发表机构
City University of Hong Kong; Hon Hai Research Institute（香港城市大学; 鸿海研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对野外4D驾驶场景重建，现有方法依赖精确先验，噪声先验下有问题。提出自适应高斯图（AGG）框架，含语义引导策略和自适应拓扑进化模块。在KITTI和Wild-30实验验证，AGG在视觉保真度和鲁棒性上优于现有方法。
AI 中文摘要
在野外重建4D驾驶场景对各种自动驾驶模拟至关重要。近期高斯场景图（GSG）方法虽视觉质量不错，但严重依赖精确先验（相机姿态、激光雷达深度或手动标注）。用野外视频估计的噪声先验初始化时，现有GSG方法会有优化模糊和拓扑失败问题。我们引入自适应高斯图（AGG），一种自校正4D框架。语义引导的滴答策略利用2D基础特征解耦静态背景和相机姿态更新与动态代理学习。自适应拓扑进化模块通过生成缺失代理、重新分配错误分类的高斯和修剪误报来纠正图结构。我们引入Wild-30作为具有挑战性的野外基准。在KITTI和Wild-30上的大量实验验证了AGG在噪声先验下视觉保真度和鲁棒性方面优于现有方法。
英文摘要
Reconstructing 4D driving scenes in the wild (e.g., internet and AI-generated videos) is critical for diverse autonomous driving simulation. While recent Gaussian Scene Graph (GSG) methods achieve impressive visual quality, they heavily rely on precise priors, such as accurate camera poses and LiDAR depth, or manual annotations. When initialized with noisy priors estimated from in-the-wild videos, existing GSG methods suffer from optimization ambiguity (e.g., entangling camera and agent poses) and topological failures (e.g., missing objects), causing severe rendering artifacts. To enable robust in-the-wild reconstruction, we introduce Adaptive Gaussian Graph (AGG), a self-correcting 4D framework. Our Semantically-Guided Tick-Tock Strategy leverages 2D foundation features to explicitly decouple static background and camera pose updates from dynamic agent learning. Concurrently, our Adaptive Topology Evolution module actively rectifies graph structures by spawning missing agents, reassigning misclassified Gaussians, and pruning false positives. To rigorously evaluate this in-the-wild setting, we introduce Wild-30, a challenging benchmark of internet and generative videos. Extensive experiments on KITTI and Wild-30 validate that AGG consistently outperforms state-of-the-art approaches in visual fidelity and robustness under noisy priors.
