Research map / 3D vision / NeRF and radiance fields
CLNeRF: Continual Learning Meets NeRF
Zhipeng Cai, Matthias Müller
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 generative replay (ablation) | CLNeRF · Synth-NeRF | PSNR: 27.35 -> 32.16 | Improved |
| add generative replay (ablation) | CLNeRF · WAT | PSNR: 18.52 -> 25.45 | Improved |
| use NGP instead of vanilla NeRF (ablation) | CLNeRF · Synth-NeRF | PSNR: 29.23 -> 32.16 | Improved |
| use NGP instead of vanilla NeRF (ablation) | CLNeRF · WAT | PSNR: 23.50 -> 25.45 | Improved |
| add trainable appearance and geometry embeddings (ablation) | CLNeRF · WAT | PSNR: 21.09 -> 25.45 | Improved |
| add experience replay with 10 images (ablation) | CLNeRF · Synth-NeRF | PSNR: 31.96 -> 32.16 | Improved |
| add experience replay with 10 images (ablation) | CLNeRF · WAT | PSNR: 25.44 -> 25.45 | No clear effect |
| prioritized instead of reservoir replay buffer (ablation) | CLNeRF · WAT | PSNR: 25.45 -> 25.40 | No clear effect |
| prioritized instead of reservoir replay buffer (ablation) | CLNeRF · Synth-NeRF | PSNR: 32.16 -> 32.16 | No clear effect |
| add trainable embeddings to baselines | MEIL-NeRF · WAT | PSNR: 20.92 -> 24.05 | Improved |
| add trainable embeddings to baselines | ER (NeRF) · WAT | PSNR: 17.99 -> 21.36 | Improved |
| use vanilla NeRF with model inheritance instead of NGP | ER · Synth-NeRF | PSNR: 27.35 -> 30.29 | Improved |
Closest papers by meaning
- ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models (CVPR 2024 · similarity 0.88)
- SIGNeRF: Scene Integrated Generation for Neural Radiance Fields (CVPR 2024 · similarity 0.87)
- Learning Neural Exposure Fields for View Synthesis (NeurIPS 2025 · similarity 0.86)
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules (ICLR 2024 · similarity 0.86)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.86)
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (AAAI 2024 · similarity 0.85)
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.
