Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis
Abstract
While 3D-based GAN techniques have been successfully applied to render photo-realistic 3D images with a variety of attributes while preserving view consistency, there has been little research on how to fine-control 3D images without limiting to a specific category of objects of their properties. To fill such research gap, we propose a novel image manipulation model of 3D-based GAN representations for a fine-grained control of specific custom attributes. By extending the latest 3D-based GAN models (e.g., EG3D), our user-friendly quantitative manipulation model enables a fine yet normalized control of 3D manipulation of multi-attribute quantities while achieving view consistency. We validate the effectiveness of our proposed technique both qualitatively and quantitatively through various experiments.
Cite
Text
Do et al. "Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.00824Markdown
[Do et al. "Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/do2023cvpr-quantitative/) doi:10.1109/CVPR52729.2023.00824BibTeX
@inproceedings{do2023cvpr-quantitative,
title = {{Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis}},
author = {Do, Hoseok and Yoo, EunKyung and Kim, Taehyeong and Lee, Chul and Choi, Jin Young},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2023},
pages = {8529-8538},
doi = {10.1109/CVPR52729.2023.00824},
url = {https://mlanthology.org/cvpr/2023/do2023cvpr-quantitative/}
}