AI RESEARCH
VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning
arXiv CS.CV
•
ArXi:2606.02346v1 Announce Type: new 3D Gaussian Splatting (3DGS) achieves remarkable novel view synthesis quality with real-time rendering, yet suffers from excessive memory consumption due to millions of Gaussian primitives. Existing pruning methods rely on heuristic importance scores or synchronous batch updates, leading to suboptimal compression and