Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes

TL;DR

This paper introduces Kinematics-GS, a novel framework that models motion-induced blur as deformation along motion trajectories, improving 3D scene reconstruction from blurry monocular videos.

Contribution

It proposes a kinematics-aware approach with a kinematic prior and a coarse-to-fine deformation strategy to better handle non-rigid motion and blur in scene reconstruction.

Findings

Outperforms prior methods on real-world benchmarks.

Effectively handles complex non-rigid and elastic motions.

Mitigates shape collapse without auxiliary supervision.

Abstract

Reconstructing dynamic 3D scenes from blurry monocular videos is challenging as motion-induced blur entangles object motion and geometry, hindering geometric consistency. We present Kinematics-GS, a kinematics-aware framework that models blur as motion-aligned deformation and introduces a kinematic prior to reparameterize Gaussian shapes along motion trajectories, thereby mitigating degenerate shape collapse without auxiliary motion supervision. To stabilize optimization, we decompose scenes into dynamic and static components using temporal deformation variance and employ a coarse-to-fine deformation strategy to capture both global motion and fine-grained details. We also introduce a challenging real-world dataset of deformable and elastic objects exhibiting non-rigid motion with spatially non-uniform motion blur that obscures geometric cues. Extensive experiments on real-world benchmarks with realistic motion blur demonstrate that Kinematics-GS outperforms prior methods by a clear margin in monocular dynamic scene reconstruction, highlighting its effectiveness in handling complex and non-rigid motion scenarios.