Learning-based single image super-resolution (SISR) methods are continuously showing
superior effectiveness and efficiency over traditional model-based methods, largely due to …

As the state-of-the-art machine learning methods in many fields rely on larger datasets,
storing datasets and training models on them become significantly more expensive. This …

Real-world image noise removal is a long-standing yet very challenging task in computer
vision. The success of deep neural network in denoising stimulates the research of noise …

Due to the fast inference and good performance, discriminative learning methods have been
widely studied in image denoising. However, these methods mostly learn a specific model …

The discriminative model learning for image denoising has been recently attracting
considerable attentions due to its favorable denoising performance. In this paper, we take …

Many state-of-the-art image restoration approaches do not scale well to larger images, such
as megapixel images common in the consumer segment. Computationally expensive …

Achieving fusion of deep learning with combinatorial algorithms promises transformative
changes to artificial intelligence. One possible approach is to introduce combinatorial …

We explore a class of end-to-end learnable models wherein data processing nodes (or
network layers) are defined in terms of desired behavior rather than an explicit forward …

Achieving fusion of deep learning with combinatorial algorithms promises transformative
changes to artificial intelligence. One possible approach is to introduce combinatorial …

Abstract" Energy” models for continuous domains can be applied to many problems, but
often suffer from high computational expense in training, due to the need to repeatedly …