Výsledky vyhledávání - "Zhang, Mingjian"

Report

Multi-Scale Implicit Transformer with Re-parameterize for Arbitrary-Scale Super-Resolution

Autor: Zhu, Jinchen, Zhang, Mingjian, Zheng, Ling, Weng, Shizhuang

Recently, the methods based on implicit neural representations have shown excellent capabilities for arbitrary-scale super-resolution (ASSR). Although these methods represent the features of an image by generating latent codes, these latent codes are

Externí odkaz: http://arxiv.org/abs/2403.06536

Zobrazit plný text záznamu

Report

Image Super-Resolution using Efficient Striped Window Transformer

Autor: Shi, Jinpeng, Li, Hui, Liu, Tianle, Liu, Yulong, Zhang, Mingjian, Zhu, Jinchen, Zheng, Ling, Weng, Shizhuang

Transformers have achieved remarkable results in single-image super-resolution (SR). However, the challenge of balancing model performance and complexity has hindered their application in lightweight SR (LSR). To tackle this challenge, we propose an

Externí odkaz: http://arxiv.org/abs/2301.09869

Zobrazit plný text záznamu