Research map / Point clouds / Point cloud classification
Revisiting Nonlocal Self-Similarity from Continuous Representation
Yisi Luo, Xi-Le Zhao, Deyu Meng
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 CRNL instead of DIP | image inpainting · Color images (sampling rate 0.05) | PSNR: 23.06 -> 23.39 | Improved |
| use CRNL instead of DIP | image inpainting · MSI inpainting (sampling rate 0.05) | PSNR: 34.74 -> 36.71 | Improved |
| use CRNL instead of HLRTF | image inpainting · MSI inpainting (sampling rate 0.25) | PSNR: 47.22 -> 48.82 | Improved |
| use CRNL instead of TCTV | image inpainting · Video inpainting (sampling rate 0.25) | PSNR: 31.65 -> 31.58 | No clear effect |
| use CRNL instead of TCTV | image inpainting · Color images inpainting | average time (s): 107 -> 16 | Improved |
| use CRNL instead of LTDL | denoising · MSI denoising (sigma 0.3) | PSNR: 36.28 -> 37.38 | Improved |
| use CRNL instead of LTDL | denoising · MSI denoising | average time (s): 632 -> 33 | Improved |
| use CRNL instead of FSA-HTF | multivariate regression · Synthetic f4(x,y) | NRMSE: 0.103 -> 0.013 | Improved |
| use CRNL instead of FSA-HTF | multivariate regression · Weather precipitation (55N 117W) | NRMSE: 0.027 -> 0.015 | Improved |
| use CRNL instead of KNR | multivariate regression · Weather precipitation (53N 111W) | R-Square: 0.696 -> 0.686 | Hurt |
| use CRNL instead of RF | multivariate regression · Weather precipitation (50N 106W) | R-Square: 0.760 -> 0.779 | Improved |
Closest papers by meaning
- How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings (ICLR 2025 · similarity 0.81)
- NOFE – Neural Operator Function Embedding (NeurIPS 2026 · similarity 0.81)
- Validating Climate Models with Spherical Convolutional Wasserstein Distance (NeurIPS 2024 · similarity 0.81)
- LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Space (NeurIPS 2025 · similarity 0.81)
- Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation (CVPR 2025 · similarity 0.81)
- Adaptive Flow Matching for Resolving Small-Scale Physics (ICML 2025 · similarity 0.81)
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.
