Divide-and-Conquer: Dual-Hierarchical Optimization for Semantic 4D Gaussian Spatting
This work addresses dynamic scene reconstruction for applications like robotics or AR/VR, but it appears incremental as it builds on Gaussian Splatting with specific optimizations.
The paper tackles the problem of dynamic scene understanding using Semantic 4D Gaussians by proposing Dual-Hierarchical Optimization to address artifacts and noise from static methods, achieving consistent outperformance over baselines on synthetic and real-world datasets.
Semantic 4D Gaussians can be used for reconstructing and understanding dynamic scenes, with temporal variations than static scenes. Directly applying static methods to understand dynamic scenes will fail to capture the temporal features. Few works focus on dynamic scene understanding based on Gaussian Splatting, since once the same update strategy is employed for both dynamic and static parts, regardless of the distinction and interaction between Gaussians, significant artifacts and noise appear. We propose Dual-Hierarchical Optimization (DHO), which consists of Hierarchical Gaussian Flow and Hierarchical Gaussian Guidance in a divide-and-conquer manner. The former implements effective division of static and dynamic rendering and features. The latter helps to mitigate the issue of dynamic foreground rendering distortion in textured complex scenes. Extensive experiments show that our method consistently outperforms the baselines on both synthetic and real-world datasets, and supports various downstream tasks. Project Page: https://sweety-yan.github.io/DHO.