Multiple view geometry in computer visiond
Multiple view geometry in computer visiond
PG '02 Proceedings of the 10th Pacific Conference on Computer Graphics and Applications
Free-viewpoint video of human actors
ACM SIGGRAPH 2003 Papers
Accurate Head Pose Tracking in Low Resolution Video
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Photo tourism: exploring photo collections in 3D
ACM SIGGRAPH 2006 Papers
Modeling the World from Internet Photo Collections
International Journal of Computer Vision
3D Face Reconstruction from 2D Images
DICTA '08 Proceedings of the 2008 Digital Image Computing: Techniques and Applications
High-quality single-shot capture of facial geometry
ACM SIGGRAPH 2010 papers
High resolution passive facial performance capture
ACM SIGGRAPH 2010 papers
Automatic Acquisition of Time-Slice Image Sequences
CVMP '10 Proceedings of the 2010 Conference on Visual Media Production
Hi-index | 0.00 |
We propose a method for creating flexible-viewpoint facial video from monocular input employing highly detailed static 3D reconstructions of an actor's head. We use the term flexible-viewpoint to indicate that the viewpoint can be arbitrarily chosen (as in free-viewpoint video), but from a restricted set of viewing directions. Our method enables dynamic changes of the viewpoint without requiring estimation of the head geometry form the video sequences which is hard with the methods typically used for creating free-viewpoint video. Alongside video capture of a certain actor, we record static high resolution stereo images of the actor's head and face. From these images, we create a detailed 3D model of the head by image-based reconstruction methods. We propose two methods to register this 3D model to the a starting frame of the video stream following the actors head and facial action. Furthermore, we show how model-based tracking over the whole video sequence provides precise head pose estimates for each video frame. Once the registration is complete, the 3D model serves as geometric proxy for image-based rendering techniques in order to create novel viewpoints using the video stream as texture.