# Decouple Learning for Parameterized Image Operators

arXiv: https://arxiv.org/abs/1807.08186 · HTML: https://mlsanity.com/paper/1807.08186/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2018.

## Built on by (most cited first, 11 of 11)

- [Toward Interactive Modulation for Photo-Realistic Image Restoration](https://mlsanity.com/paper/2105.03085/) (2021)
- [APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction](https://mlsanity.com/paper/2203.16218/) (2022)
- [Neural Camera Simulators](https://mlsanity.com/paper/2104.05237/) (2021)
- [EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration](https://mlsanity.com/paper/2105.04872/) (2021)
- [Real-time Controllable Denoising for Image and Video](https://mlsanity.com/paper/2303.16425/) (2023)
- [Hypernetwork-Based Adaptive Image Restoration](https://mlsanity.com/paper/2206.05970/) (2022)
- [Multi-Curve Translator for High-Resolution Photorealistic Image Translation](https://mlsanity.com/paper/2203.07756/) (2022)
- [Strong and Controllable Blind Image Decomposition](https://mlsanity.com/paper/2403.10520/) (2024)
- [Pupil-Adaptive 3D Holography Beyond Coherent Depth-of-Field](https://mlsanity.com/paper/2409.00028/) (2024)
- [Metropolis Theorem and Its Applications in Single Image Detail Enhancement](https://mlsanity.com/paper/2302.09762/) (2023)
- [A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing](https://mlsanity.com/paper/2107.07058/) (2021)

## Abstract (arXiv)

Many different deep networks have been used to approximate, accelerate or improve traditional image operators, such as image smoothing, super-resolution and denoising. Among these traditional operators, many contain parameters which need to be tweaked to obtain the satisfactory results, which we refer to as "parameterized image operators". However, most existing deep networks trained for these operators are only designed for one specific parameter configuration, which does not meet the needs of real scenarios that usually require flexible parameters settings. To overcome this limitation, we propose a new decouple learning algorithm to learn from the operator parameters to dynamically adjust the weights of a deep network for image operators, denoted as the base network. The learned algorithm is formed as another network, namely the weight learning network, which can be end-to-end jointly trained with the base network. Experiments demonstrate that the proposed framework can be successfully applied to many traditional parameterized image operators. We provide more analysis to better understand the proposed framework, which may inspire more promising research in this direction. Our codes and models have been released in https://github.com/fqnchina/DecoupleLearning