让单目相机实现无人机实时环境重建，无需深度传感器
ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo
- 构建视图因子图指导多视角立体匹配，提升深度估计精度
- 在线生成全局一致的稠密深度图，支持机器人实时避障
- 首个纯视觉单目主动重建框架，适合轻量级无人系统
主动场景重建使机器人/无人机可自主规划路径并重建环境，无需昂贵的人工数据采集。与被动方法不同，主动重建需实时构建高置信度占用地图以实现无碰撞导航。现有方法依赖深度传感器更新地图，增加平台成本和重量。为提升空间智能，我们提出纯视觉单目解决方案。然而，当前单目重建方法多为离线处理，无法在机器人/无人机导航所需的帧率下生成全局一致的稠密深度图。为此，我们提出ActMVS，首个单目主动重建框架。该框架结合视图因子图构建用于有信息量的多视角立体深度预测，以及全局深度优化，实现高质量、全局一致的稠密深度图在线生成。这使单目机器人/无人机在重建过程中维持可靠的占用地图，支持安全轨迹规划。在Replica数据集上的实验表明，性能可媲美RGB-D方法。代码与数据见https://github.com/TrickyGo/ActMVS。
原文摘要 · Abstract (English)
Active scene reconstruction enables robots/UAVs to autonomously plan trajectories and reconstruct environments without costly manual data acquisition. Unlike passive methods, active reconstruction requires real-time construction of high-confidence occupancy maps for collision-free navigation. Existing approaches rely on depth sensors for occupancy map updates, increasing platform cost and weight. To advance spatial intelligence, we aim for a vision-only monocular solution. However, current monocular scene reconstruction methods operate offline and fail to deliver globally consistent dense depth at the frame rates required for robots/UAVs navigation. To bridge this gap, we introduce ActMVS, the first framework for monocular active reconstruction. Our framework integrates a view factor graph construction for informed Multi-View Stereo depth prediction, along with a global depth optimization, to enable the online generation of high-quality, globally consistent dense depth maps. This enables monocular robots/UAVs to maintain reliable occupancy maps for safe trajectory planning during reconstruction. Experiments on Replica datasets demonstrate performance competitive with RGB-D methods. Our code and data are available at https://github.com/TrickyGo/ActMVS.
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。