Metraipolis › archive › dc_7e3217bcbba7
ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting — arXiv:2610.39399
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39399
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:41:56.992Z
- SHA-256 of the archived text
dba14497dbac2fddbd88fe572c4eaa470d21d79f30c01fde260fe042d2c2de68- Stable URL of this page
https://metraipolis.com/documento/dc_7e3217bcbba7
How to cite
ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting — arXiv:2610.39399 — arXiv (en), https://arxiv.org/abs/2610.39399 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e3217bcbba7 (Metraipolis archive dc_7e3217bcbba7, sha256 dba14497dbac2fddbd88fe572c4eaa470d21d79f30c01fde260fe042d2c2de68)
BibTeX
@misc{dc7e3217bcbba7,
title = {ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting — arXiv:2610.39399},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39399},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e3217bcbba7; sha256 dba14497dbac2fddbd88fe572c4eaa470d21d79f30c01fde260fe042d2c2de68},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39399. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time photorealistic novel view synthesis. However, its training-time densification remains largely heuristic, often resulting in redundant Gaussian proliferation and inaccurate geometric reconstruction. Existing methods predominantly rely on first-order screen-space gradients to trigger cloning and splitting, which fail to distinguish true geometric discontinuities from high-frequency textures or noisy residuals. To address this limitation, we propose ACD-GS, an Asymmetric Curvature-aware Densification framework for compact and geometry-aware 3D Gaussian optimization. Our key insight is that second-order depth responses provide a more reliable structural prior for density control, enabling asymmetric regulation of cloning and splitting to better capture geometric discontinuities. Building on this, we introduce a multi-view photometric consistency constraint to suppress transient single-view errors, together with a capacity-aware adaptive regulation strategy that balances densification and pruning during training. Unlike post-hoc compression or quantization-based approaches, ACD-GS directly prevents redundant Gaussian generation during training, yielding inherently compact representations. Extensive experiments demonstrate that our method reduces nearly 60% of Gaussian count and storage while maintaining competitive rendering fidelity, consistently outperforming existing methods across multiple datasets. Our code is available in this https URL . 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/2610.39399 — 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 2026-11-01T02:16:43.925Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).