GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network
This work addresses human pose estimation for applications like portable electronics and mobile robots where low latency and energy efficiency are critical, representing a novel approach in this domain.
The authors tackled human pose estimation using event-based cameras by proposing GraphEnet, a graph neural network that leverages sparse event data with an intermediate line-based representation, achieving high-frequency 2D pose estimation for a single person.
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. The code is open-source at https://github.com/event-driven-robotics/GraphEnet-NeVi-ICCV2025.