Member-only story

Your Daily AI Research tl;dr 2022–07–18🧠

One-shot Megapixel Neural Head Avatars, a dataset for podcast audio separation and PLEX: a framework to improve the reliability of deep learning systems!

Louis-François Bouchard
2 min readJul 18, 2022

Welcome to your official daily AI research tl;dr (often with code and news) for AI enthusiasts 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. I will also take this opportunity to share daily exciting news in the field.

Let’s get started with this iteration!

1️⃣ MegaPortraits: One-shot Megapixel Neural Head Avatars

They bring megapixel resolution to animated face generations (neural head avatars), focusing on the “cross-driving synthesis” task: when the appearance of the driving image is substantially different from the animated source image.

Link to the paper: https://arxiv.org/pdf/2207.07621.pdf

More results: https://samsunglabs.github.io/MegaPortraits/

2️⃣ PodcastMix: A dataset for separating music and speech in podcasts

--

--

Louis-François Bouchard
Louis-François Bouchard

Written by Louis-François Bouchard

I try to make Artificial Intelligence accessible to everyone. Ex-PhD student, AI Research Scientist, and YouTube (What’s AI). https://www.louisbouchard.ai/

No responses yet