paper-with-me

Papers

When A Conventional Filter Meets Deep Learning: Basis Composition Learning on Image Filters

2022-03-01 · Fu Lee Wang, Yidan Feng, Haoran Xie, Gary Cheng, Mingqiang Wei

Image filters are fast, lightweight and effective, which make these conventional wisdoms preferable as basic tools in vision tasks. In practical scenarios, users have to tweak parameters multiple times to obtain satisfied results. This inconvenience heavily discounts the efficiency and user experience. We propose basis composition learning on single image filters to automatically determine their optimal formulas. The feasibility is based on a two-step strategy: first, we build a set of filtered basis (FB) consisting of approximations under selected parameter configurations; second, a dual-branch composition module is proposed to learn how the candidates in FB are combined to better approximate the target image. Our method is simple yet effective in practice; it renders filters to be user-friendly and benefits fundamental low-level vision problems including denoising, deraining and texture removal. Extensive experiments demonstrate that our method achieves an appropriate balance among the performance, time complexity and memory efficiency.

📄 PDF Abstract BibTeX arXiv:2203.00258

Code (1)

dengsgithub/composition-learning 공식 구현 pytorch

Tasks

DenoisingRain Removal

Similar Papers 제목 키워드 기반

When atomic norm meets the G-filter: A general framework for line spectral estimation

2024-10-16 · Bin Zhu, Jiale Tang

This paper proposes a novel approach for line spectral estimation which combines Georgiou's filter bank (G-filter) with atomic norm minimization (ANM). A key ingredient is a Carath\'{e}odory--Fej\'{e}r-type decomposition…

Decoupling multivariate functions using a non-parametric Filtered CPD approach

2021-05-18 · Jan Decuyper, Koen Tiels, Siep Weiland, Johan Schoukens

Black-box model structures are dominated by large multivariate functions. Usually a generic basis function expansion is used, e.g. a polynomial basis, and the parameters of the function are tuned given the data. This is …

An Effective Universal Polynomial Basis for Spectral Graph Neural Networks

2023-11-30 · Keke Huang, Pietro Liò

Spectral Graph Neural Networks (GNNs), also referred to as graph filters have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigendecomposition for Fourier transform. In an a…

When Slepian Meets Fiedler: Putting a Focus on the Graph Spectrum

2017-01-29 · Dimitri Van De Ville, Robin Demesmaeker, Maria Giulia Preti

The study of complex systems benefits from graph models and their analysis. In particular, the eigendecomposition of the graph Laplacian lets emerge properties of global organization from local interactions; e.g., the Fi…

ClusteringGraph Clustering

How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing

2024-05-21 · Keke Huang, Yu Guang Wang, Ming Li, and Pietro Liò

Spectral Graph Neural Networks (GNNs), alternatively known as graph filters, have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigendecomposition for Fourier transform. In …

Graph Neural Network