Youyi Zhan — accepted AI-conference papers

2026

High-Fidelity Mobile Avatars with Pruned Local Blendshapes

Youyi Zhan, He Wang, Tianjia Shao, Kun Zhou

CVPR 2026

We propose a method to reconstruct high-fidelity human avatars from multi-view video that can run on mobile devices. Many works can model high-quality Gaussian-based full-body avatars from multi-view video. However, these methods require heavy computation to obtain pose-dependent appearance, making

Cited by 0 Source ↗Scholar ↗

2025

Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs

Youyi Zhan, Tianjia Shao, Yin Yang, Kun Zhou

CVPR 2025highlight

Many works have succeeded in reconstructing Gaussian human avatars from multi-view videos. However, they either struggle to capture pose-dependent appearance details with a single MLP, or rely on a computationally intensive neural network to reconstruct high-fidelity appearance but with rendering pe…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗