Related papers: CASSPR: Cross Attention Single Scan Place Recognit…
Weakly supervised object localization (WSOL) aims at predicting object locations in an image using only image-level category labels. Common challenges that image classification models encounter when localizing objects are, (a) they tend to…
Accurate 3D object detection in large-scale outdoor scenes, characterized by considerable variations in object scales, necessitates features rich in both long-range and fine-grained information. While recent detectors have utilized…
Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…
Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…
Camera and lidar are important sensor modalities for robotics in general and self-driving cars in particular. The sensors provide complementary information offering an opportunity for tight sensor-fusion. Surprisingly, lidar-only methods…
Although convolutional representation of multiscale sparse tensor demonstrated its superior efficiency to accurately model the occupancy probability for the compression of geometry component of dense object point clouds, its capacity for…
This paper studies 3D LiDAR mapping with a focus on developing an updatable and localizable map representation that enables continuity, compactness and consistency in 3D maps. Traditional LiDAR Simultaneous Localization and Mapping (SLAM)…
The use of infrastructure sensor technology for traffic detection has already been proven several times. However, extrinsic sensor calibration is still a challenge for the operator. While previous approaches are unable to calibrate the…
3D object detection from point clouds plays a critical role in autonomous driving. Currently, the primary methods for point cloud processing are voxel-based and pillar-based approaches. Voxel-based methods offer high accuracy through…
Visual Place Recognition (VPR) is a major challenge for robotics and autonomous systems, with the goal of predicting the location of an image based solely on its visual features. State-of-the-art (SOTA) models extract global descriptors…
Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either…
Place recognition is a fundamental task for robotic application, allowing robots to perform loop closure detection within simultaneous localization and mapping (SLAM), and achieve relocalization on prior maps. Current range image-based…
3D detection is a critical task that enables machines to identify and locate objects in three-dimensional space. It has a broad range of applications in several fields, including autonomous driving, robotics and augmented reality. Monocular…
Ground surface detection in point cloud is widely used as a key module in autonomous driving systems. Different from previous approaches which are mostly developed for lidars with high beam resolution, e.g. Velodyne HDL-64, this paper…
Robots and autonomous vehicles should be aware of what happens in their surroundings. The segmentation and tracking of moving objects are essential for reliable path planning, including collision avoidance. We investigate this estimation…
Place Recognition is a crucial capability for mobile robot localization and navigation. Image-based or Visual Place Recognition (VPR) is a challenging problem as scene appearance and camera viewpoint can change significantly when places are…
Monocular 3D object detection poses a significant challenge in 3D scene understanding due to its inherently ill-posed nature in monocular depth estimation. Existing methods heavily rely on supervised learning using abundant 3D labels,…
Visual localization is considered to be one of the crucial parts in many robotic and vision systems. While state-of-the art methods that relies on feature matching have proven to be accurate for visual localization, its requirements for…
This paper considers online object-level mapping using partial point-cloud observations obtained online in an unknown environment. We develop and approach for fully Convolutional Object Retrieval and Symmetry-AIded Registration (CORSAIR).…
Transformer-based models have significantly advanced natural language processing and computer vision in recent years. However, due to the irregular and disordered structure of point cloud data, transformer-based models for 3D deep learning…