Research map / Point clouds / Shape and surface completion
Pointersect: Neural Rendering With Cloud-Ray Intersection
Read the paperCheck 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 Pointersect instead of Poisson reconstruction | Point-cloud rendering · tex-models | normal angle: 8.48 ± 3.97 -> 6.77 ± 2.71 | Helped |
| Use Pointersect instead of Poisson reconstruction | Point-cloud rendering · tex-models | PSNR: 25.7 ± 2.4 -> 28.2 ± 1.9 | Helped |
| Use Pointersect instead of Poisson reconstruction | Point-cloud rendering · ShapeNet | normal angle: 16.89 ± 7.96 -> 11.29 ± 5.08 | Helped |
| Use Pointersect instead of Poisson reconstruction | Point-cloud rendering · ShapeNet | depth RMSE: 0.03 ± 0.05 -> 0.03 ± 0.03 | No clear effect |
| Use Pointersect instead of Poisson reconstruction | Point-cloud rendering · Sketchfab | PSNR: 25.0 ± 3.1 -> 28.1 ± 2.7 | Helped |
| Use Pointersect instead of Visibility splatting | Point-cloud rendering · Sketchfab | normal angle: 14.04 ± 4.73 -> 8.53 ± 2.79 | Helped |
| Use Pointersect instead of NGP | Room-scale point-cloud rendering · Hypersim | PSNR: 28.5 ± 5.8 -> 29.8 ± 5.1 | Helped |
| Use Pointersect instead of NGP | Room-scale point-cloud rendering · Hypersim | LPIPS: 0.31 ± 0.08 -> 0.25 ± 0.04 | Helped |
| Optimize the noisy point cloud's xyz and rgb through differentiable rendering | Pointersect inverse rendering · 100 input views | PSNR: 10.1 ± 0.5 -> 24.6 ± 0.5 | Helped |
| Optimize the noisy point cloud's xyz and rgb through differentiable rendering | Pointersect inverse rendering · 144 novel views | PSNR: 13.9 ± 0.8 -> 25.7 ± 1.2 | Helped |
| Optimize the noisy point cloud's xyz and rgb through differentiable rendering | Pointersect inverse rendering · 144 novel views | normal angle: 55.3 ± 0.4 -> 18.3 ± 2.7 | Helped |
Closest papers by meaning
- Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians (CVPR 2025 · similarity 0.88)
- HashPoint: Accelerated Point Searching and Sampling for Neural Rendering (CVPR 2024 · similarity 0.87)
- UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting (CVPR 2025 · similarity 0.87)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.87)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.86)
- ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors (ICLR 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.