PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: A, Ying, Sun, Wenzhang, Zeng, Chang, Wang, Chunfeng, Li, Hao, Cui, Jianxun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914091434508288
author A, Ying
Sun, Wenzhang
Zeng, Chang
Wang, Chunfeng
Li, Hao
Cui, Jianxun
author_facet A, Ying
Sun, Wenzhang
Zeng, Chang
Wang, Chunfeng
Li, Hao
Cui, Jianxun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12282
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes
A, Ying
Sun, Wenzhang
Zeng, Chang
Wang, Chunfeng
Li, Hao
Cui, Jianxun
Computer Vision and Pattern Recognition
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.
title PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12282