Metraipolis › archive › dc_7e8065628fa2

DIFTA-3D: Depth-Consistent Instance-Level Feature Transfer and Adaptation of DINOv3 for 3D Detection — arXiv:2609.26702

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26702
License (as archived): CC0-1.0
Archived: 2026-10-08T16:39:50.541Z
SHA-256 of the archived text: e6ac0015a5f6d4fe664d3f6f6d369ee0dfd5cd0d93edcf606d934b9306c17bb9
Stable URL of this page: https://metraipolis.com/documento/dc_7e8065628fa2

How to cite

DIFTA-3D: Depth-Consistent Instance-Level Feature Transfer and Adaptation of DINOv3 for 3D Detection — arXiv:2609.26702 — arXiv (en), https://arxiv.org/abs/2609.26702 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e8065628fa2 (Metraipolis archive dc_7e8065628fa2, sha256 e6ac0015a5f6d4fe664d3f6f6d369ee0dfd5cd0d93edcf606d934b9306c17bb9)

BibTeX

@misc{dc7e8065628fa2,
  title = {DIFTA-3D: Depth-Consistent Instance-Level Feature Transfer and Adaptation of DINOv3 for 3D Detection — arXiv:2609.26702},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26702},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e8065628fa2; sha256 e6ac0015a5f6d4fe664d3f6f6d369ee0dfd5cd0d93edcf606d934b9306c17bb9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26702. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

RGB-D 3D instance detectors benefit from visual semantics, but the task-specific Faster R-CNN/ResNet branch used by IIFNet3D couples feature extraction to a separately trained 2D detector and its image-domain labels. Replacing that branch with a frozen vision foundation model removes this task-specific dependency, but may introduce occlusion noise and a mismatch between patch features and geometry-aware detection features. In this work, we investigate this replacement through an adaptation of DINOv3 to the instance-level fusion pipeline of IIFNet3D. At the core of our approach is a depth-consistent feature pipeline that projects scene points into calibrated RGB-D frames, applies a metric depth-residual check, averages the accepted DINOv3 features into an offline point cache, and aggregates the cached features inside proposal-aligned RoI grids. The geometric and bidirectional instance-fusion paths are preserved, while Conservative VAID is evaluated as a low-strength, support-weighted semantic distillation recipe applied only to positive RoIs. We conduct extensive evaluations on ScanNetV2 to assess the proposed transfer recipes. On ScanNetV2, our DINOv3 control achieves mAP scores of 76.15 and 60.93 at IoU thresholds of 0.25 and 0.50, respectively. The Conservative VAID setting achieves mAP scores of 76.59 and 62.16, corresponding to numerical gains of 0.44 and 1.23 points over the control, respectively, in this checkpoint-level recipe comparison. The reported IIFNet3D result of 75.7/63.8 is used only as an external reference because the visual branch and processing protocol differ. Accordingly, we interpret these results as evidence for a controlled transfer recipe rather than as a causal estimate of the individual contributions of VAID or depth filtering.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.26702 — 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 2026-10-08T15:56:18.221Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).