Research map / Image generation / Editing and style transfer
InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space
Jiarui Wu, Yujin Wang, Ruikang Li, Fan Zhang, Mingde Yao, Tianfan Xue
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 variational score distillation loss (ablation) | InstantRetouch with L_base · iRetouch | overall score O: 7.036 -> 8.087 | Improved |
| add prompt alignment loss (ablation) | InstantRetouch with L_base + L_VSD · iRetouch | overall score O: 8.087 -> 8.553 | Improved |
| add prompt alignment loss (ablation) | InstantRetouch with L_base + L_VSD · iRetouch | SC: 7.257 -> 8.140 | Improved |
| add VSD distillation to base loss (ablation) | InstantRetouch with L_base · iRetouch | SC: 5.978 -> 7.257 | Improved |
| add diffusion priors via one-step distillation to bilateral grid prediction (ablation) | Bilateral Grid Prediction · iRetouch | overall score O: 6.09 -> 8.54 | Improved |
| add bilateral branch to diffusion-only student (ablation) | Student (Diffusion-Only) · iRetouch | SSIM: 0.788 -> 0.989 | Improved |
| add bilateral branch to diffusion-only student (ablation) | Student (Diffusion-Only) · iRetouch | overall score O: 8.64 -> 8.54 | Hurt |
| add bilateral branch to diffusion-only student (ablation) | Student (Diffusion-Only) · iRetouch | runtime (s): 0.319 -> 0.065 | Improved |
| distill one-step student with bilateral branch instead of using teacher features in hybrid (ablation) | Hybrid (Teacher Features + Bilateral) · iRetouch | overall score O: 6.56 -> 8.54 | Improved |
| replace multi-step teacher with one-step bilateral student (ablation) | Teacher (Multi-step Diffusion) · iRetouch | runtime (s): 4.602 -> 0.065 | Improved |
| replace multi-step teacher with one-step bilateral student (ablation) | Teacher (Multi-step Diffusion) · iRetouch | SSIM: 0.833 -> 0.989 | Improved |
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.
- InstructPix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · better on 4 of 4 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
- DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts (AAAI 2025 · similarity 0.90)
- Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (NeurIPS 2025 · similarity 0.86)
- Inversion-Free Image Editing with Language-Guided Diffusion Models (CVPR 2024 · similarity 0.86)
- Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps (NeurIPS 2024 · similarity 0.86)
- RetouchGPT: LLM-based Interactive High-Fidelity Face Retouching via Imperfection Prompting (AAAI 2025 · similarity 0.86)
- PIXELS: Progressive Image Xemplar-based Editing with Latent Surgery (AAAI 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.
