The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates. In this work, we present the Isometry-Aware Monocular Generative Adversarial Network (IsMo-GAN) — an approach for direct 3D reconstruction from a single image, trained for the deformation model in an adversarial manner on a light-weight synthetic dataset. IsMo-GAN reconstructs surfaces from real images under varying illumination, camera poses, textures and shading at over 250 Hz. In multiple experiments, it consistently outperforms several approaches in the reconstruction accuracy, runtime, generalisation to unknown surfaces and robustness to occlusions. In comparison to the state-of-the-art, we reduce the reconstruction error by 10-30% including the textureless case and our surfaces evince fewer artefacts qualitatively.



BibTeX, 1 KB

    author = {Shimada, Soshi and Golyanik, Vladislav and Theobalt, Christian and Stricker, Didier}, 
    title = {{IsMo-GAN}: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction}, 
    booktitle = {Computer Vision and Pattern Recognition Workshops (CVPRW)}, 
    year = {2019} 


This work was supported by project VIDETE (01IW18002) of the the German Federal Ministry of Education and Research (BMBF).


For questions and clarifications please get in touch with:
Soshi Shimada sshimada@mpi-inf.mpg.de

This page is Zotero translator friendly. Page last updated Imprint. Data Protection.