Real-ESRGAN-ncnn-vulkan VS pifuhd

Don't even need topaz, there's plenty of free upscale models check the openmodeldb, and you have reve which is based on Real-ESRGAN-ncnn-vulkan.

Real-ESRGAN/GFPGAN https://github.com/xinntao/Real-ESRGAN (Real-ESRAN - Upscale images, facial restoration with GFPGAN setting) https://github.com/TencentARC/GFPGAN (GFPGAN - Facial restoration and Upscale) -------MATTE AND COMPOSITE--------

If you mean by free software, sure there are options. But you'll spend a lot of time to do that. You can try https://github.com/xinntao/Real-ESRGAN or similar tools

I’m actually on a Mac using the ncnn Vulkan binaries for Real ESRGAN. It’s not all that flexible but it’s pretty quick. There are other options but I have not looked into it.

I personally use real esrgan and I think it's great. it requires manual work tho but it's easy once you do it a few times

REAL-ESRGAN was used for upscaling (using waifu2x-extension GUI) and can be found here.

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.