cs.CVNov 15, 2026

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

Authors: Mayank Mayank, Bharanidhar Duraisamy, Rohit Mohan, Abhinav Valada

Organizations: Research and Development, Mercedes-Benz AG, Germany. · Department of Computer Science, University of Freiburg, Germany. · Institute for Intelligent Systems, Esslingen University of Applied Sciences, Germany.

Abstract

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.

Figures & tables

Explore similar work

CardsList
  1. Real-Time Radar Semantic and Panoptic Scene Understanding

    Oct 19, 2026Santosh Parit, Julia Hindel, Rohit Mohan +4Autonomous Driving PerceptionPanoptic Segmentation

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

    Nov 16, 2026Christof Leitgeb, Thomas Puchleitner, Max Peter Ronecker +1Autonomous Driving PerceptionPoint Cloud Learning

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

    Feb 23, 2026Christof Leitgeb, Thomas Puchleitner, Max Peter Ronecker +13D Object DetectionmmWave Radar Sensing