Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Rawal, Hamza"'
Flow based garment warping is an integral part of image-based virtual try-on networks. However, optimizing a single flow predicting network for simultaneous global boundary alignment and local texture preservation results in sub-optimal flow fields.
Externí odkaz:
http://arxiv.org/abs/2311.04932
This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to greedily learn t
Externí odkaz:
http://arxiv.org/abs/2206.09683
Estimating the number of buildings in any geographical region is a vital component of urban analysis, disaster management, and public policy decision. Deep learning methods for building localization and counting in satellite imagery, can serve as a v
Externí odkaz:
http://arxiv.org/abs/2110.13558
Autor:
Zakria, Muaaz1 (AUTHOR), Rawal, Hamza1 (AUTHOR), Sultani, Waqas1 (AUTHOR) waqas.sultani@itu.edu.pk, Ali, Mohsen1 (AUTHOR)
Publikováno v:
Neural Computing & Applications. Oct2023, Vol. 35 Issue 30, p22621-22636. 16p.
