Temporally Consistent Depth Enabled by a Multi-Task Approach [Neural Network Checkpoint]

This collection contains a neural network checkpoint (.pth) required for the sample inference code provided in association with the paper entitled: Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach / written by A. Atapour-Abarghouei and T.P. Breckon. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2019 : Long Beach, California).