> For the complete documentation index, see [llms.txt](https://docs.supervisely.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.supervisely.com/import-and-export/import/supported-annotation-formats/pointclouds/point_clouds.md).

# .PCD, .PLY, .LAS, .LAZ pointclouds

## Overview

This option allows you to upload point clouds to the platform without any annotations. All items from the input directory and its subdirectories will be uploaded to a single dataset. Supported formats are `.pcd`, `.ply`, `.las`, and `.laz`, and they are imported natively without conversion. If you need to preserve the directory structure, you can use the [Import Pointclouds PCD](https://ecosystem.supervisely.com/apps/import-pointcloud-pcd) application from the Supervisely Ecosystem.

## Format description

**Supported point cloud formats:** `.pcd`, `.ply`, `.las`, `.laz`.\
**With annotations:** No\
**Supported annotation format:** Not applicable.\
**Grouped by:** Any structure (will be uploaded to a single dataset).<br>

## Why native LAS/LAZ/PLY import matters

Import Wizard loads `.las`, `.laz`, and `.ply` files natively.

`PCD` is a simpler point cloud format. `LAS` / `LAZ` and many `PLY` variants can store richer source data, so native import helps preserve more of the information already present in your files.

Practical advantages:

* **More source attributes preserved**: `LAS` / `LAZ` can contain intensity, return information, classification, GPS time, and other LiDAR-specific fields. `PLY` can contain RGB, normals, and custom per-point properties. With native import, these attributes do not need to be flattened into a simpler intermediate representation.
* **No data loss from PCD conversion**: when point clouds are converted to `PCD`, some source-specific fields may be dropped, remapped, or normalized depending on the conversion path. Native import avoids that lossy step.
* **Smaller files can speed up the workflow**: some source formats, especially compressed `LAZ`, can be much smaller than converted `PCD`. That reduces upload volume, download volume in the labeling tool, and time spent opening dense scenes.
* **Faster time to first annotation**: skipping conversion removes an entire preprocessing stage before import.
* **Immediate benefit from rendering improvements**: once the data is loaded, the WebGPU pipeline can use preserved attributes such as RGB and Intensity while keeping interaction smooth on dense scenes.

## Input files structure

{% hint style="success" %}
Example data: [download ⬇️](https://github.com/supervisely-ecosystem/import-wizard-docs/files/15025187/sample_pcd.zip)
{% endhint %}

Recommended directory structure:

```
📦 folder
├── 📄 item_01.pcd
├── 📄 item_02.ply
├── 📄 item_03.las
├── 📄 item_04.laz
├── 📄 item_05.pcd
├── 📄 item_06.ply
├── 📄 item_07.las
├── 📄 item_08.laz
├── 📄 item_09.pcd
└── 📄 item_10.ply
```

## Format LAS/LAZ

In Import Wizard, LAS and LAZ files are supported natively, so no conversion to PCD is required.

### Coordinate handling

In Import Wizard, Supervisely preserves source coordinates as provided in the input file.

Coordinate shift is applicable only when using the [Import LAS format](https://ecosystem.supervisely.com/apps/import-las-format) app, where LAS/LAZ files are converted to PCD. This app is optional and is not required for Auto Import Wizard.

Example log entry:

```
Applied coordinate shift for filename: X=1234567.89, Y=9876543.21, Z=123.45
```

## Format PLY

In Import Wizard, PLY files are supported natively, so no conversion is required.

If you use the [Import Pointcloud PLY](http://ecosystem.supervisely.com/apps/import-pointcloud-ply) app, files are converted from PLY to PCD during import. This app is optional and is not required for Auto Import Wizard.

## Useful links

* [\[Supervisely Ecosystem\] Import Pointclouds PCD](https://ecosystem.supervisely.com/apps/import-pointcloud-pcd)
* [\[Supervisely Ecosystem\] Import LAS format](https://ecosystem.supervisely.com/apps/import-las-format)
* [\[Supervisely Ecosystem\] Import Pointcloud PLY](http://ecosystem.supervisely.com/apps/import-pointcloud-ply)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.supervisely.com/import-and-export/import/supported-annotation-formats/pointclouds/point_clouds.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.