Physical Primitive Decomposition
Name
1809.05070.pdf
Description
Accepted version
Size
8.52 MB
Format
Adobe PDF
Checksum (MD5)
7ae5eb05f6cb06eab06cd1df3406bcbd
Author(s)
Liu, Zhijian
Freeman, William T
Tenenbaum, Joshua B
Wu, Jiajun
Date Issued
October 2018
Journal
European Conference on Computer Vision
Publisher
Springer International Publishing
Citation
Liu, Zhijian et al. "Physical Primitive Decomposition." European Conference on Computer Vision, September 2018, Munich, Germany, Springer International Publishing, October 2018. © 2018 Springer Nature
Version
Author's final manuscript
Abstract
Objects are made of parts, each with distinct geometry, physics, functionality, and affordances. Developing such a distributed, physical, interpretable representation of objects will facilitate intelligent agents to better explore and interact with the world. In this paper, we study physical primitive decomposition—understanding an object through its components, each with physical and geometric attributes. As annotated data for object parts and physics are rare, we propose a novel formulation that learns physical primitives by explaining both an object’s appearance and its behaviors in physical events. Our model performs well on block towers and tools in both synthetic and real scenarios; we also demonstrate that visual and physical observations often provide complementary signals. We further present ablation and behavioral studies to better understand our model and contrast it with human performance.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-01258-8_1
