Related papers: Multi-bin Trainable Linear Unit for Fast Image Res…
Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions. Various new activation functions and improvements on…
In this work, we study the problem of non-blind image deconvolution and propose a novel recurrent network architecture that leads to very competitive restoration results of high image quality. Motivated by the computational efficiency and…
Conventionally, image denoising and high-level vision tasks are handled separately in computer vision. In this paper, we cope with the two jointly and explore the mutual influence between them. First we propose a convolutional neural…
Optical neural networks are emerging as powerful machine learning and information processing tools because of their potential advantages in speed and energy efficiency. The training methods of these physical models, however, remain…
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 for each noise level, and require multiple models for…
Magnetic resonance imaging has been widely applied in clinical diagnosis, however, is limited by its long data acquisition time. Although imaging can be accelerated by sparse sampling and parallel imaging, achieving promising reconstruction…
All-in-one image restoration tasks are becoming increasingly important, especially for ultra-high-definition (UHD) images. Existing all-in-one UHD image restoration methods usually boost the model's performance by introducing prompt or…
Deep neural networks trained end-to-end to map a measurement of a (noisy) image to a clean image perform excellent for a variety of linear inverse problems. Current methods are only trained on a few hundreds or thousands of images as…
Successive linear transforms followed by nonlinear "activation" functions can approximate nonlinear functions to arbitrary precision given sufficient layers. The number of necessary layers is dependent on, in part, by the nature of the…
In this article, we address the challenges of image super-resolution and noise reduction, which are crucial for enhancing the quality of images derived from low-resolution or noisy data. We compared and assessed several approaches for…
We propose the Moderate Adaptive Linear Unit (MoLU), a novel activation function for deep neural networks, defined analytically as: f(x)=x \times (1+tanh(x))/2. MoLU combines mathematical elegance with empirical effectiveness, exhibiting…
Low-count PET is an efficient way to reduce radiation exposure and acquisition time, but the reconstructed images often suffer from low signal-to-noise ratio (SNR), thus affecting diagnosis and other downstream tasks. Recent advances in…
Many industrial and real life problems exhibit highly nonlinear periodic behaviors and the conventional methods may fall short of finding their analytical or closed form solutions. Such problems demand some cutting edge computational tools…
The choice of activation functions is crucial for modern deep neural networks. Popular hand-designed activation functions like Rectified Linear Unit(ReLU) and its variants show promising performance in various tasks and models. Swish, the…
The great advances of learning-based approaches in image processing and computer vision are largely based on deeply nested networks that compose linear transfer functions with suitable non-linearities. Interestingly, the most frequently…
In the field of fusing multi-spectral and panchromatic images (Pan-sharpening), the impressive effectiveness of deep neural networks has been recently employed to overcome the drawbacks of traditional linear models and boost the fusing…
Image denoising is a classical problem in low level computer vision. Model-based optimization methods and deep learning approaches have been the two main strategies for solving the problem. Model-based optimization methods are flexible for…
Modulo-Imaging (MI) offers a promising alternative for expanding the dynamic range of images by resetting the signal intensity when it reaches the saturation level. Subsequently, high-dynamic range (HDR) modulo imaging requires a recovery…
Previous work has shown that it is possible to train deep neural networks with low precision weights and activations. In the extreme case it is even possible to constrain the network to binary values. The costly floating point…
Non-linear activation functions, e.g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs). Due to the complex non-linear characteristic of samples, the objective of those activation functions is to project samples…