CVPR2024

In-Context Matting

He Guo, Zixuan Ye, Zhiguo Cao, Hao Lu

摘要

In-Context Matting Auxiliary-Input Based Matting Nimage + 1prompt + 1model Npredictions Nimage + Mmodel Npredictions Nimage + Nprompt Npredictions Mask Points Scribbles Figure 1. In-Context Matting. This novel task setting for image matting enables automatic natural image matting of target images of a certain object category conditioned on a reference image of the same category, with user-provided priors such as masks and scribbles on the reference image only. Notice that, our approach exhibits remarkable cross-domain matting quality.