Computer Vision news and analysis on Web Pulse: 3346 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
San Francisco City Attorney David Chiu sent cease-and-desist letters to Apple and Google on Thursday demanding the removal of 13 AI face-swap apps that generate nonconsensual nude images, arguing the companies are aiding…
Upscayl, the local AI image enhancer, has improved with new models and faster processing, according to a user review. The latest version adds a 'Lite' model for quick previews and a 'High Fidelity' model that delivers be…
Microsoft offers three distinct Azure AI services—Azure AI Vision, Azure Document Intelligence, and Azure Content Understanding—that all process images or documents but solve different business problems, according to a d…
A new AI-powered medical software called Dr. Noon can detect cardiovascular disease risk by analyzing retinal images, according to clinician scientist Dr. Sahil Thakur from Singapore. The non-invasive tool captures retin…
Roboflow released a guide for building an automated beverage shelf-monitoring system using RF-DETR object detection and Gemini 2.5 Pro, which detects and counts Coca-Cola, Fanta, and Sprite bottles, calculates replenishm…
A new generation of fashion designers is incorporating 'adversarial patterns' into garments to confuse facial recognition systems, as the technology expands across British public spaces. Companies are creating clothing w…
Belfort released the fastest encrypted image classifier available, a CIFAR demo of ResNet-20 that achieves a total latency of less than 200ms, outperforming recent state-of-the-art by 3x. The model maintains 92.5% accura…
Krista Campbell received an AUD$1,251 (about US$820) fine in Queensland, Australia, after an AI-assisted mobile phone detection camera captured her phone resting face-down on her lap while driving, even though both hands…
Researchers at ETH Zurich and EPFL have built a prototype particle detector called PLATON that uses a light-field camera, highly sensitive photon sensors, and AI to reconstruct particle paths in 3D from a single block of…
Un nuevo libro de Afonso Bandeira, Amit Singer y Thomas Strohmer, 'Mathematics of Data Science', dedica un capítulo a SVD y PCA, las técnicas de álgebra lineal que permiten comprimir matrices de un millón de columnas a d…
Icop, an open-source AI content filtering plugin for VLC media player, uses local ONNX Runtime inference to classify video frames before display, keeping processing on-device with no cloud uploads or telemetry. The plugi…
PixLab has launched a WebGL/WASM video editor that processes video edits locally in the browser with GPU acceleration, featuring a timeline for captions, text overlays, trims, and exports to MP4 or WebM. The editor integ…
Polygraf AI released Meeting Guard, a real-time deepfake detection solution for enterprise meetings that joins as a visible participant and delivers near-real-time security analysis. The product was among the week's new …
DS@GT ARC achieved third place in the PlantCLEF 2026 challenge with a multi-scale ViT inference pipeline that blends a fine-tuned DINOv2 ViT-L/14 classifier with FAISS kNN retrieval and habitat-fit priors, reaching a pri…
Researchers propose ReportMedSAM, a report-driven segmentation framework that uses a learnable concept bank and frozen medical vision-language encoder (BiomedCLIP) to align organ-level embeddings with clinical corpora vi…
Researchers propose DialogueVPR, a conversational visual place recognition framework that shifts from static one-shot retrieval to interactive dialogue-driven reasoning. The team introduces DlgQuest-Cities, the first lar…
Researchers introduce Ego Scene Augmentation (ESA), an egocentric spatial perception framework that enhances spatial reasoning in Multimodal Large Language Models (MLLMs) for egocentric Visual Question Answering (VQA). T…
Researchers propose $K$-NeAS, a scalable architecture for multi-material CT reconstruction using neural signed distance functions, achieving superior 3D volumetric fidelity on clinical Cone-Beam CT datasets. The method r…
Researchers propose DCVC-Mamba (DCVC-MB), a neural video codec framework for B-frame coding that incorporates an IBP frame strategy, a spatio-temporal fusion model based on state-space models, and an entropy-aware skippi…
Researchers introduce SD-MAR, a framework using synthetic data and reinforcement learning to train vision-language models on multi-image analytical reasoning tasks such as change detection and visual comparison. Fine-tun…