Zero-shot spatial layout conditioning for text-to-image diffusion models.
Guillaume CouaironMarlène CareilMatthieu CordStéphane LathuilièreJakob VerbeekPublished in: ICCV (2023)
Keyphrases
- spatial layout
- scene recognition
- input image
- single image
- diffusion models
- image data
- image retrieval
- low level
- image segmentation
- image content
- multiscale
- indoor environments
- scene classification
- feature points
- image representation
- image classification
- diffusion model
- image regions
- scene understanding
- information retrieval
- test images
- keypoints
- text mining
- high resolution