Skip to content

tobias-mayer/monocular-depth-estimation-torch

Repository files navigation

High Quality Monocular Depth Estimation via Transfer Learning

PyTorch implementation of I. Alhashim and P. Wonka, “High Quality Monocular Depth Estimation via Transfer Learning,” CoRR, vol. abs/1812.11941, [LINK]

Model Architecture

To verify the correct implementation of the model, the model is trained on the NYU_V2 dataset as in the paper. The model is currently used to create a 3D map of a robot's surroundings, enabling it to detect and avoid obstacles.

Setup

pip install -r requirements.txt
python train.py --batch-size 8 --epochs 20 --learning-rate 0.0001

About

PyTorch implementation of High Quality Monocular Depth Estimation via Transfer Learning

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published