Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting
This work provides a dataset for researchers in computer vision and graphics to benchmark inverse rendering methods for object relighting, addressing a gap in existing evaluations.
The authors tackled the problem of evaluating object reconstruction and rendering for relighting by introducing a real-world dataset that captures objects in multiple lighting environments, and they demonstrated that novel view synthesis is not a reliable proxy for measuring performance on this task.
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 .