Computer Vision news and analysis on Web Pulse: 4325 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Palona AI, officially incorporated as Proactive AI Lab Inc., has raised $20 million in Series A funding led by Ardenwood Ventures to expand its AI automation platform for brick-and-mortar businesses. The startup's multim…
OpenAI's GPT 5.6 Sol model delivers a major leap in OCR accuracy and spatial awareness, making it the most usable vision model the company has released for real-world applications like browser automation and visual QA, a…
Sainsbury's has suspended its use of live facial recognition technology at its East Dulwich branch after customer Matt Arnold, 46, was wrongly identified as a shoplifter and escorted out on August 6. The company apologiz…
Microsoft Store now hosts an AI-powered image management app that lets users find images by visual content, rename them automatically, and sort them easily, according to a Show HN post on Hacker News. The app, available …
McAfee research found that free AI vision models can geolocate travel photos with up to 91% accuracy, enabling scammers to craft personalized phishing scams. In tests with over 20,000 images, one model achieved 87% accur…
Google Research scientists Cassie Zhou and Ahmed Metwally demonstrated that PhotoScan, a deep learning framework estimating body composition from smartphone photos, can predict insulin resistance with accuracy comparable…
Gujarat Police has launched the Gujarat Police Innovation Challenge 2026, India's largest hackathon focused on CCTV integration and AI-based video analytics, to unify more than 80,000 police and government CCTV cameras a…
Sainsbury's has suspended live facial recognition at its East Dulwich store after customer Matt Arnold, 46, was wrongly accused of shoplifting when the technology flagged him during a self-service checkout. The supermark…
Sainsbury's paused its AI-powered security cameras after a shopper was falsely flagged as stealing, highlighting the risk of high-recall, low-precision vision systems in retail. The article advises implementing confidenc…
A developer built Nose ID, a biometric system that identifies dogs by their unique nose-prints using a pretrained MobileNetV2 as a feature extractor and cosine similarity for matching. The system also uses Google Gemini …
Sainsbury's has suspended its use of live facial recognition technology at its East Dulwich branch after Matt Arnold, 46, was wrongly challenged as a shoplifter and asked to leave on 6 August. The supermarket apologized,…
A new AI tool is helping doctors locate sperm in men with severe infertility where traditional methods failed, according to a report from the Seattle Times. The technology, developed by researchers, uses machine learning…
Researchers propose a fast implicit neural light field representation that decomposes a 4D light field into horizontal disparity, spatial texture, and vertical disparity planes, each represented by multi-resolution low-r…
Researchers introduced a visual-interactive system that explains deep learning predictions for computer network traffic classification using aggregated class activation maps, addressing the challenge of diverging pattern…
A new arXiv study (2608.13729v1) finds that synthetic image generation from diffusion-based models fails to consistently improve downstream classifier performance over non-generative augmentation in specialized, data-sca…
Researchers introduced RGBX-Next, a unified generative framework for forward and inverse rendering that uses diffusion transformer (DiT) models to estimate G-buffers from images, videos, and streams, and to render realis…
Researchers propose CoANeRV, a coordinate-aware token-space framework for amortized video representation that forms compact video tokens in one feed-forward pass and uses a shared coordinate-conditioned decoder, avoiding…
A controlled eye-tracking study (N=59) reveals that whether humans notice AI image edits and whether they judge them as fake are dissociable stages: edit area drives attention capture (p<0.001) while semantic plausibilit…
A new diagnostic framework called ChartProbe, introduced in an arXiv paper (arXiv:2608.13766v1), shows that vision-language models (VLMs) can improve complex visual reasoning by training on simpler skills—perception, gro…
Researchers introduced CMCNet, a model that aligns ultrasound image embeddings with textual TI-RADS representations for fine-grained thyroid classification, achieving superior performance over InfoNCE, center loss, multi…