cs.CVNov 3, 2026

Lightweight graph transformers for clutter and target classification in automotive radar

Authors: Adrian Gheorghiu, Tunc Alkanat, Ashish Pandharipande

Organizations: NXP Semiconductors, The Netherlands

Abstract

Radar is a core sensor modality for scene perception to achieve higher levels of autonomy in automotive driving. A common occurrence in automotive radars is clutter - detections of non-existent moving objects, that can adversely impact target detection and classification performance and subsequent driving actions. We propose lightweight tiny graph transformer network (TGTNet) models for classifying clutter from stationary and moving targets in the scene. Performance evaluation on the public RadarScenes show that our proposed TGTNet models achieve similar classification performance in precision and recall metrics in comparison to state of the art models, with one to two orders of magnitude lower model size and significantly faster inference.

Figures & tables

Explore similar work

Nov 15, 2026

Radar Panoptic Transformer: Semantic-Guided Mask Queries for Dynamic Scene Understanding

Automotive radar provides long-range sensing and direct Doppler velocity measurements, but its sparse and non-uniformly sampled point clouds pose significant challenges for panoptic segmentation. Dynamic objects often yield only a few detections amid a dominant static background, providing limiting the geometric cues for separating object instances. We propose Radar Panoptic Transformer (RPT), an end-to-end point-based network that incorporates radar-adaptive feature extraction with semantic-guided mask prediction. Its backbone aggregates pose-aligned temporal context through grouped vector attention and learns per-point neighborhood radii conditioned on range, azimuth, and radar cross section (RCS). Point-wise semantic predictions initialize queries at likely foreground detections and guide masked cross-attention through query-point class agreement, producing instance masks without geometric clustering. An auxiliary RCS-consistency loss matches instance-level statistics between predicted and annotated instances. RPT achieves state-of-the-art performance on RadarScenes with 71.6%71.6\% mIoU and 82.2%82.2\% PQ. We further evaluate RPT on MAN TruckScenes, where it outperforms the evaluated baselines in a long-range, full-surround radar setting with sensing ranges up to 230 m230\,\mathrm{m}. RPT achieves real-time end-to-end inference at 3131,Hz on RadarScenes, exceeding the sensor frame rate.
Nov 16, 2026

DRaGAN: Dynamic Graph Attention Network for Multi-Radar Point Cloud Encoding in Automotive Radar Perception

Radar represents a key modality for weather-robust perception. Unlike optical sensors such as camera and LiDAR, radar can penetrate fog, rain and snow due to its longer wavelength, and recent hardware advances have steadily improved its spatial resolution, thus making it increasingly relevant for autonomous systems. While processing raw radar data requires substantial memory computation, most existing work has focused on preprocessed point-cloud data similar to LiDAR. However, the sparse radar points and sensor-relative anisotropy make LiDAR-oriented encoders suboptimal. To address this problem, we present DRaGAN, a dynamic graph attention network for multi-radar point clouds. DRaGAN introduces a sensor-relative Fourier encoding of angle and range to capture fixed-aperture radar characteristics, gated short- and long-range hub nodes along each sensor's line of sight for efficient local-global message passing, and attention-guided dynamic rewiring that prunes weak edges and adds a bounded number of latent connections restricted to two-hop neighborhoods. This reduces the number of processed edges in deeper layers while preserving representation quality. On TruckScenes, DRaGAN improves test NDS by 10.10 points over the evaluated RadarGNN baseline and reduces the reported model FLOP count by 63.7%. This trade-off includes an increase in model latency from 40 to 53.16 ms and in trainable parameters from 1.2M to 1.7M on the evaluated implementations. Code and pretrained models are available at https://github.com/chr-is-tof/DRaGAN.
Feb 23, 2026

RADE-Net: Robust Attention Network for Radar-Only Object Detection in Adverse Weather

Automotive perception systems are obligated to meet high requirements. While optical sensors such as Camera and Lidar struggle in adverse weather conditions, Radar provides a more robust perception performance, effectively penetrating fog, rain, and snow. Since full Radar tensors have large data sizes and very few datasets provide them, most Radar-based approaches work with sparse point clouds or 2D projections, which can result in information loss. Additionally, deep learning methods show potential to extract richer and more dense features from low level Radar data and therefore significantly increase the perception performance. Therefore, we propose a 3D projection method for fast-Fourier-transformed 4D Range-Azimuth-Doppler-Elevation (RADE) tensors. Our method preserves rich Doppler and Elevation features while reducing the required data size for a single frame by 91.9% compared to a full tensor, thus achieving higher training and inference speed as well as lower model complexity. We introduce RADE-Net, a lightweight model tailored to 3D projections of the RADE tensor. The backbone enables exploitation of low-level and high-level cues of Radar tensors with spatial and channel-attention. The decoupled detection heads predict object center-points directly in the Range-Azimuth domain and regress rotated 3D bounding boxes from rich feature maps in the cartesian scene. We evaluate the model on scenes with multiple different road users and under various weather conditions on the large-scale K-Radar dataset and achieve a 16.7% improvement compared to their baseline, as well as 6.5% improvement over current Radar-only models. Additionally, we outperform several Lidar approaches in scenarios with adverse weather conditions. The code is available under https://github.com/chr-is-tof/RADE-Net.