# Reversible GANs for Memory-efficient Image-to-Image Translation

arXiv: https://arxiv.org/abs/1902.02729 · HTML: https://mlsanity.com/paper/1902.02729/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

## Built on by (most cited first, 19 of 19)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms](https://mlsanity.com/paper/2212.12678/) (2022)
- [WavMark: Watermarking for Audio Generation](https://mlsanity.com/paper/2308.12770/) (2023)
- [Reversible Vision Transformers](https://mlsanity.com/paper/2302.04869/) (2023)
- [Learning to Immunize Images for Tamper Localization and Self-Recovery](https://mlsanity.com/paper/2210.15902/) (2022)
- [Slice-Consistent 3D Volumetric Brain CT-to-MRI Translation with 2D Brownian Bridge Diffusion Model](https://mlsanity.com/paper/2407.05059/) (2024)
- [Invertible Rescaling Network and Its Extensions](https://mlsanity.com/paper/2210.04188/) (2022)
- [Applications of Generative Adversarial Networks in Neuroimaging and Clinical Neuroscience](https://mlsanity.com/paper/2206.07081/) (2022)
- [Duplex Sequence-to-Sequence Learning for Reversible Machine Translation](https://mlsanity.com/paper/2105.03458/) (2021)
- [Robust Message Embedding via Attention Flow-Based Steganography](https://mlsanity.com/paper/2405.16414/) (2024)
- [3D Brain and Heart Volume Generative Models: A Survey](https://mlsanity.com/paper/2210.05952/) (2022)
- [Self Supervised Low Dose Computed Tomography Image Denoising Using Invertible Network Exploiting Inter Slice Congruence](https://mlsanity.com/paper/2211.01618/) (2022)
- [Exploiting Fine-Grained DCT Representations for Hiding Image-Level Messages within JPEG Images](https://mlsanity.com/paper/2305.06582/) (2023)
- [Deep Boosting Robustness of DNN-based Image Watermarking via DBMark](https://mlsanity.com/paper/2210.13801/) (2022)
- [PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flow](https://mlsanity.com/paper/2307.09146/) (2023)
- [Sparse Domain Transfer via Elastic Net Regularization](https://mlsanity.com/paper/2405.07489/) (2024)
- [FIIH: Fully Invertible Image Hiding for Secure and Robust](https://mlsanity.com/paper/2407.17155/) (2024)
- [Structure-Accurate Medical Image Translation via Dynamic Frequency Balance and Knowledge Guidance](https://mlsanity.com/paper/2504.09441/) (2025)
- [Breaking the Resolution Barrier: Arbitrary-resolution Deep Image Steganography Framework](https://mlsanity.com/paper/2601.15739/) (2026)

## Abstract (arXiv)

The Pix2pix and CycleGAN losses have vastly improved the qualitative and quantitative visual quality of results in image-to-image translation tasks. We extend this framework by exploring approximately invertible architectures which are well suited to these losses. These architectures are approximately invertible by design and thus partially satisfy cycle-consistency before training even begins. Furthermore, since invertible architectures have constant memory complexity in depth, these models can be built arbitrarily deep. We are able to demonstrate superior quantitative output on the Cityscapes and Maps datasets at near constant memory budget.