U-shaped Networks for Shape from Light Field

Stefan Heber, Wei Yu and Thomas Pock

Abstract

This paper presents a novel technique for Shape from Light Field (SfLF), that utilizes deep learning strategies. Our model is based on a fully convolutional network, that involves two symmetric parts, an encoding and a decoding part, leading to a u-shaped network architecture. By leveraging a recently proposed Light Field (LF) dataset, we are able to effectively train our model using supervised training. To process an entire LF we split the LF data into the corresponding Epipolar Plane Image (EPI) representation and predict each EPI separately. This strategy provides good reconstruction results combined with a fast prediction time. In the experimental section we compare our method to the state of the art. The method performs well in terms of depth accuracy, and is able to outperform competing methods in terms of prediction time by a large margin.

Session

Posters 1

Files

PDF iconExtended Abstract (PDF, 1M)
PDF iconPaper (PDF, 3M)

DOI

10.5244/C.30.37
https://dx.doi.org/10.5244/C.30.37

Citation

Stefan Heber, Wei Yu and Thomas Pock. U-shaped Networks for Shape from Light Field. In Richard C. Wilson, Edwin R. Hancock and William A. P. Smith, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 37.1-37.12. BMVA Press, September 2016.

Bibtex

        @inproceedings{BMVC2016_37,
        	title={U-shaped Networks for Shape from Light Field},
        	author={Stefan Heber, Wei Yu and Thomas Pock},
        	year={2016},
        	month={September},
        	pages={37.1-37.12},
        	articleno={37},
        	numpages={12},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.37},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.37}
        }