# Pose-Invariant Face Alignment with a Single CNN

arXiv: https://arxiv.org/abs/1707.06286 · HTML: https://mlsanity.com/paper/1707.06286/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2017.

## Built on by (most cited first, 11 of 11)

- [Text and Image Guided 3D Avatar Generation and Manipulation](https://mlsanity.com/paper/2202.06079/) (2022)
- [Supervision by Registration and Triangulation for Landmark Detection](https://mlsanity.com/paper/2101.09866/) (2021)
- [ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation](https://mlsanity.com/paper/2103.00119/) (2021)
- [Robust Egocentric Photo-realistic Facial Expression Transfer for Virtual Reality](https://mlsanity.com/paper/2104.04794/) (2021)
- [Tree-gated Deep Mixture-of-Experts For Pose-robust Face Alignment](https://mlsanity.com/paper/1910.09450/) (2019)
- [FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration](https://mlsanity.com/paper/2311.15445/) (2023)
- [A survey and classification of face alignment methods based on face models](https://mlsanity.com/paper/2311.03082/) (2023)
- [Wide Aspect Ratio Matching for Robust Face Detection](https://mlsanity.com/paper/2103.05993/) (2021)
- [Bounding-box deep calibration for high performance face detection](https://mlsanity.com/paper/2110.03892/) (2021)
- [Robust Boosting Forests with Richer Deep Feature Hierarchy](https://mlsanity.com/paper/2210.16451/) (2022)
- [A Unified Framework to Super-Resolve Face Images of Varied Low Resolutions](https://mlsanity.com/paper/2306.03380/) (2023)

## Abstract (arXiv)

Face alignment has witnessed substantial progress in the last decade. One of the recent focuses has been aligning a dense 3D face shape to face images with large head poses. The dominant technology used is based on the cascade of regressors, e.g., CNN, which has shown promising results. Nonetheless, the cascade of CNNs suffers from several drawbacks, e.g., lack of end-to-end training, hand-crafted features and slow training speed. To address these issues, we propose a new layer, named visualization layer, that can be integrated into the CNN architecture and enables joint optimization with different loss functions. Extensive evaluation of the proposed method on multiple datasets demonstrates state-of-the-art accuracy, while reducing the training time by more than half compared to the typical cascade of CNNs. In addition, we compare multiple CNN architectures with the visualization layer to further demonstrate the advantage of its utilization.