Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data

Nilesh Kulkarni, Linyi Jin, Justin Johnson, David F. Fouhey

CVPR 2023 pp. 17256-17265

doi:10.1109/CVPR52729.2023.01655 /cvpr/2023/kulkarni2023cvpr-learning/

Abstract

We introduce a method that can learn to predict scene-level implicit functions for 3D reconstruction from posed RGBD data. At test time, our system maps a previously unseen RGB image to a 3D reconstruction of a scene via implicit functions. While implicit functions for 3D reconstruction have often been tied to meshes, we show that we can train one using only a set of posed RGBD images. This setting may help 3D reconstruction unlock the sea of accelerometer+RGBD data that is coming with new phones. Our system, D2-DRDF, can match and sometimes outperform current methods that use mesh supervision and shows better robustness to sparse data.

PDF CVPR Semantic Scholar

Cite

Text

Kulkarni et al. "Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.01655

Markdown

[Kulkarni et al. "Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/kulkarni2023cvpr-learning/) doi:10.1109/CVPR52729.2023.01655

BibTeX

@inproceedings{kulkarni2023cvpr-learning,
  title     = {{Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data}},
  author    = {Kulkarni, Nilesh and Jin, Linyi and Johnson, Justin and Fouhey, David F.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {17256-17265},
  doi       = {10.1109/CVPR52729.2023.01655},
  url       = {https://mlanthology.org/cvpr/2023/kulkarni2023cvpr-learning/}
}