Related papers: SoK: Vehicle Orientation Representations for Deep …

Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…

The task of detecting 3D objects is important to various robotic applications. The existing deep learning-based detection techniques have achieved impressive performance. However, these techniques are limited to run with a graphics…

We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain…

We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the…

We propose a complete pipeline that allows object detection and simultaneously estimate the pose of these multiple object instances using just a single image. A novel "keypoint regression" scheme with a cross-ratio term is introduced that…

In this paper we propose a novel 3D single-shot object detection method for detecting vehicles in monocular RGB images. Our approach lifts 2D detections to 3D space by predicting additional regression and classification parameters and hence…

There exist numerous ways of representing 3D orientations. Each representation has both limitations and unique features. Choosing the best representation for one task is often a difficult chore, and there exist conflicting opinions on which…

We propose a 3D object detection system with multi-sensor refinement in the context of autonomous driving. In our framework, the monocular camera serves as the fundamental sensor for 2D object proposal and initial 3D bounding box…

In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for simultaneous vehicle detection, part localization,…

Image-only and pseudo-LiDAR representations are commonly used for monocular 3D object detection. However, methods based on them have shortcomings of either not well capturing the spatial relationships in neighbored image pixels or being…

Robotic kitting has attracted considerable attention in logistics and industrial settings. However, existing kitting methods encounter challenges such as low precision and poor efficiency, limiting their widespread applications. To address…

Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence of accurate depth information. Though this issue can be…

Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping. Previous methods follow a local optimization approach which minimizes the distance between closest point pairs to handle the rotation ambiguity of…

We present a novel learning framework for vehicle recognition from a single RGB image. Unlike existing methods which only use attention mechanisms to locate 2D discriminative information, our work learns a novel 3D perspective feature…

Object detection is a crucial component of autonomous driving, and many detection applications have been developed to address this task. These applications often rely on backbone architectures, which extract representation features from…

Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas…

Latest deep learning methods for object detection provide remarkable performance, but have limits when used in robotic applications. One of the most relevant issues is the long training time, which is due to the large size and imbalance of…

Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior…

Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have…

The task of detecting 3D objects in traffic scenes has a pivotal role in many real-world applications. However, the performance of 3D object detection is lower than that of 2D object detection due to the lack of powerful 3D feature…