Hui Zeng

Hui Zeng

Auto-generated profile, based on publicly available information

Hui Zeng

Water Agriculture Energy Nexus Research Analyst WRI China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2024 in AI Open
Verified
Journal Article
Open access
HZHui Zeng
Hui Zeng
JXJingyuan Xue
Jingyuan Xue
MHMeng Hao
Meng Hao
CSChen Sun
Chen Sun
BNBin Ning
Bin Ning
NZNa Zhang
Na Zhang

20 July 2024 in Applied Catalysis B: Environment and Energy
Verified
Journal Article
Closed access
YTYing Tang
Ying Tang
ZLZhipeng Liu
Zhipeng Liu
JJJuan Jia
Juan Jia
HZHui Zeng
Hui Zeng
ZRZebao Rui
Zebao Rui

24 November 2022 in Microchemical Journal
Verified
Journal Article
Closed access
DLDongmei Liu
Dongmei Liu
XCXuejia Chen
Xuejia Chen
HZHui Zeng
Hui Zeng
CLChang Liu
Chang Liu
BTBiyu Tang
Biyu Tang
Min ZhangMin Zhang
Min Zhang

17 March 2022 in arXiv
Verified
Preprint
Open access
PDF file
JLJie Liang
Jie Liang
HZHui Zeng
Hui Zeng
LZLei Zhang
Lei Zhang
Single image super-resolution (SISR) with generative adversarial networks (GAN) has recently attracted increasing attention due to its potentials to generate rich details. However, the training of GAN is unstable, and it often introduces many perceptually unpleasant artifacts along with the generated details. In this paper, we demonstrate that it is possible to train a GAN-based SISR model which can stably generate perceptually realistic details while inhibiting visual artifacts. Based on the observation that the local statistics (e.g., residual variance) of artifact areas are often different from the areas of perceptually friendly details, we develop a framework to discriminate between GAN-generated artifacts and realistic details, and consequently generate an artifact map to regularize and stabilize the model training process. Our proposed locally discriminative learning (LDL) method is simple yet effective, which can be easily plugged in off-the-shelf SISR methods and boost their performance. Experiments demonstrate that LDL outperforms the state-of-the-art GAN based SISR methods, achieving not only higher reconstruction accuracy but also superior perceptual quality on both synthetic and real-world datasets. Codes and models are available at https://github.com/csjliang/LDL.

27 March 2022 in arXiv
Verified
Preprint
Open access
PDF file
JLJie Liang
Jie Liang
HZHui Zeng
Hui Zeng
LZLei Zhang
Lei Zhang
Efficient and effective real-world image super-resolution (Real-ISR) is a challenging task due to the unknown complex degradation of real-world images and the limited computation resources in practical applications. Recent research on Real-ISR has achieved significant progress by modeling the image degradation space; however, these methods largely rely on heavy backbone networks and they are inflexible to handle images of different degradation levels. In this paper, we propose an efficient and effective degradation-adaptive super-resolution (DASR) network, whose parameters are adaptively specified by estimating the degradation of each input image. Specifically, a tiny regression network is employed to predict the degradation parameters of the input image, while several convolutional experts with the same topology are jointly optimized to specify the network parameters via a non-linear mixture of experts. The joint optimization of multiple experts and the degradation-adaptive pipeline significantly extend the model capacity to handle degradations of various levels, while the inference remains efficient since only one adaptively specified network is used for super-resolving the input image. Our extensive experiments demonstrate that the proposed DASR is not only much more effective than existing methods on handling real-world images with different degradation levels but also efficient for easy deployment. Codes, models and datasets are available at https://github.com/csjliang/DASR.

1 May 2023
Verified
Journal Article
Open access
PDF file
SASophie Attwood
Sophie Attwood
LPLiqing Peng
Liqing Peng
HZHui Zeng
Hui Zeng
SBStacy Blondin
Stacy Blondin
XFXiaotian Fu
Xiaotian Fu
China’s economic development has driven significant changes to diets in the country. In this report, WRI examines how ways of eating are changing in China and outlines a behavior science framework to promote healthier and more sustainable diets.