VGGT-SLAM 2.0：实时密集前馈场景重建
VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction
AI总结：
VGGT-SLAM 2.0通过改进因子图设计和利用注意力层，实现了更精确的实时场景重建和开放集物体检测。
摘要：
我们提出了VGGT-SLAM 2.0，一种实时RGB前馈SLAM系统，显著改进了VGGT-SLAM在逐步对齐由VGGT生成的子地图的能力。首先，我们通过创建新的因子图设计，消除了VGGT-SLAM中的高维15自由度漂移和平面退化现象，同时仍然解决VGGT在未知相机内参下的重建歧义问题。其次，通过研究VGGT的注意力层，我们发现其中一层非常适合在不额外训练的情况下协助图像检索验证，这使系统能够拒绝虚假匹配并完成更多的环闭合。最后，我们进行了一系列实验，包括展示VGGT-SLAM 2.0可以轻松适应开放集物体检测，并在地面机器人上实时运行，使用Jetson Thor。我们在从杂乱的室内公寓和办公室场景到4200平方英尺谷仓的环境中进行了测试，并展示了VGGT-SLAM 2.0在TUM数据集上实现了最高精度，其姿态误差比VGGT-SLAM低约23%。代码将在发表时发布。
英文摘要：
We present VGGT-SLAM 2.0, a real-time RGB feed-forward SLAM system which substantially improves upon VGGT-SLAM for incrementally aligning submaps created from VGGT. Firstly, we remove high-dimensional 15-degree-of-freedom drift and planar degeneracy from VGGT-SLAM by creating a new factor graph design while still addressing the reconstruction ambiguity of VGGT given unknown camera intrinsics. Secondly, by studying the attention layers of VGGT, we show that one of the layers is well suited to assist in image retrieval verification for free without additional training, which enables both rejecting false positive matches and allows for completing more loop closures. Finally, we conduct a suite of experiments which includes showing VGGT-SLAM 2.0 can easily be adapted for open-set object detection and demonstrating real-time performance while running online onboard a ground robot using a Jetson Thor. We test in environments ranging from cluttered indoor apartments and office scenes to a 4,200 square foot barn, and we also demonstrate VGGT-SLAM 2.0 achieves the highest accuracy on the TUM dataset with about 23 percent less pose error than VGGT-SLAM. Code will be released upon publication.
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。
