Image Restoration with Deep Generative Models

• Published in: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6772 - 6776
• Main Authors: Yeh, Raymond A., Lim, Teck Yian, Chen, Chen, Schwing, Alexander G., Hasegawa-Johnson, Mark, Do, Minh N.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2018
• Subjects: deep generative models; Gallium nitride; generative adversarial networks; Generators; Image resolution; Image restoration; Noise reduction; Quantization (signal); Task analysis
• DOI: 10.1109/ICASSP.2018.8462317

Many image restoration problems are ill-posed in nature, hence, beyond the input image, most existing methods rely on a carefully engineered image prior, which enforces some local image consistency in the recovered image. How tightly the prior assumptions are fulfilled has a big impact on the resulting task performance. To obtain more flexibility, in this work, we proposed to design the image prior in a data-driven manner. Instead of explicitly defining the prior, we learn it using deep generative models. We demonstrate that this learned prior can be applied to many image restoration problems using an unified framework.