Search papers, labs, and topics across Lattice.
MotionScale introduces a 4D Gaussian Splatting framework for reconstructing dynamic scenes from monocular videos, tackling challenges in geometry and motion coherence. It employs a scalable motion field with cluster-centric basis transformations and a progressive optimization strategy with background extension and foreground propagation stages. Experiments show MotionScale significantly outperforms state-of-the-art methods in reconstruction quality and temporal stability on real-world benchmarks.
Reconstructing dynamic 3D scenes from video just got a whole lot better: MotionScale achieves state-of-the-art fidelity and temporal stability by scaling Gaussian splatting to long, complex sequences.
Realistic reconstruction of dynamic 4D scenes from monocular videos is essential for understanding the physical world. Despite recent progress in neural rendering, existing methods often struggle to recover accurate 3D geometry and temporally consistent motion in complex environments. To address these challenges, we propose MotionScale, a 4D Gaussian Splatting framework that scales efficiently to large scenes and extended sequences while maintaining high-fidelity structural and motion coherence. At the core of our approach is a scalable motion field parameterized by cluster-centric basis transformations that adaptively expand to capture diverse and evolving motion patterns. To ensure robust reconstruction over long durations, we introduce a progressive optimization strategy comprising two decoupled propagation stages: 1) A background extension stage that adapts to newly visible regions, refines camera poses, and explicitly models transient shadows; 2) A foreground propagation stage that enforces motion consistency through a specialized three-stage refinement process. Extensive experiments on challenging real-world benchmarks demonstrate that MotionScale significantly outperforms state-of-the-art methods in both reconstruction quality and temporal stability. Project page: https://hrzhou2.github.io/motion-scale-web/.
