Depth-Adapted CNN for RGB-D cameras

Zongwei Wu, Guillaume Allibert, Christophe Stolz, Cedric Demonceaux; Proceedings of the Asian Conference on Computer Vision (ACCV), 2020


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 X and 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.

Related Material

@InProceedings{Wu_2020_ACCV, author = {Wu, Zongwei and Allibert, Guillaume and Stolz, Christophe and Demonceaux, Cedric}, title = {Depth-Adapted CNN for RGB-D cameras}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {November}, year = {2020} }