image labeling

A short explainer from Nat and Friends on where Google Earth's 3D imagery comes from, how it is stitched together, and how often it is updated. It describes aircraft carrying camera rigs and photogrammetry that turns the photos into 3D models.

A six-minute clip of Adobe's MAX 2011 sneak peek showing a Photoshop prototype that removes motion blur from photos. The audience reacts with astonishment as blurry images become legible.

A guest video by Welch Labs on 3Blue1Brown explaining how text-to-image and video models work. It covers CLIP, shared embedding spaces, diffusion models (DDPM, DDIM), conditioning, guidance and negative prompts.

The Thought Emporium shows how to receive clear images directly from GOES-15, 16 and 17 and Himawari 8 geostationary weather satellites with software-defined radio. It covers the extra effort needed to receive GOES data.

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.

A one-minute scene from the film Enemy of the State showing absurdly implausible image enhancement, with freezing, rotating, zooming and focusing on a video.

A short Harris Corporation (L3Harris) promotional video showing wide-area airborne motion imagery, a sensor system for persistent real-time aerial surveillance of large areas.

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.

Alex O'Connor shows that ChatGPT cannot draw a wine glass filled to the brim, and ties the failure to David Hume's missing shade of blue. It asks what the failure says about how image models learn.

A 2006 Google TechTalk in which Luis von Ahn introduces human computation, using people's effort to solve problems like image recognition that computers cannot yet handle. It covers games with a purpose and related ideas such as CAPTCHAs.

A short side-by-side demo of a large image loading over a slow connection in JPEG, progressive mozjpeg, JPEG XL and AVIF. It shows how each codec renders partial data.

Benn Jordan's video about storing a PNG image in a living bird, a starling that learns to reproduce encoded sounds. It mixes ornithology, audio engineering, and data encoding.

Peter Norvig, then Director of Research at Google, talks at Startup School 2008 about leveraging large amounts of data and about technical challenges in Google projects such as image search. A central idea is that data can beat hand-written programming.

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.

Jessie Frazelle's DockerCon SF 2015 talk on running Docker containers for desktop applications, with fun container hacks and images. It shows how far containers can be pushed beyond servers.

A one-minute clip from a CSI episode featuring the trope of zooming and enhancing low-resolution images. The uploader says it was the last CSI episode they watched.

A two-minute supercut of film and TV characters ordering a computer to 'enhance' a blurry image into a perfectly sharp one. It is a remaster of an earlier 2009 version.

A spectrogram analysis of Aphex Twin's track commonly called [Equation] from Windowlicker, rendered from a lossless version. At about 5:30 the spectrogram reveals an image of Richard D. James's face.

A King of the Hill clip in which Hank-style character rants about saving images as PNG instead of JPEG after exporting from Windows Paint.

A two-minute compilation of TV and film scenes where investigators say 'enhance' and a blurry image becomes sharp. It mocks the trope.

A full upload of Alan Kay's 1987 talk, with demos of several Smalltalk-era software systems and ideas about visual, kinesthetic and symbolic reasoning. It includes a Smalltalk program written by a 12-year-old and footage of the Rand tablet.

MinutePhysics explains that computers store brightness nonlinearly, so blurring and blending colors in raw RGB gives wrong, dark results. It shows why mixed colors, such as in gradients, look off.

A short conference talk from !!Con 2017 in which Kevin Chen explains the HDR imaging algorithm from a foundational paper, framing it as a system of linear equations, and implements it in a Microsoft Excel spreadsheet. No prior image processing knowledge is needed.

Andrew Adams, a Halide developer, presents the Halide language for image processing and tensor computation. The talk explains the separation of algorithm from schedule with illustrated examples of parallelism, locality and redundancy tradeoffs.

An episode of the comedic You Suck at Photoshop series in which Donnie Hoyle teaches distort, warp and layer effects while vandalizing a Vanagon in the image. It won Webby awards as a how-to and comedy series.

Lesson 1 of fast.ai's Practical Deep Learning for Coders, taught by Jeremy Howard. It takes coders from running code in a Jupyter notebook straight into training a real image model.

A short demo of an open-source Krita plugin that uses Stable Diffusion to generate and edit images in place. It adds ControlNet scribble and line-art support. You select an area, push a button, and new matching content appears.

An artist describes discovering she has aphantasia, the inability to form mental images, and how it affects her work. She asks viewers about their own visualization.

A 2023 University of Toronto conversation between Geoffrey Hinton and Fei-Fei Li on responsible AI development. They look back at the history of deep learning and ImageNet and discuss the ethics and risks of AI.

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.

A short Techquickie explainer on why laptop webcams are much worse than phone cameras. It covers sensor size, image processing, and the interface differences between laptops and phones, with input from a Logitech engineer.

An HBO clip from Silicon Valley season 4 in which the 'Not Hotdog' app is demoed. The app classifies food photos as hot dog or not hot dog.

Adobe's sneak-peek demo of Content-Aware Fill ahead of Photoshop CS5, showing objects being removed and areas repaired seamlessly with the delete key.

An NBC Today Show correspondent appears to row a canoe in deep storm floodwater, though the water is only about six inches deep. The uploader notes it is a misleading depiction rather than intentional fake news.

The Blade Runner scene in which Deckard uses a voice-controlled machine to enhance a photograph, zooming into hidden details.

GeoGuessr pro Rainbolt plays head-to-head against an AI built by Stanford students that guesses locations from street-view images. The video shows the AI repeatedly beating him.

Mike Pound explains the discrete cosine transform and how it underpins JPEG compression. It is part two of Computerphile's JPEG series.

An excerpt from the 1983 BBC series Fun to Imagine in which Richard Feynman describes how he and a mathematician friend counted in their heads in different ways, one verbally and one visually. It shows that people can reach the same goal through quite different mental methods.

The first lecture in an 18-part series on digital photography from Marc Levoy's Stanford CS 178 course, recorded at Google in 2016. The series covers how digital cameras work and computational photography, with slides and assignments available on the course site.

Veritasium explains what a black hole should look like, using J.P. Luminet's 1979 work and a cardboard 3D model to show how light bends around it. It was made just as the first black hole image was released.