3D perception on point-cloud is a challenging and crucial computer vision task. A point-
cloud consists of a sparse, unstructured, and unordered set of points. To understand a point …

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training
(CLIP) have shown inspirational performance on 2D visual recognition, which learns to …

Point cloud processing is very challenging, as the diverse shapes formed by irregular points
are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently …

In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we
show that the receptive field size is directly related to the performance of 3D point cloud …

Unsupervised feature learning for point clouds has been vital for large-scale point cloud
understanding. Recent deep learning based methods depend on learning global geometry …

Processing 3D data efficiently has always been a challenge. Spatial operations on large-
scale point clouds, stored as sparse data, require extra cost. Attracted by the success of …

Recent advances in deep learning for 3D point clouds have shown great promises in scene
understanding tasks thanks to the introduction of convolution operators to consume 3D point …

Features that are equivariant to a larger group of symmetries have been shown to be more
discriminative and powerful in recent studies. However, higher-order equivariant features …

Deep neural networks have established themselves as the state-of-the-art methodology in
almost all computer vision tasks to date. But their application to processing data lying on non …

In 2D image processing, some attempts decompose images into high and low frequency
components for describing edge and smooth parts respectively. Similarly, the contour and …