3D Point Splatting for mmWave Radar Novel View Synthesis

• URL: http://arxiv.org/abs/2609.11894v1
• Date: Thu, 10 Sep 2026 17:52:17 GMT
• Title: 3D Point Splatting for mmWave Radar Novel View Synthesis
• Abstract summary: novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires acompute that is physically faithful, complex-valued, and multi-viewpoint-tractable.<n>No prior method achieves these three properties simultaneously.<n>Differentiable Monte Carlo (MC) ray tracers implement the radar forward model directly with explicit material modeling and complex outputs.<n>We propose 3D Point Point Splatting, the first differentiable point for radar, derived directly from the standard solid-angle form of the radar.
• Score: 18.777328493392762
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior method achieves these three properties simultaneously. Differentiable Monte Carlo (MC) ray tracers implement the radar forward model directly with explicit material modeling and complex outputs, but do not scale to the multi-view optimization NVS demands. Optical-NVS ports of NeRF, hash grids, and 3D Gaussians train fast but discard phase and replace explicit material modeling with opaque learned features, restricting them to power-only range-azimuth (RA) magnitudes. We propose 3D Point Splatting (3DPS), the first differentiable point renderer for radar, derived directly from the standard solid-angle form of the radar equation. Each oriented 3D point carries an ITU-R P.2040 material model, evaluated in closed form, with the resulting complex phasor splatted into range bins through a precomputed point spread function (PSF). The complex-valued output makes the renderer product-agnostic. The same optimized scene yields analog-to-digital converter (ADC), complex range profile (CRP), and RA outputs through standard fast Fourier transform (FFT) pipelines without retraining for each format. On six outdoor ColoRadar scenes, 3DPS reaches 0.587 mean Pearson correlation on held-out RA images. This is between 1.7x and 5.2x the three optical-NVS baselines (RadarSplat, Radar Fields, DART). Training takes approximately 3 minutes per scene on a single RTX 4090.

Related papers

• mmIR: Frequency-Space Inverse Rendering for 3D Millimeter-Wave Radar ADC Synthesis [18.777328493392762]
  We present mmIR, an open-source differentiable frequency-modulated continuouswave radar inverse that fits a physics-based forward model to real captures and re-renders from dense virtual apertures to synthesize high-resolution 3D radar data.<n>Because radar resolution is too coarse to recover geometry directly, mmIR performs LiDAR-assisted inverse rendering using LiDAR-derived meshes as a geometric scaffold.<n>On seven outdoor and six indoor ColoRadar scenes, mmIR achieves 0.914 mean Pearson correlation on range-azimuth maps versus 0.307 for Sionna-RT.
  arXiv  Detail & Related papers  (2026-08-28T22:21:47Z)
• Talk2Sensors: 3D Visual Grounding in Autonomous Driving via Sensor-Adaptive Physical Cue Matching [66.91228384649921]
  We introduce Talk2Sensors, the first multi-sensor 3D visual grounding dataset built upon camera, LiDAR, and 4D radar.<n>We propose TSFormer, a unified Transformer-based framework for language-guided 3D visual grounding in autonomous driving.
  arXiv  Detail & Related papers  (2026-08-05T07:58:35Z)
• RCGDet3D: Rethinking 4D Radar-Camera Fusion-based 3D Object Detection with Enhanced Radar Feature Encoding [3.65399248155853]
  We show that simply enhancing radar feature extraction can achieve comparable or even higher performance than elaborate fusion modules.<n>We propose RCGDet3D, which centers on radar feature encoding and simplifies multi-modal fusion.<n> Experiments on View-of-Delft (VoD) and TJ4DRadSet show that RCGDet3D outperforms state-of-the-art methods in both accuracy and speed.
  arXiv  Detail & Related papers  (2026-05-20T12:45:01Z)
• 4D Radar Gaussian Modeling and Scan Matching with RCS [80.74019565026542]
  Radar Cross Section (RCS) information is often overlooked and not usually used in modeling and scan matching processes.<n>We propose incorporating the physical behavior of RCS in the model, in order to further enrich the summarized information about the scene.
  arXiv  Detail & Related papers  (2026-04-16T10:58:29Z)
• RadioGen3D: 3D Radio Map Generation via Adversarial Learning on Large-Scale Synthetic Data [62.63849426834315]
  Radio maps are essential for efficient radio resource management in future 6G and low-altitude networks.<n>Deep learning (DL) techniques have emerged as an efficient alternative to conventional ray-tracing for radio map estimation.<n>We present the RadioGen3D framework to capture essential 3D signal propagation characteristics and antenna polarization effects.
  arXiv  Detail & Related papers  (2026-02-21T07:50:05Z)
• Wavelet-based Multi-View Fusion of 4D Radar Tensor and Camera for Robust 3D Object Detection [44.78575994732947]
  WRCFormer is a novel 3D object detection framework that fuses raw radar cubes with camera inputs via multi-view representations of the decoupled radar cube.<n>WRCFormer achieves state-of-the-art performance on the K-Radar benchmarks, surpassing the best model by approximately 2.4% in all scenarios.
  arXiv  Detail & Related papers  (2025-12-28T15:32:17Z)
• MLF-4DRCNet: Multi-Level Fusion with 4D Radar and Camera for 3D Object Detection in Autonomous Driving [31.26862558777292]
  MLF-4DRCNet is a novel framework for 3D object detection via multi-level fusion of 4D radar and camera images.<n>It incorporates the point-, scene-, and proposal-level multi-modal information, enabling comprehensive feature representation.<n>It attains performance comparable to LiDAR-based models on the View-of-Delft dataset.
  arXiv  Detail & Related papers  (2025-09-23T04:02:28Z)
• 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes [87.01284850604495]
  We introduce 3D Convexting (3DCS), which leverages 3D smooth convexes as primitives for modeling geometrically-meaningful radiance fields from multiview images.<n>3DCS achieves superior performance over 3DGS on benchmarks such as MipNeizer, Tanks and Temples, and Deep Blending.<n>Our results highlight the potential of 3D Convexting to become the new standard for high-quality scene reconstruction.
  arXiv  Detail & Related papers  (2024-11-22T14:31:39Z)
• V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection [64.93675471780209]
  We present V2X-R, the first simulated V2X dataset incorporating LiDAR, camera, and 4D radar.<n>V2X-R contains 12,079 scenarios with 37,727 frames of LiDAR and 4D radar point clouds, 150,908 images, and 170,859 annotated 3D vehicle bounding boxes.<n>We propose a novel cooperative LiDAR-4D radar fusion pipeline for 3D object detection and implement it with various fusion strategies.
  arXiv  Detail & Related papers  (2024-11-13T07:41:47Z)
• CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs [65.80187860906115]
  We propose a novel approach to improve NeRF's performance with sparse inputs. We first adopt a voxel-based ray sampling strategy to ensure that the sampled rays intersect with a certain voxel in 3D space. We then randomly sample additional points within the voxel and apply a Transformer to infer the properties of other points on each ray, which are then incorporated into the volume rendering.
  arXiv  Detail & Related papers  (2024-03-25T15:56:17Z)
• Differentiable Radio Frequency Ray Tracing for Millimeter-Wave Sensing [29.352303349003165]
  We propose DiffSBR, a differentiable framework for mmWave-based 3D reconstruction. DiffSBR incorporates a differentiable ray tracing engine to simulate radar point clouds from virtual 3D models. Experiments using various radar hardware validate DiffSBR's capability for fine-grained 3D reconstruction.
  arXiv  Detail & Related papers  (2023-11-22T06:13:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.