Related papers: GKNet: Graph-based Keypoints Network for Monocular…

Monocular geometric scene understanding combines panoptic segmentation and self-supervised depth estimation, focusing on real-time application in autonomous vehicles. We introduce MGNiceNet, a unified approach that uses a linked kernel…

Monocular 6-DoF pose estimation plays an important role in multiple spacecraft missions. Most existing pose estimation approaches rely on single images with static keypoint localisation, failing to exploit valuable temporal information…

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D…

Traditional 2D pose estimation models are limited by their category-specific design, making them suitable only for predefined object categories. This restriction becomes particularly challenging when dealing with novel objects due to the…

6D object pose estimation is a fundamental yet challenging problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even under monocular settings.…

We propose a novel attention-based 2D-to-3D pose estimation network for graph-structured data, named KOG-Transformer, and a 3D pose-to-shape estimation network for hand data, named GASE-Net. Previous 3D pose estimation methods have focused…

Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions. Their intrinsic problem is that they directly localize the…

Autonomous space operations such as on-orbit servicing and active debris removal demand robust part-level semantic understanding and precise relative navigation of target spacecraft, yet collecting large-scale real data in orbit remains…

Human pose estimation (HPE) with convolutional neural networks (CNNs) for indoor monitoring is one of the major challenges in computer vision. In contrast to HPE in perspective views, an indoor monitoring system can consist of an…

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth…

High-level robotic manipulation tasks demand flexible 6-DoF grasp estimation to serve as a basic function. Previous approaches either directly generate grasps from point-cloud data, suffering from challenges with small objects and sensor…

Perceiving the three-dimensional (3D) structure of the spacecraft is a prerequisite for successfully executing many on-orbit space missions, and it can provide critical input for many downstream vision algorithms. In this paper, we propose…

Since the PointNet was proposed, deep learning on point cloud has been the concentration of intense 3D research. However, existing point-based methods usually are not adequate to extract the local features and the spatial pattern of a point…

Category-level object pose estimation, which predicts the pose of objects within a known category without prior knowledge of individual instances, is essential in applications like warehouse automation and manufacturing. Existing methods…

Multi-person pose estimation and tracking serve as crucial steps for video understanding. Most state-of-the-art approaches rely on first estimating poses in each frame and only then implementing data association and refinement. Despite the…

We present a novel end-to-end framework named as GSNet (Geometric and Scene-aware Network), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view. GSNet utilizes a unique four-way feature…

Great success has been achieved in the 6-DoF grasp learning from the point cloud input, yet the computational cost due to the point set orderlessness remains a concern. Alternatively, we explore the grasp generation from the RGB-D input in…

This work presents Spacecraft Pose Network v2 (SPNv2), a Convolutional Neural Network (CNN) for pose estimation of noncooperative spacecraft across domain gap. SPNv2 is a multi-scale, multi-task CNN which consists of a shared multi-scale…

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose…

Pose tracking of uncooperative spacecraft is an essential technology for space exploration and on-orbit servicing, which remains an open problem. Event cameras possess numerous advantages, such as high dynamic range, high temporal…