用分块+循环闭合，让单目3D重建突破千米级极限。
VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
- 分块处理长序列，重叠对齐保证连续性。
- 在KITTI等数据集上达到传统方法水平。
- 无需标定/重训，适合自动驾驶场景。
三维视觉基础模型在三维感知方面已展现卓越能力，但将其扩展至大规模RGB流三维重建仍受内存限制困扰。本文提出VGGT-Long，一种简单而高效的方法，将单目三维重建推进至千米级、无界户外环境。通过基于分块的处理策略，结合重叠对齐与轻量级回环优化，解决了现有模型的可扩展性瓶颈。无需相机标定、深度监督或模型重训练，VGGT-Long在轨迹和重建性能上可媲美传统方法。我们在KITTI、Waymo和Virtual KITTI数据集上进行评估，结果表明该方法不仅能在基础模型通常失效的长序列中成功运行，还能在多种条件下生成准确一致的几何结构。实验凸显了利用基础模型实现真实世界场景下可扩展单目三维重建的巨大潜力，尤其适用于自动驾驶场景。代码已公开于https://github.com/DengKaiCQ/VGGT-Long。
原文摘要 · Abstract (English)
Foundation models for 3D vision have recently demonstrated remarkable capabilities in 3D perception. However, extending these models to large-scale RGB stream 3D reconstruction remains challenging due to memory limitations. In this work, we propose VGGT-Long, a simple yet effective system that pushes the limits of monocular 3D reconstruction to kilometer-scale, unbounded outdoor environments. Our approach addresses the scalability bottlenecks of existing models through a chunk-based processing strategy combined with overlapping alignment and lightweight loop closure optimization. Without requiring camera calibration, depth supervision or model retraining, VGGT-Long achieves trajectory and reconstruction performance comparable to traditional methods. We evaluate our method on KITTI, Waymo, and Virtual KITTI datasets. VGGT-Long not only runs successfully on long RGB sequences where foundation models typically fail, but also produces accurate and consistent geometry across various conditions. Our results highlight the potential of leveraging foundation models for scalable monocular 3D scene in real-world settings, especially for autonomous driving scenarios. Code is available at https://github.com/DengKaiCQ/VGGT-Long.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。