Face Normal Estimation from Rags to Riches

TL;DR

This paper introduces a coarse-to-fine face normal estimation method that reduces dependency on large paired datasets by using a two-stage process with exemplars and a self-attention mechanism, achieving high-quality results efficiently.

Contribution

A novel coarse-to-fine face normal estimation framework that minimizes training data requirements and computational resources while improving estimation quality.

Findings

Outperforms state-of-the-art methods in quality and efficiency

Requires less paired data and computational resources

Effective in producing high-quality facial normals

Abstract

Although recent approaches to face normal estimation have achieved promising results, their effectiveness heavily depends on large-scale paired data for training. This paper concentrates on relieving this requirement via developing a coarse-to-fine normal estimator. Concretely, our method first trains a neat model from a small dataset to produce coarse face normals that perform as guidance (called exemplars) for the following refinement. A self-attention mechanism is employed to capture long-range dependencies, thus remedying severe local artifacts left in estimated coarse facial normals. Then, a refinement network is customized for the sake of mapping input face images together with corresponding exemplars to fine-grained high-quality facial normals. Such a logical function split can significantly cut the requirement of massive paired data and computational resource. Extensive experiments and ablation studies are conducted to demonstrate the efficacy of our design and reveal its superiority over state-of-the-art methods in terms of both training expense as well as estimation quality. Our code and models are open-sourced at: https://github.com/AutoHDR/FNR2R.git.