SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis
2017
Conference Paper
avg
This paper proposes an end-to-end learning framework for multiview stereopsis. We term the network SurfaceNet. It takes a set of images and their corresponding camera parameters as input and directly infers the 3D model. The key advantage of the framework is that both photo-consistency as well geometric relations of the surface structure can be directly learned for the purpose of multiview stereopsis in an end-to-end fashion. SurfaceNet is a fully 3D convolutional network which is achieved by encoding the camera parameters together with the images in a 3D voxel representation. We evaluate SurfaceNet on the large-scale DTU benchmark. Code is available in https://github.com/mjiUST/SurfaceNet
Author(s): | Ji, Mengqi and Gall, Juergen and Zheng, Haitian and Liu, Yebin and Fang, Lu |
Book Title: | IEEE International Conference on Computer Vision (ICCV), 2017 |
Year: | 2017 |
Publisher: | IEEE Computer Society |
Department(s): | Autonomes Maschinelles Sehen |
Bibtex Type: | Conference Paper (inproceedings) |
Paper Type: | Conference |
Event Name: | 2017 IEEE International Conference on Computer Vision (ICCV) |
Event Place: | Venice, Italy |
URL: | https://github.com/mjiUST/SurfaceNet |
BibTex @inproceedings{ji2017surfacenet, title = {SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis}, author = {Ji, Mengqi and Gall, Juergen and Zheng, Haitian and Liu, Yebin and Fang, Lu}, booktitle = {IEEE International Conference on Computer Vision (ICCV), 2017}, publisher = {IEEE Computer Society}, year = {2017}, doi = {}, url = {https://github.com/mjiUST/SurfaceNet} } |