Related papers: Multistream ValidNet: Improving 6D Object Pose Est…

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels…

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, rather than being heuristically selected as has been the standard…

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…

Accurate 6D object pose estimation is vital for robotics, augmented reality, and scene understanding. For seen objects, high accuracy is often attainable via per-object fine-tuning but generalizing to unseen objects remains a challenge. To…

We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry…

Modern deep learning techniques that regress the relative camera pose between two images have difficulty dealing with challenging scenarios, such as large camera motions resulting in occlusions and significant changes in perspective that…

Object pose estimation is an integral part of robot vision and AR. Previous 6D pose retrieval pipelines treat the problem either as a regression task or discretize the pose space to classify. We change this paradigm and reformulate the…

In this work, we explore how a strategic selection of camera movements can facilitate the task of 6D multi-object pose estimation in cluttered scenarios while respecting real-world constraints important in robotics and augmented reality…

Object pose estimation is a fundamental problem in robotics and computer vision, yet it remains challenging due to partial observability, occlusions, and object symmetries, which inevitably lead to pose ambiguity and multiple hypotheses…

We introduce FocalPose++, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object. The contributions of this work are threefold.…

Most recent 6D object pose estimation methods, including unsupervised ones, require many real training images. Unfortunately, for some applications, such as those in space or deep under water, acquiring real images, even unannotated, is…

We propose a new 2D pose refinement network that learns to predict the human bias in the estimated 2D pose. There are biases in 2D pose estimations that are due to differences between annotations of 2D joint locations based on annotators'…

Object pose estimation underwater allows an autonomous system to perform tracking and intervention tasks. Nonetheless, underwater target pose estimation is remarkably challenging due to, among many factors, limited visibility, light…

Most successful approaches to estimate the 6D pose of an object typically train a neural network by supervising the learning with annotated poses in real world images. These annotations are generally expensive to obtain and a common…

This paper studies the complex task of simultaneous multi-object 3D reconstruction, 6D pose and size estimation from a single-view RGB-D observation. In contrast to instance-level pose estimation, we focus on a more challenging problem…

Recent progress in object pose prediction provides a promising path for robots to build object-level scene representations during navigation. However, as we deploy a robot in novel environments, the out-of-distribution data can degrade the…

We propose a method for 6DoF pose estimation of rigid objects that uses a state-of-the-art deep learning based instance detector to segment object instances in an RGB image, followed by a point-pair based voting method to recover the…

Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances. This naturally hampers possible applications as, for instance, robots seamlessly integrated in everyday processes necessarily require the…

Single-view RGB model-based object pose estimation methods achieve strong generalization but are fundamentally limited by depth ambiguity, clutter, and occlusions. Multi-view pose estimation methods have the potential to solve these issues,…

Big neural networks trained on large datasets have advanced the state-of-the-art for a large variety of challenging problems, improving performance by a large margin. However, under low memory and limited computational power constraints,…