README.md

September 23, 2025 · View on GitHub

Accepted to ICRA 2025!

Deep Height Decoupling for Precise Vision-based 3D Occupancy Prediction

Yuan Wu1*;, Zhiqiang Yan1*† , Zhengxue Wang1, Xiang Li2, Le Hui3, Jian Yang1†

*equal contribution    †corresponding author   
1Nanjing University of Science and Technology    2Nankai University    3Northwestern Polytechnical University   

[Paper] [Project Page]

demo

Method

model

DHD comprises a feature extractor, HeightNet, DepthNet, MGHS, SFA, and predictor. The feature extractor first acquires 2D image feature. Then, DepthNet extracts context feature and depth prediction. HeightNet generates the height map to determine the height value at each pixel. Next, MGHS integrates the output of HeightNet and DepthNet, acquiring height-refined feature and depth-based feature. Finally, the dual features are fed into the SFA to obtain the aggregated feature, which serves as input for the predictor.

Get Started

Installation and Data Preparation

Step1、Prepare environment as that in Install.

Step2、Prepare nuScene and generate pkl file by runing：

python tools/create_data_bevdet.py

The final directory structure for 'data' folder is like

└── data
  └── nuscenes
      ├── v1.0-trainval
      ├── maps  
      ├── sweeps  
      ├── samples
      ├── gts
      ├── bevdetv2-nuscenes_infos_train.pkl 
      └── bevdetv2-nuscenes_infos_val.pkl

Train & Test

# train:
tools/dist_train.sh ${config} ${num_gpu}
# train DHD-S:
tools/dist_train.sh projects/configs/DHD/DHD-S.py 4

# test:
tools/dist_test.sh ${config} ${ckpt} ${num_gpu} --eval mAP
# test DHD-S:
tools/dist_test.sh projects/configs/DHD/DHD-S.py model_weight/DHD-S.pth 4 --eval mAP

Model weights

The pretrained weights in 'ckpts' folder can be found here.

All DHD model weights can be found here.

Experiment

Quantitative comparison

tab

Visual comparison

model

Acknowledgements

Many thanks to the authors of BEVDet and FlashOcc.

Citation

@inproceedings{wu2025deep,
  title={Deep height decoupling for precise vision-based 3d occupancy prediction},
  author={Wu, Yuan and Yan, Zhiqiang and Wang, Zhengxue and Li, Xiang and Hui, Le and Yang, Jian},
  booktitle={2025 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={12647--12654},
  year={2025},
  organization={IEEE}
}