AtlantaNet: Inferring the 3D Indoor Layout from a Single $360^\circ $ Image Beyond the Manhattan World Assumption.
Giovanni PintoreMarco AgusEnrico GobbettiPublished in: ECCV (8) (2020)
Keyphrases
- manhattan world
- single image
- vanishing points
- image features
- man made environments
- image analysis
- multiscale
- image content
- input image
- image segmentation
- image retrieval
- calibrated cameras
- image structure
- scale space
- piecewise planar
- man made
- high resolution
- geometric constraints
- perceptual grouping
- aerial images
- image matching
- human motion analysis
- hough transform
- video sequences