# Invertible Image Rescaling

arXiv: https://arxiv.org/abs/2005.05650 · HTML: https://mlsanity.com/paper/2005.05650/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2020.

## Built on by (most cited first, 30 of 92)

- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection](https://mlsanity.com/paper/2312.08883/) (2023)
- [Enhanced Invertible Encoding for Learned Image Compression](https://mlsanity.com/paper/2108.03690/) (2021)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Fast Vision Transformers with HiLo Attention](https://mlsanity.com/paper/2205.13213/) (2022)
- [Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling](https://mlsanity.com/paper/2108.05301/) (2021)
- [Invertible Denoising Network: A Light Solution for Real Noise Removal](https://mlsanity.com/paper/2104.10546/) (2021)
- [Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms](https://mlsanity.com/paper/2212.12678/) (2022)
- [CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography](https://mlsanity.com/paper/2305.16936/) (2023)
- [GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors](https://mlsanity.com/paper/2504.01016/) (2025)
- [Resolution learning in deep convolutional networks using scale-space theory](https://mlsanity.com/paper/2106.03412/) (2021)
- [Global Spectral Filter Memory Network for Video Object Segmentation](https://mlsanity.com/paper/2210.05567/) (2022)
- [Large-capacity and Flexible Video Steganography via Invertible Neural Network](https://mlsanity.com/paper/2304.12300/) (2023)
- [Self-Conditioned Probabilistic Learning of Video Rescaling](https://mlsanity.com/paper/2107.11639/) (2021)
- [Learning to Immunize Images for Tamper Localization and Self-Recovery](https://mlsanity.com/paper/2210.15902/) (2022)
- [Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence](https://mlsanity.com/paper/2203.00911/) (2022)
- [Invertible Rescaling Network and Its Extensions](https://mlsanity.com/paper/2210.04188/) (2022)
- [IICNet: A Generic Framework for Reversible Image Conversion](https://mlsanity.com/paper/2109.04242/) (2021)
- [A Review of Change of Variable Formulas for Generative Modeling](https://mlsanity.com/paper/2308.02652/) (2023)
- [Imperceptible Adversarial Attack via Invertible Neural Networks](https://mlsanity.com/paper/2211.15030/) (2022)
- [From Image to Imuge: Immunized Image Generation](https://mlsanity.com/paper/2110.14196/) (2021)
- [Scale-arbitrary Invertible Image Downscaling](https://mlsanity.com/paper/2201.12576/) (2022)
- [Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution](https://mlsanity.com/paper/2111.03649/) (2021)
- [Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey](https://mlsanity.com/paper/2405.01725/) (2024)
- [Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions](https://mlsanity.com/paper/2106.03727/) (2021)
- [RWN: Robust Watermarking Network for Image Cropping Localization](https://mlsanity.com/paper/2110.05687/) (2021)
- [High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation](https://mlsanity.com/paper/2209.05054/) (2022)
- [Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling](https://mlsanity.com/paper/2303.02353/) (2023)
- [Approaching the Limit of Image Rescaling via Flow Guidance](https://mlsanity.com/paper/2111.05133/) (2021)

## Abstract (arXiv)

High-resolution digital images are usually downscaled to fit various display screens or save the cost of storage and bandwidth, meanwhile the post-upscaling is adpoted to recover the original resolutions or the details in the zoom-in images. However, typical image downscaling is a non-injective mapping due to the loss of high-frequency information, which leads to the ill-posed problem of the inverse upscaling procedure and poses great challenges for recovering details from the downscaled low-resolution images. Simply upscaling with image super-resolution methods results in unsatisfactory recovering performance. In this work, we propose to solve this problem by modeling the downscaling and upscaling processes from a new perspective, i.e. an invertible bijective transformation, which can largely mitigate the ill-posed nature of image upscaling. We develop an Invertible Rescaling Net (IRN) with deliberately designed framework and objectives to produce visually-pleasing low-resolution images and meanwhile capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process. In this way, upscaling is made tractable by inversely passing a randomly-drawn latent variable with the low-resolution image through the network. Experimental results demonstrate the significant improvement of our model over existing methods in terms of both quantitative and qualitative evaluations of image upscaling reconstruction from downscaled images.