Metraipolis › archive › dc_9ce99a033e66

Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent Flows — arXiv:2609.27779

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.27779
License (as archived): CC0-1.0
Archived: 2026-10-08T12:35:03.181Z
SHA-256 of the archived text: 794006d0b2fb422509ebf95eee9b662153ab7520e38d201542b2e355a0315679
Stable URL of this page: https://metraipolis.com/documento/dc_9ce99a033e66

How to cite

Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent Flows — arXiv:2609.27779 — arXiv (en), https://arxiv.org/abs/2609.27779 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ce99a033e66 (Metraipolis archive dc_9ce99a033e66, sha256 794006d0b2fb422509ebf95eee9b662153ab7520e38d201542b2e355a0315679)

BibTeX

@misc{dc9ce99a033e66,
  title = {Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent Flows — arXiv:2609.27779},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27779},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ce99a033e66; sha256 794006d0b2fb422509ebf95eee9b662153ab7520e38d201542b2e355a0315679},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27779. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Class-guided 3D object generation is important for intelligent content creation, virtual environments, and digital asset design. Although 3D Gaussian Splatting (3DGS) offers an explicit and render-efficient representation, directly generating 3D Gaussian objects is difficult because Gaussian primitives are unordered, variable-sized, locally dense, and highly sensitive to rendering. Existing 3DGS generation methods usually depend on multi-view synthesis, reconstruction, or lifted 2D priors, fusing information mainly from observed views rather than modeling the intrinsic structural distribution of 3D Gaussian objects. This paper proposes a fusion-aware hierarchical Gaussian patch representation for direct class-guided 3DGS generation with rectified flow. Irregular Gaussian sets are decomposed into canonical local patches and encoded as structured tokens. The resulting hierarchical latent space fuses global class semantics, patch-level geometry and appearance, spatial correspondence, and rendering-sensitive cues. On this basis, we design a structure-aware rectified flow model with patch-position conditioning, global-local coupled velocity prediction, and density-aware velocity weighting, enabling direct latent generation of class-conditioned 3DGS objects within seconds. A render-feedback fusion strategy further aligns latent flow learning with decoded multi-view rendering quality. Experiments show that the proposed method generates 3D Gaussian objects with more coherent geometry, sharper local details, and better multi-view consistency than baseline latent generative models. Ablation studies confirm the contributions of hierarchical information fusion, global-local coupling, density-aware supervision, and render-feedback learning while preserving practical sampling efficiency overall.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.27779 — 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 2026-10-08T12:12:35.726Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).