# Misalignment-Robust Frequency Distribution Loss for Image Transformation

arXiv: https://arxiv.org/abs/2402.18192 · HTML: https://mlsanity.com/paper/2402.18192/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 50 references that are in the map.
- First posted on arXiv 28 Feb 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Human-Aware Motion Deblurring](https://mlsanity.com/paper/2001.06816/) (2020)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [The Contextual Loss for Image Transformation with Non-Aligned Data](https://mlsanity.com/paper/1803.02077/) (2018)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [Distributional Sliced-Wasserstein and Applications to Generative Modeling](https://mlsanity.com/paper/2002.07367/) (2020)
- [Camera Lens Super-Resolution](https://mlsanity.com/paper/1904.03378/) (2019)
- [Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving](https://mlsanity.com/paper/2011.13611/) (2020)
- [Shift-tolerant Perceptual Similarity Metric](https://mlsanity.com/paper/2207.13686/) (2022)
- [Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network](https://mlsanity.com/paper/2012.15020/) (2020)
- [Projected Distribution Loss for Image Enhancement](https://mlsanity.com/paper/2012.09289/) (2020)
- [Generating natural images with direct Patch Distributions Matching](https://mlsanity.com/paper/2203.11862/) (2022)
- [EffNet: An Efficient Structure for Convolutional Neural Networks](https://mlsanity.com/paper/1801.06434/) (2018)
- [Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement](https://mlsanity.com/paper/2207.00965/) (2022)

## Built on by (most cited first, 6 of 6)

- [Any-Resolution AI-Generated Image Detection by Spectral Learning](https://mlsanity.com/paper/2411.19417/) (2024)
- [NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge](https://mlsanity.com/paper/2405.09923/) (2024)
- [DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor](https://mlsanity.com/paper/2406.08377/) (2024)
- [Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution](https://mlsanity.com/paper/2603.06275/) (2026)
- [FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator](https://mlsanity.com/paper/2508.21040/) (2025)
- [SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation](https://mlsanity.com/paper/2607.06949/) (2026)

## Abstract (arXiv)

This paper aims to address a common challenge in deep learning-based image transformation methods, such as image enhancement and super-resolution, which heavily rely on precisely aligned paired datasets with pixel-level alignments. However, creating precisely aligned paired images presents significant challenges and hinders the advancement of methods trained on such data. To overcome this challenge, this paper introduces a novel and simple Frequency Distribution Loss (FDL) for computing distribution distance within the frequency domain. Specifically, we transform image features into the frequency domain using Discrete Fourier Transformation (DFT). Subsequently, frequency components (amplitude and phase) are processed separately to form the FDL loss function. Our method is empirically proven effective as a training constraint due to the thoughtful utilization of global information in the frequency domain. Extensive experimental evaluations, focusing on image enhancement and super-resolution tasks, demonstrate that FDL outperforms existing misalignment-robust loss functions. Furthermore, we explore the potential of our FDL for image style transfer that relies solely on completely misaligned data. Our code is available at: https://github.com/eezkni/FDL