2 papers
cs.CV2026
Self-supervised Automatic Matting
Xiaonan Hu, Zhiyuan Lu, Jingdong Zhao +1
High-quality alpha mattes are notoriously expensive to annotate, creating a fundamental data bottleneck for deep image matting. While prior work attempts to reduce annotation cost…
cs.CV2025
Efficient Portrait Matte Creation With Layer Diffusion and Connectivity Priors
Zhiyuan Lu, Hao Lu, Hua Huang
Learning effective deep portrait matting models requires training data of both high quality and large quantity. Neither quality nor quantity can be easily met for portrait matting,…