ParkGaussian：面向自动驾驶泊车的环视3D高斯泼溅
ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking
将3D高斯泼溅用于环视鱼眼相机的泊车场景重建，并提出车位感知的重建策略，利用现有车位检测模型增强车位区域合成质量，为自动驾驶中重建与下游感知的一致性提供了可复用的思路。
原文依据 we introduce a slot-aware reconstruction strategy that leverages existing parking perception methods to enhance the synthesis quality of slot regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论泊车是自动驾驶系统（ADS）的一项关键任务，在拥挤的车位和GPS拒止环境中面临独特挑战。然而，现有工作集中于2D车位感知、建图与定位，3D重建仍探索不足，而3D重建对于捕捉泊车场景中的复杂空间几何至关重要。单纯提升重建泊车场景的视觉质量并不能直接惠及自动驾驶泊车，因为泊车的关键切入点在于车位感知模块。为解决这些局限，我们构建了首个专门面向泊车场景重建的基准，命名为ParkRecon3D。它包含来自四个环视鱼眼相机的传感器数据，附带标定外参和密集的车位标注。随后我们提出ParkGaussian，这是首个集成3D高斯泼溅（3DGS）进行泊车场景重建的框架。为进一步提升重建与下游车位检测之间的对齐，我们引入车位感知重建策略，利用现有泊车感知方法增强车位区域的合成质量。在ParkRecon3D上的实验表明，ParkGaussian取得了最优的重建质量，并为下游任务更好地保持了感知一致性。代码和数据集将公开。
英文原文摘要 1378 字符
Parking is a critical task for autonomous driving systems (ADS), with unique challenges in crowded parking slots and GPS-denied environments. However, existing works focus on 2D parking slot perception, mapping, and localization, 3D reconstruction remains underexplored, which is crucial for capturing complex spatial geometry in parking scenarios. Naively improving the visual quality of reconstructed parking scenes does not directly benefit autonomous parking, as the key entry point for parking is the slots perception module. To address these limitations, we curate the first benchmark named ParkRecon3D, specifically designed for parking scene reconstruction. It includes sensor data from four surround-view fisheye cameras with calibrated extrinsics and dense parking slot annotations. We then propose ParkGaussian, the first framework that integrates 3D Gaussian Splatting (3DGS) for parking scene reconstruction. To further improve the alignment between reconstruction and downstream parking slot detection, we introduce a slot-aware reconstruction strategy that leverages existing parking perception methods to enhance the synthesis quality of slot regions. Experiments on ParkRecon3D demonstrate that ParkGaussian achieves state-of-the-art reconstruction quality and better preserves perception consistency for downstream tasks. The code and dataset will be released.