# Structure-Preserving Image Super-resolution via Contextualized Multi-task Learning

arXiv: https://arxiv.org/abs/1707.08340 · HTML: https://mlsanity.com/paper/1707.08340/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2017.

## Built on by (most cited first, 15 of 15)

- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution](https://mlsanity.com/paper/2112.04488/) (2021)
- [Asymmetric CNN for image super-resolution](https://mlsanity.com/paper/2103.13634/) (2021)
- [A heterogeneous group CNN for image super-resolution](https://mlsanity.com/paper/2209.12406/) (2022)
- [Real-World Image Super-Resolution by Exclusionary Dual-Learning](https://mlsanity.com/paper/2206.02609/) (2022)
- [Criteria Comparative Learning for Real-scene Image Super-Resolution](https://mlsanity.com/paper/2207.12767/) (2022)
- [Image Super-resolution with An Enhanced Group Convolutional Neural Network](https://mlsanity.com/paper/2205.14548/) (2022)
- [GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer](https://mlsanity.com/paper/2102.00769/) (2021)
- [Single Image Super-Resolution Methods: A Survey](https://mlsanity.com/paper/2202.11763/) (2022)
- [FlowLUT: Efficient Image Enhancement via Differentiable LUTs and Iterative Flow Matching](https://mlsanity.com/paper/2509.23608/) (2025)
- [Image super-resolution via dynamic network](https://mlsanity.com/paper/2310.10413/) (2023)
- [Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution](https://mlsanity.com/paper/2212.01628/) (2022)
- [Adaptive Convolutional Neural Network for Image Super-resolution](https://mlsanity.com/paper/2402.15704/) (2024)
- [A Tree-guided CNN for image super-resolution](https://mlsanity.com/paper/2506.02585/) (2025)
- [A Cosine Network for Image Super-Resolution](https://mlsanity.com/paper/2601.16413/) (2026)

## Abstract (arXiv)

Single image super resolution (SR), which refers to reconstruct a higher-resolution (HR) image from the observed low-resolution (LR) image, has received substantial attention due to its tremendous application potentials. Despite the breakthroughs of recently proposed SR methods using convolutional neural networks (CNNs), their generated results usually lack of preserving structural (high-frequency) details. In this paper, regarding global boundary context and residual context as complimentary information for enhancing structural details in image restoration, we develop a contextualized multi-task learning framework to address the SR problem. Specifically, our method first extracts convolutional features from the input LR image and applies one deconvolutional module to interpolate the LR feature maps in a content-adaptive way. Then, the resulting feature maps are fed into two branched sub-networks. During the neural network training, one sub-network outputs salient image boundaries and the HR image, and the other sub-network outputs the local residual map, i.e., the residual difference between the generated HR image and ground-truth image. On several standard benchmarks (i.e., Set5, Set14 and BSD200), our extensive evaluations demonstrate the effectiveness of our SR method on achieving both higher restoration quality and computational efficiency compared with several state-of-the-art SR approaches. The source code and some SR results can be found at: http://hcp.sysu.edu.cn/structure-preserving-image-super-resolution/