Search

Your search keyword '"Wang, Yuxin"' showing total 198 results
Start Over Author "Wang, Yuxin" Publisher ieee
198 results on '"Wang, Yuxin"'

6. A Review of Multi-View Clustering Algorithms

Author

Wang, Yuxin, primary, Liu, Xiaowei, additional, Qi, Yifeng, additional, Guo, Jiangyang, additional, Han, Jianing, additional, Zhang, Jialiang, additional, Zhang, Zhi, additional, Lian, Jianguo, additional, and Nie, Weizhi, additional

Published
2023
Full Text
View/download PDF

18. Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis

Author

Wang, Yuxin, Wu, Wayne, Xu, Dan, Wang, Yuxin, Wu, Wayne, and Xu, Dan

Abstract

Implicit neural representations have shown powerful capacity in modeling real-world 3D scenes, offering superior performance in novel view synthesis. In this paper, we target a more challenging scenario, i.e., joint scene novel view synthesis and editing based on implicit neural scene representations. State-of-the-art methods in this direction typically consider building separate networks for these two tasks (i.e., view synthesis and editing). Thus, the modeling of interactions and correlations between these two tasks is very limited, which, however, is critical for learning high-quality scene representations. To tackle this problem, in this paper, we propose a unified Neural Radiance Field (NeRF) framework to effectively perform joint scene decomposition and composition for modeling real-world scenes. The decomposition aims at learning disentangled 3D representations of different objects and the background, allowing for scene editing, while scene composition models an entire scene representation for novel view synthesis. Specifically, with a two-stage NeRF framework, we learn a coarse stage for predicting a global radiance field as guidance for point sampling, and in the second fine-grained stage, we perform scene decomposition by a novel one-hot object radiance field regularization module and a pseudo supervision via inpainting to handle ambiguous background regions occluded by objects. The decomposed object-level radiance fields are further composed by using activations from the decomposition module. Extensive quantitative and qualitative results show the effectiveness of our method for scene decomposition and composition, outperforming state-of-the-art methods for both novel-view synthesis and editing tasks 1 .

Published
2023

41. A Vision-based Irregular Obstacle Avoidance Framework via Deep Reinforcement Learning

Author

Gao, Lingping, Ding, Jianchuan, Liu, Wenxi, Piao, Haiyin, Wang, Yuxin, Yang, Xin, and Yin, Baocai

Subjects
FOS: Computer and information sciences, Computer Science - Robotics, Robotics (cs.RO)
Abstract

Deep reinforcement learning has achieved great success in laser-based collision avoidance work because the laser can sense accurate depth information without too much redundant data, which can maintain the robustness of the algorithm when it is migrated from the simulation environment to the real world. However, high-cost laser devices are not only difficult to apply on a large scale but also have poor robustness to irregular objects, e.g., tables, chairs, shelves, etc. In this paper, we propose a vision-based collision avoidance framework to solve the challenging problem. Our method attempts to estimate the depth and incorporate the semantic information from RGB data to obtain a new form of data, pseudo-laser data, which combines the advantages of visual information and laser information. Compared to traditional laser data that only contains the one-dimensional distance information captured at a certain height, our proposed pseudo-laser data encodes the depth information and semantic information within the image, which makes our method more effective for irregular obstacles. Besides, we adaptively add noise to the laser data during the training stage to increase the robustness of our model in the real world, due to the estimated depth information is not accurate. Experimental results show that our framework achieves state-of-the-art performance in several unseen virtual and real-world scenarios., IROS 2021

Published
2021

49. Design of Dual-Frequency MIMO Antenna with High Isolation Based on Odd-Even Mode Analysis Method and Defected Ground Structure

Author

Wang Yuxin, Ke Yang, Zhaojun Zhu, and Xiufeng Ren

Subjects
Computer science, business.industry, Frequency band, Impedance matching, Mode (statistics), Mobile telephony, Antenna (radio), business, Topology, Decoupling (electronics), Radio spectrum, Computer Science::Information Theory, Time–frequency analysis
Abstract

This paper proposes a MIMO antenna that can work in two frequency bands of 2. 45GHz and 5. 8GHz. For this antenna structure, two decoupling methods are designed to improve the isolation of the two working frequency bands of the MIMO antenna In this way, the influence between multiple ports can be reduced and the normal operation of the antenna can be guaranteed. For the 2. 45GHz frequency band, the odd-even mode analysis method is adopted to achieve the effect of improving the isolation through impedance matching under the odd-even mode excitation. The process is mainly through theoretical calculation and analysis to obtain a decoupling structure, avoiding the tedious structural optimization process. The actual antenna experiment shows that S12 is reduced by 9dB. For the frequency band of 5. 8GHz, the E-shaped defected ground structure is selected, and S12 is reduced by 13dB without affecting the working effect of the low frequency band.

Published
2021

50. A Research on Age of Information Minimization Scheme of Wireless Sensor Network Assisted by UAV

Author

Jia Xiangdong, Zhao Yuhua, Cao Shengnan, and Wang Yuxin

Subjects
Data processing, business.industry, Computer science, 010401 analytical chemistry, Real-time computing, Process (computing), 020206 networking & telecommunications, 02 engineering and technology, Trajectory optimization, 01 natural sciences, 0104 chemical sciences, Transmission (telecommunications), Convex optimization, 0202 electrical engineering, electronic engineering, information engineering, Wireless, business, Wireless sensor network, Power control
Abstract

Aiming at the problem of information freshness in the process of massive data processing in wireless sensor networks, this paper proposes the system AoI (Age of Information, AoI) based on the constraints of drone flight speed, altitude, collision avoidance, and reliable transmission. A non-convex optimization strategy for AoI minimization that combines acquisition point selection, trajectory optimization and power control. Taking a scene of multiple drones communicating with multiple sensor nodes at the same time under the same frequency band as the object, the information acquisition process of multiple drones in three-dimensional space is simulated and verified. Through the SCA (Successive Convex Approximation, SCA) optimization algorithm, the established non-convex problem is transformed into a convex optimization problem to be solved, and the optimal hover position, hover time and transmission power during the flight of the UAV are obtained. The experimental results show, The optimal solution obtained by the scheme can effectively minimize the system AoI.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results