Resumen: We present a real-time method for computing the mechanical interaction between real and virtual objects in an augmented reality environment. Using model order reduction methods we are able to estimate the physical behavior of deformable objects in real time, with the precision of a high-fidelity solver but working at the speed of a video sequence. We merge tools of machine learning, computer vision, and computer graphics in a single application to describe the behavior of deformable virtual objects allowing the user to interact with them in a natural way. Three examples are provided to test the performance of the method. Idioma: Inglés DOI: 10.1002/nme.6385 Año: 2020 Publicado en: International Journal for Numerical Methods in Engineering 121, 17 (2020), 3849-3868 ISSN: 0029-5981 Factor impacto JCR: 3.477 (2020) Categ. JCR: MATHEMATICS, INTERDISCIPLINARY APPLICATIONS rank: 21 / 108 = 0.194 (2020) - Q1 - T1 Categ. JCR: ENGINEERING, MULTIDISCIPLINARY rank: 25 / 91 = 0.275 (2020) - Q2 - T1 Factor impacto SCIMAGO: 1.421 - Applied Mathematics (Q1) - Numerical Analysis (Q1) - Engineering (miscellaneous) (Q1)