Invention Grant
- Patent Title: Deep image compression using lie algebras
-
Application No.: US15135392Application Date: 2016-04-21
-
Publication No.: US10013775B2Publication Date: 2018-07-03
- Inventor: Thomas Douglas Selkirk Duff
- Applicant: Pixar
- Applicant Address: US CA Emeryville
- Assignee: Pixar
- Current Assignee: Pixar
- Current Assignee Address: US CA Emeryville
- Agency: Patterson + Sheridan, LLP
- Main IPC: G06T9/00
- IPC: G06T9/00 ; G06T15/50

Abstract:
Systems, method, and computer program products for compressing a deep image comprising a plurality of voxels by, for each of the plurality of voxels, converting a voxel value to a corresponding value in a Lie algebra based on a logarithmic mapping function, interpolating a first subset of the plurality of values in the Lie algebra using a linear interpolation function applied to a first endpoint and a second endpoint of a first voxel column of the deep image, and upon determining that a deviation of the interpolation of each value in the first subset of the plurality of values does not exceed a threshold, storing an indication of the first endpoint, the second endpoint, and the respective values in the Lie algebra corresponding to the first and second endpoints.
Public/Granted literature
- US20160314598A1 DEEP IMAGE COMPRESSION USING LIE ALGEBRAS Public/Granted day:2016-10-27
Information query