Computer Vision news and analysis on Web Pulse: 1848 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers have developed a collaborative inference method for occlusion-robust object detection on edge devices with less than 1 MB SRAM, combining an MCUNet backbone, YOLOv2 detection head, and TensorFlow Lite quantiz…
Researchers introduced Any2Poster Bench, a benchmark for evaluating automatic poster generation across eight input modalities and five content domains, alongside Any2Poster Agent, a system that parses diverse sources and…
Researchers have developed Pixel Cube, a diffusion-based method for relighting dynamic portrait videos that achieves photorealism and temporal consistency. The system uses a hybrid dataset of real-captured and rendered v…
Researchers have developed a two-stage geometric registration method that aligns CAD models to CT scans of cylindrical objects by detecting elliptical cross-sections and estimating the 3D rotation axis. The approach achi…
A developer built MangoGuard, an edge AI system that detects mango diseases directly on an Arduino Nano microcontroller without requiring cloud connectivity or internet access. The quantized MobileNetV1 model classifies …
A developer built an AI thumbnail generator in pure Python using only the Pillow library, capable of producing professional images for YouTube, blogs, and social media in under two seconds. The tool runs entirely offline…
A developer built a "Medicine Box Expert" pipeline that uses YOLOv8 for object detection and OpenAI CLIP for multimodal understanding to turn photos of medicine packaging into a searchable digital database. The system em…
XAI released Grok Imagine Video 1.5 on AI Gateway, a model that generates video from an input image with synchronized audio in a single pass. The update improves audio quality, prompt following, photorealism, face accura…
24ad.info has deployed an AI-powered classifieds stack that processes photo uploads, generates listing details, and posts ads in seconds. The system uses OpenRouter and Gemini 2.5 Flash for vision processing, assigns cat…
Microsoft unveiled seven in-house AI models on Wednesday, claiming its flagship reasoning and image systems outperform competitors including Anthropic's Claude, OpenAI's models, and Google's Nano Banana. The company's pe…
Meta has reportedly planned a slate of new smart glasses for 2025, including a December release codenamed "Mojito VIP" and two prototypes called "Artemis" and "SSG" for fall testing, according to a report from The Inform…
Microsoft's new image generation model, released alongside the MAI family, outperformed OpenAI and Google in a stress test focused on generating complex software interfaces like dashboards and admin panels. The benchmark…
Rudus, an AI platform developed by YC-backed founders Rishi and Sahil, automates material quantity takeoffs for concrete subcontractors by using computer vision to analyze structural PDFs and generate detailed line items…
Microsoft unveiled two new concept AI devices at its Build developer conference, including a high-tech badge with a touchscreen, fingerprint sensor, 5G connectivity, and a side-facing camera. The badge, part of the new "…
Amazon faces a class action lawsuit filed Monday in Seattle over privacy violations from its Ring doorbell cameras' Familiar Faces facial-recognition feature. Virginia resident Charles Sigwalt alleges the feature stores …
Kapa, a company building AI assistants for technical documentation, developed a method to incorporate images into its RAG pipeline without incurring per-query vision costs. The firm indexes images by describing each one …
XREAL launched its new xbx brand with the $299 a01 smart glasses, a 62-gram device featuring a 1600-nit Micro-OLED display that creates a 147-inch virtual screen. The glasses cut costs by removing cameras, spatial tracki…
Visual AI is shifting from generating final images and videos to producing the underlying code artifacts that create those visuals, according to a new analysis. This transition from pixel-native to code-native generation…
A walking tour of surveillance infrastructure in downtown Seattle, developed by the Tech Equity Coalition and ACLU of Washington, guides participants to identify hidden surveillance technologies such as cameras and Amazo…
Amazon was sued Monday over the facial-recognition feature in its Ring doorbells, with a Virginia resident alleging the "Familiar Faces" setting captures and stores images of passersby without their permission. The propo…