Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling

Autor:	Back, Seunghyeok, Lee, Joosoon, Kim, Taewon, Noh, Sangjun, Kang, Raeyoung, Bak, Seongho, Lee, Kyoobin
Rok vydání:	2021
Předmět:	Computer Science - Robotics Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Instance-aware segmentation of unseen objects is essential for a robotic system in an unstructured environment. Although previous works achieved encouraging results, they were limited to segmenting the only visible regions of unseen objects. For robotic manipulation in a cluttered scene, amodal perception is required to handle the occluded objects behind others. This paper addresses Unseen Object Amodal Instance Segmentation (UOAIS) to detect 1) visible masks, 2) amodal masks, and 3) occlusions on unseen object instances. For this, we propose a Hierarchical Occlusion Modeling (HOM) scheme designed to reason about the occlusion by assigning a hierarchy to a feature fusion and prediction order. We evaluated our method on three benchmarks (tabletop, indoors, and bin environments) and achieved state-of-the-art (SOTA) performance. Robot demos for picking up occluded objects, codes, and datasets are available at https://sites.google.com/view/uoais Comment: Accepted at ICRA 2022, Project page: https://sites.google.com/view/uoais
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2109.11103 Zobrazit plný text záznamu View this record from Arxiv