Computer Vision news and analysis on Web Pulse: 3335 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Astrallist launches as a smart assistant for home cooks, meal planners, and creators, featuring AI-powered fridge scanning, real-time pantry management, budget tracking, and 1-click Amazon ordering. The app also includes…
A new technique called 'Decoy Fonts' bypasses Claude's vision system by embedding thin, high-contrast decoy characters that the AI's OCR prioritizes over actual letterforms, causing the model to hallucinate the decoy tex…
A developer built a production-ready automated nutrition logging system combining Meta's Segment Anything Model (SAM) with GPT-4o Vision, using FastAPI and Pydantic to transform food photos into structured JSON reports o…
A new forensic tool called Saga enables users to identify which generative AI video model produced a given clip, such as Sora, Kling, or Runway Gen-3, by detecting invisible architectural artifacts left by the diffusion …
A Rust developer introduced ez-ffmpeg 0.15's FrameExtractor, which extracts video frames in-process without shelling out to ffmpeg or writing a manual decode loop. The tool provides a one-call API that returns tightly pa…
Mixfont released Ghost Font in July 2026, an animated dot pattern that encodes text in motion, making it unreadable in a paused frame. Creator Eric Lu and Mixfont reported that models labeled Claude Fable and GPT Sol 5.6…
A developer built Pixel Isolate, an in-browser AI background remover that runs entirely via WebAssembly and C++ OpenCV bindings, eliminating cloud GPU latency and privacy concerns. The tool uses HSV color keying and is b…
A 77-year-old Republican man, Carl Gunn, staged a solo protest against Flock cameras in St. Petersburg, Florida, by blocking a camera's view with a sign reading "DOWN WITH FLOCK CAMERAS" to protest what he calls an invas…
Ghost Font, marketed as a font AI cannot read, was decoded by Claude Code in two minutes. The AI wrote its own decoder from scratch and extracted the hidden message "RECOVER THIS MESSAGE" from a video clip of the font, w…
A developer fixed a critical gap in their open-source video tool crv after a user reported that extracted frames lacked timestamps, making it impossible for an LLM to know when a slide appeared. The fix uses ffmpeg's sho…
A new website offers a suite of browser-based AI tools for image background removal, upscaling, text extraction, object segmentation, audio transcription, text-to-speech, voice cloning, and video clipping, all running lo…
Mediavox released a document analysis API that extracts structured data from invoices, contracts, and receipts in a single call, supporting Spanish and Portuguese. The multimodal AI endpoint handles scanned PDFs, Word fi…
The Massachusetts Institute of Technology is spending over $3 million to install more than 500 AI-integrated surveillance cameras across its campus, capable of real-time facial recognition and object classification, acco…
Microsoft has open-sourced its ML Video Codec (MLVC), a machine learning-based video compression technology designed to improve efficiency and quality. The release on GitHub includes the codec's source code, models, and …
Primate Labs released Geekbench 7, a major overhaul of the cross-platform benchmark suite with updated CPU and GPU tests, including NVIDIA CUDA support. The CPU benchmark now includes a media group and uses a Lenovo Legi…
Meshy AI's Image-to-3D feature lets users upload a product photo or sketch and receive a textured 3D mesh in minutes, replacing hours of marketplace searching. The workflow involves uploading a high-res image, generating…
A developer compiled the top 10 most upvoted papers on Hugging Face, covering deep research agents, post-training large models on Ascend SuperPOD, embodied visual tracking, K-12 knowledge graphs, self-distillation for vi…
California Governor Gavin Newsom announced July 21 that the state's ALERTCalifornia network of 1,260 mountaintop cameras, 915 of which run AI smoke detection, has flagged more than 900 fires on state lands before any 911…
Researchers have introduced SAGA (Source Attribution of Generative AI videos), the first comprehensive framework for identifying the specific generative model used to create AI-generated videos, achieving state-of-the-ar…
A developer built hwatu, a browser designed for coding agents to verify UI changes via pixel diffing, achieving a 97.49% match in about 87 ms per verification loop. The tool runs headlessly on Linux using WebKitGTK, supp…