Skip to content

Advanced data augmentation with Generative Adversarial Networks for vehicle detection

Notifications You must be signed in to change notification settings

yuanmengzhixing/AugGAN-Cross-Domain-Adaptation-with-GAN-based-DataAugmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

45 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Semantic preserving image-to-image translation

Day to Night Style-transfer with Semantic Segmentation Assistant

auggan_testing_result

Figure 1: Day-to-Night style transfer result comparison

1st row: SYNTHIA input images, 2nd row: cycle-GAN day-to-night output, 3rd row: Aug-GAN day-to-night output;
4th row: KITTI input images, 5th row: cycle-GAN day-to-night output, 6th row: Aug-GAN day-to-night output.

comparison video

Video 1: Sequencial Comparison with cycle-GAN

Left: input sequence, Mid: cycle-GAN output, Right: AugGAN output

Prerequisite

  • Python 3.6+
  • scikit-image, tqdm

About

Advanced data augmentation with Generative Adversarial Networks for vehicle detection

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages