Related papers: OctSqueeze: Octree-Structured Entropy Model for Li…
Volume-based reconstruction is usually expensive both in terms of memory consumption and runtime. Especially for sparse geometric structures, volumetric representations produce a huge computational overhead. We present an efficient way to…
Efficient storage of large-scale point cloud data has become increasingly challenging due to advancements in scanning technology. Recent deep learning techniques have revolutionized this field; However, most existing approaches rely on…
The $k^2$-tree is a compact data structure designed to efficiently store sparse binary matrices by leveraging both sparsity and clustering of nonzero elements. This representation supports efficiently navigational operations and complex…
We propose octree-based transformers, named OctFormer, for 3D point cloud learning. OctFormer can not only serve as a general and effective backbone for 3D point cloud segmentation and object detection but also have linear complexity and is…
Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting and immense demands for computation and storage, which…
Machine learning-based applications are increasingly prevalent in IoT devices. The power and storage constraints of these devices make it particularly challenging to run modern neural networks, limiting the number of new applications that…
The incorporation of LiDAR technology into some high-end smartphones has unlocked numerous possibilities across various applications, including photography, image restoration, augmented reality, and more. In this paper, we introduce a novel…
Since the data volume of LiDAR point clouds is very huge, efficient compression is necessary to reduce their storage and transmission costs. However, existing learning-based compression methods do not exploit the inherent angular resolution…
We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the…
Many 3D generative models rely on variational autoencoders (VAEs) to learn compact shape representations. However, existing methods encode all shapes into a fixed-size token, disregarding the inherent variations in scale and complexity…
Odometry is a critical task for autonomous systems for self-localization and navigation. We propose a novel LiDAR-Visual odometry framework that integrates LiDAR point clouds and images for accurate and robust pose estimation. Our method…
We present a deep convolutional decoder architecture that can generate volumetric 3D outputs in a compute- and memory-efficient manner by using an octree representation. The network learns to predict both the structure of the octree, and…
Optimizing computation in an edge-cloud system is an important yet challenging problem. In this paper, we consider a three-way trade-off between bit rate, classification accuracy, and encoding complexity in an edge-cloud image…
LiDAR provides accurate geometric measurements of the 3D world. Unfortunately, dense LiDARs are very expensive and the point clouds captured by low-beam LiDAR are often sparse. To address these issues, we present UltraLiDAR, a data-driven…
3D visual content streaming is a key technology for emerging 3D telepresence and AR/VR applications. One fundamental element underlying the technology is a versatile 3D representation that is capable of producing high-quality renders and…
This paper presents error-bounded lossy compression tailored for particle datasets from diverse scientific applications in cosmology, fluid dynamics, and fusion energy sciences. As today's high-performance computing capabilities advance,…
Currently, visual odometry and LIDAR odometry are performing well in pose estimation in some typical environments, but they still cannot recover the localization state at high speed or reduce accumulated drifts. In order to solve these…
Efficient 3D LiDAR point cloud compression (LPCC) and streaming are critical for edge server-assisted robotic systems, enabling real-time communication with compact data representations. A widely adopted approach represents LiDAR point…
Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…
3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge…