Toward high-quality HDR deghosting with conditional diffusion models

Q Yan, T Hu, Y Sun, H Tang, Y Zhu… - … on Circuits and …, 2023‏ - ieeexplore.ieee.org
High Dynamic Range (HDR) images can be recovered from several Low Dynamic Range
(LDR) images by existing Deep Neural Networks (DNNs) techniques. Despite the …

Uncertainty estimation in HDR imaging with Bayesian neural networks

Q Yan, H Wang, Y Ma, Y Liu, W Dong, M Woźniak… - Pattern Recognition, 2024‏ - Elsevier
The goal of high dynamic range (HDR) imaging is to estimate potential high-quality images
from multi-exposed low dynamic range (LDR) inputs. Intuitively, there exist various possible …

[PDF][PDF] Deep high dynamic range imaging of dynamic scenes.

NK Kalantari, R Ramamoorthi - ACM Trans. Graph., 2017‏ - people.engr.tamu.edu
Standard digital cameras typically take images with under/overexposed regions because of
their sensors' limited dynamic range. The most common way to capture high dynamic range …

Alike: Accurate and lightweight keypoint detection and descriptor extraction

X Zhao, X Wu, J Miao, W Chen… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Existing methods detect the keypoints in a non-differentiable way, therefore they can not
directly optimize the position of keypoints through back-propagation. To address this issue …

Robust multi-exposure image fusion: a structural patch decomposition approach

K Ma, H Li, H Yong, Z Wang, D Meng… - IEEE Transactions on …, 2017‏ - ieeexplore.ieee.org
We propose a simple yet effective structural patch decomposition approach for multi-
exposure image fusion (MEF) that is robust to ghosting effect. We decompose an image …

The state of the art in HDR deghosting: A survey and evaluation

OT Tursun, AO Akyüz, A Erdem… - Computer Graphics …, 2015‏ - Wiley Online Library
Obtaining a high quality high dynamic range (HDR) image in the presence of camera and
object movement has been a long‐standing challenge. Many methods, known as HDR …

Deep HDR imaging via a non-local network

Q Yan, L Zhang, Y Liu, Y Zhu, J Sun… - IEEE Transactions on …, 2020‏ - ieeexplore.ieee.org
One of the most challenging problems in reconstructing a high dynamic range (HDR) image
from multiple low dynamic range (LDR) inputs is the ghosting artifacts caused by the object …

Joint hdr denoising and fusion: A real-world mobile hdr image dataset

S Liu, X Zhang, L Sun, Z Liang… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Mobile phones have become a ubiquitous and indispensable photographing device in our
daily life, while the small aperture and sensor size make mobile phones more susceptible to …

Dual-scale single image dehazing via neural augmentation

Z Li, C Zheng, H Shu, S Wu - IEEE Transactions on Image …, 2022‏ - ieeexplore.ieee.org
Model-based single image dehazing algorithms restore haze-free images with sharp edges
and rich details for real-world hazy images at the expense of low PSNR and SSIM values for …

Detail-enhanced multi-scale exposure fusion

Z Li, Z Wei, C Wen, J Zheng - IEEE Transactions on Image …, 2017‏ - ieeexplore.ieee.org
Multi-scale exposure fusion is an effective image enhancement technique for a high
dynamic range (HDR) scene. In this paper, a new multi-scale exposure fusion algorithm is …