Archives
/
GIMP-ML
mirror of https://github.com/kritiksoman/GIMP-ML
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs

Browse Source
GIMP3-ML
DESKTOP-F04AGRR\Kritik Soman 3 years ago
parent 5e0f7cbae0
commit 085931c93d
4 changed files with 116 additions and 0 deletions
Show Stats Download Patch File Download Diff File

18
docs/DEMOS.md
Unescape Escape View File

@ -0,0 +1,18 @@
[<img src="http://img.youtube.com/vi/e6q7_CPw_rk/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=e6q7_CPw_rk)
[<img src="http://img.youtube.com/vi/FPeQ5g3WIWk/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=FPeQ5g3WIWk)
[<img src="http://img.youtube.com/vi/squyQYrllBg/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=squyQYrllBg)
[<img src="http://img.youtube.com/vi/eMEd6vs47c4/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=eMEd6vs47c4)
[<img src="http://img.youtube.com/vi/q9Ny5XqIUKk/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=q9Ny5XqIUKk)
[<img src="http://img.youtube.com/vi/4YpTa-gqEIw/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=4YpTa-gqEIw)
[<img src="http://img.youtube.com/vi/kXYsWvOB4uk/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=kXYsWvOB4uk)
[<img src="http://img.youtube.com/vi/HVwISLRow_0/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=HVwISLRow_0)
[<img src="http://img.youtube.com/vi/U1CieWi--gc/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=U1CieWi--gc)
[<img src="http://img.youtube.com/vi/HeBgWcXFQpI/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=HeBgWcXFQpI)
[<img src="http://img.youtube.com/vi/adgHtu4chyU/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=adgHtu4chyU)
[<img src="http://img.youtube.com/vi/thS8VqPvuhE/0.jpg" width="400" height="300">](http://www.youtube.com/watch?v=thS8VqPvuhE)

7
docs/HOME.md
Unescape Escape View File

@ -0,0 +1,7 @@
# Welcome to the GIMP ML wiki!
This repository introduces GIMP3-ML, a set of Python plugins for the widely popular GNU Image Manipulation Program (GIMP). It enables the use of recent advances in computer vision to the conventional image editing pipeline. Applications from deep learning such as monocular depth estimation, semantic segmentation, mask generative adversarial networks, image super-resolution, de-noising and coloring have been incorporated with GIMP through Python-based plugins. Additionally, operations on images such as edge detection and color clustering have also been added. GIMP-ML relies on standard Python packages such as numpy, scikit-image, pillow, pytorch, open-cv, scipy. In addition, GIMP-ML also aims to bring the benefits of using deep learning networks used for computer vision tasks to routine image processing workflows.
The plugins have been tested with GIMP 2.99 on the following machines: <br>
[1] ubuntu 20.04 LTS <br>
[2] Windows 10

64
docs/MANUAL.md
Unescape Escape View File

@ -0,0 +1,64 @@
## In-painting
Requires 2 inputs:<br>
[1] Image Layer. <br>
[2] Mask Layer containing mask of object to be removed. Background should be black (255,255,255) and object should be white (0,0,0). <br>
Both layers should be selected and then the plugin should be run from the GIMP-ML menu.
## Interpolate-frames
Requires 3 inputs:<br>
[1] Image Layer which will be the starting frame. <br>
[2] Image Layer which will be the ending frame. <br>
[3] Output Location: Folder where interpolated frames should be saved. <br>
Both layers should be selected and then the plugin should be run from the GIMP-ML menu.
## De-blur
Works on currently selected layer as input.
## De-haze
Works on currently selected layer as input.
## De-noise
Works on currently selected layer as input.
## Enlightening
Works on currently selected layer as input.
## MonoDepth
Works on currently selected layer as input.
## Semantic Segmentation
Works on currently selected layer as input containing any of the following: person, bird, cat, cow, dog, horse, sheep, aeroplane, bicycle, boat, bus, car, motorbike, train, bottle, chair, dining table, potted plant, sofa, and tv/monitor. <br>
## Face Parsing
Works on currently selected layer as input containing only portrait image of a person.<br>
## Image Super-resolution
Requires the factor by which the image is to be enlarged as input.<br>
Set "Use as filter" to True if image size is medium/large in size (i.e., >~ 400pixels in height or width), otherwise you might run out of memory.<br>
## K-means Clustering
[1] Number of clusters/colors in output. <br>
[2] Use position: if (x,y) coordinates should be used as features for clustering. <br>
## Deep Image Matting
Requires 2 layers as input:
[1] Image Layer <br>
[2] Trimap Layer: Use RGB as [128,128,128] for boundaries, [255,255,255] for object and [0,0,0] for background. <br>
Example: <br>
![image1](https://github.com/kritiksoman/tmp/blob/master/trimap.png)<br>
Both layers should be selected and then the plugin should be run from the GIMP-ML menu.
## Deep Image Coloring
The image should be greyscale but the image mode should be RGB. This can be done from Image->Mode->RGB... <br>
Requires 2 layers as input:
[1] Image Layer <br>
[2] Color Mask Layer: A transparent RGB layer (with alpha channel) that contains (local points) dots of size 6 pixels specifying which color should be present at which location.<br>
Both layers should be selected and then the plugin should be run from the GIMP-ML menu.

27
docs/REFERENCES.md
Unescape Escape View File

@ -0,0 +1,27 @@
# Paper References
[1] [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://arxiv.org/abs/1609.04802) <br>
[2] [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://arxiv.org/abs/1908.03826) <br>
[3] [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://arxiv.org/abs/1907.01341v2) <br>
[4] [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://arxiv.org/abs/1808.00897) <br>
[5] [Real-Time User-Guided Image Colorization with Learned Deep Priors](https://arxiv.org/abs/1705.02999) <br>
[6] [Rethinking Atrous Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1706.05587) <br>
[7] [Deep Image Matting](https://openaccess.thecvf.com/content_cvpr_2017/papers/Xu_Deep_Image_Matting_CVPR_2017_paper.pdf) <br>
[8] [AOD-Net: All-In-One Dehazing Network](https://openaccess.thecvf.com/content_ICCV_2017/papers/Li_AOD-Net_All-In-One_Dehazing_ICCV_2017_paper.pdf) <br>
[9] [When AWGN-based Denoiser Meets Real Noises](https://arxiv.org/pdf/1904.03485.pdf)<br>
[10] [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://arxiv.org/pdf/1906.06972.pdf)<br>
[11] [RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://arxiv.org/pdf/2011.06294.pdf)<br>
[12] [EdgeConnect: Structure Guided Image Inpainting using Edge Prediction](https://openaccess.thecvf.com/content_ICCVW_2019/papers/AIM/Nazeri_EdgeConnect_Structure_Guided_Image_Inpainting_using_Edge_Prediction_ICCVW_2019_paper.pdf)<br>
# Code References
The following have been ported : <br>
[1] https://github.com/TAMU-VITA/DeblurGANv2 <br>
[2] https://github.com/zllrunning/face-parsing.PyTorch <br>
[3] https://github.com/junyanz/interactive-deep-colorization <br>
[4] https://github.com/intel-isl/MiDaS <br>
[5] https://github.com/twtygqyy/pytorch-SRResNet <br>
[6] https://github.com/huochaitiantang/pytorch-deep-image-matting <br>
[7] https://github.com/MayankSingal/PyTorch-Image-Dehazing <br>
[8] https://github.com/yzhouas/PD-Denoising-pytorch <br>
[9] https://github.com/VITA-Group/EnlightenGAN <br>
[10] https://github.com/hzwer/arXiv2020-RIFE <br>
[11] https://github.com/knazeri/edge-connect <br>
Write Preview
Loading…
Cancel
Save