# StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation

arXiv: https://arxiv.org/abs/2403.20142 · HTML: https://mlsanity.com/paper/2403.20142/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge](https://mlsanity.com/paper/1811.02629/) (2018)
- [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Dual Diffusion Implicit Bridges for Image-to-Image Translation](https://mlsanity.com/paper/2203.08382/) (2022)
- [A study of the effect of JPG compression on adversarial images](https://mlsanity.com/paper/1608.00853/) (2016)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1809.05852/) (2018)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm](https://mlsanity.com/paper/1906.03720/) (2019)
- [AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks](https://mlsanity.com/paper/1911.11897/) (2019)
- [CycleGAN, a Master of Steganography](https://mlsanity.com/paper/1712.02950/) (2017)
- [Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2108.04547/) (2021)
- [Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks](https://mlsanity.com/paper/2203.01532/) (2022)
- [DiffI2I: Efficient Diffusion Model for Image-to-Image Translation](https://mlsanity.com/paper/2308.13767/) (2023)
- [FUN-SIS: a Fully UNsupervised approach for Surgical Instrument Segmentation](https://mlsanity.com/paper/2202.08141/) (2022)
- [Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statistics](https://mlsanity.com/paper/2012.04932/) (2020)
- [Asymmetric GAN for Unpaired Image-to-image Translation](https://mlsanity.com/paper/1912.11660/) (2019)
- [Pathology Segmentation using Distributional Differences to Images of Healthy Origin](https://mlsanity.com/paper/1805.10344/) (2018)

## Built on by (most cited first, 18 of 18)

- [PID: Physics-Informed Diffusion Model for Infrared Image Generation](https://mlsanity.com/paper/2407.09299/) (2024)
- [C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object Generation](https://mlsanity.com/paper/2411.10788/) (2024)
- [A Pattern Language for Machine Learning Tasks](https://mlsanity.com/paper/2407.02424/) (2024)
- [Seg-CycleGAN : SAR-to-optical image translation guided by a downstream task](https://mlsanity.com/paper/2408.05777/) (2024)
- [TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation](https://mlsanity.com/paper/2602.19430/) (2026)
- [FlowEO: Generative Unsupervised Domain Adaptation for Earth Observation](https://mlsanity.com/paper/2512.05140/) (2025)
- [CAS-GAN for Contrast-free Angiography Synthesis](https://mlsanity.com/paper/2410.08490/) (2024)
- [CSHNet: A Novel Information Asymmetric Image Translation Method](https://mlsanity.com/paper/2501.10197/) (2025)
- [EarthMapper: Visual Autoregressive Models for Controllable Bidirectional Satellite-Map Translation](https://mlsanity.com/paper/2504.19432/) (2025)
- [Generative AI for Misalignment-Resistant Virtual Staining to Accelerate Histopathology Workflows](https://mlsanity.com/paper/2509.14119/) (2025)
- [MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling](https://mlsanity.com/paper/2605.20090/) (2026)
- [IMPLICITSTAINER: Resolution Agnostic Data-Efficient Virtual Staining Using Neural Implicit Functions](https://mlsanity.com/paper/2505.09831/) (2025)
- [OSCAR: Optical-aware Semantic Control for Aleatoric Refinement in Sar-to-Optical Translation](https://mlsanity.com/paper/2601.06835/) (2026)
- [GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth Observation](https://mlsanity.com/paper/2608.01896/) (2026)
- [FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis](https://mlsanity.com/paper/2608.03822/) (2026)
- [SC-Diff: Semantically Calibrated Diffusion for Visible-to-Infrared Image Translation](https://mlsanity.com/paper/2608.08555/) (2026)
- [ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation](https://mlsanity.com/paper/2609.00968/) (2026)
- [GeoSET: Generalist Foundation Model for SAR-to-EO Image Translation](https://mlsanity.com/paper/2609.37496/) (2026)

## Abstract (arXiv)

Most image-to-image translation models postulate that a unique correspondence exists between the semantic classes of the source and target domains. However, this assumption does not always hold in real-world scenarios due to divergent distributions, different class sets, and asymmetrical information representation. As conventional GANs attempt to generate images that match the distribution of the target domain, they may hallucinate spurious instances of classes absent from the source domain, thereby diminishing the usefulness and reliability of translated images. CycleGAN-based methods are also known to hide the mismatched information in the generated images to bypass cycle consistency objectives, a process known as steganography. In response to the challenge of non-bijective image translation, we introduce StegoGAN, a novel model that leverages steganography to prevent spurious features in generated images. Our approach enhances the semantic consistency of the translated images without requiring additional postprocessing or supervision. Our experimental evaluations demonstrate that StegoGAN outperforms existing GAN-based models across various non-bijective image-to-image translation tasks, both qualitatively and quantitatively. Our code and pretrained models are accessible at https://github.com/sian-wusidi/StegoGAN.