汽车工程学报2026，Vol.16Issue(2)：203-214,12.DOI:10.3969/j.issn.2095‒1469.2026.02.04
基于神经渲染的自动驾驶场景解耦表征与感知数据生成
Decoupled Representation and Perception Data Generation for Autonomous Driving Scenarios Based on Neural Rendering
摘要
Abstract
High-quality perception data is crucial for designing and testing autonomous-driving algorithms.To address the limited scenario coverage of traditional data collection caused by high costs and the scarcity of long-tail data,the paper proposes a 4D scenarios modeling approach based on Neural Radiance Fields(NeRF).This method uses self-supervised learning to separate static and dynamic elements,and utilizes controllable appearance encoding to decouple the geometric and appearance features of the scenarios.Without retraining the model,diverse perception data can be generated simply by embedding appearance feature vectors.Tests on the Waymo dataset show that the perception data generated by this method achieves high realism,with a PSNR of 27.75 and an SSIM of 0.808,outperforming both D2NeRF and HyperNeRF.关键词
自动驾驶/数据生成/场景重构/神经辐射场/可微渲染Key words
autonomous driving/data generation/scenarios reconstruction/neural radiance fields/differentiable rendering分类
交通工程引用本文复制引用
吕叶祥子,蒋渊德,宋家乐,王润民,刘妮,徐志刚..基于神经渲染的自动驾驶场景解耦表征与感知数据生成[J].汽车工程学报,2026,16(2):203-214,12.基金项目
国家自然科学基金区域创新发展联合基金项目(U22A20247,U23A20682) （U22A20247,U23A20682）
陕西省自然科学基础研究计划项目(2023-JC-QN-0393) （2023-JC-QN-0393）
