News

This project controls a Universal Robots UR5 using real-time face tracking built with OpenCV. A standard webcam provides a live video stream that detects a human face, computes its position

Simultaneous Localization & Mapping (SLAM) is one of the most active and contentious areas of CV & robotics. Should you use purely visual SLAM? Do you need LiDAR? What about

This year the Low-Power Computer Vision Challenge (LPCV) has three tracks with serious prize money including Image-to-Text Retrieval, Action Recognition in Video and AI Generated Images Detection. Each track has

In this blog, we explore Visual Place Recognition (VPR) with hands-on examples using OpenCV and lightweight Python tools. You will create a practical VPR pipeline that includes visual descriptor extraction,
Explore the elegant intersection of nature-inspired algorithms and computer vision. This comprehensive technical guide unveils the powerful watershed segmentation technique, demonstrating how a simple topographic analogy translates into sophisticated image
In this blog post, we'll tackle this challenge head-on with a practical approach to shadow correction using OpenCV. Our method leverages Multi-Scale Retinex (MSR) for illumination normalization, combined with adaptive
This blog explores how to build a smart, browser-based document scanner using OpenCV.js and live OCR. It covers document detection, perspective correction, interactive preprocessing, and client-side text extraction—all running entirely
Explore OpenCV G-API and how it transforms image-processing pipelines from imperative to declarative with graph-based execution.

EgoX introduces a novel framework for translating third-person (exocentric) videos into realistic first-person (egocentric) videos using only a single input video. The work tackles a highly challenging problem of extreme

Underwater images often suffer from color loss, low contrast, and haze due to light absorption and scattering. This blog presents a multi-stage OpenCV pipeline in Python to enhance underwater images

Omni-Attribute introduces a new paradigm for fine-grained visual concept personalization, solving a long-standing problem in image generation: how to transfer only the desired attribute (identity, hairstyle, lighting, style, etc.) without

We capture the world with cameras that compress depth, texture, and geometry into flat pixel grids, yet our minds effortlessly reconstruct the 3D structure behind them. What if computers could