Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Luo, Zhengxiong"'
Autor:
Wang, Xinlong, Zhang, Xiaosong, Luo, Zhengxiong, Sun, Quan, Cui, Yufeng, Wang, Jinsheng, Zhang, Fan, Wang, Yueze, Li, Zhen, Yu, Qiying, Zhao, Yingli, Ao, Yulong, Min, Xuebin, Li, Tao, Wu, Boya, Zhao, Bo, Zhang, Bowen, Wang, Liangdong, Liu, Guang, He, Zheqi, Yang, Xi, Liu, Jingjing, Lin, Yonghua, Huang, Tiejun, Wang, Zhongyuan
While next-token prediction is considered a promising path towards artificial general intelligence, it has struggled to excel in multimodal tasks, which are still dominated by diffusion models (e.g., Stable Diffusion) and compositional approaches (e.
Externí odkaz:
http://arxiv.org/abs/2409.18869
Autor:
Sun, Quan, Cui, Yufeng, Zhang, Xiaosong, Zhang, Fan, Yu, Qiying, Luo, Zhengxiong, Wang, Yueze, Rao, Yongming, Liu, Jingjing, Huang, Tiejun, Wang, Xinlong
The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the task-agnostic in-
Externí odkaz:
http://arxiv.org/abs/2312.13286
Publikováno v:
International Journal of Computer Vision (IJCV) 2023
Blind Super-Resolution (SR) usually involves two sub-problems: 1) estimating the degradation of the given low-resolution (LR) image; 2) super-resolving the LR image to its high-resolution (HR) counterpart. Both problems are ill-posed due to the infor
Externí odkaz:
http://arxiv.org/abs/2308.08816
Autor:
Luo, Zhengxiong, Chen, Dayou, Zhang, Yingya, Huang, Yan, Wang, Liang, Shen, Yujun, Zhao, Deli, Zhou, Jingren, Tan, Tieniu
A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data distribution. Despite
Externí odkaz:
http://arxiv.org/abs/2303.08320
Synthetic high-resolution (HR) \& low-resolution (LR) pairs are widely used in existing super-resolution (SR) methods. To avoid the domain gap between synthetic and test images, most previous methods try to adaptively learn the synthesizing (degradin
Externí odkaz:
http://arxiv.org/abs/2203.04962
Image downscaling and upscaling are two basic rescaling operations. Once the image is downscaled, it is difficult to be reconstructed via upscaling due to the loss of information. To make these two processes more compatible and improve the reconstruc
Externí odkaz:
http://arxiv.org/abs/2111.05133
Most existing human pose estimation (HPE) methods exploit multi-scale information by fusing feature maps of four different spatial sizes, \ie $1/4$, $1/8$, $1/16$, and $1/32$ of the input image. There are two drawbacks of this strategy: 1) feature ma
Externí odkaz:
http://arxiv.org/abs/2107.10477
Publikováno v:
Pattern Recognition, Volume 127, July 2022, 108613
Most deep learning-based super-resolution (SR) methods are not image-specific: 1) They are trained on samples synthesized by predefined degradations (e.g. bicubic downsampling), regardless of the domain gap between training and testing data. 2) Durin
Externí odkaz:
http://arxiv.org/abs/2107.02398
Publikováno v:
In Neurocomputing 14 May 2024 582
Previous methods decompose the blind super-resolution (SR) problem into two sequential steps: \textit{i}) estimating the blur kernel from given low-resolution (LR) image and \textit{ii}) restoring the SR image based on the estimated kernel. This two-
Externí odkaz:
http://arxiv.org/abs/2105.06878