A dynamic multi-scale voxel flow network for video prediction
The performance of video prediction has been greatly boosted by advanced deep neural
networks. However, most of the current methods suffer from large model sizes and require …
networks. However, most of the current methods suffer from large model sizes and require …
Semi-cycled generative adversarial networks for real-world face super-resolution
Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-
cycled Cycle-GAN architecture is widely employed to achieve promising performance on …
cycled Cycle-GAN architecture is widely employed to achieve promising performance on …
CAMixerSR: Only Details Need More" Attention"
To satisfy the rapidly increasing demands on the large image (2K-8K) super-resolution (SR)
prevailing methods follow two independent tracks: 1) accelerate existing networks by …
prevailing methods follow two independent tracks: 1) accelerate existing networks by …
Scale-adaptive feature aggregation for efficient space-time video super-resolution
Abstract The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual
quality of videos, by simultaneously performing video frame interpolation (VFI) and video …
quality of videos, by simultaneously performing video frame interpolation (VFI) and video …
DF3Net: Dual frequency feature fusion network with hierarchical transformer for image inpainting
In recent years, researchers have made significant strides in computer vision by leveraging
transformers, achieving remarkable breakthroughs in low-level vision tasks. The inherent …
transformers, achieving remarkable breakthroughs in low-level vision tasks. The inherent …
Lightweight improved residual network for efficient inverse tone mapping
The display devices like HDR10 televisions are increasingly prevalent in our daily life for
visualizing high dynamic range (HDR) images. But the majority of media images on the …
visualizing high dynamic range (HDR) images. But the majority of media images on the …
Adaptive Student Inference Network for Efficient Single Image Super-Resolution
Recent advances in single image super-resolution (SISR) have achieved remarkable
performance through deep learning. However, the high computational cost hinders the …
performance through deep learning. However, the high computational cost hinders the …
[HTML][HTML] 单帧非自然图像深度估计与动态合成
余林江， 杨伊欣 - Computer Science and Application, 2023 - hanspub.org
深度学习在单目深度估计任务上表现优异, 通过学习单帧图像与深度图像之间存在的映射关系来
估计图像的深度. 但是, 目前单目深度估计的研究仅关注于自然图像, 当把它应用于非自然图像 …
估计图像的深度. 但是, 目前单目深度估计的研究仅关注于自然图像, 当把它应用于非自然图像 …