Your Daily AI Research tl;dr — 2022–08–25 🧠

A GitHub repository full of pre-trained diffuser models, the GTA-Human dataset and human body estimation…

Welcome to your official daily AI research tl;dr (often with code and news) for AI professionals where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating.

1️⃣ Learning Visibility for Robust Dense Human Body Estimation

“We learn dense human body estimation that is robust to partial observations (parts of the body are occluded or outside the frame).”

Link to the paper: https://arxiv.org/pdf/2208.10652.pdf

Code: https://github.com/chhankyao/visdb

2️⃣ Playing for 3D Human Recovery

They introduce GTA-Human, “a large-scale 3D human dataset generated with the GTA-V game engine, featuring a highly diverse set of subjects, actions, and scenarios. More importantly, [they] study the use of game-playing data and obtain five major insights…”

Link to the paper: https://arxiv.org/pdf/2110.07588.pdf