Related papers: Canonical Voting: Towards Robust Oriented Bounding…
Lidar based 3D object detection and classification tasks are essential for autonomous driving(AD). A lidar sensor can provide the 3D point cloud data reconstruction of the surrounding environment. However, real time detection in 3D point…
Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments.…
Limited capture range, and the requirement to provide high quality initialization for optimization-based 2D/3D image registration methods, can significantly degrade the performance of 3D image reconstruction and motion compensation…
3D object detection and pose estimation has been studied extensively in recent decades for its potential applications in robotics. However, there still remains challenges when we aim at detecting multiple objects while retaining low false…
Interference detection of arbitrary geometric objects is not a trivial task due to the heavy computational load imposed by implementation issues. The hierarchically structured bounding boxes help us to quickly isolate the contour of…
We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule decompositions of objects through permutation-equivariant attention, and self-supervise the process by training with pairs of randomly rotated…
This paper aims to design a 3D object detection model from 2D images taken by monocular cameras by combining the estimated bird's-eye view elevation map and the deep representation of object features. The proposed model has a pre-trained…
Distribution-to-distribution (D2D) point cloud registration techniques such as the Normal Distributions Transform (NDT) can align point clouds sampled from unstructured scenes and provide accurate bounds of their own solution error…
As an important part of linear perspective, vanishing points (VPs) provide useful clues for mapping objects from 2D photos to 3D space. Existing methods are mainly focused on extracting structural features such as lines or contours and then…
In the field of remote sensing, we often utilize oriented bounding boxes (OBB) to bound the objects. This approach significantly reduces the overlap among dense detection boxes and minimizes the inclusion of background content within the…
3D object classification is a crucial problem due to its significant practical relevance in many fields, including computer vision, robotics, and autonomous driving. Although deep learning methods applied to point clouds sampled on CAD…
Keypoint-based methods are a relatively new paradigm in object detection, eliminating the need for anchor boxes and offering a simplified detection framework. Keypoint-based CornerNet achieves state of the art accuracy among single-stage…
While modern text-to-image diffusion models generate high-fidelity images, they offer limited control over the spatial and geometric structure of the output. To address this, we introduce and evaluate two ControlNets specialized for…
3D object detection has been wildly studied in recent years, especially for robot perception systems. However, existing 3D object detection is under a closed-set condition, meaning that the network can only output boxes of trained classes.…
Voxel-based 3D object classification has been thoroughly studied in recent years. Most previous methods convert the classic 2D convolution into a 3D form that will be further applied to objects with binary voxel representation for…
Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…
We apply convolutional neural networks (CNN) to the problem of image orientation detection in the context of determining the correct orientation (from 0, 90, 180, and 270 degrees) of a consumer photo. The problem is especially important for…
The quality of training datasets for deep neural networks is a key factor contributing to the accuracy of resulting models. This effect is amplified in difficult tasks such as object detection. Dealing with errors in datasets is often…
Recognizing scenes and objects in 3D from a single image is a longstanding goal of computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets and scalable solutions have led to unprecedented advances. In 3D,…
Methods tackling multi-object tracking need to estimate the number of targets in the sensing area as well as to estimate their continuous state. While the majority of existing methods focus on data association, precise state (3D pose)…