Three-dimensional (3D) object detection based on multiple two-dimensional (2D) views

An apparatus configured for object detection, comprising:

• one or more memories configured to store a first two-dimensional (2D) view of a scene and a second 2D view of the scene;
• and
• one or more processors, coupled to the one or more memories, configured to:
• obtain one or more inputs associated with one or more 2D views of the scene, wherein the one or more inputs comprise a 2D image of the scene corresponding to at least one 2D view of the scene of a plurality of 2D views of the scene;
• select a set of 2D views of the scene from the plurality of 2D views of the scene based on the one or more inputs, the set of 2D views comprising the first 2D view and the second 2D view, wherein the selection of the set of 2D views includes to:
• perform 2D object detection on the 2D image, and
• refrain from including the at least one 2D view of the scene in the set of 2D views based on the 2D object detection not indicating a detected object;
• and
• perform three-dimensional (3D) object detection in the scene based on the set of 2D views.