Adversarial semantic scene completion from a single depth image
Wang Y, Tan DJ, Navab N, Tombari F (2018)
Publication Type: Conference contribution
Publication year: 2018
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 426-434
Conference Proceedings Title: Proceedings - 2018 International Conference on 3D Vision, 3DV 2018
Event location: Verona, ITA
ISBN: 9781538684252
Abstract
We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image. We improve the accuracy of the regressed semantic 3D maps by a novel architecture based on adversarial learning. In particular, we suggest using multiple adversarial loss terms that not only enforce realistic outputs with respect to the ground truth, but also an effective embedding of the internal features. This is done by correlating the latent features of the encoder working on partial 2.5D data with the latent features extracted from a variational 3D auto-encoder trained to reconstruct the complete semantic scene. In addition, differently from other approaches that operate entirely through 3D convolutions, at test time we retain the original 2.5D structure of the input during downsampling to improve the effectiveness of the internal representation of our model. We test our approach on the main benchmark datasets for semantic scene completion to qualitatively and quantitatively assess the effectiveness of our proposal.
Involved external institutions
Germany (DE)How to cite
APA:
Wang, Y., Tan, D.J., Navab, N., & Tombari, F. (2018). Adversarial semantic scene completion from a single depth image. In Proceedings - 2018 International Conference on 3D Vision, 3DV 2018 (pp. 426-434). Verona, ITA: Institute of Electrical and Electronics Engineers Inc..
MLA:
Wang, Yida, et al. "Adversarial semantic scene completion from a single depth image." Proceedings of the 6th International Conference on 3D Vision, 3DV 2018, Verona, ITA Institute of Electrical and Electronics Engineers Inc., 2018. 426-434.
BibTeX: Download