A neural network for recovering 3D shape from erroneous and few depth maps of shaded images.
Mohamad Ivan FananyItsuo KumazawaPublished in: Pattern Recognit. Lett. (2004)
Keyphrases
- depth map
- three dimensional
- input image
- multi view
- multi view stereo
- image data
- depth estimation
- depth information
- stereoscopic images
- scene reconstruction
- stereo algorithm
- temporally consistent
- image registration
- multiple images
- single image
- dense depth maps
- d scene
- stereo matching
- scene geometry
- multiview images
- view synthesis
- high quality
- intermediate views
- depth data
- real scenes
- object recognition
- stereo camera
- stereo pair
- lighting conditions
- temporal consistency
- image matching
- stereo reconstruction
- multiple views
- free viewpoint
- feature points
- input data
- d objects
- image sequences