Research map / Image generation / Editing and style transfer
Ultrafast Photorealistic Style Transfer via Neural Architecture Search
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 PhotoNAS rather than WCT² | Photorealistic style transfer · 73 content-style photo pairs | SSIM-Edge: 0.6112 -> 0.6932 | Helped |
| Use PhotoNet rather than WCT² | Photorealistic style transfer · 73 content-style photo pairs | SSIM-Whole: 0.4723 -> 0.7047 | Helped |
| Use PhotoNAS rather than WCT² | Photorealistic style transfer · 73 content-style photo pairs | Gram Loss: 1.1244 -> 1.7565 | Hurt |
| Prune PhotoNet using StyleNAS | PhotoNet · 73 content-style photo pairs | SSIM-Edge: 0.6922 -> 0.6932 | Helped |
| Prune PhotoNet using StyleNAS | PhotoNet · 73 content-style photo pairs | SSIM-Whole: 0.7047 -> 0.6728 | Hurt |
| Prune PhotoNet using StyleNAS | PhotoNet · 73 content-style photo pairs | Gram Loss: 1.1270 -> 1.7565 | Hurt |
| Use PhotoNAS rather than WCT² | Photorealistic style transfer · 25 content-style photo pairs | preference percentage: 16.11% -> 42.78% | Helped |
| Prune PhotoNet using StyleNAS | PhotoNet · 1024×512 | computing time: 1.06 -> 0.32 | Helped |
| Use evolutionary StyleNAS rather than random architecture search | PhotoNet search space · StyleNAS search | overall search objective: 0.0709 -> 0.0472 | Helped |
| Add bottleneck feature aggregation (BFA) (ablation) | PhotoNet · Photorealistic style transfer | fine-detail preservation | Helped |
| Replace skip connections with instance-normalized skip links (INSL) (ablation) | Photorealistic style transfer auto-encoder · Photorealistic style transfer | stylization and detail preservation | Helped |
| Add style-transfer modules at decoder stages (ablation) | PhotoNet · Photorealistic style transfer | stylization effects | Helped |
Closest papers by meaning
- Deep Translation Prior: Test-Time Training for Photorealistic Style Transfer (AAAI 2022 · similarity 0.88)
- Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer (CVPR 2017 · similarity 0.88)
- MicroAST: Towards Super-fast Ultra-Resolution Arbitrary Style Transfer (AAAI 2023 · similarity 0.88)
- FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields (AAAI 2024 · similarity 0.86)
- Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles (NeurIPS 2025 · similarity 0.86)
- Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network (CVPR 2024 · 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.