GENERATING DEVELOPABLE DEPTH IMAGES USING RANK MINIMIZATION

Patent №

US 11,080,819

Granted

2021-08-03

Filed 2020

Owner

ADOBE INC.

Lab

AI components

5

ml · vision · planning · evo · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16923936

An image processing system receives an input depth image with a surface that is not developable and generates an output depth image with a piecewise developable surface that approximates the input depth image. Height values for the output depth image are determined using an optimization problem that balances data fidelity and developability. Data fidelity is based on minimizing differences in height values of pixels in the output depth image and height values of pixels in the input depth image. Developability is based on rank minimization of Hessians computed for pixels in the output depth image. In some configurations, the optimization problem is formulated as a semi-definite programming problem and solved using a tailor-made alternating direction method of multipliers algorithm.

Machine learningVisionPlanningEvolutionary computationAI hardwareG06T 3/18G06T 19/20G06T 5/20G06T 5/70G06T 7/13G06T 7/50G06T 2207/10028G06T 2219/2021

AI classification

Vision1.00
Planning0.98
Machine learning0.98
AI hardware0.97
Evolutionary computation0.94
Natural language0.00
Knowledge representation0.00
Speech0.00

Ownership

ADOBE INC.

assignment · 531610700

Assignors

AIGERMAN, NOAM, JACOBSON, ALEC, GONZALEZ SELLAN, SILVIA

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC