English
Related papers

Related papers: ParaPose: Parameter and Domain Randomization Optim…

200 papers

Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Xiaoling Hu , Xiangrui Zeng , Oula Puonti , Juan Eugenio Iglesias , Bruce Fischl , Yael Balbastre

Spacecraft pose estimation is a key task to enable space missions in which two spacecrafts must navigate around each other. Current state-of-the-art algorithms for pose estimation employ data-driven techniques. However, there is an absence…

Computer Vision and Pattern Recognition · Computer Science 2022-12-29 Juan Ignacio Bravo Pérez-Villar , Álvaro García-Martín , Jesús Bescós

Most self-supervised 6D object pose estimation methods can only work with additional depth information or rely on the accurate annotation of 2D segmentation masks, limiting their application range. In this paper, we propose a 6D object pose…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Yang Hai , Rui Song , Jiaojiao Li , David Ferstl , Yinlin Hu

This paper addresses the problem of 3D human pose estimation in the wild. A significant challenge is the lack of training data, i.e., 2D images of humans annotated with 3D poses. Such data is necessary to train state-of-the-art CNN…

Computer Vision and Pattern Recognition · Computer Science 2018-02-13 Grégory Rogez , Cordelia Schmid

6D object pose estimation is one of the fundamental problems in computer vision and robotics research. While a lot of recent efforts have been made on generalizing pose estimation to novel object instances within the same category, namely…

Computer Vision and Pattern Recognition · Computer Science 2022-07-01 Yang Fu , Xiaolong Wang

Along with the recent development of deep neural networks, appearance-based gaze estimation has succeeded considerably when training and testing within the same domain. Compared to the within-domain task, the variance of different domains…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Jiawei Qin , Takuru Shimoyama , Xucong Zhang , Yusuke Sugano

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-25 Jonathan Tremblay , Aayush Prakash , David Acuna , Mark Brophy , Varun Jampani , Cem Anil , Thang To , Eric Cameracci , Shaad Boochoon , Stan Birchfield

We address the problem of estimating the pose of humans using RGB image input. More specifically, we are using a random forest classifier to classify pixels into joint-based body part categories, much similar to the famous Kinect pose…

Computer Vision and Pattern Recognition · Computer Science 2014-05-28 Oscar Danielsson , Omid Aghazadeh

In recent years, synthetic data has been widely used in the training of 6D pose estimation networks, in part because it automatically provides perfect annotation at low cost. However, there are still non-trivial domain gaps, such as…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Takuya Ikeda , Suomi Tanishige , Ayako Amma , Michael Sudano , Hervé Audren , Koichi Nishiwaki

Analysis-by-synthesis has been a successful approach for many tasks in computer vision, such as 6D pose estimation of an object in an RGB-D image which is the topic of this work. The idea is to compare the observation with the output of a…

Computer Vision and Pattern Recognition · Computer Science 2015-08-20 Alexander Krull , Eric Brachmann , Frank Michel , Michael Ying Yang , Stefan Gumhold , Carsten Rother

Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated…

Computer Vision and Pattern Recognition · Computer Science 2021-12-15 Bastian Wandt , James J. Little , Helge Rhodin

One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities. Focusing on the task of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Jack Langerman , Ziming Qiu , Gábor Sörös , Dávid Sebők , Yao Wang , Howard Huang

Estimating the 3D pose of an object is a challenging task that can be considered within augmented reality or robotic applications. In this paper, we propose a novel approach to perform 6 DoF object pose estimation from a single RGB-D image.…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Mathieu Gonzalez , Amine Kacete , Albert Murienne , Eric Marchand

This paper revisits camera pose estimation through the lens of self-supervised pretraining, focusing on inverse-dynamics pretraining as a scalable alternative to the current trend of fully supervised training with 3D annotations.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Zhengqing Wang , Saurabh Nair , Prajwal Chidananda , Pujith Kachana , Samuel Li , Matthew Brown , Yasutaka Furukawa

Visual place recognition techniques based on deep learning, which have imposed themselves as the state-of-the-art in recent years, do not generalize well to environments visually different from the training set. Thus, to achieve top…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Pierre-Yves Lajoie , Giovanni Beltrame

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…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Fabian Manhardt , Gu Wang , Benjamin Busam , Manuel Nickel , Sven Meier , Luca Minciullo , Xiangyang Ji , Nassir Navab

It is difficult to precisely annotate object instances and their semantics in 3D space, and as such, synthetic data are extensively used for these tasks, e.g., category-level 6D object pose and size estimation. However, the easy annotations…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Jiehong Lin , Zewei Wei , Changxing Ding , Kui Jia

This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Mohsen Gholami , Bastian Wandt , Helge Rhodin , Rabab Ward , Z. Jane Wang

Surgical robots are usually controlled using a priori models based on the robots' geometric parameters, which are calibrated before the surgical procedure. One of the challenges in using robots in real surgical settings is that those…

Robotics · Computer Science 2022-06-03 Masakazu Yoshimura , Murilo Marques Marinho , Kanako Harada , Mamoru Mitsuishi

It is often desired to train 6D pose estimation systems on synthetic data because manual annotation is expensive. However, due to the large domain gap between the synthetic and real images, synthesizing color images is expensive. In…

Computer Vision and Pattern Recognition · Computer Science 2021-03-04 Ge Gao , Mikko Lauri , Xiaolin Hu , Jianwei Zhang , Simone Frintrop