Benutzer: Gast  Login
Titel:

Adversarial Semantic Scene Completion from a Single Depth Image

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Wang, Y.; Tan, D. J.; Navab, N.; Tombari, F.
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 parti...     »
Stichworte:
ICCV,3DV2018,CAMP,CAMPComputerVision,ComputerVision,ARXIV,Ambiguity,CNN,Semantic Completion,Deep Learning,deeplearning
Kongress- / Buchtitel:
2018 International Conference on 3D Vision (3DV)
Ausrichter der Konferenz:
Ieee
Jahr:
2018
Seiten:
426--434
 BibTeX