PulseAugur
EN
LIVE 13:14:10

New fashion datasets boost AI sketch-to-image and retrieval capabilities

By PulseAugur Editorial · [4 sources] ·

Two new large-scale datasets, GarmentSketch and VietFashion, have been released to advance sketch-to-image generation and retrieval in the fashion industry. GarmentSketch offers 26,249 fashion sketches paired with detailed textual descriptions, aiming to improve human-AI collaboration in design. VietFashion focuses on cultural outfits, specifically the Vietnamese áo dài, providing a benchmark for sketch-text composed image retrieval with over 21,000 images and aligned captions. AI

IMPACT These datasets will enable advancements in AI-driven fashion design tools, improving sketch understanding and retrieval of culturally specific garments.

RANK_REASON Two new academic papers introducing large-scale datasets for fashion-related AI tasks.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

New fashion datasets boost AI sketch-to-image and retrieval capabilities

COVERAGE [4]

  1. arXiv cs.CV TIER_1 English(EN) · Duong-Duy-Khang Bui, Minh-Tan Pham, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le ·

    GarmentSketch: Large-scale Sketch-to-Fashion Benchmark

    arXiv: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…

  2. arXiv cs.CV TIER_1 English(EN) · Hoang-Nguyen Cao, Le-Hoang Bui, Dinh-Khoi Vo, Minh-Triet Tran, Trung-Nghia Le ·

    VietFashion: Benchmarking Sketch-Text Composed Image Retrieval for Cultural Outfits

    arXiv:2606.13427v1 Announce Type: new Abstract: Cultural garments pose a unique challenge for visual retrieval systems, as their identity often depends on subtle structural and symbolic details that are poorly captured by standard AI models. We introduce VietFashion, a new benchm…

  3. arXiv cs.CV TIER_1 English(EN) · Trung-Nghia Le ·

    GarmentSketch: Large-scale Sketch-to-Fashion Benchmark

    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…

  4. arXiv cs.CV TIER_1 English(EN) · Trung-Nghia Le ·

    VietFashion: Benchmarking Sketch-Text Composed Image Retrieval for Cultural Outfits

    Cultural garments pose a unique challenge for visual retrieval systems, as their identity often depends on subtle structural and symbolic details that are poorly captured by standard AI models. We introduce VietFashion, a new benchmark for sketch-text composed image retrieval cen…

RELATED ENTITIES

RELATED TOPICS