Computer Vision news and analysis on Web Pulse: 3328 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Google is expanding Gemini Omni video editing with relighting tools in Google Photos and Google Vids, allowing users to change a clip's lighting through natural-language prompts. The feature is part of a broader conversa…
Apptronik's Apollo 2 humanoid robot demonstrated fine-motor tasks and kitchen chores using Google DeepMind's Gemini Robotics 2 vision-language-action model on July 30, with the system achieving a 68.4% success rate picki…
Google Photos has launched Video Remix, an AI-powered editing feature that applies stylized templates to users' existing video clips. Powered by Gemini Omni, the tool offers one-tap cinematic relighting, background repla…
Marble, a New York-based Y Combinator-backed startup founded by Aakar Khanna and Arjun Chaliha, launched an AI operating system for restaurant back-office tasks including inventory, purchasing, and labor planning. The co…
Google DeepMind released Gemini Robotics 2.0, a trio of AI sub-models that improve robot dexterity and safety, with the embodied reasoning model Gemini Robotics ER 2 now publicly available for developers via the Gemini L…
A new online live face swap app lets users swap faces in real time without needing a GPU, as AI processing runs in the cloud with less than 500 ms latency. The app offers browser-based preview and a Desktop app with virt…
Google DeepMind released Gemini Robotics 2, a family of three models that gives humanoid robots full-body control and enables teamwork, moving beyond tabletop demos to tasks like walking, crouching, and multi-step chores…
Seedance 2.5, the next version of the Seedance AI video platform, will support up to 50 media inputs in a single creative task, including 44 images, three video clips and three audio files, enabling multimodal workflows …
Google launched Gemini Robotics ER 2, an embodied reasoning model that helps robots understand surroundings, communicate, and complete complex physical tasks in real time, available through the Gemini API and Google AI S…
Google has launched Gemini Robotics ER 2, an embodied-reasoning model that serves as a robot's high-level planner while a separate model handles motors, available to developers through the Gemini API and Google AI Studio…
OpenAI researchers demonstrated in 2021 that CLIP, a vision language model, misclassifies a Granny Smith apple as an iPod when a paper label reading 'iPod' is attached, revealing that grounding in AI is statistical proxi…
Google launched Gemini Robotics ER 2 on July 30, making the embodied-reasoning model publicly available through the Gemini API and Google AI Studio. Google reports 57.4% accuracy on progress classification and 91.3% on m…
Google DeepMind launched Gemini Robotics ER 2, its most capable embodied reasoning model for robotics, enabling robots to understand video feeds, orchestrate multi-step tasks, and collaborate in shared spaces. The model,…
EssilorLuxottica reported that revenue from its smart glasses nearly doubled in the second quarter compared to the same period last year, despite growing privacy concerns and backlash, particularly against Meta's Ray-Ban…
A developer optimized person comparison in recognition knowledge bases by replacing inefficient Python loops with a NumPy-based solution that leverages the squared Euclidean distance identity. The approach achieved a 2.8…
Snap Inc. will launch SPECS, its new augmented reality glasses, on September 16 in Los Angeles, with CEO Evan Spiegel demonstrating how the device integrates AI assistance, work tools, and entertainment to help users sta…
Google Earth now uses Gemini's Nano Banana 2 image generation model to create AI-powered visual concepts based on real-world locations, using satellite, aerial, and 3D map data. The feature, rolling out globally today fo…
Google is integrating its latest AI image generation model, known as Nano Banana 2, into Google Earth on the web, allowing users to generate AI images based on aerial, satellite, and 3D imagery. The feature enables histo…
The Orange Pi Zero 4 is a compact 50×55 mm single-board computer featuring an Allwinner A733 octa-core processor, up to 16 GB LPDDR5 RAM, and a 3 TOPS NPU for edge AI workloads. It offers Wi-Fi 6, Gigabit Ethernet, 4K vi…
Procore Technologies is acquiring DroneDeploy for $845 million in cash to give its AI-powered digital coworkers the ability to see and analyze physical construction sites via drones, ground robots, and cameras. The deal,…