PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes
This addresses inefficiencies in 3D reconstruction for autonomous driving by prioritizing safety-critical objects, though it is an incremental improvement over existing methods.
The paper tackles the trade-off between fidelity and computational cost in reconstructing dynamic 3D urban scenes for autonomous driving by introducing PAGS, which uses semantic priorities to simplify non-critical elements and preserve details on safety-critical objects, achieving over 350 FPS rendering speeds.
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.