# EyePreserve: Identity-Preserving Iris Synthesis

arXiv: https://arxiv.org/abs/2312.12028 · HTML: https://mlsanity.com/paper/2312.12028/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 65 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [DCFace: Synthetic Face Generation with Dual Condition Diffusion Model](https://mlsanity.com/paper/2304.07060/) (2023)
- [GAN-Control: Explicitly Controllable GANs](https://mlsanity.com/paper/2101.02477/) (2021)
- [IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models](https://mlsanity.com/paper/2308.04995/) (2023)
- [Towards Large-Pose Face Frontalization in the Wild](https://mlsanity.com/paper/1704.06244/) (2017)
- [WarpedGANSpace: Finding non-linear RBF paths in GAN latent space](https://mlsanity.com/paper/2109.13357/) (2021)
- [Domain-Specific Human-Inspired Binarized Statistical Image Features for Iris Recognition](https://mlsanity.com/paper/1807.05248/) (2018)
- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [Labeled pupils in the wild: A dataset for studying pupil detection in unconstrained environments](https://mlsanity.com/paper/1511.05768/) (2015)
- [Assessment of iris recognition reliability for eyes affected by ocular pathologies](https://mlsanity.com/paper/1809.00206/) (2018)
- [Deception Detection and Remote Physiological Monitoring: A Dataset and Baseline Experimental Results](https://mlsanity.com/paper/2106.06583/) (2021)
- [FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis](https://mlsanity.com/paper/1812.01288/) (2018)
- [Haven't I Seen You Before? Assessing Identity Leakage in Synthetic Irises](https://mlsanity.com/paper/2211.05629/) (2022)
- [Learning-Free Iris Segmentation Revisited: A First Step Toward Fast Volumetric Operation Over Video Samples](https://mlsanity.com/paper/1901.01575/) (2019)
- [DeformIrisNet: An Identity-Preserving Model of Iris Texture Deformation](https://mlsanity.com/paper/2207.08980/) (2022)
- [iWarpGAN: Disentangling Identity and Style to Generate Synthetic Iris Images](https://mlsanity.com/paper/2305.12596/) (2023)
- [BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images](https://mlsanity.com/paper/2205.01536/) (2022)
- [Cross-spectral Iris Recognition for Mobile Applications using High-quality Color Images](https://mlsanity.com/paper/1807.04061/) (2018)

## Built on by (most cited first, 3 of 3)

- [Privacy-Safe Iris Presentation Attack Detection](https://mlsanity.com/paper/2408.02750/) (2024)
- [Synthetic Iris Image Databases and Identity Leakage: Risks and Mitigation Strategies](https://mlsanity.com/paper/2506.02626/) (2025)
- [When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge](https://mlsanity.com/paper/2601.06725/) (2026)

## Abstract (arXiv)

Synthesis of same-identity biometric iris images, both for existing and non-existing identities, while preserving the identity across a wide range of pupil sizes, is complex due to the intricate iris muscle constriction mechanism, requiring a precise model of iris non-linear texture deformations to be embedded into the synthesis pipeline. This paper presents EyePreserve, a novel, fully data-driven non-linear texture deformation model, embedded within an identity-preserving, pupil size-varying synthesis framework. This approach is capable of synthesizing images of irises with different pupil sizes representing non-existing identities, as well as non-linearly deforming the texture of iris images of existing subjects, given the segmentation mask of the target iris image. Iris recognition experiments suggest that the proposed deformation model both preserves the identity when changing the pupil size, and offers better similarity between same-identity iris samples with significant differences in pupil size, compared to state-of-the-art linear and non-linear (biomechanical-based) iris deformation models. Two immediate applications of the proposed approach are: (a) synthesis of new, or enhancement of the existing datasets of same-identity iris images with varying pupil sizes, with correct modeling of complex iris texture deformations, and (b) helping forensic human experts examine iris image pairs with significant differences in pupil dilation by deforming one or both images to align the pupil size. Images considered in this work conform to selected ISO/IEC 29794-6 quality metrics to make them applicable in biometric systems. The source codes and model weights are offered with this paper.