IConFace: Identity-Structure Asymmetric Conditioning for Unified Reference-Aware Face Restoration

• URL: http://arxiv.org/abs/2605.02814v1
• Date: Mon, 04 May 2026 16:49:51 GMT
• Title: IConFace: Identity-Structure Asymmetric Conditioning for Unified Reference-Aware Face Restoration
• Abstract summary: Blind face restoration is highly ill-posed under severe degradation.<n>Same-identity references reduce this ambiguity, but mismatched pose, expression, illumination, age, makeup, or local facial states can lead to overuse of reference appearance.<n>We propose textbfIConFace, a unified reference-aware and no-reference framework with identity--structure asymmetric conditioning.
• Score: 2.7652581048436864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Blind face restoration is highly ill-posed under severe degradation, where identity-critical details may be missing from the degraded input. Same-identity references reduce this ambiguity, but mismatched pose, expression, illumination, age, makeup, or local facial states can lead to overuse of reference appearance. We propose \textbf{IConFace}, a unified reference-aware and no-reference framework with identity--structure asymmetric conditioning. References are distilled into a norm-weighted global AdaFace identity anchor for image-only modulation, while the degraded image is reinforced as the spatial structure anchor through low-rank residuals and block-wise degraded cross-attention with two-route memory. The resulting single checkpoint exploits references when available and falls back to no-reference restoration when absent, improving identity consistency, fine-detail recovery, and degraded-only restoration quality in a unified model.

Related papers

• When Diffusion Models Forget Who You Are: Identity Preservation in Face Inpainting under Large Occlusions [14.50832575272006]
  ReSem-Face is a cascaded diffusion framework that introduces an explicit identity-conditioned semantic prior for face inpainting.<n>Our approach distills representative identity features from multiple references to reconstruct missing semantic regions.<n> Experiments on CelebAHQ-IDI-5 and VGGFace2 demonstrate that ReSem-Face yields more reliable identity-preserving completion under severe semantic masks.
  arXiv  Detail & Related papers  (2026-08-05T13:23:40Z)
• TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation [24.354251784441217]
  TimeWeaver is a reference-based face restoration framework supporting cross-age references.<n>We decouple identity and age conditioning across training and inference.<n>Extensive experiments show that TimeWeaver surpasses existing methods in visual quality, identity preservation, and age consistency.
  arXiv  Detail & Related papers  (2026-03-24T01:48:27Z)
• MeInTime: Bridging Age Gap in Identity-Preserving Face Restoration [24.354251784441217]
  MeInTime is a diffusion-based face restoration method that extends reference-based restoration from same-age to cross-age settings.<n>Given one or few reference images along with an age prompt corresponding to the degraded input, MeInTime achieves faithful restoration with both identity fidelity and age consistency.
  arXiv  Detail & Related papers  (2026-03-19T09:11:07Z)
• 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)
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization [55.29071072675132]
  Face anonymization aims to conceal identity information while preserving non-identity attributes.<n>We propose textbfIDsuperscript2Face, a training-centric anonymization framework.<n>We show that IDtextsuperscript2Face outperforms existing methods in visual quality, identity suppression, and utility preservation.
  arXiv  Detail & Related papers  (2025-10-28T09:28:12Z)
• RefSTAR: Blind Facial Image Restoration with Reference Selection, Transfer, and Reconstruction [75.00967931348409]
  We present a novel blind facial image restoration method that considers reference selection, transfer, and reconstruction.<n>Experiments on various backbone models demonstrate superior performance, showing better identity preservation ability and reference feature transfer quality.
  arXiv  Detail & Related papers  (2025-07-14T16:50:29Z)
• Reference-Guided Identity Preserving Face Restoration [54.10295747851343]
  Preserving face identity is a critical yet persistent challenge in diffusion-based image restoration.<n>This paper introduces a novel approach that maximizes reference face utility for improved face restoration and identity preservation.
  arXiv  Detail & Related papers  (2025-05-28T02:46:34Z)
• 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)
• RestorerID: Towards Tuning-Free Face Restoration with ID Preservation [18.022455458259305]
  We propose a tuning-free method named RestorerID that incorporates ID preservation during face restoration. To achieve this, we propose a unified framework to combine the ID injection with the base blind face restoration model. Experimental results on the Celeb-Ref dataset and real-world scenarios demonstrate that RestorerID effectively delivers high-quality face restoration with ID preservation.
  arXiv  Detail & Related papers  (2024-11-21T13:50:25Z)
• Learning Dual Memory Dictionaries for Blind Face Restoration [75.66195723349512]
  Recent works mainly treat the two aspects, i.e., generic and specific restoration, separately. This paper suggests a DMDNet by explicitly memorizing the generic and specific features through dual dictionaries. A new high-quality dataset, termed CelebRef-HQ, is constructed to promote the exploration of specific face restoration in the high-resolution space.
  arXiv  Detail & Related papers  (2022-10-15T01:55:41Z)

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.