In this paper, we propose a novel local descriptor-based framework, called You Only Hypothesize Once (YOHO), for the registration of two unaligned point clouds. In contrast to …
Equivariance has been a long-standing concern in various fields ranging from computer vision to physical modeling. Most previous methods struggle with generality, simplicity, and …
Z Zhang, BS Hua, SK Yeung - International Journal of Computer Vision, 2022 - Springer
Abstract 3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene …
We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by synchronizing the maps that relate learned functions defined on the point clouds. Even …
In this work, we introduce Deep Bingham Networks (DBN), a generic framework that can naturally handle pose-related uncertainties and ambiguities arising in almost all real life …
J Chen, Y Yin, T Birdal, B Chen… - Proceedings of the …, 2022 - openaccess.thecvf.com
Regressing rotations on SO (3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non …
Transformation equivariance has been widely investigated in 3D point cloud representation learning for more informative descriptors, which formulates the change of the representation …
Capsule networks were proposed as an alternative approach to Convolutional Neural Networks (CNNs) for learning object-centric representations, which can be leveraged for …
Even though considerable progress has been made in deep learning-based 3D point cloud processing, how to obtain accurate correspondences for robust registration remains a major …