Computer Vision news and analysis on Web Pulse: 4325 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
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,…
An AI-powered thermal camera system called WhaleSpotter is being piloted on a San Francisco Bay ferry and on Angel Island to detect gray whales and alert crews to avoid collisions, after 21 whales died in the bay last ye…
Google has launched Custom Satellite Embeddings, a new feature on Google Maps Platform that enables organizations to monitor changes in a region with higher frequency using AI, now available in Enterprise Private Preview…
Better, an all-in-one fitness and nutrition app, launches with AI-powered photo meal logging that estimates portion size and breaks meals into calories, protein, carbs, and fat. The app offers 300+ exercises, a 1M+ verif…
Luxonis introduced a prototype M8 Controller Box, an industrial I/O expansion module for its OAK4 AI vision edge AI cameras powered by a Qualcomm DragonWing QCS8550, adding 16 GPIOs, four 16A relays, CAN 2.0, RS232, two …
Hyundai Motor Group has hired Kwon Jung-hyun, a former Samsung Electronics executive and Nvidia autonomous driving software veteran, to lead its Autonomous Driving Development Center. Kwon will oversee development and co…
InHand Networks introduced the Mo 62A and Mo 68A, credit card-sized Edge AI single board computers powered by Texas Instruments AM62A and AM68A processors, delivering 2 TOPS and 8 TOPS of AI performance respectively. Des…
Zero Zero Robotics founder Mengqiu 'MQ' Wang unveiled the HOVERAir VERSA, a pocket-size stabilized camera that becomes an autonomous flying camera when attached to snap-on wings. The device combines a 3-axis gimbal for h…
A hybrid deep learning method developed by researchers uses Mask R-CNN and a color-based algorithm to quantify exposed skin from images for dermal exposure assessment. Testing on 170 indoor-painting images, the approach …
Researchers introduce LumaGuide, a training-free framework that shapes output distributions of pretrained diffusion models to generate high dynamic range (HDR) content without retraining. By steering the sampling process…
Researchers introduce TraceCLIP, a training-free framework that recovers latent patch-level semantic evidence from CLIP's CLS attention output, achieving gains of 1.3 to 4.5 points in average mIoU over prior training-fre…
Researchers have developed a deep neural network approach to estimate weight, height, and Body Mass Index (BMI) from a single human image captured in the wild, achieving best results with full-body images. The team creat…
Researchers propose Zero-Fi, a contrastive signal-language alignment framework that enables zero-shot Wi-Fi-based human activity recognition by aligning Wi-Fi signal features with natural-language activity descriptions i…
Researchers at University College London propose Eddeep, a deep-learning framework for fast eddy-current distortion correction in diffusion MRI. The method achieves correction quality comparable to FSL Eddy while substan…
MoSAIC, a latent diffusion framework for part-local reference-conditioned motion style transfer, achieves a preserved-region error of 66.45 mm and off-target leakage of 9.88 mm, outperforming whole-body routing by reduci…
A study using CT Foundation embeddings achieved a Receiver Operating Characteristic Area Under the Curve (AUC) of 0.791 for predicting distant metastasis risk in head and neck cancer, outperforming radiomics (AUC 0.772) …
Researchers introduce WildShadowRemover, a framework that adapts a pretrained video diffusion model via LoRA fine-tuning for robust video shadow removal in unconstrained real-world scenarios. The method augments the froz…