Details

Autor(en) / Beteiligte

• Tej, Akella Ravi
• Sukanta Halder, Shirsendu
• Shandeelya, Arunav Pratap
• Pankajakshan, Vinod

Titel

Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution

Ist Teil von

• 2020 International Joint Conference on Neural Networks (IJCNN), 2020, p.1-8

Ort / Verlag

IEEE

Erscheinungsjahr

2020

Link zum Volltext

• Volltext

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• Single image super-resolution (SISR) is an ill-posed problem with an indeterminate number of valid solutions. Solving this problem with neural networks would require access to extensive experience, either presented as a large training set over natural images or a condensed representation from another pre-trained network. Perceptual loss functions, which belong to the latter category, have achieved breakthrough success in SISR and several other computer vision tasks. While perceptual loss plays a central role in the generation of photo-realistic images, it also produces undesired pattern artifacts in the super-resolved outputs. In this paper, we show that the root cause of these pattern artifacts can be traced back to a mismatch between the pre-training objective of perceptual loss and the super-resolution objective. To address this issue, we propose to augment the existing perceptual loss formulation with a novel content loss function that uses the latent features of a discriminator network to filter the unwanted artifacts across several levels of adversarial similarity. Further, our modification has a stabilizing effect on non-convex optimization in adversarial training. The proposed approach offers notable gains in perceptual quality based on an extensive human evaluation study and a competent reconstruction fidelity when tested on objective evaluation metrics.