LogInThe method uses a VR headset and takes the surroundings into account.
Researchers from Meta's Reality Labs and Seoul National University have presented QuestEnvSim – a motion tracking method that takes the surrounding environment into account.
"Using Reinforcement Learning, we show that headset and controller pose, if combined with physics simulation and environment observations can generate realistic full-body poses even in highly constrained environments."
This method allows achieving high-quality interaction motions without artifacts such as penetration or contact sliding. In their paper, the researchers discuss the environment representation, the contact reward, and scene randomization – the features important to the performance of the method.
QuestEnvSim allows tracking motion reliably when a person sits, steps over obstacles, and interacts with other objects.
Read more about it here and don't forget to join our 80 Level Talent platform and our Telegram channel, follow us on Instagram and Twitter, where we share breakdowns, the latest news, awesome artworks, and more.