image processing

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

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.

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.

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

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.

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 University of Tokyo lab demonstrates a book scanner that flips pages automatically and scans over 250 pages per minute. It uses real-time 3D recognition of the flipped pages and then restores each one to a flat image.

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.

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 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.

A player piano is made to reproduce human speech, here reciting a European Environmental Criminal Court proclamation in German at the 2009 World Venice Forum. This upload adds subtitles so the words become understandable.

Neural-network upscaled, 60 fps, stabilized and colorized version of 1902 footage of the Wuppertal Schwebebahn suspended railway in Germany. The source film comes from MoMA. It gives a vivid view of an early-1900s city and a train system that still runs.

SoundHound's CEO demos Hound, a voice assistant, handling fast compound natural language queries with context and detailed criteria. The video leaked before the product's official launch.

A Burnistoun sketch from BBC Scotland in which two men try to use a voice-recognition elevator that cannot understand their Scottish accents.

UploadVR covers a Facebook Reality Labs prototype that tracks facial expressions using cameras mounted in a VR headset. The updated version captures subtle micro-expressions for realistic avatars.

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 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.

Jack Gallant's lab demonstrates reconstructing movie trailer clips a subject watched from fMRI brain activity, using regression models trained on hours of viewing data. The video shows the original clip beside the reconstruction.

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.

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 short live demo of Dental Wings' Virtuo Vivo intraoral scanner at IDS 2019. It shows a fast color scan with a small, lightweight handpiece.

A BBC News segment on University of Washington research that synthesized a photorealistic Obama video, modeling mouth movement so any audio can be put in his mouth.

A sketch from the Scottish comedy show Burnistoun in which two men cannot get a voice-recognition elevator to understand the word eleven in their accents.

Google ATAP's short 2014 introduction to Project Tango, a mobile device effort to give phones and tablets a human-scale understanding of space and motion. It pitches ideas like indoor navigation and games that interact with your physical space.

A Burnistoun sketch in which a voice-recognition elevator cannot understand two Scottish men saying the number eleven. It satirizes voice interfaces that fail on accents.

A three-minute clip about Ernst Dickmanns' VaMoR and VaMP projects, in which fully autonomous vehicles drove thousands of miles on public roads in the 1980s. It is a brief look at early German self-driving research.

A one-minute demo of Word Lens, an iPhone app that translates printed text in real time by overlaying the translation on the camera view. It was later folded into Google Translate.

A short 2009 amateur video showing an HP MediaSmart webcam whose face tracking follows a white face but fails to track a black face. The uploader presents it as humorous.

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

Jamie Oliver shows school kids how chicken nuggets are made by blending skin and mechanically reclaimed meat, as part of his school lunch campaign. The kids react with disgust.

Elevated is a 4 kilobyte PC demo by RGBA and TBC from Breakpoint 2009. It fly-throughs a realistic procedurally generated landscape with synthesized music and post-processing, all from a tiny executable.

A short Stanford video in which Chao-Lin Kuo surprises Professor Andrei Linde with BICEP2 evidence supporting cosmic inflation, the first apparent images of primordial gravitational waves.

A short demo of interactive AI live painting in Krita using the Stable Diffusion plugin, where canvas changes update the generated image immediately. It uses an LCM sampler for speed and needs a high-end GPU for the interactive feel.

A spectrogram visualization of the sounds in a dial-up modem handshake, with an annotated image explaining each noise. It shows how the handshake's tones map to the negotiation steps.

The famous 1984 Apple Macintosh Super Bowl commercial, directed by Ridley Scott and based on Orwell's Nineteen Eighty-Four. It casts the Mac as a force freeing individuals from a Big Brother figure, widely read as aimed at IBM.

A short clip of Venetian Snares' track 'Look' from Songs About My Cats (2001), shown as a spectrogram. The audio encodes an image in its frequency content.