Yunpeng Zhang, Jiwen Lu, Jie zhou
The precise localization of 3D objects from a single image without depth information is a highly challenging problem. Most existing methods adopt the same approach for all objects regardless of their diverse distributions, leading to limited performance for truncated objects. In this paper, we propose a flexible framework for monocular 3D object detection which explicitly decouples the truncated objects and adaptively combines multiple approaches for object depth estimation. Specifically, we decouple the edge of the feature map for predicting long-tail truncated objects so that the optimization of normal objects is not influenced. Furthermore, we formulate the object depth estimation as an uncertainty-guided ensemble of directly regressed object depth and solved depths from different groups of keypoints. Experiments demonstrate that our method outperforms the state-of-the-art method by relatively 27\% for the moderate level and 30\% for the hard level in the test set of KITTI benchmark while maintaining real-time efficiency. Code will be available at \url{https://github.com/zhangyp15/MonoFlex}.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Object Detection | KITTI Cars Moderate | AP Medium | 13.89 | MonoFLEX |
| 3D | KITTI Cars Moderate | AP Medium | 13.89 | MonoFLEX |
| 3D Object Detection | KITTI Cars Moderate | AP Medium | 13.89 | MonoFLEX |
| 2D Classification | KITTI Cars Moderate | AP Medium | 13.89 | MonoFLEX |
| 2D Object Detection | KITTI Cars Moderate | AP Medium | 13.89 | MonoFLEX |
| 16k | KITTI Cars Moderate | AP Medium | 13.89 | MonoFLEX |