Your Daily AI Research tl;dr — 2022–08–16 🧠

TikTok introduces “AI greenscreen”, 3D style transfer and video inpainting…

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 Flow-Guided Transformer for Video Inpainting

A “flow-guided transformer, which innovatively leverage the motion discrepancy exposed by optical flows to instruct the attention retrieval in transformer for high fidelity video inpainting.

Link to the paper: https://arxiv.org/pdf/2208.06768.pdf

2️⃣ UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scene

A novel 3D scene photorealistic style transfer framework for transferring photorealistic style from an input image to a 3D scene, merging a 2D style transfer approach with voxel representations.

Link to the paper: https://arxiv.org/pdf/2208.07059.pdf

Join the discussion with fellow AI professionals on Discord!