PAGS让3D道路场景重建更智能，关键物体保真度高且渲染快超350帧。
PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes
- 根据任务重要性动态分配资源，关键物体重点保留细节。
- 在Waymo和KITTI数据集上实现超350帧/秒的渲染速度。
- 适合自动驾驶中需要实时高精度3D重建的场景。
动态城市场景的三维重建对自动驾驶至关重要，但现有方法在精度与计算成本间存在显著权衡。其根源在于语义无关的设计，使静态背景与安全关键物体同等对待。为此，我们提出优先自适应高斯点云（PAGS），将任务感知的语义优先级直接注入三维重建与渲染流程。PAGS包含两项核心贡献：(1) 语义引导的剪枝与正则化策略，采用混合重要性度量，大幅简化非关键场景元素，同时保留导航关键物体的精细细节；(2) 优先级驱动的渲染流水线，通过基于优先级的深度预遍历，高效剔除被遮挡的原始图元，加速最终着色计算。在Waymo与KITTI数据集上的大量实验表明，PAGS在安全关键物体上实现了卓越的重建质量，同时显著缩短训练时间，并将渲染速度提升至超过350 FPS。
原文摘要 · Abstract (English)
Reconstructing dynamic 3D urban scenes is crucial for autonomous driving, yet current methods face a stark trade-off between fidelity and computational cost. This inefficiency stems from their semantically agnostic design, which allocates resources uniformly, treating static backgrounds and safety-critical objects with equal importance. To address this, we introduce Priority-Adaptive Gaussian Splatting (PAGS), a framework that injects task-aware semantic priorities directly into the 3D reconstruction and rendering pipeline. PAGS introduces two core contributions: (1) Semantically-Guided Pruning and Regularization strategy, which employs a hybrid importance metric to aggressively simplify non-critical scene elements while preserving fine-grained details on objects vital for navigation. (2) Priority-Driven Rendering pipeline, which employs a priority-based depth pre-pass to aggressively cull occluded primitives and accelerate the final shading computations. Extensive experiments on the Waymo and KITTI datasets demonstrate that PAGS achieves exceptional reconstruction quality, particularly on safety-critical objects, while significantly reducing training time and boosting rendering speeds to over 350 FPS.
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。