articleMar 18, 2024Closed access

Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis

Carnegie Mellon University · RWTH Aachen University · +1 more institution

Indexed incrossref

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

344
total citations
FWCI
76.44
Percentile
100%
References
49
Citations per year

Authors

4

Topics & keywords

Keywords
  • Computer science
  • Rendering (computer graphics)
  • Computer vision
  • Artificial intelligence
  • View synthesis
  • Rotation (mathematics)
  • Computer graphics (images)
  • Mixture model
UN Sustainable Development Goals
  • Climate action
No related works found for this paper.

Funding