Computer Vision news and analysis on Web Pulse: 3371 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Emir Yüksel released Caddy, an open-source modular viewer for 3D Gaussian Splatting models that supports linking multiple PLY checkpoints, custom renderers, and remote GPU rendering. The tool allows users to visualize re…
Microsoft's MAI-Image-2.5 model ranks second in image editing and third in text-to-image generation on the Artificial Analysis Image Arena, outranking Google Gemini offerings and prior Microsoft models. OpenAI's GPT Imag…
General Intuition raised $320 million at a $2.3 billion valuation to develop AI agents trained on video game footage that can operate in the real world. The startup uses action labels from hundreds of millions of hours o…
ByteDance's open-source SeedVR2 video restoration model is now deployable on Amazon SageMaker AI, enabling scalable super resolution for low-resolution video libraries. The solution uses a three-tier AWS architecture wit…
General Intuition raised $320 million at a $2.3 billion valuation to develop AI agents trained on video game footage that can operate in the real world. The startup uses action labels from gameplay clips to teach spatial…
Adobe has agreed to acquire Topaz Labs, an Emmy-winning AI company specializing in image and video enhancement, to integrate its upscaling, restoration, and on-device AI capabilities into Adobe's creative tools like Phot…
Adobe is acquiring Topaz Labs to integrate its on-device AI inference technology, NeuroStream, and Emmy-winning enhancement models into Creative Cloud, aiming to compete with Canva and Blackmagic Design. The deal, announ…
Baidu released Unlimited OCR, an open-source 3-billion-parameter model that uses Reference Sliding Window Attention to parse multi-page documents in a single pass, eliminating the need for page-by-page OCR pipelines. The…
Chinese physical AI start-up Fysics AI launched Fysiverse, a physics-based world model that embeds real-world physical laws into its code, diverging from data-driven approaches used by OpenAI and Meta. Founded by former …
Adobe acquired Topaz Labs, an AI-powered image and video enhancement tool maker, to integrate its models into Adobe's Firefly app and Creative Cloud suite. The deal aims to strengthen Adobe's AI capabilities and retain u…
Hugging Face's top-voted papers on June 25, 2026, reveal a trend of AI shifting from question-answering to world-acting models. Key papers include Qwen-AgentWorld, which uses a language world model for generalist agents;…
AAEON released the EPIC-PTH9, a 4-inch industrial single-board computer with Intel Core Ultra Series 3 processors, delivering up to 180 TOPS of AI performance. The board features PCIe Gen 5 x8 expansion, multiple LAN and…
Samsung's Galaxy S26 Ultra, starting at $1,300, introduces a Privacy Display feature that effectively blocks screen peeking but comes with tradeoffs like reduced screen quality. The phone offers flagship performance, sol…
LocalClicky, a new open-source voice assistant for Mac, runs entirely offline using local AI models like Whisper.cpp and Ollama, ensuring no voice data, screenshots, or commands leave the user's machine. The tool offers …
FIFA is tracking 150 million data points per match at the 2026 World Cup, with AI companies like Stats Perform and Lenovo providing tools for player scouting, tactics, and penalty analysis. Teams such as Curaçao use data…
A developer participating in the Gemma 4 challenge built Dresscode, an AI stylist that uses computer vision to digitize wardrobes and LLM function calling to recommend weather-appropriate outfits. The project demonstrate…
AMD engineer Steven Xiao contributed an ONNX Runtime back-end for FFmpeg's DNN filter, enabling AI model inferencing on multiple GPU and NPU platforms including NVIDIA CUDA, Windows DirectML, and AMD Ryzen AI NPU. This i…
Berlin-based Almetra, formerly Deltia, raised €16.3M in Series A funding led by blisce/ to expand its AI-powered factory video analytics platform into the US. The startup mounts AI cameras above assembly lines to convert…
A developer built two browser-based background removal tools—one using the Canvas API for uniform backgrounds and another using WebAssembly with an ONNX Runtime machine learning model for complex backgrounds. Benchmarkin…
Seeed's reComputer AI Lab, an edge AI development platform, now supports one-click deployment of YOLO models on RK3588/RK3576 hardware. The platform pre-packages 18 YOLO variants across YOLOv5, YOLOv8, and YOLO11, using …