Text-image conditioned diffusion for consistent text-to-3D generation.
Yuze HeYushi BaiMatthieu LinJenny ShengYubin HuQi WangYu-Hui WenYong-Jin LiuPublished in: Comput. Aided Geom. Des. (2024)
Keyphrases
- single image
- multiscale
- image data
- image features
- input image
- text retrieval
- image content
- text graphics
- image analysis
- text generation
- image classification
- image segmentation
- template matching
- text information
- information retrieval
- keywords
- textual and visual information
- image matching
- hough transform
- segmentation method
- text mining
- image representation
- feature points
- image collections
- image structure
- image retrieval
- spatial information
- binary images
- test images
- textual information
- co occurrence
- object recognition