Face inpainting with Identity Preserving Latent Diffusion Models

• URL: http://arxiv.org/abs/2605.16696v1
• Date: Fri, 15 May 2026 23:19:43 GMT
• Title: Face inpainting with Identity Preserving Latent Diffusion Models
• Abstract summary: ID-ControlNet is an identity-preserving face inpainting framework built upon latent diffusion models.<n>We introduce an identity consistency and triplet loss training strategy that explicitly enforces alignment between the generated face and the target identity representation.
• Score: 10.348748950921667
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output remains a fundamental challenge. Identity consistency is crucial for downstream applications such as face recognition, digital forensics, and human-computer interaction, where even subtle identity distortions can significantly degrade performance or trust. Although diffusion-based generative models have recently achieved remarkable progress in image inpainting, they often struggle to faithfully retain individual-specific facial characteristics. On the other hand, existing identity-aware methods typically rely on costly fine-tuning, auxiliary supervision, or exhibit limited robustness to diverse occlusions, poses, and facial variations. To address these limitations, we propose ID-ControlNet, an identity-preserving face inpainting framework built upon latent diffusion models. Based on ControlNet architecture, our approach conditions the diffusion process on facial identity embeddings extracted from a pretrained face recognition network. This design enables reconstruction of occluded facial regions while maintaining global facial coherence and identity fidelity. Furthermore, we introduce an identity consistency and triplet loss training strategy that explicitly enforces alignment between the generated face and the target identity representation. Extensive experiments on CelebA-HQ, FFHQ, and on a new E-Mask dataset demonstrate that ID-ControlNet significantly improves identity preservation over standard diffusion-based inpainting methods, achieving performance comparable to SOTA identity-aware approaches.

Related papers

• CA-IDD: Cross-Attention Guided Identity-Conditional Diffusion for Identity-Consistent Face Swapping [1.4323566945483497]
  Face swapping aims to optimize realistic facial image generation by leveraging the identity of a source face onto a target face.<n>Existing methods, especially GAN-based methods, often struggle to balance identity preservation and visual realism.<n>We introduce CA-IDD, the first diffusion-based face swapping approach that integrates gaze, identity, and facial parsing.
  arXiv  Detail & Related papers  (2026-04-27T13:59:08Z)
• Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement [54.199726425201895]
  Multimodal editing large models have demonstrated powerful editing capabilities across diverse tasks.<n>Current facial ID preservation methods struggle to achieve consistent restoration of both facial identity and edited element IP.<n>We propose EditedID, an Alignment-Disentanglement-Entanglement framework for robust identity-specific facial restoration.
  arXiv  Detail & Related papers  (2026-02-21T08:24:42Z)
• SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy [53.75084833636302]
  We propose SIDeR, a Semantic decoupling-driven framework for unrestricted face privacy protection.<n> SIDeR decomposes a facial image into a machine-recognizable identity feature vector and a visually perceptible semantic appearance component.<n>For authorized access, SIDeR can be restored to its original form when the correct password is provided.
  arXiv  Detail & Related papers  (2026-02-04T19:30:48Z)
• DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping [16.846179110602737]
  We propose DiffSwap++, a novel diffusion-based face-swapping pipeline that incorporates 3D facial latent features during training.<n>Our method enhances geometric consistency and improves the disentanglement of facial identity from appearance attributes.<n>Experiments on CelebA, FFHQ, and CelebV-Text demonstrate that DiffSwap++ outperforms prior methods in preserving source identity while maintaining target pose and expression.
  arXiv  Detail & Related papers  (2025-11-04T18:56:49Z)
• High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning [39.09330483562798]
  Face swapping aims to seamlessly transfer a source facial identity onto a target while preserving target attributes such as pose and expression.<n> Diffusion models, known for their superior generative capabilities, have recently shown promise in advancing face-swapping quality.<n>This paper addresses two key challenges in diffusion-based face swapping: the prioritized preservation of identity over target attributes and the inherent conflict between identity and attribute conditioning.
  arXiv  Detail & Related papers  (2025-03-28T06:50:17Z)
• iFADIT: Invertible Face Anonymization via Disentangled Identity Transform [51.123936665445356]
  Face anonymization aims to conceal the visual identity of a face to safeguard the individual's privacy.<n>This paper proposes a novel framework named iFADIT, an acronym for Invertible Face Anonymization via Disentangled Identity Transform.
  arXiv  Detail & Related papers  (2025-01-08T10:08:09Z)
• ID$^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition [60.15830516741776]
  Synthetic face recognition (SFR) aims to generate datasets that mimic the distribution of real face data. We introduce a diffusion-fueled SFR model termed $textID3$. $textID3$ employs an ID-preserving loss to generate diverse yet identity-consistent facial appearances.
  arXiv  Detail & Related papers  (2024-09-26T06:46:40Z)
• ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving [64.90148669690228]
  ConsistentID is an innovative method crafted for diverseidentity-preserving portrait generation under fine-grained multimodal facial prompts.<n>We present a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets.
  arXiv  Detail & Related papers  (2024-04-25T17:23:43Z)
• Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification [55.741525129613535]
  "Disentangle Before Anonymize" is a novel two-stage Framework(DBAF)<n>This framework includes a Contrastive Identity Disentanglement (CID) module and a Key-authorized Reversible Identity Anonymization (KRIA) module.<n>Extensive experiments demonstrate that our method outperforms state-of-the-art de-identification approaches.
  arXiv  Detail & Related papers  (2023-11-15T08:59:02Z)
• Controllable Inversion of Black-Box Face Recognition Models via Diffusion [8.620807177029892]
  We tackle the task of inverting the latent space of pre-trained face recognition models without full model access. We show that the conditional diffusion model loss naturally emerges and that we can effectively sample from the inverse distribution. Our method is the first black-box face recognition model inversion method that offers intuitive control over the generation process.
  arXiv  Detail & Related papers  (2023-03-23T03:02:09Z)
• FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping [62.38898610210771]
  We present a new single-stage method for subject face swapping and identity transfer, named FaceDancer. We have two major contributions: Adaptive Feature Fusion Attention (AFFA) and Interpreted Feature Similarity Regularization (IFSR)
  arXiv  Detail & Related papers  (2022-10-19T11:31:38Z)

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.