Your Daily AI Research tl;dr — 2022–09–22 🧠

Getty Images bans AI-generated content, Learning to Relight Portrait Images and Learning Image to Document Attention…

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 I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

I2DFormer, a novel transformer-based zero-shot learning (ZSL) framework that jointly learns to encode images and documents (from Wikipedia) by aligning both modalities in a shared embedding space.

Link to the paper: https://arxiv.org/pdf/2209.10304.pdf

2️⃣ Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation

“We propose a new approach that can perform on par with the state-of-the-art (SOTA) relighting methods without requiring a light stage.”

Link to the paper: https://arxiv.org/pdf/2209.10510.pdf