vision

Luke Miani removes the screen from a MacBook Air and tests using it headless as the host for an Apple Vision Pro virtual display.

Marques Brownlee shares his hands-on impressions of Apple's $3500 Vision Pro headset after trying it. He covers the spatial computing experience, eye tracking, and how it compares to other devices.

Andrew Ng presents unsupervised feature learning and deep learning, showing how algorithms can learn representations from unlabeled data instead of hand-designed features. He gives examples in vision and audio, including visualizations of features learned by successive layers.

A PyCon 2012 talk by Kurt Grandis on building an automated water-squirting turret that uses Python and computer vision to detect and drive off squirrels from a bird feeder.

Veritasium visits the US Navy's Crane facility to test top night vision goggles. It explains how image intensifier tubes and thermal or digital systems work and compares the generations of the technology.

Technology Connections explains how analog television produced moving images without computers, covering scanning, CRTs and standards like NTSC and PAL. It is part of a series on analog TV.

Overdrive 2 by TiTAN, a Sega Mega Drive demo that won first place in the Oldskool competition at Revision 2017. It shows effects and 3D graphics on the stock console.

Hartverdrahtet by Akronyme Analogiker, the winning PC 4k intro at Revision 2012. It is a realtime demo with music and fractal visuals in 4096 bytes.

A one-minute clip from James Burke's 1978 BBC series Connections in which he walks past a Saturn V rocket and a timed take-off happens behind him in a single shot, with no green screen.

Jellyvision hosts Basecamp founders Jason Fried and David Heinemeier Hansson for a Q&A about open source, productivity, feature requests and taking care of customers.

Mark Handley of UCL looks at how SpaceX's November 2018 revisions to the Starlink constellation affect network behavior. The video visualizes the orbits and routing and estimates latencies, building on his earlier video and research paper.

Megan McArdle's AEI Vision Talk 'Capital and Poverty' argues that social and financial capital work differently in low-income communities, and that this explains barriers to reaching the middle class.

A one-minute clip about Paul Otlet, the Belgian bibliographer who in 1934 imagined users accessing a remote database through an electric telescope over a phone line. It presents his vision as a precursor of the web.

A two-minute clip of Steve Jobs at WWDC 2007 introducing the plan for iPhone third-party apps as web apps built on Safari and Ajax. It shows the original vision before the native SDK and App Store.

Jafar Husain of Netflix explains at React.js Conf 2015 how Netflix runs React-style rendering without the DOM on smart TVs and game consoles. It uses a canvas-like API for performance.

Retro Game Mechanics Explained shows how the Atari 2600 draws images with almost no video memory, by having the CPU race the CRT beam line by line. It walks through the techniques in detail.

Microsoft's 2015 concept video imagining how ubiquitous computing, collaboration services and data analytics might change work 5-10 years later.

CNN footage of correspondent Omar Jimenez and his crew being arrested live on air by police while covering protests in Minneapolis in 2020, after identifying themselves as press.

Andrej Karpathy, then Tesla's head of AI, gives a CVPR 2021 workshop keynote on how Autopilot's neural networks work. A large part covers the move to a vision-only stack, including why radar was dropped and how vision produces depth estimates.

Andrej Karpathy's CVPR 2021 presentation on Tesla's Autopilot, covering its vision-based approach, sensor choices and the scale of Tesla's deep learning compute cluster. This upload is a lower-quality copy of the talk.

A University of Tokyo demo of a rock-paper-scissors robot that always wins, using high-speed vision to read the human hand and respond faster than people can perceive.

The first lecture of Stanford's CS231n course on convolutional neural networks for visual recognition. It surveys the history and key challenges of computer vision, from the Cambrian explosion and Hubel and Wiesel to ImageNet.

The first lecture of Stanford's CS231n Winter 2016 course on convolutional neural networks for visual recognition, introducing the course and the historical context of computer vision.

A short demo from the Ishikawa Komuro Lab of a high-speed robot hand paired with a 1000fps vision system performing dexterous manipulation. It shows what very low-latency vision and actuation can do.

A demo of PREDATOR (TLD), a real-time object tracker that learns the appearance of its target and improves while it tracks. The technology was later developed commercially.

Short Airbus footage of its ATTOL project, in which a test aircraft performed a fully automatic, vision-based take-off at Toulouse-Blagnac. The crew ran eight take-offs over several hours.

A three-minute demo of ProFORMA, a system from Cambridge that builds textured 3D models live from a video of an object.

Andrej Karpathy, then Tesla's head of AI, presents at ScaledML 2020 on how Tesla builds full self-driving using vision-based neural nets and fleet data collection. He covers training custom detectors and neural nets gradually replacing traditional code.

A long livestream of George Hotz live-coding a toy SLAM implementation, twitchslam, over two days in May 2018. It is an unedited session of Python programming with computer vision and visualization.

FortNine looks at why Tesla Autopilot has rear-ended motorcyclists, speculating that the vision system misreads motorcycle taillights as a distant car. It argues that radar and other sensors would help.

The CVPR 2016 oral demo of Face2Face, a system that captures a person's face and reenacts another video's face in real time using only RGB video. The authors frame it as research on modern vision and graphics.

A one-minute clip of Steve Jobs at the D3 conference in 2005 discussing virtual reality. He compares VR headsets to headphones for video, an analogy later applied to Apple's Vision Pro.

Apple's full WWDC 2023 keynote, covering the 15-inch MacBook Air, new Mac hardware, iOS, iPadOS, macOS, watchOS and the unveiling of Apple Vision Pro. It runs about two hours.

A SIGGRAPH Asia 2013 research demo of 3-Sweep, a tool for extracting editable 3D objects from a single photo using a few user strokes. It predates modern AI image tools.

Mobileye co-founder and CTO Amnon Shashua explains what goes into sensing for autonomous driving and whether end-to-end deep learning can work for it. He argues for decomposing the problem.

A short demo of the Deep Visualization Toolbox, which shows the activations inside a convolutional neural network as it processes live camera input. Viewers see individual units responding to edges, faces and text.

A short video accompanying the CVPR 2018 paper Learning to See in the Dark. It shows a neural network producing sharp images from very low-light raw sensor data, compared against denoising approaches.

Steve Mould explains motion amplification and video magnification, techniques that find tiny changes in video invisible to the eye and exaggerate them. He covers the MIT research and industrial uses such as diagnosing vibrating machinery.

Berkeley neuroscientist Jack Gallant shows how fMRI brain mapping can be used to decode what a person sees, with visualizations of brain activity and its implications.

The video accompanying the SIGGRAPH 2012 paper on Eulerian Video Magnification. It amplifies subtle changes in ordinary video, such as skin color shifts from a heartbeat, to reveal pulse and tiny motions.