CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection
This addresses the problem of multi-modal fusion for autonomous driving systems, offering a low-complexity solution that enhances detection accuracy, though it is incremental as it builds on existing single-modality detectors.
The paper tackles the challenge of effectively fusing camera and LiDAR data for 3D object detection by proposing the CLOCs fusion network, which improves performance over single-modality detectors and achieves state-of-the-art results on the KITTI benchmark, especially at long distances.
There have been significant advances in neural networks for both 3D object detection using LiDAR and 2D object detection using video. However, it has been surprisingly difficult to train networks to effectively use both modalities in a way that demonstrates gain over single-modality networks. In this paper, we propose a novel Camera-LiDAR Object Candidates (CLOCs) fusion network. CLOCs fusion provides a low-complexity multi-modal fusion framework that significantly improves the performance of single-modality detectors. CLOCs operates on the combined output candidates before Non-Maximum Suppression (NMS) of any 2D and any 3D detector, and is trained to leverage their geometric and semantic consistencies to produce more accurate final 3D and 2D detection results. Our experimental evaluation on the challenging KITTI object detection benchmark, including 3D and bird's eye view metrics, shows significant improvements, especially at long distance, over the state-of-the-art fusion based methods. At time of submission, CLOCs ranks the highest among all the fusion-based methods in the official KITTI leaderboard. We will release our code upon acceptance.