Your Daily AI Research tl;dr — 2022–11–01 🧠

A weekly newsletter you should follow, a compositional generative model and new metrics for monocular dynamic view synthesis!

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 gCoRF: Generative Compositional Radiance Fields

“We present a compositional generative model, where each semantic part of the object is represented as an independent 3D representation learnt from only in-the-wild 2D data.”

Link to the paper: https://arxiv.org/pdf/2210.17344.pdf

2️⃣ Monocular Dynamic View Synthesis: A Reality Check

They introduce two new metrics for monocular dynamic view synthesis: co-visibility masked image metrics and correspondence accuracy, which overcome the issue in existing protocols, and propose a new iPhone dataset that includes more diverse real-life deformation sequences.

Link to the paper: https://arxiv.org/pdf/2210.13445.pdf