Filters








93 Hits in 5.9 sec

The Phong Surface: Efficient 3D Model Fitting using Lifted Optimization [article]

Jingjing Shen, Thomas J. Cashman, Qi Ye, Tim Hutton, Toby Sharp, Federica Bogo, Andrew William Fitzgibbon, Jamie Shotton
2020 arXiv   pre-print
Using ideas from computer graphics, the Phong surface describes the same 3D shape as a triangulated mesh model, but with continuous surface normals which enable the use of lifting-based optimization, providing  ...  To solve model-fitting problems for HoloLens 2 hand tracking, where the computational budget is approximately 100 times smaller than an iPhone 7, we introduce a new surface model: the 'Phong surface'.  ...  The Phong Surface: Efficient 3D Model Fitting using Lifted Optimization -Supplemental Materials S-I Lifting vs. point-to-plane ICP Here we show that lifted optimization is related to point-to-plane ICP  ... 
arXiv:2007.04940v1 fatcat:h26y7gv57rcifa2ppe65obmrky

The impact of specular highlights on 3D-2D face recognition

Vincent Christlein, Christian Riess, Elli Angelopoulou, Georgios Evangelopoulos, Ioannis Kakadiaris, Ioannis Kakadiaris, Walter J. Scheirer, Laurence G. Hassebrook
2013 Biometric and Surveillance Technology for Human and Activity Identification X  
In this work, we analyze the impact of such highlights on a 3D-2D face recognition system.  ...  Then, we explicitly model facial specularities within the face detection system with the Cook-Torrance reflectance model.  ...  of the excellence initiative.  ... 
doi:10.1117/12.2019014 fatcat:dft4ylq2s5cutjg45c6dyptfxu

Estimation of 3D Faces and Illumination from Single Photographs Using A Bilinear Illumination Model [article]

Jinho Lee, Hanspeter Pfister, Baback Moghaddam, Raghu Machiraju
2005 Symposium on Rendering  
Using both models we, in turn, propose a novel fitting framework that estimates the parameters of the morphable model given a single photograph.  ...  3D Face modeling is still one of the biggest challenges in computer graphics.  ...  The main challenge in the application of a morphable model for face reconstruction is the formulation of an efficient, robust, and general fitting procedure.  ... 
doi:10.2312/egwr/egsr05/073-082 fatcat:x3u4inzulzaexjatfft6vtobhe

Real-Time Fluid Effects on Surfaces using the Closest Point Method

S. Auer, C. B. Macdonald, M. Treib, J. Schneider, R. Westermann
2012 Computer graphics forum (Print)  
We propose a surface-embedding adaptive 3D spatial grid for efficient representation of the surface, and present a high-performance approach using CUDA for converting surfaces given by triangulations into  ...  The CPM uses a closest point representation of the surface, to solve the unmodified Cartesian version of a surface PDE in a 3D volume embedding, using simple and well-understood techniques.  ...  Acknowledgements This publication was based on work supported in part by the Munich Centre of Advanced Computing at the Technische Universität München (TUM) and by Awards No.  ... 
doi:10.1111/j.1467-8659.2012.03071.x fatcat:irzdz44oubhqfofyb6iulhmpdm

BRDF Measurement Modelling using Wavelets for Efficient Path Tracing

L. Claustres, M. Paulin, Y. Boucher
2003 Computer graphics forum (Print)  
The model is based on the separation of spectral and geometrical aspect of the BRDF and allows a compact and efficient representation of isotropic, anisotropic and/or spectral BRDFs.  ...  After a brief survey of BRDF and wavelet theory, we present our software architecture for generic wavelet transform and how to use it to model BRDFs.  ...  Dodgson for his contribution to the final version of this paper.  ... 
doi:10.1111/j.1467-8659..00718.x fatcat:6npn2566vzgpverl2cwyfcj7fi

3D Morphable Face Models – Past, Present and Future [article]

Bernhard Egger, William A. P. Smith, Ayush Tewari, Stefanie Wuhrer, Michael Zollhoefer, Thabo Beeler, Florian Bernard, Timo Bolkart, Adam Kortylewski, Sami Romdhani, Christian Theobalt, Volker Blanz (+1 others)
2020 arXiv   pre-print
In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed.  ...  The challenges in building and applying these models, namely capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these  ...  ACKNOWLEDGMENTS This survey paper was initiated at the Dagstuhl Seminar 19102 on 3D Morphable Models ] and contains ideas resulting from discussions at this seminar.  ... 
arXiv:1909.01815v2 fatcat:g3wtdppy7ze3dildi6a3siq4qy

Application of Hyperspectral LiDAR on 3D Chlorophyll-Nitrogen Mapping of Rohdea japonica in Laboratory

Lin Du, Jin Zhili, Bowen Chen, Biwu Chen, Wei Gao, Jian Yang, Shuo Shi, Shalei Song, Mengmeng Wang, Wei Gong, Wei Wang
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Thus, HSL can be efficiently applied to 3D Chl-N content mapping of vegetation and has great potential in GSV monitoring.  ...  even obtain a model R 2 of 0.84 for N content inversion.  ...  the optimal ANN model.  ... 
doi:10.1109/jstars.2021.3111295 fatcat:7hjl6qreojfqrpgukvnxzujsly

Spectral BRDF modeling using wavelets

Luc Claustres, Yannick Boucher, Mathias Paulin, Harold H. Szu, James R. Buss
2002 Wavelet and Independent Component Analysis Applications IX  
These reasons lead us to choose a numerical approach and particularly wavelets. This paper shows how wavelets can be used to provide an efficient BRDF model.  ...  A numerical optimization technique, like simplex, allows to retrieve the best parameters of the model by minimizing the error with regard to measurements.  ...  The virtual measurement dataset was generated from the Phong model [18] used intensively in computer graphics to represent shiny surfaces.  ... 
doi:10.1117/12.458726 fatcat:kcfiznjhefebth3mthconzyvsm

Variational PatchMatch MultiView Reconstruction and Refinement

Philipp Heise, Brian Jensen, Sebastian Klose, Alois Knoll
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
To speed up the optimization of the variational formulation an adapted scheme is used for faster convergence.  ...  We formulate the combined multi-view stereo reconstruction and refinement as a variational optimization problem.  ...  Further the propagation should be faster if particles are closer to their local optimal configuration e.g. best local plane fit.  ... 
doi:10.1109/iccv.2015.107 dblp:conf/iccv/HeiseJKK15 fatcat:5y5fa3j5ubamtog4k4euoagoei

Real-time shading-based refinement for consumer depth cameras

Chenglei Wu, Michael Zollhöfer, Matthias Nießner, Marc Stamminger, Shahram Izadi, Christian Theobalt
2014 ACM Transactions on Graphics  
Our optimization problem is minimized using a new regular grid Gauss-Newton solver implemented fully on the GPU.  ...  to original depth map (bottom right); full 3D reconstruction using our refined depth maps in the real-time scan integration method of [Nießner et al. 2013] (far right) Abstract We present the first real-time  ...  Acknowledgements This research was co-funded by the German Research Foundation (DFG), grant GRK-1773 Heterogeneous Image Systems, the ERC Starting Grant 335545 CapReal, and the Max Planck Center for Visual  ... 
doi:10.1145/2661229.2661232 fatcat:d7ix3rgmj5gldabgi23gfcfqji

Novel Views of Objects from a Single Image

Konstantinos Rematas, Chuong H. Nguyen, Tobias Ritschel, Mario Fritz, Tinne Tuytelaars
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
For the latter part, we propose an efficient 2D-to-3D alignment method that associates precisely the image appearance with the 3D model geometry with minimal user interaction.  ...  We propose a technique to use the structural information extracted from a 3D model that matches the image object in terms of viewpoint and shape.  ...  When a shape deformation model is available, the 3D shape can be deformed to fitting the 2D silhouette also leading to a 2D-to-3D alignment [24] .  ... 
doi:10.1109/tpami.2016.2601093 pmid:27541489 fatcat:6wwrt447knfxnn3o5dnyrkm3fy

Novel Views of Objects from a Single Image [article]

Konstantinos Rematas, Chuong Nguyen, Tobias Ritschel, Mario Fritz and Tinne Tuytelaars
2016 arXiv   pre-print
For the latter part, we propose an efficient 2D-to-3D alignment method that associates precisely the image appearance with the 3D model geometry with minimal user interaction.  ...  We propose a technique to use the structural information extracted from a 3D model that matches the image object in terms of viewpoint and shape.  ...  When a shape deformation model is available, the 3D shape can be deformed to fitting the 2D silhouette also leading to a 2D-to-3D alignment [20] .  ... 
arXiv:1602.00328v2 fatcat:wgvzi5fodrhbrpcppil52z5xcm

Ambient Occlusion and Edge Cueing for Enhancing Real Time Molecular Visualization

Marco Tarini, Paolo Cignoni, Claudio Montani
2006 IEEE Transactions on Visualization and Computer Graphics  
The proposed approach includes an innovative technique for efficient computation and storage of ambient occlusion terms, a small set of GPU accelerated procedural impostors for space-fill and ball-and-stick  ...  As a result, the user's understanding of the three-dimensional structure under inspection is strongly increased (even for still images), while the rendering still occurs in real time. !  ...  Zoppè for having introduced us to the field of Molecular Visualization.  ... 
doi:10.1109/tvcg.2006.115 pmid:17080857 fatcat:bk4toxvfeje3xgsjw3wuxiie6e

Geometric modeling based on polygonal meshes

Mario Botsch, Mark Pauly, Leif Kobbelt, Pierre Alliez, Bruno Lévy, Stephan Bischoff, Christian Rössl
2007 ACM SIGGRAPH 2007 courses on - SIGGRAPH '07  
He has published several papers in the area of geometry compression, mesh approximation, surface remeshing, mesh generation and surface parameterization.  ...  His current research interests include shape approximation, mesh generation, surface remeshing and surface reconstruction. Dr.  ...  In this context geometric models are often acquired by 3D scanning techniques and have to undergo post-processing and shape optimization techniques before being actually used in production.  ... 
doi:10.1145/1281500.1281640 dblp:conf/siggraph/BotschPKALBR07 fatcat:khwj3g4lu5eurovnvvt7hzenye

Real-time dense multi-scale workspace modeling on a humanoid robot

Rene Wagner, Udo Frese, Berthold Bauml
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Ideally, the robot should create a dense 3D environment model in real-time, all the time, and respect obstacle information from it in every move it makes as well as obtain the information it needs for  ...  We show how to extend the KinectFusion real-time SLAM algorithm to the multi-scale case as well as how to compute a multi-scale Euclidean distance transform (EDT) thereby establishing the link to optimization-based  ...  Birbach for performing the Kinect calibration and T. Hammer for preparing the graphics in Fig. 2 .  ... 
doi:10.1109/iros.2013.6697103 dblp:conf/iros/WagnerFB13 fatcat:cxmqxubla5ghjocjt4osb6ibve
« Previous Showing results 1 — 15 out of 93 results