English
Related papers

Related papers: Deep Model-Based 6D Pose Refinement in RGB

200 papers

Estimating the relative rigid pose between two RGB-D scans of the same underlying environment is a fundamental problem in computer vision, robotics, and computer graphics. Most existing approaches allow only limited maximum relative pose…

Computer Vision and Pattern Recognition · Computer Science 2019-01-08 Zhenpei Yang , Jeffrey Z. Pan , Linjie Luo , Xiaowei Zhou , Kristen Grauman , Qixing Huang

We present a novel approach to robotic grasp planning using both a learned grasp proposal network and a learned 3D shape reconstruction network. Our system generates 6-DOF grasps from a single RGB-D image of the target object, which is…

Robotics · Computer Science 2020-11-09 Daniel Yang , Tarik Tosun , Ben Eisner , Volkan Isler , Daniel Lee

We introduce T-LESS, a new public dataset for estimating the 6D pose, i.e. translation and rotation, of texture-less rigid objects. The dataset features thirty industry-relevant objects with no significant texture and no discriminative…

Computer Vision and Pattern Recognition · Computer Science 2017-01-20 Tomas Hodan , Pavel Haluza , Stepan Obdrzalek , Jiri Matas , Manolis Lourakis , Xenophon Zabulis

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…

Computer Vision and Pattern Recognition · Computer Science 2020-11-12 Rebecca König , Bertram Drost

Single shot approaches have demonstrated tremendous success on various computer vision tasks. Finding good parameterizations for 6D object pose estimation remains an open challenge. In this work, we propose different novel parameterizations…

Computer Vision and Pattern Recognition · Computer Science 2021-04-16 Kilian Kleeberger , Markus Völk , Richard Bormann , Marco F. Huber

We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to…

Computer Vision and Pattern Recognition · Computer Science 2020-11-02 Mihir Prabhudesai , Shamit Lal , Hsiao-Yu Fish Tung , Adam W. Harley , Shubhankar Potdar , Katerina Fragkiadaki

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these…

Computer Vision and Pattern Recognition · Computer Science 2016-05-18 Bugra Tekin , Isinsu Katircioglu , Mathieu Salzmann , Vincent Lepetit , Pascal Fua

We present an approach for recognizing all objects in a scene and estimating their full pose from an accurate 3D instance-aware semantic reconstruction using an RGB-D camera. Our framework couples convolutional neural networks (CNNs) and a…

Robotics · Computer Science 2019-10-01 Dinh-Cuong Hoang , Todor Stoyanov , Achim J. Lilienthal

Recently, various methods for 6D pose and shape estimation of objects have been proposed. Typically, these methods evaluate their pose estimation in terms of average precision, and reconstruction quality with chamfer distance. In this work…

Computer Vision and Pattern Recognition · Computer Science 2022-02-22 Leonard Bruns , Patric Jensfelt

This paper presents an efficient symmetry-agnostic and correspondence-free framework, referred to as SC6D, for 6D object pose estimation from a single monocular RGB image. SC6D requires neither the 3D CAD model of the object nor any prior…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Dingding Cai , Janne Heikkilä , Esa Rahtu

6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity object CAD models. In this work, we study a new open set…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Yisheng He , Yao Wang , Haoqiang Fan , Jian Sun , Qifeng Chen

We present a robust and real-time monocular six degree of freedom visual relocalization system. We use a Bayesian convolutional neural network to regress the 6-DOF camera pose from a single RGB image. It is trained in an end-to-end manner…

Computer Vision and Pattern Recognition · Computer Science 2016-02-19 Alex Kendall , Roberto Cipolla

Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…

Robotics · Computer Science 2018-10-01 Jonathan Tremblay , Thang To , Balakumar Sundaralingam , Yu Xiang , Dieter Fox , Stan Birchfield

We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Jian Liu , Naveed Akhtar , Ajmal Mian

Establishing correspondences from image to 3D has been a key task of 6DoF object pose estimation for a long time. To predict pose more accurately, deeply learned dense maps replaced sparse templates. Dense methods also improved pose…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Yongzhi Su , Mahdi Saleh , Torben Fetzer , Jason Rambach , Nassir Navab , Benjamin Busam , Didier Stricker , Federico Tombari

In this work, we bridge the gap between recent pose estimation and tracking work to develop a powerful method for robots to track objects in their surroundings. Motion-Nets use a segmentation model to segment the scene, and separate…

Robotics · Computer Science 2019-10-31 Felix Leeb , Arunkumar Byravan , Dieter Fox

This paper presents a convolutional neural network based approach for estimating the relative pose between two cameras. The proposed network takes RGB images from both cameras as input and directly produces the relative rotation and…

Computer Vision and Pattern Recognition · Computer Science 2017-07-31 Iaroslav Melekhov , Juha Ylioinas , Juho Kannala , Esa Rahtu

We propose a neural head reenactment system, which is driven by a latent pose representation and is capable of predicting the foreground segmentation alongside the RGB image. The latent pose representation is learned as a part of the entire…

Computer Vision and Pattern Recognition · Computer Science 2020-11-02 Egor Burkov , Igor Pasechnik , Artur Grigorev , Victor Lempitsky

Estimating the 6-DoF pose of a rigid object from a single RGB image is a crucial yet challenging task. Recent studies have shown the great potential of dense correspondence-based solutions, yet improvements are still needed to reach…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Ruyi Lian , Haibin Ling

The goal of our work is to complete the depth channel of an RGB-D image. Commodity-grade depth cameras often fail to sense depth for shiny, bright, transparent, and distant surfaces. To address this problem, we train a deep network that…

Computer Vision and Pattern Recognition · Computer Science 2018-05-03 Yinda Zhang , Thomas Funkhouser
‹ Prev 1 8 9 10 Next ›