ProLiF: Progressively-connected Light Field network for efficient view synthesis
Lists
Only you see this
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},
}