OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
This dataset enables quantitative evaluation for researchers in computer vision and graphics working on inverse rendering, though it is incremental as it builds on existing data collection efforts.
The authors tackled the problem of evaluating inverse rendering and material decomposition methods by introducing OpenIllumination, a real-world dataset with over 108K images of 64 objects under varied illuminations, providing camera parameters, illumination ground truth, and segmentation masks, and they used it to compare several state-of-the-art methods.
We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations. For each image in the dataset, we provide accurate camera parameters, illumination ground truth, and foreground segmentation masks. Our dataset enables the quantitative evaluation of most inverse rendering and material decomposition methods for real objects. We examine several state-of-the-art inverse rendering methods on our dataset and compare their performances. The dataset and code can be found on the project page: https://oppo-us-research.github.io/OpenIllumination.