Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Guo, Mengxi"'
We present MambaCSR, a simple but effective framework based on Mamba for the challenging compressed image super-resolution (CSR) task. Particularly, the scanning strategies of Mamba are crucial for effective contextual knowledge modeling in the resto
Externí odkaz:
http://arxiv.org/abs/2408.11758
Autor:
Ren, Yulin, Li, Xin, Li, Bingchen, Wang, Xingrui, Guo, Mengxi, Zhao, Shijie, Zhang, Li, Chen, Zhibo
We present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adaptability and universality for d
Externí odkaz:
http://arxiv.org/abs/2407.10833
Autor:
Li, Bingchen, Li, Xin, Lu, Yiting, Feng, Ruoyu, Guo, Mengxi, Zhao, Shijie, Zhang, Li, Chen, Zhibo
Blind Compressed Image Restoration (CIR) has garnered significant attention due to its practical applications. It aims to mitigate compression artifacts caused by unknown quality factors, particularly with JPEG codecs. Existing works on blind CIR oft
Externí odkaz:
http://arxiv.org/abs/2404.17433
Adaptive video streaming requires efficient bitrate ladder construction to meet heterogeneous network conditions and end-user demands. Per-title optimized encoding typically traverses numerous encoding parameters to search the Pareto-optimal operatin
Externí odkaz:
http://arxiv.org/abs/2401.04405
Autor:
Ma, Rui, Guo, Mengxi, Yuming, Li, Zhang, Hengyuan, Ma, Cong, Li, Yuan, Xie, Xiaodong, Zhang, Shanghang
Integrating watermarks into generative images is a critical strategy for protecting intellectual property and enhancing artificial intelligence security. This paper proposes Plug-in Generative Watermarking (PiGW) as a general framework for integratin
Externí odkaz:
http://arxiv.org/abs/2403.12053
Most video platforms provide video streaming services with different qualities, and the quality of the services is usually adjusted by the resolution of the videos. So high-resolution videos need to be downsampled for compression. In order to solve t
Externí odkaz:
http://arxiv.org/abs/2306.04202
High-resolution (HR) images are usually downscaled to low-resolution (LR) ones for better display and afterward upscaled back to the original size to recover details. Recent work in image rescaling formulates downscaling and upscaling as a unified ta
Externí odkaz:
http://arxiv.org/abs/2303.02353
Blind watermarking provides powerful evidence for copyright protection, image authentication, and tampering identification. However, it remains a challenge to design a watermarking model with high imperceptibility and robustness against strong noise
Externí odkaz:
http://arxiv.org/abs/2212.12678
Graphic design is ubiquitous in people's daily lives. For graphic design, the most time-consuming task is laying out various components in the interface. Repetitive manual layout design will waste a lot of time for professional graphic designers. Exi
Externí odkaz:
http://arxiv.org/abs/2110.06794
Autor:
Yang, Ren, Timofte, Radu, Liu, Jing, Xu, Yi, Zhang, Xinjian, Zhao, Minyi, Zhou, Shuigeng, Chan, Kelvin C. K., Zhou, Shangchen, Xu, Xiangyu, Loy, Chen Change, Li, Xin, Liu, Fanglong, Zheng, He, Jiang, Lielin, Zhang, Qi, He, Dongliang, Li, Fu, Dang, Qingqing, Huang, Yibin, Maggioni, Matteo, Fu, Zhongqian, Xiao, Shuai, li, Cheng, Tanay, Thomas, Song, Fenglong, Chao, Wentao, Guo, Qiang, Liu, Yan, Li, Jiang, Qu, Xiaochao, Hou, Dewang, Yang, Jiayu, Jiang, Lyn, You, Di, Zhang, Zhenyu, Mou, Chong, Koshelev, Iaroslav, Ostyakov, Pavel, Somov, Andrey, Hao, Jia, Zou, Xueyi, Zhao, Shijie, Sun, Xiaopeng, Liao, Yiting, Zhang, Yuanzhi, Wang, Qing, Zhan, Gen, Guo, Mengxi, Li, Junlin, Lu, Ming, Ma, Zhan, Michelini, Pablo Navarrete, Wang, Hai, Chen, Yiyun, Guo, Jingyu, Zhang, Liliang, Yang, Wenming, Kim, Sijung, Oh, Syehoon, Wang, Yucong, Cai, Minjie, Hao, Wei, Shi, Kangdi, Li, Liangyan, Chen, Jun, Gao, Wei, Liu, Wang, Zhang, Xiaoyu, Zhou, Linjie, Lin, Sixin, Wang, Ru
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks.
Externí odkaz:
http://arxiv.org/abs/2104.10781