Computer Vision news and analysis on Web Pulse: 3349 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Apple released the macOS 27 Golden Gate public beta this week, featuring Siri AI, Liquid Glass transparency controls, and Visual Intelligence for screen-based queries. Users can test the update on secondary devices with …
Meta's SAM 3 model natively performs promptable concept segmentation, accepting a plain-language prompt such as "helmet" or "safety vest" and returning pixel-level masks for every matching object in a single pass without…
Google is marking the 25th anniversary of Google Images by adding AI image generation powered by its Nano Banana model, allowing users to create images from plain-English prompts when a desired image does not exist on th…
Google is rolling out the biggest visual search update in years, featuring a redesigned, personalized Google Images homepage and built-in AI image generation in AI Overviews using its new Nano Banana model. The refresh, …
NVIDIA announced that combining its open physical AI foundation model Cosmos 3 with TAO agent skills enables post-training of the Cosmos 3 Nano model for video question answering in a single day, boosting exact-match acc…
A solo student developer launched Souva, a free app that turns photos of a user's fridge and pantry into recipes using AI, with photo scans costing about $0.002 each and capped at 3 per day, and AI generations capped at …
Researchers have introduced a novel approach using normalizing flows, specifically RealNVP, to model human body poses in 6D rotation format, offering a new probabilistic foundation for motion capture. The method inverts …
Researchers have developed a deep-learning method for MR elastography that reconstructs high-resolution images from highly undersampled data, achieving 2mm isotropic resolution in one minute with a total R value of 10. T…
Roboflow released a tutorial demonstrating how to build a real-time process monitoring pipeline using RF-DETR for object detection, ByteTrack for tracking, and custom counting logic within Roboflow Workflows, enabling au…
A new self-supervised learning framework, Tiny Vision Transformer with Pathology-Aware Prototype Distillation (TVT-PAPD), achieved a weighted F1-score of 93.02% on the TCGA LGG and GBM dataset and 90.23% on the IPD-Brain…
Researchers have introduced GradSkip, a new method for Vision Transformers that uses adaptive head weighting and re-evaluates residual connections to achieve a 14-times reduction in GFLOPs while improving faithfulness on…
AI shows strong promise in detecting cardiac amyloidosis (CA) through bone scintigraphy and SPECT/CT, backed by large externally validated cohorts, but lags in subtype classification and prognosis due to small study grou…
MeshRefinery, a mesh repair and format-conversion tool, diagnoses broken STL files by analyzing edge-face maps, welding coincident vertices with a bounding-box-scaled tolerance, and tracing boundary loops. The tool runs …
DynaFilter, a new technique for satellite edge data processing, enables selective inference directly in compressed domains, reducing data needed for decoding and inference by 1.6x to 7.1x for images and achieving 92.0% b…
The Obywatel Bielik app is now available on Android and iOS, enabling users to contribute photos and descriptions to train the first Polish multimodal AI model, Bielik.AI. The project, led by Fundacja SpeakLeash in partn…
Singapore-based AI video startup PixVerse is now valued at over $2 billion after an extended Series C round, signaling that investors still see room for another winner in the AI video generation space.
Researchers are shifting AI video detection from pixel-level artifact analysis to high-level factual fidelity verification, driven by the increasing realism of AI-generated content (AIGC-V). A new taxonomy called Vision-…
VehAnchor, a lightweight deterministic geometric perception skill developed for LLM-based agents, achieves a median GSD error of 6.87% on the DOTA v1.5 benchmark, enabling autonomous drones to recover metric scale in GPS…
A security service blocked access to a page about warehouse object detection on edge AI devices, with the Cloudflare Ray ID available for site owner notification.
Coura AI, a new online tool, lets users generate realistic outfit photos by uploading a portrait and a garment image or selecting a style, then applying AI clothes changing to adapt the clothing to the user's body shape …