# Gaussian Vector: An Efficient Solution for Facial Landmark Detection

arXiv: https://arxiv.org/abs/2010.01318 · HTML: https://mlsanity.com/paper/2010.01318/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation](https://mlsanity.com/paper/2107.03332/) (2021)
- [LOTR: Face Landmark Localization Using Localization Transformer](https://mlsanity.com/paper/2109.10057/) (2021)
- [Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks](https://mlsanity.com/paper/2111.07047/) (2021)
- [PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation](https://mlsanity.com/paper/2306.06656/) (2023)
- [Sub-pixel face landmarks using heatmaps and a bag of tricks](https://mlsanity.com/paper/2103.03059/) (2021)
- [LocalEyenet: Deep Attention framework for Localization of Eyes](https://mlsanity.com/paper/2303.12728/) (2023)
- [1DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking](https://mlsanity.com/paper/2311.00241/) (2023)

## Abstract (arXiv)

Significant progress has been made in facial landmark detection with the development of Convolutional Neural Networks. The widely-used algorithms can be classified into coordinate regression methods and heatmap based methods. However, the former loses spatial information, resulting in poor performance while the latter suffers from large output size or high post-processing complexity. This paper proposes a new solution, Gaussian Vector, to preserve the spatial information as well as reduce the output size and simplify the post-processing. Our method provides novel vector supervision and introduces Band Pooling Module to convert heatmap into a pair of vectors for each landmark. This is a plug-and-play component which is simple and effective. Moreover, Beyond Box Strategy is proposed to handle the landmarks out of the face bounding box. We evaluate our method on 300W, COFW, WFLW and JD-landmark. That the results significantly surpass previous works demonstrates the effectiveness of our approach.