用归一化流提升低分辨率图像表征能力，实现高效重建与多任务应用。
Enhancing Low-resolution Image Representation Through Normalizing Flows
- 结合小波紧框架与归一化流，构建可逆神经网络学习低频图像表示。
- 在图像缩放、压缩和去噪任务中均实现优于基线的重建精度。
- 适合需要高保真低分辨率表征的图像处理场景，如传输与存储优化。
低分辨率图像表示是一种特殊的稀疏表示形式，仅保留低频信息而舍弃高频成分，有助于降低存储与传输成本，并促进各类图像处理任务。然而，如何在保持可精确重构原图能力的同时保留关键视觉内容，仍是核心挑战。本文提出LR2Flow，一种非线性框架，通过将小波紧框架块与归一化流相结合，学习低分辨率图像表示。我们对所提网络进行了重建误差分析，证实了在小波紧框架域设计可逆神经网络的必要性。在图像缩放、压缩和去噪等任务上的实验结果表明，该方法学习到的表示具有显著有效性与框架鲁棒性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。