paper-with-me

Papers

Frequency-Controlled Diffusion Model for Versatile Text-Guided Image-to-Image Translation

2024-07-03 · Xiang Gao, Zhengbo Xu, Junhan Zhao, Jiaying Liu

Recently, large-scale text-to-image (T2I) diffusion models have emerged as a powerful tool for image-to-image translation (I2I), allowing open-domain image translation via user-provided text prompts. This paper proposes frequency-controlled diffusion model (FCDiffusion), an end-to-end diffusion-based framework that contributes a novel solution to text-guided I2I from a frequency-domain perspective. At the heart of our framework is a feature-space frequency-domain filtering module based on Discrete Cosine Transform, which filters the latent features of the source image in the DCT domain, yielding filtered image features bearing different DCT spectral bands as different control signals to the pre-trained Latent Diffusion Model. We reveal that control signals of different DCT spectral bands bridge the source image and the T2I generated image in different correlations (e.g., style, structure, layout, contour, etc.), and thus enable versatile I2I applications emphasizing different I2I correlations, including style-guided content creation, image semantic manipulation, image scene translation, and image style translation. Different from related approaches, FCDiffusion establishes a unified text-guided I2I framework suitable for diverse image translation tasks simply by switching among different frequency control branches at inference time. The effectiveness and superiority of our method for text-guided I2I are demonstrated with extensive experiments both qualitatively and quantitatively. Our project is publicly available at: https://xianggao1102.github.io/FCDiffusion/.

📄 PDF Abstract BibTeX arXiv:2407.03006

Code (2)

xianggao1102/fcdiffusion 공식 구현 pytorch
XiangGao1102/FCDiffusion_code pytorch

Tasks

Image-to-Image TranslationTranslation

Methods 이 논문이 사용한 방법론

Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Discrete Cosine Transform Discrete Cosine Transform (DCT) is an orthogonal transformation method that decomposes an image to its spatial frequency spectrum. It expresses a finite sequence of data…

Similar Papers 제목 키워드 기반

FBSDiff++: Improved Frequency Band Substitution of Diffusion Features for Efficient and Highly Controllable Text-Driven Image-to-Image Translation

2026-01-27 · Xiang Gao, Yunpeng Jia arxiv

With large-scale text-to-image (T2I) diffusion models achieving significant advancements in open-domain image creation, increasing attention has been focused on their natural extension to the realm of text-driven image-t…

Image-to-Image TranslationContinuous ControlImage Manipulation

One Stone with Two Birds: A Null-Text-Null Frequency-Aware Diffusion Models for Text-Guided Image Inpainting

2025-10-09 · Haipeng Liu, Yang Wang, Meng Wang arxiv

Text-guided image inpainting aims at reconstructing the masked regions as per text prompts, where the longstanding challenges lie in the preservation for unmasked regions, while achieving the semantics consistency betwee…

Image Inpainting

FADE: Frequency-Aware Diffusion Model Factorization for Video Editing

2025-06-06 · CVPR 2025 1 · Yixuan Zhu, Haolin Wang, Shilin Ma, Wenliang Zhao 외

Recent advancements in diffusion frameworks have significantly enhanced video editing, achieving high fidelity and strong alignment with textual prompts. However, conventional approaches using image diffusion models fall…

Video Editing

Generic 3D Diffusion Adapter Using Controlled Multi-View Editing

2024-03-18 · Hansheng Chen, Ruoxi Shi, Yulin Liu, Bokui Shen 외

Open-domain 3D object synthesis has been lagging behind image synthesis due to limited data and higher computational complexity. To bridge this gap, recent works have investigated multi-view diffusion but often fall shor…

3D GenerationImage GenerationImage to 3DText to 3D+1

NFCDS: A Plug-and-Play Noise Frequency-Controlled Diffusion Sampling Strategy for Image Restoration

2026-01-29 · Zhen Wang, Hongyi Liu, Jianing Li, Zhihui Wei arxiv

Diffusion sampling-based Plug-and-Play (PnP) methods produce images with high perceptual quality but often suffer from reduced data fidelity, primarily due to the noise introduced during reverse diffusion. To address thi…

Image Restoration