EUVIMEDEUVIMED entdecken
Crossref

Simple and Effective Synthesis of Indoor 3D Scenes

Jing Yu Koh, Harsh Agrawal, Dhruv Batra, Richard Tucker, Austin Waters, Honglak Lee, Yinfei Yang, Jason Baldridge, Peter Anderson

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (1) · 1169-1178

DOI: 10.1609/aaai.v37i1.25199 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Jing Yu Koh und 8 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We study the problem of synthesizing immersive 3D indoor scenes from one or a few images. Our aim is to generate high-resolution images and videos from novel viewpoints, including viewpoints that extrapolate far beyond the input images while maintaining 3D consistency. Existing approaches are highly complex, with many separately trained stages and components. We propose a simple alternative: an image-to-image GAN that maps directly from reprojections of incomplete point clouds to full high-resolution RGB-D images. On the Matterport3D and RealEstate10K datasets, our approach significantly outperforms prior work when evaluated by humans, as well as on FID scores. Further, we show that our model is useful for generative data augmentation. A vision-and-language navigation (VLN) agent trained with trajectories spatially-perturbed by our model improves success rate by up to 1.5% over a state of the art baseline on the mature R2R benchmark. Our code will be made available to facilitate generative data augmentation and applications to downstream robotics and embodied AI tasks.

Zitieren

APA

Koh, J. Y., Agrawal, H., Batra, D., Tucker, R., Waters, A., Lee, H., Yang, Y., Baldridge, J., & Anderson, P. (2023). Simple and Effective Synthesis of Indoor 3D Scenes. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 1169-1178. https://doi.org/10.1609/aaai.v37i1.25199

Vancouver

Koh JY, Agrawal H, Batra D, Tucker R, Waters A, Lee H, et al. Simple and Effective Synthesis of Indoor 3D Scenes. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(1):1169-1178. doi:10.1609/aaai.v37i1.25199

BibTeX
@article{Koh2023,
  author = {Koh, Jing Yu and Agrawal, Harsh and Batra, Dhruv and Tucker, Richard and Waters, Austin and Lee, Honglak and Yang, Yinfei and Baldridge, Jason and Anderson, Peter},
  title = {Simple and Effective Synthesis of Indoor 3D Scenes},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {1},
  pages = {1169--1178},
  doi = {10.1609/aaai.v37i1.25199}
}
Kostenlos starten →