A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
Face Recognition Based on Fitting a 3D Morphable Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Stereo Matching Using Reliability-Based Dynamic Programming and Consistency Constraints
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
A Quasi-Dense Approach to Surface Reconstruction from Uncalibrated Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Dense Stereo Matching Using Two-Pass Dynamic Programming with Generalized Ground Control Points
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Efficient Belief Propagation for Early Vision
International Journal of Computer Vision
Region-Tree Based Stereo Using Dynamic Programming Optimization
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
An Improved 3D Human Face Reconstruction Approach Based on Cubic Splines Models
3DPVT '06 Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)
Stereo Processing by Semiglobal Matching and Mutual Information
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Alignment Via Component-Based Discriminative Search
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
A quantitative evaluation for 3D face reconstruction algorithms
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Fast acquisition of dense depth data by a new structured light scheme
Computer Vision and Image Understanding
High-quality single-shot capture of facial geometry
ACM SIGGRAPH 2010 papers
High resolution passive facial performance capture
ACM SIGGRAPH 2010 papers
Efficient large-scale stereo matching
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
3D reconstruction of human face based on an improved seeds-growing algorithm
Machine Vision and Applications - Special Issue on Dynamic Textures in Video
Rapid acquisition of specular and diffuse normal maps from polarized spherical gradient illumination
EGSR'07 Proceedings of the 18th Eurographics conference on Rendering Techniques
| Hi-index | 0.00 |
This paper describes a robust 3D human face reconstruction approach by consumer binocular-stereo cameras. It aims to handle the ambiguity due to the captured noisy or distorted stereo images and the textureless nature of human face. First, seven facial feature points are extracted to deform a generic 3D face for initialization. A novel two-pass seed searching algorithm is then employed to deliver a set of sparse seeds. Also proposed is the seed outlier detection algorithm by using polynomial curves to introduce the smoothness prior. The resulting seeds significantly reduce the ambiguity, and propagate to remaining pixels using a modified seed growing strategy. The discussion also addresses polynomial curve fitting based disparity map denoising, stereo refinement and multibase-line matching for epipolar misalignment. They allow us to produce dense and detail preserving face models despite the low quality of image capture with consumer cameras. Both qualitative and quantitative evaluations demonstrate the state-of-the-art performance of our approach, and the accuracy is comparable to some active systems. Our approach can also deal with large facial expressions.