Computer Vision news and analysis on Web Pulse: 3314 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers propose V-RAE, a video representation autoencoder that builds compact generative latents on top of frozen vision foundation model representations, achieving 2.13 rFVD on K600 and outperforming all evaluated l…
Artist Simon Weckert presented Digital Camouflage in 2025, a garment using an adversarial texture to make AI person-detection systems fail to recognize its wearer. Ars Electronica describes the textile as designed to con…
Meta has filed a patent for AI smartglasses that use facial recognition to identify people and automatically generate highlight reels of events such as dinner parties, according to a patent published Thursday. The system…
Indie iOS developer built Reeliva, an iOS app that automates visual cutout effects, seamless looping, and audio-to-video syncing for short-form video creation. The app uses the Vision framework and Core Image for real-ti…
NoRecognition, a project by an unnamed team, is selling custom adversarial clothing—tees, hoodies, and gaiters—printed with patterns tested to stymie machine vision systems' human detection, now available for pre-order o…
On February 2, 2026, the FDA's Quality System Regulation was replaced by the Quality Management System Regulation, incorporating ISO 13485:2016 by reference, and removing the legacy 820.180(c) exemption that kept interna…
Roboflow published a tutorial for building a local AI basketball shot evaluator that logs makes, misses, release velocity, shot arc, and form using an RF-DETR object detection model and an RF-DETR keypoint estimation mod…
Artist Trevor Paglen's new book argues that the rise of computer vision and generative media has transformed visual culture more profoundly than the discovery of perspective or photography, turning digital images into op…
Samsung Electronics has hired Han Bo-hyung, a deep-learning and computer-vision specialist, and Hahn Tai-rin, a data-engineering expert, to strengthen its AI capabilities in semiconductor research and manufacturing. Han …
Flock Safety, the Atlanta-based operator of 120,000 automatic licence-plate readers across the US, has reduced its recommended default image retention period from 30 days to 7 days and introduced mandatory audit features…
DJI launched the Osmo 360 II, an 8K 360-degree camera, in China with a starting price of RMB3,299. The camera features a 1-inch panoramic imaging sensor, 14.5 stops of dynamic range, native 8K/60fps video, AI Super Night…
A study evaluating three open-source vision-language models (VLMs) — InternVL, Qwen-VL, and SmolVLM — on classifying proxemic danger from egocentric robot images found that without fine-tuning, all models perform near a …
Researchers propose a data-model co-design framework to scale representation diversity in Referring Expression Comprehension, introducing the Modulated Attention-Contrastive Head (mACH) and a text-conditioned JEPA auxili…
Researchers introduced Generative Defect Isolation (GDI), a method using the LaMa inpainting model with Fast Fourier Convolutions to generate realistic single-defect training samples for multi-label defect classification…
Researchers introduced HIMEC, a remote sensing image change captioning method combining Directional Change Representation with fixed-interface decoding, achieving a CIDEr score of 142.81±0.60 on LEVIR-CC, outperforming d…
Researchers introduced WidgetGen, a lightweight tool-grounded framework that extracts observable text and color evidence, performs high-level layout and optional chart reasoning, and directly generates executable JavaScr…
A new arXiv study (2608.12658v1) finds that using three orthogonal seed slices—axial, coronal, and sagittal—during inference improves 3D organ segmentation in slice-propagation methods like Sli2Vol, boosting Dice by 21.9…
VOS-Agent, a collaborative framework built on SAM3, won first place in the MOSEv2 Track of the 8th LSVOS Challenge at ECCV 2026, achieving 69.82% on the official J&F metric. The framework uses a Target Perception and Rou…
RAGFlow, an open-source RAG engine launched in April 2024 by InfiniFlow, has reached 88,000 GitHub stars and continues trending in August 2026, despite repeated declarations that RAG is dead. The project's success stems …
The @liustack/modlens CLI toolkit, version 3.11.0, converts images into structured JSON evidence (OCR, layout, semantics) for AI agents, and is available via dsh plugin installation with mirror acceleration. The toolkit,…