Metraipolis › archive › dc_d8bad812e048

DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes — arXiv:2609.39841

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39841
License (as archived)
CC0-1.0
Archived
2026-10-07T14:46:27.486Z
SHA-256 of the archived text
edbfbc18144bad1cda7e666f464cc1ec295b5bfefd1e78d609396002e0ba4a9d
Stable URL of this page
https://metraipolis.com/documento/dc_d8bad812e048

How to cite

DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes — arXiv:2609.39841 — arXiv (en), https://arxiv.org/abs/2609.39841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8bad812e048 (Metraipolis archive dc_d8bad812e048, sha256 edbfbc18144bad1cda7e666f464cc1ec295b5bfefd1e78d609396002e0ba4a9d)
BibTeX
@misc{dcd8bad812e048,
  title = {DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes — arXiv:2609.39841},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39841},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8bad812e048; sha256 edbfbc18144bad1cda7e666f464cc1ec295b5bfefd1e78d609396002e0ba4a9d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstructing dynamic driving scenes from recorded sensor data supports closed-loop evaluation of autonomous driving systems by synthesizing observations beyond the original trajectory. Unlike cameras and LiDAR, radar measures radial velocity directly through Doppler. Yet existing radar novel-view synthesis fails to exploit this capability: methods addressing dynamic scenes reconstruct only range-azimuth tensors, while methods that render Doppler assume static scenes. Moreover, because radar processing spreads each reflection across multiple bins, existing representations absorb this spread into scene geometry, causing it to render incorrectly when the viewpoint moves. We present DyRAD, which models dynamic driving scenes using static background reflectors and motion-tracked dynamic point reflectors to render complete range-azimuth-Doppler (RAD) tensors. Reflector velocities are derived from object tracks and projected onto the line of sight, making Doppler both a rendered output and supervision for those tracks. Crucially, we render reflectors through a fixed analytic point-spread function (PSF) derived from the radar's signal-processing chain, preventing sensor-induced spread from being baked into the scene representation. Beyond improving scene reconstruction, this separation also enables zero-shot sensor-configuration transfer, allowing the same reconstructed scene to be rendered under different radar specifications without refitting. We evaluate DyRAD on RADIal, Boreas, and a synthetic benchmark across both on-path poses and displaced viewpoints untested by prior work. On RADIal, DyRAD recovers radar detections in 90.7% of reference-detected objects, compared with 26.9% for the strongest baseline.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.39841 — 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 2026-10-07T14:19:00.813Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).