OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects

Published: 26 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 Datasets and Benchmarks PosterEveryoneRevisionsBibTeX
Keywords: Inverse Rendering; Neural Rendering
TL;DR: A multi-illumination multiview dataset for inverse rendering evaluation on real objects
Abstract: 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:
Supplementary Material: pdf
Submission Number: 103