no code implementations • 29 Mar 2024 • Yunhao Li, Jing Wu, Lingzhe Zhao, Peidong Liu
When capturing images through the glass during rainy or snowy weather conditions, the resulting images often contain waterdrops adhered on the glass surface, and these waterdrops significantly degrade the image quality and performance of many computer vision algorithms.
1 code implementation • 29 Mar 2024 • Yunhao Li, Xiaodong Wang, Ping Wang, Xin Yuan, Peidong Liu
SCI is a cost-effective method that enables the recording of high-dimensional data, such as hyperspectral or temporal information, into a single image using low-cost 2D imaging sensors.
1 code implementation • 25 Mar 2024 • Yin Zhang, Jinhong Deng, Peidong Liu, Wen Li, Shiyu Zhao
A new benchmark for cross-domain MAV detection is proposed based on the proposed dataset.
1 code implementation • 18 Mar 2024 • Lingzhe Zhao, Peng Wang, Peidong Liu
In this paper, we introduce a novel approach, named BAD-Gaussians (Bundle Adjusted Deblur Gaussian Splatting), which leverages explicit Gaussian representation and handles severe motion-blurred images with inaccurate camera poses to achieve high-quality scene reconstruction.
2 code implementations • 15 Mar 2024 • Zhiqi Li, Yiming Chen, Lingzhe Zhao, Peidong Liu
Building upon our MVControl architecture, we employ a unique hybrid diffusion guidance method to direct the optimization process.
no code implementations • 27 Nov 2023 • Yiming Chen, Zhiqi Li, Peidong Liu
The main insight is that we exploit the images generated by a large pre-trained text-to-image diffusion model, to supervise the training of a text conditioned 3D generative adversarial network.
no code implementations • 25 Nov 2023 • Haotian Luo, Yixin Liu, Peidong Liu, Xianggen Liu
Therefore, we present vector-quantized prompts as the cues to control the generation of pre-trained models.
1 code implementation • 24 Nov 2023 • Zhiqi Li, Yiming Chen, Lingzhe Zhao, Peidong Liu
Our approach enables the generation of controllable multi-view images and view-consistent 3D content.
1 code implementation • 4 Oct 2023 • Moyang Li, Peng Wang, Lingzhe Zhao, Bangyan Liao, Peidong Liu
USB-NeRF is able to correct rolling shutter distortions and recover accurate camera motion trajectory simultaneously under the framework of NeRF, by modeling the physical image formation process of a RS camera.
no code implementations • 27 Nov 2022 • Zhenjun Zhao, Yu Zhai, Ben M. Chen, Peidong Liu
Local feature detection is a key ingredient of many image processing and computer vision applications, such as visual odometry and localization.
1 code implementation • CVPR 2023 • Peng Wang, Lingzhe Zhao, Ruijie Ma, Peidong Liu
Our approach models the physical image formation process of a motion blurred image, and jointly learns the parameters of NeRF and recovers the camera motion trajectories during exposure time.
no code implementations • 7 Jul 2021 • Peidong Liu, Zibin He, Xiyu Yan, Yong Jiang, Shutao Xia, Feng Zheng, Maowei Hu
In this work, we propose an effective weakly-supervised video semantic segmentation pipeline with click annotations, called WeClick, for saving laborious annotating effort by segmenting an instance of the semantic class with only a single click.
3 code implementations • 7 Jul 2021 • YanJie Li, Sen yang, Peidong Liu, Shoukui Zhang, Yunxiao Wang, Zhicheng Wang, Wankou Yang, Shu-Tao Xia
The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance.
no code implementations • ICCV 2021 • Peidong Liu, Xingxing Zuo, Viktor Larsson, Marc Pollefeys
Motion blur is one of the major challenges remaining for visual odometry methods.
1 code implementation • ICLR 2021 • Peidong Liu, Gengwei Zhang, Bochao Wang, Hang Xu, Xiaodan Liang, Yong Jiang, Zhenguo Li
For object detection, the well-established classification and regression loss functions have been carefully designed by considering diverse learning challenges.
1 code implementation • CVPR 2020 • Peidong Liu, Zhaopeng Cui, Viktor Larsson, Marc Pollefeys
The dense displacement field from a rolling shutter image to its corresponding global shutter image is estimated via a motion estimation network.
1 code implementation • 10 Feb 2020 • Peidong Liu, Joel Janai, Marc Pollefeys, Torsten Sattler, Andreas Geiger
Motion blurry images challenge many computer vision algorithms, e. g, feature detection, motion estimation, or object recognition.
no code implementations • 5 Nov 2019 • Peidong Liu, Xiyu Yan, Yong Jiang, Shu-Tao Xia
The deep learning-based visual tracking algorithms such as MDNet achieve high performance leveraging to the feature extraction ability of a deep neural network.
1 code implementation • 5 Nov 2019 • Yiming Li, Peidong Liu, Yong Jiang, Shu-Tao Xia
To a large extent, the privacy of visual classification data is mainly in the mapping between the image and its corresponding label, since this relation provides a great amount of information and can be used in other scenarios.
no code implementations • 7 May 2019 • Ioan Andrei Bârsan, Peidong Liu, Marc Pollefeys, Andreas Geiger
We use both instance-aware semantic segmentation and sparse scene flow to classify objects as either background, moving, or potentially moving, thereby ensuring that the system is able to model objects with the potential to transition from static to dynamic, such as parked cars.
no code implementations • 17 Sep 2018 • Marcel Geppert, Peidong Liu, Zhaopeng Cui, Marc Pollefeys, Torsten Sattler
This results in a system that provides reliable and drift-less pose estimations for high speed autonomous driving.
Robotics