GlassesGB: Controllable 2D GAN-Based Eyewear Personalization for 3D Gaussian Blendshapes Head Avatars

IEEE VR 2026 Poster
Rui-Yang Ju, Jen-Shiun Chiang
Kyoto University, Tamkang University
Paper arXiv
We introduce a novel framework, named GlassesGB, that generates personalized eyewear via a 2D GAN-based method and jointly renders it as true 3D geometry on a 3D head avatar using 3D Gaussian Blendshapes, rather than as texture overlays.

Abstract

Virtual try-on systems allow users to interactively try different products within Virtual Reality (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.

Live Demo

Depth Map Comparison


We present pseudo-colored depth maps to show geometric details in the eyewear region, where warmer colors denote regions closer to the camera and cooler colors correspond to greater depth. The results show that the eyewear generated by GlassesGB exhibits real 3D geometry rather than appearing as texture overlays. Depth maps from novel views further demonstrate that GlassesGB preserves the original geometry of 3DGB while introducing additional structural details for the eyewear, without causing geometric degradation.

BibTeX


    @article{ju2026glassesgb,
      title={GlassesGB: Controllable 2D GAN-Based Eyewear Personalization for 3D Gaussian Blendshapes Head Avatars},
      author={Ju, Rui-Yang and Chiang, Jen-Shiun},
      journal={arXiv preprint arXiv:2601.17088},
      year={2026}
    }