Research map / Point clouds / Shape and surface completion
Routing on Demand: DSNet for Efficient Progressive Point Cloud Denoising
Xiaoqian Cheng, Dong Xiao, Husen Li, Zheng Liu, Renjie Chen
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 |
|---|---|---|---|
| replace fixed progressive path (IterativePFN) with dynamic per-patch routing | IterativePFN · PU-Net 50K points, 2.5% noise | Chamfer Distance (x10^4): 1.015 -> 0.762 | Improved |
| dynamic path selection versus static sequential path (4 stages) (ablation) | DSNet-4 · PU-Net 50K points, 2.5% noise | Chamfer Distance (x10^4): 1.017 -> 0.762 | Improved |
| dynamic path selection versus static sequential path (4 stages) (ablation) | DSNet-4 · PU-Net 10K points, 2.5% noise | Chamfer Distance (x10^4): 2.824 -> 2.604 | Improved |
| dynamic path selection versus static path at low noise (4 stages, 10K, 1%) (ablation) | DSNet-4 · PU-Net 10K points, 1% noise | Chamfer Distance (x10^4): 1.897 -> 1.829 | Improved |
| dynamic versus static path with 3 stages (ablation) | DSNet-3 · PU-Net 10K points, 2% noise and 50K points, 2.5% noise | Chamfer Distance (x10^4): 2.539 vs 2.521 (static) at 10K 2%; 0.845 vs 0.811 (static) at 50K 2.5% | Mixed |
| increase number of denoising stages from 2 to 4 (ablation) | DSNet · PU-Net 10K points, 2.5% noise | Chamfer Distance (x10^4): 2.756 (L=2) -> 2.723 (L=3) -> 2.604 (L=4) | Improved |
| increase number of denoising stages from 4 to 5 (ablation) | DSNet · PU-Net 10K points, 2.5% noise | Chamfer Distance (x10^4): 2.604 -> 2.635 | Hurt |
| DSNet on real Kinect scans versus best baseline | DSNet · Kinect (real scans) | Chamfer Distance (x10^4): 1.040 vs 0.974 (P2P-Bridge) | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- IterativePFN — IterativePFN: True Iterative Point Cloud Filtering (CVPR 2023) · better on 4 of 5 shared results
- 3DMambaIPF — 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (AAAI 2025) · better on 4 of 4 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
- You Should Learn to Stop Denoising on Point Clouds in Advance (AAAI 2025 · similarity 0.91)
- U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching (NeurIPS 2025 · similarity 0.88)
- 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (AAAI 2025 · similarity 0.88)
- SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization (CVPR 2025 · similarity 0.87)
- Point Cloud Upsampling Using Conditional Diffusion Module with Adaptive Noise Suppression (CVPR 2025 · similarity 0.87)
- TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process (CVPR 2024 · similarity 0.87)
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.
