Identity-Consistent Expression Fields: A Disentangled Neural Radiance Field Framework for Few-Shot Facial Expression Synthesis

• URL: http://arxiv.org/abs/2607.16287v1
• Date: Sat, 11 Jul 2026 16:05:17 GMT
• Title: Identity-Consistent Expression Fields: A Disentangled Neural Radiance Field Framework for Few-Shot Facial Expression Synthesis
• Abstract summary: Identity-Consistent Expression Fields (ICEF) is a framework that disentangles a static, identity-specific radiance component from a dynamic, expression-conditioned deformation component.<n>ICEF incorporates a confidence-weighted conditional feature warping step that down-weights unreliable warps for target expressions that are far, in parameter space, from the observed few-shot inputs.
• Score: 3.4658060802121624
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural Radiance Fields (NeRF) have enabled photorealistic novel-view synthesis of 3D scenes and, in the facial domain, have been extended to reconstruct and animate 3D face models from a small number of images. However, existing few-shot dynamic NeRF methods for facial expression editing typically warp a single learned feature volume conditioned on target expression parameters, which can cause identity-specific appearance details (skin texture, fine geometric structure) to drift when the model is driven toward expressions far from those seen in the few-shot input set. We propose Identity-Consistent Expression Fields (ICEF), a framework that explicitly disentangles a static, identity-specific radiance component from a dynamic, expression-conditioned deformation component, and introduces an identity preservation regularizer that constrains the deformation network to modify only expression-relevant regions while leaving identity-specific canonical appearance untouched. ICEF further incorporates a confidence-weighted conditional feature warping step that down-weights unreliable warps for target expressions that are far, in parameter space, from the observed few-shot inputs, mitigating artifacts observed in prior few-shot dynamic NeRF methods when extrapolating to novel expressions. We relate ICEF to prior few-shot dynamic NeRF, static 3D-aware face generation, and disentangled face-editing radiance field methods, and describe an evaluation protocol measuring both novel-expression rendering quality and, specifically, identity-consistency metrics across a range of expression-parameter extrapolation distances.

Related papers

• PartNerFace: Part-based Neural Radiance Fields for Animatable Facial Avatar Reconstruction [74.52310899576547]
  We present PartNerFace, a part-based neural radiance fields approach for reconstructing animatable facial avatar from monocular RGB videos.<n>Our method generalizes well to unseen expressions and is capable of modeling fine-scale facial motions.
  arXiv  Detail & Related papers  (2026-04-15T14:28:44Z)
• SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargeting [4.083283519300837]
  We propose SEREP, a model that disentangles expression from identity at the semantic level.<n>We train a model to predict expression from monocular images relying on a novel semi-supervised scheme using low quality synthetic data.<n>Our experiments show that SEREP outperforms state-of-the-art methods, capturing challenging expressions and transferring them to new identities.
  arXiv  Detail & Related papers  (2024-12-18T22:12:28Z)
• ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations [25.016000421755162]
  This paper presents a novel 3D morphable face model, named ImFace++, to learn a sophisticated and continuous space with implicit neural representations. ImFace++ first constructs two explicitly disentangled deformation fields to model complex shapes associated with identities and expressions. A refinement displacement field within the template space is further incorporated, enabling fine-grained learning of individual-specific facial details.
  arXiv  Detail & Related papers  (2023-12-07T03:53:53Z)
• GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images [55.431697263581626]
  We introduce a novel Geometry-aware Facial Expression Translation framework, which is based on parametric 3D facial representations and can stably decoupled expression. We achieve higher-quality and more accurate facial expression transfer results compared to state-of-the-art methods, and demonstrate applicability of various poses and complex textures.
  arXiv  Detail & Related papers  (2023-08-07T09:03:35Z)
• Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization [91.52882218901627]
  We propose a novel method for constructing implicit 3D morphable face models that are both generalizable and intuitive for editing. Our method improves upon photo-realism, geometry, and expression accuracy compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-04T17:58:40Z)
• One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field [81.07651217942679]
  Talking head generation aims to generate faces that maintain the identity information of the source image and imitate the motion of the driving image. We propose HiDe-NeRF, which achieves high-fidelity and free-view talking-head synthesis.
  arXiv  Detail & Related papers  (2023-04-11T09:47:35Z)
• FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing [27.014582934266492]
  We propose a Few-shot Dynamic Neural Radiance Field (FDNeRF), the first NeRF-based method capable of reconstruction and expression editing of 3D faces. Unlike existing dynamic NeRFs that require dense images as input and can only be modeled for a single identity, our method enables face reconstruction across different persons with few-shot inputs.
  arXiv  Detail & Related papers  (2022-08-11T11:05:59Z)
• ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations [21.389170615787368]
  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. In addition to ImFace, an effective preprocessing pipeline is proposed to address the issue of watertight input requirement in implicit representations.
  arXiv  Detail & Related papers  (2022-03-28T05:37:59Z)
• Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection [65.92058628082322]
  Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions. This paper presents a novel Learning to Aggregate and Personalize framework for unsupervised robust 3D face modeling.
  arXiv  Detail & Related papers  (2021-06-15T03:10:17Z)
• Learning an Animatable Detailed 3D Face Model from In-The-Wild Images [50.09971525995828]
  We present the first approach to jointly learn a model with animatable detail and a detailed 3D face regressor from in-the-wild images. Our DECA model is trained to robustly produce a UV displacement map from a low-dimensional latent representation. We introduce a novel detail-consistency loss to disentangle person-specific details and expression-dependent wrinkles.
  arXiv  Detail & Related papers  (2020-12-07T19:30:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.