Related papers: Atmospheric Turbulence Removal with Complex-Valued…
Recovering images from optical interferometric observations is one of the major challenges in the field. Unlike the case of observations at radio wavelengths, in the optical the atmospheric turbulence changes the phases on a very short time…
Super-resolution of turbulence is a term used to describe the prediction of high-resolution snapshots of a flow from coarse-grained observations. This is typically accomplished with a deep neural network and training usually requires a…
A variational model for learning convolutional image atoms from corrupted and/or incomplete data is introduced and analyzed both in function space and numerically. Building on lifting and relaxation strategies, the proposed approach is…
Long distance imaging is subject to the impact of the turbulent atmosphere. This results into geometric distortions and some blur effect in the observed frames. Despite the existence of several turbulence mitigation algorithms in the…
State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. However, most existing methods are based on batch processing and thus need access to…
Video stabilization technique is essential for most hand-held captured videos due to high-frequency shakes. Several 2D-, 2.5D- and 3D-based stabilization techniques are well studied, but to our knowledge, no solutions based on deep neural…
In this technical report, we briefly introduce the solution of our team VIELab-HUST for coded target restoration through atmospheric turbulence in CVPR 2023 UG$^2$+ Track 2.2. In this task, we propose an efficient multi-stage framework to…
Video-based behavior recognition is essential in fields such as public safety, intelligent surveillance, and human-computer interaction. Traditional 3D Convolutional Neural Network (3D CNN) effectively capture local spatiotemporal features…
Space-time video super-resolution (STVSR) aims to increase the spatial and temporal resolutions of low-resolution and low-frame-rate videos. Recently, deformable convolution based methods have achieved promising STVSR performance, but they…
Atmospheric tomography, the problem of reconstructing atmospheric turbulence profiles from wavefront sensor measurements, is an integral part of many adaptive optics systems used for enhancing the image quality of ground-based telescopes.…
Fluid turbulence is characterized by strong coupling across a broad range of scales. Furthermore, besides the usual local cascades, such coupling may extend to interactions that are non-local in scale-space. As such the computational…
Modern machine-learning techniques are generally considered data-hungry. However, this may not be the case for turbulence as each of its snapshots can hold more information than a single data file in general machine-learning settings. This…
Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of…
We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera. Our method leverages the motion differences…
The problem of classifying turbulent environments from partial observation is key for some theoretical and applied fields, from engineering to earth observation and astrophysics, e.g. to precondition searching of optimal control policies in…
Motion blur in scene text images severely impairs readability and hinders the reliability of computer vision tasks, including autonomous driving, document digitization, and visual information retrieval. Conventional deblurring approaches…
We present a new data-driven video inpainting method for recovering missing regions of video frames. A novel deep learning architecture is proposed which contains two sub-networks: a temporal structure inference network and a spatial detail…
In this technical report, we briefly introduce the solution of our team ''summer'' for Atomospheric Turbulence Mitigation in UG$^2$+ Challenge in CVPR 2022. In this task, we propose a unified end-to-end framework to reconstruct a high…
High-fidelity modeling of turbulent flows is one of the major challenges in computational physics, with diverse applications in engineering, earth sciences and astrophysics, among many others. The rising popularity of high-fidelity…
Synthetic turbulence models are a useful tool that provide realistic representations of turbulence, necessary to test theoretical results, to serve as background fields in some numerical simulations, and to test analysis tools. Models of 1D…