GaitFace: A Multimodal Dataset for Long-Range Person Identification

2026-07-26

AI Summary

This study addresses the significant performance degradation of existing biometric recognition systems under real-world border surveillance conditions—such as long distances, low resolution, and high俯视角 (high pitch angles)—and the absence of realistic multimodal benchmark datasets. To bridge this gap, the authors introduce GaitFace, the first long-range, multi-view, multi-camera dataset that jointly captures facial and gait modalities, employing a “mobile pre-enrollment followed by unconstrained, multi-angle, long-distance capture” paradigm to simulate realistic border-crossing scenarios. Benchmark evaluations on GaitFace reveal that current state-of-the-art models exhibit marked vulnerability under unassisted optical conditions, thereby underscoring the dataset’s critical role in advancing research on unconstrained, long-range biometric recognition.

Abstract

Efficient border control is becoming a significant global challenge, mainly due to severe congestion and extended passenger waiting times. To mitigate these bottlenecks and facilitate passenger flow, biometric technologies are increasingly deployed to streamline identity verification and enhance crossing efficiency. Technical limitations frequently impede biometric identification, particularly in long-range surveillance, where systems must deal with adverse atmospheric conditions and degraded image quality. While high-quality frameworks like BRIAR exist, they are frequently restricted to specific government agencies. This paper introduces GaitFace, a new public dataset that contains face and gait data captured at long distances. To ensure that the research reflects authentic border scenarios, we use Pre-Enrollment data, where a traveler registers via a mobile device, and "In-the-Wild" captures, which records individuals at a distance across multiple viewing angles and different cameras. Benchmarking SOTA face and gait models reveals that current architectures fail under low-resolution and elevated viewpoints despite success with optical assistance. GaitFace exposes these critical vulnerabilities, providing a rigorous public benchmark to drive more robust, unconstrained biometric research.

Problem

• long-range person identification
• biometric recognition
• gait recognition
• face recognition
• low-resolution imaging

Innovation

• multimodal biometrics
• long-range identification
• gait recognition
• face recognition
• public dataset