ML Anthology

Novel View Synthesis in Tensor Space

Shai Avidan, Amnon Shashua
CVPR 1997 pp. 1034-1040
doi:10.1109/CVPR.1997.609457 /cvpr/1997/avidan1997cvpr-novel/

Abstract

We present a new method for synthesizing novel views of a 3D scene from few model images in full correspondence. The core of this work is the derivation of a tensorial operator that describes the transformation from a given tensor of three views to a novel tensor of a new configuration of three views. By repeated application of the operator on a seed tensor with a sequence of desired virtual camera positions we obtain a chain of warping functions (tensors) from the set of model images to create the desired virtual views.

CVPR Semantic Scholar

Cite

Text

Avidan and Shashua. "Novel View Synthesis in Tensor Space." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609457

Markdown

[Avidan and Shashua. "Novel View Synthesis in Tensor Space." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/avidan1997cvpr-novel/) doi:10.1109/CVPR.1997.609457

BibTeX

@inproceedings{avidan1997cvpr-novel,
  title     = {{Novel View Synthesis in Tensor Space}},
  author    = {Avidan, Shai and Shashua, Amnon},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {1034-1040},
  doi       = {10.1109/CVPR.1997.609457},
  url       = {https://mlanthology.org/cvpr/1997/avidan1997cvpr-novel/}
}