Monocularly Generated 3D High Level Semantic Model by Integrating Deep Learning Models and Traditional Vision Techniques

Abstract

Scene reconstruction using Monodepth2 (Monocular Depth Inference) which provides depth maps from a single RGB camera, the outputs are filled with noise and inconsistencies. Instance segmentation using a Mask R-CNN (Region Based Convolution Neural Networks) deep model can provide object segmentation results in 2D but lacks 3D information.

Year of Publication
2021
Conference Name
2021 IEEE International Conference on Imaging Systems and Techniques (IST)
Date Published
08