Skip to Main content Skip to Navigation
Conference papers

Depth-Adapted CNN for RGB-D cameras

Zongwei Wu 1 Guillaume Allibert 2 Christophe Stolz 1 Cédric Demonceaux 1
1 VIBOT - Equipe VIBOT - VIsion pour la roBOTique [ImViA EA7535 - ERL CNRS 6000]
CNRS - Centre National de la Recherche Scientifique : ERL 6000, ImViA - Imagerie et Vision Artificielle [Dijon]
Abstract : Conventional 2D Convolutional Neural Networks (CNN) extract features from an input image by applying linear filters. These filters compute the spatial coherence by weighting the photometric information on a fixed neighborhood without taking into account the geometric information. We tackle the problem of improving the classical RGB CNN methods by using the depth information provided by the RGB-D cameras. State-of-the-art approaches use depth as an additional channel or image (HHA) or pass from 2D CNN to 3D CNN. This paper proposes a novel and generic procedure to articulate both photometric and geometric information in CNN architecture. The depth data is represented as a 2D offset to adapt spatial sampling locations. The new model presented is invariant to scale and rotation around the X and the Y axis of the camera coordinate system. Moreover, when depth data is constant, our model is equivalent to a regular CNN. Experiments of benchmarks validate the effectiveness of our model.
Document type :
Conference papers
Complete list of metadata

Cited literature [53 references]  Display  Hide  Download
Contributor : Guillaume Allibert <>
Submitted on : Wednesday, September 23, 2020 - 3:08:59 PM
Last modification on : Wednesday, October 14, 2020 - 4:14:29 AM
Long-term archiving on: : Thursday, December 3, 2020 - 4:08:34 PM


Files produced by the author(s)


  • HAL Id : hal-02946902, version 1


Zongwei Wu, Guillaume Allibert, Christophe Stolz, Cédric Demonceaux. Depth-Adapted CNN for RGB-D cameras. ACCV 2020, Nov 2020, Kyoto (Virtual conference), Japan. ⟨hal-02946902⟩



Record views


Files downloads