2,435 Hits in 5.8 sec

Statistically and perceptually motivated nonlinear image representation

Siwei Lyu, Eero P. Simoncelli, Bernice E. Rogowitz, Thrasyvoulos N. Pappas, Scott J. Daly
2007 Human Vision and Electronic Imaging XII  
Finally, we probe the statistical and perceptual advantages of this image representation, examining robustness to added noise, rate-distortion behavior, and artifact-free local contrast enhancement.  ...  We develop a reliable and efficient iterative procedure for inverting the divisive transformation.  ...  Last, we demonstrate the promise of this representation in terms of perceptual resilience to noise contamination, image compression, and adaptive enhancement of local contrast.  ... 
doi:10.1117/12.720848 dblp:conf/hvei/LyuS07 fatcat:jloaqzxtqvhblpc73fh7z5crxe

A Linear Programming Approach for Optimal Contrast-Tone Mapping

Xiaolin Wu
2011 IEEE Transactions on Image Processing  
This paper proposes a novel algorithmic approach of image enhancement via optimal contrast-tone mapping (OCTM).  ...  This new constrained optimization approach for image enhancement is general, and the user can add and fine tune the constraints to achieve desired visual effects.  ...  Analogously to global and local histogram equalization, OCTM can be performed based on either global or local statistics.  ... 
doi:10.1109/tip.2010.2092438 pmid:21078574 fatcat:ctlir6ilwvexrm7otbdsn3pnwq

Joint Learning of Super-Resolution and Perceptual Image Enhancement for Single Image

Yifei Xu, Nuo Zhang, Li Li, Genan Sang, Yuewan Zhang, Zhengyang Wang, Pingping Wei
2021 IEEE Access  
Since global enhancement adjustment methods work for all the pixels, they always over-/under-enhance local regions in most cases.  ...  For the purpose of enhancing perceptual quality, color loss is incorporated to solve our joint SR-PIE problem.  ... 
doi:10.1109/access.2021.3068861 fatcat:el7xciykonbihhmpel3vge3uqy

NIMA: Neural Image Assessment

Hossein Talebi, Peyman Milanfar
2018 IEEE Transactions on Image Processing  
Our resulting network can be used to not only score images reliably and with high correlation to human perception, but also to assist with adaptation and optimization of photo editing/enhancement algorithms  ...  All this is done without need for a "golden" reference image, consequently allowing for single-image, semantic- and perceptually-aware, no-reference quality assessment.  ...  Pascal Getreuer for valuable discussions and helpful advice on approximation of score distributions.  ... 
doi:10.1109/tip.2018.2831899 pmid:29994025 fatcat:acw7dcpcfng5rmkxphai63ihwa

MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification [article]

Yajun Gao, Tengfei Liang, Yi Jin, Xiaoyan Gu, Wu Liu, Yidong Li, Congyan Lang
2021 arXiv   pre-print
Moreover, to increase the difference between cross-modality distance and class distance, we introduce a novel cross-modality contrastive-center (CMCC) loss into the modality-joint constraints in the common  ...  To solve it, in this paper, we present a novel multi-feature space joint optimization (MSO) network, which can learn modality-sharable features in both the single-modality space and the common space.  ...  ACKNOWLEDGMENTS This work was supported by the National Natural Science Foundation of China (Nos.61972030), and the Grapevine Scholar Plan of JD AI Research.  ... 
arXiv:2110.11264v1 fatcat:xqvyhua6lnajdm766xqqf7xcj4

Table of Contents

2020 IEEE Transactions on Computational Imaging  
Marek1586 Machine Learning based Computational Image Formation Joint Demosaicing and Super-Resolution (JDSR): Network Design and Perceptual Optimization . . . . . . . . . . . . . . . . . . . . . . . .  ...  Chan 1571 Building Stereoscopic Zoomer via Global and Local Warping Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tci.2021.3054280 fatcat:7se3scatcrcutgat3tpk5mz2nm

Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation [article]

Yueming Jin, Yang Yu, Cheng Chen, Zixu Zhao, Pheng-Ann Heng, Danail Stoyanov
2022 arXiv   pre-print
A multi-source contrast training objective is developed to group the pixel embeddings across videos with the ground-truth guidance, which is crucial for learning the global property of the whole data.  ...  A joint space-time window shift scheme is proposed to efficiently aggregate these two cues into each pixel embedding.  ...  Two types of relations are explored to boost segmentation by gradually capturing the global context of surgical videos.  ... 
arXiv:2203.15251v1 fatcat:e75vcfoz3jbx7nmknb4akhudlu

Progressive Joint Low-light Enhancement and Noise Removal for Raw Images [article]

Yucheng Lu, Seung-Won Jung
2021 arXiv   pre-print
The coefficient estimation branch works in a low-resolution space and predicts the coefficients for enhancement via bilateral learning, whereas the joint enhancement and denoising branch works in a full-resolution  ...  space and progressively performs joint enhancement and denoising.  ...  Sean Moran for helping reproduce their results and strengthen this paper through constructive discussions.  ... 
arXiv:2106.14844v3 fatcat:ixovvbu5wjdzzij7ktq54ny6la

An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement [article]

Dario Fuoli, Zhiwu Huang, Danda Pani Paudel, Luc Van Gool, Radu Timofte
2020 arXiv   pre-print
In particular, our framework introduces new recurrent cells that consist of interleaved local and global modules for implicit integration of spatial and temporal information.  ...  Efficient training is accomplished by introducing one single discriminator that learns the joint distribution of source and target domain simultaneously.  ...  Local/Global Module (LGM): Our introduced LGM block for efficient interleaved local and global information processing consists of two convolutional blocks.  ... 
arXiv:2012.13033v1 fatcat:e4u5gu7oh5b7xaxmxxiofhvevq

A Survey on Perceptually Optimized Video Coding [article]

Yun Zhang, Linwei Zhu, Gangyi Jiang, Sam Kwong, C.-C.Jay Kuo
2021 arXiv   pre-print
However, the amount of video data increases exponentially and requires high efficiency video compression for storage and network transmission.  ...  , filtering and enhancement.  ...  for stereo, and gradient boosting decision tree was used for feature selection and fusion.  ... 
arXiv:2112.12284v1 fatcat:i32kehwyzbgu5ffhok3p5qxyum

Visual saliency guided perceptual adaptive quantization based on HEVC intra-coding for planetary images

Yuqi Dai, Changbin Xue, Li Zhou, Zhaoqing Pan
2022 PLoS ONE  
Furthermore, based on the saliency map, a CTU level QP adjustment technique combining global saliency contrast and local saliency perception is exploited to realize a flexible and adaptive bit allocation  ...  Applicable for planetary images, this study proposes a perceptual adaptive quantization technique based on Convolutional Neural Network (CNN) and High Efficiency Video Coding (HEVC).  ...  represents the global saliency contrast-driven weighted quantization component for a CTU, and QP sal_offset indicates the perceptual quantization component based on local saliency perception.  ... 
doi:10.1371/journal.pone.0263729 pmid:35139132 pmcid:PMC8827453 fatcat:af4mpsjcgfe6phifynqobsyyei

On Coupling Classification and Super-Resolution in Remote Urban Sensing: An Integrated Deep Learning Approach

Yang Zhang, Ruohan Zong, Lanyu Shang, Dong Wang
2022 IEEE Transactions on Geoscience and Remote Sensing  
and super-resolution) to concurrently boost the performance of both the tasks.  ...  urban environment for intelligent city monitoring, planning, and management.  ...  Therefore, our SCLearn jointly uses both the enhanced global features and local details to effectively boost the land usage classification accuracy. .  ... 
doi:10.1109/tgrs.2022.3169703 fatcat:6gechw66f5hlfmntpdgwwrfn4m

Multi Kernel Boosting Algorithm for Image Segmentation and Analysis

Sanjuna Sq
2017 IJARCCE  
First, a novel regional descriptor consisting of regional self-information, regional variance, and regional contrast on a number of features with local, global, and border context is proposed to describe  ...  The bootstrap learning algorithm for salient object detection in which both weak and strong models are exploited.  ...  from a joint optimization process?  ... 
doi:10.17148/ijarcce.2017.6681 fatcat:c2dtizdfabcy3pemlkn6duej4a

Warm-cool color-based high-speed decolorization: an empirical approach for tone mapping applications

Prasoon Ambalathankandy, Yafei Ou, Masayuki Ikebe
2021 Journal of Electronic Imaging (JEI)  
Third, we demonstrate that an effective luminance distribution can be achieved using our algorithm by using global and local tone mapping applications.  ...  Second, our optimal color conversion method produces luminance in images that are comparable to other state of the art methods which we quantified using the objective metrics (E-score and C2G-SSIM) and  ...  • We demonstrate effective luminance distribution by performing objective evaluations and a subjective user study. There are many well defined methods to convert any color image to a grayscale image.  ... 
doi:10.1117/1.jei.30.4.043026 fatcat:kt7kr7whcvbhfia2dywgoh5fhu

Deep Learning-based Face Super-Resolution: A Survey [article]

Junjun Jiang, Chenyang Wang, Xianming Liu, Jiayi Ma
2021 arXiv   pre-print
Fourth, we evaluate the performance of some state-of-the-art methods. Fifth, joint FSR and other tasks, and FSR-related applications are roughly introduced.  ...  Face super-resolution (FSR), also known as face hallucination, which is aimed at enhancing the resolution of low-resolution (LR) face images to generate high-resolution (HR) face images, is a domain-specific  ...  global and local methods for capturing global structure and recovering local details simultaneously.  ... 
arXiv:2101.03749v2 fatcat:q56d2mpn4rfyzmi5fo36d2ecja
« Previous Showing results 1 — 15 out of 2,435 results