Facial Expression Animation by Landmark Guided Residual Module

Wang, Xueping; Wang, Yunlong; Li, Weixin; Du, Zhengyin; Huang, Di

doi:10.1109/taffc.2021.3100352

Cited by 6 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In computer vision, facial landmarks have a wide range of applications, such as high-precision face pose alignment [17,9], accurate analysis of facial features and expressions based on landmarks, processing, and synthesis of specific parts to achieve entertainment functions such as beautification and animation [18,19].…”

Section: Landmark Selection Strategymentioning

confidence: 99%

“…Jeong et al [34] propose a facial landmark detection algorithm for realworld driving situations by integrating a locally weighted random forest regressor with random sampling consistency and an explicit global shape model. With the rapid development of deep learning, a large number of networks have also been proposed for 2D facial landmark detection [18,35,36]. Compared with 2D, the research on 3D facial landmark detection is relatively new.…”

Section: Landmarks Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic labeling of 3D facial acupoint landmarks

Yin,

Fang,

2024

Metaverse

View full text Add to dashboard Cite

As special marks on a human face, facial landmarks reflect the facial features of various parts of the face, which is crucial in biomedicine and medical imaging. In addition, facial landmarks are also important features in computer vision such as face detection, face recognition, facial pose estimation, and facial animation. In this paper, we construct a 3D facial acupoint annotated dataset by labeling 37 facial acupoints on 846 neutral face triangle mesh on the FaceScape dataset. Based on these annotated data, we use a feature template matching method to realize the automatic annotation of 37 acupoints on triangle meshes. We used 40 meshes as the training set to extract the geometric patterns of 3D acupoints and then measured the performance of the automatic labeling algorithm on 20 meshes and 806 meshes as the test sets. In the training process, we extract the tangent plane for each landmark, project the neighbor vertices of the landmark to the tangent plane, and construct the feature image with R × R resolution through the bounding box of the projected points. In the testing process, we use the pattern images extracted during training to find the average features and use them as a guide to optimize the predicted landmarks. The experimental results show that our automatic acupoint labeling method has achieved good results.

show abstract