Unimore logo AImageLab

Future Urban Scenes Generation Through Vehicles Synthesis

Abstract: In this work we propose a deep learning pipeline to predict the visual future appearance of an urban scene. Despite recent advances, generating the entire scene in an end-to-end fashion is still far from being achieved. Instead, here we follow a two stages approach, where interpretable information is included in the loop and each actor is modelled independently. We leverage a per-object novel view synthesis paradigm; i.e. generating a synthetic representation of an object undergoing a geometrical roto-translation in the 3D space. Our model can be easily conditioned with constraints (e.g. input trajectories) provided by state-of-the-art tracking methods or by the user itself. This allows us to generate a set of diverse realistic futures starting from the same input in a multi-modal fashion. We visually and quantitatively show the superiority of this approach over traditional end-to-end scene-generation methods on CityFlow, a challenging real world dataset.


Simoni, Alessandro; Bergamini, Luca; Palazzi, Andrea; Calderara, Simone; Cucchiara, Rita "Future Urban Scenes Generation Through Vehicles Synthesis" 2020 25th International Conference on Pattern Recognition (ICPR), Online, pp. 4552 -4559 , 10-15 January 2021, 2021 DOI: 10.1109/ICPR48806.2021.9412880

 not available

Paper download:

Related projects: