Learning light field synthesis with Multi-Plane Images: scene encoding as a recurrent segmentation task.
Tomás VölkerGuillaume BoissonBertrand ChupeauPublished in: CoRR (2020)
Keyphrases
- light field rendering
- light field
- epipolar plane
- scene geometry
- image based rendering
- acquired images
- image formation
- static scene
- scene depth
- multi view
- face recognition across pose
- super resolution
- planar regions
- imaging systems
- three dimensional
- active learning
- plenoptic function
- outdoor scenes
- densely sampled
- captured images
- input image
- real scenes
- raw image
- camera array
- complex scenes
- video frames
- feature points
- level set
- video sequences