Metraipolis › archive › dc_cf38ff9cb4de

View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing — arXiv:2610.08179

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08179
License (as archived)
CC0-1.0
Archived
2026-10-07T13:07:31.162Z
SHA-256 of the archived text
0b5626e5eb864cb951355e0b7d113d456a4d72a6faaf13d33b26037b319f2103
Stable URL of this page
https://metraipolis.com/documento/dc_cf38ff9cb4de

How to cite

View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing — arXiv:2610.08179 — arXiv (en), https://arxiv.org/abs/2610.08179 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf38ff9cb4de (Metraipolis archive dc_cf38ff9cb4de, sha256 0b5626e5eb864cb951355e0b7d113d456a4d72a6faaf13d33b26037b319f2103)
BibTeX
@misc{dccf38ff9cb4de,
  title = {View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing — arXiv:2610.08179},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08179},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf38ff9cb4de; sha256 0b5626e5eb864cb951355e0b7d113d456a4d72a6faaf13d33b26037b319f2103},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08179. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-driven 3D Gaussian editing commonly does not distinguish the editing reliability of rendered views, although different viewpoints provide supervision of substantially different quality. Views that clearly show the scene and match the edit instruction provide reliable guidance, while less informative views may weaken the edit when all views are treated equally. We present View Matters, a view-importance-aware framework that conducts editing around reliable keyframes. Keyframe Importance Estimation (KIE) identifies reliable views using geometric visibility, semantic distinctiveness, and edit relevance. Keyframe-Guided Editing (KGE) then propagates their editing signals asymmetrically to non-keyframes without noisy reverse influence, while Importance-Aware Optimization (IAO) preserves this reliability preference during 3DGS optimization. Across 23 scene-prompt pairs, View Matters achieves the highest average CLIP text-image similarity of 0.2822 and directional similarity of 0.2564 among the evaluated methods, with a four-minute editing time. Additional adjacent-view analysis indicates that the fidelity-oriented editing process maintains cross-view coherence.

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/2610.08179 — 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 2026-10-07T12:37:32.953Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).