Metraipolis › archive › dc_5bfaacb8746c

3D Point Splatting for mmWave Radar Novel View Synthesis — arXiv:2609.11894

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11894
License (as archived)
CC0-1.0
Archived
2026-10-16T05:55:27.019Z
SHA-256 of the archived text
dd14e86ab3bb84f8d2126c71d0911bdea924fa8d545c68d5d639421a94911374
Stable URL of this page
https://metraipolis.com/documento/dc_5bfaacb8746c

How to cite

3D Point Splatting for mmWave Radar Novel View Synthesis — arXiv:2609.11894 — arXiv (en), https://arxiv.org/abs/2609.11894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bfaacb8746c (Metraipolis archive dc_5bfaacb8746c, sha256 dd14e86ab3bb84f8d2126c71d0911bdea924fa8d545c68d5d639421a94911374)
BibTeX
@misc{dc5bfaacb8746c,
  title = {3D Point Splatting for mmWave Radar Novel View Synthesis — arXiv:2609.11894},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11894},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bfaacb8746c; sha256 dd14e86ab3bb84f8d2126c71d0911bdea924fa8d545c68d5d639421a94911374},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR); Machine Learning (cs.LG); Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2609.11894 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:44:25.112Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).