search

aim-uofa / AdelaiDepth

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.
Creative Commons Zero v1.0 Universal
1.07k stars 144 forks source link

Obtaining ground-truth focal length #34

Closed ayman-saleh closed 2 years ago

ayman-saleh commented 2 years ago

Hello,

Upon reading your paper, in order to generate the training samples for the PCM, on the fly you perturb the focal length by some delta, then generate the point cloud. It seems that the diverse depth dataset does not have the focal length in the annotations. Is this information not yet released?

Thanks

YvanYin commented 2 years ago

Hi, The released DiverseDepth dataset is for DiverseDepth project. Please see the paper "Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction" and "diversedepth: affine-invariant depth prediction using diverse data" for details. If you want to get more details of PCM module, please see the paper "Learning to recover 3D scene shape from a single image".