English
Related papers

Related papers: SE3-Pose-Nets: Structured Deep Dynamics Models for…

200 papers

End-to-end learning for visual robotic manipulation is known to suffer from sample inefficiency, requiring large numbers of demonstrations. The spatial roto-translation equivariance, or the SE(3)-equivariance can be exploited to improve the…

Robotics · Computer Science 2023-11-08 Hyunwoo Ryu , Hong-in Lee , Jeong-Hoon Lee , Jongeun Choi

Physics-constrained data-driven computing is an emerging computational paradigm that allows simulation of complex materials directly based on material database and bypass the classical constitutive model construction. However, it remains…

Numerical Analysis · Mathematics 2022-09-12 Xiaolong He , Qizhi He , Jiun-Shyan Chen

3D pose estimation is a challenging problem in computer vision. Most of the existing neural-network-based approaches address color or depth images through convolution networks (CNNs). In this paper, we study the task of 3D human pose…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Yufan Zhou , Haiwei Dong , Abdulmotaleb El Saddik

Recent advances in 3D human shape reconstruction from single images have shown impressive results, leveraging on deep networks that model the so-called implicit function to learn the occupancy status of arbitrarily dense 3D points in space.…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Nicolas Ugrinovic , Albert Pumarola , Alberto Sanfeliu , Francesc Moreno-Noguer

Tactile and visual perception are both crucial for humans to perform fine-grained interactions with their environment. Developing similar multi-modal sensing capabilities for robots can significantly enhance and expand their manipulation…

Robotics · Computer Science 2025-01-08 Binghao Huang , Yixuan Wang , Xinyi Yang , Yiyue Luo , Yunzhu Li

Category-level 6D object pose and size estimation is to predict full pose configurations of rotation, translation, and size for object instances observed in single, arbitrary views of cluttered scenes. In this paper, we propose a new method…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Jiehong Lin , Zewei Wei , Zhihao Li , Songcen Xu , Kui Jia , Yuanqing Li

This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the…

Computer Vision and Pattern Recognition · Computer Science 2016-06-22 Özgün Çiçek , Ahmed Abdulkadir , Soeren S. Lienkamp , Thomas Brox , Olaf Ronneberger

In this paper, we present our work on developing robot arm prosthetic via deep learning. Our work proposes to use transfer learning techniques applied to the Google Inception model to retrain the final layer for surface electromyography…

Signal Processing · Electrical Eng. & Systems 2020-05-06 David Lonsdale , Li Zhang , Richard Jiang

Hyper-redundant robots offer high dexterity, making them good at operating in confined and unstructured environments. To extend the reachable workspace, we built a multi-segment flexible rack actuated planar robot. However, the compliance…

Robotics · Computer Science 2026-03-12 Yuli Song , Wenbo Li , Wenci Xin , Zhiqiang Tang , Daniela Rus , Cecilia Laschi

Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D…

Robotics · Computer Science 2025-09-22 Quanhao Qian , Guoyang Zhao , Gongjie Zhang , Jiuniu Wang , Ran Xu , Junlong Gao , Deli Zhao

Knowing the exact 3D location of workers and robots in a collaborative environment enables several real applications, such as the detection of unsafe situations or the study of mutual interactions for statistical and social purposes. In…

Computer Vision and Pattern Recognition · Computer Science 2022-07-07 Alessandro Simoni , Stefano Pini , Guido Borghi , Roberto Vezzani

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…

Computer Vision and Pattern Recognition · Computer Science 2020-03-03 Matthias Minderer , Chen Sun , Ruben Villegas , Forrester Cole , Kevin Murphy , Honglak Lee

We use a data-driven approach to model a three-dimensional turbulent flow using cutting-edge Deep Learning techniques. The deep learning framework incorporates physical constraints on the flow, such as preserving incompressibility and…

Fluid Dynamics · Physics 2021-12-08 Mohammadreza Momenifar , Enmao Diao , Vahid Tarokh , Andrew D. Bragg

Estimating accurate camera poses, 3D scene geometry, and object motion from in-the-wild videos is a long-standing challenge for classical structure from motion pipelines due to the presence of dynamic objects. Recent learning-based methods…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Zhuoyuan Wu , Xurui Yang , Jiahui Huang , Yue Wang , Jun Gao

Even though deep neural networks have shown tremendous success in countless applications, explaining model behaviour or predictions is an open research problem. In this paper, we address this issue by employing a simple yet effective method…

Computer Vision and Pattern Recognition · Computer Science 2023-01-12 Ryan Benkert , Oluwaseun Joseph Aribido , Ghassan AlRegib

Tracking the full body motions of users in XR (AR/VR) devices is a fundamental challenge to bring a sense of authentic social presence. Due to the absence of dedicated leg sensors, currently available body tracking methods adopt a synthesis…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Denys Rozumnyi , Nadine Bertsch , Othman Sbai , Filippo Arcadu , Yuhua Chen , Artsiom Sanakoyeu , Manoj Kumar , Catherine Herold , Robin Kips

Multi-objective optimization problems are ubiquitous in robotics, e.g., the optimization of a robot manipulation task requires a joint consideration of grasp pose configurations, collisions and joint limits. While some demands can be easily…

Robotics · Computer Science 2023-06-21 Julen Urain , Niklas Funk , Jan Peters , Georgia Chalvatzaki

We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to…

Machine Learning · Computer Science 2015-11-23 Manuel Watter , Jost Tobias Springenberg , Joschka Boedecker , Martin Riedmiller

Is a deep learning model capable of understanding systems governed by certain first principle laws by only observing the system's output? Can deep learning learn the underlying physics and honor the physics when making predictions? The…

Computational Physics · Physics 2020-06-11 Rohan Thavarajah , Xiang Zhai , Zheren Ma , David Castineira

Modern deep learning developments create new opportunities for 3D mapping technology, scene reconstruction pipelines, and virtual reality development. Despite advances in 3D deep learning technology, direct training of deep learning models…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Xueyang Kang