Metraipolis › archive › dc_08a5bb4937c2

Unified Loss-Aware Density Control for 3D Gaussian Splatting — arXiv:2611.02044

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02044
License (as archived)
CC0-1.0
Archived
2026-11-03T11:41:48.984Z
SHA-256 of the archived text
eedbbaf75ddc3b93e9b180f0ca1003a1562eedea36340e673d8de91735878444
Stable URL of this page
https://metraipolis.com/documento/dc_08a5bb4937c2

How to cite

Unified Loss-Aware Density Control for 3D Gaussian Splatting — arXiv:2611.02044 — arXiv (en), https://arxiv.org/abs/2611.02044 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08a5bb4937c2 (Metraipolis archive dc_08a5bb4937c2, sha256 eedbbaf75ddc3b93e9b180f0ca1003a1562eedea36340e673d8de91735878444)
BibTeX
@misc{dc08a5bb4937c2,
  title = {Unified Loss-Aware Density Control for 3D Gaussian Splatting — arXiv:2611.02044},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02044},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08a5bb4937c2; sha256 eedbbaf75ddc3b93e9b180f0ca1003a1562eedea36340e673d8de91735878444},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02044. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The efficiency and fidelity of 3D Gaussian Splatting critically depend on adaptive density control, which grows and suppresses Gaussian primitives throughout optimization. However, the standard pipeline still relies on heuristic view-space gradients, scale thresholds, and global opacity resets, rather than explicitly assessing the loss-reducing effect of each split, clone, or opacity update. This mismatch can allocate primitives to already-sufficient regions, miss under-reconstructed structures, and destabilize training through blanket opacity changes. In this work, we recast adaptive density control as a collection of local loss-reduction decisions. We derive efficient Taylor-based per-Gaussian surrogates that predict the objective change caused by three primitive-level operations: splitting, cloning, and opacity decay. This yields a unified loss-aware framework with three components. First, we extend second-order splitting to a normalized joint position-scale space, enabling children to adapt not only their locations but also their anisotropic extents. Second, we formulate duplicate cloning as a surrogate minimization problem, selecting only Gaussians whose duplicated contribution is predicted to improve reconstruction and assigning each child a principled opacity. Third, we replace global opacity reset with selective soft opacity decay that weakens harmful primitives while preserving useful ones. Across standard 3DGS benchmarks, our method produces more targeted primitive allocation and achieves improved rendering quality with comparable or smaller Gaussian budgets compared to baselines.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.02044 — 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 2026-11-03T11:06:37.538Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).