Determining structure and functionality of scanned objects

Patent metadata

Field	Value
Publication number	US-10380317-B2
Application number	US-201615063183-A
Country	US
Kind code	B2
Filing date	Mar 7, 2016
Priority date	Mar 7, 2016
Publication date	Aug 13, 2019
Grant date	Aug 13, 2019

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.

First claim

What is claimed is:

1. 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.

2. The non-transitory computer readable storage medium as recited in claim 1 , wherein the instructions that cause the computer system to determine the plurality of correspondences for the first component and the second component cause the computer system to:
determine at least one correspondence associated with a feature of the first component in the first digital scan and a feature of the first component in the second digital scan; and
determine at least one correspondence associated with a feature of the second component in the first digital scan and a feature of the second component in the second digital scan.

3. The non-transitory computer readable storage medium as recited in claim 2 , further comprising instructions that, when executed by the at least one processor, cause the computer system to identify a visual feature of the first component and the second component as a correspondence at a location of the object.

4. The non-transitory computer readable storage medium as recited in claim 1 , wherein the instructions that cause the computer system to estimate the joint cause the computer system to use singular value decomposition to estimate a joint type of the joint.

5. The non-transitory computer readable storage medium as recited in claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:
generate a first digital model based on the first digital scan, the first digital model comprising the first component and the second component; and
generate a second digital model based on the second digital scan, the second digital model comprising the first component and the second component.

6. The non-transitory computer readable storage medium as recited in claim 5 , wherein the instructions that cause the computer system to determine the global transformation and one or more joint parameters cause the computer system to:
determine a global transformation that aligns the first component of the first digital model with the first component of the second digital model, the global transformation comprising a rotation and a translation of the first component; and
determine a joint parameter for the joint that aligns the second component of the first digital model with the second component of the second digital model.

7. The non-transitory computer readable storage medium as recited in claim 1 , wherein the instructions that cause the computer system to determine the joint connecting the first component and the second component cause the computer system to iterate between determining the global transformation and the joint parameter using the minimization algorithm and updating the plurality of correspondences until at least one confidence level of the plurality of candidate joints meets the confidence threshold.

8. The non-transitory computer readable storage medium as recited in claim 1 , wherein the instructions that cause the computer system to determine the global transformation and the joint parameter cause the computer system to:
segment the plurality of correspondences into a plurality of correspondence groups; and
jointly determine the global transformation and the joint parameter that fit the first component and the second component of the first digital scan to the second digital scan by applying the minimization algorithm to the plurality of correspondence groups.

9. The non-transitory computer readable storage medium as recited in claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:
receive a user input to modify the first component of the object; and
modify the first component in the generated digital model according to the user input and according to a functionality of the determined joint.

10. 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 s

Assignees

• Adobe Inc

Inventors

• Ceylan Duygu
• Kim Byungmoon
• Monszpart Aron
• Kim Vladimir
• Mitra Niloy

Classifications

• G06F30/17 Primary

  Mechanical parametric or variational design · CPC title

• G06F17/5086 Primary

  Physics · mapped topic