AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

arXiv:2306.00977v4 Announce Type: replace
Abstract: During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point to an object (or the background), while the user corrects errors in the resulting segmentation and feeds them back into the model. The current best practice formulates the problem as binary classification and segments objects one at a time. The model expects the user to …

abstract arxiv attention cloud cs.cv cs.hc data errors interactive iterative object objects process segmentation them together type work