SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettes

Olivia Wiles and Andrew Zisserman

Abstract

The objective of this paper is 3D shape understanding from single and multiple images. To this end, we introduce a new deep-learning architecture and loss function, SilNet, that can handle multiple views in an order-agnostic manner. The architecture is fully convolutional, and for training we use a proxy task of silhouette prediction, rather than directly learning a mapping from 2D images to 3D shape as has been the target in most recent work. We demonstrate that with the SilNet architecture there is generalisation over the number of views – for example, SilNet trained on 2 views can be used with 3 or 4 views at test-time; and performance improves with more views. We introduce two new synthetics datasets: a blobby object dataset useful for pretraining, and a challenging and realistic sculpture dataset; and demonstrate on these datasets that SilNet has indeed learnt 3D shape.

Session

Spotlights

Files

Paper (PDF)
Supplementary (PDF)
Video (MP4)

DOI

10.5244/C.31.99
https://dx.doi.org/10.5244/C.31.99

Citation

Bibtex

            @inproceedings{BMVC2017_99,
                title={SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettes},
                author={Olivia Wiles and Andrew Zisserman},
                year={2017},
                month={September},
                pages={99.1-99.13},
                articleno={99},
                numpages={13},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.99},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.99}
            }