DecoupleGS: Interactive 3D Gaussian Splatting for End-to-End Autonomous Driving Testing
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new simulation method called DecoupleGS to better test self-driving car software. Their approach breaks down scenes into a detailed static background and movable dynamic objects, making it easier to handle complex traffic situations realistically. They solved challenges like compressing assets for fast rendering, aligning objects precisely on maps, and adjusting lighting to make everything look natural. This method strikes a good balance between visual quality and speed, helping researchers test driving systems in a realistic and interactive virtual world.
end-to-end autonomous driving3D Gaussian Splattingclosed-loop simulationtraffic renderinggeometric registrationvector quantizationphotometric consistencydynamic scene compositionsensor simulationrelighting
Authors
Siying Li, Ying Ni, Jie Sun, Jian Sun, Haotian Shi
Abstract
End-to-end (E2E) autonomous driving algorithms require rigorous closed-loop validation in simulation environments offering high visual fidelity, strong interactivity, and real-time performance. Existing approaches, from game engines to static neural rendering, inherently trade off these requirements and struggle with the dynamic scene composition essential for E2E testing. To bridge this gap, we propose a novel decoupled 3D Gaussian Splatting (3DGS) framework tailored for large-scale E2E evaluation. We fundamentally decompose scenes into a high-fidelity static background and manipulable dynamic agents using an object-centric canonical representation. To resolve resulting representational conflicts, we introduce three targeted modules: (1) asset compression via perceptual pruning and vector quantization for real-time traffic rendering; (2) map-guided geometric registration leveraging semantic topology to strictly align trajectories; and (3) proxy-based relighting transferring ambient illumination for seamless photometric integration. Extensive experiments demonstrate that DecoupleGS achieves a balanced fidelity-efficiency trade-off, improves metric and photometric consistency, and provides a practical closed-loop sensor simulation platform for E2E autonomous driving evaluation.