DIAL-GS：基于4D高斯溅射的无标签街景动态实例感知重建
DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting
AI总结：
针对现有自监督街景重建方法无法区分动态对象的问题，提出DIAL-GS方法，通过4D高斯溅射实现实例感知的动态重建，性能优于现有基线。
摘要：
城市场景重建对自动驾驶至关重要，可为数据合成和闭环测试提供结构化的3D表示。监督式方法依赖昂贵的人工标注，可扩展性不足；而当前自监督方法常混淆静态与动态元素，且无法区分单个动态对象，限制了细粒度编辑能力。我们提出DIAL-GS，一种基于4D高斯溅射的无标签街景动态实例感知重建新方法。首先，我们利用扭曲渲染结果与实际观测之间的外观-位置不一致性，精准识别动态实例；在实例级动态感知的引导下，采用实例感知的4D高斯作为统一体积表示，实现动态自适应且实例感知的重建。此外，我们引入一种互强化机制，使身份信息与动态信息相互增强，提升完整性与一致性。在城市驾驶场景上的实验表明，DIAL-GS在重建质量和实例级编辑性能上优于现有自监督基线，为城市场景建模提供了简洁且强大的解决方案。
英文摘要：
Urban scene reconstruction is critical for autonomous driving, enabling structured 3D representations for data synthesis and closed-loop testing. Supervised approaches rely on costly human annotations and lack scalability, while current self-supervised methods often confuse static and dynamic elements and fail to distinguish individual dynamic objects, limiting fine-grained editing. We propose DIAL-GS, a novel dynamic instance-aware reconstruction method for label-free street scenes with 4D Gaussian Splatting. We first accurately identify dynamic instances by exploiting appearance-position inconsistency between warped rendering and actual observation. Guided by instance-level dynamic perception, we employ instance-aware 4D Gaussians as the unified volumetric representation, realizing dynamic-adaptive and instance-aware reconstruction. Furthermore, we introduce a reciprocal mechanism through which identity and dynamics reinforce each other, enhancing both integrity and consistency. Experiments on urban driving scenarios show that DIAL-GS surpasses existing self-supervised baselines in reconstruction quality and instance-level editing, offering a concise yet powerful solution for urban scene modeling.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
