- 🔥(2023.2.28) LoGoNet has been accepted by CVPR 2023!
- 🔥(2023.3) Our improved version, LoGoNet_Ens v2, ranks 1st leaderboard among all submissions. All the submission, please refer the 3D object detection leaderboard of Waymo Open Dataset for more details.
- (2022.10) Our LoGoNet_Ens ranks 1st in the term of mAPH (L2) on the Waymo leaderboard among all methods with 81.02 mAPH (L2) and It is the first time for detection performance on three classes surpasses 80 APH (L2) simultaneously.
- (2022.10) Our LoGoNet ranks 1st in the term of mAPH (L2) on the Waymo leaderboard among all methods that don't use TTA and Ensemble.
| Model | VEH_L2 | PED_L2 | CYC_L2 |
|---|---|---|---|
| LoGoNet-1frame (val) | 71.21/70.71 | 75.49/69.94 | 74.53/73.48 |
| LoGoNet-3frames (val) | 74.60/74.17 | 78.62/75.79 | 75.44/74.61 |
| LoGoNet-5frames (val) | 75.84/75.38 | 78.97/76.33 | 75.67/74.91 |
| LoGoNet-5frames (test) | 79.69/79.30 | 81.55/78.91 | 73.89/73.10 |
| LoGoNet_Ens-5frames (test) | 82.17/81.72 | 84.27/81.28 | 80.93/80.06 |
| Model | Car@40 | Ped@40 | Cyc@40 |
|---|---|---|---|
| LoGoNet (val) | 87.13 | 64.46 | 79.84 |
| LoGoNet (test) | 85.87 | 48.57 | 73.61 |
We sincerely appreciate the following open-source projects for providing valuable and high-quality codes:
If you find our paper useful, please kindly cite us via:
@inproceedings{logonet,
title={LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion},
author={Xin Li and Tao Ma and Yuenan Hou and Botian Shi and Yuchen Yang and Youquan Liu and Xingjiao Wu and Qin Chen and Yikang Li and Yu Qiao and Liang He},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2023}
}