VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders.

Xuyang Liu Siteng Huang Yachen Kang Honggang Chen Donglin Wang

Published in: CoRR (2023)

Keyphrases

web images
input image
image features
image data
image segmentation
image analysis
diffusion models
image retrieval
multiscale
vector field
edge detection
information retrieval
optical flow
visual information
high resolution
keywords
text mining
visual features
information processing
social networks