Research map / Label-efficient and robust learning / Recognition and long-tail
CAP-VSTNet: Content Affinity Preserved Versatile 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 |
|---|---|---|---|
| Add the reversible residual block design rather than inverted residuals (ablation) | CAP-VSTNet · Ablation study | SSIM: 0.643 -> 0.650 | Helped |
| Add injective padding (ablation) | CAP-VSTNet · Ablation study | Gram loss: 0.874 -> 0.750 | Helped |
| Add channel refinement CR-RRB (ablation) | CAP-VSTNet · Ablation study | SSIM: 0.630 -> 0.650 | Helped |
| Use CR-RRB rather than CR-MLP for channel refinement (ablation) | CAP-VSTNet · Ablation study | SSIM: 0.640 -> 0.650 | Helped |
| Add Matting Laplacian and cycle consistency losses (ablation) | CAP-VSTNet · Ablation study | SSIM: 0.421 -> 0.650 | Helped |
| Add cycle consistency loss (ablation) | CAP-VSTNet · Ablation study | SSIM: 0.638 -> 0.650 | Helped |
| Use CAP-VSTNet instead of WCT² | Photorealistic video style transfer · Photorealistic video style transfer | Temporal loss (i=1): 0.040 -> 0.039 | Helped |
| Use CAP-VSTNet instead of CCPL | Artistic video style transfer · Artistic video style transfer | Gram loss: 0.371 -> 0.436 | Hurt |
Closest papers by meaning
- Rethinking and Improving the Robustness of Image Style Transfer (CVPR 2021 · similarity 0.89)
- Learning Linear Transformations for Fast Image and Video Style Transfer (CVPR 2019 · similarity 0.88)
- A Content Transformation Block for Image Style Transfer (CVPR 2019 · similarity 0.87)
- Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer (CVPR 2021 · similarity 0.86)
- Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network (CVPR 2024 · similarity 0.86)
- CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style Transfer (NeurIPS 2026 · similarity 0.85)
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.