SD-GAN: Structural and Denoising GAN reveals facial parts under occlusion
This work addresses occlusion issues in face recognition systems, which is a domain-specific problem, and it is incremental as it builds on existing GAN methods with novel training and loss components.
The paper tackles the problem of face recognition under occlusion by proposing SD-GAN, a generative model that reconstructs missing facial parts while preserving illumination and identity, and it outperforms competing methods with significant improvements in performance.
Certain facial parts are salient (unique) in appearance, which substantially contribute to the holistic recognition of a subject. Occlusion of these salient parts deteriorates the performance of face recognition algorithms. In this paper, we propose a generative model to reconstruct the missing parts of the face which are under occlusion. The proposed generative model (SD-GAN) reconstructs a face preserving the illumination variation and identity of the face. A novel adversarial training algorithm has been designed for a bimodal mutually exclusive Generative Adversarial Network (GAN) model, for faster convergence. A novel adversarial "structural" loss function is also proposed, comprising of two components: a holistic and a local loss, characterized by SSIM and patch-wise MSE. Ablation studies on real and synthetically occluded face datasets reveal that our proposed technique outperforms the competing methods by a considerable margin, even for boosting the performance of Face Recognition.