Search

Your search keyword '"Zheng, Yuxin"' showing total 1,711 results
Start Over Author "Zheng, Yuxin"
1,711 results on '"Zheng, Yuxin"'

1. OmniSR: Shadow Removal under Direct and Indirect Lighting

Author

Xu, Jiamin, Li, Zelong, Zheng, Yuxin, Huang, Chenyu, Gu, Renshu, Xu, Weiwei, and Xu, Gang

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Shadows can originate from occlusions in both direct and indirect illumination. Although most current shadow removal research focuses on shadows caused by direct illumination, shadows from indirect illumination are often just as pervasive, particularly in indoor scenes. A significant challenge in removing shadows from indirect illumination is obtaining shadow-free images to train the shadow removal network. To overcome this challenge, we propose a novel rendering pipeline for generating shadowed and shadow-free images under direct and indirect illumination, and create a comprehensive synthetic dataset that contains over 30,000 image pairs, covering various object types and lighting conditions. We also propose an innovative shadow removal network that explicitly integrates semantic and geometric priors through concatenation and attention mechanisms. The experiments show that our method outperforms state-of-the-art shadow removal techniques and can effectively generalize to indoor and outdoor scenes under various lighting conditions, enhancing the overall effectiveness and applicability of shadow removal methods.

Published
2024

2. NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results

Author

Liu, Xiaoning, Wu, Zongwei, Li, Ao, Vasluianu, Florin-Alexandru, Zhang, Yulun, Gu, Shuhang, Zhang, Le, Zhu, Ce, Timofte, Radu, Jin, Zhi, Wu, Hongjun, Wang, Chenxi, Ling, Haitao, Cai, Yuanhao, Bian, Hao, Zheng, Yuxin, Lin, Jing, Yuille, Alan, Shao, Ben, Guo, Jin, Liu, Tianli, Wu, Mohao, Feng, Yixu, Hou, Shuo, Lin, Haotian, Zhu, Yu, Wu, Peng, Dong, Wei, Sun, Jinqiu, Zhang, Yanning, Yan, Qingsen, Zou, Wenbin, Yang, Weipeng, Li, Yunxiang, Wei, Qiaomu, Ye, Tian, Chen, Sixiang, Zhang, Zhao, Zhao, Suiyi, Wang, Bo, Luo, Yan, Zuo, Zhichao, Wang, Mingshen, Wang, Junhu, Wei, Yanyan, Sun, Xiaopeng, Gao, Yu, Huang, Jiancheng, Chen, Hongming, Chen, Xiang, Tang, Hui, Chen, Yuanbin, Zhou, Yuanbo, Dai, Xinwei, Qiu, Xintao, Deng, Wei, Gao, Qinquan, Tong, Tong, Li, Mingjia, Hu, Jin, He, Xinyu, Guo, Xiaojie, Sabarinathan, Uma, K, Sasithradevi, A, Bama, B Sathya, Roomi, S. Mohamed Mansoor, Srivatsav, V., Wang, Jinjuan, Sun, Long, Chen, Qiuying, Shao, Jiahong, Zhang, Yizhi, Conde, Marcos V., Feijoo, Daniel, Benito, Juan C., García, Alvaro, Lee, Jaeho, Kim, Seongwan, A, Sharif S M, Khujaev, Nodirkhuja, Tsoy, Roman, Murtaza, Ali, Khairuddin, Uswah, Faudzi, Ahmad 'Athif Mohd, Malagi, Sampada, Joshi, Amogh, Akalwadi, Nikhil, Desai, Chaitra, Tabib, Ramesh Ashok, Mudenagudi, Uma, Lian, Wenyi, Lian, Wenjing, Kalyanshetti, Jagadeesh, Aralikatti, Vijayalaxmi Ashok, Yashaswini, Palani, Upasi, Nitish, Hegde, Dikshit, Patil, Ujwala, C, Sujata, Yan, Xingzhuo, Hao, Wei, Fu, Minghan, choksy, Pooja, Sarvaiya, Anjali, Upla, Kishor, Raja, Kiran, Yan, Hailong, Zhang, Yunkai, Li, Baiang, Zhang, Jingyi, and Zheng, Huan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective network design or solution capable of generating brighter, clearer, and visually appealing results when dealing with a variety of conditions, including ultra-high resolution (4K and beyond), non-uniform illumination, backlighting, extreme darkness, and night scenes. A notable total of 428 participants registered for the challenge, with 22 teams ultimately making valid submissions. This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field., Comment: NTIRE 2024 Challenge Report

Published
2024

11. Conversational Swarm Intelligence, a Pilot Study

Author

Rosenberg, Louis, Willcox, Gregg, Schumann, Hans, Bader, Miles, Mani, Ganesh, Sagae, Kokoro, Acharya, Devang, Zheng, Yuxin, Kim, Andrew, and Deng, Jialing

Subjects
Computer Science - Human-Computer Interaction, Computer Science - Neural and Evolutionary Computing, H.5.2, H.1.2
Abstract

Conversational Swarm Intelligence (CSI) is a new method for enabling large human groups to hold real-time networked conversations using a technique modeled on the dynamics of biological swarms. Through the novel use of conversational agents powered by Large Language Models (LLMs), the CSI structure simultaneously enables local dialog among small deliberative groups and global propagation of conversational content across a larger population. In this way, CSI combines the benefits of small-group deliberative reasoning and large-scale collective intelligence. In this pilot study, participants deliberating in conversational swarms (via text chat) (a) produced 30% more contributions (p<0.05) than participants deliberating in a standard centralized chat room and (b) demonstrated 7.2% less variance in contribution quantity. These results indicate that users contributed more content and participated more evenly when using the CSI structure., Comment: Pending for conference, Collective Intelligence 2023 (ACM)

Published
2023

14. Binarized Spectral Compressive Imaging

Author

Cai, Yuanhao, Zheng, Yuxin, Lin, Jing, Yuan, Xin, Zhang, Yulun, and Wang, Haoqian

Subjects
Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Existing deep learning models for hyperspectral image (HSI) reconstruction achieve good performance but require powerful hardwares with enormous memory and computational resources. Consequently, these methods can hardly be deployed on resource-limited mobile devices. In this paper, we propose a novel method, Binarized Spectral-Redistribution Network (BiSRNet), for efficient and practical HSI restoration from compressed measurement in snapshot compressive imaging (SCI) systems. Firstly, we redesign a compact and easy-to-deploy base model to be binarized. Then we present the basic unit, Binarized Spectral-Redistribution Convolution (BiSR-Conv). BiSR-Conv can adaptively redistribute the HSI representations before binarizing activation and uses a scalable hyperbolic tangent function to closer approximate the Sign function in backpropagation. Based on our BiSR-Conv, we customize four binarized convolutional modules to address the dimension mismatch and propagate full-precision information throughout the whole network. Finally, our BiSRNet is derived by using the proposed techniques to binarize the base model. Comprehensive quantitative and qualitative experiments manifest that our proposed BiSRNet outperforms state-of-the-art binarization methods and achieves comparable performance with full-precision algorithms. Code and models are publicly available at https://github.com/caiyuanhao1998/BiSCI and https://github.com/caiyuanhao1998/MST, Comment: NeurIPS 2023; The first work to study binarized spectral compressive imaging reconstruction problem

Published
2023

15. Microbiota-mediated reactivation of triclosan oxidative metabolites in colon tissues.

Author

Zhang, Hongna, Sanidad, Katherine, Zhang, Jianan, Wang, Guangqiang, Zhang, Rong, Hu, Chengchen, Lin, Yongfeng, Haggerty, Thomas, Parsonnet, Julie, Zheng, Yuxin, Cai, Zongwei, and Zhang, Guodong

Subjects
Colon, Gut microbiota, Hydroxylation, Metabolism, Triclosan, Mice, Humans, Animals, Triclosan, Cohort Studies, Colon, Gastrointestinal Microbiome, Oxidative Stress
Abstract

Triclosan (TCS) is a widespread antimicrobial agent that is associated with many adverse health outcomes. Its gut toxicity has been attributed to the molecular modifications mediated by commensal microbes, but microbial transformations of TCS derivatives in the gut lumen are still largely unknown. Aromatic hydroxylation is the predominant oxidative metabolism of TCS that linked to its toxicological effects in host tissues. Here, we aimed to reveal the biological fates of hydroxyl-TCS (OH-TCS) in the colon, where intestinal microbes mainly reside. Unlike the profiles generated via host metabolism, OH-TCS species remain unconjugated in human stools from a cohort study. Through tracking molecular compositions in mouse intestinal tract, elevated abundance of free-form OH-TCS while reduced abundance of conjugated forms was observed in the colon digesta and mucosa. Using antibiotic-treated and germ-free mice, as well as in vitro approaches, we demonstrate that gut microbiota-encoded enzymes efficiently convert glucuronide/sulfate-conjugated OH-TCS, which are generated from host metabolism, back to their bioactive free-forms in colon tissues. Thus, host-gut microbiota metabolic interactions of TCS derivatives were proposed. These results shed light on the crucial roles of microbial metabolism in TCS toxicity, and highlight the importance of incorporating gut microbial transformations in health risk assessment of environmental chemicals.

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results