GeoMAR：释放几何对齐特征用于掩码自回归盲人脸复原
GeoMAR: Unleashing Geometrically Aligned Features for Masked Autoregressive Blind Face Restoration
浏览论文内容
中文总结 AI 辅助
GeoMAR框架通过双输入提取流水线与KV-Q交换策略生成几何对齐特征，结合多步骤掩码自回归细化，在合成与真实基准上实现了鲁棒的盲人脸复原。
中文摘要 AI 辅助
基于码本的盲人脸复原（BFR）在严重退化场景下常面临条件特征模糊、预测机制脆弱的问题。为应对这些挑战，本文提出GeoMAR框架，旨在结合掩码自回归（MAR）细化过程释放几何对齐特征，实现鲁棒人脸复原。在特征条件化方面，引入双输入提取流水线，提取带有明确、空间忠实锚点的组件级几何描述，通过对齐几何先验注入器将这些文本先验与低质量（LQ）特征融合，该注入器采用KV-Q交换策略生成几何对齐特征。在预测机制方面，将单步映射重新表述为多步骤MAR过程，这种从粗到细的生成方式基于日益可靠的上下文逐步细化复杂人脸区域。在1个合成基准和3个真实世界基准上的实验表明，与现有方法相比，GeoMAR能实现极具竞争力的感知质量与连贯视觉结构，代码可在指定URL获取。
英文摘要
Codebook-based blind face restoration (BFR) often suffers from ambiguous conditioning features and a fragile prediction mechanism under severe degradation. To address these challenges, we propose GeoMAR, a framework designed to unleash geometrically aligned features with masked autoregressive (MAR) refinement for robust face restoration. For feature conditioning, we introduce a dual-input extraction pipeline to extract component-based geometric descriptions with explicit, spatially faithful anchors. These textual priors are integrated with low-quality (LQ) features via an Aligned Geometric Priors Injector, which employs a KV-Q exchange strategy to generate geometrically aligned features. For prediction mechanism, we reformulate the one-step mapping into a multi-step MAR process. This coarse-to-fine generation progressively refines complex facial regions based on increasingly reliable context. Experiments on one synthetic and three real-world benchmarks demonstrate that GeoMAR achieves highly competitive perceptual quality and coherent visual structures compared with existing methods. The code is available at https://github.com/BRL-SYSU/GeoMAR.git.
