The baseline method in NTIRE2024_ESR is RLFN (Kong, et al, 2022), the winner of NTIRE2022 Efficient Super-Resolution Challenge. Details are shown below: 🏆 Main-track: Overall Performance (Runtime, Parameters, FLOPs,) the aim is to obtain a network design / solution with the best ...
● Efficient Super Resolution ● Image Super Resolution (x4) ● Light Field Image Super-Resolution ● Stereo Image Super-Resolution ● HR Depth from Images of Specular and Transparent Surfaces ● Bracketing Image Restoration and Enhancement ● Portrait Quality Assessment ...
团队采用了潘金山老师团队的工作FFTformer(Efficient frequency domain-based transformers for high-quality image deblurring),这里团队应该是分析过数据特征找到主要的劣化来自于blur,并且这种blur并不是单纯的虚焦模糊,而是有很多光学成像素质引入的模糊,因此特别需要不设限的模糊核估计。 团队放开了以往去模糊/超分工作中...
DVMSR: Distillated Vision Mamba for Efficient Super-Resolution CVPRW 2024 Xiaoyan Lei, Wenlong Zhang, Weifeng Cao Abstract Efficient Image Super-Resolution (SR) aims to accelerate SR network inference by minimizing computational complexity and network parameters while preserving performance. Existing state...
In collaboration with the NTIRE workshop, we are hosting a challenge focused on Efficient Super-Resolution (NTIRE2024_ESR). This involves the task of enhancing the resolution of an input image by a factor of x4, utilizing a set of pre-existing examples comprising both low-resolution and their...
The baseline method in NTIRE2025_ESR is EFDN (Wang Yan, 2023), the 1st place for the overall performance of NTIRE2023 Efficient Super-Resolution Challenge. Details are shown below: 🏆 Main-track: Overall Performance (Runtime, Parameters, FLOPs,) the aim is to obtain a network design / ...