# Radar2Shape: 3D Shape Reconstruction from High-Frequency Radar using Multiresolution Signed Distance Functions

arXiv: https://arxiv.org/abs/2511.17484 · HTML: https://mlsanity.com/paper/2511.17484/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 59 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Learning a Predictable and Generative Vector Representation for Objects](https://mlsanity.com/paper/1603.08637/) (2016)
- [MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers](https://mlsanity.com/paper/2406.10163/) (2024)
- [Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions](https://mlsanity.com/paper/2211.13757/) (2022)
- [Locally Attentional SDF Diffusion for Controllable 3D Shape Generation](https://mlsanity.com/paper/2305.04461/) (2023)
- [Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks](https://mlsanity.com/paper/1909.00321/) (2019)
- [Subdivision-Based Mesh Convolution Networks](https://mlsanity.com/paper/2106.02285/) (2021)
- [Category-Specific Object Reconstruction from a Single Image](https://mlsanity.com/paper/1411.6069/) (2014)
- [VConv-DAE: Deep Volumetric Shape Learning Without Object Labels](https://mlsanity.com/paper/1604.03755/) (2016)
- [OctFusion: Octree-based Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2408.14732/) (2024)
- [D2IM-Net: Learning Detail Disentangled Implicit Fields from Single Images](https://mlsanity.com/paper/2012.06650/) (2020)
- [mmBody Benchmark: 3D Body Reconstruction Dataset and Analysis for Millimeter Wave Radar](https://mlsanity.com/paper/2209.05070/) (2022)
- [Single Image 3D Interpreter Network](https://mlsanity.com/paper/1604.08685/) (2016)
- [Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar](https://mlsanity.com/paper/2405.04662/) (2024)
- [Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar](https://mlsanity.com/paper/2001.10789/) (2020)
- [Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model](https://mlsanity.com/paper/2403.08460/) (2024)
- [DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models with 3D Diffusion Models](https://mlsanity.com/paper/2409.11601/) (2024)

## Abstract (arXiv)

Determining the shape of 3D objects from high-frequency radar signals is analytically complex but critical for commercial and aerospace applications. Previous deep learning methods have been applied to radar modeling; however, they often fail to represent arbitrary shapes or have difficulty with real-world radar signals which are collected over limited viewing angles. Existing methods in optical 3D reconstruction can generate arbitrary shapes from limited camera views, but struggle when they naively treat the radar signal as a camera view. In this work, we present Radar2Shape, a denoising diffusion model that handles a partially observable radar signal for 3D reconstruction by correlating its frequencies with multiresolution shape features. Our method consists of a two-stage approach: first, Radar2Shape learns a regularized latent space with hierarchical resolutions of shape features, and second, it diffuses into this latent space by conditioning on the frequencies of the radar signal in an analogous coarse-to-fine manner. We demonstrate that Radar2Shape can successfully reconstruct arbitrary 3D shapes even from partially-observed radar signals, and we show robust generalization to two different simulation methods and real-world data. Additionally, we release two synthetic benchmark datasets to encourage future research in the high-frequency radar domain so that models like Radar2Shape can safely be adapted into real-world radar systems.