FlowPalm：光流驱动的非刚性形变用于几何多样化的掌纹生成
FlowPalm: Optical Flow Driven Non-Rigid Deformation for Geometrically Diverse Palmprint Generation
利用光流估计真实掌纹对之间的非刚性形变统计先验，并在扩散采样过程中渐进引入几何形变，为生成具有几何多样性的合成数据提供了可复用的技术思路，可迁移到其他需要模拟形变的生物特征生成任务。
原文依据 FlowPalm estimates optical flows between real palmprint pairs to capture the statistical patterns of geometric deformations.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近年来，合成掌纹越来越多地被用作真实数据的替代品来训练识别模型。为了有效，此类合成数据必须反映真实掌纹的多样性，包括风格变化和几何变化。然而，现有的掌纹生成方法主要关注风格转换，而几何变化要么被忽略，要么通过简单的手工增强来近似。在本工作中，我们提出了FlowPalm，一个光流驱动的掌纹生成框架，能够模拟在真实手掌中观察到的复杂非刚性形变。具体来说，FlowPalm估计真实掌纹对之间的光流，以捕捉几何形变的统计模式。基于这些先验，我们设计了一个渐进式采样过程，在扩散过程中逐渐引入几何形变，同时保持身份一致性。在六个基准数据集上的大量实验表明，FlowPalm在下游识别任务中显著优于最优的掌纹生成方法。项目页面：https://yuchenzou.github.io/FlowPalm/
英文原文摘要 1155 字符
Recently, synthetic palmprints have been increasingly used as substitutes for real data to train recognition models. To be effective, such synthetic data must reflect the diversity of real palmprints, including both style variation and geometric variation. However, existing palmprint generation methods mainly focus on style translation, while geometric variation is either ignored or approximated by simple handcrafted augmentations. In this work, we propose FlowPalm, an optical-flow-driven palmprint generation framework capable of simulating the complex non-rigid deformations observed in real palms. Specifically, FlowPalm estimates optical flows between real palmprint pairs to capture the statistical patterns of geometric deformations. Building on these priors, we design a progressive sampling process that gradually introduces the geometric deformations during diffusion while maintaining identity consistency. Extensive experiments on six benchmark datasets demonstrate that FlowPalm significantly outperforms state-of-the-art palmprint generation approaches in downstream recognition tasks. Project page: https://yuchenzou.github.io/FlowPalm/