Monodepth2 - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
UG1354
Release Date
2023-06-29
Version
3.5 English

The monodepth2 model infers a dense depth image from an input image. It has a set of improvements, which result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods.

The following image shows the result of Monodepth2.

Figure 1. Monodepth2 Example



The following table lists the Monodepth2 model supported by the Vitis AI Library.

Table 1. Monodepth2 Model
No Model Name Framework
1 monodepth2_pt PyTorch