JewelTry enables mask-free accurate scale jewelry virtual try-on
JewelTry: Mask-Free Scale Aware Jewelry Virtual Try-On
Computer Vision and Pattern Recognition
Summary
Seeing how jewelry looks on you before buying online is tricky because jewelry is small and detailed. The authors created JewelTry, a new way to digitally try on jewelry that understands the right size and position without needing extra image masks. They also made a dataset to teach and test this method, helping the system place jewelry accurately on a person's photo. This makes virtual try-on for rings, bracelets, earrings, and necklaces look more realistic.
What this means in practice
- •For online fashion retailers: Integrate JewelTry technology to show customers how jewelry fits accurately without extra image annotations.$Commercial implications: Jewelry virtual try-on feature can be sold to e-commerce platforms to improve customer experience and reduce returns.
- •For augmented reality developers: Use JewelTry's scale-aware model components to place small accessories realistically in AR applications without mask data.
Authors
Xinlei Niu, Peixia Li, Jun Wang, Chenchen Xu, Jiayu Yang, Jing Zhang, Pulak Purkait, Hongdong Li
Abstract
Virtual try-on (VTON) enables customers to visualize how fashion products appear when worn and has become an important technology for online shopping. While recent advances have substantially improved garment VTON, jewelry remains a challenging and underexplored category due to its small size, rigid structure, and sensitivity to fine-grained visual details. Realistic jewelry VTON requires not only faithful appearance transfer but also accurate scale and placement relative to the wearer. Existing jewelry VTON methods typically rely on mask guidance, whereas mask-free approaches lack explicit guidance for modeling the product scale. To bridge this gap, we introduce JVTO-Bench, a benchmark dataset for scale-faithful jewelry VTON, providing reference source target triplets with real-world product-scale annotations across four major jewelry categories. Building upon this benchmark, we propose JewelTry, a mask-free diffusion framework for scale-aware jewelry VTON. JewelTry incorporates a scale adapter that encodes product dimensions into a scale token, enabling the model to learn scale relationships between jewelry items and surrounding human anatomy in-context. To further improve jewelry consistency, we introduce a single-directional condition attention mechanism and an attention refinement loss that preserve both coarse geometry and fine-grained structural details of the reference jewelry. Extensive experiments show that JewelTry achieves a balance among visual fidelity, background preservation, object consistency and scale accuracy, establishing a strong baseline for mask-free, scale-aware jewelry virtual try-on.