Related papers: VoxelTrack: Exploring Voxel Representation for 3D …

Visual object tracking (VOT) plays a pivotal role in unmanned aerial vehicle (UAV) applications. Addressing the trade-off between accuracy and efficiency, especially under challenging conditions like unpredictable occlusion, remains a…

3D object tracking in point clouds is still a challenging problem due to the sparsity of LiDAR points in dynamic environments. In this work, we propose a Siamese voxel-to-BEV tracker, which can significantly improve the tracking performance…

In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data. The majority of learning-based point cloud compression methods work on a downsampled representation of the data.…

The recent success of neural networks enables a better interpretation of 3D point clouds, but processing a large-scale 3D scene remains a challenging problem. Most current approaches divide a large-scale scene into small regions and combine…

Feature fusion and similarity computation are two core problems in 3D object tracking, especially for object tracking using sparse and disordered point clouds. Feature fusion could make similarity computing more efficient by including…

Estimating the states of surrounding traffic participants stays at the core of autonomous driving. In this paper, we study a novel setting of this problem: model-free single-object tracking (SOT), which takes the object state in the first…

Single-stream architectures using Vision Transformer (ViT) backbones show great potential for real-time UAV tracking recently. However, frequent occlusions from obstacles like buildings and trees expose a major drawback: these models often…

While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds. Existing methods attempt to overcome this issue by…

Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and signaling the model's certainty in its predictions to the…

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…

With the prevalence of LiDAR sensors in autonomous driving, 3D object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames…

We revisit Semantic Scene Completion (SSC), a useful task to predict the semantic and occupancy representation of 3D scenes, in this paper. A number of methods for this task are always based on voxelized scene representations for keeping…

3D single object tracking with point clouds is a critical task in 3D computer vision. Previous methods usually input the last two frames and use the predicted box to get the template point cloud in previous frame and the search area point…

3D Single Object Tracking (3D-SOT) aims to localize a target object across a sequence of LiDAR point clouds, given its 3D bounding box in the first frame. Recent methods have adopted a memory-based approach to utilize previously observed…

Accurate 3D object detection from point clouds has become a crucial component in autonomous driving. However, the volumetric representations and the projection methods in previous works fail to establish the relationships between the local…

The point cloud based 3D single object tracking has drawn increasing attention. Although many breakthroughs have been achieved, we also reveal two severe issues. By extensive analysis, we find the prediction manner of current approaches is…

The goal of this paper is to compare surface-based and volumetric 3D object shape representations, as well as viewer-centered and object-centered reference frames for single-view 3D shape prediction. We propose a new algorithm for…

3D LiDAR-based single object tracking (SOT) relies on sparse and irregular point clouds, posing challenges from geometric variations in scale, motion patterns, and structural complexity across object categories. Current category-specific…

We present an efficient voxelization method to encode the geometry and attributes of 3D point clouds obtained from autonomous vehicles. Due to the circular scanning trajectory of sensors, the geometry of LiDAR point clouds is inherently…

Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the tracked targets, the genuine bounding box fails to capture…