Computer Vision / Video Analytics

Jun 01, 2023

Neuralangelo by NVIDIA Research Reconstructs 3D Scenes from 2D Videos

A new model generates 3D reconstructions using neural networks, turns 2D video clips into detailed 3D structures — generating lifelike virtual replicas of...

1 MIN READ

May 24, 2023

Design Your Robot on Hardware-in-the-Loop with NVIDIA Jetson

Hardware-in-the-loop (HIL) testing is a powerful tool used to validate and verify the performance of complex systems, including robotics and computer vision....

10 MIN READ

May 15, 2023

How NeRFs Helped Me Re-Imagine the World

Why have images not evolved past two dimensions yet? Why are we satisfied with century-old technology? What if the technology already exists that’s ready to...

10 MIN READ

May 05, 2023

Why Automatic Augmentation Matters

Deep learning models require hundreds of gigabytes of data to generalize well on unseen samples. Data augmentation helps by increasing the variability of...

13 MIN READ

May 04, 2023

Increasing Throughput and Reducing Costs for AI-Based Computer Vision with CV-CUDA

Real-time cloud-scale applications that involve AI-based computer vision are growing rapidly. The use cases include image understanding, content creation,...

11 MIN READ

Title slide for GTC session, A startup's Guide to Success in CEE.

May 03, 2023

A Startup’s Guide to Success in Central and Eastern Europe

Central and Eastern Europe (CEE) is quickly gaining recognition as one of the world’s most important rising technology ecosystems. A highly skilled workforce,...

6 MIN READ

May 01, 2023

Exelon Uses Synthetic Data Generation of Grid Infrastructure to Automate Drone Inspection

Most drone inspections still require a human to manually inspect the video for defects. Training a computer vision model to automate inspection is difficult...

8 MIN READ

Apr 27, 2023

New Reference Applications for Edge AI Developers on HoloHub with NVIDIA Holoscan v0.5

Edge AI applications, whether in airports, cars, military operations, or hospitals, rely on high-powered sensor streaming applications that enable real-time...

10 MIN READ

Apr 25, 2023

End-to-End AI for NVIDIA-Based PCs: ONNX and DirectML

This post is part of a series about optimizing end-to-end AI. While NVIDIA hardware can process the individual operations that constitute a neural network...

14 MIN READ

Workshop promo card with an abstract illustration of a neural network.

Apr 19, 2023

Model Parallelism Virtual Workshop

Learn to build and deploy large neural networks to production with this virtual workshop on May 3 from the NVIDIA Deep Learning Institute.

1 MIN READ

Apr 19, 2023

How to Train a Defect Detection Model Using Synthetic Data with NVIDIA Omniverse Replicator

According to the American Society of Quality (ASQ), defects cost manufacturers nearly 20% of overall sales revenue. The products that we interact with on a...

9 MIN READ

Apr 19, 2023

State-of-the-Art Real-time Multi-Object Trackers with NVIDIA DeepStream SDK 6.2

When you observe something over a period of time, you can find trends or patterns that enable predictions. With predictions, you can, for example, proactively...

9 MIN READ

Apr 13, 2023

Accelerated Motion Processing Brought to Vulkan with the NVIDIA Optical Flow SDK

The NVIDIA Optical Flow Accelerator (NVOFA) is a dedicated hardware unit on newer NVIDIA GPUs for computing optical flow between a pair of images at high...

3 MIN READ

Apr 12, 2023

Metropolis Spotlight: Lumeo Simplifies Vision AI Development

Over a billion cameras are deployed in the most important spaces worldwide and these cameras are critical sources of video and data. It is becoming increasingly...

4 MIN READ

Apr 04, 2023

Topic Modeling and Image Classification with Dataiku and NVIDIA Data Science

The Dataiku platform for everyday AI simplifies deep learning. Use cases are far-reaching, from image classification to object detection and natural language...

11 MIN READ

Mar 29, 2023

Bootstrapping Object Detection Model Training with 3D Synthetic Data

Training AI models requires mountains of data. Acquiring large sets of training data can be difficult, time-consuming, and expensive. Also, the data collected...

12 MIN READ