Model Zoo

Common settings

• We use distributed training.

• For fair comparison with other codebases, we report the GPU memory as the maximum value of torch.cuda.max_memory_allocated() for all 8 GPUs. Note that this value is usually less than what nvidia-smi shows.

• We report the inference time as the total time of network forwarding and post-processing, excluding the data loading time. Results are obtained with the script benchmark.py which computes the average time on 2000 images.

Baselines

SECOND

Please refer to SECOND for details. We provide SECOND baselines on KITTI and Waymo datasets.

PointPillars

Please refer to PointPillars for details. We provide pointpillars baselines on KITTI, nuScenes, Lyft, and Waymo datasets.

Part-A2

Please refer to Part-A2 for details.

VoteNet

Please refer to VoteNet for details. We provide VoteNet baselines on ScanNet and SUNRGBD datasets.

Dynamic Voxelization

Please refer to Dynamic Voxelization for details.

MVXNet

Please refer to MVXNet for details.

RegNetX

Please refer to RegNet for details. We provide pointpillars baselines with RegNetX backbones on nuScenes and Lyft datasets currently.

nuImages

We also support baseline models on nuImages dataset. Please refer to nuImages for details. We report Mask R-CNN, Cascade Mask R-CNN and HTC results currently.

H3DNet

Please refer to H3DNet for details.

3DSSD

Please refer to 3DSSD for details.

CenterPoint

Please refer to CenterPoint for details.

SSN

Please refer to SSN for details. We provide pointpillars with shape-aware grouping heads used in SSN on the nuScenes and Lyft datasets currently.

ImVoteNet

Please refer to ImVoteNet for details. We provide ImVoteNet baselines on SUNRGBD dataset.

FCOS3D

Please refer to FCOS3D for details. We provide FCOS3D baselines on the nuScenes dataset.

PointNet++

Please refer to PointNet++ for details. We provide PointNet++ baselines on ScanNet and S3DIS datasets.

Group-Free-3D

Please refer to Group-Free-3D for details. We provide Group-Free-3D baselines on ScanNet dataset.

ImVoxelNet

Please refer to ImVoxelNet for details. We provide ImVoxelNet baselines on KITTI dataset.

PAConv

Please refer to PAConv for details. We provide PAConv baselines on S3DIS dataset.

DGCNN

Please refer to DGCNN for details. We provide DGCNN baselines on S3DIS dataset.

SMOKE

Please refer to SMOKE for details. We provide SMOKE baselines on KITTI dataset.

PGD

Please refer to PGD for details. We provide PGD baselines on KITTI and nuScenes dataset.

PointRCNN

Please refer to PointRCNN for details. We provide PointRCNN baselines on KITTI dataset.

MonoFlex

Please refer to MonoFlex for details. We provide MonoFlex baselines on KITTI dataset.

SA-SSD

Please refer to SA-SSD for details. We provide SA-SSD baselines on the KITTI dataset.

FCAF3D

Please refer to FCAF3D for details. We provide FCAF3D baselines on the ScanNet, S3DIS, and SUN RGB-D datasets.

PV-RCNN

Please refer to PV-RCNN for details. We provide PV-RCNN baselines on the KITTI dataset.

BEVFusion

Please refer to BEVFusion for details. We provide BEVFusion baselines on the NuScenes dataset.

CenterFormer

Please refer to CenterFormer for details. We provide CenterFormer baselines on the Waymo dataset.

TR3D

Please refer to TR3D for details. We provide TR3D baselines on the ScanNet, SUN RGB-D and S3DIS dataset.

DETR3D

Please refer to DETR3D for details. We provide DETR3D baselines on the nuScenes dataset.

PETR

Please refer to PETR for details. We provide PETR baselines on the nuScenes dataset.

TPVFormer

Please refer to TPVFormer for details. We provide TPVFormer baselines on the nuScenes dataset.

Mixed Precision (FP16) Training

Please refer to Mixed Precision (FP16) Training on PointPillars for details.