Computer Vision news and analysis on Web Pulse: 3331 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Roboflow explains that a unified namespace (UNS) is a single hierarchical data model, typically carried over MQTT, where every system in a plant publishes its current state once and consumers subscribe to needed topics, …
Apple is expected to unveil its N50 smart glasses at WWDC 17 in June 2027, but faces a privacy challenge as the device will include a hidden camera. According to a Bloomberg report by Mark Gurman, Apple is considering a …
PostSlate, a video editing startup, achieves up to 10x faster inference on edge devices by switching from ONNX Runtime CPU to ncnn with Vulkan GPU backend, with ArcFace R50 dropping from 30 ms to 3 ms and SCRFD face dete…
Roboflow's AI1 Camera turns production line cameras into real-time inspection systems by combining an RF-DETR detection model, Roboflow Workflows, and edge inference. A bottle inspection pipeline built with this system t…
Feyn Labs released FeyNoBg, a background-removal model, and its open-source NoBg training library on July 21, claiming the model achieved the highest published S-measure on four of eight benchmarks and finished within 2%…
BitMind Forensics, a deepfake detection system built on Bittensor's decentralized AI network, achieved an AUC of 0.915 on the Deepfake-Eval-2024 image benchmark, outperforming the best commercial model's 0.90, according …
Sungkyunkwan University researchers, in collaboration with KAIST and Texas Tech University, developed an AI-based passenger movement estimation system to prevent subway door entrapment accidents. The system uses CCTV foo…
Feyn released FeyNoBg, an automatic background removal model, and open-sourced NoBg, a Python library for training and running such models. The model achieves the best published score on four of eight benchmarks and come…
NVIDIA released Ising Calibration 1.5, an open-source vision language model for fully automated quantum processor calibration, which is 11.4% smaller at BF16 precision and 86.68% better than its predecessor at in-context…
Apple will unveil smart glasses at WWDC in June 2026 with a target release by end of 2027, Bloomberg's Mark Gurman reports, as the company grapples with privacy concerns that have given Meta's Ray-Ban smart glasses a bad…
Leaked photos and video of the DJI Matrice 5, shared by Russian drone watcher Igor Bogdanov on July 26, show a gray airframe with an integrated LiDAR sensor on the top deck and a five-window gimbal, suggesting DJI is fol…
Nvidia released Cosmos-H-Dreams, an interactive generative model that lets researchers operate a surgical robot inside a synthesized video environment, generating action-conditioned video rollouts at about 160 frames per…
Meta announced the recipients of its AI Glasses Impact Grants, providing nearly $2 million to 30 organizations across the U.S. that are using Ray-Ban Meta AI glasses to solve problems in accessibility, workforce safety, …
ViralVidVault built a perceptual hash pipeline in Python to deduplicate near-identical videos that evade SHA-256. The system samples frames, computes DCT-based 64-bit hashes, and queries millions of fingerprints using SQ…
Researchers at an unnamed institution have developed a multimodal AI pipeline to analyze emergent non-verbal communication in the competitive video game Delta Force, marking a shift from prior studies focused on MOBA gam…
University of Minnesota researchers have developed an AI system that enables underwater robots to track diver stress levels by analyzing exhaled bubbles, a breakthrough that could improve safety for commercial and scient…
A developer built a browser-based video editor that removes watermarks and unwanted objects entirely on the user's device using MI-GAN, ONNX Runtime Web, and WebGPU, eliminating upload latency, infrastructure costs, and …
Apple is targeting a June 2027 unveiling of AI-powered smart glasses at its developer conference, with a consumer launch expected by the holiday season, according to Bloomberg. The device, developed for years, faces inte…
A systematic review of 60 studies on diffusion models for medical image inpainting finds that denoising diffusion probabilistic models and latent diffusion models are the dominant architectures, primarily used for artifa…
Researchers propose Visual Saliency Steering Distillation (VSSD) to improve multimodal chain-of-thought reasoning in small models by using attention maps from multimodal large language models to generate perturbed images…