Airtight
发表于 2025-3-28 17:59:50
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Resultsask was to super-resolve an input image with a magnification factor .4 based on a set of prior examples of low and corresponding high resolution images. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption wh
Herd-Immunity
发表于 2025-3-28 20:14:45
http://reply.papertrans.cn/24/2343/234236/234236_42.png
先行
发表于 2025-3-29 02:54:20
Efficient Image Super-Resolution Using Pixel Attentionretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention (PA) is similar as channel attention and spatial attention in formulation. The difference is that PA produces 3D attention maps instead of a 1D attention vector or a 2D map. This attention scheme introd
合法
发表于 2025-3-29 04:02:51
LarvaNet: Hierarchical Super-Resolution via Multi-exit Architectureoften difficult to apply them in resource-constrained environments due to the requirement of heavy computation and huge storage capacity. To address this issue, we propose an efficient network model for SR, called LarvaNet. First, we investigate a number of architectural factors for a baseline model
faucet
发表于 2025-3-29 07:33:26
http://reply.papertrans.cn/24/2343/234236/234236_45.png
Metamorphosis
发表于 2025-3-29 12:35:06
Multi-attention Based Ultra Lightweight Image Super-Resolutionthods with remarkable performance, but their memory and computational cost are hindrances in practical usage. To tackle this problem, we propose a Multi-Attentive Feature Fusion Super-Resolution Network (MAFFSRN). MAFFSRN consists of proposed feature fusion groups (FFGs) that serve as a feature extr
apiary
发表于 2025-3-29 16:32:13
http://reply.papertrans.cn/24/2343/234236/234236_47.png
endarterectomy
发表于 2025-3-29 21:00:35
IdleSR: Efficient Super-Resolution Network with Multi-scale IdleBlocksire high computational and memory resources beyond the capability of most mobile and embedded devices. How to significantly reduce the number of operations and parameters while maintaining the performance is a meaningful and challenging problem. To address this problem, we propose an efficient super
photopsia
发表于 2025-3-30 03:55:29
http://reply.papertrans.cn/24/2343/234236/234236_49.png
线
发表于 2025-3-30 06:05:44
http://reply.papertrans.cn/24/2343/234236/234236_50.png