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

Noise level added to point clouds #18

Closed MiZhenxing closed 5 years ago

MiZhenxing commented 5 years ago

Hello, thanks for your code and data. As described in paper, you "apply noise using a Gaussian distribution with zero mean and standard deviation 0.05 to the point clouds." However, I found in the configs/pointcloud/onet.yaml that the pointcloud_noise is set as 0.005. So I am wondering which noise level you used in your paper and in the pretrained model in configs/pointcloud/onet_pretrained.yaml. Many thanks.

LMescheder commented 5 years ago

Hi @MiZhenxing , in the paper, we report all values in terms of 1/10 of the maximal edge length of the object's bounding box (as stated on p. 5 in the paper). Because in the implementation the maximal edge length is 1, there is a factor 10 difference in all distances (stddev, chamfer distance, ...). I hope that answers your questions. Best, Lars

MiZhenxing commented 5 years ago

Hi @LMescheder , Thank you for your kind response. It's very helpful for my experiments. Best, Zhenxing.