Research map / Image generation / Editing and style transfer
MicroAST: Towards Super-fast Ultra-Resolution Arbitrary Style Transfer
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use MicroAST instead of the strongest SSIM baseline, LST-U | 4K arbitrary style transfer · 4K ultra-resolution | SSIM: 0.441 -> 0.531 | Helped |
| Use MicroAST instead of Collab-Distill | 4K arbitrary style transfer · 4K ultra-resolution | time (sec): 7.139 -> 0.522 | Helped |
| Use MicroAST instead of the lowest-parameter baseline, Collab-Distill | 4K arbitrary style transfer · 4K ultra-resolution | parameters (millions): 2.146 -> 0.472 | Helped |
| Use MicroAST instead of Collab-Distill | 4K arbitrary style transfer · 4K ultra-resolution | preference (%): 20.5 -> 29.1 | Helped |
| Use MicroAST instead of Collab-Distill | 4K arbitrary style transfer · 4K ultra-resolution | Style Loss: 2.183 -> 2.342 | Hurt |
| Add style signal contrastive loss (ablation) | MicroAST · arbitrary style transfer | stylization quality | Helped |
| Add style signal contrastive loss (ablation) | MicroAST · arbitrary style transfer | SSIM | Helped |
| Add style signal contrastive loss (ablation) | MicroAST · arbitrary style transfer | Style Loss | Helped |
| Use multi-level rather than single-level DualMod (ablation) | MicroAST · arbitrary style transfer | stylization effects | Helped |
| Use DualMod rather than feature modulation or filter modulation alone (ablation) | MicroAST · arbitrary style transfer | stylization quality | Helped |
Closest papers by meaning
- Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer (CVPR 2017 · similarity 0.90)
- Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer (CVPR 2023 · similarity 0.90)
- Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization (AAAI 2022 · similarity 0.90)
- A Content Transformation Block for Image Style Transfer (CVPR 2019 · similarity 0.89)
- SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer (CVPR 2025 · similarity 0.87)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.87)
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.