Metraipolis › archive › dc_ace4be1e0736

Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations — arXiv:2609.03657

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03657
License (as archived)
CC0-1.0
Archived
2026-10-17T02:56:23.927Z
SHA-256 of the archived text
164fa4822ee695616a6883e6c467ed876fb0076ae6b7baff40faccc4bf157265
Stable URL of this page
https://metraipolis.com/documento/dc_ace4be1e0736

How to cite

Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations — arXiv:2609.03657 — arXiv (en), https://arxiv.org/abs/2609.03657 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ace4be1e0736 (Metraipolis archive dc_ace4be1e0736, sha256 164fa4822ee695616a6883e6c467ed876fb0076ae6b7baff40faccc4bf157265)
BibTeX
@misc{dcace4be1e0736,
  title = {Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations — arXiv:2609.03657},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03657},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ace4be1e0736; sha256 164fa4822ee695616a6883e6c467ed876fb0076ae6b7baff40faccc4bf157265},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03657. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D scene representations like NeRF and 3D Gaussian Splatting (3DGS) suffer severe artifacts in sparse-view settings. Recent generative 3D artifact fixers attempt to address this, but rely on paired corrupted and clean renders requiring costly, per-scene reconstructions across varying view configurations. While 2D image augmentations act as instant regularizers, no explicit equivalents exist for 3D representations to preserve spatial consistency across views, an essential property for 3D-aware training. We propose 3D Morphological Perturbations as an optimization-free regularizer that preserves spatial consistency. Leveraging explicit 3DGS, we treat each Gaussian as a fundamental building block - analogous to a 2D pixel - and apply perturbations across its morphological parameter space via scale, rotation, and pruning. Our method eliminates per-scene 3DGS optimization loops from dataset curation while enabling models to learn stronger geometric priors than sparse-view baselines in diagnostic ablations conducted on a lightweight video diffusion sandbox. Scaled to a 14B-parameter video model via ControlNet, our approach maintains visual fidelity while reducing mean depth error by 12.5% over state-of-the-art image-to-image 3D artifact refiners, ultimately boosting downstream robotics policy success rates by up to 8.0% across 3 of 4 manipulation tasks.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.03657 — 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 2026-10-17T02:27:18.981Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).