让奢侈品配饰也能虚拟试戴，提升位置预测精度。
GlamTry: Advancing Virtual Try-On for High-End Accessories
- 用服装虚拟试穿技术+手部关键点模型，适配配饰场景。
- 小数据下位置预测优于原有服装模型。
- 适合电商配饰试穿、数字零售等应用研究者。
本文针对珠宝、手表等高端配饰缺乏逼真虚拟试戴模型的问题展开研究，填补了现有虚拟试穿技术主要聚焦服装而忽视配饰的空白。研究借鉴2D服装虚拟试穿模型VITON-HD的技术，并结合MediaPipe手部关键点检测模型，通过专属配饰数据集与网络结构优化，定制并重训练出一款新模型。实验表明，在仅使用小规模数据的情况下，该模型在位置预测性能上已优于原服装模型。当数据量超过10,000张图像时，其潜力将得到进一步释放，为未来高端配饰虚拟试穿应用提供可行路径。
原文摘要 · Abstract (English)
The paper aims to address the lack of photorealistic virtual try-on models for accessories such as jewelry and watches, which are particularly relevant for online retail applications. While existing virtual try-on models focus primarily on clothing items, there is a gap in the market for accessories. This research explores the application of techniques from 2D virtual try-on models for clothing, such as VITON-HD, and integrates them with other computer vision models, notably MediaPipe Hand Landmarker. Drawing on existing literature, the study customizes and retrains a unique model using accessory-specific data and network architecture modifications to assess the feasibility of extending virtual try-on technology to accessories. Results demonstrate improved location prediction compared to the original model for clothes, even with a small dataset. This underscores the model's potential with larger datasets exceeding 10,000 images, paving the way for future research in virtual accessory try-on applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。