GarmentSketch: Large-scale Sketch-to-Fashion Benchmark
Quick Answer
GarmentSketch introduces a dataset of 26,249 fashion sketches across 21 categories, paired with detailed textual descriptions, enhancing sketch-based fashion image synthesis.
Quick Take
GarmentSketch introduces a dataset of 26,249 fashion sketches across 21 categories, paired with detailed textual descriptions, enhancing sketch-based fashion image synthesis. It benchmarks state-of-the-art generative models, revealing both potential and limitations in current methods, and aims to foster advancements in sketch understanding and AI collaboration in design.
Key Points
- Dataset includes 26,249 fashion sketches across 21 garment categories.
- Captions generated using multimodal large language models with human refinement.
- Benchmarks reveal both promise and limitations of existing generative methods.
- Aims to advance sketch understanding and creative AI collaboration in fashion design.
- Dataset available at: https://khangbdd.github.io/garmentsketch.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 14025v1 Announce Type: new Abstract: Fashion sketching is a cornerstone of design workflows, allowing rapid visualization of creative concepts prior to physical prototyping. Yet, progress in sketch-based fashion image synthesis has been hindered by the absence of large-scale, high-quality paired resources. To bridge this gap, we present GarmentSketch, a novel dataset comprising 26,249 fashion sketches across 21 garment categories, each paired with detailed textual descriptions.
Captions were produced through a multi-stage pipeline that integrates multiple multimodal large language models (MLLMs) with human-in-the-loop refinement, ensuring both semantic accuracy and descriptive richness. We benchmark GarmentSketch on state-of-the-art generative models, providing baseline performance for sketch-guided text-to-image generation. Our experiments reveal both the promise and the current limitations of existing methods.
By offering a comprehensive and richly annotated resource, GarmentSketch establishes a foundation for advancing sketch understanding, fine-grained fashion image generation, and creative human-AI collaboration in design. The dataset will be available at: https://khangbdd. github. io/garmentsketch.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.