ProLiF: Progressively-connected Light Field network for efficient view synthesis

Peng Wang, Yuan Liu, Guying Lin, Jiatao Gu, Lingjie Liu, Taku Komura, Wenping WangComput. Graph 2024 · OpenReview

Abstract

Highlights•Introduction of ProLiF, a simple and efficient network architecture for differentiable view synthesis.•Development of a progressive training strategy with novel regularization losses to ensure multi-view 3D consistency.•Demonstration of ProLiF’s compatibility with various loss functions for enhanced robustness and style editing capabilities.
BibTeX
@inproceedings{wang2024prolif,
  author = {Peng Wang and Yuan Liu and Guying Lin and Jiatao Gu and Lingjie Liu and Taku Komura and Wenping Wang},
  title = {{ProLiF: Progressively-connected Light Field network for efficient view synthesis}},
  booktitle = {Comput. Graph},
  year = {2024},
  url = {https://openreview.net/forum?id=4gDkn6Jyfn},
}
Figure