Metraipolis › archive › dc_048af5883fd0

SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection — arXiv:2609.04886

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04886
License (as archived)
CC0-1.0
Archived
2026-10-16T22:26:45.853Z
SHA-256 of the archived text
42bfdc688e6075e4b9cd798b943d74d20d625f8cb42511a1f942bd89664638ff
Stable URL of this page
https://metraipolis.com/documento/dc_048af5883fd0

How to cite

SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection — arXiv:2609.04886 — arXiv (en), https://arxiv.org/abs/2609.04886 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_048af5883fd0 (Metraipolis archive dc_048af5883fd0, sha256 42bfdc688e6075e4b9cd798b943d74d20d625f8cb42511a1f942bd89664638ff)
BibTeX
@misc{dc048af5883fd0,
  title = {SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection — arXiv:2609.04886},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04886},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_048af5883fd0; sha256 42bfdc688e6075e4b9cd798b943d74d20d625f8cb42511a1f942bd89664638ff},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04886. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Changes in sensor height and viewpoint alter object-level point distributions, making cross-platform LiDAR unsupervised domain adaptation (UDA) difficult. Self-training uses labeled source scans and unlabeled target scans, yet a retained prediction may provide a useful target location while enclosing sparse foreground returns, background clutter, or points inconsistent with the predicted box. We refer to this mismatch as box-point inconsistency. We introduce SimFuse3D, which preserves the target placement and repairs the associated pseudo object using measured geometry from labeled source scans. Object Memory retrieves a similar labeled source instance. Target Simulation places the retrieved source geometry at the target location, aligns its points with the target viewing geometry, and filters the aligned crop to approximate the target observation. Confidence-Guided Multi-Stage Localization Reweighting (CMLR) maps each target pseudo-object confidence score to a bounded weight shared by RPN localization and R-CNN box regression. All components operate only during adaptation, leaving the detector architecture and inference graph unchanged. Across six cross-platform transfers, SimFuse3D consistently outperforms Pi3DET-Net and achieves the best performance among the compared adaptation methods on nearly all metrics. On nuScenes-to-KITTI, it ranks first among the compared adaptation methods with both evaluated detectors.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.04886 — 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 2026-10-16T22:18:11.543Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).