paper-with-me

홈 › Papers

FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform

2021-11-21 · Runyuan Cai, Yue Ding, Hongtao Lu

Single image super-resolution(SISR) is an ill-posed problem that aims to obtain high-resolution (HR) output from low-resolution (LR) input, during which extra high-frequency information is supposed to be added to improve the perceptual quality. Existing SISR works mainly operate in the spatial domain by minimizing the mean squared reconstruction error. Despite the high peak signal-to-noise ratios(PSNR) results, it is difficult to determine whether the model correctly adds desired high-frequency details. Some residual-based structures are proposed to guide the model to focus on high-frequency features implicitly. However, how to verify the fidelity of those artificial details remains a problem since the interpretation from spatial-domain metrics is limited. In this paper, we propose FreqNet, an intuitive pipeline from the frequency domain perspective, to solve this problem. Inspired by existing frequency-domain works, we convert images into discrete cosine transform (DCT) blocks, then reform them to obtain the DCT feature maps, which serve as the input and target of our model. A specialized pipeline is designed, and we further propose a frequency loss function to fit the nature of our frequency-domain task. Our SISR method in the frequency domain can learn the high-frequency information explicitly, provide fidelity and good perceptual quality for the SR images. We further observe that our model can be merged with other spatial super-resolution models to enhance the quality of their original SR output.

📄 PDF Abstract BibTeX arXiv:2111.10800

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

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

Dual-Control Frequency-Aware Diffusion Model for Depth-Dependent Optical Microrobot Microscopy Image Generation

2026-04-13 · Lan Wei, Zongcai Tan, Kangyi Lu, Jian-Qing Zheng 외 arxiv

Optical microrobots actuated by optical tweezers (OT) are important for cell manipulation and microscale assembly, but their autonomous operation depends on accurate 3D perception. Developing such perception systems is c…

Data AugmentationDepth EstimationImage GenerationPoint Clouds

Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning

2024-03-12 · Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu 외

This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images despite limited training data. Existing frequency-based paradigms have relied on freq…

DeepFake DetectionFace Swapping

Accelerating Inference of Networks in the Frequency Domain

2024-10-06 · Chenqiu Zhao, Guanfang Dong, Anup Basu

It has been demonstrated that networks' parameters can be significantly reduced in the frequency domain with a very small decrease in accuracy. However, given the cost of frequency transforms, the computational complexit…

Frequency-Domain Refinement with Multiscale Diffusion for Super Resolution

2024-05-16 · Xingjian Wang, Li Chai, Jiming Chen

The performance of single image super-resolution depends heavily on how to generate and complement high-frequency details to low-resolution images. Recently, diffusion-based models exhibit great potential in generating h…

Image Super-ResolutionSuper-Resolution

Dual-domain Modulation Network for Lightweight Image Super-Resolution

2025-03-13 · Wenjie Li, Heng Guo, Yuefeng Hou, Guangwei Gao 외

Lightweight image super-resolution (SR) aims to reconstruct high-resolution images from low-resolution images with limited computational costs. We find existing frequency-based SR methods cannot balance the reconstructio…

Image Super-ResolutionSuper-Resolution