Research map / Image generation / Editing and style transfer
Region-Aware Adaptive Instance Normalization for Image Harmonization
Jun Ling, Han Xue, Li Song, Rong Xie, Xiao Gu
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 background-to-foreground RAIN style transfer | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 36.12 | Improved |
| Add background-to-foreground RAIN style transfer | Baseline image harmonization network · iHarmony4 average | fMSE: 808.68 -> 469.60 | Improved |
| Add RAIN style transfer | DIH · iHarmony4 | PSNR: 33.36dB -> 33.84dB (+0.48dB) | Improved |
| Add instance normalization (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 35.32 | Improved |
| Add batch normalization (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 35.34 | Improved |
| Add region normalization (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 34.57 | Improved |
| Use RAIN-1 placement instead of the baseline configuration (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 36.06 | Improved |
| Use RAIN-2 placement instead of the baseline configuration (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 36.01 | Improved |
| Use RAIN-3 placement instead of the baseline configuration (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 35.95 | Improved |
| Use RAIN-4 placement instead of the baseline configuration (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 35.96 | Improved |
| Use RAIN only in the encoder and IN in the decoder (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 35.31 | Improved |
| Use RAIN only in the decoder and IN in the encoder (ablation) | Baseline image harmonization network · iHarmony4 average | PSNR: 33.92 -> 36.12 | 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.
- DoveNet — DoveNet: Deep Image Harmonization via Domain Verification (CVPR 2020) · better on 6 of 7 shared results
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
- SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization (CVPR 2022 · similarity 0.89)
- FRIH: Fine-Grained Region-Aware Image Harmonization (AAAI 2024 · similarity 0.89)
- Progressive Painterly Image Harmonization from Low-Level Styles to High-Level Styles (AAAI 2024 · similarity 0.88)
- Relightful Harmonization: Lighting-aware Portrait Background Replacement (CVPR 2024 · similarity 0.87)
- Training-and-Prompt-Free General Painterly Harmonization via Zero-Shot Disentenglement on Style and Content References (AAAI 2025 · similarity 0.87)
- Painterly Image Harmonization by Learning from Painterly Objects (AAAI 2024 · similarity 0.85)
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.
