OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
University of California, San Diego · Zhejiang University · Computer Science and Engineering Department, University of California, San Diego · Cornell University · InnoPeak Technology · Innopeak Technology, Inc. · OPPO US Research Center · University of California San Diego · Adobe Research · UCSD
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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.