Washington RGB-D

Washington RGB-D is a widely used testbed in the robotic community, consisting of 41,877 RGB-D images organized into 300 instances divided in 51 classes of common indoor objects (e.g. scissors, cereal box, keyboard etc). Each object instance was positioned on a turntable and captured from three different viewpoints while rotating.

Source: Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work Image Source: https://rgbd-dataset.cs.washington.edu/