Research map / Point clouds / Point cloud classification
Neural Point Cloud Rendering via Multi-Plane Projection
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 |
|---|---|---|---|
| use learned point features rather than point RGB values (ablation) | Multi-Plane Projection renderer · ScanNet | PSNR: 22.259 -> 22.813 | Helped |
| use learned point features rather than point RGB values (ablation) | Multi-Plane Projection renderer · ScanNet | SSIM: 0.818 -> 0.835 | Helped |
| use learned point features rather than point RGB values (ablation) | Multi-Plane Projection renderer · ScanNet | LPIPS: 0.290 -> 0.234 | Helped |
| use learned point features rather than point RGB values (ablation) | Multi-Plane Projection renderer · Matterport 3D | PSNR: 17.833 -> 18.09 | Helped |
| use learned point features rather than point RGB values (ablation) | Multi-Plane Projection renderer · Matterport 3D | SSIM: 0.601 -> 0.649 | Helped |
| use learned point features rather than point RGB values (ablation) | Multi-Plane Projection renderer · Matterport 3D | LPIPS: 0.610 -> 0.534 | Helped |
| project point features into layered camera-frustum volume instead of directly onto the 2D image plane | Multi-Plane Projection renderer · ScanNet | PSNR: 22.911 -> 22.813 | Hurt |
| project point features into layered camera-frustum volume instead of directly onto the 2D image plane | Multi-Plane Projection renderer · ScanNet | LPIPS: 0.245 -> 0.234 | Helped |
| project point features into layered camera-frustum volume instead of directly onto the 2D image plane | Multi-Plane Projection renderer · Matterport 3D | PSNR: 17.931 -> 18.09 | Helped |
| project point features into layered camera-frustum volume instead of directly onto the 2D image plane | Multi-Plane Projection renderer · Matterport 3D | SSIM: 0.622 -> 0.649 | Helped |
| project point features into layered camera-frustum volume instead of directly onto the 2D image plane | Multi-Plane Projection renderer · Matterport 3D | LPIPS: 0.597 -> 0.534 | Helped |
Closest papers by meaning
- Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction (AAAI 2018 · similarity 0.88)
- Pointersect: Neural Rendering With Cloud-Ray Intersection (CVPR 2023 · similarity 0.88)
- Point2Real: Bridging the Gap between Point Cloud and Realistic Image for Open-World 3D Recognition (AAAI 2024 · similarity 0.86)
- Multi-View Representation is What You Need for Point-Cloud Pre-Training (ICLR 2024 · similarity 0.86)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.86)
- Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians (CVPR 2025 · similarity 0.86)
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.