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

arXiv: https://arxiv.org/abs/2203.00258 · HTML: https://mlsanity.com/paper/2203.00258/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 60 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Builds on (most cited first, 13 of 13)

- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining](https://mlsanity.com/paper/1807.05698/) (2018)
- [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015)
- [A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing](https://mlsanity.com/paper/1708.03474/) (2017)
- [Fast Image Processing with Fully-Convolutional Networks](https://mlsanity.com/paper/1709.00643/) (2017)
- [Semantically Contrastive Learning for Low-light Image Enhancement](https://mlsanity.com/paper/2112.06451/) (2021)
- [Side Window Filtering](https://mlsanity.com/paper/1905.07177/) (2019)
- [DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks](https://mlsanity.com/paper/1908.10267/) (2019)
- [A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing](https://mlsanity.com/paper/1907.09642/) (2019)
- [Image Denoising using New Adaptive Based Median Filters](https://mlsanity.com/paper/1410.2175/) (2014)
- [Direction-aware Feature-level Frequency Decomposition for Single Image Deraining](https://mlsanity.com/paper/2106.07941/) (2021)

## Abstract (arXiv)

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.