GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network

Human Pose Estimation is a crucial module in human-machine interaction applications and, especially since the rise in deep learning technology, robust methods are available to consumers using RGB cameras and commercial GPUs. On the other hand, event-based cameras have gained popularity in the vision research community for their low latency and low energy advantages that make them ideal for applications where those resources are constrained like portable electronics and mobile robots. In this work we propose a Graph Neural Network, GraphEnet, that leverages the sparse nature of event camera output, with an intermediate line based event representation, to estimate 2D Human Pose of a single person at a high frequency. The architecture incorporates a novel offset vector learning paradigm with confidence based pooling to estimate the human pose. This is the first work that applies Graph Neural Networks to event data for Human Pose Estimation. Code is available here: https://github.com/event-driven-robotics/GraphEnet-NeVi-ICCV2025 @article{goyalGraphEnet2025, title={GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network}, author={Goyal, Gaurvi and Thuong, Pham Cong and Glover, Arren and Mizuno, Masayoshi and Bartolozzi, Chiara}, journal={2nd Workshop on Neuromorphic Vision: Advantages and Applications of Event Cameras, in conjunction with the International Conference on Computer Vision}, year={2025} }