Metraipolis › archive › dc_2068eb3fdd01
GeoCond: A Conditioning-Aware Reliability Adapter for Feed-Forward 3D Reconstruction — arXiv:2609.18465
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18465
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T16:16:32.244Z
- SHA-256 of the archived text
32423d65bba093619ab44702da575a8aa6c1da1e389e2a617a3bb4f4af00d3b5- Stable URL of this page
https://metraipolis.com/documento/dc_2068eb3fdd01
How to cite
GeoCond: A Conditioning-Aware Reliability Adapter for Feed-Forward 3D Reconstruction — arXiv:2609.18465 — arXiv (en), https://arxiv.org/abs/2609.18465 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2068eb3fdd01 (Metraipolis archive dc_2068eb3fdd01, sha256 32423d65bba093619ab44702da575a8aa6c1da1e389e2a617a3bb4f4af00d3b5)
BibTeX
@misc{dc2068eb3fdd01,
title = {GeoCond: A Conditioning-Aware Reliability Adapter for Feed-Forward 3D Reconstruction — arXiv:2609.18465},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18465},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2068eb3fdd01; sha256 32423d65bba093619ab44702da575a8aa6c1da1e389e2a617a3bb4f4af00d3b5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18465. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feed-forward 3D foundation models such as VGGT predict cameras, depth, and point maps in a single pass, but can fail silently under low overlap, low parallax, and extreme relative rotation. Stratified analyses over these factors show that these failures are governed by geometric conditioning and are poorly captured by native aleatoric confidence. We introduce GeoCond, a lightweight reliability adapter for frozen feed-forward 3D backbones. GeoCond reads the backbone's predicted geometry and outputs pose-level uncertainty and a refinement gate. During training, it can be supervised by frame-permutation orbit variance, ground-truth pose error when labels are available, or cycle residuals from unlabelled independent pose graphs. At inference, the default head requires only one backbone pass and a small MLP. On VGGT, GeoCond improves out-of-distribution (OOD) AUSE (area under the sparsification-error curve; lower is better) from $0.32$ to $0.20$ over native confidence, transfers zero-shot to outdoor extreme-view scenes, and avoids the collapse caused by applying bundle adjustment uniformly. Across multiple backbones, cycle-distilled variants provide a ground-truth-free adaptation route, including cases where permutation variance vanishes on equivariant models. The same reliability signal supports gated refinement, pose-graph weighting, calibration, curation, and capture decisions. Reliable feed-forward 3D reconstruction requires not only predicting geometry, but also knowing when that geometry should be trusted. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.18465 — 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 2026-10-15T15:45:19.792Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).