ML Anthology

NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects

Dakshit Agrawal, Jiajie Xu, Siva Karthik Mustikovela, Ioannis Gkioulekas, Ashish Shrivastava, Yuning Chai
ICCVW 2023 pp. 4290-4294
doi:10.1109/ICCVW60793.2023.00463 /iccvw/2023/agrawal2023iccvw-nova/

Abstract

We propose a novel-view augmentation (NOVA) strategy to train NeRFs for photo-realistic 3D composition of dynamic objects in a static scene. Compared to prior work, our framework significantly reduces blending artifacts when inserting multiple dynamic objects into a 3D scene at novel views and times; achieves comparable PSNR without the need for additional ground truth modalities like optical flow; and overall provides ease, flexibility, and scalability in neural composition. Our codebase is on GitHub.

PDF ICCVW Semantic Scholar

Cite

Text

Agrawal et al. "NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects." IEEE/CVF International Conference on Computer Vision Workshops, 2023. doi:10.1109/ICCVW60793.2023.00463

Markdown

[Agrawal et al. "NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects." IEEE/CVF International Conference on Computer Vision Workshops, 2023.](https://mlanthology.org/iccvw/2023/agrawal2023iccvw-nova/) doi:10.1109/ICCVW60793.2023.00463

BibTeX

@inproceedings{agrawal2023iccvw-nova,
  title     = {{NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects}},
  author    = {Agrawal, Dakshit and Xu, Jiajie and Mustikovela, Siva Karthik and Gkioulekas, Ioannis and Shrivastava, Ashish and Chai, Yuning},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2023},
  pages     = {4290-4294},
  doi       = {10.1109/ICCVW60793.2023.00463},
  url       = {https://mlanthology.org/iccvw/2023/agrawal2023iccvw-nova/}
}