OpenCV Live
OpenCV Live is the audio-only version of the official livestream from the OpenCV project. Hosted by OpenCV CEO Dr. Satya Mallick and co-host Phil Nelson, the show features guests from the computer vision and AI community. Episodes cover the latest technology trends, practical insights, and live audience Q&A. OpenCV itself is the world's largest computer vision library, offering over 2,500 algorithms and continuously developed since 2000.
Episodes
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
Join Jason Ren of Ai2 (Allen Institute for AI) for MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction, a live look at how open multimodal models move past describing a scene to predicting where things go next. Building on the Molmo family's pointing and tracking capabilities, MolmoMotion takes a plain-language instruction and forecasts point trajectories through 3D space,
Transforming Air Cargo Operations: Optimizing with Vision & Robotics
Air cargo still runs on estimates — dimensions eyeballed at acceptance, and containers packed by "feel." Suraj Nair, founder of Singapore-based Speedcargo, joins OpenCV Live to show how 3D computer vision, optimization algorithms, and gantry robotics replace that guesswork with measured cargo data. He'll cover what it takes to get perception working reliably in a live cargo terminal, and where the
A Software Engineer's Guide to Scaling Robotics
One robot is a demo; a hundred robots is an operations problem. Civ Robotics CTO Amit Moran walks through the software practices that keep a distributed rover fleet alive in the field — pinned builds, heartbeats on everything, remote restarts, and the mission data that saves you after the fact. OpenCV is a 501(c)(3) registered non-profit in the United States. See how you can support open source CV
Building the Next Generation of Synthetic Media
Join us this week for a presentation titled "Building the Next Generation of Synthetic Media," where Victor Erukhimov shows us how generative AI is reshaping the way digital humans and video content are created. The talk covers two products built by the team: Avatar SDK, a toolkit for generating photorealistic 3D avatars, and CraftStory, their GenAI-driven storytelling product. Viewers will learn
Rethinking Drone Autonomy in GPS-Denied Environments - OpenCV Live 217
Autonomous drones only fly as well as they can figure out where they are. Drop one into a forest, a dense city, or a disaster zone, and that gets a lot harder — the signals they normally lean on just aren't there. This week we get into HUNT, a navigation approach built for exactly the places where the usual answers fall apart. OpenCV is a 501(c)(3) registered non-profit in the United States. See
Adaptive Human-AI Collaboration with Mixed Reality
Our guest this week is Alireza Taheritajar, a Ph.D. Student an Augusta University focusing on In-Situ Intelligent Mixed Reality Assistants for Adaptive Human-AI Collaboration. Mixed-reality overlays have been around for awhile, but with the recent upgrades in camera quality, lens resolution, and processing power they are becoming more useful than ever. Join us for a look at some very cool research
COOL: The Official Cloud Version of OpenCV
Cloud Optimized OpenCV Library (COOL) delivers a high-performance build of OpenCV, enabling faster computation of core computer vision operations such as resize, adaptive gaussian, contour detection functions. This optimized edition is designed for accelerated computer vision workloads on AWS Graviton and ARM-based environments, helping developers achieve improved efficiency for AI, ML, and image
OpenCV Community Spotlight August 2025
On this week's episode we turn the focus to the worldwide community of creators and hobbyists that make awesome OpenCV stuff. We'll take a look at some recent projects posted to Hackster.io, and have a short presentation from an OpenCV community member about their project. Got a cool project of your own? Send it to us and you may be featured https://www.jotform.com/form/233105358823151 Become a pa
Granite Vision: Lightweight, Enterprise-grade Large Vision-Language Models
In this talk, Pengyuan Li will present the team's efforts in building the Granite Vision model—a lightweight, large vision-language model specifically designed to excel in enterprise use cases, particularly in visual document understanding. Compared to other models of similar parameter size, Granite Vision achieves state-of-the-art performance on established benchmarks for visual document understa
Keras 3: Train your JAX models with `model.fit(...)`
We welcome Monica Song (Product Manager, Google AI Frameworks) to the show for a technical talk this week: How to train your JAX models with `model.fit(...)` for use with the latest version of the deep learning framework Keras (3.X). A version of this talk was presented at OpenCV's first conference, OSCCA, earlier this year and we look forward to sharing it with the broader OpenCV community. OpenC
Vision Language Models: Understanding CLIP
Vision Language Models are one of the most important concepts for understanding modern AI workflows, and on this episode we'll take a look at Contrastive Language-Image Pre-training (CLIP), released in 2021 by OpenAI. Wikipedia: "CLIP is a technique for training a pair of neural network models, one for image understanding and one for text understanding, using a contrastive objective." It's also a
Pysimverse, A Python Drone Programming Simulator with Murtaza Hassan
Murtaza Hassan is a prolific online educator, maker, and Youtuber, with his channel attracting over 430,000 subscribers and featuring courses, projects, and more. Murtaza returns to OpenCV Live in this episode to show off a new project of particular interest to the CV and AI community- Pysimverse, a powerful Python drone programming simulator. Tune in to see how it works, and how you can get acces
The Winners of the Perception Challenge for Bin-Picking
At CVPR 2025 in Nashville we announced the grand prize winners of the Perception Challenge for Bin-Picking during our workshop on Perception for Industrial Robotics Applications. It was a tight competition, but in the end one team stood above the others. OpenCV is a 501(c)(3) registered non-profit in the United States. See how you can support open source CV & AI: http://opencv.org/support/ Join t
Recommended
Bad Friends
The Swerve Podcast: Obscure Topics | Conspiracy Theories
The Bread and Banter Podcast
The Church of What's Happening Now: The New Testament
Deadline: White House
English Vocabulary Help
این نقطه
Solved Murders - True Crime Stories
紐約鳥｜New York Aperture
Doctor Zhivago Slow Read
Apple News In Conversation
The Young and Called Podcast .
