Is this face motion tracking using a camera to apply to 3D models?
Show HN: I made a computer vision addon for Blender
21–30 of 36 posts
Re: Show HN: I made a computer vision addon for Blender
#22Very cool! I've done something similar for improving an OCR system on crinkled paper[0]. Blender is a powerful and totally underutilized tool for this kind of work 0. https://www.arwmoffat.com/work/synthetic-training-data
Does using synthetic training data introduce any problems? How do you ensure your synthetic data matches real data?
Re: Show HN: I made a computer vision addon for Blender
#23"synthetic ground truth"... isn't that an oxymoron?
Re: Show HN: I made a computer vision addon for Blender
#24A few related projects:
- https://github.com/DLR-RM/BlenderProc
- https://github.com/cheind/pytorch-blender
- https://github.com/DIYer22/bpycv
- https://github.com/yuki-koyama/blender-cli-rendering
and youtube videos covering blender for synthetic data:
- https://www.youtube.com/playlist?list=PLq7npTWbkgVAt4cnrsEzo...
Re: Show HN: I made a computer vision addon for Blender
#25A few related projects: - https://github.com/DLR-RM/BlenderProc - https://github.com/cheind/pytorch-blender - https://github.com/DIYer22/bpycv - https://github.com/yuki-koyama/blender-cli-rendering and youtube videos covering blender for synthetic data: - https://www.youtube.com/playlist?list=PLq7npTWbkgVAt4cnrsEzo... - https://www.youtube.com/watch?v=EaXy-m2I5hs
The difference is that none of the above examples actually process real image input - the Cartucho app utilizes stereo cam images.
Re: Show HN: I made a computer vision addon for Blender
#26Very, very cool work, I fully expect to use this exact project in the future! To those of you who always thought this stuff looked neat but never tried it out, and to those who may have used blender in the past and gave up, I would HIGHLY encourage you to try again with the latest version of the software. Although there is still a bit of a learning curve, there have been massive improvements have to the software suit…
Similarly, when my niece recently got married I was tasked with putting together the photo/video show for the event.
I chose Blender because it's easy to use and loaded with image and video capability.
Plus, it gave me a good reason to come upto speed on the latest version.
Re: Show HN: I made a computer vision addon for Blender
#27"synthetic ground truth"... isn't that an oxymoron?
Ground truth in this case means images with labels of some sort on parts of the image or objects in the image, not that they're real images themselves. So a cat in a photo with a label or mask on the cat would be "ground truth" on what part of the image a cat is in, or that there is a cat.
Re: Show HN: I made a computer vision addon for Blender
#28One question: why does it need to run inside Blender instead of just using its graphical primitives as a library?
That's a good idea, it would make it faster for sure.
Re: Show HN: I made a computer vision addon for Blender
#29A few related projects: - https://github.com/DLR-RM/BlenderProc - https://github.com/cheind/pytorch-blender - https://github.com/DIYer22/bpycv - https://github.com/yuki-koyama/blender-cli-rendering and youtube videos covering blender for synthetic data: - https://www.youtube.com/playlist?list=PLq7npTWbkgVAt4cnrsEzo... - https://www.youtube.com/watch?v=EaXy-m2I5hs
The difference is that none of the above examples actually process real image input - the Cartucho app utilizes stereo cam images.
I dont think so. It generates stereo images from 3D (not takes them as an input) so it is exactly related to blenderproc and other tools.
Re: Show HN: I made a computer vision addon for Blender
#30So many likes, was not expecting that! I will be presenting this work tomorrow at MICCAI and then I will post my presentation link in the README of the repository!
Thank you for your work! Looking forward to the presentation. I had to look up MICCAI. To others: 23rd INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING & COMPUTER ASSISTED INTERVENTION (4-8 OCTOBER 2020) https://www.miccai2020.org/en
done! added to the GitHub README
[presentation video](https://imperialcollegelondon.box.com/s/cg54pddsf2pkx4ngf4pg...)