MACARONS：基于RGB在线自监督的建图与覆盖预测
MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision
AI总结：
本研究提出仅用RGB图像的自监督方法MACARONS，同时学习体素占用场预测与次佳视角（NBV）决策，实现大场景探索与3D重建，在新场景上性能超越依赖深度传感器的现有NBV方法。
摘要：
我们提出了一种仅利用彩色图像，同时实现新的大尺度环境探索与3D重建的方法。该问题与次佳视角问题（Next Best View，NBV）密切相关，NBV需要确定相机的下一个移动位置以提升未知场景的覆盖度。但当前多数NBV方法依赖深度传感器，需要3D监督，且/或无法扩展到大尺度场景。我们的方法仅需彩色相机，无需3D监督。它以自监督方式同时学习从彩色图像预测“体素占用场”，再基于该场预测NBV。得益于这一思路，我们的方法不会受任何训练3D数据的偏置影响，在新场景上表现优异。我们在包含多种3D场景的最新数据集上验证了该方法，结果显示其性能甚至优于需要深度传感器的最新方法——而对于飞行无人机拍摄的户外场景而言，配备深度传感器并非现实假设。
英文摘要：
We introduce a method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only. This is closely related to the Next Best View problem (NBV), where one has to identify where to move the camera next to improve the coverage of an unknown scene. However, most of the current NBV methods rely on depth sensors, need 3D supervision and/or do not scale to large scenes. Our method requires only a color camera and no 3D supervision. It simultaneously learns in a self-supervised fashion to predict a "volume occupancy field" from color images and, from this field, to predict the NBV. Thanks to this approach, our method performs well on new scenes as it is not biased towards any training 3D data. We demonstrate this on a recent dataset made of various 3D scenes and show it performs even better than recent methods requiring a depth sensor, which is not a realistic assumption for outdoor scenes captured with a flying drone.
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。
