Depth-Adapted CNN for RGB-D cameras

09/21/2020
by   Zongwei Wu, et al.
0

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.

READ FULL TEXT

page 2

page 8

research
03/19/2018

Depth-aware CNN for RGB-D Segmentation

Convolutional neural networks (CNN) are limited by the lack of capabilit...
research
06/08/2022

Depth-Adapted CNNs for RGB-D Semantic Segmentation

Recent RGB-D semantic segmentation has motivated research interest thank...
research
03/02/2017

Towards CNN Map Compression for camera relocalisation

This paper presents a study on the use of Convolutional Neural Networks ...
research
06/05/2022

U(1) Symmetry-breaking Observed in Generic CNN Bottleneck Layers

We report on a significant discovery linking deep convolutional neural n...
research
03/28/2022

Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation

As RGB-D sensors become more affordable, using RGB-D images to obtain hi...
research
12/04/2018

SurfConv: Bridging 3D and 2D Convolution for RGBD Images

We tackle the problem of using 3D information in convolutional neural ne...
research
07/03/2020

ODE-CNN: Omnidirectional Depth Extension Networks

Omnidirectional 360 camera proliferates rapidly for autonomous robots si...

Please sign up or login with your details

Forgot password? Click here to reset