AI Powered 3D Human Shape Estimation

In this short tutorial, we are going to look at the very cool and interesting image-based 3D human shape estimation model. We are going to implement a pipeline on Spell workplace with a jupyter lab and run the pre-trained model to turn our custom image into a 3D model. Signup to the Spell if you haven't and you can get 10$ with of GPU time on T4, P100, k80, and V100 GPUs for free. We are going to use Facebook research's pifuhd model which contains a PyTorch implementation of "Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization". Note: At least 8GB GPU memory is recommended to run the PIFuHD model. We can use any GPU from Spell.