Templates for 3d object pose estimation revisited: Generalization to new objects and robustness to occlusions
We present a method that can recognize new objects and estimate their 3D pose in RGB
images even under partial occlusions. Our method requires neither a training phase on …
images even under partial occlusions. Our method requires neither a training phase on …
Texpose: Neural texture learning for self-supervised 6d object pose estimation
In this paper, we introduce neural texture learning for 6D object pose estimation from
synthetic data and a few unlabelled real images. Our major contribution is a novel learning …
synthetic data and a few unlabelled real images. Our major contribution is a novel learning …
Dsc-posenet: Learning 6dof object pose estimation via dual-scale consistency
Compared to 2D object bounding-box labeling, it is very difficult for humans to annotate 3D
object poses, especially when depth images of scenes are unavailable. This paper …
object poses, especially when depth images of scenes are unavailable. This paper …
Vote from the center: 6 dof pose estimation in rgb-d images by radial keypoint voting
We propose a novel keypoint voting scheme based on intersecting spheres, that is more
accurate than existing schemes and allows for fewer, more disperse keypoints. The scheme …
accurate than existing schemes and allows for fewer, more disperse keypoints. The scheme …
Stablepose: Learning 6d object poses from geometrically stable patches
We introduce the concept of geometric stability to the problem of 6D object pose estimation
and propose to learn pose inference based on geometrically stable patches extracted from …
and propose to learn pose inference based on geometrically stable patches extracted from …
Pizza: A powerful image-only zero-shot zero-cad approach to 6 dof tracking
Estimating the relative pose of a new object without prior knowledge is a hard problem,
while it is an ability very much needed in robotics and Augmented Reality. We present a …
while it is an ability very much needed in robotics and Augmented Reality. We present a …
[HTML][HTML] Self-supervised vision transformers for 3d pose estimation of novel objects
Object pose estimation is important for object manipulation and scene understanding. In
order to improve the general applicability of pose estimators, recent research focuses on …
order to improve the general applicability of pose estimators, recent research focuses on …
Depth from camera motion and object detection
BA Griffin, JJ Corso - … of the IEEE/CVF Conference on …, 2021 - openaccess.thecvf.com
This paper addresses the problem of learning to estimate the depth of detected objects
given some measurement of camera motion (eg, from robot kinematics or vehicle odometry) …
given some measurement of camera motion (eg, from robot kinematics or vehicle odometry) …
Deep Learning-Based Object Pose Estimation: A Comprehensive Survey
J Liu, W Sun, H Yang, Z Zeng, C Liu, J Zheng… - arXiv preprint arXiv …, 2024 - arxiv.org
Object pose estimation is a fundamental computer vision problem with broad applications in
augmented reality and robotics. Over the past decade, deep learning models, due to their …
augmented reality and robotics. Over the past decade, deep learning models, due to their …
Learning Better Keypoints for Multi-Object 6DoF Pose Estimation
Y Wu, M Greenspan - Proceedings of the IEEE/CVF Winter …, 2024 - openaccess.thecvf.com
We address the problem of keypoint selection, and find that the performance of 6DoF pose
estimation methods can be improved when pre-defined keypoint locations are learned …
estimation methods can be improved when pre-defined keypoint locations are learned …