NVIDIA's New AI: Enhance! 🔍

6:25

NVIDIA's New AI: Enhance! 🔍

Two Minute Papers 27.03.2022 208 839 просмотров 10 515 лайков

Machine-readable: Markdown · JSON API · Site index

Смотреть на YouTube

Поделиться Telegram VK Бот

Транскрипт Скачать .md

Анализ с AI

Описание видео

❤️ Check out Lambda here and sign up for their GPU Cloud: https://lambdalabs.com/papers 📝 The paper "EG3D: Efficient Geometry-aware 3D Generative Adversarial Networks" is available here: https://matthew-a-chan.github.io/EG3D/ 📝 The latent space material synthesis paper "Gaussian Material Synthesis" is available here: https://users.cg.tuwien.ac.at/zsolnai/gfx/gaussian-material-synthesis/ ❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: - https://www.patreon.com/TwoMinutePapers - https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Balfanz, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bryan Learn, Christian Ahlin, Eric Martel, Gordon Child, Ivo Galic, Jace O'Brien, Javier Bustamante, John Le, Jonas, Jonathan, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Paul F, Rajarshi Nigam, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Ted Johnson, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi. If you wish to appear here or pick up other perks, click here: https://www.patreon.com/TwoMinutePapers Thumbnail background image credit: https://pixabay.com/photos/discus-fish-fish-aquarium-fauna-1943755/ Thumbnail background design: Felícia Zsolnai-Fehér - http://felicia.hu The thumbnail is used as illustration. Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://discordapp.com/invite/hbcTJu2 Károly Zsolnai-Fehér's links: Instagram: https://www.instagram.com/twominutepapers/ Twitter: https://twitter.com/twominutepapers Web: https://cg.tuwien.ac.at/~zsolnai/ #NVIDIA

Оглавление (11 сегментов)

Intro

Dear Fellow Scholars, this is Two Minute Papers with Dr. Károly Zsolnai-Fehér. Today we are going to see how NVIDIA’s new AI can do 3 seemingly impossible things with just one elegant technique.

Nerve Based Technique

For reference, here is a previous method that can take a collection of photos like these, and magically, create a video where we can fly through these photos. This is what we call a NERF-based technique, and these are truly amazing. Essentially, photos go in, and reality comes out. So, I know you are thinking, Károly, this looks like science fiction. Can even this be topped? And the answer is yes. Yes it can! Now, you see, this new technique can also look at a small collection of photos, and, be it people or cats, and it learns to create a continuous video of them. These look fantastic. And remember, most of the information that you see here is synthetic. Which means, it is created by the AI. So good! But, wait, hold on to your papers, because there is a twist! It is often the case for some techniques that they think in terms of photos. While other techniques think in terms of volumes. And get this,

Hybrid Technique

this is a hybrid technique that thinks in terms of both! Okay…so what does that mean? It means this! Yes, it also learned to now only generate these photos, but also, the 3D geometry of these models at the same time. And this quality for the results is truly something else. Look at how previous

Previous Techniques

techniques struggle with the same task. Wow. They are completely different than the input model. And you might think that of course they are not so good. They are probably very old methods. Well, not quite! Look, these are not some ancient techniques, for instance, GIRAFFE is from the end of 2020 to the end of 2021 depending on which variant they used. And, let’s see what the new method does on the same data…wow. My goodness. Now that is something. Such improvement in so little time. The pace of progress in AI research is nothing short of amazing. And not only that, but everything it produces is multi-view consistent. This means that we don’t see a significant amount of flickering as we rotate these models. There is a tiny bit on the

Usability

fur of the cats, but other than that, very little. That is a super important usability feature. But wait, it does even more. Two, it can also perform one of our favorites, super resolution.

Super Resolution

What is super resolution? Simple, a coarse, pixelated image goes in, and what comes out? Of course, a beautiful, detailed image. And here comes number three. It projects these images into a latent space. What does that mean?

Latent Space

A latent space is a made-up place where we are trying to organize data in a way that similar things are close to each other. In our earlier work, we were looking to generate hundreds of variants of a material model to populate this scene. In this latent space, we can concoct all of these really cool digital material models. A link to this work is available in the video description.

Human Faces

Now, let's see. Yes. When we take a walk in the internal latent space of this technique, we can pick a starting point, a human face, and generate these animations as this face morphs into other possible human faces. In short, this can generate a variety of different people. Very cool. I love it! Now, of course, not even this technique is perfect, I see some flickering around the teeth, but otherwise,

Virtual People

this will be a fantastic tool for creating virtual people. And remember, not only photos of virtual people, we get the 3D geometry for their heads too. With this, we are one step closer to democratizing the creation of virtual humans in our virtual worlds. What a time to be alive! And, if you have been holding on to your papers so far, now, squeeze that paper! Because get this,

Conclusion

you can do all of this in real time. And all of these applications can be done with just one elegant AI technique. Once again, scientists at NVIDIA knocked it out of the park with this one. Bravo. So, what about you? If all this can be done in real time, what would you use this for? I’d love to know - please let me know in the comments below.

Outro

Thanks for watching and for your generous support, and I'll see you next time!

Другие видео автора — Two Minute Papers

Ctrl+V

Экстракт Знаний в Telegram

Экстракты и дистилляты из лучших YouTube-каналов — сразу после публикации.

Подписаться

Лучшие методички за неделю — каждый понедельник