pith. sign in

arxiv: 2406.17741 · v2 · pith:FBNZNZV6new · submitted 2024-06-25 · 💻 cs.CV · cs.AI

Point-SAM: Promptable 3D Segmentation Model for Point Clouds

classification 💻 cs.CV cs.AI
keywords modelpoint-samsegmentationcloudsdatamodelspointpromptable
0
0 comments X
read the original abstract

The development of 2D foundation models for image segmentation has been significantly advanced by the Segment Anything Model (SAM). However, achieving similar success in 3D models remains a challenge due to issues such as non-unified data formats, poor model scalability, and the scarcity of labeled data with diverse masks. To this end, we propose a 3D promptable segmentation model Point-SAM, focusing on point clouds. We employ an efficient transformer-based architecture tailored for point clouds, extending SAM to the 3D domain. We then distill the rich knowledge from 2D SAM for Point-SAM training by introducing a data engine to generate part-level and object-level pseudo-labels at scale from 2D SAM. Our model outperforms state-of-the-art 3D segmentation models on several indoor and outdoor benchmarks and demonstrates a variety of applications, such as interactive 3D annotation and zero-shot 3D instance proposal. Codes and demo can be found at https://github.com/zyc00/Point-SAM.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. 3AM: 3egment Anything with Geometric Consistency in Videos

    cs.CV 2026-01 unverdicted novelty 7.0

    3AM integrates MUSt3R 3D features into SAM2 via a Feature Merger and FOV-aware sampling to deliver geometry-consistent video object segmentation from RGB alone, with large gains on wide-baseline datasets.

  2. PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding

    cs.CV 2026-06 unverdicted novelty 6.0

    PAR3D is a part-aware 3D-MLLM framework with ScenePart dataset, Part-Aware 3D Representation Learning, and Hierarchical Segmentation Query Generation to improve part-level 3D scene understanding.

  3. ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings

    cs.CV 2026-05 unverdicted novelty 6.0

    A point-Transformer interactive 3D instance segmentation model handles multiple clicks jointly in one pass and reports over 20% mIoU gains versus baselines plus 8-10% cross-dataset improvement for one-click-per-instan...

  4. ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings

    cs.CV 2026-05 unverdicted novelty 6.0

    ClickSeg3D uses a point Transformer encoder and hierarchical mask decoder with semantic embeddings to enable single-pass multi-object 3D interactive segmentation from sparse points, reporting over 20% mIoU gains versu...

  5. R3D: Revisiting 3D Policy Learning

    cs.CV 2026-04 unverdicted novelty 5.0

    A transformer 3D encoder plus diffusion decoder architecture, with 3D-specific augmentations, outperforms prior 3D policy methods on manipulation benchmarks by improving training stability.

  6. S2AM3D: Scale-controllable Part Segmentation of 3D Point Clouds

    cs.CV 2025-11 unverdicted novelty 5.0

    S2AM3D combines multi-view 2D priors with 3D contrastive learning and a scale-aware decoder to deliver consistent, granularity-controllable part segmentation on point clouds, supported by a new dataset exceeding 100k samples.