Výsledky vyhledávání

Report

Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs

Autor: Cui, Qinpeng, Liu, Yixuan, Zhang, Xinyi, Bao, Qiqi, Wang, Zhongdao, Liao, Qingmin, Wang, Li, Lu, Tian, Barsoum, Emad

Diffusion-based image super-resolution (SR) models have attracted substantial interest due to their powerful image restoration capabilities. However, prevailing diffusion models often struggle to strike an optimal balance between efficiency and perfo

Externí odkaz: http://arxiv.org/abs/2409.17778

Zobrazit plný text záznamu

Report

Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network

Autor: Zhang, Xinyi, Bao, Qiqi, Cui, Qinpeng, Yang, Wenming, Liao, Qingmin

Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. To resolve

Externí odkaz: http://arxiv.org/abs/2408.02922

Zobrazit plný text záznamu

Report

RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark

Autor: Deng, Zhuo, Cai, Yuanhao, Chen, Lu, Gong, Zheng, Bao, Qiqi, Yao, Xue, Fang, Dong, Zhang, Shaochong, Ma, Lan

Ophthalmologists have used fundus images to screen and diagnose eye diseases. However, different equipments and ophthalmologists pose large variations to the quality of fundus images. Low-quality (LQ) degraded fundus images easily lead to uncertainty

Externí odkaz: http://arxiv.org/abs/2201.00466

Zobrazit plný text záznamu