Unsupervised Point Cloud Registration via Training-Time Semantic Guidance
We propose CAESAR, a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training.
Citation
Coming Soon
Publications
You can also find my articles on my Google Scholar profile.
Conference Papers
TACO: Task-Aware Contrastive Learning for Joint LiDAR Localization and 3D Object Detection
This paper proposes TACO, the first Task-Aware COntrastive learning framework, which performs joint LiDAR localization and 3D object detection within a single, unified network.
Citation
Leyuan, Xing, et al. "TACO: Task-Aware Contrastive Learning for Joint LiDAR Localization and 3D Object Detection", In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
In this paper, we propose a novel unsupervised registration method termed INTEGER to incorporate high-level contextual information for reliable pseudo-label mining.
Citation
Xiong, Kezheng, et al. "Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration." The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024).
SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration
In this paper, we propose a novel method termed SPEAL to leverage skeletal representations for effective learning of intrinsic topologies of point clouds, facilitating robust capture of geometric intricacy.
Citation
Xiong, Kezheng, et al. "SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38. No. 6. 2024.