DeepAI AI Chat
Log In Sign Up

Controllable Data Augmentation Through Deep Relighting

by   George Chogovadze, et al.

At the heart of the success of deep learning is the quality of the data. Through data augmentation, one can train models with better generalization capabilities and thus achieve greater results in their field of interest. In this work, we explore how to augment a varied set of image datasets through relighting so as to improve the ability of existing models to be invariant to illumination changes, namely for learned descriptors. We develop a tool, based on an encoder-decoder network, that is able to quickly generate multiple variations of the illumination of various input scenes whilst also allowing the user to define parameters such as the angle of incidence and intensity. We demonstrate that by training models on datasets that have been augmented with our pipeline, it is possible to achieve higher performance on localization benchmarks.


page 4

page 5

page 6

page 7


Illumination-Based Data Augmentation for Robust Background Subtraction

A core challenge in background subtraction (BGS) is handling videos with...

RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather

Camera localization is a fundamental and crucial problem for many roboti...

JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment

Despite substantial progress in no-reference image quality assessment (N...

Augmentation Invariant Manifold Learning

Data augmentation is a widely used technique and an essential ingredient...

3D-Aided Data Augmentation for Robust Face Understanding

Data augmentation has been highly effective in narrowing the data gap an...

Controllable User Dialogue Act Augmentation for Dialogue State Tracking

Prior work has demonstrated that data augmentation is useful for improvi...

Auctus: A Dataset Search Engine for Data Augmentation

Machine Learning models are increasingly being adopted in many applicati...

Code Repositories


Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

view repo