# Face Normal Estimation from Rags to Riches

arXiv: https://arxiv.org/abs/2601.01950 · HTML: https://mlsanity.com/paper/2601.01950/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 65 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [EMOCA: Emotion Driven Monocular Face Capture and Animation](https://mlsanity.com/paper/2204.11312/) (2022)
- [PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering](https://mlsanity.com/paper/2109.08379/) (2021)
- [UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory](https://mlsanity.com/paper/1609.02132/) (2016)
- [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](https://mlsanity.com/paper/1803.07835/) (2018)
- [Deep Photo Style Transfer](https://mlsanity.com/paper/1703.07511/) (2017)
- [Semantic Image Inpainting with Deep Generative Models](https://mlsanity.com/paper/1607.07539/) (2016)
- [Nonlinear 3D Face Morphable Model](https://mlsanity.com/paper/1804.03786/) (2018)
- [Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition](https://mlsanity.com/paper/2302.11566/) (2023)
- [Cross-domain Correspondence Learning for Exemplar-based Image Translation](https://mlsanity.com/paper/2004.05571/) (2020)
- [SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild](https://mlsanity.com/paper/1712.01261/) (2017)
- [Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network](https://mlsanity.com/paper/1612.04904/) (2016)
- [Towards High-fidelity Nonlinear 3D Face Morphable Model](https://mlsanity.com/paper/1904.04933/) (2019)
- [Deep Exemplar-based Colorization](https://mlsanity.com/paper/1807.06587/) (2018)
- [Deep Exemplar-based Video Colorization](https://mlsanity.com/paper/1906.09909/) (2019)
- [Deep Colorization](https://mlsanity.com/paper/1605.00075/) (2016)
- [Neural Face Editing with Intrinsic Image Disentangling](https://mlsanity.com/paper/1704.04131/) (2017)
- [Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression](https://mlsanity.com/paper/1703.07834/) (2017)

## Abstract (arXiv)

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.