RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects

TL;DR

This paper introduces RefRef, a synthetic dataset and benchmark designed to evaluate 3D reconstruction methods on scenes with refractive and reflective objects, highlighting current challenges and gaps in existing techniques.

Contribution

The paper presents a novel dataset with diverse refractive and reflective objects, an oracle method for accurate light path calculation, and benchmarks that reveal the limitations of current methods.

Findings

All evaluated methods perform significantly worse than the oracle.

The dataset includes 150 scenes with varying complexity.

Current techniques struggle with refractive and reflective materials.

Abstract

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.