cs.CVNov 3, 2026

On the Learnability of Footwear Robustness: Footstep Recognition Under Unseen Conditions

Authors: Robyn Larracy, Erik Scheme

Organizations: Movement and Biosignals Intelligence Lab (MoBIL), University of New Brunswick, Fredericton, NB, Canada

Abstract

Footstep patterns, captured using pressure or force-sensitive walkways during natural walking, offer a convenient and passive approach to biometric recognition. However, footwear variability poses a major challenge to practical deployment, as it impacts both the foot-sensor interface and the user's underlying gait mechanics. This study considers the particularly difficult scenario where users enroll under one fixed footwear condition but must later be recognized in arbitrary, unseen footwear. Using the StepUP-P150 dataset, we show that footwear-induced shift, while substantial and heterogeneous across individuals, contains shared structure that can be learned from a training population and transferred, zero-shot, to previously unseen users and footwear styles. We do this using BiStepNet, a novel architecture that decomposes spatial and temporal identity cues into independently trainable streams and outperforms compact 3D spatiotemporal baselines for cross-footwear recognition. We demonstrate that cross-footwear recognition performance scales systematically with the volume and diversity of footwear representation in the training set, with gains transferring to footwear styles not directly observed during training. Moreover, we show that auxiliary gait datasets with only partial modality overlap (incorporated through the architecture's decomposed design) can be leveraged to further improve robustness to unseen footwear conditions.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jul 15, 2026

The 2nd International StepUP Competition for Biometric Footstep Recognition: From Steps to Strides

The International StepUP Competition Series was launched to advance research in pressure-based footstep biometrics through a standardized and challenging evaluation framework. Using the large-scale StepUP-P150 dataset (with more than 200,000 high-resolution dynamic footsteps from 150 individuals) and a previously unreleased test set, the 2nd edition of the competition addressed three key challenges: (1) generalization to unseen users with limited enrollment data, (2) robustness to domain shift caused by variations in footwear and walking speed and (3) effective fusion of paired left-right footsteps. While the first two challenges built on the inaugural competition, this edition introduced more extreme cross-domain conditions and moved beyond isolated footsteps to stride-level verification, enabling new opportunities for representation learning and inter-step information fusion. The competition attracted 26 registrants from academia and industry, with a best equal error rate of 8.00% achieved by the ArogyaPandit Research Team using a spatiotemporal CNN combined with an ensemble-based scoring strategy. The top solutions showcase the value of harnessing temporal patterns and of incorporating inference-time normalization and calibration strategies to improve scoring. However, the results also reveal that recognizing users in unseen personal footwear remains a challenge, especially in the presence of distractors with similar characteristics.
Oct 31, 2026

Now You See Them, Now You Dont FusionGhost Gait for Occlusion-Robust Gait Recognition with ArabGait dataset

Skeleton-based gait recognition is generally more robust to appearance changes than pixel-based methods, but this robustness depends on stable pose extraction. Clothing variation in gait recognition includes changes in garments, silhouette, and carried items; under Gulf clothing (Kandoora/Abaya), the dominant failure mode shifts from appearance change to lower-limb pose degradation caused by severe occlusion. To study this regime, we introduce ArabGait, a 45-subject indoor multi-view dataset with four walking conditions across three viewpoints, and show that Gulf clothing lowers mean lower-limb confidence from 0.811 to 0.683 and raises lower-limb failure rate from 7.98% to 17.82%, with ankles most affected. We propose FusionGhost-Gait, a fused spatiotemporal architecture that integrates spatial graph blocks and temporal modeling in one residual unit, removes redundant channel projections, and uses compact temporal Ghost kernels as a lightweight regularization mechanism for pose-noisy trajectories while preserving efficient temporal downsampling. On ArabGait cross-clothing evaluation, including Protocol A and Protocol B, FusionGhost-Gait reaches up to 67.91% Rank-1 while remaining compact (108,970- 133,674 parameters and 0.035-0.052 billion floating-point operations (GFLOPs)), achieving more than 65% fewer parameters and 75% lower FLOPs than existing baselines. These results indicate that the proposed model generalizes effectively to challenging Gulf-clothing conditions while remaining lightweight and deployable for surveillance and access-control biometric systems.
Apr 17, 2026

MMGait: Towards Multi-Modal Gait Recognition

Gait recognition has emerged as a powerful biometric technique for identifying individuals at a distance without requiring user cooperation. Most existing methods focus primarily on RGB-derived modalities, which fall short in real-world scenarios requiring multi-modal collaboration and cross-modal retrieval. To overcome these challenges, we present MMGait, a comprehensive multi-modal gait benchmark integrating data from five heterogeneous sensors, including an RGB camera, a depth camera, an infrared camera, a LiDAR scanner, and a 4D Radar system. MMGait contains twelve modalities and 334,060 sequences from 725 subjects, enabling systematic exploration across geometric, photometric, and motion domains. Based on MMGait, we conduct extensive evaluations on single-modal, cross-modal, and multi-modal paradigms to analyze modality robustness and complementarity. Furthermore, we introduce a new task, Omni Multi-Modal Gait Recognition, which aims to unify the above three gait recognition paradigms within a single model. We also propose a simple yet powerful baseline, OmniGait, which learns a shared embedding space across diverse modalities and achieves promising recognition performance. The MMGait benchmark, codebase, and pretrained checkpoints are publicly available at https://github.com/BNU-IVC/MMGait.