GPU-accelerated depth codec for real-time, high-quality light field reconstruction.
Babis KoniarisMaggie KosekDavid SinclairKenny MitchellPublished in: Proc. ACM Comput. Graph. Interact. Tech. (2018)
Keyphrases
- gpu accelerated
- light field
- real time
- high quality
- super resolution
- depth map
- single shot
- epipolar plane
- scene depth
- high resolution
- multi view
- scene geometry
- finite element
- image reconstruction
- d scene
- image formation
- face recognition across pose
- sequence alignment
- image based rendering
- three dimensional
- light field rendering
- single image
- defocus blur
- active learning
- multimedia
- depth images
- depth estimation
- motion estimation
- viewpoint
- plenoptic function