Research map / 3D vision / NeRF and radiance fields
TensoIR: Tensorial Inverse Rendering
Haian Jin, Isabella Liu, Peijia Xu, Xiaoshuai Zhang, Songfang Han, Sai Bi, Xiaowei Zhou, 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 |
|---|---|---|---|
| Use TensoRF-based joint reconstruction with physically based rendering and radiance-field rendering | Inverse rendering on synthetic scenes · Synthetic scenes | Albedo PSNR: 27.367 -> 35.088 | Improved |
| Use TensoRF-based joint reconstruction with physically based rendering and radiance-field rendering | Inverse rendering on synthetic scenes · Synthetic scenes | Relighting PSNR: 23.973 -> 28.580 | Improved |
| Use TensoRF-based joint reconstruction instead of the strongest reported baseline | Inverse rendering on synthetic scenes · Synthetic scenes | Average Runtime: 15 hrs -> 5 hrs | Improved |
| Add rotated multi-light capture | TensoIR · Synthetic scenes | Normal MAE: 4.100 -> 3.602 | Improved |
| Add general multi-light capture | TensoIR · Synthetic scenes | Normal MAE: 4.100 -> 3.551 | Improved |
| Remove lighting visibility (ablation) | TensoIR · Synthetic scenes | Normal MAE: 4.100 -> 4.716 | Hurt |
| Add lighting visibility (ablation) | TensoIR without indirect illumination · Synthetic scenes | Albedo PSNR: 27.265 -> 29.275 | Improved |
| Remove indirect illumination (ablation) | TensoIR · Synthetic scenes | Albedo PSNR: 29.275 -> 29.003 | Hurt |
| Add indirect illumination (ablation) | TensoIR without indirect illumination · Synthetic scenes | Novel View Synthesis PSNR: 34.910 -> 35.088 | Improved |
Closest papers by meaning
- TensoRF: Tensorial Radiance Fields (ECCV 2022 · similarity 0.92)
- ReNeRF: Relightable Neural Radiance Fields with Nearfield Lighting (ICCV 2023 · similarity 0.90)
- Inverse Image-Based Rendering for Light Field Generation from Single Images (ICCV 2025 · similarity 0.89)
- Neural Inverse Rendering of an Indoor Scene From a Single Image (ICCV 2019 · similarity 0.89)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.89)
- IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024 · similarity 0.89)
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.
