Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision.
Hsiao-Yu Fish TungAdam W. HarleyWilliam SetoKaterina FragkiadakiPublished in: ICCV (2017)
Keyphrases
- input image
- image data
- image representation
- multiscale
- image retrieval
- image analysis
- image features
- test images
- image segmentation
- single image
- segmentation method
- edge detection
- high resolution
- image collections
- low level
- object detection
- image set
- spatial information
- vector field
- pixel values
- grey level
- image pixels
- template matching
- image processing
- region of interest
- image content
- hough transform
- active learning
- multi agent
- similarity measure
- multimedia