Guiding Instruction-based Image Editing via Multimodal Large Language Models.
Tsu-Jui FuWenze HuXianzhi DuWilliam Yang WangYinfei YangZhe GanPublished in: ICLR (2024)
Keyphrases
- language model
- image editing
- language modeling
- n gram
- gradient domain
- retrieval model
- multimedia
- document retrieval
- probabilistic model
- adobe photoshop
- query expansion
- image processing
- language modelling
- test collection
- multi modal
- statistical language models
- information retrieval
- speech recognition
- language models for information retrieval
- context sensitive
- digital imaging
- vector space model
- pseudo relevance feedback
- black and white
- translation model
- smoothing methods
- document ranking
- okapi bm
- ad hoc information retrieval
- query specific
- query terms
- image enhancement
- audio visual
- low cost
- bayesian networks