Metraipolis › archive › dc_9d735fe375ed

PQR3D: Progressive Query Refinement over Reference-Conditioned Temporal Windows for Multi-View 3D Object Detection — arXiv:2609.32163

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32163
License (as archived)
CC0-1.0
Archived
2026-10-07T23:50:45.203Z
SHA-256 of the archived text
60e7cf52feb2787bb70d46ab6bc3ff22bdea4740d32a8b29750dfa08a5f21bc5
Stable URL of this page
https://metraipolis.com/documento/dc_9d735fe375ed

How to cite

PQR3D: Progressive Query Refinement over Reference-Conditioned Temporal Windows for Multi-View 3D Object Detection — arXiv:2609.32163 — arXiv (en), https://arxiv.org/abs/2609.32163 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9d735fe375ed (Metraipolis archive dc_9d735fe375ed, sha256 60e7cf52feb2787bb70d46ab6bc3ff22bdea4740d32a8b29750dfa08a5f21bc5)
BibTeX
@misc{dc9d735fe375ed,
  title = {PQR3D: Progressive Query Refinement over Reference-Conditioned Temporal Windows for Multi-View 3D Object Detection — arXiv:2609.32163},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32163},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9d735fe375ed; sha256 60e7cf52feb2787bb70d46ab6bc3ff22bdea4740d32a8b29750dfa08a5f21bc5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32163. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Temporal context is essential for camera-only multi-view 3D object detection. Existing streaming detectors maintain and propagate query states from one frame to the next, requiring sequence-aware training and chronological inference. We propose PQR3D, which performs progressive query refinement within referenceconditioned temporal windows. This design enables random frame sampling and independent inference without persistent query memory. Within each window, PQR3D progressively transfers motion-aligned high-confidence queries from earlier timestamps toward the target frame. We further introduce masked selfattention to regulate interactions among regular, propagated, and denoising queries while keeping denoising supervision isolated from detection queries. In addition, a stage-decoupled anchor embedding injects position before self-attention and size, orientation, and velocity afterward, reducing interference from temporally inconsistent attributes. With a ViT-L backbone, PQR3D sets a new state of the art on the nuScenes test set, achieving 71.6 NDS and 64.9 mAP. Source code is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.32163 — 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 2026-10-07T23:29:26.972Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).