Question about the Position of Lidar Backbone in the Model Architecture

mit-han-lab / bevfusion

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

https://bevfusion.mit.edu

Apache License 2.0

2.37k stars 428 forks source link

Question about the Position of Lidar Backbone in the Model Architecture #576

Closed barrydoooit closed 4 months ago

barrydoooit commented 11 months ago

Hi Authors, thanks for your fancy paper and code. I've been reading the forward procedures of BEVFusion. Regarding these lines, it shows that the Lidar backbone SECOND is applied after the fusion module. I wonder that if this is an update from your original design, or that "Lidar Backbone" is actually the "BEV encoder" shown in Fig 2 (the model pipeline) of your paper. Looking forward to your reply.

zhijian-liu commented 4 months ago

Thank you for your interest in our project. This repository is no longer actively maintained, so we will be closing this issue. Please refer to the amazing implementation at MMDetection3D. Thank you again!