5 papers
Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs
Pei An, Junfeng Ding, Jiaqi Yang +3
Image-to-point-cloud (I2P) registration aims to align 2D images with 3D point clouds by establishing reliable 2D-3D correspondences. The drastic modality gap between images and poi…
SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries
Chenxu Dang, Haiyan Liu, Jason Bao +6
Semantic occupancy has emerged as a powerful representation in world models for its ability to capture rich spatial semantics. However, most existing occupancy world models rely on…
Multimodal Point Cloud Semantic Segmentation With Virtual Point Enhancement
Zaipeng Duan, Xuzhong Hu, Pei An +1
LiDAR-based 3D point cloud recognition has been proven beneficial in various applications. However, the sparsity and varying density pose a significant challenge in capturing intri…
Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection
Xuzhong Hu, Zaipeng Duan, Pei An +2
Fusing LiDAR and image features in a homogeneous BEV domain has become popular for 3D object detection in autonomous driving. However, this paradigm is constrained by the excessive…
FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detection
Chenxu Dang, Zaipeng Duan, Pei An +3
Recent top-performing temporal 3D detectors based on Lidars have increasingly adopted region-based paradigms. They first generate coarse proposals, followed by encoding and fusing…