Research map / Image generation / Editing and style transfer
Precise Object and Effect Removal with Adaptive Target-Aware Attention
Jixin Zhao, Zhouxia Wang, Peiqing Yang, Shangchen Zhou
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 |
|---|---|---|---|
| add Adaptive Target-Aware Attention (ablation) | ObjectClear (camera-captured data) · OBER-Test | PSNR: 27.29 -> 27.56 | Improved |
| add simulated training data (ablation) | ObjectClear with ATA · OBER-Test | PSNR: 27.56 -> 28.04 | Improved |
| add Attention-Guided Fusion (ablation) | ObjectClear · OBER-Test | PSNR: 28.04 -> 32.77 | Improved |
| add Attention-Guided Fusion (ablation) | ObjectClear · OBER-Test | PSNR-BG: 28.80 -> 35.50 | Improved |
| use spatially-varying denoising strength instead of uniform 0.99 (ablation) | ObjectClear · OBER-Test | PSNR: 32.77 -> 33.04 | Improved |
| use spatially-varying denoising strength instead of uniform 1.0 (ablation) | ObjectClear · OBER-Test | PSNR: 31.49 -> 33.04 | Improved |
| use ObjectClear with only object mask vs baselines given object-effect masks | ObjectClear · OBER-Test | PSNR: 33.04 vs 27.42 (Attentive Eraser, object-effect mask) | Improved |
| ObjectClear vs OmniPaint on in-the-wild images | ObjectClear · OBER-Wild | ReMOVE†: 0.8656 (OmniPaint) vs 0.8470 | Hurt |
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.
- OmniPaint — OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting (ICCV 2025) · better on 5 of 6 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
- SmartEraser: Remove Anything from Images using Masked-Region Guidance (CVPR 2025 · similarity 0.87)
- Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance (AAAI 2025 · similarity 0.87)
- ROSE: Remove Objects with Side Effects in Videos (NeurIPS 2025 · similarity 0.86)
- GeoRemover: Removing Objects and Their Causal Visual Artifacts (NeurIPS 2025 · similarity 0.85)
- Detail-Preserving Latent Diffusion for Stable Shadow Removal (CVPR 2025 · similarity 0.85)
- RORem: Training a Robust Object Remover with Human-in-the-Loop (CVPR 2025 · 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.
