Metraipolis › archive › dc_157a207c76ec

CADSplat: Sparse-View 3D Gaussian Splatting Aided by CAD Models for Robust, Photorealistic Digital-Twin Reconstruction — arXiv:2609.18473

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.18473
License (as archived): CC0-1.0
Archived: 2026-10-15T16:16:32.789Z
SHA-256 of the archived text: 89f7243ce42a8cbeeab1ec725d33754032043ee25d14105e73e12672659860a2
Stable URL of this page: https://metraipolis.com/documento/dc_157a207c76ec

How to cite

CADSplat: Sparse-View 3D Gaussian Splatting Aided by CAD Models for Robust, Photorealistic Digital-Twin Reconstruction — arXiv:2609.18473 — arXiv (en), https://arxiv.org/abs/2609.18473 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_157a207c76ec (Metraipolis archive dc_157a207c76ec, sha256 89f7243ce42a8cbeeab1ec725d33754032043ee25d14105e73e12672659860a2)

BibTeX

@misc{dc157a207c76ec,
  title = {CADSplat: Sparse-View 3D Gaussian Splatting Aided by CAD Models for Robust, Photorealistic Digital-Twin Reconstruction — arXiv:2609.18473},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18473},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_157a207c76ec; sha256 89f7243ce42a8cbeeab1ec725d33754032043ee25d14105e73e12672659860a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18473. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present CADSplat, a framework that reconstructs photorealistic, geometrically accurate digital twins from sparse ($<15$ views), wide-baseline posed images of an object by regularizing 3D Gaussian Splatting (3DGS) with an explicit CAD shape prior. Using such a prior requires finding a CAD model whose shape resembles the object depicted in the images and determining the pose of each camera relative to the object. We obtain both by matching segmented object silhouettes against silhouettes rendered from a CAD library and keeping the camera-to-object poses of the best-matching model. We then anchor 3D Gaussian primitives to the surface of the retrieved model and jointly optimize the 3DGS parameters, the camera-to-object registration, and a non-rigid deformation field to account for shape differences between the physical object and the CAD model. Across two real-world datasets, CADSplat outperforms unconstrained, few-shot, and mesh-texturing baselines and degrades gracefully to as few as 3 views. Our experiments show that most of the gain in rendering quality comes from how the splats are constrained---a fixed set of splats tied to a surface and moved by a single smooth deformation field---rather than from the CAD shape itself. The CAD model adds shape knowledge where views are scarcest, in the sparsest captures and on strongly self-occluded objects, and it places every camera in the object's own frame. This enables applications beyond novel-view synthesis, such as markerless augmented reality registration, per-image object pose estimation, physical simulations, and the transfer of part labels from the design to the reconstruction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.18473 — 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 2026-10-15T15:45:19.793Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).