AI RESEARCH

ARGS: Auto-Regressive Gaussian Splatting via Parallel Progressive Next-Scale Prediction

arXiv CS.CV

ArXi:2604.00494v1 Announce Type: new Auto-regressive frameworks for next-scale prediction of 2D images have nstrated strong potential for producing diverse and sophisticated content by progressively refining a coarse input. However, extending this paradigm to 3D object generation remains largely unexplored. In this paper, we