Research map / Image generation / Editing and style transfer
Cross-Domain Correspondence Learning for Exemplar-Based Image Translation
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 |
|---|---|---|---|
| add L_feat (ablation) | CoCosNet · DeepFashion | FID: 14.4 -> 14.3 | Helped |
| add L_domain (ablation) | CoCosNet · DeepFashion | FID: 21.1 -> 14.3 | Helped |
| add L_perc (ablation) | CoCosNet · DeepFashion | FID: 59.3 -> 14.3 | Helped |
| add L_context (ablation) | CoCosNet · DeepFashion | FID: 28.4 -> 14.3 | Helped |
| add L_reg (ablation) | CoCosNet · DeepFashion | FID: 19.3 -> 14.3 | Helped |
| use positional normalization instead of batch normalization (ablation) | CoCosNet translation network · ADE20k | image quality lower bound | Helped |
Closest papers by meaning
- Marginal Contrastive Correspondence for Guided Image Generation (CVPR 2022 · similarity 0.93)
- Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency (ICLR 2019 · similarity 0.92)
- Masked and Adaptive Transformer for Exemplar Based Image Translation (CVPR 2023 · similarity 0.92)
- CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation (CVPR 2021 · similarity 0.90)
- Unbalanced Feature Transport for Exemplar-Based Image Translation (CVPR 2021 · similarity 0.89)
- Learning to Manipulate Artistic Images (AAAI 2024 · similarity 0.87)
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.