基于编解码网络的多姿态人脸图像正面化方法

A multi-pose face frontalization method based on encoder-decoder network

多姿态人脸图像正面化可以缓解头部姿态变化对人脸分析任务的影响.以往直接从多姿态人脸图像合成正面人脸图像的方法存在细节特征缺失的问题.针对这一问题,本文提出一种基于编解码网络的多姿态人脸图像正面化方法——多任务卷积编解码网络(MCEDN).该方法引入正面基础特征网络合成正面人脸基础特征,并在此基础上融合编码网络提取的多姿态人脸局部特征进行细节补偿,最终合成更加清晰的正面人脸图像.利用多任务学习机制建立端到端模型,统一局部特征提取、正面基础特征解析、正面图像合成3个模块,通过共享参数提升整个模型的效果.与已有方法对比, MCEDN在多个数据集上都可以合成结构稳定、细节清晰的正面人脸图像.我们直接使用合成的正面人脸图像进行人脸识别和表情识别,识别准确率达到先进水平,这表明MCEDN可以有效保留人脸细节特征,支持人脸分析任务.

Multi-pose face frontalization can alleviate the influence of pose variance on face analysis.The traditional method of synthesizing a frontal face image directly from a multi-pose face image presents a problem in missing face details.To overcome this problem,we propose a face frontalization method based on the encoderdecoder network,namely multitask convolutional encoder-decoder network(MCEDN).The MCEDN introduces a frontal raw feature network to synthesize the global raw features of the frontal face.Then,the network utilizes the decoder to synthesize a clearer frontal face image by fusing local features extracted by the encoder and global raw features.We use a multitask learning mechanism to build an end-to-end model.The method then integrates three modules,namely local feature extraction,global raw feature synthesis,and frontal image synthesis.The model performance was improved by sharing parameters.In comparison with existing methods,MCEDN can synthesize frontal face images with a stable structure and rich details on multiple datasets.Then,we use the synthesized frontal images for face recognition and face expression recognition,and the state-of-the-art results demonstrate that the MCEDN preserves a number of face details.