Výsledky vyhledávání

Report

DemMamba: Alignment-free Raw Video Demoireing with Frequency-assisted Spatio-Temporal Mamba

Autor: Xu, Shuning, Liu, Xina, Song, Binbin, Chen, Xiangyu, Chen, Qiubo, Zhou, Jiantao

Moire patterns, resulting from the interference of two similar repetitive patterns, are frequently observed during the capture of images or videos on screens. These patterns vary in color, shape, and location across video frames, posing challenges in

Externí odkaz: http://arxiv.org/abs/2408.10679

Zobrazit plný text záznamu

Report

Image Demoireing in RAW and sRGB Domains

Autor: Xu, Shuning, Song, Binbin, Chen, Xiangyu, Liu, Xina, Zhou, Jiantao

Moire patterns frequently appear when capturing screens with smartphones or cameras, potentially compromising image quality. Previous studies suggest that moire pattern elimination in the RAW domain offers greater effectiveness compared to demoireing

Externí odkaz: http://arxiv.org/abs/2312.09063

Zobrazit plný text záznamu

Report

UDC-UNet: Under-Display Camera Image Restoration via U-Shape Dynamic Network

Autor: Liu, Xina, Hu, Jinfan, Chen, Xiangyu, Dong, Chao

Under-Display Camera (UDC) has been widely exploited to help smartphones realize full screen display. However, as the screen could inevitably affect the light propagation process, the images captured by the UDC system usually contain flare, haze, blu

Externí odkaz: http://arxiv.org/abs/2209.01809

Zobrazit plný text záznamu

Report

Reflash Dropout in Image Super-Resolution

Autor: Kong, Xiangtao, Liu, Xina, Gu, Jinjin, Qiao, Yu, Dong, Chao

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as high-level task

Externí odkaz: http://arxiv.org/abs/2112.12089

Zobrazit plný text záznamu