Metraipolis › archive › dc_e213f8aaf503

A Differentiable Optimization Framework for Registering Sequential Bounding Boxes with Point Cloud Stream — arXiv:2609.34103

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34103
License (as archived)
CC0-1.0
Archived
2026-10-07T20:57:22.223Z
SHA-256 of the archived text
12af95b735148289b749f9c1c18829ed9d140c77b15a371de27c820feceb6336
Stable URL of this page
https://metraipolis.com/documento/dc_e213f8aaf503

How to cite

A Differentiable Optimization Framework for Registering Sequential Bounding Boxes with Point Cloud Stream — arXiv:2609.34103 — arXiv (en), https://arxiv.org/abs/2609.34103 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e213f8aaf503 (Metraipolis archive dc_e213f8aaf503, sha256 12af95b735148289b749f9c1c18829ed9d140c77b15a371de27c820feceb6336)
BibTeX
@misc{dce213f8aaf503,
  title = {A Differentiable Optimization Framework for Registering Sequential Bounding Boxes with Point Cloud Stream — arXiv:2609.34103},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34103},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e213f8aaf503; sha256 12af95b735148289b749f9c1c18829ed9d140c77b15a371de27c820feceb6336},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34103. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Refining a sequence of coarse 3D bounding boxes against a LiDAR point-cloud stream demands tracks that are geometrically accurate (high IoU) and temporally coherent (low roughness), preferably without training data. The usual recipe keeps the two concerns apart: register each frame independently, then smooth the trajectory afterwards with a Kalman~RTS or Savitzky--Golay filter. Smoothing displaces boxes from a geometric optimum and never re-optimises, so it trades accuracy for smoothness. We instead fold the temporal smoothness constraint into a training-free registration objective and solve for all poses jointly with L-BFGS. The payoff depends on how well the object is seen. On well-observed tracks it is large: within the low-roughness budget, the joint objective beats both post-hoc smoothers on paired multi-seed statistics and cuts roughness several-fold relative to frame-wise registration at matched accuracy. Treating visibility as an experimental variable exposes the limit. The advantage decays monotonically as views become one-sided, until it is indistinguishable from zero for near-edge-on objects and slightly negative under a ray-cast simulator with range-dependent density and ego motion, where the decoupled pipeline is in fact ahead at tight roughness budgets. We locate that boundary and trace it to one term: orientation alignment ties yaw to the estimated velocity and fails once that estimate is noisy. A ground-truth-free rule can choose the temporal scale and keep every track inside the roughness budget.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34103 — 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 2026-10-07T20:29:01.424Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).