Refining Strokes by Learning Offset Attributes between Strokes for Flexible Sketch Edit at Stroke-Level
Not on the map. Why?
Abstract (arXiv)
Sketch edit at stroke-level aims to transplant source strokes onto a target sketch via stroke expansion or replacement, while preserving semantic consistency and visual fidelity with the target sketch. Recent studies addressed it by relocating source strokes at appropriate canvas positions. However, as source strokes could exhibit significant variations in both size and orientation, we may fail to produce plausible sketch editing results by merely repositioning them without further adjustments. For example, anchoring an oversized source stroke onto the target without proper scaling would fail to produce a semantically coherent outcome. In this paper, we propose SketchMod to refine the source stroke through transformation so as to align it with the target sketch's patterns, further realize flexible sketch edit at stroke-level. As the source stroke refinement is governed by the patterns of the target sketch, we learn three key offset attributes (scale, orientation and position) from the source stroke to another, and align it with the target by: 1) resizing to match spatial proportions by scale, 2) rotating to align with local geometry by orientation, and 3) displacing to meet with semantic layout by position. Besides, a stroke's profiles can be precisely controlled during sketch edit via the exposed captured stroke attributes. Experimental results indicate that SketchMod achieves precise and flexible performances on stroke-level sketch edit.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 19 references that are in the map. First posted on arXiv 31 Jan 2026.
Builds on
9 of 19 references.
References · 9
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
- 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
- 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
- 2017A Neural Representation of Sketch Drawingscited by 311
- 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
- 2023SketchXAI: A First Look at Explainability for Human Sketchescited by 10
- 2022Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representationcited by 4
- 2024Equipping Sketch Patches with Context-Aware Positional Encoding for Graphic Sketch Representationcited by 2
- 2025Generating Sketches in a Hierarchical Auto-Regressive Process for Flexible Sketch Drawing Manipulation at Stroke-Levelcited by 2
Built on by
Not cited yet.