Systems and methods for editing, animating, and processing point clouds using bounding volume hierarchies

A system comprising:

• one or more hardware processors configured to:
• receive a point cloud comprising a plurality of data points that are distributed non-uniformly in a three-dimensional (“3D”) space, the plurality of data points generating a first frame of an animation with each particular data point of the plurality of data points comprising a plurality of elements that define a position and visual characteristics of the particular data point in the 3D space;
• generate a tree representation of the point cloud, the tree representation comprising a plurality of leaf nodes and a plurality of branches that connect two or more leaf nodes directly or indirectly to parent nodes at one or more levels above the plurality of leaf nodes, wherein the plurality of leaf nodes correspond to the plurality of data points;
• detect a set of the plurality of data points that change between the first frame and a second frame of the animation;
• determine a particular branch from the plurality of branches that directly or indirectly connects to a set of leaf nodes that correspond to the set of data points that change between the first frame and a second frame of the animation;
• generate a replacement branch for the particular branch, the replacement branch comprising a set of replacement leaf nodes that capture the change between the first frame and the second frame;
• and
• encode the first frame and the second frame of the animation with the tree representation and the particular replacement branch.

A non-transitory computer-readable medium storing program instructions that, when executed by one or more hardware processors, cause a computing system to perform operations comprising:

• receive a point cloud comprising a plurality of data points that are distributed non-uniformly in a three-dimensional (“3D”) space, the plurality of data points generating a first frame of an animation with each particular data point of the plurality of data points comprising a plurality of elements that define a position and visual characteristics of the particular data point in the 3D space;
• generate a tree representation of the point cloud, the tree representation comprising a plurality of leaf nodes and a plurality of branches that connect two or more leaf nodes directly or indirectly to parent nodes at one or more levels above the plurality of leaf nodes, wherein the plurality of leaf nodes correspond to the plurality of data points;
• detect a set of the plurality of data points that change between the first frame and a second frame of the animation;
• determine a particular branch from the plurality of branches that directly or indirectly connects to a set of leaf nodes that correspond to the set of data points that change between the first frame and a second frame of the animation;
• generate a replacement branch for the particular branch, the replacement branch comprising a set of replacement leaf nodes that capture the change between the first frame and the second frame;
• and
• encode the first frame and the second frame of the animation with the tree representation and the particular replacement branch.