ECCV 2022!CAIR:Instagram滤镜移除的快速轻量级多尺度色彩注意力网络!论文/代码速递2022.11.14!

2022-12-11 13:19:57 浏览数 (1)

整理:AI算法与图像处理

CVPR2022论文和代码整理:https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo

ECCV2022论文和代码整理:https://github.com/DWCTOD/ECCV2022-Papers-with-Code-Demo

最新成果demo展示:

CAIR: Multi-Scale Color Attention Network for Instagram Filter Removal

论文:https://arxiv.org/abs/2208.14039

代码:https://github.com/HnV-Lab/CAIR

图像恢复是计算机视觉中一项重要而富有挑战性的任务。将过滤后的图像还原为其原始图像在各种计算机视觉任务中都很有用。我们使用非线性无激活函数网络(NAFNet)来实现快速和轻量级的模型,并添加了颜色注意力模块,该模块提取有用的颜色信息以提高准确性。我们提出了一种精确、快速、轻量级的网络,具有多尺度和颜色关注,用于Instagram滤镜移除(CAIR)。实验结果表明,在IFFI数据集上,所提出的CAIR在快速和轻量化方面优于现有的Instagram滤波器去除网络,大约快11倍,轻2.4倍,同时超过3.69 dB PSNR。CAIR可以成功地以高质量移除

最新论文整理

ECCV2022

ECCV 2022
Updated on : 14 Nov 2022
total number : 1

LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation

  • 论文/Paper: http://arxiv.org/pdf/2211.05997
  • 代码/Code: https://github.com/hzykent/lidal

CVPR2022

NeurIPS

Updated on : 14 Nov 2022
total number : 3

A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation

  • 论文/Paper: http://arxiv.org/pdf/2211.06241
  • 代码/Code: None

Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models

  • 论文/Paper: http://arxiv.org/pdf/2211.06250
  • 代码/Code: None

From Competition to Collaboration: Making Toy Datasets on Kaggle Clinically Useful for Chest X-Ray Diagnosis Using Federated Learning

  • 论文/Paper: http://arxiv.org/pdf/2211.06212
  • 代码/Code: None

0 人点赞