Adversarial Scene Editing: Automatic Object Removal from Weak Supervision
This addresses the challenge of scene-level image editing without manual interaction, though it is incremental as it builds on existing GAN methods.
The paper tackles the problem of automatic object removal from general scene images by developing a model that uses weak supervision and unpaired data in a GAN framework, achieving effective removal of a wide variety of objects on two datasets.
While great progress has been made recently in automatic image manipulation, it has been limited to object centric images like faces or structured scene datasets. In this work, we take a step towards general scene-level image editing by developing an automatic interaction-free object removal model. Our model learns to find and remove objects from general scene images using image-level labels and unpaired data in a generative adversarial network (GAN) framework. We achieve this with two key contributions: a two-stage editor architecture consisting of a mask generator and image in-painter that co-operate to remove objects, and a novel GAN based prior for the mask generator that allows us to flexibly incorporate knowledge about object shapes. We experimentally show on two datasets that our method effectively removes a wide variety of objects using weak supervision only