Skip to content

frank-Regal/EgocentricDepthEstimator

 
 

Repository files navigation

Egocentric Depth Estimator

This is the repo for work on egocentric depth estimation.

This is a part of the paper:

Scene-aware Egocentric 3D Human Pose Estimation

Jian Wang, Diogo Luvizon, Weipeng Xu, Lingjie Liu, Kripasindhu Sarkar, Christian Theobalt

CVPR 2023

[Project Page] [Datasets]

Run the demo

  1. Download the pretrained model and put it in the checkpoints folder.
  2. Run the demo script:
python demo.py --img_dir ./data/example_sequence --model_path ./checkpoints/ego_depth.pth.tar
  1. The estimated depth maps will be saved in the data/example_sequence/depths folder.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 75.6%
  • Cuda 17.7%
  • C++ 4.9%
  • C 1.8%