Research map / Label-efficient and robust learning / Recognition and long-tail
SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization
Yucheng Hang, Bin Xia, Wenming Yang, Qingmin Liao
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 |
|---|---|---|---|
| Add BAIN (ablation) | Image harmonization baseline · iHarmony4 Average | PSNR: 37.55 -> 37.84 | Improved |
| Add SCS-Co (ablation) | Image harmonization baseline · iHarmony4 Average | PSNR: 37.55 -> 38.42 | Improved |
| Add both BAIN and SCS-Co (ablation) | Image harmonization baseline · iHarmony4 Average | PSNR: 37.55 -> 38.75 | Improved |
| Add SS-CR (ablation) | Image harmonization baseline · iHarmony4 Average | PSNR: 37.55 -> 38.03 | Improved |
| Add CS-CR (ablation) | Image harmonization baseline · iHarmony4 Average | PSNR: 37.55 -> 37.88 | Improved |
| Add both SS-CR and CS-CR (ablation) | Image harmonization baseline · iHarmony4 Average | PSNR: 37.55 -> 38.42 | Improved |
| Use SCS-Co rather than triplet loss (ablation) | Image harmonization baseline · iHarmony4 Average | PSNR: 37.94 -> 38.42 | Improved |
| Use SCS-Co with K=1 negative sample rather than triplet loss (ablation) | Image harmonization baseline · iHarmony4 Average | PSNR: 37.94 -> 38.13 | Improved |
| Increase the number of negative samples (ablation) | SCS-Co · iHarmony4 | PSNR | Improved |
| Increase the number of negative samples (ablation) | SCS-Co · iHarmony4 | training time | Hurt |
| Integrate SCS-Co (ablation) | RainNet · iHarmony4 | PSNR: +0.95 | Improved |
| Integrate SCS-Co (ablation) | DIH · iHarmony4 | PSNR: +0.68 | Improved |
Closest papers by meaning
- FRIH: Fine-Grained Region-Aware Image Harmonization (AAAI 2024 · similarity 0.88)
- Training-and-Prompt-Free General Painterly Harmonization via Zero-Shot Disentenglement on Style and Content References (AAAI 2025 · similarity 0.86)
- Progressive Painterly Image Harmonization from Low-Level Styles to High-Level Styles (AAAI 2024 · similarity 0.85)
- Relightful Harmonization: Lighting-aware Portrait Background Replacement (CVPR 2024 · similarity 0.84)
- OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data (NeurIPS 2025 · similarity 0.84)
- Painterly Image Harmonization by Learning from Painterly Objects (AAAI 2024 · similarity 0.83)
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.
