AI Paper Atlas

Research map / Image generation / Editing and style transfer

StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model

Zipeng Xu, Enver Sangineto, Nicu Sebe

ICCV 2023 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use CLIP similarity as an RL reward on discrete tokens instead of directly optimizing CLIP scoreStyleDALLE-1 · MS-COCO, AFHQ, ImageNet-100CLIP similarity score: 26.11 -> 30.61 (Fauvism, COCO)Improved
remove image captions from the prompt-based rewardStyleDALLE-1 · style transfer (qualitative)visual qualityNo clear effect
add captions to the prompt-based rewardStyleDALLE-Ru · style transfer (qualitative)content consistencyImproved
down-sample discrete tokens before the NAT modelStyleDALLE · style transfer (qualitative)style incorporationImproved
use Ru-DALLE VQGAN instead of DALL-E dVAEStyleDALLE · user studypreference (%): 15.33 -> 68.76Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy