Research map / Image generation / Editing and style transfer
Deep Image Harmonization
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 scene parsing semantics (ablation) | Deep Image Harmonization · MSCOCO | MSE: 80.5 -> 76.1 | Helped |
| add scene parsing semantics (ablation) | Deep Image Harmonization · MIT-Adobe | MSE: 168.8 -> 142.8 | Helped |
| add scene parsing semantics (ablation) | Deep Image Harmonization · Flickr | MSE: 491.7 -> 406.8 | Helped |
| add scene parsing semantics (ablation) | Deep Image Harmonization · MSCOCO | PSNR: 32.2 -> 32.9 | Helped |
| add scene parsing semantics (ablation) | Deep Image Harmonization · MIT-Adobe | PSNR: 27.5 -> 28.7 | Helped |
| add scene parsing semantics (ablation) | Deep Image Harmonization · Flickr | PSNR: 27.2 -> 27.4 | Helped |
| use the joint network for scene parsing | Scene parsing · ADE20K validation, top 25 labels | mean IoU: 36.0 -> 32.2 | Hurt |
| use Deep Image Harmonization instead of cut-and-paste | Real composite image harmonization · Real composite images from Xue et al. | B-T score: 1.130 -> 1.237 | Helped |
| use Deep Image Harmonization instead of cut-and-paste | Real composite image harmonization · Our real composite test set | B-T score: 1.168 -> 1.568 | Helped |
| use Deep Image Harmonization instead of cut-and-paste | Real composite image harmonization · Overall real composite images | B-T score: 1.139 -> 1.424 | Helped |
| use Deep Image Harmonization instead of Zhu | Image harmonization · MSCOCO | MSE: 322.2 -> 76.1 | Helped |
| use Deep Image Harmonization instead of Zhu | Image harmonization · MIT-Adobe | PSNR: 25.8 -> 28.7 | Helped |
Closest papers by meaning
- DoveNet: Deep Image Harmonization via Domain Verification (CVPR 2020 · similarity 0.90)
- Progressive Painterly Image Harmonization from Low-Level Styles to High-Level Styles (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)
- Painterly Image Harmonization by Learning from Painterly Objects (AAAI 2024 · similarity 0.85)
- FRIH: Fine-Grained Region-Aware Image Harmonization (AAAI 2024 · similarity 0.85)
- Relightful Harmonization: Lighting-aware Portrait Background Replacement (CVPR 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.