Lie Flow: Video Dynamic Fields Modeling and Predicting with Lie Algebra as Geometric Physics Principle
This work addresses the problem of physically plausible dynamic scene representation for computer vision and graphics applications, offering a novel geometric approach that is incremental in advancing motion modeling beyond existing methods.
The paper tackled the challenge of modeling 4D scenes with physically consistent motion by introducing LieFlow, a framework that uses SE(3) Lie group transformations to unify translation and rotation, resulting in improved view-synthesis fidelity, temporal coherence, and physical realism over NeRF-based baselines across synthetic and real-world datasets.
Modeling 4D scenes requires capturing both spatial structure and temporal motion, which is challenging due to the need for physically consistent representations of complex rigid and non-rigid motions. Existing approaches mainly rely on translational displacements, which struggle to represent rotations, articulated transformations, often leading to spatial inconsistency and physically implausible motion. LieFlow, a dynamic radiance representation framework that explicitly models motion within the SE(3) Lie group, enabling coherent learning of translation and rotation in a unified geometric space. The SE(3) transformation field enforces physically inspired constraints to maintain motion continuity and geometric consistency. The evaluation includes a synthetic dataset with rigid-body trajectories and two real-world datasets capturing complex motion under natural lighting and occlusions. Across all datasets, LieFlow consistently improves view-synthesis fidelity, temporal coherence, and physical realism over NeRF-based baselines. These results confirm that SE(3)-based motion modeling offers a robust and physically grounded framework for representing dynamic 4D scenes.