Hierarchical Point Attention for Indoor 3D Object Detection

arXiv:2301.02650v2 Announce Type: replace
Abstract: 3D object detection is an essential vision technique for various robotic systems, such as augmented reality and domestic robots. Transformers as versatile network architectures have recently seen great success in 3D point cloud object detection. However, the lack of hierarchy in a plain transformer restrains its ability to learn features at different scales. Such limitation makes transformer detectors perform worse on smaller objects and affects their reliability in indoor environments where small objects are the …

3d object 3d object detection abstract architectures arxiv attention augmented reality cloud cs.cv detection domestic robots hierarchical however network object reality robotic robots success systems transformer transformers type vision