RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects
RefRef is a synthetic dataset and benchmark designed for the task of reconstructing scenes with complex refractive and reflective objects.
Our dataset consists of 50 objects categorized based on their geometric and material complexity: single-material convex objects, single-material non-convex objects, and multi-material non-convex objects, where the materials have different colors, opacities, and refractive indices.
Each object is placed in three distinct bounded environments and one unbounded environment, resulting in 150 unique scenes with diverse geometries, material properties, and backgrounds.
Our dataset provides a controlled setting for evaluating and developing 3D reconstruction and novel view synthesis methods that handle complex optical effects.
Variants: RefRef
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Novel View Synthesis | R3F-Oracle | RefRef: A Synthetic Dataset and … | 2025-05-09 |
| Novel View Synthesis | R3F | RefRef: A Synthetic Dataset and … | 2025-05-09 |
| Novel View Synthesis | Zip-NeRF | Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance … | 2023-04-13 |
| Novel View Synthesis | Splatfacto | Nerfstudio: A Modular Framework for … | 2023-02-08 |
| Novel View Synthesis | NeuS | NeuS: Learning Neural Implicit Surfaces … | 2021-06-20 |
Recent papers with results on this dataset: