Skip to Main content Skip to Navigation
Conference papers

PanoRoom: From the Sphere to the 3D Layout

Abstract : We propose a novel FCN able to work with omnidirectional images that outputs accurate probability maps representing the main structure of indoor scenes, which is able to generalize on different data. Our approach handles occlusions and recovers complex shaped rooms more faithful to the actual shape of the real scenes. We outperform the state of the art not only in accuracy of the 3D models but also in speed.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02158448
Contributor : Patrick Juillion <>
Submitted on : Tuesday, June 18, 2019 - 9:44:09 AM
Last modification on : Thursday, March 5, 2020 - 5:52:54 PM

File

PanoRoom__From_the_Sphere_to_t...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02158448, version 1

Collections

Citation

Clara Fernandez-Labrador, José Fácil, Alejandro Perez-Yus, Cédric Demonceaux, Jose Guerrero. PanoRoom: From the Sphere to the 3D Layout. ECCV 2018 Workshops, Sep 2018, Munich, Germany. ⟨hal-02158448⟩

Share

Metrics

Record views

45

Files downloads

75