Skip to main content
GameDev.net gamedev.net

Vision Transformer News

The latest Vision Transformer coverage curated for game developers.

Estimating Accurate Hand Pose in Camera Space with Vision Transformer

arXiv cs.GR details a Vision Transformer hand-pose method that estimates wrist position in camera space from a single RGB image. The approach tackles depth ambiguity and pose/wrist coupling, and it …

Research arXiv cs.GR · 2 days, 13 hours ago
Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors

A CVPR 2026 paper tackles a practical depth problem for VR, robotics, and 3D perception: turning sparse direct time-of-flight readings into dense metric depth. The system uses a dual-branch Vision …

Research arXiv cs.GR · 1 month, 2 weeks ago