huochaitiantang / pytorch-deep-image-matting

Pytorch implementation of deep image matting
294 stars 71 forks source link

Automatic Background Removal technology #34

Closed InternetMaster1 closed 4 years ago

InternetMaster1 commented 4 years ago

I am looking for a deep learning library/sdk which can be used to remove the background from any image automatically (with quality as good as www.remove.bg).

I tried some image segmentation SDKs with pre-trained models such as Tensorflow Lite & Fritz AI, but the accuracy of the cutout mask was very low, amongst other issues.

Criteria :-

1) Background Removal rather than just Human/Portrait Segmentation

If the foreground consists of person holding a balloon, sitting on a chair, with a pet on his side, then I want all of this to get extracted. Not just the human cutout. The segmentation SDKs I tried are only extracting humans (the chair gets vanished), that too with a very low quality mask (hair gets cut, parts of ear gets cut, etc).

2) Mask quality should be Super-Accurate

I want even the finer details like the hair, delicate clothes, etc to be extracted perfectly.

3) Fast & Lightweight (for mobile phone)

I want to use this technology on mobile phones (in an Android app) which should ideally work even in an offline environment. If this option is difficult to achieve, then plan B would be install the technoloy on our server.

4) Technology

What technology should I be exploring to achieve this? Is it called image segmentation or the better term would be image matting? (e.g. http://alphamatting.com/eval_25.php)

I have been reading a lot and I am currently lost in the sea of various technologies out there (OpenCV, Deep Matting, Mask RCNN, Instance Segmentation, Detectron2, Tensorflow, Pytorch, etc). I wonder what magic is happening behind the curtains of www.remove.bg

Would your library help me to achieve what I am looking for? Any help you could provide or a nudge in the right direction would be awesome.

Thanks a ton!

shivam13juna commented 4 years ago

@InternetMaster1 did you find out anything?

ahmetybilgin commented 4 years ago

Are there any improvements? @huochaitiantang @InternetMaster1 @shivam13juna

shivam13juna commented 4 years ago

Nope. But I've posted a repository which has remove.bg level performance. Try it out

On Thu, May 28, 2020, 14:22 ahmetybilgin notifications@github.com wrote:

Are there any improvements? @huochaitiantang https://github.com/huochaitiantang @InternetMaster1 https://github.com/InternetMaster1 @shivam13juna https://github.com/shivam13juna

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/huochaitiantang/pytorch-deep-image-matting/issues/34#issuecomment-635210255, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFQRN5W2BTGLMG5JOGR63ETRTYQ4HANCNFSM4J3BHQUQ .

InternetMaster1 commented 4 years ago

@shivam13juna Your library looks interesting, I will check it out

develoboi commented 4 years ago

@huochaitiantang @InternetMaster1 @shivam13juna @ahmetybilgin You got the solution guys ? I'm pissed off but can't get the remover.bg type accuracy. I want offline Image Segmentation for java/android.

shivam13juna commented 4 years ago

@develoboi check my repo, https://github.com/shivam13juna/Quick_Image_Matting_remove.bg_equivalent

I got pretty much remove.bg level performance. Good luck!

develoboi commented 4 years ago

Thank you for replying bro but i want java/android code.

On Tue, Sep 1, 2020 at 6:09 PM SHIVAM PRASAD notifications@github.com wrote:

@develoboi https://github.com/develoboi check my repo, https://github.com/shivam13juna/Quick_Image_Matting_remove.bg_equivalent

I got pretty much remove.bg level performance. Good luck!

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/huochaitiantang/pytorch-deep-image-matting/issues/34#issuecomment-684822395, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO4QMQD5CRCWGX35Q7VSK4TSDTTRBANCNFSM4J3BHQUQ .

Barnello commented 2 years ago

Any luck @develoboi