Member-only story
Your Daily AI Research tl;dr — 2022–06–28 🧠
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 Text-Driven Stylization of Video Objects
This paper provides a new approach for video style transfer following a text prompt harnessing the representational power of CLIP to generate consistent style changes in time for a variety of objects and videos, that adhere to the specification of the target texts.
Link to the paper: https://arxiv.org/abs/2206.12396
2️⃣ Megapixel Image Generation with Step-Unrolled Denoising Autoencoders
Tackling image generation on mega pixel images optimizing computation needs and processing time via the combination of techniques, processing 1024x1024 images in approximately two seconds with a single GTX 1080Ti.
Link to the paper: https://arxiv.org/abs/2206.12351
