Results 71 to 80 of about 4,876 (175)

Light Field Blind Motion Deblurring

, 2017
We study the problem of deblurring light fields of general 3D scenes captured under 3D camera motion and present both theoretical and practical contributions.
Ng, Ren, Ramamoorthi, Ravi, Srinivasan, Pratul P.   +2 more
core   +1 more source

DAVIDE: Depth-Aware Video Deblurring

Video deblurring aims at recovering sharp details from a sequence of blurry frames. Despite the proliferation of depth sensors in mobile phones and the potential of depth information to guide deblurring, depth-aware deblurring has received only limited attention.
German F. Torres, Jussi Kalliola, Soumya Tripathy, Erman Acar, Joni-Kristian Kämäräinen   +4 more
openaire   +2 more sources

Fourier‐Based Action Recognition for Wildlife Behavior Quantification with Event Cameras

Advanced Intelligent Systems, Volume 7, Issue 2, February 2025.
This article investigates the detection of oscillatory motion in nature, such as in a penguin colony in Antarctica, by combining neuromorphic cameras with frequency‐domain techniques. The pixels of the camera capture the oscillating patterns only when the animals move, even in low light conditions, helping biologist understand better their behavior in ...
Friedhelm Hamann, Suman Ghosh, Ignacio Juárez Martínez, Tom Hart, Alex Kacelnik, Guillermo Gallego   +5 more
wiley   +1 more source

Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications

, 2019
Networked video applications, e.g., video conferencing, often suffer from poor visual quality due to unexpected network fluctuation and limited bandwidth.
Cheng, Ming, Lu, Ming, Ma, Zhan, Pu, Shiliang, Shen, Qiu, Xu, Yiling   +5 more
core   +1 more source

Improving SLAM‐Based Navigation in Flexible Ureteroscopy by Kidney Stone and Surgical Tool Segmentation

Healthcare Technology Letters, Volume 12, Issue 1, January/December 2025.
Navigation in flexible ureteroscopy is challenging due to its dynamic environment. We propose to segment the possible dynamic objects (kidney stones and surgical tools) and use the segmentation mask in the SLAM system to improve its accuracy. ABSTRACT Flexible ureteroscopy is a widely used surgical procedure for diagnosing and treating various urinary ...
Laura Oliva‐Maza, Florian Steidle, Julian Klodmann, Klaus H. Strobl, Arkadiusz Miernik, Rudolph Triebel   +5 more
wiley   +1 more source

The World of Fast Moving Objects

, 2016
The notion of a Fast Moving Object (FMO), i.e. an object that moves over a distance exceeding its size within the exposure time, is introduced. FMOs may, and typically do, rotate with high angular speed. FMOs are very common in sports videos, but are not
Kotera, Jan, Matas, Jiri, Novotny, Lukas, Rozumnyi, Denys, Sroubek, Filip   +4 more
core   +1 more source

An adaptive lucky imaging method for turbulence‐degraded image restoration

IET Image Processing, Volume 19, Issue 1, January/December 2025.
This study divides turbulence degraded images into regions for processing and proposes an adaptive restoration method that improves efficiency. In addition, this study proposes a restoration method that combines lucky imaging and generative adversarial networks for areas with high turbulence intensity, which improves the restoration effect.
Pin Lv, Tiezhu Shi, Dongping Den, Mengdi Wang, Qian Liu, Guofeng Wu   +5 more
wiley   +1 more source

Deformable Attention Network for Efficient Space‐Time Video Super‐Resolution

IET Image Processing, Volume 19, Issue 1, January/December 2025.
Recent space‐time video super‐resolution (STVSR) works combine temporal interpolation and spatial super‐resolution in a unified framework, they face challenges in computational complexity across both temporal and spatial dimensions, particularly in achieving accurate intermediate frame interpolation and efficient temporal information utilisation.
Hua Wang, Rapeeporn Chamchong, Phatthanaphong Chomphuwiset, Pornntiwa Pawara   +3 more
wiley   +1 more source

DB-RNN: An RNN for Precipitation Nowcasting Deblurring

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Precipitation nowcasting based on artificial intelligence has garnered widespread attention in the meteorological and computer communities in recent years.
Zhifeng Ma, Hao Zhang, Jie Liu
doaj   +1 more source

More Realistic Edges, Textures, and Colors for Image Non‐Homogeneous Dehazing

IET Image Processing, Volume 19, Issue 1, January/December 2025.
The study proposes an image dehazing method to improve performance in non‐homogeneous and/or dense haze scenarios, ensuring high texture detail and color fidelity in dehazed images.The proposed method employs a multi‐scale encoder–decoder structure to effectively capture finer edge and texture details.
Hairu Guo, Yaning Li, Zhanqiang Huo, Shan Zhao, Yingxu Qiao   +4 more
wiley   +1 more source