# 3D vision

Project 2D detections into 3D point cloud objects, and read depth data from a depth camera to measure distance to detected objects.
> Source: https://docs.viam.com/vision/3d-vision/


Move from 2D images to 3D positions: segment detected objects in point clouds and measure distance from a depth camera so a robot can reason about physical space.

<div class="card-container">
  <div class="row-no-margin">
<div class="col hover-card "><a href="/vision/3d-vision/segment-3d/"><div ><div>Segment 3D objects</div><p>Use the vision service&#39;s GetObjectPointClouds method to find and label objects in 3D space, combining a 2D detector with a depth camera&#39;s point cloud.</p></div>
    </a></div>

<div class="col hover-card "><a href="/vision/3d-vision/measure-depth/"><div ><div>Measure depth</div><p>Retrieve point clouds and depth images from a depth camera, read depth at specific pixels, and measure distance to detected objects.</p></div>
    </a></div>

</div>
</div>