Innovation at the Edge and in the Metaverse with Ziad Asghar

Ziad Asghar, Qualcomm’s Vice President of Product Management joined Sam to discuss what they’ve been cooking up to provide consumers with smarter, more capable and more useful devices using AI. Sam and Ziad discus how Qualcomm is innovating new technologies across different use cases such as AI-enabled modems for mobile communications, multi-sensor fusion and “shadow […]

#78 – Prof. NOAM CHOMSKY (Special Edition)

Patreon: https://www.patreon.com/mlst Discord: https://discord.gg/ESrGqhf5CB In this special edition episode, we have a conversation with Prof. Noam Chomsky, the father of modern linguistics and the most important intellectual of the 20th century. With a career spanning the better part of a century, we took the chance to ask Prof. Chomsky his thoughts not only on the […]

Acoustic synthesis for AR/VR experiences

Existing AI models do a good job of understanding images but require more work to understand the acoustics of environments in the related image. This is why researchers from Meta AI and the University of Texas are open-sourcing three new models for audio-visual understanding of human speech and sounds in video, helping us achieve immersive […]

Computer Vision – Lecture 1.1 (Introduction: Organization)

Lecture: Computer Vision (Prof. Andreas Geiger, University of Tübingen) Course Website with Slides, Lecture Notes, Problems and Solutions: https://uni-tuebingen.de/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/autonomous-vision/lectures/computer-vision/ The goal of computer vision is to compute geometric and semantic properties of the three-dimensional world from digital images. Problems in this field include reconstructing the 3D shape of an object, determining how things are moving […]

Embedding Invisible Codes in Objects for Augmented Reality

InfraredTags is a system for fabricating objects with embedded codes that are only visible to infrared cameras. These codes can be used for purposes such as metadata or interaction with devices through augmented reality. Read the technical paper: https://groups.csail.mit.edu/hcie/files/research-projects/infraredtags/2022-CHI-InfraredTags-paper.pdf YouTube Source for this AI Video

CoRL 2020, Spotlight Talk 417: Few-shot Object Grounding and Mapping for Natural Language Robot I…

“**Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following** Valts Blukis (Cornell University)*; Ross Knepper (Cornell University); Yoav Artzi (Cornell University) Publication: http://corlconf.github.io/paper_417/ **Abstract** We study the problem of learning a robot policy to follow natural language instructions that can be easily extended to reason about new objects. We introduce a few-shot language-conditioned […]

CoRL 2020, Spotlight Talk 158: Assisted Perception: Optimizing Observations to Communicate State

“**Assisted Perception: Optimizing Observations to Communicate State** Siddharth Reddy (UC Berkeley)*; Sergey Levine (UC Berkeley); Anca Dragan (EECS Department, University of California, Berkeley) Publication: http://corlconf.github.io/paper_158/ **Abstract** We aim to help users estimate the state of the world in tasks like robotic teleoperation and navigation with visual impairment, where user may have systematic biases that lead […]

Why the Metaverse is a Dystopian Nightmare & Niantic's Solution

Facebook’s vision of the Metaverse has been criticized by both consumers & other companies for its obvious dystopian outlook. But one of the most prominent Augmented Reality Companies in the world, Niantic has shown a much better looking futuristic vision of the metaverse. One in which the real world would only get augmented instead of […]

An AI Learned To See Through Obstructions! 👀

❤️ Check out Snap’s Residency Program and apply here: https://lensstudio.snapchat.com/snap-ar-creator-residency-program/?utm_source=twominutepapers&utm_medium=video&utm_campaign=tmp_ml_residency ❤️ Try Snap’s Lens Studio here: https://lensstudio.snapchat.com/ 📝 The paper “Learning to See Through Obstructions” is available here: https://alex04072000.github.io/ObstructionRemoval/ https://github.com/alex04072000/ObstructionRemoval 📝 Try it out here: https://colab.research.google.com/drive/1iOKknc0dePekUH2TEh28EhcRPCS1mgwz  🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex […]

Why Facebook is beating Apple in Augmented Reality – Facebook AR Glasses

Facebook isn’t just fighting Apple in a lawsuit due to Apple’s strict privacy rules, but is also trying to beat Apple in what both consider to be the next computing platform of the future: Augmented Reality Glasses and Headsets. Both see the future of Apple and Facebook away from regular old Smartphones and instead in […]

Creating Real-Time Depth Maps for Occlusions in AR •

In order to make augmented reality (AR) more realistic, we need to be able to apply AR effects both in front and behind objects in a scene. Most AR systems, however, are based on SLAM, which only tracks a few sparse point features. This allows for overlays in front of objects, but not behind them. […]

Amazing AR Effects Are Coming!

❤️ Check out Weights & Biases and sign up for a free demo here: https://www.wandb.com/papers Their mentioned post is available here: https://app.wandb.ai/latentspace/published-work/The-Science-of-Debugging-with-W%26B-Reports–Vmlldzo4OTI3Ng 📝 The paper “Consistent Video Depth Estimation” is available here: https://roxanneluo.github.io/Consistent-Video-Depth-Estimation/ 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Paden, […]

Incredible New Battery Stays Charged Forever! – Human-Powered Battery

Batteries are about to stay charged for up to 100X longer very soon due to a new futuristic breakthrough Battery Technology. These new batteries are partially being charged by human movement and sweat. This new technology will soon power things like phones, smart watches and soon even augmented reality glasses for much longer than before. […]

Computer Vision for Remote AR with Flora Tasse – #390 (Video)

Today we conclude our CVPR coverage joined by Flora Tasse, Head of Computer Vision & AI Research at Streem. Flora, a keynote speaker at the AR/VR workshop at CVPR, walks us through some of the interesting use cases at the intersection of AI, computer vision, and augmented reality technology. In our conversation, we discuss how […]

Next Gen Infrastructure & Industry 4.0: Immersive tech and Industry 4.0

Next Gen Infrastructure & Industry 4.0: Immersive tech and Industry 4.0 Adoption of AR and VR technologies are already driving tangible benefits and providing a clear ROI for industry 4.0. From helping to build industrial digital twins and exploring the future of an augmented workforce, immersive tech has been crucial during the pandemic to build […]

Smartphones are OBSOLETE! – Vuzix Next Generation Smart Glasses

Smartphones have become old technology by now and is soon going to be replaced by the next big thing. Vuzix has created the first lightweight Smart AR Glasses that can project holograms at high contrast while still looking like regular glasses. The Vuzix next generation smart glasses feature futuristic micro-LED display technology to project augmented […]

The Rise of Consumer Augmented Reality Glasses – Magic Leap 2

The next generation of Augmented Reality Glasses is about to release to consumers and buisnesses. They finally seem to have everything in terms of display technology to controls and even futuristic features no previous smart glasses gadget had. And most importantly, they seem to be the best looking AR Glasses around. Magic Leap originally became […]

The Shocking Plans of Facebook Revealed – The Metaverse & More

Facebook is currently working on a bunch of secret and rather creepy projects like what they call the metaverse and another secret project which is meant to revolutionize the way humans interact with each other. Ever since Oculus VR was absorbed by Facebook Reality Labs, its goal is to put every human in a virtual […]

TensorFlow.js (TF Dev Summit '20)

TensorFlow.js allows you to use machine learning anywhere that JavaScript can run – which is pretty much everywhere! Check out our latest easy to use machine learning models we launched this year: 1. FaceMesh which can detect 486 points on a human face in real time enabling AR or whatever creative idea you may have. […]

4 Opportunities and 1 Warning for Technology Leaders Wanting to Adopt Deep Learning

I presented four 4 opportunities and 1 warning for technology leaders wanting to adopt deep learning for Washington University McKelvey School of Engineering. In this video I look at automation, prediction, augmented reality, and personalization applications offered by deep learning. We look at how traditional predictive modeling compares to deep learning, and where it all […]

TensorFlow.js Community "Show & Tell" #4

6 new demos from the #MadeWithTFJS global community pushing the boundaries of on device machine learning in JavaScript. Hosted by Jason Mayes. TensorFlow.js Show & Tell music video → https://goo.gle/3qR2NNQ Scroobly → https://goo.gle/379dK5x Sudoku in-depth how it was made → https://goo.gle/2W9fkxC Sudoku live demo → https://goo.gle/3qNGx7m AVA – Automated Videoing Assistant → https://goo.gle/3m4dAQY AVA Twitter […]

Attomoto by James Seo – Made with TensorFlow.js

In our 8th episode of Made with TensorFlow.js we head to the USA to meet with James Seo who has created a visually stunning mixed reality demo to help us understand human pose over space and time that can be inspected from any angle you desire using WebXR. Attomoto by James Seo → https://goo.gle/2FGgJaj Watch […]

Haptic Intelligence with Katherine J. Kuchenbecker – #491

In this episode, we’re joined @Katherine J. Kuchenbecker, director at the @Max Planck Institute for Intelligent Systems. In our conversation, we explore Katherine’s research interests, which lie at the intersection of #haptics (physical interaction with the world) and #machinelearning, introducing us to the concept of “haptic intelligence.” We discuss how #ML, mainly #computervision, has been […]

Neural Synthesis of Binaural Speech From Mono Audio with Alexander Richard – #514

Today we’re joined by Alexander Richard, a research scientist at Facebook Reality Labs, and recipient of the ICLR Best Paper Award for his paper “Neural Synthesis of Binaural Speech From Mono Audio.” We begin our conversation with a look into the charter of Facebook Reality Labs, and Alex’s specific Codec Avatar project, where they’re developing […]