Related papers: D-Align: Dual Query Co-attention Network for 3D Ob…

With the prevalence of LiDAR sensors in autonomous driving, 3D object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames…

Lidar point cloud distortion from moving object is an important problem in autonomous driving, and recently becomes even more demanding with the emerging of newer lidars, which feature back-and-forth scanning patterns. Accurately estimating…

Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently. In this paper, we propose a Label-Guided auxiliary training method for 3D object detection (LG3D), which serves as…

3-D object detection is pivotal for autonomous driving. Point cloud based methods have become increasingly popular for 3-D object detection, owing to their accurate depth information. NuTonomy's nuScenes dataset greatly extends commonly…

Object detection using LiDAR point clouds relies on a large amount of human-annotated samples when training the underlying detectors' deep neural networks. However, generating 3D bounding box annotation for a large-scale dataset could be…

In autonomous driving, LiDAR sensors are vital for acquiring 3D point clouds, providing reliable geometric information. However, traditional sampling methods of preprocessing often ignore semantic features, leading to detail loss and ground…

Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area. However, due to the common occlusion in LiDAR scans, it is non-trivial to conduct accurate feature…

Recently, self-attention mechanisms have shown impressive performance in various NLP and CV tasks, which can help capture sequential characteristics and derive global information. In this work, we explore how to extend self-attention…

Although LiDAR sensors are crucial for autonomous systems due to providing precise depth information, they struggle with capturing fine object details, especially at a distance, due to sparse and non-uniform data. Recent advances introduced…

3D object detection with a single image is an essential and challenging task for autonomous driving. Recently, keypoint-based monocular 3D object detection has made tremendous progress and achieved great speed-accuracy trade-off. However,…

We propose a late-to-early recurrent feature fusion scheme for 3D object detection using temporal LiDAR point clouds. Our main motivation is fusing object-aware latent embeddings into the early stages of a 3D object detector. This feature…

Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at…

Object detection and global localization play a crucial role in robotics, spanning across a great spectrum of applications from autonomous cars to multi-layered 3D Scene Graphs for semantic scene understanding. This article proposes BOX3D,…

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.…

Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of object classification and semantic segmentation. However, the…

Object detection is a significant field in autonomous driving. Popular sensors for this task include cameras and LiDAR sensors. LiDAR sensors offer several advantages, such as insensitivity to light changes, like in a dark setting and the…

Recent works in object detection in LiDAR point clouds mostly focus on predicting bounding boxes around objects. This prediction is commonly achieved using anchor-based or anchor-free detectors that predict bounding boxes, requiring…

This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D…

Since the introduction of the self-attention mechanism and the adoption of the Transformer architecture for Computer Vision tasks, the Vision Transformer-based architectures gained a lot of popularity in the field, being used for tasks such…

Unsupervised 3D object detection methods have emerged to leverage vast amounts of data without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect mobile objects but penalize the detections…