# CFSNet: Toward a Controllable Feature Space for Image Restoration

arXiv: https://arxiv.org/abs/1904.00634 · HTML: https://mlsanity.com/paper/1904.00634/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2019.

## Built on by (most cited first, 25 of 25)

- [Towards Flexible Blind JPEG Artifacts Removal](https://mlsanity.com/paper/2109.14573/) (2021)
- [Temporal Modulation Network for Controllable Space-Time Video Super-Resolution](https://mlsanity.com/paper/2104.10642/) (2021)
- [MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution](https://mlsanity.com/paper/2205.05065/) (2022)
- [ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems](https://mlsanity.com/paper/2312.06573/) (2023)
- [Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution](https://mlsanity.com/paper/2208.03324/) (2022)
- [Structure-Preserving Image Super-Resolution](https://mlsanity.com/paper/2109.12530/) (2021)
- [Toward Interactive Modulation for Photo-Realistic Image Restoration](https://mlsanity.com/paper/2105.03085/) (2021)
- [From Posterior Sampling to Meaningful Diversity in Image Restoration](https://mlsanity.com/paper/2310.16047/) (2023)
- [Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution](https://mlsanity.com/paper/2207.09156/) (2022)
- [Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective](https://mlsanity.com/paper/2312.15408/) (2023)
- [Functional Neural Networks for Parametric Image Restoration Problems](https://mlsanity.com/paper/2111.00361/) (2021)
- [Flexible Style Image Super-Resolution using Conditional Objective](https://mlsanity.com/paper/2201.04898/) (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)
- [Restore Anything Pipeline: Segment Anything Meets Image Restoration](https://mlsanity.com/paper/2305.13093/) (2023)
- [Sensitivity Decouple Learning for Image Compression Artifacts Reduction](https://mlsanity.com/paper/2405.09291/) (2024)
- [Tunable Convolutions with Parametric Multi-Loss Optimization](https://mlsanity.com/paper/2304.00898/) (2023)
- [Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem](https://mlsanity.com/paper/2409.03179/) (2024)
- [Contrastive Monotonic Pixel-Level Modulation](https://mlsanity.com/paper/2207.11517/) (2022)
- [Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworks](https://mlsanity.com/paper/2307.06771/) (2023)
- [Regression-free Blind Image Quality Assessment with Content-Distortion Consistency](https://mlsanity.com/paper/2307.09279/) (2023)
- [HyperCoil-Recon: A Hypernetwork-based Adaptive Coil Configuration Task Switching Network for MRI Reconstruction](https://mlsanity.com/paper/2308.04821/) (2023)
- [QueryCDR: Query-Based Controllable Distortion Rectification Network for Fisheye Images](https://mlsanity.com/paper/2412.13496/) (2024)
- [Towards Imperceptible Query-limited Adversarial Attacks with Perceptual Feature Fidelity Loss](https://mlsanity.com/paper/2102.00449/) (2021)
- [SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction](https://mlsanity.com/paper/2607.20159/) (2026)

## Abstract (arXiv)

Deep learning methods have witnessed the great progress in image restoration with specific metrics (e.g., PSNR, SSIM). However, the perceptual quality of the restored image is relatively subjective, and it is necessary for users to control the reconstruction result according to personal preferences or image characteristics, which cannot be done using existing deterministic networks. This motivates us to exquisitely design a unified interactive framework for general image restoration tasks. Under this framework, users can control continuous transition of different objectives, e.g., the perception-distortion trade-off of image super-resolution, the trade-off between noise reduction and detail preservation. We achieve this goal by controlling the latent features of the designed network. To be specific, our proposed framework, named Controllable Feature Space Network (CFSNet), is entangled by two branches based on different objectives. Our framework can adaptively learn the coupling coefficients of different layers and channels, which provides finer control of the restored image quality. Experiments on several typical image restoration tasks fully validate the effective benefits of the proposed method. Code is available at https://github.com/qibao77/CFSNet.