Camouflaging an Object from Many Viewpoints
Author(s)
Owens, Andrew Hale; Barnes, Connelly; Flint, Alex; Singh, Hanumant; Freeman, William
DownloadAccepted version (5.842Mb)
Terms of use
Metadata
Show full item recordAbstract
© 2014 IEEE. We address the problem of camouflaging a 3D object from the many viewpoints that one might see it from. Given photographs of an object's surroundings, we produce a surface texture that will make the object difficult for a human to detect. To do this, we introduce several background matching algorithms that attempt to make the object look like whatever is behind it. Of course, it is impossible to exactly match the background from every possible viewpoint. Thus our models are forced to make trade-offs between different perceptual factors, such as the conspicuousness of the occlusion boundaries and the amount of texture distortion. We use experiments with human subjects to evaluate the effectiveness of these models for the task of camouflaging a cube, finding that they significantly outperform naïve strategies.
Date issued
2014-06Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryPublisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Owens, Andrew, Barnes, Connelly, Flint, Alex, Singh, Hanumant and Freeman, William. 2014. "Camouflaging an Object from Many Viewpoints."
Version: Author's final manuscript