AI RESEARCH
Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
arXiv CS.CV
•
ArXi:2605.00408v1 Announce Type: new While 3D Gaussian Splatting (3DGS) has nstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, such methods inherently lack the flexibility to adapt to diverse scenes with complex geometries. In this paper, we propose a paradigm shift for density control from rigid heuristics to fully learnable policies. Specifically, we