Research map / Image generation / Text-to-image diffusion
Addressing Text Embedding Leakage in Diffusion-based Image Editing
Sunung Mun, Jinhwan Nam, Sunghyun Cho, Jungseul Ok
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 |
|---|---|---|---|
| use ALE (ORE + RGB-CAM + BB) instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (1 object) | TELS: 21.98 -> 16.41 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (2 objects) | TELS: 19.16 -> 16.00 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (3 objects) | TELS: 17.62 -> 15.89 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (2 objects) | TILS: 16.86 -> 15.42 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (3 objects) | TILS: 16.51 -> 15.36 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (1 object) | structure distance: 0.0504 -> 0.0088 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (1 object) | background PSNR: 15.34 -> 30.01 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (1 object) | editing performance (CLIP): 22.71 -> 22.62 | No clear effect |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (object change) | TELS: 18.67 -> 15.86 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (color change) | TELS: 19.68 -> 17.63 | Improved |
| use ALE instead of InfEdit | InfEdit (DDCM dual-branch editing) · ALE-Bench (material change) | TELS: 20.33 -> 17.15 | Improved |
| use ALE instead of InfEdit (runtime) | InfEdit (DDCM dual-branch editing) · ALE-Bench runtime | runtime per edit (sec): 5.41 -> 4.31 | Improved |
Closest papers by meaning
- DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing (CVPR 2024 · similarity 0.87)
- Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models (NeurIPS 2025 · similarity 0.85)
- A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization (NeurIPS 2024 · similarity 0.85)
- Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks (AAAI 2024 · similarity 0.85)
- Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models (ICLR 2024 · similarity 0.85)
- Textualize Visual Prompt for Image Editing via Diffusion Bridge (AAAI 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.
