Computer Vision news and analysis on Web Pulse: 1699 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
NVIDIA released LocateAnything-3B, a vision-language model designed for visual grounding that can identify and locate objects in complex scenes using natural language queries. The 3-billion-parameter model, trained on 7 …
LogicTronix and Sundance have developed a real-time event-based vision application on the Sundance VCS3 MPSoC platform, integrating a Prophesee IMX636 event sensor and a Vitis AI machine learning model. The compact syste…
OpenAI is preparing upgraded controls for its Codex AI assistant that would allow it to operate Microsoft Excel and PowerPoint through dedicated add-in layers, rather than generic screen-clicking. The unreleased features…
A developer named carlostkd is inviting users to be the first to test a new Proton Lumo image generation API and provide feedback.
The Samsung 9100 Pro 1TB NVMe SSD has dropped to $206.99 on Amazon, a 39% discount from its $339.99 list price, matching its lowest price since the start of the year. The PCIe 5.0 drive offers sequential read speeds up t…
The New South Wales government will invest an additional A$34 million in shark-surveillance measures, expanding drone patrols to about 70 beaches with year-round coverage and trialling two AI detection systems over summe…
A developer created a guide to identify AI-generated maps, highlighting common artifacts such as distorted coastlines, mislabeled landmarks, and unnatural color gradients. The guide aims to help users distinguish between…
A developer created Foveon, a Mac app that uses a modified U-Net deep learning model to transform photos from any Bayer-array camera into the distinctive look of a Sigma DP2 Merrill Foveon X3 sensor, known for its stacke…
A developer built an AI commentator that watches live World Cup streams, analyzes frames in real time, and generates play-by-play commentary, demonstrated on the 2022 final.
Khronos Group presented an open standards roadmap at SIGGRAPH ASIA 2025 in Hong Kong, December 15-18, covering cross-platform ML inferencing acceleration, glTF Gaussian Splats, and OpenXR Spatial Entities. The Machine Le…
ByteDance's Seed research team released Seedance 2.5, a video generation model that produces 30-second clips in 4K resolution with support for 50 multimodal references, addressing key limitations in AI video production s…
Bytedance Seedance V1.5 Pro Image To Video defeated Luma Ray 3.2 Image to Video 15.8 to 15.3 in a head-to-head test of two AI video generation models. Seedance won because it more reliably followed exacting prompts for s…
Florida International University researchers developed JaiLIP, a technique using subtle image modifications to bypass AI safety guardrails in vision-language models like BLIP-2, nearly doubling harmful outputs. The attac…
A developer launched a webcam motion detector that offers local and cloud storage with AI-powered person detection, starting at $10/month for premium features.
A developer built an artist attribution system using PyTorch and a pretrained ResNet-50 model. The system classifies paintings by artist with top-3 predictions, leveraging transfer learning for efficient training. The pr…
Luma Uni-1 Text to Image defeated Bagel 26.3 to 15.7 in a head-to-head comparison of text-to-image models, demonstrating superior instruction following in spatial relationships, perspective, and legible text generation a…
Researchers have used artificial intelligence and advanced imaging to decipher a carbonized scroll buried by the eruption of Mount Vesuvius in 79 AD, recovering all surviving text from a single scroll for the first time.…
Synaptics and Google Research debuted the Coralboard edge AI development platform at Google I/O 2026, featuring the Astra SL2610/SL2619 SoC family and integrated NPUs. The platform supports on-device models like Gemma 3 …
A developer describes a technique to eliminate flicker when applying diffusion-based restyling to video frames. The approach stylizes only a sparse set of keyframes and uses optical flow to warp those stylized frames to …
Photon Matrix Lab, a Chinese startup, raised US$2.7 million on Indiegogo for its AI-powered laser mosquito zapper, far exceeding its US$20,000 goal. The device uses AI vision and lidar to detect and kill mosquitoes mid-f…