Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos

Add to your list(s) Download to your calendar using vCal

• Hanxue Liang, University of Cambridge
• Thursday 06 February 2025, 14:00-15:00
• Webinar (via Zoom online) ID: 87457263100 Passcode: 708172.

If you have a question about this talk, please contact Yancheng Cai.

Hanxue Liang will present his recent work BulletTimer. BulletTimer is the first motion-aware feed-forward model for real-time dynamic scene reconstruction. It takes a monocular video as input and reconstructs a 3D Gaussian Splatting (3DGS) representation at any desired timestamp in a feed-forward manner within just 150 ms. This innovation opens doors for real-time interactive 3D/4D content in areas such as AR/VR, gaming, and virtual cinematography.

This talk is part of the Rainbow Group Seminars series.

This talk is included in these lists:

• Webinar (via Zoom online) ID: 87457263100 Passcode: 708172
• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Interested Talks
• Rainbow Group Seminars
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.