# Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

arXiv: https://arxiv.org/abs/2303.02353 · HTML: https://mlsanity.com/paper/2303.02353/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 4 Mar 2023.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design](https://mlsanity.com/paper/1902.00275/) (2019)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Invertible Image Rescaling](https://mlsanity.com/paper/2005.05650/) (2020)
- [Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling](https://mlsanity.com/paper/2108.05301/) (2021)
- [Learned Image Downscaling for Upscaling using Content Adaptive Resampler](https://mlsanity.com/paper/1907.12904/) (2019)
- [Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks](https://mlsanity.com/paper/2009.14754/) (2020)
- [Maximum Number of Modes of Gaussian Mixtures](https://mlsanity.com/paper/1702.05066/) (2017)

## Built on by (most cited first, 9 of 9)

- [ResVR: Joint Rescaling and Viewport Rendering of Omnidirectional Images](https://mlsanity.com/paper/2404.16825/) (2024)
- [Plug-and-Play Tri-Branch Invertible Block for Image Rescaling](https://mlsanity.com/paper/2412.13508/) (2024)
- [Timestep-Aware Diffusion Model for Extreme Image Rescaling](https://mlsanity.com/paper/2408.09151/) (2024)
- [Enhancing Low-resolution Image Representation Through Normalizing Flows](https://mlsanity.com/paper/2601.06834/) (2026)
- [Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network](https://mlsanity.com/paper/2508.02111/) (2025)
- [Versatile Recompression-Aware Perceptual Image Super-Resolution](https://mlsanity.com/paper/2511.18090/) (2025)
- [Faithful Extreme Image Rescaling with Learnable Reversible Transformation and Semantic Priors](https://mlsanity.com/paper/2605.00605/) (2026)
- [TVRN: Invertible Neural Networks for Compression-Aware Temporal Video Rescaling](https://mlsanity.com/paper/2605.15579/) (2026)
- [A Projection-Based Surrogate Gradient Interpretation for Neural Codec Wrappers](https://mlsanity.com/paper/2606.20671/) (2026)

## Abstract (arXiv)

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).