A training-free method that compares channel-wise statistics of diffusion model features retrieves images by artistic style and outperforms trained baselines.
Im- age style transfer using convolutional neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
IntroStyle: Training-Free Introspective Style Attribution using Diffusion Features
A training-free method that compares channel-wise statistics of diffusion model features retrieves images by artistic style and outperforms trained baselines.