A Dataset of Multi-Illumination Images in the Wild

Lukas Murmann, Michael Gharbi, Miika Aittala, Fredo Durand
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
input ours GT Figure 1 . Using our multi-illumination image dataset of over 1000 scenes, we can train neural networks to solve challenging vision tasks. For instance, one of our models can relight an input image to a novel light direction. Specular highlights pose a significant challenge for many relighting algorithms, but are handled gracefully by our network. Further analysis is presented in Section 4.2. Abstract Collections of images under a single, uncontrolled illumination [42] have
more » ... on [42] have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation [26, 43, 18] . 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. The data simply does not contain the necessary supervisory signals. Multiillumination datasets are notoriously hard to capture, so the data is typically collected at small scale, in controlled environments, either using multiple light sources [10, 53], or robotic gantries [8, 20] . This leads to image collections that are not representative of the variety and complexity of real-world scenes. We introduce a new multi-illumination dataset of more than 1000 real scenes, each captured in high dynamic range and high resolution, 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.
doi:10.1109/iccv.2019.00418 dblp:conf/iccv/MurmannGAD19 fatcat:7ulb5kdahjewfl5kwbzh6oh36a