Computer Vision news and analysis on Web Pulse: 4325 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers introduced Self-Geometry, a test-time adaptation method that enforces explicit epipolar consistency to improve vision foundation models' depth and pose predictions without full retraining. On the ETH3D benchm…
Contrastive learning, a self-supervised machine learning technique, trains models to pull similar data points together and push dissimilar ones apart in feature space without human labels, using methods like instance dis…
Researchers introduced a physical tokenizer that performs analogue light-to-token conversion directly at the sensor level for vision transformers, integrating a 32 × 32 photosensitive memory array of monolayer MoS2 float…
Amnesty International published a report on August 19 alleging that Argentina expanded AI-enabled surveillance infrastructure during President Javier Milei's first two years in office, with government procurement from 20…
A developer built a smart pill reminder system using YOLOv8 for semantic segmentation on a Raspberry Pi, with MQTT to trigger alarms and notifications. The system detects and identifies pills in real time, checking them …
Roboflow published a tutorial by Aarnav Shah detailing a DIY Connect 4 robot that uses a HiWonder MaxArm, RF-DETR object detection, a negamax engine, and Gemini 3.6 Flash with ElevenLabs to play and trash-talk. The syste…
Chinese AI company Deepseek released Deepseek-V4-Flash-Vision-Exp, an experimental multimodal model that adds image understanding to its text capabilities, and on Deepseek's internal benchmarks it nearly matches Opus 4.8…
Start-up noRecognition, founded by cybersecurity researcher Bill Swearingen, has proposed using its anti-AI computer-generated patterns as vehicle wraps to hide cars from Flock's AI-powered automatic license plate reader…
Police have wrongfully arrested individuals based on faulty AI-assisted Flock surveillance footage, as documented by Reason Magazine, with one woman spending seven months in legal battles after being identified as the wr…
DJI named 15 winners of its Enterprise Drone Onboard AI Challenge 2026 on August 20, including five Best Onboard AI Model Award winners and ten Industry Application Excellence Award winners, with projects ranging from ba…
Apple's forthcoming AirPods with cameras, revealed in a leaked macOS Tahoe video, are designed for computer vision and AI interpretation rather than personal photography, according to MacRumors. The earbuds will feature …
China's DeepSeek has announced a new experimental AI model capable of image processing, adding a visual dimension to its latest AI systems. The release comes amid reports of an $86 billion IPO buzz, positioning DeepSeek …
Researchers from the National Institute for Basic Biology in Japan found that an artificial neural network trained on first-person videos of natural landscapes also perceives the Benham's Top optical illusion, producing …
A developer released truden, an open-source npm package that lets users capture UI screenshots for AI assistants by holding Alt and shaking the mouse. The tool integrates with existing chat interfaces or vision LLM backe…
Brunswick CEO David Foulkes is betting on AI-powered auto-docking, an AI customer assistant, and a defense partnership with Textron to drive growth, including an unmanned surface vessel of which about 20 have been sold t…
Meta AI glasses, the most popular smart glasses on the market, are raising privacy concerns as their widespread use increases the risk of nonconsensual recording, prompting bans in schools, courts, restaurants, and enter…
VLM Run, founded by CEO Sudeep Pillai, launched an OpenAI-compatible gateway on August 19 that routes document-processing work across six open OCR and vision-language models, including GLM-OCR, DeepSeek-OCR-2, dots.mocr,…
DeepSeek released deepseek-v4-flash-vision-exp, a vision-language model that accepts images alongside text via the OpenAI-compatible Chat Completions API, supporting JPEG, PNG, GIF, and WebP formats. The model can be acc…
Hacker Bill Swearingen turned 31 million surveillance-evasion trials into a line of privacy-first clothing, letting wearers slip past facial-recognition cameras without a trace. The noRecognition project, launched in 202…
Video to Prompt, a free AI tool, generates editable English prompts from short videos or YouTube Shorts links, extracting visual style, subject, action, lighting, camera movement, and audio cues. The free tier allows 1 a…