Research map / 3D vision / Depth and stereo
OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
Isabella Liu, Linghao Chen, Ziyang Fu, Liwen Wu, Haian Jin, Zhong Li, Chin Ming Ryan Wong, Yi Xu, Ravi Ramamoorthi, Zexiang Xu, Hao Su
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| switch from single to multi illumination | NeRD · OpenIllumination, bucket | PSNR: 26.14 -> 16.48 | Hurt |
| switch from single to multi illumination | NeRD · OpenIllumination, egg | PSNR: 33.40 -> 26.32 | Hurt |
| switch from single to multi illumination | Neural-PIL · OpenIllumination, egg | PSNR: 34.42 -> 30.84 | Hurt |
| switch from single to multi illumination | TensoIR · OpenIllumination, bucket | PSNR: 29.32 -> 28.91 | No clear effect |
| switch from single to multi illumination | TensoIR · OpenIllumination, egg | PSNR: 34.88 -> 34.51 | No clear effect |
| object material is metal or clear plastic instead of diffuse (egg) | TensoIR · OpenIllumination single illumination | PSNR: 34.88 -> 22.13 | Hurt |
| object material is metal bucket instead of paper egg | TensoIR · OpenIllumination relighting | PSNR: 31.99 -> 27.13 | Hurt |
| use I-NGP instead of TensoRF for novel view synthesis on cup | TensoRF · OpenIllumination, cup | PSNR: 20.87 -> 22.51 | Improved |
| use NeuS instead of NeRF for novel view synthesis on bucket | NeRF · OpenIllumination, bucket | PSNR: 28.54 -> 29.99 | Improved |
| use nvdiffrec-mc instead of InvRender on egg-less comparison, bucket | InvRender · OpenIllumination, bucket | PSNR: 26.18 -> 28.52 | Improved |
| capture with handheld camera instead of dome (ablation) | dataset capture · geometry reconstruction | completeness | Hurt |
Closest papers by meaning
- Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image (CVPR 2020 · similarity 0.89)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.88)
- Latent Intrinsics Emerge from Training to Relight (NeurIPS 2024 · similarity 0.88)
- Eclipse: Disambiguating Illumination and Materials using Unintended Shadows (CVPR 2024 · similarity 0.88)
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.87)
- Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
