Combining dense nonrigid structure from motion and 3D morphable models for monocular 4D face reconstruction.
Mohammad Rami KoujanAnastasios RoussosPublished in: CVMP (2018)
Keyphrases
- structure from motion
- image sequences
- bundle adjustment
- camera parameters
- d morphable model
- point cloud
- computer vision
- human faces
- missing data
- camera motion
- motion analysis
- architectural scenes
- object tracking
- pose estimation
- depth information
- optical flow
- stereo camera
- camera pose
- active appearance models
- three dimensional
- depth map
- motion estimation
- motion parameters
- object recognition
- ego motion
- video sequences