Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

ImFace model

The ImFace model is a nonlinear three-dimensional morphable face model that uses implicit neural representations to model continuous facial shape, identity, and expression. Unlike traditional morphable models that rely on discrete polygonal meshes and linear shape combinations, it represents facial geometry within a continuous coordinate space using neural networks. The architecture explicitly disentangles facial geometry into separate deformation fields for individual identity and facial expressions relative to a shared reference template. By adaptively blending local implicit fields and supporting standard open, non-watertight facial surface data, the model effectively captures fine-grained geometric details and diverse facial dynamics for computer vision and graphics applications.

1 item

ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations

ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations

Mingwu Zheng, Hongyu Yang, Di Huang, Liming Chen

OrganizationsBeihang UniversityÉcole Centrale de LyonLIRIS

Why you should read this

Proposes a nonlinear 3D morphable face model based on implicit neural representations that explicitly disentangles identity and expression deformation fields, enabling high-fidelity face reconstruction and synthesis directly from non-watertight surfaces.

Precise representations of 3D faces are beneficial to various computer vision and graphics applications. Due to the data discretization and model linearity, however, it remains challenging to capture accurate identity and expression clues in current studies. This paper presents a novel 3D morphable face model, namely ImFace, to learn a nonlinear and continuous space with implicit neural representations. It builds two explicitly disentangled deformation fields to model complex shapes associated with identities and expressions, respectively, and designs an improved learning strategy to extend embeddings of expressions to allow more diverse changes. We further introduce a Neural Blend-Field to learn sophisticated details by adaptively blending a series of local fields. In addition to ImFace, an effective preprocessing pipeline is proposed to address the issue of watertight input requirement in implicit representations, enabling them to work with common facial surfaces for the first time. Extensive experiments are performed to demonstrate the superiority of ImFace.

Added

2026-09-26