SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation.
Aysim TokerMarvin EisenbergerDaniel CremersLaura Leal-TaixéPublished in: CoRR (2024)
Keyphrases
- semantic segmentation
- image data
- superpixels
- conditional random fields
- image features
- input image
- bounding box
- multiscale
- image content
- diffusion models
- scene classification
- image classification
- image analysis
- weakly supervised
- pascal voc
- test images
- image retrieval
- single image
- spatial information
- segmentation algorithm
- image segmentation
- pairwise
- high resolution
- segmentation method
- image representation
- image set
- pixel level
- image matching
- object recognition