physical-ai-neural-reconstruction

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Physical AI Neural Reconstruction (NuRec) Router

Physical AI神经重建（NuRec）路由工具

Purpose

用途

This is a thin router for NVIDIA Neural Reconstruction (NuRec) requests. It points at the upstream

nurec-index

skill at

https://github.com/NVIDIA/nurec-skills

and its five sibling skills (

physical-ai-datasets

ncore

nre

asset-harvester

nurec-fixer

). Use this skill to:

Identify which upstream sibling skill answers a NuRec question.
Locate, clone, or refresh the canonical
```
nurec-skills
```
checkout.
Order multi-step NuRec workflows (data → conversion → train → render → cleanup) before opening the upstream recipe.

The canonical recipes (training, rendering, data conversion, dataset downloads, object harvesting, frame cleanup) live in the upstream sibling skills. Never copy or reconstruct their commands here.

Do NOT use this skill for:

SimReady packaging of CAD or source meshes → use
```
omniverse-cad-to-simready
```
.
Generic USD performance tuning unrelated to NuRec → use
```
omniverse-usd-performance-tuning
```
.
AKS / OSMO / NIM Operator infrastructure setup → use
```
physical-ai-infrastructure-setup-and-resilient-scaling
```
.

这是一款用于NVIDIA神经重建（NuRec）请求的轻量路由工具。它指向位于

https://github.com/NVIDIA/nurec-skills

的上游

nurec-index

技能及其五个关联技能（

physical-ai-datasets

、

ncore

、

nre

、

asset-harvester

、

nurec-fixer

）。使用本技能可实现以下操作：

确定哪个上游关联技能可解答NuRec相关问题。
定位、克隆或更新
```
nurec-skills
```
的标准代码克隆版本。
在调用上游流程前，编排多步骤NuRec工作流（数据→转换→训练→渲染→清理）。

标准流程（训练、渲染、数据转换、数据集下载、对象提取、帧清理）均存于上游关联技能中。请勿在此处复制或重构这些技能的命令。

请勿将本技能用于以下场景：

CAD或源网格的SimReady打包 → 请使用
```
omniverse-cad-to-simready
```
。
与NuRec无关的通用USD性能调优 → 请使用
```
omniverse-usd-performance-tuning
```
。
AKS / OSMO / NIM Operator基础设施搭建 → 请使用
```
physical-ai-infrastructure-setup-and-resilient-scaling
```
。

When to Use

使用时机

Read this skill first whenever a user mentions any of:

nurec

nurec router

nurec index

neural reconstruction

neural reconstruction engine

NRE

3DGUT

3DGRT

USDZ

NCore V4

sensor sim

novel view synthesis

PhysicalAI-Autonomous-Vehicles-NuRec

PhysicalAI-NuRec-PPISP

Cosmos-Drive-Dreams

asset harvester

nurec fixer

DiffusionHarmonizer

harmonizer

difix

difix3d

serve-grpc

render-grpc

warm serve-grpc

nre thin client

batch_render_rgb

nurec teardown

, "where do I start with NuRec", "which NuRec skill should I use for X?".

Decide which upstream sibling skill answers the question, fetch it (see Locate and fetch the upstream skills), then follow that skill's body.

当用户提及以下任一内容时，请首先查阅本技能：

nurec

、

nurec router

、

nurec index

、

neural reconstruction

、

neural reconstruction engine

、

NRE

、

3DGUT

、

3DGRT

、

USDZ

、

NCore V4

、

sensor sim

、

novel view synthesis

、

PhysicalAI-Autonomous-Vehicles-NuRec

、

PhysicalAI-NuRec-PPISP

、

Cosmos-Drive-Dreams

、

asset harvester

、

nurec fixer

、

DiffusionHarmonizer

、

harmonizer

、

difix

、

difix3d

、

serve-grpc

、

render-grpc

、

warm serve-grpc

、

nre thin client

、

batch_render_rgb

、

nurec teardown

、“我该从哪里开始使用NuRec？”、“针对X场景我应该使用哪个NuRec技能？”。

确定哪个上游关联技能可解答问题后，获取该技能（参见定位并获取上游技能），然后遵循该技能的操作说明。

Prerequisites

前置条件

Router skill itself has no runtime prerequisites beyond

git

for fetching the upstream. Downstream sibling skills require:

Docker + NVIDIA Container Toolkit + GPU — for

nre

nre-tools

, and

nurec-fixer

containers (

nvcr.io/nvidia/nre/nre

nvcr.io/nvidia/nre/nre-tools

nvcr.io/nvidia/cosmos/cosmos-predict2-container:1.2

NGC API key (
```
NGC_API_KEY
```
) — for pulling NGC containers.
Hugging Face token (
```
HF_TOKEN
```
) with the
```
nvidia/PhysicalAI-*
```
,
```
nvidia/DiffusionHarmonizer
```
, and
```
nvidia/asset-harvester
```
gated licenses accepted in advance on Hugging Face.
Python 3.10+ with
```
huggingface_hub
```
installed.
(Optional) CARLA, Isaac Sim 5.1, or AlpaSim for simulator integration over
```
serve-grpc
```
.

Verify secrets safely (do not echo values):

bash

hf auth whoami
[ -n "${HF_TOKEN:-}" ]      && echo "HF_TOKEN length=${#HF_TOKEN}"      || echo "HF_TOKEN unset"
[ -n "${NGC_API_KEY:-}" ]   && echo "NGC_API_KEY length=${#NGC_API_KEY}" || echo "NGC_API_KEY unset"

See

references/secrets-handling.md

for the bash anti-patterns to avoid.

路由工具本身除了用于获取上游代码的

git

外，无其他运行时前置条件。下游关联技能需要满足以下条件：

Docker + NVIDIA Container Toolkit + GPU — 用于

nre

、

nre-tools

和

nurec-fixer

容器（

nvcr.io/nvidia/nre/nre

、

nvcr.io/nvidia/nre/nre-tools

、

nvcr.io/nvidia/cosmos/cosmos-predict2-container:1.2

）。

NGC API密钥（
```
NGC_API_KEY
```
） — 用于拉取NGC容器。
Hugging Face令牌（
```
HF_TOKEN
```
），且已提前在Hugging Face上接受
```
nvidia/PhysicalAI-*
```
、
```
nvidia/DiffusionHarmonizer
```
和
```
nvidia/asset-harvester
```
的 gated许可。
Python 3.10+，并已安装
```
huggingface_hub
```
。
（可选） CARLA、Isaac Sim 5.1或AlpaSim，用于通过
```
serve-grpc
```
进行模拟器集成。

安全验证密钥（请勿回显密钥值）：

bash

hf auth whoami
[ -n "${HF_TOKEN:-}" ]      && echo "HF_TOKEN length=${#HF_TOKEN}"      || echo "HF_TOKEN unset"
[ -n "${NGC_API_KEY:-}" ]   && echo "NGC_API_KEY length=${#NGC_API_KEY}" || echo "NGC_API_KEY unset"

有关需避免的bash反模式，请参见

references/secrets-handling.md

。

What is NuRec?

什么是NuRec？

NuRec (NVIDIA Omniverse Neural Reconstruction) takes camera, LiDAR, radar, or stereo recordings — typically from a self-driving car or a robot — and turns them into a 3D scene you can re-render from any viewpoint. Names that come up a lot:

NRE — "Neural Reconstruction Engine". NuRec is the product; NRE is the engine that trains and renders. Both route to the upstream
```
nre
```
skill.
USDZ — the file format of a trained scene. A zip archive that Omniverse, Isaac Sim, and CARLA can open.
NCore V4 — the input format NRE consumes. Raw recordings must be converted to NCore V4 before training.
3DGUT / 3DGRT — the two 3D Gaussian Splatting flavours used internally by NRE. The default Hydra recipe picks one; most users never set it manually.

A typical NuRec project has three stages:

Get the input — convert your own recording to NCore V4 (
```
ncore
```
), or download a pre-converted dataset (
```
physical-ai-datasets
```
).
Train the reconstruction — feed NCore V4 to NRE; out comes a USDZ (
```
nre
```
).
Render new views — render images, videos, or LiDAR sweeps from the USDZ (
```
nre
```
).

Projects that just want to use an existing NVIDIA-published scene skip step 2.

NuRec（NVIDIA Omniverse神经重建）可将来自自动驾驶汽车或机器人的摄像头、激光雷达、雷达或立体影像记录转换为可从任意视角重新渲染的3D场景。以下是常见相关术语：

NRE — “神经重建引擎”。NuRec是产品名称；NRE是用于训练和渲染的引擎。两者均指向上游
```
nre
```
技能。
USDZ — 训练完成场景的文件格式。一种可被Omniverse、Isaac Sim和CARLA打开的压缩归档文件。
NCore V4 — NRE接受的输入格式。原始记录必须先转换为NCore V4格式才能进行训练。
3DGUT / 3DGRT — NRE内部使用的两种3D高斯溅射（3D Gaussian Splatting）变体。默认Hydra流程会选择其中一种；大多数用户无需手动设置。

典型的NuRec项目包含三个阶段：

获取输入 — 将自有记录转换为NCore V4格式（
```
ncore
```
），或下载预转换的数据集（
```
physical-ai-datasets
```
）。
训练重建模型 — 将NCore V4数据输入NRE，输出USDZ格式文件（
```
nre
```
）。
渲染新视角 — 从USDZ文件渲染图像、视频或激光雷达扫描结果（
```
nre
```
）。

若仅需使用NVIDIA已发布的现有场景，可跳过步骤2。

Pick a skill

选择合适的技能

Match the user's goal in the left column and open the named upstream skill on the right. Arrows mean "do these in order".

I want to…	Upstream skill
Find or download a NuRec dataset NVIDIA has published	`physical-ai-datasets`
Convert my own camera / LiDAR / radar / depth / stereo recording into NCore V4	`ncore`
Write a new converter for an unsupported sensor setup (drone, RGB-D, ROS 2 bag, COLMAP, ScanNet++)	`ncore`
Train a 3D reconstruction from an NCore clip	`ncore` → `nre`
Generate the extra inputs NRE needs (segmentation masks, depth, ego mask)	`nre` (uses the `nre-tools` container)
Render a USDZ along the original camera positions	`nre`
Render at full resolution / highest quality	`nre` (see "Quality presets")
Render along a shifted trajectory (e.g. car moved 3 m left)	`nre`
Render through a server so CARLA / Isaac Sim / AlpaSim / a custom simulator can ask for frames	`nre` ( `serve-grpc` )
Render the same USDZ many times back-to-back from Python with minimal per-call latency	`nre` (warm `serve-grpc` + thin Python client / `batch_render_rgb` )
Render LiDAR sweeps (point clouds) from a USDZ	`nre` ( `render-grpc --lidar` )
Skip training and just render a NuRec scene NVIDIA already built	`physical-ai-datasets` → `nre`
Extract individual 3D objects (cars, pedestrians) from a driving clip	`asset-harvester`
Add, remove, or replace cars / pedestrians in a NuRec scene	`asset-harvester` → `nre`
Clean up or harmonize rendered frames (ghosting, floaters, flicker, lighting/shadows)	`nurec-fixer` , or `--enable-difix` inside `nre` for inline rendering
Export the scene as a PLY, mesh, depth maps, ego mask, etc.	`nre`
Upgrade an old USDZ so newer NRE versions load it faster	`nre` ( `upgrade-artifact` )
Open a USDZ or PLY in a browser viewer	`nre` ( `viewer` / `ply_viewer` )
Measure rendering quality (PSNR, SSIM, LPIPS) against ground truth	`nre` ( `eval-rendering-metrics` )
Benchmark different reconstruction methods on the same scenes	`physical-ai-datasets` ( `PhysicalAI-NuRec-PPISP` ) → `nre`
Train on multiple GPUs or on SLURM	`nre` (Workflow D)

将用户目标与左列匹配，然后打开右列指定的上游技能。箭头表示“按顺序执行这些步骤”。

我想…	上游技能
查找或下载NVIDIA发布的NuRec数据集	`physical-ai-datasets`
将自有摄像头/激光雷达/雷达/深度/立体影像记录转换为NCore V4格式	`ncore`
为不支持的传感器设置（无人机、RGB-D、ROS 2 bag、COLMAP、ScanNet++）编写新的转换器	`ncore`
从NCore片段训练3D重建模型	`ncore` → `nre`
生成NRE所需的额外输入（分割掩码、深度图、 ego mask）	`nre` （使用 `nre-tools` 容器）
沿原始摄像头位置渲染USDZ文件	`nre`
以全分辨率/最高质量渲染	`nre` （参见“质量预设”）
沿偏移轨迹渲染（例如车辆向左移动3米）	`nre`
通过服务器渲染，以便CARLA/Isaac Sim/AlpaSim/自定义模拟器请求帧数据	`nre` （ `serve-grpc` ）
通过Python多次连续渲染同一USDZ文件，将每次调用的延迟降至最低	`nre` （预热 `serve-grpc` + 轻量Python客户端 / `batch_render_rgb` ）
从USDZ文件渲染激光雷达扫描结果（点云）	`nre` （ `render-grpc --lidar` ）
跳过训练，直接渲染NVIDIA已构建的NuRec场景	`physical-ai-datasets` → `nre`
从驾驶片段中提取单个3D对象（汽车、行人）	`asset-harvester`
在NuRec场景中添加、移除或替换汽车/行人	`asset-harvester` → `nre`
清理或协调渲染帧（重影、漂浮物、闪烁、光照/阴影问题）	`nurec-fixer` ，或在 `nre` 中使用 `--enable-difix` 进行内联渲染
将场景导出为PLY、网格、深度图、ego mask等格式	`nre`
升级旧版USDZ文件，使其在新版NRE中加载更快	`nre` （ `upgrade-artifact` ）
在浏览器查看器中打开USDZ或PLY文件	`nre` （ `viewer` / `ply_viewer` ）
对照真实数据衡量渲染质量（PSNR、SSIM、LPIPS）	`nre` （ `eval-rendering-metrics` ）
在同一场景上对比不同重建方法的性能	`physical-ai-datasets` （ `PhysicalAI-NuRec-PPISP` ） → `nre`
在多GPU或SLURM集群上训练	`nre` （工作流D）

Common workflows

常见工作流

Six end-to-end workflows are documented in

references/workflows.md

A. Make a NuRec scene from your own recording.
B. Use a NuRec scene NVIDIA has already trained.
C. Add, remove, or replace 3D objects in a scene.
D. Clean up rendered frames.
E. Benchmark reconstruction quality.
F. Connect NuRec to a simulator.

Open that file when the user's task spans more than one sibling skill.

references/workflows.md

中记录了六种端到端工作流：

A. 从自有记录创建NuRec场景。
B. 使用NVIDIA已训练完成的NuRec场景。
C. 在场景中添加、移除或替换3D对象。
D. 清理渲染帧。
E. 评估重建质量。
F. 将NuRec与模拟器连接。

当用户任务涉及多个关联技能时，请打开该文件。

Sibling skills (upstream)

上游关联技能

Name	Upstream folder	What it does
`physical-ai-datasets`	`.agents/skills/physical-ai-datasets/`	Catalog and download recipes for every NVIDIA Physical AI dataset on Hugging Face (driving, robotics, manipulation, NuRec scenes, benchmarks).
`ncore`	`.agents/skills/ncore/`	Converts any sensor recording to NCore V4 (the format NRE needs). Also covers writing a new converter.
`nre`	`.agents/skills/nre/`	The Neural Reconstruction Engine itself. Trains, renders (locally, via warm `serve-grpc` + thin Python client / `batch_render_rgb` , or to an external simulator), exports meshes / point clouds / depth, edits actors, evaluates quality.
`asset-harvester`	`.agents/skills/asset-harvester/`	Open-source Apache-2.0 pipeline that extracts individual 3D objects from sparse views in a driving clip and saves them as `.ply` Gaussian splats with metadata.
`nurec-fixer`	`.agents/skills/nurec-fixer/`	Standalone NVIDIA DiffusionHarmonizer workflow — public successor to the older Fixer / Difix3D+ recipes — that cleans rendered frames, harmonizes inserted actors, evaluates PSNR/LPIPS, and optionally fine-tunes the model.

For naming overlaps (NRE vs Fixer, ncore vs nre, AV-NuRec vs Cosmos-Drive-Dreams, NuRec vs SimReady) see

references/mix-ups.md

名称	上游文件夹	功能
`physical-ai-datasets`	`.agents/skills/physical-ai-datasets/`	编目并下载Hugging Face上所有NVIDIA Physical AI数据集的流程（驾驶、机器人、操作、NuRec场景、基准测试）。
`ncore`	`.agents/skills/ncore/`	将任意传感器记录转换为NCore V4格式（NRE所需格式）。同时涵盖编写新转换器的内容。
`nre`	`.agents/skills/nre/`	神经重建引擎本身。负责训练、渲染（本地、通过预热 `serve-grpc` +轻量Python客户端/ `batch_render_rgb` 、或输出到外部模拟器）、导出网格/点云/深度图、编辑角色、评估质量。
`asset-harvester`	`.agents/skills/asset-harvester/`	开源Apache-2.0流水线，可从驾驶片段的稀疏视角中提取单个3D对象，并保存为带元数据的 `.ply` 高斯溅射文件。
`nurec-fixer`	`.agents/skills/nurec-fixer/`	独立的NVIDIA DiffusionHarmonizer工作流 — 旧版Fixer/Difix3D+流程的公开继任者，可清理渲染帧、协调插入的角色、评估PSNR/LPIPS，并可选择性微调模型。

有关命名重叠问题（NRE与Fixer、ncore与nre、AV-NuRec与Cosmos-Drive-Dreams、NuRec与SimReady），请参见

references/mix-ups.md

。

Locate and fetch the upstream skills

定位并获取上游技能

Quick recipe (full version in

references/upstream-fetch.md

bash

UPSTREAM_ROOT="${NUREC_SKILLS_UPSTREAM_ROOT:-${PHYSICAL_AI_SKILL_HUB_UPSTREAM_ROOT:-$HOME/.physical-ai-skill-hub/upstreams}}"
mkdir -p "$UPSTREAM_ROOT"
if [ -d "$UPSTREAM_ROOT/nurec-skills/.git" ]; then
  git -C "$UPSTREAM_ROOT/nurec-skills" fetch --tags
  git -C "$UPSTREAM_ROOT/nurec-skills" checkout main
  git -C "$UPSTREAM_ROOT/nurec-skills" pull --ff-only
else
  git clone --depth 1 https://github.com/NVIDIA/nurec-skills.git \
    "$UPSTREAM_ROOT/nurec-skills"
fi
test -f "$UPSTREAM_ROOT/nurec-skills/.agents/skills/SKILL.md"

Then read the upstream skill before running any mutating command:

bash

cat "$UPSTREAM_ROOT/nurec-skills/.agents/skills/SKILL.md"          # router
cat "$UPSTREAM_ROOT/nurec-skills/.agents/skills/<folder>/SKILL.md" # sibling

Local lookup order (try in order before the upstream clone):

```
.agents/skills/<name>/SKILL.md
```
(Cursor, Codex, NemoClaw)
```
.claude/skills/<name>/SKILL.md
```
(Claude Code)
```
.cursor/skills/<name>/SKILL.md
```
(project-scoped)
```
~/.cursor/skills/<name>/SKILL.md
```
(personal skills)

快速流程（完整版本参见

references/upstream-fetch.md

）：

bash

UPSTREAM_ROOT="${NUREC_SKILLS_UPSTREAM_ROOT:-${PHYSICAL_AI_SKILL_HUB_UPSTREAM_ROOT:-$HOME/.physical-ai-skill-hub/upstreams}}"
mkdir -p "$UPSTREAM_ROOT"
if [ -d "$UPSTREAM_ROOT/nurec-skills/.git" ]; then
  git -C "$UPSTREAM_ROOT/nurec-skills" fetch --tags
  git -C "$UPSTREAM_ROOT/nurec-skills" checkout main
  git -C "$UPSTREAM_ROOT/nurec-skills" pull --ff-only
else
  git clone --depth 1 https://github.com/NVIDIA/nurec-skills.git \
    "$UPSTREAM_ROOT/nurec-skills"
fi
test -f "$UPSTREAM_ROOT/nurec-skills/.agents/skills/SKILL.md"

然后在运行任何修改性命令前，阅读上游技能文档：

bash

cat "$UPSTREAM_ROOT/nurec-skills/.agents/skills/SKILL.md"          # 路由工具
cat "$UPSTREAM_ROOT/nurec-skills/.agents/skills/<folder>/SKILL.md" # 关联技能

本地查找顺序（在克隆上游代码前按以下顺序尝试）：

```
.agents/skills/<name>/SKILL.md
```
（Cursor、Codex、NemoClaw）
```
.claude/skills/<name>/SKILL.md
```
（Claude Code）
```
.cursor/skills/<name>/SKILL.md
```
（项目范围）
```
~/.cursor/skills/<name>/SKILL.md
```
（个人技能）

Hard Rules

硬性规则

Router only — do not duplicate upstream NuRec recipes here. Read the upstream sibling skill body before running any mutating command.
Refer to sibling skills by their
```
name:
```
(e.g.
```
nre
```
), not by repo path. Folder layouts can change; the name is portable.

Clone or refresh

https://github.com/NVIDIA/nurec-skills

under the shared upstream root (

${NUREC_SKILLS_UPSTREAM_ROOT:-${PHYSICAL_AI_SKILL_HUB_UPSTREAM_ROOT:-$HOME/.physical-ai-skill-hub/upstreams}}/nurec-skills

). Do not scan broad developer workspaces such as

~/Codes

or reuse unrelated old clones.

```
physical-ai-datasets
```
covers gated Hugging Face datasets. Do not bypass dataset license terms; the user must accept the
```
PhysicalAI-*
```
gated licenses on Hugging Face and provide a token before downloading.
Asset Harvester runs before packaging into a USDZ. Do not call
```
nre
```
's
```
export-external-assets
```
on hand-rolled
```
.ply
```
files unless the user explicitly asks to skip Asset Harvester.
For artifact cleanup, prefer the built-in
```
--enable-difix
```
path in
```
nre
```
. Route to the standalone
```
nurec-fixer
```
only when the user needs the public code/model card, paired evaluation, fine-tuning, or fixes on previously rendered frames.
Do not invent NRE / NCore / DiffusionHarmonizer commands from memory. Re-read the upstream sibling skill — versions move fast (NRE
```
release_26.04
```
is the current pinned tag).
This router does not deploy infrastructure. Route AKS / OSMO / NIM Operator setup to
```
physical-ai-infrastructure-setup-and-resilient-scaling
```
.

仅作为路由工具 — 请勿在此处复制上游NuRec流程。在运行任何修改性命令前，务必阅读上游关联技能的文档。
以技能的
```
name:
```
（例如
```
nre
```
）指代关联技能，而非仓库路径。文件夹布局可能会变化；技能名称具有可移植性。

在共享上游根目录（

${NUREC_SKILLS_UPSTREAM_ROOT:-${PHYSICAL_AI_SKILL_HUB_UPSTREAM_ROOT:-$HOME/.physical-ai-skill-hub/upstreams}}/nurec-skills

）下克隆或更新

https://github.com/NVIDIA/nurec-skills

。请勿扫描宽泛的开发者工作区（如

~/Codes

）或复用无关的旧克隆版本。

```
physical-ai-datasets
```
涵盖Hugging Face上的 gated数据集。请勿绕过数据集许可条款；用户必须先在Hugging Face上接受
```
PhysicalAI-*
```
的 gated许可，并提供令牌才能下载。
Asset Harvester需在打包为USDZ文件之前运行。除非用户明确要求跳过Asset Harvester，否则请勿对手动生成的
```
.ply
```
文件调用
```
nre
```
的
```
export-external-assets
```
命令。
对于工件清理，优先使用
```
nre
```
中内置的
```
--enable-difix
```
流程。仅当用户需要公开代码/模型卡片、配对评估、微调或修复已渲染帧时，才路由到独立的
```
nurec-fixer
```
。
请勿凭记忆编写NRE/NCore/DiffusionHarmonizer命令。请重新阅读上游关联技能文档 — 版本更新速度快（当前固定标签为NRE
```
release_26.04
```
）。
本路由工具不负责部署基础设施。AKS/OSMO/NIM Operator搭建请路由到
```
physical-ai-infrastructure-setup-and-resilient-scaling
```
。

Limitations

局限性

Router only. This skill never executes mutating NuRec commands. All training, rendering, conversion, and harmonization happens in upstream sibling skills.
Upstream-pinned. Recipes live in
```
https://github.com/NVIDIA/nurec-skills
```
, which evolves outside this repo. Stale clones can drift; always
```
git pull
```
the upstream before relying on a sibling skill.
Gated content.
```
nvidia/PhysicalAI-*
```
,
```
nvidia/DiffusionHarmonizer
```
, and
```
nvidia/asset-harvester
```
require the user to accept license terms on Hugging Face first. The router cannot bypass this.
Heavy footprint. A complete NuRec workflow can leave 150 GB+ on disk. See
```
references/teardown.md
```
.
NVIDIA-only stack. Requires an NVIDIA GPU plus the NVIDIA Container Toolkit. AMD / Intel / Apple Silicon are not supported.
Not a SimReady pipeline. NuRec produces a renderable USDZ from a recording; SimReady packaging of CAD or source meshes is a different pipeline (see
```
omniverse-cad-to-simready
```
).

仅作为路由工具。本技能从不执行修改性NuRec命令。所有训练、渲染、转换和协调操作均在上游关联技能中完成。
依赖上游更新。流程存于
```
https://github.com/NVIDIA/nurec-skills
```
，该仓库独立于本仓库演进。过时的克隆版本可能会与上游脱节；在依赖关联技能前，请务必
```
git pull
```
更新上游代码。
内容受 gated限制。
```
nvidia/PhysicalAI-*
```
、
```
nvidia/DiffusionHarmonizer
```
和
```
nvidia/asset-harvester
```
要求用户先在Hugging Face上接受许可条款。路由工具无法绕过此限制。
占用空间大。完整的NuRec工作流可能会在磁盘上留下150 GB以上的数据，包括容器镜像、模型权重、代码克隆、conda环境和输出目录。请参见
```
references/teardown.md
```
。
仅支持NVIDIA栈。需要NVIDIA GPU及NVIDIA Container Toolkit。不支持AMD/Intel/Apple Silicon。
非SimReady流水线。NuRec从记录生成可渲染的USDZ文件；CAD或源网格的SimReady打包是另一条独立流水线（参见
```
omniverse-cad-to-simready
```
）。

Troubleshooting

故障排除

Error / symptom	Likely cause	Solution
`nurec-skills` clone missing or empty	Upstream not fetched yet	Run the clone block in Locate and fetch the upstream skills
`403` / `401` pulling `nvidia/PhysicalAI-*` from HF	Gated license not accepted, or `HF_TOKEN` unset / wrong scope	Accept the gated license on Hugging Face, then `hf auth login` with a token that has `read` access
`denied: requested access to the resource is denied` from `nvcr.io/nvidia/nre/*`	Missing or expired `NGC_API_KEY`	`docker login nvcr.io` with `$oauthtoken` / `NGC_API_KEY` ; rotate the key at `org.ngc.nvidia.com/setup/api-key` if needed
NRE refuses to load a clip ("not valid NCore V4")	Recording was not converted	Run the `ncore` skill before invoking `nre`
`serve-grpc` cold-start latency dominates a Python loop	One-shot Docker invocation per render	Use the `nre` warm `serve-grpc` + thin Python client ( `batch_render_rgb` ) recipe
Output files are owned by `root` after a `docker run`	`-u $(id -u):$(id -g)` was missing	`sudo chown -R "$(id -u):$(id -g)" <output_dir>` ; add the `-u` flag next time
Frames have ghosting / floaters / flicker after rendering	Inline cleanup not enabled	Re-render with `nre --enable-difix` , or post-process with `nurec-fixer` (DiffusionHarmonizer)
Stale skill names ( `ncore-data-conversion` , old `nvidia/Fixer` ) in agent output	Out-of-date cached skill	Update references to `ncore` and `nurec-fixer` (DiffusionHarmonizer); see `references/maintenance.md`
Bash anti-pattern `${HF_TOKEN:+yes}${HF_TOKEN:-no}` echoed token value	Misuse of bash parameter expansion	Rotate the token; use `hf auth whoami` or length-only checks (see `references/secrets-handling.md` )

错误/症状	可能原因	解决方案
`nurec-skills` 克隆缺失或为空	尚未获取上游代码	运行定位并获取上游技能中的克隆代码块
从HF拉取 `nvidia/PhysicalAI-*` 时出现 `403` / `401` 错误	未接受gated许可，或 `HF_TOKEN` 未设置/权限范围错误	在Hugging Face上接受gated许可，然后使用具有 `read` 权限的令牌执行 `hf auth login`
从 `nvcr.io/nvidia/nre/*` 拉取时出现 `denied: requested access to the resource is denied` 错误	`NGC_API_KEY` 缺失或过期	使用 `$oauthtoken` / `NGC_API_KEY` 执行 `docker login nvcr.io` ；若需要，在 `org.ngc.nvidia.com/setup/api-key` 页面轮换密钥
NRE拒绝加载片段（“not valid NCore V4”）	记录未转换	在调用 `nre` 前运行 `ncore` 技能
`serve-grpc` 冷启动延迟在Python循环中占主导	每次渲染都启动一次Docker	使用 `nre` 的预热 `serve-grpc` +轻量Python客户端（ `batch_render_rgb` ）流程
`docker run` 后输出文件归 `root` 所有	缺少 `-u $(id -u):$(id -g)` 参数	执行 `sudo chown -R "$(id -u):$(id -g)" <output_dir>` ；下次运行时添加 `-u` 参数
渲染后帧出现重影/漂浮物/闪烁	未启用内联清理	使用 `nre --enable-difix` 重新渲染，或使用 `nurec-fixer` （DiffusionHarmonizer）进行后处理
代理输出中出现过时技能名称（ `ncore-data-conversion` 、旧版 `nvidia/Fixer` ）	技能缓存过时	更新为 `ncore` 和 `nurec-fixer` （DiffusionHarmonizer）的引用；请参见 `references/maintenance.md`
Bash反模式 `${HF_TOKEN:+yes}${HF_TOKEN:-no}` 回显令牌值	错误使用bash参数扩展	轮换令牌；使用 `hf auth whoami` 或仅检查长度的方式（参见 `references/secrets-handling.md` ）

Cross-skill teardown

跨技能清理

A complete NuRec workflow can leave 150 GB+ on disk between container images, model weights, code clones, conda envs, and output directories. Each sibling skill has its own dedicated

Teardown

section — read them in the order documented in

references/teardown.md

when the user no longer needs the workflow.

完整的NuRec工作流可能会在磁盘上留下150 GB以上的数据，包括容器镜像、模型权重、代码克隆、conda环境和输出目录。每个关联技能都有自己专门的“清理”部分 — 当用户不再需要该工作流时，请按照

references/teardown.md

中记录的顺序阅读这些内容。

Keeping this router up to date

保持路由工具更新

Procedure for adding new sibling skills, renames, or upstream URL changes lives in

references/maintenance.md

. Treat the upstream

nurec-index

at https://github.com/NVIDIA/nurec-skills/blob/main/.agents/skills/SKILL.md as authoritative; this skill mirrors only the picker tables, the workflow ordering, and the upstream fetch recipe.

添加新关联技能、重命名或更改上游URL的流程记录在

references/maintenance.md

中。请以位于https://github.com/NVIDIA/nurec-skills/blob/main/.agents/skills/SKILL.md的上游

nurec-index

为准；本技能仅镜像选择器表格、工作流顺序和上游获取流程。