Bake It Till You Make It: Ultrafast Spatial Texture-Atlas Splatting
For real-time rendering applications, this work offers a practical speedup without sacrificing quality, but it is an incremental improvement over existing 3DGS methods.
The paper introduces a decoupled radiance representation for 3D Gaussian Splatting that bakes high-frequency textures into a compact atlas, achieving up to 5x speedup over 3DGS while maintaining state-of-the-art visual quality, enabling real-time 4K rendering at 60 FPS on consumer hardware.
Recent extensions of 3D Gaussian Splatting (3DGS) capture fine color details using hash-grid-based appearance parameterization but incur high computational cost during fragment rendering. We introduce a decoupled radiance representation that models low-frequency geometry and view dependent appearance features with 2D surfels while representing high-frequency textures via a view-independent spatial hash grid that is baked into a compact texture atlas. By including sparsity-enhancing optimizations that penalize semi-transparency and per-primitive falloff, our method aggressively prunes insignificant surfels and achieves significantly faster and sparser reconstructions than prior work. Exploiting geometric sparsity and efficient GPU texture mapping, our approach achieves up to a fivefold speedup over 3DGS while preserving state-of-the-art visual fidelity, enabling real-time 4K rendering at 60 FPS on consumer hardware.