FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction
This addresses the problem of real-time dynamic view synthesis for scenes with complex motions, representing an incremental improvement over existing methods that use deformation fields.
The paper tackles dynamic 3D scene reconstruction with complex motions by proposing FreeTimeGS, a 4D representation that allows Gaussian primitives to appear at arbitrary times and locations, resulting in rendering quality that outperforms recent methods by a large margin.
This paper addresses the challenge of reconstructing dynamic 3D scenes with complex motions. Some recent works define 3D Gaussian primitives in the canonical space and use deformation fields to map canonical primitives to observation spaces, achieving real-time dynamic view synthesis. However, these methods often struggle to handle scenes with complex motions due to the difficulty of optimizing deformation fields. To overcome this problem, we propose FreeTimeGS, a novel 4D representation that allows Gaussian primitives to appear at arbitrary time and locations. In contrast to canonical Gaussian primitives, our representation possesses the strong flexibility, thus improving the ability to model dynamic 3D scenes. In addition, we endow each Gaussian primitive with an motion function, allowing it to move to neighboring regions over time, which reduces the temporal redundancy. Experiments results on several datasets show that the rendering quality of our method outperforms recent methods by a large margin. Project page: https://zju3dv.github.io/freetimegs/ .