Computer Vision news and analysis on Web Pulse: 3307 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
AMD presented a lightweight attention-based indirect illumination model at SIGGRAPH 2026 that augments screen-space G-buffers with reflective shadow maps to capture off-screen light, improving indirect shadow quality. Th…
Flock Safety's communications team has stopped responding to media inquiries, telling reporters in an email that it is 'taking a break' and 'touching grass,' following a Washington Post investigation that found at least …
Google has introduced an AI model that estimates body fat from a single selfie, with a mean absolute error of about 3.8% across BMI 18–35, using a MobileNetV3-small backbone with 1.2 million parameters quantized to INT8 …
ITW Universe will produce the India vs Afghanistan T20I series in New Delhi from September 13-17 using FIFA World Cup host-broadcast standards, including AI-stabilized POV cameras, volumetric free-viewpoint technology, S…
Blind Egyptian entrepreneur Mark Morad has launched an AI-assisted app that narrates the visual world for people with vision loss, supporting Arabic and English and processing some tasks on-device. The app, developed in …
CAL FIRE tested Seneca's autonomous firefighting drones on July 15, with five aircraft participating in a field demonstration, according to Deputy Chief Jack Worden. Seneca's system uses AI and computer vision to locate …
Researchers at Google developed PhotoScan, a deep learning method that estimates body composition from smartphone selfies, achieving a mean absolute error of 2.15% for total body fat percentage against DXA in a validatio…
Anita Klesch and A. Gary Klesch, founders of The Klesch Collection, are funding a two-year postdoctoral fellowship in history of art and technology at Birkbeck, University of London, focused on artificial intelligence. T…
Flock Safety, a surveillance company valued at $8.4 billion, has installed 120,000 AI-powered license plate cameras across every US state except Alaska, used by 7,000 law enforcement agencies (40% of US police department…
Talecut, an AI-powered video editing tool, converts movies and TV episodes into vertical micro-episodes for platforms like TikTok, Reels, and Shorts, using AI scene analysis to track speakers and generate captions. The t…
ImgIng, a browser-based image tool from Datadance, processes images locally on-device for formats including PNG-8, WebP, JPG, and AVIF, with server fallback only for formats the browser cannot handle, such as HEIC write.…
Researchers introduced LumiTokens, a framework that performs 3D relighting by directly transforming latent scene tokens, avoiding explicit 3D representations and physics-based decomposition. The method, detailed in arXiv…
Researchers introduced COSTA, a cluster-centric paradigm for annotation-free open-set semantic segmentation of aerial point clouds under domain shifts, achieving up to 70.09% mIoU when adapting from the DALES source doma…
Researchers introduced SparsePR, a training-free sparse attention method that combines Response-Coupled Partitioning with Probe-Fitted Residual Reconstruction to accelerate video transformers. Across four video generatio…
A new arXiv paper (2608.18339v1) proposes a test-time adaptation method for vision-language models (VLMs) that unifies inference and adaptation objectives via optimal transport, improving accuracy by up to 7% over state-…
Researchers propose DyG$^2$T, a dynamics modeling framework that uses a 3D Gaussian Temporal-Spatial Particle Graph Transformer to predict object motion trajectories from limited visual observations, achieving accurate d…
A new method called Role-Conditioned Sub-Token Routing (RoleSub) compresses vision-language-action (VLA) model representations, outperforming token-only pruning in 33 of 36 settings on the LIBERO suites when tested with …
Bongard problems, visual puzzles that challenge AI to identify latent properties distinguishing two sets of images, remain a benchmark for visual reasoning, as highlighted in a new essay revisiting Douglas Hofstadter's 1…
Meta's smart glasses, sold by Oakley and Ray-Ban, include a hidden facial recognition feature called NameTag that can identify unsuspecting individuals, raising privacy concerns. The feature was removed from the app afte…
A developer built an AI Pharmacist Assistant that uses OCR to scan drug labels and retrieval-augmented generation (RAG) to detect drug-drug interactions. The system extracts drug names from images, cross-references a SQL…