MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting

2026-03-31

AI Summary

Existing approaches struggle to simultaneously achieve accurate 3D geometry reconstruction and temporally consistent motion modeling in complex dynamic scenes. To address this challenge, this work proposes MotionScale—a scalable 4D Gaussian splatting framework that introduces an adaptive clustered motion basis to parameterize the motion field and explicitly models instantaneous shadows. The method employs a decoupled two-stage progressive optimization strategy: it first optimizes background geometry expansion and then propagates foreground motion, while jointly refining camera poses throughout. Evaluated on real-world long-sequence dynamic scenes, MotionScale significantly outperforms state-of-the-art methods in both reconstruction fidelity and temporal consistency.

Abstract

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/.

Problem

• dynamic 4D reconstruction
• 3D geometry
• temporal consistency
• monocular video
• motion coherence

Innovation

• 4D Gaussian Splatting
• Scalable Motion Field
• Temporal Consistency
• Progressive Optimization
• Dynamic Scene Reconstruction