Recently, self-supervised neural networks have shown excellent image denoising
performance. However, current dataset free methods are either computationally expensive …

Single image defocus deblurring (SIDD) is a challenging task due to the spatially-varying
nature of defocus blur, characterized by per-pixel point spread functions (PSFs). Existing …

How to effectively explore multi-scale representations of rain streaks is important for image
deraining. In contrast to existing Transformer-based methods that depend mostly on single …

Abstract We introduce Functional Diffusion Processes (FDPs), which generalize score-
based diffusion models to infinite-dimensional function spaces. FDPs require a new …

Recently, deep learning has been introduced to solve important medical image
reconstruction problems such as sparse-view CT reconstruction. However, the developed …

Since higher-order tensors are naturally suitable for representing multi-dimensional data in
real-world, eg, color images and videos, low-rank tensor representation has become one of …

We introduce ICE-TIDE, a method for cryogenic electron tomography (cryo-ET) that
simultaneously aligns observations and reconstructs a high-resolution volume. The …

We propose using a coordinate network decoder for the task of super-resolution in MRI. The
continuous signal representation of coordinate networks enables this approach to be scale …

Nonlocal self-similarity (NSS) is an important prior that has been successfully applied in
multi-dimensional data processing tasks, eg, image and video recovery. However, existing …

This dissertation presents innovative methods to enhance assistive technologies for
individuals with visual impairment, focusing on improving answer grounding accuracy in …