Research map / Image generation / Editing and style transfer
Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation
Check 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 multi-hop rather than single-hop style injection (ablation) | GDWCT · Ukiyoe | qualitative style detail transfer | Helped |
| Increase whitening regularization strength (ablation) | GDWCT · BAM Watercolor → Pen Ink | texture retention | Hurt |
| Increase coloring regularization strength (ablation) | GDWCT · BAM Watercolor → Pen Ink | style intensity | Helped |
| Increase group count (ablation) | GDWCT · Image translation | style representation | Mixed |
| Use GDWCT instead of DRIT | Unsupervised exemplar-based CelebA translation · CelebA Gender classification | classification accuracy (%): 95.55 -> 92.65 | Hurt |
| Use GDWCT instead of DRIT | Unsupervised exemplar-based CelebA translation · CelebA Bangs classification | classification accuracy (%): 66.88 -> 76.05 | Helped |
| Use GDWCT instead of DRIT | Unsupervised exemplar-based CelebA translation · CelebA Smile classification | classification accuracy (%): 78.15 -> 92.85 | Helped |
| Use GDWCT instead of DRIT | Unsupervised exemplar-based CelebA translation · CelebA average classification | classification accuracy (%): 80.19 -> 87.18 | Helped |
| Use GDWCT instead of DRIT | Unsupervised exemplar-based CelebA translation · CelebA Female → Male | user preference (%): 48.89 -> 38.89 | Hurt |
| Use GDWCT instead of DRIT | Unsupervised exemplar-based CelebA translation · CelebA Male → Female | user preference (%): 42.25 -> 44.52 | Helped |
Closest papers by meaning
- Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency (ICLR 2019 · similarity 0.90)
- Universal Style Transfer via Feature Transforms (NeurIPS 2017 · similarity 0.89)
- A Content Transformation Block for Image Style Transfer (CVPR 2019 · similarity 0.88)
- Encoding in Style: A StyleGAN Encoder for Image-to-Image Translation (CVPR 2021 · similarity 0.88)
- Free-Lunch Color-Texture Disentanglement for Stylized Image Generation (NeurIPS 2025 · similarity 0.87)
- Learning to Manipulate Artistic Images (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.