Feb. 27, 2024, 5:48 a.m. | Zhen Zhou, Junfeng Fan, Yunkai Ma, Sihan Zhao, Fengshui Jing, Min Tan

cs.CV updates on arXiv.org arxiv.org

arXiv:2401.08174v2 Announce Type: replace
Abstract: Instance segmentation for completely occluded objects and dense objects in robot vision measurement are two challenging tasks. To uniformly deal with them, this paper proposes a unified coarse-to-fine instance segmentation framework, CFNet, which uses box prompt-based segmentation foundation models (BSMs), e.g., Segment Anything Model. Specifically, CFNet first detects oriented bounding boxes (OBBs) to distinguish instances and provide coarse localization information. Then, it predicts OBB prompt-related masks for fine segmentation. CFNet performs instance segmentation with OBBs …

arxiv cs.cv framework instance measurement objects robot segmentation type vision

Data Scientist (m/f/x/d)

@ Symanto Research GmbH & Co. KG | Spain, Germany

Data Science Analyst I - Pulmonary

@ Mount Sinai Health System | United States

Data Engineering, Lead

@ Booz Allen Hamilton | USA, GA, Atlanta (1349 W Peachtree St NW)

Data Science Recruiter (US Hiring)

@ Tiger Analytics | India - Remote

Business Intelligence Analyst (I, II, III, Senior)

@ C Spire | Ridgeland, MS, United States

Senior Staff Infrastructure Engineer (Data Infrastructure)

@ Coupang | Seattle, USA