Regularizing Dynamic Radiance Fields with Kinematic Fields
This work addresses the challenge of sparse monocular video data for dynamic scene reconstruction, offering an incremental improvement with physics-driven regularization.
The paper tackles the problem of reconstructing dynamic radiance fields from monocular videos by integrating kinematics to capture motion patterns, resulting in state-of-the-art performance on challenging real-world videos.
This paper presents a novel approach for reconstructing dynamic radiance fields from monocular videos. We integrate kinematics with dynamic radiance fields, bridging the gap between the sparse nature of monocular videos and the real-world physics. Our method introduces the kinematic field, capturing motion through kinematic quantities: velocity, acceleration, and jerk. The kinematic field is jointly learned with the dynamic radiance field by minimizing the photometric loss without motion ground truth. We further augment our method with physics-driven regularizers grounded in kinematics. We propose physics-driven regularizers that ensure the physical validity of predicted kinematic quantities, including advective acceleration and jerk. Additionally, we control the motion trajectory based on rigidity equations formed with the predicted kinematic quantities. In experiments, our method outperforms the state-of-the-arts by capturing physical motion patterns within challenging real-world monocular videos.