Research map / Image generation / Editing and style transfer
SketchEdit: Mask-Free Local Image Manipulation With Partial Sketches
Yu Zeng, Zhe Lin, Vishal M. Patel
Check 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 mask-free local editing with the full image and predicted modification mask instead of conditional inpainting with masked input | SketchEdit · CelebAHQ validation | L1 error: 0.0115 -> 0.0071 | Improved |
| Use mask-free local editing with the full image and predicted modification mask instead of conditional inpainting with masked input | SketchEdit · Places validation | PSNR: 24.06 -> 26.35 | Improved |
| Use mask-free local editing with the full image and predicted modification mask instead of conditional inpainting with masked input | SketchEdit · SketchFace | SL_1: 2859 -> 2211 | Improved |
| Use mask-free local editing with the full image and predicted modification mask instead of conditional inpainting with masked input | SketchEdit · SketchImg | FID: 27.11 -> 24.27 | Improved |
| Add a learned mask estimator (ablation) | SketchEdit · CelebAHQ validation | L1 error: 0.0127 -> 0.0071 | Improved |
| Add a learned mask estimator rather than using minimum bounding boxes around sketches (ablation) | SketchEdit · CelebAHQ validation | PSNR: 31.87 -> 34.21 | Improved |
| Add the style encoder to preserve appearance information from the modification region (ablation) | SketchEdit · CelebAHQ validation | L1 error: 0.0074 -> 0.0071 | Improved |
| Add the style encoder to preserve appearance information from the modification region (ablation) | SketchEdit · CelebAHQ validation | PSNR: 33.98 -> 34.21 | 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.
- SC-FEGAN — SC-FEGAN: Face Editing Generative Adversarial Network With User's Sketch and Color (ICCV 2019) · 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
- Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches (ECCV 2020 · similarity 0.89)
- SketchAssist: A Practical Assistant for Semantic Edits and Precise Local Redrawing (CVPR 2026 · similarity 0.88)
- Learning to Manipulate Artistic Images (AAAI 2024 · similarity 0.87)
- Paint by Inpaint: Learning to Add Image Objects by Removing Them First (CVPR 2025 · similarity 0.86)
- SketchVideo: Sketch-based Video Generation and Editing (CVPR 2025 · similarity 0.86)
- Zero-shot Image Editing with Reference Imitation (NeurIPS 2024 · similarity 0.85)
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.
