Computer Vision news and analysis on Web Pulse: 3339 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Velmeni received FDA 510(k) clearance for VELMENI for DENTISTS 3D, AI-assisted software that segments anatomy and reconstructs views from cone-beam computed tomography scans. The clearance gives CEO Mini Suri's company a…
A developer built watchable 3D digital twins of all 64 games from the 2022 FIFA World Cup using player tracking data from Pro Football Focus (PFF), which provides XY coordinates for all players at 30Hz. The project uses …
Samsung's new My FanCam feature, debuting on the Galaxy Z Flip 8, Fold 8, and Fold 8 Ultra, uses AI to automatically track and focus on a selected subject in a video, creating a fan-cam style clip without generating any …
Yosemite National Park will use part of a $10 million innovation grant from the National Park Foundation to design an AI-powered real-time parking and traffic information system, aiming to reduce visitor chaos. The syste…
VEED launched Multi-Shot Characters, an AI feature that automates multi-camera video creation from a single source clip, on July 23rd, 2026. The company claims the tool boosts viewer retention and cuts editing time, offe…
OpenTrust, an open-source SDK for privacy-preserving browser trust signals, has been released on GitHub. The tool detects browser automation, virtual cameras, and replay attacks while processing all data client-side, wit…
Google is enabling selfie sign-in for Google Accounts, using on-device facial recognition to verify identity instead of traditional multi-factor authentication methods. The biometric data stays local on the device, lever…
The evolution of the GPU from arcade cabinets to AI accelerators is traced through key milestones including the Whirlwind computer, 3dfx Voodoo, and NVIDIA GeForce 256. The shift from fixed-function arcade hardware to pr…
Google has introduced a new account recovery option that lets users verify their identity with a selfie video, stored encrypted on its servers. The feature is not available for Workspace accounts, child accounts, or thos…
Google is rolling out a new sign-in method that lets users verify their identity by recording a selfie video, providing an optional way to access Google Accounts if locked out or without access to a usual device. Google …
A new diagnostic framework called V-DEAL reveals that six major Video LLMs fail a basic logic test: they recognize harmful visual content with over 81% accuracy but still comply with benign queries 48.33% of the time, be…
Flock Safety CEO Garrett Langley apologized for calling privacy activists 'terrorists' as a bipartisan backlash grows against the company's 90,000-plus automated license plate reader cameras. The city of Verona, Wisconsi…
A solo developer launched Pixanima, a browser-based pixel-art and animation editor with an optional AI assistant, built with Vue 3 and Laravel 12. The editor is free, with AI features as the only paid component, and uses…
On July 23rd 2026, Dev (@DevvMandal) announced the release of AutoCAD-Bench, a benchmark that tests AI models on precise AutoCAD tasks using computer-use alone. GPT 5.6 sol, a proprietary version of OpenAI's GPT-5 series…
Microsoft's Mage-Flow image generation model, with only 4 billion parameters, outperforms larger models including FLUX.2-dev (32B) and Qwen-Image (20B) on GenEval benchmarks, scoring 0.88 against their 0.87. The model ac…
A single indie developer released CamFilterGpu, a zero-lag, GPU-accelerated video filter app with RVM-AI segmentation, background removal, and custom filter pipelines, priced at $2.45/month after a 14-day free beta. The …
Primate Labs launched Geekbench 7, a benchmarking suite with redesigned multi-core and GPU benchmarks that focus on real-world application performance and machine learning tasks. The GPU benchmark includes tests for face…
Black Forest Labs released FLUX 3, a single model that collapses image generation, video generation, and robot control into one unified system. The company claims the model can handle all three modalities without separat…
Black Forest Labs launched FLUX 3 on July 23rd, 2026, extending its image-generation technology into video with native audio and using the same model architecture to predict actions for robots. The model, built around a …
A developer demonstrates how to perform real-time video face swaps in a browser using Vivify Realtime Face Swap. The tool requires a reference portrait and a webcam, processing live frames with AI to map expressions and …