Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting

TL;DR

This paper introduces a real-world dataset and evaluation framework for object reconstruction and relighting, highlighting the limitations of using novel view synthesis as a performance proxy.

Contribution

It provides a new dataset capturing objects in multiple lighting environments and evaluates existing methods for object relighting in real-world scenarios.

Findings

Novel view synthesis is not a reliable performance proxy.

The dataset enables quantitative analysis of relighting quality.

Baseline methods show significant room for improvement.

Abstract

Reconstructing an object from photos and placing it virtually in a new environment goes beyond the standard novel view synthesis task as the appearance of the object has to not only adapt to the novel viewpoint but also to the new lighting conditions and yet evaluations of inverse rendering methods rely on novel view synthesis data or simplistic synthetic datasets for quantitative analysis. This work presents a real-world dataset for measuring the reconstruction and rendering of objects for relighting. To this end, we capture the environment lighting and ground truth images of the same objects in multiple environments allowing to reconstruct the objects from images taken in one environment and quantify the quality of the rendered views for the unseen lighting environments. Further, we introduce a simple baseline composed of off-the-shelf methods and test several state-of-the-art methods on the relighting task and show that novel view synthesis is not a reliable proxy to measure performance. Code and dataset are available at https://github.com/isl-org/objects-with-lighting .