Compositional GAN: Learning Conditional Image Composition

07/19/2018
by   Samaneh Azadi, et al.
16

Generative Adversarial Networks (GANs) can produce images of surprising complexity and realism, but are generally modeled to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene. Capturing such complex interactions between different objects in the world, including their relative scaling, spatial layout, occlusion, or viewpoint transformation is a challenging problem. In this work, we propose to model object composition in a GAN framework as a self-consistent composition-decomposition network. Our model is conditioned on the object images from their marginal distributions to generate a realistic image from their joint distribution by explicitly learning the possible interactions. We evaluate our model through qualitative experiments and user evaluations in both the scenarios when either paired or unpaired examples for the individual object images and the joint scenes are given during training. Our results reveal that the learned model captures potential interactions between the two object domains given as input to output new instances of composed scene at test time in a reasonable fashion.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

page 7

page 9

page 10

page 11

09/02/2019

Relationship-Aware Spatial Perception Fusion for Realistic Scene Layout Generation

The significant progress on Generative Adversarial Networks (GANs) have ...
01/23/2019

Composition and decomposition of GANs

In this work, we propose a composition/decomposition framework for adver...
06/03/2021

Semantic Palette: Guiding Scene Generation with Class Proportions

Despite the recent progress of generative adversarial networks (GANs) at...
02/02/2019

A Layer-Based Sequential Framework for Scene Generation with GANs

The visual world we sense, interpret and interact everyday is a complex ...
11/26/2018

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks

Generative Adversarial Networks (GANs) have recently achieved impressive...
11/21/2019

Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis

Despite the success of Generative Adversarial Networks (GANs) in image s...
10/18/2021

Boosting Image Outpainting with Semantic Layout Prediction

The objective of image outpainting is to extend image current border and...

Code Repositories

CompositionalGAN

Compositional GAN: Learning Image-Conditional Binary Composition at IJCV 2020


view repo

Compositional-GAN

張歓歓ー卒研


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.