Metraipolis › archive › dc_577e7c57253d
RDT-3D: Resolution-Decoupled Training for High-Fidelity 3D Geometry Generation — arXiv:2611.06141
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06141
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:29:57.677Z
- SHA-256 of the archived text
20f1ec996287feaa227b5d03dc0a23a793307bb94622725804d02a6ecde54ba2- Stable URL of this page
https://metraipolis.com/documento/dc_577e7c57253d
How to cite
RDT-3D: Resolution-Decoupled Training for High-Fidelity 3D Geometry Generation — arXiv:2611.06141 — arXiv (en), https://arxiv.org/abs/2611.06141 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_577e7c57253d (Metraipolis archive dc_577e7c57253d, sha256 20f1ec996287feaa227b5d03dc0a23a793307bb94622725804d02a6ecde54ba2)
BibTeX
@misc{dc577e7c57253d,
title = {RDT-3D: Resolution-Decoupled Training for High-Fidelity 3D Geometry Generation — arXiv:2611.06141},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06141},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_577e7c57253d; sha256 20f1ec996287feaa227b5d03dc0a23a793307bb94622725804d02a6ecde54ba2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06141. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-fidelity 3D geometry generation requires maintaining global structural coherence alongside fine-grained surface details. While recent coarse-to-fine frameworks leverage Rotary Position Embeddings (RoPE) to condition local queries, we reveal a critical training-inference resolution discrepancy: coordinate guidance and geometric supervision are aligned during training, whereas inference decodes high-resolution geometry from coarse spatial coordinates. This mismatch introduces a severe distribution shift that degrades fine details. To overcome this, we propose Resolution-Decoupled Training (RDT), which anchors RoPE guidance at 512 resolution while supervising geometry at 1536, enabling robust detail extrapolation. Additionally, to eliminate high-resolution data bottlenecks, we present Dual3D-300K, a large-scale paired dataset comprising 300K watertight 3D point clouds explicitly aligned across 512 and 1536 resolutions. Extensive experiments demonstrate that RDT substantially improves sharp geometric regions, while Dual3D-300K offers a scalable benchmark for high-resolution 3D generation. 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/2611.06141 — 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 2026-11-05T18:19:49.052Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).