Related papers: Cross-Level Cross-Scale Cross-Attention Network fo…

This paper introduces the Point Cloud Network (PCN) architecture, a novel implementation of linear layers in deep learning networks, and provides empirical evidence to advocate for its preference over the Multilayer Perceptron (MLP) in…

3D point cloud segmentation has a wide range of applications in areas such as autonomous driving, augmented reality, virtual reality and digital twins. The point cloud data collected in real scenes often contain small objects and categories…

Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…

Transformers have shown superior performance on various computer vision tasks with their capabilities to capture long-range dependencies. Despite the success, it is challenging to directly apply Transformers on point clouds due to their…

Directly learning features from the point cloud has become an active research direction in 3D understanding. Existing learning-based methods usually construct local regions from the point cloud and extract the corresponding features.…

Among 2D convolutional networks on point clouds, point-based approaches consume point clouds of fixed size directly. By analysis of PointNet, a pioneer in introducing deep learning into point sets, we reveal that current point-based methods…

The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets. However, compared with 2D image datasets, the current pre-training data of 3D point cloud is limited. To overcome this…

In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational…

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…

Facial expression recognition faces challenges where labeled significant features in datasets are mixed with unlabeled redundant ones. In this paper, we introduce Cross Similarity Attention (CSA) to mine richer intrinsic information from…

Hyperspectral image (HSI) classification faces critical challenges, including high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. While CNNs excel at local feature…

We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well…

Point cloud segmentation, which helps us understand the environment of specific structures and objects, can be performed in class-specific and class-agnostic ways. We propose a novel region-based transformer model called Region-Transformer…

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naively applying convolutions on this lattice scales…

Scene parsing is a great challenge for real-time semantic segmentation. Although traditional semantic segmentation networks have made remarkable leap-forwards in semantic accuracy, the performance of inference speed is unsatisfactory.…

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in…

Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction paradigm in…

Environment perception including detection, classification, tracking, and motion prediction are key enablers for automated driving systems and intelligent transportation applications. Fueled by the advances in sensing technologies and…

We propose a unified point cloud video self-supervised learning framework for object-centric and scene-centric data. Previous methods commonly conduct representation learning at the clip or frame level and cannot well capture fine-grained…

We present Attention Zoom, a modular and model-agnostic spatial attention mechanism designed to improve feature extraction in convolutional neural networks (CNNs). Unlike traditional attention approaches that require architecture-specific…