Computer Vision news and analysis on Web Pulse: 1773 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers introduced RegimeVGGT, a training-free accelerator for Visual Geometry Grounded Transformer (VGGT) that achieves a 6.7x speedup over VGGT* at matched reconstruction quality by applying layer-wise U-shaped com…
Elva, a personal AI video agent, edits, directs, and shapes user memories by guiding framing, timing, and capture, then automatically generating polished, shareable videos without manual editing tools.
Collart AI built a video watermark remover that addresses the challenge of temporal consistency across frames. The tool optimizes for short clips, prioritizes preview and review workflows, and focuses on legitimate asset…
A developer building WearEdge Pro, a wearable industrial edge AI runtime, tested five small multimodal models on a Jetson device to find the best baseline for an industrial edge agent. Gemma 4 E2B emerged as the best pro…
David Holz's Midjourney announced Midjourney Medical, a full-body ultrasound scanner that uses sound waves to create 3D body maps in under 60 seconds. The self-funded AI lab is moving from image generation into medical h…
A new project demonstrates streaming AI-annotated video from Seeed Studio's reCamera edge device to any browser via WebRTC, using on-device YOLO11n object detection, RTSP video output, and MQTT for detection data. A ligh…
British defense company OpenWorks Engineering has been selected to supply its Vision Guard intelligent optics system for evaluation under the Australian Defence Force's Project Land 156, a AU$1.3 billion counter-drone mo…
A developer built the AI Newscaster, a zero-dependency desktop device using an Arduino UNO Q that uses edge computer vision to verify a user's presence and then fetches a personalized news briefing via RSS feeds, bypassi…
Artificial intelligence is transforming cardiac CT by enabling real-time coronary analysis, automated TAVI planning, and detection of coronary inflammation invisible to the human eye. A panel discussion with Dr. Ronak Ra…
A developer built a high-precision food nutrition AI engine by combining Meta's Segment Anything Model (SAM) for pixel-perfect object isolation and GPT-4o Vision for multi-modal reasoning and volume estimation. The syste…
Recraft V4.1, Midjourney, and GPT Image 2 compete for professional design use, with Recraft offering native SVG output and brand consistency, Midjourney leading in photorealism, and GPT Image 2 providing strong text rend…
KerasFormers, an open-source library built entirely in Keras 3, launches with over 100 transformer models spanning vision, language, multimodal, and speech, supporting seamless execution on TensorFlow, JAX, and PyTorch. …
Defense contractor Leonardo is marketing SignalTrace, a technology that pairs automatic license plate readers with sensors to capture unique identifiers from phones, wearables, and other devices, enabling law enforcement…
In a head-to-head test of two video-generation models, Happy Horse defeated Bernini-R Edit Video with a score of 17.6 to 14.4, demonstrating superior precision in following detailed prompts. Happy Horse excelled in tasks…
Snap unveiled its first consumer augmented reality glasses, SPECS, at $2,195, alongside a revamped Lens Studio with AI-powered agentic tooling integrated into Claude Code, Codex, and Cursor. The developer tools allow bui…
Simonetta Vespucci, the model for Botticelli's The Birth of Venus, likely died at age 23 from a bleeding pituitary tumor, possibly triggered by dancing or assault, according to a new study in Endocrinology, Diabetes & Me…
A study by RMIT University surveying over 16,000 adults across ten countries found that 14.5% have experienced sextortion, with 4.8% admitting to perpetrating it. The Australian eSafety Commissioner has launched an aware…
GPT Image 2 API defeated Bagel 26.9 to 14.3 in a head-to-head image generation test, consistently following prompts and preserving scene logic while Bagel produced occasional appealing fragments but failed to honor the b…
Manako Labs launched a vision AI agent platform that converts standard enterprise cameras into real-time monitoring systems using Bittensor's decentralized Score Subnet 44. The platform processes video at the edge and se…
Qualcomm announced the Snapdragon Reality Elite XR platform at Augmented World Expo, offering up to 48 TOPS of on-device AI performance and significant GPU, CPU, and NPU improvements over its predecessor. The chipset wil…