Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation
This paper presents an example-based method to interpret a 3D shape from a single image depicting that shape. A major difficulty in applying an example-based approach to shape interpretation is the combinatorial explosion of shape possibilities that occur at occluding contours. Our key technical con...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Springer-Verlag
2017
|
| Online Access: | http://hdl.handle.net/1721.1/111992 https://orcid.org/0000-0002-1411-6704 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0003-2222-6775 |
| _version_ | 1826208757110013952 |
|---|---|
| author | Cole, Forrester Isola, Phillip John Freeman, William T. Durand, Frederic Adelson, Edward H. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Cole, Forrester Isola, Phillip John Freeman, William T. Durand, Frederic Adelson, Edward H. |
| author_sort | Cole, Forrester |
| collection | MIT |
| description | This paper presents an example-based method to interpret a 3D shape from a single image depicting that shape. A major difficulty in applying an example-based approach to shape interpretation is the combinatorial explosion of shape possibilities that occur at occluding contours. Our key technical contribution is a new shape patch representation and corresponding pairwise compatibility terms that allow for flexible matching of overlapping patches, avoiding the combinatorial explosion by allowing patches to explain only the parts of the image they best fit. We infer the best set of localized shape patches over a graph of keypoints at multiple scales to produce a discontinuous shape representation we term a shape collage. To reconstruct a smooth result, we fit a surface to the collage using the predicted confidence of each shape patch. We demonstrate the method on shapes depicted in line drawing, diffuse and glossy shading, and textured styles. |
| first_indexed | 2024-09-23T14:11:16Z |
| format | Article |
| id | mit-1721.1/111992 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T14:11:16Z |
| publishDate | 2017 |
| publisher | Springer-Verlag |
| record_format | dspace |
| spelling | mit-1721.1/1119922022-10-01T19:42:39Z Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation Cole, Forrester Isola, Phillip John Freeman, William T. Durand, Frederic Adelson, Edward H. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Cole, Forrester Isola, Phillip John Freeman, William T. Durand, Frederic Adelson, Edward H. This paper presents an example-based method to interpret a 3D shape from a single image depicting that shape. A major difficulty in applying an example-based approach to shape interpretation is the combinatorial explosion of shape possibilities that occur at occluding contours. Our key technical contribution is a new shape patch representation and corresponding pairwise compatibility terms that allow for flexible matching of overlapping patches, avoiding the combinatorial explosion by allowing patches to explain only the parts of the image they best fit. We infer the best set of localized shape patches over a graph of keypoints at multiple scales to produce a discontinuous shape representation we term a shape collage. To reconstruct a smooth result, we fit a surface to the collage using the predicted confidence of each shape patch. We demonstrate the method on shapes depicted in line drawing, diffuse and glossy shading, and textured styles. National Science Foundation (U.S.) (Grant 1111415) United States. Office of Naval Research (Grant N00014-09-1-1051) National Institutes of Health (U.S.) (Grant R01-EY019262) 2017-10-30T14:25:49Z 2017-10-30T14:25:49Z 2012 2017-10-25T17:58:40Z Article http://purl.org/eprint/type/ConferencePaper 978-3-642-33711-6 978-3-642-33712-3 0302-9743 1611-3349 http://hdl.handle.net/1721.1/111992 Cole, Forrester et al. “Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation.” 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part III, edited by Fitzgibbon A. et al., Springer-Verlag, 2012: 665–678. © 2012 Springer-Verlag https://orcid.org/0000-0002-1411-6704 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0003-2222-6775 http://dx.doi.org/10.1007/978-3-642-33712-3_48 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part III Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Springer-Verlag MIT Web Domain |
| spellingShingle | Cole, Forrester Isola, Phillip John Freeman, William T. Durand, Frederic Adelson, Edward H. Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation |
| title | Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation |
| title_full | Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation |
| title_fullStr | Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation |
| title_full_unstemmed | Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation |
| title_short | Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation |
| title_sort | shapecollage occlusion aware example based shape interpretation |
| url | http://hdl.handle.net/1721.1/111992 https://orcid.org/0000-0002-1411-6704 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0003-2222-6775 |
| work_keys_str_mv | AT coleforrester shapecollageocclusionawareexamplebasedshapeinterpretation AT isolaphillipjohn shapecollageocclusionawareexamplebasedshapeinterpretation AT freemanwilliamt shapecollageocclusionawareexamplebasedshapeinterpretation AT durandfrederic shapecollageocclusionawareexamplebasedshapeinterpretation AT adelsonedwardh shapecollageocclusionawareexamplebasedshapeinterpretation |