Research map / Point clouds / Point cloud classification
"PointNeRF++: A multi-scale, point-based Neural Radiance Field"
Weiwei Sun, Eduard Trulls, Yang-Che Tseng, Sneha Sambandam, Gopal Sharma, Andrea Tagliasacchi, Kwang Moo Yi
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 coarser scale levels to a global-only model (0 to 4 scales) (ablation) | PointNeRF++ · KITTI-360 validation | PSNR: 17.95 -> 20.05 | Improved |
| add scales beyond the first local scale (1 to 3 scales) (ablation) | PointNeRF++ · KITTI-360 validation | PSNR: 19.88 -> 19.90 | No clear effect |
| add more scale levels (ablation) | PointNeRF++ · KITTI-360 validation | LPIPS: 0.283 -> 0.305 | Hurt |
| use tri-plane instead of MLP for coarsest scales (ablation) | PointNeRF++ · KITTI-360 validation | PSNR: 19.59 -> 20.05 | Improved |
| add global voxel at coarsest scale (ablation) | PointNeRF++ · KITTI-360 validation | PSNR: 19.78 -> 20.05 | Improved |
| add local point-based scales to global-only (point-agnostic NeRF) (ablation) | PointNeRF++ · KITTI-360 validation | PSNR: 17.95 -> 19.78 | Improved |
| keep more points in the point cloud (1% to full) (ablation) | PointNeRF++ · KITTI-360 validation | PSNR: 18.71 -> 20.05 | Improved |
| replace PointNeRF with multi-scale aggregation (PointNeRF++) | point-based NeRF · ScanNet Scene-101 | PSNR: 21.98 -> 30.27 | Improved |
| replace PointNeRF with PointNeRF++ | point-based NeRF · KITTI-360 test | PSNR: 19.44 -> 22.44 | Improved |
| PointNeRF++ vs Gaussian Splatting on NeRF Synthetic | PointNeRF++ · NeRF Synthetic | PSNR: 33.60 -> 33.70 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PointNeRF — Point-NeRF: Point-Based Neural Radiance Fields (CVPR 2022) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Point-NeRF: Point-Based Neural Radiance Fields (CVPR 2022 · similarity 0.90)
- Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields (CVPR 2023 · similarity 0.90)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.89)
- ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field (NeurIPS 2024 · similarity 0.88)
- Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views (AAAI 2024 · similarity 0.88)
- Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians (CVPR 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.
