AI RESEARCH
A Step to Decouple Optimization in 3DGS
arXiv CS.CV
•
ArXi:2601.16736v4 Announce Type: replace 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time novel view synthesis. As an explicit representation optimized through gradient propagation among primitives, optimization widely accepted in deep neural networks (DNNs) is actually adopted in 3DGS, such as synchronous weight updating and Adam with the adaptive gradient.