Datasets › RefRef

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

Introduced by Yue Yin et al. in RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects27 Apr 2025 archive 2025-07-28

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.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Novel View Synthesis RefRef R3F-Oracle Average PSNR (dB) 29.34 RefRef: A Synthetic Dataset and Benchmark for... yueyin27/refref 8 Compare

Papers archive 2025-07-28

5 shown of 5 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 5. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects 1 2 9 May 2025 not harvested
Differentiable Neural Surface Refinement for Modeling Transparent Objects 0 1 1 Jan 2024 not harvested
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields 1 1 13 Apr 2023 ran 2 of 5 samples (3 unverified)
Nerfstudio: A Modular Framework for Neural Radiance Field Development 2 1 8 Feb 2023 ran 1 of 1 samples (0 unverified)
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction 7 1 20 Jun 2021 ran 8 of 16 samples (8 unverified)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

apache-2.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • RefRef

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections