Image-Based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models
Abstract
We propose a technique to use the structural information extracted from a set of 3D models of an object class to improve novel-view synthesis for images showing unknown instances of this class. These novel views can be used to "amplify" training image collections that typically contain only a low number of views or lack certain classes of views entirely (e.g. top views). We extract the correlation of position, normal, reflectance and appearance from computer-generated images of a few exemplars and use this information to infer new appearance for new instances. We show that our approach can improve performance of state-of-the-art detectors using real-world training data. Additional applications include guided versions of inpainting, 2D-to-3D conversion, super-resolution and non-local smoothing.
Cite
Text
Rematas et al. "Image-Based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.498Markdown
[Rematas et al. "Image-Based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/rematas2014cvpr-imagebased/) doi:10.1109/CVPR.2014.498BibTeX
@inproceedings{rematas2014cvpr-imagebased,
title = {{Image-Based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models}},
author = {Rematas, Konstantinos and Ritschel, Tobias and Fritz, Mario and Tuytelaars, Tinne},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2014},
doi = {10.1109/CVPR.2014.498},
url = {https://mlanthology.org/cvpr/2014/rematas2014cvpr-imagebased/}
}