Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912853976416256 |
|---|---|
| author | Yao, Zhengjian Hu, Jiakui Li, Kaiwen He, Hangzhou Zhang, Xinliang Zeng, Shuang Zhu, Lei Lu, Yanye |
| author_facet | Yao, Zhengjian Hu, Jiakui Li, Kaiwen He, Hangzhou Zhang, Xinliang Zeng, Shuang Zhu, Lei Lu, Yanye |
| contents | Blind face restoration remains a persistent challenge due to the inherent ill-posedness of reconstructing holistic structures from severely constrained observations. Current generative approaches, while capable of synthesizing realistic textures, often suffer from information asymmetry -- the intrinsic disparity between the information-sparse low quality inputs and the information-dense high quality outputs. This imbalance leads to a one-to-many mapping, where insufficient constraints result in stochastic uncertainty and hallucinatory artifacts. To bridge this gap, we present \textbf{Pref-Restore}, a hierarchical framework that integrates discrete semantic logic with continuous texture generation to achieve deterministic, preference-aligned restoration. Our methodology fundamentally addresses this information disparity through two complementary strategies: (1) Augmenting Input Density: We employ an auto-regressive integrator to reformulate textual instructions into dense latent queries, injecting high-level semantic stability to constrain the degraded signals; (2) Pruning Output Distribution: We pioneer the integration of on-policy reinforcement learning directly into the diffusion restoration loop. By transforming human preferences into differentiable constraints, we explicitly penalize stochastic deviations, thereby sharpening the posterior distribution toward the desired high-fidelity outcomes. Extensive experiments demonstrate that Pref-Restore achieves state-of-the-art performance across synthetic and real-world benchmarks. Furthermore, empirical analysis confirms that our preference-aligned strategy significantly reduces solution entropy, establishing a robust pathway toward reliable and deterministic blind restoration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19506 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration Yao, Zhengjian Hu, Jiakui Li, Kaiwen He, Hangzhou Zhang, Xinliang Zeng, Shuang Zhu, Lei Lu, Yanye Computer Vision and Pattern Recognition Blind face restoration remains a persistent challenge due to the inherent ill-posedness of reconstructing holistic structures from severely constrained observations. Current generative approaches, while capable of synthesizing realistic textures, often suffer from information asymmetry -- the intrinsic disparity between the information-sparse low quality inputs and the information-dense high quality outputs. This imbalance leads to a one-to-many mapping, where insufficient constraints result in stochastic uncertainty and hallucinatory artifacts. To bridge this gap, we present \textbf{Pref-Restore}, a hierarchical framework that integrates discrete semantic logic with continuous texture generation to achieve deterministic, preference-aligned restoration. Our methodology fundamentally addresses this information disparity through two complementary strategies: (1) Augmenting Input Density: We employ an auto-regressive integrator to reformulate textual instructions into dense latent queries, injecting high-level semantic stability to constrain the degraded signals; (2) Pruning Output Distribution: We pioneer the integration of on-policy reinforcement learning directly into the diffusion restoration loop. By transforming human preferences into differentiable constraints, we explicitly penalize stochastic deviations, thereby sharpening the posterior distribution toward the desired high-fidelity outcomes. Extensive experiments demonstrate that Pref-Restore achieves state-of-the-art performance across synthetic and real-world benchmarks. Furthermore, empirical analysis confirms that our preference-aligned strategy significantly reduces solution entropy, establishing a robust pathway toward reliable and deterministic blind restoration. |
| title | Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.19506 |