StylizedFacePoint: Facial Landmark Detection for Stylized Characters
Open Access
- 28 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 8072-8080
Abstract
Facial landmark detection forms the foundation for numerous face-related tasks. Recently, this field has gained substantial attention and made significant advancements. Nonetheless, detecting facial landmarks for stylized characters still remains a challenge. Existing approaches, which are mostly trained on real-human face datasets, struggle to perform well due to the structural variations between real and stylized characters. Additionally, a comprehensive dataset for analyzing stylized characters' facial features is lacking. This study proposes a novel dataset, the Facial Landmark Dataset for Stylized Characters (FLSC), which contains 2674 images and 4086 faces selected from 16 cartoon video clips, together with 98 landmarks per image, labeled by professionals. Besides, we propose StylizedFacePoint: a deep-learning-based method for stylized facial landmark detection that outperforms the existing approaches. This method has also proven to work well for characters with styles outside the training domain. Moreover, we outline two primary types of applications for our dataset and method. For each, we provide a detailed illustrative example.Keywords
Funding Information
- National Natural Science Foundation of China (62102255)
This publication has 32 references indexed in Scilit:
- Facial landmark points detection using knowledge distillation-based neural networksComputer Vision and Image Understanding, 2022
- Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the WildInternational Journal of Computer Vision, 2021
- Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric ModelGraphical Models, 2021
- Cascade of encoder-decoder CNNs with learned coordinates regressor for robust facial landmarks detectionPattern Recognition Letters, 2020
- Style Aggregated Network for Facial Landmark Detection2018
- Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors2018
- A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection2017
- One millisecond face alignment with an ensemble of regression trees2014
- Deep Convolutional Network Cascade for Facial Point Detection2013
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004