This is the official PyTorch implementation for our paper:

SparseOcc: Fully Sparse 3D Occupancy Prediction
🏫 Presented by Nanjing University and Shanghai AI Lab
📧 Primary contact: Haisong Liu ([email protected])
🏆 CVPR 2024 Autonomous Driving Challenge - Occupancy and Flow
📖 第三方中文解读: 自动驾驶之心，AIming。谢谢你们！

New model🥇: SparseOcc initially reconstructs a sparse 3D representation from visual inputs and subsequently predicts semantic/instance occupancy from the 3D sparse representation by sparse queries.

New evaluation metric📈: We design a thoughtful ray-based evaluation metric, namely RayIoU, to solve the inconsistency penalty along depths raised in traditional voxel-level mIoU criteria.

• 2024-04-11: The panoptic version of SparseOcc (configs/r50_nuimg_704x256_8f_pano.py) is released.
• 2024-04-09: An updated arXiv version https://arxiv.org/abs/2312.17118v3 has been released.
• 2024-03-31: We release the code and pretrained weights.
• 2023-12-30: We release the paper.

• FPS is measured with Intel(R) Xeon(R) Platinum 8369B CPU and NVIDIA A100-SXM4-80GB GPU (PyTorch fp32 backend, including data loading).
• We will release more settings in the future.

The requirements are the same as those of SparseBEV.

Install PyTorch 2.0 + CUDA 11.8:

conda create -n sparseocc python=3.8
conda activate sparseocc
conda install pytorch==2.0.0 torchvision==0.15.0 pytorch-cuda=11.8 -c pytorch -c nvidia

or PyTorch 1.10.2 + CUDA 10.2 for older GPUs:

conda create -n sparseocc python=3.8
conda activate sparseocc
conda install pytorch==1.10.2 torchvision==0.11.3 cudatoolkit=10.2 -c pytorch

Install other dependencies:

pip install openmim
mim install mmcv-full==1.6.0
mim install mmdet==2.28.2
mim install mmsegmentation==0.30.0
mim install mmdet3d==1.0.0rc6
pip install setuptools==59.5.0
pip install numpy==1.23.5

Install turbojpeg and pillow-simd to speed up data loading (optional but important):

sudo apt-get update
sudo apt-get install -y libturbojpeg
pip install pyturbojpeg
pip uninstall pillow
pip install pillow-simd==9.0.0.post1

Compile CUDA extensions:

cd models/csrc
python setup.py build_ext --inplace

The first two steps are the same as those of SparseBEV.

1. Download nuScenes from https://www.nuscenes.org/nuscenes, put it to data/nuscenes and preprocess it with mmdetection3d.

2. Download the generated info file from gdrive and unzip it. These *.pkl files can also be generated with our script: gen_sweep_info.py.

3. Download Occ3D-nuScenes occupancy GT from gdrive, unzip it, and save it to data/nuscenes/occ3d.

4. Folder structure:

data/nuscenes
├── maps
├── nuscenes_infos_test_sweep.pkl
├── nuscenes_infos_train_sweep.pkl
├── nuscenes_infos_val_sweep.pkl
├── samples
├── sweeps
├── v1.0-test
└── v1.0-trainval
└── occ3d
    ├── scene-0001
    │   ├── 0037a705a2e04559b1bba6c01beca1cf
    │   │   └── labels.npz
    │   ├── 026155aa1c554e2f87914ec9ba80acae
    │   │   └── labels.npz
    ...

5. (Optional) Generate the panoptic occupancy ground truth with gen_instance_info.py. The panoptic version of Occ3D will be saved to data/nuscenes/occ3d_panoptic.

Train SparseOcc with 8 GPUs:

torchrun --nproc_per_node 8 train.py --config configs/r50_nuimg_704x256_8f.py

Train SparseOcc with 4 GPUs (i.e the last four GPUs):

export CUDA_VISIBLE_DEVICES=4,5,6,7
torchrun --nproc_per_node 4 train.py --config configs/r50_nuimg_704x256_8f.py

The batch size for each GPU will be scaled automatically. So there is no need to modify the batch_size in config files.

Single-GPU evaluation:

export CUDA_VISIBLE_DEVICES=0
python val.py --config configs/r50_nuimg_704x256_8f.py --weights checkpoints/sparseocc_r50_nuimg_704x256_8f.pth

Multi-GPU evaluation:

export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
torchrun --nproc_per_node 8 val.py --config configs/r50_nuimg_704x256_8f.py --weights checkpoints/sparseocc_r50_nuimg_704x256_8f.pth

FPS is measured with a single GPU:

export CUDA_VISIBLE_DEVICES=0
python timing.py --config configs/r50_nuimg_704x256_8f.py --weights checkpoints/sparseocc_r50_nuimg_704x256_8f.pth

Many thanks to these excellent open-source projects:

• MaskFormer
• NeuralRecon
• 4D-Occ
• MMDetection3D