HeadNeRF+

01 — Overview

Overview

HeadNeRF can render photorealistic, controllable faces, but fitting its latent codes to each image is slow and prone to overfitting. HeadNeRF+ replaces iterative fitting with a learned encoder that directly predicts the disentangled reconstruction features.

The framework also introduces explicit semantic face-part guidance even though the underlying NeRF does not expose a conventional mesh.

02 — Contributions

Key Contributions

• 01

  Predicts HeadNeRF’s disentangled identity, expression, and appearance features directly from an input image.

• 02

  Adds a lightweight semantic face-segmentation network to expose facial-part structure.

• 03

  Uses a facial-part loss to improve reconstruction accuracy and local visual quality.

03 — Method

Method

A face encoder estimates the latent parameters consumed by a pretrained HeadNeRF renderer. A lightweight segmentation branch supplies semantic facial regions, and part-aware losses guide the encoder toward more accurate local reconstruction.

04 — Evaluation

Results

The experiments report much lower reconstruction time than per-image fitting together with improved reconstruction accuracy and visual quality.

05 — Reference

Citation

@InProceedings{Yan_2023_HeadNeRF,
  author    = {Yan, Peizhi and Ward, Rabab and Wang, Dan and Tang, Qiang and Du, Shan},
  title     = {Learning Disentangled Features for NeRF-Based Face Reconstruction},
  booktitle = {2023 IEEE International Conference on Image Processing (ICIP)},
  year      = {2023},
  pages     = {1135--1139},
  doi       = {10.1109/ICIP49359.2023.10222432}
}