Metraipolis › archive › dc_fd22b20d07f8

M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera--LiDAR Novel View Synthesis — arXiv:2609.30056

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30056
License (as archived)
CC0-1.0
Archived
2026-10-08T06:44:47.049Z
SHA-256 of the archived text
2c37960bd579e38f64100c579a7c1f97b21637c208b8ed558fd76c9c75630b0c
Stable URL of this page
https://metraipolis.com/documento/dc_fd22b20d07f8

How to cite

M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera--LiDAR Novel View Synthesis — arXiv:2609.30056 — arXiv (en), https://arxiv.org/abs/2609.30056 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd22b20d07f8 (Metraipolis archive dc_fd22b20d07f8, sha256 2c37960bd579e38f64100c579a7c1f97b21637c208b8ed558fd76c9c75630b0c)
BibTeX
@misc{dcfd22b20d07f8,
  title = {M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera--LiDAR Novel View Synthesis — arXiv:2609.30056},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30056},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd22b20d07f8; sha256 2c37960bd579e38f64100c579a7c1f97b21637c208b8ed558fd76c9c75630b0c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30056. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robotic novel view synthesis (NVS) must recover both visual appearance and metric 3D structure, yet most generative NVS methods rely only on images, overlooking LiDAR, a complementary sensor common on robotic platforms. We present M3GD, a Camera--LiDAR multimodal representation for generative NVS that composes independently pretrained 2D image and 3D point-cloud foundation models without separately pretraining a cross-modal translator. We show that, after camera projection, frozen LiDAR and image features exhibit substantial shared spatial structure, providing a natural cross-modal representation. M3GD conditions generation on LiDAR through this structure: it combines explicit geometry statistics with learned point-cloud descriptors into view-aligned packets on the image-latent grid, injected through a lightweight residual adapter into a multi-view flow-matching generator whose latent space, decoders, and training objective remain intact. On the GrandTour dataset, M3GD improves target-view RGB and depth synthesis over an image-only version of the same backbone. Ablations show that the gains come from pixel-aligned LiDAR content and that target-view LiDAR acts as a geometric query linking the requested view to source observations. Deployment on a ground robot demonstrates practical real-world operation, with a configurable quality--cost trade-off controlled by the number of Euler integration steps.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.30056 — 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 2026-10-08T06:09:29.942Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).