Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2512.14140 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911717363023872 |
|---|---|
| author | Zou, Han Zhang, Yan Yu, Ruiqi Xie, Cong Huang, Jie Zhan, Zhenpeng |
| author_facet | Zou, Han Zhang, Yan Yu, Ruiqi Xie, Cong Huang, Jie Zhan, Zhenpeng |
| contents | Sketch editing requires jointly handling high-level semantic changes and precise local redrawing, a combination that is particularly challenging for sparse, style-sensitive line art. Unlike natural images, sketches rely on minimal visual cues, making it difficult for existing methods to reconcile global semantic modifications with fine-grained structural control while preserving overall coherence. We present SketchAssist, an interactive sketch assistant that unifies instruction-guided editing with line-guided region redrawing, enabling efficient and controllable sketch manipulation while preserving overall composition. To support this task, we introduce a controllable data generation pipeline that constructs structured edit sequences with precise attribute variations and maintains structural alignment across multi-step modifications, while expanding stylistic diversity via style-preserving transformations. Building on this data, SketchAssist adopts a unified framework based on DiT, using a multi-channel input representation to encode sketches, masks, and guidance signals within a single interface. To further handle different editing modes, we integrate a Task-guided Mixture-of-Experts (T-MoE) into LoRA layers, enabling adaptive control over semantic and structural guidance. Extensive experiments demonstrate state-of-the-art performance on both tasks, achieving strong instruction adherence and improved structural and style consistency compared to recent methods. Together, our method provide a practical and controllable solution for sketch editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14140 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SketchAssist: A Practical Assistant for Semantic Edits and Precise Local Redrawing Zou, Han Zhang, Yan Yu, Ruiqi Xie, Cong Huang, Jie Zhan, Zhenpeng Computer Vision and Pattern Recognition Sketch editing requires jointly handling high-level semantic changes and precise local redrawing, a combination that is particularly challenging for sparse, style-sensitive line art. Unlike natural images, sketches rely on minimal visual cues, making it difficult for existing methods to reconcile global semantic modifications with fine-grained structural control while preserving overall coherence. We present SketchAssist, an interactive sketch assistant that unifies instruction-guided editing with line-guided region redrawing, enabling efficient and controllable sketch manipulation while preserving overall composition. To support this task, we introduce a controllable data generation pipeline that constructs structured edit sequences with precise attribute variations and maintains structural alignment across multi-step modifications, while expanding stylistic diversity via style-preserving transformations. Building on this data, SketchAssist adopts a unified framework based on DiT, using a multi-channel input representation to encode sketches, masks, and guidance signals within a single interface. To further handle different editing modes, we integrate a Task-guided Mixture-of-Experts (T-MoE) into LoRA layers, enabling adaptive control over semantic and structural guidance. Extensive experiments demonstrate state-of-the-art performance on both tasks, achieving strong instruction adherence and improved structural and style consistency compared to recent methods. Together, our method provide a practical and controllable solution for sketch editing. |
| title | SketchAssist: A Practical Assistant for Semantic Edits and Precise Local Redrawing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.14140 |