Tag results for monocular
Results from all user's collections (4 out of ~4)
The results from your search appear low, try our web search for better results.
|
head tracking for ipad: glasses-free 3d display
Bookmarked 804 weeks ago head-coupled perspective on mobile devices we track the head of the user with the front facing camera in order to create a glasses-free monocular 3d display such spatially-aware mobile display enables to improve the possibilities of interaction it does not use the accelerometers and relies only on the front camera the demo with the targets has been inspired by the work of johnny lee http:youtubejd3-eiid-uw with a wii remote if you want to try this demo just download i3d on the app store but remember this is still work on progress jeremie francone laurence nigayehci research group http:iihmimagfrenlaboratory of informatics of grenoble http:wwwliglabfr university joseph fourier http:wwwujf-grenoblefrsong: quotet apresquot by daduk |
|
face2face: real-time face capture and reenactment of rgb videos cvpr 2016 oral
Bookmarked 553 weeks ago cvpr 2016 paper video oralproject page: http:wwwgraphicsstanfordeduniessnerthies2016facehtmlwe present a novel approach for real-time facial reenactment of a monocular target video sequence eg youtube video the source sequence is also a monocular video stream captured live with a commodity webcam our goal is to animate the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion to this end we first address the under-constrained problem of facial identity recovery from monocular video by non-rigid model-based bundling at run time we track facial expressions of both source and target video using a dense photometric consistency measure reenactment is then achieved by fast and efficient deformation transfer between source and target the mouth interior that best matches the re-targeted expression is retrieved from the target sequence and warped to produce an accurate fit finally we convincingly re-render the synthesized target face on top of the corresponding video stream such that it seamlessly blends with the real-world illumination we demonstrate our method in a live setup where youtube videos are reenacted in real time |
< prev | next > |