Abstract: Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences ...
Abstract: Transformers are increasingly popular in computer vision, which treat an image as a sequence of image patches and learn robust global features from the sequence. However, pure transformers ...
In this paper, we propose a Rotation-Invariant Coordinate Convolution (RIC-C), which achieves natural invariance to arbitrary rotations around the input center without additional trainable parameters ...