Computer Vision news and analysis on Web Pulse: 3409 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Humanoid robots walked a runway alongside human models in coordinated outfits at the "Physical AI Fashion Show" in Seoul's Gangdong District. Galaxy Corporation organized the event, with its chief executive stating robot…
Shift, an AI training startup, is offering limited-time free home cleanings in New York City where cleaners wear head-mounted cameras to record first-person footage. The recordings capture tasks like scrubbing bathrooms,…
Processing a single image through a vision-language model can cost anywhere from a fraction of a cent to several cents depending on the provider and image size, with GPT-5.5, Claude Opus 4.7, and Gemini 3.1 Pro each usin…
A developer released textsnap, a command-line tool that performs OCR on images, screenshots, PDFs, and webpages entirely on a local CPU without requiring a GPU or cloud connection. The tool uses a quantized 0.9B vision-l…
A software developer built a fully automated document management system using Paperless-NGX that processes over 900 documents for a family of four across multiple languages. The system ingests physical papers via a ScanS…
Google Cloud has launched Nano Banana 2 and Nano Banana Pro, two image generation and editing models now generally available through the Gemini Enterprise Agent Platform. The models, which support 1K and 2K image output …
DeepFace Cloud launched a managed API for face recognition, offering face verification, embedding generation, and vector comparison without requiring users to manage GPU infrastructure. The service provides anonymous sig…
Brooklyn engineer Brian Streem, CEO of Vermeer, has developed a Visual Positioning System (VPS) that uses onboard cameras and edge computing to navigate drones without relying on vulnerable GPS signals. The technology, a…
Shift, an AI training startup, announced Thursday it is offering free home cleanings in New York City in exchange for allowing cleaners to record first-person footage with head-mounted cameras. The company will use the f…
The UK Home Office has awarded a £322,000 contract to Akhter Computers Ltd to develop and test an AI facial-recognition tool that estimates the ages of asylum seekers at the border, with a planned rollout by mid-2027. Th…
The UK Home Office will deploy an AI age estimation tool at the border starting next year to identify adult migrants falsely claiming to be children, awarding a £322,000 contract to Akhter Computers Ltd for development a…
MoodStream, an open-source real-time emotion recognition module, has been released to enable machines to detect human facial expressions during interactions. The system processes video frames through a pipeline that capt…
Utilora has released a browser-based video captioning tool that runs entirely on the user's device using Whisper AI, eliminating the need to upload files to external servers. The tool downloads a 74MB model on first use,…
Researchers have developed RORA-VLM, a robust retrieval-augmented framework for vision-language models that enables accurate question-answering using external knowledge even when retrieved information contains noise. The…
Researchers have introduced Embodied3DBench, a benchmark designed to evaluate low-level spatial intelligence in Vision Language Models (VLMs) within embodied 3D environments. The benchmark includes over 21,000 question-a…
Researchers have developed GeRaF, the first neural implicit learning method for reconstructing 3D geometry from radio frequency signals, enabling see-through-occlusion sensing without relying on RGB or LiDAR. The system …
Researchers have developed a self-supervised deep learning framework that enhances Sentinel-1 Stripmap imagery by exploiting azimuth subaperture decomposition, generating paired training data without external sensors or …
Researchers introduced Spectral Guidance, a framework that controls diffusion models by exploiting the geometric structure of noise corruption to identify a small set of informative features. The method projects guidance…
A team of researchers has developed a training-free multi-signal segmentation pipeline for the CVPR 2026 UG2+ Challenge's Dynamic Object Segmentation in Turbulence (DOST) track. The system combines RAFT motion estimation…
Researchers have developed Deep Visual Coding, a frequency-domain representation inspired by 1990s image codes that creates psychovisual-style abstractions for deep learning. The approach enables the first psychovisual-b…