Computer Vision news and analysis on Web Pulse: 1949 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
A multi-stage vision pipeline combining object detection, optical character recognition, and a large language model now enables automated processing of shopping receipts. The system first uses a custom-trained RF-DETR mo…
Meta has granted developers full access to the hardware in its Meta Ray-Ban Display smart glasses, leading to experimental apps that let users unlock their cars, control smart home devices, and play boxing games using he…
San Francisco-based Reactor, co-founded by former Apple Vision Pro technical leads Alberto Taiuti and Bryce Schmidtchen, has raised $59 million in Series A funding led by Lightspeed Venture Partners, with participation f…
UVeye, an Israeli vehicle-inspection company founded in 2014 by brothers Amir and Ohad Hever, is expanding its drive-thru computer-vision platform globally, operating over 1,000 systems and scanning more than 3.5 million…
Apple plans to introduce AI-powered upgrades to its Camera and Photos apps in iOS 27, including a dedicated Siri mode for visual analysis and new tools called "Reframe" and "Extend" for photo editing, according to a Bloo…
PR Eye Ltd has released Colour Memory, a Model Context Protocol (MCP) server that connects Claude AI to over 40 historical colour archives containing 15,000+ named colours. The tool enables hex matching, concept queries,…
Duke University researchers have developed Argus, a spherical robot with 20 telescoping legs and depth-sensing cameras that can move in any direction without a defined front, back, top, or bottom. The robot, named after …
Google is rolling out a new Gemini-powered automation feature for Google Home that allows users to trigger smart home routines based on visual cues detected by security cameras. The update, announced yesterday alongside …
Israeli defense-AI startup Airis Labs emerged from stealth and announced a $60 million total funding round, including a $31 million Series B led by PSG Equity. Founded in 2023, the Tel Aviv-based company developed a vide…
A developer building a time-lapse from hundreds of photos taken over several years found that image alignment—not capture or assembly—was the hardest challenge. Using OpenCV's ORB feature matching and RANSAC transformati…
A developer completed training a frontier font generation model that powers Mixfont, a tool capable of generating functional TTF font files from images or text prompts. The project, which took two months, aimed to fill a…
A software engineering student completed Photremium, a serverless image-processing platform, after reviving a forgotten repository using GitHub Copilot. The platform, now live at photremium.com, offers tools like AI back…
A developer building a garden visualizer for homeowners found that using example images as prompts produced more realistic results than text descriptions alone. By sending positive and negative reference images to GPT al…
Researchers have developed ICG, a framework that uses multimodal large language models and personalized preference alignment to generate cover images tailored to individual users. The system extracts semantic features fr…
The 10th Affective & Behavior Analysis in-the-Wild (ABAW) Workshop and Competition, held at CVPR 2026, introduced new challenges for multimodal human-centered AI, including emotional mimicry intensity estimation, ambival…
Researchers in Japan fine-tuned the LLaVA-1.5-7B vision-language model on up to 4,000 bridge damage images to automate damage assessment and repair priority scoring, addressing significant inter-rater variability in mand…
Researchers at the University of Cambridge have developed the first large-scale Ukrainian handwritten text generation system, creating a dataset of 126,177 images from 308 writers and retraining a diffusion-based model t…
Researchers have developed representation-conditioned diffusion models that generate synthetic training images by conditioning on learned representations from DINOv2, DINOv3, and CLIP, achieving a 10.76 percentage point …
A preliminary clinical validation of the Melanoscope AI mobile dermoscopy clinical decision support system, conducted across four "Melanoma Day" screening sessions in Orel, Russia from June 2025 to April 2026, found no f…
Researchers have developed ForestHG-Trace, a framework enabling traceable long-horizon ecological reasoning over large-scale forest scenes by representing multimodal NEON forest data as ecological hypergraphs. The system…