Skip to content

Official implementation of our ICCV19 paper "Image Synthesis From Reconfigurable Layout and Style"

Notifications You must be signed in to change notification settings

No1WellDone/LostGANs

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LostGANs: Image Synthesis From Reconfigurable Layout and Style

This is implementation of our ICCV19 paper Image Synthesis From Reconfigurable Layout and Style

Network Structure

network_structure

Installation

Check INSTALL.md for installation instructions.

1. Download pretrained model

Download pretrained models to pretrained_model/

  • Pretrained model on COCO
  • Pretrained model on VG

2. Train models

python train.py --dataset coco --out_path outputs/

3. Run pretrained model

python test.py --dataset coco --model_path pretrained_model/G_coco.pth --sample_path samples/coco/

Results

Multiple samples generated from same layout

various_out

Generation results by adding new objects or change spatial position of object

add_obj

Linear interpolation of instance style

style_morph

Synthesized images and learned masks for given layout

mask

Contact

Please feel free to report issues and any related problems to Wei Sun (wsun12 at ncsu dot edu) and Tianfu Wu (tianfu_wu at ncsu dot edu).

Reference

About

Official implementation of our ICCV19 paper "Image Synthesis From Reconfigurable Layout and Style"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages

  • Python 75.9%
  • Cuda 12.3%
  • C++ 10.0%
  • Shell 1.8%