no code implementations • 24 Nov 2023 • Yuanfeng Ji, Chongjian Ge, Weikai Kong, Enze Xie, Zhengying Liu, Zhengguo Li, Ping Luo
In this work, we address the limitations via Auto-Bench, which delves into exploring LLMs as proficient aligners, measuring the alignment between VLMs and human intelligence and value through automatic data curation and assessment.
1 code implementation • 13 Nov 2023 • Shuwei Shao, Zhongcai Pei, Weihai Chen, Peter C. Y. Chen, Zhengguo Li
To this end, we develop a normal-distance head that outputs pixel-level surface normal and distance.
1 code implementation • 13 Nov 2023 • Shuwei Shao, Zhongcai Pei, Weihai Chen, Dingchi Sun, Peter C. Y. Chen, Zhengguo Li
Because the depth ground-truth is unavailable in the training phase, we develop a pseudo ground-truth diffusion process to assist the diffusion in MonoDiffusion.
1 code implementation • NeurIPS 2023 • Shuwei Shao, Zhongcai Pei, Xingming Wu, Zhong Liu, Weihai Chen, Zhengguo Li
To alleviate the possible error accumulation during the iterative process, we utilize a novel elastic target bin to replace the original target bin, the width of which is adjusted elastically based on the depth uncertainty.
Ranked #13 on Monocular Depth Estimation on KITTI Eigen split
1 code implementation • ICCV 2023 • Shuwei Shao, Zhongcai Pei, Weihai Chen, Xingming Wu, Zhengguo Li
Meanwhile, the normal and distance are regularized by a developed plane-aware consistency constraint.
Ranked #13 on Monocular Depth Estimation on KITTI Eigen split
no code implementations • 30 Aug 2023 • Jianwu Fang, iahuan Qiao, Jianru Xue, Zhengguo Li
We present the first survey on Vision-TAD in the deep learning era and the first-ever survey for Vision-TAA.
no code implementations • 18 Aug 2023 • Ruibing Jin, Guosheng Lin, Min Wu, Jie Lin, Zhengguo Li, XiaoLi Li, Zhenghua Chen
To address this issue, we propose an unlimited knowledge distillation (UKD) in this paper.
2 code implementations • 21 Jun 2023 • Lin Xi, Weihai Chen, Xingming Wu, Zhong Liu, Zhengguo Li
Online unsupervised video object segmentation (UVOS) uses the previous frames as its input to automatically separate the primary object(s) from a streaming video without using any further manual annotation.
2 code implementations • 7 Apr 2023 • Xiaoming Zhao, Xingming Wu, Weihai Chen, Peter C. Y. Chen, Qingsong Xu, Zhengguo Li
Image keypoints and descriptors play a crucial role in many visual measurement tasks.
1 code implementation • 16 Feb 2023 • Shuwei Shao, Zhongcai Pei, Weihai Chen, Ran Li, Zhong Liu, Zhengguo Li
Specifically, we use the depth estimates from the Transformer branch and the CNN branch as pseudo labels to teach each other.
Ranked #13 on Monocular Depth Estimation on KITTI Eigen split
no code implementations • 13 Sep 2022 • Zhengguo Li, Chaobing Zheng, Haiyan Shu, Shiqian Wu
Model-based single image dehazing algorithms restore haze-free images with sharp edges and rich details for real-world hazy images at the expense of low PSNR and SSIM values for synthetic hazy images.
no code implementations • 30 May 2022 • Shuwei Shao, Zhongcai Pei, Weihai Chen, Xingming Wu, Zhong Liu, Zhengguo Li
Unsupervised monocular trained depth estimation models make use of adjacent frames as a supervisory signal during the training phase.
1 code implementation • 6 Apr 2022 • Lin Xi, Weihai Chen, Xingming Wu, Zhong Liu, Zhengguo Li
Unsupervised video object segmentation (UVOS) aims at automatically separating the primary foreground object(s) from the background in a video sequence.
no code implementations • 19 Feb 2022 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Jianxiong Yin, Zhenghua Chen, XiaoLi Li, Zhengguo Li, Qianwen Xu
While action recognition (AR) has gained large improvements with the introduction of large-scale video datasets and the development of deep neural networks, AR models robust to challenging environments in real-world scenarios are still under-explored.
no code implementations • 18 Jan 2022 • Yuwen Li, Zhengguo Li, Chaobing Zheng, Shiqian Wu
In order to preserve the edges accurately in the refined depth map, the guidance image is constructed from the multi-focus image sequence, and the coefficient of the AWGIF is utilized to suppress the noise while enhancing the fine depth details.
Ranked #8 on Spectral Reconstruction on ARAD-1K
no code implementations • 31 Dec 2021 • Xiaoming Zhao, Weihai Chen, Xingming Wu, Peter C. Y. Chen, Zhengguo Li
Deep stereo matching has made significant progress in recent years.
no code implementations • 25 Dec 2021 • Ziyang Liu, Zhengguo Li, Xingming Wu, Zhong Liu, Weihai Chen
The proposed method, named DSRGAN, includes a well designed detail extraction algorithm to capture the most important high frequency information from images.
2 code implementations • 6 Dec 2021 • Xiaoming Zhao, Xingming Wu, Jinyu Miao, Weihai Chen, Peter C. Y. Chen, Zhengguo Li
The reprojection loss is then proposed to directly optimize these sub-pixel keypoints, and the dispersity peak loss is presented for accurate keypoints regularization.
no code implementations • 22 Nov 2021 • Zhengguo Li, Chaobing Zheng, Haiyan Shu, Shiqian Wu
Model-based single image dehazing algorithms restore images with sharp edges and rich details at the expense of low PSNR values.
1 code implementation • 20 Nov 2021 • Ziyang Liu, Jingmeng Liu, Weihai Chen, Xingming Wu, Zhengguo Li
A FAMINet, which consists of a feature extraction network (F), an appearance network (A), a motion network (M), and an integration network (I), is proposed in this study to address the abovementioned problem.
no code implementations • 17 Nov 2021 • Xiaoming Zhao, Jingmeng Liu, Xingming Wu, Weihai Chen, Fanghong Guo, Zhengguo Li
Keypoints matching is a pivotal component for many image-relevant applications such as image stitching, visual simultaneous localization and mapping (SLAM), and so on.
no code implementations • 14 Nov 2021 • Yilun Xu, Ziyang Liu, Xingming Wu, Weihai Chen, Changyun Wen, Zhengguo Li
For the former challenge, a spatially varying convolution (SVC) is designed to process the Bayer images carried with varying exposures.
no code implementations • 14 Nov 2021 • Yilun Xu, Zhengguo Li, Weihai Chen, Changyun Wen
It is challenging to align the brightness distribution of the images with different exposures due to possible color distortion and loss of details in the brightest and darkest regions of input images.
no code implementations • 11 Nov 2021 • Chaobing Zheng, Zhengguo Li, Shiqian Wu
It is an ill-posed problem to restore the saturated regions of the LDR image.
no code implementations • 10 Nov 2021 • Zhengguo Li, Haiyan Shu, Chaobing Zheng
Ambiguity between object radiance and haze and noise amplification in sky regions are two inherent problems of model driven single image dehazing.
no code implementations • 30 Jul 2021 • Haosong Yue, Jinyu Miao, Weihai Chen, Wei Wang, Fanghong Guo, Zhengguo Li
Localizing pre-visited places during long-term simultaneous localization and mapping, i. e. loop closure detection (LCD), is a crucial technique to correct accumulated inconsistencies.
Loop Closure Detection Simultaneous Localization and Mapping
no code implementations • 18 Jan 2021 • Rooholla Khorrambakht, Chris Xiaoxuan Lu, Hamed Damirchi, Zhenghua Chen, Zhengguo Li
Inertial Measurement Units (IMUs) are interceptive modalities that provide ego-motion measurements independent of the environmental factors.
no code implementations • 4 Jul 2020 • Chaobing Zheng, Zhengguo Li, Yi Yang, Shiqian Wu
In this paper, a single image brightening algorithm is introduced to brighten such an image.
no code implementations • 13 Jul 2019 • Lei Zhang, Weihai Chen, Chao Hu, Xingming Wu, Zhengguo Li
In this paper, a lightweight yet efficient network (S\&CNet) is proposed to obtain a good trade-off between efficiency and accuracy for the dense depth completion.
no code implementations • 9 May 2019 • Chaobing Zheng, Zhengguo Li, Shiqian Wu
A natural question raised here is "Is there any space for conventional methods on these problems?"
no code implementations • 8 Nov 2018 • Mingyang Guan, Zhengguo Li, Renjie He, Changyun Wen
This is achieved due to the attribute of Convolution Theorem that the correlation in spatial domain corresponds to an element-wise product in the Fourier domain, resulting in that the l1-norm optimization problem could be decomposed into multiple sub-optimization spaces in the Fourier domain.
no code implementations • 27 Oct 2018 • Kar-Ann Toh, Zhiping Lin, Zhengguo Li, Beomseok Oh, Lei Sun
In this article, we show that solving the system of linear equations by manipulating the kernel and the range space is equivalent to solving the problem of least squares error approximation.
no code implementations • 17 May 2018 • Jun Cheng, Zhengguo Li, Zaiwang Gu, Huazhu Fu, Damon Wing Kee Wong, Jiang Liu
It often obscures the details in the retinal images and posts challenges in retinal image processing and analysing tasks.