Setforge - Synthetic RGB-D Training Data Generation to Support CNN-Based Pose Estimation for Augmented Reality.
Shu ZhangCheng SongRafael RadkowskiPublished in: ISMAR Adjunct (2019)
Keyphrases
- augmented reality
- pose estimation
- markerless
- data generation
- camera tracking
- real scenes
- depth images
- d objects
- virtual reality
- computer vision
- human body
- degrees of freedom
- human computer interaction
- real environment
- active learning
- body parts
- training set
- feature points
- data streams
- multiple cameras
- focal length
- position and orientation
- three dimensional
- machine learning
- multi camera
- human motion
- object recognition
- virtual environment