# Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers

arXiv: https://arxiv.org/abs/1904.08118 · HTML: https://mlsanity.com/paper/1904.08118/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 30 of 39)

- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [InstructIR: High-Quality Image Restoration Following Human Instructions](https://mlsanity.com/paper/2401.16468/) (2024)
- [HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization](https://mlsanity.com/paper/2105.13084/) (2021)
- [Temporal Modulation Network for Controllable Space-Time Video Super-Resolution](https://mlsanity.com/paper/2104.10642/) (2021)
- [Neural Degradation Representation Learning for All-In-One Image Restoration](https://mlsanity.com/paper/2310.12848/) (2023)
- [MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution](https://mlsanity.com/paper/2205.05065/) (2022)
- [DVMSR: Distillated Vision Mamba for Efficient Super-Resolution](https://mlsanity.com/paper/2405.03008/) (2024)
- [A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds](https://mlsanity.com/paper/2205.04910/) (2022)
- [Adaptive Denoising via GainTuning](https://mlsanity.com/paper/2107.12815/) (2021)
- [Toward Interactive Modulation for Photo-Realistic Image Restoration](https://mlsanity.com/paper/2105.03085/) (2021)
- [Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation](https://mlsanity.com/paper/2108.08202/) (2021)
- [Very Lightweight Photo Retouching Network with Conditional Sequential Modulation](https://mlsanity.com/paper/2104.06279/) (2021)
- [UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity](https://mlsanity.com/paper/2412.20157/) (2024)
- [RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank](https://mlsanity.com/paper/2107.09427/) (2021)
- [Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal](https://mlsanity.com/paper/2310.18293/) (2023)
- [Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution](https://mlsanity.com/paper/2207.09156/) (2022)
- [WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement](https://mlsanity.com/paper/2212.08327/) (2022)
- [Flexible Style Image Super-Resolution using Conditional Objective](https://mlsanity.com/paper/2201.04898/) (2022)
- [ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2211.12417/) (2022)
- [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)
- [Self-Supervised Scalable Deep Compressed Sensing](https://mlsanity.com/paper/2308.13777/) (2023)
- [A Preliminary Exploration Towards General Image Restoration](https://mlsanity.com/paper/2408.15143/) (2024)
- [Scale-Aware Dynamic Network for Continuous-Scale Super-Resolution](https://mlsanity.com/paper/2110.15655/) (2021)
- [Coordinate-Aware Modulation for Neural Fields](https://mlsanity.com/paper/2311.14993/) (2023)
- [YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency](https://mlsanity.com/paper/2506.03645/) (2025)
- [Parameter-Free Channel Attention for Image Classification and Super-Resolution](https://mlsanity.com/paper/2303.11055/) (2023)
- [Grounding Degradations in Natural Language for All-In-One Video Restoration](https://mlsanity.com/paper/2507.14851/) (2025)
- [Contrastive Monotonic Pixel-Level Modulation](https://mlsanity.com/paper/2207.11517/) (2022)
- [Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains](https://mlsanity.com/paper/2404.12091/) (2024)

## Abstract (arXiv)

In image restoration tasks, like denoising and super resolution, continual modulation of restoration levels is of great importance for real-world applications, but has failed most of existing deep learning based image restoration methods. Learning from discrete and fixed restoration levels, deep models cannot be easily generalized to data of continuous and unseen levels. This topic is rarely touched in literature, due to the difficulty of modulating well-trained models with certain hyper-parameters. We make a step forward by proposing a unified CNN framework that consists of few additional parameters than a single-level model yet could handle arbitrary restoration levels between a start and an end level. The additional module, namely AdaFM layer, performs channel-wise feature modification, and can adapt a model to another restoration level with high accuracy. By simply tweaking an interpolation coefficient, the intermediate model - AdaFM-Net could generate smooth and continuous restoration effects without artifacts. Extensive experiments on three image restoration tasks demonstrate the effectiveness of both model training and modulation testing. Besides, we carefully investigate the properties of AdaFM layers, providing a detailed guidance on the usage of the proposed method.