Enhancing Low-resolution Image Representation Through Normalizing Flows

2026-01-11

arXiv.org

AI Summary

This work addresses the challenge of preserving critical visual information while enabling high-fidelity reconstruction in low-resolution image representations. To this end, the authors propose LR2Flow, a novel framework that uniquely integrates normalizing flows with wavelet tight frames to construct an invertible neural network in the wavelet domain, facilitating nonlinear low-dimensional representation learning. Theoretical analysis of reconstruction error is provided, and the necessity of the invertible architecture for accurate reconstruction is rigorously validated. Extensive experiments demonstrate that LR2Flow achieves state-of-the-art performance across multiple tasks—including image super-resolution, compression, and denoising—thereby confirming both the effectiveness of the learned representations and the robustness of the proposed framework.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Representation Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Responsible Web: Measurement, analysis, and circumvention of Web censorship

Abstract

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.

Problem

• low-resolution image representation
• image reconstruction
• visual content preservation
• sparse representation
• invertible representation

Innovation

• normalizing flows
• wavelet tight frame
• invertible neural networks
• low-resolution representation
• image reconstruction