烘焙直至成功：超快速空间纹理图集喷涂
Bake It Till You Make It: Ultrafast Spatial Texture-Atlas Splatting
浏览论文内容
中文总结 AI 辅助
研究针对3D高斯喷涂渲染成本高的问题，引入解耦辐射表示，结合稀疏性增强优化，利用几何稀疏性和GPU纹理映射，实现更快更稀疏重建，比3DGS速度提升五倍，能在消费硬件上实时4K 60帧渲染。
中文摘要 AI 辅助
近期3D高斯喷涂（3DGS）的扩展使用基于哈希网格的外观参数化来捕捉精细颜色细节，但在片段渲染期间计算成本很高。我们引入一种解耦辐射表示，用二维表面元素对低频几何和视图相关外观特征建模，通过烘焙到紧凑纹理图集中的视图无关空间哈希网格表示高频纹理。通过包含惩罚半透明和逐原语衰减的稀疏性增强优化，我们的方法积极修剪无关紧要的表面元素，比之前工作实现更快、更稀疏的重建。利用几何稀疏性和高效GPU纹理映射，我们的方法比3DGS速度提高五倍，同时保持视觉保真度，能在消费硬件上以60帧每秒实时渲染4K画面。
英文摘要
Neural radiance representations in Gaussian Splatting (GS) deliver high-fidelity color detail but impose substantial rendering overhead from network evaluations. We present a learned sparse scene representation based on 2D surfels, which enables baking the neural component into a hardware-accelerated 2D texture atlas and eliminates runtime network inference. Our 2D surfels carry low-frequency geometry and view-dependent appearance, while view-independent, per-primitive high-frequency texture is encoded with a spatial hash grid and converted into the texture atlas. A novel sparsity objective that penalizes per-primitive kernel falloffs achieves a substantially sparser representation than prior methods. With a compute-optimized ray-surfel intersection shader our approach renders roughly $7$ to $9\times$ faster than 3DGS on common benchmarks, and over an order of magnitude faster on individual scenes, while surpassing the perceptual quality and speed of the fastest sparsification methods (FastGS and Speedy-Splat) at PSNR parity. A quality-optimized variant matches the perceptual quality of the strongest baseline while still rendering several times faster. Because inference is one texture fetch per fragment, frame rates can be pushed to $2{,}700$--$4{,}400$ FPS with no loss in quality when using the GPU hardware rasterizer.
发表机构
- Technical University of Munich（慕尼黑工业大学）
- Siemens-Healthineers（西门子医疗）
机构由 AI 辅助整理，请以论文原文为准。
