3DPytorch-API NVIDIA Kaolin

NVIDIA Kaolin library provides a PyTorch API for working with a variety of 3D representations and includes a growing collection of GPU-optimized operations such as modular differentiable rendering, fast conversions between representations, data loading, 3D checkpoints and more.

提供了一个PyTorch API，用于处理各种3D表示形式，并包括越来越多的GPU优化操作集合，例如模块化的可区分渲染，表示之间的快速转换，数据加载，3D检查点等等。

NVIDIA Omniverse Kaolin App is an interactive application for 3D deep learning researchers that allows inspecting 3D datasets, interactive visualization of 3D outputs of a model during training, and synthetic dataset rendering. Built on Omniverse Kit, the research application benefits from high-fidelity RTX rendering and will gain new functionality periodically from new extensions.

In combination, these tools can massively reduce the time needed to develop AI research for a wide range of 3D applications.

一款面向3D深度学习研究人员的交互式应用程序，它可以检查3D数据集，在训练期间对模型的3D输出进行交互式可视化以及合成数据集渲染。该研究应用程序基于Omniverse Kit构建，得益于高保真RTX渲染，并将定期从新扩展中获得新功能。

结合使用，这些工​​具可以大大减少开发用于各种3D应用程序的AI研究所需的时间。

Kaolin Library

Modular Differentiable Renderer

Develop cutting-edge inverse graphics applications using modular and optimized mesh differentiable renderer.

使用模块化和优化的网格可微分渲染器开发最先进的逆向图形应用程序。

 

 

 

3D Data Loading

Easily load large 3D datasets to train your machine learning models. Make use of import and export utilities for OBJ and USD formats.

轻松加载大型3D数据集以训练机器学习模型。利用OBJ和USD格式的导入和导出实用程序。

GPU Optimized 3D Operations

Convert between 3D representations using fast and reliable conversion operations. Use GPU-optimized implementations of 3D loss functions and a growing collection of other operations on 3D data.

使用快速可靠的转换操作在3D表示形式之间进行转换。使用GPU优化的3D损失功能实现以及对3D数据的其他操作不断增长的集合。

 

 

 

3D Checkpoints

Export 3D checkpoints for meshes, point clouds and voxel grids in USD format, allowing interactive visualization of model training.

以USD格式导出网格，点云和体素网格的3D检查点，以交互方式可视化模型训练。

Omniverse Kaolin App

(Coming Soon)

Leveraging the NVIDIA Omniverse Platform, Omniverse Kaolin App allows high fidelity rendering and interactive visualization of 3D data and training results.

利用NVIDIA Omniverse平台，Omniverse Kaolin  App可以实现高保真渲染以及3D数据和培训结果的交互式可视化。

Visualize Model Training

Scrub through iterations of 3D checkpoints exported using the Kaolin python API to understand how your model is training. Debug models in development by inspecting 3D outputs and produce beautiful renderings of final results.

通过使用Kaolin python API导出的3D检查点的迭代进行清理，以了解模型的训练方式。通过检查3D输出来调试开发中的模型，并生成最终结果的精美效果图。

 

 

 

Render Synthetic Data

Render massive training datasets with RTX ray and path tracing and export useful ground truth labels, such as segmentation maps, bounding boxes, depth maps and normals.

使用RTX射线和路径跟踪渲染大量的训练数据集，并导出有用的地面真相标签，例如分段图，边界框，深度图和法线。

Inspect 3D Datasets

Effortlessly sample, render and inspect 3D datasets to gain intuition about your training data and identify inconsistencies.

毫不费力地采样，渲染和检查3D数据集，以获取有关您的训练数据的直觉并找出不一致之处。