Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation
This addresses the problem of limited training data for open-vocabulary 3D segmentation, enabling more flexible scene understanding for applications in robotics and AR/VR, though it is incremental in scaling up existing methods.
The paper tackles open-vocabulary 3D scene understanding by introducing a novel data generation pipeline and training framework, resulting in state-of-the-art performance on tasks like ScanNet200 and Matterport3D with a dataset of over 30K scenes and 5.6M mask-text pairs.
We tackle open-vocabulary 3D scene understanding by introducing a novel data generation pipeline and training framework. Our method addresses three critical requirements for effective training: precise 3D region segmentation, comprehensive textual descriptions, and sufficient dataset scale. By leveraging state-of-the-art open-vocabulary image segmentation models and region-aware Vision-Language Models, we develop an automatic pipeline that generates high-quality 3D mask-text pairs. Applying this pipeline to multiple 3D scene datasets, we create Mosaic3D-5.6M, a dataset of over 30K annotated scenes with 5.6M mask-text pairs, significantly larger than existing datasets. Building upon this data, we propose Mosaic3D, a foundation model combining a 3D encoder trained with contrastive learning and a lightweight mask decoder for open-vocabulary 3D semantic and instance segmentation. Our approach achieves state-of-the-art results on open-vocabulary 3D semantic and instance segmentation tasks including ScanNet200, Matterport3D, and ScanNet++, with ablation studies validating the effectiveness of our large-scale training data.