Super-Identity Convolutional Neural Network for Face Hallucination
This work addresses the specific challenge of identity preservation in face hallucination for applications like surveillance or biometrics, representing an incremental improvement over prior methods.
The paper tackles the problem of face hallucination by focusing on identity recovery, proposing a Super-Identity Convolutional Neural Network (SICNN) that achieves superior visual quality and significantly improves recognizability for ultra-low-resolution faces with an 8× upscaling factor.
Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information. However, previous face hallucination approaches largely ignore facial identity recovery. This paper proposes Super-Identity Convolutional Neural Network (SICNN) to recover identity information for generating faces closed to the real identity. Specifically, we define a super-identity loss to measure the identity difference between a hallucinated face and its corresponding high-resolution face within the hypersphere identity metric space. However, directly using this loss will lead to a Dynamic Domain Divergence problem, which is caused by the large margin between the high-resolution domain and the hallucination domain. To overcome this challenge, we present a domain-integrated training approach by constructing a robust identity metric for faces from these two domains. Extensive experimental evaluations demonstrate that the proposed SICNN achieves superior visual quality over the state-of-the-art methods on a challenging task to super-resolve 12$\times$14 faces with an 8$\times$ upscaling factor. In addition, SICNN significantly improves the recognizability of ultra-low-resolution faces.