VIDIT: Virtual Image Dataset for Illumination Transfer
This provides a standardized dataset for researchers in computer vision to improve image relighting techniques, though it is incremental as it builds on existing virtual dataset approaches.
The authors tackled the challenge of deep image relighting by introducing VIDIT, a virtual dataset containing 300 scenes each captured 40 times under varying illumination conditions, to serve as a benchmark for evaluating and advancing illumination manipulation methods.
Deep image relighting is gaining more interest lately, as it allows photo enhancement through illumination-specific retouching without human effort. Aside from aesthetic enhancement and photo montage, image relighting is valuable for domain adaptation, whether to augment datasets for training or to normalize input test data. Accurate relighting is, however, very challenging for various reasons, such as the difficulty in removing and recasting shadows and the modeling of different surfaces. We present a novel dataset, the Virtual Image Dataset for Illumination Transfer (VIDIT), in an effort to create a reference evaluation benchmark and to push forward the development of illumination manipulation methods. Virtual datasets are not only an important step towards achieving real-image performance but have also proven capable of improving training even when real datasets are possible to acquire and available. VIDIT contains 300 virtual scenes used for training, where every scene is captured 40 times in total: from 8 equally-spaced azimuthal angles, each lit with 5 different illuminants.