QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity

12/20/2022
by   Siyu Huang, et al.
0

The mechanism of existing style transfer algorithms is by minimizing a hybrid loss function to push the generated image toward high similarities in both content and style. However, this type of approach cannot guarantee visual fidelity, i.e., the generated artworks should be indistinguishable from real ones. In this paper, we devise a new style transfer framework called QuantArt for high visual-fidelity stylization. QuantArt pushes the latent representation of the generated artwork toward the centroids of the real artwork distribution with vector quantization. By fusing the quantized and continuous latent representations, QuantArt allows flexible control over the generated artworks in terms of content preservation, style similarity, and visual fidelity. Experiments on various style transfer settings show that our QuantArt framework achieves significantly higher visual fidelity compared with the existing style transfer methods.

READ FULL TEXT

page 13

page 14

page 15

page 16

page 17

page 18

page 21

page 27

research
04/29/2019

Style Transfer by Relaxed Optimal Transport and Self-Similarity

Style transfer algorithms strive to render the content of one image usin...
research
11/07/2018

SurReal: enhancing Surgical simulation Realism using style transfer

Surgical simulation is an increasingly important element of surgical edu...
research
08/29/2023

WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification

Currently, style augmentation is capturing attention due to convolutiona...
research
08/14/2023

Hierarchy Flow For High-Fidelity Image-to-Image Translation

Image-to-image (I2I) translation comprises a wide spectrum of tasks. Her...
research
06/25/2021

Interactive Multi-level Stroke Control for Neural Style Transfer

We present StyleTune, a mobile app for interactive multi-level control o...
research
03/02/2022

Styleverse: Towards Identity Stylization across Heterogeneous Domains

We propose a new challenging task namely IDentity Stylization (IDS) acro...
research
08/29/2021

Non-Parametric Neural Style Transfer

It seems easy to imagine a photograph of the Eiffel Tower painted in the...

Please sign up or login with your details

Forgot password? Click here to reset