no code implementations • 9 Feb 2024 • Zhuoran Zheng, Jun Zhang
In endoscopic imaging, the recorded images are prone to exposure abnormalities, so maintaining high-quality images is important to assist healthcare professionals in performing decision-making.
1 code implementation • 6 Feb 2024 • Zhuoran Zheng, Chen Wu
Currently, Transformer is the most popular architecture for image dehazing, but due to its large computational complexity, its ability to handle long-range dependency is limited on resource-constrained devices.
no code implementations • 3 Feb 2024 • Zhuoran Zheng, Chen Wu, Wei Wang, Yeying Jin, Xiuyi Jia
In this paper, we unfold a new perspective on polyp segmentation modeling by leveraging the Depth Anything Model (DAM) to provide depth prior to polyp segmentation models.
1 code implementation • 19 Jan 2024 • Chen Wu, Zhuoran Zheng, Xiuyi Jia, Wenqi Ren
To capture the long-range dependency of features without introducing excessive computational complexity, we present the Global Feature Modulation Layer (GFML).
no code implementations • 30 Nov 2023 • Zhuoran Zheng, Boxue Xiao
Currently, to further improve visual enjoyment, Ultra-High-Definition (UHD) images are catching wide attention.
no code implementations • 20 Apr 2023 • Zhuoran Zheng, Xiuyi Jia
With the development of the medical image field, researchers seek to develop a class of datasets to block the need for medical knowledge, such as \text{MedMNIST} (v2).
1 code implementation • 28 Mar 2023 • Zhuoran Zheng, Xiuyi Jia
The challenges in building ultra-high-definition (UHD) dehazing datasets are the absence of estimation methods for UHD depth maps, high-quality 4K depth estimation datasets, and migration strategies for UHD haze images from synthetic to real domains.
no code implementations • 25 Oct 2022 • Weiyi Cong, Zhuoran Zheng, Xiuyi Jia
Unfortunately, the feature space of the label distribution dataset is affected by human factors and the inductive bias of the feature extractor causing uncertainty in the feature space.
no code implementations • 15 Oct 2022 • Qimeng Guo, Zhuoran Zheng, Xiuyi Jia, Liancheng Xu
Specifically, we compute a covariance matrix for the label space in the training set to represent the relationships between labels, then model the information distribution (Gaussian distribution function) for each element in the covariance matrix to obtain an LCG.
no code implementations • 28 Sep 2022 • Zhuoran Zheng, Xiuyi Jia
Specifically, we use deep implicit representation learning to construct a label distribution matrix with Gaussian prior constraints, where each row component corresponds to the distribution estimate of each label value, and this row component is constrained by a prior Gaussian distribution to moderate the noise and uncertainty interference of the label distribution dataset.
1 code implementation • 16 Sep 2022 • Yunliang Zhuang, Zhuoran Zheng, Chen Lyu
To alleviate this problem, we propose a novel module using the Fourier coefficients, which can recover high-quality texture details under the constraint of semantics in the frequency phase and supplement the spatial domain.
no code implementations • 8 Jun 2022 • Zhuoran Zheng, Xiuyi Jia
Currently, transformer-based algorithms are making a splash in the domain of image deblurring.
no code implementations • 15 Mar 2022 • Xiang Chen, Zhentao Fan, Pengpeng Li, Longgang Dai, Caihua Kong, Zhuoran Zheng, Yufeng Huang, Yufeng Li
Then these negative adversaries are trained end-to-end together with the backbone representation network to enhance the discriminative information and promote factor disentanglement performance by maximizing the adversarial contrastive loss.
1 code implementation • 17 Feb 2022 • Boxue Xiao, Zhuoran Zheng, Xiang Chen, Chen Lv, Yunliang Zhuang, Tao Wang
Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time.
1 code implementation • 13 Feb 2022 • Zhuoran Zheng, Xiuyi Jia, Yunliang Zhuang
The exposed cameras of UAV can shake, shift, or even malfunction under the influence of harsh weather, while the add-on devices (Dupont lines) are very vulnerable to damage.
1 code implementation • CVPR 2021 • Zhuoran Zheng, Wenqi Ren, Xiaochun Cao, Xiaobin Hu, Tao Wang, Fenglong Song, Xiuyi Jia
To address the problem, we propose a novel network capable of real-time dehazing of 4K images on a single GPU, which consists of three deep CNNs.
1 code implementation • 26 May 2021 • Xue Jiang, Zhuoran Zheng, Chen Lyu, Liang Li, Lei Lyu
In this paper, we present TreeBERT, a tree-based pre-trained model for improving programming language-oriented generation tasks.
no code implementations • ICCV 2021 • Zhuoran Zheng, Wenqi Ren, Xiaochun Cao, Tao Wang, Xiuyi Jia
First, we propose a dual-path network to extract content and chromatic features at a reduced resolution of the low dynamic range (LDR) input.