Microsoft Technology Licensing, LLC

Jae Yong Lee

Sudipta Narayan Sinha

Victor Manuel Fragoso Rojas

Joseph Michael Degol

Daniel Glick

One example provides a computing system comprising a storage machine storing instructions executable by a logic machine to extract features from a source and target images to form source and target feature maps, form a correlation map comprising a plurality of similarity scores, form an initial correspondence map comprising initial mappings between pixels of the source feature map and corresponding pixels of the target feature map, refine the initial correspondence map by, for each of one or more pixels of the source feature map, for each of a plurality of candidate correspondences, inputting a four-dimensional patch into a trained scoring function, the trained scoring function being configured to output a correctness score, and selecting a refined correspondence based at least upon the correctness scores, and output a refined correspondence map comprising a refined correspondence for each of the one or more pixels of the source feature map.

Pixel correspondence via patch-based neighborhood consensus

A framework for aggregating updates for individual modules into an update for a containing module is disclosed. The containing module may be an entire program or workflow, for example. The updates may include changes to the contract of a module. Embodiments of the invention further provide a framework for detecting when changes to an inner module are incompatible with changes to the containing module.

Growing community of inventors

Urbana, IL, United States of America

Jae Yong Lee