Closed lubinBoooos closed 1 year ago
After reading the paper of Scene as Occupancy I am troubled by the effectiveness of cascade voxel decoder. When I come out to read the code OCCNET, I cannot find the implementation of cascade voxel decoder, perhaps the decoder is not necessary ?
The cascade voxel decoder is implemented in the code. Please refer to https://github.com/OpenDriveLab/OccNet/blob/HEAD/projects/mmdet3d_plugin/bevformer/modules/hybrid_transformer.py#L25-L26
After reading the paper of Scene as Occupancy I am troubled by the effectiveness of cascade voxel decoder. When I come out to read the code OCCNET, I cannot find the implementation of cascade voxel decoder, perhaps the decoder is not necessary ?