2026

CompetitorFormer: Mitigating Query Conflicts for 3D Instance Segmentation via Competitive Strategy
CompetitorFormer: Mitigating Query Conflicts for 3D Instance Segmentation via Competitive Strategy

Duanchu Wang, Junjie Yang, Haoran Gong, Jing Liu, Di Wang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification confidence and Io......
CompetitorFormer: Mitigating Query Conflicts for 3D Instance Segmentation via Competitive Strategy

Duanchu Wang, Junjie Yang, Haoran Gong, Jing Liu, Di Wang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries......
BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds
BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds

Tongyan Hua, Haoran Gong, Yuan Liu, Di Wang, Ying-Cong Chen, Wufan Zhao ( Equal contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

We introduce BuildAnyPoint, a novel generative framework for structured 3D building reconstruction from point clouds with diverse distributions, such as those captured by airborne LiDAR and Structu......
BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds

Tongyan Hua, Haoran Gong, Yuan Liu, Di Wang, Ying-Cong Chen, Wufan Zhao ( Equal contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

We introduce BuildAnyPoint, a novel generative framework for structured 3D building reconstruction from point clouds with diverse distributions, su......

2025

Robust Building Wireframe Reconstruction: A Hypergraph and Transformer-Enhanced Framework for Large-Scale and Real-World Urban Point Clouds
Robust Building Wireframe Reconstruction: A Hypergraph and Transformer-Enhanced Framework for Large-Scale and Real-World Urban Point Clouds

Haoran Gong, Jing Liu, Rui Tong, Fuqiang Tian, Di Wang

International Journal of Remote Sensing 2025

Accurate 3D building reconstruction is crucial for advancing urban digital twinning, city planning, and sustainable development. As a key architectural component, rooftops facilitate urban energy m......
Robust Building Wireframe Reconstruction: A Hypergraph and Transformer-Enhanced Framework for Large-Scale and Real-World Urban Point Clouds

Haoran Gong, Jing Liu, Rui Tong, Fuqiang Tian, Di Wang

International Journal of Remote Sensing 2025

Accurate 3D building reconstruction is crucial for advancing urban digital twinning, city planning, and sustainable development. As a key architect......
Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds
Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds

Haoran Gong, Haodong Wang, Di Wang

IEEE Geoscience and Remote Sensing Letters 2025

Semantic segmentation of large-scale outdoor point clouds is of significant importance in environment perception and scene understanding. However, this task continues to present a significant resea......
Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds

Haoran Gong, Haodong Wang, Di Wang

IEEE Geoscience and Remote Sensing Letters 2025

Semantic segmentation of large-scale outdoor point clouds is of significant importance in environment perception and scene understanding. However, ......
Enhancing 3D Instance Segmentation with Dense Connection Decoder and Layer-Aware Fusion
Enhancing 3D Instance Segmentation with Dense Connection Decoder and Layer-Aware Fusion

Duanchu Wang, Haoran Gong, Di Wang

IEEE Robotics and Automation Letters 2025

3D instance segmentation (3DIS) aims to identify object instances in a 3D scene by predicting binary foreground masks with corresponding semantic labels. Transformer-based methods have demonstrated......
Enhancing 3D Instance Segmentation with Dense Connection Decoder and Layer-Aware Fusion

Duanchu Wang, Haoran Gong, Di Wang

IEEE Robotics and Automation Letters 2025

3D instance segmentation (3DIS) aims to identify object instances in a 3D scene by predicting binary foreground masks with corresponding semantic l......
Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Dataset
Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Dataset

Jing Liu, Duanchu Wang, Haoran Gong, Chongyu Wang, Jihua Zhu, Di Wang

Remote Sensing of Environment 2025

Understanding and analyzing the spatial semantics and structure of forests is essential for accurate forest resource monitoring and ecosystem research. However, the lack of large-scale and annotate......
Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Dataset

Jing Liu, Duanchu Wang, Haoran Gong, Chongyu Wang, Jihua Zhu, Di Wang

Remote Sensing of Environment 2025

Understanding and analyzing the spatial semantics and structure of forests is essential for accurate forest resource monitoring and ecosystem resea......