Filters








4,981 Hits in 4.6 sec

EventHands: Real-Time Neural 3D Hand Pose Estimation from an Event Stream [article]

Viktor Rudnev and Vladislav Golyanik and Jiayi Wang and Hans-Peter Seidel and Franziska Mueller and Mohamed Elgharib and Christian Theobalt
2021 arXiv   pre-print
Our method, the event stream simulator and the dataset are publicly available; see https://4dqv.mpi-inf.mpg.de/EventHands/  ...  We thus design a new neural approach which accepts a new event stream representation suitable for learning, which is trained on newly-generated synthetic event streams and can generalise to real data.  ...  We thank Jalees Nehvi and Navami Kairanda for help with comparisons.  ... 
arXiv:2012.06475v3 fatcat:fx5frkvw75botn7sjurvruwpgu

Shape Animation with Combined Captured and Simulated Dynamics [article]

Benjamin Allain, Li Wang, Jean-Sebastien Franco, Franck Hetroy, and Edmond Boyer
2016 arXiv   pre-print
as unified volumetric representation of the real captured actor, which we show can be used seamlessly as a building block for all processing stages, from capture and tracking to virtual physic simulation  ...  The framework considers as input time incoherent 3D observations of a moving shape, and is thus particularly suitable for the output of performance capture platforms.  ...  Finally, in SLACKLINE a male acrobat evolves on a non rigid line above the ground, for 25 s.  ... 
arXiv:1601.01232v1 fatcat:mcul24jicvaw5axwwaxan5afru

MuJoCo HAPTIX: A virtual reality system for hand manipulation

Vikash Kumar, Emanuel Todorov
2015 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)  
To fill this gap, we developed a virtual reality system combining real-time motion capture, physics simulation and stereoscopic visualization.  ...  The system enables a user wearing a CyberGlove to "reach-in" the simulation, and manipulate virtual objects through contacts with a tele-operated virtual hand.  ...  For the head and the hand tracking we use custom 3D-printed parts to which the markers are glued. There are three markers per rigid body.  ... 
doi:10.1109/humanoids.2015.7363441 dblp:conf/humanoids/KumarT15 fatcat:ox5srnz67rd7jaukremqapkwui

Tracking surfaces with evolving topology

Morten Bojsen-Hansen, Hao Li, Chris Wojtan
2012 ACM Transactions on Graphics  
Our system combines a proven strategy for triangle mesh improvement, a robust multi-resolution non-rigid registration routine, and a reliable technique for changing surface mesh topology.  ...  We reliably extract correspondences from a level set and track textures backwards through a fluid simulation.  ...  Acknowledgements We would like to thank Xiaochen Hu for implementing mesh conversion tools, Duygu Ceylan for helping with the rendering, and Art Tevs for the human performance data comparison.  ... 
doi:10.1145/2185520.2335404 fatcat:irdx33qv3za2fkqtxac7zcazd4

Tracking surfaces with evolving topology

Morten Bojsen-Hansen, Hao Li, Chris Wojtan
2012 ACM Transactions on Graphics  
Our system combines a proven strategy for triangle mesh improvement, a robust multi-resolution non-rigid registration routine, and a reliable technique for changing surface mesh topology.  ...  We reliably extract correspondences from a level set and track textures backwards through a fluid simulation.  ...  Acknowledgements We would like to thank Xiaochen Hu for implementing mesh conversion tools, Duygu Ceylan for helping with the rendering, and Art Tevs for the human performance data comparison.  ... 
doi:10.1145/2185520.2185549 fatcat:wgjpr3hpbna3nminfkdlnftlei

Timing-Based Local Descriptor for Dynamic Surfaces

Tony Tung, Takashi Matsuyama
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we present the first local descriptor designed for dynamic surfaces. A dynamic surface is a surface that can undergo non-rigid deformation (e.g., human body surface).  ...  We show the proposed descriptor can be used for challenging dynamic surface classification and segmentation with respect to rigidity at surface keypoints.  ...  We evaluate our method against [34, 33, 43] for quantitative evaluations of rigid/non-rigid surface classification. Each surface point is manually labeled as rigid or non-rigid (see Fig. 5 ).  ... 
doi:10.1109/cvpr.2014.60 dblp:conf/cvpr/TungM14 fatcat:ioynxt7hkzabra2bk72ijvv2ve

EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras [article]

Anton Mitrokhin, Chengxi Ye, Cornelia Fermuller, Yiannis Aloimonos, Tobi Delbruck
2020 arXiv   pre-print
We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground  ...  The objects and the camera are tracked by the VICON motion capture system.  ...  Specifically, we consider it crucial to study event stream augmentation using partially or fully simulated data.  ... 
arXiv:1903.07520v2 fatcat:56uvc4u6cba3firmurxmwip244

A Dataset for Visual Navigation with Neuromorphic Methods

Francisco Barranco, Cornelia Fermuller, Yiannis Aloimonos, Tobi Delbruck
2016 Frontiers in Neuroscience  
For both datasets the cameras move with a rigid motion in a static scene, and the data includes the images, events, optic flow, 3D camera motion, and the depth of the scene, along with calibration procedures  ...  Finally, we also provide simulated event data generated synthetically from well-known frame-based optical flow datasets.  ...  ACKNOWLEDGMENTS Thanks are due to Michael Stevens for helping with the Pioneer 3DX mobile platform.  ... 
doi:10.3389/fnins.2016.00049 pmid:26941595 pmcid:PMC4763084 fatcat:kejvcqhn2fghxfgiyx4azphrnq

MCMR: A Fluid View on Time Dependent Volume Data [article]

Wim De Leeuw, Robert Van Liere
2003 EUROVIS 2005: Eurographics / IEEE VGTC Symposium on Visualization  
Mass Conservative Motion Reconstruction is a new method for estimating motion in time dependent volume data.  ...  Standard flow visualization techniques are used for the visualization of the derived vector field.  ...  On the other hand, feature tracking algorithms provide an explicit set of events and features that can be useful to reason about properties of the data.  ... 
doi:10.2312/vissym/vissym03/149-156 fatcat:w2ytx6kjozhlnf23yhaeu4rqdi

Enhancing realism of mixed reality applications through real-time depth-imaging devices in X3D

Tobias Franke, Svenja Kahn, Manuel Olbrich, Yvonne Jung
2011 Proceedings of the 16th International Conference on 3D Web Technology - Web3D '11  
The underlying OpenNI framework not only allows to extract the depth image from the camera, but also provides tracking information of gestures or user skeletons.  ...  With the introduction of the Microsoft Kinect device, realtime depth imaging is now available for the ordinary developer at low expenses and so far it has been received with great interest from both the  ...  For single user interaction a common event system might be more consistent for the application developer.  ... 
doi:10.1145/2010425.2010439 dblp:conf/vrml/FrankeKOJ11 fatcat:7mf45y2r5bagtnmrdioxlx2hli

Interactive 3D fluid jet painting

Sangwon Lee, Sven C. Olsen, Bruce Gooch
2006 ACM SIGGRAPH 2006 Emerging technologies on - SIGGRAPH '06  
Our fluid jet model consists of two coupled simulations: a Navier-Stokes solver for an axis-symmetric fluid column and a linked-mass system for tracking the three dimensional motion of the jet's axis line  ...  Pollock's paintings were created by using streams of household paint to make guided, semi-random patterns on his canvas.  ...  Because φ i (r) and p i do not change over time, we can keep track of F(x) by accumulating the results of each new φ i to a high resolution texture the moment that each impact event is registered.  ... 
doi:10.1145/1179133.1179151 dblp:conf/siggraph/LeeOG06 fatcat:pzlza5abrvccniraicnlf3u2gm

Interactive 3D fluid jet painting

Sangwon Lee, Sven C. Olsen, Bruce Gooch
2006 Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering - NPAR '06  
Our fluid jet model consists of two coupled simulations: a Navier-Stokes solver for an axis-symmetric fluid column and a linked-mass system for tracking the three dimensional motion of the jet's axis line  ...  Pollock's paintings were created by using streams of household paint to make guided, semi-random patterns on his canvas.  ...  Because φ i (r) and p i do not change over time, we can keep track of F(x) by accumulating the results of each new φ i to a high resolution texture the moment that each impact event is registered.  ... 
doi:10.1145/1124728.1124745 dblp:conf/npar/LeeOG06 fatcat:c4lfsbr4tzb6ld3pxiegsmcyy4

Enabling and Analyzing Natural Interaction with Functional Virtual Prototypes [chapter]

Frank Gommlich, Guido Heumer, Bernhard Jung, Matthias Lenk, Arnd Vitzthum
2012 Modeling and Simulation in Engineering  
Since object behavior is simulated by a rigid body dynamics engine, this approach to implement direct object manipulation simulation enables the user to pick up and release objects and to manipulate them  ...  in prehensile and non-prehensile ways.  ...  The book consists of 12 chapters arranged in two sections (3D Modeling and Virtual Prototyping), reflecting the multidimensionality of applications related to modeling and simulation.  ... 
doi:10.5772/25965 fatcat:fv4wchczgbcy7fu6imtfiev73i

2020 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 42

2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Jiang, S., +, TPAMI May 2020 1097-1111 Complexity theory One Shot Segmentation: Unifying Rigid Detection and Non-Rigid Segmen- tation Using Elastic Regularization.  ...  Wan, R., +, TPAMI Dec. 2020 2969-2982 Arnab, A., +, TPAMI Dec. 2020 3040-3053 One Shot Segmentation: Unifying Rigid Detection and Non-Rigid Segmen- tation Using Elastic Regularization.  ...  ., +, 2670 -2683 DART: Distribution Aware Retinal Transform for Event-Based Cameras.  ... 
doi:10.1109/tpami.2020.3036557 fatcat:3j6s2l53x5eqxnlsptsgbjeebe

Virtual Robot Experimentation Platform V-REP: A Versatile 3D Robot Simulator [chapter]

Marc Freese, Surya Singh, Fumio Ozaki, Nobuto Matsuhira
2010 Lecture Notes in Computer Science  
As the Virtual Robot Experimentation Platform (V-REP) demonstrates, this gives a smallfootprint 3D robot simulator that concurrently simulates control, actuation, sensing and monitoring.  ...  This paper introduces a modular and decentralized architecture for robotics simulation.  ...  Data streams can be displayed directly (time graph of a given data type), or combined with each other to display X/Y graphs, or 3D curves.  ... 
doi:10.1007/978-3-642-17319-6_8 fatcat:5egtpozmxbhjxogubgage4a6wy
« Previous Showing results 1 — 15 out of 4,981 results