Saved in:
Bibliographic Details
Main Authors: Bao, Chenglong, Pang, Tongyao, Shen, Zuowei, Zheng, Dihan, Zou, Yihang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.06834
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915720887009280
author Bao, Chenglong
Pang, Tongyao
Shen, Zuowei
Zheng, Dihan
Zou, Yihang
author_facet Bao, Chenglong
Pang, Tongyao
Shen, Zuowei
Zheng, Dihan
Zou, Yihang
contents Low-resolution image representation is 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06834
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Low-resolution Image Representation Through Normalizing Flows
Bao, Chenglong
Pang, Tongyao
Shen, Zuowei
Zheng, Dihan
Zou, Yihang
Computer Vision and Pattern Recognition
Low-resolution image representation is 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.
title Enhancing Low-resolution Image Representation Through Normalizing Flows
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.06834