Locally Adaptive Decay Surfaces for High-Speed Face and Landmark Detection with Event Cameras

2026-02-26

AI Summary

This work addresses the challenge that event cameras produce sparse, asynchronous outputs, making it difficult for conventional time-surface representations with fixed global parameters to simultaneously preserve static structures and maintain edge sharpness under high-speed motion. To overcome this limitation, the paper proposes the Local Adaptive Decay Surface (LADS), which introduces, for the first time, a locally adaptive temporal decay mechanism guided by dynamic scene content. LADS dynamically adjusts per-pixel decay parameters based on three complementary cues: local event rate, Laplacian-of-Gaussian response, and high-frequency spectral energy. Coupled with a lightweight neural network, the method enables real-time processing. Experiments demonstrate consistent superiority over baseline approaches at both 30 Hz and 240 Hz frame rates, achieving a face detection mAP50 of 0.966 and a normalized mean error of only 2.44% for keypoint localization at 240 Hz.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Local Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Event cameras record luminance changes with microsecond resolution, but converting their sparse, asynchronous output into dense tensors that neural networks can exploit remains a core challenge. Conventional histograms or globally-decayed time-surface representations apply fixed temporal parameters across the entire image plane, which in practice creates a trade-off between preserving spatial structure during still periods and retaining sharp edges during rapid motion. We introduce Locally Adaptive Decay Surfaces (LADS), a family of event representations in which the temporal decay at each location is modulated according to local signal dynamics. Three strategies are explored, based on event rate, Laplacian-of-Gaussian response, and high-frequency spectral energy. These adaptive schemes preserve detail in quiescent regions while reducing blur in regions of dense activity. Extensive experiments on the public data show that LADS consistently improves both face detection and facial landmark accuracy compared to standard non-adaptive representations. At 30 Hz, LADS achieves higher detection accuracy and lower landmark error than either baseline, and at 240 Hz it mitigates the accuracy decline typically observed at higher frequencies, sustaining 2.44 % normalized mean error for landmarks and 0.966 mAP50 in face detection. These high-frequency results even surpass the accuracy reported in prior works operating at 30 Hz, setting new benchmarks for event-based face analysis. Moreover, by preserving spatial structure at the representation stage, LADS supports the use of much lighter network architectures while still retaining real-time performance. These results highlight the importance of context-aware temporal integration for neuromorphic vision and point toward real-time, high-frequency human-computer interaction systems that exploit the unique advantages of event cameras.

Problem

• event cameras
• face detection
• facial landmark detection
• temporal representation
• spatio-temporal integration

Innovation

• Locally Adaptive Decay Surfaces
• event cameras
• adaptive temporal integration
• face detection
• facial landmark localization