Your Daily AI Research tl;dr — 2022–08–12 🧠

A follow-up on Meta’s new bot BlenderBot 3, 3D Face Synthesis with HDRI Relighting and estimating a 3D character pose from a bitmap sketch!

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 VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting

A generative framework to synthesize 3D-aware faces with convincing relighting

Link to the paper: https://arxiv.org/pdf/2201.04873.pdf

2️⃣ Sketch2Pose: estimating a 3D character pose from a bitmap sketch

“The first system for automatically inferring a 3D character pose from a single bitmap sketch, producing poses consistent with viewer expectations.”

Link to the paper: https://dl.acm.org/doi/10.1145/3528223.3530106

Code: https://github.com/kbrodt/sketch2pose