# PropagationNet: Propagate Points to Curve to Learn Structure Information

arXiv: https://arxiv.org/abs/2006.14308 · HTML: https://mlsanity.com/paper/2006.14308/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

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

- [ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment](https://mlsanity.com/paper/2109.05721/) (2021)
- [Shape Preserving Facial Landmarks with Graph Attention Networks](https://mlsanity.com/paper/2210.07233/) (2022)
- [Fast Facial Landmark Detection and Applications: A Survey](https://mlsanity.com/paper/2101.10808/) (2021)
- [FaceShot: Bring Any Character into Life](https://mlsanity.com/paper/2503.00740/) (2025)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [FreeEnricher: Enriching Face Landmarks without Additional Cost](https://mlsanity.com/paper/2212.09525/) (2022)
- [An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking](https://mlsanity.com/paper/2103.07615/) (2021)
- [Reasoning Structural Relation for Occlusion-Robust Facial Landmark Localization](https://mlsanity.com/paper/2112.10087/) (2021)
- [Fiducial Focus Augmentation for Facial Landmark Detection](https://mlsanity.com/paper/2402.15044/) (2024)
- [Spatio-Temporal Fuzzy-oriented Multi-Modal Meta-Learning for Fine-grained Emotion Recognition](https://mlsanity.com/paper/2412.13541/) (2024)

## Abstract (arXiv)

Deep learning technique has dramatically boosted the performance of face alignment algorithms. However, due to large variability and lack of samples, the alignment problem in unconstrained situations, e.gonedot large head poses, exaggerated expression, and uneven illumination, is still largely unsolved. In this paper, we explore the instincts and reasons behind our two proposals, i.eonedot Propagation Module and Focal Wing Loss, to tackle the problem. Concretely, we present a novel structure-infused face alignment algorithm based on heatmap regression via propagating landmark heatmaps to boundary heatmaps, which provide structure information for further attention map generation. Moreover, we propose a Focal Wing Loss for mining and emphasizing the difficult samples under in-the-wild condition. In addition, we adopt methods like CoordConv and Anti-aliased CNN from other fields that address the shift-variance problem of CNN for face alignment. When implementing extensive experiments on different benchmarks, i.eonedot WFLW, 300W, and COFW, our method outperforms state-of-the-arts by a significant margin. Our proposed approach achieves 4.05% mean error on WFLW, 2.93% mean error on 300W full-set, and 3.71% mean error on COFW.