Research map / Image generation / Editing and style transfer
SketchAssist: A Practical Assistant for Semantic Edits and Precise Local Redrawing
Han Zou, Yan Zhang, Ruiqi Yu, Cong Xie, Jie Huang, Zhenpeng Zhan
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 atomic addition sequence data (ablation) | FLUX.1 Kontext baseline · Instruction-guided sketch editing | Q_O: 6.42 -> 7.20 | Improved |
| add atomic addition sequence data (line-guided DINO) (ablation) | FLUX.1 Kontext baseline · Line-guided region redrawing | DINO: 0.890 -> 0.937 | Improved |
| add atomic addition sequence data (CLIP-T) (ablation) | FLUX.1 Kontext baseline · Instruction-guided sketch editing | CLIP-T: 0.296 -> 0.288 | Hurt |
| add cross-sequence sampling (ablation) | atomic addition model · Instruction-guided sketch editing | Q_O: 7.20 -> 7.55 | Improved |
| add cross-sequence sampling (DINO) (ablation) | atomic addition model · Instruction-guided sketch editing | DINO: +0.016 | Improved |
| add style diversity data (ablation) | cross-sequence model · Instruction-guided sketch editing | Q_O: 7.55 -> 7.86 | Improved |
| add style diversity data (Q_PQ) (ablation) | cross-sequence model · Instruction-guided sketch editing | Q_PQ: 7.67 -> 7.44 | Hurt |
| add style diversity data (LPIPS) (ablation) | cross-sequence model · Line-guided region redrawing | LPIPS: 0.112 -> 0.0915 | Improved |
| add task-guided MoE (T-MoE) to LoRA (ablation) | style-diversity model · Instruction-guided sketch editing | Q_O: 7.86 -> 8.04 | Improved |
| add T-MoE (LPIPS) (ablation) | style-diversity model · Line-guided region redrawing | LPIPS: 0.0915 -> 0.0904 | Improved |
| SketchAssist vs Prompt-to-Prompt for multi-step edits | SketchAssist · user study | success rate (%): 46.89 -> 87.88 | Improved |
| SketchAssist vs FLUX.1-fill for object removal | SketchAssist · user study | success rate (%): 35.31 -> 91.50 | 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.
- BrushNet — BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion (ECCV 2024) · better on 2 of 2 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
- Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches (ECCV 2020 · similarity 0.88)
- SketchEdit: Mask-Free Local Image Manipulation With Partial Sketches (CVPR 2022 · similarity 0.88)
- One-Shot Reference-based Structure-Aware Image to Sketch Synthesis (AAAI 2025 · similarity 0.87)
- Text to Sketch Generation with Multi-Styles (NeurIPS 2025 · similarity 0.87)
- SketchAgent: Language-Driven Sequential Sketch Generation (CVPR 2025 · similarity 0.87)
- SketchVideo: Sketch-based Video Generation and Editing (CVPR 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.
