Search

Your search keyword '"Zhou, Guangyuan"' showing total 429 results
Start Over Author "Zhou, Guangyuan"
429 results on '"Zhou, Guangyuan"'

1. The Third Monocular Depth Estimation Challenge

Author

Spencer, Jaime, Tosi, Fabio, Poggi, Matteo, Arora, Ripudaman Singh, Russell, Chris, Hadfield, Simon, Bowden, Richard, Zhou, GuangYuan, Li, ZhengXin, Rao, Qiang, Bao, YiPing, Liu, Xiao, Kim, Dohyeong, Kim, Jinseong, Kim, Myunghyun, Lavreniuk, Mykola, Li, Rui, Mao, Qing, Wu, Jiang, Zhu, Yu, Sun, Jinqiu, Zhang, Yanning, Patni, Suraj, Agarwal, Aradhye, Arora, Chetan, Sun, Pihai, Jiang, Kui, Wu, Gang, Liu, Jian, Liu, Xianming, Jiang, Junjun, Zhang, Xidan, Wei, Jianing, Wang, Fangjun, Tan, Zhiming, Wang, Jiabao, Luginov, Albert, Shahzad, Muhammad, Hosseini, Seyed, Trajcevski, Aleksander, and Elder, James H.

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%., Comment: To appear in CVPRW2024

Published
2024

10. PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation

Author

Zhou, Guangyuan, Wang, Huiqun, Chen, Jiaxin, and Huang, Di

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

RGB-D based 6D pose estimation has recently achieved remarkable progress, but still suffers from two major limitations: (1) ineffective representation of depth data and (2) insufficient integration of different modalities. This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way. It first introduces the Point Refinement Network (PRN) to polish 3D point clouds, recovering missing parts with noise removed. Subsequently, the Multi-Modal Fusion Graph Convolutional Network (MMF-GCN) is presented to strengthen RGB-D combination, which captures geometry-aware inter-modality correlation through local information propagation in the graph convolutional network. Extensive experiments are conducted on three widely used benchmarks, and state-of-the-art performance is reached. Besides, it is also shown that the proposed PRN and MMF-GCN modules are well generalized to other frameworks.

Published
2021

37. Ultra‐light fluorinated polyimide foams with excellent thermal insulation, low dielectric loss and high heat resistance.

Author

Jia, Jialin, Sun, Yunlong, Zang, Shuyan, Nie, Heran, Zhou, Huafeng, and Zhou, Guangyuan

Subjects
THERMAL insulation, DIELECTRIC loss, AEROSPACE materials, INSULATING materials, HEAT losses, GLASS transition temperature
Abstract

High efficiency thermal insulation materials are highly desirable in aerospace industry, whereas combining low density and low thermal conductivity of thermal insulation materials still remains a challenge. In this work, a series of fluorinated polyimide foams (PIFs) based on 4,4‐(hexafluoroisopropylidene) diphthalic anhydride (6FDA) were successfully prepared by microwave‐assisted powder foaming. The modification of fluorination decreased the melt strength while simultaneously enhanced the thermal properties of fluorinated PIFs through the high bonding energy of CF bond. Thus, fluorinated PIFs exhibited one of the lowest densities of reported PIFs, among them, the density of PIF6FDA‐DMBZ was as low as 9.34 kg m−3. The glass transition temperature of all fluorinated PIFs was greater than 295°C. Microwave‐assisted foaming optimized the cell structure effectively, resulting in the thermal conductivity of PIF6FDA‐ODA as low as 0.029 W m−1 K−1. The incorporation of hexafluoroisopropylidene groups reduced the polarization and enhanced the free volume of fluorinated PIFs, leading to hydrophobic characteristics (CA >105°) and ultra‐low dielectric loss properties (tan δ <0.001 at 20 GHz). PIF6FDA‐ODA demonstrated the most excellent comprehensive performance. The excellent comprehensive performance of fluorinated PIFs indicated their potential application as thermal insulation and wave‐transparent materials in aerospace, railway, and shipbuilding industries. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

39. Ligand‐engineered Zr‐MOF membranes with fast water transport channels for alcohol–water separation.

Author

Mo, Binyu, Jin, Yuanhang, Zhou, Guangyuan, Liu, Guozhen, Chen, Cailing, Liu, Zhengkun, Liu, Gongping, and Jin, Wanqin

Subjects
SEPARATION of gases, METAL-organic frameworks, POLYMERIC membranes, METHYL groups, PERVAPORATION, RIVER channels, BUTANOL
Abstract

Metal–organic framework (MOF) membranes with rich functionality and a tunable pore system are promising for molecular separation. However, an inadequate pore microenvironment and low water stability may hamper the extension of their use in gas separation to liquid separation (e.g., organic solvent dehydration). In this study, we report a high‐valence Zr‐MOF membrane with high stability and tunable pore microenvironment, prepared using a mixed‐ligand strategy based on fumarate (fum) and 2‐methylfumarate (mes) ligands for the pervaporation dehydration of alcohols. The introduction of a methyl group in the ligand side chain narrowed the aperture size while balancing the hydrophilicity, thus facilitating the fast and selective permeation of water over alcohol molecules. The resulting mes/fum‐Zr‐MOF membrane with a mes content of 30% displayed excellent butanol/water separation performance with total flux of 5226 g−1·m−2·h−1, separation factor of 1281, and water content of 99.3% in the permeate, transcending the upper‐bound of state‐of‐the‐art MOF and polymer membranes, thereby exhibiting immense potential for alcohols dehydration. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results