Reconstructing Images of Two Adjacent Objects through Scattering Medium Using Generative Adversarial Network.
Xuetian LaiQiongyao LiZiyang ChenXiaopeng ShaoJixiong PuPublished in: CoRR (2021)
Keyphrases
- complex scenes
- input image
- real world objects
- image data
- image regions
- three dimensional
- spatial relationships
- image database
- image features
- ground truth
- image analysis
- bounding box
- image classification
- multiple objects
- image registration
- individual objects
- image pixels
- visual appearance
- target object
- real objects
- image matching
- spatial information
- image retrieval
- object recognition
- outdoor scenes
- geometric information
- visual data
- image set
- viewing conditions
- objects represented
- multiple images
- partial occlusion
- image collections
- test images
- image annotation
- keypoints
- computer graphics
- generative model
- feature points
- edge detection
- real world scenes
- wireless sensor networks
- sample images
- detecting objects
- face recognition