Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics
We describe how inflation, the act of mapping a 2D silhouette to a 3D region, can be applied in two disparate problems to offer insight and improvement: silhouette part segmentation and image-based material transfer. To demonstrate this, we introduce Puffball, a novel inflation technique, which achi...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for Computing Machinery (ACM)
2015
|
| Online Access: | http://hdl.handle.net/1721.1/95489 https://orcid.org/0000-0003-2222-6775 |
| _version_ | 1826205835223629824 |
|---|---|
| author | Twarog, Nathaniel R. Tappen, Marshall F. Adelson, Edward H. |
| author2 | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
| author_facet | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Twarog, Nathaniel R. Tappen, Marshall F. Adelson, Edward H. |
| author_sort | Twarog, Nathaniel R. |
| collection | MIT |
| description | We describe how inflation, the act of mapping a 2D silhouette to a 3D region, can be applied in two disparate problems to offer insight and improvement: silhouette part segmentation and image-based material transfer. To demonstrate this, we introduce Puffball, a novel inflation technique, which achieves similar results to existing inflation approaches -- including smoothness, robustness, and scale and shift-invariance -- through an exceedingly simple and accessible formulation. The part segmentation algorithm avoids many of the pitfalls of previous approaches by finding part boundaries on a canonical 3-D shape rather than in the contour of the 2-D shape; the algorithm gives reliable and intuitive boundaries, even in cases where traditional approaches based on the 2D Minima Rule are misled. To demonstrate its effectiveness, we present data in which subjects prefer Puffball's segmentations to more traditional Minima Rule-based segmentations across several categories of silhouettes. The texture transfer algorithm utilizes Puffball's estimated shape information to produce visually pleasing and realistically synthesized surface textures with no explicit knowledge of either underlying shape. |
| first_indexed | 2024-09-23T13:19:51Z |
| format | Article |
| id | mit-1721.1/95489 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:19:51Z |
| publishDate | 2015 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | dspace |
| spelling | mit-1721.1/954892022-09-28T13:26:00Z Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics Twarog, Nathaniel R. Tappen, Marshall F. Adelson, Edward H. Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Adelson, Edward H. Twarog, Nathaniel R. Adelson, Edward H. We describe how inflation, the act of mapping a 2D silhouette to a 3D region, can be applied in two disparate problems to offer insight and improvement: silhouette part segmentation and image-based material transfer. To demonstrate this, we introduce Puffball, a novel inflation technique, which achieves similar results to existing inflation approaches -- including smoothness, robustness, and scale and shift-invariance -- through an exceedingly simple and accessible formulation. The part segmentation algorithm avoids many of the pitfalls of previous approaches by finding part boundaries on a canonical 3-D shape rather than in the contour of the 2-D shape; the algorithm gives reliable and intuitive boundaries, even in cases where traditional approaches based on the 2D Minima Rule are misled. To demonstrate its effectiveness, we present data in which subjects prefer Puffball's segmentations to more traditional Minima Rule-based segmentations across several categories of silhouettes. The texture transfer algorithm utilizes Puffball's estimated shape information to produce visually pleasing and realistically synthesized surface textures with no explicit knowledge of either underlying shape. National Eye Institute (Special Training Grant) 2015-02-24T20:05:35Z 2015-02-24T20:05:35Z 2012-08 Article http://purl.org/eprint/type/ConferencePaper 9781450314312 http://hdl.handle.net/1721.1/95489 Nathaniel R. Twarog, Marshall F. Tappen, and Edward H. Adelson. 2012. Playing with Puffball: simple scale-invariant inflation for use in vision and graphics. In Proceedings of the ACM Symposium on Applied Perception (SAP '12). ACM, New York, NY, USA, 47-54. https://orcid.org/0000-0003-2222-6775 en_US http://dx.doi.org/10.1145/2338676.2338686 Proceedings of the ACM Symposium on Applied Perception (SAP '12) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery (ACM) Adelson via Courtney Crummett |
| spellingShingle | Twarog, Nathaniel R. Tappen, Marshall F. Adelson, Edward H. Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics |
| title | Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics |
| title_full | Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics |
| title_fullStr | Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics |
| title_full_unstemmed | Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics |
| title_short | Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics |
| title_sort | playing with puffball simple scale invariant inflation for use in vision and graphics |
| url | http://hdl.handle.net/1721.1/95489 https://orcid.org/0000-0003-2222-6775 |
| work_keys_str_mv | AT twarognathanielr playingwithpuffballsimplescaleinvariantinflationforuseinvisionandgraphics AT tappenmarshallf playingwithpuffballsimplescaleinvariantinflationforuseinvisionandgraphics AT adelsonedwardh playingwithpuffballsimplescaleinvariantinflationforuseinvisionandgraphics |