FlowPalm: Optical Flow Driven Non-Rigid Deformation for Geometrically Diverse Palmprint Generation

2026-04-10

AI Summary

Existing palmprint generation methods struggle to model the complex non-rigid geometric deformations present in real-world palmprints, resulting in limited diversity of synthetic data. This work proposes FlowPalm, a novel framework that introduces optical flow–driven non-rigid deformation modeling into palmprint synthesis for the first time. By estimating optical flow between real palmprint pairs to capture statistical patterns of geometric deformation, and integrating a progressive sampling strategy within the diffusion process, FlowPalm jointly models style and geometric diversity while preserving identity consistency. Experimental results demonstrate that FlowPalm significantly outperforms existing methods across six benchmark datasets and effectively enhances downstream palmprint recognition performance.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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/

Problem

• palmprint generation
• geometric variation
• non-rigid deformation
• optical flow
• synthetic data

Innovation

• optical flow
• non-rigid deformation
• palmprint generation
• geometric diversity
• diffusion model