Convolutional Point-set Representation: A Convolutional Bridge Between a Densely Annotated Image and 3D Face Alignment
We present a robust method for estimating the facial pose and shape information from a densely annotated facial image. The method relies on Convolutional Point-set Representation (CPR), a carefully designed matrix representation to summarize different layers of information encoded in the set of detected points in the annotated image. The CPR disentangles the dependencies of shape and different pose parameters and enables updating different parameters in a sequential manner via convolutional neural networks and recurrent layers. When updating the pose parameters, we sample reprojection errors along with a predicted direction and update the parameters based on the pattern of reprojection errors. This technique boosts the model's capability in searching a local minimum under challenging scenarios. We also demonstrate that annotation from different sources can be merged under the framework of CPR and contributes to outperforming the current state-of-the-art solutions for 3D face alignment. Experiments indicate the proposed CPRFA (CPR-based Face Alignment) significantly improves 3D alignment accuracy when the densely annotated image contains noise and missing values, which is common under "in-the-wild" acquisition scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Face AlignmentFace AlignmentMissing ValuesSimilar Papers 제목 키워드 기반
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we …
Conditional Image GenerationImage ClusteringRepresentation LearningDeep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
Deep clustering has shown its promising capability in joint representation learning and clustering via deep neural networks. Despite the significant progress, the existing deep clustering works mostly utilize some distri…
ClusteringContrastive LearningDeep ClusteringImage Clustering+1Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network
Training a Convolutional Neural Network (CNN) to be robust against rotation has mostly been done with data augmentation. In this paper, another progressive vision of research direction is highlighted to encourage less de…
Data Augmentationimage-classificationImage ClassificationRepresentation Learning+1Revisiting 2D Convolutional Neural Networks for Graph-based Applications
Graph convolutional networks (GCNs) are widely used in graph-based applications such as graph classification and segmentation. However, current GCNs have limitations on implementation such as network architectures due to…
Computational EfficiencyGraph ClassificationPoint Cloud SegmentationLearning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks
In this paper, we tackle the problem of RGB-D semantic segmentation of indoor images. We take advantage of deconvolutional networks which can predict pixel-wise class labels, and develop a new structure for deconvolution…
SegmentationSemantic Segmentation