Bruno Berenguel-Baeta

FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions from Single Panoramas

In this work we present FreDSNet, a deep learning solution which obtains semantic 3D understanding of indoor environments from single panoramas. Omnidirectional images reveal task-specific advantages when addressing scene understanding problems due to the 360-degree contextual information about the…