# When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation with Weak-and-Noisy Supervision

arXiv: https://arxiv.org/abs/2309.00828 · HTML: https://mlsanity.com/paper/2309.00828/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 37 references that are in the map.
- First posted on arXiv 2 Sep 2023.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [Inpaint Anything: Segment Anything Meets Image Inpainting](https://mlsanity.com/paper/2304.06790/) (2023)
- [Segment Anything in Medical Images](https://mlsanity.com/paper/2304.12306/) (2023)
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://mlsanity.com/paper/1812.07003/) (2018)
- [Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts](https://mlsanity.com/paper/2012.09165/) (2020)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [Mask2Former for Video Instance Segmentation](https://mlsanity.com/paper/2112.10764/) (2021)
- [Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/1906.01140/) (2019)
- [3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2003.13867/) (2020)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [Segment Any Point Cloud Sequences by Distilling Vision Foundation Models](https://mlsanity.com/paper/2306.09347/) (2023)
- [Superpoint Transformer for 3D Scene Instance Segmentation](https://mlsanity.com/paper/2211.15766/) (2022)
- [Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks](https://mlsanity.com/paper/2108.07478/) (2021)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution](https://mlsanity.com/paper/2303.00246/) (2023)
- [Learning Gaussian Instance Segmentation in Point Clouds](https://mlsanity.com/paper/2007.09860/) (2020)
- [Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics](https://mlsanity.com/paper/2307.16620/) (2023)
- [MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation](https://mlsanity.com/paper/1902.04478/) (2019)
- [Detect Any Shadow: Segment Anything for Video Shadow Detection](https://mlsanity.com/paper/2305.16698/) (2023)
- [Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation](https://mlsanity.com/paper/2207.09084/) (2022)

## Built on by (most cited first, 9 of 9)

- [ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation](https://mlsanity.com/paper/2311.14262/) (2023)
- [Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2403.10001/) (2024)
- [3x2: 3D Object Part Segmentation by 2D Semantic Correspondences](https://mlsanity.com/paper/2407.09648/) (2024)
- [LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives](https://mlsanity.com/paper/2503.18384/) (2025)
- [Sketchy Bounding-box Supervision for 3D Instance Segmentation](https://mlsanity.com/paper/2505.16399/) (2025)
- [Investigating Domain Gaps for Indoor 3D Object Detection](https://mlsanity.com/paper/2508.17439/) (2025)
- [You Only Click Once: Single Point Weakly Supervised 3D Instance Segmentation for Autonomous Driving](https://mlsanity.com/paper/2502.19698/) (2025)
- [BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation](https://mlsanity.com/paper/2510.12182/) (2025)
- [GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence](https://mlsanity.com/paper/2606.08014/) (2026)

## Abstract (arXiv)

Learning from bounding-boxes annotations has shown great potential in weakly-supervised 3D point cloud instance segmentation. However, we observed that existing methods would suffer severe performance degradation with perturbed bounding box annotations. To tackle this issue, we propose a complementary image prompt-induced weakly-supervised point cloud instance segmentation (CIP-WPIS) method. CIP-WPIS leverages pretrained knowledge embedded in the 2D foundation model SAM and 3D geometric prior to achieve accurate point-wise instance labels from the bounding box annotations. Specifically, CP-WPIS first selects image views in which 3D candidate points of an instance are fully visible. Then, we generate complementary background and foreground prompts from projections to obtain SAM 2D instance mask predictions. According to these, we assign the confidence values to points indicating the likelihood of points belonging to the instance. Furthermore, we utilize 3D geometric homogeneity provided by superpoints to decide the final instance label assignments. In this fashion, we achieve high-quality 3D point-wise instance labels. Extensive experiments on both Scannet-v2 and S3DIS benchmarks demonstrate that our method is robust against noisy 3D bounding-box annotations and achieves state-of-the-art performance.