Research map / Image generation / Editing and style transfer
Industrial Style Transfer With Large-Scale Geometric Warping and Content Preservation
Jinchao Yang, Fei Guo, Shuo Chen, Jun Li, Jian Yang
Check 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 LGW instead of GTST for large-scale geometric warping | Geometric warping · Geometric warping | mIoU: 0.7285 -> 0.9284 | Improved |
| Use LGW instead of DST for large-scale geometric warping | Geometric warping · Geometric warping | mIoU: 0.6000 -> 0.9284 | Improved |
| Add interest regularization (IR) to AdaIN (ablation) | AdaIN · Stylization content preservation | SSIM: 0.3424 -> 0.3886 | Improved |
| Add interest regularization (IR) to LinearWCT (ablation) | LinearWCT · Stylization content preservation | SSIM: 0.4612 -> 0.4932 | Improved |
| Add interest regularization (IR) to ArtFlow (ablation) | ArtFlow · Stylization content preservation | SSIM: 0.5042 -> 0.5643 | Improved |
| Add interest regularization (IR) to AdaIN (ablation) | AdaIN · Stylization content preservation | Time(s): 0.054 -> 0.054 | No clear effect |
| Add interest regularization (IR) to LinearWCT (ablation) | LinearWCT · Stylization content preservation | Time(s): 0.419 -> 0.416 | Improved |
| Add interest regularization (IR) to ArtFlow (ablation) | ArtFlow · Stylization content preservation | Time(s): 0.138 -> 0.140 | Hurt |
| Add position embedding to mask RAFT features (ablation) | LGW · Geometric warping | Warping quality | Improved |
| Use mask inputs instead of RGB inputs for RAFT warping | LGW · Geometric warping | Warping loss and convergence | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ArtFlow — ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows (CVPR 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning To Warp for Style Transfer (CVPR 2021 · similarity 0.90)
- Multimodal Style Transfer via Graph Cuts (ICCV 2019 · similarity 0.86)
- 3DStyleNet: Creating 3D Shapes With Geometric and Texture Style Variations (ICCV 2021 · similarity 0.86)
- LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model (CVPR 2025 · similarity 0.86)
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 2024 · similarity 0.85)
- AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer (AAAI 2024 · similarity 0.84)
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.
