cs.CVNov 10, 2026

ViGA-FLAME: Aligning Latent Visual and Geometric Representations for Robust 3D Head Expression Estimation

Authors: Wen Hao He, Jiacheng Wu, Jie Chen

Organizations: Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR

Abstract

Estimating 3D head expression from a single image requires mapping visual appearance to underlying facial geometry. We propose ViGA-FLAME, a two-stage framework that aligns semantic visual features with a structured geometric latent space. First, a Parametric-Geometric Variational Autoencoder (PG-VAE) learns a unified representation of canonical head surfaces and FLAME parameters, supporting both detailed surface reconstruction and interpretable parameter recovery. Supervision on geometry and parameters, together with consistency between the two decoding branches, connects surface detail with parametric structure. Second, a trainable Visual-Geometric Adapter (ViGA) maps features from a pretrained semantic visual encoder into this latent space. Asymmetric attention enables ViGA to align semantic image features from the visual encoder with the structured geometric information represented in the PG-VAE latent space, without altering the original visual stream. By grounding image evidence in this latent prior, ViGA-FLAME enables robust 3D head expression estimation across severe facial deformations and large viewing angles, efficiently improving robustness over competing feed-forward methods.

Figures & tables

Explore similar work

CardsList
  1. EAvatar: Expression-Aware Head Avatar Reconstruction with Generative Geometry Priors

    Aug 19, 2025Shikun Zhang, Cunjian Chen, Yiqun Wang +13D Face Reconstruction3D Gaussian Splatting

  2. GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction

    Feb 27, 2026Chao Xu, Xiaochen Zhao, Xiang Deng +43D Avatar Generation3D Face Reconstruction

  3. Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces

    Apr 30, 2026Andrew Bond, Ilkin Umut Melanlioglu, Erkut Erdem +1Variational AutoencodersHyperspherical Representation Learning