Metraipolis › archive › dc_11eff7dc2a14

GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model — arXiv:2609.19716

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19716
License (as archived)
CC0-1.0
Archived
2026-10-10T05:05:29.673Z
SHA-256 of the archived text
b2527909eb79702bea50a0fb0ee7647e280fc63ec3533f459a784a3f47fb4e8a
Stable URL of this page
https://metraipolis.com/documento/dc_11eff7dc2a14

How to cite

GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model — arXiv:2609.19716 — arXiv (en), https://arxiv.org/abs/2609.19716 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11eff7dc2a14 (Metraipolis archive dc_11eff7dc2a14, sha256 b2527909eb79702bea50a0fb0ee7647e280fc63ec3533f459a784a3f47fb4e8a)
BibTeX
@misc{dc11eff7dc2a14,
  title = {GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model — arXiv:2609.19716},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19716},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11eff7dc2a14; sha256 b2527909eb79702bea50a0fb0ee7647e280fc63ec3533f459a784a3f47fb4e8a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19716. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pre-trained 3D vision models have substantially advanced point cloud analysis, yet adapting them to downstream tasks via full fine-tuning is computationally expensive and storage-intensive. Parameter-Efficient Fine-Tuning (PEFT) offers a promising alternative by reducing both adaptation cost and storage burden. However, existing prompting-based approaches ignore the intrinsic geometric structures of point clouds, thereby limiting their adaptation capability. This limitation stems from their inability to encode both fine-grained geometric cues and coarse-grained structural semantics, as well as failing to propagate such information effectively through the model hierarchy. To address these challenges, we propose GAPrompt++, a multi-granular geometry-aware prompting method that provides richer geometric guidance for efficient 3D task adaptation. Specifically, we introduce a Point Shift Prompter that extracts multi-granular geometric features across different scales, enabling instance-specific geometric adjustments during adaptation. Next, a Keypoint Prompter adaptively generates point-level prompts to highlight local geometric saliency and fine-grained structural details. Furthermore, a Prompt Propagation mechanism injects these multi-granular geometric cues throughout the feature extraction hierarchy, strengthening the ability to capture essential geometric characteristics. Extensive experiments show that GAPrompt++ achieves state-of-the-art performance among prompting-based PEFT methods and even surpasses full fine-tuning across diverse benchmarks, while requiring less than 2\% trainable parameters. In addition, to address the saturation of existing evaluation datasets, we construct two more challenging benchmarks derived from 3D Gaussian Splatting and Multi-View Stereo reconstruction, offering diverse and realistic point cloud scenarios to promote future research.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.19716 — 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 2026-10-10T04:26:09.527Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).