computer-vision

Scientific Reports, Published online: 12 September 2026; doi:10.1038/s41598-026-67207-4 RGB-T object tracking method based on multi-granularity adaptive fusion

A new AI-powered reconstruction method has transformed radio observations into a continuous video, revealing unexpected motion inside a distant black hole jet.

Accurate and efficient automated analysis of Optical Coherence Tomography (OCT) images is critical for large-scale retinal disease screening. However, current deep learning models often fail to simultaneously achieve high classification accuracy, practical computational feasibility, and interpretability. To deal with these problems, this paper presents a deep learning framework on YOLOv11 for eig…

Scientific Data, Published online: 11 September 2026; doi:10.1038/s41597-026-08245-5 An Annotated Aerial Dataset for Training and Benchmarking Computer Vision Models in Turkey Behavior Analysis

A Smaller Model, A Bigger Window Most model launches ask customers to upgrade. DeepSeek’s latest asks them to

Scientific Reports, Published online: 11 September 2026; doi:10.1038/s41598-026-68706-0 Concrete surface deterioration detection and classification using YOLO26n: an AI-driven approach

Doctors looking for disease inside the digestive system can face a surprisingly difficult problem: too many pictures. A tiny camera swallowed like a pill can travel through the gut and take tens of thousands of images, leaving specialists with a huge amount of material to examine. Researchers at the Norwegian University of Science and Technology, […] The post AI Images Could Help Doctors Find Bow…

MultiMatte: Keep What You Want, Cut the Rest We’re introducing MultiMatte, a background removal model you can aim with words. MultiMatte keeps the object you name and removes everything else. Try MultiMatte on your own images at usefeyn.com/multimatte. MultiMatte is built on SAM 3 (Meta, 2025). We used low-rank fine-tuning to modify 19.49M of its 860M parameters. That update touches only 2.27% of…

Check The local check looks for one supported green color-cast pattern in visible pixels. It does not identify a named filter, app, edit history, authenticity, identity, or original image. Checking visible pixels Private photo color correction Matcha Filter Remover reduces strong green casts. Start free in your browser, or choose AI for difficult photos. Every Matcha Filter Remover result is an e…

IntroductionRapid detection of war-induced damage is vital for humanitarian response and post-war reconstruction, yet large-scale, well-annotated benchmarks for war-damage change detection are still lacking.MethodsWe present a large-scale, high-resolution bi-temporal optical remote sensing benchmark for war-damage change detection, named WD-CD. WD-CD contains 9,687 bi-temporal image pairs of 512 …

🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6

Cell membranes and the proteins within them control many vital processes and play a key role in health and disease. But studying them in 3D images of cells has so far meant slow, manual work. A team from Helmholtz Munich, the Technical University of Munich (TUM) and the Biozentrum of the University ...

arXiv:2609.09212v1 Announce Type: cross Abstract: This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment execution. We train and deploy p…

Arm unveiled its second-generation mobile Compute Subsystem (CSS), Arm CSS for Mobile 2, at its annual Arm Everywhere China event in Shanghai on September 8, further integrating AI computing capabilities across the CPU, GPU, and system interconnect while strengthening its presence in the Chinese market.

Commercial UAV Expo panelists point to data analysis, scale and human oversight as the near-term value of artificial intelligence. As commercial drone programs scale, artificial intelligence may be solving a problem that drones themselves helped create: too much data for people to reasonably review. That was one of the key takeaways from a session at […] The post When Drones Generate 6,000 Images…

A new embedded vision platform combines AI processing, camera integration, wireless connectivity and power management to accelerate development of edge-based intelligent imaging systems for devices. Phytec has introduced the phyVIP platform, a development solution designed to speed up embedded AI vision projects by bringing key vision and connectivity functions together on a compact hardware plat…

Artificial intelligence-based image analysis is transforming medical diagnosis; however, its clinical usefulness is limited by inherent noise and the quality of available medical datasets. Recent advances in generative AI promise to improve image quality through denoising, enhanced resolution, and more. This study applies the Segment Anything Model 2 (SAM2) and the Enhanced Super-Resolution Gener…

The Swiss startup is currently expanding its AI operating system to more Waste-to-Energy and other industrial plants across several continents. Jaipur Robotics, the Swiss AI company transforming waste plant operations with computer vision and automation, today announced a EUR 4.3 million Seed round ...

arXiv:2609.06058v1 Announce Type: cross Abstract: As vision-language models (VLMs) become increasingly capable and are deployed in consequential real-world settings, they must evaluate evidence independently rather than defer uncritically to human authority. We introduce GradeTrap, a controlled evaluation that places two social cues in direct conflict: a student answer, which should attract sycop…