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

TL;DR

OpenIllumination is a comprehensive real-world dataset with over 108,000 images of diverse objects under various lighting conditions, designed to evaluate inverse rendering methods quantitatively.

Contribution

The paper introduces a large-scale, annotated dataset for inverse rendering evaluation on real objects, facilitating benchmarking of existing methods.

Findings

State-of-the-art inverse rendering methods are evaluated on the dataset.

The dataset provides accurate camera parameters and illumination ground truth.

Comparison results highlight strengths and weaknesses of current approaches.

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: https://oppo-us-research.github.io/OpenIllumination.