paper-with-me

홈 › Papers

Enhancing Low-resolution Image Representation Through Normalizing Flows

2026-01-11 · Chenglong Bao, Tongyao Pang, Zuowei Shen, Dihan Zheng, Yihang Zou arxiv

Low-resolution image representation can be regarded as a special form of sparse representation that retains only low-frequency information while discarding high-frequency components. This property reduces storage and transmission costs and benefits various image processing tasks. However, a key challenge is to preserve essential visual content while maintaining the ability to accurately reconstruct the original images. This work proposes LR2Flow, a nonlinear framework that learns low-resolution image representations by integrating wavelet tight frame blocks with normalizing flows. We conduct a reconstruction error analysis of the proposed network, which demonstrates the necessity of designing invertible neural networks in the wavelet tight frame domain. Experimental results on various tasks, including image rescaling, compression, and denoising, demonstrate the effectiveness of the learned representations and the robustness of the proposed framework. Code is available at https://github.com/Evanescentlove/LR2Flow-main.

📄 PDF Abstract BibTeX arXiv:2601.06834

Code (0)

등록된 구현이 없습니다.

Tasks

Image Rescaling

Similar Papers 제목 키워드 기반

SRFlow: Learning the Super-Resolution Space with Normalizing Flow

2020-06-25 · ECCV 2020 8 · Andreas Lugmayr, Martin Danelljan, Luc van Gool, Radu Timofte

Super-resolution is an ill-posed problem, since it allows for multiple predictions for a given low-resolution image. This fundamental fact is largely ignored by state-of-the-art deep learning based approaches. These meth…

DiversityImage ManipulationImage Super-ResolutionSuper-Resolution

Wavelet Flow: Fast Training of High Resolution Normalizing Flows

2020-10-26 · NeurIPS 2020 12 · Jason J. Yu, Konstantinos G. Derpanis, Marcus A. Brubaker

Normalizing flows are a class of probabilistic generative models which allow for both fast density computation and efficient sampling and are effective at modelling complex distributions like images. A drawback among cur…

GPUSuper-ResolutionVocal Bursts Intensity Prediction

Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network

2022-07-24 · Min Zhang, Zhihong Pan, Xin Zhou, C. -C. Jay Kuo

Normalizing flow models have been used successfully for generative image super-resolution (SR) by approximating complex distribution of natural images to simple tractable distribution in latent space through Invertible N…

Image RescalingImage RestorationImage Super-ResolutionSuper-Resolution

Multi-Resolution Continuous Normalizing Flows

2021-06-15 · Vikram Voleti, Chris Finlay, Adam Oberman, Christopher Pal

Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as generative models of images using the perspective of Continuous Normalizing Flows (CNFs). Such models offer exact likelihood calculati…

Density EstimationGPUImage Generation

LoLiSRFlow: Joint Single Image Low-light Enhancement and Super-resolution via Cross-scale Transformer-based Conditional Flow

2024-02-29 · Ziyu Yue, Jiaxin Gao, Sihan Xie, Yang Liu 외

The visibility of real-world images is often limited by both low-light and low-resolution, however, these issues are only addressed in the literature through Low-Light Enhancement (LLE) and Super- Resolution (SR) methods…

Super-Resolution