Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
This addresses the need for scalable and generalizable 3D segmentation for applications like robotics or AR/VR, though it is incremental as it adapts existing 2D techniques to 3D.
The paper tackles the problem of labor-intensive manual annotations and poor generalization in 3D scene segmentation by proposing Segment3D, a method that uses 2D foundation models to automatically generate training labels, resulting in high-quality, fine-grained 3D segmentation masks without manual labels.
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.