search

autonomousvision / occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"
https://avg.is.tuebingen.mpg.de/publications/occupancy-networks
MIT License
1.5k stars 292 forks source link

The unit of Chamfer-L1 in the paper #20

Closed MiZhenxing closed 5 years ago

MiZhenxing commented 5 years ago

Hi, sorry to bother you again. I have run your code on ShapeNet point cloud data and got the evaluation result. However, the Chamfer-L1 in the result is several orders of magnitude lower than that in the table 2. So I am wondering if you have multiplied a large factor on the Chamfer-L1 when reporting in the paper, which is also common in other papers using Chamfer Distance. Best, Zhenxing

LMescheder commented 5 years ago

Hi @MiZhenxing, Chamfer-L1 in the paper is the average of the accuracy and completness score from the evaluator (Please see the supplementary of our paper for a formal definition). The Chamfer the evaluator outputs is the Chamfer-L2 distance. Whereas Chamfer-L1 has unit m, Chamfer-L2 has unit m^2. We chose to report Chamfer-L1 as it is more interpretable: it's unit is distance instead of squared distance.

MiZhenxing commented 5 years ago

@LMescheder Thank you very much.

LMescheder commented 4 years ago

Fixed in 2fa5496d14ea2f3340865af24dbd06b988e95651.