Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme
This work addresses image relighting for applications in photography, cinematography, and computer graphics, but it appears incremental as it describes methods tried without clear advancements.
The authors tackled the problem of image relighting by transferring illumination conditions between images, using a network with an illumination estimation component trained on a rendered dataset of artificial locations with varied scene content, light source location, and color temperature, but no concrete results or numbers were reported.
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.