2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision

Yang, Cheng-Kun; Chen, Min-Hung; Chuang, Yung-Yu; Lin, Yen-Yu

doi:10.1109/iccv51070.2023.00096

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Other2

Article1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

Umam,

Yang,

Chen

et al. 2024

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

Umam,

Yang,

Chen

et al. 2024

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle

Kweon,

Kim,

Yoon

2024

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Material augmented semantic segmentation of point clouds for building elements

Liang,

Yeoh,

Chua

2024

Computer aided Civil Eng

View full text Add to dashboard Cite

Point clouds are utilized to enable automated engineering applications for their ability to represent spatial geometry. However, they inherently lack detailed surface textures, posing challenges in differentiating objects at the texture level. Hence, this study introduces a 2D–3D fusing approach, leveraging material properties recognized from registered images as an augmented feature to enhance deep learning methods for the segmentation of building elements within point clouds. The proposed method was evaluated quantitatively on a 3D indoor data set with an implementation in an office room. The results are promising, showing improvement in recognition performance, particularly for objects with similar geometry but having different material properties. For instance, the segmentation of boards increased by 70.87%, and doors improved by 41.06% using the PointNet architecture. This enhanced segmentation not only reduces the time for interpreting point clouds but also has the potential to benefit downstream applications such as Scan‐to‐building information modeling (BIM), as defining regions for objects is essential.

show abstract

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision

Cited by 3 publications

References 58 publications

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle

Material augmented semantic segmentation of point clouds for building elements

Contact Info

Product

Resources

About