Computer Vision news and analysis on Web Pulse: 3371 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
XAI's Grok Imagine image generation model, now available on Puter.js, claims to be 15-20x faster than competitors. Puter.js tested both standard and quality tiers against GPT Image 2 and Nano Banana models, measuring end…
Samsara launched Ride Along, an AI-powered virtual ride-along feature that evaluates driver behavior over continuous 10-30 minute sessions to provide a full behavioral picture rather than flagging only rare negative even…
Brazilian startup Gabriel uses AI-powered cameras to scan license plates and share data with police, aiming to solve theft cases in São Paulo, Rio de Janeiro, and Belo Horizonte. Critics raise privacy concerns after reve…
A developer demonstrates how transfer learning enables high accuracy with few examples by reusing a pretrained model's general features. An interactive demo races accuracy curves for training from scratch versus transfer…
Scientists have fully read a charred Herculaneum scroll without opening it, using X-ray tomography and machine learning. The scroll, PHerc. 1667, contains a Stoic philosophical treatise on ethics. This breakthrough was a…
China's government issued a voluntary code of conduct for smart glasses manufacturers, urging them to obtain explicit consent before recording and to include LED recording indicators. The guidelines also promote a minimu…
Aleph Neuro published a technical analysis of its through-skull ultrasound imaging approach, using microbubbles and localization microscopy to produce high-resolution vascular brain images without opening the skull. The …
Orbbec showcased AI-powered 3D vision systems at Automate 2026 in Chicago, including the LingBot-Depth for Gemini 330 Series developed with Robbyant to enhance robotic spatial perception. The systems address industrial c…
Yuri Zaporozhets of QRV Systems has built a RISC-V-based personal computer and a mainframe on an FPGA, both using the Olimex GateMate A1-EVB board. The GateMate PC emulates a late-1980s IBM PC-compatible with a 25 MHz RI…
Roboflow released a tutorial on fine-tuning RF-DETR Keypoints on custom data, demonstrating the process using a basketball court detection dataset with 33 landmarks. The model extends the RF-DETR architecture for real-ti…
Researchers developed a computer vision system to automate core alignment inspection in multi-core optical fibers, replacing manual methods that are slow and error-prone. The system uses image processing to detect fiber …
The most upvoted papers on Hugging Face on June 26, 2026, reveal three major AI trends: smarter agents, more flexible image/video generation models, and more efficient multimodal representations. Notable papers include a…
A developer built a multimodal AI pipeline in under 55 lines of Python using yait_aichain's Skill and Model primitives, chaining Claude, an image generation model, and Qwen Vision across three providers (Anthropic, xAI, …
A scoping review in npj Digital Medicine maps the use of AI to fight malaria, which killed nearly 600,000 people in 2023, 94% in Africa. While AI shows high accuracy in lab settings, the review highlights bottlenecks inc…
Runway's fourth annual AI Film Festival in Los Angeles showcased 10 short films made entirely with AI video tools, leaving a Fast Company reporter feeling optimistic about the technology's creative potential. The festiva…
Two new reports from IAB and Integral Ad Science show that keyword-based brand safety blocking excludes 54% of video content unnecessarily, but multimodal AI can now evaluate video, audio, and images together to unlock p…
Scientists revealed insights from ancient Herculaneum scrolls burned by Mount Vesuvius nearly 2,000 years ago, using AI to decode texts on ethics and philosophy. The breakthrough, led by researchers from the University o…
Google has launched Vids, an AI-powered video creation and editing tool integrated with Gemini, enabling users to generate storyboards, scripts, and video clips from prompts. The tool offers features like screen recordin…
Greece has deployed a constellation of four AI-enabled CubeSats, developed by OroraTech and launched in May 2026, to detect and track wildfires as small as 4 meters. The system, supported by the European Space Agency and…
Researchers introduced Mapping Networks, a novel approach that replaces high-dimensional weight spaces with compact latent vectors, achieving a 500x reduction in trainable parameters while maintaining comparable or bette…