pifuhd VS mediapipe

PIFuHD (Generate 3d Models from a single image) https://github.com/facebookresearch/pifuhd

git clone https://github.com/facebookresearch/pifuhd

Code for https://arxiv.org/abs/2004.00452 found: https://github.com/facebookresearch/pifuhd

I'm very interested in converting images to 3d models. Really cool tech that feels like it's nearly there.

Have you by chance seen any of the work Facebook has been doing related to the 2d to 3d conversions?

https://github.com/facebookresearch/pifuhd

Yes you're correct. That's why I thought having a dome of raspberry pis around a turntable, getting multiple angles at once, but also the movement would provide a solid dataset to be able to train a neural network to generate a 3D model of a person, or an object or possibly even an animal from a single photo, sort of like PifuHD.

PIFuHD

facebookresearch/pifuhd (Python): High-Resolution 3D Human Digitization from A Single Image.

mediapipe/docs/solutions/pose.md at master · google/mediapipe · GitHub

Today, we announce MediaPipe diffusion plugins, which enable controllable text-to-image generation to be run on-device. Expanding upon our prior work on GPU inference for on-device large generative models, we introduce new low-cost solutions for controllable text-to-image generation that can be plugged into existing diffusion models and their Low-Rank Adaptation (LoRA) variants.

You can just grab the TFLite version! https://github.com/google/mediapipe/blob/master/docs/solutions/models.md

I believe Google already released transformers under an apache 2 license with a patent grant:

https://github.com/google/mediapipe/blob/master/mediapipe/mo...

I was going to say that I like the MediaPipe Selfie Segmentation model for doing this sort of thing in a web page, but I've just noticed (when getting the GitHub link[1]) that Google have marked the code as legacy[2] ... no idea if the new solution is better/easier to use[3].

For what it's worth, my CodePen using the old model is here: https://codepen.io/kaliedarik/pen/PopBxBM

[1] - https://github.com/google/mediapipe/blob/master/docs/solutio...

[2] - "Attention: Thank you for your interest in MediaPipe Solutions. As of April 4, 2023, this solution was upgraded to a new MediaPipe Solution."

[3] - https://developers.google.com/mediapipe/solutions/vision/ima...

I have used mediapipe very successfully in multiple projects and it's very easy to get running. You can choose from many different vision tasks including hand landmarks ( https://github.com/google/mediapipe/blob/master/docs/solutions/hands.md )

I found MediaPipe's Face Mesh and was impressed with how simple it was to get going, but it just gives you the landmark points and I've not gone any further yet.

We've trained ControlNet on a subset of the LAION-Face dataset using modified output from MediaPipe's face mesh annotator to provide a new level of control when generating images of faces.

Medipaipe library link: https://mediapipe.dev/