Research map / Image generation / Editing and style transfer
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
Yucheng Wang, Zedong Wang, Yuetong Wu, Yue Ma, Dan Xu
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 expert routing (ablation) | CARE-Edit · DreamBench++ multi-object | DINO-I: 0.485 -> 0.568 | Improved |
| add expert routing (ablation) | CARE-Edit · DreamBench++ multi-object | CLIP-I: 0.652 -> 0.720 | Improved |
| add expert routing (ablation) | CARE-Edit · DreamBench++ multi-object | CLIP-T: 0.296 -> 0.327 | Improved |
| add Latent Mixture (ablation) | CARE-Edit · DreamBench++ multi-object | DINO-I: 0.509 -> 0.568 | Improved |
| add Latent Mixture (ablation) | CARE-Edit · DreamBench++ multi-object | CLIP-T: 0.301 -> 0.327 | Improved |
| add Mask Repaint (ablation) | CARE-Edit · DreamBench++ multi-object | DINO-I: 0.523 -> 0.568 | Improved |
| add Mask Repaint (ablation) | CARE-Edit · DreamBench++ multi-object | CLIP-T: 0.304 -> 0.327 | Improved |
| increase activated experts K from 2 to 3 (ablation) | CARE-Edit · DreamBench++ multi-object | DINO-I: 0.541 -> 0.568 | Improved |
| increase activated experts K from 3 to 4 (ablation) | CARE-Edit · DreamBench++ multi-object | DINO-I: 0.568 -> 0.562 | Hurt |
| increase activated experts K from 3 to 4 (ablation) | CARE-Edit · DreamBench++ multi-object | CLIP-T: 0.327 -> 0.325 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- AnyEdit — AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025) · better on 3 of 3 shared results
- EMU-Edit — Emu Edit: Precise Image Editing via Recognition and Generation Tasks (CVPR 2024) · better on 3 of 3 shared results
- InstructPix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · better on 1 of 1 shared result
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
- Deconstructing Guidance: A Semantic Hierarchy for Precise Diffusion Model Editing (ICLR 2026 · similarity 0.88)
- Semantically Aligned Gradient-Driven Context-Preserving Image Editing (ECCV 2026 · similarity 0.87)
- Disentangling Local and Global Semantics in Diffusion Models for Image Editing (IJCV 2026 · similarity 0.87)
- Improving Editability in Image Generation with Layer-wise Memory (CVPR 2025 · similarity 0.87)
- Stable Flow: Vital Layers for Training-Free Image Editing (CVPR 2025 · similarity 0.86)
- Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization (NeurIPS 2025 · similarity 0.86)
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.
