SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition
Reconstructing dynamic 3D scenes from monocular video remains fundamentally challenging due to the need to jointly infer motion, structure, and appearance from limited observations. Existing dynamic scene reconstruction methods based on Gaussian Splatting often entangle static and dynamic elements in a shared representation, leading to motion leakage, geometric distortions, and temporal flickering. We identify that the root cause lies in the coupled modeling of geometry and appearance across time, which hampers both stability and interpretability. To address this, we propose \textbf{SplitGaussian}, a novel framework that explicitly decomposes scene representations into static and dynamic components. By decoupling motion modeling from background geometry and allowing only the dynamic branch to deform over time, our method prevents motion artifacts in static regions while supporting view- and time-dependent appearance refinement. This disentangled design not only enhances temporal consistency and reconstruction fidelity but also accelerates convergence. Extensive experiments demonstrate that SplitGaussian outperforms prior state-of-the-art methods in rendering quality, geometric stability, and motion separation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting
Novel view synthesis is a task of generating scenes from unseen perspectives; however, synthesizing dynamic scenes from blurry monocular videos remains an unresolved challenge that has yet to be effectively addressed. Ex…
3D geometryNovel View SynthesisDynamicFusion: Reconstruction and Tracking of Non-Rigid Scenes in Real-Time
We present the first dense SLAM system capable of reconstructing non-rigidly deforming scenes in real-time, by fusing together RGBD scans captured from commodity sensors. Our DynamicFusion approach reconstructs scene geo…
Dynamic Multi-View Scene Reconstruction Using Neural Implicit Surface
Reconstructing general dynamic scenes is important for many computer vision and graphics applications. Recent works represent the dynamic scene with neural radiance fields for photorealistic view synthesis, while their s…
Novel View SynthesisSurface ReconstructionAdaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction
3D Gaussian Splatting has recently achieved notable success in novel view synthesis for dynamic scenes and geometry reconstruction in static scenes. Building on these advancements, early methods have been developed for d…
Dynamic ReconstructionNovel View SynthesisSurface ReconstructionFlow3r: Factored Flow Prediction for Scalable Visual Geometry Learning
Current feed-forward 3D/4D reconstruction systems rely on dense geometry and pose supervision -- expensive to obtain at scale and particularly scarce for dynamic real-world scenes. We present Flow3r, a framework that aug…