Face super-resolution by learning multi-view texture compensation
Y Wang, T Lu, R Xu, Y Zhang - … 2020, Daejeon, South Korea, January 5–8 …, 2020 - Springer
… SR is widely used in video surveillance, face recognition, entertainment, etc. In general, …
person has 14 face images. We select two images for each person, one for the frontal image and …
person has 14 face images. We select two images for each person, one for the frontal image and …
Multi-view texture learning for face super-resolution
Y Wang, T Lu, F Yao, Y Wu, Y Zhang - IEICE TRANSACTIONS on …, 2021 - search.ieice.org
… face images is challenging. In order to effectively solve the above problems, we propose a
novel face SR network based on multi-view face images, … of unrestricted face recognition in …
novel face SR network based on multi-view face images, … of unrestricted face recognition in …
Towards a super-resolution based approach for improved face recognition in low resolution environment
N Singh, SS Rathore, S Kumar - Multimedia Tools and Applications, 2022 - Springer
… aims to enhance the resolution of an image to generate a desirable high-resolution one. …
-time face recognition approach that uses super-resolution to improve images and detect faces …
-time face recognition approach that uses super-resolution to improve images and detect faces …
Detailed 3D human body reconstruction from multi-view images combining voxel super-resolution and learned implicit representation
Z Li, M Oskarsson, A Heyden - Applied Intelligence, 2022 - Springer
… method to reconstruct detailed 3D human body from multi-view images combining Voxel
Super-Resolution … -stage hourglass networks from the multi-view images. Then, taking the low …
Super-Resolution … -stage hourglass networks from the multi-view images. Then, taking the low …
Perspective registration and multi-frame super-resolution of license plates in surveillance videos
G Guarnieri, M Fontani, F Guzzi, S Carrato… - Forensic Science …, 2021 - Elsevier
… In the present paper, we will deal with multi-view projection transform that can be
described by plane homographies (Hartley and Zisserman, 2004). For a projective transform, …
described by plane homographies (Hartley and Zisserman, 2004). For a projective transform, …
Superfront: From low-resolution to high-resolution frontal face synthesis
… Furthermore, we integrate a super-resolution (SR) side-view … face recognition accuracy
on synthesized frontal images. … the benefits of the multi-view fusion method, SR-integrated …
on synthesized frontal images. … the benefits of the multi-view fusion method, SR-integrated …
[HTML][HTML] Feature super-resolution based facial expression recognition for multi-scale low-resolution images
… images or carry ISR and FER jointly. Here we focus on static images FER and super-resolution
methods. … Cause the face detection failed in 24 images, we assign random uniform …
methods. … Cause the face detection failed in 24 images, we assign random uniform …
A multi-view references image super-resolution framework for generating the large-FOV and high-resolution image
… multi-view reference image super-resolution framework (MVRefSR) is proposed to generate
a large-FOV HR image, utilizing N small-FOV HR reference images … -FOV LR image I LR , as …
a large-FOV HR image, utilizing N small-FOV HR reference images … -FOV LR image I LR , as …
Image super-resolution via multi-view information fusion networks
… CNN) have achieved substantial advantages for single image super resolution (SISR). However,
as … network structure for super-resolution which adopts the multi-view information fusion …
as … network structure for super-resolution which adopts the multi-view information fusion …
Geometry-aware reference synthesis for multi-view image super-resolution
… HR multi-view images face substantial … Multi-View Image Super-Resolution (MVISR) task,
which increases the resolution of multi-view images by using all low-resolution (LR) multi-view …
which increases the resolution of multi-view images by using all low-resolution (LR) multi-view …