mlsanityData to 14 Oct 2026

Enabling Visual Recognition at Radio Frequency

arXiv 2405.19516 ↗First posted 29 May 2024eess.SP cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

This paper introduces PanoRadar, a novel RF imaging system that brings RF resolution close to that of LiDAR, while providing resilience against conditions challenging for optical signals. Our LiDAR-comparable 3D imaging results enable, for the first time, a variety of visual recognition tasks at radio frequency, including surface normal estimation, semantic segmentation, and object detection. PanoRadar utilizes a rotating single-chip mmWave radar, along with a combination of novel signal processing and machine learning algorithms, to create high-resolution 3D images of the surroundings. Our system accurately estimates robot motion, allowing for coherent imaging through a dense grid of synthetic antennas. It also exploits the high azimuth resolution to enhance elevation resolution using learning-based methods. Furthermore, PanoRadar tackles 3D learning via 2D convolutions and addresses challenges due to the unique characteristics of RF signals. Our results demonstrate PanoRadar's robust performance across 12 buildings.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 24 of its 93 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

24 of 93 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  7. 2015Fast R-CNNcited by 2,933
  8. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  9. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  10. 2020A Survey of Deep Active Learningcited by 554
  11. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  12. 2019The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Datasetcited by 134
12 more
  1. 2022Boreas: A Multi-Season Autonomous Driving Datasetcited by 76
  2. 2021AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognitioncited by 36
  3. 2018Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360deg Panoramic Imagerycited by 35
  4. 2019See Through Smoke: Robust Indoor Mapping with Low-cost mmWave Radarcited by 35
  5. 2019Making the Invisible Visible: Action Recognition Through Walls and Occlusionscited by 25
  6. 2022Pointillism: Accurate 3D bounding box estimation with multi-radarscited by 23
  7. 2022High Resolution Point Clouds from mmWave Radarcited by 23
  8. 2018mD-Track: Leveraging Multi-Dimensionality in Passive Indoor Wi-Fi Trackingcited by 17
  9. 2018Probably Unknown: Deep Inverse Sensor Modelling In Radarcited by 16
  10. 20213DRIMR: 3D Reconstruction and Imaging via mmWave Radar based on Deep Learningcited by 16
  11. 2020Deep Depth Estimation from Visual-Inertial SLAMcited by 13
  12. 2021DeepPoint: A Deep Learning Model for 3D Reconstruction in Point Clouds via mmWave Radarcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 5.

11 papers.

  1. 2025Towards Foundational Models for Single-Chip Radarcited by 6
  2. 2025Scalable RF Simulation in Generative 4D Worldscited by 2
  3. 2025RaLD: Generating High-Resolution 3D Radar Point Clouds with Latent Diffusioncited by 1
  4. 2025RaGNNarok: A Light-Weight Graph Neural Network for Enhancing Radar Point Clouds on Unmanned Ground Vehiclescited by 0
  5. 2025Towards Seeing Bones at Radio Frequencycited by 0
  6. 2025Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completioncited by 0
  7. 2026Rascene: High-Fidelity 3D Scene Imaging with mmWave Communication Signalscited by 0
  8. 2026RF-LEGO: Modularized Signal Processing-Deep Learning Co-Design for RF Sensing via Deep Unrollingcited by 0
  9. 2026GeRaF: Neural Geometry Reconstruction from Radio Frequency Signalscited by 0
  10. 2026Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signalscited by 0
  11. 2026GRADE: Single-Frame Generative Radar Depth Estimation Under Visual Degradationcited by 0