Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

NVPanoptix3D training for 3D panoptic segmentation v1.0.0

Use this resource to train and deploy a NVPanoptix3D model for 3D scene segmentation with TAO

New

  • 450 downloads
  • 218 likes
  • 226 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install nvpanoptix3d-3d-scene-training

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent prepares the training, evaluation, export and inference specs, with the 2D and 3D checkpoints for staged initialization. You get semantic, instance and panoptic masks in 3D, with occupancy completion.

Mostly picked by

Updated November 2, 2026

Card for the “NVPanoptix3D training for 3D panoptic segmentation” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • references/spec_template_train.yaml: training spec
  • references/spec_template_export.yaml: export spec
  • schemas/manifest.json: manifest schema

Good fit for

  • You want to reconstruct a segmented 3D scene from several views
  • You have 2D and 3D checkpoints to load in stages

Not for

    Tags

    • nvpanoptix3d
    • 3d scene
    • panoptic
    • tao

    About

    You say

    “Prepare the NVPanoptix3D training with my 2D and 3D checkpoints.”

    Card for the “NVPanoptix3D training for 3D panoptic segmentation” skill

    Skill published by nvidia under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to train and deploy a NVPanoptix3D model for 3D scene segmentation with TAO
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.1 KB
    • config/skillspector-baseline.yaml1 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/skill_info.yaml6.5 KB
    • references/spec_template_evaluate.yaml3.8 KB
    • references/spec_template_export.yaml4 KB
    • references/spec_template_inference.yaml3.8 KB
    • references/spec_template_train.yaml3.7 KB
    • schemas/evaluate.schema.json60.2 KB
    • schemas/export.schema.json61.9 KB
    • schemas/inference.schema.json60.7 KB
    • schemas/manifest.json11.1 KB
    • schemas/train.schema.json57.5 KB
    • skill-card.md4.5 KB
    • SKILL.md16.9 KB
    • skill.oms.sig7.1 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-train-nvpanoptix3d
    Licence
    Apache-2.0

    Notice

    « tao-train-nvpanoptix3d » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.