Computer Vision news and analysis on Web Pulse: 3337 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Andre Luecht of Zebra Technologies explains how the company's "physical AI" approach empowers frontline workers with real-time feedback to transform warehouse and logistics operations. The technology provides granular vi…
Delhi Police have deployed AI-aided facial recognition surveillance vans at the Jantar Mantar student protest, scanning demonstrators against criminal databases via live video feeds, prompting a legal challenge in the De…
A developer built a 100% client-side background removal tool using Transformers.js and ONNX Runtime Web, avoiding server uploads. The project overcame an AGPL licensing issue, memory crashes from transformer models, and …
A developer built a stateful image-editing skill for Google Antigravity CLI by wrapping Google's gemini-3.1-flash-lite-image model (NB2Lite) in a FastMCP server. The skill leverages Gemini's Interactions API to allow ite…
A roundup of top AI papers on Hugging Face highlights trends in recursive self-improving research agents, interpretability of diffusion transformers, fast generative world models, large-scale post-training on Ascend hard…
Meta launched Facebook Verified, a free badge that uses facial recognition to confirm human users are real, aiming to combat AI-generated fake profiles and scams. The feature, requiring users over 18 in good standing, wi…
Meta and Snapchat are facing a privacy backlash over their AI-powered smart glasses, with critics drawing parallels to the failed Google Glass. Meta updated its glasses after reports that owners paid hackers to disable t…
Nvidia unveiled Synthetic Video Detector (SVD) at SIGGRAPH 2026, an AI-powered tool that detects AI-generated videos with up to 92% accuracy on uncompressed 1080p video, processing frames in as little as 22 milliseconds …
Black Forest Labs and Mimic Robotics have connected an early version of FLUX 3 to industrial robots, creating FLUX-mimic, which is being tested and deployed with Audi on manipulation jobs involving components, seals, cab…
A free, open-source tool called Draw Your Font lets users turn a photo of their handwritten alphabet into an installable TTF, WOFF, or WOFF2 font entirely on their local machine, with no uploads or credits required. The …
Developer Danilo Znamerovszkij built and open-sourced a pipeline that turns a single photo of handwriting into an installable TTF font. The tool runs locally with no system dependencies, using npm libraries for image pro…
Google launched selfie video sign-in on 23 July 2026, allowing users to recover their Google Account by recording a short video of their face instead of using a password or code. The enrolled selfie is stored on Google's…
Researchers Timo Bolkart, Daoye Wang, and Prashanth Chandran introduced SHELLS, a method for topologically consistent multi-view 3D head reconstruction using a DinoV2 backbone with LoRA adaptation and an XCiT-based trans…
NVIDIA Research's Efficient AI Team and Singapore Lab introduced SANA-Video 2.0, a hybrid video diffusion transformer at 5B and 14B scales that generates 720p video on a single H100 GPU. The model achieves a VBench score…
Baidu's Unlimited-OCR, a 3B-parameter vision-language model, enables end-to-end OCR for high-resolution images and multi-page PDFs without separate layout analysis, according to a tutorial published on Hugging Face. The …
Ethan Hu's Meshy, an AI-powered 3D creation startup spun out of MIT research, raised $400 million in funding, valuing the company at $1.5 billion. The company aims to reduce the time and expertise needed to build 3D mode…
An artist used neural networks to generate emoji-like images of Mark Zuckerberg's face, combining CNNMRF, Deep-Image-Analogy, and neural-style to create stickers for Telegram.
Flux 3, an advanced AI visual intelligence model, enables users to generate realistic images, videos, and creative content through multimodal workflows and simple prompts. The platform offers a premium unlimited plan wit…
Researchers have introduced RealVDeblur, an efficient generative framework for real-world video deblurring that uses a physically grounded blur synthesis pipeline from 3D Gaussian Splatting assets and high-frame-rate vid…
Researchers propose Uncertainty-Guided Cascade Forward Refinement (U-CFR), a new inference-time framework for interactive image segmentation that enables models to autonomously self-correct after each user interaction. U…