# PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model

arXiv: https://arxiv.org/abs/2410.16545 · HTML: https://mlsanity.com/paper/2410.16545/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [Dice Loss for Data-imbalanced NLP Tasks](https://mlsanity.com/paper/1911.02855/) (2019)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1804.06278/) (2018)
- [Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding](https://mlsanity.com/paper/1902.09777/) (2019)
- [PlaneTR: Structure-Guided Transformers for 3D Plane Recovery](https://mlsanity.com/paper/2107.13108/) (2021)
- [Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning](https://mlsanity.com/paper/2312.00360/) (2023)
- [2D-3D Geometric Fusion Network using Multi-Neighbourhood Graph Convolution for RGB-D Indoor Scene Classification](https://mlsanity.com/paper/2009.11154/) (2020)
- [PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN](https://mlsanity.com/paper/2103.15428/) (2021)
- [A boundary-aware point clustering approach in Euclidean and embedding spaces for roof plane segmentation](https://mlsanity.com/paper/2309.03722/) (2023)
- [X-PDNet: Accurate Joint Plane Instance Segmentation and Monocular Depth Estimation with Cross-Task Distillation and Boundary Correction](https://mlsanity.com/paper/2309.08424/) (2023)

## Abstract (arXiv)

Plane instance segmentation from RGB-D data is a crucial research topic for many downstream tasks. However, most existing deep-learning-based methods utilize only information within the RGB bands, neglecting the important role of the depth band in plane instance segmentation. Based on EfficientSAM, a fast version of SAM, we propose a plane instance segmentation network called PlaneSAM, which can fully integrate the information of the RGB bands (spectral bands) and the D band (geometric band), thereby improving the effectiveness of plane instance segmentation in a multimodal manner. Specifically, we use a dual-complexity backbone, with primarily the simpler branch learning D-band features and primarily the more complex branch learning RGB-band features. Consequently, the backbone can effectively learn D-band feature representations even when D-band training data is limited in scale, retain the powerful RGB-band feature representations of EfficientSAM, and allow the original backbone branch to be fine-tuned for the current task. To enhance the adaptability of our PlaneSAM to the RGB-D domain, we pretrain our dual-complexity backbone using the segment anything task on large-scale RGB-D data through a self-supervised pretraining strategy based on imperfect pseudo-labels. To support the segmentation of large planes, we optimize the loss function combination ratio of EfficientSAM. In addition, Faster R-CNN is used as a plane detector, and its predicted bounding boxes are fed into our dual-complexity network as prompts, thereby enabling fully automatic plane instance segmentation. Experimental results show that the proposed PlaneSAM sets a new SOTA performance on the ScanNet dataset, and outperforms previous SOTA approaches in zero-shot transfer on the 2D-3D-S, Matterport3D, and ICL-NUIM RGB-D datasets, while only incurring a 10% increase in computational overhead compared to EfficientSAM.