PillarNeSt

PillarNeSt copied to clipboard

about the pretrained ConvNeXt model

3

Hi, thanks for open sourcing this brilliant work! I read your paper in detail. You use ConvNeXt as the pretrained model of PointPillars. This is very pioneering. I want to...

wyf0414

when will release the code

1

I am really interested in your work. The model surprisingly doesn't use the sparseconv. When will you release your implemented code. Look forward to your reply!

c122-ode

How to correctly import an existing detection model and replace its feature extraction module with PillarNeSt, using it solely as a point cloud feature extraction module? I look forward to...

Lancer-Archer-Caster

The encoding of pillar

1

Thank you for excellent work. I'm a begginer. In your pillar encoder, has the number of points per pillar been limited by applying random sampling? Is it not dynamic encoding？

ouyangziyao