A Dataset of Multi-Illumination Images in the Wild
This dataset addresses a gap for researchers in computer vision working on lighting and material understanding, though it is incremental as it builds on existing single-illumination datasets.
The authors tackled the problem of limited data for inverse lighting and material tasks by introducing a new multi-illumination dataset of over 1000 real scenes captured under 25 lighting conditions, and demonstrated its utility by training state-of-the-art models for illumination estimation, relighting, and white balance.
Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation. But even with modern learning techniques, many inverse problems involving lighting and material understanding remain too severely ill-posed to be solved with single-illumination datasets. To fill this gap, we introduce a new multi-illumination dataset of more than 1000 real scenes, each captured under 25 lighting conditions. We demonstrate the richness of this dataset by training state-of-the-art models for three challenging applications: single-image illumination estimation, image relighting, and mixed-illuminant white balance.