Abstract: This paper introduces an innovative content-based image retrieval system for precise and effective retrieval of satellite images. The system integrates liquid autoencoders with shearlet ...
As shown below, the inferred masks predicted by our segmentation model trained by the dataset appear similar to the ground truth masks. If you use this dataset in any work, please reference our paper: ...
Abstract: Semantic image synthesis aims to generate high-quality images given semantic conditions, i.e., segmentation masks and style reference images. Existing methods widely adopt generative ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results