# DREAM-PCD: Deep Reconstruction and Enhancement of mmWave Radar Pointcloud

arXiv: https://arxiv.org/abs/2309.15374 · HTML: https://mlsanity.com/paper/2309.15374/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2023.

## Built on by (most cited first, 13 of 13)

- [Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model](https://mlsanity.com/paper/2403.08460/) (2024)
- [Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems](https://mlsanity.com/paper/2407.09352/) (2024)
- [Diffusion-Based mmWave Radar Point Cloud Enhancement Driven by Range Images](https://mlsanity.com/paper/2503.02300/) (2025)
- [HyperDet: 3D Object Detection with Hyper 4D Radar Point Clouds](https://mlsanity.com/paper/2602.11554/) (2026)
- [R3D: Regional-guided Residual Radar Diffusion](https://mlsanity.com/paper/2601.06465/) (2026)
- [RaLD: Generating High-Resolution 3D Radar Point Clouds with Latent Diffusion](https://mlsanity.com/paper/2511.07067/) (2025)
- [IFNet: Deep Imaging and Focusing for Handheld SAR with Millimeter-wave Signals](https://mlsanity.com/paper/2405.02023/) (2024)
- [Geographical hotspot prediction based on point cloud-voxel-community partition clustering](https://mlsanity.com/paper/2503.21084/) (2025)
- [Electromagnetic Inverse Scattering from a Single Transmitter](https://mlsanity.com/paper/2506.21349/) (2025)
- [RaGNNarok: A Light-Weight Graph Neural Network for Enhancing Radar Point Clouds on Unmanned Ground Vehicles](https://mlsanity.com/paper/2507.00937/) (2025)
- [Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completion](https://mlsanity.com/paper/2511.14152/) (2025)
- [Radar2Shape: 3D Shape Reconstruction from High-Frequency Radar using Multiresolution Signed Distance Functions](https://mlsanity.com/paper/2511.17484/) (2025)
- [Depth-Semantic Alignment and Affinity-Guided Fusion for Structured Radar Point Cloud Generation](https://mlsanity.com/paper/2606.26743/) (2026)

## Abstract (arXiv)

Millimeter-wave (mmWave) radar pointcloud offers attractive potential for 3D sensing, thanks to its robustness in challenging conditions such as smoke and low illumination. However, existing methods failed to simultaneously address the three main challenges in mmWave radar pointcloud reconstruction: specular information lost, low angular resolution, and strong interference and noise. In this paper, we propose DREAM-PCD, a novel framework that combines signal processing and deep learning methods into three well-designed components to tackle all three challenges: Non-Coherent Accumulation for dense points, Synthetic Aperture Accumulation for improved angular resolution, and Real-Denoise Multiframe network for noise and interference removal. Moreover, the causal multiframe and "real-denoise" mechanisms in DREAM-PCD significantly enhance the generalization performance. We also introduce RadarEyes, the largest mmWave indoor dataset with over 1,000,000 frames, featuring a unique design incorporating two orthogonal single-chip radars, lidar, and camera, enriching dataset diversity and applications. Experimental results demonstrate that DREAM-PCD surpasses existing methods in reconstruction quality, and exhibits superior generalization and real-time capabilities, enabling high-quality real-time reconstruction of radar pointcloud under various parameters and scenarios. We believe that DREAM-PCD, along with the RadarEyes dataset, will significantly advance mmWave radar perception in future real-world applications.