Deng, WenlongBertoni, LorenzoKreiss, SvenAlahi, Alexandre2020-02-132020-02-132020-02-132020-06-0110.1109/ICRA40945.2020.9197069https://infoscience.epfl.ch/handle/20.500.14299/165523WOS:000712319501102We present an end-to-end trainable Neural Network architecture for stereo imaging that jointly locates and estimates human body poses in 3D. Our method defines a 2D pose for each human in a stereo pair of images and uses a correlation layer with a composite field to associate each left-right pair of joints. In the absence of a stereo pose dataset, we show that we can train our method with synthetic data only and test it on real-world images (\textit{i.e.}, our training stage is domain invariant). Our method is particularly suitable for autonomous vehicles. We achieve state-of-the-art results for the 3D localization task on the challenging real-world KITTI dataset while running four times faster.3D localizationStereo matchingPose estimationDeep learningRoboticstext::conference output::conference proceedings::conference paper