Computer Vision news and analysis on Web Pulse: 1697 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Roboflow released a tutorial on building an injection molding defect detection system for medical components using its RF-DETR model and Gemini 2.5 Pro. The system automatically detects cracks, breaks, and surface contam…
Apple plans to adopt OLED panels covering approximately 95% of the BT.2020 color gamut across future MacBook Pro, iPad Pro, and iMac lines, according to a TrendForce report. The upgrade will enable creative professionals…
The team behind MakeMyVisuals reduced AI background removal time from 18 seconds to near-instant by optimizing image preprocessing, caching, and UI responsiveness. Key improvements included adaptive resizing, offloading …
AR glasses competition intensifies as Rokid, Xreal, and RayNeo unveil new models with advanced features like 6DoF tracking, standalone platforms, and premium displays, signaling a faster-than-expected race to dominate th…
Qwen's new image model, Qwen-Image-2.0-RL, achieves improved benchmark scores through reinforcement learning, but the key insight lies in the training methodology. The team found that using classifier-free guidance durin…
TikTok creator Plonk is teaching viewers how to blind AI-powered surveillance cameras from Flock Safety, a network used by roughly one-third of U.S. law enforcement agencies. His satirical videos promote countermeasures …
The integration of artificial intelligence into judicial and medical decision-making is accelerating, with systems like MIT's Sybil model detecting lung cancer years before symptoms and forensic tools entering expert rep…
Firefly Aerospace will operate the NVIDIA Jetson edge AI platform in lunar orbit for the first time on its Blue Ghost Mission 2, launching in late 2026. The Ocula moon imaging service will use Jetson to process imagery a…
A developer built ClassifierAI, a Chrome extension that uses TensorFlow.js to detect AI-generated articles and images on Dev.to. The model was trained on 866 images using Google's Teachable Machine. The project was devel…
Developer Ayush has released Screenmind, an open-source, privacy-first alternative to Microsoft Recall that runs vision models locally on device. The tool captures and indexes screenshots, enabling search, chat with scre…
Flock Safety's surveillance cameras, including AI-powered license plate readers and audio-detection poles, are rapidly spreading across the US, logging every car and enabling law enforcement to search footage via natural…
XPENG unveiled its Physical-World Foundation Model roadmap and VLA 2.0 autonomous driving system at CVPR 2026, with the model already in mass production and capturing over 50% of assisted-driving mileage share in its fir…
Retail stores are evolving from static transaction endpoints into dynamic decision engines, driven by AI-informed shoppers who seek confidence and personalization. Brands like Sephora and Nike are redesigning spaces with…
China's Ministry of State Security warned that a popular augmented reality game may be providing geospatial data to train foreign military AI models. The ministry cited reports that an AI company linked to the game harve…
A developer argues that browser-based AI agents fail not because of model limitations but because they lack a structured runtime perception layer that captures live page state. The post introduces SiFR (Structured Interf…
A solo developer added AI background removal to Convertify, a free image converter, in one week using only Rust and no Python. The backend runs ONNX models natively via the ort crate, avoiding the need for a separate Pyt…
The Mano-P team released Mano-CUA 2.0, a 4B-parameter GUI agent that runs on a MacBook, and found that the primary bottleneck was not model size but insufficient Chinese GUI training data. After adding more Chinese inter…
Recent AI research introduces RL-driven agentic optimization using dense token-level supervision and progress advantage signals to stabilize training. PhysiFormer injects 3D geometric reasoning into diffusion transformer…
Researchers introduced NormAct, a benchmark evaluating whether multimodal large language models comply with hidden social norms during embodied planning. Tests on GPT-5.4, Claude Opus 4.7, and Gemini 3 Pro showed models …
Researchers have developed OverFlowLight, a real-time framework that uses multi-modal sensing from cameras and radars to detect and prevent queue overflow at urban intersections. Deployed across 43 intersections in three…