Metraipolis › archive › dc_808f77418a66
StyleFields: Multi-Scale AdaIN-Modulated Implicit SDFs for Coarse-to-Fine 3D Shape Reconstruction and Editing — arXiv:2610.09200
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09200
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:47:00.874Z
- SHA-256 of the archived text
46f6df4d40c48761cea96055e707ff15ad72524538291c78e4cb9a2c141f1160- Stable URL of this page
https://metraipolis.com/documento/dc_808f77418a66
How to cite
StyleFields: Multi-Scale AdaIN-Modulated Implicit SDFs for Coarse-to-Fine 3D Shape Reconstruction and Editing — arXiv:2610.09200 — arXiv (en), https://arxiv.org/abs/2610.09200 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_808f77418a66 (Metraipolis archive dc_808f77418a66, sha256 46f6df4d40c48761cea96055e707ff15ad72524538291c78e4cb9a2c141f1160)
BibTeX
@misc{dc808f77418a66,
title = {StyleFields: Multi-Scale AdaIN-Modulated Implicit SDFs for Coarse-to-Fine 3D Shape Reconstruction and Editing — arXiv:2610.09200},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09200},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_808f77418a66; sha256 46f6df4d40c48761cea96055e707ff15ad72524538291c78e4cb9a2c141f1160},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09200. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce StyleFields, a DeepSDF-based architecture for high-fidelity 3D reconstruction that enables controllable geometric style mixing: the coarse structure of one object can be combined with the fine-scale details of another. The core idea is depth-aware modulation: instead of a single global code, we inject latents via multi-level Adaptive Instance Normalization at several decoder depths, and supervise matching auxiliary heads with a coarse-to-fine schedule while gradually growing network depth. This aligns early layers with global shape and later layers with high-frequency detail, achieving content-style decoupling without part labels or adversarial training. StyleFields delivers faithful reconstructions, convincing cross-instance hybrids, and consistent gains in ablations over injection depth and supervision granularity. We further demonstrate a practical application in automotive aerodynamics: a learned surrogate drag predictor serves as a differentiable objective to optimize reconstructed cars, allowing targeted edits of global form or surface details by freezing the complementary latent stream. StyleFields offers a simple, effective recipe for controllable implicit reconstruction and downstream performance-driven design. 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) ; Graphics (cs.GR). Pagina del lavoro: https://arxiv.org/abs/2610.09200 — 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 2026-10-08T12:18:15.318Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).