GRCVPFFeb 3

WebSplatter: Enabling Cross-Device Efficient Gaussian Splatting in Web Browsers via WebGPU

arXiv:2602.03207v1h-index: 5
Originality Incremental advance
AI Analysis

This work addresses the challenge of cross-device 3D rendering in web browsers, providing significant performance improvements for web-based graphics applications.

The paper tackled the problem of enabling efficient Gaussian splatting for 3D rendering in web browsers by developing WebSplatter, which introduced a wait-free hierarchical radix sort and opacity-aware geometry culling, resulting in speedups of 1.2× to 4.5× over state-of-the-art web viewers.

We present WebSplatter, an end-to-end GPU rendering pipeline for the heterogeneous web ecosystem. Unlike naive ports, WebSplatter introduces a wait-free hierarchical radix sort that circumvents the lack of global atomics in WebGPU, ensuring deterministic execution across diverse hardware. Furthermore, we propose an opacity-aware geometry culling stage that dynamically prunes splats before rasterization, significantly reducing overdraw and peak memory footprint. Evaluation demonstrates that WebSplatter consistently achieves 1.2$\times$ to 4.5$\times$ speedups over state-of-the-art web viewers.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes