Filters








3,484 Hits in 8.1 sec

Regression based automatic face annotation for deformable model building

Akshay Asthana, Simon Lucey, Roland Goecke
2011 Pattern Recognition  
We show the generalisability of the proposed approach by automatically annotating the face images from four different databases and verifying the results by comparing them with a ground truth obtained  ...  We propose a regression-based approach for automatic annotation of face images at arbitrary pose and expression, and for deformable model building using only the annotated frontal images.  ...  Acknowledgement The authors would like to thank Jason Saragih (CSIRO) for the use of the DeMoLib software, and Tom Gedeon (ANU) and Novi Quadrianto (NICTA/ANU) for their insightful suggestions and comments  ... 
doi:10.1016/j.patcog.2011.03.014 fatcat:bxhbuddbozdbbdktd3qsz4iv2e

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
MOBIO: Mobile Biometric Face and Speaker Authentication Specular Surface Reconstruction from Sparse Reflection Correspondences Demo: A Practical and Robust System for Object Detection and Pose Estimation  ...  Weakly Supervised Learning from Multiple Imperfect Oracles Liu, Shuaicheng Super Resolution using Edge Prior and Single Image Detail Synthesis Liu, Shubao Ray Markov Random Fields for Image-Based  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Pose-robust face signature for multi-view face recognition

Pengfei Dou, Lingfeng Zhang, Yuhang Wu, Shishir K. Shah, Ioannis A. Kakadiaris
2015 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS)  
We propose a novel framework for multi-view face recognition based on extracting and matching pose-robust face signatures from 2D images.  ...  Specifically, we propose an efficient method for monocular 3D face reconstruction, which is used to lift the 2D facial appearance to a canonical texture space and estimate the self-occlusion.  ...  This research was funded in part by the US Army Research Lab (W911NF-13-1-0127) and the UH Hugh Roy and Lillie Cranz Cullen Endowment Fund.  ... 
doi:10.1109/btas.2015.7358788 dblp:conf/btas/DouZWSK15 fatcat:6bxncscu6rhjdeb2gesjhdmqai

Spotting the Details: The Various Facets of Facial Expressions

Carl Martin Grewe, Gabriel Le Roux, Sven-Kristofer Pilz, Stefan Zachow
2018 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)  
We present a novel high-quality 3D Facial Expression Morphable Model built from a large-scale face database as a tool for expression analysis and synthesis.  ...  Establishment of accurate dense correspondence, up to finest skin features, enables a detailed statistical analysis of facial expressions.  ...  ACKNOWLEDGEMENTS We kindly thank Sophie Buchner and Alexander Tack for their valuable support and discussions during preparation of this paper.  ... 
doi:10.1109/fg.2018.00049 dblp:conf/fgr/GreweRPZ18 fatcat:vj3yxyn2azg25gxydekwxsf2yu

Facial Performance Transfer via Deformable Models and Parametric Correspondence

A. Asthana, M. de la Hunty, A. Dhall, R. Goecke
2012 IEEE Transactions on Visualization and Computer Graphics  
The main advantage of modelling this parametric correspondence is that it allows a "meaningful" transfer of both the non-rigid shape and texture across faces irrespective of the speakers' gender, shape  ...  We explore linear and non-linear methods for modelling the parametric correspondence between the AAMs and show that the sparse linear regression method performs the best.  ...  functions were learnt from 99 correspondence images and the remaining single image A1 was used to synthesise the correspondence image A2.  ... 
doi:10.1109/tvcg.2011.157 pmid:21931176 fatcat:ab6cqgs5uveyrh7o7tpayoxko4

Free-Viewpoint RGB-D Human Performance Capture and Rendering [article]

Phong Nguyen-Ha, Nikolaos Sarafianos, Christoph Lassner, Janne Heikkila, Tony Tung
2022 arXiv   pre-print
To tackle these challenges we introduce a novel view synthesis framework that generates realistic renders from unseen views of any human captured from a single-view and sparse RGB-D sensor, similar to  ...  Our approach outperforms prior view synthesis methods and is robust to different levels of depth sparsity.  ...  Le, H.A., Mensink, T., Das, P., Gevers, T.: Novel view synthesis from a single image via point cloud transformation. In: BMVC (2020) 5, 6 35.  ... 
arXiv:2112.13889v4 fatcat:syvjqwsf3jgi3psxhjfd32u2gm

BodyMap: Learning Full-Body Dense Correspondence Map [article]

Anastasia Ianina, Nikolaos Sarafianos, Yuanlu Xu, Ignacio Rocco, Tony Tung
2022 arXiv   pre-print
Furthermore, we show various applications ranging from multi-layer dense cloth correspondence, neural rendering with novel-view synthesis and appearance swapping.  ...  In this paper we present BodyMap, a new framework for obtaining high-definition full-body and continuous dense correspondence between in-the-wild images of clothed humans and the surface of a 3D template  ...  We thank Tuur Stuyck for his help to run cloth simulation and Vasil Khalidov for his help with running the code of the Continuous Surface Embeddings paper.  ... 
arXiv:2205.09111v1 fatcat:s4eo3yvasjbtplj7raaq7s2eki

Digital ira and beyond

Javier von der Pahlen, Jorge Jimenez, Etienne Danvoye, Paul Debevec, Graham Fyffe, Oleg Alexander
2014 ACM SIGGRAPH 2014 Courses on - SIGGRAPH '14  
An animation solver creates a performance graph representing dense GPU optical flow between video frames and the eight expressions; dense optical flow and 3D triangulation are computed, yielding per-frame  ...  Expression UVs were interactively corresponded to the neutral expression, retopologized to an artist mesh.  ...  We thank the authors of [Beeler et al. 2010] and [Klaudiny et al. 2010] for graciously  ... 
doi:10.1145/2614028.2615407 dblp:conf/siggraph/PahlenJDDFA14 fatcat:fon6t6inx5cdlj5bpg3p53dr7i

A Comprehensive Survey on Pose-Invariant Face Recognition [article]

Changxing Ding, Dacheng Tao
2016 arXiv   pre-print
., pose-robust feature extraction approaches, multi-view subspace learning approaches, face synthesis approaches, and hybrid approaches.  ...  Compared to frontal face recognition, which has been intensively studied and has gradually matured in the past few decades, pose-invariant face recognition (PIFR) remains a largely unsolved problem.  ...  In Arashloo and Kittler (2014)'s work, semantically corresponding patches are densely sampled via MRF and features are extracted by multiple face descriptors.  ... 
arXiv:1502.04383v3 fatcat:opz5onz775cj5hxvoaggvmp52q

A Comprehensive Survey on Pose-Invariant Face Recognition

Changxing Ding, Dacheng Tao
2016 ACM Transactions on Intelligent Systems and Technology  
., pose-robust feature extraction approaches, multi-view subspace learning approaches, face synthesis approaches, and hybrid approaches.  ...  Compared to frontal face recognition, which has been intensively studied and has gradually matured in the past few decades, pose-invariant face recognition (PIFR) remains a largely unsolved problem.  ...  In Arashloo and Kittler (2014)'s work, semantically corresponding patches are densely sampled via MRF and features are extracted by multiple face descriptors.  ... 
doi:10.1145/2845089 fatcat:dbzheowl5vha7h3rglrpkphsla

Casual 6-DoF: free-viewpoint panorama using a handheld 360 camera [article]

Rongsen Chen, Fang-Lue Zhang, Simon Finnie, Andrew Chalmers, Teahyun Rhee
2022 arXiv   pre-print
When used to reconstruct 6-DoF views, it often requires capturing hundreds of images, making data capture a tedious and time-consuming process.  ...  Our method shows better visual quality and robustness in the tested scenes.  ...  The estimated sparse and dense depths will then be refined to produce high-quality depth panoramas in several steps; sparse and dense depth fusion, depth correction via raymarching, and forward depth projection  ... 
arXiv:2203.16756v1 fatcat:7zabtcsfa5a4vjp3su3g2sidfm

RotoTexture: Automated Tools for Texturing Raw Video

Hui Fang, J.C. Hart
2006 IEEE Transactions on Visualization and Computer Graphics  
of a texture image and the surface texture synthesis from a texture swatch.  ...  The texture synthesis method uses a coarse optical flow to advect clusters of pixels corresponding to patches of similarly oriented surface points.  ...  Yizhou Yu provided helpful tools for feature tracking and optical flow interpolation, and he and David Raila provided video equipment.  ... 
doi:10.1109/tvcg.2006.102 pmid:17073379 fatcat:zjnugu6vyzhirjtagg3q7bdlta

GazeDirector: Fully Articulated Eye Gaze Redirection in Video [article]

Erroll Wood, Tadas Baltrusaitis, Louis-Philippe Morency, Peter Robinson, Andreas Bulling
2017 arXiv   pre-print
It then redirects gaze by 1) warping the eyelids from the original image using a model-derived flow field, and 2) rendering and compositing synthesized 3D eyeballs onto the output image in a photorealistic  ...  Our method first tracks the eyes by fitting a multi-part eye region model to video frames using analysis-by-synthesis, thereby recovering eye region shape, texture, pose, and gaze simultaneously.  ...  Acknowledgements This work was funded, in part, by the Cluster of Excellence on Multimodal Computing and Interaction at Saarland University, Germany.  ... 
arXiv:1704.08763v1 fatcat:u2wilgnxpncfjmnf6olb5pdafe

Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

Dongyu Zhang, Liang Lin, Tianshui Chen, Xian Wu, Wenwei Tan, Ebroul Izquierdo
2017 IEEE Transactions on Image Processing  
In the stage of sketch rendering, our approach automatically generates structural and textural representations for the input photo and produces the final result via a probabilistic fusion scheme.  ...  In the training stage, we first decompose the input face photo into different components according to their representational contents (i.e., structural and textural parts) by using a pre-trained Convolutional  ...  Currently, in the training BFCN, a face image and its corresponding sketch are roughly aligned by eyes.  ... 
doi:10.1109/tip.2016.2623485 pmid:27831874 fatcat:oedqykupxbbe3llk274azx67he

Intuitive, Interactive Beard and Hair Synthesis With Generative Models

Kyle Olszewski, Duygu Ceylan, Jun Xing, Jose Echevarria, Zhili Chen, Weikai Chen, Hao Li
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
The synthesis is controlled by simple and sparse guide strokes from the user defining the general structural and color properties of the target hairstyle.  ...  We present an interactive approach to synthesizing realistic variations in facial hair in images, ranging from subtle edits to existing hair to the addition of complex and challenging hair in images of  ...  [51] propose to edit and synthesize beards by modeling faces as a composition of multiple layers. Mohammed et al.  ... 
doi:10.1109/cvpr42600.2020.00747 dblp:conf/cvpr/OlszewskiCXEC0L20 fatcat:byc66fwmtre3jchntod3kalxm4
« Previous Showing results 1 — 15 out of 3,484 results