We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SLAM consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense Bundle Adjustment layer. DROID-SLAM is accurate, achieving large improvements over prior work, and robust, suffering from substantially fewer catastrophic failures. Despite training on monocular video, it can leverage stereo or RGB-D video to achieve improved performance at test time. The URL to our open source code is https://github.com/princeton-vl/DROID-SLAM.
翻译:我们引入了DROID-SLAM,这是一个以深层次学习为基础的新的SLAM系统。DROID-SLAM包含通过Dense Bundle调整层对摄像面和像素深度的反复迭代更新。DROID-SLAM是准确的,比以前的工作有很大的改进,而且强劲有力,遭受的灾难性失败要少得多。尽管对单向视频进行了培训,但它可以利用立体或RGB-D视频来提高测试时的性能。我们的开放源代码的 URL是 https://github.com/princton-vl/DROID-SLAM。