High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinement

2023-06-28 · Seunghyeok Back, Sangbeom Lee, KangMin Kim, Joosoon Lee, Sungho Shin, Jemo Maeng, Kyoobin Lee

Accurate and efficient segmentation of unknown objects in unstructured environments is essential for robotic manipulation. Unknown Object Instance Segmentation (UOIS), which aims to identify all objects in unknown categories and backgrounds, has become a key capability for various robotic tasks. However, existing methods struggle with over-segmentation and under-segmentation, leading to failures in manipulation tasks such as grasping. To address these challenges, we propose QuBER (Quadruple Boundary Error Refinement), a novel error-informed refinement approach for high-quality UOIS. QuBER first estimates quadruple boundary errors-true positive, true negative, false positive, and false negative pixels-at the instance boundaries of the initial segmentation. It then refines the segmentation using an error-guided fusion mechanism, effectively correcting both fine-grained and instance-level segmentation errors. Extensive evaluations on three public benchmarks demonstrate that QuBER outperforms state-of-the-art methods and consistently improves various UOIS methods while maintaining a fast inference time of less than 0.1 seconds. Furthermore, we show that QuBER improves the success rate of grasping target objects in cluttered environments. Code and supplementary materials are available at https://sites.google.com/view/uois-quber.

📄 PDF Abstract BibTeX arXiv:2306.16132

Code (1)

gist-ailab/QuBER 공식 구현 pytorch

Tasks

Instance SegmentationObjectSegmentation Semantic Segmentation Unseen Object Instance Segmentation

3D Indoor Instance Segmentation in an Open-World

2023-09-25 · NeurIPS 2023 11 · Mohamed El Amine Boudjoghra, Salwa K. Al Khatib, Jean Lahoud, Hisham Cholakkal 외

Existing 3D instance segmentation methods typically assume that all semantic classes to be segmented would be available during training and only seen categories are segmented at inference. We argue that such a closed-wor…

3D Instance Segmentation Instance Segmentation Segmentation Semantic Segmentation

ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR Data

2023-03-08 · Wenbang Deng, Kaihong Huang, Qinghua Yu, Huimin Lu 외

Open-world Instance Segmentation (OIS) is a challenging task that aims to accurately segment every object instance appearing in the current observation, regardless of whether these instances have been labeled in the trai…

Autonomous Navigation Clustering Instance Segmentation Open-World Instance Segmentation+3

Bayesian Semantic Instance Segmentation in Open Set World

2018-06-04 · ECCV 2018 9 · Trung Pham, Vijay Kumar B G, Thanh-Toan Do, Gustavo Carneiro 외

This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation me…

Instance Segmentation Object Segmentation Semantic Segmentation

Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning

2025-06-16 · Rohit Mohan, Julia Hindel, Florian Drews, Claudius Gläser 외

Autonomous vehicles that navigate in open-world environments may encounter previously unseen object classes. However, most existing LiDAR panoptic segmentation models rely on closed-set assumptions, failing to detect unk…

Autonomous Vehicles Navigate Panoptic Segmentation Segmentation+1

SOS: Segment Object System for Open-World Instance Segmentation With Object Priors

2024-09-22 · Christian Wilms, Tim Rolff, Maris Hillemann, Robert Johanson 외

We propose an approach for Open-World Instance Segmentation (OWIS), a task that aims to segment arbitrary unknown objects in images by generalizing from a limited set of annotated object classes during training. Our Segm…

Instance Segmentation Object Open-World Instance Segmentation Semantic Segmentation