Computer Vision news and analysis on Web Pulse: 3361 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Roboflow released a text prompt object detection workflow using SAM3 that lets users find objects by typing descriptions instead of training models, enabling rapid prototyping for plant disease detection without labeled …
Google DeepMind launched the Nano Banana 2 Lite, officially branded as Gemini 3.1 Flash Lite Image, on February 26, 2026, ranking fifth in text-to-image leaderboards with an Elo score of 1,255. The model prioritizes spee…
CNET updated its list of best AI video generators for 2026 after OpenAI discontinued Sora. Adobe Firefly, Google Veo 3, Runway, and Midjourney are top picks, with Firefly offering commercially safe content and Veo 3 lead…
Google made Nano Banana 2 Lite (gemini-3.1-flash-lite-image) generally available and launched Gemini Omni Flash in public preview, expanding its lineup of fast, cost-efficient generative media tools. Nano Banana 2 Lite g…
Apple updated its Creator Studio apps with new AI features, integrating Pixelmator Pro with Final Cut Pro, Keynote, Numbers, and Pages, and adding AI-powered tools like Generate Captions, Edit Detection, and Auto Mask. T…
Google launched two new generative AI models: Nano Banana 2 Lite for fast image generation and Gemini Omni Flash for video generation via API. Nano Banana 2 Lite generates images in four seconds at $0.034 each, while Gem…
Apple announced updates for its Creator Studio apps, including AI-powered features in Pixelmator Pro, Final Cut Pro, and Logic Pro, rolling out today. The updates add integrations, intelligent tools, and new capabilities…
Ambarella's stock surged after the AI chipmaker received a 'Top Pick' rating from an analyst, highlighting strong demand for its edge AI processors. The company's focus on computer vision and AI infrastructure positions …
Tesla is testing a production Cybercab with no steering wheel or pedals on public roads in Austin and the Bay Area, with a safety monitor in the passenger seat. The vehicle relies solely on cameras and Tesla's Hardware 5…
Outpost VFX achieved 8x faster AI model training for visual effects face replacement by using AWS multi-GPU EC2 P5 instances, overcoming single-GPU bottlenecks that previously caused week-long delays. The collaboration w…
Purdue researchers tested 24 deepfake detection systems and found commercial tools generally performed better as AI identity fraud raises new risks for crypto KYC. The study found Incode's DeepSight achieved the lowest f…
Ancestry has deployed machine learning to accelerate its record digitization pipeline from nine months to under nine days, with its corpus now exceeding 71 billion records. The company adds about 10 million records daily…
A developer built a multi-modal evidence review agent for damage claims using Python, OpenAI GPT-4o, and structured prompting. The system processes text, images, and historical context to produce consistent, explainable …
Google released Nano Banana 2 Lite, its fastest and most cost-efficient image model, and made Gemini Omni Flash available to developers for video generation and editing. The models are accessible via Google AI Studio, Ge…
Google announced Nano Banana 2 Lite, its fastest and most cost-efficient image generation model, and previewed Gemini Omni Flash for video generation. NotebookLM will use Nano Banana 2 Lite to create 60-second short vide…
Google Cloud announced the general availability of Nano Banana 2 Lite and the public preview of Gemini Omni Flash on its Gemini Enterprise Agent Platform, offering cost-efficient image generation and conversational video…
Google announced the general availability of Nano Banana 2 Lite and the public preview of Gemini Omni Flash, new generative AI models for image and video creation, now available in the Gemini Enterprise Agent Platform. T…
NVIDIA used Nsight Systems and Nsight Compute to optimize its NuRec neural reconstruction pipeline, reducing reconstruction times from hours toward a goal of real-time performance for autonomous vehicle and robotics appl…
Ancestry has spent 42 years digitizing 71 billion family records from 88 countries, a process that was slow and costly. Since 2014, the company has used AI, including machine learning and natural language processing mode…
A developer built a drone-based security reconnaissance system that uses computer vision to detect restricted-zone breaches. The system relays PTZ camera and drone feeds through MediaMTX, samples frames every two seconds…