Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes
This work addresses the challenge of reconstructing dynamic scenes from blurry monocular videos, which is important for applications like robotics and AR/VR, and demonstrates clear improvements over prior methods.
Kinematics-GS reconstructs dynamic 3D scenes from blurry monocular videos by modeling motion blur as kinematics-aligned deformation, achieving state-of-the-art performance on real-world benchmarks with non-rigid motion.
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.