US 10,380,317 B2Granted

Determining structure and functionality of scanned objects

AssigneeAdobe Inc.

InventorsDuygu Ceylan, Byungmoon Kim, Aron Monszpart, Vladimir Kim, Niloy Mitra

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods and systems for generating digital models from objects. In particular, one or more embodiments determine a plurality of correspondences for first and second components of an object. One or more embodiments estimate a joint connecting the first and second components based on the correspondences. One or more embodiments jointly determine a global transformation and one or more joint parameters that map the plurality of components of the object from the first digital scan to the second digital scan. One or more embodiments also updating the correspondences based on the determined global transformation and parameter(s). One or more embodiments re-estimate the joint based on the updated correspondences. One or more embodiments select a candidate joint with a lowest error estimate from a plurality of candidate joints according to determined global transformations and joint parameter(s) for the candidate joints.

Claims20

Dependent claims

A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause a computer system to:

identify, by at least one processor, a first component and a second component in a first digital scan of an object;
identify, by the at least one processor, the first component and the second component in a second digital scan of the object;
determine, by the at least one processor, a plurality of correspondences for the first component and the second component in the first digital scan and the second digital scan;
estimate, by the at least one processor, a joint connecting the first component and the second component based on the plurality of correspondences by determining a plurality of candidate joints between the first component and the second component, wherein each candidate joint of the plurality of candidate joints comprises a separate confidence level;
determine, by the at least one processor in response to determining that the confidence levels of the plurality of candidate joints are below a confidence threshold, a global transformation and a joint parameter that map the first component and the second component of the object from the first digital scan to the second digital scan using a minimization algorithm that jointly determines the global transformation and the joint parameter for the joint;
align, by the at least one processor, the first digital scan with the second digital scan using the global transformation and the joint parameter;
update, by the at least one processor, the plurality of correspondences by modifying at least one correspondence of the plurality of correspondences for the first component and the second component using the determined global transformation and joint parameter;
determine, by the at least one processor, updated confidence levels for the plurality of candidate joints based on the updated plurality of correspondences;
determine, by the at least one processor and from the plurality of candidate joints in response to determining that a confidence level of a candidate joint of the plurality of candidate joints meets the confidence threshold, the joint connecting the first component and the second component based on the plurality of updated correspondences;
and
generate a digital model comprising the determined joint representing a functionality of the object based on the plurality of updated correspondences.

8 more elements

A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause a computer system to:

identify, by at least one processor, a first component and a second component in a first digital scan of an object;
identify, by the at least one processor, the first component and the second component in a second digital scan of the object;
determine, by the at least one processor, a plurality of correspondences for the first component and the second component in the first digital scan and the second digital scan;
determine, by the at least one processor, a plurality of candidate joints between the first component and the second component based on the plurality of correspondences;
determine, by the at least one processor and for a candidate joint from the plurality of candidate joints, a global transformation and a joint parameter that map the first component and the second component from the first digital scan to the second digital scan using a minimization algorithm that jointly determines the global transformation and the joint parameter, each candidate joint from the plurality of candidate joints comprising a separate estimation error;
align the first digital scan with the second digital scan using the global transformation and the joint parameter;
update the plurality of correspondences by modifying at least one correspondence of the plurality of correspondences for the first component and the second component using the global transformation and the joint parameter;
determine updated estimation errors for the plurality of candidate joints based on the updated plurality of correspondences;
select, by the at least one processor in connection with the first component and the second component in response to updating the estimation errors for the plurality of candidate joints, a candidate joint from the plurality of candidate joints with a lowest estimation error according to the global transformation and the joint parameter;
and
generate a digital model comprising the selected candidate joint representing a functionality of the object.

8 more elements

In a digital medium environment for determining structure of scanned objects, a system comprising:

at least one processor;
a non-transitory computer readable storage medium comprising instructions that, when executed by the at least one processor, cause the system to:
identify a first component and a second component in a first digital scan of an object;
identify the first component and the second component in a second digital scan of the object;
determine a plurality of correspondences for the first component and the second component in the first digital scan and the second digital scan;
estimate a joint connecting the first component and the second component based on the plurality of correspondences by determining a plurality of candidate joints between the first component and the second component, wherein each candidate joint of the plurality of candidate joints comprises a separate confidence level;
determine, in response to determining that the confidence levels of the plurality of candidate joints are below a confidence threshold, a global transformation and a joint parameter that map the first component and the second component of the object from the first digital scan to the second digital scan using a minimization algorithm that jointly determines the global transformation and the joint parameter for the joint;
align the first digital scan with the second digital scan using the global transformation and the joint parameter;
update the plurality of correspondences by modifying at least one correspondence of the plurality of correspondences for the first component and the second component using the determined global transformation and the joint parameter;
determine updated confidence levels for the plurality of candidate joints based on the updated plurality of correspondences;
determine, from the plurality of candidate joints in response to determining that a confidence level of a candidate joint of the plurality of candidate joints meets the confidence threshold, the joint connecting the first component and the second component based on the plurality of updated correspondences;
and
generate a digital model comprising the determined joint representing a functionality of the object based on the plurality of updated correspondences.

10 more elements

Dependencies are inferred from the claim text.