Research map / Image generation / Editing and style transfer
FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing
Kaixiang Yang, Boyang Shen, Xin Li, Yuchen Dai, Yuxuan Luo, Yueran Ma, Wei Fang, Qiang Li, Zhiwei Wang
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 Feature Injection (FIJ) to FlowEdit backbone (ablation) | FlowEdit (SD3.5) · PIE-Bench | Structure Distance x10^3: 23.62 -> 14.89 | Improved |
| add Feature Injection (FIJ) to FlowEdit backbone (ablation) | FlowEdit (SD3.5) · PIE-Bench | CLIP similarity (edited): 23.73 -> 23.12 | Hurt |
| add frequency-domain FRI on top of FIJ (ablation) | FIA-Edit · PIE-Bench | PSNR: 25.59 -> 27.32 | Improved |
| add frequency-domain FRI on top of FIJ (ablation) | FIA-Edit · PIE-Bench | Structure Distance x10^3: 14.89 -> 10.34 | Improved |
| use frequency fusion instead of simple feature addition in FRI (ablation) | FIA-Edit · PIE-Bench | Structure Distance x10^3: 16.50 -> 10.34 | Improved |
| use frequency fusion instead of simple feature addition in FRI (ablation) | FIA-Edit · PIE-Bench | CLIP similarity (edited): 22.68 -> 22.82 | Improved |
| add FIA constraint (FRI + FIJ) to FlowEdit | FlowEdit (SD3.5) · PIE-Bench | PSNR: 23.21 -> 27.32 | Improved |
| add FIA constraint (FRI + FIJ) to FlowEdit | FlowEdit (SD3.5) · PIE-Bench | CLIP similarity (whole): 26.78 -> 25.89 | Hurt |
| add FIA constraint to FlowEdit | FlowEdit (SD3.5) · PIE-Bench runtime | Time (s): 3.49 -> 6.30 | Hurt |
| augment training with FIA-Edit edited bleeding images | ConvNeXt-T bleeding classifier · Surgical bleeding classification | Recall (%): 29.49 -> 32.90 | Improved |
| augment training with FlowEdit edited bleeding images instead of FIA-Edit | ConvNeXt-T bleeding classifier · Surgical bleeding classification | F1-score (%): 40.89 -> 38.86 | Hurt |
| augment with inversion-based SD1.5 editing methods | ConvNeXt-T bleeding classifier · Surgical bleeding classification | Recall (%): 29.49 -> 26.57 (PnP) | Hurt |
Later papers that compared with this method
1 later accepted paper reports FIA-Edit as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Wavelet-Guided Semantic Signal Compensation for Inversion-Free Image Editing (ECCV 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FlowEdit — FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models (ICCV 2025) · better on 3 of 5 shared results
- DNAEdit — DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing (NeurIPS 2025) · better on 3 of 3 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
- Inversion-Free Image Editing with Language-Guided Diffusion Models (CVPR 2024 · similarity 0.87)
- FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing (CVPR 2025 · similarity 0.87)
- Object-Aware Inversion and Reassembly for Image Editing (ICLR 2024 · similarity 0.86)
- BARET: Balanced Attention Based Real Image Editing Driven by Target-Text Inversion (AAAI 2024 · similarity 0.86)
- Tuning-Free Inversion-Enhanced Control for Consistent Image Editing (AAAI 2024 · similarity 0.86)
- Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space (NeurIPS 2026 · 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.
