Your Daily AI Research tl;dr — 2022–06–26 🧠

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 HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction

A new a photo-realistic objectcentric dataset constructed by composing realistic indoor scene and realistic object providing a multi-view RGB representation, a water-tight mush model, the ground truth depth maps and object mask for each scene.

Link to the paper: https://arxiv.org/abs/2206.12356

Dataset: https://github.com/zhenpeiyang/HM3D-ABO

2️⃣ PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction

“The first million-level protein structure prediction dataset with high coverage and diversity.” This dataset consists of 570k true structure sequences (10TB) and 745k complementary distillation sequences (15TB)