• Our dataset is freely available to researchers. Please download and sign our agreement and send it to the provided email address ([email protected]). You will receive the download link within one week.

• The calib.txt contains tree parts. The dataset consists of two parts: the data part and the alignment calibration file. The data part is image data in png format and point cloud data in bin format. The alignment calibration file includes calibration parameters for the four sensors. The camera-LiDAR, camera-4D radar joint calibration are shown here as examples for illustration.

   S2R-Bench_cam.Intrinsics.RadialDistortion: Barrel distortion of Dual Radar_cam [ k1, k2, k3 ]
   S2R-Bench_cam.Intrinsics.TangentialDistortion: radial distortion of Dual Radar_cam [ p1, p2 ]
   S2R-Bench_cam.IntrinsicMatrix: Dual Radar_cam's intrinsic matrix [ af, 0, 0; 0, bf, 0; u, v, 1]
   S2R-Bench_LiDAR-->Dual Radar_cam: Dual Radar_lidar to Dual Radar cam's single response matrix P(4×4)
   S2R-Bench_radar--> Dual Radar_cam: Dual Radar_radar to Dual Radar_cam rotation matrix + translation matrix P(3×4)

• All values (numerical or strings) are separated via spaces, each row corresponds to one object. The 19 columns represent:

  Value       Name             Description
  -------------------------------------------------------------------------------------------------------
  1        type               Describes the type of object: 'Car', 'Van', 'Truck', 'Pedestrian',  'Person_sitting', 'Cyclist', 'Tram', 'Misc' or 'DonCare'
  1        truncated          Float from 0 (non-truncated) to 1 (truncated), where truncated refers to the object leaving image boundaries
  1        occluded           Integer (0,1,2,3) indicating occlusion state: 0 = fully visible, 1 = partly ccluded, 2 = largely occluded, 3 = unknown
  1        alpha              Observation angle of object, ranging [-pi..pi]
  4        bbox               2D bounding box of object in the image (0-based index): contains left, top, right, bottom pixel coordinates. 
  3        dimensions         3D object dimensions: height, width, length (in meters).
  3        location           3D object location x,y,z in camera coordinates (in meters).
  1        rotation_y         Rotation ry around Y-axis in camera coordinates [-pi..pi].
  1        score              Only for results: Float,indicating confidence in detection, needed for p/r curves , higher is better.
  1        track_id           Path tracking of the same object

• Since the labeling work is done in label coordinate, the bounding box out of the image FOV(1920×1080) needs to be cut.

Figure 6. The statistics of the number of objects in different labels. The result suggests that the main labels like Car, Pedestrian, and Cyclist take up over three-quarters of the total amount of objects.

• We performed a118statistical analysis of the 9981 frames of labeled data, counting the number of objects in each label category, as shown in Fig 5.A pie chart illustrates the counts of objects in the top six labeled categories, with the "others" category primarily consisting of tricycles. As shown in the figure, the majority of labels are concentrated in the categories of "car", "pedestrian", and "cyclist", accounting for approximately 53%, 20%, and 19%, respectively.

Figure 7. The statistic of different annotated objects at different ranges of distance from the ego vehicle. From the results, the majority of the annotated objects are in the range of 20m-80m.

• We also conduct a statistical analysis of the number of objects with each label at different distance ranges from our vehicle, as shown in Figure 7. Most objects are within 60 meters of our ego vehicle.

This is the documentation for how to use our detection frameworks with Dual-Radar dataset. We test the Dual-Radar detection frameworks on the following environment:

• Python 3.8.16 (3.10+ does not support open3d.)
• Ubuntu 18.04/20.04
• Torch 1.10.1+cu113
• CUDA 11.3
• opencv 4.2.0.32

• Clone the repository

 git clone https://github.com/adept-thu/****.git
 cd ****

• Create a conda environment

conda create -n Dual-Radardet python=3.8.16
conda activate Dual-Radardet

• Install PyTorch (We recommend pytorch 1.10.1.)

• Install the dependencies

pip install -r requirements.txt

• Install Spconv（our cuda version is 113）

pip install spconv-cu113

• Build packages for Dual-Radardet

python setup.py develop

Here we provide a quick demo to test a pretrained model on the custom point cloud data and visualize the predicted results

• Download the pretrained model as shown in Table 4~8.
• Make sure you have installed the Open3d and mayavi visualization tools. If not, you could install it as follow:

pip install open3d
pip install mayavi

• prepare your point cloud data

points[:, 3] = 0 
np.save(`my_data.npy`, points)

• Run the demo with a pretrained model and point cloud data as follows

python demo.py --cfg_file ${CONFIG_FILE} \
    --ckpt ${CKPT} \
    --data_path ${POINT_CLOUD_DATA}

THE COMPARISON OF THE “CAR” CATEGORY WITH THE POINTPILLARS MODEL AT MEDIUM DIFFICULTY USING "S2R-C".

THE COMPARISON OF THE “CAR” CATEGORY WITH THE SMOKE MODEL AT MEDIUM DIFFICULTY USING “S2R-C”.

THE COMPARISON OF THE “CAR” CATEGORY WITH THE FOCALS CONV MODEL AT MEDIUM DIFFICULTY USING S2R-C.

THE COMPARISON OF THE “CAR” CATEGORY WITH THE POINTPILLARS MODEL AT MEDIUM DIFFICULTY USING SIMULATED-DATASET.

• Thanks for the sensor support provided by Beijing Jingwei Hirain Technologies Co., Inc.

@misc{wang2025s2rbenchsimtorealevaluationbenchmark,
      title={S2R-Bench: A Sim-to-Real Evaluation Benchmark for Autonomous Driving}, 
      author={Li Wang and Guangqi Yang and Lei Yang and Ziying Song and Xinyu Zhang and Ying Chen and Lin Liu and Junjie Gao and Zhiwei Li and Qingshan Yang and Jun Li and Liangliang Wang and Wenhao Yu and Bin Xu and Weida Wang and Huaping Liu},
      year={2025},
      eprint={2505.18631},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2505.18631}, 
}