AIM 2020: Scene relighting and illumination estimation challenge
We review the AIM 2020 challenge on virtual image relighting and illumination estimation.
This paper presents the novel VIDIT dataset used in the challenge and the different …
This paper presents the novel VIDIT dataset used in the challenge and the different …
NTIRE 2021 depth guided image relighting challenge
Image relighting is attracting increasing interest due to its various applications. From a
research perspective, image relighting can be exploited to conduct both image …
research perspective, image relighting can be exploited to conduct both image …
Stochastic frequency masking to improve super-resolution and denoising networks
Super-resolution and denoising are ill-posed yet fundamental image restoration tasks. In
blind settings, the degradation kernel or the noise level are unknown. This makes restoration …
blind settings, the degradation kernel or the noise level are unknown. This makes restoration …
A model-driven network for guided image denoising
Guided image denoising recovers clean target images by fusing guidance images and noisy
target images. Several deep neural networks have been designed for this task, but they are …
target images. Several deep neural networks have been designed for this task, but they are …
Focus measurement in color space for shape from focus systems
Shape from Focus (SFF) has been studied extensively in computer vision for 3D shape and
depth recovery. The first stage in SFF methods is to compute the focus value of every pixel …
depth recovery. The first stage in SFF methods is to compute the focus value of every pixel …
Modified color CCD moiré method and its application in optical distortion correction
J Zhao, Y Hou, Z Liu, H Xie, S Liu - Precision Engineering, 2020 - Elsevier
The characterization and correction of lens distortion is an important part of optical
measurement. This work analyzes the formation mechanism of color fringes and …
measurement. This work analyzes the formation mechanism of color fringes and …
Simultaneous demosaicing and chromatic aberration correction through spectral reconstruction
B Llanos, YH Yang - 2020 17th Conference on Computer and …, 2020 - ieeexplore.ieee.org
We present an algorithm for simultaneously demosaicing digital images, and correcting
chromatic aberration, that operates in terms of spectral bands. Chromatic aberration …
chromatic aberration, that operates in terms of spectral bands. Chromatic aberration …
Solving the depth ambiguity in single-perspective images
M El Helou, M Shahpaski, S Süsstrunk - OSA Continuum, 2019 - opg.optica.org
Scene depth estimation is gaining importance as more and more AR/VR and robot vision
applications are developed. Conventional depth-from-defocus techniques can passively …
applications are developed. Conventional depth-from-defocus techniques can passively …
Chromatic aberration correction and spectral reconstruction from colour images
B Llanos - 2019 - era.library.ualberta.ca
We present an algorithm for simultaneously demosaicing digital images, and correcting
chromatic aberration, that operates in a latent space of spectral bands. Light refraction by a …
chromatic aberration, that operates in a latent space of spectral bands. Light refraction by a …
Learning degraded image classification with restoration data fidelity
X Lin - arXiv preprint arXiv:2101.09606, 2021 - arxiv.org
Learning-based methods especially with convolutional neural networks (CNN) are
continuously showing superior performance in computer vision applications, ranging from …
continuously showing superior performance in computer vision applications, ranging from …