Related papers: Rethinking Pseudo-LiDAR Representation

Here we propose a new design paradigm for a superconducting nanowire single photon detector that uses a multi-layer architecture that places the electric leads beneath the nanowires. This allows for a very large number of detector elements,…

LiDAR semantic segmentation plays a pivotal role in 3D scene understanding for edge applications such as autonomous driving. However, significant challenges remain for real-world deployments, particularly for on-device post-deployment…

The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors…

This paper presents a fully unsupervised deep change detection approach for mobile robots with 3D LiDAR. In unstructured environments, it is infeasible to define a closed set of semantic classes. Instead, semantic segmentation is…

Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This…

\emph{Objective and Impact Statement}. With the renaissance of deep learning, automatic diagnostic systems for computed tomography (CT) have achieved many successful applications. However, they are mostly attributed to careful expert…

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses…

Place recognition is one of the hot research fields in automation technology and is still an open issue, Camera and Lidar are two mainstream sensors used in this task, Camera-based methods are easily affected by illumination and season…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…

Advances in LiDAR sensors provide rich 3D data that supports 3D scene understanding. However, due to occlusion and signal miss, LiDAR point clouds are in practice 2.5D as they cover only partial underlying shapes, which poses a fundamental…

Monocular 3D object detection is a challenging task in the self-driving and computer vision community. As a common practice, most previous works use manually annotated 3D box labels, where the annotating process is expensive. In this paper,…

Perception in 3D has become standard practice for a large part of robotics applications. High quality 3D perception is costly. Our previous work on a nodding 2D Lidar provides high quality 3D depth information with low cost, but the sparse…

Vehicle detection and tracking is a core ingredient for developing autonomous driving applications in urban scenarios. Recent image-based Deep Learning (DL) techniques are obtaining breakthrough results in these perceptive tasks. However,…

Change point detection (CPD) methods aim to identify abrupt shifts in the distribution of input data streams. Accurate estimators for this task are crucial across various real-world scenarios. Yet, traditional unsupervised CPD techniques…

Patch attacks, one of the most threatening forms of physical attack in adversarial examples, can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous region. Certifiable patch defense can guarantee…

Modern approaches for vision-centric environment perception for autonomous navigation make extensive use of self-supervised monocular depth estimation algorithms that output disparity maps. However, when this disparity map is projected onto…

In recent years, the LiDAR images, as a 2D compact representation of 3D LiDAR point clouds, are widely applied in various tasks, e.g., 3D semantic segmentation, LiDAR point cloud compression (PCC). Among these works, the optical flow…

Training deep CNNs to capture localized image artifacts on a relatively small dataset is a challenging task. With enough images at hand, one can hope that a deep CNN characterizes localized artifacts over the entire data and their effect on…

We propose LU-Net -- for LiDAR U-Net, a new method for the semantic segmentation of a 3D LiDAR point cloud. Instead of applying some global 3D segmentation method such as PointNet, we propose an end-to-end architecture for LiDAR point cloud…

An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object…