Related papers: HgPCN: A Heterogeneous Architecture for E2E Embedd…
Point cloud processing is a computational bottleneck in autonomous driving systems, especially for real-time applications, while energy efficiency remains a critical system constraint. This work presents FPPS, an FPGA-accelerated point…
The high computational, memory, and energy demands of Deep Learning (DL) applications often exceed the capabilities of battery-powered edge devices, creating difficulties in meeting task deadlines and accuracy requirements. Unlike previous…
Point clouds captured in real-world applications are often incomplete due to the limited sensor resolution, single viewpoint, and occlusion. Therefore, recovering the complete point clouds from partial ones becomes an indispensable task in…
Significant progress has been made recently in point cloud segmentation utilizing an encoder-decoder framework, which initially encodes point clouds into low-resolution representations and subsequently decodes high-resolution predictions.…
The rapid growth of 3D point cloud data, driven by applications in autonomous driving, robotics, and immersive environments, has led to criticals demand for efficient compression and quality assessment techniques. Unlike traditional 2D…
We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e.,lines, circles, and B-splines). Accordingly, our deep neural…
Point completion refers to completing the missing geometries of an object from incomplete observations. Main-stream methods predict the missing shapes by decoding a global feature learned from the input point cloud, which often leads to…
Infrastructure as a Service (IaaS) clouds have become the predominant underlying infrastructure for the operation of modern and smart technology. IaaS clouds have proven to be useful for multiple reasons such as reduced costs, increased…
With the rapid advancement of 3D sensing technologies, obtaining 3D shape information of objects has become increasingly convenient. Lidar technology, with its capability to accurately capture the 3D information of objects at long…
Deep learning technique has yielded significant improvements in point cloud completion with the aim of completing missing object shapes from partial inputs. However, most existing methods fail to recover realistic structures due to…
Deep models are capable of fitting complex high dimensional functions while usually yielding large computation load. There is no way to speed up the inference process by classical lookup tables due to the high-dimensional input and limited…
With the increased availability of 3D scanning technology, point clouds are moving into the focus of computer vision as a rich representation of everyday scenes. However, they are hard to handle for machine learning algorithms due to their…
In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical…
Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the…
A non-invasive, cloud-agnostic approach is demonstrated for extending existing cloud platforms to include checkpoint-restart capability. Most cloud platforms currently rely on each application to provide its own fault tolerance. A uniform…
Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which…
3D perception in point clouds is transforming the perception ability of future intelligent machines. Point cloud algorithms, however, are plagued by irregular memory accesses, leading to massive inefficiencies in the memory sub-system,…
PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion. However, recent works in literature…
Real-world environment-derived point clouds invariably exhibit noise across varying modalities and intensities. Hence, point cloud denoising (PCD) is essential as a preprocessing step to improve downstream task performance. Deep learning…
Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc. In this paper, we propose a set of…