Zobrazeno 1 - 10
of 218
pro vyhledávání: '"Zhao Zixiang"'
Publikováno v:
Zhongguo quanke yixue, Vol 26, Iss 10, Pp 1278-1281 (2023)
Intimate partner violence (IPV) is the most common type of domestic violence, which not only harms the victim's physical and mental health and life safety but also leads to the degradation of marriage, family, and children's development. IPV occurs a
Externí odkaz:
https://doaj.org/article/aa3de05c2caa47b88ae3c97c9504a6c5
Autor:
Xu, Shuang, Zhao, Zixiang, Bai, Haowen, Yu, Chang, Peng, Jiangjun, Cao, Xiangyong, Meng, Deyu
Hyperspectral images (HSIs) are frequently noisy and of low resolution due to the constraints of imaging devices. Recently launched satellites can concurrently acquire HSIs and panchromatic (PAN) images, enabling the restoration of HSIs to generate c
Externí odkaz:
http://arxiv.org/abs/2412.04201
Autor:
Bai, Haowen, Zhang, Jiangshe, Zhao, Zixiang, Wu, Yichen, Deng, Lilun, Cui, Yukun, Feng, Tao, Xu, Shuang
Multi-modal image fusion aggregates information from multiple sensor sources, achieving superior visual quality and perceptual characteristics compared to any single source, often enhancing downstream tasks. However, current fusion methods for downst
Externí odkaz:
http://arxiv.org/abs/2412.03240
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing, vol. 62, art. no. 5528714, 2024
This paper introduces a novel paradigm for hyperspectral image (HSI) denoising, which is termed \textit{pan-denoising}. In a given scene, panchromatic (PAN) images capture similar structures and textures to HSIs but with less noise. This enables the
Externí odkaz:
http://arxiv.org/abs/2407.06064
Autor:
Yang, Yixuan, Lu, Junru, Zhao, Zixiang, Luo, Zhen, Yu, James J. Q., Sanchez, Victor, Zheng, Feng
Designing 3D indoor layouts is a crucial task with significant applications in virtual reality, interior design, and automated space planning. Existing methods for 3D layout design either rely on diffusion models, which utilize spatial relationship p
Externí odkaz:
http://arxiv.org/abs/2406.03866
Autor:
Zheng, Xingyu, Liu, Xianglong, Qin, Haotong, Ma, Xudong, Zhang, Mingyuan, Hao, Haojie, Wang, Jiakai, Zhao, Zixiang, Guo, Jinyang, Magno, Michele
With the advancement of diffusion models (DMs) and the substantially increased computational requirements, quantization emerges as a practical solution to obtain compact and efficient low-bit DMs. However, the highly discrete representation leads to
Externí odkaz:
http://arxiv.org/abs/2404.05662
Autor:
Bian, Ang, Li, Wei, Yuan, Hangjie, Yu, Chengrong, Wang, Mang, Zhao, Zixiang, Lu, Aojun, Ji, Pengliang, Feng, Tao
Model generalization ability upon incrementally acquiring dynamically updating knowledge from sequentially arriving tasks is crucial to tackle the sensitivity-stability dilemma in Continual Learning (CL). Weight loss landscape sharpness minimization
Externí odkaz:
http://arxiv.org/abs/2404.00986
Autor:
Zhao, Zixiang, Deng, Lilun, Bai, Haowen, Cui, Yukun, Zhang, Zhipeng, Zhang, Yulun, Qin, Haotong, Chen, Dongdong, Zhang, Jiangshe, Wang, Peng, Van Gool, Luc
Image fusion integrates essential information from multiple images into a single composite, enhancing structures, textures, and refining imperfections. Existing methods predominantly focus on pixel-level and semantic visual features for recognition,
Externí odkaz:
http://arxiv.org/abs/2402.02235
Autor:
Bai, Haowen, Zhao, Zixiang, Zhang, Jiangshe, Wu, Yichen, Deng, Lilun, Cui, Yukun, Xu, Shuang, Jiang, Baisong
Image fusion aims to combine information from multiple source images into a single one with more comprehensive informational content. The significant challenges for deep learning-based image fusion algorithms are the lack of a definitive ground truth
Externí odkaz:
http://arxiv.org/abs/2312.07943
Autor:
Xu, Shuang, Wang, Yifan, Zhao, Zixiang, Peng, Jiangjun, Cao, Xiangyong, Meng, Deyu, Zhang, Yulun, Timofte, Radu, Van Gool, Luc
Owing to its significant success, the prior imposed on gradient maps has consistently been a subject of great interest in the field of image processing. Total variation (TV), one of the most representative regularizers, is known for its ability to ca
Externí odkaz:
http://arxiv.org/abs/2308.16612