Article
Neurosciences
Tianshu Song, Leida Li, Hancheng Zhu, Jiansheng Qian
Summary: Current image quality assessment metrics mainly focus on distortion aspects, neglecting the importance of intelligibility for robust quality estimation. This study proposes a new framework for integrating intelligibility to build a highly generalizable image quality model, achieving better performance than state-of-the-art metrics. Feature selection strategy is devised to avoid negative transfer during the fusion process.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Computer Science, Hardware & Architecture
Tian Yuan, Chen Li, Lihua Tian, Guo Li
Summary: Recent years have seen significant progress in image quality assessment, especially in the field of no-reference (NR)-IQA with the development of deep learning. The proposed framework in this study utilizes a range mapping method to enhance the accuracy and generalization of NR-IQA models by mapping existing full-reference (FR)-IQA datasets to NR-IQA datasets. Experimental results using the largest available datasets have confirmed the effectiveness of this approach.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Article
Computer Science, Software Engineering
Wangkang Huang, Zhenyang Zhu, Ligeng Chen, Kentaro Go, Xiaodiao Chen, Xiaoyang Mao
Summary: This paper proposes a novel image recoloring method to compensate for color vision deficiency (CVD) by considering the luminance channel and imposing constraints on the amount of color changes, aiming to enhance contrast and preserve naturalness effectively.
Article
Computer Science, Information Systems
Imran Mehmood, Xinye Shi, Muhammad Usman Khan, Ming Ronnier Luo
Summary: One of the key challenges in tone mapping is to preserve the perceptual quality of high dynamic range (HDR) images when mapping them to standard dynamic range (SDR) displays. This research proposes a new tone mapping operator (TMOz) that leverages CIECAM16 perceptual attributes to achieve more optimal colorfulness reproduction. Both objective and subjective evaluations show that the proposed model outperforms existing TMO algorithms.
Article
Chemistry, Analytical
Ivana Shopovska, Ana Stojkovic, Jan Aelterman, David Van Hamme, Wilfried Philips
Summary: Intelligent driver assistance systems are increasingly popular and have the ability to detect vulnerable road users. However, standard imaging sensors perform poorly in strong illumination contrast conditions. This study focuses on the use of HDR imaging sensors and the need for tone mapping in vehicle perception systems. The proposed DI-TM method achieves the best performance in terms of detection metrics in challenging dynamic range conditions, with a 13% improvement compared to existing methods.
Article
Chemistry, Analytical
Yumei Li, Ningfang Liao, Wenmin Wu, Chenyang Deng, Yasheng Li, Qiumei Fan, Chuanjie Liu
Summary: This study aims to solve the difficulties in displaying high dynamic range (HDR) images on conventional standard display devices. The proposed modified tone-mapping operator (TMO), called iCAM06-m, combines iCAM06 and a multi-scale enhancement algorithm to compensate for saturation and hue drift. Subjective evaluation shows the better performance of iCAM06-m compared to other TMOs, confirming the effectiveness of chroma compensation and multi-scale decomposition. The proposed algorithm overcomes the limitations of other algorithms and is a good candidate for a general purpose TMO.
Review
Engineering, Electrical & Electronic
Xueyu Han, Ishtiaq Rasool Khan, Susanto Rahardja
Summary: Compared to conventional digital imaging, high dynamic range (HDR) image tone mapping technology faithfully reproduces real-world scenes on common displays for enhanced viewing experience. This paper presents a literature review and benchmarks of existing tone mapping methods, providing updated information and paving the way for further developments in the field.
DIGITAL SIGNAL PROCESSING
(2023)
Article
Materials Science, Multidisciplinary
Y. Rao, W. A. Curtin
Summary: In this study, a statistical-mechanics analysis is used to estimate the short-range order (SRO) parameters in solid solution alloys. The analysis assumes pair interactions among atoms at different distances and treats the crystal as a set of independent clusters. The results allow for a fast assessment of likely SRO using estimated or computed inputs for atom-atom interaction energies.
Article
Anatomy & Morphology
Harbinder Singh, Gabriel Cristobal, Saul Blanco, Gloria Bueno, Carlos Sanchez
Summary: This study utilizes high dynamic range imaging to examine the cell structure of diatoms, using multi-scale decomposition and tone mapping methods to extract more details, and evaluates its performance through quantitative and qualitative analysis.
MICROSCOPY RESEARCH AND TECHNIQUE
(2021)
Article
Computer Science, Information Systems
Nam Hoang Nguyen, Tu Van Vo, Chul Lee
Summary: This study introduces an optimized tone-mapping algorithm based on human visual system response model to preserve perceptual responses between HDR and SDR devices, improving image quality. By efficiently solving optimization problems to obtain the optimal tone-mapping curve, experimental results demonstrate the algorithm's superiority in subjective and objective evaluations compared to conventional algorithms.
Article
Physics, Multidisciplinary
Chongchong Jin, Zongju Peng, Wenhui Zou, Fen Chen, Gangyi Jiang, Mei Yu
Summary: This study proposes a no-reference 3D synthesized image quality assessment method based on visual-entropy-guided multi-layer feature analysis, dividing geometric distortions into bottom-up and top-down layers of visual attention, and integrating features from both layers to establish a more visually perceptive quality evaluation model.
Article
Engineering, Electrical & Electronic
Fei Zhou, Guangsen Liao, Jiang Duan, Bozhi Liu, Guoping Qiu
Summary: This paper presents a new region-adaptive self-supervised deep learning technique for HDR image tone mapping. The experimental results demonstrate that this technique achieves excellent performance in preserving overall contrasts, revealing fine details, and eliminating visual artifacts.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2022)
Article
Mathematical & Computational Biology
Ishtiaq Rasool Khan, Susanto Rahardja
Summary: This paper proposes a unified structure that can represent any global tone-mapping algorithm with a small array of coefficients. The unified implementation can convert HDR images and videos to LDR in real time, producing identical LDR images to the original algorithm. It has low and fixed execution time, independent of algorithm and content type.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Pedram Mohammadi, Mahsa T. Pourazad, Panos Nasiopoulos
Summary: The introduction of High Dynamic Range (HDR) technologies has brought about significant visual improvements and opened up new markets for a wide range of industries. Owners of legacy Standard Dynamic Range (SDR) content now have the opportunity to convert their content to the HDR standard and take advantage of the enhanced capabilities of HDR displays. A novel high visual quality video inverse Tone Mapping Operator (iTMO) has been proposed, which is based on human visual perception and employs a segmentation method according to the Human Visual System (HVS) sensitivity, resulting in high visual quality HDR videos.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Software Engineering
Yufan Zhang, Wenbiao Zhou, Jinling Xu
Summary: This paper proposes a dynamic range adjustable inverse tone mapping algorithm based on single LDR image, which combines photoreceptor response and adaptation. It can effectively reconstruct HDR images and reduce distortion.
Article
Geochemistry & Geophysics
Kaiwei Zhang, Dandan Zhu, Xiongkuo Min, Guangtao Zhai
Summary: This paper proposes a novel hyperspectral image (HSI) super-resolution (SR) reconstruction model based on implicit neural representations (INRs), which maps spatial coordinates to corresponding spectral radiance values using a continuous function. The model combines hypernetworks, convolution networks, and periodic spatial encoding to recover high-frequency details. Experimental results demonstrate competitive reconstruction performance compared to state-of-the-art methods, and an ablation study is conducted to evaluate the individual components of the model.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Engineering, Civil
Xiaohong Liu, Zhihao Shi, Zijun Wu, Jun Chen, Guangtao Zhai
Summary: This study proposes an enhanced multi-scale network, GridDehazeNet+, for single image dehazing. The method improves on the traditional Atmosphere Scattering Model and incorporates pre-processing, backbone, and post-processing modules. Domain adaptation and knowledge transfer are used to enhance performance, resulting in superior performance compared to existing methods.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Yizhe Zhang, Wen He, Dazhi He, Yin Xu, Yunfeng Guan, Wenjun Zhang
Summary: In this paper, we proposed the use of reconfigurable intelligent surface (RIS) to improve the reception quality in the LDM system, especially in the edge area. By jointly optimizing power control and pairing mechanism using the convex-concave procedure, we addressed the problem of maximizing the minimum SINR. We also explored the high-mobility scenario and used Brownian Motion to model terminal positions and improve the successful reception probability.
IEEE TRANSACTIONS ON BROADCASTING
(2023)
Article
Computer Science, Artificial Intelligence
Shanyan Guan, Jingwei Xu, Michelle Zhang He, Yunbo Wang, Bingbing Ni, Xiaokang Yang
Summary: This research discusses the problem of adapting a human mesh reconstruction model to different domain videos. It proposes an online adaptation method to gradually correct the model bias. The challenges include the lack of 3D annotations and the difficulty of balancing regular frames and hard samples with occlusions or dramatic changes.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Runzhong Wang, Junchi Yan, Xiaokang Yang
Summary: This paper utilizes deep neural networks to learn node and edge features, as well as an affinity model for graph matching. The approach is flexible, capable of handling varying numbers of nodes, and shows state-of-the-art performance on extensive benchmarks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei-Shi Zheng, Xiaokang Yang, Ling Shao
Summary: This paper introduces the importance of learning to re-identify or retrieve a group of people across non-overlapped camera systems in video surveillance. A novel unified framework based on graph neural networks is proposed to simultaneously address group re-id and group-aware person re-id tasks. The framework constructs a context graph to exploit dependencies among group members and utilizes multi-level attention mechanism and self-attention module to extract robust graph-level representations for both tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Zongxi Han, Yutao Liu, Rong Xie, Guangtao Zhai
Summary: This paper reports the dominance of user-generated content in our lives over traditional DSLRs due to new CMOS imaging sensor (CIS) techniques in smartphones. However, zoom photos captured with tiny sensor sizes and fixed focal lengths tend to have grainy details and zigzag textures due to multi-frame stacking and post-sharpening algorithms. To address this issue, a real-world zoom photo database is constructed, and a novel no-reference zoom quality metric that combines sharpness estimation and image naturalness is proposed. Experimental results show that this quality metric outperforms general-purpose and sharpness models in terms of SROCC and PLCC.
Article
Electrochemistry
Wenjun Zhang, Yongzhong Jin, Zhengquan Zhang, Ge Chen, Dongwei Jiang
Summary: In this study, a two-step method was used to prepare a composite anode material consisting of SnS2 nanoparticles and helical carbon nanofibers. The composite anode exhibited superior reversible discharge specific capacity, higher capacity retention rate, and excellent ultra-long cycle capacity. The outstanding electrochemical performance was attributed to the synergistic contribution between the helical carbon nanofibers and SnS2.
ELECTROCHIMICA ACTA
(2023)
Article
Engineering, Electrical & Electronic
Xiaowu Ou, Yin Xu, Hanjiang Hong, Dazhi He, Yiyan Wu, Yihang Huang, Wenjun Zhang
Summary: With the increasing demand for data services, the spectrum has become a valuable resource. The cooperative transmission mechanism, which allows broadcast and unicast to share the same spectrum, can effectively alleviate this issue. A flexible LDM scheme with a variable power injection ratio is proposed to further improve radio resource utilization. Through a DRL-based algorithm, the optimal scheduling scheme is obtained, and the Lyapunov optimization method is applied to convert the problem to a more conducive form for the agent to learn the optimal strategy. Simulation results show significant improvement in system throughput while ensuring the quality of the broadcast service.
IEEE TRANSACTIONS ON BROADCASTING
(2023)
Article
Computer Science, Artificial Intelligence
Qian Li, Chao Xue, Mingming Li, Chun-Guang Li, Chao Ma, Xiaokang Yang
Summary: Proposed a novel approach to discretize and select a proper single-path architecture by formulating it as an architecture game and extracting the architecture with the maximal Nash equilibrium coefficient. Also employed a mini-batch entanglement mechanism based on Gaussian representation to improve efficiency.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yuan Tian, Yichao Yan, Guangtao Zhai, Li Chen, Zhiyong Gao
Summary: The proposed framework, CLSA, for video rescaling addresses the challenges of information loss and local information aggregation by introducing a contrastive learning framework and a selective global aggregation module. Experimental results demonstrate that CLSA achieves state-of-the-art performance on five datasets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Information Systems
Yucheng Zhu, Yunhao Li, Wei Sun, Xiongkuo Min, Guangtao Zhai, Xiaokang Yang
Summary: Image quality assessment is crucial for both end-users and service-providers, and a new blind image quality assessment model is proposed in this study, which includes self-supervised feature learning and self-attention-based feature fusion to achieve remarkable assessment results on in-the-wild images.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Jun Jia, Zhongpai Gao, Dandan Zhu, Xiongkuo Min, Menghan Hu, Guangtao Zhai
Summary: This paper proposes a deep learning-based method for hiding information in videos and transmitting it from screens to cameras while maintaining visual quality. By training a spatio-temporal generator using simulated data and using a distortion network to simulate real-world imaging, the hidden information in videos can be extracted by cameras without impacting the visual quality. This method has the potential for wide application in fields such as advertisement, entertainment, and education.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Jian Jin, Xingxing Zhang, Lili Meng, Weisi Lin, Jie Liang, Huaxiang Zhang, Yao Zhao
Summary: In this paper, an auto-weighted layer representation based view synthesis distortion estimation model is proposed, which calculates sub-synthesis distortion and learns a nonlinear mapping function to obtain the associated weights. It can efficiently and accurately estimate the view synthesis distortion.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Jingwen Hou, Weisi Lin, Guanghui Yue, Weide Liu, Baoquan Zhao
Summary: Personalized image aesthetics assessment aims to estimate aesthetic experiences based on individual preferences. This research proposes a method that directly estimates personalized aesthetic experiences from the interaction between image contents and user preferences, without the need for prior knowledge on generic aesthetics assessment. Extensive experiments show that the proposed method outperforms previous personalized methods and generic methods in terms of both personalized and generic aesthetics assessment.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)