image classification

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 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.

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.

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.

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.

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.

3Blue1Brown introduces group theory and abstract groups, then builds toward classification of finite simple groups and the enormous Monster group with its 196,883 dimensions.

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.

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

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.

A short video built around an animation of the roughly 10,000 galaxies in the Hubble Ultra Deep Field, placed at their measured redshift distances. It gives a brief history of deep field images and ends with a 3D fly-through.

Explains the proposed NASA JPL plan to use the Sun as a gravitational lens, sending solar sail craft to its focal region to image an exoplanet's surface. It covers the distances involved, how imaging with the Sun would work and the mission design.

PBS Space Time explains the proposal to use the Sun's gravity as a giant lens, sending a train of small light-sail spacecraft to the focal point roughly 550 AU out. It covers how such a telescope could image exoplanets in surprising detail and the engineering challenges involved.

3Blue1Brown explains space-filling curves and the Hilbert curve, and how infinite mathematical constructions connect to finite, practical approximations. It touches on mapping between dimensions and sensory ideas.

Wes Bos breaks down the techniques behind the McMaster-Carr website's speed: server-rendered HTML, prefetching, CDN and service worker caching, preloading, critical CSS and fixed-size images. He also notes its old-school jQuery and YUI JavaScript.

The Slow Mo Guys film a TV and screens with a high-speed camera to show how displays build an image. The footage includes CRT-style scanning and how pixels light up over time.

A Two Minute Papers episode on NVIDIA's recurrent denoising autoencoder, which cleans up noisy Monte Carlo path-traced image sequences. It shows how a neural network can produce usable renders from very few samples.

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.

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.