Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

by   Rakshith Shetty, et al.

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


page 6

page 8

page 13


BlobGAN-3D: A Spatially-Disentangled 3D-Aware Generative Model for Indoor Scenes

3D-aware image synthesis has attracted increasing interest as it models ...

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis

Existing 3D-aware image synthesis approaches mainly focus on generating ...

Object Discovery with a Copy-Pasting GAN

We tackle the problem of object discovery, where objects are segmented f...

Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data

This paper presents a new method for shadow removal using unpaired data,...

How to make a pizza: Learning a compositional layer-based GAN model

A food recipe is an ordered set of instructions for preparing a particul...

MBA-RainGAN: Multi-branch Attention Generative Adversarial Network for Mixture of Rain Removal from Single Images

Rain severely hampers the visibility of scene objects when images are ca...

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

We study the problem of 3D object generation. We propose a novel framewo...

Please sign up or login with your details

Forgot password? Click here to reset