Title
deepRGBXYZ: Dense Pixel Description Utilizing RGB and Depth with Stacked Dilated Convolutions
Abstract
In this paper, we propose deepRGBXYZ - a feature descriptor to represent pixels for robust dense pixel matching. To this end, we concatenate RGB image (appearance) information with the depth (geometric) information represented as XYZ in order to build a robust descriptor which is more invariant to photometric and geometric changes. Both information (RGB and depth) are embedded as an early fusion into one neural network which is based on stacked dilated convolutions for enlarging the receptive field. We alleviate the limitations of image-only descriptors especially within ill-conditioned light regions or textureless objects. Additionally, we overcome the difficulty of using depth-only information which show less descriptive details compared to image-only. We demonstrate the superior accuracy of our deepRGBXYZ descriptor against the state-of-the-art image-only descriptors and we verify our design decision. In addition, we investigate the superior robustness of our deepRGBXYZ descriptor by bringing it into the application of optical flow and scene flow estimation on the established data sets KITTI and FlyingThings3D.
Year
DOI
Venue
2020
10.1109/ITSC45102.2020.9294195
2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)
Keywords
DocType
ISBN
deepRGBXYZ descriptor,stacked dilated convolutions,feature descriptor,robust dense pixel matching,RGB image information,depth information,robust descriptor,photometric changes,geometric changes,neural network,ill-conditioned light regions,depth-only information,dense pixel description,image-only descriptors,geometric information,textureless objects,optical flow,scene flow estimation,data sets KITTI,data sets FlyingThings3D,RGB image information concatenation
Conference
978-1-7281-4150-3
Citations 
PageRank 
References 
0
0.34
7
Authors
5
Name
Order
Citations
PageRank
Ramy Battrawy101.01
René Schuster2145.44
Oliver Wasenmüller300.34
Qing Rao493.20
Didier Stricker51266138.03