RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects
This addresses the need for specialized datasets and benchmarks for evaluating and developing techniques for refractive and reflective objects in computer vision, though it is incremental in providing a synthetic dataset.
The paper tackles the problem of 3D reconstruction and novel view synthesis for scenes with refractive and reflective objects, which existing methods struggle with due to limited datasets. It introduces a synthetic dataset of 150 scenes and shows that state-of-the-art methods lag significantly behind an oracle, highlighting the challenges.
Modern 3D reconstruction and novel view synthesis approaches have demonstrated strong performance on scenes with opaque Lambertian objects. However, most assume straight light paths and therefore cannot properly handle refractive and reflective materials. Moreover, datasets specialized for these effects are limited, stymieing efforts to evaluate performance and develop suitable techniques. In this work, we introduce a synthetic RefRef dataset and benchmark for reconstructing scenes with refractive and reflective objects from posed images. Our dataset has 50 such objects of varying complexity, from single-material convex shapes to multi-material non-convex shapes, each placed in three different background types, resulting in 150 scenes. We also propose an oracle method that, given the object geometry and refractive indices, calculates accurate light paths for neural rendering, and an approach based on this that avoids these assumptions. We benchmark these against several state-of-the-art methods and show that all methods lag significantly behind the oracle, highlighting the challenges of the task and dataset.