Computer Vision news and analysis on Web Pulse: 1847 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Vision-enabled large language models (VE-LLMs) were evaluated in an exploratory study for their ability to interpret electrocardiogram (ECG) images. The performance assessment focused on the models' image interpretation …
Ideogram 4 outperformed image generators from OpenAI, Google, and Microsoft in a four-part stress test evaluating capabilities beyond basic text rendering. The test measured performance on challenges designed to assess d…
SnapCal, a new web-based food scanner, allows users to photograph meals and receive editable nutrition estimates including calories, macros, and a food quality score. The tool also features a Macro Coach that calculates …
Ideogram released version 4.0 of its text-to-image model as an open-weight model featuring native 2K resolution, bounding box control, and improved text rendering. The model ranks first among all open models on the Desig…
Microsoft on Tuesday released two new text-to-image AI models, MAI-Image-2.5 and MAI-Image-2.5 Flash, which outperformed Google's Nano Banana 2 in image editing benchmarks on the Arena AI leaderboard. The models, part of…
Amazon-owned smart doorbell company Ring faces a class-action lawsuit alleging it illegally collected and stored facial recognition data from visitors without their consent. The lawsuit claims Ring's cameras captured bio…
Nvidia announced that its Cosmos 3 model for physical AI ranks first on seven leaderboards for world generation, robot action policy, and industrial vision understanding. The company described Cosmos 3 as an "open omni m…
Dr. Fei-Fei Li and the World Labs team published a functional taxonomy of world models, distinguishing between renderers, simulators, planners, and the reinforcement learning loop that connects them. The taxonomy clarifi…
Apple's incoming CEO John Ternus has authorized a major overhaul of the company's Vision products roadmap, scaling back plans from seven head-mounted wearables to just two active products, according to analyst Ming-Chi K…
Amazon's updated search bar will generate AI-created images of clothing and home goods based on user descriptions, though the products depicted do not exist and cannot be purchased. The feature, rolling out on Android an…
TeamViewer integrated Microsoft's Windows AI Video Super Resolution (VSR) into its Assist AR remote-assistance product for frontline workers, announced via a press release distributed by PR Newswire. The on-device AI cap…
NVIDIA Research presented three papers at the CVPR conference addressing challenges in physical AI, including a foundation model for robotic grasping, a faster reasoning model for autonomous vehicles, and a scalable trai…
At CVPR, NVIDIA announced new physical AI agent skills designed to accelerate research and development for autonomous vehicles, robotics, and vision AI systems. The company introduced NVIDIA Cosmos 3, an open frontier mo…
Nvidia released Cosmos 3, an open-source omni-model for physical AI that handles vision reasoning and multimodal generation, with two variants available under the OpenMDW 1.1 license. In tests on fixed-camera footage fro…
Blackmagic Design released DaVinci Resolve 21, adding a dedicated Photo page for still image color grading and introducing AI tools for facial de-aging, blemish removal, and content-based media search. The update also in…
Google reported that search interest in "vintage" and "how to thrift" hit all-time highs in 2026, prompting the company to release five new Google Search tools to assist thrift shoppers. The features include AI Mode for …
Dharma-AI released DharmaOCR, a structured OCR model, and published a paper demonstrating that Direct Preference Optimization (DPO) reduced text degeneration rates by an average of 59.4% across all tested vision-language…
NVIDIA released Cosmos 3, a family of open-source omnimodal world models that unify physical reasoning, world generation, and action generation within a single Mixture-of-Transformers architecture. The models, available …
OpenAI is leading a new funding round for Opal Electronics, a San Francisco startup known for its high-end webcams, as part of a broader push into hardware development. The investment will help Opal expand beyond cameras…
Acer announced two new wearable devices on May 29: the AR Vision GR0 tethered augmented-reality headset and the GI0 AI smart glasses, the latter integrating Google Gemini for voice and image features. The AR Vision GR0 f…