Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zou, Han, Zhang, Yan, Yu, Ruiqi, Xie, Cong, Huang, Jie, Zhan, Zhenpeng
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