Computer Vision news and analysis on Web Pulse: 3358 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers have developed a $3,000 open-source maskless photolithography stepper that uses a DLP projector and deep learning computer vision to achieve sub-2-micron resolution, enabling low-cost microfabrication of devi…
Large language models lack grounding in the physical world and proposes creating Large Earth Models (LEMs) that combine satellite imagery and sensor data with AI to form a 'Planetary Intelligence.' This system could grou…
GPT Image 2 API defeated AuraFlow 27.4 to 20.5 in a head-to-head image generation test, winning on prompt-following accuracy across three tasks including a rooftop concert scene, a festival poster, and a tram stop vignet…
Developer EekoSystems released VisionBridge, an open-source proxy that gives text-only large language models vision capabilities by routing image analysis to a separate vision model. The MIT-licensed tool sits between ch…
A developer built Cutout, an AI background remover that runs entirely in the browser using WebAssembly and WebGPU, ensuring no photos are uploaded to any server. The tool offers instant removal, batch mode, background re…
Fans are increasingly using reverse image search tools like Face2social to verify celebrity social media profiles amid a surge of AI-generated fake accounts. Impersonators use advanced image editing to create convincing …
Meta released Muse Image, its first image generation tool from Meta Superintelligence Labs, now available in the Meta AI app. The tool uses Muse Spark AI reasoning to interpret prompts and create visuals, and it also pow…
Meta released Muse Image on July 7, its first image-generation model from Meta Superintelligence Labs, led by Alexandr Wang. The model integrates web searching and planning capabilities into Meta AI, powering new effects…
A new tool called Design Slop Cop lets users paste a URL to score how AI-generated a website looks, based on common AI design patterns. The project aims to classify the visual patterns that signal a site is purely AI-gen…
Meta launched Muse Image, its first image generation model from Meta Superintelligence Labs, now available in Meta AI. The model powers new creative tools across Instagram Stories and WhatsApp, allowing users to generate…
Meta Platforms rolled out Muse Image, its first image-generation model from Meta Superintelligence Labs, integrating it into Meta AI chatbot to power over 30 new effects for Instagram Stories and enable image generation …
Meta is donating Ray-Ban Meta AI glasses to every blind veteran in America, with over 130,000 eligible. The glasses assist with reading, navigation, and object identification via voice commands, restoring independence fo…
Apple's upcoming OS 27 updates introduce AI-powered features for the Home app, including multi-camera activity merging and plain-language event descriptions, but require a 2TB iCloud+ subscription ($9.99/month) to enable…
Amazon Web Services (AWS) announced a serverless image editing agent built on the Amazon Bedrock AgentCore harness, enabling users to edit photos via natural language prompts. The agent uses configuration-driven orchestr…
AI4Eyes has been accepted into the MEDTEQ+ Avise Program and awarded $700,000 to validate its AI-powered dry eye platform in real-world clinical settings within Quebec's health system. The one-year project, evaluated by …
Hisense has reduced the price of its 65-inch Hi-QLED 4K TV by 21%, dropping the cost from $478 to $377.99. The TV features a QLED panel, Total HDR Solution, and AI-powered enhancements like 4K upscaling and light sensing…
Researchers bypassed the age verification system of a website using AWS Rekognition by leveraging generative video AI models, demonstrating how attackers can exploit these tools to fool KYC processes. The French PVID fra…
BIOSTAR launched the EdgeComp MS-NAT4000, a compact edge AI computing system supporting the NVIDIA Jetson Thor T4000 module for high-performance AI computing, real-time sensor processing, and intelligent automation at th…
A bioRxiv preprint covered by Neuroscience News and PsyPost on July 7, 2026, reports that researchers recorded 79 infants with simultaneous EEG and DeepLabCut pose tracking, finding neural sensitivity to structured music…
Meta's SAM3 (Segment Anything Model 3) enables open-vocabulary object detection from text prompts without labeled data or training. Roboflow Workflows integrates SAM3 to build a warehouse asset search engine that detects…