1 code implementation • 18 Apr 2024 • Haoyue Liu, Shihan Peng, Lin Zhu, Yi Chang, Hanyu Zhou, Luxin Yan
In this work, we present a novel nighttime dynamic imaging method with an event camera.
no code implementations • 21 Mar 2024 • Shilv Cai, Xiaoguo Liang, Shuning Cao, Luxin Yan, Sheng Zhong, Liqun Chen, Xu Zou
Image compression and denoising represent fundamental challenges in image processing with many real-world applications.
no code implementations • 18 Mar 2024 • Howard Zhang, Yunhao Ba, Ethan Yang, Rishi Upadhyay, Alex Wong, Achuta Kadambi, Yun Guo, Xueyao Xiao, Xiaoxiong Wang, Yi Li, Yi Chang, Luxin Yan, Chaochao Zheng, Luping Wang, Bin Liu, Sunder Ali Khowaja, Jiseok Yoon, Ik-Hyun Lee, Zhao Zhang, Yanyan Wei, Jiahuan Ren, Suiyi Zhao, Huan Zheng
This report reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023.
no code implementations • 12 Mar 2024 • Hanyu Zhou, Zhiwei Shi, Hao Dong, Shihan Peng, Yi Chang, Luxin Yan
In spatial reasoning stage, we project the compensated events into the same image coordinate, discretize the timestamp of events to obtain a time image that can reflect the motion confidence, and further segment the moving object through adaptive threshold on the time image.
no code implementations • 12 Mar 2024 • Hanyu Zhou, Yi Chang, Zhiwei Shi, Luxin Yan
In this work, we bring the event as a bridge between RGB and LiDAR, and propose a novel hierarchical visual-motion fusion framework for scene flow, which explores a homogeneous space to fuse the cross-modal complementary knowledge for physical interpretation.
no code implementations • 31 Jan 2024 • Hanyu Zhou, Yi Chang, Haoyue Liu, Wending Yan, Yuxing Duan, Zhiwei Shi, Luxin Yan
In appearance adaptation, we employ the intrinsic image decomposition to embed the auxiliary daytime image and the nighttime image into a reflectance-aligned common space.
1 code implementation • ICCV 2023 • Yun Guo, Xueyao Xiao, Yi Chang, Shumin Deng, Luxin Yan
Learning-based image deraining methods have made great progress.
1 code implementation • 15 Jun 2023 • Shengqi Xu, Xueyao Xiao, Shuning Cao, Yi Chang, Luxin Yan
In this technical report, we present the solution developed by our team VIELab-HUST for text recognition through atmospheric turbulence in Track 2. 1 of the CVPR 2023 UG$^{2}$+ challenge.
1 code implementation • 15 Jun 2023 • Shengqi Xu, Shuning Cao, Haoyue Liu, Xueyao Xiao, Yi Chang, Luxin Yan
We subsequently select the sharpest set of registered frames by employing a frame selection approach based on image sharpness, and average them to produce an image that is largely free of geometric distortion, albeit with blurriness.
1 code implementation • 24 May 2023 • Shilv Cai, Liqun Chen, Sheng Zhong, Luxin Yan, Jiahuan Zhou, Xu Zou
Experimental results show that our proposed joint solution achieves a significant improvement over different combinations of existing state-of-the-art sequential ``Compress before Enhance'' or ``Enhance before Compress'' solutions for low-light images, which would make lossy low-light image compression more meaningful.
1 code implementation • 13 May 2023 • Yun Guo, Xueyao Xiao, Xiaoxiong Wang, Yi Li, Yi Chang, Luxin Yan
Secondly, a transformer-based single image deraining network Uformer is implemented to pre-train on large real rain dataset and then fine-tuned on pseudo GT to further improve image restoration.
no code implementations • 24 Mar 2023 • Hanyu Zhou, Yi Chang, Gang Chen, Luxin Yan
In motion adaptation, we utilize the flow consistency knowledge to align the cross-domain optical flows into a motion-invariance common space, where the optical flow from clean weather is used as the guidance-knowledge to obtain a preliminary optical flow for adverse weather.
no code implementations • CVPR 2023 • Hanyu Zhou, Yi Chang, Wending Yan, Luxin Yan
To handle the practical optical flow under real foggy scenes, in this work, we propose a novel unsupervised cumulative domain adaptation optical flow (UCDA-Flow) framework: depth-association motion adaptation and correlation-alignment motion adaptation.
no code implementations • ICCV 2023 • Changfeng Yu, Shiming Chen, Yi Chang, Yibing Song, Luxin Yan
To solve this dilemma, we propose a physical alignment and controllable generation network (PCGNet) for diverse and realistic rain generation.
no code implementations • 2 Nov 2022 • Yi Chang, Yun Guo, Yuntong Ye, Changfeng Yu, Lin Zhu, XiLe Zhao, Luxin Yan, Yonghong Tian
In addition, considering that the existing real rain datasets are of low quality, either small scale or downloaded from the internet, we collect a real large-scale dataset under various rainy kinds of weather that contains high-resolution rainy images.
1 code implementation • 12 Sep 2022 • Shilv Cai, Zhijun Zhang, Liqun Chen, Luxin Yan, Sheng Zhong, Xu Zou
We implement the IAT in a mathematical invertible manner on a single rate Invertible Neural Network (INN) based model and the quality level (QLevel) would be fed into the IAT to generate scaling and bias tensors.
no code implementations • CVPR 2022 • Leizhen Dong, Zhimin Li, Kunlun Xu, Zhijun Zhang, Luxin Yan, Sheng Zhong, Xu Zou
Specifically, the Object Query would be initialized via category priors represented by an external object detection model to yield better performance.
no code implementations • 25 Mar 2022 • Changfeng Yu, Yi Chang, Yi Li, XiLe Zhao, Luxin Yan
Consequently, we design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network for better generalization.
no code implementations • 24 Feb 2022 • Kunlun Xu, Zhimin Li, Zhijun Zhang, Leizhen Dong, Wenhui Xu, Luxin Yan, Sheng Zhong, Xu Zou
Moreover, we also use an actor branch to get interaction prediction of the actor and propose a novel composition strategy based on center-point indexing to generate the final HOI prediction.
1 code implementation • CVPR 2022 • Yi Li, Yi Chang, Yan Gao, Changfeng Yu, Luxin Yan
Consequently, we perform inter-domain adaptation between the synthetic and real images by mutually exchanging the background and other two components.
no code implementations • 1 Dec 2021 • Yanjie Wang, Xu Zou, Zhijun Zhang, Wenhui Xu, Liqun Chen, Sheng Zhong, Luxin Yan, Guodong Wang
Detecting oriented objects along with estimating their rotation information is one crucial step for analyzing remote sensing images.
no code implementations • CVPR 2021 • Yuntong Ye, Yi Chang, Hanyu Zhou, Luxin Yan
Existing deep learning-based image deraining methods have achieved promising performance for synthetic rainy images, typically rely on the pairs of sharp images and simulated rainy counterparts.
no code implementations • ICCV 2017 • Yi Chang, Luxin Yan, Sheng Zhong
This paper addresses the problem of line pattern noise removal from a single image, such as rain streak, hyperspectral stripe and so on.
no code implementations • 1 Sep 2017 • Yi Chang, Luxin Yan, Houzhang Fang, Sheng Zhong, Zhijun Zhang
To overcome these limitations, in this work, we propose a unified low-rank tensor recovery model for comprehensive HSI restoration tasks, in which non-local similarity between spectral-spatial cubic and spectral correlation are simultaneously captured by 3-order tensors.
Ranked #12 on Hyperspectral Image Denoising on ICVL-HSI-Gaussian50
no code implementations • CVPR 2017 • Yi Chang, Luxin Yan, Sheng Zhong
Recent low-rank based matrix/tensor recovery methods have been widely explored in multispectral images (MSI) denoising.