Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

Authors

  • Jinhai Yang Bytedance Inc.
  • Mengxi Guo Bytedance Inc.
  • Shijie Zhao Bytedance Inc.
  • Junlin Li Bytedance Inc.
  • Li Zhang Bytedance Inc.

DOI:

https://doi.org/10.1609/aaai.v37i3.25420

Keywords:

CV: Low Level & Physics-Based Vision, CV: Applications

Abstract

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). Code is available at https://github.com/yang-jin-hai/SAIN.

Downloads

Published

2023-06-26

How to Cite

Yang, J., Guo, M., Zhao, S., Li, J., & Zhang, L. (2023). Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3155-3163. https://doi.org/10.1609/aaai.v37i3.25420

Issue

Section

AAAI Technical Track on Computer Vision III