Layer Segmentation
Layer segmentation, the process of partitioning data (images, videos, or other multi-layered data) into meaningful constituent layers, aims to improve analysis and processing by isolating individual components. Current research focuses on applying deep learning models, including GANs, CNNs, Transformers, and diffusion models, to achieve accurate segmentation across diverse applications such as medical imaging (e.g., separating bone layers in radiographs, delineating kidney structures), video quality assessment, and UI design. These advancements enable improved diagnostics, enhanced video analysis, more efficient model compression, and automated UI design processes, ultimately impacting various scientific fields and practical applications.
Papers
Generative Image Layer Decomposition with Visual Effects
Jinrui Yang, Qing Liu, Yijun Li, Soo Ye Kim, Daniil Pakhomov, Mengwei Ren, Jianming Zhang, Zhe Lin, Cihang Xie, Yuyin Zhou
A Bilayer Segmentation-Recombination Network for Accurate Segmentation of Overlapping C. elegans
Mengqian Dinga, Jun Liua, Yang Luo, Jinshan Tang