Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme
arXiv:2006.02333
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.
arXiv commentReport for the CS-413 project at EPFL, Switzerland
References in corpus (7)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Conditional Generative Adversarial Nets
- The relativistic discriminator: a key element missing from standard GAN
- Single Image Portrait Relighting
- High-Resolution Daytime Translation Without Domain Labels
- Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
- VIDIT: Virtual Image Dataset for Illumination Transfer