Monocular Estimation of Translation, Pose and 3D Shape on Detected Objects using a Convolutional Autoencoder Topics: 3D Deep Learning; Deep Learning for Visual Understanding ; Image-Based Modeling and 3D Reconstruction; Machine Learning Technologies for Vision In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP, 390-396, 2022