Results 81 to 90 of about 1,132,388 (176)

Inpainting with style: forcing style coherence to image inpainting with deep image prior

Frontiers in Computer Science
In this paper, we combine the deep image prior (DIP) framework with a style transfer (ST) technique to propose a novel approach (called DIP-ST) for image inpainting of artworks. We specifically tackle cases where the regions to fill in are large.
Elena Morotti, Fabio Merizzi, Davide Evangelista, Pasquale Cascarano   +3 more
doaj   +1 more source

Simultaneous High-Resolution Blind Image Reconstruction and Perturbation Defense

IEEE Access
High-resolution image reconstruction from partial observations plays an important role in modern electronic information systems and has attracted widespread intense attention in both the academic and industrial fields.
Bin Xue, Qinghua Zheng, Zhinan Li, Chunwang Mu, Jungang Yang, Xue Feng, Hongqi Fan, Xiang Li   +7 more
doaj   +1 more source

Parallel Region-Based Deep Residual Networks for Face Hallucination

IEEE Access, 2019
Face hallucination is a super-resolution algorithm specially designed to improve the resolution and quality of low-resolution (LR) input face images. Although a deep neural network offers an end-to-end mapping from LR to high-resolution (HR) images, most
Tao Lu, Xiaohui Hao, Yanduo Zhang, Kai Liu, Zixiang Xiong   +4 more
doaj   +1 more source

DPDU-Net: Double Prior Deep Unrolling Network for Pansharpening

Remote Sensing
The objective of the pansharpening task is to integrate multispectral (MS) images with low spatial resolution (LR) and to integrate panchromatic (PAN) images with high spatial resolution (HR) to generate HRMS images.
Yingxia Chen, Yuqi Li, Tingting Wang, Yan Chen, Faming Fang   +4 more
doaj   +1 more source

The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior. [PDF]

Proc IEEE Int Conf Comput Vis, 2023
Liu Y, Li J, Yunkui Pang, Nie D, Yap PT.
europepmc   +1 more source

Image reconstruction of multispectral sparse sampling photoacoustic tomography based on deep algorithm unrolling

Photoacoustics
Photoacoustic tomography (PAT), as a novel medical imaging technology, provides structural, functional, and metabolism information of biological tissue in vivo.
Jia Ge, Zongxin Mo, Shuangyang Zhang, Xiaoming Zhang, Yutian Zhong, Zhaoyong Liang, Chaobin Hu, Wufan Chen, Li Qi   +8 more
doaj   +1 more source

Unsupervised deep learning method for single image super-resolution of the thick pinhole imaging system using deep image prior

Nuclear Engineering and Technology
Thick pinhole imaging system is widely used for diagnosing intense pulsed radiation sources. However, owing to the trade-off among spatial resolution, field of view (FOV) and signal-to-noise ratio (SNR), the imaging system normally falls short in ...
Guoguang Li, Liang Sheng, Baojun Duan, Yang Li, Dongwei Hei, Qingzi Xing   +5 more
doaj   +1 more source

Deep image prior inpainting of ancient frescoes in the Mediterranean Alpine arc

Heritage Science
The unprecedented success of image reconstruction approaches based on deep neural networks has revolutionised both the processing and the analysis paradigms in several applied disciplines.
Fabio Merizzi, Perrine Saillard, Oceane Acquier, Elena Morotti, Elena Loli Piccolomini, Luca Calatroni, Rosa Maria Dessì   +6 more
doaj   +1 more source

A low-rank deep image prior reconstruction for free-breathing ungated spiral functional CMR at 0.55 T and 1.5 T. [PDF]

MAGMA, 2023
Hamilton JI, Truesdell W, Galizia M, Burris N, Agarwal P, Seiberlich N.   +5 more
europepmc   +1 more source

Deep image prior for limited-angle electron tomography [PDF]

BIO Web of Conferences
Saghi Zineb, Guetaz Laure, David Thomas, Ciuciu Philippe, Saghi Zineb   +4 more
doaj   +1 more source