Your Daily AI Research tl;dr — 2022–10–05 🧠

Blueprint for an AI Bill of Rights, Frame Interpolation for Large Motion and a diffusion model for 3D novel view synthesis from as few as a single image!

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 NOVEL VIEW SYNTHESIS WITH DIFFUSION MODELS

3DiM: a diffusion model for 3D novel view synthesis from as few as a single image.

Link to the paper: https://3d-diffusion.github.io/static/paper.pdf

2️⃣ FILM: Frame Interpolation for Large Motion

A frame interpolation algorithm that synthesizes an engaging slow-motion video from near-duplicate photos which often exhibit large scene motion.

Link to the paper: https://arxiv.org/pdf/2202.04901.pdf

Join the discussion with fellow AI professionals on Discord!

🆕 “Blueprint for an AI Bill of Rights”