Metraipolis › archive › dc_85ebcab54b10

Local-Global Joint Modeling for Point Cloud Super-Resolution Guided by Multi-Scale Spatial Priors — arXiv:2611.02786

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02786
License (as archived)
CC0-1.0
Archived
2026-11-03T11:42:38.983Z
SHA-256 of the archived text
7c859f21fe07aa79a6ee6121f285ea3e9f0f9d27424f78735d02ecaf5c65508c
Stable URL of this page
https://metraipolis.com/documento/dc_85ebcab54b10

How to cite

Local-Global Joint Modeling for Point Cloud Super-Resolution Guided by Multi-Scale Spatial Priors — arXiv:2611.02786 — arXiv (en), https://arxiv.org/abs/2611.02786 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85ebcab54b10 (Metraipolis archive dc_85ebcab54b10, sha256 7c859f21fe07aa79a6ee6121f285ea3e9f0f9d27424f78735d02ecaf5c65508c)
BibTeX
@misc{dc85ebcab54b10,
  title = {Local-Global Joint Modeling for Point Cloud Super-Resolution Guided by Multi-Scale Spatial Priors — arXiv:2611.02786},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02786},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85ebcab54b10; sha256 7c859f21fe07aa79a6ee6121f285ea3e9f0f9d27424f78735d02ecaf5c65508c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02786. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Range-image-based point cloud super-resolution provides an effective way to reconstruct sparse outdoor point clouds by projecting low-resolution LiDAR scans into a regular 2D representation. However, current methods still face three challenges. First, range images exhibit pronounced vertical nonuniformity, with sparse observations in distant regions and denser observations in nearby regions. Some cross-scale fusion mechanisms do not account for the varying reliability of features at different vertical positions, allowing invalid values and noise from distant sparse regions to propagate into the decoder. Second, a single convolutional or sequence-modeling architecture often struggles to preserve both local high-frequency geometric details and global long-range dependencies, resulting in over-smoothed reconstructions. Third, smooth transition depths near foreground-background boundaries can produce spike artifacts when the 2D range image is back-projected into 3D. To address these issues, we propose a point cloud super-resolution method based on multi-scale spatial priors and joint local-global modeling. The design comprises a spatially gated fusion module, a multi-granularity local-global cooperative perception module, and 2D median-residual denoising. Experiments on KITTI-360 and nuScenes demonstrate effective reconstruction, with IoU scores of 0.4703 and 0.3593, respectively, supporting the feasibility of the proposed method for range-image super-resolution.

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/2611.02786 — 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 2026-11-03T11:06:37.592Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).