Research map / Point clouds / Shape and surface completion
IterativePFN: True Iterative Point Cloud Filtering
Dasith de Silva Edirimuni, Xuequan Lu, Zhiwen Shao, Gang Li, Antonio Robles-Kelly, Ying He
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 |
|---|---|---|---|
| Use IterativePFN instead of PDFlow | Point cloud filtering · PUNet 10K, 2.5% noise | CD: 36.27 -> 33.52 | Improved |
| Use IterativePFN instead of Pointfilter | Point cloud filtering · PUNet 50K, 2.5% noise | P2M: 6.29 -> 5.88 | Improved |
| Use IterativePFN with patch size 100 instead of Pointfilter | Kinect v1 scans · Kinect v1 | CD: 13.77 -> 13.2 | Improved |
| Use IterativePFN with patch size 100 instead of Pointfilter | Kinect v2 scans · Kinect v2 | P2M: 10.29 -> 10.92 | Hurt |
| Use 8 rather than 4 IterationModules (ablation) | IterativePFN · PUNet 10K, 1% and 2% noise versus 2.5% noise | CD: 20.56 -> 19.78; 30.43 -> 30.12; 33.52 -> 33.88 | Mixed |
| Use 12 rather than 4 IterationModules (ablation) | IterativePFN · PUNet 10K, 2.5% noise | CD: 33.52 -> 34.46 | Hurt |
| Use 1 rather than 4 IterationModules (ablation) | IterativePFN · PUNet 10K, 2.5% noise | CD: 33.52 -> 36.98 | Hurt |
| Use 2 rather than 4 IterationModules (ablation) | IterativePFN · PUNet 10K, 2.5% noise | CD: 33.52 -> 34.33 | Hurt |
| Replace multi-module iterative filtering with a parameter-matched 1-ItM deep network (ablation) | IterativePFN · PUNet 10K, 2.5% noise | CD: 33.52 -> 35.2 | Hurt |
| Use adaptive rather than fixed clean ground-truth targets (ablation) | IterativePFN · PUNet 10K, 2.5% noise | CD: 34.17 -> 33.52 | Improved |
| Use adaptive rather than fixed clean ground-truth targets (ablation) | IterativePFN · PUNet 10K, 2.5% noise | P2M: 10.87 -> 10.45 | Improved |
Later papers that compared with this method
5 later accepted papers report IterativePFN as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Routing on Demand: DSNet for Efficient Progressive Point Cloud Denoising (CVPR 2026 · better on 4 of 5 shared results)
- 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (AAAI 2025 · better on 8 of 8 shared results)
- You Should Learn to Stop Denoising on Point Clouds in Advance (AAAI 2025 · better on 3 of 3 shared results)
- Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network (CVPR 2024 · better on 12 of 12 shared results)
- StraightPCF: Straight Point Cloud Filtering (CVPR 2024 · better on 2 of 2 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
- StraightPCF: Straight Point Cloud Filtering (CVPR 2024 · similarity 0.88)
- You Should Learn to Stop Denoising on Point Clouds in Advance (AAAI 2025 · similarity 0.87)
- 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (AAAI 2025 · similarity 0.86)
- Point Cloud Upsampling Using Conditional Diffusion Module with Adaptive Noise Suppression (CVPR 2025 · similarity 0.86)
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.85)
- U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching (NeurIPS 2025 · similarity 0.84)
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.
