Skip to main content
SearchSearch thousands of GPU-optimized Containers, pretrained Models, SDKs, and Helm charts—ready to accelerate AI, digital twins, and HPC from cloud to edge.
NVIDIA AI Enterprise
NVIDIA AI Enterprise
  • NVIDIA NIM
    NVIDIA NIM
  • NIM Container GPUs
    NIM Container GPUs
  • Use Case
    Use Case
  • NVIDIA Platform
    NVIDIA Platform
  • Industry
    Industry
  • Solution
    Solution
  • Publisher
    Publisher
    15
  • Policy
    Policy
  • Displaying 15 results
    PAIDF Augmentation is an image & video augmentation pipeline that leverages NVIDIA Cosmos and other generative models to produce photorealistic synthetic video data. It supports multiple augmentation strategies including weather, lighting, and scene transformations for training and validating models in NVIDIA Metropolis applications.
    Container
    PAIDF Auto Labeling is an automated data annotation pipeline that processes raw video data through object detection, multi-object tracking, vision-language model (VLM) classification, and multiple-choice question (MCQ) generation stages. It produces high-quality pseudo-labels for training computer vision models in NVIDIA Metropolis synthetic data generation workflows.
    Container
    PAIDF Simulation provides synthetic data generation and domain registration tooling for PCB Automated Optical Inspection. It leverages NVIDIA Omniverse Replicator to generate photorealistic synthetic PCB images with defect annotations for training and validating defect detection models in manufacturing quality assurance pipelines.
    Container
    Generates visual QA evidence and converts it into structured annotation artifacts.
    Container
    Runs RF-DETR object detection and multi-object tracking.
    Container
    Generates image and video captions for the Auto Labeling pipeline.
    Container
    Assembles person attributes and generates search queries from visual QA results.
    Container
    Generates discriminative referring expressions for known image objects.
    Container
    Extracts groundable expressions from image captions.
    Container
    Adds reasoning traces to existing annotations using captioning, visual QA, and other available scene context.
    Container
    Enhances images and videos before downstream annotation stages.
    Container
    Compiles and launches Dockerized Auto Labeling service workflows.
    Container
    Uses SAM3 to ground image expressions into bounding boxes and masks.
    Container
    Runs SAM3 text-prompted object detection and tracking.
    Container
    Exports completed scene annotations to supported training formats.
    Container