VROOM - Visual Reconstruction over Onboard Multiview
Yajat Yadav, Varun Bharadwaj, Jathin Korrapati, Tanish Baranwal

TL;DR
VROOM demonstrates the potential of onboard camera footage for 3D reconstruction of complex environments like Formula 1 circuits, addressing high-speed motion and dynamic challenges with a novel pipeline.
Contribution
This work introduces VROOM, a new system that reconstructs 3D models from onboard racecar videos, combining multiple methods and preprocessing techniques for improved accuracy.
Findings
Partial recovery of track and vehicle trajectories
Feasibility of onboard video for scalable 4D reconstruction
Effective handling of high-speed motion and camera cuts
Abstract
We introduce VROOM, a system for reconstructing 3D models of Formula 1 circuits using only onboard camera footage from racecars. Leveraging video data from the 2023 Monaco Grand Prix, we address video challenges such as high-speed motion and sharp cuts in camera frames. Our pipeline analyzes different methods such as DROID-SLAM, AnyCam, and Monst3r and combines preprocessing techniques such as different methods of masking, temporal chunking, and resolution scaling to account for dynamic motion and computational constraints. We show that Vroom is able to partially recover track and vehicle trajectories in complex environments. These findings indicate the feasibility of using onboard video for scalable 4D reconstruction in real-world settings. The project page can be found at https://varun-bharadwaj.github.io/vroom, and our code is available at https://github.com/yajatyadav/vroom.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
