Computer Vision news and analysis on Web Pulse: 3399 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
A new AI research video explores how world models enable artificial intelligence to develop a first-person perspective, potentially advancing autonomous decision-making and machine consciousness studies.
BonSplit, an AI-powered receipt and expense app for couples and shared households, automatically recognizes individual line items from receipts and splits costs per item or evenly among members. The app, built as a mobil…
A developer used Anthropic's Claude Fable 5 model to create Inkwash, a WebGL2-based watercolor sketching app that simulates pen-and-brush nature journaling in a browser. The app uses a stack of floating-point textures an…
Newegg is offering a $400 discount on an iBUYPOWER gaming desktop featuring an RTX 5080 GPU and Intel Core Ultra 7 270K CPU, priced at a reduced rate for a limited time. The deal includes 32GB DDR5 RAM, a 2TB NVMe SSD, a…
A developer built a Medication Safety Assistant using a multimodal RAG pipeline with LLaVA, ChromaDB, and Ollama. The system identifies medicine from images, retrieves safety guidelines from a vector database, and genera…
Bol.ai launched a new API that extracts structured JSON data from Bill of Lading and other freight documents via a single endpoint. The API automatically classifies document types and returns key fields like carrier, ves…
NVIDIA released a bundle of physical AI agent skills at CVPR 2026, offering pre-packaged workflows for robots, self-driving cars, and visual inspection. The open-source tools aim to streamline research by providing simul…
AnimateDiff Turbo scored 5.3 in a head-to-head comparison against Luma Ray 3.2 Image to Video, which scored 14.4, demonstrating that Luma Ray 3.2 better executes prompt-specific scene generation from still images.
ScreenMind, an open-source AI memory tool, analyzes every screenshot locally using Gemma 4 on a 4GB GPU, offering 100% private, searchable screen history as a privacy-first alternative to Microsoft's Recall.
A generative artist created 25 different designs using only Perlin noise fields, a simple algorithm that simulates particle movement on a canvas. The project, completed over a weekend, demonstrates how self-imposed const…
The FIFA World Cup 2026 will deploy AI across officiating, player analytics, and operations, including an upgraded semi-automated offside system with 10cm detection and a generative AI assistant for all 48 teams. The tou…
VTubeMe launches a web app that converts a single selfie into a photorealistic VRM avatar for VTubing, requiring no 3D modeling skills. Users can create and preview avatars for free, then download VRM and GLB files for a…
FriendlyElec released the NanoPi M6V2, an updated single-board computer with Rockchip's RK3588S SoC, 8 GB LPDDR5, a 6 TOPS NPU, and HDMI 2.1 supporting 8K/60Hz output. Priced at $172, the board targets embedded vision an…
Israeli startups Airis and Conntour are driving a shift in global intelligence by developing AI tools that analyze vast video networks, as demonstrated by Israel's use of hacked traffic cameras and AI to track movements …
A new AI model called 'Count Anything' can count objects in images using text prompts, halving error rates compared to previous systems, though it still struggles with dense objects and ambiguous terms.
A developer built Fud AI, a free, open-source, privacy-first calorie tracker for iOS and Android. The app uses AI to estimate calories and macros from a photo of a meal, stores all data locally, and requires no account o…
Apple unveiled major AI updates at WWDC 2026, including a smarter Siri AI with conversational abilities, Visual Intelligence, and personal context. The new features will debut in iOS 27 this fall, requiring iPhone 16 or …
Researchers trained a collaborative robot to read human emotions using a vision language model that considers contextual factors beyond facial expressions. In experiments with 40 volunteers, the VLM outperformed conventi…
Researchers developed DVD-JEPA, a Joint-Embedding Predictive Architecture world model that learns the physics of a bouncing DVD logo from pixels without explicit coordinates. The model predicts future frames in a latent …
Apple introduced new AI photo editing tools in iOS 27, including an improved Clean Up feature, Extend for expanding photo edges, and Spatial Reframing for recomposing images. The tools mostly work well but raise question…