DiffusionLight: Light Probes for Free by Painting a Chrome Ball

arXiv:2312.09168v3 Announce Type: replace-cross
Abstract: We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment map. However, these approaches often struggle with real-world, uncontrolled settings due to the limited diversity and size of their datasets. To address this problem, we leverage diffusion models trained on billions of standard images to render a …

abstract arxiv chrome cs.cv cs.gr cs.lg current datasets environment free however image light lighting map networks neural networks painting panorama simple struggle train type view