Comments (21)
@rainsun1 many thanks for sharing this, actually, it'll be better if the trimap can be automatically generated so that the whole process can be automatic. recently, i found a useful website which can do bg removal all in automation: http://remove.bg
from deep-image-matting.
@tsing90 A paper named "Semantic Human Matting" is in this automatic trimap way.
from deep-image-matting.
remove.bg,so wonderful
from deep-image-matting.
@tsing90 you can use Deep Lab v3+(https://github.com/tensorflow/models/blob/master/research/deeplab/deeplab_demo.ipynb) to get segmentation mask and then apply trimap generator to produce trimaps.
https://github.com/lnugraha/trimap_generator
from deep-image-matting.
@farazBhatti thanks for your suggestion. actually I've already tried its xception model which is good to get decent masks. To get trimaps, it's enough just by doing dilating and eroding. The key problem is that the masks we got from semantic segmentation (like deeplab v3+) is binary, its quality is lower than alpha matting
from deep-image-matting.
@tsing90, yes true we only need medium quality segmentation mask to get trimap and from that trimap along with original colored image alpha matte is predicted. Alpha matte segmented image will always be superior to any other segmented mask , but we really don't need that good quality of segmented mask to predict alpha matte.
from deep-image-matting.
@farazBhatti I got them from the author, due to license issue, you have to contact the author of that paper
from deep-image-matting.
@xaibeing The trimaps are in the dataset obtained from the author.
Only the test dataset has trimaps. The training set does not have them. @foamliu Can you explain a little bit how you generated trimaps for your training set? Thank you.
from deep-image-matting.
good question, refer to #5
from deep-image-matting.
You can use the "Robust Matting" demo to produce the trimap.
from deep-image-matting.
@rainsun1 could you put a link of code here so that we can have a try? I searched for the code, it seemed 'robust matting' algorithm also need trimap to produce final result.
from deep-image-matting.
Here is a robust matting demo, you could load an image and then create a trimap yourself by the brushes and inpainting.
from deep-image-matting.
@rainsun1 many thanks, that's what I need. unfortunately, the big datasets shown in that paper are not available for us. that kind of big datasets is essential for training a good model.
from deep-image-matting.
@tsing90 yes, but can you find some other implementations on "Semantic Human Matting" on github?
from deep-image-matting.
@rainsun1 yes, I found some, like
https://github.com/lizhengwei1992/Semantic_Human_Matting
https://github.com/CapsulE07/semantic-human-matting
from deep-image-matting.
@wodsoe that's our benchmark from industry ;)
from deep-image-matting.
@wodsoe that's our benchmark from industry ;)
How to re-implement
from deep-image-matting.
Does anyone have this problem? when producing trimap using the alpoha matte image from Adobe's DIM datasets, the trimap is kind of jagged, shown like below. My first guess of this issue is due to the image quality of .jpg, because .png images in that datasets don't have this problem.
from deep-image-matting.
Yes it could be the result of jpg compression quality. By the way is there any link to this data(
Adobe's DIM dataset) set which you are using?Thanks
from deep-image-matting.
@tsing90 Hi, I'm re-implementing the work nowadays. Could you please share some details of your tests. Hope to have a talk, my email [email protected]
from deep-image-matting.
@xaibeing Hi, I'm also doing segmentation with mask RCNN and now I'm trying to use image matting to improve edge identification. I would like to private message you because now I have some trouble and maybe discussing could help both, if you want this is my email: [email protected]
from deep-image-matting.
Related Issues (20)
- Doubt about alpha and trimap HOT 3
- Why is the result pixel not 0 or 1? HOT 1
- Training errors?
- Noisy output HOT 2
- Failed to get convolution algorithm HOT 1
- loss computational error HOT 1
- train higher resolution image HOT 1
- 问题解决了
- Ask
- Ask for metrics code HOT 6
- How can we train on higher resolution images ? HOT 1
- What is accuracy in your model ? HOT 1
- ValueError: You are trying to load a weight file containing 47 layers into a model with 33 layers. HOT 1
- annotate image
- Run train.py ERROR
- can you share adobe dataset? HOT 1
- Unknown region predicting foreground only
- the bgpath in pre_process
- dataset request HOT 1
- About the foreground in Composition 1K
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deep-image-matting.