NVIDIA | Taking Autonomous Vehicle Occupancy Prediction into the Third Dimension - NVIDIA DRIVE Labs Ep. 30 @NVIDIA | Uploaded 1 year ago | Updated 1 day ago
Humans naturally perceive the 3D geometry of objects and scenes in order to make decisions. Likewise, in the world of #autonomousdriving, the concept of “3D occupancy prediction” is critical to the development of safe and robust self-driving systems. In this episode of #DRIVELabs, we go beyond the traditional bird’s eye view approach and showcase NVIDIA’s 3D perception technology, which recently won the 3D Occupancy Prediction Challenge at CVPR 2023.

Timestamps:
00:00:00 - 3D occupancy prediction is a critical piece of the perception stack
00:01:00 - VoxFormer: camera based solution for 3D occupancy prediction
00:01:27 - FB-OCC uses multiple cameras as input
00:02:20 - CVPR 2023 Leaderboard (winner out of 400 entries)
00:03:09 - How do transformer models exploit different hardware engines?
00:03:33 - To learn more, visit our project pages and blog

Read the blog: nvda.ws/3qJSKPg
Watch the full series here: nvda.ws/3lHQP7H
Learn more about DRIVE Labs: nvda.ws/36r5c6t
Follow us on social:
Twitter: nvda.ws/3LRdkSs
LinkedIn: nvda.ws/3wI4kue