DynamicVGGT：学习动态点图用于自动驾驶中的4D场景重建
DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
将前馈式三维重建模型（VGGT）扩展到动态场景，通过联合预测当前与未来点图并引入运动感知时序注意力与动态高斯泼溅头，为自动驾驶中的4D重建提供了一种无需优化的前馈方案。
原文依据 we propose DynamicVGGT, a unified feed-forward framework that extends VGGT from static 3D perception to dynamic 4D reconstruction.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自动驾驶中的动态场景重建由于显著的时间变化、运动物体和复杂的场景动态而仍然是一项基本挑战。现有的前馈三维模型在静态重建中表现出强大性能，但仍难以捕捉动态运动。为了解决这些局限，我们提出了DynamicVGGT，一个统一的前馈框架，将VGGT从静态三维感知扩展到动态4D重建。我们的目标是在前馈三维模型中以动态且时序连贯的方式建模点运动。为此，我们在共享参考坐标系中联合预测当前和未来的点图，使模型能够通过时序对应隐式学习动态点表示。为了高效捕捉时序依赖，我们引入了一个运动感知时序注意力（MTA）模块来学习运动连续性。此外，我们设计了一个动态三维高斯泼溅头（DGSH），通过在场景流监督下使用可学习运动令牌预测高斯速度来显式建模点运动。它通过连续三维高斯优化来细化动态几何。在自动驾驶数据集上的大量实验表明，DynamicVGGT在重建精度和时序一致性上显著优于现有方法，在复杂驾驶场景下实现了鲁棒的前馈4D动态场景重建。
英文原文摘要 1469 字符
Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed-forward 3D models have demonstrated strong performance in static reconstruction but still struggle to capture dynamic motion. To address these limitations, we propose DynamicVGGT, a unified feed-forward framework that extends VGGT from static 3D perception to dynamic 4D reconstruction. Our goal is to model point motion within feed-forward 3D models in a dynamic and temporally coherent manner. To this end, we jointly predict the current and future point maps within a shared reference coordinate system, allowing the model to implicitly learn dynamic point representations through temporal correspondence. To efficiently capture temporal dependencies, we introduce a Motion-aware Temporal Attention (MTA) module that learns motion continuity. Furthermore, we design a Dynamic 3D Gaussian Splatting Head (DGSH) that explicitly models point motion by predicting Gaussian velocities using learnable motion tokens under scene flow supervision. It refines dynamic geometry through continuous 3D Gaussian optimization. Extensive experiments on autonomous driving datasets demonstrate that DynamicVGGT significantly outperforms existing methods in reconstruction accuracy and temporal consistency, achieving robust feed-forward 4D dynamic scene reconstruction under complex driving scenarios.