Metraipolis › archive › dc_cf7d8bf261f0

Partition-Invariant Tuning for 3D Scene Understanding — arXiv:2609.12473

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12473
License (as archived)
CC0-1.0
Archived
2026-10-16T03:57:36.267Z
SHA-256 of the archived text
af205d3ed3b93c1ae1abac4d326e35a6a48e7e60c61cbf1a5441375cb36f64db
Stable URL of this page
https://metraipolis.com/documento/dc_cf7d8bf261f0

How to cite

Partition-Invariant Tuning for 3D Scene Understanding — arXiv:2609.12473 — arXiv (en), https://arxiv.org/abs/2609.12473 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf7d8bf261f0 (Metraipolis archive dc_cf7d8bf261f0, sha256 af205d3ed3b93c1ae1abac4d326e35a6a48e7e60c61cbf1a5441375cb36f64db)
BibTeX
@misc{dccf7d8bf261f0,
  title = {Partition-Invariant Tuning for 3D Scene Understanding — arXiv:2609.12473},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12473},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf7d8bf261f0; sha256 af205d3ed3b93c1ae1abac4d326e35a6a48e7e60c61cbf1a5441375cb36f64db},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12473. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scene-level point cloud understanding remains challenging due to diverse geometries and spatial layouts. While pre-trained 3D point cloud foundation models (PFMs) offer strong transferability, full fine-tuning (FFT) incurs substantial computational and storage costs. Parameter-efficient fine-tuning (PEFT) provides a promising alternative, but existing PEFT methods largely focus on object-level point clouds and overlook serialization-induced partition variations in large-scale scenes. To address this issue, we propose PointPiT, a partition-invariant tuning framework for scene-level point clouds. Specifically, a Scene-aware Structural Adapter (SSA) integrates local geometric patterns with global scene context to mitigate partition-induced representation shifts. Moreover, Gradient Subspace Optimization (GSO) selects informative and partition-stable update directions, suppressing partition-dependent variations during optimization. Extensive experiments across multiple scene-level benchmarks demonstrate that PointPiT achieves competitive or even superior performance to full fine-tuning with less than 1% of backbone's parameters, while achieving consistent state-of-the-art performance among representative PEFT methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.12473 — 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 2026-10-16T03:44:26.253Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).