Metraipolis › archive › dc_12918632bc86

SGDet3D++: Geometry-Grounded Semantics for 4D Radar and Camera 3D Object Detection — arXiv:2609.27671

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27671
License (as archived)
CC0-1.0
Archived
2026-10-08T12:34:56.486Z
SHA-256 of the archived text
d7a06afb164190fdca26c317879caceb69a696c5fee26bbadad0e2163c8d033b
Stable URL of this page
https://metraipolis.com/documento/dc_12918632bc86

How to cite

SGDet3D++: Geometry-Grounded Semantics for 4D Radar and Camera 3D Object Detection — arXiv:2609.27671 — arXiv (en), https://arxiv.org/abs/2609.27671 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_12918632bc86 (Metraipolis archive dc_12918632bc86, sha256 d7a06afb164190fdca26c317879caceb69a696c5fee26bbadad0e2163c8d033b)
BibTeX
@misc{dc12918632bc86,
  title = {SGDet3D++: Geometry-Grounded Semantics for 4D Radar and Camera 3D Object Detection — arXiv:2609.27671},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27671},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_12918632bc86; sha256 d7a06afb164190fdca26c317879caceb69a696c5fee26bbadad0e2163c8d033b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27671. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

4D radar complements dense image semantics with long-range geometry and radial motion, but existing radar--camera detectors largely solve \emph{where} to align the modalities while leaving \emph{whether} a piece of evidence supports an evolving object hypothesis implicit. An image token may describe an occluder, a nearby radar return may belong to another object, and a pose-aligned memory slot may carry incompatible motion. We formulate \emph{hypothesis-conditioned evidence grounding}, which separates candidate access from evidence use: semantic, geometric, or temporal evidence is filtered or conditioned by the evolving 3D state before updating the corresponding query. \sgdetpp{} instantiates this principle through Anchor-Grounded Semantic Retrieval (AGR), which conditions deformable image retrieval on pooled anchor-consistent radar support; Geometry-Consistent Anchor Refinement (GCR), which attentively aggregates individual associated returns; and Doppler-Verified Correspondence (DVC), which replaces history only when current radial motion contradicts it. \sgdetpp{} improves the strongest compared method by 3.82 mAP and 6.82 ODS on OmniHD-Scenes and by 6.82 mAP and 9.22 NDS on ManTruckScenes, while also leading the listed methods in the TJ4DRadSet test comparison. Mechanism-targeted evaluations show that AGR improves strict AP in every projected-occlusion bin, the yaw-aligned box gate raises target-return purity from 29.95\% to 58.87\%, and DVC preserves 96.11\% of motion-consistent history while retaining 75.90\% contradiction recall. Code will be released.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.27671 — 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 2026-10-08T12:12:35.700Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).