Seeing Machines Unveils Real-Time 3D Human Understanding for Physical AI

CANBERRA, Australia, Sept. 30, 2026 /CourierPR/ -- Seeing Machines, a 25-year-old Australian technology company that has long been at the forefront of human-sensing solutions, has made a significant breakthrough in the field of Physical AI. The company has published a technical paper detailing a new technology that allows robots and other Physical AI systems to achieve real-time 3D human understanding directly on embedded hardware. This advancement is set to revolutionize the way machines interact with people in dynamic environments.

The paper, which was launched in August 2026, introduces Seeing Machines’ Human Mesh Recovery (HMR) technology. This core capability of the company’s Human-Centred Physical AI Platform is designed to enable robots to understand a person’s position, posture, and movement in real time. HMR reconstructs a detailed 3D representation of a person using a single camera view, making it possible for machines to respond safely and effectively as interactions unfold.

Until now, high-fidelity 3D human reconstruction has typically required significant computing resources, making real-time deployment on embedded devices challenging. Seeing Machines’ HMR technology addresses this constraint by delivering detailed 3D human understanding at the edge. This means that robots can respond to a person’s position and movement in real time without relying on a remote cloud connection. The technology is particularly relevant for environments where robots and people need to work safely and effectively together, such as factories, hospitals, warehouses, and other dynamic settings.

The paper demonstrates the compelling balance of accuracy, inference speed, and model efficiency that HMR offers when deployed on the NVIDIA Jetson Thor hardware. The results show that high-fidelity 3D human reconstruction can be performed in real time on embedded hardware that was previously considered unsuitable for this level of scene understanding. This breakthrough is significant because it brings detailed 3D human understanding into real-world environments, where machines need to interpret people and their surroundings in three dimensions.

Paul McGlone, CEO of Seeing Machines, emphasized the importance of this technology in ensuring safe and effective human-machine interaction.

The HMR model supports both standard RGB cameras and RGB-D cameras without increasing its parameter count. This flexibility makes it adaptable to a wide range of applications and environments. Seeing Machines’ Human-Centred Physical AI Platform combines the company’s expertise in computer vision, human behavior, and safety-critical AI to enable machines to interpret people and their environments in three dimensions. The platform builds on the company’s extensive experience in developing and deploying Human-Centred AI solutions across various industries, including automotive, commercial fleet, aviation, rail, and off-road applications.

This advancement in 3D human understanding is expected to have far-reaching implications for industries that rely on human-machine interaction. By enabling real-time, accurate, and efficient 3D human understanding, Seeing Machines is paving the way for safer and more natural interactions in dynamic environments. The company’s 25 years of experience in human-sensing technology and its commitment to advancing Physical AI are likely to position it as a leader in this rapidly evolving field.