Research map / Image generation / Editing and style transfer
Adjustable Real-time 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 |
|---|---|---|---|
| Adjust per-layer style-loss parameters at inference time | Adjustable Real-time Style Transfer · Style transfer | style loss at the corresponding layer | Helped |
| Adjust loss parameters after training instead of retraining with different loss weights | Adjustable Real-time Style Transfer · Style transfer | stylization similarity to retrained model | No clear effect |
| Randomize loss-adjustment parameters | Adjustable Real-time Style Transfer · Fixed content/style image pair | stylization diversity while preserving style and content | Helped |
| Add small-magnitude noise to the content image | Adjustable Real-time Style Transfer · Fixed content/style image pair | spatial diversity of style elements | Helped |
| Combine randomized loss-adjustment parameters with content-image noise | Adjustable Real-time Style Transfer · Fixed content/style image pair | stylization diversity | Helped |
| Add random noise to style parameters at run time | Conditional-instance-normalization baseline · Fixed style image | similarity to input style | Hurt |
| Train with random noise on style parameters and add noise again at run time | Conditional-instance-normalization baseline · Fixed style image | stylization diversity | Hurt |
| Increase the number of residual blocks by 3 (ablation) | Base stylizing network T · Style transfer | stylization quality | Helped |
| Use StyleNet to generate multiple stylizations instead of adjustable loss parameters | StyleNet · Fixed content/style image pair | stylization diversity | Hurt |
Closest papers by meaning
- Real-Time Neural Style Transfer for Videos (CVPR 2017 · similarity 0.90)
- MetaStyle: Three-Way Trade-off among Speed, Flexibility, and Quality in Neural Style Transfer (AAAI 2019 · similarity 0.90)
- Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer (CVPR 2017 · similarity 0.90)
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 2024 · similarity 0.89)
- HSI: A Holistic Style Injector for Arbitrary Style Transfer (CVPR 2025 · similarity 0.88)
- Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer (CVPR 2024 · similarity 0.88)
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.