Metraipolis › archive › dc_a0076fe2bc62

ChromaGS: Text-Driven Semantic Editing of 4D Gaussian Avatars — arXiv:2610.03441

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.03441
License (as archived): CC0-1.0
Archived: 2026-10-06T09:08:34.284Z
SHA-256 of the archived text: ce827132b9c0f56ff3b94a786213036060f924f576464e15bf620363d9db309c
Stable URL of this page: https://metraipolis.com/documento/dc_a0076fe2bc62

How to cite

ChromaGS: Text-Driven Semantic Editing of 4D Gaussian Avatars — arXiv:2610.03441 — arXiv (en), https://arxiv.org/abs/2610.03441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0076fe2bc62 (Metraipolis archive dc_a0076fe2bc62, sha256 ce827132b9c0f56ff3b94a786213036060f924f576464e15bf620363d9db309c)

BibTeX

@misc{dca0076fe2bc62,
  title = {ChromaGS: Text-Driven Semantic Editing of 4D Gaussian Avatars — arXiv:2610.03441},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.03441},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0076fe2bc62; sha256 ce827132b9c0f56ff3b94a786213036060f924f576464e15bf620363d9db309c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present ChromaGS, a method for real-time, language-guided color editing of animatable 3D Gaussian head avatars. Given a trained animatable avatar, users can instantly modify the color of semantic regions through natural language, with edits applied at render time and no retraining required. Our key insight is to augment each Gaussian primitive with learned soft assignments to semantic regions and decompose colors into region-level base colors and Gaussian-level residuals. This decomposition enables coherent color transfer: modifying a region's base color propagates naturally through all associated Gaussians while preserving fine appearance details encoded in residuals. A two-stage language pipeline translates text instructions into target colors, supporting both absolute specifications and relative adjustments. Unlike generative editing methods that may introduce unintended modifications, our approach provides deterministic, precisely localized semantic control. Experiments demonstrate faithful appearance preservation and intuitive interaction across diverse subjects. Project page and code are available at: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.03441 — 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 2026-10-06T08:21:44.250Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).