Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076637> ?p ?o ?g. }
- W4386076637 abstract "3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g. 3D computer-aided design models. However, the domain gap between synthetic and real data limits the generalizability of these methods. Thus, we propose a new task, SCoDA, for the domain adaptation of real scan shape completion from synthetic data. A new dataset, ScanSalon, is contributed with a bunch of elaborate 3D models created by skillful artists according to scans. To address this new task, we propose a novel cross-domain feature fusion method for knowledge transfer and a novel volume-consistent self-training framework for robust learning from real data. Extensive experiments prove our method is effective to bring an improvement of 6%~7% mIoU." @default.
- W4386076637 created "2023-08-23" @default.
- W4386076637 creator A5009164482 @default.
- W4386076637 creator A5015323906 @default.
- W4386076637 creator A5024718359 @default.
- W4386076637 creator A5034378184 @default.
- W4386076637 creator A5036114121 @default.
- W4386076637 creator A5042965510 @default.
- W4386076637 creator A5053521834 @default.
- W4386076637 creator A5081747483 @default.
- W4386076637 creator A5090780152 @default.
- W4386076637 date "2023-06-01" @default.
- W4386076637 modified "2023-10-01" @default.
- W4386076637 title "SCoDA: Domain Adaptive Shape Completion for Real Scans" @default.
- W4386076637 cites W2150066425 @default.
- W4386076637 cites W2593768305 @default.
- W4386076637 cites W2594519801 @default.
- W4386076637 cites W2698857938 @default.
- W4386076637 cites W2886499109 @default.
- W4386076637 cites W2903435684 @default.
- W4386076637 cites W2944579304 @default.
- W4386076637 cites W2950111065 @default.
- W4386076637 cites W2953668091 @default.
- W4386076637 cites W2962849139 @default.
- W4386076637 cites W2963197375 @default.
- W4386076637 cites W2963627347 @default.
- W4386076637 cites W2963926543 @default.
- W4386076637 cites W2973014570 @default.
- W4386076637 cites W2981705647 @default.
- W4386076637 cites W2981978060 @default.
- W4386076637 cites W2997088169 @default.
- W4386076637 cites W2998083796 @default.
- W4386076637 cites W3034493208 @default.
- W4386076637 cites W3034584726 @default.
- W4386076637 cites W3034591020 @default.
- W4386076637 cites W3034950592 @default.
- W4386076637 cites W3035014292 @default.
- W4386076637 cites W3035175896 @default.
- W4386076637 cites W3035507572 @default.
- W4386076637 cites W3035515538 @default.
- W4386076637 cites W3035750252 @default.
- W4386076637 cites W3084053805 @default.
- W4386076637 cites W3095473874 @default.
- W4386076637 cites W3097606102 @default.
- W4386076637 cites W3101027576 @default.
- W4386076637 cites W3105863736 @default.
- W4386076637 cites W3116155584 @default.
- W4386076637 cites W3170469318 @default.
- W4386076637 cites W3170754649 @default.
- W4386076637 cites W3173744995 @default.
- W4386076637 cites W3177015573 @default.
- W4386076637 cites W3184081648 @default.
- W4386076637 cites W3191573718 @default.
- W4386076637 cites W3192240783 @default.
- W4386076637 cites W3201726317 @default.
- W4386076637 cites W3202277637 @default.
- W4386076637 cites W3202589837 @default.
- W4386076637 cites W3203745213 @default.
- W4386076637 cites W3203898101 @default.
- W4386076637 cites W3206676377 @default.
- W4386076637 cites W3215071557 @default.
- W4386076637 cites W3216186826 @default.
- W4386076637 cites W3216568609 @default.
- W4386076637 cites W3217147624 @default.
- W4386076637 cites W4214535475 @default.
- W4386076637 cites W4225285600 @default.
- W4386076637 cites W4226254397 @default.
- W4386076637 cites W4242710771 @default.
- W4386076637 cites W4283377170 @default.
- W4386076637 cites W4285197168 @default.
- W4386076637 cites W4312317653 @default.
- W4386076637 cites W4312592225 @default.
- W4386076637 cites W4312607395 @default.
- W4386076637 cites W4312704718 @default.
- W4386076637 cites W4312780402 @default.
- W4386076637 cites W4313127740 @default.
- W4386076637 cites W4313156707 @default.
- W4386076637 doi "https://doi.org/10.1109/cvpr52729.2023.01691" @default.
- W4386076637 hasPublicationYear "2023" @default.
- W4386076637 type Work @default.
- W4386076637 citedByCount "0" @default.
- W4386076637 crossrefType "proceedings-article" @default.
- W4386076637 hasAuthorship W4386076637A5009164482 @default.
- W4386076637 hasAuthorship W4386076637A5015323906 @default.
- W4386076637 hasAuthorship W4386076637A5024718359 @default.
- W4386076637 hasAuthorship W4386076637A5034378184 @default.
- W4386076637 hasAuthorship W4386076637A5036114121 @default.
- W4386076637 hasAuthorship W4386076637A5042965510 @default.
- W4386076637 hasAuthorship W4386076637A5053521834 @default.
- W4386076637 hasAuthorship W4386076637A5081747483 @default.
- W4386076637 hasAuthorship W4386076637A5090780152 @default.
- W4386076637 hasConcept C105795698 @default.
- W4386076637 hasConcept C119857082 @default.
- W4386076637 hasConcept C120665830 @default.
- W4386076637 hasConcept C121332964 @default.
- W4386076637 hasConcept C131979681 @default.
- W4386076637 hasConcept C134306372 @default.
- W4386076637 hasConcept C138885662 @default.
- W4386076637 hasConcept C144133560 @default.
- W4386076637 hasConcept C154945302 @default.