6 papers
Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration
Shiqi Li, Jihua Zhu, Yifan Xie +2
Multiview point cloud registration plays a crucial role in robotics, automation, and computer vision fields. This paper concentrates on pose graph construction and motion synchroni…
Hyperbolic Image-and-Pointcloud Contrastive Learning for 3D Classification
Naiwen Hu, Haozhe Cheng, Yifan Xie +2
3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarit…
3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
Naiwen Hu, Haozhe Cheng, Yifan Xie +2
Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data…
Multiple Rotation Averaging with Constrained Reweighting Deep Matrix Factorization
Shiqi Li, Jihua Zhu, Yifan Xie +4
Multiple rotation averaging plays a crucial role in computer vision and robotics domains. The conventional optimization-based methods optimize a nonlinear cost function based on ce…
Incremental Multiview Point Cloud Registration with Two-stage Candidate Retrieval
Shiqi Li, Jihua Zhu, Yifan Xie +1
Multiview point cloud registration serves as a cornerstone of various computer vision tasks. Previous approaches typically adhere to a global paradigm, where a pose graph is initia…
A Classifier-Free Incremental Learning Framework for Scalable Medical Image Segmentation
Xiaoyang Chen, Hao Zheng, Yifang Xie +2
Current methods for developing foundation models in medical image segmentation rely on two primary assumptions: a fixed set of classes and the immediate availability of a substanti…