Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction
created: June 6, 2025, 3:16 p.m. | updated: June 6, 2025, 10:34 p.m.
AbstractThis 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.
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.
Experiments results on several datasets show that the rendering quality of our method outperforms recent methods by a large margin.
1 day, 10 hours ago: Hacker News