AI RESEARCH

AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting

arXiv CS.CV

ArXi:2605.06876v1 Announce Type: new Adaptive density control in 3D Gaussian Splatting (3DGS) repeatedly grows the Gaussian population through fixed-cardinality random splitting to discover useful scene structure. However, in vanilla 3DGS, its binary split operator requires many densification rounds to expose fine details, making it a bottleneck for efficient