Metraipolis › archive › dc_e163c7ec490f
Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models — arXiv:2608.10708
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10708
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:30:24.817Z
- SHA-256 of the archived text
cd84668dfd3cb3e0fd25ac91c474fa62360cb1ee69f098f234f25499962a78f0- Stable URL of this page
https://metraipolis.com/documento/dc_e163c7ec490f
How to cite
Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models — arXiv:2608.10708 — arXiv (en), https://arxiv.org/abs/2608.10708 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e163c7ec490f (Metraipolis archive dc_e163c7ec490f, sha256 cd84668dfd3cb3e0fd25ac91c474fa62360cb1ee69f098f234f25499962a78f0)
BibTeX
@misc{dce163c7ec490f,
title = {Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models — arXiv:2608.10708},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10708},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e163c7ec490f; sha256 cd84668dfd3cb3e0fd25ac91c474fa62360cb1ee69f098f234f25499962a78f0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10708. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving strong generalization. However, enforcing explicit multi-view geometric consistency, e.g., through bundle adjustment, is computationally costly and is thus not imposed during VFM pretraining, so such inconsistency can arise. To address this, implicit self-consistency derived from model outputs (e.g., pointmaps, features), though enforced at test-time in prior work, delivers inherently limited performance gain, especially on scenes where the pretrained VFM is highly inaccurate. In contrast to this implicit signal, we propose Self-Geometry, a plug-and-play test-time adaptation pipeline that directly imposes explicit multi-view geometric constraints using 2D pixel correspondences as pseudo ground-truth. Our proposed Self-Geometry consists of Geometric Disentanglement Optimization, which combines Multi-View Consistency and Epipolar Consistency losses with Gradient Disentanglement to prevent gradient conflict; Frame Angular-Neighbor, a view sampler based on SO(3) geodesic distances for lightly imposing these constraints; and Lightweight TTA, which adapts VFMs via LoRA. Our method achieves consistent improvements in both pose and geometry estimation across six VFMs (VGGT, $\pi^3$, DA3-Giant/Large/Base/Small) and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom). Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.10708 — 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 2026-10-19T06:25:27.275Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).