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

TL;DR

GlassesGB introduces a novel framework that combines 2D GAN-based eyewear customization with 3D Gaussian Blendshapes head avatars, enabling personalized eyewear design for VR applications.

Contribution

The paper presents a new method integrating 2D generative models with 3D head avatars for customizable eyewear creation, bridging a gap in VR personalization tools.

Findings

Supports fine-grained user-driven eyewear customization

Bridges 2D generative design with 3D avatar rendering

Enables personalized eyewear for VR headsets

Abstract

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.