Metraipolis › archive › dc_0e8057eaeb59
PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation — arXiv:2611.07873
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07873
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:53:36.000Z
- SHA-256 of the archived text
670fd487de2ea28ab446138f44114dd9ebb65757e2b15da90cfad6afe0c61726- Stable URL of this page
https://metraipolis.com/documento/dc_0e8057eaeb59
How to cite
PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation — arXiv:2611.07873 — arXiv (en), https://arxiv.org/abs/2611.07873 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0e8057eaeb59 (Metraipolis archive dc_0e8057eaeb59, sha256 670fd487de2ea28ab446138f44114dd9ebb65757e2b15da90cfad6afe0c61726)
BibTeX
@misc{dc0e8057eaeb59,
title = {PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation — arXiv:2611.07873},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07873},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0e8057eaeb59; sha256 670fd487de2ea28ab446138f44114dd9ebb65757e2b15da90cfad6afe0c61726},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07873. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Panoramic video depth estimation is pivotal for applications such as Virtual Reality and World Models. However, advancements in this field are impeded by two primary obstacles: the scarcity of large-scale training data and the unique spatiotemporal challenges of Equirectangular Projection (ERP), which hinder the direct transfer of perspective models. In this paper, we first present PanoCARLA, a large-scale synthetic RGB-D panoramic video dataset, featuring natural motion trajectories and drone-like roaming perspectives. Building on this foundation, we propose PVDepth, an end-to-end framework adapted from perspective video depth models. To tackle ERP-specific geometric distortions and consequent non-linear temporal dynamics, we introduce two core mechanisms: (1) A Progressive Sphere-aware Noise Initialization strategy that anneals the noise distribution from planar to spherical, guiding the model to adapt to non-uniform information density; and (2) A Cube-rectified Temporal Modeling module that incorporates an auxiliary cubemap temporal branch to rectify non-linear temporal dynamics in the ERP domain. Extensive experiments demonstrate that PVDepth achieves superior performance, generating geometrically accurate and temporally consistent depth sequences. Code and data will be released at https:// this http URL . 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/2611.07873 — 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 2026-11-06T14:25:42.620Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).