Metraipolis › archive › dc_4fe838eff348

Refine Then Fusion: Training-Free 3D Point Cloud Adaptation with Priority Refinement and Multi-Modal Knowledge Fusion — arXiv:2609.21522

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21522
License (as archived)
CC0-1.0
Archived
2026-10-10T02:29:36.495Z
SHA-256 of the archived text
ef781267de165cc4509979d03530a88df237f45884d10467b8729834ce80b70f
Stable URL of this page
https://metraipolis.com/documento/dc_4fe838eff348

How to cite

Refine Then Fusion: Training-Free 3D Point Cloud Adaptation with Priority Refinement and Multi-Modal Knowledge Fusion — arXiv:2609.21522 — arXiv (en), https://arxiv.org/abs/2609.21522 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fe838eff348 (Metraipolis archive dc_4fe838eff348, sha256 ef781267de165cc4509979d03530a88df237f45884d10467b8729834ce80b70f)
BibTeX
@misc{dc4fe838eff348,
  title = {Refine Then Fusion: Training-Free 3D Point Cloud Adaptation with Priority Refinement and Multi-Modal Knowledge Fusion — arXiv:2609.21522},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21522},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fe838eff348; sha256 ef781267de165cc4509979d03530a88df237f45884d10467b8729834ce80b70f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21522. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent pre-trained foundation models provide rich multi-modal priors for downstream 3D vision tasks. However, the effectiveness of these representations in few-shot scenarios is limited by two fundamental challenges: High-dimensional features often contain substantial channel redundancy and task-irrelevant noise, while the reliability of different modalities varies across samples. Consequently, direct aggregation of heterogeneous representations overlooks sample-dependent modality reliability and may obscure the discriminative cues essential. To address these limitations, we propose Refine Then Fusion(RTF), a training-free framework for few-shot 3D recognition. RTF first identifies discriminative feature channels by jointly modeling inter-class similarity and intra-class stability, thereby decoupling domain-specific knowledge refinement from the cached representations of pre-trained models. It then introduces a reliability-aware fusion mechanism that estimates sample-wise modality reliability from the distribution shifts induced by feature refinement, enabling adaptive aggregation of multi-modal representations. Furthermore, RTF constructs a memory cache that integrates instance-level support features with class-level prototypes to infer query labels. Extensive experiments on five benchmarks demonstrate that RTF consistently outperforms single-modal baselines, partial-fusion variants, and existing lightweight adaptation methods, achieving state-of-the-art few-shot 3D recognition performance without gradient optimization, additional training data, auxiliary training, or parameter updates.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.21522 — 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 2026-10-10T02:07:36.076Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).