High-resolution (HR) images are usually downscaled to low-resolution (LR) ones for better display and afterward upscaled back to the original size to recover details. Recent work in image rescaling formulates downscaling and upscaling as a unified task and learns a bijective mapping between HR and LR via invertible networks. However, in real-world applications (e.g., social media), most images are compressed for transmission. Lossy compression will lead to irreversible information loss on LR images, hence damaging the inverse upscaling procedure and degrading the reconstruction accuracy. In this paper, we propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling. To tackle the distribution shift, we first develop an end-to-end asymmetric framework with two separate bijective mappings for high-quality and compressed LR images, respectively. Then, based on empirical analysis of this framework, we model the distribution of the lost information (including downscaling and compression) using isotropic Gaussian mixtures and propose the Enhanced Invertible Block to derive high-quality/compressed LR images in one forward pass. Besides, we design a set of losses to regularize the learned LR images and enhance the invertibility. Extensive experiments demonstrate the consistent improvements of SAIN across various image rescaling datasets in terms of both quantitative and qualitative evaluation under standard image compression formats (i.e., JPEG and WebP).

翻译：高分辨率图像通常被降采样为低分辨率图像以便更好显示，随后再升采样回原始尺寸以恢复细节。近期图像缩放研究将降采样与升采样视为统一任务，通过可逆网络学习高分辨率与低分辨率图像之间的双射映射。然而在现实应用（如社交媒体）中，多数图像需经压缩后传输。有损压缩会导致低分辨率图像产生不可逆信息损失，从而破坏逆向升采样过程并降低重建精度。本文提出自对称可逆网络用于压缩感知图像缩放。为解决分布偏移问题，我们首先构建端到端非对称框架，分别为高质量与压缩低分辨率图像建立独立双射映射。随后基于该框架的实证分析，利用各向同性高斯混合模型对信息损失（含降采样与压缩损失）的分布进行建模，并提出增强型可逆模块以单次前向传播同时生成高质量/压缩低分辨率图像。此外，我们设计一组损失函数以正则化学习到的低分辨率图像并增强可逆性。大量实验表明，在标准图像压缩格式（JPEG与WebP）下，SAIN在多种图像缩放数据集上均实现一致性的量化与定性评估性能提升。