# Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration

arXiv: https://arxiv.org/abs/2510.14463 · HTML: https://mlsanity.com/paper/2510.14463/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 65 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [The Lottery Ticket Hypothesis for Pre-trained BERT Networks](https://mlsanity.com/paper/2007.12223/) (2020)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2108.11084/) (2021)
- [Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining](https://mlsanity.com/paper/1906.11129/) (2019)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models](https://mlsanity.com/paper/2012.06908/) (2020)
- [FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing](https://mlsanity.com/paper/2001.06968/) (2020)
- [Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP](https://mlsanity.com/paper/1906.02768/) (2019)
- [A General Decoupled Learning Framework for Parameterized Image Operators](https://mlsanity.com/paper/1907.05852/) (2019)
- [Only Train Once: A One-Shot Neural Network Training And Pruning Framework](https://mlsanity.com/paper/2107.07467/) (2021)
- [Quantization Guided JPEG Artifact Correction](https://mlsanity.com/paper/2004.09320/) (2020)
- [MSSNet: Multi-Scale-Stage Network for Single Image Deblurring](https://mlsanity.com/paper/2202.09652/) (2022)
- [All-In-One Medical Image Restoration via Task-Adaptive Routing](https://mlsanity.com/paper/2405.19769/) (2024)
- [OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization](https://mlsanity.com/paper/2205.11141/) (2022)
- [DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution](https://mlsanity.com/paper/2304.07018/) (2023)
- [The Need for Speed: Pruning Transformers with One Recipe](https://mlsanity.com/paper/2403.17921/) (2024)
- [KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow](https://mlsanity.com/paper/2004.05319/) (2020)
- [P3: Toward Privacy-Preserving Photo Sharing](https://mlsanity.com/paper/1302.5062/) (2013)
- [Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration](https://mlsanity.com/paper/2404.02154/) (2024)
- [Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification](https://mlsanity.com/paper/2106.11197/) (2021)

## Abstract (arXiv)

Image quality is a critical factor in delivering visually appealing content on web platforms. However, images often suffer from degradation due to lossy operations applied by online social networks (OSNs), negatively affecting user experience. Image restoration is the process of recovering a clean high-quality image from a given degraded input. Recently, multi-task (all-in-one) image restoration models have gained significant attention, due to their ability to simultaneously handle different types of image degradations. However, these models often come with an excessively high number of trainable parameters, making them computationally inefficient. In this paper, we propose a strategy for compressing multi-task image restoration models. We aim to discover highly sparse subnetworks within overparameterized deep models that can match or even surpass the performance of their dense counterparts. The proposed model, namely MIR-L, utilizes an iterative pruning strategy that removes low-magnitude weights across multiple rounds, while resetting the remaining weights to their original initialization. This iterative process is important for the multi-task image restoration model's optimization, effectively uncovering "winning tickets" that maintain or exceed state-of-the-art performance at high sparsity levels. Experimental evaluation on benchmark datasets for the deraining, dehazing, and denoising tasks shows that MIR-L retains only 10% of the trainable parameters while maintaining high image restoration performance. Our code, datasets and pre-trained models are made publicly available at https://github.com/Thomkat/MIR-L.