logo
episode-header-image
Jul 2024
1 h

Generating 3D Animals with YouDream

Kyle Polich
About this episode

Generative AI can struggle to create realistic animals and 2D representations often have mistakes like extra limbs and tails. If 2D wasn’t hard enough, there are researchers working on generative 3D models. 3D models present an extra challenge because there is paucity of training datasets.In this episode, PhD students Sandeep and Oindrila walked us through their work on creating 3D animals using 2D data. Join us to learn about their pipelines, quality control, tie in with iNaturalist, and how this tech could streamline FX pipelines.

Up next
Aug 17
Networks and Recommender Systems
Kyle reveals the next season's topic will be "Recommender Systems". Asaf shares insights on how network science contributes to the recommender system field. 
17m 45s
Jul 21
Network of Past Guests Collaborations
Kyle and Asaf discuss a project in which we link former guests of the podcast based on their co-authorship of academic papers. 
34m 10s
Jul 6
The Network Diversion Problem
In this episode, Professor Pål Grønås Drange from the University of Bergen, introduces the field of Parameterized Complexity - a powerful framework for tackling hard computational problems by focusing on specific structural aspects of the input. This framework allows researchers ... Show More
46m 14s
Recommended Episodes
Aug 2024
AI that connects the digital and physical worlds | Anima Anandkumar
While language models may help generate new ideas, they cannot attack the hard part of science, which is simulating the necessary physics," says AI professor Anima Anandkumar. She explains how her team developed neural operators — AI trained on the finest details of the real worl ... Show More
12m 14s
Dec 2024
The TED AI Show: How AI robots learn just like babies — but a million times faster w/ NVIDIA’s Rev Lebaredian
Computers have been outperforming humans for years on tasks like solving complex equations or analyzing data, but when it comes to the physical world, robots struggle to keep up. It can take years to train robots to function in the messy chaos of the “real world” — but thanks to ... Show More
53m 27s
Dec 2024
How AI robots learn just like babies — but a million times faster w/ NVIDIA’s Rev Lebaredian
Computers have been outperforming humans for years on tasks like solving complex equations or analyzing data, but when it comes to the physical world, robots struggle to keep up. It can take years to train robots to function in the messy chaos of the “real world” — but thanks to ... Show More
53m 27s
Jul 2024
AI that connects the digital and physical worlds | Anima Anandkumar
“While language models may help generate new ideas, they cannot attack the hard part of science, which is simulating the necessary physics,” says AI professor Anima Anandkumar. She explains how her team developed neural operators — AI trained on the finest details of the real wor ... Show More
11m 6s
Sep 2024
Episode 490 - Matthias Christen - Head of CG Design, The Scope
Matthias Christen, the main 3D artist from The Scope on Ray Tracing FTW, shares his fascinating journey from traditional analog painting to becoming an expert in 3D and virtual production. Starting with a passion for drawing, Matthias entered the advertising industry, where he ho ... Show More
1h 14m
Jan 2025
How a worm could save humanity from bad AI | Ramin Hasani
What if AI could think and adapt like a real brain? TED Fellow and AI scientist Ramin Hasani shares how liquid neural networks — a new, more flexible AI technology inspired by physics and living brains — could transform how we solve complex problems. Hosted on Acast. See acast.co ... Show More
6m 21s
Dec 2024
Adam Brown – How Future Civilizations Could Change The Laws of Physics
Adam Brown is a founder and lead of BlueShift with is cracking maths and reasoning at Google DeepMind and a theoretical physicist at Stanford.We discuss: destroying the light cone with vacuum decay, holographic principle, mining black holes, & what it would take to train LLMs tha ... Show More
2h 43m
May 30
How AI models steal creative work — and what to do about it | Ed Newton-Rex
Generative AI is built on three key resources: people, compute and data. While companies invest heavily in the first two, they often use unlicensed creative work as training data without permission or payment — a practice that pits AI against the very creators it relies on. AI ex ... Show More
20m 5s
Nov 2023
3D Print Stem Cells, Puzzling Elephants, Believing Delusion
Today, you’ll learn about a new technique that can print stem cells, how elephants can solve puzzles, and if delulu is really the solulu. 3D Print Stem Cells “Scientists develop 3D printing method that shows promise for repairing brain injuries.” Science News. 2023. “Oxford resea ... Show More
11m 11s
Dec 2024
World's First Carbon-14 Diamond Battery, DeepMind's Genie 2, and Amazon's AI Mega-Computer
We're experimenting and would love to hear from you!In this episode of Discover Daily, we explore groundbreaking developments in battery technology as researchers from the University of Bristol and UK Atomic Energy Authority unveil a revolutionary diamond-encased battery powe ... Show More
9m 19s