AI Paper Atlas

Research map / Image generation / Editing and style transfer

QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity

Siyu Huang, Jie An, Donglai Wei, Jiebo Luo, Hanspeter Pfister

CVPR 2023 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 52 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
Increase visual-fidelity control from α=0 to α=1QuantArt with β=1 · Photo-to-ArtworkFID: 25.590 -> 17.787Improved
Increase visual-fidelity control from α=0 to α=1QuantArt with β=1 · Photo-to-ArtworkGram loss: 0.395 -> 0.864Hurt
Add quantization in SGA (ablation)QuantArt · Photo-to-ArtworkFID: 18.757 -> 17.787Improved
Add all quantization operators (ablation)QuantArt · Photo-to-ArtworkFID: 25.590 -> 17.787Improved
Use code size 16×16 rather than 8×8 (ablation)QuantArt · Photo-to-ArtworkFID: 27.741 -> 17.787Improved
Use code size 16×16 rather than 32×32 (ablation)QuantArt · Photo-to-ArtworkFID: 28.663 -> 17.787Improved
Add self-attention in SGA (ablation)QuantArt · Photo-to-ArtworkFID: 19.025 -> 17.787Improved
Add ResBlock in SGA (ablation)QuantArt · Photo-to-ArtworkFID: 27.177 -> 17.787Improved
Use SGA instead of the StyTR2 decoder layer (ablation)QuantArt · Photo-to-ArtworkFID: 26.299 -> 17.787Improved
Use separate encoders rather than shared encoders (ablation)QuantArt · Photo-to-ArtworkFID: 30.806 -> 17.787Improved
Use separate encoders and decoders rather than sharing both (ablation)QuantArt · Photo-to-ArtworkFID: 35.830 -> 17.787Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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