CVMar 14

RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting

arXiv:2603.1378362.8h-index: 5
AI Analysis

This addresses temporal retiming for applications like slow-motion playback and post-production, representing an incremental improvement over existing 4DGS methods.

The paper tackled the problem of temporal aliasing in 4D Gaussian Splatting, which causes ghosting artifacts when interpolating between timestamps, and proposed RetimeGS to achieve ghost-free, temporally coherent rendering with superior quality over state-of-the-art methods on datasets with fast motion and occlusions.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes