AI Navigate

RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting

arXiv cs.CV / 3/17/2026

📰 NewsIdeas & Deep AnalysisModels & Research

Key Points

  • RetimeGS introduces a continuous-time 4D Gaussian Splatting representation that reduces temporal aliasing and ghosting when rendering frames at arbitrary timestamps.
  • The approach explicitly defines the temporal behavior of the 3D Gaussians and uses optical-flow-guided initialization and supervision, plus triple-rendering supervision, to achieve smooth, temporally coherent results under large motions.
  • It addresses overfitting at discrete frame indices common in prior 4DGS methods and demonstrates superior quality on datasets with fast motion, non-rigid deformation, and occlusions.
  • Experiments show ghost-free rendering and better temporal coherence compared with state-of-the-art methods.

Abstract

Temporal retiming, the ability to reconstruct and render dynamic scenes at arbitrary timestamps, is crucial for applications such as slow-motion playback, temporal editing, and post-production. However, most existing 4D Gaussian Splatting (4DGS) methods overfit at discrete frame indices but struggle to represent continuous-time frames, leading to ghosting artifacts when interpolating between timestamps. We identify this limitation as a form of temporal aliasing and propose RetimeGS, a simple yet effective 4DGS representation that explicitly defines the temporal behavior of the 3D Gaussian and mitigates temporal aliasing. To achieve smooth and consistent interpolation, we incorporate optical flow-guided initialization and supervision, triple-rendering supervision, and other targeted strategies. Together, these components enable ghost-free, temporally coherent rendering even under large motions. Experiments on datasets featuring fast motion, non-rigid deformation, and severe occlusions demonstrate that RetimeGS achieves superior quality and coherence over state-of-the-art methods.