Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation

TL;DR

This paper introduces a novel point cloud-based framework for human pose estimation using event cameras, leveraging spatiotemporal properties to improve accuracy and efficiency without dense frame conversion.

Contribution

It proposes new modules for structured temporal modeling and an edge-enhanced representation, advancing event-driven pose estimation performance and computational efficiency.

Findings

Achieved an average MPJPE reduction of 4% across multiple backbones.

Consistently improved pose estimation accuracy on the DHP19 dataset.

Enhanced spatial edge information under sparse event conditions.

Abstract

Human pose estimation focuses on predicting body keypoints to analyze human motion. Currently, most pose estimation tasks rely on conventional RGB cameras. In contrast, event cameras provide high temporal resolution and low latency, enabling robust estimation under challenging conditions and opening up new possibilities for pose estimation. However, most existing methods convert event streams into dense event frames, which adds extra computation and sacrifices the high temporal resolution of the event signal. In this work, we aim to exploit the spatiotemporal properties of event streams based on point cloud-based framework, designed to enhance human pose estimation performance while maintaining computational efficiency. We design Event Temporal Slicing Convolution module to capture short-term dependencies across event slices, and combine it with Event Slice Sequencing module for structured temporal modeling. We further propose an edge-enhanced point cloud-based event representation to enhance spatial edge information under sparse event conditions to further improve performance. Experiments on the DHP19 dataset show our proposed method consistently improves performance across three representative point cloud backbones: PointNet, DGCNN, and Point Transformer, with an average MPJPE reduction of 4%.