Evaluation of image features using a photorealistic virtual world
Image features are widely used in computer vision applications. They need to be robust to scene changes and image transformations. Designing and comparing feature descriptors requires the ability to evaluate their performance with respect to those transformations. We want to know how robust the desc...
Main Authors: | Kaneva, Biliana K., Torralba, Antonio, Freeman, William T. |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | en_US |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2012
|
Online Access: | http://hdl.handle.net/1721.1/72588 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 |
Similar Items
-
Infinite Images: Creating and Exploring a Large Photorealistic Virtual Space
by: Kaneva, Biliana K., et al.
Published: (2012) -
Large databases of real and synthetic images for feature evaluation and prediction
by: Kaneva, Biliana K
Published: (2012) -
Matching and Predicting Street Level Images
by: Kaneva, Biliana K., et al.
Published: (2011) -
Photorealistic sensor simulation for perception-driven robotics using virtual reality
by: Guerra, Winter Joseph.
Published: (2020) -
Synthesizing photorealistic images with deep generative learning
by: Zheng, Chuanxia
Published: (2021)