SOURCE-LINKED INTELLIGENCE

From Splats to Silicon: Rethinking Computational Efficiency of 3DGS

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

3D Gaussian splatting (3DGS) represents scenes with explicit primitives and supports real-time novel-view synthesis, yet its system efficiency varies substantially across scenes, viewpoints, rendering paths, and platform constraints. Existing studies pursue efficiency through representation and algorithm design, GPU runtime optimization, and architectural support, but their reported gains correspond to different points along the rendering and update paths. Connecting these indicators to end-to-end system benefit requires tracing how each optimization changes Gaussian selection, screen-space wo

Read original source ↗ Open in workspace

recordType

paper

region

Global