检索结果-内蒙古大学图书馆

Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lu, Zhan Zheng, Qian Shi, Boxin Jiang, Xudong School of Electrical and Electronic Engineering Nanyang Technological University Singapore College of Computer Science and Technology Zhejiang University China The State Key Lab of Brain-Machine Intelligence Zhejiang University China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China

Panoramic imaging research on geometry recovery and High Dynamic Range (HDR) reconstruction becomes a trend with the development of Extended Reality (XR). Neural Radiance Fields (NeRF) provide a promising scene representation for both tasks without requiring extensive prior data. However, in the case of inputting sparse Low Dynamic Range (LDR) panoramic images, NeRF often degrades with under-constrained geometry and is unable to reconstruct HDR radiance from LDR inputs. We observe that the radiance from each pixel in panoramic images can be modeled as both a signal to convey scene lighting information and a light source to illuminate other pixels. Hence, we propose the irradiance fields from sparse LDR panoramic images, which increases the observation counts for faithful geometry recovery and leverages the irradiance-radiance attenuation for HDR reconstruction. Extensive experiments demonstrate that the irradiance fields outperform state-of-the-art methods on both geometry recovery and HDR reconstruction and validate their effectiveness. Furthermore, we show a promising byproduct of spatially-varying lighting estimation. The code is available at https://***/Lu-Zhan/Pano-NeRF. Copyright © 2023, The Authors. All rights reserved.

关键词： Recovery

Self-Supervised Speech Denoising Using Only Noisy Audio Signals

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Jiasong Li, Qingchun Yang, Guanyu Li, Lei Senhadji, Lotfi Shu, Huazhong LIST Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast University Nanjing210096 China RennesF-35042 France The 28th Research Institute of China Electronics Technology Group Corporation Nanjing210007 China Univ Rennes INSERM LTSI UMR 1099 RennesF-35042 France

In traditional speech denoising tasks, clean audio signals are often used as the training target, but absolutely clean signals are collected from expensive recording equipment or in studios with the strict environments. To overcome this drawback, we propose an end-to-end self-supervised speech denoising training scheme using only noisy audio signals, named Only-Noisy Training (ONT), without extra training conditions. The proposed ONT strategy constructs training pairs only from each single noisy audio, and it contains two modules: training audio pairs generated module and speech denoising module. The first module adopts a random audio sub-sampler on each noisy audio to generate training pairs. The sub-sampled pairs are then fed into a novel complex-valued speech denoising module. Experimental results show that the proposed method not only eliminates the high dependence on clean targets of traditional audio denoising tasks, but also achieves on-par or better performance than other training strategies. Availability-ONT is available at https://***/liqingchunnnn/Only-Noisy-Training. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

A secure broadcasting method based on the generalized aryabhata remainder theorem

学校读者我要写书评

暂无评论

Journal of information Hiding and Multimedia Signal processing 2014年第4期5卷 709-718页

作者： Liu, Yanjun Chang, Chin-Chen Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University No.111 Jiulong Rd Hefei230601 China Department of Computer Science and Information Engineering Asia University No.500 Lioufeng Rd Wufeng Taichung413 Taiwan Department of Information Engineering and Computer Science Feng Chia University No.100 Wenhwa Rd Seatwen Taichung407 Taiwan

With the prevalence of group communications, how to implement secure broadcasting among group members has become one of the most important issues. Broadcasting is a point-to-multipoint communication, and secure broadcasting should ensure that only authorized group members can obtain the correct content of the message that is broadcast by a sender. In this paper, we propose a secure broadcasting method based on the generalized Aryabhata remainder theorem (GART). By the use of the RSA public-key scheme, the proposed scheme allows the sender to send one copy of an encrypted message to all group members, but only the authorized members can recover the plaintext. Analysis showed that our scheme is secure and efficient. © 2014.

关键词： Cryptography

Multi-view multi-instance multi-label learning based on collaborative matrix factorization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xing, Yuying Yu, Guoxian Domeniconi, Carlotta Wang, Jun Zhang, Zili Guo, Maozu College of Computer and Information Science Southwest University Chongqing China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan China Department of Computer Science George Mason University FairfaxVA United States School of Information Technology Deakin University GeelongVIC Australia School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China

Multi-view Multi-instance Multi-label Learning(M3L) deals with complex objects encompassing diverse instances, represented with different feature views, and annotated with multiple labels. Existing M3L solutions only partially explore the inter or intra relations between objects (or bags), instances, and labels, which can convey important contextual information for M3L. As such, they may have a compromised performance. In this paper, we propose a collaborative matrix factorization based solution called M3Lcmf. M3Lcmf first uses a heterogeneous network composed of nodes of bags, instances, and labels, to encode different types of relations via multiple relational data matrices. To preserve the intrinsic structure of the data matrices, M3Lcmf collaboratively factorizes them into low-rank matrices, explores the latent relationships between bags, instances, and labels, and selectively merges the data matrices. An aggregation scheme is further introduced to aggregate the instance-level labels into bag-level and to guide the factorization. An empirical study on benchmark datasets show that M3Lcmf outperforms other related competitive solutions both in the instance-level and bag-level prediction. Copyright © 2019, The Authors. All rights reserved.

关键词： Matrix factorization

Multi-rate nyquist-SCM for C-band 100Gbit/s signal over 50km dispersion-uncompensated link

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Haide Zhou, Ji Wei, Jinlong Guo, Dong Feng, Yuanhua Liu, Weiping Yu, Changyuan Wang, Dawei Li, Zhaohui Department of Electronic Engineering College of Information Science and Technology Jinan University Guangzhou510632 China Huawei Technologies Duesseldorf GmbH European Research Center Germany School of Information and Electronics Beijing Institute of Technology Beijing100081 China Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hong Kong Hong Kong Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Sun Yat-sen University Guangzhou510275 China State Key Laboratory of Optoelectronic Materials and Technologies 519000 China

In this paper, to the best of our knowledge, we propose the first multi-rate Nyquist-subcarriers modulation (SCM) for C-band 100Gbit/s signal transmission over 50km dispersionuncompensated link. Chromatic dispersion (CD) introduces severe spectral nulls on optical double-sideband signal, which greatly degrades the performance of intensity-modulation and direct-detection systems. Based on the prior knowledge of the dispersive channel, Nyquist-SCM with multi-rate subcarriers is proposed to keep away from the CD-caused spectral nulls flexibly. Signal on each subcarrier can be individually recovered by a digital signal processing, including the feed-forward equalizer with no more than 31 taps, a two-tap post filter, and maximum likelihood sequence estimation with one memory length. Combining with entropy loading based on probabilistic constellation shaping to maximize the capacity-reach, the C-band 100Gbit/s multi-rate Nyquist-SCM signal over 50km dispersion-uncompensated link can achieve 7% hard-decision forward error correction limit and average normalized generalized mutual information of 0.967 at received optical power of -4dBm and optical signal-to-noise ratio of 47.67dB. In conclusion, the multi-rate Nyquist-SCM shows great potentials in solving the CD-caused spectral distortions. © 2021, CC BY.

关键词： Chromatic dispersion

A multicast routing algorithm with multiple trees

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2005年第2期000卷 426-432页

作者： Cui Xunxue Gao Wei Fang Hongyu New Star Research Institute of Applied Technology， Hefei 230031， P. R. China Jiangsu Key Laboratory of Computer Information Processing Technology，Soochow University， Suzhou 215006， P. R. China Department of Electronic Engineering and Information Science， University of Science and Technology of China， Hefei 230027， P. R. China School of Electronic Science and Technology， Anhui University， Hefei 230039， P. R. China

Quality of service (QoS) multicast routing has continued to be a very important research topic in the Internet.A method of multicast routing is proposed to simultaneously optimize several parameters based on multiobjective genetic algorithm, after the related work is reviewed. The contribution lies on that the selection process of such routing is treated with multiobjective optimization. Different quality criterions in IP network are taken into account for multicast communications. A set of routing trees is generated to approximate the Pareto front of multicast problem. Multiple trees can be selected from the final set of nondominated solutions, and applied to obtain a good overall link cost and balance traffic distribution according to some simulation results.

关键词： multicast routing quality of service multiobjective optimization genetic algorithms

Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Tianying Zhang, Lu Wang, Yang Guan, Jihong Fu, Yanwei Zhao, Jiajia Zhou, Shuigeng Department of Computer Science and Technology Tongji University Shanghai201804 China The Project Management Office of China National Scientific Seafloor Observatory Tongji University Shanghai200092 China Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200438 China Shanghai Key Lab of Intelligent Information Processing The School of Data Science Fudan University Shanghai200433 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to generalize these object detectors to the novel long-tailed object classes, which have only few labeled training samples. To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes. Especially, the research in this emerging field has been flourishing in recent years with various benchmarks, backbones, and methodologies proposed. To review these FSOD works, there are several insightful FSOD survey articles [58, 59, 74, 78] that systematically study and compare them as the groups of fine-tuning/transfer learning, and meta-learning methods. In contrast, we review the existing FSOD algorithms from a new perspective under a new taxonomy based on their contributions, i.e., data-oriented, model-oriented, and algorithm-oriented. Thus, a comprehensive survey with performance comparison is conducted on recent achievements of FSOD. Furthermore, we also analyze the technical challenges, the merits and demerits of these methods, and envision the future directions of FSOD. Specifically, we give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols. The taxonomy is then proposed that groups FSOD methods into three types. Following this taxonomy, we provide a systematic review of the advances in FSOD. Finally, further discussions on performance, challenges, and future directions are presented. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

A TWO LAYERED DATA ASSOCIATION APPROACH FOR BALL TRACKING

学校读者我要写书评

暂无评论

A TWO LAYERED DATA ASSOCIATION APPROACH FOR BALL TRACKING

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Xiangzeng Zhou Qiang Huang Lei Xie Stephen Cox Shaanxi Provincial Key Laboratory of Speech & Image Information Processing (SAIIP) School of Computer Science Northwestern Polytechnical University Xi'an 710072 P. R. China School of Computing Sciences University of East Anglia Norwich NR4 7TJ United Kingdom

ISBN: (纸本)9781479903573

Ball-tracking is a key technology in processing and analyzing a ball game. Because of the complexity of visual scenes, a large number of objects are usually selected as candidates for the ball, leading to incorrect identification, and conversely, the true position of the ball may sometimes be missed. In this paper, we propose a two layered data association method to improve the robustness of ball-tracking. At a local layer, we use a sliding window based Token Transfer method to generate a set of sub-trajectory candidates. At a global layer, a single ball trajectory is obtained by applying a dynamic programming based splice method to a graph consisting of the sub-trajectory candidates. We evaluated our approach on tennis matches from the Australian Open and the U.S. Open, and the results obtained show that our approach outperforms the state-of-art approach by around 30 %.

关键词： data association tennis ball tracking trajectory layered data association tennis Ball Device Component trajectory roller path tracking sliding windows key technology associations Association

Ms-Mvs: Multi-Stage Multi-View Stereo Via Offset Regression and Uncertain Distance Estimation

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Cao, Mingwei Liu, Bowen Yi, Jun Yu, Ye Zhao, Haifeng Lyu, Zhihan Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230601 China School of Computer Science and Technology Anhui University Hefei230601 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Department of Game Design Uppsala University Visby62167 Sweden

In recent years, deep learning-based multi-view stereo (MVS) reconstruction methods have made significant progress. However, they still face challenges such as low accuracy and incomplete scene reconstruction due to the differences between the captured images from various viewpoints. To address these challenges, we propose a multi-stage MVS reconstruction network that utilizes offset regression and uncertainty distance estimation to weaken the impact of the differences. Firstly, the multi-view images are input into a dynamic feature extraction network to obtain robust image features. Secondly, we utilize the uncertainty distance estimation method to dynamically calculate the depth sampling range for each pixel. This method considers the probability distribution and contextual information of adjacent pixels to improve the depth estimation accuracy. Thirdly, we present an offset regression algorithm that combines the advantages of both classification and regression methods. It further refines the predicted depth values, bringing them closer to the ground truth values. Finally, we tested the method on public datasets and compared it to traditional MVS reconstruction methods. Results show that the new method outperforms the current methods in terms of the accuracy and completeness of point clouds while using less memory space. The source code is available at: https://***/liubowen1233/MS-MVS. © 2024, The Authors. All rights reserved.

关键词： Feature extraction