DynSUP: Dynamic Gaussian Splatting From an Unposed Image Pair
MCML Authors
Benjamin Busam
Prof. Dr.
Core PI
Daniel Cremers
Prof. Dr.
Director
Abstract
Benjamin Busam
Prof. Dr.
Core PI
Daniel Cremers
Prof. Dr.
Director
Abstract
Recent advances in 3D Gaussian Splatting have shown promising results. Existing methods typically assume static scenes and/or multiple images with prior poses. Dynamics, sparse views, and unknown poses significantly increase the problem complexity due to insufficient geometric constraints. To overcome this challenge, we propose a method that can use only two images without prior poses to fit Gaussians in dynamic environments. To achieve this, we introduce two technical contributions. First, we propose an object-level two-view bundle adjustment. This strategy decomposes dynamic scenes into piece-wise rigid components, and jointly estimates the relative camera motion and dynamic object motions for dynamic Gaussian initialization. Second, we design an SE(3) field-driven Gaussian training method. It enables fine-grained motion modeling through learnable per-Gaussian transformations. Our method leads to high-fidelity novel view synthesis of dynamic scenes while accurately preserving temporal consistency and object motion. Experiments on both synthetic and real-world datasets demonstrate that our method significantly outperforms state-of-the-art approaches designed for the cases of static environments, multiple images, and/or known poses.
article LCQ+26
IEEE Transactions on Image Processing
35. Jun. 2026.
Authors
W. Li • W. Chen • S. Qian • B. Busam • D. Cremers • H. LiLinks
DOI GitHubResearch Area
BibTeXKey: LCQ+26