Computer Vision news and analysis on Web Pulse: 3307 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Kfarr's Sharp-Ml model, based on Apple's SHARP, converts a single photograph into 3D Gaussian splats in under a second via a neural network feedforward pass. The model achieves state-of-the-art results, reducing perceptu…
FoundationVision has released Infinity, a bitwise visual autoregressive text-to-image model that generates 1024×1024 photorealistic images in 0.8 seconds, outperforming diffusion models like SD3-Medium and SDXL on key be…
A developer built an AI-powered grocery assistant using a Raspberry Pi, integrating computer vision and natural language processing to identify items and suggest recipes. The project demonstrates how low-cost hardware ca…
Researchers from Microsoft and academic institutions introduced Internalized Visual Thinking (IVT), a post-training framework that enables multimodal large language models to reason about videos without generating interm…
Flock Safety and other surveillance technology companies are shifting from centralized data storage to decentralized, on-device processing to address privacy concerns, according to an industry analysis. The new approach …
Apple's M4 Pro with 64GB RAM can run vision models like Llama 3.2 Vision, Moondream2, and Qwen2-VL locally with low latency, according to a developer guide. The guide recommends using Ollama to manage models and suggests…
An engineer built an AI-powered message router for WhatsApp-style conversations during the HackerRank Orchestrate 24-hour hackathon. The system classifies incoming messages as notify, digest, or mute, using context such …
A Gizmodo report finds that AI data centers and Flock Safety's automated license plate readers are facing growing public opposition across the United States over privacy, transparency, and local control. The ACLU has doc…
Flock Safety's license-plate recognition cameras have become a flashpoint in the 2026 midterm campaign, with critics linking the surveillance technology to broader anti-AI sentiment and fueling a political backlash that …
Apple's upcoming AirPods Pro 4 with Visual Intelligence, as revealed by leaked code in macOS Tahoe 26.7, will capture low-resolution still images (640x640 in active mode, 320x320 in passive mode) rather than video, accor…
Axios reports that Flock cameras, the AI-powered license plate readers, have become a major target in the 2026 midterm campaigns, with members of Congress and candidates leveraging grassroots anger over the surveillance …
Flock License Plate Readers, an AI-powered automated license plate reader system by Flock Safety, operate in over 5,000 communities across 49 U.S. states and perform over 20 billion vehicle scans monthly, according to co…
DeepDoctection 1.2.x enables an end-to-end document intelligence pipeline combining layout detection, table structure recognition, OCR, reading-order reconstruction, annotation linking, and structured export, as demonstr…
Meta's AI glasses, which integrate an always-on AI agent for real-time visual processing, are making it nearly impossible for bystanders to avoid being recorded, according to a new analysis. The device's continuous frame…
A developer building Roomood, a virtual staging tool for real estate, argues that the key to successful AI virtual staging is treating it as a constraint problem rather than a creativity problem. The system must preserve…
At the 2018 International Symposium on Computer Architecture, John Hennessy and David Patterson delivered their Turing Lecture 'A New Golden Age for Computer Architecture,' noting that single-threaded CPU performance gro…
China's AI deployment diverges from the West by embedding artificial intelligence into physical infrastructure, with smart cities, automated logistics, and computer vision in retail as standard practice, according to an …
The Neural Image Format (NIF), a deep-learning-based image codec developed by Gabriel Philippus, achieves up to 26.4% lower LPIPS distortion than JPEG at 0.80 bpp on the Kodak24 dataset, with a decode latency of ~202 ms …
ImageSage, a private, local AI photo gallery app for Windows 11, is now available free from the Microsoft Store. The app uses on-device AI to let users search photos by visual content, text within images via OCR, or file…
Independent researcher Samuel A. in Germany is seeking arXiv cs.CV endorsement for AcroMELD, a 39.4M parameter detector that recovers interactive form fields in flat PDFs, with weights available on Hugging Face Hub and i…