Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme
Published in
arXiv.org(2020)External Links:
TL
TL;DR
The image relighting task of transferring illumination conditions between two images offers an interesting and difficult challenge with potential applications in photography, cinematography and computer graphics and methods are presented to achieve that goal.
Abstract
The image relighting task of transferring illumination conditions between two images offers an interesting and difficult challenge with potential applications in photography, cinematography and computer graphics. In this report we present methods that we tried to achieve that goal. Our models are trained on a rendered dataset of artificial locations with varied scene content, light source location and color temperature. With this dataset, we used a network with illumination estimation component aiming to infer and replace light conditions in the latent space representation of the concerned scenes.
References31 items
1
VIDIT: Virtual Image Dataset for Illumination Transfer
2
High-Resolution Daytime Translation Without Domain Labels
3
Generating Digital Painting Lighting Effects via RGB-space Geometry
4
PyTorch: An Imperative Style, High-Performance Deep Learning Library
5