Automatic Semantic Content Removal by Learning to Neglect
This addresses the need for more efficient and integrated image editing tools, though it appears incremental as it builds on existing encoder-decoder and GAN methods.
The paper tackles the problem of automatic image content removal and inpainting by introducing a system that jointly performs region segmentation and inpainting in a single pass, outperforming state-of-the-art techniques that require external segmentation modules.
We introduce a new system for automatic image content removal and inpainting. Unlike traditional inpainting algorithms, which require advance knowledge of the region to be filled in, our system automatically detects the area to be removed and infilled. Region segmentation and inpainting are performed jointly in a single pass. In this way, potential segmentation errors are more naturally alleviated by the inpainting module. The system is implemented as an encoder-decoder architecture, with two decoder branches, one tasked with segmentation of the foreground region, the other with inpainting. The encoder and the two decoder branches are linked via neglect nodes, which guide the inpainting process in selecting which areas need reconstruction. The whole model is trained using a conditional GAN strategy. Comparative experiments show that our algorithm outperforms state-of-the-art inpainting techniques (which, unlike our system, do not segment the input image and thus must be aided by an external segmentation module.)