This repository contains the source codes for the paper "High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinement".
The paper has been authored by Seunghyeok Back, Sangbeom Lee, Kangmin Kim, Joosoon Lee, Sungho Shin, Jaemo Maeng, and Kyoobin Lee.
Accepted at ICRA 2025
Part of the code is already available, and the latest version—including an updated README—will be released in time for the ICRA 2025 conference. If you're interested in our work, please consider starring this repository or watching it to get notified of future updates.
Should you have any questions or comments about our project, feel free to reach out to us at [email protected] or open an issue in this repository.