The application tests a TFLite model or DNN-based Monocular Depth Estimation (MDE) that is based on the paper:

L. Papa, E. Alati, P. Russo and I. Amerini, "SPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings," in IEEE Access, vol. 10, pp. 44881-44890, 2022
https://doi.org/10.1109/ACCESS.2022.3170425


https://alcorlab.diag.uniroma1.it