Learning Geometric Invariance for Gait Recognition

2026-01-09

arXiv.org

AI Summary

This work addresses the challenge of extracting identity-discriminative features in gait recognition under varying conditions such as cross-view and cross-clothing scenarios. To this end, it proposes RRS-Gait, the first framework to explicitly model the geometric relationships among diverse gait conditions. The method leverages tunable convolutional kernels to achieve equivariance to reflection, rotation, and scaling transformations, and integrates global pooling to construct geometrically invariant representations, thereby ensuring identity invariance. Extensive experiments on four large-scale benchmarks—Gait3D, GREW, CCPG, and SUSTech1K—demonstrate that RRS-Gait significantly improves cross-condition recognition accuracy, confirming its robustness and effectiveness.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The goal of gait recognition is to extract identity-invariant features of an individual under various gait conditions, e.g., cross-view and cross-clothing. Most gait models strive to implicitly learn the common traits across different gait conditions in a data-driven manner to pull different gait conditions closer for recognition. However, relatively few studies have explicitly explored the inherent relations between different gait conditions. For this purpose, we attempt to establish connections among different gait conditions and propose a new perspective to achieve gait recognition: variations in different gait conditions can be approximately viewed as a combination of geometric transformations. In this case, all we need is to determine the types of geometric transformations and achieve geometric invariance, then identity invariance naturally follows. As an initial attempt, we explore three common geometric transformations (i.e., Reflect, Rotate, and Scale) and design a $\mathcal{R}$eflect-$\mathcal{R}$otate-$\mathcal{S}$cale invariance learning framework, named ${\mathcal{RRS}}$-Gait. Specifically, it first flexibly adjusts the convolution kernel based on the specific geometric transformations to achieve approximate feature equivariance. Then these three equivariant-aware features are respectively fed into a global pooling operation for final invariance-aware learning. Extensive experiments on four popular gait datasets (Gait3D, GREW, CCPG, SUSTech1K) show superior performance across various gait conditions.

Problem

• gait recognition
• geometric invariance
• identity-invariant features
• cross-view
• cross-clothing

Innovation

• geometric invariance
• gait recognition
• equivariant convolution
• reflect-rotate-scale transformation
• identity-invariant features