Research map / Point clouds / Point cloud classification
Point-NeRF: Point-Based Neural Radiance Fields
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Fine-tune the generated neural point field for 10K iterations | Point-NeRF · DTU test | LPIPS Vgg: 0.203 -> 0.117 | Helped |
| Use Point-NeRF for 20K rather than 200K iterations | Point-NeRF · NeRF Synthetic | PSNR: 30.71 vs 33.31 | Mixed |
| Add point pruning and growing (ablation) | Point-NeRF · NeRF Synthetic Ship and Hotdog scenes | PSNR: 25.50 -> 30.97; 34.91 -> 37.30 | Helped |
| Add point pruning and growing to COLMAP point initialization (ablation) | Point-NeRF initialized from COLMAP · NeRF Synthetic Ship and Hotdog scenes | PSNR: 19.35 -> 30.18; 29.91 -> 35.49 | Helped |
| Initialize point features with extracted image features instead of random values (ablation) | Point-NeRF · NeRF Synthetic | PSNR: 25.44 -> 30.09; 32.01 -> 33.00 | Helped |
| Use the full Point-NeRF reconstruction rather than the COLMAP-initialized variant | Point-NeRF · NeRF Synthetic | PSNR: 33.31 vs 31.77 | Mixed |
Closest papers by meaning
- D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021 · similarity 0.90)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.90)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.89)
- A General Implicit Framework for Fast NeRF Composition and Rendering (AAAI 2024 · similarity 0.89)
- Neural NeRF Compression (ICML 2024 · similarity 0.88)
- NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields (AAAI 2024 · 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.