DeepAI AI Chat
Log In Sign Up

Learning to Manipulate Individual Objects in an Image

by   Yanchao Yang, et al.
Tsinghua University

We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to objects. Unlike other unsupervised generative models, ours enables object-centric manipulation, without requiring object-level annotations, or any form of annotation for that matter. The key to our method is the combination of spatial disentanglement, enforced by a Contextual Information Separation loss, and perceptual cycle-consistency, enforced by a loss that penalizes changes in the image partition in response to perturbations of the latent factors. We test our method's ability to allow independent control of spatial and semantic factors of variability on existing datasets and also introduce two new ones that highlight the limitations of current methods.


page 3

page 4

page 5

page 6

page 7

page 8


GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

Generative models are emerging as promising tools in robotics and reinfo...

3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation

3D generative models have been recently successful in generating realist...

Unsupervised Semantic Attribute Discovery and Control in Generative Models

This work focuses on the ability to control via latent space factors sem...

Contextual object categorization with energy-based model

Object categorization is a hot issue of an image mining. Contextual info...

Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition

Context, as referred to situational factors related to the object of int...

Guided Generative Models using Weak Supervision for Detecting Object Spatial Arrangement in Overhead Images

The increasing availability and accessibility of numerous overhead image...

AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations

We propose AutoCorrect, a method to automatically learn object-annotatio...

Code Repositories



view repo