Research map / Image generation / Editing and style transfer
AIR-DR: Adaptive Image Retargeting with Instance Relocation and Dual-guidance Repainting
Zhitong Dong, Chao Li, Yongjian Deng, Hao Chen
Read the paperCheck 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 |
|---|---|---|---|
| replace pixel deletion with instance relocation (IR) (ablation) | AIR-DR · RetarSet 16:9 | SDR: 0.354 -> 0.198 | Improved |
| replace pixel deletion with IR (ablation) | AIR-DR · RetargetMe 16:9 | SDR: 0.448 -> 0.244 | Improved |
| replace pixel deletion with IR (ablation) | AIR-DR · RetarSet 3:4 | SDR: 0.040 -> 0.038 | No clear effect |
| add adaptive retargeting decision (ARD) to IR (ablation) | AIR-DR · RetarSet 16:9 | SDR: 0.198 -> 0.131 | Improved |
| add ARD to IR (ablation) | AIR-DR · RetarSet 9:16 | SDR: 0.099 -> 0.032 | Improved |
| add ARD to IR (ablation) | AIR-DR · RetargetMe 16:9 | SDR: 0.244 -> 0.143 | Improved |
| add ARD to IR (ablation) | AIR-DR · RetarSet 1:1 | SDR: 0.116 -> 0.092 | Mixed |
| add dual-guidance background repainting (DBR) (ablation) | AIR-DR · RetarSet 16:9 | SDR: 0.131 -> 0.113 | Improved |
| add DBR (ablation) | AIR-DR · RetargetMe 16:9 | SDR: 0.143 -> 0.114 | Improved |
| add DBR (ablation) | AIR-DR · RetarSet 9:16 | SDR: 0.032 -> 0.031 | No clear effect |
| add DBR (ablation) | AIR-DR · RetarSet 3:4 | SDR: 0.013 -> 0.013 | No clear effect |
| replace PRP's generation model with FLUX | PRP · RetarSet 16:9 | SDR: 0.354 -> 0.346 | No clear effect |
Closest papers by meaning
- Prune and Repaint: Content-Aware Image Retargeting for any Ratio (NeurIPS 2024 · similarity 0.91)
- InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model (NeurIPS 2025 · similarity 0.83)
- SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues (NeurIPS 2026 · similarity 0.83)
- Keyframe-Guided Creative Video Inpainting (CVPR 2025 · similarity 0.82)
- AnyScene: Customized Image Synthesis with Composited Foreground (CVPR 2024 · similarity 0.82)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.82)
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.
