← Search

Liqing Zhang*

1 accepted papers

2024

COIN-Matting: Confounder Intervention for Image Matting

ECCV 2024poster

"Deep learning methods have significantly advanced the performance of image matting. However, dataset biases can mislead the matting models to biased behavior. In this paper, we identify the two typical biases in existing matting models, specifically contrast bias and transparency bias, and discuss…

Cited by 0SourcePDFScholar