Metraipolis › archive › dc_2d684bdb009a

ToW3D: Consistency-aware Interactive Point-based Mesh Editing on GANs — arXiv:2609.26078

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26078
License (as archived): CC0-1.0
Archived: 2026-10-08T16:39:29.569Z
SHA-256 of the archived text: bba7c7f11794e5297dfd8e56b99bf1a7e36a485c0d0647df4ef13ddd34f40d60
Stable URL of this page: https://metraipolis.com/documento/dc_2d684bdb009a

How to cite

ToW3D: Consistency-aware Interactive Point-based Mesh Editing on GANs — arXiv:2609.26078 — arXiv (en), https://arxiv.org/abs/2609.26078 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d684bdb009a (Metraipolis archive dc_2d684bdb009a, sha256 bba7c7f11794e5297dfd8e56b99bf1a7e36a485c0d0647df4ef13ddd34f40d60)

BibTeX

@misc{dc2d684bdb009a,
  title = {ToW3D: Consistency-aware Interactive Point-based Mesh Editing on GANs — arXiv:2609.26078},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26078},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d684bdb009a; sha256 bba7c7f11794e5297dfd8e56b99bf1a7e36a485c0d0647df4ef13ddd34f40d60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26078. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we propose ToW3D that enables precise and consistent control over 3D generative adversarial networks (GANs) with the Tug-of-War competition between shape deformation and appearance consistency. Existing point-based GAN editing methods such as DragGAN and GANWarping have yielded impressive performance for 2D image manipulation. However, as 3D generators present weaker generalization ability compared with 2D due to limited training data, they would suffer from drastic changes in global appearance when editing local areas of meshes. To address this, we design a pipeline of ``drag locally, shove globally'', which iteratively performs two optimization steps: 1) pull the point towards the target, and 2) push the structure and semantics back to the source. Specifically, we design a structure adaption module based on structure which guarantees the preservation of basic geometric properties, and a semantic preservation module that maintains semantic similarity across different views. Extensive qualitative and quantitative experiments demonstrate superiority of our ToW3D approach over prior methods in terms of appearance consistency and fidelity especially under large deformations.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.26078 — 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 2026-10-08T15:56:18.171Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).