2023/12/28 by Rui Huang, Huang, Rui, Songyou Peng +13 · 25 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Infrastructure Maintenance and Monitoring
paper · pdf · doi:10.48550/arxiv.2312.17232
openalex publication_date 2023/12/28 · openalex created_date 2023/12/31 · openalex updated_date 2026/07/28
Current 3D scene segmentation methods are heavily dependent on manually annotated 3D training datasets. Such manual annotations are labor-intensive, and often lack fine-grained details. Importantly, models trained on this data typically struggle to recognize object classes beyond the annotated classes, i.e., they do not generalize well to unseen domains and require additional domain-specific annotations. In contrast, 2D foundation models demonstrate strong generalization and impressive zero-shot abilities, inspiring us to incorporate these characteristics from 2D models into 3D models. Therefore, we explore the use of image segmentation foundation models to automatically generate training labels for 3D segmentation. We propose Segment3D, a method for class-agnostic 3D scene segmentation that produces high-quality 3D segmentation masks. It improves over existing 3D segmentation models (especially on fine-grained masks), and enables easily adding new training data to further boost the segmentation performance -- all without the need for manual training labels.