Meta’s conference is planned in next 2 weeks and their researchers made this prototype to demonstrate new Quest 2 body tracking, (without any extra trackers) using AI – but there’s a catch.!!
Check out in this Research paper released to discover for more. https://1drv.ms/b/s!Aqg5fQ0Oec4tg8oD2HRXFWv_9M2RSA
It’s a neural network driven system which can estimate a plausible full body pose with just the tracking data from Quest 2 and its controllers. No extra trackers or external sensors are needed but overall it is a cool research.
My observations :
- System’s latency is also 160ms – more than 11 frames at 72Hz. This kind of system will probably require high GPU configuration like NVIDIA 10 rtx 3090.
- Good for current IK player bodies, Still good for remote player avatars, though in fast paced games the latency might still be a problem.
- As per paper, position of your elbows, torso, and legs can be estimated using a class of algorithms called inverse kinematics (IK), but this is only accurate sometimes for elbows and rarely correct for legs.
- Meta keeps on in the VR sector, imagine consumer VR in 20 years. They’re doing most of the heavy lifting research and development-wise compared to any other metaverse player. In marketplace.