Google’s New AI Model Improves 3D Image Synthesis of Outdoor Scenes

Synthesizing 3D views of a scene using multiple camera angles, cameras, and lighting conditions is a challenging task for computer vision models and an important prerequisite for AR and VR applications. A group of researchers from Google Research and Goog… Read more

Read full article

Similar

Researchers’ AI can perform 3D motion capture with any off-the-shelf camera

Researchers at the Max Planck Institute and Facebook Reality Labs describe an AI-powered motion capture system that works with any camera. (more…)

Seinfeld Episodes written by AI

artificial_seinfeld - Tools for generating artificial Seinfeld episodes using Keras LSTM w/ Hyperparameter Optimization...

Checking out a 6B parameter GPT model, GPT-J, from Eleuther AI [video]

An actually-open-AI model is available for you to download the weights to and tinker with, GPT-J. It's a 6 billion parameter large language model that can do... (more…)

Intel AI research photorealism in GTA V

Grand Theft Auto 5 is no stranger to photorealism mods, but an AI research group from Intel has taken it to the next level with their AI machine learning too... (more…)

AI Generated Pokemon Sprites with GPT-2

A few months back I started messing around with gpt-2-simple. Inspired by a few of the more unusual uses like chess playing and MIDI generation I wanted to find something funky I could do with it myself. Image generation quickly came ... (more…)

Latest News

OpenAI has a conflict of interest in calling for AI regulation: Zerodha CTO

Espanso: Cross-platform Text Expander written in Rust

Eyeloupe – The elegant Rails debug assistant (inspired by Laravel Telescope)