no code implementations • 10 Mar 2024 • Houssem Boulahbal
This method serves as an extension of self-supervised techniques to predict future depths.
no code implementations • 2 Mar 2023 • Houssem Boulahbal, Adrian Voicila, Andrew Comport
Apart from the transformer architecture, one of the main contributions with respect to prior works lies in the objective function that enforces spatio-temporal consistency across a sequence of output frames rather than a single output frame.
no code implementations • 15 Jun 2022 • Houssem Boulahbal, Adrian Voicila, Andrew Comport
This paper addresses the problem of end-to-end self-supervised forecasting of depth and ego motion.
no code implementations • 2 Mar 2022 • Houssem Boulahbal, Adrian Voicila, Andrew Comport
One novelty of the proposed method is the use of the multi-head attention of the transformer network that matches moving objects across time and models their interaction and dynamics.