CD-GAN: a robust fusion-based generative adversarial network for unsupervised change detection between heterogeneous images.
Jin-Ju WangNicolas DobigeonMarie ChabertDing-Cheng WangJie HuangTing-Zhu HuangPublished in: CoRR (2022)
Keyphrases
- image data
- image database
- image analysis
- image noise
- input image
- three dimensional
- ground truth
- image features
- multiple images
- test images
- wireless sensor networks
- image retrieval
- geometric distortions
- image classification
- image collections
- segmentation method
- pattern recognition
- partial occlusion
- multi agent
- image regions
- feature descriptors
- multiscale
- multi sensor
- generative model
- geometric transformations
- registration errors
- fusion process
- information fusion
- image set
- image matching
- segmentation algorithm
- computer vision
- edge detection
- object recognition
- image segmentation