000198219 001__ 198219
000198219 005__ 20190316235907.0
000198219 037__ $$aCONF
000198219 245__ $$aRobust 3D Tracking with Descriptor Fields
000198219 269__ $$a2014
000198219 260__ $$c2014
000198219 336__ $$aConference Papers
000198219 520__ $$aWe introduce a method that can register challenging images from specular and poorly textured 3D environments, on which previous approaches fail. We assume that a small set of reference images of the environment and a partial 3D model are available. Like previous approaches, we register the input images by aligning them with one of the reference images using the 3D information. However, these approaches typically rely on the pixel intensities for the alignment, which is prone to fail in presence of specularities or in absence of texture. Our main contribution is an efficient novel local descriptor that we use to describe each image location. We show that we can rely on this descriptor in place of the intensities to significantly improve the alignment robustness at a minor increase of the computational cost, and we analyze the reasons behind the success of our descriptor.
000198219 6531_ $$a3D Tracking
000198219 6531_ $$aImage Alignment
000198219 6531_ $$aDense Descriptor
000198219 6531_ $$aSpecular Environments
000198219 700__ $$0246960$$g224226$$aCrivellaro, Alberto
000198219 700__ $$aLepetit, Vincent$$g149007$$0240235
000198219 7112_ $$dJune 23-28, 2014$$cColumbus, Ohio, USA$$aConference on Computer Vision and Pattern Recognition (CVPR)
000198219 8564_ $$uhttps://infoscience.epfl.ch/record/198219/files/DescriptorFields.pdf$$zn/a$$s15015159$$yn/a
000198219 8564_ $$uhttps://infoscience.epfl.ch/record/198219/files/DescriptorFieldsVideo.mp4$$s49148055
000198219 909C0 $$xU10659$$0252087$$pCVLAB
000198219 909CO $$ooai:infoscience.tind.io:198219$$qGLOBAL_SET$$pconf$$pIC
000198219 917Z8 $$x224226
000198219 937__ $$aEPFL-CONF-198219
000198219 973__ $$rREVIEWED$$sACCEPTED$$aEPFL
000198219 980__ $$aCONF