# Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos

arXiv: https://arxiv.org/abs/1811.00342 · HTML: https://mlsanity.com/paper/1811.00342/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2018.

## Built on by (most cited first, 19 of 19)

- [STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection](https://mlsanity.com/paper/2306.02763/) (2023)
- [KeyPoint Relative Position Encoding for Face Recognition](https://mlsanity.com/paper/2403.14852/) (2024)
- [Cluster and Aggregate: Face Recognition with Large Probe Set](https://mlsanity.com/paper/2210.10864/) (2022)
- [HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap](https://mlsanity.com/paper/2104.03100/) (2021)
- [Subpixel Heatmap Regression for Facial Landmark Localization](https://mlsanity.com/paper/2111.02360/) (2021)
- [SapiensID: Foundation for Human Recognition](https://mlsanity.com/paper/2504.04708/) (2025)
- [KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2201.07394/) (2022)
- [ASFD: Automatic and Scalable Face Detector](https://mlsanity.com/paper/2201.10781/) (2022)
- [Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network](https://mlsanity.com/paper/2112.12328/) (2021)
- [BoundaryFace: A mining framework with noise label self-correction for Face Recognition](https://mlsanity.com/paper/2210.04567/) (2022)
- [Reasoning Structural Relation for Occlusion-Robust Facial Landmark Localization](https://mlsanity.com/paper/2112.10087/) (2021)
- [POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search](https://mlsanity.com/paper/2410.09583/) (2024)
- [Improving Robustness for Pose Estimation via Stable Heatmap Regression](https://mlsanity.com/paper/2105.03569/) (2021)
- [A survey and classification of face alignment methods based on face models](https://mlsanity.com/paper/2311.03082/) (2023)
- [Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment](https://mlsanity.com/paper/2503.22359/) (2025)
- [Heatmap Regression without Soft-Argmax for Facial Landmark Detection](https://mlsanity.com/paper/2508.14929/) (2025)
- [WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range](https://mlsanity.com/paper/2101.03826/) (2021)
- [1DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking](https://mlsanity.com/paper/2311.00241/) (2023)
- [AdaSin: Enhancing Hard Sample Metrics with Dual Adaptive Penalty for Face Recognition](https://mlsanity.com/paper/2503.03528/) (2025)

## Abstract (arXiv)

In recent years, heatmap regression based models have shown their effectiveness in face alignment and pose estimation. However, Conventional Heatmap Regression (CHR) is not accurate nor stable when dealing with high-resolution facial videos, since it finds the maximum activated location in heatmaps which are generated from rounding coordinates, and thus leads to quantization errors when scaling back to the original high-resolution space. In this paper, we propose a Fractional Heatmap Regression (FHR) for high-resolution video-based face alignment. The proposed FHR can accurately estimate the fractional part according to the 2D Gaussian function by sampling three points in heatmaps. To further stabilize the landmarks among continuous video frames while maintaining the precise at the same time, we propose a novel stabilization loss that contains two terms to address time delay and non-smooth issues, respectively. Experiments on 300W, 300-VW and Talking Face datasets clearly demonstrate that the proposed method is more accurate and stable than the state-of-the-art models.