Habitus: Boosting Mobile Immersive Content Delivery through Full-body Pose Tracking and..
Talkat 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) · 2024-04-16..04-18·
summary
Habitus is a user-space framework that combines full-body pose tracking and multipath networking (omnidirectional + mmWave) to predict mmWave throughput and schedule streams; prediction uses offline models plus online transfer learning to adapt to location, user and environment changes. Prototype on commodity phones and edge servers integrates into Vivo with a few lines of code. Pose adds 5–29% lower prediction error (17% in one LSTM example) and the system yields up to 72% QoE improvement in emulation and user trials.
AI-written summary · about
chapters (9)
- 0:00Immersive content delivery challenges
- 1:21Millimeter wave radios limitations
- 3:08Millimeter wave streaming issues
- 4:13Habitus core design
- 4:56Predicting throughput with full-body pose
- 9:12Handling model changes
- 12:06Multi-path scheduling and integration
- 14:20Habitus benefits evaluation
- 15:45Summary
related talks
23mParallel Eyes: Exploring Human Capability and Behaviors with Paralleled First Person View Sharing
13mVisMimic: Integrating Motion Chain in Feedback Video Generation for Motor Coaching
21mAI Isn't Just Chat
17mTransforming access to healthcare through Web AI
23mExperimenting with Hardware and AI to Create Dynamic Live Streaming User Experiences
22madjust.me! - AI-Based Table Auto Positiong
17mTechnologies Enabling Real-Time Interaction With Digital-Humans
10mInteractML: Making machine learning accessible for creative practitioners working with movement ...