Metraipolis › archive › dc_7e701c828fca

Multi-Path Mamba Diffusion for 3D Point Cloud Semantic Scene Completion — arXiv:2611.04583

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04583
License (as archived): CC0-1.0
Archived: 2026-11-04T19:03:21.663Z
SHA-256 of the archived text: 230bfe556622307e2c3d62902aaf40c6e95c366ccf011ebafbc4e25454e4427f
Stable URL of this page: https://metraipolis.com/documento/dc_7e701c828fca

How to cite

Multi-Path Mamba Diffusion for 3D Point Cloud Semantic Scene Completion — arXiv:2611.04583 — arXiv (en), https://arxiv.org/abs/2611.04583 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e701c828fca (Metraipolis archive dc_7e701c828fca, sha256 230bfe556622307e2c3d62902aaf40c6e95c366ccf011ebafbc4e25454e4427f)

BibTeX

@misc{dc7e701c828fca,
  title = {Multi-Path Mamba Diffusion for 3D Point Cloud Semantic Scene Completion — arXiv:2611.04583},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04583},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e701c828fca; sha256 230bfe556622307e2c3d62902aaf40c6e95c366ccf011ebafbc4e25454e4427f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04583. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D semantic scene completion plays a critical role in enabling various downstream tasks within autonomous systems by estimating both missing geometric structures and semantic information in scene data. In this work, we introduce a unique neural framework that integrates state space modeling with diffusion-based generative approaches to enhance 3D point cloud semantic scene completion. We propose \textit{MPath Mamba} diffusion network, leveraging a skip-triple Mamba structure, dimensional decomposition residuals, and multi-directional dilations within multi-path data to efficiently process long-sequence data for feature extraction. The proposed method operates in the conditioned latent space of a variational autoencoder, enhanced by a state-space mechanism to improve 3D point cloud representation and reconstruction. Extensive experiments conducted on the SemanticKITTI benchmark demonstrate that our approach achieves highly competitive performance for 3D point cloud semantic scene completion.

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/2611.04583 — 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 2026-11-04T18:39:37.523Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).