Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos (CVPR 2021)

YJ · 7K views · 2021 · 3:23

Open on YouTube

Computer vision, speech & NLPother

Why the open web links it

Presents a method to learn high-fidelity depth models of dressed humans using social media dance videos as training data.

Linked by 3 independent sites, 2 of them widely read in the 2026-10 crawl of the open web, including umn.edu, 404media.co, yasamin.page.