De-Raining-Algorithm for posttrue AI-Sunshine

Gepostet vor 3 Monaten in #Science #Tech #AI #AlgoCulture #Fake #Weather

Share: Twitter Facebook Mail

rain1

Die viel faszinierendere Lüge von Trump nach seiner Amtseinführung war ja in meinen Augen, dass er behauptete, es hätte aufgehört zu regnen und die Sonne wäre rausgekommen, als er mit seiner Rede begann. Menschenmassen mögen auch auf Bildern schwer einzuschätzen sein, aber jeder konnte mit eigenen Augen sehen, dass es regnete.

Mr. Trump said that though he had been “hit by a couple of drops” of rain as he began his address on Inauguration Day, the sky soon cleared. “And the truth is, it stopped immediately, and then became sunny,” he said. “And I walked off, and it poured after I left. It poured.”

The truth is that it began to rain lightly almost exactly as Mr. Trump began to speak and continued to do so throughout his remarks, which lasted about 18 minutes, and after he finished.

rain2

rain0Trump wird sich schon bald keine Sorgen mehr um das Wetter machen müssen, Wissenschaftler arbeiten an automatischen Entregnungsalgorithmen, die ihm schon bald die Arbeit seiner aufwändig konstruierten postfaktischen Wetterwahrheit abnehmen werden. Die Ergebnisse sind (noch) eher mau, aber wir arbeiten daran.

Paper: Image De-raining Using a Conditional Generative Adversarial Network (via CreativeAI)

Abstract: Severe weather conditions such as rain and snow adversely affect the visual quality of images captured under such conditions thus rendering them useless for further usage and sharing. In addition, such degraded images drastically affect performance of vision systems. Hence, it is important to solve the problem of single image de-raining/de-snowing. However, this is a difficult problem to solve due to its inherent ill-posed nature. Existing approaches attempt to introduce prior information to convert it into a well-posed problem. In this paper, we investigate a new point of view in addressing the single image de-raining problem. Instead of focusing only on deciding what is a good prior or a good framework to achieve good quantitative and qualitative performance, we also ensure that the de-rained image itself does not degrade the performance of a given computer vision algorithm such as detection and classification. In other words, the de-rained result should be indistinguishable from its corresponding clear image to a given discriminator. This criterion can be directly incorporated into the optimization framework by using the recently introduced conditional generative adversarial networks (GANs). To minimize artifacts introduced by GANs and ensure better visual quality, a new refined loss function is introduced. Based on this, we propose a novel single image de-raining method called Image De-raining Conditional General Adversarial Network (ID-CGAN), which considers quantitative, visual and also discriminative performance into the objective function. Experiments evaluated on synthetic images and real images show that the proposed method outperforms many recent state-of-the-art single image de-raining methods in terms of quantitative and visual performance.

Neural Network cooks with Cthulhu

Janelle Shane spielt mit Neural Networks rum und hat eins davon auf Lovecraft trainiert. Dann hat sie das Neural Network…

Next Level, photorealistic Style-Transfer

In ihrem neuen Paper stellen Fujun Luan, Sylvain Paris, Eli Shechtman und Kavita Bala eine neue Style-Transfer-Methode vor: Figure 1:…

Blacked Out Censorship-Poetry Generator

Schöne Spielerei von Max Kreminski, ein JS-Droplet, das Websites in Blacked Out Poetry verwandelt, basierend auf Liza Dalys █ Blackout…

This Bot kills Fascists

So-So-Working-Object-Detection-Algorithm + Woodie Guthrie = Fascists.exe | „This bot kills fascists“.

„Alexa? Are you connected to the CIA?“

„I always try to tell the truth.“ This reminds me of those Guilty-Dog-Videos:

Palm Generator

Es sollte mehr entspannte Algorithmen mit Urlaubs-Attitüde geben wie den hier: „The Palm Generator is a Three.js module to create…

AI Brainscans

Graphcore aus Bristol visualisieren künstliche Intelligenzen und Neural Networks: Inside an AI 'brain' - What does machine learning look like?…

A Banana Keytar and more from Stupid Hackathon: Inverted Eyetracker-Pong, Robot Porn Addict or the Shitty Sharpie Tattoo Gun)

Ein weiterer Fav vom Stupid Hackathon NYC 2017, die Banana-Keytar von Amanda Lange. Auch geil: der Twitter-Bot Robot Porn Addiction,…

Fotorealistische Pics aus der Gameboy-Camera

Roland Meertens generiert fotorealistische Farbbilder aus den Pics der Gameboy-Camera: Creating photorealistic images with neural networks and a Gameboy Camera.…

Pix2Pix: Neural Network Katzen-Compositing als Browsertoy

Schönes Spielzeug von Christopher Hesse, der ein Neural Network auf Bild-Paaren trainiert hat und mit dem man nun Katzen, Schuhe…

Automatic Handgun Detection via Machine Learning

The latest Step into an OCP-approved Ed-209-compatible Future: Automatic Handgun Detection Alarm in Videos Using Deep Learning (PDF). Usage Guide:…