# Radar Occupancy Prediction with Lidar Supervision while Preserving Long-Range Sensing and Penetrating Capabilities

arXiv: https://arxiv.org/abs/2112.04282 · HTML: https://mlsanity.com/paper/2112.04282/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 8 Dec 2021.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset](https://mlsanity.com/paper/1909.01300/) (2019)
- [RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radar](https://mlsanity.com/paper/2004.03451/) (2020)
- [Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar](https://mlsanity.com/paper/2001.10789/) (2020)
- [Probably Unknown: Deep Inverse Sensor Modelling In Radar](https://mlsanity.com/paper/1810.08151/) (2018)
- [Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning](https://mlsanity.com/paper/2001.09438/) (2020)
- [Masking by Moving: Learning Distraction-Free Radar Odometry from Pose Information](https://mlsanity.com/paper/1909.03752/) (2019)
- [RadarSLAM: Radar based Large-Scale SLAM in All Weathers](https://mlsanity.com/paper/2005.02198/) (2020)
- [There and Back Again: Learning to Simulate Radar Data for Real-World Applications](https://mlsanity.com/paper/2011.14389/) (2020)
- [Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning](https://mlsanity.com/paper/2105.14152/) (2021)
- [A Normal Distribution Transform-Based Radar Odometry Designed For Scanning and Automotive Radars](https://mlsanity.com/paper/2103.07908/) (2021)
- [Radar-only ego-motion estimation in difficult settings via graph matching](https://mlsanity.com/paper/1904.11476/) (2019)
- [Radar-on-Lidar: metric radar localization on prior lidar maps](https://mlsanity.com/paper/2005.04644/) (2020)

## Built on by (most cited first, 5 of 5)

- [RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenes](https://mlsanity.com/paper/2506.01379/) (2025)
- [Bootstrapping Autonomous Driving Radars with Self-Supervised Learning](https://mlsanity.com/paper/2312.04519/) (2023)
- [FSF-Net: Enhance 4D Occupancy Forecasting with Coarse BEV Scene Flow for Autonomous Driving](https://mlsanity.com/paper/2409.15841/) (2024)
- [RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes](https://mlsanity.com/paper/2505.20967/) (2025)
- [Deep learning for radar data exploitation of autonomous vehicle](https://mlsanity.com/paper/2203.08038/) (2022)

## Abstract (arXiv)

Radar shows great potential for autonomous driving by accomplishing long-range sensing under diverse weather conditions. But radar is also a particularly challenging sensing modality due to the radar noises. Recent works have made enormous progress in classifying free and occupied spaces in radar images by leveraging lidar label supervision. However, there are still several unsolved issues. Firstly, the sensing distance of the results is limited by the sensing range of lidar. Secondly, the performance of the results is degenerated by lidar due to the physical sensing discrepancies between the two sensors. For example, some objects visible to lidar are invisible to radar, and some objects occluded in lidar scans are visible in radar images because of the radar's penetrating capability. These sensing differences cause false positive and penetrating capability degeneration, respectively. In this paper, we propose training data preprocessing and polar sliding window inference to solve the issues. The data preprocessing aims to reduce the effect caused by radar-invisible measurements in lidar scans. The polar sliding window inference aims to solve the limited sensing range issue by applying a near-range trained network to the long-range region. Instead of using common Cartesian representation, we propose to use polar representation to reduce the shape dissimilarity between long-range and near-range data. We find that extending a near-range trained network to long-range region inference in the polar space has 4.2 times better IoU than in Cartesian space. Besides, the polar sliding window inference can preserve the radar penetrating capability by changing the viewpoint of the inference region, which makes some occluded measurements seem non-occluded for a pretrained network.