Research map / Continual learning / Online and replay-based
CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation
Xiuzhe Wu, Peng Dai, Weipeng DENG, Handi Chen, Yang Wu, Yan-Pei Cao, Ying Shan, XIAOJUAN QI
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 |
|---|---|---|---|
| remove expert adaptor (ablation) | CL-NeRF · Whiteroom SEQ new region | PSNR: 29.74 -> 24.30 | Hurt |
| remove expert adaptor (ablation) | CL-NeRF · Whiteroom SEQ old region | PSNR: 33.38 -> 29.39 | Hurt |
| remove knowledge distillation (ablation) | CL-NeRF · Whiteroom SEQ old region | PSNR: 33.38 -> 18.63 | Hurt |
| remove knowledge distillation (ablation) | CL-NeRF · Whiteroom SEQ new region | PSNR: 29.74 -> 28.19 | Hurt |
| remove mask loss Lm (ablation) | CL-NeRF · Whiteroom SEQ old region | PSNR: 33.38 -> 30.70 | Hurt |
| remove mask loss Lm (ablation) | CL-NeRF · Whiteroom DELETE new region | PSNR: 34.77 -> 31.73 | Hurt |
| CL-NeRF instead of fine-tuning | naive fine-tuning · Whiteroom SEQ old region | PSNR: 16.91 -> 33.38 | Improved |
| CL-NeRF instead of memory replay | memory replay · Whiteroom SEQ old region | PSNR: 25.95 -> 33.38 | Improved |
| CL-NeRF instead of DyNeRF with memory replay | DyNeRF · Whiteroom SEQ old region | PSNR: 25.80 -> 33.38 | Improved |
| CL-NeRF instead of DyNeRF | DyNeRF · Whiteroom SEQ new region | PSNR: 29.83 -> 29.74 | No clear effect |
| CL-NeRF instead of fine-tuning | FT · Whiteroom DELETE new region | PSNR: 34.76 -> 34.77 | No clear effect |
| CL-NeRF instead of fine-tuning | FT · Whiteroom sequential operations | FM: 20.908 -> 28.638 | Improved |
Closest papers by meaning
- Meta-Continual Learning of Neural Fields (ICLR 2025 · similarity 0.89)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.89)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.89)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.89)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · similarity 0.89)
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules (ICLR 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.
