Data & Analysis ✓ NVIDIA · Official panoptic-3dscene-reconstructionsemantic-segmentationoccupancy-completiontao-toolkitautomldocker

TAO NVPanoptix3D

Train and run 3D panoptic reconstruction with occupancy completion from posed RGB images.

FollowSkills review · FSRS-2.0
Not recommended
49/ 100 5-point scale 2.5 / 5
Trust14 / 25 · 2.8/5

The documentation defines Docker, NVIDIA Container Toolkit, dataset files, checkpoints, result directories, and excludes inputs/ from uploads. However, Bash is allowed, Weights & Biases is enabled by default, and training/evaluation/export create external effects without explicit confirmation, sensitive-data guidance, rollback, or complete data-flow disclosure, so points are deducted.

Reliability8 / 20 · 2.0/5

Commands, parameters, dataset requirements, and several failure patterns are concrete. Reliability is reduced by contradictions: fsdp is listed as an option but later declared unsupported, templates default to val_loss while the policy requires train_loss, and fp16 remains advertised although training rejects it. Nothing was executed, so the score stays within static-review limits.

Adaptability8 / 15 · 2.7/5

Trigger phrases, dataset formats, action scenarios, and hardware requirements are reasonably clear. Non-fit boundaries, minimum viable resources, Chinese-language support, and mainland-China network reachability are not documented; the high-end multi-GPU requirement also narrows applicability, so points are deducted.

Convention9 / 15 · 3.0/5

The skill includes metadata, structured sections, parameter tables, troubleshooting, a version, Apache-2.0 licensing, and an NVIDIA author. It lacks dedicated Instructions, Examples, FAQs, a changelog, explicit maintenance ownership, and a compatibility matrix; the benchmark also reports structural and author-format findings, so points are deducted.

Effectiveness6 / 15 · 2.0/5

The documentation covers data preparation, training, evaluation, inference, and 2D ONNX export, with reusable spec_overrides examples. The benchmark records strong Codex correctness and effectiveness for one positive task, but the sample is tiny, execution was not independently verified, and the documented export path does not produce a 3D ONNX artifact, so points are deducted.

Verifiability4 / 10 · 2.0/5

Committed benchmark material, evals.json, schemas, templates, and concrete error notes provide limited auditability. Evidence is limited to one evaluation task, with no independent reproduction or committed test suite covering key execution paths; conclusions therefore rely substantially on repository claims, so points are deducted.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • Training policy, templates, and architecture notes conflict on train_loss versus val_loss, fp16 versus fp32, and FSDP versus ddp; validate against the actual entrypoint and packaged schemas before use.
  • Weights & Biases is enabled by default, but the documentation does not explain whether data, logs, or code are sent externally; confirm or disable that flow before processing sensitive data.
  • The stated requirement is at least two GPUs with roughly 40GB or more VRAM per GPU; usability on lower-resource systems and through mainland-China networks is not established.
  • This was a static review with no command execution; the benchmark contains only one positive task and does not establish real correctness of training, evaluation, inference, or export artifacts.
See the full review method →

What does this skill do, and when should you use it?

This skill supports NVIDIA TAO workflows for NVPanoptix3D, which reconstructs 3D scenes from posed RGB images. It covers training, evaluation, inference, and export, producing semantic, instance, and panoptic 3D segmentation with occupancy completion. The model uses a VGGT backbone, a Mask2Former-style head, and 3D frustum reconstruction. Docker, nvidia-container-toolkit, and at least two GPUs are required.

Reads packaged TAO Core schemas, training templates, and model metadata; constructs the required dataset paths for frustum_mask.npz, colormap.json, and train.json, val.json, and test.json; routes enabled training runs through tao-run-automl by default, optimizing train_loss in the minimize direction; supports direct training when AutoML is disabled or its packaged schema/template is unavailable; handles separate 2D and 3D stage checkpoints; runs the NVPanoptix3D Python module for train, evaluate, inference, and export actions; produces semantic, instance, or panoptic predictions and exports the 2D model component to ONNX.

  1. TAO users training a 3D panoptic scene segmentation model on Front3D or Matterport data.
  2. Researchers evaluating an NVPanoptix3D checkpoint and reviewing PRQ, RSQ, and RRQ status metrics.
  3. Engineers running semantic, instance, or panoptic inference on a flat directory of JPG or PNG RGB images.
  4. Model developers using AutoML to optimize training configurations against train_loss.
  5. Users exporting a trained model's 2D ONNX component for downstream deployment preparation.

What are this skill's strengths and limitations?

Pros
  • Covers training, evaluation, inference, and export workflows.
  • Provides concrete rules for dataset files, checkpoint handoff, AutoML metrics, and common failure modes.
  • Supports Front3D, Matterport, and listed synthetic dataset configurations.
  • Supports semantic, instance, and panoptic inference modes.
Limitations
  • Requires a minimum of two GPUs, with four recommended and 40GB or more VRAM per GPU suggested.
  • The current training entrypoint supports fp32 only; fp16 is rejected.
  • The current export entrypoint produces only a 2D ONNX file, not a 3D ONNX file.
  • Inference scans only top-level JPG and PNG files in a flat image directory.
  • The supplied material does not document pricing, hosted operation, or standalone performance benchmarks.

How do you install this skill?

Install the individual skill with the NVIDIA skills CLI:

npx skills add nvidia/skills --skill tao-train-nvpanoptix3d --yes

The README does not document a separate standalone package or source repository for this skill. The runtime also requires Docker and nvidia-container-toolkit.

How do you use this skill?

After installation, ask a compatible agent for a concrete task such as "train NVPanoptix3D", "run panoptic 3D reconstruction", or "evaluate this NVPanoptix3D checkpoint". Training, evaluation, and inference require the relevant dataset paths and metadata files; use downsample_factor=2 for Matterport and 1 for Front3D and synthetic datasets. The documented direct module form is:

python -m nvidia_tao_pytorch.cv.nvpanoptix3d.entrypoint.nvpanoptix3d <action> -e <spec>

AutoML is enabled by default for training. Set automl_policy to off for a direct-training run.

FAQ

Which datasets are supported?
Training uses the nvpanoptix3d dataset type and supports front3d and matterport formats. The parameter section also lists synthetic_hospital and synthetic_warehouse as dataset.name options.
Is AutoML mandatory for training?
AutoML is enabled at the model layer and is the default route, using train_loss with minimize direction. Set automl_policy to off to use direct model training for that run.
Why does fp16 training fail?
Although the schema advertises fp16, the current training entrypoint raises a ValueError because only fp32 is supported. Use train.precision=fp32 for training and resume training.
Why is there no 3D ONNX output after export?
The current export entrypoint calls only the 2D ONNX exporter and writes export.onnx_file_2d. The skill therefore does not require export.onnx_file_3d.

More skills from this repository

All from NVIDIA/skills

Data & Analysis ✓ NVIDIA · Official

TAO SegFormer Semantic Segmentation

Guidance for training, evaluating, exporting, and deploying TAO SegFormer models.

Data & Analysis ✓ NVIDIA · Official

TAO Standard Training Workflow

Run a controlled TAO train, evaluate, and export workflow on labeled data.

Data & Analysis ✓ NVIDIA · Official

TAO OneFormer Universal Segmentation

Train and deploy one task-conditioned model for panoptic, instance, and semantic image segmentation.

Data & Analysis ✓ NVIDIA · Official

TAO FoundationStereo Stereo Depth

Generate disparity maps from stereo images and manage FoundationStereo training, evaluation, and deployment for 3D reconstruction.

Dev & Engineering ✓ NVIDIA · Official

TAO Sparse4D Training Skill

Guides agents through training, evaluation, export, quantization, and inference for multi-camera temporal 3D detection and tracking.

Data & Analysis ✓ NVIDIA · Official

TAO MAL Weakly Supervised Segmentation

Train segmentation models from point or box annotations and produce masks with minimal labeling.

Data & Analysis ✓ NVIDIA · Official

TAO BEVFusion Training

Train, evaluate, and run inference on BEV 3D detection models that fuse LiDAR and camera data with TAO.

Data & Analysis ✓ NVIDIA · Official

TAO Visual ChangeNet Inspection

Train paired-image classifiers and change-segmentation models for PCB defect inspection.

Data & Analysis ✓ NVIDIA · Official

TAO Video Action Recognition

Train, evaluate, export, and run inference for RGB, optical-flow, and multi-stream video action models with NVIDIA TAO.

Data & Analysis ✓ NVIDIA · Official

TAO DINO Object Detection

Run NVIDIA TAO workflows for training and deploying DINO 2D object detectors.

Data & Analysis ✓ NVIDIA · Official

TAO Grounding DINO Open-Vocabulary Detection

Train and deploy text-guided object detectors without a fixed class vocabulary.

Data & Analysis ✓ NVIDIA · Official

TAO FastFoundationStereo Real-Time Stereo Depth

Run TAO FastFoundationStereo workflows that produce low-latency disparity maps from stereo images.

Automation & Ops ✓ NVIDIA · Official

TAO on Brev GPU Instances

Run and manage TAO training, evaluation, and inference on Brev GPU instances.

Data & Analysis ✓ NVIDIA · Official

TAO CenterPose Pose Estimation Skill

Guides agents through training, evaluation, export, and deployment of CenterPose models for 6-DoF object pose estimation.

Data & Analysis ✓ NVIDIA · Official

TAO Person Re-Identification

Train and deploy TAO ReID models for cross-camera person matching.

Dev & Engineering ✓ NVIDIA · Official

TAO Skill Bank Capability Discovery

Query TAO Skill Bank workflows, models, platforms, and AutoML support from packaged manifests.

Automation & Ops ✓ NVIDIA · Official

TAO Local Docker Runner

Run TAO jobs on a local or remote single-node Docker host with NVIDIA GPU support.

Data & Analysis ✓ NVIDIA · Official

TAO Optical Inspection Training

Train and deploy Siamese-network models for manufacturing defect inspection.

Data & Analysis ✓ NVIDIA · Official

TAO Video Reasoning Annotation Pipeline

Convert raw videos into chain-of-thought training data.

Data & Analysis ✓ NVIDIA · Official

TAO RT-DETR Object Detection

Guides NVIDIA TAO workflows for training and deploying real-time RT-DETR detectors.

Related skills