paper-with-me

홈 › Papers

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

2020-11-27 · ICCV 2021 10 · Mu Cai, Hong Zhang, Huijuan Huang, Qichuan Geng, Yixuan Li, Gao Huang

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.

📄 PDF Abstract BibTeX arXiv:2011.13611

Code (1)

mu-cai/frequency-domain-image-translation 공식 구현 pytorch

Tasks

Image GenerationImage-to-Image TranslationTranslation

Similar Papers 제목 키워드 기반

Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile

2024-03-08 · SeokJun Lee, Seung-Won Jung, Hyunseok Seo

Currently, image generation and synthesis have remarkably progressed with generative models. Despite photo-realistic results, intrinsic discrepancies are still observed in the frequency domain. The spectral discrepancy a…

Contrastive LearningFace SwappingImage GenerationImage-to-Image Translation+1

Learning Latent Representations for Image Translation using Frequency Distributed CycleGAN

2025-08-05 · Shivangi Nigam, Adarsh Prasad Behera, Shekhar Verma, P. Nagabhushan arxiv

This paper presents Fd-CycleGAN, an image-to-image (I2I) translation framework that enhances latent representation learning to approximate real data distributions. Building upon the foundation of CycleGAN, our approach i…

Representation LearningStyle Transfer

High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network

2021-05-19 · CVPR 2021 1 · Jie Liang, Hui Zeng, Lei Zhang

Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps. In thi…

4kAttributeColor ManipulationGPU+4

Wavelet-based Unsupervised Label-to-Image Translation

2023-05-16 · IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022 5 · George Eskandar, Mohamed Abdelsamad, Karim Armanious, Shuai Zhang 외

Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a semantic layout is used to generate a photorealistic image. State-of-the-art conditional Generative Adversarial Networks (GANs) need a hu…

Image GenerationImage-to-Image TranslationMultimodal Unsupervised Image-To-Image TranslationTranslation+1

Old Photo Restoration via Deep Latent Space Translation

2020-09-14 · Zi-Yu Wan, Bo Zhang, Dong-Dong Chen, Pan Zhang 외

We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos …

Image RestorationTranslationTriplet