# Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving

arXiv: https://arxiv.org/abs/2011.13611 · HTML: https://mlsanity.com/paper/2011.13611/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 30 of 46)

- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [ARGS: Alignment as Reward-Guided Search](https://mlsanity.com/paper/2402.01694/) (2024)
- [Process Reward Model with Q-Value Rankings](https://mlsanity.com/paper/2410.11287/) (2024)
- [Spectral Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2106.06112/) (2021)
- [EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer](https://mlsanity.com/paper/2207.09840/) (2022)
- [Out-of-distribution Detection via Frequency-regularized Generative Models](https://mlsanity.com/paper/2208.09083/) (2022)
- [Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions](https://mlsanity.com/paper/2106.07451/) (2021)
- [GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting](https://mlsanity.com/paper/2205.07162/) (2022)
- [DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data](https://mlsanity.com/paper/2306.14153/) (2023)
- [Learning to Distill Global Representation for Sparse-View CT](https://mlsanity.com/paper/2308.08463/) (2023)
- [Frequency-Controlled Diffusion Model for Versatile Text-Guided Image-to-Image Translation](https://mlsanity.com/paper/2407.03006/) (2024)
- [FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing](https://mlsanity.com/paper/2503.19191/) (2025)
- [Painterly Image Harmonization in Dual Domains](https://mlsanity.com/paper/2212.08846/) (2022)
- [ORIDa: Object-centric Real-world Image Composition Dataset](https://mlsanity.com/paper/2506.08964/) (2025)
- [Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpainting](https://mlsanity.com/paper/2401.10564/) (2024)
- [FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model](https://mlsanity.com/paper/2311.14926/) (2023)
- [On the Learnability of Out-of-distribution Detection](https://mlsanity.com/paper/2404.04865/) (2024)
- [Learning Plug-and-play Memory for Guiding Video Diffusion Models](https://mlsanity.com/paper/2511.19229/) (2025)
- [Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2204.11018/) (2022)
- [FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment](https://mlsanity.com/paper/2301.07330/) (2023)
- [Misalignment-Robust Frequency Distribution Loss for Image Transformation](https://mlsanity.com/paper/2402.18192/) (2024)
- [Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations](https://mlsanity.com/paper/2401.05752/) (2024)
- [FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image Translation](https://mlsanity.com/paper/2408.00998/) (2024)
- [Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2505.15217/) (2025)
- [Unsupervised Image Denoising with Frequency Domain Knowledge](https://mlsanity.com/paper/2111.14362/) (2021)
- [Text-driven Video Prediction](https://mlsanity.com/paper/2210.02872/) (2022)
- [fRegGAN with K-space Loss Regularization for Medical Image Translation](https://mlsanity.com/paper/2303.15938/) (2023)
- [Guided Frequency Loss for Image Restoration](https://mlsanity.com/paper/2309.15563/) (2023)
- [AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2312.05928/) (2023)
- [Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification](https://mlsanity.com/paper/2401.01839/) (2024)

## Abstract (arXiv)

Image-to-image translation has been revolutionized with GAN-based methods. However, existing methods lack the ability to preserve the identity of the source domain. As a result, synthesized images can often over-adapt to the reference domain, losing important structural characteristics and suffering from suboptimal visual quality. To solve these challenges, we propose a novel frequency domain image translation (FDIT) framework, exploiting frequency information for enhancing the image generation process. Our key idea is to decompose the image into low-frequency and high-frequency components, where the high-frequency feature captures object structure akin to the identity. Our training objective facilitates the preservation of frequency information in both pixel space and Fourier spectral space. We broadly evaluate FDIT across five large-scale datasets and multiple tasks including image translation and GAN inversion. Extensive experiments and ablations show that FDIT effectively preserves the identity of the source image, and produces photo-realistic images. FDIT establishes state-of-the-art performance, reducing the average FID score by 5.6% compared to the previous best method.