Single Image Object Counting and Localizing using Active-Learning.
Inbar Huberman-SpiegelglasRaanan FattalPublished in: CoRR (2021)
Keyphrases
- single image
- active learning
- partially occluded
- multiple images
- shape recovery
- image pairs
- d scene
- scene geometry
- light source
- shape from shading
- information from multiple images
- multiple objects
- d objects
- machine learning
- indoor scenes
- vanishing points
- structured light
- spherical harmonics
- super resolution
- semi supervised
- cast shadows
- complex scenes
- multiscale
- high quality
- multiple views
- intrinsic images
- lambertian surface
- intrinsic image decomposition
- lighting conditions