 100	99.31 106	96.00 230	99.93 46	98.58 103	99.97 20	99.60 89
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MIMVSNet		96.62 304	96.25 312	97.71 291	99.04 232	94.66 311	99.16 51	96.92 375	97.23 257	97.87 291	99.10 155	86.11 366	99.65 301	91.65 386	99.21 291	98.82 309

CANet_DTU		97.26 268	97.06 267	97.84 275	97.57 387	94.65 312	96.19 341	98.79 299	97.23 257	95.14 398	98.24 305	93.22 302	99.84 156	97.34 177	99.84 95	99.04 274

WTY-MVS		96.67 301	96.27 311	97.87 274	98.81 277	94.61 313	96.77 307	97.92 346	94.94 347	97.12 336	97.74 339	91.11 331	99.82 183	93.89 345	98.15 368	99.18 254

PMMVS2		98.07 203	98.08 196	98.04 267	99.41 144	94.59 314	94.59 403	99.40 142	97.50 223	98.82 199	98.83 222	96.83 190	99.84 156	97.50 171	99.81 109	99.71 57

Syy-MVS		96.04 321	95.56 327	97.49 312	97.10 408	94.48 315	96.18 343	96.58 381	95.65 326	94.77 401	92.29 430	91.27 330	99.36 379	98.17 127	98.05 375	98.63 338

ET-MVSNet_ETH3D		94.30 358	93.21 369	97.58 301	98.14 359	94.47 316	94.78 395	93.24 417	94.72 351	89.56 429	95.87 392	78.57 408	99.81 197	96.91 207	97.11 402	98.46 348

testing3		93.51 371	92.09 382	97.75 285	98.60 317	94.40 317	97.32 272	95.26 401	97.56 217	96.79 358	95.50 399	53.57 439	99.77 234	95.26 307	98.97 324	99.08 266

thisisatest0530		95.27 342	94.45 353	97.74 287	99.19 195	94.37 318	97.86 205	90.20 427	97.17 262	98.22 263	97.65 344	73.53 415	99.90 72	96.90 212	99.35 266	98.95 290

TinyColmap		97.89 215	97.98 205	97.60 299	98.86 265	94.35 319	96.21 339	99.44 126	97.45 233	99.06 149	98.88 213	97.99 110	99.28 393	94.38 333	99.58 219	99.18 254

CR-MVSNet		96.28 315	95.95 314	97.28 322	97.71 380	94.22 320	98.11 166	98.92 273	92.31 391	96.91 348	99.37 90	85.44 372	99.81 197	97.39 175	97.36 396	97.81 390

RPMNet		97.02 286	96.93 273	97.30 321	97.71 380	94.22 320	98.11 166	99.30 187	99.37 51	96.91 348	99.34 99	86.72 359	99.87 117	97.53 169	97.36 396	97.81 390

MVSTER		96.86 294	96.55 301	97.79 279	97.91 370	94.21 322	97.56 249	98.87 282	97.49 225	99.06 149	99.05 167	80.72 396	99.80 204	98.44 112	99.82 105	99.37 200

DeepMVS_CX				93.44 407	98.24 352	94.21 322		94.34 407	64.28 433	91.34 427	94.87 414	89.45 345	92.77 434	77.54 431	93.14 427	93.35 429

test_vis1_n		98.31 179	98.50 136	97.73 290	99.76 29	94.17 324	98.68 102	99.91 9	96.31 304	99.79 33	99.57 46	92.85 312	99.42 372	99.79 16	99.84 95	99.60 89

GA-MVS		95.86 327	95.32 337	97.49 312	98.60 317	94.15 325	93.83 416	97.93 345	95.49 332	96.68 360	97.42 358	83.21 388	99.30 389	96.22 269	98.55 353	99.01 278

ttmdpeth		97.91 212	98.02 201	97.58 301	98.69 300	94.10 326	98.13 162	98.90 276	97.95 184	97.32 332	99.58 44	95.95 238	98.75 416	96.41 258	99.22 288	99.87 20

test_fmvs2		98.70 117	98.97 77	97.89 273	99.54 100	94.05 327	98.55 114	99.92 7	96.78 284	99.72 41	99.78 10	96.60 205	99.67 285	99.91 2	99.90 75	99.94 10

BH-RMVSNet		96.83 295	96.58 300	97.58 301	98.47 333	94.05 327	96.67 313	97.36 358	96.70 289	97.87 291	97.98 325	95.14 261	99.44 369	90.47 404	98.58 352	99.25 236

cl____		97.02 286	96.83 282	97.58 301	97.82 374	94.04 329	94.66 399	99.16 233	97.04 269	98.63 221	98.71 242	88.68 350	99.69 273	97.00 199	99.81 109	99.00 282

DIV-MVS_self_test		97.02 286	96.84 281	97.58 301	97.82 374	94.03 330	94.66 399	99.16 233	97.04 269	98.63 221	98.71 242	88.69 348	99.69 273	97.00 199	99.81 109	99.01 278

MVS		93.19 377	92.09 382	96.50 354	96.91 411	94.03 330	98.07 172	98.06 343	68.01 432	94.56 406	96.48 379	95.96 237	99.30 389	83.84 422	96.89 405	96.17 419

JIA-IIPM		95.52 338	95.03 344	97.00 334	96.85 413	94.03 330	96.93 299	95.82 394	99.20 71	94.63 405	99.71 19	83.09 389	99.60 318	94.42 329	94.64 422	97.36 407

baseline1		95.96 325	95.44 331	97.52 309	98.51 331	93.99 333	98.39 138	96.09 389	98.21 164	98.40 254	97.76 338	86.88 358	99.63 307	95.42 304	89.27 431	98.95 290

TR-MVS		95.55 337	95.12 343	96.86 345	97.54 390	93.94 334	96.49 322	96.53 383	94.36 362	97.03 343	96.61 376	94.26 287	99.16 401	86.91 417	96.31 411	97.47 404

jason		97.45 253	97.35 251	97.76 284	99.24 181	93.93 335	95.86 361	98.42 327	94.24 363	98.50 242	98.13 312	94.82 270	99.91 65	97.22 183	99.73 155	99.43 175
jason: jason.
xiu_mvs_v1_base_debu		97.86 220	98.17 184	96.92 339	98.98 242	93.91 336	96.45 323	99.17 230	97.85 194	98.41 250	97.14 368	98.47 63	99.92 56	98.02 136	99.05 309	96.92 410

xiu_mvs_v1_base		97.86 220	98.17 184	96.92 339	98.98 242	93.91 336	96.45 323	99.17 230	97.85 194	98.41 250	97.14 368	98.47 63	99.92 56	98.02 136	99.05 309	96.92 410

xiu_mvs_v1_base_debi		97.86 220	98.17 184	96.92 339	98.98 242	93.91 336	96.45 323	99.17 230	97.85 194	98.41 250	97.14 368	98.47 63	99.92 56	98.02 136	99.05 309	96.92 410

MVSFormer		98.26 186	98.43 149	97.77 281	98.88 263	93.89 339	99.39 17	99.56 81	99.11 82	98.16 268	98.13 312	93.81 296	99.97 5	99.26 55	99.57 223	99.43 175

lupinMVS		97.06 283	96.86 279	97.65 294	98.88 263	93.89 339	95.48 376	97.97 344	93.53 375	98.16 268	97.58 348	93.81 296	99.91 65	96.77 223	99.57 223	99.17 258

tttt0517		95.64 335	94.98 345	97.64 296	99.36 154	93.81 341	98.72 97	90.47 426	98.08 177	98.67 216	98.34 298	73.88 414	99.92 56	97.77 154	99.51 241	99.20 246

MS-PatchMatch		97.68 235	97.75 222	97.45 315	98.23 354	93.78 342	97.29 275	98.84 291	96.10 311	98.64 220	98.65 256	96.04 227	99.36 379	96.84 218	99.14 301	99.20 246

RRT-MVS		97.88 217	97.98 205	97.61 298	98.15 358	93.77 343	98.97 73	99.64 58	99.16 79	98.69 213	99.42 82	91.60 326	99.89 85	97.63 162	98.52 354	99.16 261

PVSNet_BlendedMVS		97.55 245	97.53 239	97.60 299	98.92 253	93.77 343	96.64 314	99.43 132	94.49 355	97.62 307	99.18 136	96.82 191	99.67 285	94.73 318	99.93 49	99.36 207

PVSNet_Blended		96.88 293	96.68 292	97.47 314	98.92 253	93.77 343	94.71 396	99.43 132	90.98 405	97.62 307	97.36 362	96.82 191	99.67 285	94.73 318	99.56 226	98.98 284

dcpmvs_2		98.78 104	99.11 61	97.78 280	99.56 91	93.67 346	99.06 62	99.86 16	99.50 34	99.66 52	99.26 118	97.21 170	99.99 2	98.00 139	99.91 69	99.68 65

USDC		97.41 257	97.40 246	97.44 316	98.94 247	93.67 346	95.17 385	99.53 92	94.03 369	98.97 167	99.10 155	95.29 257	99.34 383	95.84 290	99.73 155	99.30 227

ETVMVS		92.60 385	91.08 394	97.18 326	97.70 382	93.65 348	96.54 317	95.70 396	96.51 294	94.68 403	92.39 429	61.80 436	99.50 354	86.97 415	97.41 392	98.40 359

SSC-MVS3.2		98.53 151	98.79 94	97.74 287	99.46 130	93.62 349	96.45 323	99.34 166	99.33 56	98.93 179	98.70 245	97.90 115	99.90 72	99.12 64	99.92 60	99.69 64

test0.0.03 1		94.51 353	93.69 363	96.99 335	96.05 426	93.61 350	94.97 391	93.49 414	96.17 307	97.57 313	94.88 412	82.30 393	99.01 407	93.60 353	94.17 425	98.37 363

test_fmvs1_n		98.09 201	98.28 170	97.52 309	99.68 57	93.47 351	98.63 105	99.93 5	95.41 337	99.68 49	99.64 34	91.88 325	99.48 360	99.82 9	99.87 86	99.62 80

BH-untuned		96.83 295	96.75 288	97.08 331	98.74 285	93.33 352	96.71 311	98.26 333	96.72 287	98.44 247	97.37 361	95.20 259	99.47 363	91.89 381	97.43 391	98.44 354

c3_l		97.36 260	97.37 249	97.31 320	98.09 362	93.25 353	95.01 390	99.16 233	97.05 268	98.77 205	98.72 241	92.88 310	99.64 304	96.93 206	99.76 148	99.05 270

MDA-MVSNet_test_wron		97.60 240	97.66 231	97.41 318	99.04 232	93.09 354	95.27 382	98.42 327	97.26 250	98.88 188	98.95 198	95.43 255	99.73 257	97.02 198	98.72 338	99.41 181

miper_ehance_all_eth		97.06 283	97.03 268	97.16 330	97.83 373	93.06 355	94.66 399	99.09 245	95.99 317	98.69 213	98.45 286	92.73 315	99.61 317	96.79 220	99.03 313	98.82 309

Patchmatch-test		96.55 305	96.34 307	97.17 328	98.35 345	93.06 355	98.40 137	97.79 347	97.33 242	98.41 250	98.67 251	83.68 386	99.69 273	95.16 309	99.31 272	98.77 322

MG-MVS		96.77 298	96.61 297	97.26 324	98.31 348	93.06 355	95.93 357	98.12 341	96.45 299	97.92 286	98.73 239	93.77 298	99.39 376	91.19 396	99.04 312	99.33 218

YYNet1		97.60 240	97.67 228	97.39 319	99.04 232	93.04 358	95.27 382	98.38 330	97.25 251	98.92 181	98.95 198	95.48 254	99.73 257	96.99 201	98.74 336	99.41 181

thisisatest0515		94.12 362	93.16 370	96.97 337	98.60 317	92.90 359	93.77 417	90.61 425	94.10 367	96.91 348	95.87 392	74.99 413	99.80 204	94.52 324	99.12 306	98.20 369

miper_lstm_enhance		97.18 276	97.16 261	97.25 325	98.16 357	92.85 360	95.15 387	99.31 179	97.25 251	98.74 210	98.78 232	90.07 339	99.78 228	97.19 184	99.80 120	99.11 265

cl22		95.79 330	95.39 334	96.98 336	96.77 415	92.79 361	94.40 407	98.53 321	94.59 354	97.89 289	98.17 311	82.82 392	99.24 395	96.37 260	99.03 313	98.92 296

eth_miper_zixun_eth		97.23 272	97.25 256	97.17 328	98.00 366	92.77 362	94.71 396	99.18 226	97.27 249	98.56 234	98.74 238	91.89 324	99.69 273	97.06 197	99.81 109	99.05 270

1314		95.74 331	95.60 323	96.17 367	97.53 392	92.75 363	98.07 172	98.31 332	91.22 402	94.25 408	96.68 374	95.53 250	99.03 404	91.64 387	97.18 400	96.74 414

testing222		91.96 393	90.37 397	96.72 350	97.47 399	92.59 364	96.11 347	94.76 403	96.83 281	92.90 421	92.87 427	57.92 437	99.55 337	86.93 416	97.52 386	98.00 381

PAPM		91.88 395	90.34 398	96.51 353	98.06 364	92.56 365	92.44 424	97.17 365	86.35 421	90.38 428	96.01 387	86.61 360	99.21 398	70.65 434	95.43 419	97.75 394

pmmvs3		95.03 347	94.40 354	96.93 338	97.70 382	92.53 366	95.08 388	97.71 350	88.57 417	97.71 302	98.08 319	79.39 403	99.82 183	96.19 271	99.11 307	98.43 356

xiu_mvs_v2_base		97.16 278	97.49 242	96.17 367	98.54 327	92.46 367	95.45 377	98.84 291	97.25 251	97.48 321	96.49 378	98.31 78	99.90 72	96.34 263	98.68 345	96.15 421

PS-MVSNAJ		97.08 282	97.39 247	96.16 369	98.56 325	92.46 367	95.24 384	98.85 290	97.25 251	97.49 320	95.99 388	98.07 101	99.90 72	96.37 260	98.67 346	96.12 422

test_fmvs1		97.72 232	97.94 210	97.07 333	98.66 310	92.39 369	97.68 229	99.81 28	95.20 342	99.54 66	99.44 79	91.56 328	99.41 373	99.78 18	99.77 136	99.40 190

gg-mvs-nofinetune		92.37 389	91.20 393	95.85 373	95.80 430	92.38 370	99.31 27	81.84 437	99.75 8	91.83 426	99.74 15	68.29 421	99.02 405	87.15 414	97.12 401	96.16 420

cascas		94.79 351	94.33 357	96.15 370	96.02 428	92.36 371	92.34 425	99.26 206	85.34 424	95.08 399	94.96 411	92.96 309	98.53 419	94.41 332	98.59 351	97.56 402

test_cas_vis1_n_1920		98.33 176	98.68 111	97.27 323	99.69 54	92.29 372	98.03 178	99.85 18	97.62 208	99.96 4	99.62 37	93.98 293	99.74 252	99.52 42	99.86 90	99.79 39

miper_enhance_ethall		96.01 322	95.74 317	96.81 346	96.41 423	92.27 373	93.69 418	98.89 279	91.14 404	98.30 256	97.35 363	90.58 336	99.58 328	96.31 264	99.03 313	98.60 340

new-patchmatchnet		98.35 172	98.74 98	97.18 326	99.24 181	92.23 374	96.42 327	99.48 107	98.30 155	99.69 47	99.53 60	97.44 156	99.82 183	98.84 85	99.77 136	99.49 144

GG-mvs-BLEND				94.76 392	94.54 432	92.13 375	99.31 27	80.47 438		88.73 432	91.01 432	67.59 425	98.16 425	82.30 427	94.53 424	93.98 428

mvs_anonymous		97.83 228	98.16 187	96.87 342	98.18 356	91.89 376	97.31 273	98.90 276	97.37 239	98.83 196	99.46 74	96.28 219	99.79 217	98.90 80	98.16 367	98.95 290

ADS-MVSNet2		95.43 340	94.98 345	96.76 349	98.14 359	91.74 377	97.92 196	97.76 348	90.23 407	96.51 369	98.91 203	85.61 369	99.85 138	92.88 367	96.90 403	98.69 332

MVStest1		95.86 327	95.60 323	96.63 351	95.87 429	91.70 378	97.93 193	98.94 267	98.03 178	99.56 62	99.66 29	71.83 416	98.26 422	99.35 49	99.24 284	99.91 13

MVE	83.40 22	92.50 386	91.92 388	94.25 396	98.83 271	91.64 379	92.71 422	83.52 436	95.92 320	86.46 434	95.46 402	95.20 259	95.40 432	80.51 428	98.64 347	95.73 425
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres600view7		94.45 354	93.83 361	96.29 360	99.06 228	91.53 380	97.99 188	94.24 410	98.34 150	97.44 325	95.01 408	79.84 399	99.67 285	84.33 421	98.23 361	97.66 398

DSMNet-mixed		97.42 256	97.60 236	96.87 342	99.15 209	91.46 381	98.54 116	99.12 240	92.87 385	97.58 311	99.63 36	96.21 221	99.90 72	95.74 293	99.54 232	99.27 232

tfpn200view9		94.03 363	93.44 366	95.78 375	98.93 249	91.44 382	97.60 244	94.29 408	97.94 186	97.10 337	94.31 417	79.67 401	99.62 310	83.05 423	98.08 372	96.29 417

thres400		94.14 361	93.44 366	96.24 363	98.93 249	91.44 382	97.60 244	94.29 408	97.94 186	97.10 337	94.31 417	79.67 401	99.62 310	83.05 423	98.08 372	97.66 398

thres100view900		94.19 359	93.67 364	95.75 376	99.06 228	91.35 384	98.03 178	94.24 410	98.33 151	97.40 327	94.98 410	79.84 399	99.62 310	83.05 423	98.08 372	96.29 417

BH-w/o		95.13 345	94.89 349	95.86 372	98.20 355	91.31 385	95.65 369	97.37 357	93.64 373	96.52 368	95.70 395	93.04 308	99.02 405	88.10 412	95.82 417	97.24 408

thres200		93.72 369	93.14 371	95.46 384	98.66 310	91.29 386	96.61 316	94.63 405	97.39 237	96.83 355	93.71 420	79.88 398	99.56 333	82.40 426	98.13 369	95.54 426

baseline2		93.73 368	92.83 374	96.42 356	97.70 382	91.28 387	96.84 304	89.77 428	93.96 371	92.44 423	95.93 390	79.14 404	99.77 234	92.94 365	96.76 407	98.21 368

testing91		93.32 374	92.27 379	96.47 355	97.54 390	91.25 388	96.17 345	96.76 378	97.18 261	93.65 418	93.50 422	65.11 433	99.63 307	93.04 364	97.45 389	98.53 345

IB-MVS	91.63 19	92.24 391	90.90 395	96.27 361	97.22 405	91.24 389	94.36 408	93.33 416	92.37 390	92.24 425	94.58 416	66.20 429	99.89 85	93.16 363	94.63 423	97.66 398
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
ppachtmachnet_test		97.50 246	97.74 223	96.78 348	98.70 295	91.23 390	94.55 404	99.05 251	96.36 301	99.21 133	98.79 230	96.39 213	99.78 228	96.74 226	99.82 105	99.34 213

IterMVS-SCA-FT		97.85 225	98.18 183	96.87 342	99.27 174	91.16 391	95.53 373	99.25 207	99.10 89	99.41 94	99.35 95	93.10 305	99.96 12	98.65 100	99.94 44	99.49 144

MonoMVSNet		96.25 316	96.53 303	95.39 385	96.57 418	91.01 392	98.82 90	97.68 352	98.57 137	98.03 282	99.37 90	90.92 333	97.78 426	94.99 311	93.88 426	97.38 406

dmvs_testset		92.94 381	92.21 381	95.13 388	98.59 320	90.99 393	97.65 235	92.09 421	96.95 274	94.00 413	93.55 421	92.34 319	96.97 430	72.20 432	92.52 428	97.43 405

WAC-MVS						90.90 394								91.37 392

myMVS_eth3d		91.92 394	90.45 396	96.30 359	97.10 408	90.90 394	96.18 343	96.58 381	95.65 326	94.77 401	92.29 430	53.88 438	99.36 379	89.59 408	98.05 375	98.63 338

testing11		93.08 379	92.02 384	96.26 362	97.56 388	90.83 396	96.32 333	95.70 396	96.47 298	92.66 422	93.73 419	64.36 434	99.59 322	93.77 350	97.57 385	98.37 363

test_vis1_n_1920		98.40 166	98.92 80	96.81 346	99.74 35	90.76 397	98.15 160	99.91 9	98.33 151	99.89 16	99.55 54	95.07 263	99.88 99	99.76 20	99.93 49	99.79 39

testing99		93.04 380	91.98 387	96.23 364	97.53 392	90.70 398	96.35 331	95.94 392	96.87 279	93.41 419	93.43 424	63.84 435	99.59 322	93.24 362	97.19 399	98.40 359

WB-MVSnew		95.73 332	95.57 326	96.23 364	96.70 416	90.70 398	96.07 349	93.86 413	95.60 328	97.04 341	95.45 405	96.00 230	99.55 337	91.04 397	98.31 359	98.43 356

IterMVS		97.73 231	98.11 192	96.57 352	99.24 181	90.28 400	95.52 375	99.21 216	98.86 116	99.33 109	99.33 101	93.11 304	99.94 39	98.49 110	99.94 44	99.48 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UBG		93.25 376	92.32 377	96.04 371	97.72 377	90.16 401	95.92 359	95.91 393	96.03 315	93.95 415	93.04 426	69.60 420	99.52 348	90.72 403	97.98 378	98.45 351

ADS-MVSNet		95.24 343	94.93 348	96.18 366	98.14 359	90.10 402	97.92 196	97.32 361	90.23 407	96.51 369	98.91 203	85.61 369	99.74 252	92.88 367	96.90 403	98.69 332

our_test_3		97.39 259	97.73 225	96.34 358	98.70 295	89.78 403	94.61 402	98.97 266	96.50 295	99.04 156	98.85 219	95.98 235	99.84 156	97.26 181	99.67 189	99.41 181

WBMVS		95.18 344	94.78 350	96.37 357	97.68 385	89.74 404	95.80 365	98.73 309	97.54 220	98.30 256	98.44 287	70.06 418	99.82 183	96.62 237	99.87 86	99.54 123

KD-MVS_2432*1600		92.87 383	91.99 385	95.51 382	91.37 436	89.27 405	94.07 411	98.14 339	95.42 334	97.25 334	96.44 381	67.86 422	99.24 395	91.28 393	96.08 415	98.02 378

miper_refine_blended		92.87 383	91.99 385	95.51 382	91.37 436	89.27 405	94.07 411	98.14 339	95.42 334	97.25 334	96.44 381	67.86 422	99.24 395	91.28 393	96.08 415	98.02 378

PVSNet	93.40 17	95.67 333	95.70 319	95.57 380	98.83 271	88.57 407	92.50 423	97.72 349	92.69 387	96.49 372	96.44 381	93.72 299	99.43 370	93.61 352	99.28 278	98.71 328

tpm		94.67 352	94.34 356	95.66 378	97.68 385	88.42 408	97.88 201	94.90 402	94.46 357	96.03 382	98.56 271	78.66 406	99.79 217	95.88 284	95.01 421	98.78 321

SCA		96.41 312	96.66 295	95.67 377	98.24 352	88.35 409	95.85 363	96.88 376	96.11 310	97.67 305	98.67 251	93.10 305	99.85 138	94.16 335	99.22 288	98.81 314

CHOSEN 280x420		95.51 339	95.47 328	95.65 379	98.25 351	88.27 410	93.25 420	98.88 280	93.53 375	94.65 404	97.15 367	86.17 364	99.93 46	97.41 174	99.93 49	98.73 327

ECVR-MVS		96.42 311	96.61 297	95.85 373	99.38 147	88.18 411	99.22 42	86.00 434	99.08 94	99.36 104	99.57 46	88.47 353	99.82 183	98.52 109	99.95 35	99.54 123

EPMVS		93.72 369	93.27 368	95.09 390	96.04 427	87.76 412	98.13 162	85.01 435	94.69 352	96.92 346	98.64 259	78.47 410	99.31 387	95.04 310	96.46 409	98.20 369

EPNet_dtu		94.93 350	94.78 350	95.38 386	93.58 434	87.68 413	96.78 306	95.69 398	97.35 241	89.14 431	98.09 318	88.15 355	99.49 357	94.95 314	99.30 275	98.98 284
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
myMVS_eth3d28		92.92 382	92.31 378	94.77 391	97.84 372	87.59 414	96.19 341	96.11 388	97.08 267	94.27 407	93.49 423	66.07 430	98.78 415	91.78 383	97.93 380	97.92 384

PatchmatchNet		95.58 336	95.67 321	95.30 387	97.34 402	87.32 415	97.65 235	96.65 379	95.30 338	97.07 339	98.69 247	84.77 375	99.75 247	94.97 313	98.64 347	98.83 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test1111		96.49 309	96.82 283	95.52 381	99.42 142	87.08 416	99.22 42	87.14 432	99.11 82	99.46 84	99.58 44	88.69 348	99.86 125	98.80 86	99.95 35	99.62 80

tpm2		93.09 378	92.58 376	94.62 393	97.56 388	86.53 417	97.66 233	95.79 395	86.15 422	94.07 412	98.23 307	75.95 411	99.53 344	90.91 400	96.86 406	97.81 390

tpmvs		95.02 348	95.25 338	94.33 395	96.39 424	85.87 418	98.08 170	96.83 377	95.46 333	95.51 394	98.69 247	85.91 367	99.53 344	94.16 335	96.23 412	97.58 401

EU-MVSNet		97.66 237	98.50 136	95.13 388	99.63 74	85.84 419	98.35 142	98.21 335	98.23 162	99.54 66	99.46 74	95.02 264	99.68 282	98.24 121	99.87 86	99.87 20

CostFormer		93.97 364	93.78 362	94.51 394	97.53 392	85.83 420	97.98 189	95.96 391	89.29 415	94.99 400	98.63 261	78.63 407	99.62 310	94.54 323	96.50 408	98.09 375

E-PMN		94.17 360	94.37 355	93.58 405	96.86 412	85.71 421	90.11 429	97.07 368	98.17 171	97.82 297	97.19 365	84.62 377	98.94 409	89.77 406	97.68 384	96.09 423

EMVS		93.83 366	94.02 358	93.23 410	96.83 414	84.96 422	89.77 430	96.32 385	97.92 188	97.43 326	96.36 384	86.17 364	98.93 410	87.68 413	97.73 383	95.81 424

tpm cat1		93.29 375	93.13 372	93.75 403	97.39 401	84.74 423	97.39 265	97.65 353	83.39 427	94.16 409	98.41 289	82.86 391	99.39 376	91.56 389	95.35 420	97.14 409

UWE-MVS		92.38 388	91.76 391	94.21 398	97.16 406	84.65 424	95.42 379	88.45 430	95.96 318	96.17 376	95.84 394	66.36 427	99.71 265	91.87 382	98.64 347	98.28 366

test-LLR		93.90 365	93.85 360	94.04 399	96.53 419	84.62 425	94.05 413	92.39 419	96.17 307	94.12 410	95.07 406	82.30 393	99.67 285	95.87 287	98.18 364	97.82 388

test-mter		92.33 390	91.76 391	94.04 399	96.53 419	84.62 425	94.05 413	92.39 419	94.00 370	94.12 410	95.07 406	65.63 432	99.67 285	95.87 287	98.18 364	97.82 388

tpmrst		95.07 346	95.46 329	93.91 401	97.11 407	84.36 427	97.62 240	96.96 372	94.98 345	96.35 374	98.80 228	85.46 371	99.59 322	95.60 299	96.23 412	97.79 393

PVSNet_0	89.98 21	91.15 396	90.30 399	93.70 404	97.72 377	84.34 428	90.24 427	97.42 356	90.20 410	93.79 416	93.09 425	90.90 334	98.89 413	86.57 418	72.76 434	97.87 387

reproduce_monomvs		95.00 349	95.25 338	94.22 397	97.51 397	83.34 429	97.86 205	98.44 325	98.51 142	99.29 118	99.30 107	67.68 424	99.56 333	98.89 82	99.81 109	99.77 45

MDTV_nov1_ep13			95.22 340		97.06 410	83.20 430	97.74 223	96.16 386	94.37 361	96.99 344	98.83 222	83.95 384	99.53 344	93.90 344	97.95 379

UWE-MVS-28		90.22 397	89.28 400	93.02 412	94.50 433	82.87 431	96.52 320	87.51 431	95.21 341	92.36 424	96.04 386	71.57 417	98.25 423	72.04 433	97.77 382	97.94 383

TESTMET0.1,1		92.19 392	91.77 390	93.46 406	96.48 421	82.80 432	94.05 413	91.52 424	94.45 359	94.00 413	94.88 412	66.65 426	99.56 333	95.78 292	98.11 370	98.02 378

test2506		92.39 387	91.89 389	93.89 402	99.38 147	82.28 433	99.32 23	66.03 440	99.08 94	98.77 205	99.57 46	66.26 428	99.84 156	98.71 96	99.95 35	99.54 123

gm-plane-assit					94.83 431	81.97 434			88.07 419		94.99 409		99.60 318	91.76 384

testing3-2		93.78 367	93.91 359	93.39 408	98.82 274	81.72 435	97.76 220	95.28 400	98.60 132	96.54 366	96.66 375	65.85 431	99.62 310	96.65 235	98.99 320	98.82 309

dp		93.47 372	93.59 365	93.13 411	96.64 417	81.62 436	97.66 233	96.42 384	92.80 386	96.11 378	98.64 259	78.55 409	99.59 322	93.31 360	92.18 430	98.16 371

CVMVSNet		96.25 316	97.21 259	93.38 409	99.10 216	80.56 437	97.20 284	98.19 338	96.94 275	99.00 161	99.02 172	89.50 344	99.80 204	96.36 262	99.59 214	99.78 42

MVS-HIRNet		94.32 356	95.62 322	90.42 414	98.46 335	75.36 438	96.29 335	89.13 429	95.25 339	95.38 395	99.75 13	92.88 310	99.19 399	94.07 341	99.39 260	96.72 415

MDTV_nov1_ep13_2view						74.92 439	97.69 228		90.06 412	97.75 301		85.78 368		93.52 355		98.69 332

tmp_tt		78.77 400	78.73 403	78.90 416	58.45 441	74.76 440	94.20 410	78.26 439	39.16 434	86.71 433	92.82 428	80.50 397	75.19 436	86.16 419	92.29 429	86.74 430

dongtai		76.24 401	75.95 404	77.12 417	92.39 435	67.91 441	90.16 428	59.44 442	82.04 428	89.42 430	94.67 415	49.68 440	81.74 435	48.06 435	77.66 433	81.72 431

kuosan		69.30 402	68.95 405	70.34 418	87.68 439	65.00 442	91.11 426	59.90 441	69.02 431	74.46 436	88.89 433	48.58 441	68.03 437	28.61 436	72.33 435	77.99 432

test_method		79.78 399	79.50 402	80.62 415	80.21 440	45.76 443	70.82 431	98.41 329	31.08 435	80.89 435	97.71 340	84.85 374	97.37 428	91.51 390	80.03 432	98.75 325

test123		17.04 405	20.11 408	7.82 419	10.25 443	4.91 444	94.80 394	4.47 444	4.93 437	10.00 439	24.28 436	9.69 442	3.64 438	10.14 437	12.43 437	14.92 434

testmvs		17.12 404	20.53 407	6.87 420	12.05 442	4.20 445	93.62 419	6.73 443	4.62 438	10.41 438	24.33 435	8.28 443	3.56 439	9.69 438	15.07 436	12.86 435

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

cdsmvs_eth3d_5k		24.66 403	32.88 406	0.00 421	0.00 444	0.00 446	0.00 432	99.10 243	0.00 439	0.00 440	97.58 348	99.21 17	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		8.17 406	10.90 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	98.07 101	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

ab-mvs-re		8.12 407	10.83 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	97.48 354	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

PC_three_1452									93.27 378	99.40 97	98.54 272	98.22 87	97.00 429	95.17 308	99.45 253	99.49 144

eth-test2					0.00 444

eth-test					0.00 444

test_241102_TWO								99.30 187	98.03 178	99.26 125	99.02 172	97.51 150	99.88 99	96.91 207	99.60 210	99.66 70

9.14			97.78 220		99.07 223		97.53 253	99.32 174	95.53 331	98.54 238	98.70 245	97.58 141	99.76 240	94.32 334	99.46 251

test_0728_THIRD									98.17 171	99.08 147	99.02 172	97.89 116	99.88 99	97.07 195	99.71 168	99.70 62

GSMVS																98.81 314

sam_mvs1												84.74 376				98.81 314

sam_mvs												84.29 382

MTGPA								99.20 218

test_post1							97.59 246				20.48 438	83.07 390	99.66 296	94.16 335

test_post											21.25 437	83.86 385	99.70 269

patchmatchnet-post											98.77 234	84.37 379	99.85 138

MTMP							97.93 193	91.91 423

test9_res														93.28 361	99.15 300	99.38 198

agg_prior2														92.50 377	99.16 298	99.37 200

test_prior2							95.74 367		96.48 297	96.11 378	97.63 346	95.92 240		94.16 335	99.20 292

旧先验2							95.76 366		88.56 418	97.52 317			99.66 296	94.48 325

新几何2							95.93 357

无先验							95.74 367	98.74 308	89.38 414				99.73 257	92.38 379		99.22 245

原ACMM2							95.53 373

testdata2													99.79 217	92.80 371

segment_acmp												97.02 180

testdata1							95.44 378		96.32 303

plane_prior5								99.27 201					99.70 269	94.42 329	99.51 241	99.45 167

plane_prior4											97.98 325

plane_prior2							97.77 217		98.20 168

plane_prior1					99.05 231

n2								0.00 445

nn								0.00 445

door-mid								99.57 74

test11								98.87 282

door								99.41 139

HQP-NCC					98.67 305		96.29 335		96.05 312	95.55 389

ACMP_Plane					98.67 305		96.29 335		96.05 312	95.55 389

BP-MVS														92.82 369

HQP4-MVS										95.56 388			99.54 342			99.32 220

HQP3-MVS								99.04 254							99.26 282

HQP2-MVS												93.84 294

ACMMP++_ref															99.77 136

ACMMP++															99.68 183

Test By Simon												96.52 208

High-resolution multi-view benchmark