Research map / Learning theory and algorithms / Matrix and tensor methods
A Generalized Framework for Edge-Preserving and Structure-Preserving Image Smoothing
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 the proposed smoother instead of TGV | Guided depth map upsampling on real ToF data · Books | MAE: 12.8mm -> 12.49mm | Helped |
| Use the proposed smoother instead of TGV | Guided depth map upsampling on real ToF data · Devil | MAE: 14.97mm -> 14.51mm | Helped |
| Use the proposed smoother instead of TGV | Guided depth map upsampling on real ToF data · Shark | MAE: 15.53mm -> 15.02mm | Helped |
| Use the proposed smoother instead of the strongest baseline | Guided depth map upsampling on noisy simulated ToF data · Art 16× | MAE: 3.46 -> 2.96 | Helped |
| Use the proposed smoother instead of the strongest baseline | Guided depth map upsampling on noisy simulated ToF data · Book 16× | MAE: 1.96 -> 1.78 | Helped |
| Use the proposed smoother instead of the strongest baseline | Guided depth map upsampling on noisy simulated ToF data · Dolls 16× | MAE: 2.45 -> 1.84 | Helped |
| Use the proposed smoother instead of the strongest baseline | Guided depth map upsampling on noisy simulated ToF data · Laundry 16× | MAE: 2.57 -> 2.12 | Helped |
| Use the proposed smoother instead of the strongest baseline | Guided depth map upsampling on noisy simulated ToF data · Moebius 16× | MAE: 2.25 -> 1.71 | Helped |
| Use the proposed smoother instead of the strongest baseline | Guided depth map upsampling on noisy simulated ToF data · Reindeer 16× | MAE: 2.52 -> 2.08 | Helped |
| Set truncation in the smoothness term below the maximum intensity, enabling edge sharpening | Proposed smoother for clip-art compression artifact removal · Clip-art compression artifacts removal | edge preservation | Helped |
| Combine edge-preserving and structure-preserving parameter settings | Proposed smoother for clip-art compression artifact removal · Clip-art compression artifacts removal | structure preservation | Helped |
| Use a structure-preserving setting with guidance weights | Proposed smoother for image texture removal · Image texture removal | structure preservation | Helped |
Closest papers by meaning
- Edge-aware Image Smoothing with Relative Wavelet Domain Representation (ICLR 2025 · similarity 0.86)
- Improved Imaging by Invex Regularizers with Global Optima Guarantees (NeurIPS 2022 · similarity 0.83)
- Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization (ICML 2024 · similarity 0.82)
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.81)
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection (CVPR 2024 · similarity 0.81)
- Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems (NeurIPS 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.