Metraipolis › archive › dc_b04fd60df5f2

UFMF: Radar-Guided Kinematic Priors for Real-Time 4D Occupancy Forecasting — arXiv:2610.40947

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40947
License (as archived)
CC0-1.0
Archived
2026-11-02T05:03:31.809Z
SHA-256 of the archived text
f89afb312d2398828dd37ac09279f237bfa282c58383c5bb99446f902cdf67de
Stable URL of this page
https://metraipolis.com/documento/dc_b04fd60df5f2

How to cite

UFMF: Radar-Guided Kinematic Priors for Real-Time 4D Occupancy Forecasting — arXiv:2610.40947 — arXiv (en), https://arxiv.org/abs/2610.40947 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b04fd60df5f2 (Metraipolis archive dc_b04fd60df5f2, sha256 f89afb312d2398828dd37ac09279f237bfa282c58383c5bb99446f902cdf67de)
BibTeX
@misc{dcb04fd60df5f2,
  title = {UFMF: Radar-Guided Kinematic Priors for Real-Time 4D Occupancy Forecasting — arXiv:2610.40947},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40947},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b04fd60df5f2; sha256 f89afb312d2398828dd37ac09279f237bfa282c58383c5bb99446f902cdf67de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40947. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-time 4D occupancy forecasting requires reliably extrapolating both ego motion and surrounding actor motion under strict latency budgets. Recent occupancy world models improve long-horizon fidelity through generative decoders and 3D volumetric modeling, yet their computational cost makes real-time deployment challenging. Light-weight BEV forecasters meet latency requirements but often blur or suppress fast-moving actors at longer horizons. We present UFMF (Ultra-Fast Multi-modal Forecaster), a real-time forecaster that keeps an attention-free diagonal state-space temporal core while injecting targeted kinematic and geometric structure where lightweight models typically fail. A radar-guided velocity-aware dynamic prior (VADP) decomposes future displacement into a linear extrapolation plus a learned horizon-dependent residual. The resulting per-cell flow fields transport a compact dynamic latent subspace during rollout. Two auxiliary training constraints complement this branch: world-frame dynamic supervision enforces inter-horizon trajectory coherence, and class-conditioned vertical-profile supervision regularizes BEV-to-3D lifting. UFMF operates at 122 FPS on a single RTX 4090 and reaches 0.45 fast-displacement mIoU on nuScenes, outperforming recent occupancy world models at a fraction of their computational cost.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.40947 — 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 2026-11-02T04:49:13.229Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).