解耦车辆运动与相机结构，提升自动驾驶几何感知精度
TRIG: Trajectory-Rig Decoupled Metric Geometry Learning
- 将相机位姿拆分为车辆轨迹和固定相机结构两部分建模
- 在5个基准上实现位姿、深度、3D重建的最新性能
- 适合需要精确几何理解的自动驾驶系统开发
视觉中心的自动驾驶需要从同步多摄像头观测中准确估计度量几何与自车运动。现有视觉几何模型在位姿估计、深度预测和3D重建上表现良好，但未针对刚性多摄像头驾驶系统设计。它们常将相机位姿编码为纠缠表示，使时变自车运动与静态相机-平台几何联合建模，限制了车辆侧几何先验的利用。本文提出轨迹-平台解耦度量几何学习（TRIG）框架，将相机位姿分解为自车轨迹与相机平台组件，实现对自车运动与固定多摄像头拓扑的独立建模。引入解耦位姿编码与监督，分别约束轨迹演化与平台几何以实现度量一致性学习。此外，稀疏时空注意力将跨相机交互与时间聚合分离，降低全局注意力开销同时保留几何推理能力。在五个自动驾驶基准上的实验表明，TRIG在位姿估计、度量深度预测和3D重建上均达到当前最优性能。
原文摘要 · Abstract (English)
Vision-centric autonomous driving requires accurate metric geometry and ego-motion estimation from synchronized multi-camera observations. Recent visual geometry models show strong performance in pose estimation, depth prediction, and 3D reconstruction, but are not tailored to rigid multi-camera driving systems. They often encode camera poses as entangled representations, in which time-varying ego-motion and static camera-rig geometry are jointly modeled, limiting the utilization of vehicle-side geometric priors. We propose Trajectory-Rig Decoupled Metric Geometry Learning (TRIG), a geometry perception framework for autonomous driving. TRIG factorizes camera poses into ego-trajectory and camera-rig components, enabling separate modeling of ego-motion and static multi-camera topology. We introduce decoupled pose encoding and supervision, which separately constrain trajectory evolution and rig geometry for metric-consistent learning. Moreover, sparse Temporal--Spatial attention separates cross-camera interaction from temporal aggregation, reducing global attention cost while preserving geometric reasoning. Experiments on five autonomous driving benchmarks show that TRIG achieves state-of-the-art performance in pose estimation, metric depth prediction, and 3D reconstruction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。