All Projects â†’ blenderskool â†’ color-pop

blenderskool / color-pop

Licence: other
🌈 Automatic Color Pop effect on any image inspired by Google Photos

Programming Languages

typescript
32286 projects

Projects that are alternatives of or similar to color-pop

Dataset
Crop/Weed Field Image Dataset
Stars: ✭ 98 (+366.67%)
Mutual labels:  segmentation, mask
google-photos-api-client-go
Google photos api client in go
Stars: ✭ 35 (+66.67%)
Mutual labels:  google-photos
wasr network
WaSR Segmentation Network for Unmanned Surface Vehicles v0.5
Stars: ✭ 32 (+52.38%)
Mutual labels:  segmentation
Basic-Image-Processing
Implementation of Basic Digital Image Processing Tasks in Python / OpenCV
Stars: ✭ 102 (+385.71%)
Mutual labels:  segmentation
AttentionGatedVNet3D
Attention Gated VNet3D Model for KiTS19——2019 Kidney Tumor Segmentation Challenge
Stars: ✭ 35 (+66.67%)
Mutual labels:  segmentation
DeepSegmentor
Sequence Segmentation using Joint RNN and Structured Prediction Models (ICASSP 2017)
Stars: ✭ 17 (-19.05%)
Mutual labels:  segmentation
vesseg
Brain vessel segmentation using 3D convolutional neural networks
Stars: ✭ 27 (+28.57%)
Mutual labels:  segmentation
hair-dye
Neural Network for Dying Hair💈
Stars: ✭ 45 (+114.29%)
Mutual labels:  segmentation
superpixelRefinement
Superpixel-based Refinement for Object Proposal Generation (ICPR 2020)
Stars: ✭ 24 (+14.29%)
Mutual labels:  segmentation
Polygonization-by-Frame-Field-Learning
This repository contains the code for our fast polygonal building extraction from overhead images pipeline.
Stars: ✭ 161 (+666.67%)
Mutual labels:  segmentation
lung-image-analysis
A basic framework for pulmonary nodule detection and characterization in CT
Stars: ✭ 26 (+23.81%)
Mutual labels:  segmentation
flickr to google photos migration
A tool for migrating your photo library from Flickr to Google Photos
Stars: ✭ 39 (+85.71%)
Mutual labels:  google-photos
ANTsR
Advanced Normalization Tools in R
Stars: ✭ 101 (+380.95%)
Mutual labels:  segmentation
Brain-MRI-Segmentation
Smart India Hackathon 2019 project given by the Department of Atomic Energy
Stars: ✭ 29 (+38.1%)
Mutual labels:  segmentation
mmrazor
OpenMMLab Model Compression Toolbox and Benchmark.
Stars: ✭ 644 (+2966.67%)
Mutual labels:  segmentation
incogly
Incogly is a video conferencing app aimed to remove any implicit bias in an interview and easing the process of remote collaboration.
Stars: ✭ 24 (+14.29%)
Mutual labels:  tensorflowjs
Fast-SCNN pytorch
A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network(PyTorch >= 1.4)
Stars: ✭ 30 (+42.86%)
Mutual labels:  segmentation
nicMSlesions
Easy multiple sclerosis white matter lesion segmentation using convolutional deep neural networks.
Stars: ✭ 33 (+57.14%)
Mutual labels:  segmentation
MiVOS
[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!
Stars: ✭ 302 (+1338.1%)
Mutual labels:  segmentation
VNet
Prostate MR Image Segmentation 2012
Stars: ✭ 54 (+157.14%)
Mutual labels:  segmentation

🌈 Color Pop

The Color Pop(aka Color splash) effect makes the subject(usually a person) stand out from the rest of the image. The subject remains in color, but the background is made black and white. This gives a pleasant look in most cases.

This app applies color pop effect on human subjects and supports images with many people.
Here's an article that I wrote explaining the working of this project at a basic level.

Examples

Image with one person

Imgur

Original left, Color pop right.

Image with many people

Imgur

Original left, Color pop right.

Behind the scenes

It uses Tensorflow.js and the BodyPix model to create segmentation masks around people in images.

It can be accessed using the colorpop cloud function once the project is deployed on Firebase.

Deployment

Instructions to deploy this project on Firebase

Options for colorpop cloud function

The colorpop is an HTTP cloud function which can be accessed by making a POST request with the binary image data as the body of the request, along with following optional query params

Param Expected data Description
model mobilenet(default) or resnet The model to use for segmentation.
Mobilenet is faster but less accurate.
Resnet is slower but more accurate

Example cURL command

curl --location --request POST 'http://{CLOUD_FUNCTION_HOST_URL}/colorpop?model=mobilenet' \
--header 'Content-Type: image/jpeg' \
--data-binary 'test.jpg' \
--output 'output.jpeg'

History

Achieving this effect manually is quite simple. It involves creating a mask around the subject and dropping the color of the background (Example using Photoshop). While it is simple, doing this manually has the following issues:

  • Tedious and time-consuming.
  • Poor results for complex subjects.
  • Not all applications(especially mobile apps) support masking.

Google announced the color pop effect for its Photos app in Google IO 2018 and although it does an incredible job of detecting the subject and applying the effect, it applies it automatically only to some images. Certain conditions have to be met before the color pop effect even shows up in the editing options of the Photos app.

This inspired me to build this tool which makes it as easy as Google Photos to apply the color pop effect on photos with people in it, without needing any manual work.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].