# AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses

arXiv: https://arxiv.org/abs/2007.03221 · HTML: https://mlsanity.com/paper/2007.03221/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation](https://mlsanity.com/paper/2111.08557/) (2021)
- [Fast Facial Landmark Detection and Applications: A Survey](https://mlsanity.com/paper/2101.10808/) (2021)
- [Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer](https://mlsanity.com/paper/2412.00740/) (2024)
- [Label Encoding for Regression Networks](https://mlsanity.com/paper/2212.01927/) (2022)
- [Bridging Gap between Image Pixels and Semantics via Supervision: A Survey](https://mlsanity.com/paper/2107.13757/) (2021)
- [Learning Label Encodings for Deep Regression](https://mlsanity.com/paper/2303.02273/) (2023)
- [DogFLW: Dog Facial Landmarks in the Wild Dataset](https://mlsanity.com/paper/2405.11501/) (2024)
- [Modelling Lips-State Detection Using CNN for Non-Verbal Communications](https://mlsanity.com/paper/2112.04752/) (2021)
- [Online Anchor-based Training for Image Classification Tasks](https://mlsanity.com/paper/2406.12662/) (2024)
- [Towards Unified Dynamic Face Landmark Detection](https://mlsanity.com/paper/2608.10346/) (2026)

## Abstract (arXiv)

Facial landmark localization aims to detect the predefined points of human faces, and the topic has been rapidly improved with the recent development of neural network based methods. However, it remains a challenging task when dealing with faces in unconstrained scenarios, especially with large pose variations. In this paper, we target the problem of facial landmark localization across large poses and address this task based on a split-and-aggregate strategy. To split the search space, we propose a set of anchor templates as references for regression, which well addresses the large variations of face poses. Based on the prediction of each anchor template, we propose to aggregate the results, which can reduce the landmark uncertainty due to the large poses. Overall, our proposed approach, named AnchorFace, obtains state-of-the-art results with extremely efficient inference speed on four challenging benchmarks, i.e. AFLW, 300W, Menpo, and WFLW dataset. Code will be available at https://github.com/nothingelse92/AnchorFace.