Research map / Image generation / GANs
DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer
Wenju Xu, Chengjiang Long, Ruisheng Wang, Guanghui Wang
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 |
|---|---|---|---|
| use SW-LIN decoder instead of instance normalization (ablation) | DRB-GAN · WikiArt ablation | deception score: 0.561 -> 0.573 | Improved |
| use SW-LIN decoder instead of layer normalization (ablation) | DRB-GAN · WikiArt ablation | deception score: 0.568 -> 0.573 | Improved |
| use Dynamic ResBlock instead of AdaIN ResBlock (ablation) | DRB-GAN · WikiArt ablation | deception score: 0.552 -> 0.573 | Improved |
| add VGG encoder to the style code (ablation) | DRB-GAN · WikiArt ablation | content score: 66.3% -> 72.2% | Improved |
| add style classification loss (ablation) | DRB-GAN · WikiArt ablation | deception score: 0.571 -> 0.573 | No clear effect |
| add adversarial loss (ablation) | DRB-GAN · WikiArt ablation | deception score: 0.542 -> 0.573 | Improved |
| add adversarial loss (ablation) | DRB-GAN · WikiArt ablation | content score: 32.2% -> 72.2% | Improved |
| increase dynamic blocks from 1 to 4 (ablation) | DRB-GAN · WikiArt | deception score: 0.567 -> 0.573 | Improved |
| use one dynamic block instead of four AdaIN blocks (ablation) | DRB-GAN · WikiArt | deception score: 0.558 -> 0.567 | Improved |
| increase collection size K from 2 to 20 | DRB-GAN · Collection style transfer | deception score: 0.576 -> 0.583 | Improved |
| increase collection size K from 2 to 20 | AdaIN · Collection style transfer | deception score: 0.066 -> 0.011 | Hurt |
| use collection discriminator instead of conditional discriminator (ablation) | DRB-GAN · Qualitative comparison | visual quality | Improved |
Closest papers by meaning
- A Geometrical Perspective on Image Style Transfer with Adversarial Learning (TPAMI 2020 · similarity 0.89)
- Preserving Structural Consistency in Arbitrary Artist and Artwork Style Transfer (AAAI 2023 · similarity 0.88)
- StyleGAN2 Distillation for Feed-forward Image Manipulation (ECCV 2020 · similarity 0.87)
- Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer (CVPR 2017 · similarity 0.87)
- A Flexible Convolutional Solver for Fast Style Transfers (CVPR 2019 · similarity 0.86)
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 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.
