Articulated mesh animation from multi-view silhouettes
Details in mesh animations are difficult to generate but they have great impact on visual quality. In this work, we demonstrate a practical software system for capturing such details from multi-view video recordings. Given a stream of synchronized video images that record a human performance from mu...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for Computing Machinery (ACM)
2015
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/100254 https://orcid.org/0000-0003-0212-5643 |
| _version_ | 1826189862109184000 |
|---|---|
| author | Vlasic, Daniel Baran, Ilya Matusik, Wojciech Popovic, Jovan |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Vlasic, Daniel Baran, Ilya Matusik, Wojciech Popovic, Jovan |
| author_sort | Vlasic, Daniel |
| collection | MIT |
| description | Details in mesh animations are difficult to generate but they have great impact on visual quality. In this work, we demonstrate a practical software system for capturing such details from multi-view video recordings. Given a stream of synchronized video images that record a human performance from multiple viewpoints and an articulated template of the performer, our system captures the motion of both the skeleton and the shape. The output mesh animation is enhanced with the details observed in the image silhouettes. For example, a performance in casual loose-fitting clothes will generate mesh animations with flowing garment motions. We accomplish this with a fast pose tracking method followed by nonrigid deformation of the template to fit the silhouettes. The entire process takes less than sixteen seconds per frame and requires no markers or texture cues. Captured meshes are in full correspondence making them readily usable for editing operations including texturing, deformation transfer, and deformation model learning. |
| first_indexed | 2024-09-23T08:25:37Z |
| format | Article |
| id | mit-1721.1/100254 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:25:37Z |
| publishDate | 2015 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | dspace |
| spelling | mit-1721.1/1002542022-09-30T09:18:58Z Articulated mesh animation from multi-view silhouettes Vlasic, Daniel Baran, Ilya Matusik, Wojciech Popovic, Jovan Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Vlasic, Daniel Baran, Ilya Matusik, Wojciech Popovic, Jovan Singapore-MIT Gambit Game Lab Details in mesh animations are difficult to generate but they have great impact on visual quality. In this work, we demonstrate a practical software system for capturing such details from multi-view video recordings. Given a stream of synchronized video images that record a human performance from multiple viewpoints and an articulated template of the performer, our system captures the motion of both the skeleton and the shape. The output mesh animation is enhanced with the details observed in the image silhouettes. For example, a performance in casual loose-fitting clothes will generate mesh animations with flowing garment motions. We accomplish this with a fast pose tracking method followed by nonrigid deformation of the template to fit the silhouettes. The entire process takes less than sixteen seconds per frame and requires no markers or texture cues. Captured meshes are in full correspondence making them readily usable for editing operations including texturing, deformation transfer, and deformation model learning. National Science Foundation (U.S.) (CCF-0541227) National Science Foundation (U.S.). Graduate Research Fellowship Adobe Systems Pixar (Firm) 2015-12-14T23:12:16Z 2015-12-14T23:12:16Z 2008-08 Article http://purl.org/eprint/type/ConferencePaper 07300301 http://hdl.handle.net/1721.1/100254 Vlasic, Daniel, Ilya Baran, Wojciech Matusik, and Jovan Popović. “Articulated Mesh Animation from Multi-View Silhouettes.” ACM Transactions on Graphics 27, no. 3 (August 1, 2008): 1. https://orcid.org/0000-0003-0212-5643 en_US http://dx.doi.org/10.1145/1360612.1360696 ACM Transactions on Graphics Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Association for Computing Machinery (ACM) MIT web domain |
| spellingShingle | Singapore-MIT Gambit Game Lab Vlasic, Daniel Baran, Ilya Matusik, Wojciech Popovic, Jovan Articulated mesh animation from multi-view silhouettes |
| title | Articulated mesh animation from multi-view silhouettes |
| title_full | Articulated mesh animation from multi-view silhouettes |
| title_fullStr | Articulated mesh animation from multi-view silhouettes |
| title_full_unstemmed | Articulated mesh animation from multi-view silhouettes |
| title_short | Articulated mesh animation from multi-view silhouettes |
| title_sort | articulated mesh animation from multi view silhouettes |
| topic | Singapore-MIT Gambit Game Lab |
| url | http://hdl.handle.net/1721.1/100254 https://orcid.org/0000-0003-0212-5643 |
| work_keys_str_mv | AT vlasicdaniel articulatedmeshanimationfrommultiviewsilhouettes AT baranilya articulatedmeshanimationfrommultiviewsilhouettes AT matusikwojciech articulatedmeshanimationfrommultiviewsilhouettes AT popovicjovan articulatedmeshanimationfrommultiviewsilhouettes |