Paper Detail

SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement

Yiqi Liang, Xiaodong Cun

huggingface Score 19.5

Published 2026-10-30 · First seen 2026-11-02

General AI

Abstract

Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simplified scenes, leaving text-guided complex scene sketching underexplored. We present SketchDirector, an agentic framework that mimics the human sketching workflow for automatic multi-concept scene sketching. Given a scene-level text prompt, SketchDirector first employs a large language model~(LLM) to decompose the scene into multiple draft assets, where each is represented by a set of Bézier curves. Then, an agentic reasoning loop iteratively plans and executes their spatial arrangement, guided by self-evolving memory. Finally, a detail refinement module leverages diffusion priors to enhance sketch quality while preserving geometric structure. To support future research and applications in multi-concept scene sketch generation, we further introduce the MCSketch8K dataset, comprising editable vector assets, compositional layouts, and object-level manipulation annotations. Extensive experiments show that SketchDirector outperforms state-of-the-art baselines in semantic and compositional quality while effectively preserving overall contour organization during refinement. The project page is: https://yiki77.github.io/SketchDirector/{https://yiki77.github.io/SketchDirector/}.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{liang2026sketchdirector,
  title = {SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement},
  author = {Yiqi Liang and Xiaodong Cun},
  year = {2026},
  abstract = {Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simplified scenes, leaving text-guided complex scene sketching underexplored. We present SketchDirector, an agentic framework that mimics the human sketching workflow for automatic multi-concept scene sketching. Given a scene-level text prompt, SketchDirector first employs a large language model\textasciitilde{}(LLM) to decompose the scene into multiple draft assets, where each is represented by a se},
  url = {https://huggingface.co/papers/2610.41260},
  keywords = {agentic framework, large language model, Bézier curves, self-evolving memory, diffusion priors, MCSketch8K, multi-concept scene sketch generation, code available, huggingface daily},
  eprint = {2610.41260},
  archiveprefix = {arXiv},
}

Metadata

{}