Related papers: 3D Siamese Voxel-to-BEV Tracker for Sparse Point C…

LiDAR-based sparse 3D object detection plays a crucial role in autonomous driving applications due to its computational efficiency advantages. Existing methods either use the features of a single central voxel as an object proxy, or treat…

With the attention gained by camera-only 3D object detection in autonomous driving, methods based on Bird-Eye-View (BEV) representation especially derived from the forward view transformation paradigm, i.e., lift-splat-shoot (LSS), have…

Accurate 3D bird's-eye view (BEV) object detection is essential for autonomous driving, and depends strongly on effective multimodal representations from complementary sensors such as cameras and LiDAR. Multimodal masked autoencoders have…

Object detection in 3D point clouds is a crucial task in a range of computer vision applications including robotics, autonomous cars, and augmented reality. This work addresses the object detection task in 3D point clouds using a highly…

Siamese networks have gained popularity as a method for modeling text semantic similarity. Traditional methods rely on pooling operation to compress the semantic representations from Transformer blocks in encoding, resulting in…

Identifying moving objects is an essential capability for autonomous systems, as it provides critical information for pose estimation, navigation, collision avoidance, and static map construction. In this paper, we present MotionBEV, a fast…

Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previous approaches formulate it as a problem of surface…

To address the challenge of capturing highly discriminative features in ther-mal infrared (TIR) tracking, we propose a novel Siamese tracker based on cross-channel fine-grained feature learning and progressive fusion. First, we introduce a…

3D single object tracking (SOT) methods based on appearance matching has long suffered from insufficient appearance information incurred by incomplete, textureless and semantically deficient LiDAR point clouds. While motion paradigm…

Scene flow estimation aims to generate the 3D motion field of points between two consecutive frames of point clouds, which has wide applications in various fields. Existing point-based methods ignore the irregularity of point clouds and…

Point clouds captured by different sensors such as RGB-D cameras and LiDAR possess non-negligible domain gaps. Most existing methods design different network architectures and train separately on point clouds from various sensors.…

3D object detection with LiDAR point clouds plays an important role in autonomous driving perception module that requires high speed, stability and accuracy. However, the existing point-based methods are challenging to reach the speed…

Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed. Unlike classification-based CNNs, deep similarity networks are specifically designed to address the image similarity problem,…

Point cloud-based large scale place recognition is fundamental for many applications like Simultaneous Localization and Mapping (SLAM). Although many models have been proposed and have achieved good performance by learning short-range local…

In this paper, we propose M$^2$BEV, a unified framework that jointly performs 3D object detection and map segmentation in the Birds Eye View~(BEV) space with multi-camera image inputs. Unlike the majority of previous works which separately…

Recently, convolutional neural network (CNN) has attracted much attention in different areas of computer vision, due to its powerful abstract feature representation. Visual object tracking is one of the interesting and important areas in…

Vision-based bird's-eye-view (BEV) 3D object detection has advanced significantly in autonomous driving by offering cost-effectiveness and rich contextual information. However, existing methods often construct BEV representations by…

Bird's-Eye View (BEV) features are popular intermediate scene representations shared by the 3D backbone and the detector head in LiDAR-based object detectors. However, little research has been done to investigate how to incorporate…

Visual object tracking is an important task in computer vision, which has many real-world applications, e.g., video surveillance, visual navigation. Visual object tracking also has many challenges, e.g., object occlusion and deformation. To…

In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT). VPIT is the first method that uses voxel pseudo images for 3D SOT. The input point cloud is structured by…