Customizing blendshapes to capture facial details

Blendshape technique is an effective tool in the computer facial animation. Every character requires its own unique blendshapes to cover numerous facial expressions in the Visual Effects industry. Despite outstanding advances in this area, existing techniques still need a professional artist’s intuition and complex hardware. In this paper, we propose a framework for customizing blendshapes to capture facial details. The suggested method primarily consists of two stages: Blendshape generation and Blendshape augmentation. In the first stage, localized blendshapes are automatically generated from real-time captured faces with two methods: linear regression and an autoencoder Han (in: IEEE International Conference on Big Data and Smart Computing (BigComp) 2021) ( 2021 ). In our experiment, face construction with the former outperforms that of the later method. However, generated blendshapes are slightly missing the source features, especially mouth movements. To overcome this, in the last stage, we extend Han (in: IEEE International Conference on Big Data and Smart Computing (BigComp) 2021), ( 2021 ) by adding a blendshape incrementally to minimize erroneous expression transfer.