Metraipolis › archive › dc_4e86bb93cf06

LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation — arXiv:2608.03851

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03851
License (as archived): CC0-1.0
Archived: 2026-10-31T12:59:48.988Z
SHA-256 of the archived text: 2222ca0cccc531a75af3eef31878c4aad7f7a0bd3a756c7640ef4030c80ce615
Stable URL of this page: https://metraipolis.com/documento/dc_4e86bb93cf06

How to cite

LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation — arXiv:2608.03851 — arXiv (en), https://arxiv.org/abs/2608.03851 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e86bb93cf06 (Metraipolis archive dc_4e86bb93cf06, sha256 2222ca0cccc531a75af3eef31878c4aad7f7a0bd3a756c7640ef4030c80ce615)

BibTeX

@misc{dc4e86bb93cf06,
  title = {LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation — arXiv:2608.03851},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03851},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e86bb93cf06; sha256 2222ca0cccc531a75af3eef31878c4aad7f7a0bd3a756c7640ef4030c80ce615},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03851. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-time 3D perception is crucial for robotics, augmented reality, and embodied intelligence applications. Existing multi-view stereo (MVS) methods primarily rely on geometric correspondences, which often fail in textureless or repetitive regions, while monocular depth models leverage strong image-level priors but lack robust multi-view geometric constraints. More importantly, in robotics and embodied manipulation scenarios, high-quality 3D geometry is not only essential for static reconstruction, but also serves as a critical foundation for learning temporally consistent 4D representations. To obtain visual representations with stronger structural awareness and greater potential for spatiotemporal extension, we present LiteMVS, a lightweight multi-view depth estimation model that integrates plane-sweep geometric reasoning with strong monocular semantic and structural priors. The central idea of LiteMVS is to efficiently inject high-level monocular knowledge, obtained from lightweight segmentation models and large-scale vision foundation models, into a multi-view stereo framework. In particular, LiteMVS enriches the cost volume with semantic descriptors and employs a Mixture-of-Experts (MoE) formulation to enable adaptive geometric aggregation across depth hypotheses. Moreover, geometric priors distilled from vision foundation models further strengthen monocular guidance without increasing inference cost. Through this design, LiteMVS not only improves depth estimation and 3D reconstruction quality in static scenes, but also provides a more reliable geometric foundation for subsequent temporal modeling and 4D representation learning. Experiments on ScanNetv2 and 7-Scenes demonstrate that LiteMVS achieves high-quality depth prediction and 3D reconstruction while maintaining competitive efficiency.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.03851 — 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 2026-10-31T12:45:33.279Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).