# Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution

arXiv: https://arxiv.org/abs/2009.13134 · HTML: https://mlsanity.com/paper/2009.13134/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Multitemporal and multispectral data fusion for super-resolution of Sentinel-2 images](https://mlsanity.com/paper/2301.11154/) (2023)
- [Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers](https://mlsanity.com/paper/2305.17313/) (2023)
- [Robust PCA Unrolling Network for Super-resolution Vessel Extraction in X-ray Coronary Angiography](https://mlsanity.com/paper/2204.08466/) (2022)
- [Convolutional neural network based on sparse graph attention mechanism for MRI super-resolution](https://mlsanity.com/paper/2305.17898/) (2023)
- [Task-driven single-image super-resolution reconstruction of document scans](https://mlsanity.com/paper/2407.08993/) (2024)
- [Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2506.11823/) (2025)
- [Image-specific Convolutional Kernel Modulation for Single Image Super-resolution](https://mlsanity.com/paper/2111.08362/) (2021)
- [Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network](https://mlsanity.com/paper/2508.02111/) (2025)
- [LaST-SR: Laplace-Inspired Steady-Transient Complex-Frequency Decomposition for Single Image Super-Resolution](https://mlsanity.com/paper/2609.02063/) (2026)

## Abstract (arXiv)

Benefiting from the strong capabilities of deep CNNs for feature representation and nonlinear mapping, deep-learning-based methods have achieved excellent performance in single image super-resolution. However, most existing SR methods depend on the high capacity of networks which is initially designed for visual recognition, and rarely consider the initial intention of super-resolution for detail fidelity. Aiming at pursuing this intention, there are two challenging issues to be solved: (1) learning appropriate operators which is adaptive to the diverse characteristics of smoothes and details; (2) improving the ability of model to preserve the low-frequency smoothes and reconstruct the high-frequency details. To solve them, we propose a purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose on improving the detail fidelity, instead of blindly designing or employing the deep CNNs architectures for merely feature representation in local receptive fields. Particularly, we propose a Hessian filtering for interpretable feature representation which is high-profile for detail inference, a dilated encoder-decoder and a distribution alignment cell to improve the inferred Hessian features in morphological manner and statistical manner respectively. Extensive experiments demonstrate that the proposed methods achieve superior performances over the state-of-the-art methods quantitatively and qualitatively. Code is available at https://github.com/YuanfeiHuang/DeFiAN.