Related papers: SVT-Net: Super Light-Weight Sparse Voxel Transform…

Object detection is a crucial task for autonomous driving. In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as well…

In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at…

The spatial attention mechanism captures long-range dependencies by aggregating global contextual information to each query location, which is beneficial for semantic segmentation. In this paper, we present a sparse spatial attention…

Support Vector Machines (SVMs) are an important tool for performing classification on scattered data, where one usually has to deal with many data points in high-dimensional spaces. We propose solving SVMs in primal form using feature maps…

We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal contributions. First, we develop a…

In this paper, we present TransMVSNet, based on our exploration of feature matching in multi-view stereo (MVS). We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer…

Visual localization is of great importance in robotics and computer vision. Recently, scene coordinate regression based methods have shown good performance in visual localization in small static scenes. However, it still estimates camera…

While large models have achieved significant progress in computer vision, challenges such as optimization complexity, the intricacy of transformer architectures, computational constraints, and practical application demands highlight the…

Point cloud based retrieval for place recognition is still a challenging problem due to drastic appearance and illumination changes of scenes in changing environments. Existing deep learning based global descriptors for the retrieval task…

LiDAR-based semantic perception tasks are critical yet challenging for autonomous driving. Due to the motion of objects and static/dynamic occlusion, temporal information plays an essential role in reinforcing perception by enhancing and…

3D object detectors for point clouds often rely on a pooling-based PointNet to encode sparse points into grid-like voxels or pillars. In this paper, we identify that the common PointNet design introduces an information bottleneck that…

Deep neural networks face numerous challenges in hyperspectral image classification, including high-dimensional data, sparse ground object distributions, and spectral redundancy, which often lead to classification overfitting and limited…

We present a novel lightweight convolutional neural network for point cloud analysis. In contrast to many current CNNs which increase receptive field by downsampling point cloud, our method directly operates on the entire point sets without…

Existing methods for Salient Object Detection in Optical Remote Sensing Images (ORSI-SOD) mainly adopt Convolutional Neural Networks (CNNs) as the backbone, such as VGG and ResNet. Since CNNs can only extract features within certain…

We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large…

We present Hybrid Voxel Network (HVNet), a novel one-stage unified network for point cloud based 3D object detection for autonomous driving. Recent studies show that 2D voxelization with per voxel PointNet style feature extractor leads to…

Large transformer models are proving to be a powerful tool for 3D vision and novel view synthesis. However, the standard Transformer's well-known quadratic complexity makes it difficult to scale these methods to large scenes. To address…

Video Salient Document Detection (VSDD) is an essential task of practical computer vision, which aims to highlight visually salient document regions in video frames. Previous techniques for VSDD focus on learning features without…

Although large-scale labeled data are essential for deep convolutional neural networks (ConvNets) to learn high-level semantic visual representations, it is time-consuming and impractical to collect and annotate large-scale datasets. A…

Semantic image segmentation plays a pivotal role in many vision applications including autonomous driving and medical image analysis. Most of the former approaches move towards enhancing the performance in terms of accuracy with a little…