Metraipolis › archive › dc_cf15b1d2d2ee
Extrapolation Matters: Sparse-Only Depth Completion Beyond LiDAR Coverage — arXiv:2611.08782
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08782
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:45:05.605Z
- SHA-256 of the archived text
ab39d27c0af0e5028e347c647f13218fdd932c2a181d97103e5b83c06aa03b96- Stable URL of this page
https://metraipolis.com/documento/dc_cf15b1d2d2ee
How to cite
Extrapolation Matters: Sparse-Only Depth Completion Beyond LiDAR Coverage — arXiv:2611.08782 — arXiv (en), https://arxiv.org/abs/2611.08782 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf15b1d2d2ee (Metraipolis archive dc_cf15b1d2d2ee, sha256 ab39d27c0af0e5028e347c647f13218fdd932c2a181d97103e5b83c06aa03b96)
BibTeX
@misc{dccf15b1d2d2ee,
title = {Extrapolation Matters: Sparse-Only Depth Completion Beyond LiDAR Coverage — arXiv:2611.08782},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08782},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf15b1d2d2ee; sha256 ab39d27c0af0e5028e347c647f13218fdd932c2a181d97103e5b83c06aa03b96},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08782. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Extrapolation beyond LiDAR coverage is an important yet under-evaluated challenge of depth completion. In real camera--LiDAR systems, partial sensor overlap, occlusions, and limited field coverage often leave large image regions weakly observed or completely unobserved by LiDAR. Thus, we investigate depth completion in this beyond-coverage regime using only sparse supervision from raw single-sweep LiDAR, without dense depth labels, LiDAR accumulation, or pseudo-LiDAR generation. Our approach leverages a frozen monocular depth foundation model, lightweight per-frame alignment to sparse LiDAR geometry, and a refinement module that fuses the aligned prior with sparse LiDAR anchors to predict dense metric depth. To regularize learning under raw sparse supervision, we introduce a high-frequency normal-consistency loss defined as the image-space gradient of the per-pixel normal cosine discrepancy. This term penalizes spatial variation in scalar angular error; it does not directly match changes in neighboring normal vectors. We further introduce an evaluation protocol that explicitly separates LiDAR-supported and beyond-coverage regions, revealing extrapolative behavior that conventional depth-completion metrics can obscure. Our method achieves strong depth accuracy beyond LiDAR coverage while remaining competitive in LiDAR-covered regions, providing a practical way to deploy monocular foundation priors in multi-sensor systems. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.08782 — 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 2026-11-09T22:37:47.200Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).