GoDe: Gaussians on Demand for Progressive Level of Detail and Scalable Compression

ArXi:2501.13558v3 Announce Type: replace Recent progress in compressing explicit radiance field representations, particularly 3D Gaussian Splatting, has substantially reduced memory consumption while improving real-time rendering performance. However, existing approaches remain inherently single-rate: each compression level requires a separately optimized model, yielding a set of fixed operating points rather than a truly scalable representation. This limits deployment in scenarios where memory, bandwidth, or computational budgets vary across devices or over time.