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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Increase visual-fidelity control from α=0 to α=1 | QuantArt with β=1 · Photo-to-Artwork | FID: 25.590 -> 17.787 | Improved |
| Increase visual-fidelity control from α=0 to α=1 | QuantArt with β=1 · Photo-to-Artwork | Gram loss: 0.395 -> 0.864 | Hurt |
| Add quantization in SGA (ablation) | QuantArt · Photo-to-Artwork | FID: 18.757 -> 17.787 | Improved |
| Add all quantization operators (ablation) | QuantArt · Photo-to-Artwork | FID: 25.590 -> 17.787 | Improved |
| Use code size 16×16 rather than 8×8 (ablation) | QuantArt · Photo-to-Artwork | FID: 27.741 -> 17.787 | Improved |
| Use code size 16×16 rather than 32×32 (ablation) | QuantArt · Photo-to-Artwork | FID: 28.663 -> 17.787 | Improved |
| Add self-attention in SGA (ablation) | QuantArt · Photo-to-Artwork | FID: 19.025 -> 17.787 | Improved |
| Add ResBlock in SGA (ablation) | QuantArt · Photo-to-Artwork | FID: 27.177 -> 17.787 | Improved |
| Use SGA instead of the StyTR2 decoder layer (ablation) | QuantArt · Photo-to-Artwork | FID: 26.299 -> 17.787 | Improved |
| Use separate encoders rather than shared encoders (ablation) | QuantArt · Photo-to-Artwork | FID: 30.806 -> 17.787 | Improved |
| Use separate encoders and decoders rather than sharing both (ablation) | QuantArt · Photo-to-Artwork | FID: 35.830 -> 17.787 | Improved |
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.
- StyTR2 — StyTr2: Image Style Transfer With Transformers (CVPR 2022) · better on 3 of 4 shared results
- ArtFlow — ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows (CVPR 2021) · better on 0 of 2 shared results
- AdaAttN — AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer (ICCV 2021) · better on 2 of 2 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
- Style Transfer by Relaxed Optimal Transport and Self-Similarity (CVPR 2019 · similarity 0.89)
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 2024 · similarity 0.88)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.87)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.87)
- Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation (CVPR 2025 · similarity 0.86)
- HSI: A Holistic Style Injector for Arbitrary Style Transfer (CVPR 2025 · similarity 0.86)
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.
