Computer Vision news and analysis on Web Pulse: 3409 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Clement Levallois has compiled a curated list of 164 generative AI applications for visual creation, organized into 11 categories. The list ranks tools for creating, editing, and enhancing images, videos, and 3D models, …
A developer has created a reverse CAPTCHA system designed to be solved by automated agents rather than humans, flipping the traditional security model. The system, called Clanker CAPTCHA, presents challenges that are del…
A Russian military KamAZ truck has been photographed with a black-and-white "dazzle camouflage" pattern, a World War I naval technique designed to confuse optical rangefinders, in an apparent attempt to evade Ukrainian s…
A developer reverse-engineered the world maps from the 1990 DOS game Test Drive III: The Passion after five years of work, using AI to reconstruct the game's 3D tile-based terrain as accurately as possible. The project e…
A three-woman research team at the Birla Institute of Technology Mesra in Ranchi has trained artificial intelligence models to detect and analyze lunar craters, with funding from the Indian Space Research Organisation. T…
A developer in Ouagadougou, Burkina Faso, built a vision-language model that detects blockchain attacks invisible to text-based security systems. The fine-tuned model, named Imina-Na, identified a Drain Star attack that …
A developer released SnapName, a Mac app that uses a local AI model to automatically rename screenshots with descriptive filenames. The app watches a designated folder and generates three AI name suggestions for each new…
XAI's Grok Imagine Video 1.5 Preview has claimed the top spot on the Image-to-Video Arena leaderboard with an Elo score of 1473, surpassing ByteDance's model at 1467. The ranking, which aggregates over 1.1 million votes …
Microsoft will preview three new AI models at its Build conference on June 2 in San Francisco, including MAI-Transcribe-1.5, MAI-Image-2.5, and MAI-Voice-2, none of which are publicly available yet. The models are design…
A promotional post for M Countdown's "Mega Concert" sparked criticism on May 30, 2026, after netizens on theqoo noticed performers' faces appeared distorted in images shared by Mega MGC Coffee's official Twitter account.…
A new age verification system called BorderAge allows users to anonymously prove their age using only hand gestures, eliminating the need for IDs, selfies, or personal data. The system generates a privacy-preserving PIN …
A Hacker News user proposes that smart glasses could automatically switch between focus modes for phone and computer use by leveraging existing device detection technology, such as iPhones recognizing when a user is look…
MicroAGI, a German startup, is offering free apartment cleaning to New York City residents in exchange for permission to record the entire process using cameras attached to cleaners' hats. The company will use the footag…
A weekly reading list shared by a blogger includes articles on AI detection failures in war propaganda, US law enforcement warnings about "anti-tech extremism," and the environmental impact of data centers. The collectio…
Shift, a startup offering free professional home cleaning in New York, is recording every cleaning task via head-mounted cameras to train future robot agents. The company trades spotless apartments for hours of first-per…
A new benchmark evaluating DocumentAI models on bounding box accuracy shows GPT-5.5 and Gemini 3.5 leading with 67.7% and 67.5% scores respectively, while Qwen, Kimi, and Mistral trail significantly. The test, run on Ope…
DESKi launched HeartFocus Link, an FDA-cleared AI-guided cardiac imaging product that connects a tablet running guidance software to any cart-based ultrasound system via HDMI. The software, previously limited to Butterfl…
A solo developer built SafetyVision, an open-source PPE compliance monitor that performs core workplace-safety detection for free, over eight weeks. The tool uses a fine-tuned YOLOv8 model to analyze camera feeds for vio…
Tapflow has released an MCP server that connects vision-capable LLMs to its mobile simulator platform, giving AI models the ability to see screenshots and execute actions like tapping, swiping, and typing. The `@tapflowi…
NVIDIA has released SANA, an efficiency-oriented codebase for high-resolution image and video generation that includes complete training and inference pipelines. The open-source repository provides models for SANA, SANA-…