We present a method for single image 3D cuboid object detection and multi-view object SLAM without prior object model, and demonstrate that the two aspects can benefit each other. For 3D detection, we generate high quality cuboid proposals from 2D bounding boxes and vanishing points sampling. The proposals are further scored and selected to align with image edges. Experiments on SUN RGBD and KITTI shows the efficiency and accuracy over existing approaches. Then in the second part, multi-view bundle adjustment with novel measurement functions is proposed to jointly optimize camera poses, objects and points, utilizing single view detection results. Objects can provide more geometric constraints and scale consistency compared to points. On the collected and public TUM and KITTI odometry datasets, we achieve better pose estimation accuracy over the state-of-the-art monocular SLAM while also improve the 3D object detection accuracy at the same time.
View on arXiv