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 introduce Diff-ID, a diffusion-based framework that enforces identity consistency in facial image generation while delivering photorealistic quality, using a custom 210K image dataset and integrating ArcFace …
Researchers propose DisasterTD, a disaster toponym disambiguation framework that integrates multimodal large language models (MLLMs) with cross-view geolocalization to improve geolocalization accuracy of social media ima…
DDH, a Korean dental AI startup, has developed Pano, an AI tool that analyzes panoramic X-rays and uses color coding to highlight potential dental issues, aiming to bridge the trust gap between patients and dentists. Fou…
Comma.ai's openpilot driver-assistance system has been plagued by bugs that caused dangerous driving behaviors, including drifting right, detecting false lanelines, and cutting turns, all traced to flaws in sensor calibr…
Green Party councillor Hau-Yu Tam, cabinet member for sanctuary and healing at Lewisham Council, shared a map on social media showing the precise location of a Metropolitan Police Live Facial Recognition van in Deptford,…
Gemini Omni Flash defeated Bernini-R Edit Video by a score of 33.8 to 27.8 in a head-to-head video generation test, winning with 94% confidence. The test, conducted by an unnamed evaluator using gpt-5.4, found Gemini sup…
Google has begun rolling out a new account sign-in and recovery method that uses a selfie video, announced in a July 23 blog post. Users record a short video performing head movements, which is encrypted and compared wit…
Jialiang Wang, a researcher in Artificial Intelligence and Machine Learning, Computer Vision, and Generative AI, has published his work on Google Scholar, with his profile accessible at https://scholar.google.com/citatio…
UC Riverside highlighted SAGA, a research framework for attributing synthetic videos to their source generator, in a July 24 announcement. The framework classifies synthetic videos at five levels, from real-versus-fake t…
Starbucks scrapped an AI inventory tool built by startup NomadGo across all 11,300 company-operated North American stores by 18 May, blindsiding the 30-person vendor and leading to layoffs. The tool, called Automated Cou…
Queue, a Silicon Valley startup, has developed what it says is the world's first fully autonomous robotic pharmacy that can identify, verify and dispense prescriptions in about 60 seconds without human handling. The syst…
The U.S. experienced an estimated 522,500 structure fires and nearly $15 billion in direct property damage in 2022, according to the NFPA's 'Fire Loss in the United States During 2022' by Shelby Hall. Fire watch provider…
An unnamed developer reports that Claude Code, an LLM agent, can hallucinate by describing a cat photo as a bridge when the file is renamed to 'golden_gate_bridge.jpg', revealing a tendency to prioritize helpfulness over…
Apple plans to release an all-new smart home hub between October and early next year, according to Bloomberg's Mark Gurman. The device will combine a HomePod-like speaker with a 7-inch display, run a new operating system…
The Allen Institute for AI (Ai2) launched the OlmoEarth Platform, infrastructure for geospatial inference at planetary scale, enabling continent-scale analysis in roughly a day at fractions of a penny per square kilomete…
A developer built a fully client-side ID photo maker using a three-tier face detection chain (MediaPipe, Browser FaceDetector, BlazeFace) with anthropometric head measurement and background removal. The solution runs ent…
Mirage launched Avatar X on Tuesday, an AI video model that the New York company says can build a speaking digital twin from 10 seconds of recorded footage. The model powers AI Twin inside Captions, Mirage's video creati…
West Virginia's Freedom Caucus, led by Delegate Chris Anders, is seeking to ban AI-powered Flock surveillance cameras statewide, arguing the technology violates the Fourth Amendment. The caucus plans to reintroduce the F…
Conflow Power Group (CPG) has installed the first UK iLamps in a Warwickshire hospital car park, which are solar-powered smart lamp-posts that can double as AI data centres with facial and number plate recognition. CPG c…
ZCode, a developer tool, misclassifies custom OpenAI-compatible vision models as text-only, blocking screenshot input. A developer provided a Python script to patch the configuration file by adding image support to the m…