Metraipolis › archive › dc_1fb6bb587c6f

Edit4D: Editable 4D Scene Generation with Textual Control — arXiv:2610.21668

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21668
License (as archived)
CC0-1.0
Archived
2026-10-16T10:35:26.154Z
SHA-256 of the archived text
bed89c06129b61f15fb5f1df169cebaeacc63030c6936bf7c619662baf23b960
Stable URL of this page
https://metraipolis.com/documento/dc_1fb6bb587c6f

How to cite

Edit4D: Editable 4D Scene Generation with Textual Control — arXiv:2610.21668 — arXiv (en), https://arxiv.org/abs/2610.21668 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1fb6bb587c6f (Metraipolis archive dc_1fb6bb587c6f, sha256 bed89c06129b61f15fb5f1df169cebaeacc63030c6936bf7c619662baf23b960)
BibTeX
@misc{dc1fb6bb587c6f,
  title = {Edit4D: Editable 4D Scene Generation with Textual Control — arXiv:2610.21668},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21668},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1fb6bb587c6f; sha256 bed89c06129b61f15fb5f1df169cebaeacc63030c6936bf7c619662baf23b960},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21668. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Edit4D, an editable text-to-4D scene generation framework that constructs 4D scenes from separate background and dynamic character representations. Recent advances in generative models have enabled text-driven dynamic scene synthesis, but editable 4D scene generation remains challenging due to the need to preserve spatial geometry and temporal dynamics. Existing approaches typically generate holistic scene videos, where the background and dynamic characters are coupled, making object-level editing and flexible camera control difficult. Edit4D addresses these limitations through a stage-specific generation pipeline. Given a user instruction, Edit4D first decomposes it into stage-specific prompts for background, dynamic character, and scene-character composition. Using these prompts, we synthesize multi-view scene images with text-to-image and camera-conditioned generative priors and reconstruct a background 3D Gaussian splatting representation. We then generate a character image, animate it with an image-conditioned video prior, reconstruct a 4D mesh, and bind Gaussian primitives to obtain a character representation. Finally, both components are composed through text-guided segmentation and contact-aware optimization. A global scene refinement is then performed to improve harmonization and rendering consistency. By integrating stage-specific components, Edit4D enables controllable camera motion, flexible object-level editing, and the practical construction of editable 4D scenes. Project page: this https URL

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/2610.21668 — 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 2026-10-16T08:52:02.682Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).