Your Daily AI Research tl;dr — 2022–10–14 🧠

Designer, a Microsoft AI design app powered by OpenAI’s DALL-E 2, video pretraining and Facial NeRF Models!

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 Self-supervised video pretraining yields strong image representations

“In this work we revisit self-supervised learning of image representations from the dynamic evolution of video frames […] and develop a contrastive learning framework which handles the complex transformations present in natural videos.”

Link to the paper: https://arxiv.org/pdf/2210.06433.pdf

2️⃣ Reconstructing Personalized Semantic Facial NeRF Models From Monocular Video

A novel semantic model for human head defined with neural radiance field. The 3D-consistent head model consist of a set of disentangled and interpretable bases, and can be driven by low-dimensional expression coefficients.