Skip to content

Bad Performance for Point Cloud with Occlusion or Outliers #14

@FishWoWater

Description

@FishWoWater

Hi, thanks for open sourcing this work

I have tried the demo of point cloud conditioning and it works well.

However, when I tried my use cases, I found it has two limitations (failure cases)

1. the input point cloud is incomplete due to occlusion

Image Image Image

2. the point cloud has some outliers

Image Image

I think it's becasue of the training strategy. As claimed in the paper, input point cloud covers 3 types: from depth maps / scans / complete point clouds, but the occlusion is NOT considered. Perhaps it can be migitated by randomly dropping out some points during training

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions