{"slug": "identity-consistent-expression-fields-a-disentangled-neural-radiance-field-for", "title": "Identity-Consistent Expression Fields: A Disentangled Neural Radiance Field Framework for Few-Shot Facial Expression Synthesis", "summary": "Researchers propose Identity-Consistent Expression Fields (ICEF), a framework that disentangles static identity-specific radiance from dynamic expression-conditioned deformation in Neural Radiance Fields for few-shot facial expression synthesis. ICEF introduces an identity preservation regularizer and confidence-weighted conditional feature warping to prevent identity drift and artifacts when extrapolating to novel expressions. The method is evaluated on novel-expression rendering quality and identity-consistency metrics across varying expression-parameter distances.", "body_md": "arXiv:2607.16287v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/identity-consistent-expression-fields-a-disentangled-neural-radiance-field-for", "canonical_source": "https://arxiv.org/abs/2607.16287", "published_at": "2026-07-21 04:00:00+00:00", "updated_at": "2026-07-21 04:08:46.885774+00:00", "lang": "en", "topics": ["computer-vision", "neural-networks", "generative-ai", "artificial-intelligence"], "entities": ["Identity-Consistent Expression Fields", "Neural Radiance Fields"], "alternates": {"html": "https://wpnews.pro/news/identity-consistent-expression-fields-a-disentangled-neural-radiance-field-for", "markdown": "https://wpnews.pro/news/identity-consistent-expression-fields-a-disentangled-neural-radiance-field-for.md", "text": "https://wpnews.pro/news/identity-consistent-expression-fields-a-disentangled-neural-radiance-field-for.txt", "jsonld": "https://wpnews.pro/news/identity-consistent-expression-fields-a-disentangled-neural-radiance-field-for.jsonld"}}