让3D虚拟头像戴上可自定义的眼镜，支持用户在VR中实时试戴。
GlassesGB: Controllable 2D GAN-Based Eyewear Personalization for 3D Gaussian Blendshapes Head Avatars
- 结合2D生成与3D混合形状，实现可定制眼镜的3D头像生成。
- 支持用户驱动的细粒度眼镜设计，突破传统模板限制。
- 适合虚拟试妆、VR社交等需要个性化头像的场景。
虚拟试戴系统使用户能在虚拟现实场景中交互式尝试不同产品。然而，现有方法仅支持预设眼镜模板，缺乏用户驱动的精细定制能力。尽管GlassesGAN能生成个性化2D眼镜图像，但其功能局限于2D生成。受3D高斯混合形状在头部重建中成功启发，我们融合两项技术，提出GlassesGB框架，支持为3D头像生成可定制眼镜。该框架有效连接2D生成定制与3D头像渲染，解决了虚拟现实应用中个性化眼镜设计的挑战。代码已公开于https://ruiyangju.github.io/GlassesGB。
原文摘要 · Abstract (English)
Virtual try-on systems allow users to interactively try different products within VR scenarios. However, most existing VTON methods operate only on predefined eyewear templates and lack support for fine-grained, user-driven customization. While GlassesGAN enables personalized 2D eyewear design, its capability remains limited to 2D image generation. Motivated by the success of 3D Gaussian Blendshapes in head reconstruction, we integrate these two techniques and propose GlassesGB, a framework that supports customizable eyewear generation for 3D head avatars. GlassesGB effectively bridges 2D generative customization with 3D head avatar rendering, addressing the challenge in achieving personalized eyewear design for VR applications. The implementation code is available at https://ruiyangju.github.io/GlassesGB.
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。