In this paper, we propose a neural network for object detection and heading forecasting based on radar by fusing three raw radar channels with a cross-attention mechanism. We also introduce an improved ground truth augmentation method based on Bivariate norm, which represents the object labels in a more realistic form for radar measurements. Our results show 5% better mAP compared to state-of-the-art methods.

In this paper, we propose a Neural Radiance Fields (NeRF) based framework, referred to as Novel View Synthesis Framework (NVSF). It jointly learns the implicit neural representation of space and time-varying scene for both LiDAR and Camera. We test this on a real-world autonomous driving scenario containing both static and dynamic scenes. Compared to existing multimodal dynamic NeRFs, our framework is self-supervised, thus eliminating the need for 3D labels. For efficient training and faster convergence, we introduce heuristic based image pixel sampling to focus on pixels with rich information. To preserve the local features of LiDAR points, a Double Gradient based mask is employed. Extensive experiments on the KITTI-360 dataset show that, compared to the baseline models, our Framework has reported best performance on both LiDAR and Camera domain.