Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis
Carnegie Mellon University · RWTH Aachen University · +1 more institution
Abstract
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work that models scenes as a collection of 3D Gaussians which are optimized to reconstruct input images via differentiable rendering. To model dynamic scenes, we allow Gaussians to move and rotate over time while enforcing that they have persistent color, opacity, and size. By regularizing Gaussians’ motion and rotation with local-rigidity constraints, we show that our Dynamic 3D Gaussians correctly model the same area of physical space over time, including the rotation of that…
Citation impact
- FWCI
- 76.44
- Percentile
- 100%
- References
- 49
Authors
4Topics & keywords
- Computer science
- Rendering (computer graphics)
- Computer vision
- Artificial intelligence
- View synthesis
- Rotation (mathematics)
- Computer graphics (images)
- Mixture model
- Climate action