Computer Vision

A team led by researchers from multiple institutions won the MeViS-Text track at the 8th Large-scale Video Object Segmentation (LSVOS) Challenge 2026 with their SSUPER pipeline, achieving a Final score of 0.9081339614 on…

Researchers introduced Semantic Prism, a generative semantic segmentation framework that achieves 72.07% mean intersection over union (mIoU) on the Cityscapes validation set, outperforming direct-interface decoding by 11…

Researchers introduced Global Style Transfer (GST), a Many-to-One artistic image synthesis paradigm that aggregates multiple artworks from a target artist to transfer their shared global style to a single content image, …

Researchers introduced S2R, a closed-loop framework for video reflection removal that includes S2R-Synthesis for physics-grounded reflection simulation, S2R-Removal as the first diffusion-based video reflection removal m…

Researchers have developed Click2Poly, a human-in-the-loop AI assistant built on the Florence-2 Vision Language Model, that speeds up manual editing of building and wall vector layers in QGIS for geospatial mapping. The …

Recraft-Ai's Recraft-Clarity-Upscale model, available on Replicate, is an image upscaling tool that enhances sharpness and clarity for web and print use. Unlike general-purpose upscalers, it focuses on definition and edg…

DeepMind has introduced SL2T, a sign language translation system that converts signing into English text in real time, with pose tracking processed on-device for privacy and translation handled server-side. The model, tr…

At Defcon 34, security researcher Bill Swearingen demonstrated a black-and-white adversarial pattern that reduced a live AI person-detection system's confidence score from above 0.75 to 0.21, triggering a 'No person dete…

Bill Swearingen's noRecognition project generates adversarial patterns that defeated all 11 open-source detection algorithms he tested, including software behind Flock license plate readers, Axon body cameras, and Clearv…

At the 2026 Embedded Vision Summit, Dr. Mahbubul Alam, Chief Research Scientist at Hitachi America Ltd., presented a session on 'Industrial Vision Meets Physical AI: From Automated Vision to Human-Centric Agentic Systems…

Honor launched its Robot Phone in China starting at RMB 9,999 (about $1,500), featuring a robotic arm with a 200MP camera and 4DoF stabilization. The device is available only in China, with no global release plans announ…

Google's Pixel 11 Pro XL, powered by the Tensor G6 chip, was tested by Mashable's Andrew Lanxon on a street photography walk through Paris, focusing on new features including customizable Camera Looks, Magic Capture, and…

Microsoft Research introduced CARE-X, a unified chest X-ray vision-language model designed to improve clinical usefulness by combining generative report generation with calibrated diagnostic predictions, and validated it…

Google DeepMind announced SL2T, a new AI model that translates American Sign Language directly into written text, powering a sign-to-text feature in Gboard and Live Transcribe on the Pixel 11 family. The on-device comput…

A new white paper from IEEE Spectrum and Wiley, sponsored by Voxel51, reports that 78% of more than 700 surveyed practitioners already see measurable value from visual and physical AI, while 74% still consider the field …

Ukraine's military intelligence directorate (HUR) recovered an Nvidia Jetson Orin AI computing module from the wreckage of Russia's new S-71 Monochrome cruise missile, identifying 35 foreign electronic components from co…

Google introduced a massively multilingual sign-language-to-text (SL2T) translation model that powers sign-to-text dictation in Gboard and Live Transcribe on Pixel 11, starting with American Sign Language (ASL) to Englis…

Liquid AI released LFM2.5-VL-3B, a 3.1B parameter vision-language model for edge devices, claiming it leads its size class on real-world image tasks while supporting screen/UI understanding, grounding, multi-image input,…

Google DeepMind launched SL2T, a multilingual sign-language-to-text AI model that debuts on the Pixel 11 smartphone, powering a new sign-to-text dictation feature in Gboard and Live Transcribe, initially translating Amer…

Google unveiled the Pixel 11, Pixel 11 Pro, Pixel 11 Pro XL, and Pixel 11 Pro Fold on Aug. 12, with prices starting at $899, $1,099, $1,299, and $1,299 respectively, and preorders opening the same day ahead of an Aug. 20…