SNAP: Towards Segmenting Anything in Any Point Cloud

Aniket Gupta, Hanhui Wang, Charles Saunders, Aruni RoyChowdhury, Hanumant Singh, Huaizu Jiang

Keywords: Promptable point cloud segmentation, Interactive segmentation, Multi-domain segmentation, Semi-automated labeling, Zero-shot point cloud generalization

TL;DR: We present SNAP, a interactive point cloud segmentation model that generalizes across outdoor, indoor and aerial scenes.

Abstract:

Interactive 3D point cloud segmentation enables efficient annotation of complex 3D scenes through user-guided prompts. However, current approaches are typically restricted in scope to a single domain (indoor or outdoor), and to a single form of user interaction (either spatial clicks or textual prompts). Moreover, training on multiple datasets often leads to negative transfer, resulting in domain-specific tools that lack generalizability.

To address these limitations, we present SNAP (Segment aNything in Any Point cloud), a unified model for interactive 3D segmentation that supports both point-based and text-based prompts across diverse domains. Our approach achieves cross-domain generalizability by training on 7 datasets spanning indoor, outdoor, and aerial environments while employing domain-adaptive normalization to prevent negative transfer. For text-prompted segmentation, we automatically generate mask proposals without human intervention and match them against CLIP embeddings of textual queries, enabling both panoptic and open-vocabulary segmentation.

Extensive experiments demonstrate that SNAP consistently delivers high-quality segmentation results. We achieve state-of-the-art performance on 8 out of 9 zero-shot benchmarks for spatial-prompted segmentation and demonstrate competitive results on all 5 text-prompted benchmarks. These results show that a unified model can match or exceed specialized domain-specific approaches, providing a practical tool for scalable 3D annotation. Project page is at https://neu-vi.github.io/SNAP/

Submission Number: 305