Computer Vision news and analysis on Web Pulse: 3347 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
A developer detailed how to build high-speed vision analyzers on Android by orchestrating data movement between the camera sensor, RAM, and hardware accelerators like NPUs, GPUs, and DSPs to minimize latency-to-insight. …
Modern generative AI systems like Midjourney and Stable Diffusion recreate paintings in different artistic styles using diffusion models and attention mechanisms, according to the article. Diffusion models gradually add …
Google Research released TimesFM 2.5, a decoder-only foundation model for time series forecasting, with 10,000 GitHub stars and support for installation, fine-tuning, and real-world applications. The model joins 40 resou…
Researchers from Google DeepMind and the University of Toronto have developed GenCeption, a method that repurposes a pre-trained video generative model into a single unified, feed-forward vision model capable of solving …
NVIDIA introduced NemoClaw, a collection of open blueprints for building autonomous agents, to integrate context-aware video AI agents into enterprise workflows. The approach combines the NVIDIA Metropolis Blueprint for …
Karachi's Sindh Safe Cities Authority has activated AI-powered no-parking cameras that automatically issue e-challans through the Traffic Police TRACS system, using over 1,300 AI-based cameras from the Karachi Safe City …
Andrew Dai, a former DeepMind researcher, raised $55 million in seed funding at a $300 million post-money valuation for his visual AI startup Elorian AI, which aims to build AI systems that reason natively in the visual …
Andrew Dai, a former Google DeepMind researcher, raised a $55 million seed round at a $300 million valuation for his visual AI startup Elorian before launching a product. Dai prioritized strategic investors like Nvidia a…
A new Arduino library, OV7725_CPUfree_Camera, captures images from the OV7725 camera without using any CPU on the RP2350 microcontroller, achieving fixed 90 FPS streaming. By leveraging DMA and PIO automation, both CPU c…
The FBI has explored using artificial intelligence to assess signatures on roughly 150,000 mail-in ballot envelopes seized from Fulton County, Georgia, as part of the Trump administration's reinvestigation of the 2020 el…
Artificial intelligence is transforming video surveillance for businesses, moving beyond passive recording to real-time object detection, behavior analysis, and predictive insights, according to a report by Securitas Tec…
ByteDance launched Seedream 5.0 Pro on July 8, a reasoning image API that builds an internal plan before generating, with a headline feature of layer separation that returns 2 to 20 transparent-PNG files per prompt. The …
A new wave of AI products sold to police departments at the International Association of Chiefs of Police Technology Conference promises to automate routine tasks like report-writing and 911 call triage, but critics warn…
OpenAI's GPT-5.6 Sol is the best vision model the company has released, scoring 46.2 mAP@50 in object detection compared to GPT-5.5's 13.8, according to Roboflow's upcoming VLM benchmark. Sol also achieved 73.0% in objec…
Wi-Fi signals can be used with AI to detect movement, presence, and activities like walking or falling without cameras. The technology analyzes how radio waves change when people move, offering privacy-preserving sensing…
A new multi-modal dataset from Catalonia, Spain, includes around a million side-scan sonar tiles, bathymetric maps, and co-registered optical images from autonomous underwater vehicle surveys, with about 36,000 tiles man…
AAEON (Stock Code: 6579) announced plans to adopt NVIDIA Jetson T2000 and T3000 modules across its Fanless Embedded AI System range, starting with the BOXER-8752AI powered by the Jetson T3000 module. The BOXER-8752AI fea…
Researchers have unveiled a new AI framework that acts as a digital twin for brain tumors, predicting tumor evolution and optimizing treatment. In tests with 387 synthetic tumor trajectories, the hybrid model reduced mea…
MedDiffuseMix, a novel saliency-guided diffusion mixing tool, improves medical image classification by selectively enhancing less important regions while preserving critical diagnostic details. Tested on four public benc…
Researchers have introduced GroundShot, a training-free agentic framework that improves visual consistency in multi-shot videos by using smart shot scheduling and a visual memory bank. To evaluate it, they also created G…