Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

TL;DR

This paper introduces an automatic, interaction-free scene object removal method using weak supervision, a two-stage GAN-based architecture, and a shape-aware prior, enabling effective general scene editing.

Contribution

It presents a novel two-stage GAN framework with a shape-aware prior for automatic object removal in general scenes using weak supervision.

Findings

Effective removal of diverse objects demonstrated on two datasets.

The method operates without manual annotations or paired data.

The shape-aware prior improves mask accuracy and object removal quality.

Abstract

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