Research map / Image generation / Editing and style transfer
Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer
Xide Xia, Meng Zhang, Tianfan Xue, Zheng Sun, Hui Fang, Brian Kulis, Jiawen Chen
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 style-based splatting blocks instead of AdaIN or WCT feature matching (ablation) | Ours (bilateral grid style transfer) · Photo test set (400 images), qualitative | visual quality | Improved |
| add bilateral-space Laplacian regularization (ablation) | Ours (bilateral grid style transfer) · Photo test set, qualitative | visual artifacts | Improved |
| add global scene summary (ablation) | Ours (bilateral grid style transfer) · Photo test set, qualitative | spatial color consistency | Improved |
| add top-path pretrained-normalized features (ablation) | Ours (bilateral grid style transfer) · Photo test set, qualitative | color correctness | Improved |
| learn affine grid end to end instead of fitting BGU to low-resolution AdaIN output (ablation) | Ours (bilateral grid style transfer) · Photo test set, qualitative | visual quality | Improved |
| increase grid spatial resolution from 1x1 or 2x2 to 8x8 (ablation) | Ours (bilateral grid style transfer) · Photo test set, qualitative | stylization quality | Improved |
| increase luma bins from 1 or 2 to 8 (ablation) | Ours (bilateral grid style transfer) · Photo test set, qualitative | stylization quality | Improved |
| use our method instead of PhotoWCT, LST, WCT2 | Ours (bilateral grid style transfer) · User study (1200 responses) | stylization and overall quality score (1-5) | Improved |
| use our method instead of WCT2 | Ours (bilateral grid style transfer) · User study (1200 responses) | photorealism score (1-5) | No clear effect |
Closest papers by meaning
- Deep Photo Style Transfer (CVPR 2017 · similarity 0.92)
- Deep Translation Prior: Test-Time Training for Photorealistic Style Transfer (AAAI 2022 · similarity 0.92)
- Ultrafast Photorealistic Style Transfer via Neural Architecture Search (AAAI 2020 · similarity 0.91)
- Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer (CVPR 2017 · similarity 0.91)
- Photorealistic Style Transfer via Wavelet Transforms (ICCV 2019 · similarity 0.90)
- FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields (AAAI 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.
