Computer Vision

A new tutorial from the open-source GeoAI project demonstrates a complete workflow for extracting building footprints from NAIP aerial imagery using U-Net with a ResNet-34 encoder, Grounding DINO, SAM, and Mask R-CNN. Th…

Developer Simon Willison released 'eyes', a free, open-source Python tool that gives terminal AI agents live vision by streaming phone camera frames as JPEGs to a local folder, with no cloud storage or third-party relay …

A developer who built an AI interior design tool found that generating images is the easy part, while making results feel realistic and addressing user needs is harder. The project, ZyoraAI, revealed that users seek quic…

A developer is building SoulFix, an AI image editor that uses a CNN-RNN architecture to interpret user intent from scribbles, and Friday, a self-aware assistant with sentiment analysis and entity recognition. The develop…

PixLog, an open-source tool by developer Zhao Xuan, adds pixel-aware visual history to Git without creating a second commit graph or staging area. It tracks exact bytes, changed regions, coordinate blame, and generation …

Adima AI has launched Adima AI Image Upscaler Pro, a Windows application that uses AI to upscale images up to 16K resolution and 16× magnification, with offline processing and support for batch upscaling. The tool offers…

NXP Semiconductors is in talks to acquire Ambarella, a Santa Clara chip designer specializing in low-power AI processors for camera systems in cars, security devices, and robots, according to the Financial Times. Ambarel…

Hanyu (Olivia) Yu, a high school sophomore, is seeking an arXiv endorser in cs.LG or cs.CV for her independent preprint on Vision Transformer Mixture of Experts (MoE) routing. Her paper proposes using three scalar signal…

HarKro753 released clone, a Claude Code plugin and Chrome extension that captures a live website's screenshot, DOM, and computed styles, then rebuilds it as HTML or React (shadcn/ui) components, verifying the clone pixel…

Researchers at Princeton University, led by Professor Ken Norman, have developed a system that reconstructs images from brain activity measured by fMRI in real time, producing reconstructions about 15 seconds after viewi…

Uber's computer vision team, led by Soumya Gupta and Jai Chopra, presented a closed-loop system to keep multimodal agents sharp in production, addressing the challenge of AI slop in food photos on Uber Eats. The system u…

Applied Electrodynamics, a Y Combinator S26 startup, unveiled WaveSight, a camera that uses radio frequencies to see through walls and opaque materials, targeting construction, industrial inspection, and security use cas…

Emergent Ventures India announced its 18th cohort of grants, awarding funding to 16 individuals and teams including 14-year-old Adithyan Madhu for computational linguistics research on the Indus Valley script, 17-year-ol…

NXP Semiconductors is in talks to acquire Ambarella, the edge AI chip specialist behind vision processors for automotive cameras and self-driving systems, in a deal that could value Ambarella at roughly $3.3 billion. The…

Roboflow published a tutorial on automating powder-coat defect detection using its RF-DETR vision model, which achieved 74.0% mAP@50 on a dataset of 2,775 images, and Gemini 2.5 Pro to generate inspection summaries. The …

An engineer at PreserveMy.World built a CPU-only Structure-from-Motion pipeline using COLMAP to reconstruct the Moorcroft Pavilion at Shalimar Gardens, Lahore. By curating 15 tightly-overlapping images instead of 43 gene…

Anduril Industries, a defense technology company, is hiring a Research Scientist in Fort Collins, Colorado, with a salary range of $165,000 to $218,000 per year. The role requires an M.S. or Ph.D. in a related field and …

LingBot-Map, an open-source streaming 3D reconstruction pipeline, enables GPU-aware inference and point cloud export through a tutorial that auto-tunes frame limits, camera iterations, scale frames, and KV-cache paramete…

A developer runs a YouTube channel where an AI agent autonomously creates and publishes videos, but only after passing a quality gate of 21 automated checks. The gate evolved from 15 checks, each added after a real failu…

A developer's guide explores how AI agents can navigate modern web applications that use Shadow DOM, HTML5 Canvas, and nested iFrames, which break traditional automation methods. The article explains the architectural en…