no code implementations • 8 Jul 2024 • Jia Liu, Changlin Li, Qirui Sun, Jiahui Ming, Chen Fang, Jue Wang, Bing Zeng, Shuaicheng Liu
Fine-tuning advanced diffusion models for high-quality image stylization usually requires large training datasets and substantial computational resources, hindering their practical applicability.
no code implementations • 3 Jul 2024 • Zhanglei Yang, Haipeng Li, Mingbo Hong, Bing Zeng, Shuaicheng Liu
We present RS-Diffusion, the first Diffusion Models-based method for single-frame Rolling Shutter (RS) correction.
no code implementations • 14 Jun 2024 • Qiang Zhu, Yajun Qiu, Yu Liu, Shuyuan Zhu, Bing Zeng
In this paper, we propose a temporal group alignment and fusion network to enhance the quality of compressed videos by using the long-short term correlations between frames.
no code implementations • 30 May 2024 • Lei Xiong, Xin Luo, ZiHao Wang, Chaofan He, Shuyuan Zhu, Bing Zeng
This image reconstruction network leverages features and texture images to reconstruct preview images for humans.
1 code implementation • CVPR 2024 • Tianhao Zhou, Haipeng Li, Ziyi Wang, Ao Luo, Chen-Lin Zhang, Jiajun Li, Bing Zeng, Shuaicheng Liu
Image stitching from different captures often results in non-rectangular boundaries, which is often considered unappealing.
no code implementations • 12 Mar 2024 • Yi Zeng, Zhengning Wang, Yuxuan Liu, Tianjiao Zeng, Xuhang Liu, Xinglong Luo, Shuaicheng Liu, Shuyuan Zhu, Bing Zeng
Since texture details intertwine with compression artifacts in compressed dark images, detail enhancement and blocking artifacts suppression contradict each other in image space.
1 code implementation • CVPR 2024 • Xinglong Luo, Ao Luo, Zhengning Wang, Chunyu Lin, Bing Zeng, Shuaicheng Liu
In this paper we explore the problem of event-based meshflow estimation a novel task that involves predicting a spatially smooth sparse motion field from event cameras.
1 code implementation • 14 Dec 2023 • Ru Li, Jia Liu, Guanghui Liu, Shengping Zhang, Bing Zeng, Shuaicheng Liu
We modify the classical spectral rendering into two main steps, 1) the generation of a series of spectrum maps spanning different wavelengths, 2) the combination of these spectrum maps for the RGB output.
1 code implementation • ICCV 2023 • Hai Jiang, Haipeng Li, Songchen Han, Haoqiang Fan, Bing Zeng, Shuaicheng Liu
In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network.
no code implementations • 9 Jun 2023 • Haipeng Li, Dingrui Liu, Yu Zeng, Shuaicheng Liu, Tao Gan, Nini Rao, Jinlin Yang, Bing Zeng
On one hand, this "one-image-one-network" learning ensures complete patient privacy as it does not use any images from other patients as the training data.
no code implementations • 10 Apr 2023 • Ru Li, Guanghui Liu, Bing Zeng, Shuaicheng Liu
The method combines the efficiency of optical flow and the accuracy of PatchMatch.
no code implementations • 23 Jan 2023 • Haipeng Li, Kunming Luo, Bing Zeng, Shuaicheng Liu
Second, we design a self-guided fusion module (SGF) to fuse the background motion extracted from the gyro field with the optical flow and guide the network to focus on motion details.
1 code implementation • ICCV 2023 • Weilong Yan, Robby T. Tan, Bing Zeng, Shuaicheng Liu
In this work, we adopt a more straightforward method to learn deep homography mixture motion between an RS image and its corresponding GS image, without large solution space or strict restrictions on image features.
1 code implementation • ICCV 2023 • Zhuofan Zhang, Zhen Liu, Ping Tan, Bing Zeng, Shuaicheng Liu
In this work, we adopt recent off-the-shelf high-quality deep motion models for motion estimation to recover the camera trajectory and focus on the latter two steps.
3 code implementations • 10 Aug 2022 • Zhen Liu, Yinglong Wang, Bing Zeng, Shuaicheng Liu
High dynamic range (HDR) deghosting algorithms aim to generate ghost-free HDR images with realistic details.
no code implementations • 9 Aug 2022 • Renwei Yang, Shuyuan Zhu, Xiaozhen Zheng, Bing Zeng
We design a DCT based convolution layer, to produce DCT coefficients that are suitable for CNN learning.
3 code implementations • 11 Jun 2022 • Hewei Liu, Renwei Yang, Shuyuan Zhu, Xing Wen, Bing Zeng
In this paper, we propose a luminance-guided chrominance image enhancement convolutional neural network for HEVC intra coding.
no code implementations • 11 Jun 2022 • Renwei Yang, Yike Liu, Bing Zeng
However, those methods are based on a hypothesis that the value of salt and pepper noise is exactly 0 and 255.
no code implementations • 14 Jan 2022 • Hewei Liu, Shuyuan Zhu, Ruiqin Xiong, Guanghui Liu, Bing Zeng
In this paper, we propose a new fast CU partition algorithm for VVC intra coding based on cross-block difference.
no code implementations • CVPR 2022 • Chengzhou Tang, Yuqiang Yang, Bing Zeng, Ping Tan, Shuaicheng Liu
To these ends, we design a method that receives a low-resolution RAW as the input and estimates the desired higher-resolution RAW jointly with the degradation model.
1 code implementation • ICCV 2021 • Cheng Zhang, Zhaopeng Cui, Cai Chen, Shuaicheng Liu, Bing Zeng, Hujun Bao, yinda zhang
Panorama images have a much larger field-of-view thus naturally encode enriched scene context information compared to standard perspective images, which however is not well exploited in the previous scene understanding methods.
no code implementations • CVPR 2021 • Zhi Lu, Yang Hu, Yan Chen, Bing Zeng
To accommodate the variety of users' preferences, we characterize each user with a set of anchors, i. e. a group of learnable latent vectors in the outfit space that are the representatives of the outfits the user likes.
no code implementations • CVPR 2021 • Yinglong Wang, Chao Ma, Bing Zeng
In this work, we aim to exploit the intrinsic priors of rainy images and develop intrinsic loss functions to facilitate training deraining networks, which decompose a rainy image into a rain-free background layer and a rainy layer containing intact rain streaks.
2 code implementations • 7 Jun 2021 • Hao Xu, Nianjin Ye, Guanghui Liu, Bing Zeng, Shuaicheng Liu
Data association is important in the point cloud registration.
1 code implementation • CVPR 2021 • Cheng Zhang, Zhaopeng Cui, yinda zhang, Bing Zeng, Marc Pollefeys, Shuaicheng Liu
We not only propose an image-based local structured implicit network to improve the object shape estimation, but also refine the 3D object pose and scene layout via a novel implicit scene graph neural network that exploits the implicit local object features.
Ranked #1 on
Monocular 3D Object Detection
on SUN RGB-D
(using extra training data)
1 code implementation • ICCV 2021 • Hao Xu, Shuaicheng Liu, Guangfu Wang, Guanghui Liu, Bing Zeng
On the other hand, previous global feature based approaches can utilize the entire point cloud for the registration, however they ignore the negative effect of non-overlapping points when aggregating global features.
no code implementations • 3 Feb 2021 • Ru Li, Chuan Wang, Jue Wang, Guanghui Liu, Heng-Yu Zhang, Bing Zeng, Shuaicheng Liu
The ground truth images play a leading role in generating reasonable HDR images.
no code implementations • 19 Jan 2021 • Ru Li, Shuaicheng Liu, Guangfu Wang, Guanghui Liu, Bing Zeng
We design a multi-task pipeline that includes, (1) a classification branch to classify jigsaw permutations, and (2) a GAN branch to recover features to images in correct orders.
no code implementations • 13 Jan 2021 • Bing Zeng, Lingze Duan
The interaction between an atomic system and a few-cycle ultrafast pulse carries rich physics and a considerable application prospect in quantum-coherence control.
Quantum Physics Optics
1 code implementation • ECCV 2020 • Yinglong Wang, Yibing Song, Chao Ma, Bing Zeng
Single image deraining regards an input image as a fusion of a background image, a transmission map, rain streaks, and atmosphere light.
no code implementations • 9 Jun 2020 • Qingdong He, Zhengning Wang, Hao Zeng, Yijun Liu, Shuaicheng Liu, Bing Zeng
After aligning the interior points with fused features, the proposed network refines the prediction in a more accurate manner and encodes the whole box in a novel compact method.
no code implementations • 16 Mar 2020 • Jiaxiong Qiu, Cai Chen, Shuaicheng Liu, Bing Zeng
The channel redundancy in feature maps of convolutional neural networks (CNNs) results in the large consumption of memories and computational resources.
1 code implementation • CVPR 2020 • Peng Dai, yinda zhang, Zhuwen Li, Shuaicheng Liu, Bing Zeng
The input to the network is the raw point cloud of a scene and the output are image or image sequences from a novel view or along a novel camera trajectory.
1 code implementation • 10 Dec 2019 • Shuaicheng Liu, Zehao Zhang, Kai Song, Bing Zeng
The unprecedented performance achieved by deep convolutional neural networks for image classification is linked primarily to their ability of capturing rich structural features at various layers within networks.
no code implementations • 25 Nov 2019 • Yinglong Wang, Chao Ma, Bing Zeng
Different rain models and novel network structures have been proposed to remove rain streaks from single rainy images.
no code implementations • 9 Oct 2019 • Yinglong Wang, Haokui Zhang, Yu Liu, Qinfeng Shi, Bing Zeng
However, the existing methods usually do not have good generalization ability, which leads to the fact that almost all of existing methods have a satisfied performance on removing a specific type of rain streaks, but may have a relatively poor performance on other types of rain streaks.
no code implementations • 22 Jun 2019 • Yinglong Wang, Qinfeng Shi, Ehsan Abbasnejad, Chao Ma, Xiaoping Ma, Bing Zeng
Instead of using the estimated atmospheric light directly to learn a network to calculate transmission, we utilize it as ground truth and design a simple but novel triangle-shaped network structure to learn atmospheric light for every rainy image, then fine-tune the network to obtain a better estimation of atmospheric light during the training of transmission network.
no code implementations • 14 May 2019 • Yinglong Wang, Dong Gong, Jie Yang, Qinfeng Shi, Anton Van Den Hengel, Dehua Xie, Bing Zeng
Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing.
2 code implementations • 28 Jan 2019 • Xiandong Meng, Xuan Deng, Shuyuan Zhu, Bing Zeng
In this paper, we propose a quality enhancement network of versatile video coding (VVC) compressed videos by jointly exploiting spatial details and temporal structure (SDTS).
no code implementations • 20 Dec 2018 • Yinglong Wang, Shuaicheng Liu, Chen Chen, Dehua Xie, Bing Zeng
We present a novel rain removal method in this paper, which consists of two steps, i. e., detection of rain streaks and reconstruction of the rain-removed image.
no code implementations • 19 Dec 2018 • Yinglong Wang, Shuaicheng Liu, Bing Zeng
Removing rain streaks from a single image continues to draw attentions today in outdoor vision systems.
1 code implementation • CVPR 2019 • Jiaxiong Qiu, Zhaopeng Cui, yinda zhang, Xingdi Zhang, Shuaicheng Liu, Bing Zeng, Marc Pollefeys
In this paper, we propose a deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth.
2 code implementations • 22 Nov 2018 • Xiandong Meng, Xuan Deng, Shuyuan Zhu, Shuaicheng Liu, Chuan Wang, Chen Chen, Bing Zeng
In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames.
no code implementations • 29 Oct 2018 • Haozhen Dong, Liang Gao, Xinyu Li, Haoran Zhong, Bing Zeng
Differential evolution(DE) is a conventional algorithm with fast convergence speed.
no code implementations • 27 Jun 2018 • Yingyu Zhang, Bing Zeng
In addition, the time complexity of the proposed algorithm is the same as that of MOEA/D, and lower than that of other known MOEAs, since it considers only individuals within the current neighborhood at each update.
no code implementations • 9 Apr 2018 • Bing Zeng, Xinyu Li, Liang Gao, Yuyan Zhang, Haozhen Dong
However, there are two difficulties urgently to be solved for most existing niching metaheuristic algorithms: how to set the optimal values of niching parameters for different optimization problems, and how to jump out of the local optima efficiently.
no code implementations • 25 Jan 2018 • Yingyu Zhang, Bing Zeng, Yuanzhen Li, Junqing Li
The decomposition-based MOEAs emphasize convergence and diversity in a simple model and have made a great success in dealing with theoretical and practical multi- or many-objective optimization problems.
no code implementations • 30 Aug 2017 • Lijun Zhao, Huihui Bai, Jie Liang, Bing Zeng, Anhong Wang, Yao Zhao
Firstly, given the low-resolution depth image and low-resolution color image, a generative network is proposed to leverage mutual information of color image and depth image to enhance each other in consideration of the geometry structural dependency of color-depth image in the same scene.
no code implementations • 8 Aug 2017 • Linxiao Yang, Jun Fang, Huiping Duan, Hongbin Li, Bing Zeng
The problem of low rank matrix completion is considered in this paper.
no code implementations • 11 Feb 2017 • Bing Zeng, Liang Gao, Xinyu Li
Increasing nature-inspired metaheuristic algorithms are applied to solving the real-world optimization problems, as they have some advantages over the classical methods of numerical optimization.
no code implementations • 15 Nov 2015 • Linxiao Yang, Jun Fang, Hongbin Li, Bing Zeng
In this paper, we focus on Tucker decomposition which represents an Nth-order tensor in terms of N factor matrices and a core tensor via multilinear operations.