NOFA++: Tuning-free NeRF-based One-shot Facial Avatar Reconstruction

Wangbo Yu, Chaoran Feng, Li Yuan, Yonghong Tian

Abstract

3D facial avatar reconstruction is a fundamental problem in computer vision and graphics with applications in digital humans, virtual reality, and telepresence. Recent neural radiance field (NeRF)-based methods have greatly improved fidelity, yet most remain subject-specific, requiring multi-view images with diverse expressions and extensive test-time finetuning, which limits their generalization to unseen identities. Achieving high-quality reconstruction from a single image is particularly challenging due to missing multi-view supervision and the need to balance efficiency with fidelity. To address these issues, we present NOFA++, a generalizable one-shot framework that reconstructs photorealistic 3D facial avatars from a single input. Our method leverages the generative prior of a pretrained 3D GAN in an encoder–generator pipeline to recover a canonical neural volume, and introduces a coarse-to-fine residual generation strategy to synthesize identity-specific details without per-subject optimization. We further design a deformation field conditioned on identity and expression parameters to model facial dynamics, enabling controllable reenactment from video or audio. Extensive experiments show that NOFA++ surpasses state-of-the-art baselines in both reconstruction fidelity and reenactment quality, while eliminating test-time finetuning and generalizing robustly across unseen subjects.
BibTeX
@article{yu2026nofa,
  author = {Wangbo Yu and Chaoran Feng and Li Yuan and Yonghong Tian},
  title = {{NOFA++: Tuning-free NeRF-based One-shot Facial Avatar Reconstruction}},
  journal = {IEEE Trans. Circuits Syst. Video Technol.},
  year = {2026},
  doi = {10.1109/tcsvt.2025.3628119},
}

Loading related content...

Figure