Leveraging Transformer Decoder for Automotive Radar Object Detection

In this paper, we present a Transformer-based architecture for 3D radar object detection that uses a novel Transformer Decoder as the prediction head to directly regress 3D bounding boxes and class scores from radar feature representations. To bridge multi-scale radar features and the decoder, we propose Pyramid Token Fusion (PTF), a lightweight module that converts a feature pyramid into a unified, scale-aware token sequence. By formulating detection as a set prediction problem with learnable object queries and positional encodings, our design models long-range spatial-temporal correlations and cross-feature interactions. This approach eliminates dense proposal generation and heuristic post-processing such as extensive non-maximum suppression (NMS) tuning. We evaluate the proposed framework on the RADDet, where it achieves significant improvements over state-of-the-art radar-only baselines.

Synthetic FMCW Radar Range Azimuth Maps Augmentation with Generative Diffusion Model

The scarcity and low diversity of well-annotated automotive radar datasets often limit the performance of deep-learning-based environmental perception. To overcome these challenges, we propose a conditional generative framework for synthesizing realistic Frequency-Modulated Continuous-Wave radar Range-Azimuth Maps. Our approach leverages a generative diffusion model to generate radar data for multiple object categories, including pedestrians, cars, and cyclists. Specifically, conditioning is achieved via Confidence Maps, where each channel represents a semantic class and encodes Gaussian-distributed annotations at target locations. To address radar-specific characteristics, we incorporate Geometry Aware Conditioning and Temporal Consistency Regularization into the generative process. Experiments on the ROD2021 dataset demonstrate that signal reconstruction quality improves by \SI{3.6}{dB} in Peak Signal-to-Noise Ratio over baseline methods, while training with a combination of real and synthetic datasets improves overall mean Average Precision by 4.15% compared with conventional image-processing-based augmentation. These results indicate that our generative framework not only produces physically plausible and diverse radar spectrum but also substantially improves model generalization in downstream tasks.

Warping of Radar Data into Camera Image for Cross-Modal Supervision in Automotive Applications

In this paper, we present a novel framework to project automotive radar range-Doppler (RD) spectrum into camera image. The utilized warping operation is designed to be fully differentiable, which allows error backpropagation through the operation. This enables the training of neural networks (NN) operating exclusively on RD spectrum by utilizing labels provided from camera vision models. As the warping operation relies on accurate scene flow, additionally, we present a novel scene flow estimation algorithm fed from camera, lidar and radar, enabling us to improve the accuracy of the warping operation. We demonstrate the framework in multiple applications like direction-of-arrival (DoA) estimation, target detection, semantic segmentation and estimation of radar power from camera data. Extensive evaluations have been carried out for the DoA application and suggest superior quality for NN based estimators compared to classical estimators. The novel scene flow estimation approach is benchmarked against state-of-the-art scene flow algorithms and outperforms them by roughly a third.