TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction
Dynamic scene reconstruction is a long-term challenge in 3D vision. Recent methods extend 3D Gaussian Splatting to dynamic scenes via additional deformation fields and apply explicit constraints like motion flow to guide the deformation. However, they learn motion changes from individual timestamps...
Gespeichert in:
Hauptverfasser: | , , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Dynamic scene reconstruction is a long-term challenge in 3D vision. Recent
methods extend 3D Gaussian Splatting to dynamic scenes via additional
deformation fields and apply explicit constraints like motion flow to guide the
deformation. However, they learn motion changes from individual timestamps
independently, making it challenging to reconstruct complex scenes,
particularly when dealing with violent movement, extreme-shaped geometries, or
reflective surfaces. To address the above issue, we design a plug-and-play
module called TimeFormer to enable existing deformable 3D Gaussians
reconstruction methods with the ability to implicitly model motion patterns
from a learning perspective. Specifically, TimeFormer includes a Cross-Temporal
Transformer Encoder, which adaptively learns the temporal relationships of
deformable 3D Gaussians. Furthermore, we propose a two-stream optimization
strategy that transfers the motion knowledge learned from TimeFormer to the
base stream during the training phase. This allows us to remove TimeFormer
during inference, thereby preserving the original rendering speed. Extensive
experiments in the multi-view and monocular dynamic scenes validate qualitative
and quantitative improvement brought by TimeFormer. Project Page:
https://patrickddj.github.io/TimeFormer/ |
---|---|
DOI: | 10.48550/arxiv.2411.11941 |