Research map / 3D vision / NeRF and radiance fields
RehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editing
Changyeon Won, Hyunjun Jung, Jungu Cho, Seonmi Park, Chi-Hoon Lee, Hae‐Gon Jeon
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 |
|---|---|---|---|
| add dynamic-object regularization L_dyn (ablation) | RehearsalNeRF · Synthetic scene editing | PSNR: 25.948 -> 29.186 | Improved |
| add rehearsal regularization L_reh (ablation) | RehearsalNeRF · Synthetic NVS | PSNR: 25.896 -> 30.117 | Improved |
| add rehearsal regularization L_reh (ablation) | RehearsalNeRF · Synthetic scene editing | PSNR: 25.190 -> 29.186 | Improved |
| add hue initialization of illumination vector v_h (ablation) | RehearsalNeRF · Real-world NVS | PSNR: 27.378 -> 28.250 | Improved |
| add psi_A (ablation) | RehearsalNeRF · Synthetic NVS | SSIM: 0.885 -> 0.883 | Mixed |
| render light color via proposed procedure instead of direct psi_L to c_L (ablation) | RehearsalNeRF · Real-world NVS | PSNR: 28.345 -> 28.250 | Mixed |
| add L_dyn (ablation) | RehearsalNeRF · Real-world NVS | SSIM: 0.859 -> 0.851 | Hurt |
| shift rehearsal video by 60 frames | RehearsalNeRF · Time mis-sync analysis | PSNR: 28.046 -> 28.069 | No clear effect |
| use only first rehearsal frame as prior | RehearsalNeRF · Time mis-sync analysis | PSNR: 28.046 -> 28.005 | No clear effect |
| speed up dynamics 5x by temporal subsampling | RehearsalNeRF · Real-world NVS dynamic objects | PSNR: 26.318 -> 27.090 | Improved |
Closest papers by meaning
- ReNeRF: Relightable Neural Radiance Fields with Nearfield Lighting (ICCV 2023 · similarity 0.90)
- IReNe: Instant Recoloring of Neural Radiance Fields (CVPR 2024 · similarity 0.89)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.89)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.88)
- LAENeRF: Local Appearance Editing for Neural Radiance Fields (CVPR 2024 · similarity 0.88)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.88)
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.
