Computer Vision news and analysis on Web Pulse: 3368 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers propose RSGPNet, a training-free geometric prompting framework for open-vocabulary semantic segmentation in remote sensing, which improves segmentation accuracy by leveraging object geometric areas and consis…
A developer reverse-engineered the Remini HD API to create an unofficial Node.js client that bypasses rate limits. The script generates device IDs, authenticates with the Remini servers, and processes images through the …
Korean safety AI firm Intellivix, profitable for 13 consecutive years, is expanding its AI video analytics technology to Japan and Southeast Asia. CEO Choi Eun-soo aims to transform CCTV from a post-incident monitoring t…
Anthropic launched Claude Design, a research-preview visual design product for subscribers, on April 17, 2026. The tool, powered by a new vision model, generates a distinctive aesthetic of warm, editorial layouts with of…
A guide to programming Lisp on the DEC PDP-1, one of the earliest interactive Lisp environments, was published. The tutorial covers bringing up the system, loading and saving programs, and mixing assembly code, highlight…
PDF Insight, a new local-first AI tool, sorts and merges PDFs entirely on-device using Ollama and Tesseract, with no upload or internet required. It targets tax preparers and individuals organizing documents, offering an…
A developer built a real-time posture tracking system using MediaPipe Pose and Electron. The system captures webcam frames, processes them through a neural network to identify body landmarks, and sends notifications when…
Google's Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is now available on Vercel's AI Gateway, offering fast, low-cost image generation at $0.034 per 1K images. The model generates images alongside text in under 4 se…
ByteDance released Seedance 2.5, an AI video generation model capable of producing 30-second clips at 4K resolution with up to 50 multimodal references, setting a new benchmark for long-form AI video. The model addresses…
ByteDance's Seedance 2 Image to Video outperformed its predecessor Seedance V1.5 Pro in a head-to-head comparison, scoring 15.1 to 12.7. Seedance 2 demonstrated superior cinematic intent, shot grammar adherence, and temp…
Allen Pike presented a talk on voice-in, visuals-out agents at the AI Engineering World's Fair, discussing the challenges and rewards of achieving immediate model responses.
A chest X-ray AI system that outputs a 93% confidence diagnosis may still be unreliable, as uncertainty estimation reveals hidden fragility in predictions. Medical AI systems must distinguish between aleatoric uncertaint…
Roboflow released a transmission line inspection AI that uses an RF-DETR model to detect foreign objects and damaged cables from drone or fixed-camera feeds, achieving 96.3% precision and 93.1% recall. The system automat…
A developer used Comma.ai's open dataset to build a case study on Automatic Emergency Braking (AEB) systems, demonstrating how the data can be leveraged for safety-critical automotive applications. The project highlights…
Roboflow released a tutorial on building an automated foreign object debris (FOD) detection system for airport runways using its RF-DETR model and Gemini 2.5 Pro. The system identifies debris and pavement holes from came…
Roboflow released a guide on building a promptable object detection project using SAM 3, enabling users to detect objects like soda cans from text prompts without datasets or training. The workflow allows rapid prototypi…
AuraFlow and Fibo image models were tested head-to-head on three architectural prompts. Fibo won the matchup with a score of 22.0 to AuraFlow's 21.1, demonstrating superior obedience to geometric and scale constraints, w…
Nvidia will present breakthroughs in neural rendering, world models, and simulation at its SIGGRAPH 2026 keynote on July 20 in Los Angeles. The session, led by VPs Jan Kautz and Ming-Yu Liu, covers AI-driven advances for…
Researchers introduced WGO-Bench, a benchmark for testing robotics subtask annotation performance across 100 egocentric and robot-video episodes with 743 annotated segments. After over 60 experiments, they found Gemini m…
Roboflow released a tutorial demonstrating video analytics with vision AI, combining RF-DETR object detection, ByteTrack multi-object tracking, and Gemini 2.5 Pro multimodal inspection to detect and classify damaged boxe…