Blind face restoration remains a persistent challenge due to the inherent ill-posedness of reconstructing holistic structures from severely constrained observations. Current generative paradigms, while capable of synthesizing realistic facial details, remain limited by the under-constrained nature of blind restoration, where severely degraded inputs can be mapped to plausible yet identity-inconsistent outputs. To address this issue, we present \textbf{Pref-Restore}, a hierarchical framework for BFR with reduced restoration uncertainty. Our design is organized around three complementary principles: (1) Semantic Information Augmentation, where an auto-regressive semantic branch converts image and text cues into structured tokens that provide a stable high-level anchor; (2) Texture-level Fidelity Alignment, where the diffusion generator is trained under this anchor to recover identity-relevant details; and (3) Fidelity-constrained Preference Optimization, where a face-aware reward refines the diffusion trajectory while controlling the quality--fidelity trade-off. Extensive experiments on synthetic and real-world benchmarks show that Pref-Restore achieves state-of-the-art performance, with stronger identity-sensitive fidelity and lower restoration uncertainty across repeated sampling. Systematic ablations further attribute these gains to the proposed hierarchical design, showing the necessity of staged training, the robustness and quality dependence of the text pathway, and the benefit of fidelity-constrained preference optimization.

翻译：盲人脸恢复因从严重受限观测中重建整体结构的内在病态性而持续面临挑战。当前生成范式虽能合成逼真面部细节，却仍受限于盲恢复的欠约束特性——严重退化输入可能映射到合理但身份不一致的输出。为应对此问题，我们提出 \textbf{Pref-Restore}——一种降低恢复不确定性的层级式盲人脸恢复框架。该设计围绕三项互补原则构建：(1) 语义信息增强：自回归语义分支将图像与文本线索转换为结构化标记，提供稳定的高层级锚点；(2) 纹理级保真对齐：扩散生成器在该锚点引导下进行训练，恢复身份相关细节；(3) 保真约束偏好优化：面部感知奖励机制在控制质量-保真度权衡的同时优化扩散轨迹。在合成与真实场景基准上的大量实验表明，Pref-Restore 达到了最先进性能，在重复采样中展现出更强的身份敏感保真度与更低的重建不确定性。系统性消融实验进一步将性能提升归因于所提出的层级设计，验证了分阶段训练的必要性、文本路径的鲁棒性与质量依赖性，以及保真约束偏好优化的增益效果。