When the Edit Changes the Patient: Measuring Identity Preservation in Counterfactual Retinal Images

• URL: http://arxiv.org/abs/2608.23024v1
• Date: Mon, 24 Aug 2026 09:29:40 GMT
• Title: When the Edit Changes the Patient: Measuring Identity Preservation in Counterfactual Retinal Images
• Abstract summary: We explicitly measure identity preservation for three groups of text-conditioned editing methods - source-anchored, structured-prompt, and paired-training.<n>We find that all methods produce high-quality OCT images with comparable editing success, yet their identity preservation differs markedly.<n>We argue that future work on medical counterfactual generation must explicitly measure and report identity preservation alongside image realism and editing success.
• Score: 44.33915499111612
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Counterfactual medical image generation aims to modify an existing image to reflect a hypothetical scenario in which certain characteristics of the imaged subject are altered, while keeping their identity fixed. Most existing works repurpose established image editing methods, which do not directly supervise identity preservation. Instead, they assume that identity is implicitly preserved by anchoring generation to the source image. This assumption is rarely tested and may fail in domains where biometric cues are subtle, such as retinal optical coherence tomography (OCT). In this work, we explicitly measure identity preservation for three groups of text-conditioned editing methods - source-anchored, structured-prompt, and paired-training - using referee classifiers, embedding alignment scores, and a blind reader study. We find that all methods produce high-quality OCT images with comparable editing success, yet their identity preservation differs markedly. Source-anchored editing frequently alters the depicted subject, while paired-training preserves it best. We argue that future work on medical counterfactual generation must explicitly measure and report identity preservation alongside image realism and editing success.

Related papers

• Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System [20.281088110768955]
  Generative image models can produce high-quality images, follow complex instructions, and support precise edits.<n>But they still struggle to preserve who or what is being depicted.<n>We show that identity preservation remains a distinct limitation of current generative foundation models.
  arXiv  Detail & Related papers  (2026-09-03T17:44:25Z)
• Latent-Identity Tuning in Text-to-Image Personalization Models [65.31471460269033]
  We present a method for fine-grained identity tuning in text-to-image personalization models.<n>Unlike standard image editing, identity tuning modifies the latent representation of a specific identity.<n>We show that meaningful directions can be identified within this space and within subspaces defined by selected tokens.
  arXiv  Detail & Related papers  (2026-07-13T17:59:49Z)
• FlowID : Enhancing Forensic Identification with Latent Flow-Matching Models [7.497692242539801]
  FlowID is an identity-preserving facial reconstruction method.<n>Our approach combines single-image fine-tuning, with attention-based masking that localizes edits to damaged regions.<n>InjuredFaces is a novel benchmark for identity-preserving facial reconstruction under severe facial damage.
  arXiv  Detail & Related papers  (2026-03-31T11:12:01Z)
• WithAnyone: Towards Controllable and ID Consistent Image Generation [83.55786496542062]
  Identity-consistent generation has become an important focus in text-to-image research.<n>We develop a large-scale paired dataset tailored for multi-person scenarios.<n>We propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity.
  arXiv  Detail & Related papers  (2025-10-16T17:59:54Z)
• Unrecognizable Yet Identifiable: Image Distortion with Preserved Embeddings [22.338328674283062]
  We introduce an innovative image transformation technique that renders facial images unrecognizable to the eye while maintaining their identifiability by neural network models. The proposed methodology can be used in various artificial intelligence applications to distort the visual data and keep the derived features close. We show that it is possible to build the distortion that changes the image content by more than 70% while maintaining the same recognition accuracy.
  arXiv  Detail & Related papers  (2024-01-26T18:20:53Z)
• When StyleGAN Meets Stable Diffusion: a $\mathscr{W}_+$ Adapter for Personalized Image Generation [60.305112612629465]
  Text-to-image diffusion models have excelled in producing diverse, high-quality, and photo-realistic images. We present a novel use of the extended StyleGAN embedding space $mathcalW_+$ to achieve enhanced identity preservation and disentanglement for diffusion models. Our method adeptly generates personalized text-to-image outputs that are not only compatible with prompt descriptions but also amenable to common StyleGAN editing directions.
  arXiv  Detail & Related papers  (2023-11-29T09:05:14Z)
• Anonymizing medical case-based explanations through disentanglement [4.006745047019996]
  We propose a novel method for disentangling identity and medical characteristics of images and apply it to anonymize medical images. The disentanglement mechanism replaces some feature vectors in an image while ensuring that the remaining features are preserved. We also propose a model to manufacture synthetic privacy-preserving identities to replace the original image's identity and achieve anonymization.
  arXiv  Detail & Related papers  (2023-11-08T16:58:58Z)
• DocMAE: Document Image Rectification via Self-supervised Representation Learning [144.44748607192147]
  We present DocMAE, a novel self-supervised framework for document image rectification. We first mask random patches of the background-excluded document images and then reconstruct the missing pixels. With such a self-supervised learning approach, the network is encouraged to learn the intrinsic structure of deformed documents.
  arXiv  Detail & Related papers  (2023-04-20T14:27:15Z)
• Pivotal Tuning for Latent-based Editing of Real Images [40.22151052441958]
  A surge of advanced facial editing techniques have been proposed that leverage the generative power of a pre-trained StyleGAN. To successfully edit an image this way, one must first project (or invert) the image into the pre-trained generator's domain. This means it is still challenging to apply ID-preserving facial latent-space editing to faces which are out of the generator's domain.
  arXiv  Detail & Related papers  (2021-06-10T13:47:59Z)
• Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation [136.53288628437355]
  Controllable semantic image editing enables a user to change entire image attributes with few clicks. Current approaches often suffer from attribute edits that are entangled, global image identity changes, and diminished photo-realism. We propose quantitative evaluation strategies for measuring controllable editing performance, unlike prior work which primarily focuses on qualitative evaluation.
  arXiv  Detail & Related papers  (2021-02-01T21:38:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.